Merge tag 'xfs-for-linus-4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs

Pull xfs updates from Dave Chinner:
 "There is nothing really major here - the only significant addition is
  the per-mount operation statistics infrastructure.  Otherwises there's
  various ACL, xattr, DAX, AIO and logging fixes, and a smattering of
  small cleanups and fixes elsewhere.

  Summary:

   - per-mount operational statistics in sysfs
   - fixes for concurrent aio append write submission
   - various logging fixes
   - detection of zeroed logs and invalid log sequence numbers on v5 filesystems
   - memory allocation failure message improvements
   - a bunch of xattr/ACL fixes
   - fdatasync optimisation
   - miscellaneous other fixes and cleanups"

* tag 'xfs-for-linus-4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs: (39 commits)
  xfs: give all workqueues rescuer threads
  xfs: fix log recovery op header validation assert
  xfs: Fix error path in xfs_get_acl
  xfs: optimise away log forces on timestamp updates for fdatasync
  xfs: don't leak uuid table on rmmod
  xfs: invalidate cached acl if set via ioctl
  xfs: Plug memory leak in xfs_attrmulti_attr_set
  xfs: Validate the length of on-disk ACLs
  xfs: invalidate cached acl if set directly via xattr
  xfs: xfs_filemap_pmd_fault treats read faults as write faults
  xfs: add ->pfn_mkwrite support for DAX
  xfs: DAX does not use IO completion callbacks
  xfs: Don't use unwritten extents for DAX
  xfs: introduce BMAPI_ZERO for allocating zeroed extents
  xfs: fix inode size update overflow in xfs_map_direct()
  xfs: clear PF_NOFREEZE for xfsaild kthread
  xfs: fix an error code in xfs_fs_fill_super()
  xfs: stats are no longer dependent on CONFIG_PROC_FS
  xfs: simplify /proc teardown & error handling
  xfs: per-filesystem stats counter implementation
  ...

1 files changed, 88 insertions, 26 deletions

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index f80e90f95ad8..f5392ab2def1 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -242,19 +242,30 @@ xfs_file_fsync(
 	}
 
 	/*
-	 * All metadata updates are logged, which means that we just have
-	 * to flush the log up to the latest LSN that touched the inode.
+	 * All metadata updates are logged, which means that we just have to
+	 * flush the log up to the latest LSN that touched the inode. If we have
+	 * concurrent fsync/fdatasync() calls, we need them to all block on the
+	 * log force before we clear the ili_fsync_fields field. This ensures
+	 * that we don't get a racing sync operation that does not wait for the
+	 * metadata to hit the journal before returning. If we race with
+	 * clearing the ili_fsync_fields, then all that will happen is the log
+	 * force will do nothing as the lsn will already be on disk. We can't
+	 * race with setting ili_fsync_fields because that is done under
+	 * XFS_ILOCK_EXCL, and that can't happen because we hold the lock shared
+	 * until after the ili_fsync_fields is cleared.
 	 */
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	if (xfs_ipincount(ip)) {
 		if (!datasync ||
-		    (ip->i_itemp->ili_fields & ~XFS_ILOG_TIMESTAMP))
+		    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
 			lsn = ip->i_itemp->ili_last_lsn;
 	}
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
-	if (lsn)
+	if (lsn) {
 		error = _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
+		ip->i_itemp->ili_fsync_fields = 0;
+	}
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
 	/*
 	 * If we only have a single device, and the log force about was
@@ -287,7 +298,7 @@ xfs_file_read_iter(
 	xfs_fsize_t		n;
 	loff_t			pos = iocb->ki_pos;
 
-	XFS_STATS_INC(xs_read_calls);
+	XFS_STATS_INC(mp, xs_read_calls);
 
 	if (unlikely(iocb->ki_flags & IOCB_DIRECT))
 		ioflags |= XFS_IO_ISDIRECT;
@@ -365,7 +376,7 @@ xfs_file_read_iter(
 
 	ret = generic_file_read_iter(iocb, to);
 	if (ret > 0)
-		XFS_STATS_ADD(xs_read_bytes, ret);
+		XFS_STATS_ADD(mp, xs_read_bytes, ret);
 
 	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 	return ret;
@@ -383,7 +394,7 @@ xfs_file_splice_read(
 	int			ioflags = 0;
 	ssize_t			ret;
 
-	XFS_STATS_INC(xs_read_calls);
+	XFS_STATS_INC(ip->i_mount, xs_read_calls);
 
 	if (infilp->f_mode & FMODE_NOCMTIME)
 		ioflags |= XFS_IO_INVIS;
@@ -401,7 +412,7 @@ xfs_file_splice_read(
 	else
 		ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
 	if (ret > 0)
-		XFS_STATS_ADD(xs_read_bytes, ret);
+		XFS_STATS_ADD(ip->i_mount, xs_read_bytes, ret);
 
 	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 	return ret;
@@ -482,6 +493,8 @@ xfs_zero_eof(
 	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
 	ASSERT(offset > isize);
 
+	trace_xfs_zero_eof(ip, isize, offset - isize);
+
 	/*
 	 * First handle zeroing the block on which isize resides.
 	 *
@@ -574,6 +587,7 @@ xfs_file_aio_write_checks(
 	struct xfs_inode	*ip = XFS_I(inode);
 	ssize_t			error = 0;
 	size_t			count = iov_iter_count(from);
+	bool			drained_dio = false;
 
 restart:
 	error = generic_write_checks(iocb, from);
@@ -611,12 +625,13 @@ restart:
 		bool	zero = false;
 
 		spin_unlock(&ip->i_flags_lock);
-		if (*iolock == XFS_IOLOCK_SHARED) {
-			xfs_rw_iunlock(ip, *iolock);
-			*iolock = XFS_IOLOCK_EXCL;
-			xfs_rw_ilock(ip, *iolock);
-			iov_iter_reexpand(from, count);
-
+		if (!drained_dio) {
+			if (*iolock == XFS_IOLOCK_SHARED) {
+				xfs_rw_iunlock(ip, *iolock);
+				*iolock = XFS_IOLOCK_EXCL;
+				xfs_rw_ilock(ip, *iolock);
+				iov_iter_reexpand(from, count);
+			}
 			/*
 			 * We now have an IO submission barrier in place, but
 			 * AIO can do EOF updates during IO completion and hence
@@ -626,6 +641,7 @@ restart:
 			 * no-op.
 			 */
 			inode_dio_wait(inode);
+			drained_dio = true;
 			goto restart;
 		}
 		error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), &zero);
@@ -867,7 +883,7 @@ xfs_file_write_iter(
 	ssize_t			ret;
 	size_t			ocount = iov_iter_count(from);
 
-	XFS_STATS_INC(xs_write_calls);
+	XFS_STATS_INC(ip->i_mount, xs_write_calls);
 
 	if (ocount == 0)
 		return 0;
@@ -883,7 +899,7 @@ xfs_file_write_iter(
 	if (ret > 0) {
 		ssize_t err;
 
-		XFS_STATS_ADD(xs_write_bytes, ret);
+		XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);
 
 		/* Handle various SYNC-type writes */
 		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
@@ -1477,7 +1493,7 @@ xfs_file_llseek(
  *
  * mmap_sem (MM)
  *   sb_start_pagefault(vfs, freeze)
- *     i_mmap_lock (XFS - truncate serialisation)
+ *     i_mmaplock (XFS - truncate serialisation)
  *       page_lock (MM)
  *         i_lock (XFS - extent map serialisation)
  */
@@ -1503,8 +1519,7 @@ xfs_filemap_page_mkwrite(
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (IS_DAX(inode)) {
-		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_direct,
-				    xfs_end_io_dax_write);
+		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault, NULL);
 	} else {
 		ret = block_page_mkwrite(vma, vmf, xfs_get_blocks);
 		ret = block_page_mkwrite_return(ret);
@@ -1538,7 +1553,7 @@ xfs_filemap_fault(
 		 * changes to xfs_get_blocks_direct() to map unwritten extent
 		 * ioend for conversion on read-only mappings.
 		 */
-		ret = __dax_fault(vma, vmf, xfs_get_blocks_direct, NULL);
+		ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
 	} else
 		ret = filemap_fault(vma, vmf);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
@@ -1546,6 +1561,13 @@ xfs_filemap_fault(
 	return ret;
 }
 
+/*
+ * Similar to xfs_filemap_fault(), the DAX fault path can call into here on
+ * both read and write faults. Hence we need to handle both cases. There is no
+ * ->pmd_mkwrite callout for huge pages, so we have a single function here to
+ * handle both cases here. @flags carries the information on the type of fault
+ * occuring.
+ */
 STATIC int
 xfs_filemap_pmd_fault(
 	struct vm_area_struct	*vma,
@@ -1562,15 +1584,54 @@ xfs_filemap_pmd_fault(
 
 	trace_xfs_filemap_pmd_fault(ip);
 
-	sb_start_pagefault(inode->i_sb);
-	file_update_time(vma->vm_file);
+	if (flags & FAULT_FLAG_WRITE) {
+		sb_start_pagefault(inode->i_sb);
+		file_update_time(vma->vm_file);
+	}
+
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_direct,
-				    xfs_end_io_dax_write);
+	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault,
+			      NULL);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	sb_end_pagefault(inode->i_sb);
 
+	if (flags & FAULT_FLAG_WRITE)
+		sb_end_pagefault(inode->i_sb);
+
+	return ret;
+}
+
+/*
+ * pfn_mkwrite was originally inteneded to ensure we capture time stamp
+ * updates on write faults. In reality, it's need to serialise against
+ * truncate similar to page_mkwrite. Hence we open-code dax_pfn_mkwrite()
+ * here and cycle the XFS_MMAPLOCK_SHARED to ensure we serialise the fault
+ * barrier in place.
+ */
+static int
+xfs_filemap_pfn_mkwrite(
+	struct vm_area_struct	*vma,
+	struct vm_fault		*vmf)
+{
+
+	struct inode		*inode = file_inode(vma->vm_file);
+	struct xfs_inode	*ip = XFS_I(inode);
+	int			ret = VM_FAULT_NOPAGE;
+	loff_t			size;
+
+	trace_xfs_filemap_pfn_mkwrite(ip);
+
+	sb_start_pagefault(inode->i_sb);
+	file_update_time(vma->vm_file);
+
+	/* check if the faulting page hasn't raced with truncate */
+	xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (vmf->pgoff >= size)
+		ret = VM_FAULT_SIGBUS;
+	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
+	sb_end_pagefault(inode->i_sb);
 	return ret;
+
 }
 
 static const struct vm_operations_struct xfs_file_vm_ops = {
@@ -1578,6 +1639,7 @@ static const struct vm_operations_struct xfs_file_vm_ops = {
 	.pmd_fault	= xfs_filemap_pmd_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= xfs_filemap_page_mkwrite,
+	.pfn_mkwrite	= xfs_filemap_pfn_mkwrite,
 };
 
 STATIC int