block: zram: Backport from Linux 4.1

Change-Id: I23f6f75979077992298d848efd79a6efc0d776bd

5 files changed, 603 insertions, 159 deletions

diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 6a7692281..f1ff39a3d 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -14,7 +14,7 @@
 #include <linux/wait.h>
 #include <linux/sched.h>
 
-#include <linux/zcomp.h>
+#include "zcomp.h"
 #include "zcomp_lzo.h"
 #ifdef CONFIG_ZRAM_LZ4_COMPRESS
 #include "zcomp_lz4.h"
diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
new file mode 100644
index 000000000..c59d1fca7
--- /dev/null
+++ b/drivers/block/zram/zcomp.h
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * 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.
+ */
+
+#ifndef _ZCOMP_H_
+#define _ZCOMP_H_
+
+#include <linux/mutex.h>
+
+struct zcomp_strm {
+	/* compression/decompression buffer */
+	void *buffer;
+	/*
+	 * The private data of the compression stream, only compression
+	 * stream backend can touch this (e.g. compression algorithm
+	 * working memory)
+	 */
+	void *private;
+	/* used in multi stream backend, protected by backend strm_lock */
+	struct list_head list;
+};
+
+/* static compression backend */
+struct zcomp_backend {
+	int (*compress)(const unsigned char *src, unsigned char *dst,
+			size_t *dst_len, void *private);
+
+	int (*decompress)(const unsigned char *src, size_t src_len,
+			unsigned char *dst);
+
+	void *(*create)(void);
+	void (*destroy)(void *private);
+
+	const char *name;
+};
+
+/* dynamic per-device compression frontend */
+struct zcomp {
+	void *stream;
+	struct zcomp_backend *backend;
+
+	struct zcomp_strm *(*strm_find)(struct zcomp *comp);
+	void (*strm_release)(struct zcomp *comp, struct zcomp_strm *zstrm);
+	bool (*set_max_streams)(struct zcomp *comp, int num_strm);
+	void (*destroy)(struct zcomp *comp);
+};
+
+ssize_t zcomp_available_show(const char *comp, char *buf);
+
+struct zcomp *zcomp_create(const char *comp, int max_strm);
+void zcomp_destroy(struct zcomp *comp);
+
+struct zcomp_strm *zcomp_strm_find(struct zcomp *comp);
+void zcomp_strm_release(struct zcomp *comp, struct zcomp_strm *zstrm);
+
+int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm,
+		const unsigned char *src, size_t *dst_len);
+
+int zcomp_decompress(struct zcomp *comp, const unsigned char *src,
+		size_t src_len, unsigned char *dst);
+
+bool zcomp_set_max_streams(struct zcomp *comp, int num_strm);
+#endif /* _ZCOMP_H_ */
diff --git a/drivers/block/zram/zcomp_lzo.h b/drivers/block/zram/zcomp_lzo.h
index a1cdc9eb9..128c5807f 100644
--- a/drivers/block/zram/zcomp_lzo.h
+++ b/drivers/block/zram/zcomp_lzo.h
@@ -10,7 +10,7 @@
 #ifndef _ZCOMP_LZO_H_
 #define _ZCOMP_LZO_H_
 
-#include <linux/zcomp.h>
+#include "zcomp.h"
 
 extern struct zcomp_backend zcomp_lzo;
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 167f94304..f9605860f 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -33,30 +33,40 @@
 #include <linux/vmalloc.h>
 #include <linux/err.h>
 
-#include <linux/zram_drv.h>
+#include "zram_drv.h"
 
 /* Globals */
 static int zram_major;
-struct zram *zram_devices;
+static struct zram *zram_devices;
 static const char *default_compressor = "lzo";
 
 /* Module params (documentation at end) */
 static unsigned int num_devices = 1;
 
+static inline void deprecated_attr_warn(const char *name)
+{
+	pr_warn_once("%d (%s) Attribute %s (and others) will be removed. %s\n",
+			task_pid_nr(current),
+			current->comm,
+			name,
+			"See zram documentation.");
+}
+
 #define ZRAM_ATTR_RO(name)						\
-static ssize_t zram_attr_##name##_show(struct device *d,		\
+static ssize_t name##_show(struct device *d,		\
 				struct device_attribute *attr, char *b)	\
 {									\
 	struct zram *zram = dev_to_zram(d);				\
+									\
+	deprecated_attr_warn(__stringify(name));			\
 	return scnprintf(b, PAGE_SIZE, "%llu\n",			\
 		(u64)atomic64_read(&zram->stats.name));			\
 }									\
-static struct device_attribute dev_attr_##name =			\
-	__ATTR(name, S_IRUGO, zram_attr_##name##_show, NULL);
+static DEVICE_ATTR_RO(name);
 
-static inline int init_done(struct zram *zram)
+static inline bool init_done(struct zram *zram)
 {
-	return zram->meta != NULL;
+	return zram->disksize;
 }
 
 static inline struct zram *dev_to_zram(struct device *dev)
@@ -64,6 +74,27 @@ static inline struct zram *dev_to_zram(struct device *dev)
 	return (struct zram *)dev_to_disk(dev)->private_data;
 }
 
