memcg: simplify charging kmem pages

Charging kmem pages proceeds in two steps.  First, we try to charge the
allocation size to the memcg the current task belongs to, then we allocate
a page and "commit" the charge storing the pointer to the memcg in the
page struct.

Such a design looks overcomplicated, because there is not much sense in
trying charging the allocation before actually allocating a page: we won't
be able to consume much memory over the limit even if we charge after
doing the actual allocation, besides we already charge user pages post
factum, so being pedantic with kmem pages just looks pointless.

So this patch simplifies the design by merging the "charge" and the
"commit" steps into the same function, which takes the allocated page.

Also, rename the charge and uncharge methods to memcg_kmem_charge and
memcg_kmem_uncharge and make the charge method return error code instead
of bool to conform to mem_cgroup_try_charge.

Signed-off-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 13 insertions, 44 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a1c05ff5892d..e249279f60c1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2404,57 +2404,26 @@ void __memcg_kmem_put_cache(struct kmem_cache *cachep)
 		css_put(&cachep->memcg_params.memcg->css);
 }
 
-/*
- * We need to verify if the allocation against current->mm->owner's memcg is
- * possible for the given order. But the page is not allocated yet, so we'll
- * need a further commit step to do the final arrangements.
- *
- * It is possible for the task to switch cgroups in this mean time, so at
- * commit time, we can't rely on task conversion any longer.  We'll then use
- * the handle argument to return to the caller which cgroup we should commit
- * against. We could also return the memcg directly and avoid the pointer
- * passing, but a boolean return value gives better semantics considering
- * the compiled-out case as well.
- *
- * Returning true means the allocation is possible.
- */
-bool
-__memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
+int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
 {
 	struct mem_cgroup *memcg;
 	int ret;
 
-	*_memcg = NULL;
-
 	memcg = get_mem_cgroup_from_mm(current->mm);
 
 	if (!memcg_kmem_is_active(memcg)) {
 		css_put(&memcg->css);
-		return true;
+		return 0;
 	}
 
 	ret = memcg_charge_kmem(memcg, gfp, 1 << order);
-	if (!ret)
-		*_memcg = memcg;
 
 	css_put(&memcg->css);
-	return (ret == 0);
-}
-
-void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg,
-			      int order)
-{
-	VM_BUG_ON(mem_cgroup_is_root(memcg));
-
-	/* The page allocation failed. Revert */
-	if (!page) {
-		memcg_uncharge_kmem(memcg, 1 << order);
-		return;
-	}
 	page->mem_cgroup = memcg;
+	return ret;
 }
 
-void __memcg_kmem_uncharge_pages(struct page *page, int order)
+void __memcg_kmem_uncharge(struct page *page, int order)
 {
 	struct mem_cgroup *memcg = page->mem_cgroup;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 06e62300d627..446bb36ee59d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3428,24 +3428,24 @@ EXPORT_SYMBOL(__free_page_frag);
 struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order)
 {
 	struct page *page;
-	struct mem_cgroup *memcg = NULL;
 
-	if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order))
-		return NULL;
 	page = alloc_pages(gfp_mask, order);
-	memcg_kmem_commit_charge(page, memcg, order);
+	if (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;
-	struct mem_cgroup *memcg = NULL;
 
-	if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order))
-		return NULL;
 	page = alloc_pages_node(nid, gfp_mask, order);
-	memcg_kmem_commit_charge(page, memcg, order);
+	if (page && memcg_kmem_charge(page, gfp_mask, order) != 0) {
+		__free_pages(page, order);
+		page = NULL;
+	}
 	return page;
 }
 
@@ -3455,7 +3455,7 @@ struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
  */
 void __free_kmem_pages(struct page *page, unsigned int order)
 {
-	memcg_kmem_uncharge_pages(page, order);
+	memcg_kmem_uncharge(page, order);
 	__free_pages(page, order);
 }