summaryrefslogtreecommitdiff
path: root/mm/zswap.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/zswap.c')
-rw-r--r--mm/zswap.c955
1 files changed, 955 insertions, 0 deletions
diff --git a/mm/zswap.c b/mm/zswap.c
new file mode 100644
index 000000000..4249e82ff
--- /dev/null
+++ b/mm/zswap.c
@@ -0,0 +1,955 @@
+/*
+ * zswap.c - zswap driver file
+ *
+ * zswap is a backend for frontswap that takes pages that are in the process
+ * of being swapped out and attempts to compress and store them in a
+ * RAM-based memory pool. This can result in a significant I/O reduction on
+ * the swap device and, in the case where decompressing from RAM is faster
+ * than reading from the swap device, can also improve workload performance.
+ *
+ * Copyright (C) 2012 Seth Jennings <sjenning@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+*/
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/cpu.h>
+#include <linux/highmem.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/atomic.h>
+#include <linux/frontswap.h>
+#include <linux/rbtree.h>
+#include <linux/swap.h>
+#include <linux/crypto.h>
+#include <linux/mempool.h>
+#include <linux/zpool.h>
+
+#include <linux/mm_types.h>
+#include <linux/page-flags.h>
+#include <linux/swapops.h>
+#include <linux/writeback.h>
+#include <linux/pagemap.h>
+
+/*********************************
+* statistics
+**********************************/
+/* Total bytes used by the compressed storage */
+static u64 zswap_pool_total_size;
+/* The number of compressed pages currently stored in zswap */
+static atomic_t zswap_stored_pages = ATOMIC_INIT(0);
+
+/*
+ * The statistics below are not protected from concurrent access for
+ * performance reasons so they may not be a 100% accurate. However,
+ * they do provide useful information on roughly how many times a
+ * certain event is occurring.
+*/
+
+/* Pool limit was hit (see zswap_max_pool_percent) */
+static u64 zswap_pool_limit_hit;
+/* Pages written back when pool limit was reached */
+static u64 zswap_written_back_pages;
+/* Store failed due to a reclaim failure after pool limit was reached */
+static u64 zswap_reject_reclaim_fail;
+/* Compressed page was too big for the allocator to (optimally) store */
+static u64 zswap_reject_compress_poor;
+/* Store failed because underlying allocator could not get memory */
+static u64 zswap_reject_alloc_fail;
+/* Store failed because the entry metadata could not be allocated (rare) */
+static u64 zswap_reject_kmemcache_fail;
+/* Duplicate store was encountered (rare) */
+static u64 zswap_duplicate_entry;
+
+/*********************************
+* tunables
+**********************************/
+/* Enable/disable zswap (disabled by default, fixed at boot for now) */
+static bool zswap_enabled __read_mostly;
+module_param_named(enabled, zswap_enabled, bool, 0444);
+
+/* Compressor to be used by zswap (fixed at boot for now) */
+#define ZSWAP_COMPRESSOR_DEFAULT "lzo"
+static char *zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT;
+module_param_named(compressor, zswap_compressor, charp, 0444);
+
+/* The maximum percentage of memory that the compressed pool can occupy */
+static unsigned int zswap_max_pool_percent = 20;
+module_param_named(max_pool_percent,
+ zswap_max_pool_percent, uint, 0644);
+
+/* Compressed storage to use */
+#define ZSWAP_ZPOOL_DEFAULT "zbud"
+static char *zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT;
+module_param_named(zpool, zswap_zpool_type, charp, 0444);
+
+/* zpool is shared by all of zswap backend */
+static struct zpool *zswap_pool;
+
+/*********************************
+* compression functions
+**********************************/
+/* per-cpu compression transforms */
+static struct crypto_comp * __percpu *zswap_comp_pcpu_tfms;
+
+enum comp_op {
+ ZSWAP_COMPOP_COMPRESS,
+ ZSWAP_COMPOP_DECOMPRESS
+};
+
