[PATCHv12,3/4] zswap: add to mm/
diff mbox series

Message ID 1369067168-12291-4-git-send-email-sjenning@linux.vnet.ibm.com
State New, archived
Headers show
Series
  • zswap: compressed swap caching
Related show

Commit Message

Seth Jennings May 20, 2013, 4:26 p.m. UTC
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>
---
 mm/Kconfig  |  22 +-
 mm/Makefile |   1 +
 mm/zswap.c  | 947 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 969 insertions(+), 1 deletion(-)
 create mode 100644 mm/zswap.c

Comments

Bob Liu May 21, 2013, 3:31 a.m. UTC | #1
On 05/21/2013 12:26 AM, Seth Jennings wrote:
> 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>
> ---
>  mm/Kconfig  |  22 +-
>  mm/Makefile |   1 +
>  mm/zswap.c  | 947 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
>  3 files changed, 969 insertions(+), 1 deletion(-)
>  create mode 100644 mm/zswap.c
> 
> diff --git a/mm/Kconfig b/mm/Kconfig
> index 45ec90d..eec97f2 100644
> --- a/mm/Kconfig
> +++ b/mm/Kconfig
> @@ -486,4 +486,24 @@ config ZBUD
>  	  It is designed to store up to two compressed pages per physical
>  	  page.  While this design limits storage density, it has simple and
>  	  deterministic reclaim properties that make it preferable to a higher
> -	  density approach when reclaim will be used.  
> +	  density approach when reclaim will be used.
> +
> +config ZSWAP
> +	bool "Compressed cache for swap pages (EXPERIMENTAL)"
> +	depends on FRONTSWAP && CRYPTO
> +	select CRYPTO_LZO
> +	select ZBUD
> +	default n
> +	help
> +	  A lightweight compressed cache for swap pages.  It takes
> +	  pages that are in the process of being swapped out and attempts to
> +	  compress them into a dynamically allocated RAM-based memory pool.
> +	  This can result in a significant I/O reduction on swap device and,
> +	  in the case where decompressing from RAM is faster that swap device
> +	  reads, can also improve workload performance.
> +
> +	  This is marked experimental because it is a new feature (as of
> +	  v3.11) that interacts heavily with memory reclaim.  While these
> +	  interactions don't cause any known issues on simple memory setups,
> +	  they have not be fully explored on the large set of potential
> +	  configurations and workloads that exist.
> diff --git a/mm/Makefile b/mm/Makefile
> index 95f0197..f008033 100644
> --- a/mm/Makefile
> +++ b/mm/Makefile
> @@ -32,6 +32,7 @@ obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o
>  obj-$(CONFIG_BOUNCE)	+= bounce.o
>  obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o
>  obj-$(CONFIG_FRONTSWAP)	+= frontswap.o
> +obj-$(CONFIG_ZSWAP)	+= zswap.o
>  obj-$(CONFIG_HAS_DMA)	+= dmapool.o
>  obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o
>  obj-$(CONFIG_NUMA) 	+= mempolicy.o
> diff --git a/mm/zswap.c b/mm/zswap.c
> new file mode 100644
> index 0000000..22cc034
> --- /dev/null
> +++ b/mm/zswap.c
> @@ -0,0 +1,947 @@
> +/*
> + * 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
> +**********************************/
> +#define ZSWAP_KMEM_CACHE_NAME "zswap_entry_cache"
> +static struct kmem_cache *zswap_entry_cache;
> +
> +static inline int zswap_entry_cache_create(void)
> +{
> +	zswap_entry_cache =
> +		kmem_cache_create(ZSWAP_KMEM_CACHE_NAME,
> +			sizeof(struct zswap_entry), 0, 0, NULL);
> +	return (zswap_entry_cache == NULL);
> +}
> +
> +static inline void zswap_entry_cache_destory(void)
> +{
> +	kmem_cache_destroy(zswap_entry_cache);
> +}
> +
> +static inline 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 inline void zswap_entry_cache_free(struct zswap_entry *entry)
> +{
> +	kmem_cache_free(zswap_entry_cache, entry);
> +}
> +
> +/* caller must hold the tree lock */
> +static inline void zswap_entry_get(struct zswap_entry *entry)
> +{
> +	entry->refcount++;
> +}
> +
> +/* caller must hold the tree lock */
> +static inline 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, it 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 inline 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 and 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)) {

