From 6ebfad33161afacb3e1e59ed1c2feefef70f9f97 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 14 Mar 2024 14:18:16 +0000 Subject: packet: annotate data-races around ignore_outgoing ignore_outgoing is read locklessly from dev_queue_xmit_nit() and packet_getsockopt() Add appropriate READ_ONCE()/WRITE_ONCE() annotations. syzbot reported: BUG: KCSAN: data-race in dev_queue_xmit_nit / packet_setsockopt write to 0xffff888107804542 of 1 bytes by task 22618 on cpu 0: packet_setsockopt+0xd83/0xfd0 net/packet/af_packet.c:4003 do_sock_setsockopt net/socket.c:2311 [inline] __sys_setsockopt+0x1d8/0x250 net/socket.c:2334 __do_sys_setsockopt net/socket.c:2343 [inline] __se_sys_setsockopt net/socket.c:2340 [inline] __x64_sys_setsockopt+0x66/0x80 net/socket.c:2340 do_syscall_64+0xd3/0x1d0 entry_SYSCALL_64_after_hwframe+0x6d/0x75 read to 0xffff888107804542 of 1 bytes by task 27 on cpu 1: dev_queue_xmit_nit+0x82/0x620 net/core/dev.c:2248 xmit_one net/core/dev.c:3527 [inline] dev_hard_start_xmit+0xcc/0x3f0 net/core/dev.c:3547 __dev_queue_xmit+0xf24/0x1dd0 net/core/dev.c:4335 dev_queue_xmit include/linux/netdevice.h:3091 [inline] batadv_send_skb_packet+0x264/0x300 net/batman-adv/send.c:108 batadv_send_broadcast_skb+0x24/0x30 net/batman-adv/send.c:127 batadv_iv_ogm_send_to_if net/batman-adv/bat_iv_ogm.c:392 [inline] batadv_iv_ogm_emit net/batman-adv/bat_iv_ogm.c:420 [inline] batadv_iv_send_outstanding_bat_ogm_packet+0x3f0/0x4b0 net/batman-adv/bat_iv_ogm.c:1700 process_one_work kernel/workqueue.c:3254 [inline] process_scheduled_works+0x465/0x990 kernel/workqueue.c:3335 worker_thread+0x526/0x730 kernel/workqueue.c:3416 kthread+0x1d1/0x210 kernel/kthread.c:388 ret_from_fork+0x4b/0x60 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:243 value changed: 0x00 -> 0x01 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 27 Comm: kworker/u8:1 Tainted: G W 6.8.0-syzkaller-08073-g480e035fc4c7 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/29/2024 Workqueue: bat_events batadv_iv_send_outstanding_bat_ogm_packet Fixes: fa788d986a3a ("packet: add sockopt to ignore outgoing packets") Reported-by: syzbot+c669c1136495a2e7c31f@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/CANn89i+Z7MfbkBLOv=p7KZ7=K1rKHO4P1OL5LYDCtBiyqsa9oQ@mail.gmail.com/T/#t Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Reviewed-by: Willem de Bruijn Reviewed-by: Jason Xing Signed-off-by: David S. Miller --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 0766a245816b..722787c32755 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2245,7 +2245,7 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); again: list_for_each_entry_rcu(ptype, ptype_list, list) { - if (ptype->ignore_outgoing) + if (READ_ONCE(ptype->ignore_outgoing)) continue; /* Never send packets back to the socket -- cgit v1.2.3 From f6e0a4984c2e7244689ea87b62b433bed9d07e94 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 14 Mar 2024 20:08:45 +0000 Subject: net: move dev->state into net_device_read_txrx group dev->state can be read in rx and tx fast paths. netif_running() which needs dev->state is called from - enqueue_to_backlog() [RX path] - __dev_direct_xmit() [TX path] Fixes: 43a71cd66b9c ("net-device: reorganize net_device fast path variables") Signed-off-by: Eric Dumazet Cc: Coco Li Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20240314200845.3050179-1-edumazet@google.com Signed-off-by: Paolo Abeni --- Documentation/networking/net_cachelines/net_device.rst | 2 +- include/linux/netdevice.h | 2 +- net/core/dev.c | 3 ++- 3 files changed, 4 insertions(+), 3 deletions(-) (limited to 'net/core/dev.c') diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst index dceb49d56a91..70c4fb9d4e5c 100644 --- a/Documentation/networking/net_cachelines/net_device.rst +++ b/Documentation/networking/net_cachelines/net_device.rst @@ -13,7 +13,7 @@ struct_dev_ifalias* ifalias unsigned_long mem_end unsigned_long mem_start unsigned_long base_addr -unsigned_long state +unsigned_long state read_mostly read_mostly netif_running(dev) struct_list_head dev_list struct_list_head napi_list struct_list_head unreg_list diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c6f6ac779b34..cb37817d6382 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2072,6 +2072,7 @@ struct net_device { struct pcpu_sw_netstats __percpu *tstats; struct pcpu_dstats __percpu *dstats; }; + unsigned long state; unsigned int flags; unsigned short hard_header_len; netdev_features_t features; @@ -2117,7 +2118,6 @@ struct net_device { * part of the usual set specified in Space.c. */ - unsigned long state; struct list_head dev_list; struct list_head napi_list; diff --git a/net/core/dev.c b/net/core/dev.c index 722787c32755..303a6ff46e4e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -11665,11 +11665,12 @@ static void __init net_dev_struct_check(void) /* TXRX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, state); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr); - CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 38); + CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 46); /* RX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific); -- cgit v1.2.3 From d6dbbb11247c71203785a2c9da474c36f4b19eae Mon Sep 17 00:00:00 2001 From: Yan Zhai Date: Tue, 19 Mar 2024 13:44:37 -0700 Subject: net: report RCU QS on threaded NAPI repolling NAPI threads can keep polling packets under load. Currently it is only calling cond_resched() before repolling, but it is not sufficient to clear out the holdout of RCU tasks, which prevent BPF tracing programs from detaching for long period. This can be reproduced easily with following set up: ip netns add test1 ip netns add test2 ip -n test1 link add veth1 type veth peer name veth2 netns test2 ip -n test1 link set veth1 up ip -n test1 link set lo up ip -n test2 link set veth2 up ip -n test2 link set lo up ip -n test1 addr add 192.168.1.2/31 dev veth1 ip -n test1 addr add 1.1.1.1/32 dev lo ip -n test2 addr add 192.168.1.3/31 dev veth2 ip -n test2 addr add 2.2.2.2/31 dev lo ip -n test1 route add default via 192.168.1.3 ip -n test2 route add default via 192.168.1.2 for i in `seq 10 210`; do for j in `seq 10 210`; do ip netns exec test2 iptables -I INPUT -s 3.3.$i.$j -p udp --dport 5201 done done ip netns exec test2 ethtool -K veth2 gro on ip netns exec test2 bash -c 'echo 1 > /sys/class/net/veth2/threaded' ip netns exec test1 ethtool -K veth1 tso off Then run an iperf3 client/server and a bpftrace script can trigger it: ip netns exec test2 iperf3 -s -B 2.2.2.2 >/dev/null& ip netns exec test1 iperf3 -c 2.2.2.2 -B 1.1.1.1 -u -l 1500 -b 3g -t 100 >/dev/null& bpftrace -e 'kfunc:__napi_poll{@=count();} interval:s:1{exit();}' Report RCU quiescent states periodically will resolve the issue. Fixes: 29863d41bb6e ("net: implement threaded-able napi poll loop support") Reviewed-by: Jesper Dangaard Brouer Signed-off-by: Yan Zhai Acked-by: Paul E. McKenney Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/4c3b0d3f32d3b18949d75b18e5e1d9f13a24f025.1710877680.git.yan@cloudflare.com Signed-off-by: Jakub Kicinski --- net/core/dev.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 303a6ff46e4e..9a67003e49db 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6743,6 +6743,8 @@ static int napi_threaded_poll(void *data) void *have; while (!napi_thread_wait(napi)) { + unsigned long last_qs = jiffies; + for (;;) { bool repoll = false; @@ -6767,6 +6769,7 @@ static int napi_threaded_poll(void *data) if (!repoll) break; + rcu_softirq_qs_periodic(last_qs); cond_resched(); } } -- cgit v1.2.3