21 files changed, 405 insertions, 230 deletions

diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 496e2f72a85b..797d5b5f7b72 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -749,7 +749,7 @@ xfs_finobt_count_blocks(
 	if (error)
 		return error;
 
-	cur = xfs_inobt_init_cursor(pag, tp, agbp);
+	cur = xfs_finobt_init_cursor(pag, tp, agbp);
 	error = xfs_btree_count_blocks(cur, tree_blocks);
 	xfs_btree_del_cursor(cur, error);
 	xfs_trans_brelse(tp, agbp);
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 513b50da6215..79babeac9d75 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -514,12 +514,18 @@ xfs_dinode_verify(
 			return __this_address;
 	}
 
-	if (dip->di_version > 1) {
+	/*
+	 * Historical note: xfsprogs in the 3.2 era set up its incore inodes to
+	 * have di_nlink track the link count, even if the actual filesystem
+	 * only supported V1 inodes (i.e. di_onlink).  When writing out the
+	 * ondisk inode, it would set both the ondisk di_nlink and di_onlink to
+	 * the the incore di_nlink value, which is why we cannot check for
+	 * di_nlink==0 on a V1 inode.  V2/3 inodes would get written out with
+	 * di_onlink==0, so we can check that.
+	 */
+	if (dip->di_version >= 2) {
 		if (dip->di_onlink)
 			return __this_address;
-	} else {
-		if (dip->di_nlink)
-			return __this_address;
 	}
 
 	/* don't allow invalid i_size */
diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h
index cb035da3f990..fb05f44f6c75 100644
--- a/fs/xfs/libxfs/xfs_quota_defs.h
+++ b/fs/xfs/libxfs/xfs_quota_defs.h
@@ -56,7 +56,7 @@ typedef uint8_t		xfs_dqtype_t;
  * And, of course, we also need to take into account the dquot log format item
  * used to describe each dquot.
  */
-#define XFS_DQUOT_LOGRES(mp)	\
+#define XFS_DQUOT_LOGRES	\
 	((sizeof(struct xfs_dq_logformat) + sizeof(struct xfs_disk_dquot)) * 6)
 
 #define XFS_IS_QUOTA_ON(mp)		((mp)->m_qflags & XFS_ALL_QUOTA_ACCT)
diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c
index 3dc8f785bf29..45aaf169806a 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.c
+++ b/fs/xfs/libxfs/xfs_trans_resv.c
@@ -338,11 +338,11 @@ xfs_calc_write_reservation(
 					blksz);
 		t1 += adj;
 		t3 += adj;
-		return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3);
+		return XFS_DQUOT_LOGRES + max3(t1, t2, t3);
 	}
 
 	t4 = xfs_calc_refcountbt_reservation(mp, 1);
-	return XFS_DQUOT_LOGRES(mp) + max(t4, max3(t1, t2, t3));
+	return XFS_DQUOT_LOGRES + max(t4, max3(t1, t2, t3));
 }
 
 unsigned int
@@ -410,11 +410,11 @@ xfs_calc_itruncate_reservation(
 					xfs_refcountbt_block_count(mp, 4),
 					blksz);
 
-		return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3);
+		return XFS_DQUOT_LOGRES + max3(t1, t2, t3);
 	}
 
 	t4 = xfs_calc_refcountbt_reservation(mp, 2);
-	return XFS_DQUOT_LOGRES(mp) + max(t4, max3(t1, t2, t3));
+	return XFS_DQUOT_LOGRES + max(t4, max3(t1, t2, t3));
 }
 
 unsigned int
@@ -466,7 +466,7 @@ STATIC uint
 xfs_calc_rename_reservation(
 	struct xfs_mount	*mp)
 {
-	unsigned int		overhead = XFS_DQUOT_LOGRES(mp);
+	unsigned int		overhead = XFS_DQUOT_LOGRES;
 	struct xfs_trans_resv	*resp = M_RES(mp);
 	unsigned int		t1, t2, t3 = 0;
 
@@ -577,7 +577,7 @@ STATIC uint
 xfs_calc_link_reservation(
 	struct xfs_mount	*mp)
 {
-	unsigned int		overhead = XFS_DQUOT_LOGRES(mp);
+	unsigned int		overhead = XFS_DQUOT_LOGRES;
 	struct xfs_trans_resv	*resp = M_RES(mp);
 	unsigned int		t1, t2, t3 = 0;
 
@@ -641,7 +641,7 @@ STATIC uint
 xfs_calc_remove_reservation(
 	struct xfs_mount	*mp)
 {
-	unsigned int            overhead = XFS_DQUOT_LOGRES(mp);
+	unsigned int            overhead = XFS_DQUOT_LOGRES;
 	struct xfs_trans_resv   *resp = M_RES(mp);
 	unsigned int            t1, t2, t3 = 0;
 
@@ -729,7 +729,7 @@ xfs_calc_icreate_reservation(
 	struct xfs_mount	*mp)
 {
 	struct xfs_trans_resv	*resp = M_RES(mp);
-	unsigned int		overhead = XFS_DQUOT_LOGRES(mp);
+	unsigned int		overhead = XFS_DQUOT_LOGRES;
 	unsigned int		t1, t2, t3 = 0;
 
 	t1 = xfs_calc_icreate_resv_alloc(mp);
@@ -747,7 +747,7 @@ STATIC uint
 xfs_calc_create_tmpfile_reservation(
 	struct xfs_mount        *mp)
 {
-	uint	res = XFS_DQUOT_LOGRES(mp);
+	uint	res = XFS_DQUOT_LOGRES;
 
 	res += xfs_calc_icreate_resv_alloc(mp);
 	return res + xfs_calc_iunlink_add_reservation(mp);
@@ -829,7 +829,7 @@ STATIC uint
 xfs_calc_ifree_reservation(
 	struct xfs_mount	*mp)
 {
-	return XFS_DQUOT_LOGRES(mp) +
+	return XFS_DQUOT_LOGRES +
 		xfs_calc_inode_res(mp, 1) +
 		xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
 		xfs_calc_iunlink_remove_reservation(mp) +
@@ -846,7 +846,7 @@ STATIC uint
 xfs_calc_ichange_reservation(
 	struct xfs_mount	*mp)
 {
-	return XFS_DQUOT_LOGRES(mp) +
+	return XFS_DQUOT_LOGRES +
 		xfs_calc_inode_res(mp, 1) +
 		xfs_calc_buf_res(1, mp->m_sb.sb_sectsize);
 
@@ -955,7 +955,7 @@ STATIC uint
 xfs_calc_addafork_reservation(
 	struct xfs_mount	*mp)
 {
-	return XFS_DQUOT_LOGRES(mp) +
+	return XFS_DQUOT_LOGRES +
 		xfs_calc_inode_res(mp, 1) +
 		xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
 		xfs_calc_buf_res(1, mp->m_dir_geo->blksize) +
@@ -1003,7 +1003,7 @@ STATIC uint
 xfs_calc_attrsetm_reservation(
 	struct xfs_mount	*mp)
 {
-	return XFS_DQUOT_LOGRES(mp) +
+	return XFS_DQUOT_LOGRES +
 		xfs_calc_inode_res(mp, 1) +
 		xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
 		xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH, XFS_FSB_TO_B(mp, 1));
@@ -1043,7 +1043,7 @@ STATIC uint
 xfs_calc_attrrm_reservation(
 	struct xfs_mount	*mp)
 {
-	return XFS_DQUOT_LOGRES(mp) +
+	return XFS_DQUOT_LOGRES +
 		max((xfs_calc_inode_res(mp, 1) +
 		     xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH,
 				      XFS_FSB_TO_B(mp, 1)) +
diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index 0dbc484b182f..2f98d90d7fd6 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -696,7 +696,7 @@ xrep_agfl_init_header(
 	 * step.
 	 */
 	xagb_bitmap_init(&af.used_extents);
-	af.agfl_bno = xfs_buf_to_agfl_bno(agfl_bp),
+	af.agfl_bno = xfs_buf_to_agfl_bno(agfl_bp);
 	xagb_bitmap_walk(agfl_extents, xrep_agfl_fill, &af);
 	error = xagb_bitmap_disunion(agfl_extents, &af.used_extents);
 	if (error)
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 24a15bf784f1..5ab2ac53c920 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -938,7 +938,13 @@ xchk_bmap(
 		}
 		break;
 	case XFS_ATTR_FORK:
-		if (!xfs_has_attr(mp) && !xfs_has_attr2(mp))
+		/*
+		 * "attr" means that an attr fork was created at some point in
+		 * the life of this filesystem.  "attr2" means that inodes have
+		 * variable-sized data/attr fork areas.  Hence we only check
+		 * attr here.
+		 */
+		if (!xfs_has_attr(mp))
 			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		break;
 	default:
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index 733c410a2279..91e7b51ce068 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -799,7 +799,7 @@ xchk_parent_pptr(
 	}
 
 	if (pp->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
-		goto out_pp;
+		goto out_names;
 
 	/*
 	 * Complain if the number of parent pointers doesn't match the link
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 92ef4cdc486e..c886d5d0eb02 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -959,18 +959,16 @@ TRACE_EVENT(xfile_create,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(unsigned long, ino)
-		__array(char, pathname, 256)
+		__array(char, pathname, MAXNAMELEN)
 	),
 	TP_fast_assign(
-		char		pathname[257];
 		char		*path;
 
 		__entry->ino = file_inode(xf->file)->i_ino;
-		memset(pathname, 0, sizeof(pathname));
-		path = file_path(xf->file, pathname, sizeof(pathname) - 1);
+		path = file_path(xf->file, __entry->pathname, MAXNAMELEN);
 		if (IS_ERR(path))
-			path = "(unknown)";
-		strncpy(__entry->pathname, path, sizeof(__entry->pathname));
+			strncpy(__entry->pathname, "(unknown)",
+					sizeof(__entry->pathname));
 	),
 	TP_printk("xfino 0x%lx path '%s'",
 		  __entry->ino,
diff --git a/fs/xfs/scrub/xfile.c b/fs/xfs/scrub/xfile.c
index d848222f802b..9b5d98fe1f8a 100644
--- a/fs/xfs/scrub/xfile.c
+++ b/fs/xfs/scrub/xfile.c
@@ -293,7 +293,7 @@ xfile_get_folio(
 	 * (potentially last) reference in xfile_put_folio.
 	 */
 	if (flags & XFILE_ALLOC)
-		folio_set_dirty(folio);
+		folio_mark_dirty(folio);
 	return folio;
 }
 
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 5c947e5ce8b8..7db386304875 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -139,7 +139,7 @@ xfs_attr_shortform_list(
 		sbp->name = sfe->nameval;
 		sbp->namelen = sfe->namelen;
 		/* These are bytes, and both on-disk, don't endian-flip */
-		sbp->value = &sfe->nameval[sfe->namelen],
+		sbp->value = &sfe->nameval[sfe->namelen];
 		sbp->valuelen = sfe->valuelen;
 		sbp->flags = sfe->flags;
 		sbp->hash = xfs_attr_hashval(dp->i_mount, sfe->flags,
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index fe2e2c930975..e9fdebaa40ea 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -653,6 +653,9 @@ xfs_alloc_file_space(
 	xfs_bmbt_irec_t		imaps[1], *imapp;
 	int			error;
 
+	if (xfs_is_always_cow_inode(ip))
+		return 0;
+
 	trace_xfs_alloc_file_space(ip);
 
 	if (xfs_is_shutdown(mp))
@@ -848,6 +851,14 @@ xfs_free_file_space(
 	if (len <= 0)	/* if nothing being freed */
 		return 0;
 
