diff options
author | David S. Miller <davem@davemloft.net> | 2017-10-22 13:36:53 +0100 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2017-10-22 13:39:14 +0100 |
commit | f8ddadc4db6c7b7029b6d0e0d9af24f74ad27ca2 (patch) | |
tree | 0a6432aba336bae42313613f4c891bcfce02bd4e /net | |
parent | bdd091bab8c631bd2801af838e344fad34566410 (diff) | |
parent | b5ac3beb5a9f0ef0ea64cd85faf94c0dc4de0e42 (diff) | |
download | op-kernel-dev-f8ddadc4db6c7b7029b6d0e0d9af24f74ad27ca2.zip op-kernel-dev-f8ddadc4db6c7b7029b6d0e0d9af24f74ad27ca2.tar.gz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
There were quite a few overlapping sets of changes here.
Daniel's bug fix for off-by-ones in the new BPF branch instructions,
along with the added allowances for "data_end > ptr + x" forms
collided with the metadata additions.
Along with those three changes came veritifer test cases, which in
their final form I tried to group together properly. If I had just
trimmed GIT's conflict tags as-is, this would have split up the
meta tests unnecessarily.
In the socketmap code, a set of preemption disabling changes
overlapped with the rename of bpf_compute_data_end() to
bpf_compute_data_pointers().
Changes were made to the mv88e6060.c driver set addr method
which got removed in net-next.
The hyperv transport socket layer had a locking change in 'net'
which overlapped with a change of socket state macro usage
in 'net-next'.
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
35 files changed, 229 insertions, 139 deletions
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index f0e8268..fb61b6c 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -578,7 +578,7 @@ static int br_process_vlan_info(struct net_bridge *br, } *vinfo_last = NULL; - return 0; + return err; } return br_vlan_info(br, p, cmd, vinfo_curr); diff --git a/net/can/af_can.c b/net/can/af_can.c index 1f75e11..003b2d6 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -78,7 +78,7 @@ MODULE_PARM_DESC(stats_timer, "enable timer for statistics (default:on)"); static struct kmem_cache *rcv_cache __read_mostly; /* table of registered CAN protocols */ -static const struct can_proto *proto_tab[CAN_NPROTO] __read_mostly; +static const struct can_proto __rcu *proto_tab[CAN_NPROTO] __read_mostly; static DEFINE_MUTEX(proto_tab_lock); static atomic_t skbcounter = ATOMIC_INIT(0); @@ -788,7 +788,7 @@ int can_proto_register(const struct can_proto *cp) mutex_lock(&proto_tab_lock); - if (proto_tab[proto]) { + if (rcu_access_pointer(proto_tab[proto])) { pr_err("can: protocol %d already registered\n", proto); err = -EBUSY; } else @@ -812,7 +812,7 @@ void can_proto_unregister(const struct can_proto *cp) int proto = cp->protocol; mutex_lock(&proto_tab_lock); - BUG_ON(proto_tab[proto] != cp); + BUG_ON(rcu_access_pointer(proto_tab[proto]) != cp); RCU_INIT_POINTER(proto_tab[proto], NULL); mutex_unlock(&proto_tab_lock); @@ -875,9 +875,14 @@ static int can_pernet_init(struct net *net) spin_lock_init(&net->can.can_rcvlists_lock); net->can.can_rx_alldev_list = kzalloc(sizeof(struct dev_rcv_lists), GFP_KERNEL); - + if (!net->can.can_rx_alldev_list) + goto out; net->can.can_stats = kzalloc(sizeof(struct s_stats), GFP_KERNEL); + if (!net->can.can_stats) + goto out_free_alldev_list; net->can.can_pstats = kzalloc(sizeof(struct s_pstats), GFP_KERNEL); + if (!net->can.can_pstats) + goto out_free_can_stats; if (IS_ENABLED(CONFIG_PROC_FS)) { /* the statistics are updated every second (timer triggered) */ @@ -892,6 +897,13 @@ static int can_pernet_init(struct net *net) } return 0; + + out_free_can_stats: + kfree(net->can.can_stats); + out_free_alldev_list: + kfree(net->can.can_rx_alldev_list); + out: + return -ENOMEM; } static void can_pernet_exit(struct net *net) diff --git a/net/can/bcm.c b/net/can/bcm.c index 47a8748d..13690334 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1493,13 +1493,14 @@ static int bcm_init(struct sock *sk) static int bcm_release(struct socket *sock) { struct sock *sk = sock->sk; - struct net *net = sock_net(sk); + struct net *net; struct bcm_sock *bo; struct bcm_op *op, *next; - if (sk == NULL) + if (!sk) return 0; + net = sock_net(sk); bo = bcm_sk(sk); /* remove bcm_ops, timer, rx_unregister(), etc. */ diff --git a/net/core/dev.c b/net/core/dev.c index cf5894f..24ac908 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1149,9 +1149,8 @@ static int dev_alloc_name_ns(struct net *net, return ret; } -static int dev_get_valid_name(struct net *net, - struct net_device *dev, - const char *name) +int dev_get_valid_name(struct net *net, struct net_device *dev, + const char *name) { BUG_ON(!net); @@ -1167,6 +1166,7 @@ static int dev_get_valid_name(struct net *net, return 0; } +EXPORT_SYMBOL(dev_get_valid_name); /** * dev_change_name - change name of a device diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 709a4e6..f9c7a88 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -303,7 +303,18 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) case SIOCSIFTXQLEN: if (ifr->ifr_qlen < 0) return -EINVAL; - dev->tx_queue_len = ifr->ifr_qlen; + if (dev->tx_queue_len ^ ifr->ifr_qlen) { + unsigned int orig_len = dev->tx_queue_len; + + dev->tx_queue_len = ifr->ifr_qlen; + err = call_netdevice_notifiers( + NETDEV_CHANGE_TX_QUEUE_LEN, dev); + err = notifier_to_errno(err); + if (err) { + dev->tx_queue_len = orig_len; + return err; + } + } return 0; case SIOCSIFNAME: diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 0c40630..f8fcf45 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -452,7 +452,7 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, EXPORT_SYMBOL(ethtool_convert_link_mode_to_legacy_u32); /* return false if legacy contained non-0 deprecated fields - * transceiver/maxtxpkt/maxrxpkt. rest of ksettings always updated + * maxtxpkt/maxrxpkt. rest of ksettings always updated */ static bool convert_legacy_settings_to_link_ksettings( @@ -467,8 +467,7 @@ convert_legacy_settings_to_link_ksettings( * deprecated legacy fields, and they should not use * %ETHTOOL_GLINKSETTINGS/%ETHTOOL_SLINKSETTINGS */ - if (legacy_settings->transceiver || - legacy_settings->maxtxpkt || + if (legacy_settings->maxtxpkt || legacy_settings->maxrxpkt) retval = false; diff --git a/net/core/filter.c b/net/core/filter.c index ccf62f4..b79c44c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1840,31 +1840,31 @@ static const struct bpf_func_proto bpf_redirect_proto = { .arg2_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_sk_redirect_map, struct bpf_map *, map, u32, key, u64, flags) +BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, + struct bpf_map *, map, u32, key, u64, flags) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); if (unlikely(flags)) return SK_ABORTED; - ri->ifindex = key; - ri->flags = flags; - ri->map = map; + tcb->bpf.key = key; + tcb->bpf.flags = flags; + tcb->bpf.map = map; return SK_REDIRECT; } -struct sock *do_sk_redirect_map(void) +struct sock *do_sk_redirect_map(struct sk_buff *skb) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); struct sock *sk = NULL; - if (ri->map) { - sk = __sock_map_lookup_elem(ri->map, ri->ifindex); + if (tcb->bpf.map) { + sk = __sock_map_lookup_elem(tcb->bpf.map, tcb->bpf.key); - ri->ifindex = 0; - ri->map = NULL; - /* we do not clear flags for future lookup */ + tcb->bpf.key = 0; + tcb->bpf.map = NULL; } return sk; @@ -1874,9 +1874,10 @@ static const struct bpf_func_proto bpf_sk_redirect_map_proto = { .func = bpf_sk_redirect_map, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_ANYTHING, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) @@ -3902,7 +3903,6 @@ static bool sk_skb_is_valid_access(int off, int size, if (type == BPF_WRITE) { switch (off) { - case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, tc_index): case bpf_ctx_range(struct __sk_buff, priority): break; @@ -3912,6 +3912,8 @@ static bool sk_skb_is_valid_access(int off, int size, } switch (off) { + case bpf_ctx_range(struct __sk_buff, mark): + return false; case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 20b550d..04680a5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1551,7 +1551,10 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_LINKINFO] = { .type = NLA_NESTED }, [IFLA_NET_NS_PID] = { .type = NLA_U32 }, [IFLA_NET_NS_FD] = { .type = NLA_U32 }, - [IFLA_IFALIAS] = { .type = NLA_STRING, .len = IFALIASZ-1 }, + /* IFLA_IFALIAS is a string, but policy is set to NLA_BINARY to + * allow 0-length string (needed to remove an alias). + */ + [IFLA_IFALIAS] = { .type = NLA_BINARY, .len = IFALIASZ - 1 }, [IFLA_VFINFO_LIST] = {. type = NLA_NESTED }, [IFLA_VF_PORTS] = { .type = NLA_NESTED }, [IFLA_PORT_SELF] = { .type = NLA_NESTED }, @@ -2172,7 +2175,7 @@ static int do_setlink(const struct sk_buff *skb, dev->tx_queue_len = orig_len; goto errout; } - status |= DO_SETLINK_NOTIFY; + status |= DO_SETLINK_MODIFIED; } } @@ -2332,7 +2335,7 @@ static int do_setlink(const struct sk_buff *skb, errout: if (status & DO_SETLINK_MODIFIED) { - if (status & DO_SETLINK_NOTIFY) + if ((status & DO_SETLINK_NOTIFY) == DO_SETLINK_NOTIFY) netdev_state_change(dev); if (err < 0) @@ -4373,13 +4376,17 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi switch (event) { case NETDEV_REBOOT: + case NETDEV_CHANGEMTU: case NETDEV_CHANGEADDR: case NETDEV_CHANGENAME: case NETDEV_FEAT_CHANGE: case NETDEV_BONDING_FAILOVER: + case NETDEV_POST_TYPE_CHANGE: case NETDEV_NOTIFY_PEERS: + case NETDEV_CHANGEUPPER: case NETDEV_RESEND_IGMP: case NETDEV_CHANGEINFODATA: + case NETDEV_CHANGE_TX_QUEUE_LEN: rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, rtnl_get_event(event), GFP_KERNEL, NULL); break; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 4071750..97e604d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1124,9 +1124,13 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, err = __zerocopy_sg_from_iter(sk, skb, &msg->msg_iter, len); if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) { + struct sock *save_sk = skb->sk; + /* Streams do not free skb on error. Reset to prev state. */ msg->msg_iter = orig_iter; + skb->sk = sk; ___pskb_trim(skb, orig_len); + skb->sk = save_sk; return err; } @@ -1895,7 +1899,7 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta) } /* If we need update frag list, we are in troubles. - * Certainly, it possible to add an offset to skb data, + * Certainly, it is possible to add an offset to skb data, * but taking into account that pulling is expected to * be very rare operation, it is worth to fight against * further bloating skb head and crucify ourselves here instead. diff --git a/net/core/sock.c b/net/core/sock.c index 35656a9..7594000 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1677,12 +1677,17 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_dst_pending_confirm = 0; newsk->sk_wmem_queued = 0; newsk->sk_forward_alloc = 0; + + /* sk->sk_memcg will be populated at accept() time */ + newsk->sk_memcg = NULL; + atomic_set(&newsk->sk_drops, 0); newsk->sk_send_head = NULL; newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; atomic_set(&newsk->sk_zckey, 0); sock_reset_flag(newsk, SOCK_DONE); + cgroup_sk_alloc(&newsk->sk_cgrp_data); rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); @@ -1714,9 +1719,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_incoming_cpu = raw_smp_processor_id(); atomic64_set(&newsk->sk_cookie, 0); - mem_cgroup_sk_alloc(newsk); - cgroup_sk_alloc(&newsk->sk_cgrp_data); - /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.txt for details) diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index eed1ebf..b1e0dbe 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -36,9 +36,14 @@ int reuseport_alloc(struct sock *sk) * soft irq of receive path or setsockopt from process context */ spin_lock_bh(&reuseport_lock); - WARN_ONCE(rcu_dereference_protected(sk->sk_reuseport_cb, - lockdep_is_held(&reuseport_lock)), - "multiple allocations for the same socket"); + + /* Allocation attempts can occur concurrently via the setsockopt path + * and the bind/hash path. Nothing to do when we lose the race. + */ + if (rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock))) + goto out; + reuse = __reuseport_alloc(INIT_SOCKS); if (!reuse) { spin_unlock_bh(&reuseport_lock); @@ -49,6 +54,7 @@ int reuseport_alloc(struct sock *sk) reuse->num_socks = 1; rcu_assign_pointer(sk->sk_reuseport_cb, reuse); +out: spin_unlock_bh(&reuseport_lock); return 0; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 001c086..0490916 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -414,8 +414,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, sk_daddr_set(newsk, ireq->ir_rmt_addr); sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); newinet->inet_saddr = ireq->ir_loc_addr; - newinet->inet_opt = ireq->opt; - ireq->opt = NULL; + RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt)); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; newinet->inet_id = jiffies; @@ -430,7 +429,10 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); - + if (*own_req) + ireq->ireq_opt = NULL; + else + newinet->inet_opt = NULL; return newsk; exit_overflow: @@ -441,6 +443,7 @@ exit: __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; put_and_exit: + newinet->inet_opt = NULL; inet_csk_prepare_forced_close(newsk); dccp_done(newsk); goto exit; @@ -492,7 +495,7 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req ireq->ir_rmt_addr); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, - ireq->opt); + rcu_dereference(ireq->ireq_opt)); err = net_xmit_eval(err); } @@ -548,7 +551,7 @@ out: static void dccp_v4_reqsk_destructor(struct request_sock *req) { dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg); - kfree(inet_rsk(req)->opt); + kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1)); } void dccp_syn_ack_timeout(const struct request_sock *req) diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 8737412..e1d4d89 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -224,7 +224,7 @@ static int dns_resolver_match_preparse(struct key_match_data *match_data) static void dns_resolver_describe(const struct key *key, struct seq_file *m) { seq_puts(m, key->description); - if (key_is_instantiated(key)) { + if (key_is_positive(key)) { int err = PTR_ERR(key->payload.data[dns_key_error]); if (err) diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 91a2557..f48fe6f 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -70,11 +70,9 @@ config IP_MULTIPLE_TABLES address into account. Furthermore, the TOS (Type-Of-Service) field of the packet can be used for routing decisions as well. - If you are interested in this, please see the preliminary - documentation at <http://www.compendium.com.ar/policy-routing.txt> - and <ftp://post.tepkom.ru/pub/vol2/Linux/docs/advanced-routing.tex>. - You will need supporting software from - <ftp://ftp.tux.org/pub/net/ip-routing/>. + If you need more information, see the Linux Advanced + Routing and Traffic Control documentation at + <http://lartc.org/howto/lartc.rpdb.html> If unsure, say N. diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 2ae8f54..82178cc 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1951,7 +1951,7 @@ int cipso_v4_req_setattr(struct request_sock *req, buf = NULL; req_inet = inet_rsk(req); - opt = xchg(&req_inet->opt, opt); + opt = xchg((__force struct ip_options_rcu **)&req_inet->ireq_opt, opt); if (opt) kfree_rcu(opt, rcu); @@ -1973,11 +1973,13 @@ req_setattr_failure: * values on failure. * */ -static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr) +static int cipso_v4_delopt(struct ip_options_rcu __rcu **opt_ptr) { + struct ip_options_rcu *opt = rcu_dereference_protected(*opt_ptr, 1); int hdr_delta = 0; - struct ip_options_rcu *opt = *opt_ptr; + if (!opt || opt->opt.cipso == 0) + return 0; if (opt->opt.srr || opt->opt.rr || opt->opt.ts || opt->opt.router_alert) { u8 cipso_len; u8 cipso_off; @@ -2039,14 +2041,10 @@ static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr) */ void cipso_v4_sock_delattr(struct sock *sk) { - int hdr_delta; - struct ip_options_rcu *opt; struct inet_sock *sk_inet; + int hdr_delta; sk_inet = inet_sk(sk); - opt = rcu_dereference_protected(sk_inet->inet_opt, 1); - if (!opt || opt->opt.cipso == 0) - return; hdr_delta = cipso_v4_delopt(&sk_inet->inet_opt); if (sk_inet->is_icsk && hdr_delta > 0) { @@ -2066,15 +2064,7 @@ void cipso_v4_sock_delattr(struct sock *sk) */ void cipso_v4_req_delattr(struct request_sock *req) { - struct ip_options_rcu *opt; - struct inet_request_sock *req_inet; - - req_inet = inet_rsk(req); - opt = req_inet->opt; - if (!opt || opt->opt.cipso == 0) - return; - - cipso_v4_delopt(&req_inet->opt); + cipso_v4_delopt(&inet_rsk(req)->ireq_opt); } /** diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 5c965ec..ca03a1d 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -475,6 +475,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) } spin_unlock_bh(&queue->fastopenq.lock); } + mem_cgroup_sk_alloc(newsk); out: release_sock(sk); if (req) @@ -537,9 +538,10 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk, { const struct inet_request_sock *ireq = inet_rsk(req); struct net *net = read_pnet(&ireq->ireq_net); - struct ip_options_rcu *opt = ireq->opt; + struct ip_options_rcu *opt; struct rtable *rt; + opt = rcu_dereference(ireq->ireq_opt); flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, sk->sk_protocol, inet_sk_flowi_flags(sk), @@ -573,10 +575,9 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct flowi4 *fl4; struct rtable *rt; + opt = rcu_dereference(ireq->ireq_opt); fl4 = &newinet->cork.fl.u.ip4; - rcu_read_lock(); - opt = rcu_dereference(newinet->inet_opt); flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, sk->sk_protocol, inet_sk_flowi_flags(sk), @@ -589,13 +590,11 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, goto no_route; if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway) goto route_err; - rcu_read_unlock(); return &rt->dst; route_err: ip_rt_put(rt); no_route: - rcu_read_unlock(); __IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 597bb4c..e7d15fb0 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -456,10 +456,7 @@ static int inet_reuseport_add_sock(struct sock *sk, return reuseport_add_sock(sk, sk2); } - /* Initial allocation may have already happened via setsockopt */ - if (!rcu_access_pointer(sk->sk_reuseport_cb)) - return reuseport_alloc(sk); - return 0; + return reuseport_alloc(sk); } int __inet_hash(struct sock *sk, struct sock *osk) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index b1bb1b3..77cf32a 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -355,7 +355,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) */ - ireq->opt = tcp_v4_save_options(sock_net(sk), skb); + RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(sock_net(sk), skb)); if (security_inet_conn_request(sk, skb, req)) { reqsk_free(req); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b2390bf..ab3f128 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6167,7 +6167,7 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, struct inet_request_sock *ireq = inet_rsk(req); kmemcheck_annotate_bitfield(ireq, flags); - ireq->opt = NULL; + ireq->ireq_opt = NULL; #if IS_ENABLED(CONFIG_IPV6) ireq->pktopts = NULL; #endif diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 28ca4e1..e22439f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -877,7 +877,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, - ireq->opt); + rcu_dereference(ireq->ireq_opt)); err = net_xmit_eval(err); } @@ -889,7 +889,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, */ static void tcp_v4_reqsk_destructor(struct request_sock *req) { - kfree(inet_rsk(req)->opt); + kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1)); } #ifdef CONFIG_TCP_MD5SIG @@ -1265,10 +1265,11 @@ static void tcp_v4_init_req(struct request_sock *req, struct sk_buff *skb) { struct inet_request_sock *ireq = inet_rsk(req); + struct net *net = sock_net(sk_listener); sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); - ireq->opt = tcp_v4_save_options(sock_net(sk_listener), skb); + RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb)); } static struct dst_entry *tcp_v4_route_req(const struct sock *sk, @@ -1355,10 +1356,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, sk_daddr_set(newsk, ireq->ir_rmt_addr); sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); newsk->sk_bound_dev_if = ireq->ir_iif; - newinet->inet_saddr = ireq->ir_loc_addr; - inet_opt = ireq->opt; - rcu_assign_pointer(newinet->inet_opt, inet_opt); - ireq->opt = NULL; + newinet->inet_saddr = ireq->ir_loc_addr; + inet_opt = rcu_dereference(ireq->ireq_opt); + RCU_INIT_POINTER(newinet->inet_opt, inet_opt); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; newinet->rcv_tos = ip_hdr(skb)->tos; @@ -1403,9 +1403,12 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); - if (*own_req) + if (likely(*own_req)) { tcp_move_syn(newtp, req); - + ireq->ireq_opt = NULL; + } else { + newinet->inet_opt = NULL; + } return newsk; exit_overflow: @@ -1416,6 +1419,7 @@ exit: tcp_listendrop(sk); return NULL; put_and_exit: + newinet->inet_opt = NULL; inet_csk_prepare_forced_close(newsk); tcp_done(newsk); goto exit; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 7c9a6e4..a6699af 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -231,10 +231,7 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot) } } - /* Initial allocation may have already happened via setsockopt */ - if (!rcu_access_pointer(sk->sk_reuseport_cb)) - return reuseport_alloc(sk); - return 0; + return reuseport_alloc(sk); } /** @@ -1061,7 +1058,7 @@ back_from_confirm: /* ... which is an evident application bug. --ANK */ release_sock(sk); - net_dbg_ratelimited("cork app bug 2\n"); + net_dbg_ratelimited("socket already corked\n"); err = -EINVAL; goto out; } @@ -1144,7 +1141,7 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, if (unlikely(!up->pending)) { release_sock(sk); - net_dbg_ratelimited("udp cork app bug 3\n"); + net_dbg_ratelimited("cork failed\n"); return -EINVAL; } diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 8081baf..15535ee 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -315,6 +315,7 @@ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, } opt_space->dst1opt = fopt->dst1opt; opt_space->opt_flen = fopt->opt_flen; + opt_space->tot_len = fopt->tot_len; return opt_space; } EXPORT_SYMBOL_GPL(fl6_merge_options); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 