Staging: Rename ramzswap files to zram

Related changes:
 - Modify revelant Kconfig and Makefile accordingly.
 - Change include filenames in code.
 - Remove dependency on CONFIG_SWAP in Kconfig as zram usage
is no longer limited to swap disks.

Signed-off-by: Nitin Gupta <ngupta@vflare.org>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

9 files changed, 1720 insertions, 0 deletions

diff --git a/drivers/staging/zram/Kconfig b/drivers/staging/zram/Kconfig
new file mode 100644
index 00000000000..5bcfe16feb1
--- /dev/null
+++ b/drivers/staging/zram/Kconfig
@@ -0,0 +1,28 @@
+config ZRAM
+	tristate "Compressed RAM block device support"
+	select LZO_COMPRESS
+	select LZO_DECOMPRESS
+	default n
+	help
+	  Creates virtual block devices called /dev/zramX (X = 0, 1, ...).
+	  Pages written to these disks are compressed and stored in memory
+	  itself. These disks allow very fast I/O and compression provides
+	  good amounts of memory savings.
+
+	  It has several use cases, for example: /tmp storage, use as swap
+	  disks and maybe many more.
+
+	  See zram.txt for more information.
+	  Project home: http://compcache.googlecode.com/
+
+config ZRAM_STATS
+	bool "Enable statistics for compressed RAM disks"
+	depends on ZRAM
+	default y
+	help
+	  Enable statistics collection for compressed RAM devices. Statistics
+	  are exported through ioctl interface, so you have to use zramconfig
+	  program to get them. This adds only a minimal overhead.
+
+	  If unsure, say Y.
+
diff --git a/drivers/staging/zram/Makefile b/drivers/staging/zram/Makefile
new file mode 100644
index 00000000000..b2c087aa105
--- /dev/null
+++ b/drivers/staging/zram/Makefile
@@ -0,0 +1,3 @@
+zram-objs	:=	zram_drv.o xvmalloc.o
+
+obj-$(CONFIG_ZRAM)	+=	zram.o
diff --git a/drivers/staging/zram/xvmalloc.c b/drivers/staging/zram/xvmalloc.c
new file mode 100644
index 00000000000..3fdbb8ada82
--- /dev/null
+++ b/drivers/staging/zram/xvmalloc.c
@@ -0,0 +1,507 @@
+/*
+ * xvmalloc memory allocator
+ *
+ * Copyright (C) 2008, 2009, 2010  Nitin Gupta
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the licence that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ */
+
+#include <linux/bitops.h>
+#include <linux/errno.h>
+#include <linux/highmem.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+
+#include "xvmalloc.h"
+#include "xvmalloc_int.h"
+
+static void stat_inc(u64 *value)
+{
+	*value = *value + 1;
+}
+
+static void stat_dec(u64 *value)
+{
+	*value = *value - 1;
+}
+
+static int test_flag(struct block_header *block, enum blockflags flag)
+{
+	return block->prev & BIT(flag);
+}
+
+static void set_flag(struct block_header *block, enum blockflags flag)
+{
+	block->prev |= BIT(flag);
+}
+
+static void clear_flag(struct block_header *block, enum blockflags flag)
+{
+	block->prev &= ~BIT(flag);
+}
+
+/*
+ * Given <page, offset> pair, provide a derefrencable pointer.
+ * This is called from xv_malloc/xv_free path, so it
+ * needs to be fast.
+ */
+static void *get_ptr_atomic(struct page *page, u16 offset, enum km_type type)
+{
+	unsigned char *base;
+
+	base = kmap_atomic(page, type);
+	return base + offset;
+}
+
+static void put_ptr_atomic(void *ptr, enum km_type type)
+{
+	kunmap_atomic(ptr, type);
+}
+
+static u32 get_blockprev(struct block_header *block)
+{
+	return block->prev & PREV_MASK;
+}
+
+static void set_blockprev(struct block_header *block, u16 new_offset)
+{
+	block->prev = new_offset | (block->prev & FLAGS_MASK);
+}
+
+static struct block_header *BLOCK_NEXT(struct block_header *block)
+{
+	return (struct block_header *)
+		((char *)block + block->size + XV_ALIGN);
+}
+
+/*
+ * Get index of free list containing blocks of maximum size
+ * which is less than or equal to given size.
+ */
+static u32 get_index_for_insert(u32 size)
+{
+	if (unlikely(size > XV_MAX_ALLOC_SIZE))
+		size = XV_MAX_ALLOC_SIZE;
+	size &= ~FL_DELTA_MASK;
+	return (size - XV_MIN_ALLOC_SIZE) >> FL_DELTA_SHIFT;
+}
+
+/*
+ * Get index of free list having blocks of size greater than
+ * or equal to requested size.
+ */
+static u32 get_index(u32 size)
+{
+	if (unlikely(size < XV_MIN_ALLOC_SIZE))
+		size = XV_MIN_ALLOC_SIZE;
+	size = ALIGN(size, FL_DELTA);
+	return (size - XV_MIN_ALLOC_SIZE) >> FL_DELTA_SHIFT;
+}
+
+/**
+ * find_block - find block of at least given size
+ * @pool: memory pool to search from
+ * @size: size of block required
+ * @page: page containing required block
+ * @offset: offset within the page where block is located.
+ *
+ * Searches two level bitmap to locate block of at least
+ * the given size. If such a block is found, it provides
+ * <page, offset> to identify this block and returns index
+ * in freelist where we found this block.
+ * Otherwise, returns 0 and <page, offset> params are not touched.
+ */
+static u32 find_block(struct xv_pool *pool, u32 size,
+			struct page **page, u32 *offset)
+{
+	ulong flbitmap, slbitmap;
+	u32 flindex, slindex, slbitstart;
+
+	/* There are no free blocks in this pool */
+	if (!pool->flbitmap)
+		return 0;
+
+	/* Get freelist index correspoding to this size */
+	slindex = get_index(size);
+	slbitmap = pool->slbitmap[slindex / BITS_PER_LONG];
+	slbitstart = slindex % BITS_PER_LONG;
+
+	/*
+	 * If freelist is not empty at this index, we found the
+	 * block - head of this list. This is approximate best-fit match.
+	 */
+	if (test_bit(slbitstart, &slbitmap)) {
+		*page = pool->freelist[slindex].page;
+		*offset = pool->freelist[slindex].offset;
+		return slindex;
+	}
+
+	/*
+	 * No best-fit found. Search a bit further in bitmap for a free block.
+	 * Second level bitmap consists of series of 32-bit chunks. Search
+	 * further in the chunk where we expected a best-fit, starting from
+	 * index location found above.
+	 */
+	slbitstart++;
+	slbitmap >>= slbitstart;
+
+	/* Skip this search if we were already at end of this bitmap chunk */
+	if ((slbitstart != BITS_PER_LONG) && slbitmap) {
+		slindex += __ffs(slbitmap) + 1;
+		*page = pool->freelist[slindex].page;
+		*offset = pool->freelist[slindex].offset;
+		return slindex;
+	}
+
+	/* Now do a full two-level bitmap search to find next nearest fit */
+	flindex = slindex / BITS_PER_LONG;
+
+	flbitmap = (pool->flbitmap) >> (flindex + 1);
+	if (!flbitmap)
+		return 0;
+
+	flindex += __ffs(flbitmap) + 1;
+	slbitmap = pool->slbitmap[flindex];
+	slindex = (flindex * BITS_PER_LONG) + __ffs(slbitmap);
+	*page = pool->freelist[slindex].page;
+	*offset = pool->freelist[slindex].offset;
+
+	return slindex;
+}
+
+/*
+ * Insert block at <page, offset> in freelist of given pool.
