diff options
Diffstat (limited to 'include/net')
-rw-r--r-- | include/net/af_unix.h | 1 | ||||
-rw-r--r-- | include/net/dst.h | 33 | ||||
-rw-r--r-- | include/net/inet_sock.h | 27 | ||||
-rw-r--r-- | include/net/inetpeer.h | 1 | ||||
-rw-r--r-- | include/net/ip6_fib.h | 3 | ||||
-rw-r--r-- | include/net/ip6_route.h | 17 | ||||
-rw-r--r-- | include/net/ip6_tunnel.h | 3 | ||||
-rw-r--r-- | include/net/ip_tunnels.h | 3 | ||||
-rw-r--r-- | include/net/ipv6.h | 22 | ||||
-rw-r--r-- | include/net/mac80211.h | 6 | ||||
-rw-r--r-- | include/net/ndisc.h | 3 | ||||
-rw-r--r-- | include/net/netfilter/nf_tables.h | 16 | ||||
-rw-r--r-- | include/net/sch_generic.h | 3 | ||||
-rw-r--r-- | include/net/sctp/structs.h | 17 | ||||
-rw-r--r-- | include/net/sock.h | 64 | ||||
-rw-r--r-- | include/net/switchdev.h | 2 | ||||
-rw-r--r-- | include/net/vxlan.h | 2 | ||||
-rw-r--r-- | include/net/xfrm.h | 25 |
18 files changed, 193 insertions, 55 deletions
diff --git a/include/net/af_unix.h b/include/net/af_unix.h index b36d837..2a91a05 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -62,6 +62,7 @@ struct unix_sock { #define UNIX_GC_CANDIDATE 0 #define UNIX_GC_MAYBE_CYCLE 1 struct socket_wq peer_wq; + wait_queue_t peer_wake; }; static inline struct unix_sock *unix_sk(const struct sock *sk) diff --git a/include/net/dst.h b/include/net/dst.h index 1279f9b..c7329dc 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -322,6 +322,39 @@ static inline void skb_dst_force(struct sk_buff *skb) } } +/** + * dst_hold_safe - Take a reference on a dst if possible + * @dst: pointer to dst entry + * + * This helper returns false if it could not safely + * take a reference on a dst. + */ +static inline bool dst_hold_safe(struct dst_entry *dst) +{ + if (dst->flags & DST_NOCACHE) + return atomic_inc_not_zero(&dst->__refcnt); + dst_hold(dst); + return true; +} + +/** + * skb_dst_force_safe - makes sure skb dst is refcounted + * @skb: buffer + * + * If dst is not yet refcounted and not destroyed, grab a ref on it. + */ +static inline void skb_dst_force_safe(struct sk_buff *skb) +{ + if (skb_dst_is_noref(skb)) { + struct dst_entry *dst = skb_dst(skb); + + if (!dst_hold_safe(dst)) + dst = NULL; + + skb->_skb_refdst = (unsigned long)dst; + } +} + /** * __skb_tunnel_rx - prepare skb for rx reinsert diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 2134e6d..625bdf9 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -210,18 +210,37 @@ struct inet_sock { #define IP_CMSG_ORIGDSTADDR BIT(6) #define IP_CMSG_CHECKSUM BIT(7) -/* SYNACK messages might be attached to request sockets. +/** + * sk_to_full_sk - Access to a full socket + * @sk: pointer to a socket + * + * SYNACK messages might be attached to request sockets. * Some places want to reach the listener in this case. */ -static inline struct sock *skb_to_full_sk(const struct sk_buff *skb) +static inline struct sock *sk_to_full_sk(struct sock *sk) { - struct sock *sk = skb->sk; - +#ifdef CONFIG_INET if (sk && sk->sk_state == TCP_NEW_SYN_RECV) sk = inet_reqsk(sk)->rsk_listener; +#endif + return sk; +} + +/* sk_to_full_sk() variant with a const argument */ +static inline const struct sock *sk_const_to_full_sk(const struct sock *sk) +{ +#ifdef CONFIG_INET + if (sk && sk->sk_state == TCP_NEW_SYN_RECV) + sk = ((const struct request_sock *)sk)->rsk_listener; +#endif return sk; } +static inline struct sock *skb_to_full_sk(const struct sk_buff *skb) +{ + return sk_to_full_sk(skb->sk); +} + static inline struct inet_sock *inet_sk(const struct sock *sk) { return (struct inet_sock *)sk; diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 4a6009d..235c781 