zram: use atomic operation for stat

Some of fields in zram->stats are protected by zram->lock which is
rather coarse-grained so let's use atomic operation without explict
locking.

This patch is ready for removing dependency of zram->lock in read path
which is very coarse-grained rw_semaphore.  Of course, this patch adds
new atomic operation so it might make slow but my 12CPU test couldn't
spot any regression.  All gain/lose is marginal within stddev.

  iozone -t -T -l 12 -u 12 -r 16K -s 60M -I +Z -V 0

  ==Initial write                ==Initial write
  records: 50                    records: 50
  avg:  412875.17                avg:  415638.23
  std:   38543.12 (9.34%)        std:   36601.11 (8.81%)
  max:  521262.03                max:  502976.72
  min:  343263.13                min:  351389.12
  ==Rewrite                      ==Rewrite
  records: 50                    records: 50
  avg:  416640.34                avg:  397914.33
  std:   60798.92 (14.59%)       std:   46150.42 (11.60%)
  max:  543057.07                max:  522669.17
  min:  304071.67                min:  316588.77
  ==Read                         ==Read
  records: 50                    records: 50
  avg: 4147338.63                avg: 4070736.51
  std:  179333.25 (4.32%)        std:  223499.89 (5.49%)
  max: 4459295.28                max: 4539514.44
  min: 3753057.53                min: 3444686.31
  ==Re-read                      ==Re-read
  records: 50                    records: 50
  avg: 4096706.71                avg: 4117218.57
  std:  229735.04 (5.61%)        std:  171676.25 (4.17%)
  max: 4430012.09                max: 4459263.94
  min: 2987217.80                min: 3666904.28
  ==Reverse Read                 ==Reverse Read
  records: 50                    records: 50
  avg: 4062763.83                avg: 4078508.32
  std:  186208.46 (4.58%)        std:  172684.34 (4.23%)
  max: 4401358.78                max: 4424757.22
  min: 3381625.00                min: 3679359.94
  ==Stride read                  ==Stride read
  records: 50                    records: 50
  avg: 4094933.49                avg: 4082170.22
  std:  185710.52 (4.54%)        std:  196346.68 (4.81%)
  max: 4478241.25                max: 4460060.97
  min: 3732593.23                min: 3584125.78
  ==Random read                  ==Random read
  records: 50                    records: 50
  avg: 4031070.04                avg: 4074847.49
  std:  192065.51 (4.76%)        std:  206911.33 (5.08%)
  max: 4356931.16                max: 4399442.56
  min: 3481619.62                min: 3548372.44
  ==Mixed workload               ==Mixed workload
  records: 50                    records: 50
  avg:  149925.73                avg:  149675.54
  std:    7701.26 (5.14%)        std:    6902.09 (4.61%)
  max:  191301.56                max:  175162.05
  min:  133566.28                min:  137762.87
  ==Random write                 ==Random write
  records: 50                    records: 50
  avg:  404050.11                avg:  393021.47
  std:   58887.57 (14.57%)       std:   42813.70 (10.89%)
  max:  601798.09                max:  524533.43
  min:  325176.99                min:  313255.34
  ==Pwrite                       ==Pwrite
  records: 50                    records: 50
  avg:  411217.70                avg:  411237.96
  std:   43114.99 (10.48%)       std:   33136.29 (8.06%)
  max:  530766.79                max:  471899.76
  min:  320786.84                min:  317906.94
  ==Pread                        ==Pread
  records: 50                    records: 50
  avg: 4154908.65                avg: 4087121.92
  std:  151272.08 (3.64%)        std:  219505.04 (5.37%)
  max: 4459478.12                max: 4435857.38
  min: 3730512.41                min: 3101101.67

Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Tested-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Jerome Marchand <jmarchan@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 16 insertions, 20 deletions

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index f39c2f9..1200ef3 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -112,7 +112,7 @@ static ssize_t zero_pages_show(struct device *dev,
 {
 	struct zram *zram = dev_to_zram(dev);
 
