Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: enable barriers by default
  jbd2: Fix barrier fallback code to re-lock the buffer head
  ext4: Display the journal_async_commit mount option in /proc/mounts
  jbd2: If a journal checksum error is detected, propagate the error to ext4
  jbd2: Fix memory leak when verifying checksums in the journal
  ext4: fix online resize bug
  ext4: Fix uninit block group initialization with FLEX_BG
  ext4: Fix use of uninitialized data with debug enabled.

Documentation/filesystems/ext4.txt

@@ -139,8 +139,16 @@ commit=nrsec	(*)	Ext4 can be told to sync all its data and metadata
 			Setting it to very large values will improve
 			performance.
 
-barrier=1		This enables/disables barriers.  barrier=0 disables
+barrier=<0|1(*)>	This enables/disables the use of write barriers in
-			it, barrier=1 enables it.
+			the jbd code.  barrier=0 disables, barrier=1 enables.
+			This also requires an IO stack which can support
+			barriers, and if jbd gets an error on a barrier
+			write, it will disable again with a warning.
+			Write barriers enforce proper on-disk ordering
+			of journal commits, making volatile disk write caches
+			safe to use, at some performance penalty.  If
+			your disks are battery-backed in one way or another,
+			disabling barriers may safely improve performance.
 
 orlov		(*)	This enables the new Orlov block allocator. It is
 			enabled by default.

fs/ext4/balloc.c

@@ -43,6 +43,46 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
 
 }
 
+static int ext4_block_in_group(struct super_block *sb, ext4_fsblk_t block,
+			ext4_group_t block_group)
+{
+	ext4_group_t actual_group;
+	ext4_get_group_no_and_offset(sb, block, &actual_group, 0);
+	if (actual_group == block_group)
+		return 1;
+	return 0;
+}
+
+static int ext4_group_used_meta_blocks(struct super_block *sb,
+				ext4_group_t block_group)
+{
+	ext4_fsblk_t tmp;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	/* block bitmap, inode bitmap, and inode table blocks */
+	int used_blocks = sbi->s_itb_per_group + 2;
+
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
+		struct ext4_group_desc *gdp;
+		struct buffer_head *bh;
+
+		gdp = ext4_get_group_desc(sb, block_group, &bh);
+		if (!ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp),
+					block_group))
+			used_blocks--;
+
+		if (!ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp),
+					block_group))
+			used_blocks--;
+
+		tmp = ext4_inode_table(sb, gdp);
+		for (; tmp < ext4_inode_table(sb, gdp) +
+				sbi->s_itb_per_group; tmp++) {
+			if (!ext4_block_in_group(sb, tmp, block_group))
+				used_blocks -= 1;
+		}
+	}
+	return used_blocks;
+}
 /* Initializes an uninitialized block bitmap if given, and returns the
  * number of blocks free in the group. */
 unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
@@ -105,20 +145,34 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 	free_blocks = group_blocks - bit_max;
 
 	if (bh) {
-		ext4_fsblk_t start;
+		ext4_fsblk_t start, tmp;
+		int flex_bg = 0;
 
 		for (bit = 0; bit < bit_max; bit++)
 			ext4_set_bit(bit, bh->b_data);
 
 		start = ext4_group_first_block_no(sb, block_group);
 
-		/* Set bits for block and inode bitmaps, and inode table */
+		if (EXT4_HAS_INCOMPAT_FEATURE(sb,
-		ext4_set_bit(ext4_block_bitmap(sb, gdp) - start, bh->b_data);
+					      EXT4_FEATURE_INCOMPAT_FLEX_BG))
-		ext4_set_bit(ext4_inode_bitmap(sb, gdp) - start, bh->b_data);
+			flex_bg = 1;
-		for (bit = (ext4_inode_table(sb, gdp) - start),
-		     bit_max = bit + sbi->s_itb_per_group; bit < bit_max; bit++)
-			ext4_set_bit(bit, bh->b_data);
 
+		/* Set bits for block and inode bitmaps, and inode table */
+		tmp = ext4_block_bitmap(sb, gdp);
+		if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+			ext4_set_bit(tmp - start, bh->b_data);
+
+		tmp = ext4_inode_bitmap(sb, gdp);
+		if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+			ext4_set_bit(tmp - start, bh->b_data);
+
+		tmp = ext4_inode_table(sb, gdp);
+		for (; tmp < ext4_inode_table(sb, gdp) +
+				sbi->s_itb_per_group; tmp++) {
+			if (!flex_bg ||
+				ext4_block_in_group(sb, tmp, block_group))
+				ext4_set_bit(tmp - start, bh->b_data);
+		}
 		/*
 		 * Also if the number of blocks within the group is
 		 * less than the blocksize * 8 ( which is the size
@@ -126,8 +180,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 		 */
 		mark_bitmap_end(group_blocks, sb->s_blocksize * 8, bh->b_data);
 	}
-
+	return free_blocks - ext4_group_used_meta_blocks(sb, block_group);
-	return free_blocks - sbi->s_itb_per_group - 2;
 }
 
 

fs/ext4/mballoc.c

@@ -2745,8 +2745,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	sbi = EXT4_SB(sb);
 	es = sbi->s_es;
 
-	ext4_debug("using block group %lu(%d)\n", ac->ac_b_ex.fe_group,
-			gdp->bg_free_blocks_count);
 
 	err = -EIO;
 	bitmap_bh = read_block_bitmap(sb, ac->ac_b_ex.fe_group);
@@ -2762,6 +2760,9 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	if (!gdp)
 		goto out_err;
 