So once the zswap is full, the performance will drop worse?
There maybe two writeback disk-IO instead of one compared with disable
zswap.
Every time frontswap_store() entered there will be two pages need to be
written out to disk.
In this case, the performance of zswap is worse than disable it?

> +			zswap_reject_reclaim_fail++;
> +			ret = -ENOMEM;
> +			goto reject;
> +		}
> +	}
Andrew Morton May 28, 2013, 9:59 p.m. UTC | #2
On Mon, 20 May 2013 11:26:07 -0500 Seth Jennings <sjenning@linux.vnet.ibm.com> wrote:

> 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/
> 
> ...

Some random doodlings:

> +/*********************************
> +* zswap entry functions
> +**********************************/
> +#define ZSWAP_KMEM_CACHE_NAME "zswap_entry_cache"

I don't think this macro needs to exist - it is only used once.

> +static struct kmem_cache *zswap_entry_cache;
> +
> +static inline int zswap_entry_cache_create(void)
> +{
> +	zswap_entry_cache =
> +		kmem_cache_create(ZSWAP_KMEM_CACHE_NAME,
> +			sizeof(struct zswap_entry), 0, 0, NULL);

Could use the KMEM_CACHE() helper here?

> +	return (zswap_entry_cache == NULL);
> +}
> +
> +static inline void zswap_entry_cache_destory(void)
> +{
> +	kmem_cache_destroy(zswap_entry_cache);
> +}
> +
> +static inline 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 inline void zswap_entry_cache_free(struct zswap_entry *entry)
> +{
> +	kmem_cache_free(zswap_entry_cache, entry);
> +}
> +
> +/* caller must hold the tree lock */
> +static inline void zswap_entry_get(struct zswap_entry *entry)
> +{
> +	entry->refcount++;
> +}
> +
> +/* caller must hold the tree lock */
> +static inline int zswap_entry_put(struct zswap_entry *entry)
> +{
> +	entry->refcount--;
> +	return entry->refcount;
> +}

Don't bother with the explicit "inline".  The compiler will ignore it
and will generally DTRT anyway.

> +/*********************************
> +* 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, it a pointer to
> + * the existing entry is stored in dupentry and the function returns -EEXIST

"it a pointer"?

> +*/

Missing leading space.

> +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;
> +}
> +
>
> ...
>
> +/*********************************
> +* helpers
> +**********************************/
> +static inline bool zswap_is_full(void)
> +{
> +	return (totalram_pages * zswap_max_pool_percent / 100 <
> +		zswap_pool_pages);
> +}

We have had issues in the past where percentage-based tunables were too
coarse on very large machines.  For example, a terabyte machine where 0
bytes is too small and 10GB is too large.

>
> ...
>
> +/*
> + * Attempts to free and entry by adding a page to the swap cache,

a/and/an/

> + * 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_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);

In all these places where the CPU alters the kmapped page: do we have
(or need) the appropriate cache flushing primitives? 
flush_dcache_page() and similar.

> +	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;
> +}
> +
> +/* invalidates a single page */

"invalidate" is a very vague term in Linux.  More specificity about
what actually happens to this page would be useful.

>
> ...
>
> +static struct zbud_ops zswap_zbud_ops = {
> +	.evict = zswap_writeback_entry
> +};
> +
> +/* NOTE: this is called in atomic context from swapon and must not sleep */

Actually from frontswap, and calling a subsystem's ->init handler in
atomic context is quite lame - *of course* that handler will want to
allocate memory!

Whereabouts is the offending calling code and how do we fix it?

