@@ -3363,25 +3363,19 @@ static int rtm_dump_nexthop_bucket_nh(struct sk_buff *skb,
dd->filter.res_bucket_nh_id != nhge->nh->id)
continue;
+ dd->ctx->bucket_index = bucket_index;
err = nh_fill_res_bucket(skb, nh, bucket, bucket_index,
RTM_NEWNEXTHOPBUCKET, portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
cb->extack);
- if (err < 0) {
- if (likely(skb->len))
- goto out;
- goto out_err;
- }
+ if (err)
+ return err;
}
dd->ctx->done_nh_idx = dd->ctx->nh.idx + 1;
- bucket_index = 0;
+ dd->ctx->bucket_index = 0;
-out:
- err = skb->len;
-out_err:
- dd->ctx->bucket_index = bucket_index;
- return err;
+ return 0;
}
static int rtm_dump_nexthop_bucket_cb(struct sk_buff *skb,
rtm_dump_nexthop_bucket_nh() is used to dump nexthop buckets belonging to a specific resilient nexthop group. The function returns a positive return code (the skb length) upon both success and failure. The above behavior is problematic. When a complete nexthop bucket dump is requested, the function that walks the different nexthops treats the non-zero return code as an error. This causes buckets belonging to different resilient nexthop groups to be dumped using different buffers even if they can all fit in the same buffer: # ip link add name dummy1 up type dummy # ip nexthop add id 1 dev dummy1 # ip nexthop add id 10 group 1 type resilient buckets 1 # ip nexthop add id 20 group 1 type resilient buckets 1 # strace -e recvmsg -s 0 ip nexthop bucket [...] recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[...], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 64 id 10 index 0 idle_time 10.27 nhid 1 [...] recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[...], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 64 id 20 index 0 idle_time 6.44 nhid 1 [...] Fix by only returning a non-zero return code when an error occurred and restarting the dump from the bucket index we failed to fill in. This allows buckets belonging to different resilient nexthop groups to be dumped using the same buffer: # ip link add name dummy1 up type dummy # ip nexthop add id 1 dev dummy1 # ip nexthop add id 10 group 1 type resilient buckets 1 # ip nexthop add id 20 group 1 type resilient buckets 1 # strace -e recvmsg -s 0 ip nexthop bucket [...] recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[...], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 128 id 10 index 0 idle_time 30.21 nhid 1 id 20 index 0 idle_time 26.7 nhid 1 [...] While this change is more of a performance improvement change than an actual bug fix, it is a prerequisite for a subsequent patch that does fix a bug. Fixes: 8a1bbabb034d ("nexthop: Add netlink handlers for bucket dump") Signed-off-by: Ido Schimmel <idosch@nvidia.com> Reviewed-by: Petr Machata <petrm@nvidia.com> --- net/ipv4/nexthop.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-)