Messages in this thread Patch in this message | | | From | Felix Fietkau <> | Subject | [PATCH v2 net-next v2 4/4] net: add heuristic for enabling TCP fraglist GRO | Date | Thu, 25 Apr 2024 17:04:27 +0200 |
| |
When forwarding TCP after GRO, software segmentation is very expensive, especially when the checksum needs to be recalculated. One case where that's currently unavoidable is when routing packets over PPPoE. Performance improves significantly when using fraglist GRO implemented in the same way as for UDP.
When NETIF_F_GRO_FRAGLIST is enabled, perform a lookup for an established socket in the same netns as the receiving device. While this may not cover all relevant use cases in multi-netns configurations, it should be good enough for most configurations that need this.
Here's a measurement of running 2 TCP streams through a MediaTek MT7622 device (2-core Cortex-A53), which runs NAT with flow offload enabled from one ethernet port to PPPoE on another ethernet port + cake qdisc set to 1Gbps.
rx-gro-list off: 630 Mbit/s, CPU 35% idle rx-gro-list on: 770 Mbit/s, CPU 40% idle
Signe-off-by: Felix Fietkau <nbd@nbd.name> --- net/ipv4/tcp_offload.c | 56 ++++++++++++++++++++++++++++++++++++++ net/ipv6/tcpv6_offload.c | 59 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 115 insertions(+)
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 68157130c264..fc836ca084dd 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -396,6 +396,60 @@ void tcp_gro_complete(struct sk_buff *skb) } EXPORT_SYMBOL(tcp_gro_complete); +static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb) +{ + const struct iphdr *iph = skb_gro_network_header(skb); + struct net *net = dev_net(skb->dev); + unsigned int off, hlen, thlen; + struct tcphdr *th, *th2; + struct sk_buff *p; + struct sock *sk; + int iif, sdif; + + if (!(skb->dev->features & NETIF_F_GRO_FRAGLIST)) + return; + + off = skb_gro_offset(skb); + hlen = off + sizeof(*th); + th = skb_gro_header(skb, hlen, off); + if (unlikely(!th)) + return; + + thlen = th->doff * 4; + if (thlen < sizeof(*th)) + return; + + hlen = off + thlen; + if (!skb_gro_may_pull(skb, hlen)) { + th = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!th)) + return; + } + + list_for_each_entry(p, head, list) { + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + th2 = tcp_hdr(p); + if (*(u32 *)&th->source ^ *(u32 *)&th2->source) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + + NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + return; + } + + inet_get_iif_sdif(skb, &iif, &sdif); + sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, + iph->saddr, th->source, + iph->daddr, ntohs(th->dest), + iif, sdif); + NAPI_GRO_CB(skb)->is_flist = !sk; + if (sk) + sock_put(sk); +} + INDIRECT_CALLABLE_SCOPE struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb) { @@ -407,6 +461,8 @@ struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb) return NULL; } + tcp4_check_fraglist_gro(head, skb); + return tcp_gro_receive(head, skb); } diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index c97d55cf036f..dffeef080889 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -7,12 +7,69 @@ */ #include <linux/indirect_call_wrapper.h> #include <linux/skbuff.h> +#include <net/inet6_hashtables.h> #include <net/gro.h> #include <net/protocol.h> #include <net/tcp.h> #include <net/ip6_checksum.h> #include "ip6_offload.h" +static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_IPV6) + const struct ipv6hdr *hdr = skb_gro_network_header(skb); + struct net *net = dev_net(skb->dev); + unsigned int off, hlen, thlen; + struct tcphdr *th, *th2; + struct sk_buff *p; + struct sock *sk; + int iif, sdif; + + if (!(skb->dev->features & NETIF_F_GRO_FRAGLIST)) + return; + + off = skb_gro_offset(skb); + hlen = off + sizeof(*th); + th = skb_gro_header(skb, hlen, off); + if (unlikely(!th)) + return; + + thlen = th->doff * 4; + if (thlen < sizeof(*th)) + return; + + hlen = off + thlen; + if (!skb_gro_may_pull(skb, hlen)) { + th = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!th)) + return; + } + + list_for_each_entry(p, head, list) { + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + th2 = tcp_hdr(p); + if (*(u32 *)&th->source ^ *(u32 *)&th2->source) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + + NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + return; + } + + inet6_get_iif_sdif(skb, &iif, &sdif); + sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, + &hdr->saddr, th->source, + &hdr->daddr, ntohs(th->dest), + iif, sdif); + NAPI_GRO_CB(skb)->is_flist = !sk; + if (sk) + sock_put(sk); +#endif /* IS_ENABLED(CONFIG_IPV6) */ +} + INDIRECT_CALLABLE_SCOPE struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb) { @@ -24,6 +81,8 @@ struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb) return NULL; } + tcp6_check_fraglist_gro(head, skb); + return tcp_gro_receive(head, skb); } -- 2.44.0
| |