@@ -386,9 +386,10 @@ struct sk_buff {
#else
__u8 deliver_no_wcard:1;
#endif
+ __u8 ooo_okay:1;
kmemcheck_bitfield_end(flags2);
- /* 0/14 bit hole */
+ /* 0/13 bit hole */
#ifdef CONFIG_NET_DMA
dma_cookie_t dma_cookie;
@@ -2125,20 +2125,24 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev,
int queue_index;
const struct net_device_ops *ops = dev->netdev_ops;
- if (ops->ndo_select_queue) {
+ if (dev->real_num_tx_queues == 1)
+ queue_index = 0;
+ else if (ops->ndo_select_queue) {
queue_index = ops->ndo_select_queue(dev, skb);
queue_index = dev_cap_txqueue(dev, queue_index);
} else {
struct sock *sk = skb->sk;
queue_index = sk_tx_queue_get(sk);
- if (queue_index < 0) {
- queue_index = 0;
- if (dev->real_num_tx_queues > 1)
- queue_index = skb_tx_hash(dev, skb);
+ if (queue_index < 0 || skb->ooo_okay ||
+ queue_index >= dev->real_num_tx_queues) {
+ int old_index = queue_index;
- if (sk) {
- struct dst_entry *dst = rcu_dereference_check(sk->sk_dst_cache, 1);
+ queue_index = skb_tx_hash(dev, skb);
+
+ if (queue_index != old_index && sk) {
+ struct dst_entry *dst =
+ rcu_dereference_check(sk->sk_dst_cache, 1);
if (dst && skb_dst(skb) == dst)
sk_tx_queue_set(sk, queue_index);
@@ -822,8 +822,11 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
&md5);
tcp_header_size = tcp_options_size + sizeof(struct tcphdr);
- if (tcp_packets_in_flight(tp) == 0)
+ if (tcp_packets_in_flight(tp) == 0) {
tcp_ca_event(sk, CA_EVENT_TX_START);
+ skb->ooo_okay = 1;
+ } else
+ skb->ooo_okay = 0;
skb_push(skb, tcp_header_size);
skb_reset_transport_header(skb);
In dev_pick_tx, don't do work in calculating queue index or setting the index in the sock unless the device has more than one queue. This allows the sock to be set only with a queue index of a multi-queue device which is desirable if device are stacked like in a tunnel. We also allow the mapping of a socket to queue to be changed. To maintain in order packet transmission a flag (ooo_okay) has been added to the sk_buff structure. If a transport layer sets this flag on a packet, the transmit queue can be changed for the socket. Presumably, the transport would set this if there was no possbility of creating OOO packets (for instance, there are no packets in flight for the socket). This patch includes the modification in TCP output for setting this flag. Signed-off-by: Tom Herbert <therbert@google.com> --- include/linux/skbuff.h | 3 ++- net/core/dev.c | 18 +++++++++++------- net/ipv4/tcp_output.c | 5 ++++- 3 files changed, 17 insertions(+), 9 deletions(-)