diff options
Diffstat (limited to 'include/net/sock.h')
| -rw-r--r-- | include/net/sock.h | 59 |
1 files changed, 43 insertions, 16 deletions
diff --git a/include/net/sock.h b/include/net/sock.h index d08cfe190a78..dcd72e6285b2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -318,12 +318,15 @@ struct sk_filter; * @sk_stamp: time stamp of last packet received * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only * @sk_tsflags: SO_TIMESTAMPING flags + * @sk_use_task_frag: allow sk_page_frag() to use current->task_frag. + * Sockets that can be used under memory reclaim should + * set this to false. * @sk_bind_phc: SO_TIMESTAMPING bind PHC index of PTP virtual clock * for timestamping * @sk_tskey: counter to disambiguate concurrent tstamp requests * @sk_zckey: counter to order MSG_ZEROCOPY notifications * @sk_socket: Identd and reporting IO signals - * @sk_user_data: RPC layer private data + * @sk_user_data: RPC layer private data. Write-protected by @sk_callback_lock. * @sk_frag: cached page frag * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit @@ -348,6 +351,7 @@ struct sk_filter; * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference + * @sk_bind2_node: bind node in the bhash2 table */ struct sock { /* @@ -502,15 +506,16 @@ struct sock { #if BITS_PER_LONG==32 seqlock_t sk_stamp_seq; #endif - u16 sk_tsflags; - u8 sk_shutdown; atomic_t sk_tskey; atomic_t sk_zckey; + u32 sk_tsflags; + u8 sk_shutdown; u8 sk_clockid; u8 sk_txtime_deadline_mode : 1, sk_txtime_report_errors : 1, sk_txtime_unused : 6; + bool sk_use_task_frag; struct socket *sk_socket; void *sk_user_data; @@ -537,6 +542,7 @@ struct sock { #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; + struct hlist_node sk_bind2_node; }; enum sk_pacing { @@ -742,11 +748,6 @@ static inline void sk_node_init(struct hlist_node *node) node->pprev = NULL; } -static inline void sk_nulls_node_init(struct hlist_nulls_node *node) -{ - node->pprev = NULL; -} - static inline void __sk_del_node(struct sock *sk) { __hlist_del(&sk->sk_node); @@ -870,6 +871,16 @@ static inline void sk_add_bind_node(struct sock *sk, hlist_add_head(&sk->sk_bind_node, list); } +static inline void __sk_del_bind2_node(struct sock *sk) +{ + __hlist_del(&sk->sk_bind2_node); +} + +static inline void sk_add_bind2_node(struct sock *sk, struct hlist_head *list) +{ + hlist_add_head(&sk->sk_bind2_node, list); +} + #define sk_for_each(__sk, list) \ hlist_for_each_entry(__sk, list, sk_node) #define sk_for_each_rcu(__sk, list) \ @@ -887,6 +898,8 @@ static inline void sk_add_bind_node(struct sock *sk, hlist_for_each_entry_safe(__sk, tmp, list, sk_node) #define sk_for_each_bound(__sk, list) \ hlist_for_each_entry(__sk, list, sk_bind_node) +#define sk_for_each_bound_bhash2(__sk, list) \ + hlist_for_each_entry(__sk, list, sk_bind2_node) /** * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset @@ -1774,6 +1787,11 @@ static inline void unlock_sock_fast(struct sock *sk, bool slow) } } +void sockopt_lock_sock(struct sock *sk); +void sockopt_release_sock(struct sock *sk); +bool sockopt_ns_capable(struct user_namespace *ns, int cap); +bool sockopt_capable(int cap); + /* Used by processes to "lock" a socket state, so that * interrupts and bottom half handlers won't change it * from under us. It essentially blocks any incoming @@ -1848,9 +1866,13 @@ void sock_pfree(struct sk_buff *skb); #define sock_edemux sock_efree #endif +int sk_setsockopt(struct sock *sk, int level, int optname, + sockptr_t optval, unsigned int optlen); int sock_setsockopt(struct socket *sock, int level, int op, sockptr_t optval, unsigned int optlen); +int sk_getsockopt(struct sock *sk, int level, int optname, + sockptr_t optval, sockptr_t optlen); int sock_getsockopt(struct socket *sock, int level, int op, char __user *optval, int __user *optlen); int sock_gettstamp(struct socket *sock, void __user *userstamp, @@ -1871,10 +1893,17 @@ void sock_kfree_s(struct sock *sk, void *mem, int size); void sock_kzfree_s(struct sock *sk, void *mem, int size); void sk_send_sigurg(struct sock *sk); +static inline void sock_replace_proto(struct sock *sk, struct proto *proto) +{ + if (sk->sk_socket) + clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); + WRITE_ONCE(sk->sk_prot, proto); +} + struct sockcm_cookie { u64 transmit_time; u32 mark; - u16 tsflags; + u32 tsflags; }; static inline void sockcm_init(struct sockcm_cookie *sockc, @@ -1883,7 +1912,7 @@ static inline void sockcm_init(struct sockcm_cookie *sockc, *sockc = (struct sockcm_cookie) { .tsflags = sk->sk_tsflags }; } -int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, +int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, struct sockcm_cookie *sockc); int sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct sockcm_cookie *sockc); @@ -2091,7 +2120,7 @@ static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk) static inline u32 net_tx_rndhash(void) { - u32 v = prandom_u32(); + u32 v = get_random_u32(); return v ?: 1; } @@ -2535,16 +2564,14 @@ static inline void sk_stream_moderate_sndbuf(struct sock *sk) * Both direct reclaim and page faults can nest inside other * socket operations and end up recursing into sk_page_frag() * while it's already in use: explicitly avoid task page_frag - * usage if the caller is potentially doing any of them. - * This assumes that page fault handlers use the GFP_NOFS flags. + * when users disable sk_use_task_frag. * * Return: a per task page_frag if context allows that, * otherwise a per socket one. */ static inline struct page_frag *sk_page_frag(struct sock *sk) { - if ((sk->sk_allocation & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC | __GFP_FS)) == - (__GFP_DIRECT_RECLAIM | __GFP_FS)) + if (sk->sk_use_task_frag) return ¤t->task_frag; return &sk->sk_frag; @@ -2567,7 +2594,7 @@ static inline gfp_t gfp_any(void) static inline gfp_t gfp_memcg_charge(void) { - return in_softirq() ? GFP_NOWAIT : GFP_KERNEL; + return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } static inline long sock_rcvtimeo(const struct sock *sk, bool noblock) |