kernel/git/stable/linux.git/drivers/net/veth.c, branch linux-6.7.y

net: veth: do not manipulate GRO when using XDP

2024-03-26T22:18:56+00:00

[ Upstream commit d7db7775ea2e31502d46427f5efd385afc4ff1eb ] Commit d3256efd8e8b ("veth: allow enabling NAPI even without XDP") tried to fix the fact that GRO was not possible without XDP, because veth did not use NAPI without XDP. However, it also introduced the behaviour that GRO is always enabled, when XDP is enabled. While it might be desired for most cases, it is confusing for the user at best as the GRO flag suddenly changes, when an XDP program is attached. It also introduces some complexities in state management as was partially addressed in commit fe9f801355f0 ("net: veth: clear GRO when clearing XDP even when down"). But the biggest problem is that it is not possible to disable GRO at all, when an XDP program is attached, which might be needed for some use cases. Fix this by not touching the GRO flag on XDP enable/disable as the code already supports switching to NAPI if either GRO or XDP is requested. Link: https://lore.kernel.org/lkml/20240311124015.38106-1-ignat@cloudflare.com/ Fixes: d3256efd8e8b ("veth: allow enabling NAPI even without XDP") Fixes: fe9f801355f0 ("net: veth: clear GRO when clearing XDP even when down") Signed-off-by: Ignat Korchagin Reviewed-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller Signed-off-by: Sasha Levin

veth: try harder when allocating queue memory

2024-03-06T14:53:50+00:00

[ Upstream commit 1ce7d306ea63f3e379557c79abd88052e0483813 ] struct veth_rq is pretty large, 832B total without debug options enabled. Since commit under Fixes we try to pre-allocate enough queues for every possible CPU. Miao Wang reports that this may lead to order-5 allocations which will fail in production. Let the allocation fallback to vmalloc() and try harder. These are the same flags we pass to netdev queue allocation. Reported-and-tested-by: Miao Wang Fixes: 9d3684c24a52 ("veth: create by default nr_possible_cpus queues") Link: https://lore.kernel.org/all/5F52CAE2-2FB7-4712-95F1-3312FBBFA8DD@gmail.com/ Signed-off-by: Jakub Kicinski Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20240223235908.693010-1-kuba@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin

net: veth: clear GRO when clearing XDP even when down

2024-03-06T14:53:49+00:00

[ Upstream commit fe9f801355f0b47668419f30f1fac1cf4539e736 ] veth sets NETIF_F_GRO automatically when XDP is enabled, because both features use the same NAPI machinery. The logic to clear NETIF_F_GRO sits in veth_disable_xdp() which is called both on ndo_stop and when XDP is turned off. To avoid the flag from being cleared when the device is brought down, the clearing is skipped when IFF_UP is not set. Bringing the device down should indeed not modify its features. Unfortunately, this means that clearing is also skipped when XDP is disabled _while_ the device is down. And there's nothing on the open path to bring the device features back into sync. IOW if user enables XDP, disables it and then brings the device up we'll end up with a stray GRO flag set but no NAPI instances. We don't depend on the GRO flag on the datapath, so the datapath won't crash. We will crash (or hang), however, next time features are sync'ed (either by user via ethtool or peer changing its config). The GRO flag will go away, and veth will try to disable the NAPIs. But the open path never created them since XDP was off, the GRO flag was a stray. If NAPI was initialized before we'll hang in napi_disable(). If it never was we'll crash trying to stop uninitialized hrtimer. Move the GRO flag updates to the XDP enable / disable paths, instead of mixing them with the ndo_open / ndo_close paths. Fixes: d3256efd8e8b ("veth: allow enabling NAPI even without XDP") Reported-by: Thomas Gleixner Reported-by: syzbot+039399a9b96297ddedca@syzkaller.appspotmail.com Signed-off-by: Jakub Kicinski Reviewed-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller Signed-off-by: Sasha Levin

net: veth: fix packet segmentation in veth_convert_skb_to_xdp_buff

2023-12-06T03:24:26+00:00

Based on the previous allocated packet, page_offset can be not null in veth_convert_skb_to_xdp_buff routine. Take into account page fragment offset during the skb paged area copy in veth_convert_skb_to_xdp_buff(). Fixes: 2d0de67da51a ("net: veth: use newly added page pool API for veth with xdp") Signed-off-by: Lorenzo Bianconi Reviewed-by: Yunsheng Lin Link: https://lore.kernel.org/r/eddfe549e7e626870071930964ac3c38a1dc8068.1701702000.git.lorenzo@kernel.org Signed-off-by: Jakub Kicinski