+static ssize_t compact_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	unsigned long nr_migrated;
+	struct zram *zram = dev_to_zram(dev);
+	struct zram_meta *meta;
+
+	down_read(&zram->init_lock);
+	if (!init_done(zram)) {
+		up_read(&zram->init_lock);
+		return -EINVAL;
+	}
+
+	meta = zram->meta;
+	nr_migrated = zs_compact(meta->mem_pool);
+	atomic64_add(nr_migrated, &zram->stats.num_migrated);
+	up_read(&zram->init_lock);
+
+	return len;
+}
+
 static ssize_t disksize_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -90,6 +121,7 @@ static ssize_t orig_data_size_show(struct device *dev,
 {
 	struct zram *zram = dev_to_zram(dev);
 
+	deprecated_attr_warn("orig_data_size");
 	return scnprintf(buf, PAGE_SIZE, "%llu\n",
 		(u64)(atomic64_read(&zram->stats.pages_stored)) << PAGE_SHIFT);
 }
@@ -99,14 +131,16 @@ static ssize_t mem_used_total_show(struct device *dev,
 {
 	u64 val = 0;
 	struct zram *zram = dev_to_zram(dev);
-	struct zram_meta *meta = zram->meta;
 
+	deprecated_attr_warn("mem_used_total");
 	down_read(&zram->init_lock);
-	if (init_done(zram))
-		val = zs_get_total_size_bytes(meta->mem_pool);
+	if (init_done(zram)) {
+		struct zram_meta *meta = zram->meta;
+		val = zs_get_total_pages(meta->mem_pool);
+	}
 	up_read(&zram->init_lock);
 
-	return scnprintf(buf, PAGE_SIZE, "%llu\n", val);
+	return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
 }
 
 static ssize_t max_comp_streams_show(struct device *dev,
@@ -122,6 +156,75 @@ static ssize_t max_comp_streams_show(struct device *dev,
 	return scnprintf(buf, PAGE_SIZE, "%d\n", val);
 }
 
+static ssize_t mem_limit_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	u64 val;
+	struct zram *zram = dev_to_zram(dev);
+
+	deprecated_attr_warn("mem_limit");
+	down_read(&zram->init_lock);
+	val = zram->limit_pages;
+	up_read(&zram->init_lock);
+
+	return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
+}
+
+static ssize_t mem_limit_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	u64 limit;
+	char *tmp;
+	struct zram *zram = dev_to_zram(dev);
+
+	limit = memparse(buf, &tmp);
+	if (buf == tmp) /* no chars parsed, invalid input */
+		return -EINVAL;
+
+	down_write(&zram->init_lock);
+	zram->limit_pages = PAGE_ALIGN(limit) >> PAGE_SHIFT;
+	up_write(&zram->init_lock);
+
+	return len;
+}
+
+static ssize_t mem_used_max_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	u64 val = 0;
+	struct zram *zram = dev_to_zram(dev);
+
+	deprecated_attr_warn("mem_used_max");
+	down_read(&zram->init_lock);
+	if (init_done(zram))
+		val = atomic_long_read(&zram->stats.max_used_pages);
+	up_read(&zram->init_lock);
+
+	return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
+}
+
+static ssize_t mem_used_max_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	int err;
+	unsigned long val;
+	struct zram *zram = dev_to_zram(dev);
+
+	err = kstrtoul(buf, 10, &val);
+	if (err || val != 0)
+		return -EINVAL;
+
+	down_read(&zram->init_lock);
+	if (init_done(zram)) {
+		struct zram_meta *meta = zram->meta;
+		atomic_long_set(&zram->stats.max_used_pages,
+				zs_get_total_pages(meta->mem_pool));
+	}
+	up_read(&zram->init_lock);
+
+	return len;
+}
+
 static ssize_t max_comp_streams_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
 {
@@ -183,19 +286,32 @@ static ssize_t comp_algorithm_store(struct device *dev,
 static int zram_test_flag(struct zram_meta *meta, u32 index,
 			enum zram_pageflags flag)
 {
-	return meta->table[index].flags & BIT(flag);
+	return meta->table[index].value & BIT(flag);
 }
 
 static void zram_set_flag(struct zram_meta *meta, u32 index,
 			enum zram_pageflags flag)
 {
-	meta->table[index].flags |= BIT(flag);
+	meta->table[index].value |= BIT(flag);
 }
 
 static void zram_clear_flag(struct zram_meta *meta, u32 index,
 			enum zram_pageflags flag)
 {
-	meta->table[index].flags &= ~BIT(flag);
+	meta->table[index].value &= ~BIT(flag);
+}
+
+static size_t zram_get_obj_size(struct zram_meta *meta, u32 index)
+{
+	return meta->table[index].value & (BIT(ZRAM_FLAG_SHIFT) - 1);
+}
+
+static void zram_set_obj_size(struct zram_meta *meta,
+					u32 index, size_t size)
+{
+	unsigned long flags = meta->table[index].value >> ZRAM_FLAG_SHIFT;
+
+	meta->table[index].value = (flags << ZRAM_FLAG_SHIFT) | size;
 }
 
 static inline int is_partial_io(struct bio_vec *bvec)
@@ -206,18 +322,18 @@ static inline int is_partial_io(struct bio_vec *bvec)
 /*
  * Check if request is within bounds and aligned on zram logical blocks.
  */
-static inline int valid_io_request(struct zram *zram, struct bio *bio)
+static inline int valid_io_request(struct zram *zram,
+		sector_t start, unsigned int size)
 {
-	u64 start, end, bound;
+	u64 end, bound;
 
 	/* unaligned request */
-	if (unlikely(bio->bi_sector & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
+	if (unlikely(start & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
 		return 0;
-	if (unlikely(bio->bi_size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
+	if (unlikely(size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
 		return 0;
 
-	start = bio->bi_sector;
-	end = start + (bio->bi_size >> SECTOR_SHIFT);
+	end = start + (size >> SECTOR_SHIFT);
 	bound = zram->disksize >> SECTOR_SHIFT;
 	/* out of range range */
 	if (unlikely(start >= bound || end > bound || start > end))
@@ -227,43 +343,67 @@ static inline int valid_io_request(struct zram *zram, struct bio *bio)
 	return 1;
 }
 
-static void zram_meta_free(struct zram_meta *meta)
+static void zram_meta_free(struct zram_meta *meta, u64 disksize)
 {
+	size_t num_pages = disksize >> PAGE_SHIFT;
+	size_t index;
+
+	/* Free all pages that are still in this zram device */
+	for (index = 0; index < num_pages; index++) {
+		unsigned long handle = meta->table[index].handle;
+
+		if (!handle)
+			continue;
+
+		zs_free(meta->mem_pool, handle);
+	}
+
 	zs_destroy_pool(meta->mem_pool);
 	vfree(meta->table);
 	kfree(meta);
 }
 
-static struct zram_meta *zram_meta_alloc(u64 disksize)
+static struct zram_meta *zram_meta_alloc(int device_id, u64 disksize)
 {
 	size_t num_pages;
+	char pool_name[8];
 	struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL);
+
 	if (!meta)
-		goto out;
+		return NULL;
 
 	num_pages = disksize >> PAGE_SHIFT;
 	meta->table = vzalloc(num_pages * sizeof(*meta->table));
 	if (!meta->table) {
 		pr_err("Error allocating zram address table\n");
-		goto free_meta;
+		goto out_error;
 	}
 
-	meta->mem_pool = zs_create_pool(GFP_NOIO | __GFP_HIGHMEM);
+	snprintf(pool_name, sizeof(pool_name), "zram%d", device_id);
+	meta->mem_pool = zs_create_pool(pool_name, GFP_NOIO | __GFP_HIGHMEM);
 	if (!meta->mem_pool) {
 		pr_err("Error creating memory pool\n");
-		goto free_table;
+		goto out_error;
 	}
 
-	rwlock_init(&meta->tb_lock);
 	return meta;
 
-free_table:
+out_error:
 	vfree(meta->table);
-free_meta:
 	kfree(meta);
-	meta = NULL;
-out:
-	return meta;
+	return NULL;
+}
+
+static inline bool zram_meta_get(struct zram *zram)
+{
+	if (atomic_inc_not_zero(&zram->refcount))
+		return true;
+	return false;
+}
+
+static inline void zram_meta_put(struct zram *zram)
+{
+	atomic_dec(&zram->refcount);
 }
 
 static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
@@ -303,7 +443,12 @@ static void handle_zero_page(struct bio_vec *bvec)
 	flush_dcache_page(page);
 }
 
-/* NOTE: caller should hold meta->tb_lock with write-side */
+
+/*
+ * To protect concurrent access to the same index entry,
+ * caller should hold this table index entry's bit_spinlock to
+ * indicate this index entry is accessing.
+ */
 static void zram_free_page(struct zram *zram, size_t index)
 {
 	struct zram_meta *meta = zram->meta;
@@ -323,11 +468,12 @@ static void zram_free_page(struct zram *zram, size_t index)
 
 	zs_free(meta->mem_pool, handle);
 
-	atomic64_sub(meta->table[index].size, &zram->stats.compr_data_size);
+	atomic64_sub(zram_get_obj_size(meta, index),
+			&zram->stats.compr_data_size);
 	atomic64_dec(&zram->stats.pages_stored);
 
 	meta->table[index].handle = 0;
-	meta->table[index].size = 0;
+	zram_set_obj_size(meta, index, 0);
 }
 
 static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
@@ -336,14 +482,14 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
 	unsigned char *cmem;
 	struct zram_meta *meta = zram->meta;
 	unsigned long handle;
-	u16 size;
+	size_t size;
 
-	read_lock(&meta->tb_lock);
+	bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
 	handle = meta->table[index].handle;
-	size = meta->table[index].size;
+	size = zram_get_obj_size(meta, index);
 
 	if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) {
-		read_unlock(&meta->tb_lock);
+		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
 		clear_page(mem);
 		return 0;
 	}
@@ -354,12 +500,11 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
 	else
 		ret = zcomp_decompress(zram->comp, cmem, size, mem);
 	zs_unmap_object(meta->mem_pool, handle);
-	read_unlock(&meta->tb_lock);
+	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
 
 	/* Should NEVER happen. Return bio error if it does. */
 	if (unlikely(ret)) {
 		pr_err("Decompression failed! err=%d, page=%u\n", ret, index);
-		atomic64_inc(&zram->stats.failed_reads);
 		return ret;
 	}
 
@@ -367,7 +512,7 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
 }
 
 static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
-			  u32 index, int offset, struct bio *bio)
+			  u32 index, int offset)
 {
 	int ret;
 	struct page *page;
@@ -375,14 +520,14 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
 	struct zram_meta *meta = zram->meta;
 	page = bvec->bv_page;
 
