diff options
34 files changed, 176 insertions, 90 deletions
diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst index adc4bf4f3c50..28925e19622d 100644 --- a/Documentation/networking/bonding.rst +++ b/Documentation/networking/bonding.rst @@ -776,10 +776,11 @@ peer_notif_delay Specify the delay, in milliseconds, between each peer notification (gratuitous ARP and unsolicited IPv6 Neighbor Advertisement) when they are issued after a failover event. - This delay should be a multiple of the link monitor interval - (arp_interval or miimon, whichever is active). The default - value is 0 which means to match the value of the link monitor - interval. + This delay should be a multiple of the MII link monitor interval + (miimon). + + The valid range is 0 - 300000. The default value is 0, which means + to match the value of the MII link monitor interval. prio Slave priority. A higher number means higher priority. diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index a164ff074356..5b75c3f7a137 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -116,8 +116,8 @@ Contents: udplite vrf vxlan - x25-iface x25 + x25-iface xfrm_device xfrm_proc xfrm_sync diff --git a/Documentation/networking/x25-iface.rst b/Documentation/networking/x25-iface.rst index f34e9ec64937..285cefcfce87 100644 --- a/Documentation/networking/x25-iface.rst +++ b/Documentation/networking/x25-iface.rst @@ -1,8 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 -============================- X.25 Device Driver Interface -============================- +============================ Version 1.1 diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index c2d080fc4fc4..27cbe148f0db 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -84,6 +84,11 @@ nla_put_failure: return -EMSGSIZE; } +/* Limit the max delay range to 300s */ +static struct netlink_range_validation delay_range = { + .max = 300000, +}; + static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = { [IFLA_BOND_MODE] = { .type = NLA_U8 }, [IFLA_BOND_ACTIVE_SLAVE] = { .type = NLA_U32 }, @@ -114,7 +119,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = { [IFLA_BOND_AD_ACTOR_SYSTEM] = { .type = NLA_BINARY, .len = ETH_ALEN }, [IFLA_BOND_TLB_DYNAMIC_LB] = { .type = NLA_U8 }, - [IFLA_BOND_PEER_NOTIF_DELAY] = { .type = NLA_U32 }, + [IFLA_BOND_PEER_NOTIF_DELAY] = NLA_POLICY_FULL_RANGE(NLA_U32, &delay_range), [IFLA_BOND_MISSED_MAX] = { .type = NLA_U8 }, [IFLA_BOND_NS_IP6_TARGET] = { .type = NLA_NESTED }, }; diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 0498fc6731f8..f3f27f0bd2a6 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -169,6 +169,12 @@ static const struct bond_opt_value bond_num_peer_notif_tbl[] = { { NULL, -1, 0} }; +static const struct bond_opt_value bond_peer_notif_delay_tbl[] = { + { "off", 0, 0}, + { "maxval", 300000, BOND_VALFLAG_MAX}, + { NULL, -1, 0} +}; + static const struct bond_opt_value bond_primary_reselect_tbl[] = { { "always", BOND_PRI_RESELECT_ALWAYS, BOND_VALFLAG_DEFAULT}, { "better", BOND_PRI_RESELECT_BETTER, 0}, @@ -488,7 +494,7 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = { .id = BOND_OPT_PEER_NOTIF_DELAY, .name = "peer_notif_delay", .desc = "Delay between each peer notification on failover event, in milliseconds", - .values = bond_intmax_tbl, + .values = bond_peer_notif_delay_tbl, .set = bond_option_peer_notif_delay_set } }; diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 57ce74315eba..caa00c72aeeb 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -294,19 +294,6 @@ static int gve_napi_poll_dqo(struct napi_struct *napi, int budget) bool reschedule = false; int work_done = 0; - /* Clear PCI MSI-X Pending Bit Array (PBA) - * - * This bit is set if an interrupt event occurs while the vector is - * masked. If this bit is set and we reenable the interrupt, it will - * fire again. Since we're just about to poll the queue state, we don't - * need it to fire again. - * - * Under high softirq load, it's possible that the interrupt condition - * is triggered twice before we got the chance to process it. - */ - gve_write_irq_doorbell_dqo(priv, block, - GVE_ITR_NO_UPDATE_DQO | GVE_ITR_CLEAR_PBA_BIT_DQO); - if (block->tx) reschedule |= gve_tx_poll_dqo(block, /*do_clean=*/true); diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index 4c205afbd230..985cff910f30 