Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs: ext2/3/4: delete unneeded includes of module.h ext{3,4}: Fix potential race when setversion ioctl updates inode udf: Mark LVID buffer as uptodate before marking it dirty ext3: Don't warn from writepage when readonly inode is spotted after error jbd: Remove j_barrier mutex reiserfs: Force inode evictions before umount to avoid crash reiserfs: Fix quota mount option parsing udf: Treat symlink component of type 2 as / udf: Fix deadlock when converting file from in-ICB one to normal one udf: Cleanup calling convention of inode_getblk() ext2: Fix error handling on inode bitmap corruption ext3: Fix error handling on inode bitmap corruption ext3: replace ll_rw_block with other functions ext3: NULL dereference in ext3_evict_inode() jbd: clear revoked flag on buffers before a new transaction started ext3: call ext3_mark_recovery_complete() when recovery is really needed
2012-01-09 12:51:21 -08:00 · 2012-01-09 12:51:21 -08:00 · ac69e09280
parent 9e203936ea 302bf2f325
commit ac69e09280
35 changed files with 200 additions and 110 deletions
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@ -573,8 +573,11 @@ got:
 	inode->i_generation = sbi->s_next_generation++;
 	spin_unlock(&sbi->s_next_gen_lock);
 	if (insert_inode_locked(inode) < 0) {
-		err = -EINVAL;
-		goto fail_drop;
+		ext2_error(sb, "ext2_new_inode",
+			   "inode number already in use - inode=%lu",
+			   (unsigned long) ino);
+		err = -EIO;
+		goto fail;
 	}

 	dquot_initialize(inode);
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@ -26,7 +26,6 @@
 #include <linux/highuid.h>
 #include <linux/pagemap.h>
 #include <linux/quotaops.h>
-#include <linux/module.h>
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>
 #include <linux/mpage.h>
@ -36,10 +35,6 @@
 #include "acl.h"
 #include "xip.h"

-MODULE_AUTHOR("Remy Card and others");
-MODULE_DESCRIPTION("Second Extended Filesystem");
-MODULE_LICENSE("GPL");
-
 static int __ext2_write_inode(struct inode *inode, int do_sync);

 /*
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@ -1520,5 +1520,8 @@ static void __exit exit_ext2_fs(void)
 	exit_ext2_xattr();
 }

+MODULE_AUTHOR("Remy Card and others");
+MODULE_DESCRIPTION("Second Extended Filesystem");
+MODULE_LICENSE("GPL");
 module_init(init_ext2_fs)
 module_exit(exit_ext2_fs)
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@ -54,7 +54,6 @@
 */

 #include <linux/buffer_head.h>
-#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/mbcache.h>
--- a/fs/ext2/xattr_security.c
+++ b/fs/ext2/xattr_security.c
@ -3,7 +3,6 @@
 * Handler for storing security labels as extended attributes.
 */

-#include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/fs.h>
--- a/fs/ext2/xattr_trusted.c
+++ b/fs/ext2/xattr_trusted.c
@ -5,7 +5,6 @@
 * Copyright (C) 2003 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
 */

-#include <linux/module.h>
 #include <linux/string.h>
 #include <linux/capability.h>
 #include <linux/fs.h>
--- a/fs/ext2/xattr_user.c
+++ b/fs/ext2/xattr_user.c
@ -6,7 +6,6 @@
 */

 #include <linux/init.h>
-#include <linux/module.h>
 #include <linux/string.h>
 #include "ext2.h"
 #include "xattr.h"
--- a/fs/ext3/ialloc.c
+++ b/fs/ext3/ialloc.c
@ -525,8 +525,12 @@ got:
 	if (IS_DIRSYNC(inode))
 		handle->h_sync = 1;
 	if (insert_inode_locked(inode) < 0) {
-		err = -EINVAL;
-		goto fail_drop;
+		/*
+		 * Likely a bitmap corruption causing inode to be allocated
+		 * twice.
+		 */
+		err = -EIO;
+		goto fail;
 	}
 	spin_lock(&sbi->s_next_gen_lock);
 	inode->i_generation = sbi->s_next_generation++;
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@ -22,7 +22,6 @@
 *  Assorted race fixes, rewrite of ext3_get_block() by Al Viro, 2000
 */

-#include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/time.h>
 #include <linux/ext3_jbd.h>
@ -223,8 +222,12 @@ void ext3_evict_inode (struct inode *inode)
 	 *
 	 * Note that directories do not have this problem because they don't
 	 * use page cache.
+	 *
+	 * The s_journal check handles the case when ext3_get_journal() fails
+	 * and puts the journal inode.
 	 */
 	if (inode->i_nlink && ext3_should_journal_data(inode) &&
+	    EXT3_SB(inode->i_sb)->s_journal &&
 	    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
 		tid_t commit_tid = atomic_read(&ei->i_datasync_tid);
 		journal_t *journal = EXT3_SB(inode->i_sb)->s_journal;
@ -1132,9 +1135,11 @@ struct buffer_head *ext3_bread(handle_t *handle, struct inode *inode,
 	bh = ext3_getblk(handle, inode, block, create, err);
 	if (!bh)
 		return bh;
-	if (buffer_uptodate(bh))
+	if (bh_uptodate_or_lock(bh))
 		return bh;
-	ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh);
+	get_bh(bh);
+	bh->b_end_io = end_buffer_read_sync;
+	submit_bh(READ | REQ_META | REQ_PRIO, bh);
 	wait_on_buffer(bh);
 	if (buffer_uptodate(bh))
 		return bh;
@ -1617,7 +1622,13 @@ static int ext3_ordered_writepage(struct page *page,
 	int err;

 	J_ASSERT(PageLocked(page));
-	WARN_ON_ONCE(IS_RDONLY(inode));
+	/*
+	 * We don't want to warn for emergency remount. The condition is
+	 * ordered to avoid dereferencing inode->i_sb in non-error case to
+	 * avoid slow-downs.
+	 */
+	WARN_ON_ONCE(IS_RDONLY(inode) &&
+		     !(EXT3_SB(inode->i_sb)->s_mount_state & EXT3_ERROR_FS));

 	/*
 	 * We give up here if we're reentered, because it might be for a
@ -1692,7 +1703,13 @@ static int ext3_writeback_writepage(struct page *page,
 	int err;

 	J_ASSERT(PageLocked(page));
-	WARN_ON_ONCE(IS_RDONLY(inode));
+	/*
+	 * We don't want to warn for emergency remount. The condition is
+	 * ordered to avoid dereferencing inode->i_sb in non-error case to
+	 * avoid slow-downs.
+	 */
+	WARN_ON_ONCE(IS_RDONLY(inode) &&
+		     !(EXT3_SB(inode->i_sb)->s_mount_state & EXT3_ERROR_FS));

 	if (ext3_journal_current_handle())
 		goto out_fail;
@ -1735,7 +1752,13 @@ static int ext3_journalled_writepage(struct page *page,
 	int err;

 	J_ASSERT(PageLocked(page));
-	WARN_ON_ONCE(IS_RDONLY(inode));
+	/*
+	 * We don't want to warn for emergency remount. The condition is
+	 * ordered to avoid dereferencing inode->i_sb in non-error case to
+	 * avoid slow-downs.
+	 */
+	WARN_ON_ONCE(IS_RDONLY(inode) &&
+		     !(EXT3_SB(inode->i_sb)->s_mount_state & EXT3_ERROR_FS));

 	if (ext3_journal_current_handle())
 		goto no_write;
@ -2064,12 +2087,10 @@ static int ext3_block_truncate_page(struct inode *inode, loff_t from)
 	if (PageUptodate(page))
 		set_buffer_uptodate(bh);

-	if (!buffer_uptodate(bh)) {
-		err = -EIO;
-		ll_rw_block(READ, 1, &bh);
-		wait_on_buffer(bh);
+	if (!bh_uptodate_or_lock(bh)) {
+		err = bh_submit_read(bh);
 		/* Uhhuh. Read error. Complain and punt. */
-		if (!buffer_uptodate(bh))
+		if (err)
 			goto unlock;
 	}

--- a/fs/ext3/ioctl.c
+++ b/fs/ext3/ioctl.c
@ -134,10 +134,11 @@ flags_out:
 			goto setversion_out;
 		}

