kernel.git/drivers/net/veth.c, branch linux-5.16.y

veth: fix races around rq->rx_notify_masked

2022-02-16T11:58:38Z

[ Upstream commit 68468d8c4cd4222a4ca1f185ab5a1c14480d078c ] veth being NETIF_F_LLTX enabled, we need to be more careful whenever we read/write rq->rx_notify_masked. BUG: KCSAN: data-race in veth_xmit / veth_xmit write to 0xffff888133d9a9f8 of 1 bytes by task 23552 on cpu 0: __veth_xdp_flush drivers/net/veth.c:269 [inline] veth_xmit+0x307/0x470 drivers/net/veth.c:350 __netdev_start_xmit include/linux/netdevice.h:4683 [inline] netdev_start_xmit include/linux/netdevice.h:4697 [inline] xmit_one+0x105/0x2f0 net/core/dev.c:3473 dev_hard_start_xmit net/core/dev.c:3489 [inline] __dev_queue_xmit+0x86d/0xf90 net/core/dev.c:4116 dev_queue_xmit+0x13/0x20 net/core/dev.c:4149 br_dev_queue_push_xmit+0x3ce/0x430 net/bridge/br_forward.c:53 NF_HOOK include/linux/netfilter.h:307 [inline] br_forward_finish net/bridge/br_forward.c:66 [inline] NF_HOOK include/linux/netfilter.h:307 [inline] __br_forward+0x2e4/0x400 net/bridge/br_forward.c:115 br_flood+0x521/0x5c0 net/bridge/br_forward.c:242 br_dev_xmit+0x8b6/0x960 __netdev_start_xmit include/linux/netdevice.h:4683 [inline] netdev_start_xmit include/linux/netdevice.h:4697 [inline] xmit_one+0x105/0x2f0 net/core/dev.c:3473 dev_hard_start_xmit net/core/dev.c:3489 [inline] __dev_queue_xmit+0x86d/0xf90 net/core/dev.c:4116 dev_queue_xmit+0x13/0x20 net/core/dev.c:4149 neigh_hh_output include/net/neighbour.h:525 [inline] neigh_output include/net/neighbour.h:539 [inline] ip_finish_output2+0x6f8/0xb70 net/ipv4/ip_output.c:228 ip_finish_output+0xfb/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:296 [inline] ip_output+0xf3/0x1a0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:451 [inline] ip_local_out net/ipv4/ip_output.c:126 [inline] ip_send_skb+0x6e/0xe0 net/ipv4/ip_output.c:1570 udp_send_skb+0x641/0x880 net/ipv4/udp.c:967 udp_sendmsg+0x12ea/0x14c0 net/ipv4/udp.c:1254 inet_sendmsg+0x5f/0x80 net/ipv4/af_inet.c:819 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmmsg+0x267/0x4c0 net/socket.c:2553 __do_sys_sendmmsg net/socket.c:2582 [inline] __se_sys_sendmmsg net/socket.c:2579 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2579 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888133d9a9f8 of 1 bytes by task 23563 on cpu 1: __veth_xdp_flush drivers/net/veth.c:268 [inline] veth_xmit+0x2d6/0x470 drivers/net/veth.c:350 __netdev_start_xmit include/linux/netdevice.h:4683 [inline] netdev_start_xmit include/linux/netdevice.h:4697 [inline] xmit_one+0x105/0x2f0 net/core/dev.c:3473 dev_hard_start_xmit net/core/dev.c:3489 [inline] __dev_queue_xmit+0x86d/0xf90 net/core/dev.c:4116 dev_queue_xmit+0x13/0x20 net/core/dev.c:4149 br_dev_queue_push_xmit+0x3ce/0x430 net/bridge/br_forward.c:53 NF_HOOK include/linux/netfilter.h:307 [inline] br_forward_finish net/bridge/br_forward.c:66 [inline] NF_HOOK include/linux/netfilter.h:307 [inline] __br_forward+0x2e4/0x400 net/bridge/br_forward.c:115 br_flood+0x521/0x5c0 net/bridge/br_forward.c:242 br_dev_xmit+0x8b6/0x960 __netdev_start_xmit include/linux/netdevice.h:4683 [inline] netdev_start_xmit include/linux/netdevice.h:4697 [inline] xmit_one+0x105/0x2f0 net/core/dev.c:3473 dev_hard_start_xmit net/core/dev.c:3489 [inline] __dev_queue_xmit+0x86d/0xf90 net/core/dev.c:4116 dev_queue_xmit+0x13/0x20 net/core/dev.c:4149 neigh_hh_output include/net/neighbour.h:525 [inline] neigh_output include/net/neighbour.h:539 [inline] ip_finish_output2+0x6f8/0xb70 net/ipv4/ip_output.c:228 ip_finish_output+0xfb/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:296 [inline] ip_output+0xf3/0x1a0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:451 [inline] ip_local_out net/ipv4/ip_output.c:126 [inline] ip_send_skb+0x6e/0xe0 net/ipv4/ip_output.c:1570 udp_send_skb+0x641/0x880 net/ipv4/udp.c:967 udp_sendmsg+0x12ea/0x14c0 net/ipv4/udp.c:1254 inet_sendmsg+0x5f/0x80 net/ipv4/af_inet.c:819 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmmsg+0x267/0x4c0 net/socket.c:2553 __do_sys_sendmmsg net/socket.c:2582 [inline] __se_sys_sendmmsg net/socket.c:2579 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2579 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x00 -> 0x01 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 23563 Comm: syz-executor.5 Not tainted 5.17.0-rc2-syzkaller-00064-gc36c04c2e132 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 948d4f214fde ("veth: Add driver XDP") Signed-off-by: Eric Dumazet Cc: Toshiaki Makita Reported-by: syzbot Signed-off-by: David S. Miller Signed-off-by: Sasha Levin

