packet: rework packet_pick_tx_queue() to use common code selection

Currently packet_pick_tx_queue() is the only caller of
ndo_select_queue() using a fallback argument other than
netdev_pick_tx.

Leveraging rx queue, we can obtain a similar queue selection
behavior using core helpers. After this change, ndo_select_queue()
is always invoked with netdev_pick_tx() as fallback.
We can change ndo_select_queue() signature in a followup patch,
dropping an indirect call per transmitted packet in some scenarios
(e.g. TCP syn and XDP generic xmit)

This changes slightly how af packet queue selection happens when
PACKET_QDISC_BYPASS is set. It's now more similar to plan dev_queue_xmit()
tacking in account both XPS and TC mapping.

 v1  -> v2:
  - rebased after helper name change
 RFC -> v1:
  - initialize sender_cpu to the expected value

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 57cd2bdd9f78fc00101b0be1c9b99e753a3c426c..0ff28db4239f46ee97453cb3dd4e8be8eaa83209 100644 (file)
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2152,6 +2152,8 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
                                  &qdisc_xmit_lock_key);        \
 }
 
+u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
+                    struct net_device *sb_dev);
 struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
                                         struct sk_buff *skb,
                                         struct net_device *sb_dev);

diff --git a/net/core/dev.c b/net/core/dev.c
index 5dd3e3f7dd1242102b6a8568cc59b4bb51dba774..1a76b4fe9b9781299248a3fdaea0b81541b15a58 100644 (file)
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3704,8 +3704,8 @@ u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(dev_pick_tx_cpu_id);
 
-static u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
-                         struct net_device *sb_dev)
+u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
+                    struct net_device *sb_dev)
 {
        struct sock *sk = skb->sk;
        int queue_index = sk_tx_queue_get(sk);
@@ -3729,6 +3729,7 @@ static u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
 
        return queue_index;
 }
+EXPORT_SYMBOL(netdev_pick_tx);
 
 struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
                                         struct sk_buff *skb,

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 323655a256746604b2d25e226f33a95f0af57233..a8809dc0e1ab1443a7c9518def58bf8c26ed3178 100644 (file)
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -275,24 +275,23 @@ static bool packet_use_direct_xmit(const struct packet_sock *po)
        return po->xmit == packet_direct_xmit;
 }
 
-static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb,
-                                 struct net_device *sb_dev)
-{
-       return dev_pick_tx_cpu_id(dev, skb, sb_dev, NULL);
-}
-
 static u16 packet_pick_tx_queue(struct sk_buff *skb)
 {
        struct net_device *dev = skb->dev;
        const struct net_device_ops *ops = dev->netdev_ops;
+       int cpu = raw_smp_processor_id();
        u16 queue_index;
 
+#ifdef CONFIG_XPS
+       skb->sender_cpu = cpu + 1;
+#endif
+       skb_record_rx_queue(skb, cpu % dev->real_num_tx_queues);
        if (ops->ndo_select_queue) {
                queue_index = ops->ndo_select_queue(dev, skb, NULL,
-                                                   __packet_pick_tx_queue);
+                                                   netdev_pick_tx);
                queue_index = netdev_cap_txqueue(dev, queue_index);
        } else {
-               queue_index = __packet_pick_tx_queue(dev, skb, NULL);
+               queue_index = netdev_pick_tx(dev, skb, NULL);
        }
 
        return queue_index;