[RFC PATCH] packet: rework packet_pick_tx_queue() to use common code selection

[Paolo Abeni <pabeni@redhat.com>]

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.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
Note: the main goal here is getting rid of the fallback() indirect
call in the device drivers implementing ndo_select_queue(). We can
obtain the same result with the INDIRECT_CALL() harness. Both ways
we need to export __netdev_pick_tx() but here we avoid the need
for additional branching.
---
 include/linux/netdevice.h | 2 ++
 net/core/dev.c            | 5 +++--
 net/packet/af_packet.c    | 9 +++++++--
 3 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c10b60297d28..29a558bded82 100644
--- 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_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 2b67f2aa59dd..004d1180671a 100644
--- 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_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 8376bc1c1508..1f7ae4a34d27 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -285,14 +285,19 @@ 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 hint = __packet_pick_tx_queue(dev, skb, NULL);
 	u16 queue_index;
 
+#ifdef CONFIG_XPS
+	skb->sender_cpu = hint + 1;
+#endif
+	skb_record_rx_queue(skb, hint);
 	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;
-- 
2.20.1