Merge tag 'xfs-4.14-fixes-2' of git://git.kernel.org/pub/scm/fs/xfs/x…

…fs-linux

Pull xfs fixes from Darrick Wong:

 - fix various problems with the copy-on-write extent maps getting freed
   at the wrong time

 - fix printk format specifier problems

 - report zeroing operation outcomes instead of dropping them on the
   floor

 - fix some crashes when dio operations partially fail

 - fix a race condition between unwritten extent conversion & dio read

 - fix some incorrect tests in the inode log item processing

 - correct the delayed allocation space reservations on rmap filesystems

 - fix some problems checking for dax support

* tag 'xfs-4.14-fixes-2' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  xfs: revert "xfs: factor rmap btree size into the indlen calculations"
  xfs: Capture state of the right inode in xfs_iflush_done
  xfs: perag initialization should only touch m_ag_max_usable for AG 0
  xfs: update i_size after unwritten conversion in dio completion
  iomap_dio_rw: Allocate AIO completion queue before submitting dio
  xfs: validate bdev support for DAX inode flag
  xfs: remove redundant re-initialization of total_nr_pages
  xfs: Output warning message when discard option was enabled even though the device does not support discard
  xfs: report zeroed or not correctly in xfs_zero_range()
  xfs: kill meaningless variable 'zero'
  fs/xfs: Use %pS printk format for direct addresses
  xfs: evict CoW fork extents when performing finsert/fcollapse
  xfs: don't unconditionally clear the reflink flag on zero-block files

fs/iomap.c

@@ -1009,6 +1009,13 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	WARN_ON_ONCE(ret);
 	ret = 0;
 
+	if (iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) &&
+	    !inode->i_sb->s_dio_done_wq) {
+		ret = sb_init_dio_done_wq(inode->i_sb);
+		if (ret < 0)
+			goto out_free_dio;
+	}
+
 	inode_dio_begin(inode);
 
 	blk_start_plug(&plug);
@@ -1031,13 +1038,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (ret < 0)
 		iomap_dio_set_error(dio, ret);
 
-	if (ret >= 0 && iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) &&
-			!inode->i_sb->s_dio_done_wq) {
-		ret = sb_init_dio_done_wq(inode->i_sb);
-		if (ret < 0)
-			iomap_dio_set_error(dio, ret);
-	}
-
 	if (!atomic_dec_and_test(&dio->ref)) {
 		if (!is_sync_kiocb(iocb))
 			return -EIOCBQUEUED;

fs/xfs/libxfs/xfs_ag_resv.c

@@ -156,7 +156,8 @@ __xfs_ag_resv_free(
 	trace_xfs_ag_resv_free(pag, type, 0);
 
 	resv = xfs_perag_resv(pag, type);
-	pag->pag_mount->m_ag_max_usable += resv->ar_asked;
+	if (pag->pag_agno == 0)
+		pag->pag_mount->m_ag_max_usable += resv->ar_asked;
 	/*
 	 * AGFL blocks are always considered "free", so whatever
 	 * was reserved at mount time must be given back at umount.
@@ -216,7 +217,14 @@ __xfs_ag_resv_init(
 		return error;
 	}
 
-	mp->m_ag_max_usable -= ask;
+	/*
+	 * Reduce the maximum per-AG allocation length by however much we're
+	 * trying to reserve for an AG.  Since this is a filesystem-wide
+	 * counter, we only make the adjustment for AG 0.  This assumes that
+	 * there aren't any AGs hungrier for per-AG reservation than AG 0.
+	 */
+	if (pag->pag_agno == 0)
+		mp->m_ag_max_usable -= ask;
 
 	resv = xfs_perag_resv(pag, type);
 	resv->ar_asked = ask;

fs/xfs/libxfs/xfs_bmap.c

@@ -49,7 +49,6 @@
 #include "xfs_rmap.h"
 #include "xfs_ag_resv.h"
 #include "xfs_refcount.h"
-#include "xfs_rmap_btree.h"
 #include "xfs_icache.h"
 
 
@@ -192,33 +191,21 @@ xfs_bmap_worst_indlen(
 	int		maxrecs;	/* maximum record count at this level */
 	xfs_mount_t	*mp;		/* mount structure */
 	xfs_filblks_t	rval;		/* return value */
-	xfs_filblks_t   orig_len;
 
 	mp = ip->i_mount;
-
-	/* Calculate the worst-case size of the bmbt. */
-	orig_len = len;
 	maxrecs = mp->m_bmap_dmxr[0];
 	for (level = 0, rval = 0;
 	     level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK);
 	     level++) {
 		len += maxrecs - 1;
 		do_div(len, maxrecs);
 		rval += len;
-		if (len == 1) {
-			rval += XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) -
+		if (len == 1)
+			return rval + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) -
 				level - 1;
-			break;
-		}
 		if (level == 0)
 			maxrecs = mp->m_bmap_dmxr[1];
 	}
-
-	/* Calculate the worst-case size of the rmapbt. */
-	if (xfs_sb_version_hasrmapbt(&mp->m_sb))
-		rval += 1 + xfs_rmapbt_calc_size(mp, orig_len) +
-				mp->m_rmap_maxlevels;
-
 	return rval;
 }
 