+		mutex_lock(&inode->i_mutex);
 		handle = ext3_journal_start(inode, 1);
 		if (IS_ERR(handle)) {
 			err = PTR_ERR(handle);
-			goto setversion_out;
+			goto unlock_out;
 		}
 		err = ext3_reserve_inode_write(handle, inode, &iloc);
 		if (err == 0) {
@ -146,6 +147,9 @@ flags_out:
 			err = ext3_mark_iloc_dirty(handle, inode, &iloc);
 		}
 		ext3_journal_stop(handle);
+
+unlock_out:
+		mutex_unlock(&inode->i_mutex);
 setversion_out:
 		mnt_drop_write_file(filp);
 		return err;
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@ -921,9 +921,12 @@ restart:
 				num++;
 				bh = ext3_getblk(NULL, dir, b++, 0, &err);
 				bh_use[ra_max] = bh;
-				if (bh)
-					ll_rw_block(READ | REQ_META | REQ_PRIO,
-						    1, &bh);
+				if (bh && !bh_uptodate_or_lock(bh)) {
+					get_bh(bh);
+					bh->b_end_io = end_buffer_read_sync;
+					submit_bh(READ | REQ_META | REQ_PRIO,
+						  bh);
+				}
 			}
 		}
 		if ((bh = bh_use[ra_ptr++]) == NULL)
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@ -2059,9 +2059,10 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 	EXT3_SB(sb)->s_mount_state |= EXT3_ORPHAN_FS;
 	ext3_orphan_cleanup(sb, es);
 	EXT3_SB(sb)->s_mount_state &= ~EXT3_ORPHAN_FS;
-	if (needs_recovery)
+	if (needs_recovery) {
+		ext3_mark_recovery_complete(sb, es);
 		ext3_msg(sb, KERN_INFO, "recovery complete");
-	ext3_mark_recovery_complete(sb, es);
+	}
 	ext3_msg(sb, KERN_INFO, "mounted filesystem with %s data mode",
 		test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA ? "journal":
 		test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA ? "ordered":
@ -2229,11 +2230,11 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb,
 		goto out_bdev;
 	}
 	journal->j_private = sb;
-	ll_rw_block(READ, 1, &journal->j_sb_buffer);
-	wait_on_buffer(journal->j_sb_buffer);
-	if (!buffer_uptodate(journal->j_sb_buffer)) {
-		ext3_msg(sb, KERN_ERR, "I/O error on journal device");
-		goto out_journal;
+	if (!bh_uptodate_or_lock(journal->j_sb_buffer)) {
+		if (bh_submit_read(journal->j_sb_buffer)) {
+			ext3_msg(sb, KERN_ERR, "I/O error on journal device");
+			goto out_journal;
+		}
 	}
 	if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) {
 		ext3_msg(sb, KERN_ERR,
--- a/fs/ext3/xattr_security.c
+++ b/fs/ext3/xattr_security.c
@ -3,7 +3,6 @@
 * Handler for storing security labels as extended attributes.
 */

-#include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/fs.h>
--- a/fs/ext3/xattr_trusted.c
+++ b/fs/ext3/xattr_trusted.c
@ -5,7 +5,6 @@
 * Copyright (C) 2003 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
 */

-#include <linux/module.h>
 #include <linux/string.h>
 #include <linux/capability.h>
 #include <linux/fs.h>
--- a/fs/ext3/xattr_user.c
+++ b/fs/ext3/xattr_user.c
@ -5,7 +5,6 @@
 * Copyright (C) 2001 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
 */

-#include <linux/module.h>
 #include <linux/string.h>
 #include <linux/fs.h>
 #include <linux/ext3_jbd.h>
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@ -13,7 +13,6 @@
 #include <linux/namei.h>
 #include <linux/quotaops.h>
 #include <linux/buffer_head.h>
-#include <linux/module.h>
 #include <linux/swap.h>
 #include <linux/pagemap.h>
 #include <linux/blkdev.h>
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@ -29,7 +29,6 @@
 *   - smart tree reduction
 */

-#include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/time.h>
 #include <linux/jbd2.h>
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@ -20,7 +20,6 @@
 *	(sct@redhat.com), 1993, 1998
 */

