Merge tag 'xfs-5.14-merge-6' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Darrick Wong:
 "Most of the work this cycle has been on refactoring various parts of
  the codebase. The biggest non-cleanup changes are (1) reducing the
  number of cache flushes sent when writing the log; (2) a substantial
  number of log recovery fixes; and (3) I started accepting pull
  requests from contributors if the commits in their branches match
  what's been sent to the list.

  For a week or so I /had/ staged a major cleanup of the logging code
  from Dave Chinner, but it exposed so many lurking bugs in other parts
  of the logging and log recovery code that I decided to defer that
  patchset until we can address those latent bugs.

  Larger cleanups this time include walking the incore inode cache (me)
  and rework of the extended attribute code (Allison) to prepare it for
  adding logged xattr updates (and directory tree parent pointers) in
  future releases.

  Summary:

   - Refactor the buffer cache to use bulk page allocation

   - Convert agnumber-based AG iteration to walk per-AG structures

   - Clean up some unit conversions and other code warts

   - Reduce spinlock contention in the directio fastpath

   - Collapse all the inode cache walks into a single function

   - Remove indirect function calls from the inode cache walk code

   - Dramatically reduce the number of cache flushes sent when writing
     log buffers

   - Preserve inode sickness reports for longer

   - Rename xfs_eofblocks since it controls inode cache walks

   - Refactor the extended attribute code to prepare it for the addition
     of log intent items to make xattrs fully transactional

   - A few fixes to earlier large patchsets

   - Log recovery fixes so that we don't accidentally mark the log clean
     when log intent recovery fails

   - Fix some latent SOB errors

   - Clean up shutdown messages that get logged to dmesg

   - Fix a regression in the online shrink code

   - Fix a UAF in the buffer logging code if the fs goes offline

   - Fix uninitialized error variables

   - Fix a UAF in the CIL when commited log item callbacks race with a
     shutdown

   - Fix a bug where the CIL could hang trying to push part of the log
     ring buffer that hasn't been filled yet"

* tag 'xfs-5.14-merge-6' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (102 commits)
  xfs: don't wait on future iclogs when pushing the CIL
  xfs: Fix a CIL UAF by getting get rid of the iclog callback lock
  xfs: remove callback dequeue loop from xlog_state_do_iclog_callbacks
  xfs: don't nest icloglock inside ic_callback_lock
  xfs: Initialize error in xfs_attr_remove_iter
  xfs: fix endianness issue in xfs_ag_shrink_space
  xfs: remove dead stale buf unpin handling code
  xfs: hold buffer across unpin and potential shutdown processing
  xfs: force the log offline when log intent item recovery fails
  xfs: fix log intent recovery ENOSPC shutdowns when inactivating inodes
  xfs: shorten the shutdown messages to a single line
  xfs: print name of function causing fs shutdown instead of hex pointer
  xfs: fix type mismatches in the inode reclaim functions
  xfs: separate primary inode selection criteria in xfs_iget_cache_hit
  xfs: refactor the inode recycling code
  xfs: add iclog state trace events
  xfs: xfs_log_force_lsn isn't passed a LSN
  xfs: Fix CIL throttle hang when CIL space used going backwards
  xfs: journal IO cache flush reductions
  xfs: remove need_start_rec parameter from xlog_write()
  ...

1 files changed, 45 insertions, 25 deletions

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 3c0749ab9e40..cc3cfb12df53 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -119,8 +119,8 @@ xfs_dir_fsync(
 	return xfs_log_force_inode(ip);
 }
 
-static xfs_lsn_t
-xfs_fsync_lsn(
+static xfs_csn_t
+xfs_fsync_seq(
 	struct xfs_inode	*ip,
 	bool			datasync)
 {
@@ -128,7 +128,7 @@ xfs_fsync_lsn(
 		return 0;
 	if (datasync && !(ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
 		return 0;
-	return ip->i_itemp->ili_last_lsn;
+	return ip->i_itemp->ili_commit_seq;
 }
 
 /*
@@ -151,12 +151,12 @@ xfs_fsync_flush_log(
 	int			*log_flushed)
 {
 	int			error = 0;
-	xfs_lsn_t		lsn;
+	xfs_csn_t		seq;
 
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	lsn = xfs_fsync_lsn(ip, datasync);
-	if (lsn) {
-		error = xfs_log_force_lsn(ip->i_mount, lsn, XFS_LOG_SYNC,
+	seq = xfs_fsync_seq(ip, datasync);
+	if (seq) {
+		error = xfs_log_force_seq(ip->i_mount, seq, XFS_LOG_SYNC,
 					  log_flushed);
 
 		spin_lock(&ip->i_itemp->ili_lock);
@@ -197,9 +197,9 @@ xfs_file_fsync(
 	 * inode size in case of an extending write.
 	 */
 	if (XFS_IS_REALTIME_INODE(ip))
-		xfs_blkdev_issue_flush(mp->m_rtdev_targp);
+		blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev);
 	else if (mp->m_logdev_targp != mp->m_ddev_targp)
-		xfs_blkdev_issue_flush(mp->m_ddev_targp);
+		blkdev_issue_flush(mp->m_ddev_targp->bt_bdev);
 
