zram: replace global tb_lock with fine grain lock

Currently, we use a rwlock tb_lock to protect concurrent access to the
whole zram meta table. However, according to the actual access model,
there is only a small chance for upper user to access the same
table[index], so the current lock granularity is too big.

The idea of optimization is to change the lock granularity from whole
meta table to per table entry (table -> table[index]), so that we can
protect concurrent access to the same table[index], meanwhile allow the
maximum concurrency.

With this in mind, several kinds of locks which could be used as a
per-entry lock were tested and compared:

Test environment:
x86-64 Intel Core2 Q8400, system memory 4GB, Ubuntu 12.04,
kernel v3.15.0-rc3 as base, zram with 4 max_comp_streams LZO.

iozone test:
iozone -t 4 -R -r 16K -s 200M -I +Z
(1GB zram with ext4 filesystem, take the average of 10 tests, KB/s)

Test base CAS spinlock rwlock bit_spinlock
-------------------------------------------------------------------
Initial write 1381094 1425435 1422860 1423075 1421521
Rewrite 1529479 1641199 1668762 1672855 1654910
Read 8468009 11324979 11305569 11117273 10997202
Re-read 8467476 11260914 11248059 11145336 10906486
Reverse Read 6821393 8106334 8282174 8279195 8109186
Stride read 7191093 8994306 9153982 8961224 9004434
Random read 7156353 8957932 9167098 8980465 8940476
Mixed workload 4172747 5680814 5927825 5489578 5972253
Random write 1483044 1605588 1594329 1600453 1596010
Pwrite 1276644 1303108 1311612 1314228 1300960
Pread 4324337 4632869 4618386 4457870 4500166

To enhance the possibility of access the same table[index] concurrently,
set zram a small disksize(10MB) and let threads run with large loop
count.

fio test:
fio --bs=32k --randrepeat=1 --randseed=100 --refill_buffers
--scramble_buffers=1 --direct=1 --loops=3000 --numjobs=4
--filename=/dev/zram0 --name=seq-write --rw=write --stonewall
--name=seq-read --rw=read --stonewall --name=seq-readwrite
--rw=rw --stonewall --name=rand-readwrite --rw=randrw --stonewall
(10MB zram raw block device, take the average of 10 tests, KB/s)

Test base CAS spinlock rwlock bit_spinlock
-------------------------------------------------------------
seq-write 933789 999357 1003298 995961 1001958
seq-read 5634130 6577930 6380861 6243912 6230006
seq-rw 1405687 1638117 1640256 1633903 1634459
rand-rw 1386119 1614664 1617211 1609267 1612471

All the optimization methods show a higher performance than the base,
however, it is hard to say which method is the most appropriate.

On the other hand, zram is mostly used on small embedded system, so we
don't want to increase any memory footprint.

This patch pick the bit_spinlock method, pack object size and page_flag
into an unsigned long table.value, so as to not increase any memory
overhead on both 32-bit and 64-bit system.

On the third hand, even though different kinds of locks have different
performances, we can ignore this difference, because: if zram is used as
zram swapfile, the swap subsystem can prevent concurrent access to the
same swapslot; if zram is used as zram-blk for set up filesystem on it,
the upper filesystem and the page cache also prevent concurrent access
of the same block mostly. So we can ignore the different performances
among locks.

Acked-by: Sergey Senozhatsky <[e-mail]>
Reviewed-by: Davidlohr Bueso <[e-mail]>
Signed-off-by: Weijie Yang <[e-mail]>
Signed-off-by: Minchan Kim <[e-mail]>
Cc: Jerome Marchand <[e-mail]>
Cc: Nitin Gupta <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

drivers/block/zram/zram_drv.c

···
 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)
···
 		goto free_table;
 	}
 
-	rwlock_init(&meta->tb_lock);
 	return meta;
 
 free_table:
···
 	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;
···
 
 	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)
···
 	unsigned long handle;
 	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;
 	}
···
 	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)) {
···
 	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 */
···
 	if (page_zero_filled(uncmem)) {
 		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;
···
 	 * 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);
···
 			     int offset, struct bio *bio)
 {
 	size_t n = bio->bi_iter.bi_size;
+	struct zram_meta *meta = zram->meta;
 
 	/*
 	 * zram manages data in physical block size units. Because logical block
···
 	}
 
 	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);
 		index++;
 		n -= PAGE_SIZE;
 	}
···
 	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);
 }
 

drivers/block/zram/zram_drv.h

···
 #define ZRAM_SECTOR_PER_LOGICAL_BLOCK	\
 	(1 << (ZRAM_LOGICAL_BLOCK_SHIFT - SECTOR_SHIFT))
 
-/* Flags for zram pages (table[page_no].flags) */
+
+/*
+ * 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_ZERO = ZRAM_FLAG_SHIFT + 1,
+	ZRAM_ACCESS,	/* page in now accessed */
 
 	__NR_ZRAM_PAGEFLAGS,
 };
···
 /* Allocated for each disk page */
 struct zram_table_entry {
 	unsigned long handle;
-	u16 size;	/* object size (excluding header) */
-	u8 flags;
-} __aligned(4);
+	unsigned long value;
+};
 
 struct zram_stats {
 	atomic64_t compr_data_size;	/* compressed size of pages stored */
···
 };
 
 struct zram_meta {
-	rwlock_t tb_lock;	/* protect table */
 	struct zram_table_entry *table;
 	struct zs_pool *mem_pool;
 };