zram: report maximum used memory

Normally, zram user could get maximum memory usage zram consumed via
polling mem_used_total with sysfs in userspace.

But it has a critical problem because user can miss peak memory usage
during update inverval of polling.  For avoiding that, user should poll it
with shorter interval(ie, 0.0000000001s) with mlocking to avoid page fault
delay when memory pressure is heavy.  It would be troublesome.

This patch adds new knob "mem_used_max" so user could see the maximum
memory usage easily via reading the knob and reset it via "echo 0 >
/sys/block/zram0/mem_used_max".
Signed-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: 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>
Reviewed-by: David Horner <ds2horner@gmail.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.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

@@ -120,6 +120,16 @@ Description:
 		statistic.
 		Unit: bytes
 
+What:		/sys/block/zram<id>/mem_used_max
+Date:		August 2014
+Contact:	Minchan Kim <minchan@kernel.org>
+Description:
+		The mem_used_max file is read/write and specifies the amount
+		of maximum memory zram have consumed to store compressed data.
+		For resetting the value, you should write "0". Otherwise,
+		you could see -EINVAL.
+		Unit: bytes
+
 What:		/sys/block/zram<id>/mem_limit
 Date:		August 2014
 Contact:	Minchan Kim <minchan@kernel.org>

Documentation/blockdev/zram.txt

@@ -111,6 +111,7 @@ size of the disk when not in use so a huge zram is wasteful.
 		orig_data_size
 		compr_data_size
 		mem_used_total
+		mem_used_max
 
 8) Deactivate:
 	swapoff /dev/zram0

drivers/block/zram/zram_drv.c

@@ -153,6 +153,41 @@ static ssize_t mem_limit_store(struct device *dev,
 	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);
+
+	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);
+	struct zram_meta *meta = zram->meta;
+
+	err = kstrtoul(buf, 10, &val);
+	if (err || val != 0)
+		return -EINVAL;
+
+	down_read(&zram->init_lock);
+	if (init_done(zram))
+		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)
 {
@@ -465,6 +500,21 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
 	return ret;
 }
 
+static inline void update_used_max(struct zram *zram,
+					const unsigned long pages)
+{
+	int 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)
 {
@@ -476,6 +526,7 @@ 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)) {
@@ -545,13 +596,15 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 		goto out;
 	}
 
-	if (zram->limit_pages &&
-		zs_get_total_pages(meta->mem_pool) > zram->limit_pages) {
+	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)) {
@@ -901,6 +954,8 @@ 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(mem_used_max, S_IRUGO | S_IWUSR, mem_used_max_show,
+		mem_used_max_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,
@@ -930,6 +985,7 @@ static struct attribute *zram_disk_attrs[] = {
 	&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,
 	NULL,

drivers/block/zram/zram_drv.h

@@ -90,6 +90,7 @@ struct zram_stats {
 	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 {