+static int zswap_comp_op(enum comp_op op, const u8 *src, unsigned int slen,
+ u8 *dst, unsigned int *dlen)
+{
+ struct crypto_comp *tfm;
+ int ret;
+
+ tfm = *per_cpu_ptr(zswap_comp_pcpu_tfms, get_cpu());
+ switch (op) {
+ case ZSWAP_COMPOP_COMPRESS:
+ ret = crypto_comp_compress(tfm, src, slen, dst, dlen);
+ break;
+ case ZSWAP_COMPOP_DECOMPRESS:
+ ret = crypto_comp_decompress(tfm, src, slen, dst, dlen);
+ break;
+ default:
+ ret = -EINVAL;
+ }
+
+ put_cpu();
+ return ret;
+}
+
+static int __init zswap_comp_init(void)
+{
+ if (!crypto_has_comp(zswap_compressor, 0, 0)) {
+ pr_info("%s compressor not available\n", zswap_compressor);
+ /* fall back to default compressor */
+ zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT;
+ if (!crypto_has_comp(zswap_compressor, 0, 0))
+ /* can't even load the default compressor */
+ return -ENODEV;
+ }
+ pr_info("using %s compressor\n", zswap_compressor);
+
+ /* alloc percpu transforms */
+ zswap_comp_pcpu_tfms = alloc_percpu(struct crypto_comp *);
+ if (!zswap_comp_pcpu_tfms)
+ return -ENOMEM;
+ return 0;
+}
+
+static void __init zswap_comp_exit(void)
+{
+ /* free percpu transforms */
+ free_percpu(zswap_comp_pcpu_tfms);
+}
+
+/*********************************
+* data structures
+**********************************/
+/*
+ * struct zswap_entry
+ *
+ * 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
+ * refcount - the number of outstanding reference to the entry. This is needed
+ * to protect against premature freeing of the entry by code
+ * concurrent calls to load, invalidate, and writeback. The lock
+ * for the zswap_tree structure that contains the entry must
+ * be held while changing the refcount. Since the lock must
+ * be held, there is no reason to also make refcount atomic.
+ * offset - the swap offset for the entry. Index into the red-black tree.
+ * handle - zpool allocation handle that stores the compressed page data
+ * length - the length in bytes of the compressed page data. Needed during
+ * decompression
+ */
+struct zswap_entry {
+ struct rb_node rbnode;
+ pgoff_t offset;
+ int refcount;
+ unsigned int length;
+ unsigned long handle;
+};
+
+struct zswap_header {
+ swp_entry_t swpentry;
+};
+
+/*
+ * The tree lock in the zswap_tree struct protects a few things:
+ * - the rbtree
+ * - the refcount field of each entry in the tree
+ */
+struct zswap_tree {
+ struct rb_root rbroot;
+ spinlock_t lock;
+};
+
+static struct zswap_tree *zswap_trees[MAX_SWAPFILES];
+
+/*********************************
+* zswap entry functions
+**********************************/
+static struct kmem_cache *zswap_entry_cache;
+
+static int __init zswap_entry_cache_create(void)
+{
+ zswap_entry_cache = KMEM_CACHE(zswap_entry, 0);
+ return zswap_entry_cache == NULL;
+}
+
+static void __init zswap_entry_cache_destroy(void)
+{
+ kmem_cache_destroy(zswap_entry_cache);
+}
+
+static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp)
+{
+ struct zswap_entry *entry;
+ entry = kmem_cache_alloc(zswap_entry_cache, gfp);
+ if (!entry)
+ return NULL;
+ entry->refcount = 1;
+ RB_CLEAR_NODE(&entry->rbnode);
+ return entry;
+}
+
+static void zswap_entry_cache_free(struct zswap_entry *entry)
+{
+ kmem_cache_free(zswap_entry_cache, entry);
+}
+
+/*********************************
+* 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;
+
+ while (node) {
+ entry = rb_entry(node, struct zswap_entry, rbnode);
+ 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;
+
+ while (*link) {
+ parent = *link;
+ myentry = rb_entry(parent, struct zswap_entry, rbnode);
+ 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)
+{
+ if (!RB_EMPTY_NODE(&entry->rbnode)) {
+ rb_erase(&entry->rbnode, root);
+ RB_CLEAR_NODE(&entry->rbnode);
+ }
+}
+
+/*
+ * Carries out the common pattern of freeing and entry's zpool allocation,
+ * freeing the entry itself, and decrementing the number of stored pages.