-	read_lock(&meta->tb_lock);
+	bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
 	if (unlikely(!meta->table[index].handle) ||
 			zram_test_flag(meta, index, ZRAM_ZERO)) {
-		read_unlock(&meta->tb_lock);
+		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
 		handle_zero_page(bvec);
 		return 0;
 	}
-	read_unlock(&meta->tb_lock);
+	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
 
 	if (is_partial_io(bvec))
 		/* Use  a temporary buffer to decompress the page */
@@ -416,6 +561,21 @@ out_cleanup:
 	return ret;
 }
 
+static inline void update_used_max(struct zram *zram,
+					const unsigned long pages)
+{
+	unsigned long old_max, cur_max;
+
+	old_max = atomic_long_read(&zram->stats.max_used_pages);
+
+	do {
+		cur_max = old_max;
+		if (pages > cur_max)
+			old_max = atomic_long_cmpxchg(
+				&zram->stats.max_used_pages, cur_max, pages);
+	} while (old_max != cur_max);
+}
+
 static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 			   int offset)
 {
@@ -427,6 +587,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 	struct zram_meta *meta = zram->meta;
 	struct zcomp_strm *zstrm;
 	bool locked = false;
+	unsigned long alloced_pages;
 
 	page = bvec->bv_page;
 	if (is_partial_io(bvec)) {
@@ -458,12 +619,13 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 	}
 
 	if (page_zero_filled(uncmem)) {
-		kunmap_atomic(user_mem);
+		if (user_mem)
+			kunmap_atomic(user_mem);
 		/* Free memory associated with this sector now. */
-		write_lock(&zram->meta->tb_lock);
+		bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
 		zram_free_page(zram, index);
 		zram_set_flag(meta, index, ZRAM_ZERO);
-		write_unlock(&zram->meta->tb_lock);
+		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
 
 		atomic64_inc(&zram->stats.zero_pages);
 		ret = 0;
@@ -495,6 +657,16 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 		ret = -ENOMEM;
 		goto out;
 	}
+
+	alloced_pages = zs_get_total_pages(meta->mem_pool);
+	if (zram->limit_pages && alloced_pages > zram->limit_pages) {
+		zs_free(meta->mem_pool, handle);
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	update_used_max(zram, alloced_pages);
+
 	cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO);
 
 	if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) {
@@ -513,12 +685,12 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 	 * Free memory associated with this sector
 	 * before overwriting unused sectors.
 	 */
-	write_lock(&zram->meta->tb_lock);
+	bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
 	zram_free_page(zram, index);
 
 	meta->table[index].handle = handle;
-	meta->table[index].size = clen;
-	write_unlock(&zram->meta->tb_lock);
+	zram_set_obj_size(meta, index, clen);
+	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
 
 	/* Update stats */
 	atomic64_add(clen, &zram->stats.compr_data_size);
@@ -528,25 +700,35 @@ out:
 		zcomp_strm_release(zram->comp, zstrm);
 	if (is_partial_io(bvec))
 		kfree(uncmem);
-	if (ret)
-		atomic64_inc(&zram->stats.failed_writes);
 	return ret;
 }
 
 static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
-			int offset, struct bio *bio)
+			int offset, int rw)
 {
+	unsigned long start_time = jiffies;
 	int ret;
-	int rw = bio_data_dir(bio);
+
+	generic_start_io_acct(rw, bvec->bv_len >> SECTOR_SHIFT,
+			&zram->disk->part0);
 
 	if (rw == READ) {
 		atomic64_inc(&zram->stats.num_reads);
-		ret = zram_bvec_read(zram, bvec, index, offset, bio);
+		ret = zram_bvec_read(zram, bvec, index, offset);
 	} else {
 		atomic64_inc(&zram->stats.num_writes);
 		ret = zram_bvec_write(zram, bvec, index, offset);
 	}
 
+	generic_end_io_acct(rw, &zram->disk->part0, start_time);
+
+	if (unlikely(ret)) {
+		if (rw == READ)
+			atomic64_inc(&zram->stats.failed_reads);
+		else
+			atomic64_inc(&zram->stats.failed_writes);
+	}
+
 	return ret;
 }
 
@@ -559,6 +741,7 @@ static void zram_bio_discard(struct zram *zram, u32 index,
 			     int offset, struct bio *bio)
 {
 	size_t n = bio->bi_size;
+	struct zram_meta *meta = zram->meta;
 
 	/*
 	 * zram manages data in physical block size units. Because logical block
@@ -579,51 +762,57 @@ static void zram_bio_discard(struct zram *zram, u32 index,
 	}
 
 	while (n >= PAGE_SIZE) {
-		/*
-		 * Discard request can be large so the lock hold times could be
-		 * lengthy.  So take the lock once per page.
-		 */
-		write_lock(&zram->meta->tb_lock);
+		bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
 		zram_free_page(zram, index);
-		write_unlock(&zram->meta->tb_lock);
+		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+		atomic64_inc(&zram->stats.notify_free);
 		index++;
 		n -= PAGE_SIZE;
 	}
 }
 