-#include <linux/module.h>
 #include "ext4_jbd2.h"
 #include "truncate.h"

--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@ -18,7 +18,6 @@
 *  Assorted race fixes, rewrite of ext4_get_block() by Al Viro, 2000
 */

-#include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/time.h>
 #include <linux/jbd2.h>
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@ -158,10 +158,11 @@ flags_out:
 			goto setversion_out;
 		}

+		mutex_lock(&inode->i_mutex);
 		handle = ext4_journal_start(inode, 1);
 		if (IS_ERR(handle)) {
 			err = PTR_ERR(handle);
-			goto setversion_out;
+			goto unlock_out;
 		}
 		err = ext4_reserve_inode_write(handle, inode, &iloc);
 		if (err == 0) {
@ -170,6 +171,9 @@ flags_out:
 			err = ext4_mark_iloc_dirty(handle, inode, &iloc);
 		}
 		ext4_journal_stop(handle);
+
+unlock_out:
+		mutex_unlock(&inode->i_mutex);
 setversion_out:
 		mnt_drop_write_file(filp);
 		return err;
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@ -12,7 +12,6 @@
 *
 */

-#include <linux/module.h>
 #include <linux/slab.h>
 #include "ext4_jbd2.h"

--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@ -6,7 +6,6 @@
 * Written by Theodore Ts'o, 2010.
 */

-#include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/time.h>
 #include <linux/jbd2.h>
--- a/fs/ext4/xattr_security.c
+++ b/fs/ext4/xattr_security.c
@ -3,7 +3,6 @@
 * Handler for storing security labels as extended attributes.
 */

-#include <linux/module.h>
 #include <linux/string.h>
 #include <linux/fs.h>
 #include <linux/security.h>
--- a/fs/ext4/xattr_trusted.c
+++ b/fs/ext4/xattr_trusted.c
@ -5,7 +5,6 @@
 * Copyright (C) 2003 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
 */

-#include <linux/module.h>
 #include <linux/string.h>
 #include <linux/capability.h>
 #include <linux/fs.h>
--- a/fs/ext4/xattr_user.c
+++ b/fs/ext4/xattr_user.c
@ -5,7 +5,6 @@
 * Copyright (C) 2001 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
 */

-#include <linux/module.h>
 #include <linux/string.h>
 #include <linux/fs.h>
 #include "ext4_jbd2.h"
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@ -391,6 +391,12 @@ void journal_commit_transaction(journal_t *journal)

 	jbd_debug (3, "JBD: commit phase 1\n");

+	/*
+	 * Clear revoked flag to reflect there is no revoked buffers
+	 * in the next transaction which is going to be started.
+	 */
+	journal_clear_buffer_revoked_flags(journal);
+
 	/*
 	 * Switch to a new revoke table.
 	 */
--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@ -721,7 +721,6 @@ static journal_t * journal_init_common (void)
 	init_waitqueue_head(&journal->j_wait_checkpoint);
 	init_waitqueue_head(&journal->j_wait_commit);
 	init_waitqueue_head(&journal->j_wait_updates);
-	mutex_init(&journal->j_barrier);
 	mutex_init(&journal->j_checkpoint_mutex);
 	spin_lock_init(&journal->j_revoke_lock);
 	spin_lock_init(&journal->j_list_lock);
--- a/fs/jbd/revoke.c
+++ b/fs/jbd/revoke.c
@ -47,6 +47,10 @@
 *   overwriting the new data.  We don't even need to clear the revoke
 *   bit here.
 *
+ * We cache revoke status of a buffer in the current transaction in b_states
+ * bits.  As the name says, revokevalid flag indicates that the cached revoke
+ * status of a buffer is valid and we can rely on the cached status.
+ *
 * Revoke information on buffers is a tri-state value:
 *
 * RevokeValid clear:	no cached revoke status, need to look it up
@ -479,6 +483,36 @@ int journal_cancel_revoke(handle_t *handle, struct journal_head *jh)
 	return did_revoke;
 }

