From c4c877b2732466b4c63217baad05c96f775912c7 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 10 Mar 2021 01:38:09 +0100 Subject: net: Consolidate common blackhole dst ops Move generic blackhole dst ops to the core and use them from both ipv4_dst_blackhole_ops and ip6_dst_blackhole_ops where possible. No functional change otherwise. We need these also in other locations and having to define them over and over again is not great. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/net/dst.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index 26f134ad3a25..75b1e734e9c2 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -550,4 +550,15 @@ static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu) dst->ops->update_pmtu(dst, NULL, skb, mtu, false); } +struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie); +void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu, bool confirm_neigh); +void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb); +u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old); +struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr); +unsigned int dst_blackhole_mtu(const struct dst_entry *dst); + #endif /* _NET_DST_H */ -- cgit v1.2.3 From 28259bac7f1dde06d8ba324e222bbec9d4e92f2b Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Tue, 9 Mar 2021 18:20:35 -0800 Subject: ipv6: fix suspecious RCU usage warning Syzbot reported the suspecious RCU usage in nexthop_fib6_nh() when called from ipv6_route_seq_show(). The reason is ipv6_route_seq_start() calls rcu_read_lock_bh(), while nexthop_fib6_nh() calls rcu_dereference_rtnl(). The fix proposed is to add a variant of nexthop_fib6_nh() to use rcu_dereference_bh_rtnl() for ipv6_route_seq_show(). The reported trace is as follows: ./include/net/nexthop.h:416 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 2 locks held by syz-executor.0/17895: at: seq_read+0x71/0x12a0 fs/seq_file.c:169 at: seq_file_net include/linux/seq_file_net.h:19 [inline] at: ipv6_route_seq_start+0xaf/0x300 net/ipv6/ip6_fib.c:2616 stack backtrace: CPU: 1 PID: 17895 Comm: syz-executor.0 Not tainted 4.15.0-syzkaller #0 Call Trace: [] __dump_stack lib/dump_stack.c:17 [inline] [] dump_stack+0xd8/0x147 lib/dump_stack.c:53 [] lockdep_rcu_suspicious+0x153/0x15d kernel/locking/lockdep.c:5745 [] nexthop_fib6_nh include/net/nexthop.h:416 [inline] [] ipv6_route_native_seq_show net/ipv6/ip6_fib.c:2488 [inline] [] ipv6_route_seq_show+0x436/0x7a0 net/ipv6/ip6_fib.c:2673 [] seq_read+0xccf/0x12a0 fs/seq_file.c:276 [] proc_reg_read+0x10c/0x1d0 fs/proc/inode.c:231 [] do_loop_readv_writev fs/read_write.c:714 [inline] [] do_loop_readv_writev fs/read_write.c:701 [inline] [] do_iter_read+0x49e/0x660 fs/read_write.c:935 [] vfs_readv+0xfb/0x170 fs/read_write.c:997 [] kernel_readv fs/splice.c:361 [inline] [] default_file_splice_read+0x487/0x9c0 fs/splice.c:416 [] do_splice_to+0x129/0x190 fs/splice.c:879 [] splice_direct_to_actor+0x256/0x890 fs/splice.c:951 [] do_splice_direct+0x1dd/0x2b0 fs/splice.c:1060 [] do_sendfile+0x597/0xce0 fs/read_write.c:1459 [] SYSC_sendfile64 fs/read_write.c:1520 [inline] [] SyS_sendfile64+0x155/0x170 fs/read_write.c:1506 [] do_syscall_64+0x1ff/0x310 arch/x86/entry/common.c:305 [] entry_SYSCALL_64_after_hwframe+0x42/0xb7 Fixes: f88d8ea67fbdb ("ipv6: Plumb support for nexthop object in a fib6_info") Reported-by: syzbot Signed-off-by: Wei Wang Cc: David Ahern Cc: Ido Schimmel Cc: Petr Machata Cc: Eric Dumazet Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/nexthop.h | 24 ++++++++++++++++++++++++ net/ipv6/ip6_fib.c | 2 +- 2 files changed, 25 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 7bc057aee40b..a10a319d7eb2 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -410,6 +410,7 @@ static inline struct fib_nh *fib_info_nh(struct fib_info *fi, int nhsel) int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, struct netlink_ext_ack *extack); +/* Caller should either hold rcu_read_lock(), or RTNL. */ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) { struct nh_info *nhi; @@ -430,6 +431,29 @@ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) return NULL; } +/* Variant of nexthop_fib6_nh(). + * Caller should either hold rcu_read_lock_bh(), or RTNL. + */ +static inline struct fib6_nh *nexthop_fib6_nh_bh(struct nexthop *nh) +{ + struct nh_info *nhi; + + if (nh->is_group) { + struct nh_group *nh_grp; + + nh_grp = rcu_dereference_bh_rtnl(nh->nh_grp); + nh = nexthop_mpath_select(nh_grp, 0); + if (!nh) + return NULL; + } + + nhi = rcu_dereference_bh_rtnl(nh->nh_info); + if (nhi->family == AF_INET6) + return &nhi->fib6_nh; + + return NULL; +} + static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i) { struct fib6_nh *fib6_nh; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index ef9d022e693f..679699e953f1 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2486,7 +2486,7 @@ static int ipv6_route_native_seq_show(struct seq_file *seq, void *v) const struct net_device *dev; if (rt->nh) - fib6_nh = nexthop_fib6_nh(rt->nh); + fib6_nh = nexthop_fib6_nh_bh(rt->nh); seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); -- cgit v1.2.3 From e323d865b36134e8c5c82c834df89109a5c60dab Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 10 Mar 2021 08:26:41 -0800 Subject: net: sched: validate stab values iproute2 package is well behaved, but malicious user space can provide illegal shift values and trigger UBSAN reports. Add stab parameter to red_check_params() to validate user input. syzbot reported: UBSAN: shift-out-of-bounds in ./include/net/red.h:312:18 shift exponent 111 is too large for 64-bit type 'long unsigned int' CPU: 1 PID: 14662 Comm: syz-executor.3 Not tainted 5.12.0-rc2-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x141/0x1d7 lib/dump_stack.c:120 ubsan_epilogue+0xb/0x5a lib/ubsan.c:148 __ubsan_handle_shift_out_of_bounds.cold+0xb1/0x181 lib/ubsan.c:327 red_calc_qavg_from_idle_time include/net/red.h:312 [inline] red_calc_qavg include/net/red.h:353 [inline] choke_enqueue.cold+0x18/0x3dd net/sched/sch_choke.c:221 __dev_xmit_skb net/core/dev.c:3837 [inline] __dev_queue_xmit+0x1943/0x2e00 net/core/dev.c:4150 neigh_hh_output include/net/neighbour.h:499 [inline] neigh_output include/net/neighbour.h:508 [inline] ip6_finish_output2+0x911/0x1700 net/ipv6/ip6_output.c:117 __ip6_finish_output net/ipv6/ip6_output.c:182 [inline] __ip6_finish_output+0x4c1/0xe10 net/ipv6/ip6_output.c:161 ip6_finish_output+0x35/0x200 net/ipv6/ip6_output.c:192 NF_HOOK_COND include/linux/netfilter.h:290 [inline] ip6_output+0x1e4/0x530 net/ipv6/ip6_output.c:215 dst_output include/net/dst.h:448 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] NF_HOOK include/linux/netfilter.h:295 [inline] ip6_xmit+0x127e/0x1eb0 net/ipv6/ip6_output.c:320 inet6_csk_xmit+0x358/0x630 net/ipv6/inet6_connection_sock.c:135 dccp_transmit_skb+0x973/0x12c0 net/dccp/output.c:138 dccp_send_reset+0x21b/0x2b0 net/dccp/output.c:535 dccp_finish_passive_close net/dccp/proto.c:123 [inline] dccp_finish_passive_close+0xed/0x140 net/dccp/proto.c:118 dccp_terminate_connection net/dccp/proto.c:958 [inline] dccp_close+0xb3c/0xe60 net/dccp/proto.c:1028 inet_release+0x12e/0x280 net/ipv4/af_inet.c:431 inet6_release+0x4c/0x70 net/ipv6/af_inet6.c:478 __sock_release+0xcd/0x280 net/socket.c:599 sock_close+0x18/0x20 net/socket.c:1258 __fput+0x288/0x920 fs/file_table.c:280 task_work_run+0xdd/0x1a0 kernel/task_work.c:140 tracehook_notify_resume include/linux/tracehook.h:189 [inline] Fixes: 8afa10cbe281 ("net_sched: red: Avoid illegal values") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- include/net/red.h | 10 +++++++++- net/sched/sch_choke.c | 7 ++++--- net/sched/sch_gred.c | 2 +- net/sched/sch_red.c | 7 +++++-- net/sched/sch_sfq.c | 2 +- 5 files changed, 20 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/include/net/red.h b/include/net/red.h index 932f0d79d60c..9e6647c4ccd1 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -168,7 +168,8 @@ static inline void red_set_vars(struct red_vars *v) v->qcount = -1; } -static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, u8 Scell_log) +static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, + u8 Scell_log, u8 *stab) { if (fls(qth_min) + Wlog > 32) return false; @@ -178,6 +179,13 @@ static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, u8 Scell_ return false; if (qth_max < qth_min) return false; + if (stab) { + int i; + + for (i = 0; i < RED_STAB_SIZE; i++) + if (stab[i] >= 32) + return false; + } return true; } diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 50f680f03a54..2adbd945bf15 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -345,6 +345,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt, struct sk_buff **old = NULL; unsigned int mask; u32 max_P; + u8 *stab; if (opt == NULL) return -EINVAL; @@ -361,8 +362,8 