zram: introduce zram->tb_lock

Currently, the zram table is protected by zram->lock but it's rather
coarse-grained lock and it makes hard for scalibility.

Let's use own rwlock instead of depending on zram->lock.  This patch
adds new locking so obviously, it would make slow but this patch is just
prepartion for removing coarse-grained rw_semaphore(ie, zram->lock)
which is hurdle about zram scalability.

Final patch in this patchset series will remove the lock from read-path
and change rw_semaphore with mutex in write path.  With bonus, we could
drop pending slot free mess in next patch.

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, 23 insertions, 6 deletions

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 9ab884999420..24e6426cf258 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -140,6 +140,7 @@ static ssize_t mem_used_total_show(struct device *dev,
         return sprintf(buf, "%llu\n", val);
 }
 
+/* flag operations needs meta->tb_lock */
 static int zram_test_flag(struct zram_meta *meta, u32 index,
                         enum zram_pageflags flag)
 {
@@ -228,6 +229,7 @@ static struct zram_meta *zram_meta_alloc(u64 disksize)
                 goto free_table;
         }
 
+        rwlock_init(&meta->tb_lock);
         return meta;
 
 free_table:
@@ -280,6 +282,7 @@ static void handle_zero_page(struct bio_vec *bvec)
         flush_dcache_page(page);
 }
 
+/* NOTE: caller should hold meta->tb_lock with write-side */
 static void zram_free_page(struct zram *zram, size_t index)
 {
         struct zram_meta *meta = zram->meta;
@@ -319,20 +322,26 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
         size_t clen = PAGE_SIZE;
         unsigned char *cmem;
         struct zram_meta *meta = zram->meta;
-        unsigned long handle = meta->table[index].handle;
+        unsigned long handle;
+        u16 size;
+
+        read_lock(&meta->tb_lock);
+        handle = meta->table[index].handle;
+        size = meta->table[index].size;
 
         if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) {
+                read_unlock(&meta->tb_lock);
                 clear_page(mem);
                 return 0;
         }
 
         cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO);
-        if (meta->table[index].size == PAGE_SIZE)
+        if (size == PAGE_SIZE)
                 copy_page(mem, cmem);
         else
-                ret = lzo1x_decompress_safe(cmem, meta->table[index].size,
-                                                mem, &clen);
+                ret = lzo1x_decompress_safe(cmem, size, mem, &clen);
         zs_unmap_object(meta->mem_pool, handle);
+        read_unlock(&meta->tb_lock);
 
         /* Should NEVER happen. Return bio error if it does. */
         if (unlikely(ret != LZO_E_OK)) {
@@ -353,11 +362,14 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
         struct zram_meta *meta = zram->meta;
         page = bvec->bv_page;
 
+        read_lock(&meta->tb_lock);
         if (unlikely(!meta->table[index].handle) ||
                         zram_test_flag(meta, index, ZRAM_ZERO)) {
+                read_unlock(&meta->tb_lock);
                 handle_zero_page(bvec);
                 return 0;
         }
+        read_unlock(&meta->tb_lock);
 
         if (is_partial_io(bvec))
                 /* Use  a temporary buffer to decompress the page */
@@ -433,10 +445,12 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
         if (page_zero_filled(uncmem)) {
                 kunmap_atomic(user_mem);
                 /* Free memory associated with this sector now. */
+                write_lock(&zram->meta->tb_lock);
                 zram_free_page(zram, index);
+                zram_set_flag(meta, index, ZRAM_ZERO);
+                write_unlock(&zram->meta->tb_lock);
 
                 atomic_inc(&zram->stats.pages_zero);
-                zram_set_flag(meta, index, ZRAM_ZERO);
                 ret = 0;
                 goto out;
         }
@@ -486,10 +500,12 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
          * Free memory associated with this sector
          * before overwriting unused sectors.
          */
+        write_lock(&zram->meta->tb_lock);
         zram_free_page(zram, index);
 
         meta->table[index].handle = handle;
         meta->table[index].size = clen;
+        write_unlock(&zram->meta->tb_lock);
 
         /* Update stats */
         atomic64_add(clen, &zram->stats.compr_size);
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 81b0170de369..c3f453f04974 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -83,6 +83,7 @@ struct zram_stats {
 };
 
 struct zram_meta {
+        rwlock_t tb_lock;       /* protect table */
         void *compress_workmem;
         void *compress_buffer;
         struct table *table;
@@ -96,7 +97,7 @@ struct zram_slot_free {
 
 struct zram {
         struct zram_meta *meta;
-        struct rw_semaphore lock; /* protect compression buffers, table,
+        struct rw_semaphore lock; /* protect compression buffers,
                                    * reads and writes
                                    */