diff mbox series

[1/3] ipv4: ignore dst hint for multipath routes

Message ID 20230819114825.30867-2-sriram.yagnaraman@est.tech
State Superseded
Headers show
Series Avoid TCP resets when using ECMP for load-balancing between multiple servers. | expand

Commit Message

Sriram Yagnaraman Aug. 19, 2023, 11:48 a.m. UTC
Route hints when the next hop is part of a multipath group causes
packets in the same receive batch to the same next hop irrespective of
multipath hash of the packet. So, do not extract route hint for packets
whose destination is part of multipath group.

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(-)

Comments

Ido Schimmel Aug. 21, 2023, 11:39 a.m. UTC | #1
On Sat, Aug 19, 2023 at 01:48:23PM +0200, Sriram Yagnaraman wrote:
> Route hints when the next hop is part of a multipath group causes
> packets in the same receive batch to the same next hop irrespective of

Looks like you are missing a word here. "causes packets in the same
receive batch to the same next hop" ?

> multipath hash of the packet. So, do not extract route hint for packets
> whose destination is part of multipath group.

The commit message should also explain how this is done.

> 
> Fixes: 02b24941619f ("ipv4: use dst hint for ipv4 list receive")
> 

No blank line between the fixes tag and the SoB.

In addition, patch prefix should be "PATCH net". See:
https://www.kernel.org/doc/html/latest/process/maintainer-netdev.html

Same comments for the IPv6 patch.

Thanks

> Signed-off-by: Sriram Yagnaraman <sriram.yagnaraman@est.tech>
diff mbox series

Patch

diff --git a/include/net/ip.h b/include/net/ip.h
index 332521170d9b..bdce572fa422 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