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -654,7 +654,7 @@ __mtk_wed_detach(struct mtk_wed_device *dev) BIT(hw->index), BIT(hw->index)); } - if (!hw_list[!hw->index]->wed_dev && + if ((!hw_list[!hw->index] || !hw_list[!hw->index]->wed_dev) && hw->eth->dma_dev != hw->eth->dev) mtk_eth_set_dma_device(hw->eth, hw->eth->dev); diff --git a/drivers/net/ethernet/mscc/vsc7514_regs.c b/drivers/net/ethernet/mscc/vsc7514_regs.c index ef6fd3f6be30..5595bfe84bbb 100644 --- a/drivers/net/ethernet/mscc/vsc7514_regs.c +++ b/drivers/net/ethernet/mscc/vsc7514_regs.c @@ -307,15 +307,15 @@ static const u32 vsc7514_sys_regmap[] = { REG(SYS_COUNT_DROP_YELLOW_PRIO_4, 0x000218), REG(SYS_COUNT_DROP_YELLOW_PRIO_5, 0x00021c), REG(SYS_COUNT_DROP_YELLOW_PRIO_6, 0x000220), - REG(SYS_COUNT_DROP_YELLOW_PRIO_7, 0x000214), - REG(SYS_COUNT_DROP_GREEN_PRIO_0, 0x000218), - REG(SYS_COUNT_DROP_GREEN_PRIO_1, 0x00021c), - REG(SYS_COUNT_DROP_GREEN_PRIO_2, 0x000220), - REG(SYS_COUNT_DROP_GREEN_PRIO_3, 0x000224), - REG(SYS_COUNT_DROP_GREEN_PRIO_4, 0x000228), - REG(SYS_COUNT_DROP_GREEN_PRIO_5, 0x00022c), - REG(SYS_COUNT_DROP_GREEN_PRIO_6, 0x000230), - REG(SYS_COUNT_DROP_GREEN_PRIO_7, 0x000234), + REG(SYS_COUNT_DROP_YELLOW_PRIO_7, 0x000224), + REG(SYS_COUNT_DROP_GREEN_PRIO_0, 0x000228), + REG(SYS_COUNT_DROP_GREEN_PRIO_1, 0x00022c), + REG(SYS_COUNT_DROP_GREEN_PRIO_2, 0x000230), + REG(SYS_COUNT_DROP_GREEN_PRIO_3, 0x000234), + REG(SYS_COUNT_DROP_GREEN_PRIO_4, 0x000238), + REG(SYS_COUNT_DROP_GREEN_PRIO_5, 0x00023c), + REG(SYS_COUNT_DROP_GREEN_PRIO_6, 0x000240), + REG(SYS_COUNT_DROP_GREEN_PRIO_7, 0x000244), REG(SYS_RESET_CFG, 0x000508), REG(SYS_CMID, 0x00050c), REG(SYS_VLAN_ETYPE_CFG, 0x000510), diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 460b3d4f2245..ab5133eb1d51 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -436,6 +436,9 @@ static int ipvlan_process_v4_outbound(struct sk_buff *skb) goto err; } skb_dst_set(skb, &rt->dst); + + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + err = ip_local_out(net, skb->sk, skb); if (unlikely(net_xmit_eval(err))) dev->stats.tx_errors++; @@ -474,6 +477,9 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb) goto err; } skb_dst_set(skb, dst); + + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + err = ip6_local_out(net, skb->sk, skb); if (unlikely(net_xmit_eval(err))) dev->stats.tx_errors++; diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 539cd43eae8d..f19d48c94fe0 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -1203,7 +1203,7 @@ static const struct xpcs_compat synopsys_xpcs_compat[DW_XPCS_INTERFACE_MAX] = { [DW_XPCS_2500BASEX] = { .supported = xpcs_2500basex_features, .interface = xpcs_2500basex_interfaces, - .num_interfaces = ARRAY_SIZE(xpcs_2500basex_features), + .num_interfaces = ARRAY_SIZE(xpcs_2500basex_interfaces), .an_mode = DW_2500BASEX, }, }; diff --git a/drivers/net/tap.c b/drivers/net/tap.c index ce993cc75bf3..d30d730ed5a7 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -742,7 +742,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control, /* Move network header to the right position for VLAN tagged packets */ if (eth_type_vlan(skb->protocol) && - __vlan_get_protocol(skb, skb->protocol, &depth) != 0) + vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); /* copy skb_ubuf_info for callback when skb has no error */ @@ -1197,7 +1197,7 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp) /* Move network header to the right position for VLAN tagged packets */ if (eth_type_vlan(skb->protocol) && - __vlan_get_protocol(skb, skb->protocol, &depth) != 0) + vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); rcu_read_lock(); diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 0f40f379d75c..6ba71957851e 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -637,6 +637,23 @@ static inline __be16 vlan_get_protocol(const struct sk_buff *skb) return __vlan_get_protocol(skb, skb->protocol, NULL); } +/* This version of __vlan_get_protocol() also pulls mac header in skb->head */ +static inline __be16 vlan_get_protocol_and_depth(struct sk_buff *skb, + __be16 type, int *depth) +{ + int maclen; + + type = __vlan_get_protocol(skb, type, &maclen); + + if (type) { + if (!pskb_may_pull(skb, maclen)) + type = 0; + else if (depth) + *depth = maclen; + } + return type; +} + /* A getter for the SKB protocol