4 files changed, 145 insertions, 96 deletions
diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index a8ba7e83127..a7571303110 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -80,13 +80,57 @@ struct ext3_group_desc * ext3_get_group_desc(struct super_block * sb,
 	return desc + offset;
 }
 
+static int ext3_valid_block_bitmap(struct super_block *sb,
+					struct ext3_group_desc *desc,
+					unsigned int block_group,
+					struct buffer_head *bh)
+{
+	ext3_grpblk_t offset;
+	ext3_grpblk_t next_zero_bit;
+	ext3_fsblk_t bitmap_blk;
+	ext3_fsblk_t group_first_block;
+
+	group_first_block = ext3_group_first_block_no(sb, block_group);
+
+	/* check whether block bitmap block number is set */
+	bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
+	offset = bitmap_blk - group_first_block;
+	if (!ext3_test_bit(offset, bh->b_data))
+		/* bad block bitmap */
+		goto err_out;
+
+	/* check whether the inode bitmap block number is set */
+	bitmap_blk = le32_to_cpu(desc->bg_inode_bitmap);
+	offset = bitmap_blk - group_first_block;
+	if (!ext3_test_bit(offset, bh->b_data))
+		/* bad block bitmap */
+		goto err_out;
+
+	/* check whether the inode table block number is set */
+	bitmap_blk = le32_to_cpu(desc->bg_inode_table);
+	offset = bitmap_blk - group_first_block;
+	next_zero_bit = ext3_find_next_zero_bit(bh->b_data,
+				offset + EXT3_SB(sb)->s_itb_per_group,
+				offset);
+	if (next_zero_bit >= offset + EXT3_SB(sb)->s_itb_per_group)
+		/* good bitmap for inode tables */
+		return 1;
+
+err_out:
+	ext3_error(sb, __FUNCTION__,
+			"Invalid block bitmap - "
+			"block_group = %d, block = %lu",
+			block_group, bitmap_blk);
+	return 0;
+}
+
 /**
  * read_block_bitmap()
  * @sb:			super block
  * @block_group:	given block group
  *
- * Read the bitmap for a given block_group, reading into the specified
- * slot in the superblock's bitmap cache.
+ * 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.
  */
@@ -95,17 +139,35 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group)
 {
 	struct ext3_group_desc * desc;
 	struct buffer_head * bh = NULL;
+	ext3_fsblk_t bitmap_blk;
 
-	desc = ext3_get_group_desc (sb, block_group, NULL);
+	desc = ext3_get_group_desc(sb, block_group, NULL);
 	if (!desc)
-		goto error_out;
-	bh = sb_bread(sb, le32_to_cpu(desc->bg_block_bitmap));
-	if (!bh)
-		ext3_error (sb, "read_block_bitmap",
+		return NULL;
+	bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
+	bh = sb_getblk(sb, bitmap_blk);
+	if (unlikely(!bh)) {
+		ext3_error(sb, __FUNCTION__,
 			    "Cannot read block bitmap - "
 			    "block_group = %d, block_bitmap = %u",
 			    block_group, le32_to_cpu(desc->bg_block_bitmap));
-error_out:
+		return NULL;
+	}
+	if (likely(bh_uptodate_or_lock(bh)))
+		return bh;
+
+	if (bh_submit_read(bh) < 0) {
+		brelse(bh);
+		ext3_error(sb, __FUNCTION__,
+			    "Cannot read block bitmap - "
+			    "block_group = %d, block_bitmap = %u",
+			    block_group, le32_to_cpu(desc->bg_block_bitmap));
+		return NULL;
+	}
+	if (!ext3_valid_block_bitmap(sb, desc, block_group, bh)) {
+		brelse(bh);
+		return NULL;
+	}
 	return bh;
 }
 /*
@@ -468,11 +530,13 @@ do_more:
 	    in_range (block, le32_to_cpu(desc->bg_inode_table),
 		      sbi->s_itb_per_group) ||
 	    in_range (block + count - 1, le32_to_cpu(desc->bg_inode_table),
-		      sbi->s_itb_per_group))
+		      sbi->s_itb_per_group)) {
 		ext3_error (sb, "ext3_free_blocks",
 			    "Freeing blocks in system zones - "
 			    "Block = "E3FSBLK", count = %lu",
 			    block, count);
+		goto error_return;
+	}
 
