From 19d3046bc5d682d2d478c95cf73f8e394e304d14 Mon Sep 17 00:00:00 2001 From: Huan Yang Date: Fri, 25 Apr 2025 11:19:24 +0800 Subject: [PATCH] BACKPORT: mm/memcg: use kmem_cache when alloc memcg 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 4096-byte chunks. This occurs because: 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 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 2368bytes(include hw cacheline align), compare to 4096, avoid waste. Link: https://lkml.kernel.org/r/20250425031935.76411-3-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 (cherry picked from commit 97e4fc4b35dc1b98f28671fda35bd37d4f401bca) [TJ: struct_size_t not available. Open code it with struct_size.] Change-Id: Ib5c73e7af6eaf2b3066088566690cd0c6f4c796c Bug: 417296244 Signed-off-by: T.J. Mercier --- mm/memcontrol.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 434391a31387..b395871dd23c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -90,6 +90,8 @@ static bool cgroup_memory_nosocket __ro_after_init; /* Kernel memory accounting disabled? */ static bool cgroup_memory_nokmem __ro_after_init; +static struct kmem_cache *memcg_cachep; + #ifdef CONFIG_CGROUP_WRITEBACK static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq); #endif @@ -5320,7 +5322,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) int __maybe_unused i; long error = -ENOMEM; - memcg = kzalloc(struct_size(memcg, nodeinfo, nr_node_ids), GFP_KERNEL); + memcg = kmem_cache_zalloc(memcg_cachep, GFP_KERNEL); if (!memcg) return ERR_PTR(error); @@ -7345,6 +7347,7 @@ __setup("cgroup.memory=", cgroup_memory); */ int __init mem_cgroup_init(void) { + unsigned int memcg_size; int cpu, node; /* @@ -7362,6 +7365,10 @@ int __init mem_cgroup_init(void) INIT_WORK(&per_cpu_ptr(&memcg_stock, cpu)->work, drain_local_stock); + memcg_size = struct_size((struct mem_cgroup *)NULL, nodeinfo, nr_node_ids); + memcg_cachep = kmem_cache_create("mem_cgroup", memcg_size, 0, + SLAB_PANIC | SLAB_HWCACHE_ALIGN, NULL); + for_each_node(node) { struct mem_cgroup_tree_per_node *rtpn;