veth: Do not record rx queue hint in veth_xmit

2022-01-16T08:11:13Z

commit 710ad98c363a66a0cd8526465426c5c5f8377ee0 upstream. Laurent reported that they have seen a significant amount of TCP retransmissions at high throughput from applications residing in network namespaces talking to the outside world via veths. The drops were seen on the qdisc layer (fq_codel, as per systemd default) of the phys device such as ena or virtio_net due to all traffic hitting a _single_ TX queue _despite_ multi-queue device. (Note that the setup was _not_ using XDP on veths as the issue is generic.) More specifically, after edbea9220251 ("veth: Store queue_mapping independently of XDP prog presence") which made it all the way back to v4.19.184+, skb_record_rx_queue() would set skb->queue_mapping to 1 (given 1 RX and 1 TX queue by default for veths) instead of leaving at 0. This is eventually retained and callbacks like ena_select_queue() will also pick single queue via netdev_core_pick_tx()'s ndo_select_queue() once all the traffic is forwarded to that device via upper stack or other means. Similarly, for others not implementing ndo_select_queue() if XPS is disabled, netdev_pick_tx() might call into the skb_tx_hash() and check for prior skb_rx_queue_recorded() as well. In general, it is a _bad_ idea for virtual devices like veth to mess around with queue selection [by default]. Given dev->real_num_tx_queues is by default 1, the skb->queue_mapping was left untouched, and so prior to edbea9220251 the netdev_core_pick_tx() could do its job upon __dev_queue_xmit() on the phys device. Unbreak this and restore prior behavior by removing the skb_record_rx_queue() from veth_xmit() altogether. If the veth peer has an XDP program attached, then it would return the first RX queue index in xdp_md->rx_queue_index (unless configured in non-default manner). However, this is still better than breaking the generic case. Fixes: edbea9220251 ("veth: Store queue_mapping independently of XDP prog presence") Fixes: 638264dc9022 ("veth: Support per queue XDP ring") Reported-by: Laurent Bernaille Signed-off-by: Daniel Borkmann Cc: Maciej Fijalkowski Cc: Toshiaki Makita Cc: Eric Dumazet Cc: Paolo Abeni Cc: John Fastabend Cc: Willem de Bruijn Acked-by: John Fastabend Reviewed-by: Eric Dumazet Acked-by: Toshiaki Makita Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman

veth: ensure skb entering GRO are not cloned.