+ * freelist used depends on block size.
+ */
+static void insert_block(struct xv_pool *pool, struct page *page, u32 offset,
+			struct block_header *block)
+{
+	u32 flindex, slindex;
+	struct block_header *nextblock;
+
+	slindex = get_index_for_insert(block->size);
+	flindex = slindex / BITS_PER_LONG;
+
+	block->link.prev_page = 0;
+	block->link.prev_offset = 0;
+	block->link.next_page = pool->freelist[slindex].page;
+	block->link.next_offset = pool->freelist[slindex].offset;
+	pool->freelist[slindex].page = page;
+	pool->freelist[slindex].offset = offset;
+
+	if (block->link.next_page) {
+		nextblock = get_ptr_atomic(block->link.next_page,
+					block->link.next_offset, KM_USER1);
+		nextblock->link.prev_page = page;
+		nextblock->link.prev_offset = offset;
+		put_ptr_atomic(nextblock, KM_USER1);
+	}
+
+	__set_bit(slindex % BITS_PER_LONG, &pool->slbitmap[flindex]);
+	__set_bit(flindex, &pool->flbitmap);
+}
+
+/*
+ * Remove block from head of freelist. Index 'slindex' identifies the freelist.
+ */
+static void remove_block_head(struct xv_pool *pool,
+			struct block_header *block, u32 slindex)
+{
+	struct block_header *tmpblock;
+	u32 flindex = slindex / BITS_PER_LONG;
+
+	pool->freelist[slindex].page = block->link.next_page;
+	pool->freelist[slindex].offset = block->link.next_offset;
+	block->link.prev_page = 0;
+	block->link.prev_offset = 0;
+
+	if (!pool->freelist[slindex].page) {
+		__clear_bit(slindex % BITS_PER_LONG, &pool->slbitmap[flindex]);
+		if (!pool->slbitmap[flindex])
+			__clear_bit(flindex, &pool->flbitmap);
+	} else {
+		/*
+		 * DEBUG ONLY: We need not reinitialize freelist head previous
+		 * pointer to 0 - we never depend on its value. But just for
+		 * sanity, lets do it.
+		 */
+		tmpblock = get_ptr_atomic(pool->freelist[slindex].page,
+				pool->freelist[slindex].offset, KM_USER1);
+		tmpblock->link.prev_page = 0;
+		tmpblock->link.prev_offset = 0;
+		put_ptr_atomic(tmpblock, KM_USER1);
+	}
+}
+
+/*
+ * Remove block from freelist. Index 'slindex' identifies the freelist.
+ */
+static void remove_block(struct xv_pool *pool, struct page *page, u32 offset,
+			struct block_header *block, u32 slindex)
+{
+	u32 flindex;
+	struct block_header *tmpblock;
+
+	if (pool->freelist[slindex].page == page
+	   && pool->freelist[slindex].offset == offset) {
+		remove_block_head(pool, block, slindex);
+		return;
+	}
+
+	flindex = slindex / BITS_PER_LONG;
+
+	if (block->link.prev_page) {
+		tmpblock = get_ptr_atomic(block->link.prev_page,
+				block->link.prev_offset, KM_USER1);
+		tmpblock->link.next_page = block->link.next_page;
+		tmpblock->link.next_offset = block->link.next_offset;
+		put_ptr_atomic(tmpblock, KM_USER1);
+	}
+
+	if (block->link.next_page) {
+		tmpblock = get_ptr_atomic(block->link.next_page,
+				block->link.next_offset, KM_USER1);
+		tmpblock->link.prev_page = block->link.prev_page;
+		tmpblock->link.prev_offset = block->link.prev_offset;
+		put_ptr_atomic(tmpblock, KM_USER1);
+	}
+}
+
+/*
+ * Allocate a page and add it to freelist of given pool.
+ */
+static int grow_pool(struct xv_pool *pool, gfp_t flags)
+{
+	struct page *page;
+	struct block_header *block;
+
+	page = alloc_page(flags);
+	if (unlikely(!page))
+		return -ENOMEM;
+
+	stat_inc(&pool->total_pages);
+
+	spin_lock(&pool->lock);
+	block = get_ptr_atomic(page, 0, KM_USER0);
+
+	block->size = PAGE_SIZE - XV_ALIGN;
+	set_flag(block, BLOCK_FREE);
+	clear_flag(block, PREV_FREE);
+	set_blockprev(block, 0);
+
+	insert_block(pool, page, 0, block);
+
+	put_ptr_atomic(block, KM_USER0);
+	spin_unlock(&pool->lock);
+
+	return 0;
+}
+
+/*
+ * Create a memory pool. Allocates freelist, bitmaps and other
+ * per-pool metadata.
+ */
+struct xv_pool *xv_create_pool(void)
+{
+	u32 ovhd_size;
+	struct xv_pool *pool;
+
+	ovhd_size = roundup(sizeof(*pool), PAGE_SIZE);
+	pool = kzalloc(ovhd_size, GFP_KERNEL);
+	if (!pool)
+		return NULL;
+
+	spin_lock_init(&pool->lock);
+
+	return pool;
+}
+
+void xv_destroy_pool(struct xv_pool *pool)
+{
+	kfree(pool);
+}
+
+/**
+ * xv_malloc - Allocate block of given size from pool.
+ * @pool: pool to allocate from
+ * @size: size of block to allocate
+ * @page: page no. that holds the object
+ * @offset: location of object within page
+ *
+ * On success, <page, offset> identifies block allocated
+ * and 0 is returned. On failure, <page, offset> is set to
+ * 0 and -ENOMEM is returned.
+ *
+ * Allocation requests with size > XV_MAX_ALLOC_SIZE will fail.
