zram: zram memory size limitation

Since zram has no control feature to limit memory usage, it makes hard to
manage system memrory.

This patch adds new knob "mem_limit" via sysfs to set up the a limit so
that zram could fail allocation once it reaches the limit.

In addition, user could change the limit in runtime so that he could
manage the memory more dynamically.

Initial state is no limit so it doesn't break old behavior.

[akpm@linux-foundation.org: fix typo, per Sergey]
Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: <juno.choi@lge.com>
Cc: <seungho1.park@lge.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Seth Jennings <sjennings@variantweb.net>
Cc: David Horner <ds2horner@gmail.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Documentation/ABI/testing/sysfs-block-zram

@@ -119,3 +119,12 @@ Description:
 		efficiency can be calculated using compr_data_size and this
 		statistic.
 		Unit: bytes
+
+What:		/sys/block/zram<id>/mem_limit
+Date:		August 2014
+Contact:	Minchan Kim <minchan@kernel.org>
+Description:
+		The mem_limit file is read/write and specifies the maximum
+		amount of memory ZRAM can use to store the compressed data.  The
+		limit could be changed in run time and "0" means disable the
+		limit.  No limit is the initial state.  Unit: bytes

Documentation/blockdev/zram.txt

@@ -74,14 +74,30 @@ There is little point creating a zram of greater than twice the size of memory
 since we expect a 2:1 compression ratio. Note that zram uses about 0.1% of the
 size of the disk when not in use so a huge zram is wasteful.
 
-5) Activate:
+5) Set memory limit: Optional
+	Set memory limit by writing the value to sysfs node 'mem_limit'.
+	The value can be either in bytes or you can use mem suffixes.
+	In addition, you could change the value in runtime.
+	Examples:
+	    # limit /dev/zram0 with 50MB memory
+	    echo $((50*1024*1024)) > /sys/block/zram0/mem_limit
+
+	    # Using mem suffixes
+	    echo 256K > /sys/block/zram0/mem_limit
+	    echo 512M > /sys/block/zram0/mem_limit
+	    echo 1G > /sys/block/zram0/mem_limit
+
+	    # To disable memory limit
+	    echo 0 > /sys/block/zram0/mem_limit
+
+6) Activate:
 	mkswap /dev/zram0
 	swapon /dev/zram0
 
 	mkfs.ext4 /dev/zram1
 	mount /dev/zram1 /tmp
 
-6) Stats:
+7) Stats:
 	Per-device statistics are exported as various nodes under
 	/sys/block/zram<id>/
 		disksize
@@ -96,11 +112,11 @@ size of the disk when not in use so a huge zram is wasteful.
 		compr_data_size
 		mem_used_total
 
-7) Deactivate:
+8) Deactivate:
 	swapoff /dev/zram0
 	umount /dev/zram1
 
-8) Reset:
+9) Reset:
 	Write any positive value to 'reset' sysfs node
 	echo 1 > /sys/block/zram0/reset
 	echo 1 > /sys/block/zram1/reset

drivers/block/zram/zram_drv.c

@@ -122,6 +122,37 @@ 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);
+
+	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 max_comp_streams_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
 {
@@ -513,6 +544,14 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 		ret = -ENOMEM;
 		goto out;
 	}
+
+	if (zram->limit_pages &&
+		zs_get_total_pages(meta->mem_pool) > zram->limit_pages) {
+		zs_free(meta->mem_pool, handle);
+		ret = -ENOMEM;
+		goto out;
+	}
+
 	cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO);
 
 	if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) {
@@ -617,6 +656,9 @@ static void zram_reset_device(struct zram *zram, bool reset_capacity)
 	struct zram_meta *meta;
 
 	down_write(&zram->init_lock);
+
+	zram->limit_pages = 0;
+
 	if (!init_done(zram)) {
 		up_write(&zram->init_lock);
 		return;
@@ -857,6 +899,8 @@ 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(mem_limit, S_IRUGO | S_IWUSR, mem_limit_show,
+		mem_limit_store);
 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,
@@ -885,6 +929,7 @@ static struct attribute *zram_disk_attrs[] = {
 	&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_max_comp_streams.attr,
 	&dev_attr_comp_algorithm.attr,
 	NULL,

drivers/block/zram/zram_drv.h

@@ -112,6 +112,11 @@ struct zram {
 	u64 disksize;	/* bytes */
 	int max_comp_streams;
 	struct zram_stats stats;
+	/*
+	 * the number of pages zram can consume for storing compressed data
+	 */
+	unsigned long limit_pages;
+
 	char compressor[10];
 };
 #endif