Hi,
This patch enables TSO over IPv6. Currently Linux network stacks
restricts TSO over IPv6 by clearing of the NETIF_F_TSO bit from
"dev->features". This patch will remove this restriction.
This patch will introduce a new flag NETIF_F_TSO6 which will be used
to check whether device supports TSO over IPv6. If device support TSO
over IPv6 then we don't clear of NETIF_F_TSO and which will make the
TCP layer to create TSO packets. Any device supporting TSO over IPv6
will set NETIF_F_TSO6 flag in "dev->features" along with NETIF_F_TSO.
In case when user disables TSO using ethtool, NETIF_F_TSO will get
cleared from "dev->features". So even if we have NETIF_F_TSO6 we don't
get TSO packets created by TCP layer.
SKB_GSO_TCPV4 renamed to SKB_GSO_TCP to make it generic GSO packet.
SKB_GSO_UDPV4 renamed to SKB_GSO_UDP as UFO is not a IPv4 feature.
UFO is supported over IPv6 also
The following table shows there is significant improvement in
throughput with normal frames and CPU usage for both normal and jumbo.
--------------------------------------------------
| | 1500 | 9600 |
| ------------------|-------------------|
| | thru CPU | thru CPU |
--------------------------------------------------
| TSO OFF | 2.00 5.5% id | 5.66 20.0% id |
--------------------------------------------------
| TSO ON | 2.63 78.0 id | 5.67 39.0% id |
--------------------------------------------------
Please review the patch.
Signed-off-by: Ananda Raju <[EMAIL PROTECTED]>
---
diff -upNr netdev.org/drivers/net/s2io.c netdev.ipv6_tso/drivers/net/s2io.c
--- netdev.org/drivers/net/s2io.c 2006-06-27 07:30:36.000000000 -0700
+++ netdev.ipv6_tso/drivers/net/s2io.c 2006-06-27 07:38:48.000000000 -0700
@@ -3960,7 +3960,7 @@ static int s2io_xmit(struct sk_buff *skb
txdp->Control_2 = 0;
#ifdef NETIF_F_TSO
mss = skb_shinfo(skb)->gso_size;
- if (skb_shinfo(skb)->gso_type == SKB_GSO_TCPV4) {
+ if (skb_shinfo(skb)->gso_type == SKB_GSO_TCP) {
txdp->Control_1 |= TXD_TCP_LSO_EN;
txdp->Control_1 |= TXD_TCP_LSO_MSS(mss);
}
@@ -3980,7 +3980,7 @@ static int s2io_xmit(struct sk_buff *skb
}
frg_len = skb->len - skb->data_len;
- if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4) {
+ if (skb_shinfo(skb)->gso_type == SKB_GSO_UDP) {
int ufo_size;
ufo_size = skb_shinfo(skb)->gso_size;
@@ -4009,7 +4009,7 @@ static int s2io_xmit(struct sk_buff *skb
txdp->Host_Control = (unsigned long) skb;
txdp->Control_1 |= TXD_BUFFER0_SIZE(frg_len);
- if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4)
+ if (skb_shinfo(skb)->gso_type == SKB_GSO_UDP)
txdp->Control_1 |= TXD_UFO_EN;
frg_cnt = skb_shinfo(skb)->nr_frags;
@@ -4024,12 +4024,12 @@ static int s2io_xmit(struct sk_buff *skb
(sp->pdev, frag->page, frag->page_offset,
frag->size, PCI_DMA_TODEVICE);
txdp->Control_1 = TXD_BUFFER0_SIZE(frag->size);
- if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4)
+ if (skb_shinfo(skb)->gso_type == SKB_GSO_UDP)
txdp->Control_1 |= TXD_UFO_EN;
}
txdp->Control_1 |= TXD_GATHER_CODE_LAST;
- if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4)
+ if (skb_shinfo(skb)->gso_type == SKB_GSO_UDP)
frg_cnt++; /* as Txd0 was used for inband header */
tx_fifo = mac_control->tx_FIFO_start[queue];
@@ -4043,7 +4043,7 @@ static int s2io_xmit(struct sk_buff *skb