 	/*
 	 * Any inode that has dirty modifications in the log is pinned.  The
@@ -219,7 +219,7 @@ xfs_file_fsync(
 	 */
 	if (!log_flushed && !XFS_IS_REALTIME_INODE(ip) &&
 	    mp->m_logdev_targp == mp->m_ddev_targp)
-		xfs_blkdev_issue_flush(mp->m_ddev_targp);
+		blkdev_issue_flush(mp->m_ddev_targp->bt_bdev);
 
 	return error;
 }
@@ -384,21 +384,30 @@ restart:
 		}
 		goto restart;
 	}
+
 	/*
 	 * If the offset is beyond the size of the file, we need to zero any
 	 * blocks that fall between the existing EOF and the start of this
-	 * write.  If zeroing is needed and we are currently holding the
-	 * iolock shared, we need to update it to exclusive which implies
-	 * having to redo all checks before.
+	 * write.  If zeroing is needed and we are currently holding the iolock
+	 * shared, we need to update it to exclusive which implies having to
+	 * redo all checks before.
+	 *
+	 * We need to serialise against EOF updates that occur in IO completions
+	 * here. We want to make sure that nobody is changing the size while we
+	 * do this check until we have placed an IO barrier (i.e.  hold the
+	 * XFS_IOLOCK_EXCL) that prevents new IO from being dispatched.  The
+	 * spinlock effectively forms a memory barrier once we have the
+	 * XFS_IOLOCK_EXCL so we are guaranteed to see the latest EOF value and
+	 * hence be able to correctly determine if we need to run zeroing.
 	 *
-	 * We need to serialise against EOF updates that occur in IO
-	 * completions here. We want to make sure that nobody is changing the
-	 * size while we do this check until we have placed an IO barrier (i.e.
-	 * hold the XFS_IOLOCK_EXCL) that prevents new IO from being dispatched.
-	 * The spinlock effectively forms a memory barrier once we have the
-	 * XFS_IOLOCK_EXCL so we are guaranteed to see the latest EOF value
-	 * and hence be able to correctly determine if we need to run zeroing.
+	 * We can do an unlocked check here safely as IO completion can only
+	 * extend EOF. Truncate is locked out at this point, so the EOF can
+	 * not move backwards, only forwards. Hence we only need to take the
+	 * slow path and spin locks when we are at or beyond the current EOF.
 	 */
+	if (iocb->ki_pos <= i_size_read(inode))
+		goto out;
+
 	spin_lock(&ip->i_flags_lock);
 	isize = i_size_read(inode);
 	if (iocb->ki_pos > isize) {
@@ -426,7 +435,7 @@ restart:
 			drained_dio = true;
 			goto restart;
 		}
-	
+
 		trace_xfs_zero_eof(ip, isize, iocb->ki_pos - isize);
 		error = iomap_zero_range(inode, isize, iocb->ki_pos - isize,
 				NULL, &xfs_buffered_write_iomap_ops);
@@ -435,6 +444,7 @@ restart:
 	} else
 		spin_unlock(&ip->i_flags_lock);
 
+out:
 	return file_modified(file);
 }
 
@@ -500,7 +510,17 @@ xfs_dio_write_end_io(
 	 * other IO completions here to update the EOF. Failing to serialise
 	 * here can result in EOF moving backwards and Bad Things Happen when
 	 * that occurs.
+	 *
+	 * As IO completion only ever extends EOF, we can do an unlocked check
+	 * here to avoid taking the spinlock. If we land within the current EOF,
+	 * then we do not need to do an extending update at all, and we don't
+	 * need to take the lock to check this. If we race with an update moving
+	 * EOF, then we'll either still be beyond EOF and need to take the lock,
+	 * or we'll be within EOF and we don't need to take it at all.
 	 */
+	if (offset + size <= i_size_read(inode))
+		goto out;
+
 	spin_lock(&ip->i_flags_lock);
 	if (offset + size > i_size_read(inode)) {
 		i_size_write(inode, offset + size);
@@ -749,18 +769,18 @@ write_retry:
 	 */
 	if (ret == -EDQUOT && !cleared_space) {
 		xfs_iunlock(ip, iolock);
-		xfs_blockgc_free_quota(ip, XFS_EOF_FLAGS_SYNC);
+		xfs_blockgc_free_quota(ip, XFS_ICWALK_FLAG_SYNC);
 		cleared_space = true;
 		goto write_retry;
 	} else if (ret == -ENOSPC && !cleared_space) {
-		struct xfs_eofblocks eofb = {0};
+		struct xfs_icwalk	icw = {0};
 
 		cleared_space = true;
 		xfs_flush_inodes(ip->i_mount);
 
 		xfs_iunlock(ip, iolock);
-		eofb.eof_flags = XFS_EOF_FLAGS_SYNC;
-		xfs_blockgc_free_space(ip->i_mount, &eofb);
+		icw.icw_flags = XFS_ICWALK_FLAG_SYNC;
+		xfs_blockgc_free_space(ip->i_mount, &icw);
 		goto write_retry;
 	}