@@ -1557,7 +1557,7 @@ xfs_file_open(
if (xfs_is_shutdown(XFS_M(inode->i_sb)))
return -EIO;
file->f_mode |= FMODE_NOWAIT | FMODE_CAN_ODIRECT;
- if (xfs_inode_can_hw_atomicwrite(XFS_I(inode)))
+ if (xfs_get_atomic_write_min(XFS_I(inode)))
file->f_mode |= FMODE_CAN_ATOMIC_WRITE;
return generic_file_open(inode, file);
}
@@ -605,27 +605,52 @@ unsigned int
xfs_get_atomic_write_min(
struct xfs_inode *ip)
{
- if (!xfs_inode_can_hw_atomicwrite(ip))
- return 0;
+ if (xfs_inode_can_hw_atomicwrite(ip) || xfs_has_reflink(ip->i_mount))
+ return ip->i_mount->m_sb.sb_blocksize;
- return ip->i_mount->m_sb.sb_blocksize;
+ return 0;
}
unsigned int
xfs_get_atomic_write_max(
struct xfs_inode *ip)
{
- if (!xfs_inode_can_hw_atomicwrite(ip))
+ struct xfs_mount *mp = ip->i_mount;
+
+ /*
+ * If no reflink, then best we can do is 1x block as no CoW fallback
+ * for when HW offload not possible.
+ *
+ * rtvol is not commonly used and supporting large atomic writes
+ * would also be complicated to support there, so limit to a single
+ * block for now.
+ */
+ if (!xfs_has_reflink(mp) || XFS_IS_REALTIME_INODE(ip)) {
+ if (xfs_inode_can_hw_atomicwrite(ip))
+ return ip->i_mount->m_sb.sb_blocksize;
return 0;
+ }
- return ip->i_mount->m_sb.sb_blocksize;
+ /*
+ * Even though HW support could be larger (than CoW), we rely on
+ * CoW-based method as a fallback for when HW-based is not possible,
+ * so always limit at m_atomic_write_unit_max (which is evaluated
+ * according to CoW-based limit.
+ */
+ return XFS_FSB_TO_B(mp, mp->m_atomic_write_unit_max);
}
unsigned int
xfs_get_atomic_write_max_opt(
struct xfs_inode *ip)
{
- return 0;
+ struct xfs_buftarg *target = xfs_inode_buftarg(ip);
+
+ /* if the max is 1x block, then just keep behaviour that opt is 0 */
+ if (xfs_get_atomic_write_max(ip) <= ip->i_mount->m_sb.sb_blocksize)
+ return 0;
+
+ return min(xfs_get_atomic_write_max(ip), target->bt_bdev_awu_max);
}
static void
Update the limits returned from xfs_get_atomic_write_{min, max, max_opt)(). No reflink support always means no CoW-based atomic writes. For updating xfs_get_atomic_write_min(), we support blocksize only and that depends on HW or reflink support. For updating xfs_get_atomic_write_max(), for rtvol or no reflink, we are limited to blocksize but only if HW support. Otherwise we are limited to combined limit in mp->m_atomic_write_unit_max. For updating xfs_get_atomic_write_max_opt(), ultimately we are limited by the bdev atomic write limit. If xfs_get_atomic_write_max() does not report > 1x blocksize, then just continue to report 0 as before. Signed-off-by: John Garry <john.g.garry@oracle.com> --- fs/xfs/xfs_file.c | 2 +- fs/xfs/xfs_iops.c | 37 +++++++++++++++++++++++++++++++------ 2 files changed, 32 insertions(+), 7 deletions(-)