From 9840036786d90cea11a90d1f30b6dc003b34ee67 Mon Sep 17 00:00:00 2001 From: Yan Zhai Date: Thu, 13 Jul 2023 10:28:00 -0700 Subject: gso: fix dodgy bit handling for GSO_UDP_L4 Commit 1fd54773c267 ("udp: allow header check for dodgy GSO_UDP_L4 packets.") checks DODGY bit for UDP, but for packets that can be fed directly to the device after gso_segs reset, it actually falls through to fragmentation: https://lore.kernel.org/all/CAJPywTKDdjtwkLVUW6LRA2FU912qcDmQOQGt2WaDo28KzYDg+A@mail.gmail.com/ This change restores the expected behavior of GSO_UDP_L4 packets. Fixes: 1fd54773c267 ("udp: allow header check for dodgy GSO_UDP_L4 packets.") Suggested-by: Willem de Bruijn Signed-off-by: Yan Zhai Reviewed-by: Willem de Bruijn Acked-by: Jason Wang Signed-off-by: David S. Miller --- net/ipv4/udp_offload.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 75aa4de5b731..f402946da344 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -274,13 +274,20 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, __sum16 check; __be16 newlen; - if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) - return __udp_gso_segment_list(gso_skb, features, is_ipv6); - mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); + if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { + /* Packet is from an untrusted source, reset gso_segs. */ + skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), + mss); + return NULL; + } + + if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) + return __udp_gso_segment_list(gso_skb, features, is_ipv6); + skb_pull(gso_skb, sizeof(*uh)); /* clear destructor to avoid skb_segment assigning it to tail */ @@ -388,8 +395,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && - !skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, false); mss = skb_shinfo(skb)->gso_size; -- cgit v1.2.3 From 5e5265522a9a7f91d1b0bd411d634bdaf16c80cd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 17 Jul 2023 14:44:44 +0000 Subject: tcp: annotate data-races around tcp_rsk(req)->txhash TCP request sockets are lockless, some of their fields can change while being read by another cpu as syzbot noticed. This is usually harmless, but we should annotate the known races. This patch takes care of tcp_rsk(req)->txhash, a separate one is needed for tcp_rsk(req)->ts_recent. BUG: KCSAN: data-race in tcp_make_synack / tcp_rtx_synack write to 0xffff8881362304bc of 4 bytes by task 32083 on cpu 1: tcp_rtx_synack+0x9d/0x2a0 net/ipv4/tcp_output.c:4213 inet_rtx_syn_ack+0x38/0x80 net/ipv4/inet_connection_sock.c:880 tcp_check_req+0x379/0xc70 net/ipv4/tcp_minisocks.c:665 tcp_v6_rcv+0x125b/0x1b20 net/ipv6/tcp_ipv6.c:1673 ip6_protocol_deliver_rcu+0x92f/0xf30 net/ipv6/ip6_input.c:437 ip6_input_finish net/ipv6/ip6_input.c:482 [inline] NF_HOOK include/linux/netfilter.h:303 [inline] ip6_input+0xbd/0x1b0 net/ipv6/ip6_input.c:491 dst_input include/net/dst.h:468 [inline] ip6_rcv_finish+0x1e2/0x2e0 net/ipv6/ip6_input.c:79 NF_HOOK include/linux/netfilter.h:303 [inline] ipv6_rcv+0x74/0x150 net/ipv6/ip6_input.c:309 __netif_receive_skb_one_core net/core/dev.c:5452 [inline] __netif_receive_skb+0x90/0x1b0 net/core/dev.c:5566 netif_receive_skb_internal net/core/dev.c:5652 [inline] netif_receive_skb+0x4a/0x310 net/core/dev.c:5711 tun_rx_batched+0x3bf/0x400 tun_get_user+0x1d24/0x22b0 drivers/net/tun.c:1997 tun_chr_write_iter+0x18e/0x240 drivers/net/tun.c:2043 call_write_iter include/linux/fs.h:1871 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x4ab/0x7d0 fs/read_write.c:584 ksys_write+0xeb/0x1a0 fs/read_write.c:637 __do_sys_write fs/read_write.c:649 [inline] __se_sys_write fs/read_write.c:646 [inline] __x64_sys_write+0x42/0x50 fs/read_write.c:646 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff8881362304bc of 4 bytes by task 32078 on cpu 0: tcp_make_synack+0x367/0xb40 net/ipv4/tcp_output.c:3663 tcp_v6_send_synack+0x72/0x420 net/ipv6/tcp_ipv6.c:544 tcp_conn_request+0x11a8/0x1560 net/ipv4/tcp_input.c:7059 tcp_v6_conn_request+0x13f/0x180 net/ipv6/tcp_ipv6.c:1175 tcp_rcv_state_process+0x156/0x1de0 net/ipv4/tcp_input.c:6494 tcp_v6_do_rcv+0x98a/0xb70 net/ipv6/tcp_ipv6.c:1509 tcp_v6_rcv+0x17b8/0x1b20 net/ipv6/tcp_ipv6.c:1735 ip6_protocol_deliver_rcu+0x92f/0xf30 net/ipv6/ip6_input.c:437 ip6_input_finish net/ipv6/ip6_input.c:482 [inline] NF_HOOK include/linux/netfilter.h:303 [inline] ip6_input+0xbd/0x1b0 net/ipv6/ip6_input.c:491 dst_input include/net/dst.h:468 [inline] ip6_rcv_finish+0x1e2/0x2e0 net/ipv6/ip6_input.c:79 NF_HOOK include/linux/netfilter.h:303 [inline] ipv6_rcv+0x74/0x150 net/ipv6/ip6_input.c:309 __netif_receive_skb_one_core net/core/dev.c:5452 [inline] __netif_receive_skb+0x90/0x1b0 net/core/dev.c:5566 