+ */
+int xv_malloc(struct xv_pool *pool, u32 size, struct page **page,
+		u32 *offset, gfp_t flags)
+{
+	int error;
+	u32 index, tmpsize, origsize, tmpoffset;
+	struct block_header *block, *tmpblock;
+
+	*page = NULL;
+	*offset = 0;
+	origsize = size;
+
+	if (unlikely(!size || size > XV_MAX_ALLOC_SIZE))
+		return -ENOMEM;
+
+	size = ALIGN(size, XV_ALIGN);
+
+	spin_lock(&pool->lock);
+
+	index = find_block(pool, size, page, offset);
+
+	if (!*page) {
+		spin_unlock(&pool->lock);
+		if (flags & GFP_NOWAIT)
+			return -ENOMEM;
+		error = grow_pool(pool, flags);
+		if (unlikely(error))
+			return error;
+
+		spin_lock(&pool->lock);
+		index = find_block(pool, size, page, offset);
+	}
+
+	if (!*page) {
+		spin_unlock(&pool->lock);
+		return -ENOMEM;
+	}
+
+	block = get_ptr_atomic(*page, *offset, KM_USER0);
+
+	remove_block_head(pool, block, index);
+
+	/* Split the block if required */
+	tmpoffset = *offset + size + XV_ALIGN;
+	tmpsize = block->size - size;
+	tmpblock = (struct block_header *)((char *)block + size + XV_ALIGN);
+	if (tmpsize) {
+		tmpblock->size = tmpsize - XV_ALIGN;
+		set_flag(tmpblock, BLOCK_FREE);
+		clear_flag(tmpblock, PREV_FREE);
+
+		set_blockprev(tmpblock, *offset);
+		if (tmpblock->size >= XV_MIN_ALLOC_SIZE)
+			insert_block(pool, *page, tmpoffset, tmpblock);
+
+		if (tmpoffset + XV_ALIGN + tmpblock->size != PAGE_SIZE) {
+			tmpblock = BLOCK_NEXT(tmpblock);
+			set_blockprev(tmpblock, tmpoffset);
+		}
+	} else {
+		/* This block is exact fit */
+		if (tmpoffset != PAGE_SIZE)
+			clear_flag(tmpblock, PREV_FREE);
+	}
+
+	block->size = origsize;
+	clear_flag(block, BLOCK_FREE);
+
+	put_ptr_atomic(block, KM_USER0);
+	spin_unlock(&pool->lock);
+
+	*offset += XV_ALIGN;
+
+	return 0;
+}
+
+/*
+ * Free block identified with <page, offset>
+ */
+void xv_free(struct xv_pool *pool, struct page *page, u32 offset)
+{
+	void *page_start;
+	struct block_header *block, *tmpblock;
+
+	offset -= XV_ALIGN;
+
+	spin_lock(&pool->lock);
+
+	page_start = get_ptr_atomic(page, 0, KM_USER0);
+	block = (struct block_header *)((char *)page_start + offset);
+
+	/* Catch double free bugs */
+	BUG_ON(test_flag(block, BLOCK_FREE));
+
+	block->size = ALIGN(block->size, XV_ALIGN);
+
+	tmpblock = BLOCK_NEXT(block);
+	if (offset + block->size + XV_ALIGN == PAGE_SIZE)
+		tmpblock = NULL;
+
+	/* Merge next block if its free */
+	if (tmpblock && test_flag(tmpblock, BLOCK_FREE)) {
+		/*
+		 * Blocks smaller than XV_MIN_ALLOC_SIZE
+		 * are not inserted in any free list.
+		 */
+		if (tmpblock->size >= XV_MIN_ALLOC_SIZE) {
+			remove_block(pool, page,
+				    offset + block->size + XV_ALIGN, tmpblock,
+				    get_index_for_insert(tmpblock->size));
+		}
+		block->size += tmpblock->size + XV_ALIGN;
+	}
+
+	/* Merge previous block if its free */
+	if (test_flag(block, PREV_FREE)) {
+		tmpblock = (struct block_header *)((char *)(page_start) +
+						get_blockprev(block));
+		offset = offset - tmpblock->size - XV_ALIGN;
+
+		if (tmpblock->size >= XV_MIN_ALLOC_SIZE)
+			remove_block(pool, page, offset, tmpblock,
+				    get_index_for_insert(tmpblock->size));
+
+		tmpblock->size += block->size + XV_ALIGN;
+		block = tmpblock;
+	}
+
+	/* No used objects in this page. Free it. */
+	if (block->size == PAGE_SIZE - XV_ALIGN) {
+		put_ptr_atomic(page_start, KM_USER0);
+		spin_unlock(&pool->lock);
+
+		__free_page(page);
+		stat_dec(&pool->total_pages);
+		return;
+	}
+
+	set_flag(block, BLOCK_FREE);
+	if (block->size >= XV_MIN_ALLOC_SIZE)
+		insert_block(pool, page, offset, block);
+
+	if (offset + block->size + XV_ALIGN != PAGE_SIZE) {
+		tmpblock = BLOCK_NEXT(block);
+		set_flag(tmpblock, PREV_FREE);
+		set_blockprev(tmpblock, offset);
+	}
+
+	put_ptr_atomic(page_start, KM_USER0);
+	spin_unlock(&pool->lock);
+}
+
+u32 xv_get_object_size(void *obj)
+{
+	struct block_header *blk;
+
+	blk = (struct block_header *)((char *)(obj) - XV_ALIGN);
+	return blk->size;
+}
+
+/*
+ * Returns total memory used by allocator (userdata + metadata)
+ */
+u64 xv_get_total_size_bytes(struct xv_pool *pool)
+{
+	return pool->total_pages << PAGE_SHIFT;
+}
diff --git a/drivers/staging/zram/xvmalloc.h b/drivers/staging/zram/xvmalloc.h
new file mode 100644
index 00000000000..5b1a81aa5fa
--- /dev/null
+++ b/drivers/staging/zram/xvmalloc.h
@@ -0,0 +1,30 @@
+/*
+ * xvmalloc memory allocator
+ *
+ * Copyright (C) 2008, 2009, 2010  Nitin Gupta
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the licence that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ */
+
+#ifndef _XV_MALLOC_H_
+#define _XV_MALLOC_H_
+
+#include <linux/types.h>
+
+struct xv_pool;
+
+struct xv_pool *xv_create_pool(void);
+void xv_destroy_pool(struct xv_pool *pool);
+
+int xv_malloc(struct xv_pool *pool, u32 size, struct page **page,
+			u32 *offset, gfp_t flags);
+void xv_free(struct xv_pool *pool, struct page *page, u32 offset);
+
+u32 xv_get_object_size(void *obj);
+u64 xv_get_total_size_bytes(struct xv_pool *pool);
+
+#endif
diff --git a/drivers/staging/zram/xvmalloc_int.h b/drivers/staging/zram/xvmalloc_int.h
new file mode 100644
index 00000000000..e23ed5c8b8e
--- /dev/null
+++ b/drivers/staging/zram/xvmalloc_int.h
@@ -0,0 +1,86 @@
+/*
+ * xvmalloc memory allocator
+ *
+ * Copyright (C) 2008, 2009, 2010  Nitin Gupta
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the licence that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ */
+
+#ifndef _XV_MALLOC_INT_H_
+#define _XV_MALLOC_INT_H_
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+/* User configurable params */
+
+/* Must be power of two */
+#define XV_ALIGN_SHIFT	2
+#define XV_ALIGN	(1 << XV_ALIGN_SHIFT)
+#define XV_ALIGN_MASK	(XV_ALIGN - 1)
+
+/* This must be greater than sizeof(link_free) */
+#define XV_MIN_ALLOC_SIZE	32
+#define XV_MAX_ALLOC_SIZE	(PAGE_SIZE - XV_ALIGN)
+
+/* Free lists are separated by FL_DELTA bytes */
+#define FL_DELTA_SHIFT	3
+#define FL_DELTA	(1 << FL_DELTA_SHIFT)
+#define FL_DELTA_MASK	(FL_DELTA - 1)
+#define NUM_FREE_LISTS	((XV_MAX_ALLOC_SIZE - XV_MIN_ALLOC_SIZE) \
+				/ FL_DELTA + 1)
+
+#define MAX_FLI		DIV_ROUND_UP(NUM_FREE_LISTS, BITS_PER_LONG)
+
+/* End of user params */
+
+enum blockflags {
+	BLOCK_FREE,
+	PREV_FREE,
+	__NR_BLOCKFLAGS,
+};
+
+#define FLAGS_MASK	XV_ALIGN_MASK
+#define PREV_MASK	(~FLAGS_MASK)
+
+struct freelist_entry {
+	struct page *page;
+	u16 offset;
+	u16 pad;
+};
+
+struct link_free {
+	struct page *prev_page;
+	struct page *next_page;
+	u16 prev_offset;
+	u16 next_offset;
+};
+
+struct block_header {
+	union {
+		/* This common header must be XV_ALIGN bytes */
+		u8 common[XV_ALIGN];
+		struct {
+			u16 size;
+			u16 prev;
+		};
+	};
+	struct link_free link;
+};
+
+struct xv_pool {
+	ulong flbitmap;
+	ulong slbitmap[MAX_FLI];
+	spinlock_t lock;
+
+	struct freelist_entry freelist[NUM_FREE_LISTS];
+
+	/* stats */
+	u64 total_pages;
+};
+
+#endif
diff --git a/drivers/staging/zram/zram.txt b/drivers/staging/zram/zram.txt
new file mode 100644
index 00000000000..9694acfeb43
--- /dev/null
+++ b/drivers/staging/zram/zram.txt
@@ -0,0 +1,51 @@
+ramzswap: Compressed RAM based swap device
+-------------------------------------------
+
+Project home: http://compcache.googlecode.com/
+
+* Introduction
+
+The ramzswap module creates RAM based block devices which can (only) be used as
+swap disks. Pages swapped to these devices are compressed and stored in memory
+itself. See project home for use cases, performance numbers and a lot more.
