[PATCH v2 1/3] mm/memcg: use kmem_cache when alloc memcg

[Huan Yang]

When tracing mem_cgroup_alloc() with kmalloc ftrace, we observe:

kmalloc: call_site=mem_cgroup_css_alloc+0xd8/0x5b4 ptr=000000003e4c3799
    bytes_req=2312 bytes_alloc=4096 gfp_flags=GFP_KERNEL|__GFP_ZERO node=-1
    accounted=false

The output indicates that while allocating mem_cgroup struct (2312 bytes),
the slab allocator actually provides 4KB chunks. This occurs because:

1. The slab allocator predefines bucket sizes from 64B to 8096B
2. The mem_cgroup allocation size (2312 bytes) falls between the 2KB and
   4KB slabs
3. The allocator rounds up to the nearest larger slab (4KB), resulting in
   ~1KB wasted memory per allocation

This patch introduces a dedicated kmem_cache for mem_cgroup structs,
achieving precise memory allocation. Post-patch ftrace verification shows:

kmem_cache_alloc: call_site=mem_cgroup_css_alloc+0xbc/0x5d4
    ptr=00000000695c1806 bytes_req=2312 bytes_alloc=2368
    gfp_flags=GFP_KERNEL|__GFP_ZERO node=-1 accounted=false

Each memcg alloc offer 2368 bytes(include hw cacheline align), compare to
4KB, avoid waste.

Signed-off-by: Huan Yang <link@xxxxxxxx>
---
 mm/memcontrol.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5e2ea8b8a898..cb32a498e5ae 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -95,6 +95,8 @@ static bool cgroup_memory_nokmem __ro_after_init;
 /* BPF memory accounting disabled? */
 static bool cgroup_memory_nobpf __ro_after_init;

+static struct kmem_cache *memcg_cachep;
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq);
 #endif
@@ -3652,7 +3654,10 @@ static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent)
 	int __maybe_unused i;
 	long error;

-	memcg = kzalloc(struct_size(memcg, nodeinfo, nr_node_ids), GFP_KERNEL);
+	memcg = likely(memcg_cachep) ?
+			kmem_cache_zalloc(memcg_cachep, GFP_KERNEL) :
+			kzalloc(struct_size(memcg, nodeinfo, nr_node_ids),
+				GFP_KERNEL);
 	if (!memcg)
 		return ERR_PTR(-ENOMEM);

@@ -5039,6 +5044,7 @@ __setup("cgroup.memory=", cgroup_memory);
 static int __init mem_cgroup_init(void)
 {
 	int cpu;
+	unsigned int memcg_size;

 	/*
 	 * Currently s32 type (can refer to struct batched_lruvec_stat) is
@@ -5055,6 +5061,10 @@ static int __init mem_cgroup_init(void)
 		INIT_WORK(&per_cpu_ptr(&memcg_stock, cpu)->work,
 			  drain_local_stock);

+	memcg_size = struct_size_t(struct mem_cgroup, nodeinfo, nr_node_ids);
+	memcg_cachep = kmem_cache_create("mem_cgroup", memcg_size, 0,
+					 SLAB_PANIC | SLAB_HWCACHE_ALIGN, NULL);
+
 	return 0;
 }
 subsys_initcall(mem_cgroup_init);
--
2.48.1