rxrpc: Fix resend event time calculation

Commit a158bdd3 ("rxrpc: Fix call timeouts") reworked the time calculation
for the next resend event.  For this calculation, "oldest" will be before
"now", so ktime_sub(oldest, now) will yield a negative value.  When passed
to nsecs_to_jiffies which expects an unsigned value, the end result will be
a very large value, and a resend event scheduled far into the future.  This
could cause calls to stall if some packets were lost.

Fix by ordering the arguments to ktime_sub correctly.

Fixes: a158bdd3247b ("rxrpc: Fix call timeouts")
Signed-off-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>

diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 3dee89c7a06e2e9bf5d810c99c40aa0048fd772a..6e0d788b4dc43e0674ccaeb7b1282382cae01d0a 100644 (file)
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -226,7 +226,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
                                       ktime_to_ns(ktime_sub(skb->tstamp, max_age)));
        }
 
-       resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(oldest, now)));
+       resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest)));
        resend_at += jiffies + rxrpc_resend_timeout;
        WRITE_ONCE(call->resend_at, resend_at);