Received-SPF: pass (google.com: domain of linux-kernel+bounces-118822-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
From: Vlastimil Babka <vbabka@suse.cz>
Date: Tue, 26 Mar 2024 11:37:39 +0100
Subject: [PATCH mm-unstable v3 2/2] mm, slab: move slab_memcg hooks to
 mm/memcontrol.c
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit
Message-Id: <20240326-slab-memcg-v3-2-d85d2563287a@suse.cz>
References: <20240326-slab-memcg-v3-0-d85d2563287a@suse.cz>
In-Reply-To: <20240326-slab-memcg-v3-0-d85d2563287a@suse.cz>
To: Linus Torvalds <torvalds@linux-foundation.org>, 
 Josh Poimboeuf <jpoimboe@kernel.org>, Jeff Layton <jlayton@kernel.org>, 
 Chuck Lever <chuck.lever@oracle.com>, Kees Cook <kees@kernel.org>, 
 Christoph Lameter <cl@linux.com>, Pekka Enberg <penberg@kernel.org>, 
 David Rientjes <rientjes@google.com>, Joonsoo Kim <iamjoonsoo.kim@lge.com>, 
 Andrew Morton <akpm@linux-foundation.org>, 
 Roman Gushchin <roman.gushchin@linux.dev>, 
 Hyeonggon Yoo <42.hyeyoo@gmail.com>, Johannes Weiner <hannes@cmpxchg.org>, 
 Michal Hocko <mhocko@kernel.org>, Muchun Song <muchun.song@linux.dev>, 
 Alexander Viro <viro@zeniv.linux.org.uk>, 
 Christian Brauner <brauner@kernel.org>, Jan Kara <jack@suse.cz>, 
 Shakeel Butt <shakeel.butt@linux.dev>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, 
 cgroups@vger.kernel.org, linux-fsdevel@vger.kernel.org, 
 Vlastimil Babka <vbabka@suse.cz>

The hooks make multiple calls to functions in mm/memcontrol.c, including
to th current_obj_cgroup() marked __always_inline. It might be faster to
make a single call to the hook in mm/memcontrol.c instead. The hooks
also don't use almost anything from mm/slub.c. obj_full_size() can move
with the hooks and cache_vmstat_idx() to the internal mm/slab.h

Reviewed-by: Roman Gushchin <roman.gushchin@linux.dev>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/memcontrol.c |  90 +++++++++++++++++++++++++++++++++++++++++++++++++
 mm/slab.h       |  13 +++++++
 mm/slub.c       | 103 ++------------------------------------------------------
 3 files changed, 105 insertions(+), 101 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0a0720858ddb..1b3c3394a2ba 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3558,6 +3558,96 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
 	refill_obj_stock(objcg, size, true);
 }
 