-static void zram_reset_device(struct zram *zram, bool reset_capacity)
+static void zram_reset_device(struct zram *zram)
 {
-	size_t index;
 	struct zram_meta *meta;
+	struct zcomp *comp;
+	u64 disksize;
 
 	down_write(&zram->init_lock);
+
+	zram->limit_pages = 0;
+
 	if (!init_done(zram)) {
 		up_write(&zram->init_lock);
 		return;
 	}
 
 	meta = zram->meta;
-	/* Free all pages that are still in this zram device */
-	for (index = 0; index < zram->disksize >> PAGE_SHIFT; index++) {
-		unsigned long handle = meta->table[index].handle;
-		if (!handle)
-			continue;
-
-		zs_free(meta->mem_pool, handle);
-	}
-
-	zcomp_destroy(zram->comp);
-	zram->max_comp_streams = 1;
+	comp = zram->comp;
+	disksize = zram->disksize;
+	/*
+	 * Refcount will go down to 0 eventually and r/w handler
+	 * cannot handle further I/O so it will bail out by
+	 * check zram_meta_get.
+	 */
+	zram_meta_put(zram);
+	/*
+	 * We want to free zram_meta in process context to avoid
+	 * deadlock between reclaim path and any other locks.
+	 */
+	wait_event(zram->io_done, atomic_read(&zram->refcount) == 0);
 
-	zram_meta_free(zram->meta);
-	zram->meta = NULL;
 	/* Reset stats */
 	memset(&zram->stats, 0, sizeof(zram->stats));
-
 	zram->disksize = 0;
-	if (reset_capacity)
-		set_capacity(zram->disk, 0);
+	zram->max_comp_streams = 1;
+
+	set_capacity(zram->disk, 0);
+	part_stat_set_all(&zram->disk->part0, 0);
+
 	up_write(&zram->init_lock);
+	/* I/O operation under all of CPU are done so let's free */
+	zram_meta_free(meta, disksize);
+	zcomp_destroy(comp);
 }
 
 static ssize_t disksize_store(struct device *dev,
@@ -640,7 +829,7 @@ static ssize_t disksize_store(struct device *dev,
 		return -EINVAL;
 
 	disksize = PAGE_ALIGN(disksize);
-	meta = zram_meta_alloc(disksize);
+	meta = zram_meta_alloc(zram->disk->first_minor, disksize);
 	if (!meta)
 		return -ENOMEM;
 
@@ -659,18 +848,28 @@ static ssize_t disksize_store(struct device *dev,
 		goto out_destroy_comp;
 	}
 
+	init_waitqueue_head(&zram->io_done);
+	atomic_set(&zram->refcount, 1);
 	zram->meta = meta;
 	zram->comp = comp;
 	zram->disksize = disksize;
 	set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
 	up_write(&zram->init_lock);
+
+	/*
+	 * Revalidate disk out of the init_lock to avoid lockdep splat.
+	 * It's okay because disk's capacity is protected by init_lock
+	 * so that revalidate_disk always sees up-to-date capacity.
+	 */
+	revalidate_disk(zram->disk);
+
 	return len;
 
 out_destroy_comp:
 	up_write(&zram->init_lock);
 	zcomp_destroy(comp);
 out_free_meta:
-	zram_meta_free(meta);
+	zram_meta_free(meta, disksize);
 	return err;
 }
 
@@ -688,8 +887,9 @@ static ssize_t reset_store(struct device *dev,
 	if (!bdev)
 		return -ENOMEM;
 
+	mutex_lock(&bdev->bd_mutex);
 	/* Do not reset an active device! */
-	if (bdev->bd_holders) {
+	if (bdev->bd_openers) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -705,24 +905,29 @@ static ssize_t reset_store(struct device *dev,
 
 	/* Make sure all pending I/O is finished */
 	fsync_bdev(bdev);
+	zram_reset_device(zram);
+
+	mutex_unlock(&bdev->bd_mutex);
+	revalidate_disk(zram->disk);
 	bdput(bdev);
 
-	zram_reset_device(zram, true);
 	return len;
 
 out:
+	mutex_unlock(&bdev->bd_mutex);
 	bdput(bdev);
 	return ret;
 }
 
 static void __zram_make_request(struct zram *zram, struct bio *bio)
 {
-	int i, offset;
+	int i, offset, rw;
 	u32 index;
 	struct bio_vec *bvec;
 
 	index = bio->bi_sector >> SECTORS_PER_PAGE_SHIFT;
-	offset = (bio->bi_sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
+	offset = (bio->bi_sector &
+		  (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
 
 	if (unlikely(bio->bi_rw & REQ_DISCARD)) {
 		zram_bio_discard(zram, index, offset, bio);
@@ -730,6 +935,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 		return;
 	}
 
+	rw = bio_data_dir(bio);
 	bio_for_each_segment(bvec, bio, i) {
 		int max_transfer_size = PAGE_SIZE - offset;
 
@@ -744,16 +950,15 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 			bv.bv_len = max_transfer_size;
 			bv.bv_offset = bvec->bv_offset;
 
