tuntap: set transport header before passing it to kernel (38502af7) · Commits · 戴 / test

Currently, for the packets receives from tuntap, before doing header check, kernel just reset the transport header in netif_receive_skb() which pretends no l4 header. This is suboptimal for precise packet length estimation (introduced in ) which needs correct l4 header for gso packets. So this patch set the transport header to csum_start for partial checksum packets, otherwise it first try skb_flow_dissect(), if it fails, just reset the transport header. Cc: Eric Dumazet <edumazet@google.com> Signed-off-by:

Jason Wang <jasowang@redhat.com> Signed-off-by:

David S. Miller <davem@davemloft.net>

drivers/net/tun.c

+10 −0

Original line number	Diff line number	Diff line
		@@ -70,6 +70,7 @@
		#include <net/sock.h>

		#include <asm/uaccess.h>
		#include <net/flow_keys.h>

		/* Uncomment to enable debugging */
		/* #define TUN_DEBUG 1 */
		@@ -1049,6 +1050,7 @@ static ssize_t tun_get_user(struct tun_struct tun, struct tun_file tfile,
		bool zerocopy = false;
		int err;
		u32 rxhash;
		struct flow_keys keys;

		if (!(tun->flags & TUN_NO_PI)) {
		if ((len -= sizeof(pi)) > total_len)
		@@ -1203,6 +1205,14 @@ static ssize_t tun_get_user(struct tun_struct tun, struct tun_file tfile,
		}

		skb_reset_network_header(skb);

		if (skb->ip_summed == CHECKSUM_PARTIAL)
		skb_set_transport_header(skb, skb_checksum_start_offset(skb));
		else if (skb_flow_dissect(skb, &keys))
		skb_set_transport_header(skb, keys.thoff);
		else
		skb_reset_transport_header(skb);

		rxhash = skb_get_rxhash(skb);
		netif_rx_ni(skb);

Admin message