netif_receive_skb_internal net/core/dev.c:5652 [inline] netif_receive_skb+0x4a/0x310 net/core/dev.c:5711 tun_rx_batched+0x3bf/0x400 tun_get_user+0x1d24/0x22b0 drivers/net/tun.c:1997 tun_chr_write_iter+0x18e/0x240 drivers/net/tun.c:2043 call_write_iter include/linux/fs.h:1871 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x4ab/0x7d0 fs/read_write.c:584 ksys_write+0xeb/0x1a0 fs/read_write.c:637 __do_sys_write fs/read_write.c:649 [inline] __se_sys_write fs/read_write.c:646 [inline] __x64_sys_write+0x42/0x50 fs/read_write.c:646 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0x91d25731 -> 0xe79325cd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 32078 Comm: syz-executor.4 Not tainted 6.5.0-rc1-syzkaller-00033-geb26cbb1a754 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/03/2023 Fixes: 58d607d3e52f ("tcp: provide skb->hash to synack packets") Signed-off-by: Eric Dumazet Reported-by: syzbot Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230717144445.653164-2-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_ipv4.c | 3 ++- net/ipv4/tcp_minisocks.c | 2 +- net/ipv4/tcp_output.c | 4 ++-- net/ipv6/tcp_ipv6.c | 2 +- 4 files changed, 6 insertions(+), 5 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fd365de4d5ff..fa04ff49100b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -992,7 +992,8 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, 0, tcp_md5_do_lookup(sk, l3index, addr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, - ip_hdr(skb)->tos, tcp_rsk(req)->txhash); + ip_hdr(skb)->tos, + READ_ONCE(tcp_rsk(req)->txhash)); } /* diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 04fc328727e6..ec05f277ce2e 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -528,7 +528,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newicsk->icsk_ack.lrcvtime = tcp_jiffies32; newtp->lsndtime = tcp_jiffies32; - newsk->sk_txhash = treq->txhash; + newsk->sk_txhash = READ_ONCE(treq->txhash); newtp->total_retrans = req->num_retrans; tcp_init_xmit_timers(newsk); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 2cb39b6dad02..3b09cd13e2db 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3660,7 +3660,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, rcu_read_lock(); md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); #endif - skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); + skb_set_hash(skb, READ_ONCE(tcp_rsk(req)->txhash), PKT_HASH_TYPE_L4); /* bpf program will be interested in the tcp_flags */ TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK; tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, @@ -4210,7 +4210,7 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) /* Paired with WRITE_ONCE() in sock_setsockopt() */ if (READ_ONCE(sk->sk_txrehash) == SOCK_TXREHASH_ENABLED) - tcp_rsk(req)->txhash = net_tx_rndhash(); + WRITE_ONCE(tcp_rsk(req)->txhash, net_tx_rndhash()); res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, NULL); if (!res) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 40dd92a2f480..eb96a8010414 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1129,7 +1129,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority, - tcp_rsk(req)->txhash); + READ_ONCE(tcp_rsk(req)->txhash)); } -- cgit v1.2.3 From eba20811f32652bc1a52d5e7cc403859b86390d9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 17 Jul 2023 14:44:45 +0000 Subject: tcp: annotate data-races around tcp_rsk(req)->ts_recent TCP request sockets are lockless, tcp_rsk(req)->ts_recent can change while being read by another cpu as syzbot noticed. This is harmless, but we should annotate the known races. Note that tcp_check_req() changes req->ts_recent a bit early, we might change this in the future. BUG: KCSAN: data-race in tcp_check_req / tcp_check_req write to 0xffff88813c8afb84 of 4 bytes by interrupt on cpu 1: tcp_check_req+0x694/0xc70 net/ipv4/tcp_minisocks.c:762 tcp_v4_rcv+0x12db/0x1b70 net/ipv4/tcp_ipv4.c:2071 ip_protocol_deliver_rcu+0x356/0x6d0 net/ipv4/ip_input.c:205 ip_local_deliver_finish+0x13c/0x1a0 net/ipv4/ip_input.c:233 NF_HOOK include/linux/netfilter.h:303 [inline] ip_local_deliver+0xec/0x1c0 net/ipv4/ip_input.c:254 dst_input include/net/dst.h:468 [inline] ip_rcv_finish net/ipv4/ip_input.c:449 [inline] NF_HOOK include/linux/netfilter.h:303 [inline] ip_rcv+0x197/0x270 net/ipv4/ip_input.c:569 __netif_receive_skb_one_core net/core/dev.c:5493 [inline] __netif_receive_skb+0x90/0x1b0 net/core/dev.c:5607 process_backlog+0x21f/0x380 net/core/dev.c:5935 __napi_poll+0x60/0x3b0 net/core/dev.c:6498 napi_poll net/core/dev.c:6565 [inline] net_rx_action+0x32b/0x750 net/core/dev.c:6698 __do_softirq+0xc1/0x265 kernel/softirq.c:571 