mm: introduce slabobj_ext to support slab object extensions

Currently slab pages can store only vectors of obj_cgroup pointers in
page->memcg_data.  Introduce slabobj_ext structure to allow more data to
be stored for each slab object.  Wrap obj_cgroup into slabobj_ext to
support current functionality while allowing to extend slabobj_ext in the
future.

Link: https://lkml.kernel.org/r/20240321163705.3067592-7-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Kees Cook <keescook@chromium.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alex Gaynor <alex.gaynor@gmail.com>
Cc: Alice Ryhl <aliceryhl@google.com>
Cc: Andreas Hindborg <a.hindborg@samsung.com>
Cc: Benno Lossin <benno.lossin@proton.me>
Cc: "Björn Roy Baron" <bjorn3_gh@protonmail.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Gary Guo <gary@garyguo.net>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Wedson Almeida Filho <wedsonaf@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 81 insertions, 20 deletions

diff --git a/mm/slub.c b/mm/slub.c
index bc9f40889834..5c896c76812d 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1871,13 +1871,78 @@ static inline enum node_stat_item cache_vmstat_idx(struct kmem_cache *s)
 		NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B;
 }
 
-#ifdef CONFIG_MEMCG_KMEM
-static inline void memcg_free_slab_cgroups(struct slab *slab)
+#ifdef CONFIG_SLAB_OBJ_EXT
+
+/*
+ * The allocated objcg pointers array is not accounted directly.
+ * Moreover, it should not come from DMA buffer and is not readily
+ * reclaimable. So those GFP bits should be masked off.
+ */
+#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)
 {
-	kfree(slab_objcgs(slab));
-	slab->memcg_data = 0;
+	unsigned int objects = objs_per_slab(s, slab);
+	unsigned long obj_exts;
+	void *vec;
+
+	gfp &= ~OBJCGS_CLEAR_MASK;
+	vec = kcalloc_node(objects, sizeof(struct slabobj_ext), gfp,
+			   slab_nid(slab));
+	if (!vec)
+		return -ENOMEM;
+
+	obj_exts = (unsigned long)vec;
+#ifdef CONFIG_MEMCG
+	obj_exts |= MEMCG_DATA_OBJEXTS;
+#endif
+	if (new_slab) {
+		/*
+		 * If the slab is brand new and nobody can yet access its
+		 * obj_exts, no synchronization is required and obj_exts can
+		 * be simply assigned.
+		 */
+		slab->obj_exts = obj_exts;
+	} else if (cmpxchg(&slab->obj_exts, 0, obj_exts)) {
+		/*
+		 * If the slab is already in use, somebody can allocate and
+		 * assign slabobj_exts in parallel. In this case the existing
+		 * objcg vector should be reused.
+		 */
+		kfree(vec);
+		return 0;
+	}
+
+	kmemleak_not_leak(vec);
+	return 0;
 }
 
+static inline void free_slab_obj_exts(struct slab *slab)
+{
+	struct slabobj_ext *obj_exts;
+
+	obj_exts = slab_obj_exts(slab);
+	if (!obj_exts)
+		return;
+
+	kfree(obj_exts);
+	slab->obj_exts = 0;
+}
+#else /* CONFIG_SLAB_OBJ_EXT */
+static int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
+			       gfp_t gfp, bool new_slab)
+{
+	return 0;
+}
+
+static inline void free_slab_obj_exts(struct slab *slab)
+{
+}
+#endif /* CONFIG_SLAB_OBJ_EXT */
+
+#ifdef CONFIG_MEMCG_KMEM
 static inline size_t obj_full_size(struct kmem_cache *s)
 {
 	/*
@@ -1956,15 +2021,15 @@ static void __memcg_slab_post_alloc_hook(struct kmem_cache *s,
 		if (likely(p[i])) {
 			slab = virt_to_slab(p[i]);
 
-			if (!slab_objcgs(slab) &&
-			    memcg_alloc_slab_cgroups(slab, s, flags, false)) {
+			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_objcgs(slab)[off] = objcg;
+			slab_obj_exts(slab)[off].objcg = objcg;
 			mod_objcg_state(objcg, slab_pgdat(slab),
 					cache_vmstat_idx(s), obj_full_size(s));
 		} else {
@@ -1985,18 +2050,18 @@ void memcg_slab_post_alloc_hook(struct kmem_cache *s, struct obj_cgroup *objcg,
 
 static void __memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
 				   void **p, int objects,
-				   struct obj_cgroup **objcgs)
+				   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 = objcgs[off];
+		objcg = obj_exts[off].objcg;
 		if (!objcg)
 			continue;
 
-		objcgs[off] = NULL;
+		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));
@@ -2008,16 +2073,16 @@ static __fastpath_inline
 void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
 			  int objects)
 {
-	struct obj_cgroup **objcgs;
+	struct slabobj_ext *obj_exts;
 
 	if (!memcg_kmem_online())
 		return;
 
-	objcgs = slab_objcgs(slab);
-	if (likely(!objcgs))
+	obj_exts = slab_obj_exts(slab);
+	if (likely(!obj_exts))
 		return;
 
-	__memcg_slab_free_hook(s, slab, p, objects, objcgs);
+	__memcg_slab_free_hook(s, slab, p, objects, obj_exts);
 }
 
 static inline
@@ -2028,10 +2093,6 @@ void memcg_slab_alloc_error_hook(struct kmem_cache *s, int objects,
 		obj_cgroup_uncharge(objcg, objects * obj_full_size(s));
 }
 #else /* CONFIG_MEMCG_KMEM */
-static inline void memcg_free_slab_cgroups(struct slab *slab)
-{
-}
-
 static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
 					     struct list_lru *lru,
 					     struct obj_cgroup **objcgp,
@@ -2298,7 +2359,7 @@ static __always_inline void account_slab(struct slab *slab, int order,
 					 struct kmem_cache *s, gfp_t gfp)
 {
 	if (memcg_kmem_online() && (s->flags & SLAB_ACCOUNT))
-		memcg_alloc_slab_cgroups(slab, s, gfp, true);
+		alloc_slab_obj_exts(slab, s, gfp, true);
 
 	mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
 			    PAGE_SIZE << order);
@@ -2308,7 +2369,7 @@ static __always_inline void unaccount_slab(struct slab *slab, int order,
 					   struct kmem_cache *s)
 {
 	if (memcg_kmem_online())
-		memcg_free_slab_cgroups(slab);
+		free_slab_obj_exts(slab);
 
 	mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
 			    -(PAGE_SIZE << order));