+/*
+ * journal_clear_revoked_flags clears revoked flag of buffers in
+ * revoke table to reflect there is no revoked buffer in the next
+ * transaction which is going to be started.
+ */
+void journal_clear_buffer_revoked_flags(journal_t *journal)
+{
+	struct jbd_revoke_table_s *revoke = journal->j_revoke;
+	int i = 0;
+
+	for (i = 0; i < revoke->hash_size; i++) {
+		struct list_head *hash_list;
+		struct list_head *list_entry;
+		hash_list = &revoke->hash_table[i];
+
+		list_for_each(list_entry, hash_list) {
+			struct jbd_revoke_record_s *record;
+			struct buffer_head *bh;
+			record = (struct jbd_revoke_record_s *)list_entry;
+			bh = __find_get_block(journal->j_fs_dev,
+					      record->blocknr,
+					      journal->j_blocksize);
+			if (bh) {
+				clear_buffer_revoked(bh);
+				__brelse(bh);
+			}
+		}
+	}
+}
+
 /* journal_switch_revoke table select j_revoke for next transaction
 * we do not want to suspend any processing until all revokes are
 * written -bzzz
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@ -426,17 +426,34 @@ int journal_restart(handle_t *handle, int nblocks)
 * void journal_lock_updates () - establish a transaction barrier.
 * @journal:  Journal to establish a barrier on.
 *
- * This locks out any further updates from being started, and blocks
- * until all existing updates have completed, returning only once the
- * journal is in a quiescent state with no updates running.
+ * This locks out any further updates from being started, and blocks until all
+ * existing updates have completed, returning only once the journal is in a
+ * quiescent state with no updates running.
 *
- * The journal lock should not be held on entry.
+ * We do not use simple mutex for synchronization as there are syscalls which
+ * want to return with filesystem locked and that trips up lockdep. Also
+ * hibernate needs to lock filesystem but locked mutex then blocks hibernation.
+ * Since locking filesystem is rare operation, we use simple counter and
+ * waitqueue for locking.
 */
 void journal_lock_updates(journal_t *journal)
 {
 	DEFINE_WAIT(wait);

+wait:
+	/* Wait for previous locked operation to finish */
+	wait_event(journal->j_wait_transaction_locked,
+		   journal->j_barrier_count == 0);
+
 	spin_lock(&journal->j_state_lock);
+	/*
+	 * Check reliably under the lock whether we are the ones winning the race
+	 * and locking the journal
+	 */
+	if (journal->j_barrier_count > 0) {
+		spin_unlock(&journal->j_state_lock);
+		goto wait;
+	}
 	++journal->j_barrier_count;

 	/* Wait until there are no running updates */
@ -460,14 +477,6 @@ void journal_lock_updates(journal_t *journal)
 		spin_lock(&journal->j_state_lock);
 	}
 	spin_unlock(&journal->j_state_lock);
-
-	/*
-	 * We have now established a barrier against other normal updates, but
-	 * we also need to barrier against other journal_lock_updates() calls
-	 * to make sure that we serialise special journal-locked operations
-	 * too.
-	 */
-	mutex_lock(&journal->j_barrier);
 }

 /**
@ -475,14 +484,11 @@ void journal_lock_updates(journal_t *journal)
 * @journal:  Journal to release the barrier on.
 *
 * Release a transaction barrier obtained with journal_lock_updates().
- *
- * Should be called without the journal lock held.
 */
 void journal_unlock_updates (journal_t *journal)
 {
 	J_ASSERT(journal->j_barrier_count != 0);