> +static void zswap_frontswap_init(unsigned type)
> +{
> +	struct zswap_tree *tree;
> +
> +	tree = kzalloc(sizeof(struct zswap_tree), GFP_ATOMIC);
> +	if (!tree)
> +		goto err;
> +	tree->pool = zbud_create_pool(GFP_NOWAIT, &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);
> +}
> +
>
> ...
>

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
Seth Jennings May 29, 2013, 2:57 p.m. UTC | #3
On Tue, May 28, 2013 at 02:59:18PM -0700, Andrew Morton wrote:
> On Mon, 20 May 2013 11:26:07 -0500 Seth Jennings <sjenning@linux.vnet.ibm.com> wrote:
> 
> > 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/
> > 
> > ...
> 
> Some random doodlings:

Thanks for the feedback!

> 
> > +/*********************************
> > +* zswap entry functions
> > +**********************************/
> > +#define ZSWAP_KMEM_CACHE_NAME "zswap_entry_cache"
> 
> I don't think this macro needs to exist - it is only used once.

Yes.

> 
> > +static struct kmem_cache *zswap_entry_cache;
> > +
> > +static inline int zswap_entry_cache_create(void)
> > +{
> > +	zswap_entry_cache =
> > +		kmem_cache_create(ZSWAP_KMEM_CACHE_NAME,
> > +			sizeof(struct zswap_entry), 0, 0, NULL);
> 
> Could use the KMEM_CACHE() helper here?

Yes.

> 
> > +	return (zswap_entry_cache == NULL);
> > +}
> > +
> > +static inline void zswap_entry_cache_destory(void)
> > +{
> > +	kmem_cache_destroy(zswap_entry_cache);
> > +}
> > +
> > +static inline 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 inline void zswap_entry_cache_free(struct zswap_entry *entry)
> > +{
> > +	kmem_cache_free(zswap_entry_cache, entry);
> > +}
> > +
> > +/* caller must hold the tree lock */
> > +static inline void zswap_entry_get(struct zswap_entry *entry)
> > +{
> > +	entry->refcount++;
> > +}
> > +
> > +/* caller must hold the tree lock */
> > +static inline int zswap_entry_put(struct zswap_entry *entry)
> > +{
> > +	entry->refcount--;
> > +	return entry->refcount;
> > +}
> 
> Don't bother with the explicit "inline".  The compiler will ignore it
> and will generally DTRT anyway.

Ok.

> 
> > +/*********************************
> > +* 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, it a pointer to
> > + * the existing entry is stored in dupentry and the function returns -EEXIST
> 
> "it a pointer"?

a pointer. I'll fix it up.

> 
> > +*/
> 
> Missing leading space.

Yes.

> 
> > +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;
> > +}
> > +
> >
> > ...
> >
> > +/*********************************
> > +* helpers
> > +**********************************/
> > +static inline bool zswap_is_full(void)
> > +{
> > +	return (totalram_pages * zswap_max_pool_percent / 100 <
> > +		zswap_pool_pages);
> > +}
> 
> We have had issues in the past where percentage-based tunables were too
> coarse on very large machines.  For example, a terabyte machine where 0
> bytes is too small and 10GB is too large.

Yes, this is known limitation of the code right now and it is a high priority
to come up with something better.  It isn't clear what dynamic sizing policy
should be used so, until such time as that policy can be determined, this is a
simple stop-gap that works well enough for simple setups.

> 
> >
> > ...
> >
> > +/*
> > + * Attempts to free and entry by adding a page to the swap cache,
> 
> a/and/an/

Yes.

> 
> > + * 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_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);
> 
> In all these places where the CPU alters the kmapped page: do we have
> (or need) the appropriate cache flushing primitives? 
> flush_dcache_page() and similar.

My knowledge of flush_dcache_page() is limited, but from what I can tell, it
ensures cache coherency between kernel and userspace mappings to the same
memory page.  These pages are never mapped by userspace and so that isn't an
issue.  Also kunmap_atomic() does a tlb flush on the pte used for the mapping.

