Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1572627
| From | Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | [PATCH 4.9 26/51] net: mpls: Fix multipath selection for LSR use case |
| Date | 2017-02-02 19:40 +0100 |
| Message-ID | <t6usB-7Bs-105@gated-at.bofh.it> (permalink) |
| References | <t6usx-7Bs-3@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
4.9-stable review patch. If anyone has any objections, please let me know.
------------------
From: David Ahern <dsa@cumulusnetworks.com>
[ 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")
Acked-by: Robert Shearman <rshearma@brocade.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
net/mpls/af_mpls.c | 48 +++++++++++++++++++++++++-----------------------
1 file changed, 25 insertions(+), 23 deletions(-)
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -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;
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
[PATCH 4.9 00/51] 4.9.8-stable review Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:40 +0100
[PATCH 4.9 35/51] xfs: adjust allocation length in xfs_alloc_space_available Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:40 +0100
[PATCH 4.9 36/51] xfs: dont rely on ->total in xfs_alloc_space_available Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:40 +0100
[PATCH 4.9 09/51] tcp: fix tcp_fastopen unaligned access complaints on sparc Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:40 +0100
[PATCH 4.9 05/51] mlxsw: pci: Fix EQE structure definition Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:40 +0100
[PATCH 4.9 04/51] mlxsw: switchx2: Fix memory leak at skb reallocation Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:40 +0100
[PATCH 4.9 03/51] mlxsw: spectrum: Fix memory leak at skb reallocation Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:40 +0100
[PATCH 4.9 26/51] net: mpls: Fix multipath selection for LSR use case Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:40 +0100
[PATCH 4.9 11/51] mlx4: do not call napi_schedule() without care Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 14/51] ax25: Fix segfault after sock connection timeout Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 47/51] xfs: verify dirblocklog correctly Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 43/51] xfs: sanity check inode di_mode Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 39/51] xfs: sanity check directory inode di_size Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 15/51] net sched actions: fix refcnt when GETing of action after bind Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 50/51] xfs: clear _XBF_PAGES from buffers when readahead page Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 22/51] ipv6: addrconf: Avoid addrconf_disable_change() using RCU read-side lock Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 31/51] lwtunnel: Fix oops on state free after encap module unload Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 23/51] tcp: initialize max window for a new fastopen socket Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 49/51] xfs: extsize hints are not unlikely in xfs_bmap_btalloc Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 24/51] net/mlx5e: Do not recycle pages from emergency reserve Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 08/51] net: systemport: Decouple flow control from __bcm_sysport_tx_reclaim Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 30/51] net: Specify the owning module for lwtunnel ops Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 20/51] net: phy: bcm63xx: Utilize correct config_intr function Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 27/51] r8152: dont execute runtime suspend if the tx is not empty Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 46/51] xfs: fix COW writeback race Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 44/51] xfs: dont wrap ID in xfs_dq_get_next_id Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 06/51] net: lwtunnel: Handle lwtunnel_fill_encap failure Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 42/51] xfs: sanity check inode mode when creating new dentry Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 32/51] net: dsa: Bring back device detaching in dsa_slave_suspend() Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 41/51] xfs: replace xfs_mode_to_ftype table with switch statement Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 10/51] openvswitch: maintain correct checksum state in conntrack actions Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 13/51] ip6_tunnel: Account for tunnel header in tunnel MTU Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 45/51] xfs: fix xfs_mode_to_ftype() prototype Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 28/51] af_unix: move unix_mknod() out of bindlock Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 25/51] bridge: netlink: call br_changelink() during br_dev_newlink() Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 34/51] xfs: fix bogus minleft manipulations Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 37/51] xfs: dont print warnings when xfs_log_force fails Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 48/51] xfs: remove racy hasattr check from attr ops Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 12/51] ravb: do not use zero-length alignment DMA descriptor Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 51/51] xfs: fix bmv_count confusion w/ shared extents Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 33/51] xfs: bump up reserved blocks in xfs_alloc_set_aside Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 19:50 +0100
[PATCH 4.9 02/51] netvsc: add rcu_read locking to netvsc callback Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 20:00 +0100
[PATCH 4.9 17/51] virtio-net: restore VIRTIO_HDR_F_DATA_VALID on receiving Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 20:00 +0100
[PATCH 4.9 07/51] net: ipv4: fix table id in getroute response Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 20:00 +0100
[PATCH 4.9 01/51] r8152: fix the sw rx checksum is unavailable Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 20:00 +0100
Re: [PATCH 4.9 00/51] 4.9.8-stable review Shuah Khan <shuahkh@osg.samsung.com> - 2017-02-02 21:40 +0100
Re: [PATCH 4.9 00/51] 4.9.8-stable review Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-02 22:00 +0100
Re: [PATCH 4.9 00/51] 4.9.8-stable review Guenter Roeck <linux@roeck-us.net> - 2017-02-03 06:20 +0100
Re: [PATCH 4.9 00/51] 4.9.8-stable review Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-02-03 08:20 +0100
csiph-web