mm: memcg/slab: pre-allocate obj_cgroups for slab caches with SLAB_ACCOUNT

In general it's unknown in advance if a slab page will contain accounted
objects or not.  In order to avoid memory waste, an obj_cgroup vector is
allocated dynamically when a need to account of a new object arises.  Such
approach is memory efficient, but requires an expensive cmpxchg() to set
up the memcg/objcgs pointer, because an allocation can race with a
different allocation on another cpu.

But in some common cases it's known for sure that a slab page will contain
accounted objects: if the page belongs to a slab cache with a SLAB_ACCOUNT
flag set.  It includes such popular objects like vm_area_struct, anon_vma,
task_struct, etc.

In such cases we can pre-allocate the objcgs vector and simple assign it
to the page without any atomic operations, because at this early stage the
page is not visible to anyone else.

A very simplistic benchmark (allocating 10000000 64-bytes objects in a
row) shows ~15% win.  In the real life it seems that most workloads are
not very sensitive to the speed of (accounted) slab allocations.

[guro@fb.com: open-code set_page_objcgs() and add some comments, by Johannes]
  Link: https://lkml.kernel.org/r/20201113001926.GA2934489@carbon.dhcp.thefacebook.com
[akpm@linux-foundation.org: fix it for mm-slub-call-account_slab_page-after-slab-page-initialization-fix.patch]

Link: https://lkml.kernel.org/r/20201110195753.530157-2-guro@fb.com
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 31 insertions, 10 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0b9bd354e97e..60ce452e42e6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2935,9 +2935,10 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg)
 
 #ifdef CONFIG_MEMCG_KMEM
 int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
-				 gfp_t gfp)
+				 gfp_t gfp, bool new_page)
 {
 	unsigned int objects = objs_per_slab_page(s, page);
+	unsigned long memcg_data;
 	void *vec;
 
 	vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp,
@@ -2945,11 +2946,25 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
 	if (!vec)
 		return -ENOMEM;
 
-	if (!set_page_objcgs(page, vec))
+	memcg_data = (unsigned long) vec | MEMCG_DATA_OBJCGS;
+	if (new_page) {
+		/*
+		 * If the slab page is brand new and nobody can yet access
+		 * it's memcg_data, no synchronization is required and
+		 * memcg_data can be simply assigned.
+		 */
+		page->memcg_data = memcg_data;
+	} else if (cmpxchg(&page->memcg_data, 0, memcg_data)) {
+		/*
+		 * If the slab page is already in use, somebody can allocate
+		 * and assign obj_cgroups in parallel. In this case the existing
+		 * objcg vector should be reused.
+		 */
 		kfree(vec);
-	else
-		kmemleak_not_leak(vec);
+		return 0;
+	}
 
+	kmemleak_not_leak(vec);
 	return 0;
 }
 
diff --git a/mm/slab.c b/mm/slab.c
index cdad64b2836d..9c9e0c255c4b 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1379,7 +1379,7 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
 		return NULL;
 	}
 
-	account_slab_page(page, cachep->gfporder, cachep);
+	account_slab_page(page, cachep->gfporder, cachep, flags);
 	__SetPageSlab(page);
 	/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
 	if (sk_memalloc_socks() && page_is_pfmemalloc(page))
diff --git a/mm/slab.h b/mm/slab.h
index 48dc466a3791..076582f58f68 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -238,7 +238,7 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla
 
 #ifdef CONFIG_MEMCG_KMEM
 int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
-				 gfp_t gfp);
+				 gfp_t gfp, bool new_page);
 
 static inline void memcg_free_page_obj_cgroups(struct page *page)
 {
@@ -315,7 +315,8 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 			page = virt_to_head_page(p[i]);
 
 			if (!page_objcgs(page) &&
-			    memcg_alloc_page_obj_cgroups(page, s, flags)) {
+			    memcg_alloc_page_obj_cgroups(page, s, flags,
+							 false)) {
 				obj_cgroup_uncharge(objcg, obj_full_size(s));
 				continue;
 			}
@@ -379,7 +380,8 @@ static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
 }
 
 static inline int memcg_alloc_page_obj_cgroups(struct page *page,
-					       struct kmem_cache *s, gfp_t gfp)
+					       struct kmem_cache *s, gfp_t gfp,
+					       bool new_page)
 {
 	return 0;
 }
@@ -420,8 +422,12 @@ static inline struct kmem_cache *virt_to_cache(const void *obj)
 }
 
 static __always_inline void account_slab_page(struct page *page, int order,
-					      struct kmem_cache *s)
+					      struct kmem_cache *s,
+					      gfp_t gfp)
 {
+	if (memcg_kmem_enabled() && (s->flags & SLAB_ACCOUNT))
+		memcg_alloc_page_obj_cgroups(page, s, gfp, true);
+
 	mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
 			    PAGE_SIZE << order);
 }
diff --git a/mm/slub.c b/mm/slub.c
index e0fef8f8d4bf..ca566361561e 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1785,7 +1785,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 
 	page->objects = oo_objects(oo);
 
-	account_slab_page(page, oo_order(oo), s);
+	account_slab_page(page, oo_order(oo), s, flags);
 
 	page->slab_cache = s;
 	__SetPageSlab(page);