43ca864..5110a41 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1161,11 +1161,11 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, if (WARN_ON(v6_cork->opt)) return -EINVAL; - v6_cork->opt = kzalloc(opt->tot_len, sk->sk_allocation); + v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation); if (unlikely(!v6_cork->opt)) return -ENOBUFS; - v6_cork->opt->tot_len = opt->tot_len; + v6_cork->opt->tot_len = sizeof(*opt); v6_cork->opt->opt_flen = opt->opt_flen; v6_cork->opt->opt_nflen = opt->opt_nflen; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index bc6e8bf..f50452b 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -988,6 +988,9 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session, session->name, cmd, arg); sk = ps->sock; + if (!sk) + return -EBADR; + sock_hold(sk); switch (cmd) { diff --git a/net/mac80211/key.c b/net/mac80211/key.c index a98fc2b..ae995c8 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -4,7 +4,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007-2008 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright 2015 Intel Deutschland GmbH + * Copyright 2015-2017 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -620,9 +620,6 @@ int ieee80211_key_link(struct ieee80211_key *key, pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE; idx = key->conf.keyidx; - key->local = sdata->local; - key->sdata = sdata; - key->sta = sta; mutex_lock(&sdata->local->key_mtx); @@ -633,6 +630,21 @@ int ieee80211_key_link(struct ieee80211_key *key, else old_key = key_mtx_dereference(sdata->local, sdata->keys[idx]); + /* + * Silently accept key re-installation without really installing the + * new version of the key to avoid nonce reuse or replay issues. + */ + if (old_key && key->conf.keylen == old_key->conf.keylen && + !memcmp(key->conf.key, old_key->conf.key, key->conf.keylen)) { + ieee80211_key_free_unused(key); + ret = 0; + goto out; + } + + key->local = sdata->local; + key->sdata = sdata; + key->sta = sta; + increment_tailroom_need_count(sdata); ieee80211_key_replace(sdata, sta, pairwise, old_key, key); @@ -648,6 +660,7 @@ int ieee80211_key_link(struct ieee80211_key *key, ret = 0; } + out: mutex_unlock(&sdata->local->key_mtx); return ret; diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index af3d636..d30f7bd 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -286,6 +286,7 @@ struct ncsi_dev_priv { struct work_struct work; /* For channel management */ struct packet_type ptype; /* NCSI packet Rx handler */ struct list_head node; /* Form NCSI device list */ +#define NCSI_MAX_VLAN_VIDS 15 struct list_head vlan_vids; /* List of active VLAN IDs */ }; diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c index 6898e72..f135938 100644 --- a/net/ncsi/ncsi-aen.c +++ b/net/ncsi/ncsi-aen.c @@ -187,7 +187,7 @@ static struct ncsi_aen_handler { } ncsi_aen_handlers[] = { { NCSI_PKT_AEN_LSC, 12, ncsi_aen_handler_lsc }, { NCSI_PKT_AEN_CR, 4, ncsi_aen_handler_cr }, - { NCSI_PKT_AEN_HNCDSC, 4, ncsi_aen_handler_hncdsc } + { NCSI_PKT_AEN_HNCDSC, 8, ncsi_aen_handler_hncdsc } }; int ncsi_aen_handler(struct ncsi_dev_priv *ndp, struct sk_buff *skb) diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 3fd3c39..28c42b2 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -189,6 +189,7 @@ static void ncsi_channel_monitor(unsigned long data) struct ncsi_channel *nc = (struct ncsi_channel *)data; struct ncsi_package *np = nc->package; struct ncsi_dev_priv *ndp = np->ndp; + struct ncsi_channel_mode *ncm; struct ncsi_cmd_arg nca; bool enabled, chained; unsigned int monitor_state; @@ -202,11 +203,15 @@ static void ncsi_channel_monitor(unsigned long data) monitor_state = nc->monitor.state; spin_unlock_irqrestore(&nc->lock, flags); - if (!enabled || chained) + if (!enabled || chained) { + ncsi_stop_channel_monitor(nc); return; + } if (state != NCSI_CHANNEL_INACTIVE && - state != NCSI_CHANNEL_ACTIVE) + state != NCSI_CHANNEL_ACTIVE) { + ncsi_stop_channel_monitor(nc); return; + } switch (monitor_state) { case NCSI_CHANNEL_MONITOR_START: @@ -217,28 +222,28 @@ static void ncsi_channel_monitor(unsigned long data) nca.type = NCSI_PKT_CMD_GLS; nca.req_flags = 0; ret = ncsi_xmit_cmd(&nca); - if (ret) { + if (ret) netdev_err(ndp->ndev.dev, "Error %d sending GLS\n", ret); - return; - } - break; case NCSI_CHANNEL_MONITOR_WAIT ... NCSI_CHANNEL_MONITOR_WAIT_MAX: break; default: - if (!(ndp->flags & NCSI_DEV_HWA) && - state == NCSI_CHANNEL_ACTIVE) { + if (!