 	/*
 	 * We are about to start releasing blocks in the bitmap,
@@ -1508,7 +1572,7 @@ retry_alloc:
 
 	/*
 	 * Now search the rest of the groups.  We assume that
-	 * i and gdp correctly point to the last group visited.
+	 * group_no and gdp correctly point to the last group visited.
 	 */
 	for (bgi = 0; bgi < ngroups; bgi++) {
 		group_no++;
@@ -1575,11 +1639,13 @@ allocated:
 	    in_range(ret_block, le32_to_cpu(gdp->bg_inode_table),
 		      EXT3_SB(sb)->s_itb_per_group) ||
 	    in_range(ret_block + num - 1, le32_to_cpu(gdp->bg_inode_table),
-		      EXT3_SB(sb)->s_itb_per_group))
+		      EXT3_SB(sb)->s_itb_per_group)) {
 		ext3_error(sb, "ext3_new_block",
 			    "Allocating block in system zone - "
 			    "blocks from "E3FSBLK", length %lu",
 			     ret_block, num);
+		goto out;
+	}
 
 	performed_allocation = 1;
 
@@ -1782,11 +1848,7 @@ static unsigned long ext3_bg_num_gdb_meta(struct super_block *sb, int group)
 
 static unsigned long ext3_bg_num_gdb_nometa(struct super_block *sb, int group)
 {
-	if (EXT3_HAS_RO_COMPAT_FEATURE(sb,
-				EXT3_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
-			!ext3_group_sparse(group))
-		return 0;
-	return EXT3_SB(sb)->s_gdb_count;
+	return ext3_bg_has_super(sb, group) ? EXT3_SB(sb)->s_gdb_count : 0;
 }
 
 /**
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 07753543928..8a9ce2d09bd 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -439,16 +439,14 @@ static ext3_fsblk_t ext3_find_near(struct inode *inode, Indirect *ind)
  *	ext3_find_goal - find a prefered place for allocation.
  *	@inode: owner
  *	@block:  block we want
- *	@chain:  chain of indirect blocks
  *	@partial: pointer to the last triple within a chain
- *	@goal:	place to store the result.
  *
  *	Normally this function find the prefered place for block allocation,
- *	stores it in *@goal and returns zero.
+ *	returns it.
  */
 
 static ext3_fsblk_t ext3_find_goal(struct inode *inode, long block,
-		Indirect chain[4], Indirect *partial)
+				   Indirect *partial)
 {
 	struct ext3_block_alloc_info *block_i;
 
@@ -884,7 +882,7 @@ int ext3_get_blocks_handle(handle_t *handle, struct inode *inode,
 	if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info))
 		ext3_init_block_alloc_info(inode);
 
-	goal = ext3_find_goal(inode, iblock, chain, partial);
+	goal = ext3_find_goal(inode, iblock, partial);
 
 	/* the number of blocks need to allocate for [d,t]indirect blocks */
 	indirect_blks = (chain + depth) - partial - 1;
@@ -941,55 +939,45 @@ out:
 	return err;
 }
 
-#define DIO_CREDITS (EXT3_RESERVE_TRANS_BLOCKS + 32)
+/* Maximum number of blocks we map for direct IO at once. */
+#define DIO_MAX_BLOCKS 4096
+/*
+ * Number of credits we need for writing DIO_MAX_BLOCKS:
+ * We need sb + group descriptor + bitmap + inode -> 4
+ * For B blocks with A block pointers per block we need:
+ * 1 (triple ind.) + (B/A/A + 2) (doubly ind.) + (B/A + 2) (indirect).
+ * If we plug in 4096 for B and 256 for A (for 1KB block size), we get 25.
+ */
+#define DIO_CREDITS 25
 
 static int ext3_get_block(struct inode *inode, sector_t iblock,
 			struct buffer_head *bh_result, int create)
 {
 	handle_t *handle = ext3_journal_current_handle();
-	int ret = 0;
+	int ret = 0, started = 0;
 	unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
 
