Commit 9ab9831b authored by Zoltan Kiss's avatar Zoltan Kiss Committed by David S. Miller
Browse files

xen-netback: Fix Rx stall due to race condition

The recent patch to fix receive side flow control
(11b57f90

: xen-netback: stop vif thread
spinning if frontend is unresponsive) solved the spinning thread problem,
however caused an another one. The receive side can stall, if:
- [THREAD] xenvif_rx_action sets rx_queue_stopped to true
- [INTERRUPT] interrupt happens, and sets rx_event to true
- [THREAD] then xenvif_kthread sets rx_event to false
- [THREAD] rx_work_todo doesn't return true anymore

Also, if interrupt sent but there is still no room in the ring, it take quite a
long time until xenvif_rx_action realize it. This patch ditch that two variable,
and rework rx_work_todo. If the thread finds it can't fit more skb's into the
ring, it saves the last slot estimation into rx_last_skb_slots, otherwise it's
kept as 0. Then rx_work_todo will check if:
- there is something to send to the ring (like before)
- there is space for the topmost packet in the queue

I think that's more natural and optimal thing to test than two bool which are
set somewhere else.
Signed-off-by: default avatarZoltan Kiss <zoltan.kiss@citrix.com>
Reviewed-by: default avatarPaul Durrant <paul.durrant@citrix.com>
Acked-by: default avatarWei Liu <wei.liu2@citrix.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent bce3ea81
......@@ -143,11 +143,7 @@ struct xenvif {
char rx_irq_name[IFNAMSIZ+4]; /* DEVNAME-rx */
struct xen_netif_rx_back_ring rx;
struct sk_buff_head rx_queue;
bool rx_queue_stopped;
/* Set when the RX interrupt is triggered by the frontend.
* The worker thread may need to wake the queue.
*/
bool rx_event;
RING_IDX rx_last_skb_slots;
/* This array is allocated seperately as it is large */
struct gnttab_copy *grant_copy_op;
......
......@@ -100,7 +100,6 @@ static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id)
{
struct xenvif *vif = dev_id;
vif->rx_event = true;
xenvif_kick_thread(vif);
return IRQ_HANDLED;
......
......@@ -476,7 +476,6 @@ static void xenvif_rx_action(struct xenvif *vif)
unsigned long offset;
struct skb_cb_overlay *sco;
bool need_to_notify = false;
bool ring_full = false;
struct netrx_pending_operations npo = {
.copy = vif->grant_copy_op,
......@@ -486,7 +485,7 @@ static void xenvif_rx_action(struct xenvif *vif)
skb_queue_head_init(&rxq);
while ((skb = skb_dequeue(&vif->rx_queue)) != NULL) {
int max_slots_needed;
RING_IDX max_slots_needed;
int i;
/* We need a cheap worse case estimate for the number of
......@@ -509,9 +508,10 @@ static void xenvif_rx_action(struct xenvif *vif)
if (!xenvif_rx_ring_slots_available(vif, max_slots_needed)) {
skb_queue_head(&vif->rx_queue, skb);
need_to_notify = true;
ring_full = true;
vif->rx_last_skb_slots = max_slots_needed;
break;
}
} else
vif->rx_last_skb_slots = 0;
sco = (struct skb_cb_overlay *)skb->cb;
sco->meta_slots_used = xenvif_gop_skb(skb, &npo);
......@@ -522,8 +522,6 @@ static void xenvif_rx_action(struct xenvif *vif)
BUG_ON(npo.meta_prod > ARRAY_SIZE(vif->meta));
vif->rx_queue_stopped = !npo.copy_prod && ring_full;
if (!npo.copy_prod)
goto done;
......@@ -1473,8 +1471,8 @@ static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
static inline int rx_work_todo(struct xenvif *vif)
{
return (!skb_queue_empty(&vif->rx_queue) && !vif->rx_queue_stopped) ||
vif->rx_event;
return !skb_queue_empty(&vif->rx_queue) &&
xenvif_rx_ring_slots_available(vif, vif->rx_last_skb_slots);
}
static inline int tx_work_todo(struct xenvif *vif)
......@@ -1560,8 +1558,6 @@ int xenvif_kthread(void *data)
if (!skb_queue_empty(&vif->rx_queue))
xenvif_rx_action(vif);
vif->rx_event = false;
if (skb_queue_empty(&vif->rx_queue) &&
netif_queue_stopped(vif->dev))
xenvif_start_queue(vif);
......
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment