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:
  jbd2: update transaction t_state to T_COMMIT fix
  ext4: Retry block allocation if new blocks are allocated from system zone.
  ext4: mballoc fix mb_normalize_request algorithm for 1KB block size filesystems
  ext4: fix typos in messages and comments (journalled -> journaled)
  ext4: fix synchronization of quota files in journal=data mode
  ext4: Fix mount messages when quota disabled
  ext4: correct mount option parsing to detect when quota options can be changed

4 files changed, 116 insertions, 49 deletions

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index da994374ec3..30494c5da84 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -287,11 +287,11 @@ read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 			    (int)block_group, (unsigned long long)bitmap_blk);
 		return NULL;
 	}
-	if (!ext4_valid_block_bitmap(sb, desc, block_group, bh)) {
-		put_bh(bh);
-		return NULL;
-	}
-
+	ext4_valid_block_bitmap(sb, desc, block_group, bh);
+	/*
+	 * file system mounted not to panic on error,
+	 * continue with corrupt bitmap
+	 */
 	return bh;
 }
 /*
@@ -1770,7 +1770,12 @@ allocated:
 			    "Allocating block in system zone - "
 			    "blocks from %llu, length %lu",
 			     ret_block, num);
-		goto out;
+		/*
+		 * claim_block marked the blocks we allocated
+		 * as in use. So we may want to selectively
+		 * mark some of the blocks as free
+		 */
+		goto retry_alloc;
 	}
 
 	performed_allocation = 1;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index b128bdc0f55..873ad9b3418 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2736,7 +2736,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	struct ext4_sb_info *sbi;
 	struct super_block *sb;
 	ext4_fsblk_t block;
-	int err;
+	int err, len;
 
 	BUG_ON(ac->ac_status != AC_STATUS_FOUND);
 	BUG_ON(ac->ac_b_ex.fe_len <= 0);
@@ -2770,14 +2770,27 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 		+ ac->ac_b_ex.fe_start
 		+ le32_to_cpu(es->s_first_data_block);
 
-	if (block == ext4_block_bitmap(sb, gdp) ||
-			block == ext4_inode_bitmap(sb, gdp) ||
-			in_range(block, ext4_inode_table(sb, gdp),
-				EXT4_SB(sb)->s_itb_per_group)) {
-
+	len = ac->ac_b_ex.fe_len;
+	if (in_range(ext4_block_bitmap(sb, gdp), block, len) ||
+	    in_range(ext4_inode_bitmap(sb, gdp), block, len) ||
+	    in_range(block, ext4_inode_table(sb, gdp),
+		     EXT4_SB(sb)->s_itb_per_group) ||
+	    in_range(block + len - 1, ext4_inode_table(sb, gdp),
+		     EXT4_SB(sb)->s_itb_per_group)) {
 		ext4_error(sb, __func__,
 			   "Allocating block in system zone - block = %llu",
 			   block);
+		/* File system mounted not to panic on error
+		 * Fix the bitmap and repeat the block allocation
+		 * We leak some of the blocks here.
+		 */
+		mb_set_bits(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group),
+				bitmap_bh->b_data, ac->ac_b_ex.fe_start,
+				ac->ac_b_ex.fe_len);
+		err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+		if (!err)
+			err = -EAGAIN;
+		goto out_err;
 	}
 #ifdef AGGRESSIVE_CHECK
 	{
@@ -2880,12 +2893,11 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	if (size < i_size_read(ac->ac_inode))
 		size = i_size_read(ac->ac_inode);
 
-	/* max available blocks in a free group */
-	max = EXT4_BLOCKS_PER_GROUP(ac->ac_sb) - 1 - 1 -
-				EXT4_SB(ac->ac_sb)->s_itb_per_group;
+	/* max size of free chunks */
+	max = 2 << bsbits;
 
-#define NRL_CHECK_SIZE(req, size, max,bits)	\
-		(req <= (size) || max <= ((size) >> bits))
+#define NRL_CHECK_SIZE(req, size, max, chunk_size)	\
+		(req <= (size) || max <= (chunk_size))
 