-			if (zram_bvec_rw(zram, &bv, index, offset, bio) < 0)
+			if (zram_bvec_rw(zram, &bv, index, offset, rw) < 0)
 				goto out;
 
 			bv.bv_len = bvec->bv_len - max_transfer_size;
 			bv.bv_offset += max_transfer_size;
-			if (zram_bvec_rw(zram, &bv, index + 1, 0, bio) < 0)
+			if (zram_bvec_rw(zram, &bv, index + 1, 0, rw) < 0)
 				goto out;
 		} else
-			if (zram_bvec_rw(zram, bvec, index, offset, bio)
-			    < 0)
+			if (zram_bvec_rw(zram, bvec, index, offset, rw) < 0)
 				goto out;
 
 		update_position(&index, &offset, bvec);
@@ -774,22 +979,21 @@ static void zram_make_request(struct request_queue *queue, struct bio *bio)
 {
 	struct zram *zram = queue->queuedata;
 
-	down_read(&zram->init_lock);
-	if (unlikely(!init_done(zram)))
+	if (unlikely(!zram_meta_get(zram)))
 		goto error;
 
-	if (!valid_io_request(zram, bio)) {
+	if (!valid_io_request(zram, bio->bi_sector,
+					bio->bi_size)) {
 		atomic64_inc(&zram->stats.invalid_io);
-		goto error;
+		goto put_zram;
 	}
 
 	__zram_make_request(zram, bio);
-	up_read(&zram->init_lock);
-
+	zram_meta_put(zram);
 	return;
-
+put_zram:
+	zram_meta_put(zram);
 error:
-	up_read(&zram->init_lock);
 	bio_io_error(bio);
 }
 
@@ -802,9 +1006,9 @@ static void zram_slot_free_notify(struct block_device *bdev,
 	zram = bdev->bd_disk->private_data;
 	meta = zram->meta;
 
-	write_lock(&meta->tb_lock);
+	bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
 	zram_free_page(zram, index);
-	write_unlock(&meta->tb_lock);
+	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
 	atomic64_inc(&zram->stats.notify_free);
 }
 
@@ -813,17 +1017,66 @@ static const struct block_device_operations zram_devops = {
 	.owner = THIS_MODULE
 };
 
-static DEVICE_ATTR(disksize, S_IRUGO | S_IWUSR,
-		disksize_show, disksize_store);
-static DEVICE_ATTR(initstate, S_IRUGO, initstate_show, NULL);
-static DEVICE_ATTR(reset, S_IWUSR, NULL, reset_store);
-static DEVICE_ATTR(orig_data_size, S_IRUGO, orig_data_size_show, NULL);
-static DEVICE_ATTR(mem_used_total, S_IRUGO, mem_used_total_show, NULL);
-static DEVICE_ATTR(max_comp_streams, S_IRUGO | S_IWUSR,
-		max_comp_streams_show, max_comp_streams_store);
-static DEVICE_ATTR(comp_algorithm, S_IRUGO | S_IWUSR,
-		comp_algorithm_show, comp_algorithm_store);
+static DEVICE_ATTR_WO(compact);
+static DEVICE_ATTR_RW(disksize);
+static DEVICE_ATTR_RO(initstate);
+static DEVICE_ATTR_WO(reset);
+static DEVICE_ATTR_RO(orig_data_size);
+static DEVICE_ATTR_RO(mem_used_total);
+static DEVICE_ATTR_RW(mem_limit);
+static DEVICE_ATTR_RW(mem_used_max);
+static DEVICE_ATTR_RW(max_comp_streams);
+static DEVICE_ATTR_RW(comp_algorithm);
+
+static ssize_t io_stat_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct zram *zram = dev_to_zram(dev);
+	ssize_t ret;
+
+	down_read(&zram->init_lock);
+	ret = scnprintf(buf, PAGE_SIZE,
+			"%8llu %8llu %8llu %8llu\n",
+			(u64)atomic64_read(&zram->stats.failed_reads),
+			(u64)atomic64_read(&zram->stats.failed_writes),
+			(u64)atomic64_read(&zram->stats.invalid_io),
+			(u64)atomic64_read(&zram->stats.notify_free));
+	up_read(&zram->init_lock);
+
+	return ret;
+}
+
+static ssize_t mm_stat_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct zram *zram = dev_to_zram(dev);
+	u64 orig_size, mem_used = 0;
+	long max_used;
+	ssize_t ret;
+
+	down_read(&zram->init_lock);
+	if (init_done(zram))
+		mem_used = zs_get_total_pages(zram->meta->mem_pool);
+
+	orig_size = atomic64_read(&zram->stats.pages_stored);
+	max_used = atomic_long_read(&zram->stats.max_used_pages);
+
+	ret = scnprintf(buf, PAGE_SIZE,
+			"%8llu %8llu %8llu %8lu %8ld %8llu %8llu\n",
+			orig_size << PAGE_SHIFT,
+			(u64)atomic64_read(&zram->stats.compr_data_size),
+			mem_used << PAGE_SHIFT,
+			zram->limit_pages << PAGE_SHIFT,
+			max_used << PAGE_SHIFT,
+			(u64)atomic64_read(&zram->stats.zero_pages),
+			(u64)atomic64_read(&zram->stats.num_migrated));
+	up_read(&zram->init_lock);
 
