Skip to contentSkip to conversation

Patch "net: mpls: Fix multipath selection for LSR use case" has been added to the 4.9-stable tree

PATCH [email protected] 1 participant 1 message Feb 1, 2017

Subsystems (2)
lore
Share & tools
lore

[email protected]

author maintainer Applied
#0 lore raw

This is a note to let you know that I've just added the patch titled

net: mpls: Fix multipath selection for LSR use case

to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
net-mpls-fix-multipath-selection-for-lsr-use-case.patch
and it can be found in the queue-4.9 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree, please let <[email protected]> know about it.

Quoted 1 line

From foo@baz Wed Feb 1 08:50:24 CET 2017

From: David Ahern <[email protected]>
Date: Fri, 20 Jan 2017 12:58:34 -0800
Subject: net: mpls: Fix multipath selection for LSR use case

From: David Ahern <[email protected]>

[ Upstream commit 9f427a0e474a67b454420c131709600d44850486 ]

MPLS multipath for LSR is broken -- always selecting the first nexthop in the one label case. For example:

    $ ip -f mpls ro ls
    100
            nexthop as to 200 via inet 172.16.2.2  dev virt12
            nexthop as to 300 via inet 172.16.3.2  dev virt13
    101
            nexthop as to 201 via inet6 2000:2::2  dev virt12
            nexthop as to 301 via inet6 2000:3::2  dev virt13

In this example incoming packets have a single MPLS labels which means BOS bit is set. The BOS bit is passed from mpls_forward down to mpls_multipath_hash which never processes the hash loop because BOS is 1.

Update mpls_multipath_hash to process the entire label stack. mpls_hdr_len tracks the total mpls header length on each pass (on pass N mpls_hdr_len is N * sizeof(mpls_shim_hdr)). When the label is found with the BOS set it verifies the skb has sufficient header for ipv4 or ipv6, and find the IPv4 and IPv6 header by using the last mpls_hdr pointer and adding 1 to advance past it.

With these changes I have verified the code correctly sees the label, BOS, IPv4 and IPv6 addresses in the network header and icmp/tcp/udp traffic for ipv4 and ipv6 are distributed across the nexthops.

Fixes 1c78efa8319ca ("mpls: flow-based multipath selection")
---
 net/mpls/af_mpls.c |   48 +++++++++++++++++++++++++-----------------------
 1 file changed, 25 insertions(+), 23 deletions(-)
net/mpls/af_mpls.c +25 -23
@@ -98,18 +98,19 @@ bool mpls_pkt_too_big(const struct sk_bu
 }
 EXPORT_SYMBOL_GPL(mpls_pkt_too_big);
 
-static u32 mpls_multipath_hash(struct mpls_route *rt,
-			       struct sk_buff *skb, bool bos)
+static u32 mpls_multipath_hash(struct mpls_route *rt, struct sk_buff *skb)
 {
 	struct mpls_entry_decoded dec;
+	unsigned int mpls_hdr_len = 0;
 	struct mpls_shim_hdr *hdr;
 	bool eli_seen = false;
 	int label_index;
 	u32 hash = 0;
 
-	for (label_index = 0; label_index < MAX_MP_SELECT_LABELS && !bos;
+	for (label_index = 0; label_index < MAX_MP_SELECT_LABELS;
 	     label_index++) {
-		if (!pskb_may_pull(skb, sizeof(*hdr) * label_index))
+		mpls_hdr_len += sizeof(*hdr);
+		if (!pskb_may_pull(skb, mpls_hdr_len))
 			break;
 
 		/* Read and decode the current label */
@@ -134,37 +135,38 @@ static u32 mpls_multipath_hash(struct mp
 			eli_seen = true;
 		}
 
-		bos = dec.bos;
-		if (bos && pskb_may_pull(skb, sizeof(*hdr) * label_index +
-					 sizeof(struct iphdr))) {
+		if (!dec.bos)
+			continue;
+
+		/* found bottom label; does skb have room for a header? */
+		if (pskb_may_pull(skb, mpls_hdr_len + sizeof(struct iphdr))) {
 			const struct iphdr *v4hdr;
 
-			v4hdr = (const struct iphdr *)(mpls_hdr(skb) +
-						       label_index);
+			v4hdr = (const struct iphdr *)(hdr + 1);
 			if (v4hdr->version == 4) {
 				hash = jhash_3words(ntohl(v4hdr->saddr),
 						    ntohl(v4hdr->daddr),
 						    v4hdr->protocol, hash);
 			} else if (v4hdr->version == 6 &&
-				pskb_may_pull(skb, sizeof(*hdr) * label_index +
-					      sizeof(struct ipv6hdr))) {
+				   pskb_may_pull(skb, mpls_hdr_len +
+						 sizeof(struct ipv6hdr))) {
 				const struct ipv6hdr *v6hdr;
 
-				v6hdr = (const struct ipv6hdr *)(mpls_hdr(skb) +
-								label_index);
-
+				v6hdr = (const struct ipv6hdr *)(hdr + 1);
 				hash = __ipv6_addr_jhash(&v6hdr->saddr, hash);
 				hash = __ipv6_addr_jhash(&v6hdr->daddr, hash);
 				hash = jhash_1word(v6hdr->nexthdr, hash);
 			}
 		}
+
+		break;
 	}
 
 	return hash;
 }
 
 static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
-					     struct sk_buff *skb, bool bos)
+					     struct sk_buff *skb)
 {
 	int alive = ACCESS_ONCE(rt->rt_nhn_alive);
 	u32 hash = 0;
@@ -180,7 +182,7 @@ static struct mpls_nh *mpls_select_multi
 	if (alive <= 0)
 		return NULL;
 
-	hash = mpls_multipath_hash(rt, skb, bos);
+	hash = mpls_multipath_hash(rt, skb);
 	nh_index = hash % alive;
 	if (alive == rt->rt_nhn)
 		goto out;
@@ -278,17 +280,11 @@ static int mpls_forward(struct sk_buff *
 	hdr = mpls_hdr(skb);
 	dec = mpls_entry_decode(hdr);
 
-	/* Pop the label */
-	skb_pull(skb, sizeof(*hdr));
-	skb_reset_network_header(skb);
-
-	skb_orphan(skb);
-
 	rt = mpls_route_input_rcu(net, dec.label);
 	if (!rt)
 		goto drop;
 
-	nh = mpls_select_multipath(rt, skb, dec.bos);
+	nh = mpls_select_multipath(rt, skb);
 	if (!nh)
 		goto drop;
 
@@ -297,6 +293,12 @@ static int mpls_forward(struct sk_buff *
 	if (!mpls_output_possible(out_dev))
 		goto drop;
 
+	/* Pop the label */
+	skb_pull(skb, sizeof(*hdr));
+	skb_reset_network_header(skb);
+
+	skb_orphan(skb);
+
 	if (skb_warn_if_lro(skb))
 		goto drop;
 

Patches currently in stable-queue which might be from [email protected] are

queue-4.9/net-lwtunnel-handle-lwtunnel_fill_encap-failure.patch queue-4.9/lwtunnel-fix-autoload-of-lwt-modules.patch queue-4.9/net-ipv4-fix-table-id-in-getroute-response.patch queue-4.9/net-mpls-fix-multipath-selection-for-lsr-use-case.patch