* [PATCH net, 1/2] hv_netvsc: Remove "unlikely" from netvsc_select_queue
2020-08-20 21:53 [PATCH net, 0/2] hv_netvsc: Some fixes for the select_queue Haiyang Zhang
@ 2020-08-20 21:53 ` Haiyang Zhang
2020-08-20 21:53 ` [PATCH net, 2/2] hv_netvsc: Fix the queue_mapping in netvsc_vf_xmit() Haiyang Zhang
2020-08-20 23:24 ` [PATCH net, 0/2] hv_netvsc: Some fixes for the select_queue David Miller
2 siblings, 0 replies; 4+ messages in thread
From: Haiyang Zhang @ 2020-08-20 21:53 UTC (permalink / raw)
To: linux-hyperv, netdev
Cc: haiyangz, kys, sthemmin, olaf, vkuznets, davem, linux-kernel
When using vf_ops->ndo_select_queue, the number of queues of VF is
usually bigger than the synthetic NIC. This condition may happen
often.
Remove "unlikely" from the comparison of ndev->real_num_tx_queues.
Fixes: b3bf5666a510 ("hv_netvsc: defer queue selection to VF")
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
---
drivers/net/hyperv/netvsc_drv.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 787f17e2a971..0029292cdb9f 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -367,7 +367,7 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
}
rcu_read_unlock();
- while (unlikely(txq >= ndev->real_num_tx_queues))
+ while (txq >= ndev->real_num_tx_queues)
txq -= ndev->real_num_tx_queues;
return txq;
--
2.25.1
^ permalink raw reply related [flat|nested] 4+ messages in thread
* [PATCH net, 2/2] hv_netvsc: Fix the queue_mapping in netvsc_vf_xmit()
2020-08-20 21:53 [PATCH net, 0/2] hv_netvsc: Some fixes for the select_queue Haiyang Zhang
2020-08-20 21:53 ` [PATCH net, 1/2] hv_netvsc: Remove "unlikely" from netvsc_select_queue Haiyang Zhang
@ 2020-08-20 21:53 ` Haiyang Zhang
2020-08-20 23:24 ` [PATCH net, 0/2] hv_netvsc: Some fixes for the select_queue David Miller
2 siblings, 0 replies; 4+ messages in thread
From: Haiyang Zhang @ 2020-08-20 21:53 UTC (permalink / raw)
To: linux-hyperv, netdev
Cc: haiyangz, kys, sthemmin, olaf, vkuznets, davem, linux-kernel
netvsc_vf_xmit() / dev_queue_xmit() will call VF NIC’s ndo_select_queue
or netdev_pick_tx() again. They will use skb_get_rx_queue() to get the
queue number, so the “skb->queue_mapping - 1” will be used. This may
cause the last queue of VF not been used.
Use skb_record_rx_queue() here, so that the skb_get_rx_queue() called
later will get the correct queue number, and VF will be able to use
all queues.
Fixes: b3bf5666a510 ("hv_netvsc: defer queue selection to VF")
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
---
drivers/net/hyperv/netvsc_drv.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 0029292cdb9f..64b0a74c1523 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -502,7 +502,7 @@ static int netvsc_vf_xmit(struct net_device *net, struct net_device *vf_netdev,
int rc;
skb->dev = vf_netdev;
- skb->queue_mapping = qdisc_skb_cb(skb)->slave_dev_queue_mapping;
+ skb_record_rx_queue(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping);
rc = dev_queue_xmit(skb);
if (likely(rc == NET_XMIT_SUCCESS || rc == NET_XMIT_CN)) {
--
2.25.1
^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [PATCH net, 0/2] hv_netvsc: Some fixes for the select_queue
2020-08-20 21:53 [PATCH net, 0/2] hv_netvsc: Some fixes for the select_queue Haiyang Zhang
2020-08-20 21:53 ` [PATCH net, 1/2] hv_netvsc: Remove "unlikely" from netvsc_select_queue Haiyang Zhang
2020-08-20 21:53 ` [PATCH net, 2/2] hv_netvsc: Fix the queue_mapping in netvsc_vf_xmit() Haiyang Zhang
@ 2020-08-20 23:24 ` David Miller
2 siblings, 0 replies; 4+ messages in thread
From: David Miller @ 2020-08-20 23:24 UTC (permalink / raw)
To: haiyangz
Cc: linux-hyperv, netdev, kys, sthemmin, olaf, vkuznets, linux-kernel
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Thu, 20 Aug 2020 14:53:13 -0700
> This patch set includes two fixes for the select_queue process.
Series applied, thank you.
^ permalink raw reply [flat|nested] 4+ messages in thread