+	/*
+	 * Now AIO and DIO has drained we flush and (if necessary) invalidate
+	 * the cached range over the first operation we are about to run.
+	 */
+	error = xfs_flush_unmap_range(ip, offset, len);
+	if (error)
+		return error;
+
 	startoffset_fsb = XFS_B_TO_FSB(mp, offset);
 	endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
 
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index b1580644501f..209a389f2abc 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -210,7 +210,7 @@ struct xfs_buf {
 	 * success the write is considered to be failed permanently and the
 	 * iodone handler will take appropriate action.
 	 *
-	 * For retry timeouts, we record the jiffie of the first failure. This
+	 * For retry timeouts, we record the jiffy of the first failure. This
 	 * means that we can change the retry timeout for buffers already under
 	 * I/O and thus avoid getting stuck in a retry loop with a long timeout.
 	 *
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 6f0fc7fe1f2b..25f5dffeab2a 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -158,8 +158,7 @@ static int
 xfs_trim_gather_extents(
 	struct xfs_perag	*pag,
 	struct xfs_trim_cur	*tcur,
-	struct xfs_busy_extents	*extents,
-	uint64_t		*blocks_trimmed)
+	struct xfs_busy_extents	*extents)
 {
 	struct xfs_mount	*mp = pag->pag_mount;
 	struct xfs_trans	*tp;
@@ -280,7 +279,6 @@ xfs_trim_gather_extents(
 
 		xfs_extent_busy_insert_discard(pag, fbno, flen,
 				&extents->extent_list);
-		*blocks_trimmed += flen;
 next_extent:
 		if (tcur->by_bno)
 			error = xfs_btree_increment(cur, 0, &i);
@@ -327,8 +325,7 @@ xfs_trim_perag_extents(
 	struct xfs_perag	*pag,
 	xfs_agblock_t		start,
 	xfs_agblock_t		end,
-	xfs_extlen_t		minlen,
-	uint64_t		*blocks_trimmed)
+	xfs_extlen_t		minlen)
 {
 	struct xfs_trim_cur	tcur = {
 		.start		= start,
@@ -354,8 +351,7 @@ xfs_trim_perag_extents(
 		extents->owner = extents;
 		INIT_LIST_HEAD(&extents->extent_list);
 
-		error = xfs_trim_gather_extents(pag, &tcur, extents,
-				blocks_trimmed);
+		error = xfs_trim_gather_extents(pag, &tcur, extents);
 		if (error) {
 			kfree(extents);
 			break;
@@ -389,8 +385,7 @@ xfs_trim_datadev_extents(
 	struct xfs_mount	*mp,
 	xfs_daddr_t		start,
 	xfs_daddr_t		end,
-	xfs_extlen_t		minlen,
-	uint64_t		*blocks_trimmed)
+	xfs_extlen_t		minlen)
 {
 	xfs_agnumber_t		start_agno, end_agno;
 	xfs_agblock_t		start_agbno, end_agbno;
@@ -411,8 +406,7 @@ xfs_trim_datadev_extents(
 
 		if (start_agno == end_agno)
 			agend = end_agbno;
-		error = xfs_trim_perag_extents(pag, start_agbno, agend, minlen,
-				blocks_trimmed);
+		error = xfs_trim_perag_extents(pag, start_agbno, agend, minlen);
 		if (error)
 			last_error = error;
 
@@ -431,9 +425,6 @@ struct xfs_trim_rtdev {
 	/* list of rt extents to free */
 	struct list_head	extent_list;
 
-	/* pointer to count of blocks trimmed */
-	uint64_t		*blocks_trimmed;
-
 	/* minimum length that caller allows us to trim */
 	xfs_rtblock_t		minlen_fsb;
 
@@ -551,7 +542,6 @@ xfs_trim_gather_rtextent(
 	busyp->length = rlen;
 	INIT_LIST_HEAD(&busyp->list);
 	list_add_tail(&busyp->list, &tr->extent_list);
-	*tr->blocks_trimmed += rlen;
 
 	tr->restart_rtx = rec->ar_startext + rec->ar_extcount;
 	return 0;
@@ -562,13 +552,11 @@ xfs_trim_rtdev_extents(
 	struct xfs_mount	*mp,
 	xfs_daddr_t		start,
 	xfs_daddr_t		end,
-	xfs_daddr_t		minlen,
-	uint64_t		*blocks_trimmed)
+	xfs_daddr_t		minlen)
 {
 	struct xfs_rtalloc_rec	low = { };
 	struct xfs_rtalloc_rec	high = { };
 	struct xfs_trim_rtdev	tr = {
-		.blocks_trimmed	= blocks_trimmed,
 		.minlen_fsb	= XFS_BB_TO_FSB(mp, minlen),
 	};
 	struct xfs_trans	*tp;
@@ -634,7 +622,7 @@ xfs_trim_rtdev_extents(
 	return error;
 }
 #else
-# define xfs_trim_rtdev_extents(m,s,e,n,b)	(-EOPNOTSUPP)
+# define xfs_trim_rtdev_extents(...)	(-EOPNOTSUPP)
 #endif /* CONFIG_XFS_RT */
 
 /*
@@ -661,7 +649,6 @@ xfs_ioc_trim(
 	xfs_daddr_t		start, end;
 	xfs_extlen_t		minlen;
 	xfs_rfsblock_t		max_blocks;
-	uint64_t		blocks_trimmed = 0;
 	int			error, last_error = 0;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -706,15 +693,13 @@ xfs_ioc_trim(
 	end = start + BTOBBT(range.len) - 1;
 
 	if (bdev_max_discard_sectors(mp->m_ddev_targp->bt_bdev)) {
-		error = xfs_trim_datadev_extents(mp, start, end, minlen,
-				&blocks_trimmed);
+		error = xfs_trim_datadev_extents(mp, start, end, minlen);
 		if (error)
 			last_error = error;
 	}
 
 	if (rt_bdev && !xfs_trim_should_stop()) {
-		error = xfs_trim_rtdev_extents(mp, start, end, minlen,
-				&blocks_trimmed);
+		error = xfs_trim_rtdev_extents(mp, start, end, minlen);
 		if (error)
 			last_error = error;
 	}
@@ -722,7 +707,8 @@ xfs_ioc_trim(
 	if (last_error)
 		return last_error;
 
-	range.len = XFS_FSB_TO_B(mp, blocks_trimmed);
+	range.len = min_t(unsigned long long, range.len,
+			  XFS_FSB_TO_B(mp, max_blocks));
 	if (copy_to_user(urange, &range, sizeof(range)))
 		return -EFAULT;
 	return 0;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 4cdc54dc9686..f6e4912769a0 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -852,6 +852,192 @@ static inline bool xfs_file_sync_writes(struct file *filp)
 	return false;
 }
 
+static int
+xfs_falloc_newsize(
+	struct file		*file,
+	int			mode,
+	loff_t			offset,
+	loff_t			len,
+	loff_t			*new_size)
+{
+	struct inode		*inode = file_inode(file);
+
+	if ((mode & FALLOC_FL_KEEP_SIZE) || offset + len <= i_size_read(inode))
+		return 0;
+	*new_size = offset + len;
+	return inode_newsize_ok(inode, *new_size);
+}
+
+static int
+xfs_falloc_setsize(
+	struct file		*file,
+	loff_t			new_size)
+{
+	struct iattr iattr = {
+		.ia_valid	= ATTR_SIZE,
+		.ia_size	= new_size,
+	};
+
+	if (!new_size)
+		return 0;
+	return xfs_vn_setattr_size(file_mnt_idmap(file), file_dentry(file),
+			&iattr);
+}
+
+static int
+xfs_falloc_collapse_range(
+	struct file		*file,
+	loff_t			offset,
+	loff_t			len)
+{
+	struct inode		*inode = file_inode(file);
+	loff_t			new_size = i_size_read(inode) - len;
+	int			error;
+
+	if (!xfs_is_falloc_aligned(XFS_I(inode), offset, len))
+		return -EINVAL;
+
+	/*
+	 * There is no need to overlap collapse range with EOF, in which case it
+	 * is effectively a truncate operation
+	 */
+	if (offset + len >= i_size_read(inode))
+		return -EINVAL;
+
+	error = xfs_collapse_file_space(XFS_I(inode), offset, len);
+	if (error)
+		return error;
+	return xfs_falloc_setsize(file, new_size);
+}
+
+static int
+xfs_falloc_insert_range(
+	struct file		*file,
+	loff_t			offset,
+	loff_t			len)
+{
+	struct inode		*inode = file_inode(file);
+	loff_t			isize = i_size_read(inode);
+	int			error;
+
+	if (!xfs_is_falloc_aligned(XFS_I(inode), offset, len))
+		return -EINVAL;
+
+	/*
+	 * New inode size must not exceed ->s_maxbytes, accounting for
+	 * possible signed overflow.
+	 */
+	if (inode->i_sb->s_maxbytes - isize < len)
+		return -EFBIG;
+
+	/* Offset should be less than i_size */
+	if (offset >= isize)
+		return -EINVAL;
+
+	error = xfs_falloc_setsize(file, isize + len);
+	if (error)
+		return error;
+
+	/*
+	 * Perform hole insertion now that the file size has been updated so
+	 * that if we crash during the operation we don't leave shifted extents
+	 * past EOF and hence losing access to the data that is contained within
+	 * them.
+	 */
+	return xfs_insert_file_space(XFS_I(inode), offset, len);
+}
+
+/*
+ * Punch a hole and prealloc the range.  We use a hole punch rather than
+ * unwritten extent conversion for two reasons:
+ *
+ *   1.) Hole punch handles partial block zeroing for us.
+ *   2.) If prealloc returns ENOSPC, the file range is still zero-valued by
+ *	 virtue of the hole punch.
+ */
+static int
+xfs_falloc_zero_range(
+	struct file		*file,
+	int			mode,
+	loff_t			offset,
+	loff_t			len)
+{
+	struct inode		*inode = file_inode(file);
+	unsigned int		blksize = i_blocksize(inode);
+	loff_t			new_size = 0;
+	int			error;
+
+	trace_xfs_zero_file_space(XFS_I(inode));
+
+	error = xfs_falloc_newsize(file, mode, offset, len, &new_size);
+	if (error)
+		return error;
+
+	error = xfs_free_file_space(XFS_I(inode), offset, len);
+	if (error)
+		return error;
+
+	len = round_up(offset + len, blksize) - round_down(offset, blksize);
+	offset = round_down(offset, blksize);
+	error = xfs_alloc_file_space(XFS_I(inode), offset, len);
+	if (error)
+		return error;
+	return xfs_falloc_setsize(file, new_size);
+}
+
+static int
+xfs_falloc_unshare_range(
+	struct file		*file,
+	int			mode,
+	loff_t			offset,
+	loff_t			len)
+{
+	struct inode		*inode = file_inode(file);
+	loff_t			new_size = 0;
+	int			error;
+
+	error = xfs_falloc_newsize(file, mode, offset, len, &new_size);
+	if (error)
+		return error;
+
+	error = xfs_reflink_unshare(XFS_I(inode), offset, len);
+	if (error)
+		return error;
+
+	error = xfs_alloc_file_space(XFS_I(inode), offset, len);
+	if (error)
+		return error;
+	return xfs_falloc_setsize(file, new_size);
+}
+
+static int
+xfs_falloc_allocate_range(
+	struct file		*file,
+	int			mode,
+	loff_t			offset,
+	loff_t			len)
+{
+	struct inode		*inode = file_inode(file);
+	loff_t			new_size = 0;
+	int			error;
+
+	/*
+	 * If always_cow mode we can't use preallocations and thus should not
+	 * create them.
+	 */
+	if (xfs_is_always_cow_inode(XFS_I(inode)))
+		return -EOPNOTSUPP;
+
+	error = xfs_falloc_newsize(file, mode, offset, len, &new_size);
+	if (error)
+		return error;
+
+	error = xfs_alloc_file_space(XFS_I(inode), offset, len);
+	if (error)
+		return error;
+	return xfs_falloc_setsize(file, new_size);
+}
+
 #define	XFS_FALLOC_FL_SUPPORTED						\
 		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
 		 FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |	\
@@ -868,8 +1054,6 @@ xfs_file_fallocate(
 	struct xfs_inode	*ip = XFS_I(inode);
 	long			error;
 	uint			iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
-	loff_t			new_size = 0;
-	bool			do_file_insert = false;
 
 	if (!S_ISREG(inode->i_mode))
 		return -EINVAL;
@@ -890,156 +1074,35 @@ xfs_file_fallocate(
 	 */
 	inode_dio_wait(inode);
 
-	/*
-	 * Now AIO and DIO has drained we flush and (if necessary) invalidate
-	 * the cached range over the first operation we are about to run.
-	 *
-	 * We care about zero and collapse here because they both run a hole
-	 * punch over the range first. Because that can zero data, and the range
-	 * of invalidation for the shift operations is much larger, we still do
-	 * the required flush for collapse in xfs_prepare_shift().
-	 *
-	 * Insert has the same range requirements as collapse, and we extend the
-	 * file first which can zero data. Hence insert has the same
-	 * flush/invalidate requirements as collapse and so they are both
-	 * handled at the right time by xfs_prepare_shift().
-	 */
-	if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE |
-		    FALLOC_FL_COLLAPSE_RANGE)) {
-		error = xfs_flush_unmap_range(ip, offset, len);
-		if (error)
-			goto out_unlock;
-	}
-
 	error = file_modified(file);
 	if (error)
 		goto out_unlock;
 
-	if (mode & FALLOC_FL_PUNCH_HOLE) {
+	switch (mode & FALLOC_FL_MODE_MASK) {
+	case FALLOC_FL_PUNCH_HOLE:
 		error = xfs_free_file_space(ip, offset, len);
-		if (error)
-			goto out_unlock;
-	} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
-		if (!xfs_is_falloc_aligned(ip, offset, len)) {
-			error = -EINVAL;
-			goto out_unlock;
-		}
-
-		/*
-		 * There is no need to overlap collapse range with EOF,
-		 * in which case it is effectively a truncate operation
-		 */
-		if (offset + len >= i_size_read(inode)) {
-			error = -EINVAL;
-			goto out_unlock;
-		}
-
-		new_size = i_size_read(inode) - len;
-
-		error = xfs_collapse_file_space(ip, offset, len);
-		if (error)
-			goto out_unlock;
-	} else if (mode & FALLOC_FL_INSERT_RANGE) {
-		loff_t		isize = i_size_read(inode);
-
-		if (!xfs_is_falloc_aligned(ip, offset, len)) {
-			error = -EINVAL;
-			goto out_unlock;
-		}
-
-		/*
-		 * New inode size must not exceed ->s_maxbytes, accounting for
-		 * possible signed overflow.
-		 */
-		if (inode->i_sb->s_maxbytes - isize < len) {
-			error = -EFBIG;
-			goto out_unlock;
-		}
-		new_size = isize + len;
-
-		/* Offset should be less than i_size */
-		if (offset >= isize) {
-			error = -EINVAL;
-			goto out_unlock;
-		}
-		do_file_insert = true;
-	} else {
-		if (!(mode & FALLOC_FL_KEEP_SIZE) &&
-		    offset + len > i_size_read(inode)) {
-			new_size = offset + len;
-			error = inode_newsize_ok(inode, new_size);
-			if (error)
-				goto out_unlock;
-		}
-
-		if (mode & FALLOC_FL_ZERO_RANGE) {
-			/*
-			 * Punch a hole and prealloc the range.  We use a hole
-			 * punch rather than unwritten extent conversion for two
-			 * reasons:
-			 *
-			 *   1.) Hole punch handles partial block zeroing for us.
-			 *   2.) If prealloc returns ENOSPC, the file range is
-			 *       still zero-valued by virtue of the hole punch.
-			 */
-			unsigned int blksize = i_blocksize(inode);
-
-			trace_xfs_zero_file_space(ip);
-
-			error = xfs_free_file_space(ip, offset, len);
-			if (error)
-				goto out_unlock;
-
-			len = round_up(offset + len, blksize) -
-			      round_down(offset, blksize);
-			offset = round_down(offset, blksize);
-		} else if (mode & FALLOC_FL_UNSHARE_RANGE) {
-			error = xfs_reflink_unshare(ip, offset, len);
-			if (error)
-				goto out_unlock;
-		} else {
-			/*
-			 * If always_cow mode we can't use preallocations and
-			 * thus should not create them.
-			 */
-			if (xfs_is_always_cow_inode(ip)) {
-				error = -EOPNOTSUPP;
-				goto out_unlock;
-			}
-		}
-
-		if (!xfs_is_always_cow_inode(ip)) {
-			error = xfs_alloc_file_space(ip, offset, len);
-			if (error)
-				goto out_unlock;
-		}
-	}
-
-	/* Change file size if needed */
-	if (new_size) {
-		struct iattr iattr;
-
-		iattr.ia_valid = ATTR_SIZE;
-		iattr.ia_size = new_size;
-		error = xfs_vn_setattr_size(file_mnt_idmap(file),
-					    file_dentry(file), &iattr);
-		if (error)
-			goto out_unlock;
-	}
-
-	/*
-	 * Perform hole insertion now that the file size has been
-	 * updated so that if we crash during the operation we don't
-	 * leave shifted extents past EOF and hence losing access to
-	 * the data that is contained within them.
-	 */
-	if (do_file_insert) {
-		error = xfs_insert_file_space(ip, offset, len);
-		if (error)
-			goto out_unlock;
+		break;
+	case FALLOC_FL_COLLAPSE_RANGE:
+		error = xfs_falloc_collapse_range(file, offset, len);
+		break;
+	case FALLOC_FL_INSERT_RANGE:
+		error = xfs_falloc_insert_range(file, offset, len);
+		break;
+	case FALLOC_FL_ZERO_RANGE:
+		error = xfs_falloc_zero_range(file, mode, offset, len);
+		break;
+	case FALLOC_FL_UNSHARE_RANGE:
+		error = xfs_falloc_unshare_range(file, mode, offset, len);
+		break;
+	case FALLOC_FL_ALLOCATE_RANGE:
+		error = xfs_falloc_allocate_range(file, mode, offset, len);
+		break;
+	default:
+		error = -EOPNOTSUPP;
+		break;
 	}
 
-	if (xfs_file_sync_writes(file))
+	if (!error && xfs_file_sync_writes(file))
 		error = xfs_log_force_inode(ip);
 
 out_unlock:
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 85dbb46452ca..71f32354944e 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -71,7 +71,7 @@ xfs_fsmap_owner_to_rmap(
 	switch (src->fmr_owner) {
 	case 0:			/* "lowest owner id possible" */
 	case -1ULL:		/* "highest owner id possible" */
-		dest->rm_owner = 0;
+		dest->rm_owner = src->fmr_owner;
 		break;
 	case XFS_FMR_OWN_FREE:
 		dest->rm_owner = XFS_RMAP_OWN_NULL;
@@ -162,6 +162,7 @@ struct xfs_getfsmap_info {
 	xfs_daddr_t		next_daddr;	/* next daddr we expect */
 	/* daddr of low fsmap key when we're using the rtbitmap */
 	xfs_daddr_t		low_daddr;
+	xfs_daddr_t		end_daddr;	/* daddr of high fsmap key */
 	u64			missing_owner;	/* owner of holes */
 	u32			dev;		/* device id */
 	/*
@@ -182,6 +183,7 @@ struct xfs_getfsmap_dev {
 	int			(*fn)(struct xfs_trans *tp,
 				      const struct xfs_fsmap *keys,
 				      struct xfs_getfsmap_info *info);
+	sector_t		nr_sectors;
 };
 
 /* Compare two getfsmap device handlers. */
@@ -252,7 +254,7 @@ xfs_getfsmap_rec_before_start(
 	const struct xfs_rmap_irec	*rec,
 	xfs_daddr_t			rec_daddr)
 {
-	if (info->low_daddr != -1ULL)
+	if (info->low_daddr != XFS_BUF_DADDR_NULL)
 		return rec_daddr < info->low_daddr;
 	if (info->low.rm_blockcount)
 		return xfs_rmap_compare(rec, &info->low) < 0;
@@ -294,6 +296,18 @@ xfs_getfsmap_helper(
 		return 0;
 	}
 
+	/*
+	 * For an info->last query, we're looking for a gap between the last
+	 * mapping emitted and the high key specified by userspace.  If the
+	 * user's query spans less than 1 fsblock, then info->high and
+	 * info->low will have the same rm_startblock, which causes rec_daddr
+	 * and next_daddr to be the same.  Therefore, use the end_daddr that
+	 * we calculated from userspace's high key to synthesize the record.
+	 * Note that if the btree query found a mapping, there won't be a gap.
+	 */
+	if (info->last && info->end_daddr != XFS_BUF_DADDR_NULL)
+		rec_daddr = info->end_daddr;
+
 	/* Are we just counting mappings? */
 	if (info->head->fmh_count == 0) {
 		if (info->head->fmh_entries == UINT_MAX)
@@ -904,17 +918,21 @@ xfs_getfsmap(
 
 	/* Set up our device handlers. */
 	memset(handlers, 0, sizeof(handlers));
+	handlers[0].nr_sectors = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
 	handlers[0].dev = new_encode_dev(mp->m_ddev_targp->bt_dev);
 	if (use_rmap)
 		handlers[0].fn = xfs_getfsmap_datadev_rmapbt;
 	else
 		handlers[0].fn = xfs_getfsmap_datadev_bnobt;
 	if (mp->m_logdev_targp != mp->m_ddev_targp) {
+		handlers[1].nr_sectors = XFS_FSB_TO_BB(mp,
+						       mp->m_sb.sb_logblocks);
 		handlers[1].dev = new_encode_dev(mp->m_logdev_targp->bt_dev);
 		handlers[1].fn = xfs_getfsmap_logdev;
 	}
 #ifdef CONFIG_XFS_RT
 	if (mp->m_rtdev_targp) {
+		handlers[2].nr_sectors = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks);
 		handlers[2].dev = new_encode_dev(mp->m_rtdev_targp->bt_dev);
 		handlers[2].fn = xfs_getfsmap_rtdev_rtbitmap;
 	}
@@ -946,6 +964,7 @@ xfs_getfsmap(
 
 	info.next_daddr = head->fmh_keys[0].fmr_physical +
 			  head->fmh_keys[0].fmr_length;
+	info.end_daddr = XFS_BUF_DADDR_NULL;
 	info.fsmap_recs = fsmap_recs;
 	info.head = head;
 
@@ -966,8 +985,11 @@ xfs_getfsmap(
 		 * low key, zero out the low key so that we get
 		 * everything from the beginning.
 		 */
-		if (handlers[i].dev == head->fmh_keys[1].fmr_device)
+		if (handlers[i].dev == head->fmh_keys[1].fmr_device) {
 			dkeys[1] = head->fmh_keys[1];
+			info.end_daddr = min(handlers[i].nr_sectors - 1,
+					     dkeys[1].fmr_physical);
+		}
 		if (handlers[i].dev > head->fmh_keys[0].fmr_device)
 			memset(&dkeys[0], 0, sizeof(struct xfs_fsmap));
 
@@ -983,7 +1005,7 @@ xfs_getfsmap(
 		info.dev = handlers[i].dev;
 		info.last = false;
 		info.pag = NULL;
-		info.low_daddr = -1ULL;
+		info.low_daddr = XFS_BUF_DADDR_NULL;
 		info.low.rm_blockcount = 0;
 		error = handlers[i].fn(tp, dkeys, &info);
 		if (error)
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 4e933db75b12..6b13666d4e96 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -483,6 +483,17 @@ xfs_ioctl_setattr_xflags(
 		/* Can't change realtime flag if any extents are allocated. */
 		if (ip->i_df.if_nextents || ip->i_delayed_blks)
 			return -EINVAL;
+
+		/*
+		 * If S_DAX is enabled on this file, we can only switch the
+		 * device if both support fsdax.  We can't update S_DAX because
+		 * there might be other threads walking down the access paths.
+		 */
+		if (IS_DAX(VFS_I(ip)) &&
+		    (mp->m_ddev_targp->bt_daxdev == NULL ||
+		     (mp->m_rtdev_targp &&
+		      mp->m_rtdev_targp->bt_daxdev == NULL)))
+			return -EINVAL;
 	}
 
 	if (rtflag) {
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 0c3e96c621a6..ebeab8e4dab1 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -785,6 +785,39 @@ xfs_alloc_rsum_cache(
 }
 
 /*
+ * If we changed the rt extent size (meaning there was no rt volume previously)
+ * and the root directory had EXTSZINHERIT and RTINHERIT set, it's possible
+ * that the extent size hint on the root directory is no longer congruent with
+ * the new rt extent size.  Log the rootdir inode to fix this.
+ */
+static int
+xfs_growfs_rt_fixup_extsize(
+	struct xfs_mount	*mp)
+{
+	struct xfs_inode	*ip = mp->m_rootip;
+	struct xfs_trans	*tp;
+	int			error = 0;
+
+	xfs_ilock(ip, XFS_IOLOCK_EXCL);
+	if (!(ip->i_diflags & XFS_DIFLAG_RTINHERIT) ||
+	    !(ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT))
+		goto out_iolock;
+
+	error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_ichange, 0, 0, false,
+			&tp);
+	if (error)
+		goto out_iolock;
+
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	error = xfs_trans_commit(tp);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+out_iolock:
+	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+	return error;
+}
+
+/*
  * Visible (exported) functions.
  */
 
@@ -812,6 +845,7 @@ xfs_growfs_rt(
 	xfs_extlen_t	rsumblocks;	/* current number of rt summary blks */
 	xfs_sb_t	*sbp;		/* old superblock */
 	uint8_t		*rsum_cache;	/* old summary cache */
+	xfs_agblock_t	old_rextsize = mp->m_sb.sb_rextsize;
 
 	sbp = &mp->m_sb;
 
@@ -821,34 +855,39 @@ xfs_growfs_rt(
 	/* Needs to have been mounted with an rt device. */
 	if (!XFS_IS_REALTIME_MOUNT(mp))
 		return -EINVAL;
+
+	if (!mutex_trylock(&mp->m_growlock))
+		return -EWOULDBLOCK;
 	/*
 	 * Mount should fail if the rt bitmap/summary files don't load, but
 	 * we'll check anyway.
 	 */
+	error = -EINVAL;
 	if (!mp->m_rbmip || !mp->m_rsumip)
-		return -EINVAL;
+		goto out_unlock;
 
 	/* Shrink not supported. */
 	if (in->newblocks <= sbp->sb_rblocks)
-		return -EINVAL;
+		goto out_unlock;
 
 	/* Can only change rt extent size when adding rt volume. */
 	if (sbp->sb_rblocks > 0 && in->extsize != sbp->sb_rextsize)
-		return -EINVAL;
+		goto out_unlock;
 
 	/* Range check the extent size. */
 	if (XFS_FSB_TO_B(mp, in->extsize) > XFS_MAX_RTEXTSIZE ||
 	    XFS_FSB_TO_B(mp, in->extsize) < XFS_MIN_RTEXTSIZE)
-		return -EINVAL;
+		goto out_unlock;
 
 	/* Unsupported realtime features. */
+	error = -EOPNOTSUPP;
 	if (xfs_has_rmapbt(mp) || xfs_has_reflink(mp) || xfs_has_quota(mp))
-		return -EOPNOTSUPP;
+		goto out_unlock;
 
 	nrblocks = in->newblocks;
 	error = xfs_sb_validate_fsb_count(sbp, nrblocks);
 	if (error)
-		return error;
+		goto out_unlock;
 	/*
 	 * Read in the last block of the device, make sure it exists.
 	 */
@@ -856,7 +895,7 @@ xfs_growfs_rt(
 				XFS_FSB_TO_BB(mp, nrblocks - 1),
 				XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
 	if (error)
-		return error;
+		goto out_unlock;
 	xfs_buf_relse(bp);
 