+
+Individual ramzswap devices are configured and initialized using rzscontrol
+userspace utility as shown in examples below. See rzscontrol man page for more
+details.
+
+* Usage
+
+Following shows a typical sequence of steps for using ramzswap.
+
+1) Load Modules:
+	modprobe ramzswap num_devices=4
+	This creates 4 (uninitialized) devices: /dev/ramzswap{0,1,2,3}
+	(num_devices parameter is optional. Default: 1)
+
+2) Initialize:
+	Use rzscontrol utility to configure and initialize individual
+	ramzswap devices. Example:
+	rzscontrol /dev/ramzswap2 --init # uses default value of disksize_kb
+
+	*See rzscontrol man page for more details and examples*
+
+3) Activate:
+	swapon /dev/ramzswap2 # or any other initialized ramzswap device
+
+4) Stats:
+	rzscontrol /dev/ramzswap2 --stats
+
+5) Deactivate:
+	swapoff /dev/ramzswap2
+
+6) Reset:
+	rzscontrol /dev/ramzswap2 --reset
+	(This frees all the memory allocated for this device).
+
+
+Please report any problems at:
+ - Mailing list: linux-mm-cc at laptop dot org
+ - Issue tracker: http://code.google.com/p/compcache/issues/list
+
+Nitin Gupta
+ngupta@vflare.org
diff --git a/drivers/staging/zram/zram_drv.c b/drivers/staging/zram/zram_drv.c
new file mode 100644
index 00000000000..e9b064c2148
--- /dev/null
+++ b/drivers/staging/zram/zram_drv.c
@@ -0,0 +1,805 @@
+/*
+ * Compressed RAM based swap device
+ *
+ * Copyright (C) 2008, 2009, 2010  Nitin Gupta
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the licence that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ *
+ * Project home: http://compcache.googlecode.com
+ */
+
+#define KMSG_COMPONENT "ramzswap"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/device.h>
+#include <linux/genhd.h>
+#include <linux/highmem.h>
+#include <linux/slab.h>
+#include <linux/lzo.h>
+#include <linux/string.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/vmalloc.h>
+
+#include "zram_drv.h"
+
+/* Globals */
+static int ramzswap_major;
+static struct ramzswap *devices;
+
+/* Module params (documentation at end) */
+static unsigned int num_devices;
+
+static int rzs_test_flag(struct ramzswap *rzs, u32 index,
+			enum rzs_pageflags flag)
+{
+	return rzs->table[index].flags & BIT(flag);
+}
+
+static void rzs_set_flag(struct ramzswap *rzs, u32 index,
+			enum rzs_pageflags flag)
+{
+	rzs->table[index].flags |= BIT(flag);
+}
+
+static void rzs_clear_flag(struct ramzswap *rzs, u32 index,
+			enum rzs_pageflags flag)
+{
+	rzs->table[index].flags &= ~BIT(flag);
+}
+
+static int page_zero_filled(void *ptr)
+{
+	unsigned int pos;
+	unsigned long *page;
+
+	page = (unsigned long *)ptr;
+
+	for (pos = 0; pos != PAGE_SIZE / sizeof(*page); pos++) {
+		if (page[pos])
+			return 0;
+	}
+
+	return 1;
+}
+
+static void ramzswap_set_disksize(struct ramzswap *rzs, size_t totalram_bytes)
+{
+	if (!rzs->disksize) {
+		pr_info(
+		"disk size not provided. You can use disksize_kb module "
+		"param to specify size.\nUsing default: (%u%% of RAM).\n",
+		default_disksize_perc_ram
+		);
+		rzs->disksize = default_disksize_perc_ram *
+					(totalram_bytes / 100);
+	}
+
+	if (rzs->disksize > 2 * (totalram_bytes)) {
+		pr_info(
+		"There is little point creating a ramzswap of greater than "
+		"twice the size of memory since we expect a 2:1 compression "
+		"ratio. Note that ramzswap uses about 0.1%% of the size of "
+		"the swap device when not in use so a huge ramzswap is "
+		"wasteful.\n"
+		"\tMemory Size: %zu kB\n"
+		"\tSize you selected: %zu kB\n"
+		"Continuing anyway ...\n",
+		totalram_bytes >> 10, rzs->disksize
+		);
+	}
+
+	rzs->disksize &= PAGE_MASK;
+}
+
+static void ramzswap_ioctl_get_stats(struct ramzswap *rzs,
+			struct ramzswap_ioctl_stats *s)
+{
+	s->disksize = rzs->disksize;
+
+#if defined(CONFIG_RAMZSWAP_STATS)
+	{
+	struct ramzswap_stats *rs = &rzs->stats;
+	size_t succ_writes, mem_used;
+	unsigned int good_compress_perc = 0, no_compress_perc = 0;
+
+	mem_used = xv_get_total_size_bytes(rzs->mem_pool)
+			+ (rs->pages_expand << PAGE_SHIFT);
+	succ_writes = rzs_stat64_read(rzs, &rs->num_writes) -
+			rzs_stat64_read(rzs, &rs->failed_writes);
+
+	if (succ_writes && rs->pages_stored) {
+		good_compress_perc = rs->good_compress * 100
+					/ rs->pages_stored;
+		no_compress_perc = rs->pages_expand * 100
+					/ rs->pages_stored;
+	}
+
+	s->num_reads = rzs_stat64_read(rzs, &rs->num_reads);
+	s->num_writes = rzs_stat64_read(rzs, &rs->num_writes);
+	s->failed_reads = rzs_stat64_read(rzs, &rs->failed_reads);
+	s->failed_writes = rzs_stat64_read(rzs, &rs->failed_writes);
+	s->invalid_io = rzs_stat64_read(rzs, &rs->invalid_io);
+	s->notify_free = rzs_stat64_read(rzs, &rs->notify_free);
+	s->pages_zero = rs->pages_zero;
+
+	s->good_compress_pct = good_compress_perc;
+	s->pages_expand_pct = no_compress_perc;
+
+	s->pages_stored = rs->pages_stored;
+	s->pages_used = mem_used >> PAGE_SHIFT;
+	s->orig_data_size = rs->pages_stored << PAGE_SHIFT;
+	s->compr_data_size = rs->compr_size;
+	s->mem_used_total = mem_used;
+	}
+#endif /* CONFIG_RAMZSWAP_STATS */
+}
+
+static void ramzswap_free_page(struct ramzswap *rzs, size_t index)
+{
+	u32 clen;
+	void *obj;
+
+	struct page *page = rzs->table[index].page;
+	u32 offset = rzs->table[index].offset;
+
+	if (unlikely(!page)) {
+		/*
+		 * No memory is allocated for zero filled pages.