-	return sprintf(buf, "%u\n", zram->stats.pages_zero);
+	return sprintf(buf, "%u\n", atomic_read(&zram->stats.pages_zero));
 }
 
 static ssize_t orig_data_size_show(struct device *dev,
@@ -121,7 +121,7 @@ static ssize_t orig_data_size_show(struct device *dev,
 	struct zram *zram = dev_to_zram(dev);
 
 	return sprintf(buf, "%llu\n",
-		(u64)(zram->stats.pages_stored) << PAGE_SHIFT);
+		(u64)(atomic_read(&zram->stats.pages_stored)) << PAGE_SHIFT);
 }
 
 static ssize_t compr_data_size_show(struct device *dev,
@@ -301,21 +301,21 @@ static void zram_free_page(struct zram *zram, size_t index)
 		 */
 		if (zram_test_flag(meta, index, ZRAM_ZERO)) {
 			zram_clear_flag(meta, index, ZRAM_ZERO);
-			zram->stats.pages_zero--;
+			atomic_dec(&zram->stats.pages_zero);
 		}
 		return;
 	}
 
 	if (unlikely(size > max_zpage_size))
-		zram->stats.bad_compress--;
+		atomic_dec(&zram->stats.bad_compress);
 
 	zs_free(meta->mem_pool, handle);
 
 	if (size <= PAGE_SIZE / 2)
-		zram->stats.good_compress--;
+		atomic_dec(&zram->stats.good_compress);
 
 	atomic64_sub(meta->table[index].size, &zram->stats.compr_size);
-	zram->stats.pages_stored--;
+	atomic_dec(&zram->stats.pages_stored);
 
 	meta->table[index].handle = 0;
 	meta->table[index].size = 0;
@@ -444,7 +444,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 		/* Free memory associated with this sector now. */
 		zram_free_page(zram, index);
 
-		zram->stats.pages_zero++;
+		atomic_inc(&zram->stats.pages_zero);
 		zram_set_flag(meta, index, ZRAM_ZERO);
 		ret = 0;
 		goto out;
@@ -465,7 +465,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 	}
 
 	if (unlikely(clen > max_zpage_size)) {
-		zram->stats.bad_compress++;
+		atomic_inc(&zram->stats.bad_compress);
 		clen = PAGE_SIZE;
 		src = NULL;
 		if (is_partial_io(bvec))
@@ -504,9 +504,9 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 
 	/* Update stats */
 	atomic64_add(clen, &zram->stats.compr_size);
-	zram->stats.pages_stored++;
+	atomic_inc(&zram->stats.pages_stored);
 	if (clen <= PAGE_SIZE / 2)
-		zram->stats.good_compress++;
+		atomic_inc(&zram->stats.good_compress);
 
 out:
 	if (is_partial_io(bvec))
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index e9b2476..1526c82 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -69,10 +69,6 @@ struct table {
 	u8 flags;
 } __aligned(4);
 
-/*
- * All 64bit fields should only be manipulated by 64bit atomic accessors.
- * All modifications to 32bit counter should be protected by zram->lock.
- */
 struct zram_stats {
 	atomic64_t compr_size;	/* compressed size of pages stored */
 	atomic64_t num_reads;	/* failed + successful */
@@ -81,10 +77,10 @@ struct zram_stats {
 	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 */
-	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 bad_compress;	/* % of pages with compression ratio>=75% */
+	atomic_t pages_zero;		/* no. of zero filled pages */
+	atomic_t pages_stored;	/* no. of pages currently stored */
+	atomic_t good_compress;	/* % of pages with compression ratio<=50% */
+	atomic_t bad_compress;	/* % of pages with compression ratio>=75% */
 };
 
 struct zram_meta {
@@ -102,8 +98,8 @@ struct zram_slot_free {
 struct zram {
 	struct zram_meta *meta;
 	struct rw_semaphore lock; /* protect compression buffers, table,
-				   * 32bit stat counters against concurrent
-				   * notifications, reads and writes */
+				   * reads and writes
+				   */
 
 	struct work_struct free_work;  /* handle pending free request */
 	struct zram_slot_free *slot_free_rq; /* list head of free request */