zram: writeback throttle

If there are lots of write IO with flash device, it could have a
wearout problem of storage. To overcome the problem, admin needs
to design write limitation to guarantee flash health
for entire product life.

This patch creates a new knob "writeback_limit" for zram.

writeback_limit's default value is 0 so that it doesn't limit
any writeback. If admin want to measure writeback count in a
certain period, he could know it via /sys/block/zram0/bd_stat's
3rd column.

If admin want to limit writeback as per-day 400M, he could do it
like below.

	MB_SHIFT=20
	4K_SHIFT=12
	echo $((400<<MB_SHIFT>>4K_SHIFT)) > \
		/sys/block/zram0/writeback_limit.

If admin want to allow further write again, he could do it like below

	echo 0 > /sys/block/zram0/writeback_limit

If admin want to see remaining writeback budget,

	cat /sys/block/zram0/writeback_limit

The writeback_limit count will reset whenever you reset zram (e.g., system
reboot, echo 1 > /sys/block/zramX/reset) so keeping how many of writeback
happened until you reset the zram to allocate extra writeback budget in
next setting is user's job.

[minchan@kernel.org: v4]
  Link: http://lkml.kernel.org/r/20181203024045.153534-8-minchan@kernel.org
Link: http://lkml.kernel.org/r/20181127055429.251614-8-minchan@kernel.orgSigned-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Joey Pabalinas <joeypabalinas@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Documentation/ABI/testing/sysfs-block-zram

@@ -121,3 +121,12 @@ Description:
 		The bd_stat file is read-only and represents backing device's
 		statistics (bd_count, bd_reads, bd_writes) in a format
 		similar to block layer statistics file format.
+
+What:		/sys/block/zram<id>/writeback_limit
+Date:		November 2018
+Contact:	Minchan Kim <minchan@kernel.org>
+Description:
+		The writeback_limit file is read-write and specifies the maximum
+		amount of writeback ZRAM can do. The limit could be changed
+		in run time and "0" means disable the limit.
+		No limit is the initial state.

Documentation/blockdev/zram.txt

@@ -164,6 +164,8 @@ reset             WO    trigger device reset
 mem_used_max      WO    reset the `mem_used_max' counter (see later)
 mem_limit         WO    specifies the maximum amount of memory ZRAM can use
                         to store the compressed data
+writeback_limit   WO    specifies the maximum amount of write IO zram can
+			write out to backing device as 4KB unit
 max_comp_streams  RW    the number of possible concurrent compress operations
 comp_algorithm    RW    show and change the compression algorithm
 compact           WO    trigger memory compaction
@@ -275,6 +277,35 @@ Admin can request writeback of those idle pages at right timing via
 
 With the command, zram writeback idle pages from memory to the storage.
 
+If there are lots of write IO with flash device, potentially, it has
+flash wearout problem so that admin needs to design write limitation
+to guarantee storage health for entire product life.
+To overcome the concern, zram supports "writeback_limit".
+The "writeback_limit"'s default value is 0 so that it doesn't limit
+any writeback. If admin want to measure writeback count in a certain
+period, he could know it via /sys/block/zram0/bd_stat's 3rd column.
+
+If admin want to limit writeback as per-day 400M, he could do it
+like below.
+
+    MB_SHIFT=20
+    4K_SHIFT=12
+    echo $((400<<MB_SHIFT>>4K_SHIFT)) > \
+	    /sys/block/zram0/writeback_limit.
+
+If admin want to allow further write again, he could do it like below
+
+    echo 0 > /sys/block/zram0/writeback_limit
+
+If admin want to see remaining writeback budget since he set,
+
+    cat /sys/block/zram0/writeback_limit
+
+The writeback_limit count will reset whenever you reset zram(e.g.,
+system reboot, echo 1 > /sys/block/zramX/reset) so keeping how many of
+writeback happened until you reset the zram to allocate extra writeback
+budget in next setting is user's job.
+
 = memory tracking
 
 With CONFIG_ZRAM_MEMORY_TRACKING, user can know information of the

drivers/block/zram/zram_drv.c

@@ -330,6 +330,39 @@ static ssize_t idle_store(struct device *dev,
 }
 
 #ifdef CONFIG_ZRAM_WRITEBACK
+static ssize_t writeback_limit_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct zram *zram = dev_to_zram(dev);
+	u64 val;
+	ssize_t ret = -EINVAL;
+
+	if (kstrtoull(buf, 10, &val))
+		return ret;
+
+	down_read(&zram->init_lock);
+	atomic64_set(&zram->stats.bd_wb_limit, val);
+	if (val == 0)
+		zram->stop_writeback = false;
+	up_read(&zram->init_lock);
+	ret = len;
+
+	return ret;
+}
+
+static ssize_t writeback_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 = atomic64_read(&zram->stats.bd_wb_limit);
+	up_read(&zram->init_lock);
+
+	return scnprintf(buf, PAGE_SIZE, "%llu\n", val);
+}
+
 static void reset_bdev(struct zram *zram)
 {
 	struct block_device *bdev;
@@ -612,6 +645,11 @@ static ssize_t writeback_store(struct device *dev,
 		bvec.bv_len = PAGE_SIZE;
 		bvec.bv_offset = 0;
 
+		if (zram->stop_writeback) {
+			ret = -EIO;
+			break;
+		}
+
 		if (!blk_idx) {
 			blk_idx = alloc_block_bdev(zram);
 			if (!blk_idx) {
@@ -694,6 +732,11 @@ static ssize_t writeback_store(struct device *dev,
 		zram_set_element(zram, index, blk_idx);
 		blk_idx = 0;
 		atomic64_inc(&zram->stats.pages_stored);
+		if (atomic64_add_unless(&zram->stats.bd_wb_limit,
+					-1 << (PAGE_SHIFT - 12), 0)) {
+			if (atomic64_read(&zram->stats.bd_wb_limit) == 0)
+				zram->stop_writeback = true;
+		}
 next:
 		zram_slot_unlock(zram, index);
 	}
@@ -1018,6 +1061,7 @@ static ssize_t mm_stat_show(struct device *dev,
 }
 
 #ifdef CONFIG_ZRAM_WRITEBACK
+#define FOUR_K(x) ((x) * (1 << (PAGE_SHIFT - 12)))
 static ssize_t bd_stat_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -1027,9 +1071,9 @@ static ssize_t bd_stat_show(struct device *dev,
 	down_read(&zram->init_lock);
 	ret = scnprintf(buf, PAGE_SIZE,
 		"%8llu %8llu %8llu\n",
-		(u64)atomic64_read(&zram->stats.bd_count) * (PAGE_SHIFT - 12),
-		(u64)atomic64_read(&zram->stats.bd_reads) * (PAGE_SHIFT - 12),
-		(u64)atomic64_read(&zram->stats.bd_writes) * (PAGE_SHIFT - 12));
+			FOUR_K((u64)atomic64_read(&zram->stats.bd_count)),
+			FOUR_K((u64)atomic64_read(&zram->stats.bd_reads)),
+			FOUR_K((u64)atomic64_read(&zram->stats.bd_writes)));
 	up_read(&zram->init_lock);
 
 	return ret;
@@ -1767,6 +1811,7 @@ static DEVICE_ATTR_RW(comp_algorithm);
 #ifdef CONFIG_ZRAM_WRITEBACK
 static DEVICE_ATTR_RW(backing_dev);
 static DEVICE_ATTR_WO(writeback);
+static DEVICE_ATTR_RW(writeback_limit);
 #endif
 
 static struct attribute *zram_disk_attrs[] = {
@@ -1782,6 +1827,7 @@ static struct attribute *zram_disk_attrs[] = {
 #ifdef CONFIG_ZRAM_WRITEBACK
 	&dev_attr_backing_dev.attr,
 	&dev_attr_writeback.attr,
+	&dev_attr_writeback_limit.attr,
 #endif
 	&dev_attr_io_stat.attr,
 	&dev_attr_mm_stat.attr,

drivers/block/zram/zram_drv.h

@@ -86,6 +86,7 @@ struct zram_stats {
 	atomic64_t bd_count;		/* no. of pages in backing device */
 	atomic64_t bd_reads;		/* no. of reads from backing device */
 	atomic64_t bd_writes;		/* no. of writes from backing device */
+	atomic64_t bd_wb_limit;		/* writeback limit of backing device */
 #endif
 };
 
@@ -113,6 +114,7 @@ struct zram {
 	 */
 	bool claim; /* Protected by bdev->bd_mutex */
 	struct file *backing_dev;
+	bool stop_writeback;
 #ifdef CONFIG_ZRAM_WRITEBACK
 	struct block_device *bdev;
 	unsigned int old_block_size;