| Message ID | 20230828113221.20123-2-sriram.yagnaraman@est.tech (mailing list archive) |
|---|---|
| State | Superseded |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | Avoid TCP resets when using ECMP for load-balancing between multiple servers. | expand |
On Mon, Aug 28, 2023 at 01:32:19PM +0200, Sriram Yagnaraman wrote: > Route hints when the nexthop is part of a multipath group causes packets > in the same receive batch to be sent to the same nexthop irrespective of > the multipath hash of the packet. So, do not extract route hint for > packets whose destination is part of a multipath group. > > A new SKB flag IPSKB_MULTIPATH is introduced for this purpose, set the > flag when route is looked up in ip_mkroute_input() and use it in > ip_extract_route_hint() to check for the existence of the flag. > > Fixes: 02b24941619f ("ipv4: use dst hint for ipv4 list receive") > Signed-off-by: Sriram Yagnaraman <sriram.yagnaraman@est.tech> Reviewed-by: Ido Schimmel <idosch@nvidia.com>
On 8/28/23 5:32 AM, Sriram Yagnaraman wrote: > Route hints when the nexthop is part of a multipath group causes packets > in the same receive batch to be sent to the same nexthop irrespective of > the multipath hash of the packet. So, do not extract route hint for > packets whose destination is part of a multipath group. > > A new SKB flag IPSKB_MULTIPATH is introduced for this purpose, set the > flag when route is looked up in ip_mkroute_input() and use it in > ip_extract_route_hint() to check for the existence of the flag. > > Fixes: 02b24941619f ("ipv4: use dst hint for ipv4 list receive") > Signed-off-by: Sriram Yagnaraman <sriram.yagnaraman@est.tech> > --- > include/net/ip.h | 1 + > net/ipv4/ip_input.c | 3 ++- > net/ipv4/route.c | 1 + > 3 files changed, 4 insertions(+), 1 deletion(-) > Reviewed-by: David Ahern <dsahern@kernel.org>
diff --git a/include/net/ip.h b/include/net/ip.h index 19adacd5ece0..464176a88f86 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -57,6 +57,7 @@ struct inet_skb_parm { #define IPSKB_FRAG_PMTU BIT(6) #define IPSKB_L3SLAVE BIT(7) #define IPSKB_NOPOLICY BIT(8) +#define IPSKB_MULTIPATH BIT(9) u16 frag_max_size; }; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index fe9ead9ee863..5e9c8156656a 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -584,7 +584,8 @@ static void ip_sublist_rcv_finish(struct list_head *head) static struct sk_buff *ip_extract_route_hint(const struct net *net, struct sk_buff *skb, int rt_type) { - if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST) + if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST || + IPCB(skb)->flags & IPSKB_MULTIPATH) return NULL; return skb; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 92fede388d52..33626619aee7 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2144,6 +2144,7 @@ static int ip_mkroute_input(struct sk_buff *skb, int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys); fib_select_multipath(res, h); + IPCB(skb)->flags |= IPSKB_MULTIPATH; } #endif
Route hints when the nexthop is part of a multipath group causes packets in the same receive batch to be sent to the same nexthop irrespective of the multipath hash of the packet. So, do not extract route hint for packets whose destination is part of a multipath group. A new SKB flag IPSKB_MULTIPATH is introduced for this purpose, set the flag when route is looked up in ip_mkroute_input() and use it in ip_extract_route_hint() to check for the existence of the flag. Fixes: 02b24941619f ("ipv4: use dst hint for ipv4 list receive") Signed-off-by: Sriram Yagnaraman <sriram.yagnaraman@est.tech> --- include/net/ip.h | 1 + net/ipv4/ip_input.c | 3 ++- net/ipv4/route.c | 1 + 3 files changed, 4 insertions(+), 1 deletion(-)