if (mss)
val64 |= TX_FIFO_SPECIAL_FUNC;
#endif
- if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4)
+ if (skb_shinfo(skb)->gso_type == SKB_GSO_UDP)
val64 |= TX_FIFO_SPECIAL_FUNC;
writeq(val64, &tx_fifo->List_Control);
@@ -7021,6 +7021,9 @@ s2io_init_nic(struct pci_dev *pdev, cons
#ifdef NETIF_F_TSO
dev->features |= NETIF_F_TSO;
#endif
+#ifdef NETIF_F_TSO6
+ dev->features |= NETIF_F_TSO6;
+#endif
if (sp->device_type & XFRAME_II_DEVICE) {
dev->features |= NETIF_F_UFO;
dev->features |= NETIF_F_HW_CSUM;
diff -upNr netdev.org/include/linux/netdevice.h
netdev.ipv6_tso/include/linux/netdevice.h
--- netdev.org/include/linux/netdevice.h 2006-06-27 07:30:36.000000000
-0700
+++ netdev.ipv6_tso/include/linux/netdevice.h 2006-06-27 07:38:48.000000000
-0700
@@ -313,8 +313,9 @@ struct net_device
/* Segmentation offload features */
#define NETIF_F_GSO_SHIFT 16
-#define NETIF_F_TSO (SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT)
-#define NETIF_F_UFO (SKB_GSO_UDPV4 << NETIF_F_GSO_SHIFT)
+#define NETIF_F_TSO (SKB_GSO_TCP << NETIF_F_GSO_SHIFT)
+#define NETIF_F_UFO (SKB_GSO_UDP << NETIF_F_GSO_SHIFT)
+#define NETIF_F_TSO6 (SKB_GSO_TCPV6 << NETIF_F_GSO_SHIFT)
#define NETIF_F_GEN_CSUM (NETIF_F_NO_CSUM | NETIF_F_HW_CSUM)
#define NETIF_F_ALL_CSUM (NETIF_F_IP_CSUM | NETIF_F_GEN_CSUM)
diff -upNr netdev.org/include/linux/skbuff.h
netdev.ipv6_tso/include/linux/skbuff.h
--- netdev.org/include/linux/skbuff.h 2006-06-27 07:30:36.000000000 -0700
+++ netdev.ipv6_tso/include/linux/skbuff.h 2006-06-27 07:38:48.000000000
-0700
@@ -170,8 +170,9 @@ enum {
};
enum {
- SKB_GSO_TCPV4 = 1 << 0,
- SKB_GSO_UDPV4 = 1 << 1,
+ SKB_GSO_TCP = 1 << 0,
+ SKB_GSO_UDP = 1 << 1,
+ SKB_GSO_TCPV6 = 1 << 2,
};
/**
diff -upNr netdev.org/net/ipv4/ip_output.c netdev.ipv6_tso/net/ipv4/ip_output.c
--- netdev.org/net/ipv4/ip_output.c 2006-06-27 07:30:36.000000000 -0700
+++ netdev.ipv6_tso/net/ipv4/ip_output.c 2006-06-27 07:38:48.000000000
-0700
@@ -744,7 +744,7 @@ static inline int ip_ufo_append_data(str
if (!err) {
/* specify the length of each IP datagram fragment*/
skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
- skb_shinfo(skb)->gso_type = SKB_GSO_UDPV4;
+ skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
__skb_queue_tail(&sk->sk_write_queue, skb);
return 0;
@@ -1089,7 +1089,7 @@ ssize_t ip_append_page(struct sock *sk,
if ((sk->sk_protocol == IPPROTO_UDP) &&
(rt->u.dst.dev->features & NETIF_F_UFO)) {
skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
- skb_shinfo(skb)->gso_type = SKB_GSO_UDPV4;
+ skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
}
diff -upNr netdev.org/net/ipv4/tcp_output.c
netdev.ipv6_tso/net/ipv4/tcp_output.c
--- netdev.org/net/ipv4/tcp_output.c 2006-06-27 07:30:36.000000000 -0700
+++ netdev.ipv6_tso/net/ipv4/tcp_output.c 2006-06-27 07:38:48.000000000
-0700
@@ -525,7 +525,7 @@ static void tcp_set_skb_tso_segs(struct
factor /= mss_now;
skb_shinfo(skb)->gso_segs = factor;
skb_shinfo(skb)->gso_size = mss_now;
- skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+ skb_shinfo(skb)->gso_type = SKB_GSO_TCP;
}
}
diff -upNr netdev.org/net/ipv6/af_inet6.c netdev.ipv6_tso/net/ipv6/af_inet6.c
--- netdev.org/net/ipv6/af_inet6.c 2006-06-27 07:30:36.000000000 -0700
