Merging upstream version 6.8.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 522 insertions, 247 deletions

diff --git a/mm/zswap.c b/mm/zswap.c
index 870fd6f5a5..69766f2c5a 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -35,6 +35,7 @@
 #include <linux/writeback.h>
 #include <linux/pagemap.h>
 #include <linux/workqueue.h>
+#include <linux/list_lru.h>
 
 #include "swap.h"
 #include "internal.h"
@@ -147,6 +148,16 @@ module_param_named(exclusive_loads, zswap_exclusive_loads_enabled, bool, 0644);
 /* Number of zpools in zswap_pool (empirically determined for scalability) */
 #define ZSWAP_NR_ZPOOLS 32
 
+/* Enable/disable memory pressure-based shrinker. */
+static bool zswap_shrinker_enabled = IS_ENABLED(
+		CONFIG_ZSWAP_SHRINKER_DEFAULT_ON);
+module_param_named(shrinker_enabled, zswap_shrinker_enabled, bool, 0644);
+
+bool is_zswap_enabled(void)
+{
+	return zswap_enabled;
+}
+
 /*********************************
 * data structures
 **********************************/
@@ -155,8 +166,8 @@ struct crypto_acomp_ctx {
 	struct crypto_acomp *acomp;
 	struct acomp_req *req;
 	struct crypto_wait wait;
-	u8 *dstmem;
-	struct mutex *mutex;
+	u8 *buffer;
+	struct mutex mutex;
 };
 
 /*
@@ -174,8 +185,10 @@ struct zswap_pool {
 	struct work_struct shrink_work;
 	struct hlist_node node;
 	char tfm_name[CRYPTO_MAX_ALG_NAME];
-	struct list_head lru;
-	spinlock_t lru_lock;
+	struct list_lru list_lru;
+	struct mem_cgroup *next_shrink;
+	struct shrinker *shrinker;
+	atomic_t nr_stored;
 };
 
 /*
@@ -274,32 +287,72 @@ static bool zswap_can_accept(void)
 			DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
 }
 
+static u64 get_zswap_pool_size(struct zswap_pool *pool)
+{
+	u64 pool_size = 0;
+	int i;
+
+	for (i = 0; i < ZSWAP_NR_ZPOOLS; i++)
+		pool_size += zpool_get_total_size(pool->zpools[i]);
+
+	return pool_size;
+}
+
 static void zswap_update_total_size(void)
 {
 	struct zswap_pool *pool;
 	u64 total = 0;
-	int i;
 
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(pool, &zswap_pools, list)
-		for (i = 0; i < ZSWAP_NR_ZPOOLS; i++)
-			total += zpool_get_total_size(pool->zpools[i]);
+		total += get_zswap_pool_size(pool);
 
 	rcu_read_unlock();
 
 	zswap_pool_total_size = total;
 }
 
+/* should be called under RCU */
+#ifdef CONFIG_MEMCG
+static inline struct mem_cgroup *mem_cgroup_from_entry(struct zswap_entry *entry)
+{
+	return entry->objcg ? obj_cgroup_memcg(entry->objcg) : NULL;
+}
+#else
+static inline struct mem_cgroup *mem_cgroup_from_entry(struct zswap_entry *entry)
+{
+	return NULL;
+}
+#endif
+
+static inline int entry_to_nid(struct zswap_entry *entry)
+{
+	return page_to_nid(virt_to_page(entry));
+}
+
+void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg)
+{
+	struct zswap_pool *pool;
+
+	/* lock out zswap pools list modification */
+	spin_lock(&zswap_pools_lock);
+	list_for_each_entry(pool, &zswap_pools, list) {
+		if (pool->next_shrink == memcg)
+			pool->next_shrink = mem_cgroup_iter(NULL, pool->next_shrink, NULL);
+	}
+	spin_unlock(&zswap_pools_lock);
+}
+
 /*********************************
 * zswap entry functions
 **********************************/
 static struct kmem_cache *zswap_entry_cache;
 
-static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp)
+static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp, int nid)
 {
 	struct zswap_entry *entry;
-	entry = kmem_cache_alloc(zswap_entry_cache, gfp);
+	entry = kmem_cache_alloc_node(zswap_entry_cache, gfp, nid);
 	if (!entry)
 		return NULL;
 	entry->refcount = 1;
@@ -313,6 +366,99 @@ static void zswap_entry_cache_free(struct zswap_entry *entry)
 }
 
 /*********************************
+* zswap lruvec functions
+**********************************/
+void zswap_lruvec_state_init(struct lruvec *lruvec)
+{
+	atomic_long_set(&lruvec->zswap_lruvec_state.nr_zswap_protected, 0);
+}
+
+void zswap_folio_swapin(struct folio *folio)
+{
+	struct lruvec *lruvec;
+
+	VM_WARN_ON_ONCE(!folio_test_locked(folio));
+	lruvec = folio_lruvec(folio);
+	atomic_long_inc(&lruvec->zswap_lruvec_state.nr_zswap_protected);
+}
+
+/*********************************
+* lru functions
+**********************************/
+static void zswap_lru_add(struct list_lru *list_lru, struct zswap_entry *entry)
+{
+	atomic_long_t *nr_zswap_protected;
+	unsigned long lru_size, old, new;
+	int nid = entry_to_nid(entry);
+	struct mem_cgroup *memcg;
+	struct lruvec *lruvec;
+
+	/*
+	 * Note that it is safe to use rcu_read_lock() here, even in the face of
+	 * concurrent memcg offlining. Thanks to the memcg->kmemcg_id indirection
+	 * used in list_lru lookup, only two scenarios are possible:
+	 *
+	 * 1. list_lru_add() is called before memcg->kmemcg_id is updated. The
+	 *    new entry will be reparented to memcg's parent's list_lru.
+	 * 2. list_lru_add() is called after memcg->kmemcg_id is updated. The
+	 *    new entry will be added directly to memcg's parent's list_lru.
+	 *
+	 * Similar reasoning holds for list_lru_del() and list_lru_putback().
+	 */
+	rcu_read_lock();
+	memcg = mem_cgroup_from_entry(entry);
+	/* will always succeed */
+	list_lru_add(list_lru, &entry->lru, nid, memcg);
+
+	/* Update the protection area */
+	lru_size = list_lru_count_one(list_lru, nid, memcg);
+	lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
+	nr_zswap_protected = &lruvec->zswap_lruvec_state.nr_zswap_protected;
+	old = atomic_long_inc_return(nr_zswap_protected);
+	/*
+	 * Decay to avoid overflow and adapt to changing workloads.
+	 * This is based on LRU reclaim cost decaying heuristics.
+	 */
+	do {
+		new = old > lru_size / 4 ? old / 2 : old;
+	} while (!atomic_long_try_cmpxchg(nr_zswap_protected, &old, new));
+	rcu_read_unlock();
+}
+
+static void zswap_lru_del(struct list_lru *list_lru, struct zswap_entry *entry)
+{
+	int nid = entry_to_nid(entry);
+	struct mem_cgroup *memcg;
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_entry(entry);
+	/* will always succeed */
+	list_lru_del(list_lru, &entry->lru, nid, memcg);
+	rcu_read_unlock();
+}
+
+static void zswap_lru_putback(struct list_lru *list_lru,
+		struct zswap_entry *entry)
+{
+	int nid = entry_to_nid(entry);
+	spinlock_t *lock = &list_lru->node[nid].lock;
+	struct mem_cgroup *memcg;
+	struct lruvec *lruvec;
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_entry(entry);
+	spin_lock(lock);
+	/* we cannot use list_lru_add here, because it increments node's lru count */
+	list_lru_putback(list_lru, &entry->lru, nid, memcg);
+	spin_unlock(lock);
+
+	lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(entry_to_nid(entry)));
+	/* increment the protection area to account for the LRU rotation. */
+	atomic_long_inc(&lruvec->zswap_lruvec_state.nr_zswap_protected);
+	rcu_read_unlock();
+}
+
+/*********************************
 * rbtree functions
 **********************************/
 static struct zswap_entry *zswap_rb_search(struct rb_root *root, pgoff_t offset)
@@ -389,19 +535,18 @@ static struct zpool *zswap_find_zpool(struct zswap_entry *entry)
  */
 static void zswap_free_entry(struct zswap_entry *entry)
 {
-	if (entry->objcg) {
-		obj_cgroup_uncharge_zswap(entry->objcg, entry->length);
-		obj_cgroup_put(entry->objcg);
-	}
 	if (!entry->length)
 		atomic_dec(&zswap_same_filled_pages);
 	else {
-		spin_lock(&entry->pool->lru_lock);
-		list_del(&entry->lru);
-		spin_unlock(&entry->pool->lru_lock);
+		zswap_lru_del(&entry->pool->list_lru, entry);
 		zpool_free(zswap_find_zpool(entry), entry->handle);
+		atomic_dec(&entry->pool->nr_stored);
 		zswap_pool_put(entry->pool);
 	}
+	if (entry->objcg) {
+		obj_cgroup_uncharge_zswap(entry->objcg, entry->length);
+		obj_cgroup_put(entry->objcg);
+	}
 	zswap_entry_cache_free(entry);
 	atomic_dec(&zswap_stored_pages);
 	zswap_update_total_size();
@@ -442,65 +587,147 @@ static struct zswap_entry *zswap_entry_find_get(struct rb_root *root,
 }
 
 /*********************************
-* per-cpu code
+* shrinker functions
 **********************************/
-static DEFINE_PER_CPU(u8 *, zswap_dstmem);
-/*
- * If users dynamically change the zpool type and compressor at runtime, i.e.
- * zswap is running, zswap can have more than one zpool on one cpu, but they
- * are sharing dtsmem. So we need this mutex to be per-cpu.
- */
-static DEFINE_PER_CPU(struct mutex *, zswap_mutex);
+static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_one *l,
+				       spinlock_t *lock, void *arg);
 
-static int zswap_dstmem_prepare(unsigned int cpu)
+static unsigned long zswap_shrinker_scan(struct shrinker *shrinker,
+		struct shrink_control *sc)
 {
-	struct mutex *mutex;
-	u8 *dst;
+	struct lruvec *lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid));
+	unsigned long shrink_ret, nr_protected, lru_size;
+	struct zswap_pool *pool = shrinker->private_data;
+	bool encountered_page_in_swapcache = false;
+
+	if (!zswap_shrinker_enabled ||
+			!mem_cgroup_zswap_writeback_enabled(sc->memcg)) {
+		sc->nr_scanned = 0;
+		return SHRINK_STOP;
+	}
 
-	dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
-	if (!dst)
-		return -ENOMEM;
+	nr_protected =
+		atomic_long_read(&lruvec->zswap_lruvec_state.nr_zswap_protected);
+	lru_size = list_lru_shrink_count(&pool->list_lru, sc);
 
-	mutex = kmalloc_node(sizeof(*mutex), GFP_KERNEL, cpu_to_node(cpu));
-	if (!mutex) {
-		kfree(dst);
-		return -ENOMEM;
+	/*
+	 * Abort if we are shrinking into the protected region.
+	 *
+	 * This short-circuiting is necessary because if we have too many multiple
+	 * concurrent reclaimers getting the freeable zswap object counts at the
+	 * same time (before any of them made reasonable progress), the total
+	 * number of reclaimed objects might be more than the number of unprotected
+	 * objects (i.e the reclaimers will reclaim into the protected area of the
+	 * zswap LRU).
+	 */
+	if (nr_protected >= lru_size - sc->nr_to_scan) {
+		sc->nr_scanned = 0;
+		return SHRINK_STOP;
 	}
 
-	mutex_init(mutex);
-	per_cpu(zswap_dstmem, cpu) = dst;
-	per_cpu(zswap_mutex, cpu) = mutex;
-	return 0;
+	shrink_ret = list_lru_shrink_walk(&pool->list_lru, sc, &shrink_memcg_cb,
+		&encountered_page_in_swapcache);
+
+	if (encountered_page_in_swapcache)
+		return SHRINK_STOP;
+
+	return shrink_ret ? shrink_ret : SHRINK_STOP;
 }
 
-static int zswap_dstmem_dead(unsigned int cpu)
+static unsigned long zswap_shrinker_count(struct shrinker *shrinker,
+		struct shrink_control *sc)
 {
-	struct mutex *mutex;
-	u8 *dst;
+	struct zswap_pool *pool = shrinker->private_data;
+	struct mem_cgroup *memcg = sc->memcg;
+	struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(sc->nid));
+	unsigned long nr_backing, nr_stored, nr_freeable, nr_protected;
+
+	if (!zswap_shrinker_enabled || !mem_cgroup_zswap_writeback_enabled(memcg))
+		return 0;
+
+	/*
+	 * The shrinker resumes swap writeback, which will enter block
+	 * and may enter fs. XXX: Harmonize with vmscan.c __GFP_FS
+	 * rules (may_enter_fs()), which apply on a per-folio basis.
+	 */
+	if (!gfp_has_io_fs(sc->gfp_mask))
+		return 0;
 
-	mutex = per_cpu(zswap_mutex, cpu);
-	kfree(mutex);
-	per_cpu(zswap_mutex, cpu) = NULL;
+	/*
+	 * For memcg, use the cgroup-wide ZSWAP stats since we don't
+	 * have them per-node and thus per-lruvec. Careful if memcg is
+	 * runtime-disabled: we can get sc->memcg == NULL, which is ok
+	 * for the lruvec, but not for memcg_page_state().
+	 *
+	 * Without memcg, use the zswap pool-wide metrics.
+	 */
+	if (!mem_cgroup_disabled()) {
+		mem_cgroup_flush_stats(memcg);
+		nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT;
+		nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED);
+	} else {
+		nr_backing = get_zswap_pool_size(pool) >> PAGE_SHIFT;
+		nr_stored = atomic_read(&pool->nr_stored);
+	}
 
-	dst = per_cpu(zswap_dstmem, cpu);
-	kfree(dst);
-	per_cpu(zswap_dstmem, cpu) = NULL;
+	if (!nr_stored)
+		return 0;
 
-	return 0;
+	nr_protected =
+		atomic_long_read(&lruvec->zswap_lruvec_state.nr_zswap_protected);
+	nr_freeable = list_lru_shrink_count(&pool->list_lru, sc);
+	/*
+	 * Subtract the lru size by an estimate of the number of pages
+	 * that should be protected.
+	 */
+	nr_freeable = nr_freeable > nr_protected ? nr_freeable - nr_protected : 0;
+
+	/*
+	 * Scale the number of freeable pages by the memory saving factor.
+	 * This ensures that the better zswap compresses memory, the fewer
+	 * pages we will evict to swap (as it will otherwise incur IO for
+	 * relatively small memory saving).
+	 */
+	return mult_frac(nr_freeable, nr_backing, nr_stored);
 }
 
+static void zswap_alloc_shrinker(struct zswap_pool *pool)
+{
+	pool->shrinker =
+		shrinker_alloc(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, "mm-zswap");
+	if (!pool->shrinker)
+		return;
+
+	pool->shrinker->private_data = pool;
+	pool->shrinker->scan_objects = zswap_shrinker_scan;
+	pool->shrinker->count_objects = zswap_shrinker_count;
+	pool->shrinker->batch = 0;
+	pool->shrinker->seeks = DEFAULT_SEEKS;
+}
+
+/*********************************
+* per-cpu code
+**********************************/
 static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 {
 	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
 	struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
 	struct crypto_acomp *acomp;
 	struct acomp_req *req;
+	int ret;
+
+	mutex_init(&acomp_ctx->mutex);
+
+	acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
+	if (!acomp_ctx->buffer)
+		return -ENOMEM;
 
 	acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu));
 	if (IS_ERR(acomp)) {
 		pr_err("could not alloc crypto acomp %s : %ld\n",
 				pool->tfm_name, PTR_ERR(acomp));
-		return PTR_ERR(acomp);
+		ret = PTR_ERR(acomp);
+		goto acomp_fail;
 	}
 	acomp_ctx->acomp = acomp;
 
@@ -508,8 +735,8 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 	if (!req) {
 		pr_err("could not alloc crypto acomp_request %s\n",
 		       pool->tfm_name);
-		crypto_free_acomp(acomp_ctx->acomp);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto req_fail;
 	}
 	acomp_ctx->req = req;
 
@@ -522,10 +749,13 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 	acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				   crypto_req_done, &acomp_ctx->wait);
 
-	acomp_ctx->mutex = per_cpu(zswap_mutex, cpu);
-	acomp_ctx->dstmem = per_cpu(zswap_dstmem, cpu);
-
 	return 0;
+
+req_fail:
+	crypto_free_acomp(acomp_ctx->acomp);
+acomp_fail:
+	kfree(acomp_ctx->buffer);
+	return ret;
 }
 
 static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
@@ -538,6 +768,7 @@ static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
 			acomp_request_free(acomp_ctx->req);
 		if (!IS_ERR_OR_NULL(acomp_ctx->acomp))
 			crypto_free_acomp(acomp_ctx->acomp);
+		kfree(acomp_ctx->buffer);
 	}
 
 	return 0;
@@ -632,21 +863,16 @@ static void zswap_invalidate_entry(struct zswap_tree *tree,
 		zswap_entry_put(tree, entry);
 }
 
-static int zswap_reclaim_entry(struct zswap_pool *pool)
+static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_one *l,
+				       spinlock_t *lock, void *arg)
 {
-	struct zswap_entry *entry;
+	struct zswap_entry *entry = container_of(item, struct zswap_entry, lru);
+	bool *encountered_page_in_swapcache = (bool *)arg;
 	struct zswap_tree *tree;
 	pgoff_t swpoffset;
-	int ret;
+	enum lru_status ret = LRU_REMOVED_RETRY;
+	int writeback_result;
 
-	/* Get an entry off the LRU */
-	spin_lock(&pool->lru_lock);
-	if (list_empty(&pool->lru)) {
-		spin_unlock(&pool->lru_lock);
-		return -EINVAL;
-	}
-	entry = list_last_entry(&pool->lru, struct zswap_entry, lru);
-	list_del_init(&entry->lru);
 	/*
 	 * Once the lru lock is dropped, the entry might get freed. The
 	 * swpoffset is copied to the stack, and entry isn't deref'd again
@@ -654,29 +880,46 @@ static int zswap_reclaim_entry(struct zswap_pool *pool)
 	 */
 	swpoffset = swp_offset(entry->swpentry);
 	tree = zswap_trees[swp_type(entry->swpentry)];
-	spin_unlock(&pool->lru_lock);
+	list_lru_isolate(l, item);
+	/*
+	 * It's safe to drop the lock here because we return either
+	 * LRU_REMOVED_RETRY or LRU_RETRY.
+	 */
+	spin_unlock(lock);
 
 	/* Check for invalidate() race */
 	spin_lock(&tree->lock);
-	if (entry != zswap_rb_search(&tree->rbroot, swpoffset)) {
-		ret = -EAGAIN;
+	if (entry != zswap_rb_search(&tree->rbroot, swpoffset))
 		goto unlock;
-	}
+
 	/* Hold a reference to prevent a free during writeback */
 	zswap_entry_get(entry);
 	spin_unlock(&tree->lock);
 
-	ret = zswap_writeback_entry(entry, tree);
+	writeback_result = zswap_writeback_entry(entry, tree);
 
 	spin_lock(&tree->lock);
-	if (ret) {
-		/* Writeback failed, put entry back on LRU */
-		spin_lock(&pool->lru_lock);
-		list_move(&entry->lru, &pool->lru);
-		spin_unlock(&pool->lru_lock);
+	if (writeback_result) {
+		zswap_reject_reclaim_fail++;
+		zswap_lru_putback(&entry->pool->list_lru, entry);
+		ret = LRU_RETRY;
+
+		/*
+		 * Encountering a page already in swap cache is a sign that we are shrinking
+		 * into the warmer region. We should terminate shrinking (if we're in the dynamic
+		 * shrinker context).
+		 */
+		if (writeback_result == -EEXIST && encountered_page_in_swapcache)
+			*encountered_page_in_swapcache = true;
+
 		goto put_unlock;
 	}
+	zswap_written_back_pages++;
+
+	if (entry->objcg)
+		count_objcg_event(entry->objcg, ZSWPWB);
 
+	count_vm_event(ZSWPWB);
 	/*
 	 * Writeback started successfully, the page now belongs to the
 	 * swapcache. Drop the entry from zswap - unless invalidate already
@@ -689,24 +932,94 @@ put_unlock:
 	zswap_entry_put(tree, entry);
 unlock:
 	spin_unlock(&tree->lock);
-	return ret ? -EAGAIN : 0;
+	spin_lock(lock);
+	return ret;
+}
+
+static int shrink_memcg(struct mem_cgroup *memcg)
+{
+	struct zswap_pool *pool;
+	int nid, shrunk = 0;
+
+	if (!mem_cgroup_zswap_writeback_enabled(memcg))
+		return -EINVAL;
+
+	/*
+	 * Skip zombies because their LRUs are reparented and we would be
+	 * reclaiming from the parent instead of the dead memcg.
+	 */
+	if (memcg && !mem_cgroup_online(memcg))
+		return -ENOENT;
+
+	pool = zswap_pool_current_get();
+	if (!pool)
+		return -EINVAL;
+
+	for_each_node_state(nid, N_NORMAL_MEMORY) {
+		unsigned long nr_to_walk = 1;
+
+		shrunk += list_lru_walk_one(&pool->list_lru, nid, memcg,
+					    &shrink_memcg_cb, NULL, &nr_to_walk);
+	}
+	zswap_pool_put(pool);
+	return shrunk ? 0 : -EAGAIN;
 }
 
 static void shrink_worker(struct work_struct *w)
 {
 	struct zswap_pool *pool = container_of(w, typeof(*pool),
 						shrink_work);
+	struct mem_cgroup *memcg;
 	int ret, failures = 0;
 
+	/* global reclaim will select cgroup in a round-robin fashion. */
 	do {
-		ret = zswap_reclaim_entry(pool);
-		if (ret) {
-			zswap_reject_reclaim_fail++;
-			if (ret != -EAGAIN)
+		spin_lock(&zswap_pools_lock);
+		pool->next_shrink = mem_cgroup_iter(NULL, pool->next_shrink, NULL);
+		memcg = pool->next_shrink;
+
+		/*
+		 * We need to retry if we have gone through a full round trip, or if we
+		 * got an offline memcg (or else we risk undoing the effect of the
+		 * zswap memcg offlining cleanup callback). This is not catastrophic
+		 * per se, but it will keep the now offlined memcg hostage for a while.
+		 *
+		 * Note that if we got an online memcg, we will keep the extra
+		 * reference in case the original reference obtained by mem_cgroup_iter
+		 * is dropped by the zswap memcg offlining callback, ensuring that the
+		 * memcg is not killed when we are reclaiming.
+		 */
+		if (!memcg) {
+			spin_unlock(&zswap_pools_lock);
+			if (++failures == MAX_RECLAIM_RETRIES)
 				break;
+
+			goto resched;
+		}
+
+		if (!mem_cgroup_tryget_online(memcg)) {
+			/* drop the reference from mem_cgroup_iter() */
+			mem_cgroup_iter_break(NULL, memcg);
+			pool->next_shrink = NULL;
+			spin_unlock(&zswap_pools_lock);
+
 			if (++failures == MAX_RECLAIM_RETRIES)
 				break;
+
+			goto resched;
 		}
+		spin_unlock(&zswap_pools_lock);
+
+		ret = shrink_memcg(memcg);
+		/* drop the extra reference */
+		mem_cgroup_put(memcg);
+
+		if (ret == -EINVAL)
+			break;
+		if (ret && ++failures == MAX_RECLAIM_RETRIES)
+			break;
+
+resched:
 		cond_resched();
 	} while (!zswap_can_accept());
 	zswap_pool_put(pool);
@@ -760,6 +1073,11 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 				       &pool->node);
 	if (ret)
 		goto error;
+
+	zswap_alloc_shrinker(pool);
+	if (!pool->shrinker)
+		goto error;
+
 	pr_debug("using %s compressor\n", pool->tfm_name);
 
 	/* being the current pool takes 1 ref; this func expects the
@@ -767,14 +1085,19 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 	 */
 	kref_init(&pool->kref);
 	INIT_LIST_HEAD(&pool->list);
-	INIT_LIST_HEAD(&pool->lru);
-	spin_lock_init(&pool->lru_lock);
+	if (list_lru_init_memcg(&pool->list_lru, pool->shrinker))
+		goto lru_fail;
+	shrinker_register(pool->shrinker);
 	INIT_WORK(&pool->shrink_work, shrink_worker);
+	atomic_set(&pool->nr_stored, 0);
 
 	zswap_pool_debug("created", pool);
 
 	return pool;
 
+lru_fail:
+	list_lru_destroy(&pool->list_lru);
+	shrinker_free(pool->shrinker);
 error:
 	if (pool->acomp_ctx)
 		free_percpu(pool->acomp_ctx);
@@ -832,8 +1155,16 @@ static void zswap_pool_destroy(struct zswap_pool *pool)
 
 	zswap_pool_debug("destroying", pool);
 
+	shrinker_free(pool->shrinker);
 	cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node);
 	free_percpu(pool->acomp_ctx);
+	list_lru_destroy(&pool->list_lru);
+
+	spin_lock(&zswap_pools_lock);
+	mem_cgroup_iter_break(NULL, pool->next_shrink);
+	pool->next_shrink = NULL;
+	spin_unlock(&zswap_pools_lock);
+
 	for (i = 0; i < ZSWAP_NR_ZPOOLS; i++)
 		zpool_destroy_pool(pool->zpools[i]);
 	kfree(pool);
@@ -1040,18 +1371,47 @@ static int zswap_enabled_param_set(const char *val,
 	return ret;
 }
 
+static void __zswap_load(struct zswap_entry *entry, struct page *page)
+{
+	struct zpool *zpool = zswap_find_zpool(entry);
+	struct scatterlist input, output;
+	struct crypto_acomp_ctx *acomp_ctx;
+	u8 *src;
+
+	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
+	mutex_lock(&acomp_ctx->mutex);
+
+	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
+	if (!zpool_can_sleep_mapped(zpool)) {
+		memcpy(acomp_ctx->buffer, src, entry->length);
+		src = acomp_ctx->buffer;
+		zpool_unmap_handle(zpool, entry->handle);
+	}
+
+	sg_init_one(&input, src, entry->length);
+	sg_init_table(&output, 1);
+	sg_set_page(&output, page, PAGE_SIZE, 0);
+	acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, PAGE_SIZE);
+	BUG_ON(crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait));
+	BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE);
+	mutex_unlock(&acomp_ctx->mutex);
+
+	if (zpool_can_sleep_mapped(zpool))
+		zpool_unmap_handle(zpool, entry->handle);
+}
+
 /*********************************
 * writeback code
 **********************************/
 /*
- * Attempts to free an entry by adding a page to the swap cache,
- * decompressing the entry data into the page, and issuing a
- * bio write to write the page back to the swap device.
+ * Attempts to free an entry by adding a folio to the swap cache,
+ * decompressing the entry data into the folio, and issuing a
+ * bio write to write the folio back to the swap device.
  *
- * This can be thought of as a "resumed writeback" of the page
+ * This can be thought of as a "resumed writeback" of the folio
  * to the swap device.  We are basically resuming the same swap
  * writeback path that was intercepted with the zswap_store()
- * in the first place.  After the page has been decompressed into
+ * in the first place.  After the folio has been decompressed into
  * the swap cache, the compressed version stored by zswap can be
  * freed.
  */
@@ -1059,110 +1419,60 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 				 struct zswap_tree *tree)
 {
 	swp_entry_t swpentry = entry->swpentry;
-	struct page *page;
+	struct folio *folio;
 	struct mempolicy *mpol;
-	struct scatterlist input, output;
-	struct crypto_acomp_ctx *acomp_ctx;
-	struct zpool *pool = zswap_find_zpool(entry);
-	bool page_was_allocated;
-	u8 *src, *tmp = NULL;
-	unsigned int dlen;
-	int ret;
+	bool folio_was_allocated;
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_NONE,
 	};
 
-	if (!zpool_can_sleep_mapped(pool)) {
-		tmp = kmalloc(PAGE_SIZE, GFP_KERNEL);
-		if (!tmp)
-			return -ENOMEM;
-	}
-
-	/* try to allocate swap cache page */
+	/* try to allocate swap cache folio */
 	mpol = get_task_policy(current);
-	page = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol,
-				NO_INTERLEAVE_INDEX, &page_was_allocated);
-	if (!page) {
-		ret = -ENOMEM;
-		goto fail;
-	}
+	folio = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol,
+				NO_INTERLEAVE_INDEX, &folio_was_allocated, true);
+	if (!folio)
+		return -ENOMEM;
 
-	/* Found an existing page, we raced with load/swapin */
-	if (!page_was_allocated) {
-		put_page(page);
-		ret = -EEXIST;
-		goto fail;
+	/*
+	 * Found an existing folio, we raced with load/swapin. We generally
+	 * writeback cold folios from zswap, and swapin means the folio just
+	 * became hot. Skip this folio and let the caller find another one.
+	 */
+	if (!folio_was_allocated) {
+		folio_put(folio);
+		return -EEXIST;
 	}
 
 	/*
-	 * Page is locked, and the swapcache is now secured against
+	 * folio is locked, and the swapcache is now secured against
 	 * concurrent swapping to and from the slot. Verify that the
 	 * swap entry hasn't been invalidated and recycled behind our
 	 * backs (our zswap_entry reference doesn't prevent that), to
-	 * avoid overwriting a new swap page with old compressed data.
+	 * avoid overwriting a new swap folio with old compressed data.
 	 */
 	spin_lock(&tree->lock);
 	if (zswap_rb_search(&tree->rbroot, swp_offset(entry->swpentry)) != entry) {
 		spin_unlock(&tree->lock);
-		delete_from_swap_cache(page_folio(page));
-		unlock_page(page);
-		put_page(page);
-		ret = -ENOMEM;
-		goto fail;
+		delete_from_swap_cache(folio);
+		folio_unlock(folio);
+		folio_put(folio);
+		return -ENOMEM;
 	}
 	spin_unlock(&tree->lock);
 
-	/* decompress */
-	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
-	dlen = PAGE_SIZE;
+	__zswap_load(entry, &folio->page);
 
-	src = zpool_map_handle(pool, entry->handle, ZPOOL_MM_RO);
-	if (!zpool_can_sleep_mapped(pool)) {
-		memcpy(tmp, src, entry->length);
-		src = tmp;
-		zpool_unmap_handle(pool, entry->handle);
-	}
-
-	mutex_lock(acomp_ctx->mutex);
-	sg_init_one(&input, src, entry->length);
-	sg_init_table(&output, 1);
-	sg_set_page(&output, page, PAGE_SIZE, 0);
-	acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, dlen);
-	ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait);
-	dlen = acomp_ctx->req->dlen;
-	mutex_unlock(acomp_ctx->mutex);
-
-	if (!zpool_can_sleep_mapped(pool))
-		kfree(tmp);
-	else
-		zpool_unmap_handle(pool, entry->handle);
-
-	BUG_ON(ret);
-	BUG_ON(dlen != PAGE_SIZE);
-
-	/* page is up to date */
-	SetPageUptodate(page);
+	/* folio is up to date */
+	folio_mark_uptodate(folio);
 
 	/* move it to the tail of the inactive list after end_writeback */
-	SetPageReclaim(page);
+	folio_set_reclaim(folio);
 
 	/* start writeback */
-	__swap_writepage(page, &wbc);
-	put_page(page);
-	zswap_written_back_pages++;
+	__swap_writepage(folio, &wbc);
+	folio_put(folio);
 
-	return ret;
-
-fail:
-	if (!zpool_can_sleep_mapped(pool))
-		kfree(tmp);
-
-	/*
-	 * If we get here because the page is already in swapcache, a
-	 * load may be happening concurrently. It is safe and okay to
-	 * not free the entry. It is also okay to return !0.
-	 */
-	return ret;
+	return 0;
 }
 
 static int zswap_is_page_same_filled(void *ptr, unsigned long *value)
@@ -1206,6 +1516,7 @@ bool zswap_store(struct folio *folio)
 	struct scatterlist input, output;
 	struct crypto_acomp_ctx *acomp_ctx;
 	struct obj_cgroup *objcg = NULL;
+	struct mem_cgroup *memcg = NULL;
 	struct zswap_pool *pool;
 	struct zpool *zpool;
 	unsigned int dlen = PAGE_SIZE;
@@ -1241,14 +1552,15 @@ bool zswap_store(struct folio *folio)
 	if (!zswap_enabled)
 		return false;
 
-	/*
-	 * XXX: zswap reclaim does not work with cgroups yet. Without a
-	 * cgroup-aware entry LRU, we will push out entries system-wide based on
-	 * local cgroup limits.
-	 */
 	objcg = get_obj_cgroup_from_folio(folio);
-	if (objcg && !obj_cgroup_may_zswap(objcg))
-		goto reject;
+	if (objcg && !obj_cgroup_may_zswap(objcg)) {
+		memcg = get_mem_cgroup_from_objcg(objcg);
+		if (shrink_memcg(memcg)) {
+			mem_cgroup_put(memcg);
+			goto reject;
+		}
+		mem_cgroup_put(memcg);
+	}
 
 	/* reclaim space if needed */
 	if (zswap_is_full()) {
@@ -1265,23 +1577,23 @@ bool zswap_store(struct folio *folio)
 	}
 
 	/* allocate entry */
-	entry = zswap_entry_cache_alloc(GFP_KERNEL);
+	entry = zswap_entry_cache_alloc(GFP_KERNEL, page_to_nid(page));
 	if (!entry) {
 		zswap_reject_kmemcache_fail++;
 		goto reject;
 	}
 
 	if (zswap_same_filled_pages_enabled) {
-		src = kmap_atomic(page);
+		src = kmap_local_page(page);
 		if (zswap_is_page_same_filled(src, &value)) {
-			kunmap_atomic(src);
+			kunmap_local(src);
 			entry->swpentry = swp_entry(type, offset);
 			entry->length = 0;
 			entry->value = value;
 			atomic_inc(&zswap_same_filled_pages);
 			goto insert_entry;
 		}
-		kunmap_atomic(src);
+		kunmap_local(src);
 	}
 
 	if (!zswap_non_same_filled_pages_enabled)
@@ -1292,16 +1604,29 @@ bool zswap_store(struct folio *folio)
 	if (!entry->pool)
 		goto freepage;
 
+	if (objcg) {
+		memcg = get_mem_cgroup_from_objcg(objcg);
+		if (memcg_list_lru_alloc(memcg, &entry->pool->list_lru, GFP_KERNEL)) {
+			mem_cgroup_put(memcg);
+			goto put_pool;
+		}
+		mem_cgroup_put(memcg);
+	}
+
 	/* compress */
 	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
 
-	mutex_lock(acomp_ctx->mutex);
+	mutex_lock(&acomp_ctx->mutex);
 
-	dst = acomp_ctx->dstmem;
+	dst = acomp_ctx->buffer;
 	sg_init_table(&input, 1);
-	sg_set_page(&input, page, PAGE_SIZE, 0);
+	sg_set_page(&input, &folio->page, PAGE_SIZE, 0);
 
-	/* zswap_dstmem is of size (PAGE_SIZE * 2). Reflect same in sg_list */
+	/*
+	 * We need PAGE_SIZE * 2 here since there maybe over-compression case,
+	 * and hardware-accelerators may won't check the dst buffer size, so
+	 * giving the dst buffer with enough length to avoid buffer overflow.
+	 */
 	sg_init_one(&output, dst, PAGE_SIZE * 2);
 	acomp_request_set_params(acomp_ctx->req, &input, &output, PAGE_SIZE, dlen);
 	/*
@@ -1341,7 +1666,7 @@ bool zswap_store(struct folio *folio)
 	buf = zpool_map_handle(zpool, handle, ZPOOL_MM_WO);
 	memcpy(buf, dst, dlen);
 	zpool_unmap_handle(zpool, handle);
-	mutex_unlock(acomp_ctx->mutex);
+	mutex_unlock(&acomp_ctx->mutex);
 
 	/* populate entry */
 	entry->swpentry = swp_entry(type, offset);
@@ -1370,9 +1695,9 @@ insert_entry:
 		zswap_invalidate_entry(tree, dupentry);
 	}
 	if (entry->length) {
-		spin_lock(&entry->pool->lru_lock);
-		list_add(&entry->lru, &entry->pool->lru);
-		spin_unlock(&entry->pool->lru_lock);
+		INIT_LIST_HEAD(&entry->lru);
+		zswap_lru_add(&entry->pool->list_lru, entry);
+		atomic_inc(&entry->pool->nr_stored);
 	}
 	spin_unlock(&tree->lock);
 
@@ -1384,7 +1709,8 @@ insert_entry:
 	return true;
 
 put_dstmem:
-	mutex_unlock(acomp_ctx->mutex);
+	mutex_unlock(&acomp_ctx->mutex);
+put_pool:
 	zswap_pool_put(entry->pool);
 freepage:
 	zswap_entry_cache_free(entry);
@@ -1408,12 +1734,7 @@ bool zswap_load(struct folio *folio)
 	struct page *page = &folio->page;
 	struct zswap_tree *tree = zswap_trees[type];
 	struct zswap_entry *entry;
-	struct scatterlist input, output;
-	struct crypto_acomp_ctx *acomp_ctx;
-	u8 *src, *dst, *tmp;
-	struct zpool *zpool;
-	unsigned int dlen;
-	bool ret;
+	u8 *dst;
 
 	VM_WARN_ON_ONCE(!folio_test_locked(folio));
 
@@ -1426,67 +1747,30 @@ bool zswap_load(struct folio *folio)
 	}
 	spin_unlock(&tree->lock);
 
-	if (!entry->length) {
-		dst = kmap_atomic(page);
+	if (entry->length)
+		__zswap_load(entry, page);
+	else {
+		dst = kmap_local_page(page);
 		zswap_fill_page(dst, entry->value);
-		kunmap_atomic(dst);
-		ret = true;
-		goto stats;
-	}
-
-	zpool = zswap_find_zpool(entry);
-	if (!zpool_can_sleep_mapped(zpool)) {
-		tmp = kmalloc(entry->length, GFP_KERNEL);
-		if (!tmp) {
-			ret = false;
-			goto freeentry;
-		}
-	}
-
-	/* decompress */
-	dlen = PAGE_SIZE;
-	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
-
-	if (!zpool_can_sleep_mapped(zpool)) {
-		memcpy(tmp, src, entry->length);
-		src = tmp;
-		zpool_unmap_handle(zpool, entry->handle);
+		kunmap_local(dst);
 	}
 
-	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
-	mutex_lock(acomp_ctx->mutex);
-	sg_init_one(&input, src, entry->length);
-	sg_init_table(&output, 1);
-	sg_set_page(&output, page, PAGE_SIZE, 0);
-	acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, dlen);
-	if (crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait))
-		WARN_ON(1);
-	mutex_unlock(acomp_ctx->mutex);
-
-	if (zpool_can_sleep_mapped(zpool))
-		zpool_unmap_handle(zpool, entry->handle);
-	else
-		kfree(tmp);
-
-	ret = true;
-stats:
 	count_vm_event(ZSWPIN);
 	if (entry->objcg)
 		count_objcg_event(entry->objcg, ZSWPIN);
-freeentry:
+
 	spin_lock(&tree->lock);
-	if (ret && zswap_exclusive_loads_enabled) {
+	if (zswap_exclusive_loads_enabled) {
 		zswap_invalidate_entry(tree, entry);
 		folio_mark_dirty(folio);
 	} else if (entry->length) {
-		spin_lock(&entry->pool->lru_lock);
-		list_move(&entry->lru, &entry->pool->lru);
-		spin_unlock(&entry->pool->lru_lock);
+		zswap_lru_del(&entry->pool->list_lru, entry);
+		zswap_lru_add(&entry->pool->list_lru, entry);
 	}
 	zswap_entry_put(tree, entry);
 	spin_unlock(&tree->lock);
 
-	return ret;
+	return true;
 }
 
 void zswap_invalidate(int type, pgoff_t offset)
@@ -1600,13 +1884,6 @@ static int zswap_setup(void)
 		goto cache_fail;
 	}
 
-	ret = cpuhp_setup_state(CPUHP_MM_ZSWP_MEM_PREPARE, "mm/zswap:prepare",
-				zswap_dstmem_prepare, zswap_dstmem_dead);
-	if (ret) {
-		pr_err("dstmem alloc failed\n");
-		goto dstmem_fail;
-	}
-
 	ret = cpuhp_setup_state_multi(CPUHP_MM_ZSWP_POOL_PREPARE,
 				      "mm/zswap_pool:prepare",
 				      zswap_cpu_comp_prepare,
@@ -1638,8 +1915,6 @@ fallback_fail:
 	if (pool)
 		zswap_pool_destroy(pool);
 hp_fail:
-	cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
-dstmem_fail:
 	kmem_cache_destroy(zswap_entry_cache);
 cache_fail:
 	/* if built-in, we aren't unloaded on failure; don't allow use */