xfs: implement FALLOC_FL_ZEROINIT_RANGE

Implement this new fallocate mode so that persistent memory users can,
upon receipt of a pmem poison notification, cause the pmem to be
reinitialized to a known value (zero) and clear any hardware poison
state that might be lurking.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>

4 files changed, 48 insertions, 2 deletions

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 73a36b7be3bd..e2e7e6a488a1 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -957,6 +957,28 @@ xfs_flush_unmap_range(
 }
 
 int
+xfs_file_zeroinit_space(
+	struct xfs_inode	*ip,
+	xfs_off_t		offset,
+	xfs_off_t		len)
+{
+	struct inode		*inode = VFS_I(ip);
+	int			error;
+
+	trace_xfs_zeroinit_file_space(ip, offset, len);
+
+	if (IS_DAX(inode))
+		error = dax_zeroinit_range(inode, offset, len,
+				&xfs_read_iomap_ops);
+	else
+		error = iomap_zeroout_range(inode, offset, len,
+				&xfs_buffered_write_iomap_ops);
+	if (error == -ECANCELED)
+		return -EOPNOTSUPP;
+	return error;
+}
+
+int
 xfs_free_file_space(
 	struct xfs_inode	*ip,
 	xfs_off_t		offset,
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 9f993168b55b..7bb425d0876c 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -61,6 +61,8 @@ int	xfs_collapse_file_space(struct xfs_inode *, xfs_off_t offset,
 				xfs_off_t len);
 int	xfs_insert_file_space(struct xfs_inode *, xfs_off_t offset,
 				xfs_off_t len);
+int	xfs_file_zeroinit_space(struct xfs_inode *ip, xfs_off_t offset,
+				xfs_off_t length);
 
 /* EOF block manipulation functions */
 bool	xfs_can_free_eofblocks(struct xfs_inode *ip, bool force);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 7aa943edfc02..c6ba37703f0b 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -899,7 +899,8 @@ xfs_break_layouts(
 #define	XFS_FALLOC_FL_SUPPORTED						\
 		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
 		 FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |	\
-		 FALLOC_FL_INSERT_RANGE | FALLOC_FL_UNSHARE_RANGE)
+		 FALLOC_FL_INSERT_RANGE | FALLOC_FL_UNSHARE_RANGE |	\
+		 FALLOC_FL_ZEROINIT_DATA)
 
 STATIC long
 xfs_file_fallocate(
@@ -1005,6 +1006,8 @@ xfs_file_fallocate(
 		}
 		do_file_insert = true;
 	} else {
+		unsigned int	bmapi_flags = XFS_BMAPI_PREALLOC;
+
 		flags |= XFS_PREALLOC_SET;
 
 		if (!(mode & FALLOC_FL_KEEP_SIZE) &&
@@ -1015,6 +1018,24 @@ xfs_file_fallocate(
 				goto out_unlock;
 		}
 
+		if (mode & FALLOC_FL_ZEROINIT_DATA) {
+			if (xfs_is_always_cow_inode(ip)) {
+				error = -EOPNOTSUPP;
+				goto out_unlock;
+			}
+
+			bmapi_flags = XFS_BMAPI_ZERO;
+
+			if (mode & FALLOC_FL_ZERO_RANGE) {
+				error = xfs_file_zeroinit_space(ip, offset,
+						len);
+				if (error)
+					goto out_unlock;
+
+				mode &= ~FALLOC_FL_ZERO_RANGE;
+			}
+		}
+
 		if (mode & FALLOC_FL_ZERO_RANGE) {
 			/*
 			 * Punch a hole and prealloc the range.  We use a hole
@@ -1053,7 +1074,7 @@ xfs_file_fallocate(
 
 		if (!xfs_is_always_cow_inode(ip)) {
 			error = xfs_alloc_file_space(ip, offset, len,
-						     XFS_BMAPI_PREALLOC);
+					bmapi_flags);
 			if (error)
 				goto out_unlock;
 		}
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 4a8076ef8cb4..eccad0a5c40f 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1534,6 +1534,7 @@ DEFINE_SIMPLE_IO_EVENT(xfs_zero_eof);
 DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write);
 DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_unwritten);
 DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_append);
+DEFINE_SIMPLE_IO_EVENT(xfs_zeroinit_file_space);
 
 DECLARE_EVENT_CLASS(xfs_itrunc_class,
 	TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size),