[PATCH mm-stable v3] mm/memcontrol: batch memcg charging in __memcg_slab_post_alloc_hook

[Hui Zhu <hui.zhu@linux.dev>]

From: Hui Zhu <zhuhui@kylinos.cn>

When kmem_cache_alloc_bulk() allocates multiple objects, the post-alloc
hook __memcg_slab_post_alloc_hook() previously charged memcg one object
at a time, even though consecutive objects may reside on slabs backed by
the same pgdat node.

Batch the memcg charging by scanning ahead from the current position to
find a contiguous run of objects whose slabs share the same pgdat, then
issue a single __obj_cgroup_charge() / __consume_obj_stock() call for
the entire run. The per-object obj_ext assignment loop is preserved as-is
since it cannot be further collapsed.

This implements the TODO comment left in commit bc730030f956 ("memcg:
combine slab obj stock charging and accounting").

The existing error-recovery contract is unchanged: if size == 1 then
memcg_alloc_abort_single() will free the sole object, and for larger
bulk allocations kmem_cache_free_bulk() will uncharge any objects that
were already charged before the failure.

Benchmark using kmem_cache_alloc_bulk() with SLAB_ACCOUNT
(iters=100000):

  bulk=32  before: 215 ns/object   after: 174 ns/object  (-19%)
  bulk=1   before: 344 ns/object   after: 335 ns/object  (  ~)

No measurable regression for bulk=1, as expected.

Signed-off-by: Hui Zhu <zhuhui@kylinos.cn>
---

Changelog:
v3:
Update base from "mm-unstable" to "mm-stable".
v2:
According to the comments in [1], add code to handle the integer
overflow issue.

[1] https://sashiko.dev/#/patchset/20260316084839.1342163-1-hui.zhu%40linux.dev

 mm/memcontrol.c | 77 +++++++++++++++++++++++++++++++++++++------------
 1 file changed, 58 insertions(+), 19 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 051b82ebf371..3159bf39e060 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3277,51 +3277,90 @@ bool __memcg_slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru,
 			return false;
 	}
 
-	for (i = 0; i < size; i++) {
+	for (i = 0; i < size; ) {
 		unsigned long obj_exts;
 		struct slabobj_ext *obj_ext;
 		struct obj_stock_pcp *stock;
+		struct pglist_data *pgdat;
+		int batch_bytes;
+		size_t run_len = 0;
+		size_t j;
+		size_t max_size;
+		bool skip_next = false;
 
 		slab = virt_to_slab(p[i]);
 
 		if (!slab_obj_exts(slab) &&
 		    alloc_slab_obj_exts(slab, s, flags, false)) {
+			i++;
 			continue;
 		}
 
+		pgdat = slab_pgdat(slab);
+		run_len = 1;
+
+		/*
+		 * The value of batch_bytes must not exceed
+		 * (INT_MAX - PAGE_SIZE) to prevent integer overflow in
+		 * the final accumulation performed by __account_obj_stock().
+		 */
+		max_size = min((size_t)((INT_MAX - PAGE_SIZE) / obj_size),
+			       size);
+
+		for (j = i + 1; j < max_size; j++) {
+			struct slab *slab_j = virt_to_slab(p[j]);
+
+			if (slab_pgdat(slab_j) != pgdat)
+				break;
+
+			if (!slab_obj_exts(slab_j) &&
+			    alloc_slab_obj_exts(slab_j, s, flags, false)) {
+				skip_next = true;
+				break;
+			}
+
+			run_len++;
+		}
+
 		/*
-		 * if we fail and size is 1, memcg_alloc_abort_single() will
+		 * If we fail and size is 1, memcg_alloc_abort_single() will
 		 * just free the object, which is ok as we have not assigned
-		 * objcg to its obj_ext yet
-		 *
-		 * for larger sizes, kmem_cache_free_bulk() will uncharge
-		 * any objects that were already charged and obj_ext assigned
+		 * objcg to its obj_ext yet.
 		 *
-		 * TODO: we could batch this until slab_pgdat(slab) changes
-		 * between iterations, with a more complicated undo
+		 * For larger sizes, kmem_cache_free_bulk() will uncharge
+		 * any objects that were already charged and obj_ext assigned.
 		 */
+		batch_bytes = obj_size * run_len;
 		stock = trylock_stock();
-		if (!stock || !__consume_obj_stock(objcg, stock, obj_size)) {
+		if (!stock || !__consume_obj_stock(objcg, stock, batch_bytes)) {
 			size_t remainder;
 
 			unlock_stock(stock);
-			if (__obj_cgroup_charge(objcg, flags, obj_size, &remainder))
+			if (__obj_cgroup_charge(objcg, flags, batch_bytes, &remainder))
 				return false;
 			stock = trylock_stock();
 			if (remainder)
 				__refill_obj_stock(objcg, stock, remainder, false);
 		}
-		__account_obj_stock(objcg, stock, obj_size,
-				    slab_pgdat(slab), cache_vmstat_idx(s));
+		__account_obj_stock(objcg, stock, batch_bytes,
+				    pgdat, cache_vmstat_idx(s));
 		unlock_stock(stock);
 
-		obj_exts = slab_obj_exts(slab);
-		get_slab_obj_exts(obj_exts);
-		off = obj_to_index(s, slab, p[i]);
-		obj_ext = slab_obj_ext(slab, obj_exts, off);
-		obj_cgroup_get(objcg);
-		obj_ext->objcg = objcg;
-		put_slab_obj_exts(obj_exts);
+		for (j = 0; j < run_len; j++) {
+			slab = virt_to_slab(p[i + j]);
+			obj_exts = slab_obj_exts(slab);
+			get_slab_obj_exts(obj_exts);
+			off = obj_to_index(s, slab, p[i + j]);
+			obj_ext = slab_obj_ext(slab, obj_exts, off);
+			obj_cgroup_get(objcg);
+			obj_ext->objcg = objcg;
+			put_slab_obj_exts(obj_exts);
+		}
+
+		if (skip_next)
+			i = i + run_len + 1;
+		else
+			i += run_len;
 	}
 
 	return true;
-- 
2.43.0