+static inline size_t obj_full_size(struct kmem_cache *s)
+{
+	/*
+	 * For each accounted object there is an extra space which is used
+	 * to store obj_cgroup membership. Charge it too.
+	 */
+	return s->size + sizeof(struct obj_cgroup *);
+}
+
+bool __memcg_slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru,
+				  gfp_t flags, size_t size, void **p)
+{
+	struct obj_cgroup *objcg;
+	struct slab *slab;
+	unsigned long off;
+	size_t i;
+
+	/*
+	 * The obtained objcg pointer is safe to use within the current scope,
+	 * defined by current task or set_active_memcg() pair.
+	 * obj_cgroup_get() is used to get a permanent reference.
+	 */
+	objcg = current_obj_cgroup();
+	if (!objcg)
+		return true;
+
+	/*
+	 * slab_alloc_node() avoids the NULL check, so we might be called with a
+	 * single NULL object. kmem_cache_alloc_bulk() aborts if it can't fill
+	 * the whole requested size.
+	 * return success as there's nothing to free back
+	 */
+	if (unlikely(*p == NULL))
+		return true;
+
+	flags &= gfp_allowed_mask;
+
+	if (lru) {
+		int ret;
+		struct mem_cgroup *memcg;
+
+		memcg = get_mem_cgroup_from_objcg(objcg);
+		ret = memcg_list_lru_alloc(memcg, lru, flags);
+		css_put(&memcg->css);
+
+		if (ret)
+			return false;
+	}
+
+	if (obj_cgroup_charge(objcg, flags, size * obj_full_size(s)))
+		return false;
+
+	for (i = 0; i < size; i++) {
+		slab = virt_to_slab(p[i]);
+
+		if (!slab_obj_exts(slab) &&
+		    alloc_slab_obj_exts(slab, s, flags, false)) {
+			obj_cgroup_uncharge(objcg, obj_full_size(s));
+			continue;
+		}
+
+		off = obj_to_index(s, slab, p[i]);
+		obj_cgroup_get(objcg);
+		slab_obj_exts(slab)[off].objcg = objcg;
+		mod_objcg_state(objcg, slab_pgdat(slab),
+				cache_vmstat_idx(s), obj_full_size(s));
+	}
+
+	return true;
+}
+
+void __memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
+			    void **p, int objects, struct slabobj_ext *obj_exts)
+{
+	for (int i = 0; i < objects; i++) {
+		struct obj_cgroup *objcg;
+		unsigned int off;
+
+		off = obj_to_index(s, slab, p[i]);
+		objcg = obj_exts[off].objcg;
+		if (!objcg)
+			continue;
+
+		obj_exts[off].objcg = NULL;
+		obj_cgroup_uncharge(objcg, obj_full_size(s));
+		mod_objcg_state(objcg, slab_pgdat(slab), cache_vmstat_idx(s),
+				-obj_full_size(s));
+		obj_cgroup_put(objcg);
+	}
+}
 #endif /* CONFIG_MEMCG_KMEM */
 
 /*
diff --git a/mm/slab.h b/mm/slab.h
index 1343bfa12cee..411251b9bdd1 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -558,6 +558,9 @@ static inline struct slabobj_ext *slab_obj_exts(struct slab *slab)
 	return (struct slabobj_ext *)(obj_exts & ~OBJEXTS_FLAGS_MASK);
 }
 
+int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
+                        gfp_t gfp, bool new_slab);
+
 #else /* CONFIG_SLAB_OBJ_EXT */
 
 static inline struct slabobj_ext *slab_obj_exts(struct slab *slab)
@@ -567,7 +570,17 @@ static inline struct slabobj_ext *slab_obj_exts(struct slab *slab)
 
 #endif /* CONFIG_SLAB_OBJ_EXT */
 
+static inline enum node_stat_item cache_vmstat_idx(struct kmem_cache *s)
+{
+	return (s->flags & SLAB_RECLAIM_ACCOUNT) ?
+		NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B;
+}
+
 #ifdef CONFIG_MEMCG_KMEM
+bool __memcg_slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru,
+				  gfp_t flags, size_t size, void **p);
+void __memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
+			    void **p, int objects, struct slabobj_ext *obj_exts);
 void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
 		     enum node_stat_item idx, int nr);
 #endif
diff --git a/mm/slub.c b/mm/slub.c
index 263ff2a9f251..f5b151a58b7d 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1865,12 +1865,6 @@ static bool freelist_corrupted(struct kmem_cache *s, struct slab *slab,
 #endif
 #endif /* CONFIG_SLUB_DEBUG */
 
-static inline enum node_stat_item cache_vmstat_idx(struct kmem_cache *s)
-{
-	return (s->flags & SLAB_RECLAIM_ACCOUNT) ?
-		NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B;
-}
-
 #ifdef CONFIG_SLAB_OBJ_EXT
 
 #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG
@@ -1929,8 +1923,8 @@ static inline void handle_failed_objexts_alloc(unsigned long obj_exts,
 #define OBJCGS_CLEAR_MASK	(__GFP_DMA | __GFP_RECLAIMABLE | \
 				__GFP_ACCOUNT | __GFP_NOFAIL)
 
