1 files changed, 197 insertions, 97 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 1a4fd2504bcd..56cd4af08232 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -54,7 +54,6 @@
 #include <linux/vmpressure.h>
 #include <linux/memremap.h>
 #include <linux/mm_inline.h>
-#include <linux/swap_cgroup.h>
 #include <linux/cpu.h>
 #include <linux/oom.h>
 #include <linux/lockdep.h>
@@ -64,6 +63,7 @@
 #include <linux/sched/isolation.h>
 #include <linux/kmemleak.h>
 #include "internal.h"
+#include "swap_table.h"
 #include <net/sock.h>
 #include <net/ip.h>
 #include "slab.h"
@@ -150,15 +150,15 @@ static void obj_cgroup_release(struct percpu_ref *ref)
 	 * However, it can be PAGE_SIZE or (x * PAGE_SIZE).
 	 *
 	 * The following sequence can lead to it:
-	 * 1) CPU0: objcg == stock->cached_objcg
+	 * 1) CPU0: objcg cached in one of stock->cached[i]
 	 * 2) CPU1: we do a small allocation (e.g. 92 bytes),
 	 *          PAGE_SIZE bytes are charged
 	 * 3) CPU1: a process from another memcg is allocating something,
 	 *          the stock if flushed,
 	 *          objcg->nr_charged_bytes = PAGE_SIZE - 92
-	 * 5) CPU0: we do release this object,
-	 *          92 bytes are added to stock->nr_bytes
-	 * 6) CPU0: stock is flushed,
+	 * 4) CPU0: we do release this object,
+	 *          92 bytes are added to stock->nr_bytes[i]
+	 * 5) CPU0: stock is flushed,
 	 *          92 bytes are added to objcg->nr_charged_bytes
 	 *
 	 * In the result, nr_charged_bytes == PAGE_SIZE.
@@ -2018,24 +2018,49 @@ static DEFINE_PER_CPU_ALIGNED(struct memcg_stock_pcp, memcg_stock) = {
 	.lock = INIT_LOCAL_TRYLOCK(lock),
 };
 
+/*
+ * NR_OBJ_STOCK is sized so the entire hot path of obj_stock_pcp
+ * (lock, accounting metadata, nr_bytes[] and cached[]) fits within a
+ * single 64-byte cache line on non-debug 64-bit builds. With 5 slots:
+ *   lock(1) + index(1) + node_id(2) + slab stats(4) + nr_bytes(10)
+ *   + pad(6) + cached(40) == 64 bytes.
+ * A CPU can thus consume/refill/account against five different objcgs
+ * (typically per-node variants of the same memcg) while incurring at
+ * most one cache miss on the stock.
+ */
+#define NR_OBJ_STOCK 5
 struct obj_stock_pcp {
 	local_trylock_t lock;
-	unsigned int nr_bytes;
-	struct obj_cgroup *cached_objcg;
-	struct pglist_data *cached_pgdat;
-	int nr_slab_reclaimable_b;
-	int nr_slab_unreclaimable_b;
+	int8_t index;
+	int16_t node_id;
+	int16_t nr_slab_reclaimable_b;
+	int16_t nr_slab_unreclaimable_b;
+#if PAGE_SHIFT > 16
+	/*
+	 * On rare archs with 256KiB base page size (hexagon and powerpc 44x)
+	 * keep nr_bytes to unsigned int as uint16_t cannot represent the full
+e patches/memcg-uint16_t-for-nr_bytes-in-obj_stock_pcp.patch	 * sub-page remainder. Such archs are not cacheline optimization target.
+	 */
+	unsigned int nr_bytes[NR_OBJ_STOCK];
+#else
+	uint16_t nr_bytes[NR_OBJ_STOCK];
+#endif
+	struct obj_cgroup *cached[NR_OBJ_STOCK];
 
 	struct work_struct work;
 	unsigned long flags;
+	uint8_t drain_idx;
 };
 
 static DEFINE_PER_CPU_ALIGNED(struct obj_stock_pcp, obj_stock) = {
 	.lock = INIT_LOCAL_TRYLOCK(lock),
+	.index = -1,
+	.node_id = NUMA_NO_NODE,
 };
 
 static DEFINE_MUTEX(percpu_charge_mutex);
 
+static void drain_obj_stock_slot(struct obj_stock_pcp *stock, int i);
 static void drain_obj_stock(struct obj_stock_pcp *stock);
 static bool obj_stock_flush_required(struct obj_stock_pcp *stock,
 				     struct mem_cgroup *root_memcg);
@@ -3155,54 +3180,73 @@ static void unlock_stock(struct obj_stock_pcp *stock)
 		local_unlock(&obj_stock.lock);
 }
 
-/* Call after __refill_obj_stock() to ensure stock->cached_objg == objcg */
+/* Call after __refill_obj_stock() so a slot for objcg exists in the stock */
 static void __account_obj_stock(struct obj_cgroup *objcg,
 				struct obj_stock_pcp *stock, int nr,
 				struct pglist_data *pgdat, enum node_stat_item idx)
 {
-	int *bytes;
+	int16_t *bytes;
+	int i;
 
-	if (!stock || READ_ONCE(stock->cached_objcg) != objcg)
+	/*
+	 * Though at the moment MAX_NUMNODES <= 1024 in all archs but let's make
+	 * sure it does not exceed S16_MAX otherwise we need to fix node_id type
+	 * in struct obj_stock_pcp.
+	 */
+	BUILD_BUG_ON(MAX_NUMNODES >= S16_MAX);
+
+	if (!stock)
+		goto direct;
+
+	for (i = 0; i < NR_OBJ_STOCK; ++i) {
+		if (READ_ONCE(stock->cached[i]) == objcg)
+			break;
+	}
+	if (i == NR_OBJ_STOCK)
 		goto direct;
 
 	/*
 	 * Save vmstat data in stock and skip vmstat array update unless
-	 * accumulating over a page of vmstat data or when pgdat changes.
+	 * accumulating over a page of vmstat data or when the objcg slot or
+	 * pgdat the stats belong to changes.
 	 */
-	if (stock->cached_pgdat != pgdat) {
-		/* Flush the existing cached vmstat data */
-		struct pglist_data *oldpg = stock->cached_pgdat;
+	if (stock->index < 0) {
+		stock->index = i;
+		stock->node_id = pgdat->node_id;
+	} else if (stock->index != i || stock->node_id != pgdat->node_id) {
+		struct obj_cgroup *old = READ_ONCE(stock->cached[stock->index]);
+		struct pglist_data *oldpg = NODE_DATA(stock->node_id);
 
 		if (stock->nr_slab_reclaimable_b) {
-			mod_objcg_mlstate(objcg, oldpg, NR_SLAB_RECLAIMABLE_B,
+			mod_objcg_mlstate(old, oldpg, NR_SLAB_RECLAIMABLE_B,
 					  stock->nr_slab_reclaimable_b);
 			stock->nr_slab_reclaimable_b = 0;
 		}
 		if (stock->nr_slab_unreclaimable_b) {
-			mod_objcg_mlstate(objcg, oldpg, NR_SLAB_UNRECLAIMABLE_B,
+			mod_objcg_mlstate(old, oldpg, NR_SLAB_UNRECLAIMABLE_B,
 					  stock->nr_slab_unreclaimable_b);
 			stock->nr_slab_unreclaimable_b = 0;
 		}
-		stock->cached_pgdat = pgdat;
+		stock->index = i;
+		stock->node_id = pgdat->node_id;
 	}
 
 	bytes = (idx == NR_SLAB_RECLAIMABLE_B) ? &stock->nr_slab_reclaimable_b
 					       : &stock->nr_slab_unreclaimable_b;
+
 	/*
-	 * Even for large object >= PAGE_SIZE, the vmstat data will still be
-	 * cached locally at least once before pushing it out.
+	 * Fold @nr into the cached value and decide whether to keep it cached
+	 * or flush it directly. Cache the combined value when it fits in the
+	 * int16_t storage and either the cache was empty (so even a value
+	 * above PAGE_SIZE gets a chance to be canceled by a paired delta) or
+	 * the combined value is within the PAGE_SIZE flush threshold.
 	 */
-	if (!*bytes) {
+	nr += *bytes;
+	if (abs(nr) <= S16_MAX && (!*bytes || abs(nr) <= PAGE_SIZE)) {
 		*bytes = nr;
 		nr = 0;
 	} else {
-		*bytes += nr;
-		if (abs(*bytes) > PAGE_SIZE) {
-			nr = *bytes;
-			*bytes = 0;
-		} else {
-			nr = 0;
-		}
+		*bytes = 0;
 	}
 direct:
 	if (nr)
@@ -3213,10 +3257,16 @@ static bool __consume_obj_stock(struct obj_cgroup *objcg,
 				struct obj_stock_pcp *stock,
 				unsigned int nr_bytes)
 {
-	if (objcg == READ_ONCE(stock->cached_objcg) &&
-	    stock->nr_bytes >= nr_bytes) {
-		stock->nr_bytes -= nr_bytes;
-		return true;
+	int i;
+
+	for (i = 0; i < NR_OBJ_STOCK; ++i) {
+		if (READ_ONCE(stock->cached[i]) != objcg)
+			continue;
+		if (stock->nr_bytes[i] >= nr_bytes) {
+			stock->nr_bytes[i] -= nr_bytes;
+			return true;
+		}
+		return false;
 	}
 
 	return false;
@@ -3237,16 +3287,42 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
 	return ret;
 }
 