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -78,6 +78,7 @@ void inet_initpeers(void) __init; static inline void inetpeer_set_addr_v4(struct inetpeer_addr *iaddr, __be32 ip) { iaddr->a4.addr = ip; + iaddr->a4.vif = 0; iaddr->family = AF_INET; } diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index aaf9700..fb961a5 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -167,7 +167,8 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout) static inline u32 rt6_get_cookie(const struct rt6_info *rt) { - if (rt->rt6i_flags & RTF_PCPU || unlikely(rt->dst.flags & DST_NOCACHE)) + if (rt->rt6i_flags & RTF_PCPU || + (unlikely(rt->dst.flags & DST_NOCACHE) && rt->dst.from)) rt = (struct rt6_info *)(rt->dst.from); return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 2bfb2ad..877f682 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -133,27 +133,18 @@ void rt6_clean_tohost(struct net *net, struct in6_addr *gateway); /* * Store a destination cache entry in a socket */ -static inline void __ip6_dst_store(struct sock *sk, struct dst_entry *dst, - const struct in6_addr *daddr, - const struct in6_addr *saddr) +static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, + const struct in6_addr *daddr, + const struct in6_addr *saddr) { struct ipv6_pinfo *np = inet6_sk(sk); - struct rt6_info *rt = (struct rt6_info *) dst; + np->dst_cookie = rt6_get_cookie((struct rt6_info *)dst); sk_setup_caps(sk, dst); np->daddr_cache = daddr; #ifdef CONFIG_IPV6_SUBTREES np->saddr_cache = saddr; #endif - np->dst_cookie = rt6_get_cookie(rt); -} - -static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, - struct in6_addr *daddr, struct in6_addr *saddr) -{ - spin_lock(&sk->sk_dst_lock); - __ip6_dst_store(sk, dst, daddr, saddr); - spin_unlock(&sk->sk_dst_lock); } static inline bool ipv6_unicast_destination(const struct sk_buff *skb) diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index aaee6fa..ff788b6 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -90,11 +90,12 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb); if (net_xmit_eval(err) == 0) { - struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); + struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->tx_bytes += pkt_len; tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); + put_cpu_ptr(tstats); } else { stats->tx_errors++; stats->tx_aborted_errors++; diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index f6dafec..62a750a 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -287,12 +287,13 @@ static inline void iptunnel_xmit_stats(int err, struct pcpu_sw_netstats __percpu *stats) { if (err > 0) { - struct pcpu_sw_netstats *tstats = this_cpu_ptr(stats); + struct pcpu_sw_netstats *tstats = get_cpu_ptr(stats); u64_stats_update_begin(&tstats->syncp); tstats->tx_bytes += err; tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); + put_cpu_ptr(tstats); } else if (err < 0) { err_stats->tx_errors++; err_stats->tx_aborted_errors++; diff --git a/include/net/ipv6.h b/include/net/ipv6.h index e1a10b0..9a5c9f0 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -205,6 +205,7 @@ extern rwlock_t ip6_ra_lock; */ struct ipv6_txoptions { + atomic_t refcnt; /* Length of this structure */ int tot_len; @@ -217,7 +218,7 @@ struct ipv6_txoptions { struct ipv6_opt_hdr *dst0opt; struct ipv6_rt_hdr *srcrt; /* Routing Header */ struct ipv6_opt_hdr *dst1opt; - + struct rcu_head rcu; /* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */ }; @@ -252,6 +253,24 @@ struct ipv6_fl_socklist { struct rcu_head rcu; }; +static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) +{ + struct ipv6_txoptions *opt; + + rcu_read_lock(); + opt = rcu_dereference(np->opt); + if (opt && !atomic_inc_not_zero(&opt->refcnt)) + opt = NULL; + rcu_read_unlock(); + return opt; +} + +static inline void txopt_put(struct ipv6_txoptions *opt) +{ + if (opt && atomic_dec_and_test(&opt->refcnt)) + kfree_rcu(opt, rcu); +} + struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label); struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, struct ip6_flowlabel *fl, @@ -490,6 +509,7 @@ struct ip6_create_arg { u32 user; const struct in6_addr *src; const struct in6_addr *dst; + int iif; u8 ecn; }; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 82045fc..760bc4d 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2003,8 +2003,10 @@ enum ieee80211_hw_flags { * it shouldn't be set. * * @max_tx_aggregation_subframes: maximum number of subframes in an - * aggregate an HT driver will transmit, used by the peer as a - * hint to size its reorder buffer. + * aggregate an HT driver will transmit. Though ADDBA will advertise + * a constant value of 64 as some older APs can crash if the window + * size is smaller (an example is LinkSys WRT120N with FW v1.0.07 + * build 002 Jun 18 2012). * * @offchannel_tx_hw_queue: HW queue ID to use for offchannel TX * (if %IEEE80211_HW_QUEUE_CONTROL is set) diff --git a/include/net/ndisc.h b/include/net/ndisc.h index bf39374..2d8edaa 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -181,8 +181,7 @@ void ndisc_cleanup(void); int ndisc_rcv(struct sk_buff *skb); void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, - const struct in6_addr *daddr, const struct in6_addr *saddr, - struct sk_buff *oskb); + const struct in6_addr *daddr, const struct in6_addr *saddr); void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index c9149cc..4bd7508 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -618,6 +618,8 @@ struct nft_expr_ops { void (*eval)(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); + int (*clone)(struct nft_expr *dst, + const struct nft_expr *src); unsigned int size; int (*init)(const struct nft_ctx *ctx, @@ -660,10 +662,20 @@ void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr); int nft_expr_dump(struct sk_buff *skb, unsigned int attr, const struct nft_expr *expr); -static inline void nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) +static inline int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) { + int err; + __module_get(src->ops->type->owner); - memcpy(dst, src, src->ops->size); + if (src->ops->clone) { + dst->ops = src->ops; + err = src->ops->clone(dst, src); + if (err < 0) + return err; + } else { + memcpy(dst, src, src->ops->size); + } + return 0; } /** diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 4c79ce8..b2a8e63 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -61,6 +61,9 @@ struct Qdisc { */ #define TCQ_F_WARN_NONWC (1 << 16) #define TCQ_F_CPUSTATS 0x20 /* run using percpu statistics */ +#define TCQ_F_NOPARENT 0x40 /* root of its hierarchy : + * qdisc_tree_decrease_qlen() should stop. + */ u32 limit; const struct Qdisc_ops *ops; struct qdisc_size_table __rcu *stab; diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 495c87e..eea9bde 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -775,10 +775,10 @@ struct sctp_transport { hb_sent:1, /* Is the Path MTU update pending on this tranport */ - pmtu_pending:1; + pmtu_pending:1, - /* Has this transport moved the ctsn since we last sacked */ - __u32 sack_generation; + /* Has this transport moved the ctsn since we last sacked */ + sack_generation:1; u32 dst_cookie; struct flowi fl; @@ -1482,19 +1482,20 @@ struct sctp_association { prsctp_capable:1, /* Can