> 
> > +	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;
> > +}
> > +
> > +/* invalidates a single page */
> 
> "invalidate" is a very vague term in Linux.  More specificity about
> what actually happens to this page would be useful.

frontswap_invalidate_page() is called from swap_entry_free() where a slot in
the swap device is being freed.

This was changed to "invalidate" in the past because "flush" was too general.
Apparently "invalidate" isn't much better :-/

I'll change the comment though.

> 
> >
> > ...
> >
> > +static struct zbud_ops zswap_zbud_ops = {
> > +	.evict = zswap_writeback_entry
> > +};
> > +
> > +/* NOTE: this is called in atomic context from swapon and must not sleep */
> 
> Actually from frontswap, and calling a subsystem's ->init handler in
> atomic context is quite lame - *of course* that handler will want to
> allocate memory!
> 
> Whereabouts is the offending calling code and how do we fix it?

This was actually fixed in commit 4f89849da and merged in 3.10.

I'll fixup this comment and change the GFP_ATOMIC/NOWAIT below to GFP_KERNEL.

> 
> > +static void zswap_frontswap_init(unsigned type)
> > +{
> > +	struct zswap_tree *tree;
> > +
> > +	tree = kzalloc(sizeof(struct zswap_tree), GFP_ATOMIC);
> > +	if (!tree)
> > +		goto err;
> > +	tree->pool = zbud_create_pool(GFP_NOWAIT, &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);
> > +}
> > +
> >
> > ...
> >
> 

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
Andrew Morton May 29, 2013, 6:29 p.m. UTC | #4
On Wed, 29 May 2013 09:57:20 -0500 Seth Jennings <sjenning@linux.vnet.ibm.com> wrote:

> > > +/*********************************
> > > +* helpers
> > > +**********************************/
> > > +static inline bool zswap_is_full(void)
> > > +{
> > > +	return (totalram_pages * zswap_max_pool_percent / 100 <
> > > +		zswap_pool_pages);
> > > +}
> > 
> > We have had issues in the past where percentage-based tunables were too
> > coarse on very large machines.  For example, a terabyte machine where 0
> > bytes is too small and 10GB is too large.
> 
> Yes, this is known limitation of the code right now and it is a high priority
> to come up with something better.  It isn't clear what dynamic sizing policy
> should be used so, until such time as that policy can be determined, this is a
> simple stop-gap that works well enough for simple setups.

It's a module parameter and hence is part of the userspace interface. 
It's undesirable that the interface be changed, and it would be rather
dumb to merge it as-is when we *know* that it will be changed.

I don't think we can remove the parameter altogether (or can we?), so I
suggest we finalise it ASAP.  Perhaps rename it to
zswap_max_pool_ratio, with a range 1..999999.  Better ideas needed :(


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
Seth Jennings May 29, 2013, 7:50 p.m. UTC | #5
On Wed, May 29, 2013 at 11:29:29AM -0700, Andrew Morton wrote:
> On Wed, 29 May 2013 09:57:20 -0500 Seth Jennings <sjenning@linux.vnet.ibm.com> wrote:
> 
> > > > +/*********************************
> > > > +* helpers
> > > > +**********************************/
> > > > +static inline bool zswap_is_full(void)
> > > > +{
> > > > +	return (totalram_pages * zswap_max_pool_percent / 100 <
> > > > +		zswap_pool_pages);
> > > > +}
> > > 
> > > We have had issues in the past where percentage-based tunables were too
> > > coarse on very large machines.  For example, a terabyte machine where 0
> > > bytes is too small and 10GB is too large.
> > 
> > Yes, this is known limitation of the code right now and it is a high priority
> > to come up with something better.  It isn't clear what dynamic sizing policy
> > should be used so, until such time as that policy can be determined, this is a
> > simple stop-gap that works well enough for simple setups.
> 
> It's a module parameter and hence is part of the userspace interface. 
> It's undesirable that the interface be changed, and it would be rather
> dumb to merge it as-is when we *know* that it will be changed.
> 
> I don't think we can remove the parameter altogether (or can we?), so I
> suggest we finalise it ASAP.  Perhaps rename it to
> zswap_max_pool_ratio, with a range 1..999999.  Better ideas needed :(

zswap_max_pool_ratio is fine with me.  I'm not entirely clear on the change
though.  Would that just be a name change or a change in meaning?

Also, we can keep the tunable as I imagine there will always be some use for a
manual override of the (future) dynamic policy.  When the dynamic policy is
available, we can just say that zswap_max_pool_ratio = 0 means "use dynamic
policy" and change the default to 0.  Does that sounds reasonable?

Seth

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
Andrew Morton May 29, 2013, 7:57 p.m. UTC | #6
On Wed, 29 May 2013 14:50:27 -0500 Seth Jennings <sjenning@linux.vnet.ibm.com> wrote:

> On Wed, May 29, 2013 at 11:29:29AM -0700, Andrew Morton wrote:
> > On Wed, 29 May 2013 09:57:20 -0500 Seth Jennings <sjenning@linux.vnet.ibm.com> wrote:
> > 
> > > > > +/*********************************
> > > > > +* helpers
> > > > > +**********************************/
> > > > > +static inline bool zswap_is_full(void)
> > > > > +{
> > > > > +	return (totalram_pages * zswap_max_pool_percent / 100 <
> > > > > +		zswap_pool_pages);
> > > > > +}
> > > > 
> > > > We have had issues in the past where percentage-based tunables were too
> > > > coarse on very large machines.  For example, a terabyte machine where 0
> > > > bytes is too small and 10GB is too large.
> > > 
> > > Yes, this is known limitation of the code right now and it is a high priority
> > > to come up with something better.  It isn't clear what dynamic sizing policy
> > > should be used so, until such time as that policy can be determined, this is a
> > > simple stop-gap that works well enough for simple setups.
> > 
> > It's a module parameter and hence is part of the userspace interface. 
> > It's undesirable that the interface be changed, and it would be rather
> > dumb to merge it as-is when we *know* that it will be changed.
> > 
> > I don't think we can remove the parameter altogether (or can we?), so I
> > suggest we finalise it ASAP.  Perhaps rename it to
> > zswap_max_pool_ratio, with a range 1..999999.  Better ideas needed :(
> 
> zswap_max_pool_ratio is fine with me.  I'm not entirely clear on the change
> though.  Would that just be a name change or a change in meaning?

It would be a change in behaviour.  The problem which I'm suggesting we
address is that a 1% increment is too coarse.

> Also, we can keep the tunable as I imagine there will always be some use for a
> manual override of the (future) dynamic policy.  When the dynamic policy is
> available, we can just say that zswap_max_pool_ratio = 0 means "use dynamic
> policy" and change the default to 0.  Does that sounds reasonable?

Sounds OK.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
Seth Jennings May 29, 2013, 9:08 p.m. UTC | #7
On Wed, May 29, 2013 at 12:57:47PM -0700, Andrew Morton wrote:
> On Wed, 29 May 2013 14:50:27 -0500 Seth Jennings <sjenning@linux.vnet.ibm.com> wrote:
> 
> > On Wed, May 29, 2013 at 11:29:29AM -0700, Andrew Morton wrote:
> > > On Wed, 29 May 2013 09:57:20 -0500 Seth Jennings <sjenning@linux.vnet.ibm.com> wrote:
> > > 
> > > > > > +/*********************************
> > > > > > +* helpers
> > > > > > +**********************************/
> > > > > > +static inline bool zswap_is_full(void)
> > > > > > +{
> > > > > > +	return (totalram_pages * zswap_max_pool_percent / 100 <
> > > > > > +		zswap_pool_pages);
> > > > > > +}
> > > > > 
> > > > > We have had issues in the past where percentage-based tunables were too
> > > > > coarse on very large machines.  For example, a terabyte machine where 0
> > > > > bytes is too small and 10GB is too large.
> > > > 
> > > > Yes, this is known limitation of the code right now and it is a high priority
> > > > to come up with something better.  It isn't clear what dynamic sizing policy
> > > > should be used so, until such time as that policy can be determined, this is a
> > > > simple stop-gap that works well enough for simple setups.
> > > 
> > > It's a module parameter and hence is part of the userspace interface. 
> > > It's undesirable that the interface be changed, and it would be rather
> > > dumb to merge it as-is when we *know* that it will be changed.
> > > 
> > > I don't think we can remove the parameter altogether (or can we?), so I
> > > suggest we finalise it ASAP.  Perhaps rename it to
> > > zswap_max_pool_ratio, with a range 1..999999.  Better ideas needed :(
> > 
> > zswap_max_pool_ratio is fine with me.  I'm not entirely clear on the change
> > though.  Would that just be a name change or a change in meaning?
> 
> It would be a change in behaviour.  The problem which I'm suggesting we
> address is that a 1% increment is too coarse.