+ */
+static void zswap_free_entry(struct zswap_entry *entry)
+{
+ zpool_free(zswap_pool, entry->handle);
+ zswap_entry_cache_free(entry);
+ atomic_dec(&zswap_stored_pages);
+ zswap_pool_total_size = zpool_get_total_size(zswap_pool);
+}
+
+/* caller must hold the tree lock */
+static void zswap_entry_get(struct zswap_entry *entry)
+{
+ entry->refcount++;
+}
+
+/* caller must hold the tree lock
+* remove from the tree and free it, if nobody reference the entry
+*/
+static void zswap_entry_put(struct zswap_tree *tree,
+ struct zswap_entry *entry)
+{
+ int refcount = --entry->refcount;
+
+ BUG_ON(refcount < 0);
+ if (refcount == 0) {
+ zswap_rb_erase(&tree->rbroot, entry);
+ zswap_free_entry(entry);
+ }
+}
+
+/* caller must hold the tree lock */
+static struct zswap_entry *zswap_entry_find_get(struct rb_root *root,
+ pgoff_t offset)
+{
+ struct zswap_entry *entry = NULL;
+
+ entry = zswap_rb_search(root, offset);
+ if (entry)
+ zswap_entry_get(entry);
+
+ return entry;
+}
+
+/*********************************
+* per-cpu code
+**********************************/
+static DEFINE_PER_CPU(u8 *, zswap_dstmem);
+
+static int __zswap_cpu_notifier(unsigned long action, unsigned long cpu)
+{
+ struct crypto_comp *tfm;
+ u8 *dst;
+
+ switch (action) {
+ case CPU_UP_PREPARE:
+ tfm = crypto_alloc_comp(zswap_compressor, 0, 0);
+ if (IS_ERR(tfm)) {
+ pr_err("can't allocate compressor transform\n");
+ return NOTIFY_BAD;
+ }
+ *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = tfm;
+ dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
+ if (!dst) {
+ pr_err("can't allocate compressor buffer\n");
+ crypto_free_comp(tfm);
+ *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = NULL;
+ return NOTIFY_BAD;
+ }
+ per_cpu(zswap_dstmem, cpu) = dst;
+ break;
+ case CPU_DEAD:
+ case CPU_UP_CANCELED:
+ tfm = *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu);
+ if (tfm) {
+ crypto_free_comp(tfm);
+ *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = NULL;
+ }
+ dst = per_cpu(zswap_dstmem, cpu);
+ kfree(dst);
+ per_cpu(zswap_dstmem, cpu) = NULL;
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static int zswap_cpu_notifier(struct notifier_block *nb,
+ unsigned long action, void *pcpu)
+{
+ unsigned long cpu = (unsigned long)pcpu;
+ return __zswap_cpu_notifier(action, cpu);
+}
+
+static struct notifier_block zswap_cpu_notifier_block = {
+ .notifier_call = zswap_cpu_notifier
+};
+
+static int __init zswap_cpu_init(void)
+{
+ unsigned long cpu;
+
+ cpu_notifier_register_begin();
+ for_each_online_cpu(cpu)
+ if (__zswap_cpu_notifier(CPU_UP_PREPARE, cpu) != NOTIFY_OK)
+ goto cleanup;
+ __register_cpu_notifier(&zswap_cpu_notifier_block);
+ cpu_notifier_register_done();
+ return 0;
+
+cleanup:
+ for_each_online_cpu(cpu)
+ __zswap_cpu_notifier(CPU_UP_CANCELED, cpu);
+ cpu_notifier_register_done();
+ return -ENOMEM;
+}
+
+/*********************************
+* helpers
+**********************************/
+static bool zswap_is_full(void)
+{
+ return totalram_pages * zswap_max_pool_percent / 100 <
+ DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
+}
+
+/*********************************
+* writeback code
+**********************************/
+/* return enum for zswap_get_swap_cache_page */
+enum zswap_get_swap_ret {
+ ZSWAP_SWAPCACHE_NEW,
+ ZSWAP_SWAPCACHE_EXIST,
+ ZSWAP_SWAPCACHE_FAIL,
+};
+
+/*
+ * zswap_get_swap_cache_page
+ *
+ * This is an adaption of read_swap_cache_async()
+ *
+ * This function tries to find a page with the given swap entry
+ * in the swapper_space address space (the swap cache). If the page
+ * is found, it is returned in retpage. Otherwise, a page is allocated,
+ * added to the swap cache, and returned in retpage.
