net/hyperv: Fix the stop/wake queue mechanism

The ring buffer is only used to pass meta data for outbound packets. The
actual payload is accessed by DMA from the host. So the stop/wake queue
mechanism based on counting and comparing number of pages sent v.s. number
of pages in the ring buffer is wrong. Also, there is a race condition in
the stop/wake queue calls, which can stop xmit queue forever.

The new stop/wake queue mechanism is based on the actual bytes used by
outbound packets in the ring buffer. The check for number of outstanding
sends after stop queue prevents the race condition that can cause wake
queue happening earlier than stop queue.

Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Reported-by: Long Li <longli@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 4a807e44ec600eab77dad0233c3e66ab8ec83c77..b6ac152a9bd00df1a548dace4f652b466956e7ff 100644 (file)
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -435,6 +435,9 @@ static void netvsc_send_completion(struct hv_device *device,
                        nvsc_packet->completion.send.send_completion_ctx);
 
                atomic_dec(&net_device->num_outstanding_sends);
+
+               if (netif_queue_stopped(ndev))
+                       netif_wake_queue(ndev);
        } else {
                netdev_err(ndev, "Unknown send completion packet type- "
                           "%d received!!\n", nvsp_packet->hdr.msg_type);
@@ -485,11 +488,16 @@ int netvsc_send(struct hv_device *device,
 
        }
 
-       if (ret != 0)
+       if (ret == 0) {
+               atomic_inc(&net_device->num_outstanding_sends);
+       } else if (ret == -EAGAIN) {
+               netif_stop_queue(ndev);
+               if (atomic_read(&net_device->num_outstanding_sends) < 1)
+                       netif_wake_queue(ndev);
+       } else {
                netdev_err(ndev, "Unable to send packet %p ret %d\n",
                           packet, ret);
-       else
-               atomic_inc(&net_device->num_outstanding_sends);
+       }
 
        return ret;
 }

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index b69c3a4d1e9e41c72c6044ffb5299316b768966f..7da85ebd7ac62fa35a2d2152d94f60151e292658 100644 (file)
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -43,15 +43,10 @@
 struct net_device_context {
        /* point back to our device context */
        struct hv_device *device_ctx;
-       atomic_t avail;
        struct delayed_work dwork;
 };
 
 
-#define PACKET_PAGES_LOWATER  8
-/* Need this many pages to handle worst case fragmented packet */
-#define PACKET_PAGES_HIWATER  (MAX_SKB_FRAGS + 2)
-
 static int ring_size = 128;
 module_param(ring_size, int, S_IRUGO);
 MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)");
@@ -144,18 +139,8 @@ static void netvsc_xmit_completion(void *context)
 
        kfree(packet);
 
-       if (skb) {
-               struct net_device *net = skb->dev;
-               struct net_device_context *net_device_ctx = netdev_priv(net);
-               unsigned int num_pages = skb_shinfo(skb)->nr_frags + 2;
-
+       if (skb)
                dev_kfree_skb_any(skb);
-
-               atomic_add(num_pages, &net_device_ctx->avail);
-               if (atomic_read(&net_device_ctx->avail) >=
-                               PACKET_PAGES_HIWATER)
-                       netif_wake_queue(net);
-       }
 }
 
 static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
@@ -167,8 +152,6 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 
        /* Add 1 for skb->data and additional one for RNDIS */
        num_pages = skb_shinfo(skb)->nr_frags + 1 + 1;
-       if (num_pages > atomic_read(&net_device_ctx->avail))
-               return NETDEV_TX_BUSY;
 
        /* Allocate a netvsc packet based on # of frags. */
        packet = kzalloc(sizeof(struct hv_netvsc_packet) +
@@ -218,10 +201,6 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
        if (ret == 0) {
                net->stats.tx_bytes += skb->len;
                net->stats.tx_packets++;
-
-               atomic_sub(num_pages, &net_device_ctx->avail);
-               if (atomic_read(&net_device_ctx->avail) < PACKET_PAGES_LOWATER)
-                       netif_stop_queue(net);
        } else {
                /* we are shutting down or bus overloaded, just drop packet */
                net->stats.tx_dropped++;
@@ -391,7 +370,6 @@ static int netvsc_probe(struct hv_device *dev,
 
        net_device_ctx = netdev_priv(net);
        net_device_ctx->device_ctx = dev;
-       atomic_set(&net_device_ctx->avail, ring_size);
        hv_set_drvdata(dev, net);
        INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_send_garp);