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt, max_P = tb[TCA_CHOKE_MAX_P] ? nla_get_u32(tb[TCA_CHOKE_MAX_P]) : 0; ctl = nla_data(tb[TCA_CHOKE_PARMS]); - - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) + stab = nla_data(tb[TCA_CHOKE_STAB]); + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) return -EINVAL; if (ctl->limit > CHOKE_MAX_QUEUE) @@ -412,7 +413,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt, red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, - nla_data(tb[TCA_CHOKE_STAB]), + stab, max_P); red_set_vars(&q->vars); diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index e0bc77533acc..f4132dc25ac0 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -480,7 +480,7 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp, struct gred_sched *table = qdisc_priv(sch); struct gred_sched_data *q = table->tab[dp]; - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) { + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) { NL_SET_ERR_MSG_MOD(extack, "invalid RED parameters"); return -EINVAL; } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index b4ae34d7aa96..40adf1f07a82 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -242,6 +242,7 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb, unsigned char flags; int err; u32 max_P; + u8 *stab; if (tb[TCA_RED_PARMS] == NULL || tb[TCA_RED_STAB] == NULL) @@ -250,7 +251,9 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb, max_P = tb[TCA_RED_MAX_P] ? nla_get_u32(tb[TCA_RED_MAX_P]) : 0; ctl = nla_data(tb[TCA_RED_PARMS]); - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) + stab = nla_data(tb[TCA_RED_STAB]); + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, + ctl->Scell_log, stab)) return -EINVAL; err = red_get_flags(ctl->flags, TC_RED_HISTORIC_FLAGS, @@ -288,7 +291,7 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb, red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, - nla_data(tb[TCA_RED_STAB]), + stab, max_P); red_set_vars(&q->vars); diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index b25e51440623..066754a18569 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -647,7 +647,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) } if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max, - ctl_v1->Wlog, ctl_v1->Scell_log)) + ctl_v1->Wlog, ctl_v1->Scell_log, NULL)) return -EINVAL; if (ctl_v1 && ctl_v1->qth_min) { p = kmalloc(sizeof(*p), GFP_KERNEL); -- cgit v1.2.3 From f211ac154577ec9ccf07c15f18a6abf0d9bdb4ab Mon Sep 17 00:00:00 2001 From: liuyacan Date: Fri, 12 Mar 2021 00:32:25 +0800 Subject: net: correct sk_acceptq_is_full() The "backlog" argument in listen() specifies the maximom length of pending connections, so the accept queue should be considered full if there are exactly "backlog" elements. Signed-off-by: liuyacan Signed-off-by: David S. Miller --- include/net/sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 636810ddcd9b..0b6266fd6bf6 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -936,7 +936,7 @@ static inline void sk_acceptq_added(struct sock *sk) static inline bool sk_acceptq_is_full(const struct sock *sk) { - return READ_ONCE(sk->sk_ack_backlog) > READ_ONCE(sk->sk_max_ack_backlog); + return READ_ONCE(sk->sk_ack_backlog) >= READ_ONCE(sk->sk_max_ack_backlog); } /* -- cgit v1.2.3 From 7233da86697efef41288f8b713c10c2499cffe85 Mon Sep 17 00:00:00 2001 From: Alexander Ovechkin Date: Mon, 15 Mar 2021 14:05:45 +0300 Subject: tcp: relookup sock for RST+ACK packets handled by obsolete req sock Currently tcp_check_req can be called with obsolete req socket for which big socket have been already created (because of CPU race or early demux assigning req socket to multiple packets in gro batch). Commit e0f9759f530bf789e984 ("tcp: try to keep packet if SYN_RCV race is lost") added retry in case when tcp_check_req is called for PSH|ACK packet. But if client sends RST+ACK immediatly after connection being established (it is performing healthcheck, for example) retry does not occur. In that case tcp_check_req tries to close req socket, leaving big socket active. Fixes: e0f9759f530 ("tcp: try to keep packet if SYN_RCV race is lost") Signed-off-by: Alexander Ovechkin Reported-by: Oleg Senin Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 2 +- net/ipv4/inet_connection_sock.c | 7 +++++-- net/ipv4/tcp_minisocks.c | 7 +++++-- 3 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 10a625760de9..3c8c59471bc1 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -282,7 +282,7 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) return inet_csk_reqsk_queue_len(sk) >= sk->sk_max_ack_backlog; } -void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); +bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req); static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 6bd7ca09af03..fd472eae4f5c 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -705,12 +705,15 @@ static bool reqsk_queue_unlink(struct request_sock *req) return found; } -void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) +bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) { - if (reqsk_queue_unlink(req)) { + bool unlinked = reqsk_queue_unlink(req); + + if (unlinked) { reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); reqsk_put(req); } + return unlinked; } EXPORT_SYMBOL(inet_csk_reqsk_queue_drop); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 0055ae0a3bf8..7513ba45553d 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -804,8 +804,11 @@ embryonic_reset: tcp_reset(sk, skb); } if (!fastopen) { - inet_csk_reqsk_queue_drop(sk, req); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_EMBRYONICRSTS); + bool unlinked = inet_csk_reqsk_queue_drop(sk, req); + + if (unlinked) + __NET_INC_STATS(sock_net(sk), LINUX_MIB_EMBRYONICRSTS); + *req_stolen = !unlinked; } return NULL; } -- cgit v1.2.3 From 3a5ca857079ea022e0b1b17fc154f7ad7dbc150f Mon Sep 17 00:00:00 2001 From: Martin Willi Date: Tue, 2 Mar 2021 13:24:23 +0100 Subject: can: dev: Move device back to init netns on owning netns delete When a non-initial netns is destroyed, the usual policy is to delete all virtual network interfaces contained, but move physical interfaces back to the initial netns. This keeps the physical interface visible on the system. CAN devices are somewhat special, as they define rtnl_link_ops even if they are physical devices. If a CAN interface is moved into a non-initial netns, destroying that netns lets the interface vanish instead of moving it back to the initial netns. default_device_exit() skips CAN interfaces due to having rtnl_link_ops set. Reproducer: ip netns add foo ip link set can0 netns foo ip netns delete foo WARNING: CPU: 1 PID: 84 at net/core/dev.c:11030 ops_exit_list+0x38/0x60 CPU: 1 PID: 84 Comm: kworker/u4:2 Not tainted 5.10.19 #1 Workqueue: netns cleanup_net [] (unwind_backtrace) from [] (show_stack+0x10/0x14) [] (show_stack) from [] (dump_stack+0x94/0xa8) [] (dump_stack) from [] (__warn+0xb8/0x114) [] (__warn) from [] (warn_slowpath_fmt+0x7c/0xac) [] (warn_slowpath_fmt) from [] (ops_exit_list+0x38/0x60) [] (ops_exit_list) from [] (cleanup_net+0x230/0x380) [] (cleanup_net) from [] (process_one_work+0x1d8/0x438) [] (process_one_work) from [] (worker_thread+0x64/0x5a8) [] (worker_thread) from [] (kthread+0x148/0x14c) [] (kthread) from [] (ret_from_fork+0x14/0x2c) To properly restore physical CAN devices to the initial netns on owning netns exit, introduce a flag on rtnl_link_ops that can be set by drivers. For CAN devices setting this flag, default_device_exit() considers them non-virtual, applying the usual namespace move. The issue was introduced in the commit mentioned below, as at that time CAN devices did not have a dellink() operation. Fixes: e008b5fc8dc7 ("net: Simplfy default_device_exit and improve batching.") Link: https://lore.kernel.org/r/20210302122423.872326-1-martin@strongswan.org Signed-off-by: Martin Willi Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/netlink.c | 1 + include/net/rtnetlink.h | 2 ++ net/core/dev.c | 2 +- 3 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 867f6be31230..f5d79e6e5483 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -355,6 +355,7 @@ static void can_dellink(struct net_device *dev, struct list_head *head) struct rtnl_link_ops can_link_ops __read_mostly = { .kind = "can", + .netns_refund = true, .maxtype = IFLA_CAN_MAX, .policy = can_policy, .setup = can_setup, diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index e2091bb2b3a8..4da61c950e93 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -33,6 +33,7 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh) * * @list: Used internally * @kind: Identifier + * @netns_refund: Physical device, move to init_net on netns exit * @maxtype: Highest device specific netlink attribute number * @policy: Netlink policy for device specific attribute validation * @validate: Optional validation function for netlink/changelink parameters @@ -64,6 +65,7 @@ struct rtnl_link_ops { size_t priv_size; void (*setup)(struct net_device *dev); + bool netns_refund; unsigned int maxtype; const struct nla_policy *policy; int (*validate)(struct nlattr *tb[], diff --git a/net/core/dev.c b/net/core/dev.c index 6c5967e80132..a142a207fc1d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -11346,7 +11346,7 @@ static void __net_exit default_device_exit(struct net *net) continue; /* Leave virtual devices for the generic cleanup */ - if (dev->rtnl_link_ops) + if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund) continue; /* Push remaining network devices to init_net */ -- cgit v1.2.3 From 7b35582cd04ace2fd1807c1b624934e465cc939d Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 17 Mar 2021 12:54:57 +0100 Subject: netfilter: nftables: allow to update flowtable flags Honor flowtable flags from the control update path. Disallow disabling to toggle hardware offload support though. Fixes: 8bb69f3b2918 ("netfilter: nf_tables: add flowtable offload control plane") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 3 +++ net/netfilter/nf_tables_api.c | 15 +++++++++++++++ 2 files changed, 18 insertions(+) (limited to 'include/net') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index fdec57d862b7..5aaced6bf13e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1536,6 +1536,7 @@ struct nft_trans_flowtable { struct nft_flowtable *flowtable; bool update; struct list_head hook_list; + u32 flags; }; #define nft_trans_flowtable(trans) \ @@ -1544,6 +1545,8 @@ struct nft_trans_flowtable { (((struct nft_trans_flowtable *)trans->data)->update) #define nft_trans_flowtable_hooks(trans) \ (((struct nft_trans_flowtable *)trans->data)->hook_list) +#define nft_trans_flowtable_flags(trans) \ + (((struct nft_trans_flowtable *)trans->data)->flags) int __init nft_chain_filter_init(void); void nft_chain_filter_fini(void); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0d034f895b7b..4fcd07f1e925 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -6842,6 +6842,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, struct nft_hook *hook, *next; struct nft_trans *trans; bool unregister = false; + u32 flags; int err; err = nft_flowtable_parse_hook(ctx, nla[NFTA_FLOWTABLE_HOOK], @@ -6856,6 +6857,17 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, } } + if (nla[NFTA_FLOWTABLE_FLAGS]) { + flags = ntohl(nla_get_be32(nla[NFTA_FLOWTABLE_FLAGS])); + if (flags & ~NFT_FLOWTABLE_MASK) + return -EOPNOTSUPP; + if ((flowtable->data.flags & NFT_FLOWTABLE_HW_OFFLOAD) ^ + (flags & NFT_FLOWTABLE_HW_OFFLOAD)) + return -EOPNOTSUPP; + } else { + flags = flowtable->data.flags; + } + err = nft_register_flowtable_net_hooks(ctx->net, ctx->table, &flowtable_hook.list, flowtable); if (err < 0) @@ -6869,6 +6881,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, goto err_flowtable_update_hook; } + nft_trans_flowtable_flags(trans) = flags; nft_trans_flowtable(trans) = flowtable; nft_trans_flowtable_update(trans) = true; INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); @@ -8178,6 +8191,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) break; case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) { + nft_trans_flowtable(trans)->data.flags = + nft_trans_flowtable_flags(trans); nf_tables_flowtable_notify(&trans->ctx, nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans), -- cgit v1.2.3 From 8a2dc6af67a0c9f65a22ea40fc79974ee8f368c7 Mon Sep 17 00:00:00 2001 From: Bhaskar Chowdhury Date: Fri, 19 Mar 2021 10:16:23 +0530 Subject: sch_red: Fix a typo s/recalcultion/recalculation/ Signed-off-by: Bhaskar Chowdhury Signed-off-by: David S. Miller --- include/net/red.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/red.h b/include/net/red.h index 9e6647c4ccd1..0b39eff1d50a 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -295,7 +295,7 @@ static inline unsigned long red_calc_qavg_from_idle_time(const struct red_parms int shift; /* - * The problem: ideally, average length queue recalcultion should + * The problem: ideally, average length queue recalculation should * be done over constant clock intervals. This is too expensive, so * that the calculation is driven by outgoing packets. * When the queue is idle we have to model this clock by hand. -- cgit v1.2.3