 	/* first, try to predict filesize */
 	/* XXX: should this table be tunable? */
@@ -2904,16 +2916,16 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 		size = 512 * 1024;
 	} else if (size <= 1024 * 1024) {
 		size = 1024 * 1024;
-	} else if (NRL_CHECK_SIZE(size, 4 * 1024 * 1024, max, bsbits)) {
+	} else if (NRL_CHECK_SIZE(size, 4 * 1024 * 1024, max, 2 * 1024)) {
 		start_off = ((loff_t)ac->ac_o_ex.fe_logical >>
-						(20 - bsbits)) << 20;
-		size = 1024 * 1024;
-	} else if (NRL_CHECK_SIZE(size, 8 * 1024 * 1024, max, bsbits)) {
+						(21 - bsbits)) << 21;
+		size = 2 * 1024 * 1024;
+	} else if (NRL_CHECK_SIZE(size, 8 * 1024 * 1024, max, 4 * 1024)) {
 		start_off = ((loff_t)ac->ac_o_ex.fe_logical >>
 							(22 - bsbits)) << 22;
 		size = 4 * 1024 * 1024;
 	} else if (NRL_CHECK_SIZE(ac->ac_o_ex.fe_len,
-					(8<<20)>>bsbits, max, bsbits)) {
+					(8<<20)>>bsbits, max, 8 * 1024)) {
 		start_off = ((loff_t)ac->ac_o_ex.fe_logical >>
 							(23 - bsbits)) << 23;
 		size = 8 * 1024 * 1024;
@@ -4033,7 +4045,6 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 
 		ac->ac_op = EXT4_MB_HISTORY_ALLOC;
 		ext4_mb_normalize_request(ac, ar);
-
 repeat:
 		/* allocate space in core */
 		ext4_mb_regular_allocator(ac);
@@ -4047,10 +4058,21 @@ repeat:
 	}
 
 	if (likely(ac->ac_status == AC_STATUS_FOUND)) {
-		ext4_mb_mark_diskspace_used(ac, handle);
-		*errp = 0;
-		block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
-		ar->len = ac->ac_b_ex.fe_len;
+		*errp = ext4_mb_mark_diskspace_used(ac, handle);
+		if (*errp ==  -EAGAIN) {
+			ac->ac_b_ex.fe_group = 0;
+			ac->ac_b_ex.fe_start = 0;
+			ac->ac_b_ex.fe_len = 0;
+			ac->ac_status = AC_STATUS_CONTINUE;
+			goto repeat;
+		} else if (*errp) {
+			ac->ac_b_ex.fe_len = 0;
+			ar->len = 0;
+			ext4_mb_show_ac(ac);
+		} else {
+			block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
+			ar->len = ac->ac_b_ex.fe_len;
+		}
 	} else {
 		freed  = ext4_mb_discard_preallocations(sb, ac->ac_o_ex.fe_len);
 		if (freed)
@@ -4237,6 +4259,8 @@ do_more:
 		ext4_error(sb, __func__,
 			   "Freeing blocks in system zone - "
 			   "Block = %lu, count = %lu", block, count);
+		/* err = 0. ext4_std_error should be a no op */
+		goto error_return;
 	}
 
 	BUFFER_TRACE(bitmap_bh, "getting write access");
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 52dd0679a4e..09d9359c805 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -979,7 +979,7 @@ static int parse_options (char *options, struct super_block *sb,
 	int data_opt = 0;
 	int option;
 #ifdef CONFIG_QUOTA
-	int qtype;
+	int qtype, qfmt;
 	char *qname;
 #endif
 
@@ -1162,9 +1162,11 @@ static int parse_options (char *options, struct super_block *sb,
 		case Opt_grpjquota:
 			qtype = GRPQUOTA;
 set_qf_name:
-			if (sb_any_quota_enabled(sb)) {
+			if ((sb_any_quota_enabled(sb) ||
+			     sb_any_quota_suspended(sb)) &&
+			    !sbi->s_qf_names[qtype]) {
 				printk(KERN_ERR
-					"EXT4-fs: Cannot change journalled "
+					"EXT4-fs: Cannot change journaled "
 					"quota options when quota turned on.\n");
 				return 0;
 			}
@@ -1200,9 +1202,11 @@ set_qf_name:
 		case Opt_offgrpjquota:
 			qtype = GRPQUOTA;
 clear_qf_name:
-			if (sb_any_quota_enabled(sb)) {
+			if ((sb_any_quota_enabled(sb) ||
+			     sb_any_quota_suspended(sb)) &&
+			    sbi->s_qf_names[qtype]) {
 				printk(KERN_ERR "EXT4-fs: Cannot change "
-					"journalled quota options when "
+					"journaled quota options when "
 					"quota turned on.\n");
 				return 0;
 			}
@@ -1213,10 +1217,20 @@ clear_qf_name:
 			sbi->s_qf_names[qtype] = NULL;
 			break;
 		case Opt_jqfmt_vfsold:
-			sbi->s_jquota_fmt = QFMT_VFS_OLD;
-			break;
+			qfmt = QFMT_VFS_OLD;
+			goto set_qf_format;
 		case Opt_jqfmt_vfsv0:
-			sbi->s_jquota_fmt = QFMT_VFS_V0;
+			qfmt = QFMT_VFS_V0;
+set_qf_format:
+			if ((sb_any_quota_enabled(sb) ||
+			     sb_any_quota_suspended(sb)) &&
+			    sbi->s_jquota_fmt != qfmt) {
+				printk(KERN_ERR "EXT4-fs: Cannot change "
+					"journaled quota options when "
+					"quota turned on.\n");
+				return 0;
+			}
+			sbi->s_jquota_fmt = qfmt;
 			break;
 		case Opt_quota:
 		case Opt_usrquota:
@@ -1241,6 +1255,9 @@ clear_qf_name:
 		case Opt_quota:
 		case Opt_usrquota:
 		case Opt_grpquota:
+			printk(KERN_ERR
+				"EXT4-fs: quota options not supported.\n");
+			break;
 		case Opt_usrjquota:
 		case Opt_grpjquota:
 		case Opt_offusrjquota:
@@ -1248,7 +1265,7 @@ clear_qf_name:
 		case Opt_jqfmt_vfsold:
 		case Opt_jqfmt_vfsv0:
 			printk(KERN_ERR
-				"EXT4-fs: journalled quota options not "
+				"EXT4-fs: journaled quota options not "
 				"supported.\n");
 			break;
 		case Opt_noquota:
@@ -1333,14 +1350,14 @@ clear_qf_name:
 		}
 
