Staging: zram: Replace mutex lock by a R/W semaphore

Currently, nothing protects zram table from concurrent access.
For instance, ZRAM_UNCOMPRESSED bit can be cleared by zram_free_page()
called from a concurrent write between the time ZRAM_UNCOMPRESSED has
been set and the time it is tested to unmap KM_USER0 in
zram_bvec_write(). This ultimately leads to kernel panic.

Also, a read request can occurs when the page has been freed by a
running write request and before it has been updated, leading to
zero filled block being incorrectly read and "Read before write"
error message.

This patch replace the current mutex by a rw_semaphore. It extends
the protection to zram table (currently, only compression buffers are
protected) and read requests (currently, only write requests are
protected).

Signed-off-by: Jerome Marchand <jmarchan@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

2 files changed, 15 insertions, 14 deletions

diff --git a/drivers/staging/zram/zram_drv.c b/drivers/staging/zram/zram_drv.c
index 54ad29d6cf46..c5fdc5536186 100644
--- a/drivers/staging/zram/zram_drv.c
+++ b/drivers/staging/zram/zram_drv.c
@@ -359,8 +359,6 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 	    zram_test_flag(zram, index, ZRAM_ZERO))
 		zram_free_page(zram, index);
 
-	mutex_lock(&zram->lock);
-
 	user_mem = kmap_atomic(page, KM_USER0);
 
 	if (is_partial_io(bvec))
@@ -371,7 +369,6 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 
 	if (page_zero_filled(uncmem)) {
 		kunmap_atomic(user_mem, KM_USER0);
-		mutex_unlock(&zram->lock);
 		if (is_partial_io(bvec))
 			kfree(uncmem);
 		zram_stat_inc(&zram->stats.pages_zero);
@@ -388,7 +385,6 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 			kfree(uncmem);
 
 	if (unlikely(ret != LZO_E_OK)) {
-		mutex_unlock(&zram->lock);
 		pr_err("Compression failed! err=%d\n", ret);
 		goto out;
 	}
@@ -402,7 +398,6 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 		clen = PAGE_SIZE;
 		page_store = alloc_page(GFP_NOIO | __GFP_HIGHMEM);
 		if (unlikely(!page_store)) {
-			mutex_unlock(&zram->lock);
 			pr_info("Error allocating memory for "
 				"incompressible page: %u\n", index);
 			ret = -ENOMEM;
@@ -420,7 +415,6 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 	if (xv_malloc(zram->mem_pool, clen + sizeof(*zheader),
 		      &zram->table[index].page, &store_offset,
 		      GFP_NOIO | __GFP_HIGHMEM)) {
-		mutex_unlock(&zram->lock);
 		pr_info("Error allocating memory for compressed "
 			"page: %u, size=%zu\n", index, clen);
 		ret = -ENOMEM;
@@ -454,8 +448,6 @@ memstore:
 	if (clen <= PAGE_SIZE / 2)
 		zram_stat_inc(&zram->stats.good_compress);
 
-	mutex_unlock(&zram->lock);
-
 	return 0;
 
 out:
@@ -467,10 +459,19 @@ out:
 static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
 			int offset, struct bio *bio, int rw)
 {
-	if (rw == READ)
-		return zram_bvec_read(zram, bvec, index, offset, bio);
+	int ret;
 
-	return zram_bvec_write(zram, bvec, index, offset);
+	if (rw == READ) {
+		down_read(&zram->lock);
+		ret = zram_bvec_read(zram, bvec, index, offset, bio);
+		up_read(&zram->lock);
+	} else {
+		down_write(&zram->lock);
+		ret = zram_bvec_write(zram, bvec, index, offset);
+		up_write(&zram->lock);
+	}
+
+	return ret;
 }
 
 static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
@@ -701,7 +702,7 @@ static int create_device(struct zram *zram, int device_id)
 {
 	int ret = 0;
 
-	mutex_init(&zram->lock);
+	init_rwsem(&zram->lock);
 	mutex_init(&zram->init_lock);
 	spin_lock_init(&zram->stat64_lock);
 
diff --git a/drivers/staging/zram/zram_drv.h b/drivers/staging/zram/zram_drv.h
index 8acf9eba79c8..abe5221c100d 100644
--- a/drivers/staging/zram/zram_drv.h
+++ b/drivers/staging/zram/zram_drv.h
@@ -107,8 +107,8 @@ struct zram {
 	void *compress_buffer;
 	struct table *table;
 	spinlock_t stat64_lock;	/* protect 64-bit stats */
-	struct mutex lock;	/* protect compression buffers against
-				 * concurrent writes */
+	struct rw_semaphore lock; /* protect compression buffers and table
+				   * against concurrent read and writes */
 	struct request_queue *queue;
 	struct gendisk *disk;
 	int init_done;