-static int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
-			       gfp_t gfp, bool new_slab)
+int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
+		        gfp_t gfp, bool new_slab)
 {
 	unsigned int objects = objs_per_slab(s, slab);
 	unsigned long new_exts;
@@ -2089,78 +2083,6 @@ alloc_tagging_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
 #endif /* CONFIG_SLAB_OBJ_EXT */
 
 #ifdef CONFIG_MEMCG_KMEM
-static inline size_t obj_full_size(struct kmem_cache *s)
-{
-	/*
-	 * For each accounted object there is an extra space which is used
-	 * to store obj_cgroup membership. Charge it too.
-	 */
-	return s->size + sizeof(struct obj_cgroup *);
-}
-
-static bool __memcg_slab_post_alloc_hook(struct kmem_cache *s,
-					 struct list_lru *lru,
-					 gfp_t flags, size_t size,
-					 void **p)
-{
-	struct obj_cgroup *objcg;
-	struct slab *slab;
-	unsigned long off;
-	size_t i;
-
-	/*
-	 * The obtained objcg pointer is safe to use within the current scope,
-	 * defined by current task or set_active_memcg() pair.
-	 * obj_cgroup_get() is used to get a permanent reference.
-	 */
-	objcg = current_obj_cgroup();
-	if (!objcg)
-		return true;
-
-	/*
-	 * slab_alloc_node() avoids the NULL check, so we might be called with a
-	 * single NULL object. kmem_cache_alloc_bulk() aborts if it can't fill
-	 * the whole requested size.
-	 * return success as there's nothing to free back
-	 */
-	if (unlikely(*p == NULL))
-		return true;
-
-	flags &= gfp_allowed_mask;
-
-	if (lru) {
-		int ret;
-		struct mem_cgroup *memcg;
-
-		memcg = get_mem_cgroup_from_objcg(objcg);
-		ret = memcg_list_lru_alloc(memcg, lru, flags);
-		css_put(&memcg->css);
-
-		if (ret)
-			return false;
-	}
-
-	if (obj_cgroup_charge(objcg, flags, size * obj_full_size(s)))
-		return false;
-
-	for (i = 0; i < size; i++) {
-		slab = virt_to_slab(p[i]);
-
-		if (!slab_obj_exts(slab) &&
-		    alloc_slab_obj_exts(slab, s, flags, false)) {
-			obj_cgroup_uncharge(objcg, obj_full_size(s));
-			continue;
-		}
-
-		off = obj_to_index(s, slab, p[i]);
-		obj_cgroup_get(objcg);
-		slab_obj_exts(slab)[off].objcg = objcg;
-		mod_objcg_state(objcg, slab_pgdat(slab),
-				cache_vmstat_idx(s), obj_full_size(s));
-	}
-
-	return true;
-}
 
 static void memcg_alloc_abort_single(struct kmem_cache *s, void *object);
 
@@ -2187,27 +2109,6 @@ bool memcg_slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru,
 	return false;
 }
 
-static void __memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
-				   void **p, int objects,
-				   struct slabobj_ext *obj_exts)
-{
-	for (int i = 0; i < objects; i++) {
-		struct obj_cgroup *objcg;
-		unsigned int off;
-
-		off = obj_to_index(s, slab, p[i]);
-		objcg = obj_exts[off].objcg;
-		if (!objcg)
-			continue;
-
-		obj_exts[off].objcg = NULL;
-		obj_cgroup_uncharge(objcg, obj_full_size(s));
-		mod_objcg_state(objcg, slab_pgdat(slab), cache_vmstat_idx(s),
-				-obj_full_size(s));
-		obj_cgroup_put(objcg);
-	}
-}
-
 static __fastpath_inline
 void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
 			  int objects)

-- 
2.44.0