mm: get rid of __GFP_KMEMCG

Currently to allocate a page that should be charged to kmemcg (e.g.
threadinfo), we pass __GFP_KMEMCG flag to the page allocator.  The page
allocated is then to be freed by free_memcg_kmem_pages.  Apart from
looking asymmetrical, this also requires intrusion to the general
allocation path.  So let's introduce separate functions that will
alloc/free pages charged to kmemcg.

The new functions are called alloc_kmem_pages and free_kmem_pages.  They
should be used when the caller actually would like to use kmalloc, but
has to fall back to the page allocator for the allocation is large.
They only differ from alloc_pages and free_pages in that besides
allocating or freeing pages they also charge them to the kmem resource
counter of the current memory cgroup.

[sfr@canb.auug.org.au: export kmalloc_order() to modules]
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Glauber Costa <glommer@gmail.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 57 insertions, 29 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 56a768b..7bab1de 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3540,11 +3540,12 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
 	/*
 	 * Disabling accounting is only relevant for some specific memcg
 	 * internal allocations. Therefore we would initially not have such
-	 * check here, since direct calls to the page allocator that are marked
-	 * with GFP_KMEMCG only happen outside memcg core. We are mostly
-	 * concerned with cache allocations, and by having this test at
-	 * memcg_kmem_get_cache, we are already able to relay the allocation to
-	 * the root cache and bypass the memcg cache altogether.
+	 * check here, since direct calls to the page allocator that are
+	 * accounted to kmemcg (alloc_kmem_pages and friends) only happen
+	 * outside memcg core. We are mostly concerned with cache allocations,
+	 * and by having this test at memcg_kmem_get_cache, we are already able
+	 * to relay the allocation to the root cache and bypass the memcg cache
+	 * altogether.
 	 *
 	 * There is one exception, though: the SLUB allocator does not create
 	 * large order caches, but rather service large kmallocs directly from
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5dba293..7cfdcd8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2697,7 +2697,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	int migratetype = allocflags_to_migratetype(gfp_mask);
 	unsigned int cpuset_mems_cookie;
 	int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR;
-	struct mem_cgroup *memcg = NULL;
 
 	gfp_mask &= gfp_allowed_mask;
 
@@ -2716,13 +2715,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	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 = read_mems_allowed_begin();
 
@@ -2782,8 +2774,6 @@ out:
 	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 
-	memcg_kmem_commit_charge(page, memcg, order);
-
 	return page;
 }
 EXPORT_SYMBOL(__alloc_pages_nodemask);
@@ -2837,27 +2827,51 @@ void free_pages(unsigned long addr, unsigned int order)
 EXPORT_SYMBOL(free_pages);
 
 /*
- * __free_memcg_kmem_pages and free_memcg_kmem_pages will free
- * pages allocated with __GFP_KMEMCG.
+ * alloc_kmem_pages charges newly allocated pages to the kmem resource counter
+ * of the current memory cgroup.
  *
- * 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.
+ * 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;
+	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);
+	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);
+	return page;
+}
+
+/*
+ * __free_kmem_pages and free_kmem_pages will free pages allocated with
+ * alloc_kmem_pages.
  */
-void __free_memcg_kmem_pages(struct page *page, unsigned int order)
+void __free_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)
+void free_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);
+		__free_kmem_pages(virt_to_page((void *)addr), order);
 	}
 }
 
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 06f0c61..1950c8f 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -582,6 +582,19 @@ void __init create_kmalloc_caches(unsigned long flags)
 }
 #endif /* !CONFIG_SLOB */
 
+void *kmalloc_order(size_t size, gfp_t flags, unsigned int order)
+{
+	void *ret;
+	struct page *page;
+
+	flags |= __GFP_COMP;
+	page = alloc_kmem_pages(flags, order);
+	ret = page ? page_address(page) : NULL;
+	kmemleak_alloc(ret, size, 1, flags);
+	return ret;
+}
+EXPORT_SYMBOL(kmalloc_order);
+
 #ifdef CONFIG_TRACING
 void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order)
 {
diff --git a/mm/slub.c b/mm/slub.c
index fc98318..ddb6079 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3311,8 +3311,8 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
 	struct page *page;
 	void *ptr = NULL;
 
-	flags |= __GFP_COMP | __GFP_NOTRACK | __GFP_KMEMCG;
-	page = alloc_pages_node(node, flags, get_order(size));
+	flags |= __GFP_COMP | __GFP_NOTRACK;
+	page = alloc_kmem_pages_node(node, flags, get_order(size));
 	if (page)
 		ptr = page_address(page);
 
@@ -3381,7 +3381,7 @@ void kfree(const void *x)
 	if (unlikely(!PageSlab(page))) {
 		BUG_ON(!PageCompound(page));
 		kfree_hook(x);
-		__free_memcg_kmem_pages(page, compound_order(page));
+		__free_kmem_pages(page, compound_order(page));
 		return;
 	}
 	slab_free(page->slab_cache, page, object, _RET_IP_);