summaryrefslogtreecommitdiffstats
path: root/mm/zswap.c
diff options
context:
space:
mode:
authorSeth Jennings <sjenning@linux.vnet.ibm.com>2013-07-10 16:05:03 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2013-07-10 18:11:34 -0700
commit2b2811178e85553405b86e3fe78357b9b95889ce (patch)
tree0d5b12e7013be79a8e89d145a46bc32e82f86a81 /mm/zswap.c
parent4e2e2770b1529edc5849c86b29a6febe27e2f083 (diff)
downloadlinux-2b2811178e85553405b86e3fe78357b9b95889ce.tar.bz2
zswap: add to mm/
zswap is a thin backend for frontswap that takes pages that are in the process of being swapped out and attempts to compress them 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. It also has support for evicting swap pages that are currently compressed in zswap to the swap device on an LRU(ish) basis. This functionality makes zswap a true cache in that, once the cache is full, the oldest pages can be moved out of zswap to the swap device so newer pages can be compressed and stored in zswap. This patch adds the zswap driver to mm/ Signed-off-by: Seth Jennings <sjenning@linux.vnet.ibm.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Robert Jennings <rcj@linux.vnet.ibm.com> Cc: Jenifer Hopper <jhopper@us.ibm.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <jweiner@redhat.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dave Hansen <dave@sr71.net> Cc: Joe Perches <joe@perches.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Cody P Schafer <cody@linux.vnet.ibm.com> Cc: Hugh Dickens <hughd@google.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/zswap.c')
-rw-r--r--mm/zswap.c943
1 files changed, 943 insertions, 0 deletions
diff --git a/mm/zswap.c b/mm/zswap.c
new file mode 100644
index 000000000000..deda2b671e12
--- /dev/null
+++ b/mm/zswap.c
@@ -0,0 +1,943 @@
+/*
+ * 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/zbud.h>
+
+#include <linux/mm_types.h>
+#include <linux/page-flags.h>
+#include <linux/swapops.h>
+#include <linux/writeback.h>
+#include <linux/pagemap.h>
+
+/*********************************
+* statistics
+**********************************/
+/* Number of memory pages used by the compressed pool */
+static u64 zswap_pool_pages;
+/* 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, 0);
+
+/* 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, 0);
+
+/* 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);
+
+/*********************************
+* 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 zswap_comp_exit(void)
+{
+ /* free percpu transforms */
+ if (zswap_comp_pcpu_tfms)
+ 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
+ * concurent 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 - zsmalloc 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;
+ struct zbud_pool *pool;
+};
+
+static struct zswap_tree *zswap_trees[MAX_SWAPFILES];
+
+/*********************************
+* zswap entry functions
+**********************************/
+static struct kmem_cache *zswap_entry_cache;
+
+static int zswap_entry_cache_create(void)
+{
+ zswap_entry_cache = KMEM_CACHE(zswap_entry, 0);
+ return (zswap_entry_cache == NULL);
+}
+
+static void zswap_entry_cache_destory(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;
+ return entry;
+}
+
+static void zswap_entry_cache_free(struct zswap_entry *entry)
+{
+ kmem_cache_free(zswap_entry_cache, entry);
+}
+
+/* caller must hold the tree lock */
+static void zswap_entry_get(struct zswap_entry *entry)
+{
+ entry->refcount++;
+}
+
+/* caller must hold the tree lock */
+static int zswap_entry_put(struct zswap_entry *entry)
+{
+ entry->refcount--;
+ return entry->refcount;
+}
+
+/*********************************
+* 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;
+}
+
+/*********************************
+* 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(PAGE_SIZE * 2, GFP_KERNEL);
+ 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 zswap_cpu_init(void)
+{
+ unsigned long cpu;
+
+ get_online_cpus();
+ for_each_online_cpu(cpu)
+ if (__zswap_cpu_notifier(CPU_UP_PREPARE, cpu) != NOTIFY_OK)
+ goto cleanup;
+ register_cpu_notifier(&zswap_cpu_notifier_block);
+ put_online_cpus();
+ return 0;
+
+cleanup:
+ for_each_online_cpu(cpu)
+ __zswap_cpu_notifier(CPU_UP_CANCELED, cpu);
+ put_online_cpus();
+ return -ENOMEM;
+}
+
+/*********************************
+* helpers
+**********************************/
+static bool zswap_is_full(void)
+{
+ return (totalram_pages * zswap_max_pool_percent / 100 <
+ zswap_pool_pages);
+}
+
+/*
+ * Carries out the common pattern of freeing and entry's zsmalloc allocation,
+ * freeing the entry itself, and decrementing the number of stored pages.