-	mutex_unlock(&journal->j_barrier);
 	spin_lock(&journal->j_state_lock);
 	--journal->j_barrier_count;
 	spin_unlock(&journal->j_state_lock);
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@ -455,16 +455,20 @@ int remove_save_link(struct inode *inode, int truncate)
 static void reiserfs_kill_sb(struct super_block *s)
 {
 	if (REISERFS_SB(s)) {
-		if (REISERFS_SB(s)->xattr_root) {
-			d_invalidate(REISERFS_SB(s)->xattr_root);
-			dput(REISERFS_SB(s)->xattr_root);
-			REISERFS_SB(s)->xattr_root = NULL;
-		}
-		if (REISERFS_SB(s)->priv_root) {
-			d_invalidate(REISERFS_SB(s)->priv_root);
-			dput(REISERFS_SB(s)->priv_root);
-			REISERFS_SB(s)->priv_root = NULL;
-		}
+		/*
+		 * Force any pending inode evictions to occur now. Any
+		 * inodes to be removed that have extended attributes
+		 * associated with them need to clean them up before
+		 * we can release the extended attribute root dentries.
+		 * shrink_dcache_for_umount will BUG if we don't release
+		 * those before it's called so ->put_super is too late.
+		 */
+		shrink_dcache_sb(s);
+
+		dput(REISERFS_SB(s)->xattr_root);
+		REISERFS_SB(s)->xattr_root = NULL;
+		dput(REISERFS_SB(s)->priv_root);
+		REISERFS_SB(s)->priv_root = NULL;
 	}

 	kill_block_super(s);
@ -1249,7 +1253,8 @@ static void handle_quota_files(struct super_block *s, char **qf_names,
 			kfree(REISERFS_SB(s)->s_qf_names[i]);
 		REISERFS_SB(s)->s_qf_names[i] = qf_names[i];
 	}
-	REISERFS_SB(s)->s_jquota_fmt = *qfmt;
+	if (*qfmt)
+		REISERFS_SB(s)->s_jquota_fmt = *qfmt;
 }
 #endif

--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@ -125,7 +125,6 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 			err = udf_expand_file_adinicb(inode);
 			if (err) {
 				udf_debug("udf_expand_adinicb: err=%d\n", err);
-				up_write(&iinfo->i_data_sem);
 				return err;
 			}
 		} else {
@ -133,9 +132,10 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 				iinfo->i_lenAlloc = pos + count;
 			else
 				iinfo->i_lenAlloc = inode->i_size;
+			up_write(&iinfo->i_data_sem);
 		}
-	}
-	up_write(&iinfo->i_data_sem);
+	} else
+		up_write(&iinfo->i_data_sem);

 	retval = generic_file_aio_write(iocb, iov, nr_segs, ppos);
 	if (retval > 0)
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@ -53,8 +53,7 @@ static int udf_update_inode(struct inode *, int);
 static void udf_fill_inode(struct inode *, struct buffer_head *);
 static int udf_sync_inode(struct inode *inode);
 static int udf_alloc_i_data(struct inode *inode, size_t size);
-static struct buffer_head *inode_getblk(struct inode *, sector_t, int *,
-					sector_t *, int *);
+static sector_t inode_getblk(struct inode *, sector_t, int *, int *);
 static int8_t udf_insert_aext(struct inode *, struct extent_position,
 			      struct kernel_lb_addr, uint32_t);
 static void udf_split_extents(struct inode *, int *, int, int,
@ -151,6 +150,12 @@ const struct address_space_operations udf_aops = {
 	.bmap		= udf_bmap,
 };

+/*
+ * Expand file stored in ICB to a normal one-block-file
+ *
+ * This function requires i_data_sem for writing and releases it.
+ * This function requires i_mutex held
+ */
 int udf_expand_file_adinicb(struct inode *inode)
 {
 	struct page *page;
@ -169,9 +174,15 @@ int udf_expand_file_adinicb(struct inode *inode)
 			iinfo->i_alloc_type = ICBTAG_FLAG_AD_LONG;
 		/* from now on we have normal address_space methods */
 		inode->i_data.a_ops = &udf_aops;
+		up_write(&iinfo->i_data_sem);
 		mark_inode_dirty(inode);
 		return 0;
 	}
+	/*
+	 * Release i_data_sem so that we can lock a page - page lock ranks
+	 * above i_data_sem. i_mutex still protects us against file changes.
+	 */
+	up_write(&iinfo->i_data_sem);