+	ext4_debug("using block group %lu(%d)\n", ac->ac_b_ex.fe_group,
+			gdp->bg_free_blocks_count);
+
 	err = ext4_journal_get_write_access(handle, gdp_bh);
 	if (err)
 		goto out_err;
@@ -3094,8 +3095,7 @@ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac,
 static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac,
 				struct ext4_prealloc_space *pa)
 {
-	unsigned len = ac->ac_o_ex.fe_len;
+	unsigned int len = ac->ac_o_ex.fe_len;
-
 	ext4_get_group_no_and_offset(ac->ac_sb, pa->pa_pstart,
 					&ac->ac_b_ex.fe_group,
 					&ac->ac_b_ex.fe_start);

fs/ext4/resize.c

@@ -563,7 +563,8 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
 	}
 
 	blk = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + EXT4_SB(sb)->s_gdb_count;
-	data = (__le32 *)dind->b_data + EXT4_SB(sb)->s_gdb_count;
+	data = (__le32 *)dind->b_data + (EXT4_SB(sb)->s_gdb_count %
+					 EXT4_ADDR_PER_BLOCK(sb));
 	end = (__le32 *)dind->b_data + EXT4_ADDR_PER_BLOCK(sb);
 
 	/* Get each reserved primary GDT block and verify it holds backups */

fs/ext4/super.c

@@ -671,6 +671,7 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	unsigned long def_mount_opts;
 	struct super_block *sb = vfs->mnt_sb;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	journal_t *journal = sbi->s_journal;
 	struct ext4_super_block *es = sbi->s_es;
 
 	def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
@@ -729,8 +730,15 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_printf(seq, ",commit=%u",
 			   (unsigned) (sbi->s_commit_interval / HZ));
 	}
-	if (test_opt(sb, BARRIER))
+	/*
-		seq_puts(seq, ",barrier=1");
+	 * We're changing the default of barrier mount option, so
+	 * let's always display its mount state so it's clear what its
+	 * status is.
+	 */
+	seq_puts(seq, ",barrier=");
+	seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0");
+	if (test_opt(sb, JOURNAL_ASYNC_COMMIT))
+		seq_puts(seq, ",journal_async_commit");
 	if (test_opt(sb, NOBH))
 		seq_puts(seq, ",nobh");
 	if (!test_opt(sb, EXTENTS))
@@ -1907,6 +1915,7 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
 	sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
 
 	set_opt(sbi->s_mount_opt, RESERVATION);
+	set_opt(sbi->s_mount_opt, BARRIER);
 
 	/*
 	 * turn on extents feature by default in ext4 filesystem
@@ -2189,6 +2198,29 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
 	    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
 		if (ext4_load_journal(sb, es, journal_devnum))
 			goto failed_mount3;
+		if (!(sb->s_flags & MS_RDONLY) &&
+		    EXT4_SB(sb)->s_journal->j_failed_commit) {
+			printk(KERN_CRIT "EXT4-fs error (device %s): "
+			       "ext4_fill_super: Journal transaction "
+			       "%u is corrupt\n", sb->s_id, 
+			       EXT4_SB(sb)->s_journal->j_failed_commit);
+			if (test_opt (sb, ERRORS_RO)) {
+				printk (KERN_CRIT
+					"Mounting filesystem read-only\n");
+				sb->s_flags |= MS_RDONLY;
+				EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+				es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
+			}
+			if (test_opt(sb, ERRORS_PANIC)) {
+				EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+				es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
+				ext4_commit_super(sb, es, 1);
+				printk(KERN_CRIT
+				       "EXT4-fs (device %s): mount failed\n",
+				      sb->s_id);
+				goto failed_mount4;
+			}
+		}
 	} else if (journal_inum) {
 		if (ext4_create_journal(sb, es, journal_inum))
 			goto failed_mount3;

fs/jbd2/commit.c

@@ -168,6 +168,7 @@ static int journal_submit_commit_record(journal_t *journal,
 		spin_unlock(&journal->j_state_lock);
 
 		/* And try again, without the barrier */
+		lock_buffer(bh);
 		set_buffer_uptodate(bh);
 		set_buffer_dirty(bh);
 		ret = submit_bh(WRITE, bh);

fs/jbd2/recovery.c

@@ -344,6 +344,7 @@ static int calc_chksums(journal_t *journal, struct buffer_head *bh,
 			*crc32_sum = crc32_be(*crc32_sum, (void *)obh->b_data,
 				     obh->b_size);
 		}
+		put_bh(obh);
 	}
 	return 0;
 }
@@ -610,9 +611,8 @@ static int do_one_pass(journal_t *journal,
 				chksum_err = chksum_seen = 0;
 
 				if (info->end_transaction) {
-					printk(KERN_ERR "JBD: Transaction %u "
+					journal->j_failed_commit =
-						"found to be corrupt.\n",
+						info->end_transaction;
-						next_commit_ID - 1);
 					brelse(bh);
 					break;
 				}
@@ -643,10 +643,8 @@ static int do_one_pass(journal_t *journal,
 
 					if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
 					   JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)){
-						printk(KERN_ERR
+						journal->j_failed_commit =
-						       "JBD: Transaction %u "
+							next_commit_ID;
-						       "found to be corrupt.\n",
-						       next_commit_ID);
 						brelse(bh);
 						break;
 					}

include/linux/jbd2.h

@@ -919,6 +919,9 @@ struct journal_s
 	struct proc_dir_entry	*j_proc_entry;
 	struct transaction_stats_s j_stats;
 
+	/* Failed journal commit ID */
+	unsigned int		j_failed_commit;
+
 	/*
 	 * An opaque pointer to fs-private information.  ext3 puts its
 	 * superblock pointer here