+ */
+static void zswap_free_entry(struct zswap_tree *tree, struct zswap_entry *entry)
+{
+ zbud_free(tree->pool, entry->handle);
+ zswap_entry_cache_free(entry);
+ atomic_dec(&zswap_stored_pages);
+ zswap_pool_pages = zbud_get_pool_size(tree->pool);
+}
+
+/*********************************
+* writeback code
+**********************************/
+/* return enum for zswap_get_swap_cache_page */
+enum zswap_get_swap_ret {
+ ZSWAP_SWAPCACHE_NEW,
+ ZSWAP_SWAPCACHE_EXIST,
+ ZSWAP_SWAPCACHE_NOMEM
+};
+
+/*
+ * 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 0 if page was already in the swap cache, page is not locked
+ * Returns 1 if the new page needs to be populated, page is locked
+ * Returns <0 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 = &swapper_spaces[swp_type(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, NULL);
+ } while (err != -ENOMEM);
+
+ if (new_page)
+ page_cache_release(new_page);
+ if (!found_page)
+ return ZSWAP_SWAPCACHE_NOMEM;
+ *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 zbud_pool *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, refcount;
+ struct writeback_control wbc = {
+ .sync_mode = WB_SYNC_NONE,
+ };
+
+ /* extract swpentry from data */
+ zhdr = zbud_map(pool, handle);
+ swpentry = zhdr->swpentry; /* here */
+ zbud_unmap(pool, handle);
+ tree = zswap_trees[swp_type(swpentry)];
+ offset = swp_offset(swpentry);
+ BUG_ON(pool != tree->pool);
+
+ /* find and ref zswap entry */
+ spin_lock(&tree->lock);
+ entry = zswap_rb_search(&tree->rbroot, offset);
+ if (!entry) {
+ /* entry was invalidated */
+ spin_unlock(&tree->lock);
+ return 0;
+ }
+ zswap_entry_get(entry);
+ 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_NOMEM: /* no memory */
+ ret = -ENOMEM;
+ goto fail;
+
+ case ZSWAP_SWAPCACHE_EXIST: /* page is unlocked */
+ /* 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 *)zbud_map(tree->pool, entry->handle) +
+ sizeof(struct zswap_header);
+ dst = kmap_atomic(page);
+ ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src,
+ entry->length, dst, &dlen);
+ kunmap_atomic(dst);
+ zbud_unmap(tree->pool, entry->handle);
+ BUG_ON(ret);
+ BUG_ON(dlen != PAGE_SIZE);
+
+ /* page is up to date */
+ SetPageUptodate(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(entry);
+ /* drop the initial reference from entry creation */
+ refcount = zswap_entry_put(entry);
+
+ /*
+ * There are three possible values for refcount here:
+ * (1) refcount is 1, load is in progress, unlink from rbtree,
+ * load will free
+ * (2) refcount is 0, (normal case) entry is valid,
+ * remove from rbtree and free entry
+ * (3) refcount is -1, invalidate happened during writeback,
+ * free entry
+ */
+ if (refcount >= 0) {
+ /* no invalidate yet, remove from rbtree */
+ rb_erase(&entry->rbnode, &tree->rbroot);
+ }
+ spin_unlock(&tree->lock);
+ if (refcount <= 0) {
+ /* free the entry */
+ zswap_free_entry(tree, entry);
+ return 0;
+ }
+ return -EAGAIN;
+
+fail:
+ spin_lock(&tree->lock);
+ zswap_entry_put(entry);
+ spin_unlock(&tree->lock);
+ 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 (zbud_reclaim_page(tree->pool, 8)) {
+ 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 = zbud_alloc(tree->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 = zbud_map(tree->pool, handle);
+ zhdr->swpentry = swp_entry(type, offset);
+ buf = (u8 *)(zhdr + 1);
+ memcpy(buf, dst, dlen);
+ zbud_unmap(tree->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 */
+ rb_erase(&dupentry->rbnode, &tree->rbroot);
+ if (!zswap_entry_put(dupentry)) {
+ /* free */
+ zswap_free_entry(tree, dupentry);