-static void drain_obj_stock(struct obj_stock_pcp *stock)
+/* Flush the cached slab stats (if any) back to their owning objcg/pgdat. */
+static void drain_obj_stock_stats(struct obj_stock_pcp *stock)
 {
-	struct obj_cgroup *old = READ_ONCE(stock->cached_objcg);
+	struct obj_cgroup *old;
+	struct pglist_data *oldpg;
+
+	if (stock->index < 0)
+		return;
+
+	old = READ_ONCE(stock->cached[stock->index]);
+	oldpg = NODE_DATA(stock->node_id);
+
+	if (stock->nr_slab_reclaimable_b) {
+		mod_objcg_mlstate(old, oldpg, NR_SLAB_RECLAIMABLE_B,
+				  stock->nr_slab_reclaimable_b);
+		stock->nr_slab_reclaimable_b = 0;
+	}
+	if (stock->nr_slab_unreclaimable_b) {
+		mod_objcg_mlstate(old, oldpg, NR_SLAB_UNRECLAIMABLE_B,
+				  stock->nr_slab_unreclaimable_b);
+		stock->nr_slab_unreclaimable_b = 0;
+	}
+	stock->index = -1;
+	stock->node_id = NUMA_NO_NODE;
+}
+
+static void drain_obj_stock_slot(struct obj_stock_pcp *stock, int i)
+{
+	struct obj_cgroup *old = READ_ONCE(stock->cached[i]);
 
 	if (!old)
 		return;
 
-	if (stock->nr_bytes) {
-		unsigned int nr_pages = stock->nr_bytes >> PAGE_SHIFT;
-		unsigned int nr_bytes = stock->nr_bytes & (PAGE_SIZE - 1);
+	if (stock->nr_bytes[i]) {
+		unsigned int nr_pages = stock->nr_bytes[i] >> PAGE_SHIFT;
+		unsigned int nr_bytes = stock->nr_bytes[i] & (PAGE_SIZE - 1);
 
 		if (nr_pages) {
 			struct mem_cgroup *memcg;
@@ -3272,44 +3348,43 @@ static void drain_obj_stock(struct obj_stock_pcp *stock)
 		 * so it might be changed in the future.
 		 */
 		atomic_add(nr_bytes, &old->nr_charged_bytes);
-		stock->nr_bytes = 0;
+		stock->nr_bytes[i] = 0;
 	}
 
-	/*
-	 * Flush the vmstat data in current stock
-	 */
-	if (stock->nr_slab_reclaimable_b || stock->nr_slab_unreclaimable_b) {
-		if (stock->nr_slab_reclaimable_b) {
-			mod_objcg_mlstate(old, stock->cached_pgdat,
-					  NR_SLAB_RECLAIMABLE_B,
-					  stock->nr_slab_reclaimable_b);
-			stock->nr_slab_reclaimable_b = 0;
-		}
-		if (stock->nr_slab_unreclaimable_b) {
-			mod_objcg_mlstate(old, stock->cached_pgdat,
-					  NR_SLAB_UNRECLAIMABLE_B,
-					  stock->nr_slab_unreclaimable_b);
-			stock->nr_slab_unreclaimable_b = 0;
-		}
-		stock->cached_pgdat = NULL;
-	}
+	/* Flush vmstat data when its owning slot is being drained. */
+	if (stock->index == i)
+		drain_obj_stock_stats(stock);
 
-	WRITE_ONCE(stock->cached_objcg, NULL);
+	WRITE_ONCE(stock->cached[i], NULL);
 	obj_cgroup_put(old);
 }
 
