memcg: add charging of already allocated slab objects

At the moment, the slab objects are charged to the memcg at the
allocation time. However there are cases where slab objects are
allocated at the time where the right target memcg to charge it to is
not known. One such case is the network sockets for the incoming
connection which are allocated in the softirq context.

Couple hundred thousand connections are very normal on large loaded
server and almost all of those sockets underlying those connections get
allocated in the softirq context and thus not charged to any memcg.
However later at the accept() time we know the right target memcg to
charge. Let's add new API to charge already allocated objects, so we can
have better accounting of the memory usage.

To measure the performance impact of this change, tcp_crr is used from
the neper [1] performance suite. Basically it is a network ping pong
test with new connection for each ping pong.

The server and the client are run inside 3 level of cgroup hierarchy
using the following commands:

Server:
 $ tcp_crr -6

Client:
 $ tcp_crr -6 -c -H ${server_ip}

If the client and server run on different machines with 50 GBPS NIC,
there is no visible impact of the change.

For the same machine experiment with v6.11-rc5 as base.

          base (throughput)     with-patch
tcp_crr   14545 (+- 80)         14463 (+- 56)

It seems like the performance impact is within the noise.

Link: https://github.com/google/neper [1]
Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Roman Gushchin <roman.gushchin@linux.dev>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com> # net
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>

include/linux/slab.h

@@ -547,6 +547,35 @@ void *kmem_cache_alloc_lru_noprof(struct kmem_cache *s, struct list_lru *lru,
 			    gfp_t gfpflags) __assume_slab_alignment __malloc;
 #define kmem_cache_alloc_lru(...)	alloc_hooks(kmem_cache_alloc_lru_noprof(__VA_ARGS__))
 
+/**
+ * kmem_cache_charge - memcg charge an already allocated slab memory
+ * @objp: address of the slab object to memcg charge
+ * @gfpflags: describe the allocation context
+ *
+ * kmem_cache_charge allows charging a slab object to the current memcg,
+ * primarily in cases where charging at allocation time might not be possible
+ * because the target memcg is not known (i.e. softirq context)
+ *
+ * The objp should be pointer returned by the slab allocator functions like
+ * kmalloc (with __GFP_ACCOUNT in flags) or kmem_cache_alloc. The memcg charge
+ * behavior can be controlled through gfpflags parameter, which affects how the
+ * necessary internal metadata can be allocated. Including __GFP_NOFAIL denotes
+ * that overcharging is requested instead of failure, but is not applied for the
+ * internal metadata allocation.
+ *
+ * There are several cases where it will return true even if the charging was
+ * not done:
+ * More specifically:
+ *
+ * 1. For !CONFIG_MEMCG or cgroup_disable=memory systems.
+ * 2. Already charged slab objects.
+ * 3. For slab objects from KMALLOC_NORMAL caches - allocated by kmalloc()
+ *    without __GFP_ACCOUNT
+ * 4. Allocating internal metadata has failed
+ *
+ * Return: true if charge was successful otherwise false.
+ */
+bool kmem_cache_charge(void *objp, gfp_t gfpflags);
 void kmem_cache_free(struct kmem_cache *s, void *objp);
 
 kmem_buckets *kmem_buckets_create(const char *name, slab_flags_t flags,

mm/slab.h

@@ -443,6 +443,13 @@ static inline bool is_kmalloc_cache(struct kmem_cache *s)
 	return (s->flags & SLAB_KMALLOC);
 }
 
+static inline bool is_kmalloc_normal(struct kmem_cache *s)
+{
+	if (!is_kmalloc_cache(s))
+		return false;
+	return !(s->flags & (SLAB_CACHE_DMA|SLAB_ACCOUNT|SLAB_RECLAIM_ACCOUNT));
+}
+
 /* Legal flag mask for kmem_cache_create(), for various configurations */
 #define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \
 			 SLAB_CACHE_DMA32 | SLAB_PANIC | \

mm/slub.c

@@ -2185,6 +2185,45 @@ void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
 
 	__memcg_slab_free_hook(s, slab, p, objects, obj_exts);
 }
+
+static __fastpath_inline
+bool memcg_slab_post_charge(void *p, gfp_t flags)
+{
+	struct slabobj_ext *slab_exts;
+	struct kmem_cache *s;
+	struct folio *folio;
+	struct slab *slab;
+	unsigned long off;
+
+	folio = virt_to_folio(p);
+	if (!folio_test_slab(folio)) {
+		return folio_memcg_kmem(folio) ||
+			(__memcg_kmem_charge_page(folio_page(folio, 0), flags,
+						  folio_order(folio)) == 0);
+	}
+
+	slab = folio_slab(folio);
+	s = slab->slab_cache;
+
+	/*
+	 * Ignore KMALLOC_NORMAL cache to avoid possible circular dependency
+	 * of slab_obj_exts being allocated from the same slab and thus the slab
+	 * becoming effectively unfreeable.
+	 */
+	if (is_kmalloc_normal(s))
+		return true;
+
+	/* Ignore already charged objects. */
+	slab_exts = slab_obj_exts(slab);
+	if (slab_exts) {
+		off = obj_to_index(s, slab, p);
+		if (unlikely(slab_exts[off].objcg))
+			return true;
+	}
+
+	return __memcg_slab_post_alloc_hook(s, NULL, flags, 1, &p);
+}
+
 #else /* CONFIG_MEMCG */
 static inline bool memcg_slab_post_alloc_hook(struct kmem_cache *s,
 					      struct list_lru *lru,
@@ -2198,6 +2237,11 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
 					void **p, int objects)
 {
 }
+
+static inline bool memcg_slab_post_charge(void *p, gfp_t flags)
+{
+	return true;
+}
 #endif /* CONFIG_MEMCG */
 
 #ifdef CONFIG_SLUB_RCU_DEBUG
@@ -4105,6 +4149,15 @@ void *kmem_cache_alloc_lru_noprof(struct kmem_cache *s, struct list_lru *lru,
 }
 EXPORT_SYMBOL(kmem_cache_alloc_lru_noprof);
 
+bool kmem_cache_charge(void *objp, gfp_t gfpflags)
+{
+	if (!memcg_kmem_online())
+		return true;
+
+	return memcg_slab_post_charge(objp, gfpflags);
+}
+EXPORT_SYMBOL(kmem_cache_charge);
+
 /**
  * kmem_cache_alloc_node - Allocate an object on the specified node
  * @s: The cache to allocate from.

net/ipv4/inet_connection_sock.c

@@ -714,6 +714,7 @@ struct sock *inet_csk_accept(struct sock *sk, struct proto_accept_arg *arg)
 out:
 	release_sock(sk);
 	if (newsk && mem_cgroup_sockets_enabled) {
+		gfp_t gfp = GFP_KERNEL | __GFP_NOFAIL;
 		int amt = 0;
 
 		/* atomically get the memory usage, set and charge the
@@ -731,8 +732,8 @@ out:
 		}
 
 		if (amt)
-			mem_cgroup_charge_skmem(newsk->sk_memcg, amt,
-						GFP_KERNEL | __GFP_NOFAIL);
+			mem_cgroup_charge_skmem(newsk->sk_memcg, amt, gfp);
+		kmem_cache_charge(newsk, gfp);
 
 		release_sock(newsk);
 	}