field which will handle VLAN tags consistently * whether VLAN acceleration is enabled or not. */ diff --git a/include/net/bonding.h b/include/net/bonding.h index a60a24923b55..0efef2a952b7 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -233,7 +233,7 @@ struct bonding { */ spinlock_t mode_lock; spinlock_t stats_lock; - u8 send_peer_notif; + u32 send_peer_notif; u8 igmp_retrans; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_entry; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 57744704ff69..84d6dd5e5b1a 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -42,7 +42,7 @@ int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb eth_type_vlan(skb->protocol)) { int depth; - if (!__vlan_get_protocol(skb, skb->protocol, &depth)) + if (!vlan_get_protocol_and_depth(skb, skb->protocol, &depth)) goto drop; skb_set_network_header(skb, depth); diff --git a/net/core/datagram.c b/net/core/datagram.c index 5662dff3d381..176eb5834746 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -807,18 +807,21 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, { struct sock *sk = sock->sk; __poll_t mask; + u8 shutdown; sock_poll_wait(file, sock, wait); mask = 0; /* exceptional events? */ - if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) + if (READ_ONCE(sk->sk_err) || + !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); - if (sk->sk_shutdown & RCV_SHUTDOWN) + shutdown = READ_ONCE(sk->sk_shutdown); + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; /* readable? */ @@ -827,10 +830,12 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, /* Connection-based need to check for termination and startup */ if (connection_based(sk)) { - if (sk->sk_state == TCP_CLOSE) + int state = READ_ONCE(sk->sk_state); + + if (state == TCP_CLOSE) mask |= EPOLLHUP; /* connection hasn't started yet? */ - if (sk->sk_state == TCP_SYN_SENT) + if (state == TCP_SYN_SENT) return mask; } diff --git a/net/core/dev.c b/net/core/dev.c index 735096d42c1d..b3c13e041935 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3335,7 +3335,7 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth) type = eth->h_proto; } - return __vlan_get_protocol(skb, type, depth); + return vlan_get_protocol_and_depth(skb, type, depth); } /* openvswitch calls this on rx path, so we need a different check. diff --git a/net/core/stream.c b/net/core/stream.c index 434446ab14c5..f5c4e47df165 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -73,8 +73,8 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p) add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending++; done = sk_wait_event(sk, timeo_p, - !sk->sk_err && - !((1 << sk->sk_state) & + !READ_ONCE(sk->sk_err) && + !((1 << READ_ONCE(sk->sk_state)) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)), &wait); remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending--; @@ -87,9 +87,9 @@ EXPORT_SYMBOL(sk_stream_wait_connect); * sk_stream_closing - Return 1 if we still have things to send in our buffers. * @sk: socket to verify */ -static inline int sk_stream_closing(struct sock *sk) +static int sk_stream_closing(const struct sock *sk) { - return (1 << sk->sk_state) & + return (1 << READ_ONCE(sk->sk_state)) & (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK); } @@ -142,8 +142,8 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk->sk_write_pending++; - sk_wait_event(sk, ¤t_timeo, sk->sk_err || - (sk->sk_shutdown & SEND_SHUTDOWN) || + sk_wait_event(sk, ¤t_timeo, READ_ONCE(sk->sk_err) || + (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) || (sk_stream_memory_free(sk) && !vm_wait), &wait); sk->sk_write_pending--; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 940062e08f57..c4aab3aacbd8 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -894,7 +894,7 @@ int inet_shutdown(struct socket *sock, int how) EPOLLHUP, even on eg. unconnected UDP sockets -- RR */ fallthrough; default: - sk->sk_shutdown |= how; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | how); if (sk->sk_prot->shutdown) sk->sk_prot->shutdown(sk, how); break; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 20db115c38c4..4d6392c16b7a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -498,6 +498,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) __poll_t mask; struct sock *sk = sock->sk; const struct tcp_sock *tp = tcp_sk(sk); + u8 shutdown; int state; sock_poll_wait(file, sock, wait); @@ -540,9 +541,10 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) * NOTE. Check for TCP_CLOSE is added. The goal is to prevent * blocking on fresh not-connected or disconnected socket. --ANK */ - if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) + shutdown = READ_ONCE(sk->sk_shutdown); + if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected or passive Fast Open socket? */ @@ -559,7 +561,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (tcp_stream_is_readable(sk, target)) mask |= EPOLLIN | EPOLLRDNORM; - if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { + if (!(shutdown & SEND_SHUTDOWN)) { if (__sk_stream_is_writeable(sk, 1)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ @@ -2867,7 +2869,7 @@ void __tcp_close(struct sock *sk, long timeout) int data_was_unread = 0; int state; - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); @@ -3119,7 +3121,7 @@ int tcp_disconnect(struct sock *sk, int flags) inet_bhash2_reset_saddr(sk); - sk->sk_shutdown = 0; + WRITE_ONCE(sk->sk_shutdown, 0); sock_reset_flag(sk, SOCK_DONE); tp->srtt_us = 0; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); @@ -4649,7 +4651,7 @@ void tcp_done(struct sock *sk) if (req) reqsk_fastopen_remove(sk, req, false); - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_state_change(sk); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index ebf917511937..2e9547467edb 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -168,7 +168,7 @@ static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock, sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); ret = sk_wait_event(sk, &timeo, !list_empty(&psock->ingress_msg) || - !skb_queue_empty(&sk->sk_receive_queue), &wait); + !skb_queue_empty_lockless(&sk->sk_receive_queue), &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); return ret; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a057330d6f59..61b6710f337a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4362,7 +4362,7 @@ void tcp_fin(struct sock *sk) inet_csk_schedule_ack(sk); - sk->sk_shutdown |= RCV_SHUTDOWN; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN); sock_set_flag(sk, SOCK_DONE); switch (sk->sk_state) { @@ -6599,7 +6599,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) break; tcp_set_state(sk, TCP_FIN_WAIT2); - sk->sk_shutdown |= SEND_SHUTDOWN; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | SEND_SHUTDOWN); sk_dst_confirm(sk); diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index da7fe94bea2e..9ffbc667be6c 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -583,7 +583,8 @@ static int llc_ui_wait_for_disc(struct sock *sk, long timeout) add_wait_queue(sk_sleep(sk), &wait); while (1) { - if (sk_wait_event(sk, &timeout, sk->sk_state == TCP_CLOSE, &wait)) + if (sk_wait_event(sk, &timeout, + READ_ONCE(sk->sk_state) == TCP_CLOSE, &wait)) break; rc = -ERESTARTSYS; if (signal_pending(current)) @@ -603,7 +604,8 @@ static bool llc_ui_wait_for_conn(struct sock *sk, long timeout) add_wait_queue(sk_sleep(sk), &wait); while (1) { - if (sk_wait_event(sk, &timeout, sk->sk_state != TCP_SYN_SENT, &wait)) + if (sk_wait_event(sk, &timeout, + READ_ONCE(sk->sk_state) != TCP_SYN_SENT, &wait)) break; if (signal_pending(current) || !timeout) break; @@ -622,7 +624,7 @@ static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout) while (1) { rc = 0; if (sk_wait_event(sk, &timeout, - (sk->sk_shutdown & RCV_SHUTDOWN) || + (READ_ONCE(sk->sk_shutdown) & RCV_SHUTDOWN) || (!llc_data_accept_state(llc->state) && !llc->remote_busy_flag && !llc->p_flag), &wait)) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 7ef8b9a1e30c..c87804112d0c 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1990,7 +1990,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, skb_free_datagram(sk, skb); - if (nlk->cb_running && + if (READ_ONCE(nlk->cb_running) && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { ret = netlink_dump(sk); if (ret) { @@ -2302,7 +2302,7 @@ static int netlink_dump(struct sock *sk) if (cb->done) cb->done(cb); - nlk->cb_running = false; + WRITE_ONCE(nlk->cb_running, false); module = cb->module; skb = cb->skb; mutex_unlock(nlk->cb_mutex); @@ -2365,7 +2365,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, goto error_put; } - nlk->cb_running = true; + WRITE_ONCE(nlk->cb_running, true); nlk->dump_done_errno = INT_MAX; mutex_unlock(nlk->cb_mutex); @@ -2703,7 +2703,7 @@ static int netlink_native_seq_show(struct seq_file *seq, void *v) nlk->groups ? (u32)nlk->groups[0] : 0, sk_rmem_alloc_get(s), sk_wmem_alloc_get(s), - nlk->cb_running, + READ_ONCE(nlk->cb_running), refcount_read(&s->sk_refcnt), atomic_read(&s->sk_drops), sock_i_ino(s) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 640d94e34635..94c6a1ffa459 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1934,10 +1934,8 @@ static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) /* Move network header to the right position for VLAN tagged packets */ if (likely(skb->dev->type == ARPHRD_ETHER) && eth_type_vlan(skb->protocol) && - __vlan_get_protocol(skb, skb->protocol, &depth) != 0) { - if (pskb_may_pull(skb, depth)) - skb_set_network_header(skb, depth); - } + vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) + skb_set_network_header(skb, depth); skb_probe_transport_header(skb); } diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 31db7438857c..dbdf03e8aa5b 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -67,8 +67,8 @@ static void smc_close_stream_wait(struct smc_sock *smc, long timeout) rc = sk_wait_event(sk, &timeout, !smc_tx_prepared_sends(&smc->conn) || - sk->sk_err == ECONNABORTED || - sk->sk_err == ECONNRESET || + READ_ONCE(sk->sk_err) == ECONNABORTED || + READ_ONCE(sk->sk_err) == ECONNRESET || smc->conn.killed, &wait); if (rc) diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index 4380d32f5a5f..9a2f3638d161 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -267,9 +267,9 @@ int smc_rx_wait(struct smc_sock *smc, long *timeo, sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); add_wait_queue(sk_sleep(sk), &wait); rc = sk_wait_event(sk, timeo, - sk->sk_err || + READ_ONCE(sk->sk_err) || cflags->peer_conn_abort || - sk->sk_shutdown & RCV_SHUTDOWN || + READ_ONCE(sk->sk_shutdown) & RCV_SHUTDOWN || conn->killed || fcrit(conn), &wait); diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index f4b6a71ac488..45128443f1f1 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -113,8 +113,8 @@ static int smc_tx_wait(struct smc_sock *smc, int flags) break; /* at least 1 byte of free & no urgent data */ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk_wait_event(sk, &timeo, - sk->sk_err || - (sk->sk_shutdown & SEND_SHUTDOWN) || + READ_ONCE(sk->sk_err) || + (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) || smc_cdc_rxed_any_close(conn) || (atomic_read(&conn->sndbuf_space) && !conn->urg_tx_pend), diff --git a/net/socket.c b/net/socket.c index a7b4b37d86df..b7e01d0fe082 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2911,7 +2911,7 @@ static int do_recvmmsg(int fd, struct mmsghdr __user *mmsg, * error to return on the next call or if the * app asks about it using getsockopt(SO_ERROR). */ - sock->sk->sk_err = -err; + WRITE_ONCE(sock->sk->sk_err, -err); } out_put: fput_light(sock->file, fput_needed); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 37edfe10f8c6..dd73d71c02a9 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -314,9 +314,9 @@ static void tsk_rej_rx_queue(struct sock *sk, int error) tipc_sk_respond(sk, skb, error); } -static bool tipc_sk_connected(struct sock *sk) +static bool tipc_sk_connected(const struct sock *sk) { - return sk->sk_state == TIPC_ESTABLISHED; + return READ_ONCE(sk->sk_state) == TIPC_ESTABLISHED; } /* tipc_sk_type_connectionless - check if the socket is datagram socket diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index b32c112984dd..f2e7302a4d96 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -111,7 +111,8 @@ int wait_on_pending_writer(struct sock *sk, long *timeo) break; } - if (sk_wait_event(sk, timeo, !sk->sk_write_pending, &wait)) + if (sk_wait_event(sk, timeo, + !READ_ONCE(sk->sk_write_pending), &wait)) break; } remove_wait_queue(sk_sleep(sk), &wait); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index fb31e8a4409e..cc695c9f09ec 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -603,7 +603,7 @@ static void unix_release_sock(struct sock *sk, int embrion) /* Clear state */ unix_state_lock(sk); sock_orphan(sk); - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); path = u->path; u->path.dentry = NULL; u->path.mnt = NULL; @@ -628,7 +628,7 @@ static void unix_release_sock(struct sock *sk, int embrion) if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) { unix_state_lock(skpair); /* No more writes */ - skpair->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK); if (!skb_queue_empty(&sk->sk_receive_queue) || embrion) WRITE_ONCE(skpair->sk_err, ECONNRESET); unix_state_unlock(skpair); @@ -1442,7 +1442,7 @@ static long unix_wait_for_peer(struct sock *other, long timeo) sched = !sock_flag(other, SOCK_DEAD) && !