Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "Various cleanups and bug fixes in ext4's extent status tree,
  journalling, and block allocator subsystems.

  Also improve performance for parallel DIO overwrites"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (55 commits)
  ext4: avoid updating the superblock on a r/o mount if not needed
  jbd2: skip reading super block if it has been verified
  ext4: fix to check return value of freeze_bdev() in ext4_shutdown()
  ext4: refactoring to use the unified helper ext4_quotas_off()
  ext4: turn quotas off if mount failed after enabling quotas
  ext4: update doc about journal superblock description
  ext4: add journal cycled recording support
  jbd2: continue to record log between each mount
  jbd2: remove j_format_version
  jbd2: factor out journal initialization from journal_get_superblock()
  jbd2: switch to check format version in superblock directly
  jbd2: remove unused feature macros
  ext4: ext4_put_super: Remove redundant checking for 'sbi->s_journal_bdev'
  ext4: Fix reusing stale buffer heads from last failed mounting
  ext4: allow concurrent unaligned dio overwrites
  ext4: clean up mballoc criteria comments
  ext4: make ext4_zeroout_es() return void
  ext4: make ext4_es_insert_extent() return void
  ext4: make ext4_es_insert_delayed_block() return void
  ext4: make ext4_es_remove_extent() return void
  ...

1 files changed, 46 insertions, 40 deletions

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 6a16d07965f9c..c457c8517f0fd 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -450,13 +450,14 @@ static const struct iomap_dio_ops ext4_dio_write_ops = {
  */
 static ssize_t ext4_dio_write_checks(struct kiocb *iocb, struct iov_iter *from,
 				     bool *ilock_shared, bool *extend,
-				     bool *unwritten)
+				     bool *unwritten, int *dio_flags)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	loff_t offset;
 	size_t count;
 	ssize_t ret;
+	bool overwrite, unaligned_io;
 
 restart:
 	ret = ext4_generic_write_checks(iocb, from);
@@ -465,16 +466,20 @@ restart:
 
 	offset = iocb->ki_pos;
 	count = ret;
-	if (ext4_extending_io(inode, offset, count))
-		*extend = true;
+
+	unaligned_io = ext4_unaligned_io(inode, from, offset);
+	*extend = ext4_extending_io(inode, offset, count);
+	overwrite = ext4_overwrite_io(inode, offset, count, unwritten);
+
 	/*
-	 * Determine whether the IO operation will overwrite allocated
-	 * and initialized blocks.
-	 * We need exclusive i_rwsem for changing security info
-	 * in file_modified().
+	 * Determine whether we need to upgrade to an exclusive lock. This is
+	 * required to change security info in file_modified(), for extending
+	 * I/O, any form of non-overwrite I/O, and unaligned I/O to unwritten
+	 * extents (as partial block zeroing may be required).
 	 */
-	if (*ilock_shared && (!IS_NOSEC(inode) || *extend ||
-	     !ext4_overwrite_io(inode, offset, count, unwritten))) {
+	if (*ilock_shared &&
+	    ((!IS_NOSEC(inode) || *extend || !overwrite ||
+	     (unaligned_io && *unwritten)))) {
 		if (iocb->ki_flags & IOCB_NOWAIT) {
 			ret = -EAGAIN;
 			goto out;
@@ -485,6 +490,32 @@ restart:
 		goto restart;
 	}
 
+	/*
+	 * Now that locking is settled, determine dio flags and exclusivity
+	 * requirements. Unaligned writes are allowed under shared lock so long
+	 * as they are pure overwrites. Set the iomap overwrite only flag as an
+	 * added precaution in this case. Even though this is unnecessary, we
+	 * can detect and warn on unexpected -EAGAIN if an unsafe unaligned
+	 * write is ever submitted.
+	 *
+	 * Otherwise, concurrent unaligned writes risk data corruption due to
+	 * partial block zeroing in the dio layer, and so the I/O must occur
+	 * exclusively. The inode lock is already held exclusive if the write is
+	 * non-overwrite or extending, so drain all outstanding dio and set the
+	 * force wait dio flag.
+	 */
+	if (*ilock_shared && unaligned_io) {
+		*dio_flags = IOMAP_DIO_OVERWRITE_ONLY;
+	} else if (!*ilock_shared && (unaligned_io || *extend)) {
+		if (iocb->ki_flags & IOCB_NOWAIT) {
+			ret = -EAGAIN;
+			goto out;
+		}
+		if (unaligned_io && (!overwrite || *unwritten))
+			inode_dio_wait(inode);
+		*dio_flags = IOMAP_DIO_FORCE_WAIT;
+	}
+
 	ret = file_modified(file);
 	if (ret < 0)
 		goto out;
@@ -506,18 +537,11 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	loff_t offset = iocb->ki_pos;
 	size_t count = iov_iter_count(from);
 	const struct iomap_ops *iomap_ops = &ext4_iomap_ops;
-	bool extend = false, unaligned_io = false, unwritten = false;
+	bool extend = false, unwritten = false;
 	bool ilock_shared = true;
+	int dio_flags = 0;
 
 	/*
-	 * We initially start with shared inode lock unless it is
-	 * unaligned IO which needs exclusive lock anyways.
-	 */
-	if (ext4_unaligned_io(inode, from, offset)) {
-		unaligned_io = true;
-		ilock_shared = false;
-	}
-	/*
 	 * Quick check here without any i_rwsem lock to see if it is extending
 	 * IO. A more reliable check is done in ext4_dio_write_checks() with
 	 * proper locking in place.
@@ -549,16 +573,11 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		return ext4_buffered_write_iter(iocb, from);
 	}
 
-	ret = ext4_dio_write_checks(iocb, from,
-				    &ilock_shared, &extend, &unwritten);
+	ret = ext4_dio_write_checks(iocb, from, &ilock_shared, &extend,
+				    &unwritten, &dio_flags);
 	if (ret <= 0)
 		return ret;
 
-	/* if we're going to block and IOCB_NOWAIT is set, return -EAGAIN */
-	if ((iocb->ki_flags & IOCB_NOWAIT) && (unaligned_io || extend)) {
-		ret = -EAGAIN;
-		goto out;
-	}
 	/*
 	 * Make sure inline data cannot be created anymore since we are going
 	 * to allocate blocks for DIO. We know the inode does not have any
@@ -569,19 +588,6 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	offset = iocb->ki_pos;
 	count = ret;
 
-	/*
-	 * Unaligned direct IO must be serialized among each other as zeroing
-	 * of partial blocks of two competing unaligned IOs can result in data
-	 * corruption.
-	 *
-	 * So we make sure we don't allow any unaligned IO in flight.
-	 * For IOs where we need not wait (like unaligned non-AIO DIO),
-	 * below inode_dio_wait() may anyway become a no-op, since we start
-	 * with exclusive lock.
-	 */
-	if (unaligned_io)
-		inode_dio_wait(inode);
-
 	if (extend) {
 		handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
 		if (IS_ERR(handle)) {
@@ -601,8 +607,8 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ilock_shared && !unwritten)
 		iomap_ops = &ext4_iomap_overwrite_ops;
 	ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops,
-			   (unaligned_io || extend) ? IOMAP_DIO_FORCE_WAIT : 0,
-			   NULL, 0);
+			   dio_flags, NULL, 0);
+	WARN_ON_ONCE(ret == -EAGAIN && !(iocb->ki_flags & IOCB_NOWAIT));
 	if (ret == -ENOTBLK)
 		ret = 0;