1 files changed, 63 insertions, 30 deletions

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 8fd0b3cdab4c..8ff4b9192a9f 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -185,7 +185,7 @@ static int ext4_init_block_bitmap(struct super_block *sb,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_fsblk_t start, tmp;
 
-	J_ASSERT_BH(bh, buffer_locked(bh));
+	ASSERT(buffer_locked(bh));
 
 	/* If checksum is bad mark all blocks used to prevent allocation
 	 * essentially implementing a per-group read-only flag. */
@@ -239,7 +239,7 @@ unsigned ext4_free_clusters_after_init(struct super_block *sb,
 				       ext4_group_t block_group,
 				       struct ext4_group_desc *gdp)
 {
-	return num_clusters_in_group(sb, block_group) - 
+	return num_clusters_in_group(sb, block_group) -
 		ext4_num_overhead_clusters(sb, block_group, gdp);
 }
 
@@ -368,7 +368,12 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
 				      struct buffer_head *bh)
 {
 	ext4_fsblk_t	blk;
-	struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
+	struct ext4_group_info *grp;
+
+	if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)
+		return 0;
+
+	grp = ext4_get_group_info(sb, block_group);
 
 	if (buffer_verified(bh))
 		return 0;
@@ -406,14 +411,16 @@ verified:
  * ext4_read_block_bitmap_nowait()
  * @sb:			super block
  * @block_group:	given block group
+ * @ignore_locked:	ignore locked buffers
  *
  * Read the bitmap for a given block_group,and validate the
  * bits for block/inode/inode tables are set in the bitmaps
  *
- * Return buffer_head on success or NULL in case of failure.
+ * Return buffer_head on success or an ERR_PTR in case of failure.
  */
 struct buffer_head *
-ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
+ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group,
+			      bool ignore_locked)
 {
 	struct ext4_group_desc *desc;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -441,6 +448,12 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 		return ERR_PTR(-ENOMEM);
 	}
 
+	if (ignore_locked && buffer_locked(bh)) {
+		/* buffer under IO already, return if called for prefetching */
+		put_bh(bh);
+		return NULL;
+	}
+
 	if (bitmap_uptodate(bh))
 		goto verify;
 
@@ -487,10 +500,10 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 	 * submit the buffer_head for reading
 	 */
 	set_buffer_new(bh);
-	trace_ext4_read_block_bitmap_load(sb, block_group);
-	bh->b_end_io = ext4_end_bitmap_read;
-	get_bh(bh);
-	submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh);
+	trace_ext4_read_block_bitmap_load(sb, block_group, ignore_locked);
+	ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO |
+			    (ignore_locked ? REQ_RAHEAD : 0),
+			    ext4_end_bitmap_read);
 	return bh;
 verify:
 	err = ext4_validate_block_bitmap(sb, desc, block_group, bh);
@@ -502,7 +515,7 @@ out:
 	return ERR_PTR(err);
 }
 
-/* Returns 0 on success, 1 on error */
+/* Returns 0 on success, -errno on error */
 int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group,
 			   struct buffer_head *bh)
 {
@@ -516,10 +529,9 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group,
 	wait_on_buffer(bh);
 	ext4_simulate_fail_bh(sb, bh, EXT4_SIM_BBITMAP_EIO);
 	if (!buffer_uptodate(bh)) {
-		ext4_set_errno(sb, EIO);
-		ext4_error(sb, "Cannot read block bitmap - "
-			   "block_group = %u, block_bitmap = %llu",
-			   block_group, (unsigned long long) bh->b_blocknr);
+		ext4_error_err(sb, EIO, "Cannot read block bitmap - "
+			       "block_group = %u, block_bitmap = %llu",
+			       block_group, (unsigned long long) bh->b_blocknr);
 		ext4_mark_group_bitmap_corrupted(sb, block_group,
 					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 		return -EIO;
@@ -535,7 +547,7 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 	struct buffer_head *bh;
 	int err;
 
-	bh = ext4_read_block_bitmap_nowait(sb, block_group);
+	bh = ext4_read_block_bitmap_nowait(sb, block_group, false);
 	if (IS_ERR(bh))
 		return bh;
 	err = ext4_wait_block_bitmap(sb, block_group, bh);
@@ -615,27 +627,47 @@ int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
 
 /**
  * ext4_should_retry_alloc() - check if a block allocation should be retried
- * @sb:			super block
- * @retries:		number of attemps has been made
+ * @sb:			superblock
+ * @retries:		number of retry attempts made so far
  *
- * ext4_should_retry_alloc() is called when ENOSPC is returned, and if
- * it is profitable to retry the operation, this function will wait
- * for the current or committing transaction to complete, and then
- * return TRUE.  We will only retry once.
+ * ext4_should_retry_alloc() is called when ENOSPC is returned while
+ * attempting to allocate blocks.  If there's an indication that a pending
+ * journal transaction might free some space and allow another attempt to
+ * succeed, this function will wait for the current or committing transaction
+ * to complete and then return TRUE.
  */
 int ext4_should_retry_alloc(struct super_block *sb, int *retries)
 {
-	if (!ext4_has_free_clusters(EXT4_SB(sb), 1, 0) ||
-	    (*retries)++ > 1 ||
-	    !EXT4_SB(sb)->s_journal)
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	if (!sbi->s_journal)
 		return 0;
 
-	smp_mb();
-	if (EXT4_SB(sb)->s_mb_free_pending == 0)
+	if (++(*retries) > 3) {
+		percpu_counter_inc(&sbi->s_sra_exceeded_retry_limit);
 		return 0;
+	}
+
+	/*
+	 * if there's no indication that blocks are about to be freed it's
+	 * possible we just missed a transaction commit that did so
+	 */
+	smp_mb();
+	if (sbi->s_mb_free_pending == 0) {
+		if (test_opt(sb, DISCARD)) {
+			atomic_inc(&sbi->s_retry_alloc_pending);
+			flush_work(&sbi->s_discard_work);
+			atomic_dec(&sbi->s_retry_alloc_pending);
+		}
+		return ext4_has_free_clusters(sbi, 1, 0);
+	}
 
-	jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
-	jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
+	/*
+	 * it's possible we've just missed a transaction commit here,
+	 * so ignore the returned status
+	 */
+	ext4_debug("%s: retrying operation after ENOSPC\n", sb->s_id);
+	(void) jbd2_journal_force_commit_nested(sbi->s_journal);
 	return 1;
 }
 
@@ -904,10 +936,11 @@ ext4_fsblk_t ext4_inode_to_goal_block(struct inode *inode)
 		return bg_start;
 
 	if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
-		colour = (current->pid % 16) *
+		colour = (task_pid_nr(current) % 16) *
 			(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
 	else
-		colour = (current->pid % 16) * ((last_block - bg_start) / 16);
+		colour = (task_pid_nr(current) % 16) *
+			((last_block - bg_start) / 16);
 	return bg_start + colour;
 }