fs/xfs/xfs_aops.c

@@ -343,7 +343,8 @@ xfs_end_io(
 		error = xfs_reflink_end_cow(ip, offset, size);
 		break;
 	case XFS_IO_UNWRITTEN:
-		error = xfs_iomap_write_unwritten(ip, offset, size);
+		/* writeback should never update isize */
+		error = xfs_iomap_write_unwritten(ip, offset, size, false);
 		break;
 	default:
 		ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans);

fs/xfs/xfs_bmap_util.c

@@ -1459,7 +1459,19 @@ xfs_shift_file_space(
 		return error;
 
 	/*
-	 * The extent shiting code works on extent granularity. So, if
+	 * Clean out anything hanging around in the cow fork now that
+	 * we've flushed all the dirty data out to disk to avoid having
+	 * CoW extents at the wrong offsets.
+	 */
+	if (xfs_is_reflink_inode(ip)) {
+		error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF,
+				true);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * The extent shifting code works on extent granularity. So, if
 	 * stop_fsb is not the starting block of extent, we need to split
 	 * the extent at stop_fsb.
 	 */

fs/xfs/xfs_buf.c

@@ -1258,8 +1258,6 @@ xfs_buf_ioapply_map(
 	int		size;
 	int		offset;
 
-	total_nr_pages = bp->b_page_count;
-
 	/* skip the pages in the buffer before the start offset */
 	page_index = 0;
 	offset = *buf_offset;

fs/xfs/xfs_error.c

@@ -347,7 +347,7 @@ xfs_verifier_error(
 {
 	struct xfs_mount *mp = bp->b_target->bt_mount;
 
-	xfs_alert(mp, "Metadata %s detected at %pF, %s block 0x%llx",
+	xfs_alert(mp, "Metadata %s detected at %pS, %s block 0x%llx",
 		  bp->b_error == -EFSBADCRC ? "CRC error" : "corruption",
 		  __return_address, bp->b_ops->name, bp->b_bn);
 

fs/xfs/xfs_file.c

@@ -58,7 +58,7 @@ xfs_zero_range(
 	xfs_off_t		count,
 	bool			*did_zero)
 {
-	return iomap_zero_range(VFS_I(ip), pos, count, NULL, &xfs_iomap_ops);
+	return iomap_zero_range(VFS_I(ip), pos, count, did_zero, &xfs_iomap_ops);
 }
 
 int
@@ -377,8 +377,6 @@ xfs_file_aio_write_checks(
 	 */
 	spin_lock(&ip->i_flags_lock);
 	if (iocb->ki_pos > i_size_read(inode)) {
-		bool	zero = false;
-
 		spin_unlock(&ip->i_flags_lock);
 		if (!drained_dio) {
 			if (*iolock == XFS_IOLOCK_SHARED) {
@@ -399,7 +397,7 @@ xfs_file_aio_write_checks(
 			drained_dio = true;
 			goto restart;
 		}
-		error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), &zero);
+		error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), NULL);
 		if (error)
 			return error;
 	} else
@@ -436,7 +434,6 @@ xfs_dio_write_end_io(
 	struct inode		*inode = file_inode(iocb->ki_filp);
 	struct xfs_inode	*ip = XFS_I(inode);
 	loff_t			offset = iocb->ki_pos;
-	bool			update_size = false;
 	int			error = 0;
 
 	trace_xfs_end_io_direct_write(ip, offset, size);
@@ -447,6 +444,21 @@ xfs_dio_write_end_io(
 	if (size <= 0)
 		return size;
 
+	if (flags & IOMAP_DIO_COW) {
+		error = xfs_reflink_end_cow(ip, offset, size);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * Unwritten conversion updates the in-core isize after extent
+	 * conversion but before updating the on-disk size. Updating isize any
+	 * earlier allows a racing dio read to find unwritten extents before
+	 * they are converted.
+	 */
+	if (flags & IOMAP_DIO_UNWRITTEN)
+		return xfs_iomap_write_unwritten(ip, offset, size, true);
+
 	/*
 	 * We need to update the in-core inode size here so that we don't end up
 	 * with the on-disk inode size being outside the in-core inode size. We
@@ -461,20 +473,11 @@ xfs_dio_write_end_io(
 	spin_lock(&ip->i_flags_lock);
 	if (offset + size > i_size_read(inode)) {
 		i_size_write(inode, offset + size);
-		update_size = true;
-	}
-	spin_unlock(&ip->i_flags_lock);
-
-	if (flags & IOMAP_DIO_COW) {
-		error = xfs_reflink_end_cow(ip, offset, size);
-		if (error)
-			return error;
-	}
-
-	if (flags & IOMAP_DIO_UNWRITTEN)
-		error = xfs_iomap_write_unwritten(ip, offset, size);
-	else if (update_size)
+		spin_unlock(&ip->i_flags_lock);
 		error = xfs_setfilesize(ip, offset, size);
+	} else {
+		spin_unlock(&ip->i_flags_lock);
+	}
 
 	return error;
 }

fs/xfs/xfs_inode.c

@@ -1624,10 +1624,12 @@ xfs_itruncate_extents(
 		goto out;
 
 	/*
-	 * Clear the reflink flag if we truncated everything.
+	 * Clear the reflink flag if there are no data fork blocks and
+	 * there are no extents staged in the cow fork.
 	 */
-	if (ip->i_d.di_nblocks == 0 && xfs_is_reflink_inode(ip)) {
-		ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
+	if (xfs_is_reflink_inode(ip) && ip->i_cnextents == 0) {
+		if (ip->i_d.di_nblocks == 0)
+			ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
 		xfs_inode_clear_cowblocks_tag(ip);
 	}
 

fs/xfs/xfs_inode_item.c

@@ -745,7 +745,7 @@ xfs_iflush_done(
 		 */
 		iip = INODE_ITEM(blip);
 		if ((iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) ||
-		    lip->li_flags & XFS_LI_FAILED)
+		    (blip->li_flags & XFS_LI_FAILED))
 			need_ail++;
 
 		blip = next;

fs/xfs/xfs_ioctl.c

@@ -1088,6 +1088,7 @@ xfs_ioctl_setattr_dax_invalidate(
 	int			*join_flags)
 {
 	struct inode		*inode = VFS_I(ip);
+	struct super_block	*sb = inode->i_sb;
 	int			error;
 
 	*join_flags = 0;
@@ -1100,7 +1101,7 @@ xfs_ioctl_setattr_dax_invalidate(
 	if (fa->fsx_xflags & FS_XFLAG_DAX) {
 		if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
 			return -EINVAL;
-		if (ip->i_mount->m_sb.sb_blocksize != PAGE_SIZE)
+		if (bdev_dax_supported(sb, sb->s_blocksize) < 0)
 			return -EINVAL;
 	}
 

fs/xfs/xfs_iomap.c

@@ -829,7 +829,8 @@ int
 xfs_iomap_write_unwritten(
 	xfs_inode_t	*ip,
 	xfs_off_t	offset,
-	xfs_off_t	count)
+	xfs_off_t	count,
+	bool		update_isize)
 {
 	xfs_mount_t	*mp = ip->i_mount;
 	xfs_fileoff_t	offset_fsb;
@@ -840,6 +841,7 @@ xfs_iomap_write_unwritten(
 	xfs_trans_t	*tp;
 	xfs_bmbt_irec_t imap;
 	struct xfs_defer_ops dfops;
+	struct inode	*inode = VFS_I(ip);
 	xfs_fsize_t	i_size;
 	uint		resblks;
 	int		error;
@@ -899,7 +901,8 @@ xfs_iomap_write_unwritten(
 		i_size = XFS_FSB_TO_B(mp, offset_fsb + count_fsb);
 		if (i_size > offset + count)
 			i_size = offset + count;
-
+		if (update_isize && i_size > i_size_read(inode))
+			i_size_write(inode, i_size);
 		i_size = xfs_new_eof(ip, i_size);
 		if (i_size) {
 			ip->i_d.di_size = i_size;

fs/xfs/xfs_iomap.h

@@ -27,7 +27,7 @@ int xfs_iomap_write_direct(struct xfs_inode *, xfs_off_t, size_t,
 			struct xfs_bmbt_irec *, int);
 int xfs_iomap_write_allocate(struct xfs_inode *, int, xfs_off_t,
 			struct xfs_bmbt_irec *);
-int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t);
+int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool);
 
 void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *,
 		struct xfs_bmbt_irec *);

fs/xfs/xfs_pnfs.c

@@ -274,7 +274,7 @@ xfs_fs_commit_blocks(
 					(end - 1) >> PAGE_SHIFT);
 		WARN_ON_ONCE(error);
 
-		error = xfs_iomap_write_unwritten(ip, start, length);
+		error = xfs_iomap_write_unwritten(ip, start, length, false);
 		if (error)
 			goto out_drop_iolock;
 	}

fs/xfs/xfs_super.c

@@ -1654,6 +1654,16 @@ xfs_fs_fill_super(
 		"DAX and reflink have not been tested together!");
 	}
 
+	if (mp->m_flags & XFS_MOUNT_DISCARD) {
+		struct request_queue *q = bdev_get_queue(sb->s_bdev);
+
+		if (!blk_queue_discard(q)) {
+			xfs_warn(mp, "mounting with \"discard\" option, but "
+					"the device does not support discard");
+			mp->m_flags &= ~XFS_MOUNT_DISCARD;
+		}
+	}
+
 	if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
 		if (mp->m_sb.sb_rblocks) {
 			xfs_alert(mp,