diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-09-28 17:47:33 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-09-28 17:47:33 -0700 |
commit | 02dc96ef6c25f990452c114c59d75c368a1f4c8f (patch) | |
tree | bddda0591191f65931195d3171743507d6cae7d6 /net | |
parent | edf445ad7c8d58c2784a5b733790e80999093d8f (diff) | |
parent | faeacb6ddb13b7a020b50b9246fe098653cfbd6e (diff) | |
download | linux-02dc96ef6c25f990452c114c59d75c368a1f4c8f.tar.bz2 |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from David Miller:
1) Sanity check URB networking device parameters to avoid divide by
zero, from Oliver Neukum.
2) Disable global multicast filter in NCSI, otherwise LLDP and IPV6
don't work properly. Longer term this needs a better fix tho. From
Vijay Khemka.
3) Small fixes to selftests (use ping when ping6 is not present, etc.)
from David Ahern.
4) Bring back rt_uses_gateway member of struct rtable, it's semantics
were not well understood and trying to remove it broke things. From
David Ahern.
5) Move usbnet snaity checking, ignore endpoints with invalid
wMaxPacketSize. From Bjørn Mork.
6) Missing Kconfig deps for sja1105 driver, from Mao Wenan.
7) Various small fixes to the mlx5 DR steering code, from Alaa Hleihel,
Alex Vesker, and Yevgeny Kliteynik
8) Missing CAP_NET_RAW checks in various places, from Ori Nimron.
9) Fix crash when removing sch_cbs entry while offloading is enabled,
from Vinicius Costa Gomes.
10) Signedness bug fixes, generally in looking at the result given by
of_get_phy_mode() and friends. From Dan Crapenter.
11) Disable preemption around BPF_PROG_RUN() calls, from Eric Dumazet.
12) Don't create VRF ipv6 rules if ipv6 is disabled, from David Ahern.
13) Fix quantization code in tcp_bbr, from Kevin Yang.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (127 commits)
net: tap: clean up an indentation issue
nfp: abm: fix memory leak in nfp_abm_u32_knode_replace
tcp: better handle TCP_USER_TIMEOUT in SYN_SENT state
sk_buff: drop all skb extensions on free and skb scrubbing
tcp_bbr: fix quantization code to not raise cwnd if not probing bandwidth
mlxsw: spectrum_flower: Fail in case user specifies multiple mirror actions
Documentation: Clarify trap's description
mlxsw: spectrum: Clear VLAN filters during port initialization
net: ena: clean up indentation issue
NFC: st95hf: clean up indentation issue
net: phy: micrel: add Asym Pause workaround for KSZ9021
net: socionext: ave: Avoid using netdev_err() before calling register_netdev()
ptp: correctly disable flags on old ioctls
lib: dimlib: fix help text typos
net: dsa: microchip: Always set regmap stride to 1
nfp: flower: fix memory leak in nfp_flower_spawn_vnic_reprs
nfp: flower: prevent memory leak in nfp_flower_spawn_phy_reprs
net/sched: Set default of CONFIG_NET_TC_SKB_EXT to N
vrf: Do not attempt to create IPv6 mcast rule if IPv6 is disabled
net: sched: sch_sfb: don't call qdisc_put() while holding tree lock
...
Diffstat (limited to 'net')
51 files changed, 305 insertions, 299 deletions
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 4072e9d394d6..b41375d4d295 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1023,6 +1023,11 @@ static int atalk_create(struct net *net, struct socket *sock, int protocol, */ if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM) goto out; + + rc = -EPERM; + if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW)) + goto out; + rc = -ENOMEM; sk = sk_alloc(net, PF_APPLETALK, GFP_KERNEL, &ddp_proto, kern); if (!sk) diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index ca5207767dc2..bb222b882b67 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -855,6 +855,8 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol, break; case SOCK_RAW: + if (!capable(CAP_NET_RAW)) + return -EPERM; break; default: return -ESOCKTNOSUPPORT; diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index a3d188dfbe75..d5028af750d5 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -12,11 +12,11 @@ config BATMAN_ADV depends on NET select LIBCRC32C help - B.A.T.M.A.N. (better approach to mobile ad-hoc networking) is - a routing protocol for multi-hop ad-hoc mesh networks. The - networks may be wired or wireless. See - https://www.open-mesh.org/ for more information and user space - tools. + B.A.T.M.A.N. (better approach to mobile ad-hoc networking) is + a routing protocol for multi-hop ad-hoc mesh networks. The + networks may be wired or wireless. See + https://www.open-mesh.org/ for more information and user space + tools. config BATMAN_ADV_BATMAN_V bool "B.A.T.M.A.N. V protocol" diff --git a/net/core/dev.c b/net/core/dev.c index 71b18e80389f..bf3ed413abaf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5666,7 +5666,7 @@ EXPORT_SYMBOL(gro_find_complete_by_type); static void napi_skb_free_stolen_head(struct sk_buff *skb) { skb_dst_drop(skb); - secpath_reset(skb); + skb_ext_put(skb); kmem_cache_free(skbuff_head_cache, skb); } @@ -5733,7 +5733,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->encapsulation = 0; skb_shinfo(skb)->gso_type = 0; skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); - secpath_reset(skb); + skb_ext_reset(skb); napi->skb = skb; } diff --git a/net/core/dst.c b/net/core/dst.c index 1325316d9eab..193af526e908 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -172,7 +172,7 @@ void dst_release(struct dst_entry *dst) int newrefcnt; newrefcnt = atomic_dec_return(&dst->__refcnt); - if (unlikely(newrefcnt < 0)) + if (WARN_ONCE(newrefcnt < 0, "dst_release underflow")) net_warn_ratelimited("%s: dst:%p refcnt:%d\n", __func__, dst, newrefcnt); if (!newrefcnt) @@ -187,7 +187,7 @@ void dst_release_immediate(struct dst_entry *dst) int newrefcnt; newrefcnt = atomic_dec_return(&dst->__refcnt); - if (unlikely(newrefcnt < 0)) + if (WARN_ONCE(newrefcnt < 0, "dst_release_immediate underflow")) net_warn_ratelimited("%s: dst:%p refcnt:%d\n", __func__, dst, newrefcnt); if (!newrefcnt) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f12e8a050edb..01d65206f4fb 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5119,7 +5119,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->skb_iif = 0; skb->ignore_df = 0; skb_dst_drop(skb); - secpath_reset(skb); + skb_ext_reset(skb); nf_reset(skb); nf_reset_trace(skb); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 1b7381ff787b..25aab672fc99 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -230,7 +230,8 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, &fl6, sk->sk_mark, opt, np->tclass); + err = ip6_xmit(sk, skb, &fl6, sk->sk_mark, opt, np->tclass, + sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -284,7 +285,7 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(skb, dst); - ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0); + ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0, 0); DCCP_INC_STATS(DCCP_MIB_OUTSEGS); DCCP_INC_STATS(DCCP_MIB_OUTRSTS); return; diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index badc5cfe4dc6..d93d4531aa9b 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -1008,6 +1008,9 @@ static int ieee802154_create(struct net *net, struct socket *sock, switch (sock->type) { case SOCK_RAW: + rc = -EPERM; + if (!capable(CAP_NET_RAW)) + goto out; proto = &ieee802154_raw_prot; ops = &ieee802154_raw_ops; break; diff --git a/net/ife/Kconfig b/net/ife/Kconfig index 6cd1f6d18f30..bcf650564db4 100644 --- a/net/ife/Kconfig +++ b/net/ife/Kconfig @@ -5,7 +5,7 @@ menuconfig NET_IFE depends on NET - tristate "Inter-FE based on IETF ForCES InterFE LFB" + tristate "Inter-FE based on IETF ForCES InterFE LFB" default n help Say Y here to add support of IFE encapsulation protocol diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 974de4d20f25..03381f3e12ba 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -492,8 +492,8 @@ config TCP_CONG_WESTWOOD wired networks and throughput over wireless links. config TCP_CONG_HTCP - tristate "H-TCP" - default m + tristate "H-TCP" + default m ---help--- H-TCP is a send-side only modifications of the TCP Reno protocol stack that optimizes the performance of TCP diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index f5c163d4771b..a9183543ca30 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -560,7 +560,7 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk, rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; - if (opt && opt->opt.is_strictroute && rt->rt_gw_family) + if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway) goto route_err; rcu_read_unlock(); return &rt->dst; @@ -598,7 +598,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; - if (opt && opt->opt.is_strictroute && rt->rt_gw_family) + if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway) goto route_err; return &rt->dst; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 06f6f280b9ff..00ec819f949b 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -123,7 +123,7 @@ int ip_forward(struct sk_buff *skb) rt = skb_rtable(skb); - if (opt->is_strictroute && rt->rt_gw_family) + if (opt->is_strictroute && rt->rt_uses_gateway) goto sr_failed; IPCB(skb)->flags |= IPSKB_FORWARDED; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 5eb73775c3f7..28fca408812c 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -499,7 +499,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, skb_dst_set_noref(skb, &rt->dst); packet_routed: - if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_gw_family) + if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway) goto no_route; /* OK, we know where to send it, allocate and build IP header. */ @@ -1694,7 +1694,6 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, inet_sk(sk)->tos = arg->tos; - sk->sk_priority = skb->priority; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; sk->sk_sndbuf = sysctl_wmem_default; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index b6a6f18c3dd1..7dcce724c78b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -635,6 +635,7 @@ static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnh if (fnhe->fnhe_gw) { rt->rt_flags |= RTCF_REDIRECTED; + rt->rt_uses_gateway = 1; rt->rt_gw_family = AF_INET; rt->rt_gw4 = fnhe->fnhe_gw; } @@ -1313,7 +1314,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = READ_ONCE(dst->dev->mtu); if (unlikely(ip_mtu_locked(dst))) { - if (rt->rt_gw_family && mtu > 576) + if (rt->rt_uses_gateway && mtu > 576) mtu = 576; } @@ -1569,6 +1570,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, struct fib_nh_common *nhc = FIB_RES_NHC(*res); if (nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK) { + rt->rt_uses_gateway = 1; rt->rt_gw_family = nhc->nhc_gw_family; /* only INET and INET6 are supported */ if (likely(nhc->nhc_gw_family == AF_INET)) @@ -1634,6 +1636,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev, rt->rt_iif = 0; rt->rt_pmtu = 0; rt->rt_mtu_locked = 0; + rt->rt_uses_gateway = 0; rt->rt_gw_family = 0; rt->rt_gw4 = 0; INIT_LIST_HEAD(&rt->rt_uncached); @@ -2694,6 +2697,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_genid = rt_genid_ipv4(net); rt->rt_flags = ort->rt_flags; rt->rt_type = ort->rt_type; + rt->rt_uses_gateway = ort->rt_uses_gateway; rt->rt_gw_family = ort->rt_gw_family; if (rt->rt_gw_family == AF_INET) rt->rt_gw4 = ort->rt_gw4; @@ -2778,21 +2782,23 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, if (nla_put_in_addr(skb, RTA_PREFSRC, fl4->saddr)) goto nla_put_failure; } - if (rt->rt_gw_family == AF_INET && - nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4)) { - goto nla_put_failure; - } else if (rt->rt_gw_family == AF_INET6) { - int alen = sizeof(struct in6_addr); - struct nlattr *nla; - struct rtvia *via; - - nla = nla_reserve(skb, RTA_VIA, alen + 2); - if (!nla) + if (rt->rt_uses_gateway) { + if (rt->rt_gw_family == AF_INET && + nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4)) { goto nla_put_failure; - - via = nla_data(nla); - via->rtvia_family = AF_INET6; - memcpy(via->rtvia_addr, &rt->rt_gw6, alen); + } else if (rt->rt_gw_family == AF_INET6) { + int alen = sizeof(struct in6_addr); + struct nlattr *nla; + struct rtvia *via; + + nla = nla_reserve(skb, RTA_VIA, alen + 2); + if (!nla) + goto nla_put_failure; + + via = nla_data(nla); + via->rtvia_family = AF_INET6; + memcpy(via->rtvia_addr, &rt->rt_gw6, alen); + } } expires = rt->dst.expires; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 95b59540eee1..32772d6ded4e 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -388,7 +388,7 @@ static u32 bbr_bdp(struct sock *sk, u32 bw, int gain) * which allows 2 outstanding 2-packet sequences, to try to keep pipe * full even with ACK-every-other-packet delayed ACKs. */ -static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd, int gain) +static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd) { struct bbr *bbr = inet_csk_ca(sk); @@ -399,7 +399,7 @@ static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd, int gain) cwnd = (cwnd + 1) & ~1U; /* Ensure gain cycling gets inflight above BDP even for small BDPs. */ - if (bbr->mode == BBR_PROBE_BW && gain > BBR_UNIT) + if (bbr->mode == BBR_PROBE_BW && bbr->cycle_idx == 0) cwnd += 2; return cwnd; @@ -411,7 +411,7 @@ static u32 bbr_inflight(struct sock *sk, u32 bw, int gain) u32 inflight; inflight = bbr_bdp(sk, bw, gain); - inflight = bbr_quantization_budget(sk, inflight, gain); + inflight = bbr_quantization_budget(sk, inflight); return inflight; } @@ -531,7 +531,7 @@ static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs, * due to aggregation (of data and/or ACKs) visible in the ACK stream. */ target_cwnd += bbr_ack_aggregation_cwnd(sk); - target_cwnd = bbr_quantization_budget(sk, target_cwnd, gain); + target_cwnd = bbr_quantization_budget(sk, target_cwnd); /* If we're below target cwnd, slow start cwnd toward target cwnd. */ if (bbr_full_bw_reached(sk)) /* only cut cwnd if we filled the pipe */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fd394ad179a0..2ee45e3755e9 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -771,6 +771,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) if (sk) { ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; + ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); } ip_send_unicast_reply(ctl_sk, @@ -866,6 +868,8 @@ static void tcp_v4_send_ack(const struct sock *sk, ctl_sk = this_cpu_read(*net->ipv4.tcp_sk); ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; + ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 8bcaf2586b68..bb140a5db8c0 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -266,6 +266,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tw->tw_transparent = inet->transparent; tw->tw_mark = sk->sk_mark; + tw->tw_priority = sk->sk_priority; tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale; tcptw->tw_rcv_nxt = tp->rcv_nxt; tcptw->tw_snd_nxt = tp->snd_nxt; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index dbd9d2d0ee63..40de2d2364a1 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -210,7 +210,7 @@ static int tcp_write_timeout(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); - bool expired, do_reset; + bool expired = false, do_reset; int retry_until; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { @@ -242,9 +242,10 @@ static int tcp_write_timeout(struct sock *sk) if (tcp_out_of_resources(sk, do_reset)) return 1; } + } + if (!expired) expired = retransmits_timed_out(sk, retry_until, icsk->icsk_user_timeout); - } tcp_fastopen_active_detect_blackhole(sk, expired); if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG)) diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index cdef8f9a3b01..35b84b52b702 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -85,6 +85,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL); xdst->u.rt.rt_type = rt->rt_type; + xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; xdst->u.rt.rt_gw_family = rt->rt_gw_family; if (rt->rt_gw_family == AF_INET) xdst->u.rt.rt_gw4 = rt->rt_gw4; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index d22b6c140f23..f9e8fe3ff0c5 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -287,7 +287,8 @@ static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg return false; suppress_route: - ip6_rt_put(rt); + if (!(arg->flags & FIB_LOOKUP_NOREF)) + ip6_rt_put(rt); return true; } diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 4da24aa6c696..0a0945a5b30d 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -133,7 +133,7 @@ int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused fl6.daddr = sk->sk_v6_daddr; res = ip6_xmit(sk, skb, &fl6, sk->sk_mark, rcu_dereference(np->opt), - np->tclass); + np->tclass, sk->sk_priority); rcu_read_unlock(); return res; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 87f47bc55c5e..6e2af411cd9c 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -318,7 +318,7 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, if (rt->dst.error == -EAGAIN) { ip6_rt_put_flags(rt, flags); rt = net->ipv6.ip6_null_entry; - if (!(flags | RT6_LOOKUP_F_DST_NOREF)) + if (!(flags & RT6_LOOKUP_F_DST_NOREF)) dst_hold(&rt->dst); } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 89a4c7c2e25d..edadee4a7e76 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -193,7 +193,7 @@ bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np) * which are using proper atomic operations or spinlocks. */ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, - __u32 mark, struct ipv6_txoptions *opt, int tclass) + __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority) { struct net *net = sock_net(sk); const struct ipv6_pinfo *np = inet6_sk(sk); @@ -258,7 +258,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, hdr->daddr = *first_hop; skb->protocol = htons(ETH_P_IPV6); - skb->priority = sk->sk_priority; + skb->priority = priority; skb->mark = mark; mtu = dst_mtu(dst); diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 6120a7800975..69443e9a3aa5 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -170,13 +170,13 @@ config IP6_NF_MATCH_RT To compile it as a module, choose M here. If unsure, say N. config IP6_NF_MATCH_SRH - tristate '"srh" Segment Routing header match support' - depends on NETFILTER_ADVANCED - help - srh matching allows you to match packets based on the segment + tristate '"srh" Segment Routing header match support' + depends on NETFILTER_ADVANCED + help + srh matching allows you to match packets based on the segment routing header of the packet. - To compile it as a module, choose M here. If unsure, say N. + To compile it as a module, choose M here. If unsure, say N. # The targets config IP6_NF_TARGET_HL @@ -249,10 +249,10 @@ config IP6_NF_SECURITY depends on SECURITY depends on NETFILTER_ADVANCED help - This option adds a `security' table to iptables, for use - with Mandatory Access Control (MAC) policy. + This option adds a `security' table to iptables, for use + with Mandatory Access Control (MAC) policy. - If unsure, say N. + If unsure, say N. config IP6_NF_NAT tristate "ip6tables NAT support" diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 87f44d3250ee..e3d9f4559c99 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -512,7 +512,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, np->tclass); + err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, np->tclass, + sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -803,7 +804,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int rst, - u8 tclass, __be32 label) + u8 tclass, __be32 label, u32 priority) { const struct tcphdr *th = tcp_hdr(skb); struct tcphdr *t1; @@ -907,7 +908,8 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); - ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass); + ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass, + priority); TCP_INC_STATS(net, TCP_MIB_OUTSEGS); if (rst) TCP_INC_STATS(net, TCP_MIB_OUTRSTS); @@ -930,6 +932,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) struct sock *sk1 = NULL; #endif __be32 label = 0; + u32 priority = 0; struct net *net; int