diff options
Diffstat (limited to 'include/net/sock.h')
| -rw-r--r-- | include/net/sock.h | 114 |
1 files changed, 72 insertions, 42 deletions
diff --git a/include/net/sock.h b/include/net/sock.h index a6b9a8d1a6df..63731289186a 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -60,7 +60,7 @@ #include <linux/sched.h> #include <linux/wait.h> #include <linux/cgroup-defs.h> - +#include <linux/rbtree.h> #include <linux/filter.h> #include <linux/rculist_nulls.h> #include <linux/poll.h> @@ -72,6 +72,7 @@ #include <net/tcp_states.h> #include <linux/net_tstamp.h> #include <net/smc.h> +#include <net/l3mdev.h> /* * This structure really needs to be cleaned up. @@ -267,6 +268,7 @@ struct sock_common { * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) * @sk_gso_max_size: Maximum GSO segment size to build * @sk_gso_max_segs: Maximum number of GSO segments + * @sk_pacing_shift: scaling factor for TCP Small Queues * @sk_lingertime: %SO_LINGER l_linger setting * @sk_backlog: always used with the per-socket spinlock held * @sk_callback_lock: used with the callbacks in the end of this struct @@ -397,7 +399,10 @@ struct sock { int sk_wmem_queued; refcount_t sk_wmem_alloc; unsigned long sk_tsq_flags; - struct sk_buff *sk_send_head; + union { + struct sk_buff *sk_send_head; + struct rb_root tcp_rtx_queue; + }; struct sk_buff_head sk_write_queue; __s32 sk_peek_off; int sk_write_pending; @@ -436,7 +441,6 @@ struct sock { #define SK_FL_TYPE_MASK 0xffff0000 #endif - kmemcheck_bitfield_begin(flags); unsigned int sk_padding : 1, sk_kern_sock : 1, sk_no_check_tx : 1, @@ -445,9 +449,8 @@ struct sock { sk_protocol : 8, sk_type : 16; #define SK_PROTOCOL_MAX U8_MAX - kmemcheck_bitfield_end(flags); - u16 sk_gso_max_segs; + u8 sk_pacing_shift; unsigned long sk_lingertime; struct proto *sk_prot_creator; rwlock_t sk_callback_lock; @@ -683,11 +686,7 @@ static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list) static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { - if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && - sk->sk_family == AF_INET6) - hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list); - else - hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); + hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); } static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) @@ -734,10 +733,10 @@ static inline void sk_add_bind_node(struct sock *sk, * */ #define sk_for_each_entry_offset_rcu(tpos, pos, head, offset) \ - for (pos = rcu_dereference((head)->first); \ + for (pos = rcu_dereference(hlist_first_rcu(head)); \ pos != NULL && \ ({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;}); \ - pos = rcu_dereference(pos->next)) + pos = rcu_dereference(hlist_next_rcu(pos))) static inline struct user_namespace *sk_user_ns(struct sock *sk) { @@ -1098,14 +1097,18 @@ struct proto { */ unsigned long *memory_pressure; long *sysctl_mem; + int *sysctl_wmem; int *sysctl_rmem; + u32 sysctl_wmem_offset; + u32 sysctl_rmem_offset; + int max_header; bool no_autobind; struct kmem_cache *slab; unsigned int obj_size; - int slab_flags; + slab_flags_t slab_flags; struct percpu_counter *orphan_count; @@ -1260,6 +1263,7 @@ proto_memory_pressure(struct proto *prot) /* Called with local bh disabled */ void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc); int sock_prot_inuse_get(struct net *net, struct proto *proto); +int sock_inuse_get(struct net *net); #else static inline void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc) @@ -1443,10 +1447,8 @@ do { \ } while (0) #ifdef CONFIG_LOCKDEP -static inline bool lockdep_sock_is_held(const struct sock *csk) +static inline bool lockdep_sock_is_held(const struct sock *sk) { - struct sock *sk = (struct sock *)csk; - return lockdep_is_held(&sk->sk_lock) || lockdep_is_held(&sk->sk_lock.slock); } @@ -1512,6 +1514,11 @@ static inline bool sock_owned_by_user(const struct sock *sk) return sk->sk_lock.owned; } +static inline bool sock_owned_by_user_nocheck(const struct sock *sk) +{ + return sk->sk_lock.owned; +} + /* no reclassification while locks are held */ static inline bool sock_allow_reclassification(const struct sock *csk) { @@ -1576,7 +1583,7 @@ int sock_no_connect(struct socket *, struct sockaddr *, int, int); int sock_no_socketpair(struct socket *, struct socket *); int sock_no_accept(struct socket *, struct socket *, int, bool); int sock_no_getname(struct socket *, struct sockaddr *, int *, int); -unsigned int sock_no_poll(struct file *, struct socket *, +__poll_t sock_no_poll(struct file *, struct socket *, struct poll_table_struct *); int sock_no_ioctl(struct socket *, unsigned int, unsigned long); int sock_no_listen(struct socket *, int); @@ -2330,31 +2337,6 @@ 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 *); @@ -2387,4 +2369,52 @@ extern int sysctl_optmem_max; extern __u32 sysctl_wmem_default; extern __u32 sysctl_rmem_default; +static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto) +{ + /* Does this proto have per netns sysctl_wmem ? */ + if (proto->sysctl_wmem_offset) + return *(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset); + + return *proto->sysctl_wmem; +} + +static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto) +{ + /* Does this proto have per netns sysctl_rmem ? */ + if (proto->sysctl_rmem_offset) + return *(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset); + + return *proto->sysctl_rmem; +} + +/* Default TCP Small queue budget is ~1 ms of data (1sec >> 10) + * Some wifi drivers need to tweak it to get more chunks. + * They can use this helper from their ndo_start_xmit() + */ +static inline void sk_pacing_shift_update(struct sock *sk, int val) +{ + if (!sk || !sk_fullsock(sk) || sk->sk_pacing_shift == val) + return; + sk->sk_pacing_shift = val; +} + +/* if a socket is bound to a device, check that the given device + * index is either the same or that the socket is bound to an L3 + * master device and the given device index is also enslaved to + * that L3 master + */ +static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif) +{ + int mdif; + + if (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif) + return true; + + mdif = l3mdev_master_ifindex_by_index(sock_net(sk), dif); + if (mdif && mdif == sk->sk_bound_dev_if) + return true; + + return false; +} + #endif /* _SOCK_H */ |