Messages in this thread Patch in this message | | | From | Jon Maxwell <> | Subject | [net-next] ipv6: fix routing cache overflow for raw sockets | Date | Mon, 19 Dec 2022 10:48:01 +1100 |
| |
Sending Ipv6 packets in a loop via a raw socket triggers an issue where a route is cloned by ip6_rt_cache_alloc() for each packet sent. This quickly consumes the Ipv6 max_size threshold which defaults to 4096 resulting in these warnings:
[1] 99.187805] dst_alloc: 7728 callbacks suppressed [2] Route cache is full: consider increasing sysctl net.ipv6.route.max_size. . . [300] Route cache is full: consider increasing sysctl net.ipv6.route.max_size.
When this happens the packet is dropped and sendto() gets a network is unreachable error:
# ./a.out -s
remaining pkt 200557 errno 101 remaining pkt 196462 errno 101 . . remaining pkt 126821 errno 101
Fix this by adding a flag to prevent the cloning of routes for raw sockets. Which makes the Ipv6 routing code use per-cpu routes instead which prevents packet drop due to max_size overflow.
Ipv4 is not affected because it has a very large default max_size.
Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com> --- include/net/flow.h | 1 + net/ipv6/raw.c | 2 +- net/ipv6/route.c | 1 + 3 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/include/net/flow.h b/include/net/flow.h index 2f0da4f0318b..30b8973ffb4b 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -37,6 +37,7 @@ struct flowi_common { __u8 flowic_flags; #define FLOWI_FLAG_ANYSRC 0x01 #define FLOWI_FLAG_KNOWN_NH 0x02 +#define FLOWI_FLAG_SKIP_RAW 0x04 __u32 flowic_secid; kuid_t flowic_uid; struct flowi_tunnel flowic_tun_key; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index a06a9f847db5..0b89a7e66d09 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -884,7 +884,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); if (hdrincl) - fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH; + fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH | FLOWI_FLAG_SKIP_RAW; if (ipc6.tclass < 0) ipc6.tclass = np->tclass; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e74e0361fd92..beae0bd61738 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2226,6 +2226,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, if (rt) { goto out; } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) && + !(fl6->flowi6_flags & FLOWI_FLAG_SKIP_RAW) && !res.nh->fib_nh_gw_family)) { /* Create a RTF_CACHE clone which will not be * owned by the fib6 tree. It is for the special case where -- 2.31.1
| |