do_softirq+0x7e/0xb0 kernel/softirq.c:472 __local_bh_enable_ip+0x64/0x70 kernel/softirq.c:396 local_bh_enable+0x1f/0x20 include/linux/bottom_half.h:33 rcu_read_unlock_bh include/linux/rcupdate.h:843 [inline] __dev_queue_xmit+0xabb/0x1d10 net/core/dev.c:4271 dev_queue_xmit include/linux/netdevice.h:3088 [inline] neigh_hh_output include/net/neighbour.h:528 [inline] neigh_output include/net/neighbour.h:542 [inline] ip_finish_output2+0x700/0x840 net/ipv4/ip_output.c:229 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:317 NF_HOOK_COND include/linux/netfilter.h:292 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:431 dst_output include/net/dst.h:458 [inline] ip_local_out net/ipv4/ip_output.c:126 [inline] __ip_queue_xmit+0xa4d/0xa70 net/ipv4/ip_output.c:533 ip_queue_xmit+0x38/0x40 net/ipv4/ip_output.c:547 __tcp_transmit_skb+0x1194/0x16e0 net/ipv4/tcp_output.c:1399 tcp_transmit_skb net/ipv4/tcp_output.c:1417 [inline] tcp_write_xmit+0x13ff/0x2fd0 net/ipv4/tcp_output.c:2693 __tcp_push_pending_frames+0x6a/0x1a0 net/ipv4/tcp_output.c:2877 tcp_push_pending_frames include/net/tcp.h:1952 [inline] __tcp_sock_set_cork net/ipv4/tcp.c:3336 [inline] tcp_sock_set_cork+0xe8/0x100 net/ipv4/tcp.c:3343 rds_tcp_xmit_path_complete+0x3b/0x40 net/rds/tcp_send.c:52 rds_send_xmit+0xf8d/0x1420 net/rds/send.c:422 rds_send_worker+0x42/0x1d0 net/rds/threads.c:200 process_one_work+0x3e6/0x750 kernel/workqueue.c:2408 worker_thread+0x5f2/0xa10 kernel/workqueue.c:2555 kthread+0x1d7/0x210 kernel/kthread.c:379 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 read to 0xffff88813c8afb84 of 4 bytes by interrupt on cpu 0: tcp_check_req+0x32a/0xc70 net/ipv4/tcp_minisocks.c:622 tcp_v4_rcv+0x12db/0x1b70 net/ipv4/tcp_ipv4.c:2071 ip_protocol_deliver_rcu+0x356/0x6d0 net/ipv4/ip_input.c:205 ip_local_deliver_finish+0x13c/0x1a0 net/ipv4/ip_input.c:233 NF_HOOK include/linux/netfilter.h:303 [inline] ip_local_deliver+0xec/0x1c0 net/ipv4/ip_input.c:254 dst_input include/net/dst.h:468 [inline] ip_rcv_finish net/ipv4/ip_input.c:449 [inline] NF_HOOK include/linux/netfilter.h:303 [inline] ip_rcv+0x197/0x270 net/ipv4/ip_input.c:569 __netif_receive_skb_one_core net/core/dev.c:5493 [inline] __netif_receive_skb+0x90/0x1b0 net/core/dev.c:5607 process_backlog+0x21f/0x380 net/core/dev.c:5935 __napi_poll+0x60/0x3b0 net/core/dev.c:6498 napi_poll net/core/dev.c:6565 [inline] net_rx_action+0x32b/0x750 net/core/dev.c:6698 __do_softirq+0xc1/0x265 kernel/softirq.c:571 run_ksoftirqd+0x17/0x20 kernel/softirq.c:939 smpboot_thread_fn+0x30a/0x4a0 kernel/smpboot.c:164 kthread+0x1d7/0x210 kernel/kthread.c:379 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 value changed: 0x1cd237f1 -> 0x1cd237f2 Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet Reported-by: syzbot Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230717144445.653164-3-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_minisocks.c | 9 ++++++--- net/ipv4/tcp_output.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- 4 files changed, 9 insertions(+), 6 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fa04ff49100b..b5c81cf5b86f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -988,7 +988,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, - req->ts_recent, + READ_ONCE(req->ts_recent), 0, tcp_md5_do_lookup(sk, l3index, addr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ec05f277ce2e..c8f2aa003387 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -555,7 +555,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->max_window = newtp->snd_wnd; if (newtp->rx_opt.tstamp_ok) { - newtp->rx_opt.ts_recent = req->ts_recent; + newtp->rx_opt.ts_recent = READ_ONCE(req->ts_recent); newtp->rx_opt.ts_recent_stamp = ktime_get_seconds(); newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; } else { @@ -619,7 +619,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, NULL); if (tmp_opt.saw_tstamp) { - tmp_opt.ts_recent = req->ts_recent; + tmp_opt.ts_recent = READ_ONCE(req->ts_recent); if (tmp_opt.rcv_tsecr) tmp_opt.rcv_tsecr -= tcp_rsk(req)->ts_off; /* We do not store true stamp, but it is not required, @@ -758,8 +758,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* In sequence, PAWS is OK. */ + /* TODO: We probably should defer ts_recent change once + * we take ownership of @req. + */ if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt)) - req->ts_recent = tmp_opt.rcv_tsval; + WRITE_ONCE(req->ts_recent, tmp_opt.rcv_tsval); if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) { /* Truncate SYN, it is out of window starting diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 3b09cd13e2db..51d8638d4b4c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -878,7 +878,7 @@ static unsigned int tcp_synack_options(const struct sock *sk, if (likely(ireq->tstamp_ok)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tcp_rsk(req)->ts_off; - opts->tsecr = req->ts_recent; + opts->tsecr = READ_ONCE(req->ts_recent); remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(ireq->sack_ok)) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index eb96a8010414..4714eb695913 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1126,7 +1126,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, - req->ts_recent, sk->sk_bound_dev_if, + READ_ONCE(req->ts_recent), sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority, READ_ONCE(tcp_rsk(req)->txhash)); -- cgit v1.2.3 From daa751444fd9d4184270b1479d8af49aaf1a1ee6 Mon Sep 17 00:00:00 2001 From: Wang Ming Date: Mon, 17 Jul 2023 17:59:19 +0800 Subject: net: ipv4: Use kfree_sensitive instead of kfree key might contain private part of the key, so better use kfree_sensitive to free it. Fixes: 38320c70d282 ("[IPSEC]: Use crypto_aead and authenc in ESP") Signed-off-by: Wang Ming Reviewed-by: Tariq Toukan Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/ipv4/esp4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index ba06ed42e428..2be2d4922557 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -1132,7 +1132,7 @@ static int esp_init_authenc(struct xfrm_state *x, err = crypto_aead_setkey(aead, key, keylen); free_key: - kfree(key); + kfree_sensitive(key); error: return err; -- cgit v1.2.3 From 02d84f3eb53a5be982b17c88410fa6c58806356b Mon Sep 17 00:00:00 2001 From: Yuanjun Gong Date: Mon, 17 Jul 2023 22:49:02 +0800 Subject: ipv4: ip_gre: fix return value check in erspan_fb_xmit() goto err_free_skb if an unexpected result is returned by pskb_tirm() in erspan_fb_xmit(). Signed-off-by: Yuanjun Gong Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 81a1cce1a7d1..914cc941af55 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -548,7 +548,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { - pskb_trim(skb, dev->mtu + dev->hard_header_len); + if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) + goto err_free_skb; truncate = true; } -- cgit v1.2.3 From aa7cb3789b429d4fdfbe767e0e0cf8c769299d7a Mon Sep 17 00:00:00 2001 From: Yuanjun Gong Date: Mon, 17 Jul 2023 22:49:18 +0800 Subject: ipv4: ip_gre: fix return value check in erspan_xmit() goto free_skb if an unexpected result is returned by pskb_tirm() in erspan_xmit(). Signed-off-by: Yuanjun Gong Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 914cc941af55..22a26d1d29a0 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -690,7 +690,8 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, goto free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { - pskb_trim(skb, dev->mtu + dev->hard_header_len); + if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) + goto free_skb; truncate = true; } -- cgit v1.2.3 From 81b3ade5d2b98ad6e0a473b0e1e420a801275592 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 17 Jul 2023 14:59:18 -0700 Subject: Revert "tcp: avoid the lookup process failing to get sk in ehash table" This reverts commit 3f4ca5fafc08881d7a57daa20449d171f2887043. Commit 3f4ca5fafc08 ("tcp: avoid the lookup process failing to get sk in ehash table") reversed the order in how a socket is inserted into ehash to fix an issue that ehash-lookup could fail when reqsk/full sk/twsk are swapped. However, it introduced another lookup failure. The full socket in ehash is allocated from a slab with SLAB_TYPESAFE_BY_RCU and does not have SOCK_RCU_FREE, so the socket could be reused even while it is being referenced on another CPU doing RCU lookup. Let's say a socket is reused and inserted into the same hash bucket during lookup. After the blamed commit, a new socket is inserted at the end of the list. If that happens, we will skip sockets placed after the previous position of the reused socket, resulting in ehash lookup failure. As described in Documentation/RCU/rculist_nulls.rst, we should insert a new socket at the head of the list to avoid such an issue. This issue, the swap-lookup-failure, and another variant reported in [0] can all be handled properly by adding a locked ehash lookup suggested by Eric Dumazet [1]. However, this issue could occur for every packet, thus more likely than the other two races, so let's revert the change for now. Link: https://lore.kernel.org/netdev/20230606064306.9192-1-duanmuquan@baidu.com/ [0] Link: https://lore.kernel.org/netdev/CANn89iK8snOz8TYOhhwfimC7ykYA78GA3Nyv8x06SZYa1nKdyA@mail.gmail.com/ [1] Fixes: 3f4ca5fafc08 ("tcp: avoid the lookup process failing to get sk in