+		 * Simply clear zero page flag.
+		 */
+		if (rzs_test_flag(rzs, index, RZS_ZERO)) {
+			rzs_clear_flag(rzs, index, RZS_ZERO);
+			rzs_stat_dec(&rzs->stats.pages_zero);
+		}
+		return;
+	}
+
+	if (unlikely(rzs_test_flag(rzs, index, RZS_UNCOMPRESSED))) {
+		clen = PAGE_SIZE;
+		__free_page(page);
+		rzs_clear_flag(rzs, index, RZS_UNCOMPRESSED);
+		rzs_stat_dec(&rzs->stats.pages_expand);
+		goto out;
+	}
+
+	obj = kmap_atomic(page, KM_USER0) + offset;
+	clen = xv_get_object_size(obj) - sizeof(struct zobj_header);
+	kunmap_atomic(obj, KM_USER0);
+
+	xv_free(rzs->mem_pool, page, offset);
+	if (clen <= PAGE_SIZE / 2)
+		rzs_stat_dec(&rzs->stats.good_compress);
+
+out:
+	rzs->stats.compr_size -= clen;
+	rzs_stat_dec(&rzs->stats.pages_stored);
+
+	rzs->table[index].page = NULL;
+	rzs->table[index].offset = 0;
+}
+
+static void handle_zero_page(struct page *page)
+{
+	void *user_mem;
+
+	user_mem = kmap_atomic(page, KM_USER0);
+	memset(user_mem, 0, PAGE_SIZE);
+	kunmap_atomic(user_mem, KM_USER0);
+
+	flush_dcache_page(page);
+}
+
+static void handle_uncompressed_page(struct ramzswap *rzs,
+				struct page *page, u32 index)
+{
+	unsigned char *user_mem, *cmem;
+
+	user_mem = kmap_atomic(page, KM_USER0);
+	cmem = kmap_atomic(rzs->table[index].page, KM_USER1) +
+			rzs->table[index].offset;
+
+	memcpy(user_mem, cmem, PAGE_SIZE);
+	kunmap_atomic(user_mem, KM_USER0);
+	kunmap_atomic(cmem, KM_USER1);
+
+	flush_dcache_page(page);
+}
+
+static int ramzswap_read(struct ramzswap *rzs, struct bio *bio)
+{
+
+	int i;
+	u32 index;
+	struct bio_vec *bvec;
+
+	rzs_stat64_inc(rzs, &rzs->stats.num_reads);
+
+	index = bio->bi_sector >> SECTORS_PER_PAGE_SHIFT;
+	bio_for_each_segment(bvec, bio, i) {
+		int ret;
+		size_t clen;
+		struct page *page;
+		struct zobj_header *zheader;
+		unsigned char *user_mem, *cmem;
+
+		page = bvec->bv_page;
+
+		if (rzs_test_flag(rzs, index, RZS_ZERO)) {
+			handle_zero_page(page);
+			continue;
+		}
+
+		/* Requested page is not present in compressed area */
+		if (unlikely(!rzs->table[index].page)) {
+			pr_debug("Read before write: sector=%lu, size=%u",
+				(ulong)(bio->bi_sector), bio->bi_size);
+			/* Do nothing */
+			continue;
+		}
+
+		/* Page is stored uncompressed since it's incompressible */
+		if (unlikely(rzs_test_flag(rzs, index, RZS_UNCOMPRESSED))) {
+			handle_uncompressed_page(rzs, page, index);
+			continue;
+		}
+
+		user_mem = kmap_atomic(page, KM_USER0);
+		clen = PAGE_SIZE;
+
+		cmem = kmap_atomic(rzs->table[index].page, KM_USER1) +
+				rzs->table[index].offset;
+
+		ret = lzo1x_decompress_safe(
+			cmem + sizeof(*zheader),
+			xv_get_object_size(cmem) - sizeof(*zheader),
+			user_mem, &clen);
+
+		kunmap_atomic(user_mem, KM_USER0);
+		kunmap_atomic(cmem, KM_USER1);
+
+		/* Should NEVER happen. Return bio error if it does. */
+		if (unlikely(ret != LZO_E_OK)) {
+			pr_err("Decompression failed! err=%d, page=%u\n",
+				ret, index);
+			rzs_stat64_inc(rzs, &rzs->stats.failed_reads);
+			goto out;
+		}
+
+		flush_dcache_page(page);
+		index++;
+	}
+
+	set_bit(BIO_UPTODATE, &bio->bi_flags);
+	bio_endio(bio, 0);
+	return 0;
+
+out:
+	bio_io_error(bio);
+	return 0;
+}
+
+static int ramzswap_write(struct ramzswap *rzs, struct bio *bio)
+{
+	int i;
+	u32 index;
+	struct bio_vec *bvec;
+
+	rzs_stat64_inc(rzs, &rzs->stats.num_writes);
+
+	index = bio->bi_sector >> SECTORS_PER_PAGE_SHIFT;
+
+	bio_for_each_segment(bvec, bio, i) {
+		int ret;
+		u32 offset;
+		size_t clen;
+		struct zobj_header *zheader;
+		struct page *page, *page_store;
+		unsigned char *user_mem, *cmem, *src;
+
+		page = bvec->bv_page;
+		src = rzs->compress_buffer;
+
+		/*
+		 * System overwrites unused sectors. Free memory associated
+		 * with this sector now.
+		 */
+		if (rzs->table[index].page ||
+				rzs_test_flag(rzs, index, RZS_ZERO))
+			ramzswap_free_page(rzs, index);
+
+		mutex_lock(&rzs->lock);
+
+		user_mem = kmap_atomic(page, KM_USER0);
+		if (page_zero_filled(user_mem)) {
+			kunmap_atomic(user_mem, KM_USER0);
+			mutex_unlock(&rzs->lock);
+			rzs_stat_inc(&rzs->stats.pages_zero);
+			rzs_set_flag(rzs, index, RZS_ZERO);
+			continue;
+		}
+
+		ret = lzo1x_1_compress(user_mem, PAGE_SIZE, src, &clen,
+					rzs->compress_workmem);
+
+		kunmap_atomic(user_mem, KM_USER0);
+
+		if (unlikely(ret != LZO_E_OK)) {
+			mutex_unlock(&rzs->lock);
+			pr_err("Compression failed! err=%d\n", ret);
+			rzs_stat64_inc(rzs, &rzs->stats.failed_writes);
+			goto out;
+		}
+
+		/*
+		 * Page is incompressible. Store it as-is (uncompressed)
+		 * since we do not want to return too many swap write
+		 * errors which has side effect of hanging the system.
+		 */
+		if (unlikely(clen > max_zpage_size)) {
+			clen = PAGE_SIZE;
+			page_store = alloc_page(GFP_NOIO | __GFP_HIGHMEM);
+			if (unlikely(!page_store)) {
+				mutex_unlock(&rzs->lock);
+				pr_info("Error allocating memory for "
+					"incompressible page: %u\n", index);
+				rzs_stat64_inc(rzs, &rzs->stats.failed_writes);
+				goto out;
+			}
+
+			offset = 0;
+			rzs_set_flag(rzs, index, RZS_UNCOMPRESSED);
+			rzs_stat_inc(&rzs->stats.pages_expand);
+			rzs->table[index].page = page_store;
+			src = kmap_atomic(page, KM_USER0);
+			goto memstore;
+		}
+
+		if (xv_malloc(rzs->mem_pool, clen + sizeof(*zheader),
+				&rzs->table[index].page, &offset,
+				GFP_NOIO | __GFP_HIGHMEM)) {
+			mutex_unlock(&rzs->lock);
+			pr_info("Error allocating memory for compressed "
+				"page: %u, size=%zu\n", index, clen);
+			rzs_stat64_inc(rzs, &rzs->stats.failed_writes);
+			goto out;
+		}
+
+memstore:
+		rzs->table[index].offset = offset;
+
+		cmem = kmap_atomic(rzs->table[index].page, KM_USER1) +
+				rzs->table[index].offset;
+
+#if 0
+		/* Back-reference needed for memory defragmentation */
+		if (!rzs_test_flag(rzs, index, RZS_UNCOMPRESSED)) {
+			zheader = (struct zobj_header *)cmem;
+			zheader->table_idx = index;
+			cmem += sizeof(*zheader);
+		}
+#endif
+
+		memcpy(cmem, src, clen);
+
+		kunmap_atomic(cmem, KM_USER1);
+		if (unlikely(rzs_test_flag(rzs, index, RZS_UNCOMPRESSED)))
+			kunmap_atomic(src, KM_USER0);
+
+		/* Update stats */
+		rzs->stats.compr_size += clen;
+		rzs_stat_inc(&rzs->stats.pages_stored);
+		if (clen <= PAGE_SIZE / 2)
+			rzs_stat_inc(&rzs->stats.good_compress);
+
+		mutex_unlock(&rzs->lock);
+		index++;
+	}
+
+	set_bit(BIO_UPTODATE, &bio->bi_flags);
+	bio_endio(bio, 0);
+	return 0;
+
+out:
+	bio_io_error(bio);
+	return 0;
+}
+
+/*
+ * Check if request is within bounds and page aligned.
+ */
+static inline int valid_io_request(struct ramzswap *rzs, struct bio *bio)
+{
+	if (unlikely(
+		(bio->bi_sector >= (rzs->disksize >> SECTOR_SHIFT)) ||
+		(bio->bi_sector & (SECTORS_PER_PAGE - 1)) ||
+		(bio->bi_size & (PAGE_SIZE - 1)))) {
+
+		return 0;
+	}
+
+	/* I/O request is valid */
+	return 1;
+}
+
+/*
+ * Handler function for all ramzswap I/O requests.
+ */
+static int ramzswap_make_request(struct request_queue *queue, struct bio *bio)
+{
+	int ret = 0;
+	struct ramzswap *rzs = queue->queuedata;
+
+	if (unlikely(!rzs->init_done)) {
+		bio_io_error(bio);
+		return 0;
+	}
+
+	if (!valid_io_request(rzs, bio)) {
+		rzs_stat64_inc(rzs, &rzs->stats.invalid_io);
+		bio_io_error(bio);
+		return 0;
+	}
+
+	switch (bio_data_dir(bio)) {
+	case READ:
+		ret = ramzswap_read(rzs, bio);
+		break;
+
+	case WRITE:
+		ret = ramzswap_write(rzs, bio);
+		break;
+	}
+
+	return ret;
+}
+
+static void reset_device(struct ramzswap *rzs)
+{
+	size_t index;
+
+	/* Do not accept any new I/O request */
+	rzs->init_done = 0;
+
+	/* Free various per-device buffers */
+	kfree(rzs->compress_workmem);
+	free_pages((unsigned long)rzs->compress_buffer, 1);
+
+	rzs->compress_workmem = NULL;
+	rzs->compress_buffer = NULL;
+
+	/* Free all pages that are still in this ramzswap device */
+	for (index = 0; index < rzs->disksize >> PAGE_SHIFT; index++) {
+		struct page *page;
+		u16 offset;
+
+		page = rzs->table[index].page;
+		offset = rzs->table[index].offset;
+
+		if (!page)
+			continue;
+
+		if (unlikely(rzs_test_flag(rzs, index, RZS_UNCOMPRESSED)))
+			__free_page(page);
+		else
+			xv_free(rzs->mem_pool, page, offset);
+	}
+
+	vfree(rzs->table);
+	rzs->table = NULL;
+
+	xv_destroy_pool(rzs->mem_pool);
+	rzs->mem_pool = NULL;
+
+	/* Reset stats */
+	memset(&rzs->stats, 0, sizeof(rzs->stats));
+
+	rzs->disksize = 0;
+}
+
+static int ramzswap_ioctl_init_device(struct ramzswap *rzs)
+{
+	int ret;
+	size_t num_pages;
+
+	if (rzs->init_done) {
+		pr_info("Device already initialized!\n");
+		return -EBUSY;
+	}
+
+	ramzswap_set_disksize(rzs, totalram_pages << PAGE_SHIFT);
+
+	rzs->compress_workmem = kzalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
+	if (!rzs->compress_workmem) {
+		pr_err("Error allocating compressor working memory!\n");
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	rzs->compress_buffer = (void *)__get_free_pages(__GFP_ZERO, 1);
+	if (!rzs->compress_buffer) {
+		pr_err("Error allocating compressor buffer space\n");
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	num_pages = rzs->disksize >> PAGE_SHIFT;
+	rzs->table = vmalloc(num_pages * sizeof(*rzs->table));
+	if (!rzs->table) {
+		pr_err("Error allocating ramzswap address table\n");
+		/* To prevent accessing table entries during cleanup */
+		rzs->disksize = 0;
+		ret = -ENOMEM;
+		goto fail;
+	}
+	memset(rzs->table, 0, num_pages * sizeof(*rzs->table));
+
+	set_capacity(rzs->disk, rzs->disksize >> SECTOR_SHIFT);
+
+	/* ramzswap devices sort of resembles non-rotational disks */
+	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, rzs->disk->queue);
+
+	rzs->mem_pool = xv_create_pool();
+	if (!rzs->mem_pool) {
+		pr_err("Error creating memory pool\n");
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	rzs->init_done = 1;
+
+	pr_debug("Initialization done!\n");
+	return 0;
+
+fail:
+	reset_device(rzs);
+
+	pr_err("Initialization failed: err=%d\n", ret);
+	return ret;
+}
+
+static int ramzswap_ioctl_reset_device(struct ramzswap *rzs)
+{
+	if (rzs->init_done)
+		reset_device(rzs);
+
+	return 0;
+}
+
+static int ramzswap_ioctl(struct block_device *bdev, fmode_t mode,
+			unsigned int cmd, unsigned long arg)
+{
+	int ret = 0;
+	size_t disksize_kb;
+
+	struct ramzswap *rzs = bdev->bd_disk->private_data;
+
+	switch (cmd) {
+	case RZSIO_SET_DISKSIZE_KB:
+		if (rzs->init_done) {
+			ret = -EBUSY;
+			goto out;
+		}
+		if (copy_from_user(&disksize_kb, (void *)arg,
+						_IOC_SIZE(cmd))) {
+			ret = -EFAULT;
+			goto out;
+		}
+		rzs->disksize = disksize_kb << 10;
+		pr_info("Disk size set to %zu kB\n", disksize_kb);
+		break;
+
+	case RZSIO_GET_STATS:
+	{
+		struct ramzswap_ioctl_stats *stats;
+		if (!rzs->init_done) {
+			ret = -ENOTTY;
+			goto out;
+		}
+		stats = kzalloc(sizeof(*stats), GFP_KERNEL);
+		if (!stats) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		ramzswap_ioctl_get_stats(rzs, stats);
+		if (copy_to_user((void *)arg, stats, sizeof(*stats))) {
+			kfree(stats);
+			ret = -EFAULT;
+			goto out;
+		}
+		kfree(stats);
+		break;
+	}
+	case RZSIO_INIT:
+		ret = ramzswap_ioctl_init_device(rzs);
+		break;
+
+	case RZSIO_RESET:
+		/* Do not reset an active device! */
+		if (bdev->bd_holders) {
+			ret = -EBUSY;
+			goto out;
+		}
+
+		/* Make sure all pending I/O is finished */
+		if (bdev)
+			fsync_bdev(bdev);
+
+		ret = ramzswap_ioctl_reset_device(rzs);
+		break;
+
+	default:
+		pr_info("Invalid ioctl %u\n", cmd);
+		ret = -ENOTTY;
+	}
+
+out:
+	return ret;
+}
+
+void ramzswap_slot_free_notify(struct block_device *bdev, unsigned long index)
+{
+	struct ramzswap *rzs;
+
+	rzs = bdev->bd_disk->private_data;
+	ramzswap_free_page(rzs, index);
+	rzs_stat64_inc(rzs, &rzs->stats.notify_free);
+}
+
+static const struct block_device_operations ramzswap_devops = {
+	.ioctl = ramzswap_ioctl,
+	.swap_slot_free_notify = ramzswap_slot_free_notify,
+	.owner = THIS_MODULE
+};
+
+static int create_device(struct ramzswap *rzs, int device_id)
+{
+	int ret = 0;
+
+	mutex_init(&rzs->lock);
+	spin_lock_init(&rzs->stat64_lock);
+
+	rzs->queue = blk_alloc_queue(GFP_KERNEL);
+	if (!rzs->queue) {
+		pr_err("Error allocating disk queue for device %d\n",
+			device_id);
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	blk_queue_make_request(rzs->queue, ramzswap_make_request);
+	rzs->queue->queuedata = rzs;
+
+	 /* gendisk structure */
+	rzs->disk = alloc_disk(1);
+	if (!rzs->disk) {
+		blk_cleanup_queue(rzs->queue);
+		pr_warning("Error allocating disk structure for device %d\n",
+			device_id);
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	rzs->disk->major = ramzswap_major;
+	rzs->disk->first_minor = device_id;
+	rzs->disk->fops = &ramzswap_devops;
+	rzs->disk->queue = rzs->queue;
+	rzs->disk->private_data = rzs;
+	snprintf(rzs->disk->disk_name, 16, "ramzswap%d", device_id);
+
+	/* Actual capacity set using RZSIO_SET_DISKSIZE_KB ioctl */
+	set_capacity(rzs->disk, 0);
+
+	/*
+	 * To ensure that we always get PAGE_SIZE aligned
+	 * and n*PAGE_SIZED sized I/O requests.
+	 */
+	blk_queue_physical_block_size(rzs->disk->queue, PAGE_SIZE);
+	blk_queue_logical_block_size(rzs->disk->queue, PAGE_SIZE);
+	blk_queue_io_min(rzs->disk->queue, PAGE_SIZE);
+	blk_queue_io_opt(rzs->disk->queue, PAGE_SIZE);
+
+	add_disk(rzs->disk);
+
+	rzs->init_done = 0;
+
+out:
+	return ret;
+}
+
+static void destroy_device(struct ramzswap *rzs)
+{
+	if (rzs->disk) {
+		del_gendisk(rzs->disk);
+		put_disk(rzs->disk);
+	}
+
+	if (rzs->queue)
+		blk_cleanup_queue(rzs->queue);
+}
+
+static int __init ramzswap_init(void)
+{
+	int ret, dev_id;
+
+	if (num_devices > max_num_devices) {
+		pr_warning("Invalid value for num_devices: %u\n",
+				num_devices);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ramzswap_major = register_blkdev(0, "ramzswap");
+	if (ramzswap_major <= 0) {
+		pr_warning("Unable to get major number\n");
+		ret = -EBUSY;
+		goto out;
+	}
+
+	if (!num_devices) {
+		pr_info("num_devices not specified. Using default: 1\n");
+		num_devices = 1;
+	}
+
+	/* Allocate the device array and initialize each one */
+	pr_info("Creating %u devices ...\n", num_devices);
+	devices = kzalloc(num_devices * sizeof(struct ramzswap), GFP_KERNEL);
+	if (!devices) {
+		ret = -ENOMEM;
+		goto unregister;
+	}
+
+	for (dev_id = 0; dev_id < num_devices; dev_id++) {
+		ret = create_device(&devices[dev_id], dev_id);
+		if (ret)
+			goto free_devices;
+	}
+
+	return 0;
+
+free_devices:
+	while (dev_id)
+		destroy_device(&devices[--dev_id]);
+unregister:
+	unregister_blkdev(ramzswap_major, "ramzswap");
+out:
+	return ret;
+}
+
+static void __exit ramzswap_exit(void)
+{
+	int i;
+	struct ramzswap *rzs;
+
+	for (i = 0; i < num_devices; i++) {
+		rzs = &devices[i];
+
+		destroy_device(rzs);
+		if (rzs->init_done)
+			reset_device(rzs);
+	}
+
+	unregister_blkdev(ramzswap_major, "ramzswap");
+
+	kfree(devices);
+	pr_debug("Cleanup done!\n");
+}
+
+module_param(num_devices, uint, 0);
+MODULE_PARM_DESC(num_devices, "Number of ramzswap devices");
+
+module_init(ramzswap_init);
+module_exit(ramzswap_exit);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");
+MODULE_DESCRIPTION("Compressed RAM Based Swap Device");
diff --git a/drivers/staging/zram/zram_drv.h b/drivers/staging/zram/zram_drv.h
new file mode 100644
index 00000000000..4d2e48a2347
--- /dev/null
+++ b/drivers/staging/zram/zram_drv.h
@@ -0,0 +1,168 @@
+/*
+ * Compressed RAM based swap device
+ *
+ * Copyright (C) 2008, 2009, 2010  Nitin Gupta
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the licence that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ *
+ * Project home: http://compcache.googlecode.com
+ */
+
+#ifndef _RAMZSWAP_DRV_H_
+#define _RAMZSWAP_DRV_H_
+
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+
+#include "zram_ioctl.h"
+#include "xvmalloc.h"
+
+/*
+ * Some arbitrary value. This is just to catch
+ * invalid value for num_devices module parameter.