+ *
+ * If success, the swap cache page is returned in retpage
+ * Returns ZSWAP_SWAPCACHE_EXIST if page was already in the swap cache
+ * Returns ZSWAP_SWAPCACHE_NEW if the new page needs to be populated,
+ * the new page is added to swapcache and locked
+ * Returns ZSWAP_SWAPCACHE_FAIL on error
+ */
+static int zswap_get_swap_cache_page(swp_entry_t entry,
+ struct page **retpage)
+{
+ struct page *found_page, *new_page = NULL;
+ struct address_space *swapper_space = swap_address_space(entry);
+ int err;
+
+ *retpage = NULL;
+ do {
+ /*
+ * First check the swap cache. Since this is normally
+ * called after lookup_swap_cache() failed, re-calling
+ * that would confuse statistics.
+ */
+ found_page = find_get_page(swapper_space, entry.val);
+ if (found_page)
+ break;
+
+ /*
+ * Get a new page to read into from swap.
+ */
+ if (!new_page) {
+ new_page = alloc_page(GFP_KERNEL);
+ if (!new_page)
+ break; /* Out of memory */
+ }
+
+ /*
+ * call radix_tree_preload() while we can wait.
+ */
+ err = radix_tree_preload(GFP_KERNEL);
+ if (err)
+ break;
+
+ /*
+ * Swap entry may have been freed since our caller observed it.
+ */
+ err = swapcache_prepare(entry);
+ if (err == -EEXIST) { /* seems racy */
+ radix_tree_preload_end();
+ continue;
+ }
+ if (err) { /* swp entry is obsolete ? */
+ radix_tree_preload_end();
+ break;
+ }
+
+ /* May fail (-ENOMEM) if radix-tree node allocation failed. */
+ __set_page_locked(new_page);
+ SetPageSwapBacked(new_page);
+ err = __add_to_swap_cache(new_page, entry);
+ if (likely(!err)) {
+ radix_tree_preload_end();
+ lru_cache_add_anon(new_page);
+ *retpage = new_page;
+ return ZSWAP_SWAPCACHE_NEW;
+ }
+ radix_tree_preload_end();
+ ClearPageSwapBacked(new_page);
+ __clear_page_locked(new_page);
+ /*
+ * add_to_swap_cache() doesn't return -EEXIST, so we can safely
+ * clear SWAP_HAS_CACHE flag.
+ */
+ swapcache_free(entry);
+ } while (err != -ENOMEM);
+
+ if (new_page)
+ page_cache_release(new_page);
+ if (!found_page)
+ return ZSWAP_SWAPCACHE_FAIL;
+ *retpage = found_page;
+ return ZSWAP_SWAPCACHE_EXIST;
+}
+
+/*
+ * 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.
+ *
+ * This can be thought of as a "resumed writeback" of the page
+ * to the swap device. We are basically resuming the same swap
+ * writeback path that was intercepted with the frontswap_store()
+ * in the first place. After the page has been decompressed into
+ * the swap cache, the compressed version stored by zswap can be
+ * freed.
+ */
+static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
+{
+ struct zswap_header *zhdr;
+ swp_entry_t swpentry;
+ struct zswap_tree *tree;
+ pgoff_t offset;
+ struct zswap_entry *entry;
+ struct page *page;
+ u8 *src, *dst;
+ unsigned int dlen;
+ int ret;
+ struct writeback_control wbc = {
+ .sync_mode = WB_SYNC_NONE,
+ };
+
+ /* extract swpentry from data */
+ zhdr = zpool_map_handle(pool, handle, ZPOOL_MM_RO);
+ swpentry = zhdr->swpentry; /* here */
+ zpool_unmap_handle(pool, handle);
+ tree = zswap_trees[swp_type(swpentry)];
+ offset = swp_offset(swpentry);
+
+ /* find and ref zswap entry */
+ spin_lock(&tree->lock);
+ entry = zswap_entry_find_get(&tree->rbroot, offset);
+ if (!entry) {
+ /* entry was invalidated */
+ spin_unlock(&tree->lock);
+ return 0;
+ }
+ spin_unlock(&tree->lock);
+ BUG_ON(offset != entry->offset);
+
