[Devel] [PATCH VZ10] fs/fuse kio: track pending kRPC connect via state machine only

[Liu Kui]

Rework the previous fix ("fs/fuse kio: fix kRPC connect issues") to not
require the new struct pcs_krpc member "connect_req", so the fix can be
shipped as a livepatch.

Both things connect_req was tracking are already derivable from the
existing state machine once PCS_KRPC_STATE_CONNECT is made to mean
exactly "a connect req is in flight":

 - krpc_connect_done() settles a failed connect back to UNCONN instead
   of leaving the state in CONNECT forever;

 - pcs_krpc_abort() no longer resets CONNECT to UNCONN: the req is
   still in flight, and only its completion settles the state;

 - pcs_krpc_connect() proceeds only from UNCONN or ABORTED, refusing
   new connects (-EPERM) while a req is in flight - at most one connect
   req exists at a time, same as with the connect_req check;

 - pcs_krpc_poll() reports EPOLLERR on UNCONN: poll bails out earlier
   unless ctx->gen == krpc->gen, and the current session can only be in
   UNCONN if its connect failed or was aborted, which is what the
   (CONNECT && !connect_req) test used to detect.

gen only advances in pcs_krpc_connect(), which is blocked during
CONNECT, so within that state the in-flight req always carries the
current gen and krpc_connect_done()'s existing staleness check is
sufficient.

Related to:
https://virtuozzo.atlassian.net/browse/VSTOR-135626

Signed-off-by: Liu Kui <kui.liu at virtuozzo.com>
---
 fs/fuse/kio/pcs/pcs_krpc.c | 39 ++++++++++++++++++++++++++++----------
 fs/fuse/kio/pcs/pcs_krpc.h |  2 --
 2 files changed, 29 insertions(+), 12 deletions(-)

diff --git a/fs/fuse/kio/pcs/pcs_krpc.c b/fs/fuse/kio/pcs/pcs_krpc.c
index b55c093c13d0..bcfbfc6d9304 100644
--- a/fs/fuse/kio/pcs/pcs_krpc.c
+++ b/fs/fuse/kio/pcs/pcs_krpc.c
@@ -738,8 +738,12 @@ static int pcs_krpc_abort(struct pcs_krpc *krpc)
 	spin_lock(&krpc->lock);
 
 	if (krpc->state != PCS_KRPC_STATE_CONNECTED) {
-		if (krpc->state == PCS_KRPC_STATE_CONNECT)
-			krpc->state = PCS_KRPC_STATE_UNCONN;
+		/*
+		 * A pending connect stays in CONNECT state: its connect req
+		 * is still in flight and krpc_connect_done() will settle the
+		 * state to UNCONN when it completes.  Until then new connects
+		 * are refused, so at most one connect req exists at a time.
+		 */
 		spin_unlock(&krpc->lock);
 		return 0;
 	}
@@ -907,8 +911,13 @@ static __poll_t pcs_krpc_poll(struct file *file, poll_table *wait)
 
 	spin_lock(&krpc->lock);
 
+	/*
+	 * ctx->gen == krpc->gen (checked above) means this is the current
+	 * session, so UNCONN here can only mean its connect attempt has
+	 * failed (see krpc_connect_done()) or the session was aborted.
+	 */
 	if (krpc->state == PCS_KRPC_STATE_ABORTED ||
-	    (krpc->state == PCS_KRPC_STATE_CONNECT && !krpc->connect_req)) {
+	    krpc->state == PCS_KRPC_STATE_UNCONN) {
 		pollflags |= EPOLLERR;
 	} else if (krpc->state == PCS_KRPC_STATE_CONNECTED) {
 		pollflags |= EPOLLOUT;
@@ -999,7 +1008,6 @@ int pcs_krpc_create(struct pcs_krpc_set *krpcs, PCS_NODE_ID_T *id,
 	krpc->gen = 0;
 	krpc->state = PCS_KRPC_STATE_UNCONN;
 	krpc->cs = NULL;
-	krpc->connect_req = NULL;
 
 	krpc->rpc = pcs_rpc_clnt_create(&cc_from_krpcset(krpcs)->eng, id, addr, cs_flags);
 	if (!krpc->rpc) {
@@ -1051,8 +1059,6 @@ static void krpc_connect_done(struct pcs_msg *msg)
 	}
 
 	spin_lock(&krpc->lock);
-	if (krpc->connect_req == req)
-		krpc->connect_req = NULL;
 	/* from a stale session, do nothing  */
 	if (req->gen != krpc->gen || krpc->state != PCS_KRPC_STATE_CONNECT) {
 		spin_unlock(&krpc->lock);
@@ -1062,6 +1068,14 @@ static void krpc_connect_done(struct pcs_msg *msg)
 	if (!pcs_if_error(&msg->error)) {
 		krpc->state = PCS_KRPC_STATE_CONNECTED;
 		pollflags = EPOLLOUT;
+	} else {
+		/*
+		 * Connect failed: settle back to UNCONN so that a new connect
+		 * is allowed again, and report the failure to poll().  Since
+		 * gen is unchanged, the current session's poll sees UNCONN
+		 * and returns EPOLLERR.
+		 */
+		krpc->state = PCS_KRPC_STATE_UNCONN;
 	}
 	spin_unlock(&krpc->lock);
 
@@ -1119,9 +1133,15 @@ int pcs_krpc_connect(struct pcs_krpc_set *krpcs, PCS_NODE_ID_T *id)
 	}
 
 	spin_lock(&krpc->lock);
-	if (krpc->state == PCS_KRPC_STATE_CONNECTED ||
-	    krpc->state == PCS_KRPC_STATE_DESTROYED ||
-	    krpc->connect_req) {
+	/*
+	 * A connect is allowed only when there is neither an established
+	 * session nor a connect req in flight (CONNECT state, see
+	 * krpc_connect_done()).  This limits connect reqs to one at a time:
+	 * if userspace gave up on a connect and retries, the new connect
+	 * fails immediately until the old req completes.
+	 */
+	if (krpc->state != PCS_KRPC_STATE_UNCONN &&
+	    krpc->state != PCS_KRPC_STATE_ABORTED) {
 		spin_unlock(&krpc->lock);
 		err = -EPERM;
 		/* fput() drops ctx and its krpc reference via pcs_krpc_release() */
@@ -1133,7 +1153,6 @@ int pcs_krpc_connect(struct pcs_krpc_set *krpcs, PCS_NODE_ID_T *id)
 	connect_req->gen = krpc->gen;
 	connect_req->krpc = pcs_krpc_get(krpc);
 	krpc->state = PCS_KRPC_STATE_CONNECT;
-	krpc->connect_req = connect_req;
 	spin_unlock(&krpc->lock);
 
 	/* publish the fd only after the connect is committed */
diff --git a/fs/fuse/kio/pcs/pcs_krpc.h b/fs/fuse/kio/pcs/pcs_krpc.h
index 3db9e9712019..6a090ef66185 100644
--- a/fs/fuse/kio/pcs/pcs_krpc.h
+++ b/fs/fuse/kio/pcs/pcs_krpc.h
@@ -82,8 +82,6 @@ struct pcs_krpc {
 	/** Wait queue head for poll */
 	wait_queue_head_t		poll_wait;
 	struct pcs_cs			*cs;
-
-	struct krpc_connect_req *connect_req;
 };
 
 struct pcs_krpc_context {
-- 
2.50.1 (Apple Git-155)