diff options
Diffstat (limited to 'include/net/sock.h')
-rw-r--r-- | include/net/sock.h | 796 |
1 files changed, 572 insertions, 224 deletions
diff --git a/include/net/sock.h b/include/net/sock.h index 328564525526..5db02546941c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -56,17 +56,19 @@ #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> - +#include <linux/sockptr.h> +#include <linux/indirect_call_wrapper.h> #include <linux/atomic.h> #include <linux/refcount.h> +#include <linux/llist.h> #include <net/dst.h> #include <net/checksum.h> #include <net/tcp_states.h> #include <linux/net_tstamp.h> #include <net/l3mdev.h> +#include <uapi/linux/socket.h> /* * This structure really needs to be cleaned up. @@ -159,9 +161,6 @@ typedef __u64 __bitwise __addrpair; * for struct sock and struct inet_timewait_sock. */ struct sock_common { - /* skc_daddr and skc_rcv_saddr must be grouped on a 8 bytes aligned - * address on 64bit arches : cf INET_MATCH() - */ union { __addrpair skc_addrpair; struct { @@ -225,7 +224,7 @@ struct sock_common { struct hlist_nulls_node skc_nulls_node; }; unsigned short skc_tx_queue_mapping; -#ifdef CONFIG_XPS +#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING unsigned short skc_rx_queue_mapping; #endif union { @@ -245,7 +244,8 @@ struct sock_common { /* public: */ }; -struct bpf_sk_storage; +struct bpf_local_storage; +struct sk_filter; /** * struct sock - network layer representation of sockets @@ -257,10 +257,11 @@ struct bpf_sk_storage; * @sk_rcvbuf: size of receive buffer in bytes * @sk_wq: sock wait queue and async head * @sk_rx_dst: receive input route used by early demux + * @sk_rx_dst_ifindex: ifindex for @sk_rx_dst + * @sk_rx_dst_cookie: cookie for @sk_rx_dst * @sk_dst_cache: destination cache * @sk_dst_pending_confirm: need to confirm neighbour * @sk_policy: flow policy - * @sk_rx_skb_cache: cache copy of recently accessed RX skb * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed * @sk_tsq_flags: TCP Small Queues flags @@ -268,6 +269,7 @@ struct bpf_sk_storage; * @sk_omem_alloc: "o" is "option" or "other" * @sk_wmem_queued: persistent queue size * @sk_forward_alloc: space allocated forward + * @sk_reserved_mem: space reserved and non-reclaimable for the socket * @sk_napi_id: id of the last napi context to receive data for sk * @sk_ll_usec: usecs to busypoll when there is no data * @sk_allocation: allocation mode @@ -280,9 +282,7 @@ struct bpf_sk_storage; * @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets * @sk_no_check_rx: allow zero checksum in RX packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) - * @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK) - * @sk_route_forced_caps: static, forced route capabilities - * (set in tcp_init_sock()) + * @sk_gso_disabled: if set, NETIF_F_GSO_MASK is forbidden. * @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 @@ -300,20 +300,26 @@ struct bpf_sk_storage; * @sk_ack_backlog: current listen backlog * @sk_max_ack_backlog: listen backlog set in listen() * @sk_uid: user id of owner + * @sk_prefer_busy_poll: prefer busypolling over softirq processing + * @sk_busy_poll_budget: napi processing budget when busypolling * @sk_priority: %SO_PRIORITY setting * @sk_type: socket type (%SOCK_STREAM, etc) * @sk_protocol: which protocol this socket belongs in this network family + * @sk_peer_lock: lock protecting @sk_peer_pid and @sk_peer_cred * @sk_peer_pid: &struct pid for this socket's peer * @sk_peer_cred: %SO_PEERCRED setting * @sk_rcvlowat: %SO_RCVLOWAT setting * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting * @sk_txhash: computed flow hash for use on transmit + * @sk_txrehash: enable TX hash rethink * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer * @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 socket options + * @sk_tsflags: SO_TIMESTAMPING flags + * @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 @@ -322,7 +328,6 @@ struct bpf_sk_storage; * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit * @tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head] - * @sk_tx_skb_cache: cache copy of recently accessed TX skb * @sk_security: used by security modules * @sk_mark: generic packet mark * @sk_cgrp_data: cgroup data for this cgroup @@ -342,6 +347,8 @@ struct bpf_sk_storage; * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME * @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 { /* @@ -353,7 +360,7 @@ struct sock { #define sk_nulls_node __sk_common.skc_nulls_node #define sk_refcnt __sk_common.skc_refcnt #define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping -#ifdef CONFIG_XPS +#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING #define sk_rx_queue_mapping __sk_common.skc_rx_queue_mapping #endif @@ -383,11 +390,15 @@ struct sock { #define sk_flags __sk_common.skc_flags #define sk_rxhash __sk_common.skc_rxhash + /* early demux fields */ + struct dst_entry __rcu *sk_rx_dst; + int sk_rx_dst_ifindex; + u32 sk_rx_dst_cookie; + socket_lock_t sk_lock; atomic_t sk_drops; int sk_rcvlowat; struct sk_buff_head sk_error_queue; - struct sk_buff *sk_rx_skb_cache; struct sk_buff_head sk_receive_queue; /* * The backlog queue is special, it is always used with @@ -403,9 +414,11 @@ struct sock { struct sk_buff *head; struct sk_buff *tail; } sk_backlog; + #define sk_rmem_alloc sk_backlog.rmem_alloc int sk_forward_alloc; + u32 sk_reserved_mem; #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sk_ll_usec; /* ===== mostly read cache line ===== */ @@ -423,7 +436,7 @@ struct sock { #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; #endif - struct dst_entry *sk_rx_dst; + struct dst_entry __rcu *sk_dst_cache; atomic_t sk_omem_alloc; int sk_sndbuf; @@ -436,7 +449,6 @@ struct sock { struct sk_buff *sk_send_head; struct rb_root tcp_rtx_queue; }; - struct sk_buff *sk_tx_skb_cache; struct sk_buff_head sk_write_queue; __s32 sk_peek_off; int sk_write_pending; @@ -450,8 +462,6 @@ struct sock { unsigned long sk_max_pacing_rate; struct page_frag sk_frag; netdev_features_t sk_route_caps; - netdev_features_t sk_route_nocaps; - netdev_features_t sk_route_forced_caps; int sk_gso_type; unsigned int sk_gso_max_size; gfp_t sk_allocation; @@ -461,7 +471,7 @@ struct sock { * Because of non atomicity rules, all * changes are protected by socket lock. */ - u8 sk_padding : 1, + u8 sk_gso_disabled : 1, sk_kern_sock : 1, sk_no_check_tx : 1, sk_no_check_rx : 1, @@ -478,8 +488,16 @@ struct sock { u32 sk_ack_backlog; u32 sk_max_ack_backlog; kuid_t sk_uid; + u8 sk_txrehash; +#ifdef CONFIG_NET_RX_BUSY_POLL + u8 sk_prefer_busy_poll; + u16 sk_busy_poll_budget; +#endif + spinlock_t sk_peer_lock; + int sk_bind_phc; struct pid *sk_peer_pid; const struct cred *sk_peer_cred; + long sk_rcvtimeo; ktime_t sk_stamp; #if BITS_PER_LONG==32 @@ -487,7 +505,7 @@ struct sock { #endif u16 sk_tsflags; u8 sk_shutdown; - u32 sk_tskey; + atomic_t sk_tskey; atomic_t sk_zckey; u8 sk_clockid; @@ -516,9 +534,11 @@ struct sock { void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; #ifdef CONFIG_BPF_SYSCALL - struct bpf_sk_storage __rcu *sk_bpf_storage; + struct bpf_local_storage __rcu *sk_bpf_storage; #endif struct rcu_head sk_rcu; + netns_tracker ns_tracker; + struct hlist_node sk_bind2_node; }; enum sk_pacing { @@ -527,10 +547,109 @@ enum sk_pacing { SK_PACING_FQ = 2, }; +/* flag bits in sk_user_data + * + * - SK_USER_DATA_NOCOPY: Pointer stored in sk_user_data might + * not be suitable for copying when cloning the socket. For instance, + * it can point to a reference counted object. sk_user_data bottom + * bit is set if pointer must not be copied. + * + * - SK_USER_DATA_BPF: Mark whether sk_user_data field is + * managed/owned by a BPF reuseport array. This bit should be set + * when sk_user_data's sk is added to the bpf's reuseport_array. + * + * - SK_USER_DATA_PSOCK: Mark whether pointer stored in + * sk_user_data points to psock type. This bit should be set + * when sk_user_data is assigned to a psock object. + */ +#define SK_USER_DATA_NOCOPY 1UL +#define SK_USER_DATA_BPF 2UL +#define SK_USER_DATA_PSOCK 4UL +#define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF |\ + SK_USER_DATA_PSOCK) + +/** + * sk_user_data_is_nocopy - Test if sk_user_data pointer must not be copied + * @sk: socket + */ +static inline bool sk_user_data_is_nocopy(const struct sock *sk) +{ + return ((uintptr_t)sk->sk_user_data & SK_USER_DATA_NOCOPY); +} + #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data))) -#define rcu_dereference_sk_user_data(sk) rcu_dereference(__sk_user_data((sk))) -#define rcu_assign_sk_user_data(sk, ptr) rcu_assign_pointer(__sk_user_data((sk)), ptr) +/** + * __locked_read_sk_user_data_with_flags - return the pointer + * only if argument flags all has been set in sk_user_data. Otherwise + * return NULL + * + * @sk: socket + * @flags: flag bits + * + * The caller must be holding sk->sk_callback_lock. + */ +static inline void * +__locked_read_sk_user_data_with_flags(const struct sock *sk, + uintptr_t flags) +{ + uintptr_t sk_user_data = + (uintptr_t)rcu_dereference_check(__sk_user_data(sk), + lockdep_is_held(&sk->sk_callback_lock)); + + WARN_ON_ONCE(flags & SK_USER_DATA_PTRMASK); + + if ((sk_user_data & flags) == flags) + return (void *)(sk_user_data & SK_USER_DATA_PTRMASK); + return NULL; +} + +/** + * __rcu_dereference_sk_user_data_with_flags - return the pointer + * only if argument flags all has been set in sk_user_data. Otherwise + * return NULL + * + * @sk: socket + * @flags: flag bits + */ +static inline void * +__rcu_dereference_sk_user_data_with_flags(const struct sock *sk, + uintptr_t flags) +{ + uintptr_t sk_user_data = (uintptr_t)rcu_dereference(__sk_user_data(sk)); + + WARN_ON_ONCE(flags & SK_USER_DATA_PTRMASK); + + if ((sk_user_data & flags) == flags) + return (void *)(sk_user_data & SK_USER_DATA_PTRMASK); + return NULL; +} + +#define rcu_dereference_sk_user_data(sk) \ + __rcu_dereference_sk_user_data_with_flags(sk, 0) +#define __rcu_assign_sk_user_data_with_flags(sk, ptr, flags) \ +({ \ + uintptr_t __tmp1 = (uintptr_t)(ptr), \ + __tmp2 = (uintptr_t)(flags); \ + WARN_ON_ONCE(__tmp1 & ~SK_USER_DATA_PTRMASK); \ + WARN_ON_ONCE(__tmp2 & SK_USER_DATA_PTRMASK); \ + rcu_assign_pointer(__sk_user_data((sk)), \ + __tmp1 | __tmp2); \ +}) +#define rcu_assign_sk_user_data(sk, ptr) \ + __rcu_assign_sk_user_data_with_flags(sk, ptr, 0) + +static inline +struct net *sock_net(const struct sock *sk) +{ + return read_pnet(&sk->sk_net); +} + +static inline +void sock_net_set(struct sock *sk, struct net *net) +{ + write_pnet(&sk->sk_net, net); +} /* * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK @@ -545,7 +664,7 @@ enum sk_pacing { int sk_set_peek_off(struct sock *sk, int val); -static inline int sk_peek_offset(struct sock *sk, int flags) +static inline int sk_peek_offset(const struct sock *sk, int flags) { if (unlikely(flags & MSG_PEEK)) { return READ_ONCE(sk->sk_peek_off); @@ -625,11 +744,6 @@ 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); @@ -753,6 +867,16 @@ 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) \ @@ -770,6 +894,8 @@ 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 @@ -785,7 +911,7 @@ static inline void sk_add_bind_node(struct sock *sk, ({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;}); \ pos = rcu_dereference(hlist_next_rcu(pos))) -static inline struct user_namespace *sk_user_ns(struct sock *sk) +static inline struct user_namespace *sk_user_ns(const struct sock *sk) { /* Careful only use this in a context where these parameters * can not change and must all be valid, such as recvmsg from @@ -810,7 +936,6 @@ enum sock_flags { SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */ SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */ SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */ - SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */ SOCK_MEMALLOC, /* VM depends on this socket for swapping */ SOCK_TIMESTAMPING_RX_SOFTWARE, /* %SOF_TIMESTAMPING_RX_SOFTWARE */ SOCK_FASYNC, /* fasync() active */ @@ -827,11 +952,12 @@ enum sock_flags { SOCK_TXTIME, SOCK_XDP, /* XDP is attached */ SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */ + SOCK_RCVMARK, /* Receive SO_MARK ancillary data with packet */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) -static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) +static inline void sock_copy_flags(struct sock *nsk, const struct sock *osk) { nsk->sk_flags = osk->sk_flags; } @@ -846,6 +972,15 @@ static inline void sock_reset_flag(struct sock *sk, enum sock_flags flag) __clear_bit(flag, &sk->sk_flags); } +static inline void sock_valbool_flag(struct sock *sk, enum sock_flags bit, + int valbool) +{ + if (valbool) + sock_set_flag(sk, bit); + else + sock_reset_flag(sk, bit); +} + static inline bool sock_flag(const struct sock *sk, enum sock_flags flag) { return