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>

4 files changed, 20 insertions, 60 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index de2491c..7023a31 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -63,6 +63,7 @@
 #include <linux/sched/rt.h>
 #include <linux/page_owner.h>
 #include <linux/kthread.h>
+#include <linux/memcontrol.h>
 
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
@@ -1018,6 +1019,10 @@ static __always_inline bool free_pages_prepare(struct page *page,
 	}
 	if (PageMappingFlags(page))
 		page->mapping = NULL;
+	if (memcg_kmem_enabled() && PageKmemcg(page)) {
+		memcg_kmem_uncharge(page, order);
+		__ClearPageKmemcg(page);
+	}
 	if (check_free)
 		bad += free_pages_check(page);
 	if (bad)
@@ -3841,6 +3846,14 @@ no_zone:
 	}
 
 out:
+	if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page) {
+		if (unlikely(memcg_kmem_charge(page, gfp_mask, order))) {
+			__free_pages(page, order);
+			page = NULL;
+		} else
+			__SetPageKmemcg(page);
+	}
+
 	if (kmemcheck_enabled && page)
 		kmemcheck_pagealloc_alloc(page, order, gfp_mask);
 
@@ -3996,59 +4009,6 @@ void __free_page_frag(void *addr)
 }
 EXPORT_SYMBOL(__free_page_frag);
 
-/*
- * alloc_kmem_pages charges newly allocated pages to the kmem resource counter
- * of the current memory cgroup if __GFP_ACCOUNT is set, other than that it is
- * equivalent to alloc_pages.
- *
- * It should be used when the caller would like to use kmalloc, but since the
- * allocation is large, it has to fall back to the page allocator.
- */
-struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order)
-{
-	struct page *page;
-
-	page = alloc_pages(gfp_mask, order);
-	if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) &&
-	    page && memcg_kmem_charge(page, gfp_mask, order) != 0) {
-		__free_pages(page, order);
-		page = NULL;
-	}
-	return page;
-}
-
-struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
-{
-	struct page *page;
-
-	page = alloc_pages_node(nid, gfp_mask, order);
-	if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) &&
-	    page && memcg_kmem_charge(page, gfp_mask, order) != 0) {
-		__free_pages(page, order);
-		page = NULL;
-	}
-	return page;
-}
-
-/*
- * __free_kmem_pages and free_kmem_pages will free pages allocated with
- * alloc_kmem_pages.
- */
-void __free_kmem_pages(struct page *page, unsigned int order)
-{
-	if (memcg_kmem_enabled())
-		memcg_kmem_uncharge(page, order);
-	__free_pages(page, order);
-}
-
-void free_kmem_pages(unsigned long addr, unsigned int order)
-{
-	if (addr != 0) {
-		VM_BUG_ON(!virt_addr_valid((void *)addr));
-		__free_kmem_pages(virt_to_page((void *)addr), order);
-	}
-}
-
 static void *make_alloc_exact(unsigned long addr, unsigned int order,
 		size_t size)
 {
diff --git a/mm/slab_common.c b/mm/slab_common.c
index da88c15..71f0b28 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1012,7 +1012,7 @@ void *kmalloc_order(size_t size, gfp_t flags, unsigned int order)
 	struct page *page;
 
 	flags |= __GFP_COMP;
-	page = alloc_kmem_pages(flags, order);
+	page = alloc_pages(flags, order);
 	ret = page ? page_address(page) : NULL;
 	kmemleak_alloc(ret, size, 1, flags);
 	kasan_kmalloc_large(ret, size, flags);
diff --git a/mm/slub.c b/mm/slub.c
index c0cfa27..f9da871 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2977,7 +2977,7 @@ int build_detached_freelist(struct kmem_cache *s, size_t size,
 		if (unlikely(!PageSlab(page))) {
 			BUG_ON(!PageCompound(page));
 			kfree_hook(object);
-			__free_kmem_pages(page, compound_order(page));
+			__free_pages(page, compound_order(page));
 			p[size] = NULL; /* mark object processed */
 			return size;
 		}
@@ -3693,7 +3693,7 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
 	void *ptr = NULL;
 
 	flags |= __GFP_COMP | __GFP_NOTRACK;
-	page = alloc_kmem_pages_node(node, flags, get_order(size));
+	page = alloc_pages_node(node, flags, get_order(size));
 	if (page)
 		ptr = page_address(page);
 
@@ -3774,7 +3774,7 @@ void kfree(const void *x)
 	if (unlikely(!PageSlab(page))) {
 		BUG_ON(!PageCompound(page));
 		kfree_hook(x);
-		__free_kmem_pages(page, compound_order(page));
+		__free_pages(page, compound_order(page));
 		return;
 	}
 	slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index e11475c..91f44e7 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1501,7 +1501,7 @@ static void __vunmap(const void *addr, int deallocate_pages)
 			struct page *page = area->pages[i];
 
 			BUG_ON(!page);
-			__free_kmem_pages(page, 0);
+			__free_pages(page, 0);
 		}
 
 		kvfree(area->pages);
@@ -1629,9 +1629,9 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 		struct page *page;
 
 		if (node == NUMA_NO_NODE)
-			page = alloc_kmem_pages(alloc_mask, order);
+			page = alloc_pages(alloc_mask, order);
 		else
-			page = alloc_kmem_pages_node(node, alloc_mask, order);
+			page = alloc_pages_node(node, alloc_mask, order);
 
 		if (unlikely(!page)) {
 			/* Successfully allocated i pages, free them in __vunmap() */