ehash table") Signed-off-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230717215918.15723-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/ipv4/inet_hashtables.c | 17 ++--------------- net/ipv4/inet_timewait_sock.c | 8 ++++---- 2 files changed, 6 insertions(+), 19 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index e7391bf310a7..0819d6001b9a 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -650,20 +650,8 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) spin_lock(lock); if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); - ret = sk_hashed(osk); - if (ret) { - /* Before deleting the node, we insert a new one to make - * sure that the look-up-sk process would not miss either - * of them and that at least one node would exist in ehash - * table all the time. Otherwise there's a tiny chance - * that lookup process could find nothing in ehash table. - */ - __sk_nulls_add_node_tail_rcu(sk, list); - sk_nulls_del_node_init_rcu(osk); - } - goto unlock; - } - if (found_dup_sk) { + ret = sk_nulls_del_node_init_rcu(osk); + } else if (found_dup_sk) { *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); if (*found_dup_sk) ret = false; @@ -672,7 +660,6 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) if (ret) __sk_nulls_add_node_rcu(sk, list); -unlock: spin_unlock(lock); return ret; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 40052414c7c7..2c1b245dba8e 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -88,10 +88,10 @@ void inet_twsk_put(struct inet_timewait_sock *tw) } EXPORT_SYMBOL_GPL(inet_twsk_put); -static void inet_twsk_add_node_tail_rcu(struct inet_timewait_sock *tw, - struct hlist_nulls_head *list) +static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, + struct hlist_nulls_head *list) { - hlist_nulls_add_tail_rcu(&tw->tw_node, list); + hlist_nulls_add_head_rcu(&tw->tw_node, list); } static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw, @@ -144,7 +144,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, spin_lock(lock); - inet_twsk_add_node_tail_rcu(tw, &ehead->chain); + inet_twsk_add_node_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ if (__sk_nulls_del_node_init_rcu(sk)) -- cgit v1.2.3 From 348b81b68b13ebd489a3e6a46aa1c384c731c919 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:47 +0000 Subject: tcp: annotate data-races around tp->tcp_tx_delay do_tcp_getsockopt() reads tp->tcp_tx_delay while another cpu might change its value. Fixes: a842fe1425cb ("tcp: add optional per socket transmit delay") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-2-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e03e08745308..bd6400e1ae9f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3674,7 +3674,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_TX_DELAY: if (val) tcp_enable_tx_delay(); - tp->tcp_tx_delay = val; + WRITE_ONCE(tp->tcp_tx_delay, val); break; default: err = -ENOPROTOOPT; @@ -4154,7 +4154,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_TX_DELAY: - val = tp->tcp_tx_delay; + val = READ_ONCE(tp->tcp_tx_delay); break; case TCP_TIMESTAMP: -- cgit v1.2.3 From dd23c9f1e8d5c1d2e3d29393412385ccb9c7a948 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:48 +0000 Subject: tcp: annotate data-races around tp->tsoffset do_tcp_getsockopt() reads tp->tsoffset while another cpu might change its value. Fixes: 93be6ce0e91b ("tcp: set and get per-socket timestamp") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-3-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 4 ++-- net/ipv4/tcp_ipv4.c | 5 +++-- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bd6400e1ae9f..03ae6554c78d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3656,7 +3656,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (!tp->repair) err = -EPERM; else - tp->tsoffset = val - tcp_time_stamp_raw(); + WRITE_ONCE(tp->tsoffset, val - tcp_time_stamp_raw()); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); @@ -4158,7 +4158,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_TIMESTAMP: - val = tcp_time_stamp_raw() + tp->tsoffset; + val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset); break; case TCP_NOTSENT_LOWAT: val = tp->notsent_lowat; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b5c81cf5b86f..069642014636 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -307,8 +307,9 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, usin->sin_port)); - tp->tsoffset = secure_tcp_ts_off(net, inet->inet_saddr, - inet->inet_daddr); + WRITE_ONCE(tp->tsoffset, + secure_tcp_ts_off(net, inet->inet_saddr, + inet->inet_daddr)); } inet->inet_id = get_random_u16(); -- cgit v1.2.3 From 