 	page = find_or_create_page(inode->i_mapping, 0, GFP_NOFS);
 	if (!page)
@ -187,6 +198,7 @@ int udf_expand_file_adinicb(struct inode *inode)
 		SetPageUptodate(page);
 		kunmap(page);
 	}
+	down_write(&iinfo->i_data_sem);
 	memset(iinfo->i_ext.i_data + iinfo->i_lenEAttr, 0x00,
 	       iinfo->i_lenAlloc);
 	iinfo->i_lenAlloc = 0;
@ -196,17 +208,20 @@ int udf_expand_file_adinicb(struct inode *inode)
 		iinfo->i_alloc_type = ICBTAG_FLAG_AD_LONG;
 	/* from now on we have normal address_space methods */
 	inode->i_data.a_ops = &udf_aops;
+	up_write(&iinfo->i_data_sem);
 	err = inode->i_data.a_ops->writepage(page, &udf_wbc);
 	if (err) {
 		/* Restore everything back so that we don't lose data... */
 		lock_page(page);
 		kaddr = kmap(page);
+		down_write(&iinfo->i_data_sem);
 		memcpy(iinfo->i_ext.i_data + iinfo->i_lenEAttr, kaddr,
 		       inode->i_size);
 		kunmap(page);
 		unlock_page(page);
 		iinfo->i_alloc_type = ICBTAG_FLAG_AD_IN_ICB;
 		inode->i_data.a_ops = &udf_adinicb_aops;
+		up_write(&iinfo->i_data_sem);
 	}
 	page_cache_release(page);
 	mark_inode_dirty(inode);
@ -310,7 +325,6 @@ static int udf_get_block(struct inode *inode, sector_t block,
 			 struct buffer_head *bh_result, int create)
 {
 	int err, new;
-	struct buffer_head *bh;
 	sector_t phys = 0;
 	struct udf_inode_info *iinfo;

@ -323,7 +337,6 @@ static int udf_get_block(struct inode *inode, sector_t block,

 	err = -EIO;
 	new = 0;
-	bh = NULL;
 	iinfo = UDF_I(inode);

 	down_write(&iinfo->i_data_sem);
@ -332,13 +345,10 @@ static int udf_get_block(struct inode *inode, sector_t block,
 		iinfo->i_next_alloc_goal++;
 	}

-	err = 0;

-	bh = inode_getblk(inode, block, &err, &phys, &new);
-	BUG_ON(bh);
-	if (err)
+	phys = inode_getblk(inode, block, &err, &new);
+	if (!phys)
 		goto abort;
-	BUG_ON(!phys);

 	if (new)
 		set_buffer_new(bh_result);
@ -547,11 +557,10 @@ out:
 	return err;
 }

-static struct buffer_head *inode_getblk(struct inode *inode, sector_t block,
-					int *err, sector_t *phys, int *new)
+static sector_t inode_getblk(struct inode *inode, sector_t block,
+			     int *err, int *new)
 {
 	static sector_t last_block;
-	struct buffer_head *result = NULL;
 	struct kernel_long_ad laarr[EXTENT_MERGE_SIZE];
 	struct extent_position prev_epos, cur_epos, next_epos;
 	int count = 0, startnum = 0, endnum = 0;
@ -566,6 +575,8 @@ static struct buffer_head *inode_getblk(struct inode *inode, sector_t block,
 	int goal = 0, pgoal = iinfo->i_location.logicalBlockNum;
 	int lastblock = 0;

+	*err = 0;
+	*new = 0;
 	prev_epos.offset = udf_file_entry_alloc_offset(inode);
 	prev_epos.block = iinfo->i_location;
 	prev_epos.bh = NULL;
@ -635,8 +646,7 @@ static struct buffer_head *inode_getblk(struct inode *inode, sector_t block,
 		brelse(cur_epos.bh);
 		brelse(next_epos.bh);
 		newblock = udf_get_lb_pblock(inode->i_sb, &eloc, offset);
-		*phys = newblock;
-		return NULL;
+		return newblock;
 	}

 	last_block = block;
@ -664,7 +674,7 @@ static struct buffer_head *inode_getblk(struct inode *inode, sector_t block,
 			brelse(cur_epos.bh);
 			brelse(next_epos.bh);
 			*err = ret;
-			return NULL;
+			return 0;
 		}
 		c = 0;
 		offset = 0;
@ -729,7 +739,7 @@ static struct buffer_head *inode_getblk(struct inode *inode, sector_t block,
 		if (!newblocknum) {
 			brelse(prev_epos.bh);
 			*err = -ENOSPC;
-			return NULL;
+			return 0;
 		}
 		iinfo->i_lenExtents += inode->i_sb->s_blocksize;
 	}
@ -761,10 +771,10 @@ static struct buffer_head *inode_getblk(struct inode *inode, sector_t block,

