evtchn: don't reuse ports that are still "busy"

When using the FIFO ABI a guest may close an event channel that is
still LINKED.  If this port is reused, subsequent events may be lost
because they may become pending on the wrong queue.

This could be fixed by requiring guests to only close event channels
that are not linked.  This is difficult since: a) irq cleanup in the
guest may be done in a context that cannot wait for the event to be
unlinked; b) the guest may attempt to rebind a PIRQ whose previous
close is still pending; and c) existing guests already have the
problematic behaviour.

Instead, simply check a port is not "busy" (i.e., it's not linked)
before reusing it.

Guests should still drain any queues for VCPUs that are being
offlined, or the port will become unusable until the VCPU is onlined
and starts processing events again.

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
master commit: 78e24c269b
master date: 2015-12-02 15:21:46 +0100

xen/common/event_channel.c

@@ -171,7 +171,8 @@ static int get_free_port(struct domain *d)
     {
         if ( port > d->max_evtchn_port )
             return -ENOSPC;
-        if ( evtchn_from_port(d, port)->state == ECS_FREE )
+        if ( evtchn_from_port(d, port)->state == ECS_FREE
+             && !evtchn_port_is_busy(d, port) )
             return port;
     }
 

xen/common/event_fifo.c

@@ -313,6 +313,17 @@ static bool_t evtchn_fifo_is_masked(struct domain *d,
     return test_bit(EVTCHN_FIFO_MASKED, word);
 }
 
+static bool_t evtchn_fifo_is_busy(struct domain *d, evtchn_port_t port)
+{
+    event_word_t *word;
+
+    word = evtchn_fifo_word_from_port(d, port);
+    if ( unlikely(!word) )
+        return 0;
+
+    return test_bit(EVTCHN_FIFO_LINKED, word);
+}
+
 static int evtchn_fifo_set_priority(struct domain *d, struct evtchn *evtchn,
                                     unsigned int priority)
 {
@@ -352,6 +363,7 @@ static const struct evtchn_port_ops evtchn_port_ops_fifo =
     .unmask        = evtchn_fifo_unmask,
     .is_pending    = evtchn_fifo_is_pending,
     .is_masked     = evtchn_fifo_is_masked,
+    .is_busy       = evtchn_fifo_is_busy,
     .set_priority  = evtchn_fifo_set_priority,
     .print_state   = evtchn_fifo_print_state,
 };

xen/include/xen/event.h

@@ -138,6 +138,11 @@ struct evtchn_port_ops {
     void (*unmask)(struct domain *d, struct evtchn *evtchn);
     bool_t (*is_pending)(struct domain *d, const struct evtchn *evtchn);
     bool_t (*is_masked)(struct domain *d, const struct evtchn *evtchn);
+    /*
+     * Is the port unavailable because it's still being cleaned up
+     * after being closed?
+     */
+    bool_t (*is_busy)(struct domain *d, evtchn_port_t port);
     int (*set_priority)(struct domain *d, struct evtchn *evtchn,
                         unsigned int priority);
     void (*print_state)(struct domain *d, const struct evtchn *evtchn);
@@ -179,6 +184,13 @@ static inline bool_t evtchn_port_is_masked(struct domain *d,
     return d->evtchn_port_ops->is_masked(d, evtchn);
 }
 
+static inline bool_t evtchn_port_is_busy(struct domain *d, evtchn_port_t port)
+{
+    if ( d->evtchn_port_ops->is_busy )
+        return d->evtchn_port_ops->is_busy(d, port);
+    return 0;
+}
+
 static inline int evtchn_port_set_priority(struct domain *d,
                                            struct evtchn *evtchn,
                                            unsigned int priority)