test_bit(flag, &sk->sk_flags); @@ -857,6 +992,8 @@ static inline int sk_memalloc_socks(void) { return static_branch_unlikely(&memalloc_socks_key); } + +void __receive_sock(struct file *file); #else static inline int sk_memalloc_socks(void) @@ -864,6 +1001,8 @@ static inline int sk_memalloc_socks(void) return 0; } +static inline void __receive_sock(struct file *file) +{ } #endif static inline gfp_t sk_gfp_mask(const struct sock *sk, gfp_t gfp_mask) @@ -881,6 +1020,10 @@ static inline void sk_acceptq_added(struct sock *sk) WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog + 1); } +/* Note: If you think the test should be: + * return READ_ONCE(sk->sk_ack_backlog) >= READ_ONCE(sk->sk_max_ack_backlog); + * Then please take a look at commit 64a146513f8f ("[NET]: Revert incorrect accept queue backlog changes.") + */ static inline bool sk_acceptq_is_full(const struct sock *sk) { return READ_ONCE(sk->sk_ack_backlog) > READ_ONCE(sk->sk_max_ack_backlog); @@ -955,12 +1098,18 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb); +INDIRECT_CALLABLE_DECLARE(int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)); +INDIRECT_CALLABLE_DECLARE(int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)); + static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { if (sk_memalloc_socks() && skb_pfmemalloc(skb)) return __sk_backlog_rcv(sk, skb); - return sk->sk_backlog_rcv(sk, skb); + return INDIRECT_CALL_INET(sk->sk_backlog_rcv, + tcp_v6_do_rcv, + tcp_v4_do_rcv, + sk, skb); } static inline void sk_incoming_cpu_update(struct sock *sk) @@ -1061,6 +1210,7 @@ struct inet_hashinfo; struct raw_hashinfo; struct smc_hashinfo; struct module; +struct sk_psock; /* * caches using SLAB_TYPESAFE_BY_RCU should let .next pointer from nulls nodes @@ -1097,36 +1247,31 @@ struct proto { void (*destroy)(struct sock *sk); void (*shutdown)(struct sock *sk, int how); int (*setsockopt)(struct sock *sk, int level, - int optname, char __user *optval, + int optname, sockptr_t optval, unsigned int optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *option); void (*keepalive)(struct sock *sk, int valbool); #ifdef CONFIG_COMPAT - int (*compat_setsockopt)(struct sock *sk, - int level, - int optname, char __user *optval, - unsigned int optlen); - int (*compat_getsockopt)(struct sock *sk, - int level, - int optname, char __user *optval, - int __user *option); int (*compat_ioctl)(struct sock *sk, unsigned int cmd, unsigned long arg); #endif int (*sendmsg)(struct sock *sk, struct msghdr *msg, size_t len); int (*recvmsg)(struct sock *sk, struct msghdr *msg, - size_t len, int noblock, int flags, - int *addr_len); + size_t len, int flags, int *addr_len); int (*sendpage)(struct sock *sk, struct page *page, int offset, size_t size, int flags); int (*bind)(struct sock *sk, - struct sockaddr *uaddr, int addr_len); + struct sockaddr *addr, int addr_len); + int (*bind_add)(struct sock *sk, + struct sockaddr *addr, int addr_len); int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); + bool (*bpf_bypass_getsockopt)(int level, + int optname); void (*release_cb)(struct sock *sk); @@ -1135,19 +1280,31 @@ struct proto { void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); + void (*put_port)(struct sock *sk); +#ifdef CONFIG_BPF_SYSCALL + int (*psock_update_sk_prot)(struct sock *sk, + struct sk_psock *psock, + bool restore); +#endif /* Keeping track of sockets in use */ #ifdef CONFIG_PROC_FS unsigned int inuse_idx; #endif +#if IS_ENABLED(CONFIG_MPTCP) + int (*forward_alloc_get)(const struct sock *sk); +#endif + bool (*stream_memory_free)(const struct sock *sk, int wake); - bool (*stream_memory_read)(const struct sock *sk); + bool (*sock_is_readable)(struct sock *sk); /* Memory pressure */ void (*enter_memory_pressure)(struct sock *sk); void (*leave_memory_pressure)(struct sock *sk); atomic_long_t *memory_allocated; /* Current allocated memory. */ + int __percpu *per_cpu_fw_alloc; struct percpu_counter *sockets_allocated; /* Current number of sockets. */ + /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. @@ -1171,7 +1328,7 @@ struct proto { unsigned int useroffset; /* Usercopy region offset */ unsigned int usersize; /* Usercopy region size */ - struct percpu_counter *orphan_count; + unsigned int __percpu *orphan_count; struct