4164245c76ff906c9086758e1c3f87082a7f5ef5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:49 +0000 Subject: tcp: annotate data-races around tp->keepalive_time do_tcp_getsockopt() reads tp->keepalive_time while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-4-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 7 +++++-- net/ipv4/tcp.c | 3 ++- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/tcp.h b/include/net/tcp.h index 226bce6d1e8c..9e1c3337cdfe 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1517,9 +1517,12 @@ static inline int keepalive_intvl_when(const struct tcp_sock *tp) static inline int keepalive_time_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); + int val; - return tp->keepalive_time ? : - READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); + /* Paired with WRITE_ONCE() in tcp_sock_set_keepidle_locked() */ + val = READ_ONCE(tp->keepalive_time); + + return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); } static inline int keepalive_probes(const struct tcp_sock *tp) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 03ae6554c78d..b4f7856dfb16 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3312,7 +3312,8 @@ int tcp_sock_set_keepidle_locked(struct sock *sk, int val) if (val < 1 || val > MAX_TCP_KEEPIDLE) return -EINVAL; - tp->keepalive_time = val * HZ; + /* Paired with WRITE_ONCE() in keepalive_time_when() */ + WRITE_ONCE(tp->keepalive_time, val * HZ); if (sock_flag(sk, SOCK_KEEPOPEN) && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { u32 elapsed = keepalive_time_elapsed(tp); -- cgit v1.2.3 From 5ecf9d4f52ff2f1d4d44c9b68bc75688e82f13b4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:50 +0000 Subject: tcp: annotate data-races around tp->keepalive_intvl do_tcp_getsockopt() reads tp->keepalive_intvl while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-5-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 9 +++++++-- net/ipv4/tcp.c | 4 ++-- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/tcp.h b/include/net/tcp.h index 9e1c3337cdfe..2d8d58dec652 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1509,9 +1509,14 @@ void tcp_leave_memory_pressure(struct sock *sk); static inline int keepalive_intvl_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); + int val; + + /* Paired with WRITE_ONCE() in tcp_sock_set_keepintvl() + * and do_tcp_setsockopt(). + */ + val = READ_ONCE(tp->keepalive_intvl); - return tp->keepalive_intvl ? : - READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl); + return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl); } static inline int keepalive_time_when(const struct tcp_sock *tp) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b4f7856dfb16..d55fe014e7c9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3345,7 +3345,7 @@ int tcp_sock_set_keepintvl(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - tcp_sk(sk)->keepalive_intvl = val * HZ; + WRITE_ONCE(tcp_sk(sk)->keepalive_intvl, val * HZ); release_sock(sk); return 0; } @@ -3559,7 +3559,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 1 || val > MAX_TCP_KEEPINTVL) err = -EINVAL; else - tp->keepalive_intvl = val * HZ; + WRITE_ONCE(tp->keepalive_intvl, val * HZ); break; case TCP_KEEPCNT: if (val < 1 || val > MAX_TCP_KEEPCNT) -- cgit v1.2.3 From 6e5e1de616bf5f3df1769abc9292191dfad9110a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:51 +0000 Subject: tcp: annotate data-races around tp->keepalive_probes do_tcp_getsockopt() reads tp->keepalive_probes while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-6-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 9 +++++++-- net/ipv4/tcp.c | 5 +++-- 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/tcp.h b/include/net/tcp.h index 2d8d58dec652..a8b93b2875ea 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1533,9 +1533,14 @@ static inline int keepalive_time_when(const struct tcp_sock *tp) static inline int keepalive_probes(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); + int val; + + /* Paired with WRITE_ONCE() in tcp_sock_set_keepcnt() + * and do_tcp_setsockopt(). + */ + val = READ_ONCE(tp->keepalive_probes); - return tp->keepalive_probes ? : - READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes); + return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes); } static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d55fe014e7c9..574fd0da1673 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3357,7 +3357,8 @@ int tcp_sock_set_keepcnt(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - tcp_sk(sk)->keepalive_probes = val; + /* Paired with READ_ONCE() in keepalive_probes() */ + WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val); release_sock(sk); return 