diff --git a/mm/zswap.c b/mm/zswap.c index 01fe081474ff..e6cf6282f5fd 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include @@ -194,7 +193,6 @@ static struct shrinker *zswap_shrinker; * This structure contains the metadata for tracking a single compressed * page within zswap. * - * rbnode - links the entry into red-black tree for the appropriate swap type * swpentry - associated swap entry, the offset indexes into the red-black tree * length - the length in bytes of the compressed page data. Needed during * decompression. For a same value filled page length is 0, and both @@ -206,7 +204,6 @@ static struct shrinker *zswap_shrinker; * lru - handle to the pool's lru used to evict pages. */ struct zswap_entry { - struct rb_node rbnode; swp_entry_t swpentry; unsigned int length; struct zswap_pool *pool; @@ -218,12 +215,7 @@ struct zswap_entry { struct list_head lru; }; -struct zswap_tree { - struct rb_root rbroot; - spinlock_t lock; -}; - -static struct zswap_tree *zswap_trees[MAX_SWAPFILES]; +static struct xarray *zswap_trees[MAX_SWAPFILES]; static unsigned int nr_zswap_trees[MAX_SWAPFILES]; /* RCU-protected iteration */ @@ -251,7 +243,7 @@ static bool zswap_has_pool; * helpers and fwd declarations **********************************/ -static inline struct zswap_tree *swap_zswap_tree(swp_entry_t swp) +static inline struct xarray *swap_zswap_tree(swp_entry_t swp) { return &zswap_trees[swp_type(swp)][swp_offset(swp) >> SWAP_ADDRESS_SPACE_SHIFT]; @@ -790,63 +782,6 @@ void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) spin_unlock(&zswap_shrink_lock); } -/********************************* -* rbtree functions -**********************************/ -static struct zswap_entry *zswap_rb_search(struct rb_root *root, pgoff_t offset) -{ - struct rb_node *node = root->rb_node; - struct zswap_entry *entry; - pgoff_t entry_offset; - - while (node) { - entry = rb_entry(node, struct zswap_entry, rbnode); - entry_offset = swp_offset(entry->swpentry); - if (entry_offset > offset) - node = node->rb_left; - else if (entry_offset < offset) - node = node->rb_right; - else - return entry; - } - return NULL; -} - -/* - * In the case that a entry with the same offset is found, a pointer to - * the existing entry is stored in dupentry and the function returns -EEXIST - */ -static int zswap_rb_insert(struct rb_root *root, struct zswap_entry *entry, - struct zswap_entry **dupentry) -{ - struct rb_node **link = &root->rb_node, *parent = NULL; - struct zswap_entry *myentry; - pgoff_t myentry_offset, entry_offset = swp_offset(entry->swpentry); - - while (*link) { - parent = *link; - myentry = rb_entry(parent, struct zswap_entry, rbnode); - myentry_offset = swp_offset(myentry->swpentry); - if (myentry_offset > entry_offset) - link = &(*link)->rb_left; - else if (myentry_offset < entry_offset) - link = &(*link)->rb_right; - else { - *dupentry = myentry; - return -EEXIST; - } - } - rb_link_node(&entry->rbnode, parent, link); - rb_insert_color(&entry->rbnode, root); - return 0; -} - -static void zswap_rb_erase(struct rb_root *root, struct zswap_entry *entry) -{ - rb_erase(&entry->rbnode, root); - RB_CLEAR_NODE(&entry->rbnode); -} - /********************************* * zswap entry functions **********************************/ @@ -858,7 +793,6 @@ static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp, int nid) entry = kmem_cache_alloc_node(zswap_entry_cache, gfp, nid); if (!entry) return NULL; - RB_CLEAR_NODE(&entry->rbnode); return entry; } @@ -893,17 +827,6 @@ static void zswap_entry_free(struct zswap_entry *entry) atomic_dec(&zswap_stored_pages); } -/* - * The caller hold the tree lock and search the entry from the tree, - * so it must be on the tree, remove it from the tree and free it. - */ -static void zswap_invalidate_entry(struct zswap_tree *tree, - struct zswap_entry *entry) -{ - zswap_rb_erase(&tree->rbroot, entry); - zswap_entry_free(entry); -} - /********************************* * compressed storage functions **********************************/ @@ -1103,7 +1026,8 @@ static void zswap_decompress(struct zswap_entry *entry, struct page *page) static int zswap_writeback_entry(struct zswap_entry *entry, swp_entry_t swpentry) { - struct zswap_tree *tree; + struct xarray *tree; + pgoff_t offset = swp_offset(swpentry); struct folio *folio; struct mempolicy *mpol; bool folio_was_allocated; @@ -1140,19 +1064,13 @@ static int zswap_writeback_entry(struct zswap_entry *entry, * be dereferenced. */ tree = swap_zswap_tree(swpentry); - spin_lock(&tree->lock); - if (zswap_rb_search(&tree->rbroot, swp_offset(swpentry)) != entry) { - spin_unlock(&tree->lock); + if (entry != xa_cmpxchg(tree, offset, entry, NULL, GFP_KERNEL)) { delete_from_swap_cache(folio); folio_unlock(folio); folio_put(folio); return -ENOMEM; } - /* Safe to deref entry after the entry is verified above. */ - zswap_rb_erase(&tree->rbroot, entry); - spin_unlock(&tree->lock); - zswap_decompress(entry, &folio->page); count_vm_event(ZSWPWB); @@ -1484,8 +1402,8 @@ bool zswap_store(struct folio *folio) { swp_entry_t swp = folio->swap; pgoff_t offset = swp_offset(swp); - struct zswap_tree *tree = swap_zswap_tree(swp); - struct zswap_entry *entry, *dupentry; + struct xarray *tree = swap_zswap_tree(swp); + struct zswap_entry *entry, *old; struct obj_cgroup *objcg = NULL; struct mem_cgroup *memcg = NULL; unsigned long max_pages, cur_pages; @@ -1573,27 +1491,43 @@ bool zswap_store(struct folio *folio) insert_entry: entry->swpentry = swp; entry->objcg = objcg; + + old = xa_store(tree, offset, entry, GFP_KERNEL); + if (xa_is_err(old)) { + int err = xa_err(old); + + WARN_ONCE(err != -ENOMEM, "unexpected xarray error: %d\n", err); + zswap_reject_alloc_fail++; + goto store_failed; + } + + /* + * We may have had an existing entry that became stale when + * the folio was redirtied and now the new version is being + * swapped out. Get rid of the old. + */ + if (old) + zswap_entry_free(old); + if (objcg) { obj_cgroup_charge_zswap(objcg, entry->length); - /* Account before objcg ref is moved to tree */ count_objcg_event(objcg, ZSWPOUT); } - /* map */ - spin_lock(&tree->lock); /* - * The folio may have been dirtied again, invalidate the - * possibly stale entry before inserting the new entry. + * We finish initializing the entry while it's already in xarray. + * This is safe because: + * + * 1. Concurrent stores and invalidations are excluded by folio lock. + * + * 2. Writeback is excluded by the entry not being on the LRU yet. + * The publishing order matters to prevent writeback from seeing + * an incoherent entry. */ - if (zswap_rb_insert(&tree->rbroot, entry, &dupentry) == -EEXIST) { - zswap_invalidate_entry(tree, dupentry); - WARN_ON(zswap_rb_insert(&tree->rbroot, entry, &dupentry)); - } if (entry->length) { INIT_LIST_HEAD(&entry->lru); zswap_lru_add(&zswap_list_lru, entry); } - spin_unlock(&tree->lock); /* update stats */ atomic_inc(&zswap_stored_pages); @@ -1601,8 +1535,14 @@ insert_entry: return true; +store_failed: + if (!entry->length) + atomic_dec(&zswap_same_filled_pages); + else { + zpool_free(zswap_find_zpool(entry), entry->handle); put_pool: - zswap_pool_put(entry->pool); + zswap_pool_put(entry->pool); + } freepage: zswap_entry_cache_free(entry); reject: @@ -1613,11 +1553,9 @@ check_old: * possibly stale entry which was previously stored at this offset. * Otherwise, writeback could overwrite the new data in the swapfile. */ - spin_lock(&tree->lock); - entry = zswap_rb_search(&tree->rbroot, offset); + entry = xa_erase(tree, offset); if (entry) - zswap_invalidate_entry(tree, entry); - spin_unlock(&tree->lock); + zswap_entry_free(entry); return false; shrink: @@ -1631,18 +1569,12 @@ bool zswap_load(struct folio *folio) pgoff_t offset = swp_offset(swp); struct page *page = &folio->page; bool swapcache = folio_test_swapcache(folio); - struct zswap_tree *tree = swap_zswap_tree(swp); + struct xarray *tree = swap_zswap_tree(swp); struct zswap_entry *entry; u8 *dst; VM_WARN_ON_ONCE(!folio_test_locked(folio)); - spin_lock(&tree->lock); - entry = zswap_rb_search(&tree->rbroot, offset); - if (!entry) { - spin_unlock(&tree->lock); - return false; - } /* * When reading into the swapcache, invalidate our entry. The * swapcache can be the authoritative owner of the page and @@ -1656,8 +1588,12 @@ bool zswap_load(struct folio *folio) * the fault fails. We remain the primary owner of the entry.) */ if (swapcache) - zswap_rb_erase(&tree->rbroot, entry); - spin_unlock(&tree->lock); + entry = xa_erase(tree, offset); + else + entry = xa_load(tree, offset); + + if (!entry) + return false; if (entry->length) zswap_decompress(entry, page); @@ -1682,19 +1618,17 @@ bool zswap_load(struct folio *folio) void zswap_invalidate(swp_entry_t swp) { pgoff_t offset = swp_offset(swp); - struct zswap_tree *tree = swap_zswap_tree(swp); + struct xarray *tree = swap_zswap_tree(swp); struct zswap_entry *entry; - spin_lock(&tree->lock); - entry = zswap_rb_search(&tree->rbroot, offset); + entry = xa_erase(tree, offset); if (entry) - zswap_invalidate_entry(tree, entry); - spin_unlock(&tree->lock); + zswap_entry_free(entry); } int zswap_swapon(int type, unsigned long nr_pages) { - struct zswap_tree *trees, *tree; + struct xarray *trees, *tree; unsigned int nr, i; nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES); @@ -1704,11 +1638,8 @@ int zswap_swapon(int type, unsigned long nr_pages) return -ENOMEM; } - for (i = 0; i < nr; i++) { - tree = trees + i; - tree->rbroot = RB_ROOT; - spin_lock_init(&tree->lock); - } + for (i = 0; i < nr; i++) + xa_init(trees + i); nr_zswap_trees[type] = nr; zswap_trees[type] = trees; @@ -1717,7 +1648,7 @@ int zswap_swapon(int type, unsigned long nr_pages) void zswap_swapoff(int type) { - struct zswap_tree *trees = zswap_trees[type]; + struct xarray *trees = zswap_trees[type]; unsigned int i; if (!trees) @@ -1725,7 +1656,7 @@ void zswap_swapoff(int type) /* try_to_unuse() invalidated all the entries already */ for (i = 0; i < nr_zswap_trees[type]; i++) - WARN_ON_ONCE(!RB_EMPTY_ROOT(&trees[i].rbroot)); + WARN_ON_ONCE(!xa_empty(trees + i)); kvfree(trees); nr_zswap_trees[type] = 0;