(ndp->flags & NCSI_DEV_HWA)) { ncsi_report_link(ndp, true); ndp->flags |= NCSI_DEV_RESHUFFLE; } + ncsi_stop_channel_monitor(nc); + + ncm = &nc->modes[NCSI_MODE_LINK]; spin_lock_irqsave(&nc->lock, flags); nc->state = NCSI_CHANNEL_INVISIBLE; + ncm->data[2] &= ~0x1; spin_unlock_irqrestore(&nc->lock, flags); spin_lock_irqsave(&ndp->lock, flags); - nc->state = NCSI_CHANNEL_INACTIVE; + nc->state = NCSI_CHANNEL_ACTIVE; list_add_tail_rcu(&nc->link, &ndp->channel_queue); spin_unlock_irqrestore(&ndp->lock, flags); ncsi_process_next_channel(ndp); @@ -732,6 +737,10 @@ static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, if (index < 0) { netdev_err(ndp->ndev.dev, "Failed to add new VLAN tag, error %d\n", index); + if (index == -ENOSPC) + netdev_err(ndp->ndev.dev, + "Channel %u already has all VLAN filters set\n", + nc->id); return -1; } @@ -998,12 +1007,15 @@ static bool ncsi_check_hwa(struct ncsi_dev_priv *ndp) struct ncsi_package *np; struct ncsi_channel *nc; unsigned int cap; + bool has_channel = false; /* The hardware arbitration is disabled if any one channel * doesn't support explicitly. */ NCSI_FOR_EACH_PACKAGE(ndp, np) { NCSI_FOR_EACH_CHANNEL(np, nc) { + has_channel = true; + cap = nc->caps[NCSI_CAP_GENERIC].cap; if (!(cap & NCSI_CAP_GENERIC_HWA) || (cap & NCSI_CAP_GENERIC_HWA_MASK) != @@ -1014,8 +1026,13 @@ static bool ncsi_check_hwa(struct ncsi_dev_priv *ndp) } } - ndp->flags |= NCSI_DEV_HWA; - return true; + if (has_channel) { + ndp->flags |= NCSI_DEV_HWA; + return true; + } + + ndp->flags &= ~NCSI_DEV_HWA; + return false; } static int ncsi_enable_hwa(struct ncsi_dev_priv *ndp) @@ -1403,7 +1420,6 @@ static int ncsi_kick_channels(struct ncsi_dev_priv *ndp) int ncsi_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { - struct ncsi_channel_filter *ncf; struct ncsi_dev_priv *ndp; unsigned int n_vids = 0; struct vlan_vid *vlan; @@ -1420,7 +1436,6 @@ int ncsi_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) } ndp = TO_NCSI_DEV_PRIV(nd); - ncf = ndp->hot_channel->filters[NCSI_FILTER_VLAN]; /* Add the VLAN id to our internal list */ list_for_each_entry_rcu(vlan, &ndp->vlan_vids, list) { @@ -1431,12 +1446,11 @@ int ncsi_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) return 0; } } - - if (n_vids >= ncf->total) { - netdev_info(dev, - "NCSI Channel supports up to %u VLAN tags but %u are already set\n", - ncf->total, n_vids); - return -EINVAL; + if (n_vids >= NCSI_MAX_VLAN_VIDS) { + netdev_warn(dev, + "tried to add vlan id %u but NCSI max already registered (%u)\n", + vid, NCSI_MAX_VLAN_VIDS); + return -ENOSPC; } vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 265b9a8..927dad4 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -959,7 +959,7 @@ static struct ncsi_rsp_handler { { NCSI_PKT_RSP_EGMF, 4, ncsi_rsp_handler_egmf }, { NCSI_PKT_RSP_DGMF, 4, ncsi_rsp_handler_dgmf }, { NCSI_PKT_RSP_SNFC, 4, ncsi_rsp_handler_snfc }, - { NCSI_PKT_RSP_GVI, 36, ncsi_rsp_handler_gvi }, + { NCSI_PKT_RSP_GVI, 40, ncsi_rsp_handler_gvi }, { NCSI_PKT_RSP_GC, 32, ncsi_rsp_handler_gc }, { NCSI_PKT_RSP_GP, -1, ncsi_rsp_handler_gp }, { NCSI_PKT_RSP_GCPS, 172, ncsi_rsp_handler_gcps }, diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 336d9c6..767c84e10e 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2307,6 +2307,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, size_t tlvlen = 0; struct netlink_sock *nlk = nlk_sk(NETLINK_CB(in_skb).sk); unsigned int flags = 0; + bool nlk_has_extack = nlk->flags & NETLINK_F_EXT_ACK; /* Error messages get the original request appened, unless the user * requests to cap the error message, and get extra error data if @@ -2317,7 +2318,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, payload += nlmsg_len(nlh); else flags |= NLM_F_CAPPED; - if (nlk->flags & NETLINK_F_EXT_ACK && extack) { + if (nlk_has_extack && extack) { if (extack->_msg) tlvlen += nla_total_size(strlen(extack->_msg) + 1); if (extack->bad_attr) @@ -2326,8 +2327,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, } else { flags |= NLM_F_CAPPED; - if (nlk->flags & NETLINK_F_EXT_ACK && - extack && extack->cookie_len) + if (nlk_has_extack && extack && extack->cookie_len) tlvlen += nla_total_size(extack->cookie_len); } @@ -2347,7 +2347,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, errmsg->error = err; memcpy(&errmsg->msg, nlh, payload > sizeof(*errmsg) ? nlh->nlmsg_len : sizeof(*nlh)); - if (nlk->flags & NETLINK_F_EXT_ACK && extack) { + if (nlk_has_extack && extack) { if (err) { if (extack->_msg) WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG, diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 3f5caa3..4f4fa32 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1767,7 +1767,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) out: if (err && rollover) { - kfree(rollover); + kfree_rcu(rollover, rcu); po->rollover = NULL; } mutex_unlock(&fanout_mutex); @@ -1794,8 +1794,10 @@ static struct packet_fanout *fanout_release(struct sock *sk) else f = NULL; - if (po->rollover) + if (po->rollover) { kfree_rcu(po->rollover, rcu); + po->rollover = NULL; + } } mutex_unlock(&fanout_mutex); @@ -3849,6 +3851,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, void *data = &val; union tpacket_stats_u st; struct tpacket_rollover_stats rstats; + struct packet_rollover *rollover; if (level != SOL_PACKET) return -ENOPROTOOPT; @@ -3927,13 +3930,18 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, 0); break; case PACKET_ROLLOVER_STATS: - if (!po->rollover) + rcu_read_lock(); + rollover = rcu_dereference(po->rollover); + if (rollover) { + rstats.tp_all = atomic_long_read(&rollover->num); + rstats.tp_huge = atomic_long_read(&rollover->num_huge); + rstats.tp_failed = atomic_long_read(&rollover->num_failed); + data = &rstats; + lv = sizeof(rstats); + } + rcu_read_unlock(); + if (!rollover) return -EINVAL; - rstats.tp_all = atomic_long_read(&po->rollover->num); - rstats.tp_huge = atomic_long_read(&po->rollover->num_huge); - rstats.tp_failed = atomic_long_read(&po->rollover->num_failed); - data = &rstats; - lv = sizeof(rstats); break; case PACKET_TX_HAS_OFF: val = po->tp_tx_has_off; diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 73c980e..054e328 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -311,10 +311,11 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, tx_total_len, gfp); /* The socket has been unlocked. */ - if (!IS_ERR(call)) + if (!IS_ERR(call)) { call->notify_rx = notify_rx; + mutex_unlock(&call->user_mutex); + } - mutex_unlock(&call->user_mutex); _leave(" = %p", call); return call; } diff --git a/net/sctp/input.c b/net/sctp/input.c index 92a0714..34f10e7 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -421,7 +421,7 @@ void sctp_icmp_redirect(struct sock *sk, struct sctp_transport *t, { struct dst_entry *dst; - if (!t) + if (sock_owned_by_user(sk) || !t) return; dst = sctp_transport_dst_check(t); if (dst) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 88c2842..c75acdf 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4978,6 +4978,10 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) struct socket *sock; int err = 0; + /* Do not peel off from one netns to another one. */ + if (!net_eq(current->nsproxy->net_ns, sock_net(sk))) + return -EINVAL; + if (!asoc) return -EINVAL; diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index bbac023..5583df7 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -310,11 +310,15 @@ static void hvs_close_connection(struct vmbus_channel *chan) struct sock *sk = get_per_channel_state(chan); struct vsock_sock *vsk = vsock_sk(sk); + lock_sock(sk); + sk->sk_state = TCP_CLOSE; sock_set_flag(sk, SOCK_DONE); vsk->peer_shutdown |= SEND_SHUTDOWN | RCV_SHUTDOWN; sk->sk_state_change(sk); + + release_sock(sk); } static void hvs_open_connection(struct vmbus_channel *chan) @@ -344,6 +348,7 @@ static void hvs_open_connection(struct vmbus_channel *chan) if (!sk) return; + lock_sock(sk); if ((conn_from_host && sk->sk_state != TCP_LISTEN) || (!conn_from_host && sk->sk_state != TCP_SYN_SENT)) goto out; @@ -395,9 +400,7 @@ static void hvs_open_connection(struct vmbus_channel *chan) vsock_insert_connected(vnew); - lock_sock(sk); vsock_enqueue_accept(sk, new); - release_sock(sk); } else { sk->sk_state = TCP_ESTABLISHED; sk->sk_socket->state = SS_CONNECTED; @@ -410,6 +413,8 @@ static void hvs_open_connection(struct vmbus_channel *chan) out: /* Release refcnt obtained when we called vsock_find_bound_socket() */ sock_put(sk); + + release_sock(sk); } static u32 hvs_get_local_cid(void) @@ -476,13 +481,21 @@ out: static void hvs_release(struct vsock_sock *vsk) { + struct sock *sk = sk_vsock(vsk); struct hvsock *hvs = vsk->trans; - struct vmbus_channel *chan = hvs->chan; + struct vmbus_channel *chan; + + lock_sock(sk); + + sk->sk_state = SS_DISCONNECTING; + vsock_remove_sock(vsk); + + release_sock(sk); + chan = hvs->chan; if (chan) hvs_shutdown(vsk, RCV_SHUTDOWN | SEND_SHUTDOWN); - vsock_remove_sock(vsk); } static void hvs_destruct(struct vsock_sock *vsk) |