1 files changed, 216 insertions, 52 deletions

diff --git a/mm/zswap.c b/mm/zswap.c
index 699c6ee11222..213626e0f659 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"
@@ -174,8 +175,8 @@ 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;
 };
 
 /*
@@ -291,15 +292,46 @@ static void zswap_update_total_size(void)
 	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 +345,61 @@ static void zswap_entry_cache_free(struct zswap_entry *entry)
 }
 
 /*********************************
+* lru functions
+**********************************/
+static void zswap_lru_add(struct list_lru *list_lru, struct zswap_entry *entry)
+{
+	int nid = entry_to_nid(entry);
+	struct mem_cgroup *memcg;
+
+	/*
+	 * 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);
+	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;
+
+	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);
+	rcu_read_unlock();
+}
+
+/*********************************
 * rbtree functions
 **********************************/
 static struct zswap_entry *zswap_rb_search(struct rb_root *root, pgoff_t offset)
@@ -396,9 +483,7 @@ static void zswap_free_entry(struct zswap_entry *entry)
 	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);
 		zswap_pool_put(entry->pool);
 	}
@@ -632,21 +717,15 @@ 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);
 	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
@@ -654,28 +733,32 @@ 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;
 		goto put_unlock;
 	}
+	zswap_written_back_pages++;
 
 	/*
 	 * Writeback started successfully, the page now belongs to the
@@ -689,24 +772,91 @@ 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;
+
+	/*
+	 * 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);
@@ -767,8 +917,7 @@ 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);
+	list_lru_init_memcg(&pool->list_lru, NULL);
 	INIT_WORK(&pool->shrink_work, shrink_worker);
 
 	zswap_pool_debug("created", pool);
@@ -834,6 +983,13 @@ static void zswap_pool_destroy(struct zswap_pool *pool)
 
 	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);
@@ -1081,7 +1237,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 	/* try to allocate swap cache page */
 	mpol = get_task_policy(current);
 	page = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol,
-				NO_INTERLEAVE_INDEX, &page_was_allocated);
+				NO_INTERLEAVE_INDEX, &page_was_allocated, true);
 	if (!page) {
 		ret = -ENOMEM;
 		goto fail;
@@ -1147,7 +1303,6 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 	/* start writeback */
 	__swap_writepage(page, &wbc);
 	put_page(page);
-	zswap_written_back_pages++;
 
 	return ret;
 
@@ -1204,6 +1359,7 @@ 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;
@@ -1235,15 +1391,15 @@ bool zswap_store(struct folio *folio)
 		zswap_invalidate_entry(tree, dupentry);
 	}
 	spin_unlock(&tree->lock);
-
-	/*
-	 * 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()) {
@@ -1260,7 +1416,7 @@ 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;
@@ -1287,6 +1443,15 @@ 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);
 
@@ -1365,9 +1530,8 @@ 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);
 	}
 	spin_unlock(&tree->lock);
 
@@ -1380,6 +1544,7 @@ insert_entry:
 
 put_dstmem:
 	mutex_unlock(acomp_ctx->mutex);
+put_pool:
 	zswap_pool_put(entry->pool);
 freepage:
 	zswap_entry_cache_free(entry);
@@ -1474,9 +1639,8 @@ freeentry:
 		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);