+++ netdev.ipv6_tso/net/ipv6/af_inet6.c 2006-06-27 07:38:48.000000000 -0700
@@ -660,8 +660,11 @@ int inet6_sk_rebuild_header(struct sock
}
ip6_dst_store(sk, dst, NULL);
- sk->sk_route_caps = dst->dev->features &
- ~(NETIF_F_IP_CSUM | NETIF_F_TSO);
+ if (dst->dev->features & NETIF_F_TSO6)
+ sk->sk_route_caps = dst->dev->features;
+ else
+ sk->sk_route_caps = dst->dev->features &
+ ~(NETIF_F_IP_CSUM | NETIF_F_TSO);
}
return 0;
diff -upNr netdev.org/net/ipv6/inet6_connection_sock.c
netdev.ipv6_tso/net/ipv6/inet6_connection_sock.c
--- netdev.org/net/ipv6/inet6_connection_sock.c 2006-06-27 07:30:36.000000000
-0700
+++ netdev.ipv6_tso/net/ipv6/inet6_connection_sock.c 2006-06-27
07:38:48.000000000 -0700
@@ -187,8 +187,11 @@ int inet6_csk_xmit(struct sk_buff *skb,
}
ip6_dst_store(sk, dst, NULL);
- sk->sk_route_caps = dst->dev->features &
- ~(NETIF_F_IP_CSUM | NETIF_F_TSO);
+ if (dst->dev->features & NETIF_F_TSO6)
+ sk->sk_route_caps = dst->dev->features;
+ else
+ sk->sk_route_caps = dst->dev->features &
+ ~(NETIF_F_IP_CSUM | NETIF_F_TSO);
}
skb->dst = dst_clone(dst);
diff -upNr netdev.org/net/ipv6/ip6_output.c
netdev.ipv6_tso/net/ipv6/ip6_output.c
--- netdev.org/net/ipv6/ip6_output.c 2006-06-27 07:30:36.000000000 -0700
+++ netdev.ipv6_tso/net/ipv6/ip6_output.c 2006-06-27 07:38:48.000000000
-0700
@@ -230,7 +230,7 @@ int ip6_xmit(struct sock *sk, struct sk_
skb->priority = sk->sk_priority;
mtu = dst_mtu(dst);
- if ((skb->len <= mtu) || ipfragok) {
+ if ((skb->len <= mtu) || ipfragok || skb_shinfo(skb)->gso_size) {
IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS);
return NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev,
dst_output);
@@ -835,7 +835,7 @@ static inline int ip6_ufo_append_data(st
/* specify the length of each IP datagram fragment*/
skb_shinfo(skb)->gso_size = mtu - fragheaderlen -
sizeof(struct frag_hdr);
- skb_shinfo(skb)->gso_type = SKB_GSO_UDPV4;
+ skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
ipv6_select_ident(skb, &fhdr);
skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
__skb_queue_tail(&sk->sk_write_queue, skb);
diff -upNr netdev.org/net/ipv6/tcp_ipv6.c netdev.ipv6_tso/net/ipv6/tcp_ipv6.c
--- netdev.org/net/ipv6/tcp_ipv6.c 2006-06-27 07:30:36.000000000 -0700
+++ netdev.ipv6_tso/net/ipv6/tcp_ipv6.c 2006-06-27 07:38:48.000000000 -0700
@@ -271,8 +271,11 @@ static int tcp_v6_connect(struct sock *s
inet->rcv_saddr = LOOPBACK4_IPV6;
ip6_dst_store(sk, dst, NULL);
- sk->sk_route_caps = dst->dev->features &
- ~(NETIF_F_IP_CSUM | NETIF_F_TSO);
+ if (dst->dev->features & NETIF_F_TSO6)
+ sk->sk_route_caps = dst->dev->features;
+ else
+ sk->sk_route_caps = dst->dev->features &
+ ~(NETIF_F_IP_CSUM | NETIF_F_TSO);
icsk->icsk_ext_hdr_len = 0;
if (np->opt)
@@ -931,8 +934,11 @@ static struct sock * tcp_v6_syn_recv_soc
*/
ip6_dst_store(newsk, dst, NULL);
- newsk->sk_route_caps = dst->dev->features &
- ~(NETIF_F_IP_CSUM | NETIF_F_TSO);
+ if (dst->dev->features & NETIF_F_TSO6)
+ sk->sk_route_caps = dst->dev->features;
+ else
+ newsk->sk_route_caps = dst->dev->features &
+ ~(NETIF_F_IP_CSUM | NETIF_F_TSO);
newtcp6sk = (struct tcp6_sock *)newsk;
inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