+static void drain_obj_stock(struct obj_stock_pcp *stock)
+{
+	int i;
+
+	for (i = 0; i < NR_OBJ_STOCK; ++i)
+		drain_obj_stock_slot(stock, i);
+}
+
 static bool obj_stock_flush_required(struct obj_stock_pcp *stock,
 				     struct mem_cgroup *root_memcg)
 {
-	struct obj_cgroup *objcg = READ_ONCE(stock->cached_objcg);
+	struct obj_cgroup *objcg;
 	struct mem_cgroup *memcg;
 	bool flush = false;
+	int i;
 
 	rcu_read_lock();
-	if (objcg) {
+	for (i = 0; i < NR_OBJ_STOCK; ++i) {
+		objcg = READ_ONCE(stock->cached[i]);
+		if (!objcg)
+			continue;
 		memcg = obj_cgroup_memcg(objcg);
-		if (memcg && mem_cgroup_is_descendant(memcg, root_memcg))
+		if (memcg && mem_cgroup_is_descendant(memcg, root_memcg)) {
 			flush = true;
+			break;
+		}
 	}
 	rcu_read_unlock();
 
@@ -3322,6 +3397,8 @@ static void __refill_obj_stock(struct obj_cgroup *objcg,
 			       bool allow_uncharge)
 {
 	unsigned int nr_pages = 0;
+	unsigned int stock_nr_bytes;
+	int i, slot = -1, empty_slot = -1;
 
 	if (!stock) {
 		nr_pages = nr_bytes >> PAGE_SHIFT;
@@ -3330,21 +3407,52 @@ static void __refill_obj_stock(struct obj_cgroup *objcg,
 		goto out;
 	}
 
-	if (READ_ONCE(stock->cached_objcg) != objcg) { /* reset if necessary */
-		drain_obj_stock(stock);
+	for (i = 0; i < NR_OBJ_STOCK; ++i) {
+		struct obj_cgroup *cached = READ_ONCE(stock->cached[i]);
+
+		if (!cached) {
+			if (empty_slot == -1)
+				empty_slot = i;
+			continue;
+		}
+		if (cached == objcg) {
+			slot = i;
+			break;
+		}
+	}
+
+	if (slot == -1) {
+		slot = empty_slot;
+		if (slot == -1) {
+			slot = stock->drain_idx++;
+			if (stock->drain_idx == NR_OBJ_STOCK)
+				stock->drain_idx = 0;
+			drain_obj_stock_slot(stock, slot);
+		}
 		obj_cgroup_get(objcg);
-		stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes)
+		/*
+		 * Keep the xchg result in the unsigned int local; storing
+		 * it directly into stock->nr_bytes[slot] (uint16_t) would
+		 * silently truncate values >= U16_MAX and bypass the flush
+		 * guard below, leaking page-counter charges.
+		 */
+		stock_nr_bytes = atomic_read(&objcg->nr_charged_bytes)
 				? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0;
-		WRITE_ONCE(stock->cached_objcg, objcg);
+		WRITE_ONCE(stock->cached[slot], objcg);
 
 		allow_uncharge = true;	/* Allow uncharge when objcg changes */
+	} else {
+		stock_nr_bytes = stock->nr_bytes[slot];
 	}
-	stock->nr_bytes += nr_bytes;
 
-	if (allow_uncharge && (stock->nr_bytes > PAGE_SIZE)) {
-		nr_pages = stock->nr_bytes >> PAGE_SHIFT;
-		stock->nr_bytes &= (PAGE_SIZE - 1);
+	stock_nr_bytes += nr_bytes;
+
+	if ((allow_uncharge && (stock_nr_bytes > PAGE_SIZE)) ||
+	    stock_nr_bytes > U16_MAX) {
+		nr_pages = stock_nr_bytes >> PAGE_SHIFT;
+		stock_nr_bytes &= (PAGE_SIZE - 1);
 	}
+	stock->nr_bytes[slot] = stock_nr_bytes;
 
 out:
 	if (nr_pages)
@@ -4005,11 +4113,10 @@ static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent)
 	if (!memcg1_alloc_events(memcg))
 		goto fail;
 
+	pstatc_pcpu = parent ? parent->vmstats_percpu : NULL;
 	for_each_possible_cpu(cpu) {
-		if (parent)
-			pstatc_pcpu = parent->vmstats_percpu;
 		statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
-		statc->parent_pcpu = parent ? pstatc_pcpu : NULL;
+		statc->parent_pcpu = pstatc_pcpu;
 		statc->vmstats = memcg->vmstats;
 	}
 
@@ -4037,11 +4144,6 @@ static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent)
 		memcg->cgwb_frn[i].done =
 			__WB_COMPLETION_INIT(&memcg_cgwb_frn_waitq);
 #endif
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	spin_lock_init(&memcg->deferred_split_queue.split_queue_lock);
-	INIT_LIST_HEAD(&memcg->deferred_split_queue.split_queue);
-	memcg->deferred_split_queue.split_queue_len = 0;
-#endif
 	lru_gen_init_memcg(memcg);
 	return memcg;
 fail:
@@ -4192,11 +4294,10 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	zswap_memcg_offline_cleanup(memcg);
 
 	memcg_offline_kmem(memcg);
-	reparent_deferred_split_queue(memcg);
 	/*
-	 * The reparenting of objcg must be after the reparenting of the
-	 * list_lru and deferred_split_queue above, which ensures that they will
-	 * not mistakenly get the parent list_lru and deferred_split_queue.
+	 * The reparenting of objcg must be after the reparenting of
+	 * the list_lru in memcg_offline_kmem(), which ensures that
+	 * they will not mistakenly get the parent list_lru.
 	 */
 	memcg_reparent_objcgs(memcg);
 	reparent_shrinker_deferred(memcg);
@@ -5080,27 +5181,25 @@ out:
 
 /**
  * mem_cgroup_swapin_charge_folio - Charge a newly allocated folio for swapin.
- * @folio: folio to charge.
+ * @folio: the folio to charge
+ * @id: memory cgroup id
  * @mm: mm context of the victim
  * @gfp: reclaim mode
- * @entry: swap entry for which the folio is allocated
  *
  * This function charges a folio allocated for swapin. Please call this before
  * adding the folio to the swapcache.
  *
  * Returns 0 on success. Otherwise, an error code is returned.
  */
-int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm,
-				  gfp_t gfp, swp_entry_t entry)
+int mem_cgroup_swapin_charge_folio(struct folio *folio, unsigned short id,
+				   struct mm_struct *mm, gfp_t gfp)
 {
 	struct mem_cgroup *memcg;
-	unsigned short id;
 	int ret;
 
 	if (mem_cgroup_disabled())
 		return 0;
 
-	id = lookup_swap_cgroup_id(entry);
 	rcu_read_lock();
 	memcg = mem_cgroup_from_private_id(id);
 	if (!memcg || !css_tryget_online(&memcg->css))
@@ -5474,15 +5573,15 @@ int __init mem_cgroup_init(void)
 /**
  * __mem_cgroup_try_charge_swap - try charging swap space for a folio
  * @folio: folio being added to swap
- * @entry: swap entry to charge
  *
- * Try to charge @folio's memcg for the swap space at @entry.
+ * Try to charge @folio's memcg for the swap space at folio->swap.
  *
  * Returns 0 on success, -ENOMEM on failure.
  */
-int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry)
+int __mem_cgroup_try_charge_swap(struct folio *folio)
 {
 	unsigned int nr_pages = folio_nr_pages(folio);
+	struct swap_cluster_info *ci;
 	struct page_counter *counter;
 	struct mem_cgroup *memcg;
 	struct obj_cgroup *objcg;
@@ -5497,7 +5596,7 @@ int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry)
 
 	rcu_read_lock();
 	memcg = obj_cgroup_memcg(objcg);
-	if (!entry.val) {
+	if (!folio_test_swapcache(folio)) {
 		memcg_memory_event(memcg, MEMCG_SWAP_FAIL);
 		rcu_read_unlock();
 		return 0;
@@ -5516,22 +5615,23 @@ int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry)
 	}
 	mod_memcg_state(memcg, MEMCG_SWAP, nr_pages);
 
-	swap_cgroup_record(folio, mem_cgroup_private_id(memcg), entry);
+	ci = swap_cluster_get_and_lock(folio);
+	__swap_cgroup_set(ci, swp_cluster_offset(folio->swap), nr_pages,
+			  mem_cgroup_private_id(memcg));
+	swap_cluster_unlock(ci);
 
 	return 0;
 }
 
 /**
  * __mem_cgroup_uncharge_swap - uncharge swap space
- * @entry: swap entry to uncharge
+ * @id: cgroup id to uncharge
  * @nr_pages: the amount of swap space to uncharge
  */
-void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages)
+void __mem_cgroup_uncharge_swap(unsigned short id, unsigned int nr_pages)
 {
 	struct mem_cgroup *memcg;
-	unsigned short id;
 
-	id = swap_cgroup_clear(entry, nr_pages);
 	rcu_read_lock();
 	memcg = mem_cgroup_from_private_id(id);
 	if (memcg) {