From 34d21de99cea9cb17967874313e5b0262527833c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 14 Nov 2023 01:42:14 +0100 Subject: net: Move {l,t,d}stats allocation to core and convert veth & vrf Move {l,t,d}stats allocation to the core and let netdevs pick the stats type they need. That way the driver doesn't have to bother with error handling (allocation failure checking, making sure free happens in the right spot, etc) - all happening in the core. Co-developed-by: Jakub Kicinski Signed-off-by: Jakub Kicinski Signed-off-by: Daniel Borkmann Reviewed-by: Nikolay Aleksandrov Cc: David Ahern Link: https://lore.kernel.org/r/20231114004220.6495-3-daniel@iogearbox.net Signed-off-by: Martin KaFai Lau --- net/core/dev.c | 49 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 48 insertions(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index af53f6d838ce..0cc6e283edba 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10051,6 +10051,46 @@ void netif_tx_stop_all_queues(struct net_device *dev) } EXPORT_SYMBOL(netif_tx_stop_all_queues); +static int netdev_do_alloc_pcpu_stats(struct net_device *dev) +{ + void __percpu *v; + + switch (dev->pcpu_stat_type) { + case NETDEV_PCPU_STAT_NONE: + return 0; + case NETDEV_PCPU_STAT_LSTATS: + v = dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); + break; + case NETDEV_PCPU_STAT_TSTATS: + v = dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + break; + case NETDEV_PCPU_STAT_DSTATS: + v = dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats); + break; + default: + return -EINVAL; + } + + return v ? 0 : -ENOMEM; +} + +static void netdev_do_free_pcpu_stats(struct net_device *dev) +{ + switch (dev->pcpu_stat_type) { + case NETDEV_PCPU_STAT_NONE: + return; + case NETDEV_PCPU_STAT_LSTATS: + free_percpu(dev->lstats); + break; + case NETDEV_PCPU_STAT_TSTATS: + free_percpu(dev->tstats); + break; + case NETDEV_PCPU_STAT_DSTATS: + free_percpu(dev->dstats); + break; + } +} + /** * register_netdevice() - register a network device * @dev: device to register @@ -10111,9 +10151,13 @@ int register_netdevice(struct net_device *dev) goto err_uninit; } + ret = netdev_do_alloc_pcpu_stats(dev); + if (ret) + goto err_uninit; + ret = dev_index_reserve(net, dev->ifindex); if (ret < 0) - goto err_uninit; + goto err_free_pcpu; dev->ifindex = ret; /* Transfer changeable features to wanted_features and enable @@ -10219,6 +10263,8 @@ err_uninit_notify: call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); err_ifindex_release: dev_index_release(net, dev->ifindex); +err_free_pcpu: + netdev_do_free_pcpu_stats(dev); err_uninit: if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); @@ -10471,6 +10517,7 @@ void netdev_run_todo(void) WARN_ON(rcu_access_pointer(dev->ip_ptr)); WARN_ON(rcu_access_pointer(dev->ip6_ptr)); + netdev_do_free_pcpu_stats(dev); if (dev->priv_destructor) dev->priv_destructor(dev); if (dev->needs_free_netdev) -- cgit v1.2.3 From 024ee930cb3c9ae49e4266aee89cfde0ebb407e1 Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Tue, 14 Nov 2023 01:42:17 +0100 Subject: 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 Signed-off-by: Peilin Ye Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann Reviewed-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20231114004220.6495-6-daniel@iogearbox.net Signed-off-by: Martin KaFai Lau --- net/core/dev.c | 8 ++++++++ net/core/filter.c | 1 + 2 files changed, 9 insertions(+) (limited to 'net/core') 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 ? -- cgit v1.2.3 From 2c225425704078282e152ba692649237f78b3d7a Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 14 Nov 2023 01:42:18 +0100 Subject: bpf, netkit: Add indirect call wrapper for fetching peer dev ndo_get_peer_dev is used in tcx BPF fast path, therefore make use of indirect call wrapper and therefore optimize the bpf_redirect_peer() internal handling a bit. Add a small skb_get_peer_dev() wrapper which utilizes the INDIRECT_CALL_1() macro instead of open coding. Future work could potentially add a peer pointer directly into struct net_device in future and convert veth and netkit over to use it so that eventually ndo_get_peer_dev can be removed. Co-developed-by: Nikolay Aleksandrov Signed-off-by: Nikolay Aleksandrov Signed-off-by: Daniel Borkmann Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20231114004220.6495-7-daniel@iogearbox.net Signed-off-by: Martin KaFai Lau --- net/core/filter.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'net/core') diff --git a/net/core/filter.c b/net/core/filter.c index cca810987c8d..7e4d7c3bcc84 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -81,6 +81,7 @@ #include #include #include +#include #include #include "dev.h" @@ -2468,6 +2469,16 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = { DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info); +static struct net_device *skb_get_peer_dev(struct net_device *dev) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (likely(ops->ndo_get_peer_dev)) + return INDIRECT_CALL_1(ops->ndo_get_peer_dev, + netkit_peer_dev, dev); + return NULL; +} + int skb_do_redirect(struct sk_buff *skb) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); @@ -2481,12 +2492,9 @@ int skb_do_redirect(struct sk_buff *skb) if (unlikely(!dev)) goto out_drop; if (flags & BPF_F_PEER) { - const struct net_device_ops *ops = dev->netdev_ops; - - if (unlikely(!ops->ndo_get_peer_dev || - !skb_at_tc_ingress(skb))) + if (unlikely(!skb_at_tc_ingress(skb))) goto out_drop; - dev = ops->ndo_get_peer_dev(dev); + dev = skb_get_peer_dev(dev); if (unlikely(!dev || !(dev->flags & IFF_UP) || net_eq(net, dev_net(dev)))) -- cgit v1.2.3