+ /* try to allocate swap cache page */
+ switch (zswap_get_swap_cache_page(swpentry, &page)) {
+ case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */
+ ret = -ENOMEM;
+ goto fail;
+
+ case ZSWAP_SWAPCACHE_EXIST:
+ /* page is already in the swap cache, ignore for now */
+ page_cache_release(page);
+ ret = -EEXIST;
+ goto fail;
+
+ case ZSWAP_SWAPCACHE_NEW: /* page is locked */
+ /* decompress */
+ dlen = PAGE_SIZE;
+ src = (u8 *)zpool_map_handle(zswap_pool, entry->handle,
+ ZPOOL_MM_RO) + sizeof(struct zswap_header);
+ dst = kmap_atomic(page);
+ ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src,
+ entry->length, dst, &dlen);
+ kunmap_atomic(dst);
+ zpool_unmap_handle(zswap_pool, entry->handle);
+ BUG_ON(ret);
+ BUG_ON(dlen != PAGE_SIZE);
+
+ /* page is up to date */
+ SetPageUptodate(page);
+ }
+
+ /* move it to the tail of the inactive list after end_writeback */
+ SetPageReclaim(page);
+
+ /* start writeback */
+ __swap_writepage(page, &wbc, end_swap_bio_write);
+ page_cache_release(page);
+ zswap_written_back_pages++;
+
+ spin_lock(&tree->lock);
+ /* drop local reference */
+ zswap_entry_put(tree, entry);
+
+ /*
+ * There are two possible situations for entry here:
+ * (1) refcount is 1(normal case), entry is valid and on the tree
+ * (2) refcount is 0, entry is freed and not on the tree
+ * because invalidate happened during writeback
+ * search the tree and free the entry if find entry
+ */
+ if (entry == zswap_rb_search(&tree->rbroot, offset))
+ zswap_entry_put(tree, entry);
+ spin_unlock(&tree->lock);
+
+ goto end;
+
+ /*
+ * if we get here due to ZSWAP_SWAPCACHE_EXIST
+ * a load may happening concurrently
+ * it is safe and okay to not free the entry
+ * if we free the entry in the following put
+ * it it either okay to return !0
+ */
+fail:
+ spin_lock(&tree->lock);
+ zswap_entry_put(tree, entry);
+ spin_unlock(&tree->lock);
+
+end:
+ return ret;
+}
+
+/*********************************
+* frontswap hooks
+**********************************/
+/* attempts to compress and store an single page */
+static int zswap_frontswap_store(unsigned type, pgoff_t offset,
+ struct page *page)
+{
+ struct zswap_tree *tree = zswap_trees[type];
+ struct zswap_entry *entry, *dupentry;
+ int ret;
+ unsigned int dlen = PAGE_SIZE, len;
+ unsigned long handle;
+ char *buf;
+ u8 *src, *dst;
+ struct zswap_header *zhdr;
+
+ if (!tree) {
+ ret = -ENODEV;
+ goto reject;
+ }
+
+ /* reclaim space if needed */
+ if (zswap_is_full()) {
+ zswap_pool_limit_hit++;
+ if (zpool_shrink(zswap_pool, 1, NULL)) {
+ zswap_reject_reclaim_fail++;
+ ret = -ENOMEM;
+ goto reject;
+ }
+ }
+
+ /* allocate entry */
+ entry = zswap_entry_cache_alloc(GFP_KERNEL);
+ if (!entry) {
+ zswap_reject_kmemcache_fail++;
+ ret = -ENOMEM;
+ goto reject;
+ }
+
+ /* compress */
+ dst = get_cpu_var(zswap_dstmem);
+ src = kmap_atomic(page);
+ ret = zswap_comp_op(ZSWAP_COMPOP_COMPRESS, src, PAGE_SIZE, dst, &dlen);
+ kunmap_atomic(src);
+ if (ret) {
+ ret = -EINVAL;
+ goto freepage;
+ }
+
+ /* store */
+ len = dlen + sizeof(struct zswap_header);
+ ret = zpool_malloc(zswap_pool, len, __GFP_NORETRY | __GFP_NOWARN,
+ &handle);
+ if (ret == -ENOSPC) {
+ zswap_reject_compress_poor++;
+ goto freepage;
+ }
+ if (ret) {
+ zswap_reject_alloc_fail++;
+ goto freepage;
+ }
+ zhdr = zpool_map_handle(zswap_pool, handle, ZPOOL_MM_RW);
+ zhdr->swpentry = swp_entry(type, offset);
+ buf = (u8 *)(zhdr + 1);
+ memcpy(buf, dst, dlen);
+ zpool_unmap_handle(zswap_pool, handle);
+ put_cpu_var(zswap_dstmem);
+
+ /* populate entry */
+ entry->offset = offset;
+ entry->handle = handle;
+ entry->length = dlen;
+
+ /* map */
+ spin_lock(&tree->lock);
+ do {
+ ret = zswap_rb_insert(&tree->rbroot, entry, &dupentry);
+ if (ret == -EEXIST) {
+ zswap_duplicate_entry++;
+ /* remove from rbtree */
+ zswap_rb_erase(&tree->rbroot, dupentry);
+ zswap_entry_put(tree, dupentry);
+ }
+ } while (ret == -EEXIST);
+ spin_unlock(&tree->lock);
+
+ /* update stats */
+ atomic_inc(&zswap_stored_pages);
+ zswap_pool_total_size = zpool_get_total_size(zswap_pool);
+
+ return 0;
+
+freepage:
+ put_cpu_var(zswap_dstmem);
+ zswap_entry_cache_free(entry);
+reject:
+ return ret;
+}
+
+/*
+ * returns 0 if the page was successfully decompressed
+ * return -1 on entry not found or error
+*/
+static int zswap_frontswap_load(unsigned type, pgoff_t offset,
+ struct page *page)
+{
+ struct zswap_tree *tree = zswap_trees[type];
+ struct zswap_entry *entry;
+ u8 *src, *dst;
+ unsigned int dlen;
+ int ret;
+
+ /* find */
+ spin_lock(&tree->lock);
+ entry = zswap_entry_find_get(&tree->rbroot, offset);
+ if (!entry) {
+ /* entry was written back */
+ spin_unlock(&tree->lock);
+ return -1;
+ }
+ spin_unlock(&tree->lock);
+
+ /* decompress */
+ dlen = PAGE_SIZE;
+ src = (u8 *)zpool_map_handle(zswap_pool, entry->handle,
+ ZPOOL_MM_RO) + sizeof(struct zswap_header);
+ dst = kmap_atomic(page);
+ ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src, entry->length,
+ dst, &dlen);
+ kunmap_atomic(dst);
+ zpool_unmap_handle(zswap_pool, entry->handle);
+ BUG_ON(ret);
+
+ spin_lock(&tree->lock);
+ zswap_entry_put(tree, entry);
+ spin_unlock(&tree->lock);
+
+ return 0;
+}
+
+/* frees an entry in zswap */
+static void zswap_frontswap_invalidate_page(unsigned type, pgoff_t offset)
+{
+ struct zswap_tree *tree = zswap_trees[type];
+ struct zswap_entry *entry;
+
+ /* find */
+ spin_lock(&tree->lock);
+ entry = zswap_rb_search(&tree->rbroot, offset);
+ if (!entry) {
+ /* entry was written back */
+ spin_unlock(&tree->lock);
+ return;
+ }
+
+ /* remove from rbtree */
+ zswap_rb_erase(&tree->rbroot, entry);
+
+ /* drop the initial reference from entry creation */
+ zswap_entry_put(tree, entry);
+
+ spin_unlock(&tree->lock);
+}
+
+/* frees all zswap entries for the given swap type */
+static void zswap_frontswap_invalidate_area(unsigned type)
+{
+ struct zswap_tree *tree = zswap_trees[type];
+ struct zswap_entry *entry, *n;
+
+ if (!tree)
+ return;
+
+ /* walk the tree and free everything */
+ spin_lock(&tree->lock);
+ rbtree_postorder_for_each_entry_safe(entry, n, &tree->rbroot, rbnode)
+ zswap_free_entry(entry);
+ tree->rbroot = RB_ROOT;
+ spin_unlock(&tree->lock);
+ kfree(tree);
+ zswap_trees[type] = NULL;
+}
+
+static struct zpool_ops zswap_zpool_ops = {
+ .evict = zswap_writeback_entry
+};
+
+static void zswap_frontswap_init(unsigned type)
+{
+ struct zswap_tree *tree;
+
+ tree = kzalloc(sizeof(struct zswap_tree), GFP_KERNEL);
+ if (!tree) {
+ pr_err("alloc failed, zswap disabled for swap type %d\n", type);
+ return;
+ }
+
+ tree->rbroot = RB_ROOT;
+ spin_lock_init(&tree->lock);
+ zswap_trees[type] = tree;
+}
+
+static struct frontswap_ops zswap_frontswap_ops = {
+ .store = zswap_frontswap_store,
+ .load = zswap_frontswap_load,
+ .invalidate_page = zswap_frontswap_invalidate_page,
+ .invalidate_area = zswap_frontswap_invalidate_area,
+ .init = zswap_frontswap_init
+};
+
+/*********************************
+* debugfs functions
+**********************************/
+#ifdef CONFIG_DEBUG_FS
+#include <linux/debugfs.h>
+
+static struct dentry *zswap_debugfs_root;
+
+static int __init zswap_debugfs_init(void)
+{
+ if (!debugfs_initialized())
+ return -ENODEV;
+
+ zswap_debugfs_root = debugfs_create_dir("zswap", NULL);
+ if (!zswap_debugfs_root)
+ return -ENOMEM;
+
+ debugfs_create_u64("pool_limit_hit", S_IRUGO,
+ zswap_debugfs_root, &zswap_pool_limit_hit);
+ debugfs_create_u64("reject_reclaim_fail", S_IRUGO,
+ zswap_debugfs_root, &zswap_reject_reclaim_fail);
+ debugfs_create_u64("reject_alloc_fail", S_IRUGO,
+ zswap_debugfs_root, &zswap_reject_alloc_fail);
+ debugfs_create_u64("reject_kmemcache_fail", S_IRUGO,
+ zswap_debugfs_root, &zswap_reject_kmemcache_fail);
+ debugfs_create_u64("reject_compress_poor", S_IRUGO,
+ zswap_debugfs_root, &zswap_reject_compress_poor);
+ debugfs_create_u64("written_back_pages", S_IRUGO,
+ zswap_debugfs_root, &zswap_written_back_pages);
+ debugfs_create_u64("duplicate_entry", S_IRUGO,
+ zswap_debugfs_root, &zswap_duplicate_entry);
+ debugfs_create_u64("pool_total_size", S_IRUGO,
+ zswap_debugfs_root, &zswap_pool_total_size);
+ debugfs_create_atomic_t("stored_pages", S_IRUGO,
+ zswap_debugfs_root, &zswap_stored_pages);
+
+ return 0;
+}
+
+static void __exit zswap_debugfs_exit(void)
+{
+ debugfs_remove_recursive(zswap_debugfs_root);
+}
+#else
+static int __init zswap_debugfs_init(void)
+{
+ return 0;
+}
+
+static void __exit zswap_debugfs_exit(void) { }
+#endif
+
+/*********************************
+* module init and exit
+**********************************/
+static int __init init_zswap(void)
+{
+ gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN;
+
+ if (!zswap_enabled)
+ return 0;
+
+ pr_info("loading zswap\n");
+
+ zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp,
+ &zswap_zpool_ops);
+ if (!zswap_pool && strcmp(zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT)) {
+ pr_info("%s zpool not available\n", zswap_zpool_type);
+ zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT;
+ zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp,
+ &zswap_zpool_ops);
+ }
+ if (!zswap_pool) {
+ pr_err("%s zpool not available\n", zswap_zpool_type);
+ pr_err("zpool creation failed\n");
+ goto error;
+ }
+ pr_info("using %s pool\n", zswap_zpool_type);
+
+ if (zswap_entry_cache_create()) {
+ pr_err("entry cache creation failed\n");
+ goto cachefail;
+ }
+ if (zswap_comp_init()) {
+ pr_err("compressor initialization failed\n");
+ goto compfail;
+ }
+ if (zswap_cpu_init()) {
+ pr_err("per-cpu initialization failed\n");
+ goto pcpufail;
+ }
+
+ frontswap_register_ops(&zswap_frontswap_ops);
+ if (zswap_debugfs_init())
+ pr_warn("debugfs initialization failed\n");
+ return 0;
+pcpufail:
+ zswap_comp_exit();
+compfail:
+ zswap_entry_cache_destroy();
+cachefail:
+ zpool_destroy_pool(zswap_pool);
+error:
+ return -ENOMEM;
+}
+/* must be late so crypto has time to come up */
+late_initcall(init_zswap);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Seth Jennings <sjennings@variantweb.net>");
+MODULE_DESCRIPTION("Compressed cache for swap pages");