1 files changed, 296 insertions, 19 deletions

diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index cb23c8871f81..04f39ea15898 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -79,6 +79,9 @@ xfs_iomap_valid(
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 
+	if (iomap->type == IOMAP_HOLE)
+		return true;
+
 	if (iomap->validity_cookie !=
 			xfs_iomap_inode_sequence(ip, iomap->flags)) {
 		trace_xfs_iomap_invalid(ip, iomap);
@@ -89,7 +92,7 @@ xfs_iomap_valid(
 	return true;
 }
 
-static const struct iomap_folio_ops xfs_iomap_folio_ops = {
+const struct iomap_write_ops xfs_iomap_write_ops = {
 	.iomap_valid		= xfs_iomap_valid,
 };
 
@@ -146,12 +149,20 @@ xfs_bmbt_to_iomap(
 		iomap->bdev = target->bt_bdev;
 	iomap->flags = iomap_flags;
 
-	if (xfs_ipincount(ip) &&
-	    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
-		iomap->flags |= IOMAP_F_DIRTY;
+	/*
+	 * If the inode is dirty for datasync purposes, let iomap know so it
+	 * doesn't elide the IO completion journal flushes on O_DSYNC IO.
+	 */
+	if (ip->i_itemp) {
+		struct xfs_inode_log_item *iip = ip->i_itemp;
+
+		spin_lock(&iip->ili_lock);
+		if (iip->ili_datasync_seq)
+			iomap->flags |= IOMAP_F_DIRTY;
+		spin_unlock(&iip->ili_lock);
+	}
 
 	iomap->validity_cookie = sequence_cookie;
-	iomap->folio_ops = &xfs_iomap_folio_ops;
 	return 0;
 }
 
@@ -798,6 +809,38 @@ imap_spans_range(
 	return true;
 }
 
+static bool
+xfs_bmap_hw_atomic_write_possible(
+	struct xfs_inode	*ip,
+	struct xfs_bmbt_irec	*imap,
+	xfs_fileoff_t		offset_fsb,
+	xfs_fileoff_t		end_fsb)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	xfs_fsize_t		len = XFS_FSB_TO_B(mp, end_fsb - offset_fsb);
+
+	/*
+	 * atomic writes are required to be naturally aligned for disk blocks,
+	 * which ensures that we adhere to block layer rules that we won't
+	 * straddle any boundary or violate write alignment requirement.
+	 */
+	if (!IS_ALIGNED(imap->br_startblock, imap->br_blockcount))
+		return false;
+
+	/*
+	 * Spanning multiple extents would mean that multiple BIOs would be
+	 * issued, and so would lose atomicity required for REQ_ATOMIC-based
+	 * atomics.
+	 */
+	if (!imap_spans_range(imap, offset_fsb, end_fsb))
+		return false;
+
+	/*
+	 * The ->iomap_begin caller should ensure this, but check anyway.
+	 */
+	return len <= xfs_inode_buftarg(ip)->bt_awu_max;
+}
+
 static int
 xfs_direct_write_iomap_begin(
 	struct inode		*inode,
@@ -812,9 +855,11 @@ xfs_direct_write_iomap_begin(
 	struct xfs_bmbt_irec	imap, cmap;
 	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	xfs_fileoff_t		end_fsb = xfs_iomap_end_fsb(mp, offset, length);
+	xfs_fileoff_t		orig_end_fsb = end_fsb;
 	int			nimaps = 1, error = 0;
 	bool			shared = false;
 	u16			iomap_flags = 0;
+	bool			needs_alloc;
 	unsigned int		lockmode;
 	u64			seq;
 
@@ -875,13 +920,37 @@ relock:
 				(flags & IOMAP_DIRECT) || IS_DAX(inode));
 		if (error)
 			goto out_unlock;
-		if (shared)
+		if (shared) {
+			if ((flags & IOMAP_ATOMIC) &&
+			    !xfs_bmap_hw_atomic_write_possible(ip, &cmap,
+					offset_fsb, end_fsb)) {
+				error = -ENOPROTOOPT;
+				goto out_unlock;
+			}
 			goto out_found_cow;
+		}
 		end_fsb = imap.br_startoff + imap.br_blockcount;
 		length = XFS_FSB_TO_B(mp, end_fsb) - offset;
 	}
 