+ */
+static const unsigned max_num_devices = 32;
+
+/*
+ * Stored at beginning of each compressed object.
+ *
+ * It stores back-reference to table entry which points to this
+ * object. This is required to support memory defragmentation.
+ */
+struct zobj_header {
+#if 0
+	u32 table_idx;
+#endif
+};
+
+/*-- Configurable parameters */
+
+/* Default ramzswap disk size: 25% of total RAM */
+static const unsigned default_disksize_perc_ram = 25;
+
+/*
+ * Pages that compress to size greater than this are stored
+ * uncompressed in memory.
+ */
+static const unsigned max_zpage_size = PAGE_SIZE / 4 * 3;
+
+/*
+ * NOTE: max_zpage_size must be less than or equal to:
+ *   XV_MAX_ALLOC_SIZE - sizeof(struct zobj_header)
+ * otherwise, xv_malloc() would always return failure.
+ */
+
+/*-- End of configurable params */
+
+#define SECTOR_SHIFT		9
+#define SECTOR_SIZE		(1 << SECTOR_SHIFT)
+#define SECTORS_PER_PAGE_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
+#define SECTORS_PER_PAGE	(1 << SECTORS_PER_PAGE_SHIFT)
+
+/* Flags for ramzswap pages (table[page_no].flags) */
+enum rzs_pageflags {
+	/* Page is stored uncompressed */
+	RZS_UNCOMPRESSED,
+
+	/* Page consists entirely of zeros */
+	RZS_ZERO,
+
+	__NR_RZS_PAGEFLAGS,
+};
+
+/*-- Data structures */
+
+/*
+ * Allocated for each swap slot, indexed by page no.
+ * These table entries must fit exactly in a page.
+ */
+struct table {
+	struct page *page;
+	u16 offset;
+	u8 count;	/* object ref count (not yet used) */
+	u8 flags;
+} __attribute__((aligned(4)));
+
+struct ramzswap_stats {
+	/* basic stats */
+	size_t compr_size;	/* compressed size of pages stored -
+				 * needed to enforce memlimit */
+	/* more stats */
+#if defined(CONFIG_RAMZSWAP_STATS)
+	u64 num_reads;		/* failed + successful */
+	u64 num_writes;		/* --do-- */
+	u64 failed_reads;	/* should NEVER! happen */
+	u64 failed_writes;	/* can happen when memory is too low */
+	u64 invalid_io;		/* non-swap I/O requests */
+	u64 notify_free;	/* no. of swap slot free notifications */
+	u32 pages_zero;		/* no. of zero filled pages */
+	u32 pages_stored;	/* no. of pages currently stored */
+	u32 good_compress;	/* % of pages with compression ratio<=50% */
+	u32 pages_expand;	/* % of incompressible pages */
+#endif
+};
+
+struct ramzswap {
+	struct xv_pool *mem_pool;
+	void *compress_workmem;
+	void *compress_buffer;
+	struct table *table;
+	spinlock_t stat64_lock;	/* protect 64-bit stats */
+	struct mutex lock;	/* protect compression buffers against
+				 * concurrent writes */
+	struct request_queue *queue;
+	struct gendisk *disk;
+	int init_done;
+	/*
+	 * This is limit on amount of *uncompressed* worth of data
+	 * we can hold. When backing swap device is provided, it is
+	 * set equal to device size.
+	 */
+	size_t disksize;	/* bytes */
+
+	struct ramzswap_stats stats;
+};
+
+/*-- */
+
+/* Debugging and Stats */
+#if defined(CONFIG_RAMZSWAP_STATS)
+static void rzs_stat_inc(u32 *v)
+{
+	*v = *v + 1;
+}
+
+static void rzs_stat_dec(u32 *v)
+{
+	*v = *v - 1;
+}
+
+static void rzs_stat64_inc(struct ramzswap *rzs, u64 *v)
+{
+	spin_lock(&rzs->stat64_lock);
+	*v = *v + 1;
+	spin_unlock(&rzs->stat64_lock);
+}
+
+static u64 rzs_stat64_read(struct ramzswap *rzs, u64 *v)
+{
+	u64 val;
+
+	spin_lock(&rzs->stat64_lock);
+	val = *v;
+	spin_unlock(&rzs->stat64_lock);
+
+	return val;
+}
+#else
+#define rzs_stat_inc(v)
+#define rzs_stat_dec(v)
+#define rzs_stat64_inc(r, v)
+#define rzs_stat64_read(r, v)
+#endif /* CONFIG_RAMZSWAP_STATS */
+
+#endif
diff --git a/drivers/staging/zram/zram_ioctl.h b/drivers/staging/zram/zram_ioctl.h
new file mode 100644
index 00000000000..db94bcb4296
--- /dev/null
+++ b/drivers/staging/zram/zram_ioctl.h
@@ -0,0 +1,42 @@
+/*
+ * Compressed RAM based swap device
+ *
+ * Copyright (C) 2008, 2009, 2010  Nitin Gupta
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the licence that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ *
+ * Project home: http://compcache.googlecode.com
+ */
+
+#ifndef _RAMZSWAP_IOCTL_H_
+#define _RAMZSWAP_IOCTL_H_
+
+struct ramzswap_ioctl_stats {
+	u64 disksize;		/* user specified or equal to backing swap
+				 * size (if present) */
+	u64 num_reads;		/* failed + successful */
+	u64 num_writes;		/* --do-- */
+	u64 failed_reads;	/* should NEVER! happen */
+	u64 failed_writes;	/* can happen when memory is too low */
+	u64 invalid_io;		/* non-swap I/O requests */
+	u64 notify_free;	/* no. of swap slot free notifications */
+	u32 pages_zero;		/* no. of zero filled pages */
+	u32 good_compress_pct;	/* no. of pages with compression ratio<=50% */
+	u32 pages_expand_pct;	/* no. of incompressible pages */
+	u32 pages_stored;
+	u32 pages_used;
+	u64 orig_data_size;
+	u64 compr_data_size;
+	u64 mem_used_total;
+} __attribute__ ((packed, aligned(4)));
+
+#define RZSIO_SET_DISKSIZE_KB	_IOW('z', 0, size_t)
+#define RZSIO_GET_STATS		_IOR('z', 1, struct ramzswap_ioctl_stats)
+#define RZSIO_INIT		_IO('z', 2)
+#define RZSIO_RESET		_IO('z', 3)
+
+#endif