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>

1 files changed, 53 insertions, 0 deletions

diff --git a/mm/slub.c b/mm/slub.c
index 95977f25a760..aa512de974e7 100644
--- a/mm/slub.c
+++ b/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.