net: veth: fix ethtool stats reporting

2023-11-23T12:23:59+00:00

Fix a possible misalignment between page_pool stats and tx xdp_stats reported in veth_get_ethtool_stats routine. The issue can be reproduced configuring the veth pair with the following tx/rx queues: $ip link add v0 numtxqueues 2 numrxqueues 4 type veth peer name v1 \ numtxqueues 1 numrxqueues 1 and loading a simple XDP program on v0 that just returns XDP_PASS. In this case on v0 the page_pool stats overwrites tx xdp_stats for queue 1. Fix the issue incrementing pp_idx of dev->real_num_tx_queues * VETH_TQ_STATS_LEN since we always report xdp_stats for all tx queues in ethtool. Fixes: 4fc418053ec7 ("net: veth: add page_pool stats") Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/c5b5d0485016836448453f12846c7c4ab75b094a.1700593593.git.lorenzo@kernel.org Signed-off-by: Paolo Abeni

veth: Use tstats per-CPU traffic counters

2023-11-20T18:15:16+00:00

Currently veth devices use the lstats per-CPU traffic counters, which only cover TX traffic. veth_get_stats64() actually populates RX stats of a veth device from its peer's TX counters, based on the assumption that a veth device can _only_ receive packets from its peer, which is no longer true: For example, recent CNIs (like Cilium) can use the bpf_redirect_peer() BPF helper to redirect traffic from NIC's tc ingress to veth's tc ingress (in a different netns), skipping veth's peer device. Unfortunately, this kind of traffic isn't currently accounted for in veth's RX stats. In preparation for the fix, use tstats (instead of lstats) to maintain both RX and TX counters for each veth device. We'll use RX counters for bpf_redirect_peer() traffic, and keep using TX counters for the usual "peer-to-peer" traffic. In veth_get_stats64(), calculate RX stats by _adding_ RX count to peer's TX count, in order to cover both kinds of traffic. veth_stats_rx() might need a name change (perhaps to "veth_stats_xdp()") for less confusion, but let's leave it to another patch to keep the fix minimal. 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/20231114004220.6495-5-daniel@iogearbox.net Signed-off-by: Martin KaFai Lau

net: Move {l,t,d}stats allocation to core and convert veth & vrf

2023-11-20T18:15:16+00:00

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: veth: use newly added page pool API for veth with xdp

2023-10-24T02:14:49+00:00

Use page_pool_alloc() API to allocate memory with least memory utilization and performance penalty. Signed-off-by: Yunsheng Lin CC: Lorenzo Bianconi CC: Alexander Duyck CC: Liang Chen CC: Alexander Lobakin Link: https://lore.kernel.org/r/20231020095952.11055-6-linyunsheng@huawei.com Signed-off-by: Jakub Kicinski

veth: Update XDP feature set when bringing up device

2023-09-12T14:32:56+00:00

There's an early return in veth_set_features() if the device is in a down state, which leads to the XDP feature flags not being updated when enabling GRO while the device is down. Which in turn leads to XDP_REDIRECT not working, because the redirect code now checks the flags. Fix this by updating the feature flags after bringing the device up. Before this patch: NETDEV_XDP_ACT_BASIC: yes NETDEV_XDP_ACT_REDIRECT: yes NETDEV_XDP_ACT_NDO_XMIT: no NETDEV_XDP_ACT_XSK_ZEROCOPY: no NETDEV_XDP_ACT_HW_OFFLOAD: no NETDEV_XDP_ACT_RX_SG: yes NETDEV_XDP_ACT_NDO_XMIT_SG: no After this patch: NETDEV_XDP_ACT_BASIC: yes NETDEV_XDP_ACT_REDIRECT: yes NETDEV_XDP_ACT_NDO_XMIT: yes NETDEV_XDP_ACT_XSK_ZEROCOPY: no NETDEV_XDP_ACT_HW_OFFLOAD: no NETDEV_XDP_ACT_RX_SG: yes NETDEV_XDP_ACT_NDO_XMIT_SG: yes Fixes: fccca038f300 ("veth: take into account device reconfiguration for xdp_features flag") Fixes: 66c0e13ad236 ("drivers: net: turn on XDP features") Signed-off-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20230911135826.722295-1-toke@redhat.com Signed-off-by: Paolo Abeni

veth: Fixing transmit return status for dropped packets

2023-09-04T05:52:39+00:00

The veth_xmit function returns NETDEV_TX_OK even when packets are dropped. This behavior leads to incorrect calculations of statistics counts, as well as things like txq->trans_start updates. Fixes: e314dbdc1c0d ("[NET]: Virtual ethernet device driver.") Signed-off-by: Liang Chen Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller