libceph: call r_unsafe_callback when unsafe reply is received

commit 61c5d6bf7074ee32d014dcdf7698dc8c59eb712d upstream.

We can't use !req->r_sent to check if OSD request is sent for the
first time, this is because __cancel_request() zeros req->r_sent
when OSD map changes. Rather than adding a new variable to struct
ceph_osd_request to indicate if it's sent for the first time, We
can call the unsafe callback only when unsafe OSD reply is received.
If OSD's first reply is safe, just skip calling the unsafe callback.

The purpose of unsafe callback is adding unsafe request to a list,
so that fsync(2) can wait for the safe reply. fsync(2) doesn't need
to wait for a write(2) that hasn't returned yet. So it's OK to add
request to the unsafe list when the first OSD reply is received.
(ceph_sync_write() returns after receiving the first OSD reply)

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 7 insertions, 7 deletions

diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 3e46e538cbf..b0e9ed6aeb8 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1337,10 +1337,6 @@ static void __send_request(struct ceph_osd_client *osdc,
 
 	ceph_msg_get(req->r_request); /* send consumes a ref */
 
-	/* Mark the request unsafe if this is the first timet's being sent. */
-
-	if (!req->r_sent && req->r_unsafe_callback)
-		req->r_unsafe_callback(req, true);
 	req->r_sent = req->r_osd->o_incarnation;
 
 	ceph_con_send(&req->r_osd->o_con, req->r_request);
@@ -1431,8 +1427,6 @@ static void handle_osds_timeout(struct work_struct *work)
 
 static void complete_request(struct ceph_osd_request *req)
 {
-	if (req->r_unsafe_callback)
-		req->r_unsafe_callback(req, false);
 	complete_all(&req->r_safe_completion);  /* fsync waiter */
 }
 
@@ -1559,14 +1553,20 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg,
 	mutex_unlock(&osdc->request_mutex);
 
 	if (!already_completed) {
+		if (req->r_unsafe_callback &&
+		    result >= 0 && !(flags & CEPH_OSD_FLAG_ONDISK))
+			req->r_unsafe_callback(req, true);
 		if (req->r_callback)
 			req->r_callback(req, msg);
 		else
 			complete_all(&req->r_completion);
 	}
 
-	if (flags & CEPH_OSD_FLAG_ONDISK)
+	if (flags & CEPH_OSD_FLAG_ONDISK) {
+		if (req->r_unsafe_callback && already_completed)
+			req->r_unsafe_callback(req, false);
 		complete_request(req);
+	}
 
 done:
 	dout("req=%p req->r_linger=%d\n", req, req->r_linger);