 	/*
@@ -864,8 +903,10 @@ xfs_growfs_rt(
 	 */
 	nrextents = nrblocks;
 	do_div(nrextents, in->extsize);
-	if (!xfs_validate_rtextents(nrextents))
-		return -EINVAL;
+	if (!xfs_validate_rtextents(nrextents)) {
+		error = -EINVAL;
+		goto out_unlock;
+	}
 	nrbmblocks = xfs_rtbitmap_blockcount(mp, nrextents);
 	nrextslog = xfs_compute_rextslog(nrextents);
 	nrsumlevels = nrextslog + 1;
@@ -876,8 +917,11 @@ xfs_growfs_rt(
 	 * the log.  This prevents us from getting a log overflow,
 	 * since we'll log basically the whole summary file at once.
 	 */
-	if (nrsumblocks > (mp->m_sb.sb_logblocks >> 1))
-		return -EINVAL;
+	if (nrsumblocks > (mp->m_sb.sb_logblocks >> 1)) {
+		error = -EINVAL;
+		goto out_unlock;
+	}
+
 	/*
 	 * Get the old block counts for bitmap and summary inodes.
 	 * These can't change since other growfs callers are locked out.
@@ -889,10 +933,10 @@ xfs_growfs_rt(
 	 */
 	error = xfs_growfs_rt_alloc(mp, rbmblocks, nrbmblocks, mp->m_rbmip);
 	if (error)
-		return error;
+		goto out_unlock;
 	error = xfs_growfs_rt_alloc(mp, rsumblocks, nrsumblocks, mp->m_rsumip);
 	if (error)
-		return error;
+		goto out_unlock;
 
 	rsum_cache = mp->m_rsum_cache;
 	if (nrbmblocks != sbp->sb_rbmblocks)
@@ -1036,6 +1080,12 @@ error_cancel:
 	if (error)
 		goto out_free;
 
+	if (old_rextsize != in->extsize) {
+		error = xfs_growfs_rt_fixup_extsize(mp);
+		if (error)
+			goto out_free;
+	}
+
 	/* Update secondary superblocks now the physical grow has completed */
 	error = xfs_update_secondary_sbs(mp);
 
@@ -1059,6 +1109,8 @@ out_free:
 		}
 	}
 
+out_unlock:
+	mutex_unlock(&mp->m_growlock);
 	return error;
 }
 
diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c
index a191f6560f98..c84df23b494d 100644
--- a/fs/xfs/xfs_sysctl.c
+++ b/fs/xfs/xfs_sysctl.c
@@ -11,7 +11,7 @@ static struct ctl_table_header *xfs_table_header;
 #ifdef CONFIG_PROC_FS
 STATIC int
 xfs_stats_clear_proc_handler(
-	struct ctl_table	*ctl,
+	const struct ctl_table	*ctl,
 	int			write,
 	void			*buffer,
 	size_t			*lenp,
@@ -31,7 +31,7 @@ xfs_stats_clear_proc_handler(
 
 STATIC int
 xfs_panic_mask_proc_handler(
-	struct ctl_table	*ctl,
+	const struct ctl_table	*ctl,
 	int			write,
 	void			*buffer,
 	size_t			*lenp,
@@ -52,7 +52,7 @@ xfs_panic_mask_proc_handler(
 
 STATIC int
 xfs_deprecated_dointvec_minmax(
-	struct ctl_table	*ctl,
+	const struct ctl_table	*ctl,
 	int			write,
 	void			*buffer,
 	size_t			*lenp,
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 5646d300b286..180ce697305a 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -4715,20 +4715,18 @@ TRACE_EVENT(xmbuf_create,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(unsigned long, ino)
-		__array(char, pathname, 256)
+		__array(char, pathname, MAXNAMELEN)
 	),
 	TP_fast_assign(
-		char		pathname[257];
 		char		*path;
 		struct file	*file = btp->bt_file;
 
 		__entry->dev = btp->bt_mount->m_super->s_dev;
 		__entry->ino = file_inode(file)->i_ino;
-		memset(pathname, 0, sizeof(pathname));
-		path = file_path(file, pathname, sizeof(pathname) - 1);
+		path = file_path(file, __entry->pathname, MAXNAMELEN);
 		if (IS_ERR(path))
-			path = "(unknown)";
-		strncpy(__entry->pathname, path, sizeof(__entry->pathname));
+			strncpy(__entry->pathname, "(unknown)",
+					sizeof(__entry->pathname));
 	),
 	TP_printk("dev %d:%d xmino 0x%lx path '%s'",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 0fafcc9f3dbe..8ede9d099d1f 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -644,7 +644,12 @@ xfsaild(
 	set_freezable();
 
 	while (1) {
-		if (tout)
+		/*
+		 * Long waits of 50ms or more occur when we've run out of items
+		 * to push, so we only want uninterruptible state if we're
+		 * actually blocked on something.
+		 */
+		if (tout && tout <= 20)
 			set_current_state(TASK_KILLABLE|TASK_FREEZABLE);
 		else
 			set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index ab3d22f662f2..eaf849260bd6 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -110,7 +110,24 @@ xfs_attr_change(
 	args->whichfork = XFS_ATTR_FORK;
 	xfs_attr_sethash(args);
 
-	return xfs_attr_set(args, op, args->attr_filter & XFS_ATTR_ROOT);
+	/*
+	 * Some xattrs must be resistant to allocation failure at ENOSPC, e.g.
+	 * creating an inode with ACLs or security attributes requires the
+	 * allocation of the xattr holding that information to succeed. Hence
+	 * we allow xattrs in the VFS TRUSTED, SYSTEM, POSIX_ACL and SECURITY
+	 * (LSM xattr) namespaces to dip into the reserve block pool to allow
+	 * manipulation of these xattrs when at ENOSPC. These VFS xattr
+	 * namespaces translate to the XFS_ATTR_ROOT and XFS_ATTR_SECURE on-disk
+	 * namespaces.
+	 *
+	 * For most of these cases, these special xattrs will fit in the inode
+	 * itself and so consume no extra space or only require temporary extra
+	 * space while an overwrite is being made. Hence the use of the reserved
+	 * pool is largely to avoid the worst case reservation from preventing
+	 * the xattr from being created at ENOSPC.
+	 */
+	return xfs_attr_set(args, op,
+			args->attr_filter & (XFS_ATTR_ROOT | XFS_ATTR_SECURE));
 }