From 1b6a58e205ed0bbeeeca46388f0649f322b04f06 Mon Sep 17 00:00:00 2001 From: Huan Yang Date: Fri, 25 Apr 2025 11:19:25 +0800 Subject: [PATCH] mm/memcg: use kmem_cache when alloc memcg pernode info When tracing mem_cgroup_per_node allocations with kmalloc ftrace: kmalloc: call_site=mem_cgroup_css_alloc+0x1d8/0x5b4 ptr=00000000d798700c bytes_req=2896 bytes_alloc=4096 gfp_flags=GFP_KERNEL|__GFP_ZERO node=0 accounted=false This reveals the slab allocator provides 4096B chunks for 2896B mem_cgroup_per_node due to: 1. The slab allocator predefines bucket sizes from 64B to 8096B 2. The mem_cgroup allocation size (2312B) falls between the 2KB and 4KB slabs 3. The allocator rounds up to the nearest larger slab (4KB), resulting in ~1KB wasted memory per memcg alloc - per node. 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+0x1b8/0x5d4 ptr=000000002989e63a bytes_req=2896 bytes_alloc=2944 gfp_flags=GFP_KERNEL|__GFP_ZERO node=0 accounted=false Each mem_cgroup_per_node alloc 2944bytes(include hw cacheline align), compare to 4096, it avoid waste. Link: https://lkml.kernel.org/r/20250425031935.76411-4-link@vivo.com Signed-off-by: Huan Yang Acked-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Francesco Valla Cc: guoweikang Cc: Huang Shijie Cc: KP Singh Cc: Michal Hocko Cc: Muchun Song Cc: "Paul E . McKenney" Cc: Petr Mladek Cc: Rasmus Villemoes Cc: Raul E Rangel Cc: Roman Gushchin Cc: "Uladzislau Rezki (Sony)" Cc: Vlastimil Babka Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- mm/memcontrol.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6d713fe10221f..8ed265852423f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -97,6 +97,7 @@ static bool cgroup_memory_nokmem __ro_after_init; static bool cgroup_memory_nobpf __ro_after_init; static struct kmem_cache *memcg_cachep; +static struct kmem_cache *memcg_pn_cachep; #ifdef CONFIG_CGROUP_WRITEBACK static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq); @@ -3614,7 +3615,8 @@ static bool alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn; - pn = kzalloc_node(sizeof(*pn), GFP_KERNEL, node); + pn = kmem_cache_alloc_node(memcg_pn_cachep, GFP_KERNEL | __GFP_ZERO, + node); if (!pn) return false; @@ -5075,6 +5077,9 @@ int __init mem_cgroup_init(void) memcg_cachep = kmem_cache_create("mem_cgroup", memcg_size, 0, SLAB_PANIC | SLAB_HWCACHE_ALIGN, NULL); + memcg_pn_cachep = KMEM_CACHE(mem_cgroup_per_node, + SLAB_PANIC | SLAB_HWCACHE_ALIGN); + return 0; } -- 2.39.5