(other->sk_shutdown & RCV_SHUTDOWN) && - unix_recvq_full(other); + unix_recvq_full_lockless(other); unix_state_unlock(other); @@ -3008,7 +3008,7 @@ static int unix_shutdown(struct socket *sock, int mode) ++mode; unix_state_lock(sk); - sk->sk_shutdown |= mode; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | mode); other = unix_peer(sk); if (other) sock_hold(other); @@ -3028,7 +3028,7 @@ static int unix_shutdown(struct socket *sock, int mode) if (mode&SEND_SHUTDOWN) peer_mode |= RCV_SHUTDOWN; unix_state_lock(other); - other->sk_shutdown |= peer_mode; + WRITE_ONCE(other->sk_shutdown, other->sk_shutdown | peer_mode); unix_state_unlock(other); other->sk_state_change(other); if (peer_mode == SHUTDOWN_MASK) @@ -3160,16 +3160,18 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa { struct sock *sk = sock->sk; __poll_t mask; + u8 shutdown; sock_poll_wait(file, sock, wait); mask = 0; + shutdown = READ_ONCE(sk->sk_shutdown); /* exceptional events? */ if (READ_ONCE(sk->sk_err)) mask |= EPOLLERR; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; /* readable? */ @@ -3203,9 +3205,11 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk, *other; unsigned int writable; __poll_t mask; + u8 shutdown; sock_poll_wait(file, sock, wait); mask = 0; + shutdown = READ_ONCE(sk->sk_shutdown); /* exceptional events? */ if (READ_ONCE(sk->sk_err) || @@ -3213,9 +3217,9 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; /* readable? */ diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh index db29a3146a86..607ba5c38977 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh @@ -6,6 +6,7 @@ ALL_TESTS=" prio arp_validate + num_grat_arp " REQUIRE_MZ=no @@ -255,6 +256,55 @@ arp_validate() arp_validate_ns "active-backup" } +garp_test() +{ + local param="$1" + local active_slave exp_num real_num i + RET=0 + + # create bond + bond_reset "${param}" + + bond_check_connection + [ $RET -ne 0 ] && log_test "num_grat_arp" "$retmsg" + + + # Add tc rules to count GARP number + for i in $(seq 0 2); do + tc -n ${g_ns} filter add dev s$i ingress protocol arp pref 1 handle 101 \ + flower skip_hw arp_op request arp_sip ${s_ip4} arp_tip ${s_ip4} action pass + done + + # Do failover + active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + ip -n ${s_ns} link set ${active_slave} down + + exp_num=$(echo "${param}" | cut -f6 -d ' ') + sleep $((exp_num + 2)) + + active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + + # check result + real_num=$(tc_rule_handle_stats_get "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}") + if [ "${real_num}" -ne "${exp_num}" ]; then + echo "$real_num garp packets sent on active slave ${active_slave}" + RET=1 + fi + + for i in $(seq 0 2); do + tc -n ${g_ns} filter del dev s$i ingress + done +} + +num_grat_arp() +{ + local val + for val in 10 20 30 50; do + garp_test "mode active-backup miimon 100 num_grat_arp $val peer_notify_delay 1000" + log_test "num_grat_arp" "active-backup miimon num_grat_arp $val" + done +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh index 4045ca97fb22..69ab99a56043 100644 --- a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh @@ -61,6 +61,8 @@ server_create() ip -n ${g_ns} link set s${i} up ip -n ${g_ns} link set s${i} master br0 ip -n ${s_ns} link set eth${i} master bond0 + + tc -n ${g_ns} qdisc add dev s${i} clsact done ip -n ${s_ns} link set bond0 up diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 057c3d0ad620..9ddb68dd6a08 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -791,8 +791,9 @@ tc_rule_handle_stats_get() local id=$1; shift local handle=$1; shift local selector=${1:-.packets}; shift + local netns=${1:-""}; shift - tc -j -s filter show $id \ + tc $netns -j -s filter show $id \ | jq ".[] | select(.options.handle == $handle) | \ .options.actions[0].stats$selector" } |