request_sock_ops *rsk_prot; struct timewait_sock_ops *twsk_prot; @@ -1223,13 +1380,25 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) #define sk_refcnt_debug_release(sk) do { } while (0) #endif /* SOCK_REFCNT_DEBUG */ +INDIRECT_CALLABLE_DECLARE(bool tcp_stream_memory_free(const struct sock *sk, int wake)); + +static inline int sk_forward_alloc_get(const struct sock *sk) +{ +#if IS_ENABLED(CONFIG_MPTCP) + if (sk->sk_prot->forward_alloc_get) + return sk->sk_prot->forward_alloc_get(sk); +#endif + return sk->sk_forward_alloc; +} + static inline bool __sk_stream_memory_free(const struct sock *sk, int wake) { if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf)) return false; return sk->sk_prot->stream_memory_free ? - sk->sk_prot->stream_memory_free(sk, wake) : true; + INDIRECT_CALL_INET_1(sk->sk_prot->stream_memory_free, + tcp_stream_memory_free, sk, wake) : true; } static inline bool sk_stream_memory_free(const struct sock *sk) @@ -1277,31 +1446,60 @@ static inline bool sk_under_memory_pressure(const struct sock *sk) } static inline long -sk_memory_allocated(const struct sock *sk) +proto_memory_allocated(const struct proto *prot) { - return atomic_long_read(sk->sk_prot->memory_allocated); + return max(0L, atomic_long_read(prot->memory_allocated)); } static inline long +sk_memory_allocated(const struct sock *sk) +{ + return proto_memory_allocated(sk->sk_prot); +} + +/* 1 MB per cpu, in page units */ +#define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) + +static inline void sk_memory_allocated_add(struct sock *sk, int amt) { - return atomic_long_add_return(amt, sk->sk_prot->memory_allocated); + int local_reserve; + + preempt_disable(); + local_reserve = __this_cpu_add_return(*sk->sk_prot->per_cpu_fw_alloc, amt); + if (local_reserve >= SK_MEMORY_PCPU_RESERVE) { + __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); + atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); + } + preempt_enable(); } static inline void sk_memory_allocated_sub(struct sock *sk, int amt) { - atomic_long_sub(amt, sk->sk_prot->memory_allocated); + int local_reserve; + + preempt_disable(); + local_reserve = __this_cpu_sub_return(*sk->sk_prot->per_cpu_fw_alloc, amt); + if (local_reserve <= -SK_MEMORY_PCPU_RESERVE) { + __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); + atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); + } + preempt_enable(); } +#define SK_ALLOC_PERCPU_COUNTER_BATCH 16 + static inline void sk_sockets_allocated_dec(struct sock *sk) { - percpu_counter_dec(sk->sk_prot->sockets_allocated); + percpu_counter_add_batch(sk->sk_prot->sockets_allocated, -1, + SK_ALLOC_PERCPU_COUNTER_BATCH); } static inline void sk_sockets_allocated_inc(struct sock *sk) { - percpu_counter_inc(sk->sk_prot->sockets_allocated); + percpu_counter_add_batch(sk->sk_prot->sockets_allocated, 1, + SK_ALLOC_PERCPU_COUNTER_BATCH); } static inline u64 @@ -1316,12 +1514,6 @@ proto_sockets_allocated_sum_positive(struct proto *prot) return percpu_counter_sum_positive(prot->sockets_allocated); } -static inline long -proto_memory_allocated(struct proto *prot) -{ - return atomic_long_read(prot->memory_allocated); -} - static inline bool proto_memory_pressure(struct proto *prot) { @@ -1332,13 +1524,32 @@ proto_memory_pressure(struct proto *prot) #ifdef CONFIG_PROC_FS -/* Called with local bh disabled */ -void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc); +#define PROTO_INUSE_NR 64 /* should be enough for the first time */ +struct prot_inuse { + int all; + int val[PROTO_INUSE_NR]; +}; + +static inline void sock_prot_inuse_add(const struct net *net, + const struct proto *prot, int val) +{ + this_cpu_add(net->core.prot_inuse->val[prot->inuse_idx], val); +} + +static inline void sock_inuse_add(const struct net *net, int val) +{ + this_cpu_add(net->core.prot_inuse->all, val); +} + 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) +static inline void sock_prot_inuse_add(const struct net *net, + const struct proto *prot, int val) +{ +} + +static inline void sock_inuse_add(const struct net *net, int val) { } #endif @@ -1363,8 +1574,6 @@ static inline int __sk_prot_rehash(struct sock *sk) #define RCV_SHUTDOWN 1 #define SEND_SHUTDOWN 2 -#define SOCK_SNDBUF_LOCK 1 -#define SOCK_RCVBUF_LOCK 2 #define SOCK_BINDADDR_LOCK 4 #define SOCK_BINDPORT_LOCK 8 @@ -1391,30 +1600,18 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind); void __sk_mem_reduce_allocated(struct sock *sk, int amount); void __sk_mem_reclaim(struct sock *sk, int amount); -/* We used to have PAGE_SIZE here, but systems with 64KB pages - * do not necessarily have 16x time more memory than 4KB ones. - */ -#define SK_MEM_QUANTUM 4096 -#define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM) #define SK_MEM_SEND 0 #define SK_MEM_RECV 1 -/* sysctl_mem values are in pages, we convert them in SK_MEM_QUANTUM units */ +/* sysctl_mem values are in pages */ static inline long sk_prot_mem_limits(const struct sock *sk, int index) { - long val = sk->sk_prot->sysctl_mem[index]; - -#if PAGE_SIZE > SK_MEM_QUANTUM - val <<= PAGE_SHIFT - SK_MEM_QUANTUM_SHIFT; -#elif PAGE_SIZE < SK_MEM_QUANTUM - val >>= SK_MEM_QUANTUM_SHIFT - PAGE_SHIFT; -#endif - return val; + return READ_ONCE(sk->sk_prot->sysctl_mem[index]); } static inline int sk_mem_pages(int amt) { - return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT; + return (amt + PAGE_SIZE - 1) >> PAGE_SHIFT; } static inline bool sk_has_account(struct sock *sk) @@ -1425,36 +1622,56 @@ static inline bool sk_has_account(struct sock *sk) static inline bool sk_wmem_schedule(struct sock *sk, int size) { + int delta; + if (!sk_has_account(sk)) return true; - return size <= sk->sk_forward_alloc || - __sk_mem_schedule(sk, size, SK_MEM_SEND); + delta = size - sk->sk_forward_alloc; + return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_SEND); } static inline bool sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) { + int delta; + if (!sk_has_account(sk)) return true; - return size<= sk->sk_forward_alloc || - __sk_mem_schedule(sk, size, SK_MEM_RECV) || + delta = size - sk->sk_forward_alloc; + return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) || skb_pfmemalloc(skb); } +static inline int sk_unused_reserved_mem(const struct sock *sk) +{ + int unused_mem; + + if (likely(!sk->sk_reserved_mem)) + return 0; + + unused_mem = sk->sk_reserved_mem - sk->sk_wmem_queued - + atomic_read(&sk->sk_rmem_alloc); + + return unused_mem > 0 ? unused_mem : 0; +} + static inline void sk_mem_reclaim(struct sock *sk) { + int reclaimable; + if (!sk_has_account(sk)) return; - if (sk->sk_forward_alloc >= SK_MEM_QUANTUM) - __sk_mem_reclaim(sk, sk->sk_forward_alloc); + + reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); + + if (reclaimable >= (int)PAGE_SIZE) + __sk_mem_reclaim(sk, reclaimable); } -static inline void sk_mem_reclaim_partial(struct sock *sk) +static inline void sk_mem_reclaim_final(struct sock *sk) { - if (!sk_has_account(sk)) - return; - if (sk->sk_forward_alloc > SK_MEM_QUANTUM) - __sk_mem_reclaim(sk, sk->sk_forward_alloc - 1); + sk->sk_reserved_mem = 0; + sk_mem_reclaim(sk); } static inline void sk_mem_charge(struct sock *sk, int size) @@ -1469,42 +1686,7 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) if (!sk_has_account(sk)) return; sk->sk_forward_alloc += size; - - /* Avoid a possible overflow. - * TCP send queues can make this happen, if sk_mem_reclaim() - * is not called and more than 2 GBytes are released at once. - * - * If we reach 2 MBytes, reclaim 1 MBytes right now, there is - * no need to hold that much forward allocation anyway. - */ - if (unlikely(sk->sk_forward_alloc >= 1 << 21)) - __sk_mem_reclaim(sk, 1 << 20); -} - -DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key); -static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb) -{ - sock_set_flag(sk, SOCK_QUEUE_SHRUNK); - sk_wmem_queued_add(sk, -skb->truesize); - sk_mem_uncharge(sk, skb->truesize); - if (static_branch_unlikely(&tcp_tx_skb_cache_key) && - !sk->sk_tx_skb_cache && !skb_cloned(skb)) { - skb_ext_reset(skb); - skb_zcopy_clear(skb, true); - sk->sk_tx_skb_cache = skb; - return; - } - __kfree_skb(skb); -} - -static inline void sock_release_ownership(struct sock *sk) -{ - if (sk->sk_lock.owned) { - sk->sk_lock.owned = 0; - - /* The sk_lock has mutex_unlock() semantics: */ - mutex_release(&sk->sk_lock.dep_map, _RET_IP_); - } + sk_mem_reclaim(sk); } /* @@ -1526,13 +1708,11 @@ do { \ lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \ } while (0) -#ifdef CONFIG_LOCKDEP static inline bool lockdep_sock_is_held(const