-	if (!create)
-		goto get_block;		/* A read */
-
-	if (max_blocks == 1)
-		goto get_block;		/* A single block get */
-
-	if (handle->h_transaction->t_state == T_LOCKED) {
-		/*
-		 * Huge direct-io writes can hold off commits for long
-		 * periods of time.  Let this commit run.
-		 */
-		ext3_journal_stop(handle);
-		handle = ext3_journal_start(inode, DIO_CREDITS);
-		if (IS_ERR(handle))
+	if (create && !handle) {	/* Direct IO write... */
+		if (max_blocks > DIO_MAX_BLOCKS)
+			max_blocks = DIO_MAX_BLOCKS;
+		handle = ext3_journal_start(inode, DIO_CREDITS +
+				2 * EXT3_QUOTA_TRANS_BLOCKS(inode->i_sb));
+		if (IS_ERR(handle)) {
 			ret = PTR_ERR(handle);
-		goto get_block;
-	}
-
-	if (handle->h_buffer_credits <= EXT3_RESERVE_TRANS_BLOCKS) {
-		/*
-		 * Getting low on buffer credits...
-		 */
-		ret = ext3_journal_extend(handle, DIO_CREDITS);
-		if (ret > 0) {
-			/*
-			 * Couldn't extend the transaction.  Start a new one.
-			 */
-			ret = ext3_journal_restart(handle, DIO_CREDITS);
+			goto out;
 		}
+		started = 1;
 	}
 
-get_block:
-	if (ret == 0) {
-		ret = ext3_get_blocks_handle(handle, inode, iblock,
+	ret = ext3_get_blocks_handle(handle, inode, iblock,
 					max_blocks, bh_result, create, 0);
-		if (ret > 0) {
-			bh_result->b_size = (ret << inode->i_blkbits);
-			ret = 0;
-		}
+	if (ret > 0) {
+		bh_result->b_size = (ret << inode->i_blkbits);
+		ret = 0;
 	}
+	if (started)
+		ext3_journal_stop(handle);
+out:
 	return ret;
 }
 
@@ -1680,7 +1668,8 @@ static int ext3_releasepage(struct page *page, gfp_t wait)
  * if the machine crashes during the write.
  *
  * If the O_DIRECT write is intantiating holes inside i_size and the machine
- * crashes then stale disk data _may_ be exposed inside the file.
+ * crashes then stale disk data _may_ be exposed inside the file. But current
+ * VFS code falls back into buffered path in that case so we are safe.
  */
 static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
 			const struct iovec *iov, loff_t offset,
@@ -1689,7 +1678,7 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 	struct ext3_inode_info *ei = EXT3_I(inode);
-	handle_t *handle = NULL;
+	handle_t *handle;
 	ssize_t ret;
 	int orphan = 0;
 	size_t count = iov_length(iov, nr_segs);
@@ -1697,17 +1686,21 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
 	if (rw == WRITE) {
 		loff_t final_size = offset + count;
 
-		handle = ext3_journal_start(inode, DIO_CREDITS);
-		if (IS_ERR(handle)) {
-			ret = PTR_ERR(handle);
-			goto out;
-		}
 		if (final_size > inode->i_size) {
+			/* Credits for sb + inode write */
+			handle = ext3_journal_start(inode, 2);
+			if (IS_ERR(handle)) {
+				ret = PTR_ERR(handle);
+				goto out;
+			}
 			ret = ext3_orphan_add(handle, inode);
-			if (ret)
-				goto out_stop;
+			if (ret) {
+				ext3_journal_stop(handle);
+				goto out;
+			}
 			orphan = 1;
 			ei->i_disksize = inode->i_size;
+			ext3_journal_stop(handle);
 		}
 	}
 
@@ -1715,18 +1708,21 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
 				 offset, nr_segs,
 				 ext3_get_block, NULL);
 
-	/*
-	 * Reacquire the handle: ext3_get_block() can restart the transaction
-	 */
-	handle = ext3_journal_current_handle();
-
-out_stop:
-	if (handle) {
+	if (orphan) {
 		int err;
 
-		if (orphan && inode->i_nlink)
+		/* Credits for sb + inode write */
+		handle = ext3_journal_start(inode, 2);
+		if (IS_ERR(handle)) {
+			/* This is really bad luck. We've written the data
+			 * but cannot extend i_size. Bail out and pretend
+			 * the write failed... */
+			ret = PTR_ERR(handle);
+			goto out;
+		}
+		if (inode->i_nlink)
 			ext3_orphan_del(handle, inode);
-		if (orphan && ret > 0) {
+		if (ret > 0) {
 			loff_t end = offset + ret;
 			if (end > inode->i_size) {
 				ei->i_disksize = end;
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 4ab6f76e63d..92b83b004dd 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -860,14 +860,10 @@ static struct buffer_head * ext3_find_entry (struct dentry *dentry,
 	int nblocks, i, err;
 	struct inode *dir = dentry->d_parent->d_inode;
 	int namelen;
-	const u8 *name;
-	unsigned blocksize;
 