Sorry, but I'm not getting this.  This zswap_max_pool_ratio is a ratio of what
to what?  Maybe if you wrote out the calculation of the max pool size using
this ratio I'll get it.

Seth

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
Andrew Morton May 29, 2013, 9:16 p.m. UTC | #8
On Wed, 29 May 2013 16:08:20 -0500 Seth Jennings <sjenning@linux.vnet.ibm.com> wrote:

> On Wed, May 29, 2013 at 12:57:47PM -0700, Andrew Morton wrote:
> > On Wed, 29 May 2013 14:50:27 -0500 Seth Jennings <sjenning@linux.vnet.ibm.com> wrote:
> > 
> > > On Wed, May 29, 2013 at 11:29:29AM -0700, Andrew Morton wrote:
> > > > On Wed, 29 May 2013 09:57:20 -0500 Seth Jennings <sjenning@linux.vnet.ibm.com> wrote:
> > > > 
> > > > > > > +/*********************************
> > > > > > > +* helpers
> > > > > > > +**********************************/
> > > > > > > +static inline bool zswap_is_full(void)
> > > > > > > +{
> > > > > > > +	return (totalram_pages * zswap_max_pool_percent / 100 <
> > > > > > > +		zswap_pool_pages);
> > > > > > > +}
> > > > > > 
> > > > > > We have had issues in the past where percentage-based tunables were too
> > > > > > coarse on very large machines.  For example, a terabyte machine where 0
> > > > > > bytes is too small and 10GB is too large.
> > > > > 
> > > > > Yes, this is known limitation of the code right now and it is a high priority
> > > > > to come up with something better.  It isn't clear what dynamic sizing policy
> > > > > should be used so, until such time as that policy can be determined, this is a
> > > > > simple stop-gap that works well enough for simple setups.
> > > > 
> > > > It's a module parameter and hence is part of the userspace interface. 
> > > > It's undesirable that the interface be changed, and it would be rather
> > > > dumb to merge it as-is when we *know* that it will be changed.
> > > > 
> > > > I don't think we can remove the parameter altogether (or can we?), so I
> > > > suggest we finalise it ASAP.  Perhaps rename it to
> > > > zswap_max_pool_ratio, with a range 1..999999.  Better ideas needed :(
> > > 
> > > zswap_max_pool_ratio is fine with me.  I'm not entirely clear on the change
> > > though.  Would that just be a name change or a change in meaning?
> > 
> > It would be a change in behaviour.  The problem which I'm suggesting we
> > address is that a 1% increment is too coarse.
> 
> Sorry, but I'm not getting this.  This zswap_max_pool_ratio is a ratio of what
> to what?  Maybe if you wrote out the calculation of the max pool size using
> this ratio I'll get it.
> 

This:

	totalram_pages * zswap_max_pool_percent / 100

means that we have are able to control the pool size in 10GB increments
on a 1TB machine.  Past experience with other tunables tells us that
this can be a problem.  Hence my (lame) suggestion that we replace it
with

	totalram_pages * zswap_max_pool_ratio / 1000000


Another approach would be to stop using a ratio altogether, and make the
tunable specify an absolute number of bytes.  That's how we approached
this problem in the case of /proc/sys/vm/dirty_background_ratio.  See
https://lkml.org/lkml/2008/11/23/160.

(And it's "bytes", not "pages" because PAGE_SIZE can vary by a factor
of 16, which is a lot). 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Patch
diff mbox series

diff --git a/mm/Kconfig b/mm/Kconfig
index 45ec90d..eec97f2 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -486,4 +486,24 @@  config ZBUD
 	  It is designed to store up to two compressed pages per physical
 	  page.  While this design limits storage density, it has simple and
 	  deterministic reclaim properties that make it preferable to a higher
-	  density approach when reclaim will be used.  
+	  density approach when reclaim will be used.
+
+config ZSWAP
+	bool "Compressed cache for swap pages (EXPERIMENTAL)"
+	depends on FRONTSWAP && CRYPTO
+	select CRYPTO_LZO
+	select ZBUD
+	default n
+	help
+	  A lightweight compressed cache for swap pages.  It takes
+	  pages that are in the process of being swapped out and attempts to
+	  compress them into a dynamically allocated RAM-based memory pool.
+	  This can result in a significant I/O reduction on swap device and,
+	  in the case where decompressing from RAM is faster that swap device
+	  reads, can also improve workload performance.
+
+	  This is marked experimental because it is a new feature (as of
+	  v3.11) that interacts heavily with memory reclaim.  While these
+	  interactions don't cause any known issues on simple memory setups,
+	  they have not be fully explored on the large set of potential
+	  configurations and workloads that exist.
diff --git a/mm/Makefile b/mm/Makefile
index 95f0197..f008033 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -32,6 +32,7 @@  obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o
 obj-$(CONFIG_BOUNCE)	+= bounce.o
 obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o
 obj-$(CONFIG_FRONTSWAP)	+= frontswap.o
+obj-$(CONFIG_ZSWAP)	+= zswap.o
 obj-$(CONFIG_HAS_DMA)	+= dmapool.o
 obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o
 obj-$(CONFIG_NUMA) 	+= mempolicy.o
diff --git a/mm/zswap.c b/mm/zswap.c
new file mode 100644
index 0000000..22cc034
--- /dev/null
+++ b/mm/zswap.c
@@ -0,0 +1,947 @@ 
+/*
+ * 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
+**********************************/
+#define ZSWAP_KMEM_CACHE_NAME "zswap_entry_cache"
+static struct kmem_cache *zswap_entry_cache;
+
+static inline int zswap_entry_cache_create(void)
+{
+	zswap_entry_cache =
+		kmem_cache_create(ZSWAP_KMEM_CACHE_NAME,
+			sizeof(struct zswap_entry), 0, 0, NULL);
+	return (zswap_entry_cache == NULL);
+}
+
+static inline void zswap_entry_cache_destory(void)
+{
+	kmem_cache_destroy(zswap_entry_cache);
+}
+
+static inline 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 inline void zswap_entry_cache_free(struct zswap_entry *entry)
+{
+	kmem_cache_free(zswap_entry_cache, entry);
+}
+
+/* caller must hold the tree lock */
+static inline void zswap_entry_get(struct zswap_entry *entry)
+{
+	entry->refcount++;
+}
+
+/* caller must hold the tree lock */
+static inline 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, it 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 inline 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 and 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 == -E2BIG) {
+		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;
+}
+
+/* invalidates a single page */
+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);
+}
+
+/* invalidates all pages 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
+};
+
+/* NOTE: this is called in atomic context from swapon and must not sleep */
+static void zswap_frontswap_init(unsigned type)
+{
+	struct zswap_tree *tree;
+
+	tree = kzalloc(sizeof(struct zswap_tree), GFP_ATOMIC);
+	if (!tree)
+		goto err;
+	tree->pool = zbud_create_pool(GFP_NOWAIT, &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 inline int __init zswap_debugfs_init(void)
+{
+	return 0;
+}
+
+static inline 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");