struct sock *sk) { return lockdep_is_held(&sk->sk_lock) || lockdep_is_held(&sk->sk_lock.slock); } -#endif void lock_sock_nested(struct sock *sk, int subclass); @@ -1541,6 +1721,7 @@ static inline void lock_sock(struct sock *sk) lock_sock_nested(sk, 0); } +void __lock_sock(struct sock *sk); void __release_sock(struct sock *sk); void release_sock(struct sock *sk); @@ -1551,7 +1732,37 @@ void release_sock(struct sock *sk); SINGLE_DEPTH_NESTING) #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock)) -bool lock_sock_fast(struct sock *sk); +bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); + +/** + * lock_sock_fast - fast version of lock_sock + * @sk: socket + * + * This version should be used for very small section, where process wont block + * return false if fast path is taken: + * + * sk_lock.slock locked, owned = 0, BH disabled + * + * return true if slow path is taken: + * + * sk_lock.slock unlocked, owned = 1, BH enabled + */ +static inline bool lock_sock_fast(struct sock *sk) +{ + /* The sk_lock has mutex_lock() semantics here. */ + mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); + + return __lock_sock_fast(sk); +} + +/* fast socket lock variant for caller already holding a [different] socket lock */ +static inline bool lock_sock_fast_nested(struct sock *sk) +{ + mutex_acquire(&sk->sk_lock.dep_map, SINGLE_DEPTH_NESTING, 0, _RET_IP_); + + return __lock_sock_fast(sk); +} + /** * unlock_sock_fast - complement of lock_sock_fast * @sk: socket @@ -1561,13 +1772,22 @@ bool lock_sock_fast(struct sock *sk); * If slow mode is on, we call regular release_sock() */ static inline void unlock_sock_fast(struct sock *sk, bool slow) + __releases(&sk->sk_lock.slock) { - if (slow) + if (slow) { release_sock(sk); - else + __release(&sk->sk_lock.slock); + } else { + mutex_release(&sk->sk_lock.dep_map, _RET_IP_); spin_unlock_bh(&sk->sk_lock.slock); + } } +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 @@ -1600,12 +1820,23 @@ static inline bool sock_owned_by_user_nocheck(const struct sock *sk) return sk->sk_lock.owned; } +static inline void sock_release_ownership(struct sock *sk) +{ + if (sock_owned_by_user_nocheck(sk)) { + sk->sk_lock.owned = 0; + + /* The sk_lock has mutex_unlock() semantics: */ + mutex_release(&sk->sk_lock.dep_map, _RET_IP_); + } +} + /* no reclassification while locks are held */ static inline bool sock_allow_reclassification(const struct sock *csk) { struct sock *sk = (struct sock *)csk; - return !sk->sk_lock.owned && !spin_is_locked(&sk->sk_lock.slock); + return !sock_owned_by_user_nocheck(sk) && + !spin_is_locked(&sk->sk_lock.slock); } struct sock *sk_alloc(struct net *net, int family, gfp_t priority, @@ -1626,27 +1857,45 @@ void sock_rfree(struct sk_buff *skb); void sock_efree(struct sk_buff *skb); #ifdef CONFIG_INET void sock_edemux(struct sk_buff *skb); +void sock_pfree(struct sk_buff *skb); #else #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, - char __user *optval, unsigned int optlen); + 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, bool timeval, bool time32); -struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, - int noblock, int *errcode); struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, unsigned long data_len, int noblock, int *errcode, int max_page_order); + +static inline struct sk_buff *sock_alloc_send_skb(struct sock *sk, + unsigned long size, + int noblock, int *errcode) +{ + return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0); +} + void *sock_kmalloc(struct sock *sk, int size, gfp_t priority); 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; @@ -1676,8 +1925,6 @@ int sock_no_getname(struct socket *, struct sockaddr *, int); int sock_no_ioctl(struct socket *, unsigned int, unsigned long); int sock_no_listen(struct socket *, int); int sock_no_shutdown(struct socket *, int); -int sock_no_getsockopt(struct socket *, int , int, char __user *, int __user *); -int sock_no_setsockopt(struct socket *, int, int, char __user *, unsigned int); int sock_no_sendmsg(struct socket *, struct msghdr *, size_t); int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t len); int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int); @@ -1697,11 +1944,7 @@ int sock_common_getsockopt(struct socket *sock, int