0; } @@ -3565,7 +3566,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 1 || val > MAX_TCP_KEEPCNT) err = -EINVAL; else - tp->keepalive_probes = val; + WRITE_ONCE(tp->keepalive_probes, val); break; case TCP_SYNCNT: if (val < 1 || val > MAX_TCP_SYNCNT) -- cgit v1.2.3 From 3a037f0f3c4bfe44518f2fbb478aa2f99a9cd8bb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:52 +0000 Subject: tcp: annotate data-races around icsk->icsk_syn_retries do_tcp_getsockopt() and reqsk_timer_handler() read icsk->icsk_syn_retries while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-7-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/inet_connection_sock.c | 2 +- net/ipv4/tcp.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 0cc19cfbb673..aeebe8816689 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1019,7 +1019,7 @@ static void reqsk_timer_handler(struct timer_list *t) icsk = inet_csk(sk_listener); net = sock_net(sk_listener); - max_syn_ack_retries = icsk->icsk_syn_retries ? : + max_syn_ack_retries = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_synack_retries); /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 574fd0da1673..9f74ac16f1c1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3291,7 +3291,7 @@ int tcp_sock_set_syncnt(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - inet_csk(sk)->icsk_syn_retries = val; + WRITE_ONCE(inet_csk(sk)->icsk_syn_retries, val); release_sock(sk); return 0; } @@ -3572,7 +3572,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 1 || val > MAX_TCP_SYNCNT) err = -EINVAL; else - icsk->icsk_syn_retries = val; + WRITE_ONCE(icsk->icsk_syn_retries, val); break; case TCP_SAVE_SYN: @@ -3993,7 +3993,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, val = keepalive_probes(tp); break; case TCP_SYNCNT: - val = icsk->icsk_syn_retries ? : + val = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: -- cgit v1.2.3 From 9df5335ca974e688389c875546e5819778a80d59 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:53 +0000 Subject: tcp: annotate data-races around tp->linger2 do_tcp_getsockopt() reads tp->linger2 while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-8-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 9f74ac16f1c1..2cf129a0c00b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3585,11 +3585,11 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_LINGER2: if (val < 0) - tp->linger2 = -1; + WRITE_ONCE(tp->linger2, -1); else if (val > TCP_FIN_TIMEOUT_MAX / HZ) - tp->linger2 = TCP_FIN_TIMEOUT_MAX; + WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX); else - tp->linger2 = val * HZ; + WRITE_ONCE(tp->linger2, val * HZ); break; case TCP_DEFER_ACCEPT: @@ -3997,7 +3997,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: - val = tp->linger2; + val = READ_ONCE(tp->linger2); if (val >= 0) val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; -- cgit v1.2.3 From ae488c74422fb1dcd807c0201804b3b5e8a322a3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:54 +0000 Subject: tcp: annotate data-races around rskq_defer_accept do_tcp_getsockopt() reads rskq_defer_accept while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-9-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2cf129a0c00b..5beec71a5c41 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3594,9 +3594,9 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_DEFER_ACCEPT: /* Translate value in seconds to number of retransmits */ - icsk->icsk_accept_queue.rskq_defer_accept = - secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, - TCP_RTO_MAX / HZ); + WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept, + secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ)); break; case TCP_WINDOW_CLAMP: @@ -4002,8 +4002,9 @@ int do_tcp_getsockopt(struct sock *sk, int level, val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; case TCP_DEFER_ACCEPT: - val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept, - TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ); + val = READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept); + val = retrans_to_secs(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: val = tp->window_clamp; -- cgit v1.2.3 From 1aeb87bc1440c5447a7fa2d6e3c2cca52cbd206b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:55 +0000 Subject: tcp: annotate data-races around tp->notsent_lowat tp->notsent_lowat can be read locklessly from do_tcp_getsockopt() and tcp_poll(). Fixes: c9bee3b7fdec ("tcp: TCP_NOTSENT_LOWAT socket option") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-10-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 6 +++++- net/ipv4/tcp.c | 4 ++-- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/tcp.h b/include/net/tcp.h index a8b93b2875ea..0ca972ebd3dd 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2061,7 +2061,11 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); - return tp->notsent_lowat ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); + u32 val; + + val = READ_ONCE(tp->notsent_lowat); + + return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); } bool tcp_stream_memory_free(const struct sock *sk, int wake); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5beec71a5c41..2b2241e9b492 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3664,7 +3664,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, err = tcp_repair_set_window(tp, optval, optlen); break; case TCP_NOTSENT_LOWAT: - tp->notsent_lowat = val; + WRITE_ONCE(tp->notsent_lowat, val); sk->sk_write_space(sk); break; case TCP_INQ: @@ -4164,7 +4164,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset); break; case TCP_NOTSENT_LOWAT: - val = tp->notsent_lowat; + val = READ_ONCE(tp->notsent_lowat); break; case TCP_INQ: val = tp->recvmsg_inq; -- cgit v1.2.3 From 26023e91e12c68669db416b97234328a03d8e499 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:56 +0000 Subject: tcp: annotate data-races around icsk->icsk_user_timeout This field can be read locklessly from do_tcp_getsockopt() Fixes: dca43c75e7e5 ("tcp: Add TCP_USER_TIMEOUT socket option.") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-11-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2b2241e9b492..3e137e9a18f5 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3300,7 +3300,7 @@ EXPORT_SYMBOL(tcp_sock_set_syncnt); void tcp_sock_set_user_timeout(struct sock *sk, u32 val) { lock_sock(sk); - inet_csk(sk)->icsk_user_timeout = val; + WRITE_ONCE(inet_csk(sk)->icsk_user_timeout, val); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_user_timeout); @@ -3620,7 +3620,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 0) err = -EINVAL; else - icsk->icsk_user_timeout = val; + WRITE_ONCE(icsk->icsk_user_timeout, val); break; case TCP_FASTOPEN: @@ -4141,7 +4141,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_USER_TIMEOUT: - val = icsk->icsk_user_timeout; + val = READ_ONCE(icsk->icsk_user_timeout); break; case TCP_FASTOPEN: -- cgit v1.2.3 From 70f360dd7042cb843635ece9d28335a4addff9eb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:57 +0000 Subject: tcp: annotate data-races around fastopenq.max_qlen This field can be read locklessly. Fixes: 1536e2857bd3 ("tcp: Add a TCP_FASTOPEN socket option to get a max backlog on its listner") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-12-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/tcp.h | 2 +- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_fastopen.c | 6 ++++-- 3 files changed, 6 insertions(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index b4c08ac86983..91a37c99ba66 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -513,7 +513,7 @@ static inline void fastopen_queue_tune(struct sock *sk, int backlog) struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; int somaxconn = READ_ONCE(sock_net(sk)->core.sysctl_somaxconn); - queue->fastopenq.max_qlen = min_t(unsigned int, backlog, somaxconn); + WRITE_ONCE(queue->fastopenq.max_qlen, min_t(unsigned int, backlog, somaxconn)); } static inline void tcp_move_syn(struct tcp_sock *tp, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3e137e9a18f5..8ed52e1e3c99 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4145,7 +4145,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_FASTOPEN: - val = icsk->icsk_accept_queue.fastopenq.max_qlen; + val = READ_ONCE(icsk->icsk_accept_queue.fastopenq.max_qlen); break; case TCP_FASTOPEN_CONNECT: diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 45cc7f1ca296..85e4953f1182 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -296,6 +296,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, static bool tcp_fastopen_queue_check(struct sock *sk) { struct fastopen_queue *fastopenq; + int max_qlen; /* Make sure the listener has enabled fastopen, and we don't * exceed the max # of pending TFO requests allowed before trying @@ -308,10 +309,11 @@ static bool tcp_fastopen_queue_check(struct sock *sk) * temporarily vs a server not supporting Fast Open at all. */ fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq; - if (fastopenq->max_qlen == 0) + max_qlen = READ_ONCE(fastopenq->max_qlen); + if (max_qlen == 0) return false; - if (fastopenq->qlen >= fastopenq->max_qlen) { + if (fastopenq->qlen >= max_qlen) { struct request_sock *req1; spin_lock(&fastopenq->lock); req1 = fastopenq->rskq_rst_head; -- cgit v1.2.3