+	return ret;
+}
+
+static DEVICE_ATTR_RO(io_stat);
+static DEVICE_ATTR_RO(mm_stat);
 ZRAM_ATTR_RO(num_reads);
 ZRAM_ATTR_RO(num_writes);
 ZRAM_ATTR_RO(failed_reads);
@@ -841,14 +1094,19 @@ static struct attribute *zram_disk_attrs[] = {
 	&dev_attr_num_writes.attr,
 	&dev_attr_failed_reads.attr,
 	&dev_attr_failed_writes.attr,
+	&dev_attr_compact.attr,
 	&dev_attr_invalid_io.attr,
 	&dev_attr_notify_free.attr,
 	&dev_attr_zero_pages.attr,
 	&dev_attr_orig_data_size.attr,
 	&dev_attr_compr_data_size.attr,
 	&dev_attr_mem_used_total.attr,
+	&dev_attr_mem_limit.attr,
+	&dev_attr_mem_used_max.attr,
 	&dev_attr_max_comp_streams.attr,
 	&dev_attr_comp_algorithm.attr,
+	&dev_attr_io_stat.attr,
+	&dev_attr_mm_stat.attr,
 	NULL,
 };
 
@@ -858,32 +1116,34 @@ static struct attribute_group zram_disk_attr_group = {
 
 static int create_device(struct zram *zram, int device_id)
 {
+	struct request_queue *queue;
 	int ret = -ENOMEM;
 
 	init_rwsem(&zram->init_lock);
 
-	zram->queue = blk_alloc_queue(GFP_KERNEL);
-	if (!zram->queue) {
+	queue = blk_alloc_queue(GFP_KERNEL);
+	if (!queue) {
 		pr_err("Error allocating disk queue for device %d\n",
 			device_id);
 		goto out;
 	}
 
-	blk_queue_make_request(zram->queue, zram_make_request);
-	zram->queue->queuedata = zram;
+	blk_queue_make_request(queue, zram_make_request);
 
 	 /* gendisk structure */
 	zram->disk = alloc_disk(1);
 	if (!zram->disk) {
 		pr_warn("Error allocating disk structure for device %d\n",
 			device_id);
+		ret = -ENOMEM;
 		goto out_free_queue;
 	}
 
 	zram->disk->major = zram_major;
 	zram->disk->first_minor = device_id;
 	zram->disk->fops = &zram_devops;
-	zram->disk->queue = zram->queue;
+	zram->disk->queue = queue;
+	zram->disk->queue->queuedata = zram;
 	zram->disk->private_data = zram;
 	snprintf(zram->disk->disk_name, 16, "zram%d", device_id);
 
@@ -891,6 +1151,7 @@ static int create_device(struct zram *zram, int device_id)
 	set_capacity(zram->disk, 0);
 	/* zram devices sort of resembles non-rotational disks */
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue);
+	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, zram->disk->queue);
 	/*
 	 * To ensure that we always get PAGE_SIZE aligned
 	 * and n*PAGE_SIZED sized I/O requests.
@@ -926,27 +1187,42 @@ static int create_device(struct zram *zram, int device_id)
 	}
 	strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));
 	zram->meta = NULL;
-	zram->max_comp_streams = 3;
+	zram->max_comp_streams = 1;
 	return 0;
 
 out_free_disk:
 	del_gendisk(zram->disk);
 	put_disk(zram->disk);
 out_free_queue:
-	blk_cleanup_queue(zram->queue);
+	blk_cleanup_queue(queue);
 out:
 	return ret;
 }
 
-static void destroy_device(struct zram *zram)
+static void destroy_devices(unsigned int nr)
 {
-	sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
-			&zram_disk_attr_group);
+	struct zram *zram;
+	unsigned int i;
 
-	del_gendisk(zram->disk);
-	put_disk(zram->disk);
+	for (i = 0; i < nr; i++) {
+		zram = &zram_devices[i];
+		/*
+		 * Remove sysfs first, so no one will perform a disksize
+		 * store while we destroy the devices
+		 */
+		sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
+				&zram_disk_attr_group);
+
+		zram_reset_device(zram);
 
-	blk_cleanup_queue(zram->queue);
+		blk_cleanup_queue(zram->disk->queue);
+		del_gendisk(zram->disk);
+		put_disk(zram->disk);
+	}
+
+	kfree(zram_devices);
+	unregister_blkdev(zram_major, "zram");
+	pr_info("Destroyed %u device(s)\n", nr);
 }
 
 static int __init zram_init(void)
@@ -956,64 +1232,39 @@ static int __init zram_init(void)
 	if (num_devices > max_num_devices) {
 		pr_warn("Invalid value for num_devices: %u\n",
 				num_devices);
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	zram_major = register_blkdev(0, "zram");
 	if (zram_major <= 0) {
 		pr_warn("Unable to get major number\n");
-		ret = -EBUSY;
-		goto out;
+		return -EBUSY;
 	}
 
 	/* Allocate the device array and initialize each one */
 	zram_devices = kzalloc(num_devices * sizeof(struct zram), GFP_KERNEL);
 	if (!zram_devices) {
-		ret = -ENOMEM;
-		goto unregister;
+		unregister_blkdev(zram_major, "zram");
+		return -ENOMEM;
 	}
 
 	for (dev_id = 0; dev_id < num_devices; dev_id++) {
 		ret = create_device(&zram_devices[dev_id], dev_id);
 		if (ret)
-			goto free_devices;
+			goto out_error;
 	}
 
-	pr_info("Created %u device(s) ...\n", num_devices);
-
+	pr_info("Created %u device(s)\n", num_devices);
 	return 0;
 
-free_devices:
-	while (dev_id)
-		destroy_device(&zram_devices[--dev_id]);
-	kfree(zram_devices);
-unregister:
-	unregister_blkdev(zram_major, "zram");
-out:
+out_error:
+	destroy_devices(dev_id);
 	return ret;
 }
 
 static void __exit zram_exit(void)
 {
-	int i;
-	struct zram *zram;
-
-	for (i = 0; i < num_devices; i++) {
-		zram = &zram_devices[i];
-
-		destroy_device(zram);
-		/*
-		 * Shouldn't access zram->disk after destroy_device
-		 * because destroy_device already released zram->disk.
-		 */
-		zram_reset_device(zram, false);
-	}
-
-	unregister_blkdev(zram_major, "zram");
-
-	kfree(zram_devices);
-	pr_debug("Cleanup done!\n");
+	destroy_devices(num_devices);
 }
 
 module_init(zram_init);
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
new file mode 100644
index 000000000..570c598f4
--- /dev/null
+++ b/drivers/block/zram/zram_drv.h
@@ -0,0 +1,125 @@
+/*
+ * Compressed RAM block device
+ *
+ * Copyright (C) 2008, 2009, 2010  Nitin Gupta
+ *               2012, 2013 Minchan Kim
+ *
+ * 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 _ZRAM_DRV_H_
+#define _ZRAM_DRV_H_
+
+#include <linux/spinlock.h>
+#include <linux/zsmalloc.h>
+
+#include "zcomp.h"
+
+/*
+ * Some arbitrary value. This is just to catch
+ * invalid value for num_devices module parameter.
+ */
+static const unsigned max_num_devices = 32;
+
+/*-- Configurable parameters */
+
+/*
+ * Pages that compress to size greater than this are stored
+ * uncompressed in memory.
+ */
+static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
+
+/*
+ * NOTE: max_zpage_size must be less than or equal to:
+ *   ZS_MAX_ALLOC_SIZE. Otherwise, zs_malloc() would
+ * always return failure.
+ */
+
+/*-- End of configurable params */
+
+#define SECTOR_SHIFT		9
+#define SECTORS_PER_PAGE_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
+#define SECTORS_PER_PAGE	(1 << SECTORS_PER_PAGE_SHIFT)
+#define ZRAM_LOGICAL_BLOCK_SHIFT 12
+#define ZRAM_LOGICAL_BLOCK_SIZE	(1 << ZRAM_LOGICAL_BLOCK_SHIFT)
+#define ZRAM_SECTOR_PER_LOGICAL_BLOCK	\
+	(1 << (ZRAM_LOGICAL_BLOCK_SHIFT - SECTOR_SHIFT))
+
+
+/*
+ * The lower ZRAM_FLAG_SHIFT bits of table.value is for
+ * object size (excluding header), the higher bits is for
+ * zram_pageflags.
+ *
+ * zram is mainly used for memory efficiency so we want to keep memory
+ * footprint small so we can squeeze size and flags into a field.
+ * The lower ZRAM_FLAG_SHIFT bits is for object size (excluding header),
+ * the higher bits is for zram_pageflags.
+ */
+#define ZRAM_FLAG_SHIFT 24
+
+/* Flags for zram pages (table[page_no].value) */
+enum zram_pageflags {
+	/* Page consists entirely of zeros */
+	ZRAM_ZERO = ZRAM_FLAG_SHIFT,
+	ZRAM_ACCESS,	/* page is now accessed */
+
+	__NR_ZRAM_PAGEFLAGS,
+};
+
+/*-- Data structures */
+
+/* Allocated for each disk page */
+struct zram_table_entry {
+	unsigned long handle;
+	unsigned long value;
+};
+
+struct zram_stats {
+	atomic64_t compr_data_size;	/* compressed size of pages stored */
+	atomic64_t num_reads;	/* failed + successful */
+	atomic64_t num_writes;	/* --do-- */
+	atomic64_t num_migrated;	/* no. of migrated object */
+	atomic64_t failed_reads;	/* can happen when memory is too low */
+	atomic64_t failed_writes;	/* can happen when memory is too low */
+	atomic64_t invalid_io;	/* non-page-aligned I/O requests */
+	atomic64_t notify_free;	/* no. of swap slot free notifications */
+	atomic64_t zero_pages;		/* no. of zero filled pages */
+	atomic64_t pages_stored;	/* no. of pages currently stored */
+	atomic_long_t max_used_pages;	/* no. of maximum pages stored */
+};
+
+struct zram_meta {
+	struct zram_table_entry *table;
+	struct zs_pool *mem_pool;
+};
+
+struct zram {
+	struct zram_meta *meta;
+	struct zcomp *comp;
+	struct gendisk *disk;
+	/* Prevent concurrent execution of device init */
+	struct rw_semaphore init_lock;
+	/*
+	 * the number of pages zram can consume for storing compressed data
+	 */
+	unsigned long limit_pages;
+	int max_comp_streams;
+
+	struct zram_stats stats;
+	atomic_t refcount; /* refcount for zram_meta */
+	/* wait all IO under all of cpu are done */
+	wait_queue_head_t io_done;
+	/*
+	 * This is the limit on amount of *uncompressed* worth of data
+	 * we can store in a disk.
+	 */
+	u64 disksize;	/* bytes */
+	char compressor[10];
+};
+#endif