+ }
+ }
+ } while (ret == -EEXIST);
+ spin_unlock(&tree->lock);
+
+ /* update stats */
+ atomic_inc(&zswap_stored_pages);
+ zswap_pool_pages = zbud_get_pool_size(tree->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 refcount, ret;
+
+ /* find */
+ spin_lock(&tree->lock);
+ entry = zswap_rb_search(&tree->rbroot, offset);
+ if (!entry) {
+ /* entry was written back */
+ spin_unlock(&tree->lock);
+ return -1;
+ }
+ zswap_entry_get(entry);
+ spin_unlock(&tree->lock);
+
+ /* decompress */
+ dlen = PAGE_SIZE;
+ src = (u8 *)zbud_map(tree->pool, entry->handle) +
+ sizeof(struct zswap_header);
+ dst = kmap_atomic(page);
+ ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src, entry->length,
+ dst, &dlen);
+ kunmap_atomic(dst);
+ zbud_unmap(tree->pool, entry->handle);
+ BUG_ON(ret);
+
+ spin_lock(&tree->lock);
+ refcount = zswap_entry_put(entry);
+ if (likely(refcount)) {
+ spin_unlock(&tree->lock);
+ return 0;
+ }
+ spin_unlock(&tree->lock);
+
+ /*
+ * We don't have to unlink from the rbtree because
+ * zswap_writeback_entry() or zswap_frontswap_invalidate page()
+ * has already done this for us if we are the last reference.
+ */
+ /* free */
+
+ zswap_free_entry(tree, entry);
+
+ 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;
+ int refcount;
+
+ /* 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 */
+ rb_erase(&entry->rbnode, &tree->rbroot);
+
+ /* drop the initial reference from entry creation */
+ refcount = zswap_entry_put(entry);
+
+ spin_unlock(&tree->lock);
+
+ if (refcount) {
+ /* writeback in progress, writeback will free */
+ return;
+ }
+
+ /* free */
+ zswap_free_entry(tree, entry);
+}
+
+/* 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 rb_node *node;
+ struct zswap_entry *entry;
+
+ if (!tree)
+ return;
+
+ /* walk the tree and free everything */
+ spin_lock(&tree->lock);
+ /*
+ * TODO: Even though this code should not be executed because
+ * the try_to_unuse() in swapoff should have emptied the tree,
+ * it is very wasteful to rebalance the tree after every
+ * removal when we are freeing the whole tree.
+ *
+ * If post-order traversal code is ever added to the rbtree
+ * implementation, it should be used here.
+ */
+ while ((node = rb_first(&tree->rbroot))) {
+ entry = rb_entry(node, struct zswap_entry, rbnode);
+ rb_erase(&entry->rbnode, &tree->rbroot);
+ zbud_free(tree->pool, entry->handle);
+ zswap_entry_cache_free(entry);
+ atomic_dec(&zswap_stored_pages);
+ }
+ tree->rbroot = RB_ROOT;
+ spin_unlock(&tree->lock);
+}
+
+static struct zbud_ops zswap_zbud_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)
+ goto err;
+ tree->pool = zbud_create_pool(GFP_KERNEL, &zswap_zbud_ops);
+ if (!tree->pool)
+ goto freetree;
+ tree->rbroot = RB_ROOT;
+ spin_lock_init(&tree->lock);
+ zswap_trees[type] = tree;
+ return;
+
+freetree:
+ kfree(tree);
+err:
+ pr_err("alloc failed, zswap disabled for swap type %d\n", type);
+}
+
+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_pages", S_IRUGO,
+ zswap_debugfs_root, &zswap_pool_pages);
+ 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)
+{
+ if (!zswap_enabled)
+ return 0;
+
+ pr_info("loading zswap\n");
+ if (zswap_entry_cache_create()) {
+ pr_err("entry cache creation failed\n");
+ goto error;
+ }
+ 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_destory();
+error:
+ return -ENOMEM;
+}
+/* must be late so crypto has time to come up */
+late_initcall(init_zswap);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Seth Jennings <sjenning@linux.vnet.ibm.com>");
+MODULE_DESCRIPTION("Compressed cache for swap pages");