diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-10-21 22:44:48 -0400 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-10-21 22:44:48 -0400 |
commit | b5ac3beb5a9f0ef0ea64cd85faf94c0dc4de0e42 (patch) | |
tree | 70a8d684c18f71aa4be2d67896362f864afb4d57 /net | |
parent | e5f468b3f23313994c5e6c356135f9b0d76bcb94 (diff) | |
parent | 8d5f4b07174976c55a5f5d6967777373c6826944 (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller:
"A little more than usual this time around. Been travelling, so that is
part of it.
Anyways, here are the highlights:
1) Deal with memcontrol races wrt. listener dismantle, from Eric
Dumazet.
2) Handle page allocation failures properly in nfp driver, from Jaku
Kicinski.
3) Fix memory leaks in macsec, from Sabrina Dubroca.
4) Fix crashes in pppol2tp_session_ioctl(), from Guillaume Nault.
5) Several fixes in bnxt_en driver, including preventing potential
NVRAM parameter corruption from Michael Chan.
6) Fix for KRACK attacks in wireless, from Johannes Berg.
7) rtnetlink event generation fixes from Xin Long.
8) Deadlock in mlxsw driver, from Ido Schimmel.
9) Disallow arithmetic operations on context pointers in bpf, from
Jakub Kicinski.
10) Missing sock_owned_by_user() check in sctp_icmp_redirect(), from
Xin Long.
11) Only TCP is supported for sockmap, make that explicit with a
check, from John Fastabend.
12) Fix IP options state races in DCCP and TCP, from Eric Dumazet.
13) Fix panic in packet_getsockopt(), also from Eric Dumazet.
14) Add missing locked in hv_sock layer, from Dexuan Cui.
15) Various aquantia bug fixes, including several statistics handling
cures. From Igor Russkikh et al.
16) Fix arithmetic overflow in devmap code, from John Fastabend.
17) Fix busted socket memory accounting when we get a fault in the tcp
zero copy paths. From Willem de Bruijn.
18) Don't leave opt->tot_len uninitialized in ipv6, from Eric Dumazet"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (106 commits)
stmmac: Don't access tx_q->dirty_tx before netif_tx_lock
ipv6: flowlabel: do not leave opt->tot_len with garbage
of_mdio: Fix broken PHY IRQ in case of probe deferral
textsearch: fix typos in library helpers
rxrpc: Don't release call mutex on error pointer
net: stmmac: Prevent infinite loop in get_rx_timestamp_status()
net: stmmac: Fix stmmac_get_rx_hwtstamp()
net: stmmac: Add missing call to dev_kfree_skb()
mlxsw: spectrum_router: Configure TIGCR on init
mlxsw: reg: Add Tunneling IPinIP General Configuration Register
net: ethtool: remove error check for legacy setting transceiver type
soreuseport: fix initialization race
net: bridge: fix returning of vlan range op errors
sock: correct sk_wmem_queued accounting on efault in tcp zerocopy
bpf: add test cases to bpf selftests to cover all access tests
bpf: fix pattern matches for direct packet access
bpf: fix off by one for range markings with L{T, E} patterns
bpf: devmap fix arithmetic overflow in bitmap_size calculation
net: aquantia: Bad udp rate on default interrupt coalescing
net: aquantia: Enable coalescing management via ethtool interface
...
Diffstat (limited to 'net')
35 files changed, 230 insertions, 138 deletions
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 3bc890716c89..de2152730809 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -573,7 +573,7 @@ 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 88edac0f3e36..ecd5c703d11e 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 47a8748d953a..13690334efa3 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 588b473194a8..11596a302a26 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1147,9 +1147,8 @@ 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); @@ -1165,6 +1164,7 @@ 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 709a4e6fb447..f9c7a88cd981 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 3228411ada0f..9a9a3d77e327 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -436,7 +436,7 @@ 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( @@ -451,8 +451,7 @@ 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 74b8c91fb5f4..aa0265997f93 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1839,31 +1839,31 @@ 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; @@ -1873,9 +1873,10 @@ 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) @@ -3683,7 +3684,6 @@ 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; @@ -3693,6 +3693,7 @@ static bool sk_skb_is_valid_access(int off, int size, } switch (off) { + case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, tc_classid): return false; case bpf_ctx_range(struct __sk_buff, data): diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d4bcdcc68e92..5ace48926b19 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1483,7 +1483,10 @@ 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 }, @@ -2093,7 +2096,7 @@ 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; } } @@ -2248,7 +2251,7 @@ 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) @@ -4279,13 +4282,17 @@ 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); break; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 16982de649b9..24656076906d 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; } @@ -1896,7 +1900,7 @@ 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 23953b741a41..415f441c63b9 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 eed1ebf7f29d..b1e0dbea1e8c 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 001c08696334..0490916864f9 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/ipv4/Kconfig b/net/ipv4/Kconfig index 91a2557942fa..f48fe6fc7e8c 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 2ae8f54cb321..82178cc69c96 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 c039c937ba90..5ec9136a7c36 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) @@ -539,9 +540,10 @@ 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), @@ -575,10 +577,9 @@ 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), @@ -591,13 +592,11 @@ 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 597bb4cfe805..e7d15fb0d94d 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 b1bb1b3a1082..77cf32a80952 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 c5d7656beeee..7eec3383702b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6196,7 +6196,7 @@ 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 85164d4d3e53..4c43365c374c 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 e45177ceb0ee..ebfbccae62fd 100644 --- a/net/ipv4/udp.c +++ b/ |