 	*res_dir = NULL;
 	sb = dir->i_sb;
-	blocksize = sb->s_blocksize;
 	namelen = dentry->d_name.len;
-	name = dentry->d_name.name;
 	if (namelen > EXT3_NAME_LEN)
 		return NULL;
 	if (is_dx(dir)) {
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index f3675cc630e..343677e8c35 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -575,16 +575,16 @@ static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	    le16_to_cpu(es->s_def_resgid) != EXT3_DEF_RESGID) {
 		seq_printf(seq, ",resgid=%u", sbi->s_resgid);
 	}
-	if (test_opt(sb, ERRORS_CONT)) {
+	if (test_opt(sb, ERRORS_RO)) {
 		int def_errors = le16_to_cpu(es->s_errors);
 
 		if (def_errors == EXT3_ERRORS_PANIC ||
-		    def_errors == EXT3_ERRORS_RO) {
-			seq_puts(seq, ",errors=continue");
+		    def_errors == EXT3_ERRORS_CONTINUE) {
+			seq_puts(seq, ",errors=remount-ro");
 		}
 	}
-	if (test_opt(sb, ERRORS_RO))
-		seq_puts(seq, ",errors=remount-ro");
+	if (test_opt(sb, ERRORS_CONT))
+		seq_puts(seq, ",errors=continue");
 	if (test_opt(sb, ERRORS_PANIC))
 		seq_puts(seq, ",errors=panic");
 	if (test_opt(sb, NO_UID32))
@@ -1252,28 +1252,24 @@ static int ext3_setup_super(struct super_block *sb, struct ext3_super_block *es,
 }
 
 /* Called at mount-time, super-block is locked */
-static int ext3_check_descriptors (struct super_block * sb)
+static int ext3_check_descriptors(struct super_block *sb)
 {
 	struct ext3_sb_info *sbi = EXT3_SB(sb);
 	ext3_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
 	ext3_fsblk_t last_block;
-	struct ext3_group_desc * gdp = NULL;
-	int desc_block = 0;
 	int i;
 
 	ext3_debug ("Checking group descriptors");
 
-	for (i = 0; i < sbi->s_groups_count; i++)
-	{
+	for (i = 0; i < sbi->s_groups_count; i++) {
+		struct ext3_group_desc *gdp = ext3_get_group_desc(sb, i, NULL);
+
 		if (i == sbi->s_groups_count - 1)
 			last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1;
 		else
 			last_block = first_block +
 				(EXT3_BLOCKS_PER_GROUP(sb) - 1);
 
-		if ((i % EXT3_DESC_PER_BLOCK(sb)) == 0)
-			gdp = (struct ext3_group_desc *)
-					sbi->s_group_desc[desc_block++]->b_data;
 		if (le32_to_cpu(gdp->bg_block_bitmap) < first_block ||
 		    le32_to_cpu(gdp->bg_block_bitmap) > last_block)
 		{
@@ -1306,7 +1302,6 @@ static int ext3_check_descriptors (struct super_block * sb)
 			return 0;
 		}
 		first_block += EXT3_BLOCKS_PER_GROUP(sb);
-		gdp++;
 	}
 
 	sbi->s_es->s_free_blocks_count=cpu_to_le32(ext3_count_free_blocks(sb));
@@ -1583,10 +1578,10 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 
 	if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_PANIC)
 		set_opt(sbi->s_mount_opt, ERRORS_PANIC);
-	else if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_RO)
-		set_opt(sbi->s_mount_opt, ERRORS_RO);
-	else
+	else if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_CONTINUE)
 		set_opt(sbi->s_mount_opt, ERRORS_CONT);
+	else
+		set_opt(sbi->s_mount_opt, ERRORS_RO);
 
 	sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
 	sbi->s_resgid = le16_to_cpu(es->s_def_resgid);