peer do PR-SCTP? */ auth_capable:1; /* Is peer doing SCTP-AUTH? */ - /* Ack State : This flag indicates if the next received + /* sack_needed : This flag indicates if the next received * : packet is to be responded to with a - * : SACK. This is initializedto 0. When a packet - * : is received it is incremented. If this value + * : SACK. This is initialized to 0. When a packet + * : is received sack_cnt is incremented. If this value * : reaches 2 or more, a SACK is sent and the * : value is reset to 0. Note: This is used only * : when no DATA chunks are received out of * : order. When DATA chunks are out of order, * : SACK's are not delayed (see Section 6). */ - __u8 sack_needed; /* Do we need to sack the peer? */ + __u8 sack_needed:1, /* Do we need to sack the peer? */ + sack_generation:1, + zero_window_announced:1; __u32 sack_cnt; - __u32 sack_generation; __u32 adaptation_ind; /* Adaptation Code point. */ diff --git a/include/net/sock.h b/include/net/sock.h index bbf7c2c..14d3c07 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -254,7 +254,6 @@ struct cg_proto; * @sk_wq: sock wait queue and async head * @sk_rx_dst: receive input route used by early demux * @sk_dst_cache: destination cache - * @sk_dst_lock: destination cache lock * @sk_policy: flow policy * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed @@ -384,14 +383,16 @@ struct sock { int sk_rcvbuf; struct sk_filter __rcu *sk_filter; - struct socket_wq __rcu *sk_wq; - + union { + struct socket_wq __rcu *sk_wq; + struct socket_wq *sk_wq_raw; + }; #ifdef CONFIG_XFRM - struct xfrm_policy *sk_policy[2]; + struct xfrm_policy __rcu *sk_policy[2]; #endif struct dst_entry *sk_rx_dst; struct dst_entry __rcu *sk_dst_cache; - spinlock_t sk_dst_lock; + /* Note: 32bit hole on 64bit arches */ atomic_t sk_wmem_alloc; atomic_t sk_omem_alloc; int sk_sndbuf; @@ -403,6 +404,7 @@ struct sock { sk_userlocks : 4, sk_protocol : 8, sk_type : 16; +#define SK_PROTOCOL_MAX U8_MAX kmemcheck_bitfield_end(flags); int sk_wmem_queued; gfp_t sk_allocation; @@ -739,6 +741,8 @@ enum sock_flags { SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */ }; +#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) + static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) { nsk->sk_flags = osk->sk_flags; @@ -813,7 +817,7 @@ void sk_stream_write_space(struct sock *sk); static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) { /* dont let skb dst not refcounted, we are going to leave rcu lock */ - skb_dst_force(skb); + skb_dst_force_safe(skb); if (!sk->sk_backlog.tail) sk->sk_backlog.head = skb; @@ -2005,10 +2009,27 @@ static inline unsigned long sock_wspace(struct sock *sk) return amt; } -static inline void sk_wake_async(struct sock *sk, int how, int band) +/* Note: + * We use sk->sk_wq_raw, from contexts knowing this + * pointer is not NULL and cannot disappear/change. + */ +static inline void sk_set_bit(int nr, struct sock *sk) +{ + set_bit(nr, &sk->sk_wq_raw->flags); +} + +static inline void sk_clear_bit(int nr, struct sock *sk) +{ + clear_bit(nr, &sk->sk_wq_raw->flags); +} + +static inline void sk_wake_async(const struct sock *sk, int how, int band) { - if (sock_flag(sk, SOCK_FASYNC)) - sock_wake_async(sk->sk_socket, how, band); + if (sock_flag(sk, SOCK_FASYNC)) { + rcu_read_lock(); + sock_wake_async(rcu_dereference(sk->sk_wq), how, band); + rcu_read_unlock(); + } } /* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might @@ -2226,6 +2247,31 @@ static inline bool sk_listener(const struct sock *sk) return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); } +/** + * sk_state_load - read sk->sk_state for lockless contexts + * @sk: socket pointer + * + * Paired with sk_state_store(). Used in places we do not hold socket lock : + * tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ... + */ +static inline int sk_state_load(const struct sock *sk) +{ + return smp_load_acquire(&sk->sk_state); +} + +/** + * sk_state_store - update sk->sk_state + * @sk: socket pointer + * @newstate: new state + * + * Paired with sk_state_load(). Should be used in contexts where + * state change might impact lockless readers. + */ +static inline void sk_state_store(struct sock *sk, int newstate) +{ + smp_store_release(&sk->sk_state, newstate); +} + void sock_enable_timestamp(struct sock *sk, int flag); int sock_get_timestamp(struct sock *, struct timeval __user *); int sock_get_timestampns(struct sock *, struct timespec __user *); diff --git a/include/net/switchdev.h b/include/net/switchdev.h index bc865e2..1d22ce9 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -323,7 +323,7 @@ static inline int switchdev_port_fdb_dump(struct sk_buff *skb, struct net_device *filter_dev, int idx) { - return -EOPNOTSUPP; + return idx; } static inline void switchdev_port_fwd_mark_set(struct net_device *dev, diff --git a/include/net/vxlan.h b/include/net/vxlan.h index c1c899c..e289ada 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -79,7 +79,7 @@ struct vxlanhdr { }; /* VXLAN header flags. */ -#define VXLAN_HF_RCO BIT(24) +#define VXLAN_HF_RCO BIT(21) #define VXLAN_HF_VNI BIT(27) #define VXLAN_HF_GBP BIT(31) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 4a9c21f..d6f6e50 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -548,6 +548,7 @@ struct xfrm_policy { u16 family; struct xfrm_sec_ctx *security; struct xfrm_tmpl xfrm_vec[XFRM_MAX_DEPTH]; + struct rcu_head rcu; }; static inline struct net *xp_net(const struct xfrm_policy *xp) @@ -1141,12 +1142,14 @@ static inline int xfrm6_route_forward(struct sk_buff *skb) return xfrm_route_forward(skb, AF_INET6); } -int __xfrm_sk_clone_policy(struct sock *sk); +int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk); -static inline int xfrm_sk_clone_policy(struct sock *sk) +static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { - if (unlikely(sk->sk_policy[0] || sk->sk_policy[1])) - return __xfrm_sk_clone_policy(sk); + sk->sk_policy[0] = NULL; + sk->sk_policy[1] = NULL; + if (unlikely(osk->sk_policy[0] || osk->sk_policy[1])) + return __xfrm_sk_clone_policy(sk, osk); return 0; } @@ -1154,12 +1157,16 @@ int xfrm_policy_delete(struct xfrm_policy *pol, int dir); static inline void xfrm_sk_free_policy(struct sock *sk) { - if (unlikely(sk->sk_policy[0] != NULL)) { - xfrm_policy_delete(sk->sk_policy[0], XFRM_POLICY_MAX); + struct xfrm_policy *pol; + + pol = rcu_dereference_protected(sk->sk_policy[0], 1); + if (unlikely(pol != NULL)) { + xfrm_policy_delete(pol, XFRM_POLICY_MAX); sk->sk_policy[0] = NULL; } - if (unlikely(sk->sk_policy[1] != NULL)) { - xfrm_policy_delete(sk->sk_policy[1], XFRM_POLICY_MAX+1); + pol = rcu_dereference_protected(sk->sk_policy[1], 1); + if (unlikely(pol != NULL)) { + xfrm_policy_delete(pol, XFRM_POLICY_MAX+1); sk->sk_policy[1] = NULL; } } @@ -1169,7 +1176,7 @@ void xfrm_garbage_collect(struct net *net); #else static inline void xfrm_sk_free_policy(struct sock *sk) {} -static inline int xfrm_sk_clone_policy(struct sock *sk) { return 0; } +static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { return 0; } static inline int xfrm6_route_forward(struct sk_buff *skb) { return 1; } static inline int xfrm4_route_forward(struct sk_buff *skb) { return 1; } static inline int xfrm6_policy_check(struct sock *sk, int dir, struct sk_buff *skb) |