Drivers: hv: vmbus: Use a round-robin algorithm for picking the outgoing channel

The current algorithm for picking an outgoing channel was not distributing
the load well. Implement a simple round-robin scheme to ensure good
distribution of the outgoing traffic.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Reviewed-by: Long Li <longli@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index b1e5a5f..6117891 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -350,6 +350,7 @@
 			}
 
 			newchannel->state = CHANNEL_OPEN_STATE;
+			channel->num_sc++;
 			if (channel->sc_creation_callback != NULL)
 				/*
 				 * We need to invoke the sub-channel creation
@@ -862,9 +863,8 @@
 
 /*
  * Retrieve the (sub) channel on which to send an outgoing request.
- * When a primary channel has multiple sub-channels, we choose a
- * channel whose VCPU binding is closest to the VCPU on which
- * this call is being made.
+ * When a primary channel has multiple sub-channels, we try to
+ * distribute the load equally amongst all available channels.
  */
 struct vmbus_channel *vmbus_get_outgoing_channel(struct vmbus_channel *primary)
 {
@@ -872,11 +872,19 @@
 	int cur_cpu;
 	struct vmbus_channel *cur_channel;
 	struct vmbus_channel *outgoing_channel = primary;
-	int cpu_distance, new_cpu_distance;
+	int next_channel;
+	int i = 1;
 
 	if (list_empty(&primary->sc_list))
 		return outgoing_channel;
 
+	next_channel = primary->next_oc++;
+
+	if (next_channel > (primary->num_sc)) {
+		primary->next_oc = 0;
+		return outgoing_channel;
+	}
+
 	cur_cpu = hv_context.vp_index[get_cpu()];
 	put_cpu();
 	list_for_each_safe(cur, tmp, &primary->sc_list) {
@@ -887,18 +895,10 @@
 		if (cur_channel->target_vp == cur_cpu)
 			return cur_channel;
 
-		cpu_distance = ((outgoing_channel->target_vp > cur_cpu) ?
-				(outgoing_channel->target_vp - cur_cpu) :
-				(cur_cpu - outgoing_channel->target_vp));
+		if (i == next_channel)
+			return cur_channel;
 
-		new_cpu_distance = ((cur_channel->target_vp > cur_cpu) ?
-				(cur_channel->target_vp - cur_cpu) :
-				(cur_cpu - cur_channel->target_vp));
-
-		if (cpu_distance < new_cpu_distance)
-			continue;
-
-		outgoing_channel = cur_channel;
+		i++;
 	}
 
 	return outgoing_channel;