 	newblock = udf_get_pblock(inode->i_sb, newblocknum,
 				iinfo->i_location.partitionReferenceNum, 0);
-	if (!newblock)
-		return NULL;
-	*phys = newblock;
-	*err = 0;
+	if (!newblock) {
+		*err = -EIO;
+		return 0;
+	}
 	*new = 1;
 	iinfo->i_next_alloc_block = block;
 	iinfo->i_next_alloc_goal = newblocknum;
@ -775,7 +785,7 @@ static struct buffer_head *inode_getblk(struct inode *inode, sector_t block,
 	else
 		mark_inode_dirty(inode);

-	return result;
+	return newblock;
 }

 static void udf_split_extents(struct inode *inode, int *c, int offset,
@ -1111,10 +1121,9 @@ int udf_setsize(struct inode *inode, loff_t newsize)
 			if (bsize <
 			    (udf_file_entry_alloc_offset(inode) + newsize)) {
 				err = udf_expand_file_adinicb(inode);
-				if (err) {
-					up_write(&iinfo->i_data_sem);
+				if (err)
 					return err;
-				}
+				down_write(&iinfo->i_data_sem);
 			} else
 				iinfo->i_lenAlloc = newsize;
 		}
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@ -1798,6 +1798,12 @@ static void udf_close_lvid(struct super_block *sb)
 				le16_to_cpu(lvid->descTag.descCRCLength)));

 	lvid->descTag.tagChecksum = udf_tag_checksum(&lvid->descTag);
+	/*
+	 * We set buffer uptodate unconditionally here to avoid spurious
+	 * warnings from mark_buffer_dirty() when previous EIO has marked
+	 * the buffer as !uptodate
+	 */
+	set_buffer_uptodate(bh);
 	mark_buffer_dirty(bh);
 	sbi->s_lvid_dirty = 0;
 	mutex_unlock(&sbi->s_alloc_mutex);
--- a/fs/udf/symlink.c
+++ b/fs/udf/symlink.c
@ -41,10 +41,16 @@ static void udf_pc_to_char(struct super_block *sb, unsigned char *from,
 		pc = (struct pathComponent *)(from + elen);
 		switch (pc->componentType) {
 		case 1:
-			if (pc->lengthComponentIdent == 0) {
-				p = to;
-				*p++ = '/';
-			}
+			/*
+			 * Symlink points to some place which should be agreed
+ 			 * upon between originator and receiver of the media. Ignore.
+			 */
+			if (pc->lengthComponentIdent > 0)
+				break;
+			/* Fall through */
+		case 2:
+			p = to;
+			*p++ = '/';
 			break;
 		case 3:
 			memcpy(p, "../", 3);
--- a/include/linux/jbd.h
+++ b/include/linux/jbd.h
@ -497,7 +497,6 @@ struct transaction_s
 * @j_format_version: Version of the superblock format
 * @j_state_lock: Protect the various scalars in the journal
 * @j_barrier_count:  Number of processes waiting to create a barrier lock
- * @j_barrier: The barrier lock itself
 * @j_running_transaction: The current running transaction..
 * @j_committing_transaction: the transaction we are pushing to disk
 * @j_checkpoint_transactions: a linked circular list of all transactions
@ -580,9 +579,6 @@ struct journal_s
 	 */
 	int			j_barrier_count;

-	/* The barrier lock itself */
-	struct mutex		j_barrier;
-
 	/*
 	 * Transactions: The current running transaction...
 	 * [j_state_lock] [caller holding open handle]
@ -913,6 +909,7 @@ extern int	journal_set_revoke(journal_t *, unsigned int, tid_t);
 extern int	journal_test_revoke(journal_t *, unsigned int, tid_t);
 extern void	journal_clear_revoke(journal_t *);
 extern void	journal_switch_revoke_table(journal_t *journal);
+extern void	journal_clear_buffer_revoked_flags(journal_t *journal);

 /*
 * The log thread user interface: