ceph: no need to wait for transition RDCACHE|RD -> RD

For write when trying to get the Fwb caps we need to keep waiting
on transition from WRBUFFER|WR -> WR to avoid a new WR sync write
from going before a prior buffered writeback happens.

While for read there is no need to wait on transition from
RDCACHE|RD -> RD, and we can just exclude the revoking caps and
force to sync read.

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 0ddd91e..0dc1251 100644 (file)
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2760,13 +2760,17 @@ again:
                 * on transition from wanted -> needed caps.  This is needed
                 * for WRBUFFER|WR -> WR to avoid a new WR sync write from
                 * going before a prior buffered writeback happens.
+                *
+                * For RDCACHE|RD -> RD, there is not need to wait and we can
+                * just exclude the revoking caps and force to sync read.
                 */
                int not = want & ~(have & need);
                int revoking = implemented & ~have;
+               int exclude = revoking & not;
                dout("get_cap_refs %p have %s but not %s (revoking %s)\n",
                     inode, ceph_cap_string(have), ceph_cap_string(not),
                     ceph_cap_string(revoking));
-               if ((revoking & not) == 0) {
+               if (!exclude || !(exclude & CEPH_CAP_FILE_BUFFER)) {
                        if (!snap_rwsem_locked &&
                            !ci->i_head_snapc &&
                            (need & CEPH_CAP_FILE_WR)) {
@@ -2788,7 +2792,7 @@ again:
                                snap_rwsem_locked = true;
                        }
                        if ((have & want) == want)
-                               *got = need | want;
+                               *got = need | (want & ~exclude);
                        else
                                *got = need;
                        ceph_take_cap_refs(ci, *got, true);