oif = 0; @@ -990,16 +993,19 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) trace_tcp_send_reset(sk, skb); if (np->repflow) label = ip6_flowlabel(ipv6h); + priority = sk->sk_priority; } - if (sk->sk_state == TCP_TIME_WAIT) + if (sk->sk_state == TCP_TIME_WAIT) { label = cpu_to_be32(inet_twsk(sk)->tw_flowlabel); + priority = inet_twsk(sk)->tw_priority; + } } else { if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_TCP_RESET) label = ip6_flowlabel(ipv6h); } tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, - label); + label, priority); #ifdef CONFIG_TCP_MD5SIG out: @@ -1010,10 +1016,10 @@ out: static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, u8 tclass, - __be32 label) + __be32 label, u32 priority) { tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, key, 0, - tclass, label); + tclass, label, priority); } static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) @@ -1025,7 +1031,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp_raw() + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), - tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel)); + tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel), tw->tw_priority); inet_twsk_put(tw); } @@ -1048,7 +1054,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr), - 0, 0); + 0, 0, sk->sk_priority); } diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 8f12f5c6ab87..ea9e73428ed9 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -378,8 +378,12 @@ static int kcm_parse_func_strparser(struct strparser *strp, struct sk_buff *skb) { struct kcm_psock *psock = container_of(strp, struct kcm_psock, strp); struct bpf_prog *prog = psock->bpf_prog; + int res; - return BPF_PROG_RUN(prog, skb); + preempt_disable(); + res = BPF_PROG_RUN(prog, skb); + preempt_enable(); + return res; } static int kcm_read_sock_done(struct strparser *strp, int err) diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index 0b3f0673e1a2..ad3fd7f1da75 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -264,9 +264,7 @@ enum { ncsi_dev_state_config_ev, ncsi_dev_state_config_sma, ncsi_dev_state_config_ebf, -#if IS_ENABLED(CONFIG_IPV6) - ncsi_dev_state_config_egmf, -#endif + ncsi_dev_state_config_dgmf, ncsi_dev_state_config_ecnt, ncsi_dev_state_config_ec, ncsi_dev_state_config_ae, @@ -295,9 +293,6 @@ struct ncsi_dev_priv { #define NCSI_DEV_RESET 8 /* Reset state of NC */ unsigned int gma_flag; /* OEM GMA flag */ spinlock_t lock; /* Protect the NCSI device */ -#if IS_ENABLED(CONFIG_IPV6) - unsigned int inet6_addr_num; /* Number of IPv6 addresses */ -#endif unsigned int package_probe_id;/* Current ID during probe */ unsigned int package_num; /* Number of packages */ struct list_head packages; /* List of packages */ diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 755aab66dcab..70fe02697544 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -14,7 +14,6 @@ #include <net/sock.h> #include <net/addrconf.h> #include <net/ipv6.h> -#include <net/if_inet6.h> #include <net/genetlink.h> #include "internal.h" @@ -978,9 +977,7 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) case ncsi_dev_state_config_ev: case ncsi_dev_state_config_sma: case ncsi_dev_state_config_ebf: -#if IS_ENABLED(CONFIG_IPV6) - case ncsi_dev_state_config_egmf: -#endif + case ncsi_dev_state_config_dgmf: case ncsi_dev_state_config_ecnt: case ncsi_dev_state_config_ec: case ncsi_dev_state_config_ae: @@ -1033,23 +1030,23 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) } else if (nd->state == ncsi_dev_state_config_ebf) { nca.type = NCSI_PKT_CMD_EBF; nca.dwords[0] = nc->caps[NCSI_CAP_BC].cap; - if (ncsi_channel_is_tx(ndp, nc)) + /* if multicast global filtering is supported then + * disable it so that all multicast packet will be + * forwarded to management controller + */ + if (nc->caps[NCSI_CAP_GENERIC].cap & + NCSI_CAP_GENERIC_MC) + nd->state = ncsi_dev_state_config_dgmf; + else if (ncsi_channel_is_tx(ndp, nc)) nd->state = ncsi_dev_state_config_ecnt; else nd->state = ncsi_dev_state_config_ec; -#if IS_ENABLED(CONFIG_IPV6) - if (ndp->inet6_addr_num > 0 && - (nc->caps[NCSI_CAP_GENERIC].cap & - NCSI_CAP_GENERIC_MC)) - nd->state = ncsi_dev_state_config_egmf; - } else if (nd->state == ncsi_dev_state_config_egmf) { - nca.type = NCSI_PKT_CMD_EGMF; - nca.dwords[0] = nc->caps[NCSI_CAP_MC].cap; + } else if (nd->state == ncsi_dev_state_config_dgmf) { + nca.type = NCSI_PKT_CMD_DGMF; if (ncsi_channel_is_tx(ndp, nc)) nd->state = ncsi_dev_state_config_ecnt; else nd->state = ncsi_dev_state_config_ec; -#endif /* CONFIG_IPV6 */ } else if (nd->state == ncsi_dev_state_config_ecnt) { if (np->preferred_channel && nc != np->preferred_channel) @@ -1483,70 +1480,6 @@ out: return -ENODEV; } -#if IS_ENABLED(CONFIG_IPV6) -static int ncsi_inet6addr_event(struct notifier_block *this, - unsigned long event, void *data) -{ - struct inet6_ifaddr *ifa = data; - struct net_device *dev = ifa->idev->dev; - struct ncsi_dev *nd = ncsi_find_dev(dev); - struct ncsi_dev_priv *ndp = nd ? TO_NCSI_DEV_PRIV(nd) : NULL; - struct ncsi_package *np; - struct ncsi_channel *nc; - struct ncsi_cmd_arg nca; - bool action; - int ret; - - if (!ndp || (ipv6_addr_type(&ifa->addr) & - (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK))) - return NOTIFY_OK; - - switch (event) { - case NETDEV_UP: - action = (++ndp->inet6_addr_num) == 1; - nca.type = NCSI_PKT_CMD_EGMF; - break; - case NETDEV_DOWN: - action = (--ndp->inet6_addr_num == 0); - nca.type = NCSI_PKT_CMD_DGMF; - break; - default: - return NOTIFY_OK; - } - - /* We might not have active channel or packages. The IPv6 - * required multicast will be enabled when active channel - * or packages are chosen. - */ - np = ndp->active_package; - nc = ndp->active_channel; - if (!action || !np || !nc) - return NOTIFY_OK; - - /* We needn't enable or disable it if the function isn't supported */ - if (!(nc->caps[NCSI_CAP_GENERIC].cap & NCSI_CAP_GENERIC_MC)) - return NOTIFY_OK; - - nca.ndp = ndp; - nca.req_flags = 0; - nca.package = np->id; - nca.channel = nc->id; - nca.dwords[0] = nc->caps[NCSI_CAP_MC].cap; - ret = ncsi_xmit_cmd(&nca); - if (ret) { - netdev_warn(dev, "Fail to %s global multicast filter (%d)\n", - (event == NETDEV_UP) ? "enable" : "disable", ret); - return NOTIFY_DONE; - } - - return NOTIFY_OK; -} - -static struct notifier_block ncsi_inet6addr_notifier = { - .notifier_call = ncsi_inet6addr_event, -}; -#endif /* CONFIG_IPV6 */ - static int ncsi_kick_channels(struct ncsi_dev_priv *ndp) { struct ncsi_dev *nd = &ndp->ndev; @@ -1725,11 +1658,6 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev, } spin_lock_irqsave(&ncsi_dev_lock, flags); -#if IS_ENABLED(CONFIG_IPV6) - ndp->inet6_addr_num = 0; - if (list_empty(&ncsi_dev_list)) - register_inet6addr_notifier(&ncsi_inet6addr_notifier); -#endif list_add_tail_rcu(&ndp->node, &ncsi_dev_list); spin_unlock_irqrestore(&ncsi_dev_lock, flags); @@ -1896,10 +1824,6 @@ void ncsi_unregister_dev(struct ncsi_dev *nd) spin_lock_irqsave(&ncsi_dev_lock, flags); list_del_rcu(&ndp->node); -#if IS_ENABLED(CONFIG_IPV6) - if (list_empty(&ncsi_dev_list)) - unregister_inet6addr_notifier(&ncsi_inet6addr_notifier); -#endif spin_unlock_irqrestore(&ncsi_dev_lock, flags); ncsi_unregister_netlink(nd->dev); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 34ec7afec116..91efae88e8c2 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -697,7 +697,7 @@ config NF_FLOW_TABLE_INET tristate "Netfilter flow table mixed IPv4/IPv6 module" depends on NF_FLOW_TABLE help - This option adds the flow table mixed IPv4/IPv6 support. + This option adds the flow table mixed IPv4/IPv6 support. To compile it as a module, choose M here. diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index f6f1a0d5c47d..5b672e05d758 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -135,7 +135,7 @@ config IP_VS_WRR module, choose M here. If unsure, say N. config IP_VS_LC - tristate "least-connection scheduling" + tristate "least-connection scheduling" ---help--- The least-connection scheduling algorithm directs network connections to the server with the least number of active @@ -145,7 +145,7 @@ config IP_VS_LC module, choose M here. If unsure, say N. config IP_VS_WLC - tristate "weighted least-connection scheduling" + tristate "weighted least-connection scheduling" ---help--- The weighted least-connection scheduling algorithm directs network connections to the server with the least active connections @@ -333,7 +333,7 @@ config IP_VS_NFCT config IP_VS_PE_SIP tristate "SIP persistence engine" - depends on IP_VS_PROTO_UDP + depends on IP_VS_PROTO_UDP depends on NF_CONNTRACK_SIP ---help--- Allow persistence based on the SIP Call-ID diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e4a68dc42694..d481f9baca2f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1715,7 +1715,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, goto err2; } - nft_trans_chain_policy(trans) = -1; + nft_trans_chain_policy(trans) = NFT_CHAIN_POLICY_UNSET; if (nft_is_base_chain(chain)) nft_trans_chain_policy(trans) = policy; @@ -3562,8 +3562,11 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, NFT_SET_OBJECT)) return -EINVAL; /* Only one of these operations is supported */ - if ((flags & (NFT_SET_MAP | NFT_SET_EVAL | NFT_SET_OBJECT)) == - (NFT_SET_MAP | NFT_SET_EVAL | NFT_SET_OBJECT)) + if ((flags & (NFT_SET_MAP | NFT_SET_OBJECT)) == + (NFT_SET_MAP | NFT_SET_OBJECT)) + return -EOPNOTSUPP; + if ((flags & (NFT_SET_EVAL | NFT_SET_OBJECT)) == + (NFT_SET_EVAL | NFT_SET_OBJECT)) return -EOPNOTSUPP; } @@ -5595,6 +5598,22 @@ struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table, } EXPORT_SYMBOL_GPL(nft_flowtable_lookup); +void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx, + struct nft_flowtable *flowtable, + enum nft_trans_phase phase) +{ + switch (phase) { + case NFT_TRANS_PREPARE: + case NFT_TRANS_ABORT: + case NFT_TRANS_RELEASE: + flowtable->use--; + /* fall through */ + default: + return; + } +} +EXPORT_SYMBOL_GPL(nf_tables_deactivate_flowtable); + static struct nft_flowtable * nft_flowtable_lookup_byhandle(const struct nft_table *table, const struct nlattr *nla, u8 genmask) diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 21bb772cb4b7..e546f759b7a7 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -313,7 +313,7 @@ static int nft_flow_offload_chain(struct nft_chain *chain, policy = ppolicy ? *ppolicy : basechain->policy; /* Only default policy to accept is supported for now. */ - if (cmd == FLOW_BLOCK_BIND && policy != -1 && policy != NF_ACCEPT) + if (cmd == FLOW_BLOCK_BIND && policy == NF_DROP) return -EOPNOTSUPP; if (dev->netdev_ops->ndo_setup_tc) diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 22cf236eb5d5..f29bbc74c4bf 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -177,6 +177,23 @@ static int nft_flow_offload_init(const struct nft_ctx *ctx, return nf_ct_netns_get(ctx->net, ctx->family); } +static void nft_flow_offload_deactivate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + enum nft_trans_phase phase) +{ + struct nft_flow_offload *priv = nft_expr_priv(expr); + + nf_tables_deactivate_flowtable(ctx, priv->flowtable, phase); +} + +static void nft_flow_offload_activate(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + struct nft_flow_offload *priv = nft_expr_priv(expr); + + priv->flowtable->use++; +} + static void nft_flow_offload_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { @@ -205,6 +222,8 @@ static const struct nft_expr_ops nft_flow_offload_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_flow_offload)), .eval = nft_flow_offload_eval, .init = nft_flow_offload_init, + .activate = nft_flow_offload_activate, + .deactivate = nft_flow_offload_deactivate, .destroy = nft_flow_offload_destroy, .validate = nft_flow_offload_validate, .dump = nft_flow_offload_dump, diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index c0560bf3c31b..660bad688e2b 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -73,9 +73,6 @@ static int nft_lookup_init(const struct nft_ctx *ctx, if (IS_ERR(set)) return PTR_ERR(set); - if (set->flags & NFT_SET_EVAL) - return -EOPNOTSUPP; - priv->sreg = nft_parse_register(tb[NFTA_LOOKUP_SREG]); err = nft_validate_register_load(priv->sreg, set->klen); if (err < 0) diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 9b8742947aff..8dfea26536c9 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -1004,10 +1004,13 @@ static int llcp_sock_create(struct net *net, struct socket *sock, sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; - if (sock->type == SOCK_RAW) + if (sock->type == SOCK_RAW) { + if (!capable(CAP_NET_RAW)) + return -EPERM; sock->ops = &llcp_rawsock_ops; - else + } else { sock->ops = &llcp_sock_ops; + } sk = nfc_llcp_sock_alloc(sock, sock->type, GFP_ATOMIC, kern); if (sk == NULL) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index dde9d762edee..f30e406fbec5 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2294,7 +2294,7 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { [OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) }, [OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 }, [OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 }, - [OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 }, + [OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_UNSPEC }, [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED }, [OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 }, [OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 }, diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 6c8b0f6d28f9..88f98f27ad88 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -150,6 +150,7 @@ static void __qrtr_node_release(struct kref *kref) list_del(&node->item); mutex_unlock(&qrtr_node_lock); + cancel_work_sync(&node->work); skb_queue_purge(&node->rx_queue); kfree(node); } diff --git a/net/rds/Kconfig b/net/rds/Kconfig index 38ea7f0f2699..c64e154bc18f 100644 --- a/net/rds/Kconfig +++ b/net/rds/Kconfig @@ -23,6 +23,6 @@ config RDS_TCP This transport does not support RDMA operations. config RDS_DEBUG - bool "RDS debugging messages" + bool "RDS debugging messages" depends on RDS - default n + default n diff --git a/net/rds/bind.c b/net/rds/bind.c index 20c156a73e73..5b5fb4ca8d3e 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -244,7 +244,8 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) */ if (rs->rs_transport) { trans = rs->rs_transport; - if (trans->laddr_check(sock_net(sock->sk), + if (!trans->laddr_check || + trans->laddr_check(sock_net(sock->sk), binding_addr, scope_id) != 0) { ret = -ENOPROTOOPT; goto out; @@ -263,6 +264,8 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) sock_set_flag(sk, SOCK_RCU_FREE); ret = rds_add_bound(rs, binding_addr, &port, scope_id); + if (ret) + rs->rs_transport = NULL; out: release_sock(sk); diff --git a/net/sched/Kconfig b/net/sched/Kconfig index b3faafeafab9..2985509147a2 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -324,7 +324,7 @@ config NET_SCH_CAKE tristate "Common Applications Kept Enhanced (CAKE)" help Say Y here if you want to use the Common Applications Kept Enhanced - (CAKE) queue management algorithm. + (CAKE) queue management algorithm. To compile this driver as a module, choose M here: the module will be called sch_cake. @@ -730,8 +730,8 @@ config NET_CLS_ACT config NET_ACT_POLICE tristate "Traffic Policing" - depends on NET_CLS_ACT - ---help--- + depends on NET_CLS_ACT + ---help--- Say Y here if you want to do traffic policing, i.e. strict bandwidth limiting. This action replaces the existing policing module. @@ -740,9 +740,9 @@ config NET_ACT_POLICE module will be called act_police. config NET_ACT_GACT - tristate "Generic actions" - depends on NET_CLS_ACT - ---help--- + tristate "Generic actions" + depends on NET_CLS_ACT + ---help--- Say Y here to take generic actions such as dropping and accepting packets. @@ -750,15 +750,15 @@ config NET_ACT_GACT module will be called act_gact. config GACT_PROB - bool "Probability support" - depends on NET_ACT_GACT - ---help--- + bool "Probability support" + depends on NET_ACT_GACT + ---help--- Say Y here to use the generic action randomly or deterministically. config NET_ACT_MIRRED - tristate "Redirecting and Mirroring" - depends on NET_CLS_ACT - ---help--- + tristate "Redirecting and Mirroring" + depends on NET_CLS_ACT + ---help--- Say Y here to allow packets to be mirrored or redirected to other devices. @@ -766,10 +766,10 @@ config NET_ACT_MIRRED module will be called act_mirred. config NET_ACT_SAMPLE - tristate "Traffic Sampling" - depends on NET_CLS_ACT - select PSAMPLE - ---help--- + tristate "Traffic Sampling" + depends on NET_CLS_ACT + select PSAMPLE + ---help--- Say Y here to allow packet sampling tc action. The packet sample action consists of statistically choosing packets and sampling them using the psample module. @@ -778,9 +778,9 @@ config NET_ACT_SAMPLE module will be called act_sample. config NET_ACT_IPT - tristate "IPtables targets" - depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES - ---help--- + tristate "IPtables targets" + depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES + ---help--- Say Y here to be able to invoke iptables targets after successful classification. @@ -788,9 +788,9 @@ config NET_ACT_IPT module will be called act_ipt. config NET_ACT_NAT - tristate "Stateless NAT" - depends on NET_CLS_ACT - ---help--- + tristate "Stateless NAT" + depends on NET_CLS_ACT + ---help--- Say Y here to do stateless NAT on IPv4 packets. You should use netfilter for NAT unless you know what you are doing. @@ -798,18 +798,18 @@ config NET_ACT_NAT module will be called act_nat. config NET_ACT_PEDIT - tristate "Packet Editing" - depends on NET_CLS_ACT - ---help--- + tristate "Packet Editing" + depends on NET_CLS_ACT + ---help--- Say Y here if you want to mangle the content of packets. To compile this code as a module, choose M here: the module will be called act_pedit. config NET_ACT_SIMP - tristate "Simple Example (Debug)" - depends on NET_CLS_ACT - ---help--- + tristate "Simple Example (Debug)" + depends on NET_CLS_ACT + ---help--- Say Y here to add a simple action for demonstration purposes. It is meant as an example and for debugging purposes. It will print a configured policy string followed by the packet count @@ -821,9 +821,9 @@ config NET_ACT_SIMP module will be called act_simple. config NET_ACT_SKBEDIT - tristate "SKB Editing" - depends on NET_CLS_ACT - ---help--- + tristate "SKB Editing" + depends on NET_CLS_ACT + ---help--- Say Y here to change skb priority or queue_mapping settings. If unsure, say N. @@ -832,10 +832,10 @@ config NET_ACT_SKBEDIT module will be called act_skbedit. config NET_ACT_CSUM - tristate "Checksum Updating" - depends on NET_CLS_ACT && INET - select LIBCRC32C - ---help--- + tristate "Checksum Updating" + depends on NET_CLS_ACT && INET + select LIBCRC32C + ---help--- Say Y here to update some common checksum after some direct packet alterations. @@ -854,9 +854,9 @@ config NET_ACT_MPLS module will be called act_mpls. config NET_ACT_VLAN - tristate "Vlan manipulation" - depends on NET_CLS_ACT - ---help--- + tristate "Vlan manipulation" + depends on NET_CLS_ACT + ---help--- Say Y here to push or pop vlan headers. If unsure, say N. @@ -865,9 +865,9 @@ config NET_ACT_VLAN module will be called act_vlan. config NET_ACT_BPF - tristate "BPF based action" - depends on NET_CLS_ACT - ---help--- + tristate "BPF based action" + depends on NET_CLS_ACT + ---help--- Say Y here to execute BPF code on packets. The BPF code will decide if the packet should be dropped or not. @@ -877,10 +877,10 @@ config NET_ACT_BPF module will be called act_bpf. config NET_ACT_CONNMARK - tristate "Netfilter Connection Mark Retriever" - depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES - depends on NF_CONNTRACK && NF_CONNTRACK_MARK - ---help--- + tristate "Netfilter Connection Mark Retriever" + depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES + depends on NF_CONNTRACK && NF_CONNTRACK_MARK + ---help--- Say Y here to allow retrieving of conn mark If unsure, say N. @@ -889,10 +889,10 @@ config NET_ACT_CONNMARK module will be called act_connmark. config NET_ACT_CTINFO - tristate "Netfilter Connection Mark Actions" - depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES - depends on NF_CONNTRACK && NF_CONNTRACK_MARK - help + tristate "Netfilter Connection Mark Actions" + depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES + depends on NF_CONNTRACK && NF_CONNTRACK_MARK + help Say Y here to allow transfer of a connmark stored information. Current actions transfer connmark stored DSCP into ipv4/v6 diffserv and/or to transfer connmark to packet @@ -906,21 +906,21 @@ config NET_ACT_CTINFO module will be called act_ctinfo. config NET_ACT_SKBMOD - tristate "skb data modification action" - depends on NET_CLS_ACT - ---help--- - Say Y here to allow modification of skb data + tristate "skb data modification action" + depends on NET_CLS_ACT + ---help--- + Say Y here to allow modification of skb data - If unsure, say N. + If unsure, say N. - To compile this code as a module, choose M here: the - module will be called act_skbmod. + To compile this code as a module, choose M here: the + module will be called act_skbmod. config NET_ACT_IFE - tristate "Inter-FE action based on IETF ForCES InterFE LFB" - depends on NET_CLS_ACT - select NET_IFE - ---help--- + tristate "Inter-FE action based on IETF ForCES InterFE LFB" + depends on NET_CLS_ACT + select NET_IFE + ---help--- Say Y here to allow for sourcing and terminating metadata For details refer to netdev01 paper: "Distributing Linux Traffic Control Classifier-Action Subsystem" @@ -930,9 +930,9 @@ config NET_ACT_IFE module will be called act_ife. config NET_ACT_TUNNEL_KEY - tristate "IP tunnel metadata manipulation" - depends on NET_CLS_ACT - ---help--- + tristate "IP tunnel metadata manipulation" + depends on NET_CLS_ACT + ---help--- Say Y here to set/release ip tunnel metadata. If unsure, say N. @@ -941,9 +941,9 @@ config NET_ACT_TUNNEL_KEY module will be called act_tunnel_key. config NET_ACT_CT - tristate "connection tracking tc action" - depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT - help + tristate "connection tracking tc action" + depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT + help Say Y here to allow sending the packets to conntrack module. If unsure, say N. @@ -952,21 +952,20 @@ config NET_ACT_CT module will be called act_ct. config NET_IFE_SKBMARK - tristate "Support to encoding decoding skb mark on IFE action" - depends on NET_ACT_IFE + tristate "Support to encoding decoding skb mark on IFE action" + depends on NET_ACT_IFE config NET_IFE_SKBPRIO - tristate "Support to encoding decoding skb prio on IFE action" - depends on NET_ACT_IFE + tristate "Support to encoding decoding skb prio on IFE action" + depends on NET_ACT_IFE config NET_IFE_SKBTCINDEX - tristate "Support to encoding decoding skb tcindex on IFE action" - depends on NET_ACT_IFE + tristate "Support to encoding decoding skb tcindex on IFE action" + depends on NET_ACT_IFE config NET_TC_SKB_EXT bool "TC recirculation support" depends on NET_CLS_ACT - default y if NET_CLS_ACT select SKB_EXTENSIONS help diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 339712296164..2558f00f6b3e 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -831,6 +831,15 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) return c; } +static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = { + [TCA_ACT_KIND] = { .type = NLA_NUL_STRING, + .len = IFNAMSIZ - 1 }, + [TCA_ACT_INDEX] = { .type = NLA_U32 }, + [TCA_ACT_COOKIE] = { .type = NLA_BINARY, + .len = TC_COOKIE_MAX_SIZE }, + [TCA_ACT_OPTIONS] = { .type = NLA_NESTED }, +}; + struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, @@ -846,8 +855,8 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, int err; if (name == NULL) { - err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, NULL, - extack); + err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, + tcf_action_policy, extack); if (err < 0) goto err_out; err = -EINVAL; @@ -856,18 +865,9 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, NL_SET_ERR_MSG(extack, "TC action kind must be specified"); goto err_out; } - if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) { - NL_SET_ERR_MSG(extack, "TC action name too long"); - goto err_out; - } - if (tb[TCA_ACT_COOKIE]) { - int cklen = nla_len(tb[TCA_ACT_COOKIE]); - - if (cklen > TC_COOKIE_MAX_SIZE) { - NL_SET_ERR_MSG(extack, "TC cookie size above the maximum"); - goto err_out; - } + nla_strlcpy(act_name, kind, IFNAMSIZ); + if (tb[TCA_ACT_COOKIE]) { cookie = nla_memdup_cookie(tb); if (!cookie) { NL_SET_ERR_MSG(extack, "No memory to generate TC cookie"); @@ -1098,7 +1098,8 @@ static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla, int index; int err; - err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, NULL, extack); + err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, + tcf_action_policy, extack); if (err < 0) goto err_out; @@ -1152,7 +1153,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, b = skb_tail_pointer(skb); - err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, NULL, extack); + err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, + tcf_action_policy, extack); if (err < 0) goto err_out; @@ -1440,7 +1442,7 @@ static struct nlattr *find_dump_kind(struct nlattr **nla) if (tb[1] == NULL) return NULL; - if (nla_parse_nested_deprecated(tb2, TCA_ACT_MAX, tb[1], NULL, NULL) < 0) + if (nla_parse_nested_deprecated(tb2, TCA_ACT_MAX, tb[1], tcf_action_policy, NULL) < 0) return NULL; kind = tb2[TCA_ACT_KIND]; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 692c4c9040fd..514456a0b9a8 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -146,6 +146,7 @@ static bool tcf_sample_dev_ok_push(struct net_device *dev) case ARPHRD_TUNNEL6: case ARPHRD_SIT: case ARPHRD_IPGRE: + case ARPHRD_IP6GRE: case ARPHRD_VOID: case ARPHRD_NONE: return false; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 32577c248968..64584a1df425 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2894,8 +2894,10 @@ out: void tcf_exts_destroy(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT - tcf_action_destroy(exts->actions, TCA_ACT_UNBIND); - kfree(exts->actions); + if (exts->actions) { + tcf_action_destroy(exts->actions, TCA_ACT_UNBIND); + kfree(exts->actions); + } exts->nr_actions = 0; #endif } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 1047825d9f48..81d58b280612 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1390,7 +1390,8 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) } const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = { - [TCA_KIND] = { .type = NLA_STRING }, + [TCA_KIND] = { .type = NLA_NUL_STRING, + .len = IFNAMSIZ - 1 }, [TCA_RATE] = { .type = NLA_BINARY, .len = sizeof(struct tc_estimator) }, [TCA_STAB] = { .type = NLA_NESTED }, diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index 93b58fde99b7..1bef152c5721 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -392,7 +392,6 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt, { struct cbs_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); - int err; if (!opt) { NL_SET_ERR_MSG(extack, "Missing CBS qdisc options which are mandatory"); @@ -404,6 +403,10 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt, if (!q->qdisc) return -ENOMEM; + spin_lock(&cbs_list_lock); + list_add(&q->cbs_list, &cbs_list); + spin_unlock(&cbs_list_lock); + qdisc_hash_add(q->qdisc, false); q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0); @@ -413,17 +416,7 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt, qdisc_watchdog_init(&q->watchdog, sch); - err = cbs_change(sch, opt, extack); - if (err) - return err; - - if (!q->offload) { - spin_lock(&cbs_list_lock); - list_add(&q->cbs_list, &cbs_list); - spin_unlock(&cbs_list_lock); - } - - return 0; + return cbs_change(sch, opt, extack); } static void cbs_destroy(struct Qdisc *sch) @@ -431,15 +424,18 @@ static void cbs_destroy(struct Qdisc *sch) struct cbs_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); - spin_lock(&cbs_list_lock); - list_del(&q->cbs_list); - spin_unlock(&cbs_list_lock); + /* Nothing to do if we couldn't create the underlying qdisc */ + if (!q->qdisc) + return; qdisc_watchdog_cancel(&q->watchdog); cbs_disable_offload(dev, q); - if (q->qdisc) - qdisc_put(q->qdisc); + spin_lock(&cbs_list_lock); + list_del(&q->cbs_list); + spin_unlock(&cbs_list_lock); + + qdisc_put(q->qdisc); } static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 7bcf20ef9145..8184c87da8be 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1302,6 +1302,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, struct htb_class *cl = (struct htb_class *)*arg, *parent; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_HTB_MAX + 1]; + struct Qdisc *parent_qdisc = NULL; struct tc_htb_opt *hopt; u64 rate64, ceil64; int warn = 0; @@ -1401,7 +1402,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (parent && !parent->level) { /* turn parent into inner node */ qdisc_purge_queue(parent->leaf.q); - qdisc_put(parent->leaf.q); + parent_qdisc = parent->leaf.q; if (parent->prio_activity) htb_deactivate(q, parent); @@ -1480,6 +1481,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, cl->cbuffer = PSCHED_TICKS2NS(hopt->cbuffer); sch_tree_unlock(sch); + qdisc_put(parent_qdisc); if (warn) pr_warn("HTB: quantum of class %X is %s. Consider r2q change.\n", diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index e1087746f6a2..b2b7fdb06fc6 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -174,7 +174,8 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, { struct multiq_sched_data *q = qdisc_priv(sch); struct tc_multiq_qopt *qopt; - int i; + struct Qdisc **removed; + int i, n_removed = 0; if (!netif_is_multiqueue(qdisc_dev(sch))) return -EOPNOTSUPP; @@ -185,6 +186,11 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, qopt->bands = qdisc_dev(sch)->real_num_tx_queues; + removed = kmalloc(sizeof(*removed) * (q->max_bands - q->bands), + GFP_KERNEL); + if (!removed) + return -ENOMEM; + sch_tree_lock(sch); q->bands = qopt->bands; for (i = q->bands; i < q->max_bands; i++) { @@ -192,13 +198,17 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, struct Qdisc *child = q->queues[i]; q->queues[i] = &noop_qdisc; - qdisc_tree_flush_backlog(child); - qdisc_put(child); + qdisc_purge_queue(child); + removed[n_removed++] = child; } } sch_tree_unlock(sch); + for (i = 0; i < n_removed; i++) + qdisc_put(removed[i]); + kfree(removed); + for (i = 0; i < q->bands; i++) { if (q->queues[i] == &noop_qdisc) { struct Qdisc *child, *old; @@ -213,11 +223,10 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, if (child != &noop_qdisc) qdisc_hash_add(child, true); - if (old != &noop_qdisc) { - qdisc_tree_flush_backlog(old); - qdisc_put(old); - } + if (old != &noop_qdisc) + qdisc_purge_queue(old); sch_tree_unlock(sch); + qdisc_put(old); } } } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index b17f2ed970e2..0e44039e729c 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -476,7 +476,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, * skb will be queued. */ if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) { - struct Qdisc *rootq = qdisc_root(sch); + struct Qdisc *rootq = qdisc_root_bh(sch); u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ q->duplicate = 0; @@ -777,7 +777,7 @@ static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, struct disttable *d; int i; - if (n > NETEM_DIST_MAX) + if (!n || n > NETEM_DIST_MAX) return -EINVAL; d = kvmalloc(sizeof(struct disttable) + n * sizeof(s16), GFP_KERNEL); diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 1dff8506a715..d448fe3068e5 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -488,7 +488,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct sfb_sched_data *q = qdisc_priv(sch); - struct Qdisc *child; + struct Qdisc *child, *old; struct nlattr *tb[TCA_SFB_MAX + 1]; const struct tc_sfb_qopt *ctl = &sfb_default_ops; u32 limit; @@ -518,8 +518,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt, qdisc_hash_add(child, true); sch_tree_lock(sch); - qdisc_tree_flush_backlog(q->qdisc); - qdisc_put(q->qdisc); + qdisc_purge_queue(q->qdisc); + old = q->qdisc; q->qdisc = child; q->rehash_interval = msecs_to_jiffies(ctl->rehash_interval); @@ -542,6 +542,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt, sfb_init_perturbation(1, q); sch_tree_unlock(sch); + qdisc_put(old); return 0; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e5f2fc726a98..dd860fea0148 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -215,7 +215,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport) rcu_read_lock(); res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt), - tclass); + tclass, sk->sk_priority); rcu_read_unlock(); return res; } diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index bba3104f128f..16d5f353163a 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -376,8 +376,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) return -EINVAL; } - headroom = ALIGN(headroom, 64); - size_chk = chunk_size - headroom - XDP_PACKET_HEADROOM; if (size_chk < 0) return -EINVAL; |