-	if (imap_needs_alloc(inode, flags, &imap, nimaps))
+	needs_alloc = imap_needs_alloc(inode, flags, &imap, nimaps);
+
+	if (flags & IOMAP_ATOMIC) {
+		error = -ENOPROTOOPT;
+		/*
+		 * If we allocate less than what is required for the write
+		 * then we may end up with multiple extents, which means that
+		 * REQ_ATOMIC-based cannot be used, so avoid this possibility.
+		 */
+		if (needs_alloc && orig_end_fsb - offset_fsb > 1)
+			goto out_unlock;
+
+		if (!xfs_bmap_hw_atomic_write_possible(ip, &imap, offset_fsb,
+				orig_end_fsb))
+			goto out_unlock;
+	}
+
+	if (needs_alloc)
 		goto allocate_blocks;
 
 	/*
@@ -1022,6 +1091,190 @@ const struct iomap_ops xfs_zoned_direct_write_iomap_ops = {
 };
 #endif /* CONFIG_XFS_RT */
 
+#ifdef DEBUG
+static void
+xfs_check_atomic_cow_conversion(
+	struct xfs_inode		*ip,
+	xfs_fileoff_t			offset_fsb,
+	xfs_filblks_t			count_fsb,
+	const struct xfs_bmbt_irec	*cmap)
+{
+	struct xfs_iext_cursor		icur;
+	struct xfs_bmbt_irec		cmap2 = { };
+
+	if (xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap2))
+		xfs_trim_extent(&cmap2, offset_fsb, count_fsb);
+
+	ASSERT(cmap2.br_startoff == cmap->br_startoff);
+	ASSERT(cmap2.br_blockcount == cmap->br_blockcount);
+	ASSERT(cmap2.br_startblock == cmap->br_startblock);
+	ASSERT(cmap2.br_state == cmap->br_state);
+}
+#else
+# define xfs_check_atomic_cow_conversion(...)	((void)0)
+#endif
+
+static int
+xfs_atomic_write_cow_iomap_begin(
+	struct inode		*inode,
+	loff_t			offset,
+	loff_t			length,
+	unsigned		flags,
+	struct iomap		*iomap,
+	struct iomap		*srcmap)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	const xfs_fileoff_t	offset_fsb = XFS_B_TO_FSBT(mp, offset);
+	const xfs_fileoff_t	end_fsb = XFS_B_TO_FSB(mp, offset + length);
+	const xfs_filblks_t	count_fsb = end_fsb - offset_fsb;
+	xfs_filblks_t		hole_count_fsb;
+	int			nmaps = 1;
+	xfs_filblks_t		resaligned;
+	struct xfs_bmbt_irec	cmap;
+	struct xfs_iext_cursor	icur;
+	struct xfs_trans	*tp;
+	unsigned int		dblocks = 0, rblocks = 0;
+	int			error;
+	u64			seq;
+
+	ASSERT(flags & IOMAP_WRITE);
+	ASSERT(flags & IOMAP_DIRECT);
+
+	if (xfs_is_shutdown(mp))
+		return -EIO;
+
+	if (!xfs_can_sw_atomic_write(mp)) {
+		ASSERT(xfs_can_sw_atomic_write(mp));
+		return -EINVAL;
+	}
+
+	/* blocks are always allocated in this path */
+	if (flags & IOMAP_NOWAIT)
+		return -EAGAIN;
+
+	trace_xfs_iomap_atomic_write_cow(ip, offset, length);
+retry:
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+
+	if (!ip->i_cowfp) {
+		ASSERT(!xfs_is_reflink_inode(ip));
+		xfs_ifork_init_cow(ip);
+	}
+
+	if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap))
+		cmap.br_startoff = end_fsb;
+	if (cmap.br_startoff <= offset_fsb) {
+		if (isnullstartblock(cmap.br_startblock))
+			goto convert_delay;
+
+		/*
+		 * cmap could extend outside the write range due to previous
+		 * speculative preallocations.  We must trim cmap to the write
+		 * range because the cow fork treats written mappings to mean
+		 * "write in progress".
+		 */
+		xfs_trim_extent(&cmap, offset_fsb, count_fsb);
+		goto found;
+	}
+
+	hole_count_fsb = cmap.br_startoff - offset_fsb;
+
+	resaligned = xfs_aligned_fsb_count(offset_fsb, hole_count_fsb,
+			xfs_get_cowextsz_hint(ip));
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+	if (XFS_IS_REALTIME_INODE(ip)) {
+		dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
+		rblocks = resaligned;
+	} else {
+		dblocks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned);
+		rblocks = 0;
+	}
+
+	error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, dblocks,
+			rblocks, false, &tp);
+	if (error)
+		return error;
+
+	/* extent layout could have changed since the unlock, so check again */
+	if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap))
+		cmap.br_startoff = end_fsb;
+	if (cmap.br_startoff <= offset_fsb) {
+		xfs_trans_cancel(tp);
+		if (isnullstartblock(cmap.br_startblock))
+			goto convert_delay;
+		xfs_trim_extent(&cmap, offset_fsb, count_fsb);
+		goto found;
+	}
+
+	/*
+	 * Allocate the entire reservation as unwritten blocks.
+	 *
+	 * Use XFS_BMAPI_EXTSZALIGN to hint at aligning new extents according to
+	 * extszhint, such that there will be a greater chance that future
+	 * atomic writes to that same range will be aligned (and don't require
+	 * this COW-based method).
+	 */
+	error = xfs_bmapi_write(tp, ip, offset_fsb, hole_count_fsb,
+			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC |
+			XFS_BMAPI_EXTSZALIGN, 0, &cmap, &nmaps);
+	if (error) {
+		xfs_trans_cancel(tp);
+		goto out_unlock;
+	}
+
+	xfs_inode_set_cowblocks_tag(ip);
+	error = xfs_trans_commit(tp);
+	if (error)
+		goto out_unlock;
+
+	/*
+	 * cmap could map more blocks than the range we passed into bmapi_write
+	 * because of EXTSZALIGN or adjacent pre-existing unwritten mappings
+	 * that were merged.  Trim cmap to the original write range so that we
+	 * don't convert more than we were asked to do for this write.
+	 */
+	xfs_trim_extent(&cmap, offset_fsb, count_fsb);
+
+found:
+	if (cmap.br_state != XFS_EXT_NORM) {
+		error = xfs_reflink_convert_cow_locked(ip, cmap.br_startoff,
+				cmap.br_blockcount);
+		if (error)
+			goto out_unlock;
+		cmap.br_state = XFS_EXT_NORM;
+		xfs_check_atomic_cow_conversion(ip, offset_fsb, count_fsb,
+				&cmap);
+	}
+
+	trace_xfs_iomap_found(ip, offset, length, XFS_COW_FORK, &cmap);
+	seq = xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, IOMAP_F_SHARED, seq);
+
+convert_delay:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	error = xfs_bmapi_convert_delalloc(ip, XFS_COW_FORK, offset, iomap,
+			NULL);
+	if (error)
+		return error;
+
+	/*
+	 * Try the lookup again, because the delalloc conversion might have
+	 * turned the COW mapping into unwritten, but we need it to be in
+	 * written state.
+	 */
+	goto retry;
+out_unlock:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return error;
+}
+
+const struct iomap_ops xfs_atomic_write_cow_iomap_ops = {
+	.iomap_begin		= xfs_atomic_write_cow_iomap_begin,
+};
+
 static int
 xfs_dax_write_iomap_end(
 	struct inode		*inode,
@@ -1366,7 +1619,7 @@ xfs_zoned_buffered_write_iomap_begin(
 		return error;
 
 	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(&ip->i_df)) ||
-	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+	    XFS_TEST_ERROR(mp, XFS_ERRTAG_BMAPIFORMAT)) {
 		xfs_bmap_mark_sick(ip, XFS_DATA_FORK);
 		error = -EFSCORRUPTED;
 		goto out_unlock;
@@ -1505,6 +1758,8 @@ xfs_buffered_write_iomap_begin(
 	struct iomap		*iomap,
 	struct iomap		*srcmap)
 {
+	struct iomap_iter	*iter = container_of(iomap, struct iomap_iter,
+						     iomap);
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
@@ -1540,7 +1795,7 @@ xfs_buffered_write_iomap_begin(
 		return error;
 
 	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(&ip->i_df)) ||
-	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+	    XFS_TEST_ERROR(mp, XFS_ERRTAG_BMAPIFORMAT)) {
 		xfs_bmap_mark_sick(ip, XFS_DATA_FORK);
 		error = -EFSCORRUPTED;
 		goto out_unlock;
@@ -1570,21 +1825,41 @@ xfs_buffered_write_iomap_begin(
 	}
 
 	/*
-	 * For zeroing, trim a delalloc extent that extends beyond the EOF
-	 * block.  If it starts beyond the EOF block, convert it to an
+	 * For zeroing, trim extents that extend beyond the EOF block. If a
+	 * delalloc extent starts beyond the EOF block, convert it to an
 	 * unwritten extent.
 	 */
-	if ((flags & IOMAP_ZERO) && imap.br_startoff <= offset_fsb &&
-	    isnullstartblock(imap.br_startblock)) {
+	if (flags & IOMAP_ZERO) {
 		xfs_fileoff_t eof_fsb = XFS_B_TO_FSB(mp, XFS_ISIZE(ip));
+		u64 end;
 
-		if (offset_fsb >= eof_fsb)
+		if (isnullstartblock(imap.br_startblock) &&
+		    offset_fsb >= eof_fsb)
 			goto convert_delay;
-		if (end_fsb > eof_fsb) {
+		if (offset_fsb < eof_fsb && end_fsb > eof_fsb)
 			end_fsb = eof_fsb;
-			xfs_trim_extent(&imap, offset_fsb,
-					end_fsb - offset_fsb);
+
+		/*
+		 * Look up dirty folios for unwritten mappings within EOF.
+		 * Providing this bypasses the flush iomap uses to trigger
+		 * extent conversion when unwritten mappings have dirty
+		 * pagecache in need of zeroing.
+		 *
+		 * Trim the mapping to the end pos of the lookup, which in turn
+		 * was trimmed to the end of the batch if it became full before
+		 * the end of the mapping.
+		 */
+		if (imap.br_state == XFS_EXT_UNWRITTEN &&
+		    offset_fsb < eof_fsb) {
+			loff_t len = min(count,
+					 XFS_FSB_TO_B(mp, imap.br_blockcount));
+
+			end = iomap_fill_dirty_folios(iter, offset, len);
+			end_fsb = min_t(xfs_fileoff_t, end_fsb,
+					XFS_B_TO_FSB(mp, end));
 		}
+
+		xfs_trim_extent(&imap, offset_fsb, end_fsb - offset_fsb);
 	}
 
 	/*
@@ -2012,7 +2287,8 @@ xfs_zero_range(
 		return dax_zero_range(inode, pos, len, did_zero,
 				      &xfs_dax_write_iomap_ops);
 	return iomap_zero_range(inode, pos, len, did_zero,
-				&xfs_buffered_write_iomap_ops, ac);
+			&xfs_buffered_write_iomap_ops, &xfs_iomap_write_ops,
+			ac);
 }
 
 int
@@ -2028,5 +2304,6 @@ xfs_truncate_page(
 		return dax_truncate_page(inode, pos, did_zero,
 					&xfs_dax_write_iomap_ops);
 	return iomap_truncate_page(inode, pos, did_zero,
-				   &xfs_buffered_write_iomap_ops, ac);
+			&xfs_buffered_write_iomap_ops, &xfs_iomap_write_ops,
+			ac);
 }