summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorPeilin Ye <peilin.ye@bytedance.com>2023-11-14 01:42:17 +0100
committerMartin KaFai Lau <martin.lau@kernel.org>2023-11-20 10:15:16 -0800
commit024ee930cb3c9ae49e4266aee89cfde0ebb407e1 (patch)
tree06be9235f5eaf8e273fdaf855b488b83effb846d /net
parent6f2684bf2b4460c84d0d34612a939f78b96b03fc (diff)
bpf: Fix dev's rx stats for bpf_redirect_peer traffic
Traffic redirected by bpf_redirect_peer() (used by recent CNIs like Cilium) is not accounted for in the RX stats of supported devices (that is, veth and netkit), confusing user space metrics collectors such as cAdvisor [0], as reported by Youlun. Fix it by calling dev_sw_netstats_rx_add() in skb_do_redirect(), to update RX traffic counters. Devices that support ndo_get_peer_dev _must_ use the @tstats per-CPU counters (instead of @lstats, or @dstats). To make this more fool-proof, error out when ndo_get_peer_dev is set but @tstats are not selected. [0] Specifically, the "container_network_receive_{byte,packet}s_total" counters are affected. Fixes: 9aa1206e8f48 ("bpf: Add redirect_peer helper") Reported-by: Youlun Zhang <zhangyoulun@bytedance.com> Signed-off-by: Peilin Ye <peilin.ye@bytedance.com> Co-developed-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org> Link: https://lore.kernel.org/r/20231114004220.6495-6-daniel@iogearbox.net Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Diffstat (limited to 'net')
-rw-r--r--net/core/dev.c8
-rw-r--r--net/core/filter.c1
2 files changed, 9 insertions, 0 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 0cc6e283edba..c879246be48d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10055,6 +10055,14 @@ static int netdev_do_alloc_pcpu_stats(struct net_device *dev)
{
void __percpu *v;
+ /* Drivers implementing ndo_get_peer_dev must support tstat
+ * accounting, so that skb_do_redirect() can bump the dev's
+ * RX stats upon network namespace switch.
+ */
+ if (dev->netdev_ops->ndo_get_peer_dev &&
+ dev->pcpu_stat_type != NETDEV_PCPU_STAT_TSTATS)
+ return -EOPNOTSUPP;
+
switch (dev->pcpu_stat_type) {
case NETDEV_PCPU_STAT_NONE:
return 0;
diff --git a/net/core/filter.c b/net/core/filter.c
index 383f96b0a1c7..cca810987c8d 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2492,6 +2492,7 @@ int skb_do_redirect(struct sk_buff *skb)
net_eq(net, dev_net(dev))))
goto out_drop;
skb->dev = dev;
+ dev_sw_netstats_rx_add(dev, skb->len);
return -EAGAIN;
}
return flags & BPF_F_NEIGH ?