2021-12-23T17:44:06Z

After commit d3256efd8e8b ("veth: allow enabling NAPI even without XDP"), if GRO is enabled on a veth device and TSO is disabled on the peer device, TCP skbs will go through the NAPI callback. If there is no XDP program attached, the veth code does not perform any share check, and shared/cloned skbs could enter the GRO engine. Ignat reported a BUG triggered later-on due to the above condition: [ 53.970529][ C1] kernel BUG at net/core/skbuff.c:3574! [ 53.981755][ C1] invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI [ 53.982634][ C1] CPU: 1 PID: 19 Comm: ksoftirqd/1 Not tainted 5.16.0-rc5+ #25 [ 53.982634][ C1] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 [ 53.982634][ C1] RIP: 0010:skb_shift+0x13ef/0x23b0 [ 53.982634][ C1] Code: ea 03 0f b6 04 02 48 89 fa 83 e2 07 38 d0 7f 08 84 c0 0f 85 41 0c 00 00 41 80 7f 02 00 4d 8d b5 d0 00 00 00 0f 85 74 f5 ff ff <0f> 0b 4d 8d 77 20 be 04 00 00 00 4c 89 44 24 78 4c 89 f7 4c 89 8c [ 53.982634][ C1] RSP: 0018:ffff8881008f7008 EFLAGS: 00010246 [ 53.982634][ C1] RAX: 0000000000000000 RBX: ffff8881180b4c80 RCX: 0000000000000000 [ 53.982634][ C1] RDX: 0000000000000002 RSI: ffff8881180b4d3c RDI: ffff88810bc9cac2 [ 53.982634][ C1] RBP: ffff8881008f70b8 R08: ffff8881180b4cf4 R09: ffff8881180b4cf0 [ 53.982634][ C1] R10: ffffed1022999e5c R11: 0000000000000002 R12: 0000000000000590 [ 53.982634][ C1] R13: ffff88810f940c80 R14: ffff88810f940d50 R15: ffff88810bc9cac0 [ 53.982634][ C1] FS: 0000000000000000(0000) GS:ffff888235880000(0000) knlGS:0000000000000000 [ 53.982634][ C1] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 53.982634][ C1] CR2: 00007ff5f9b86680 CR3: 0000000108ce8004 CR4: 0000000000170ee0 [ 53.982634][ C1] Call Trace: [ 53.982634][ C1] [ 53.982634][ C1] tcp_sacktag_walk+0xaba/0x18e0 [ 53.982634][ C1] tcp_sacktag_write_queue+0xe7b/0x3460 [ 53.982634][ C1] tcp_ack+0x2666/0x54b0 [ 53.982634][ C1] tcp_rcv_established+0x4d9/0x20f0 [ 53.982634][ C1] tcp_v4_do_rcv+0x551/0x810 [ 53.982634][ C1] tcp_v4_rcv+0x22ed/0x2ed0 [ 53.982634][ C1] ip_protocol_deliver_rcu+0x96/0xaf0 [ 53.982634][ C1] ip_local_deliver_finish+0x1e0/0x2f0 [ 53.982634][ C1] ip_sublist_rcv_finish+0x211/0x440 [ 53.982634][ C1] ip_list_rcv_finish.constprop.0+0x424/0x660 [ 53.982634][ C1] ip_list_rcv+0x2c8/0x410 [ 53.982634][ C1] __netif_receive_skb_list_core+0x65c/0x910 [ 53.982634][ C1] netif_receive_skb_list_internal+0x5f9/0xcb0 [ 53.982634][ C1] napi_complete_done+0x188/0x6e0 [ 53.982634][ C1] gro_cell_poll+0x10c/0x1d0 [ 53.982634][ C1] __napi_poll+0xa1/0x530 [ 53.982634][ C1] net_rx_action+0x567/0x1270 [ 53.982634][ C1] __do_softirq+0x28a/0x9ba [ 53.982634][ C1] run_ksoftirqd+0x32/0x60 [ 53.982634][ C1] smpboot_thread_fn+0x559/0x8c0 [ 53.982634][ C1] kthread+0x3b9/0x490 [ 53.982634][ C1] ret_from_fork+0x22/0x30 [ 53.982634][ C1] Address the issue by skipping the GRO stage for shared or cloned skbs. To reduce the chance of OoO, try to unclone the skbs before giving up. v1 -> v2: - use avoid skb_copy and fallback to netif_receive_skb - Eric Reported-by: Ignat Korchagin Fixes: d3256efd8e8b ("veth: allow enabling NAPI even without XDP") Signed-off-by: Paolo Abeni Tested-by: Ignat Korchagin Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/b5f61c5602aab01bac8d711d8d1bfab0a4817db7.1640197544.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski

veth: use skb_prepare_for_gro()

2021-07-29T11:18:12Z

Leveraging the previous patch we can now avoid orphaning the skb in the veth gro path, allowing correct backpressure. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller

veth: create by default nr_possible_cpus queues

2021-07-20T13:11:18Z

This allows easier XDP usage. The number of default active queues is not changed: 1 RX and 1 TX so that this does not introduce overhead on the datapath for queue selection. v1 -> v2: - drop the module parameter, force default to nr_possible_cpus - Toke Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller

veth: implement support for set_channel ethtool op

2021-07-20T13:11:18Z

This change implements the set_channel() ethtool operation, preserving the current defaults values and allowing up set the number of queues in the range set ad device creation time. The update operation tries hard to leave the device in a consistent status in case of errors. RFC v1 -> RFC v2: - don't flip device status on set_channel() - roll-back the changes if possible on error - Jackub Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller

veth: factor out initialization helper

2021-07-20T13:11:18Z

Extract in simpler helpers the code to enable and disable a range of xdp/napi instance, with the common property that "disable" helpers can't fail. Will be used by the next patch. No functional change intended. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller

veth: always report zero combined channels

2021-07-20T13:11:18Z

veth get_channel currently reports for channels being both RX/TX and combined. As Jakub noted: """ ethtool man page is relatively clear, unfortunately the kernel code is not and few read the man page. A channel is approximately an IRQ, not a queue, and IRQ can't be dedicated and combined simultaneously """ This patch changes the information exposed by veth_get_channels, setting max_combined to zero, being more consistent with the above statement. The ethtool_channels is always cleared by the caller, we just need to avoid setting the 'combined' fields. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller

veth: check for NAPI instead of xdp_prog before xmit of XDP frame

2021-04-16T22:42:07Z

The recent patch that tied enabling of veth NAPI to the GRO flag also has the nice side effect that a veth device can be the target of an XDP_REDIRECT without an XDP program needing to be loaded on the peer device. However, the patch adding this extra NAPI mode didn't actually change the check in veth_xdp_xmit() to also look at the new NAPI pointer, so let's fix that. Fixes: 6788fa154546 ("veth: allow enabling NAPI even without XDP") Signed-off-by: Toke Høiland-Jørgensen Acked-by: Jesper Dangaard Brouer Acked-by: Paolo Abeni Signed-off-by: David S. Miller

veth: refine napi usage

2021-04-11T23:39:28Z

After the previous patch, when enabling GRO, locally generated TCP traffic experiences some measurable overhead, as it traverses the GRO engine without any chance of aggregation. This change refine the NAPI receive path admission test, to avoid unnecessary GRO overhead in most scenarios, when GRO is enabled on a veth peer. Only skbs that are eligible for aggregation enter the GRO layer, the others will go through the traditional receive path. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller