[PATCH 16/16] Implement 3-level event channel routines

[Wei Liu <wei.liu2@citrix.com>]

Signed-off-by: Wei Liu <wei.liu2@citrix.com>
---
 xen/common/event_channel.c |  110 ++++++++++++++++++++++++++++++++++++--------
 1 file changed, 90 insertions(+), 20 deletions(-)

diff --git a/xen/common/event_channel.c b/xen/common/event_channel.c
index c448c60..a0bd00f 100644
--- a/xen/common/event_channel.c
+++ b/xen/common/event_channel.c
@@ -627,10 +627,33 @@ out:
     return ret;
 }
 
+static void __check_vcpu_polling(struct vcpu *v, int port)
+{
+    int vcpuid;
+    struct domain *d = v->domain;
+
+    /* Check if some VCPU might be polling for this event. */
+    if ( likely(bitmap_empty(d->poll_mask, d->max_vcpus)) )
+        return;
+
+    /* Wake any interested (or potentially interested) pollers. */
+    for ( vcpuid = find_first_bit(d->poll_mask, d->max_vcpus);
+          vcpuid < d->max_vcpus;
+          vcpuid = find_next_bit(d->poll_mask, d->max_vcpus, vcpuid+1) )
+    {
+        v = d->vcpu[vcpuid];
+        if ( ((v->poll_evtchn <= 0) || (v->poll_evtchn == port)) &&
+             test_and_clear_bit(vcpuid, d->poll_mask) )
+        {
+            v->poll_evtchn = 0;
+            vcpu_unblock(v);
+        }
+    }
+}
+
 static void evtchn_set_pending_l2(struct vcpu *v, int port)
 {
     struct domain *d = v->domain;
-    int vcpuid;
 
     /*
      * The following bit operations must happen in strict order.
@@ -649,23 +672,35 @@ static void evtchn_set_pending_l2(struct vcpu *v, int port)
         vcpu_mark_events_pending(v);
     }
 
-    /* Check if some VCPU might be polling for this event. */
-    if ( likely(bitmap_empty(d->poll_mask, d->max_vcpus)) )
-        return;
+    __check_vcpu_polling(v, port);
+}
 
-    /* Wake any interested (or potentially interested) pollers. */
-    for ( vcpuid = find_first_bit(d->poll_mask, d->max_vcpus);
-          vcpuid < d->max_vcpus;
-          vcpuid = find_next_bit(d->poll_mask, d->max_vcpus, vcpuid+1) )
+static void evtchn_set_pending_l3(struct vcpu *v, int port)
+{
+    struct domain *d = v->domain;
+    unsigned int page_no = EVTCHN_PAGE_NO(port);
+    unsigned int offset = EVTCHN_OFFSET_IN_PAGE(port);
+    unsigned int l1bit = port >> (EVTCHN_WORD_BITORDER(d) << 1);
+    unsigned int l2bit = port >> EVTCHN_WORD_BITORDER(d);
+
+    /*
+     * The following bit operations must happen in strict order.
+     * NB. On x86, the atomic bit operations also act as memory barriers.
+     * There is therefore sufficiently strict ordering for this architecture --
+     * others may require explicit memory barriers.
+     */
+
+    if ( test_and_set_bit(offset, d->evtchn_pending[page_no]) )
+         return;
+
+    if ( !test_bit(offset, d->evtchn_mask[page_no]) &&
+         !test_and_set_bit(l2bit, v->evtchn_pending_sel_l2) &&
+         !test_and_set_bit(l1bit, &vcpu_info(v, evtchn_pending_sel)) )
     {
-        v = d->vcpu[vcpuid];
-        if ( ((v->poll_evtchn <= 0) || (v->poll_evtchn == port)) &&
-             test_and_clear_bit(vcpuid, d->poll_mask) )
-        {
-            v->poll_evtchn = 0;
-            vcpu_unblock(v);
-        }
+        vcpu_mark_events_pending(v);
     }
+
+    __check_vcpu_polling(v, port);
 }
 
 static void evtchn_set_pending(struct vcpu *v, int port)
@@ -677,6 +712,9 @@ static void evtchn_set_pending(struct vcpu *v, int port)
     case EVTCHN_2_LEVEL:
         evtchn_set_pending_l2(v, port);
         break;
+    case 3:
+        evtchn_set_pending_l3(v, port);
+        break;
     default:
         BUG();
     }
@@ -981,6 +1019,37 @@ static int evtchn_unmask_l2(unsigned int port)
     return 0;
 }
 
+static int evtchn_unmask_l3(unsigned int port)
+{
+    struct domain *d = current->domain;
+    struct vcpu   *v;
+    unsigned int page_no = EVTCHN_PAGE_NO(port);
+    unsigned int offset = EVTCHN_OFFSET_IN_PAGE(port);
+    unsigned int l1bit = port >> (EVTCHN_WORD_BITORDER(d) << 1);
+    unsigned int l2bit = port >> EVTCHN_WORD_BITORDER(d);
+
+    ASSERT(spin_is_locked(&d->event_lock));
+
+    if ( unlikely(!port_is_valid(d, port)) )
+        return -EINVAL;
+
+    v = d->vcpu[evtchn_from_port(d, port)->notify_vcpu_id];
+
+    /*
+     * These operations must happen in strict order. Based on
+     * include/xen/event.h:evtchn_set_pending().
+     */
+    if ( test_and_clear_bit(offset, d->evtchn_mask[page_no]) &&
+         test_bit          (offset, d->evtchn_pending[page_no]) &&
+         !test_and_set_bit (l2bit, v->evtchn_pending_sel_l2) &&
+         !test_and_set_bit (l1bit, &vcpu_info(v, evtchn_pending_sel)) )
+    {
+        vcpu_mark_events_pending(v);
+    }
+
+    return 0;
+}
+
 int evtchn_unmask(unsigned int port)
 {
     struct domain *d = current->domain;
@@ -991,6 +1060,9 @@ int evtchn_unmask(unsigned int port)
     case EVTCHN_2_LEVEL:
         rc = evtchn_unmask_l2(port);
         break;
+    case 3:
+        rc = evtchn_unmask_l3(port);
+        break;
     default:
         BUG();
     }
@@ -1390,10 +1462,6 @@ long do_event_channel_op(int cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
         if ( copy_from_guest(&reg, arg, 1) != 0 )
             return -EFAULT;
         rc = evtchn_register_nlevel(&reg);
-
-        /* XXX always fails this call because it is not yet completed */
-        rc = -EINVAL;
-
         break;
     }
 
@@ -1602,8 +1670,10 @@ static void domain_dump_evtchn_info(struct domain *d)
     bitmap_scnlistprintf(keyhandler_scratch, sizeof(keyhandler_scratch),
                          d->poll_mask, d->max_vcpus);
     printk("Event channel information for domain %d:\n"
+           "Using %d-level event channel\n"
            "Polling vCPUs: {%s}\n"
-           "    port [p/m]\n", d->domain_id, keyhandler_scratch);
+           "    port [p/m]\n",
+           d->domain_id, d->evtchn_level, keyhandler_scratch);
 
     spin_lock(&d->event_lock);
 
-- 
1.7.10.4