xen-netback: Aggregate TX unmap operations

Unmapping causes TLB flushing, therefore we should make it in the largest
possible batches. However we shouldn't starve the guest for too long. So if
the guest has space for at least two big packets and we don't have at least a
quarter ring to unmap, delay it for at most 1 milisec.

Signed-off-by: Zoltan Kiss <zoltan.kiss@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/xen-netback/common.h

@@ -137,6 +137,8 @@ struct xenvif {
 	u16 dealloc_ring[MAX_PENDING_REQS];
 	struct task_struct *dealloc_task;
 	wait_queue_head_t dealloc_wq;
+	struct timer_list dealloc_delay;
+	bool dealloc_delay_timed_out;
 
 	/* Use kthread for guest RX */
 	struct task_struct *task;

drivers/net/xen-netback/interface.c

@@ -408,6 +408,7 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 			  .desc = i };
 		vif->grant_tx_handle[i] = NETBACK_INVALID_HANDLE;
 	}
+	init_timer(&vif->dealloc_delay);
 
 	/*
 	 * Initialise a dummy MAC address. We choose the numerically
@@ -556,6 +557,7 @@ void xenvif_disconnect(struct xenvif *vif)
 	}
 
 	if (vif->dealloc_task) {
+		del_timer_sync(&vif->dealloc_delay);
 		kthread_stop(vif->dealloc_task);
 		vif->dealloc_task = NULL;
 	}

drivers/net/xen-netback/netback.c

@@ -133,6 +133,11 @@ static inline pending_ring_idx_t pending_index(unsigned i)
 	return i & (MAX_PENDING_REQS-1);
 }
 
+static inline pending_ring_idx_t nr_free_slots(struct xen_netif_tx_back_ring *ring)
+{
+	return ring->nr_ents -	(ring->sring->req_prod - ring->rsp_prod_pvt);
+}
+
 bool xenvif_rx_ring_slots_available(struct xenvif *vif, int needed)
 {
 	RING_IDX prod, cons;
@@ -1716,9 +1721,36 @@ static inline int tx_work_todo(struct xenvif *vif)
 	return 0;
 }
 
+static void xenvif_dealloc_delay(unsigned long data)
+{
+	struct xenvif *vif = (struct xenvif *)data;
+
+	vif->dealloc_delay_timed_out = true;
+	wake_up(&vif->dealloc_wq);
+}
+
 static inline bool tx_dealloc_work_todo(struct xenvif *vif)
 {
-	return vif->dealloc_cons != vif->dealloc_prod;
+	if (vif->dealloc_cons != vif->dealloc_prod) {
+		if ((nr_free_slots(&vif->tx) > 2 * XEN_NETBK_LEGACY_SLOTS_MAX) &&
+		    (vif->dealloc_prod - vif->dealloc_cons < MAX_PENDING_REQS / 4) &&
+		    !vif->dealloc_delay_timed_out) {
+			if (!timer_pending(&vif->dealloc_delay)) {
+				vif->dealloc_delay.function =
+					xenvif_dealloc_delay;
+				vif->dealloc_delay.data = (unsigned long)vif;
+				mod_timer(&vif->dealloc_delay,
+					  jiffies + msecs_to_jiffies(1));
+
+			}
+			return false;
+		}
+		del_timer_sync(&vif->dealloc_delay);
+		vif->dealloc_delay_timed_out = false;
+		return true;
+	}
+
+	return false;
 }
 
 void xenvif_unmap_frontend_rings(struct xenvif *vif)