From: Jason Xing <kernelxing@tencent.com>

Add batch xmit logic.

Only grabbing the lock and disable bottom half once and sent all
the aggregated packets in one loop.

Since previous patch puts descriptors in xs->skb_cache in a reversed
order, this patch sends each skb out from start to end when 'start' is
not smaller than 'end'.

Signed-off-by: Jason Xing <kernelxing@tencent.com>
---
 include/linux/netdevice.h |  3 +++
 net/core/dev.c            | 19 +++++++++++++++++++
 2 files changed, 22 insertions(+)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5e5de4b0a433..8e2688e3f2e4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h

@@ -3352,6 +3352,9 @@ u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
 
 int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev);
 int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
+int xsk_direct_xmit_batch(struct sk_buff **skbs, struct net_device *dev,
+			  struct netdev_queue *txq, int *cur,
+			  int start, int end);
 
 static inline int dev_queue_xmit(struct sk_buff *skb)
 {

diff --git a/net/core/dev.c b/net/core/dev.c
index 68dc47d7e700..a5a6b9a199e9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c

@@ -4742,6 +4742,25 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 }
 EXPORT_SYMBOL(__dev_queue_xmit);
 
+int xsk_direct_xmit_batch(struct sk_buff **skbs, struct net_device *dev,
+			  struct netdev_queue *txq, int *cur,
+			  int start, int end)
+{
+	int ret = NETDEV_TX_BUSY;
+
+	local_bh_disable();
+	HARD_TX_LOCK(dev, txq, smp_processor_id());
+	for (*cur = start; *cur >= end; (*cur)--) {