[Devel] [PATCH rh7 4/7] mm: charge/uncharge kmemcg from generic page allocator paths

[Vladimir Davydov]

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.

Signed-off-by: Vladimir Davydov <vdavydov at virtuozzo.com>
---
 include/linux/memcontrol.h |  3 ++-
 include/linux/page-flags.h | 19 +++++++++++++++++++
 mm/memcontrol.c            |  4 ++++
 mm/page_alloc.c            |  4 ++++
 4 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d26adf10eaa7..48bf2caa008d 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -23,6 +23,7 @@
 #include <linux/vm_event_item.h>
 #include <linux/hardirq.h>
 #include <linux/jump_label.h>
+#include <linux/page-flags.h>
 
 struct mem_cgroup;
 struct page_cgroup;
@@ -617,7 +618,7 @@ memcg_kmem_newpage_charge(struct page *page, gfp_t gfp, int order)
 static inline void
 memcg_kmem_uncharge_pages(struct page *page, int order)
 {
-	if (memcg_kmem_enabled())
+	if (memcg_kmem_enabled() && PageKmemcg(page))
 		__memcg_kmem_uncharge_pages(page, order);
 }
 
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index cdf83ecac8f3..d15d20d84142 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -523,6 +523,25 @@ static inline void __ClearPageBalloon(struct page *page)
 	atomic_set(&page->_mapcount, -1);
 }
 
+#define PAGE_KMEMCG_MAPCOUNT_VALUE (-256)
+
+static inline int PageKmemcg(struct page *page)
+{
+	return atomic_read(&page->_mapcount) == PAGE_KMEMCG_MAPCOUNT_VALUE;
+}
+
+static inline void __SetPageKmemcg(struct page *page)
+{
+	VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page);
+	atomic_set(&page->_mapcount, PAGE_KMEMCG_MAPCOUNT_VALUE);
+}
+
+static inline void __ClearPageKmemcg(struct page *page)
+{
+	VM_BUG_ON_PAGE(!PageKmemcg(page), page);
+	atomic_set(&page->_mapcount, -1);
+}
+
 /*
  * If network-based swap is enabled, sl*b must keep track of whether pages
  * were allocated from pfmemalloc reserves.
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8eb48071ea22..1c3fbb2d2c48 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3555,6 +3555,8 @@ __memcg_kmem_newpage_charge(struct page *page, gfp_t gfp, int order)
 	SetPageCgroupUsed(pc);
 	unlock_page_cgroup(pc);
 
+	__SetPageKmemcg(page);
+
 	return true;
 }
 
@@ -3588,6 +3590,8 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order)
 
 	VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page);
 	memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
+
+	__ClearPageKmemcg(page);
 }
 
 struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9f02d8013add..2b04f36ea016 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -748,6 +748,7 @@ static bool free_pages_prepare(struct page *page, unsigned int order)
 
 	if (PageAnon(page))
 		page->mapping = NULL;
+	memcg_kmem_uncharge_pages(page, order);
 	for (i = 0; i < (1 << order); i++) {
 		bad += free_pages_check(page + i);
 		if (static_key_false(&zero_free_pages))
@@ -2804,6 +2805,9 @@ out:
 	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
 		goto retry_cpuset;
 
+	if (page && !memcg_kmem_newpage_charge(page, gfp_mask, order))
+		__free_pages(page, order);
+
 	return page;
 }
 EXPORT_SYMBOL(__alloc_pages_nodemask);
-- 
2.1.4