 		if (!sbi->s_jquota_fmt) {
-			printk(KERN_ERR "EXT4-fs: journalled quota format "
+			printk(KERN_ERR "EXT4-fs: journaled quota format "
 					"not specified.\n");
 			return 0;
 		}
 	} else {
 		if (sbi->s_jquota_fmt) {
-			printk(KERN_ERR "EXT4-fs: journalled quota format "
-					"specified with no journalling "
+			printk(KERN_ERR "EXT4-fs: journaled quota format "
+					"specified with no journaling "
 					"enabled.\n");
 			return 0;
 		}
@@ -1581,7 +1598,7 @@ static void ext4_orphan_cleanup (struct super_block * sb,
 			int ret = ext4_quota_on_mount(sb, i);
 			if (ret < 0)
 				printk(KERN_ERR
-					"EXT4-fs: Cannot turn on journalled "
+					"EXT4-fs: Cannot turn on journaled "
 					"quota: error %d\n", ret);
 		}
 	}
@@ -3106,7 +3123,7 @@ static int ext4_release_dquot(struct dquot *dquot)
 
 static int ext4_mark_dquot_dirty(struct dquot *dquot)
 {
-	/* Are we journalling quotas? */
+	/* Are we journaling quotas? */
 	if (EXT4_SB(dquot->dq_sb)->s_qf_names[USRQUOTA] ||
 	    EXT4_SB(dquot->dq_sb)->s_qf_names[GRPQUOTA]) {
 		dquot_mark_dquot_dirty(dquot);
@@ -3153,23 +3170,42 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 
 	if (!test_opt(sb, QUOTA))
 		return -EINVAL;
-	/* Not journalling quota? */
-	if ((!EXT4_SB(sb)->s_qf_names[USRQUOTA] &&
-	    !EXT4_SB(sb)->s_qf_names[GRPQUOTA]) || remount)
+	/* When remounting, no checks are needed and in fact, path is NULL */
+	if (remount)
 		return vfs_quota_on(sb, type, format_id, path, remount);
+
 	err = path_lookup(path, LOOKUP_FOLLOW, &nd);
 	if (err)
 		return err;
+
 	/* Quotafile not on the same filesystem? */
 	if (nd.path.mnt->mnt_sb != sb) {
 		path_put(&nd.path);
 		return -EXDEV;
 	}
-	/* Quotafile not of fs root? */
-	if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode)
-		printk(KERN_WARNING
-			"EXT4-fs: Quota file not on filesystem root. "
-			"Journalled quota will not work.\n");
+	/* Journaling quota? */
+	if (EXT4_SB(sb)->s_qf_names[type]) {
+		/* Quotafile not of fs root? */
+		if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode)
+			printk(KERN_WARNING
+				"EXT4-fs: Quota file not on filesystem root. "
+				"Journaled quota will not work.\n");
+ 	}
+
+	/*
+	 * When we journal data on quota file, we have to flush journal to see
+	 * all updates to the file when we bypass pagecache...
+	 */
+	if (ext4_should_journal_data(nd.path.dentry->d_inode)) {
+		/*
+		 * We don't need to lock updates but journal_flush() could
+		 * otherwise be livelocked...
+		 */
+		jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
+		jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+	}
+
 	path_put(&nd.path);
 	return vfs_quota_on(sb, type, format_id, path, remount);
 }
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index e0139786f71..4d99685fdce 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -560,7 +560,9 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	 * transaction!  Now comes the tricky part: we need to write out
 	 * metadata.  Loop over the transaction's entire buffer list:
 	 */
+	spin_lock(&journal->j_state_lock);
 	commit_transaction->t_state = T_COMMIT;
+	spin_unlock(&journal->j_state_lock);
 
 	stats.u.run.rs_logging = jiffies;
 	stats.u.run.rs_flushing = jbd2_time_diff(stats.u.run.rs_flushing,