level, int optname, int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); int sock_common_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, unsigned int optlen); -int compat_sock_common_getsockopt(struct socket *sock, int level, - int optname, char __user *optval, int __user *optlen); -int compat_sock_common_setsockopt(struct socket *sock, int level, - int optname, char __user *optval, unsigned int optlen); + sockptr_t optval, unsigned int optlen); void sk_common_release(struct sock *sk); @@ -1779,40 +2022,54 @@ static inline int sk_tx_queue_get(const struct sock *sk) return -1; } -static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb) +static inline void __sk_rx_queue_set(struct sock *sk, + const struct sk_buff *skb, + bool force_set) { -#ifdef CONFIG_XPS +#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING if (skb_rx_queue_recorded(skb)) { u16 rx_queue = skb_get_rx_queue(skb); - if (WARN_ON_ONCE(rx_queue == NO_QUEUE_MAPPING)) - return; - - sk->sk_rx_queue_mapping = rx_queue; + if (force_set || + unlikely(READ_ONCE(sk->sk_rx_queue_mapping) != rx_queue)) + WRITE_ONCE(sk->sk_rx_queue_mapping, rx_queue); } #endif } +static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb) +{ + __sk_rx_queue_set(sk, skb, true); +} + +static inline void sk_rx_queue_update(struct sock *sk, const struct sk_buff *skb) +{ + __sk_rx_queue_set(sk, skb, false); +} + static inline void sk_rx_queue_clear(struct sock *sk) { -#ifdef CONFIG_XPS - sk->sk_rx_queue_mapping = NO_QUEUE_MAPPING; +#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING + WRITE_ONCE(sk->sk_rx_queue_mapping, NO_QUEUE_MAPPING); #endif } -#ifdef CONFIG_XPS static inline int sk_rx_queue_get(const struct sock *sk) { - if (sk && sk->sk_rx_queue_mapping != NO_QUEUE_MAPPING) - return sk->sk_rx_queue_mapping; +#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING + if (sk) { + int res = READ_ONCE(sk->sk_rx_queue_mapping); + + if (res != NO_QUEUE_MAPPING) + return res; + } +#endif return -1; } -#endif static inline void sk_set_socket(struct sock *sk, struct socket *sock) { - sk_tx_queue_clear(sk); sk->sk_socket = sock; } @@ -1859,20 +2116,24 @@ 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; } static inline void sk_set_txhash(struct sock *sk) { - sk->sk_txhash = net_tx_rndhash(); + /* This pairs with READ_ONCE() in skb_set_hash_from_sk() */ + WRITE_ONCE(sk->sk_txhash, net_tx_rndhash()); } -static inline void sk_rethink_txhash(struct sock *sk) +static inline bool sk_rethink_txhash(struct sock *sk) { - if (sk->sk_txhash) + if (sk->sk_txhash && sk->sk_txrehash == SOCK_TXREHASH_ENABLED) { sk_set_txhash(sk); + return true; + } + return false; } static inline struct dst_entry * @@ -1895,12 +2156,10 @@ sk_dst_get(struct sock *sk) return dst; } -static inline void dst_negative_advice(struct sock *sk) +static inline void __dst_negative_advice(struct sock *sk) { struct dst_entry *ndst, *dst = __sk_dst_get(sk); - sk_rethink_txhash(sk); - if (dst && dst->ops->negative_advice) { ndst = dst->ops->negative_advice(dst); @@ -1912,6 +2171,12 @@ static inline void dst_negative_advice(struct sock *sk) } } +static inline void dst_negative_advice(struct sock *sk) +{ + sk_rethink_txhash(sk); + __dst_negative_advice(sk); +} + static inline void __sk_dst_set(struct sock *sk, struct dst_entry *dst) { @@ -1962,13 +2227,10 @@ static inline void sock_confirm_neigh(struct sk_buff *skb, struct neighbour *n) { if (skb_get_dst_pending_confirm(skb)) { struct sock *sk = skb->sk; - unsigned long now = jiffies; - /* avoid dirtying neighbour */ - if (READ_ONCE(n->confirmed) != now) - WRITE_ONCE(n->confirmed, now); if (sk && READ_ONCE(sk->sk_dst_pending_confirm)) WRITE_ONCE(sk->sk_dst_pending_confirm, 0); + neigh_confirm(n); } } @@ -1981,10 +2243,10 @@ static inline bool sk_can_gso(const struct sock *sk) void sk_setup_caps(struct sock *sk, struct dst_entry *dst); -static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags) +static inline void sk_gso_disable(struct sock *sk) { - sk->sk_route_nocaps |= flags; - sk->sk_route_caps &= ~flags; + sk->sk_gso_disabled = 1; + sk->sk_route_caps &= ~NETIF_F_GSO_MASK; } static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb, @@ -2030,9 +2292,7 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *fro if (err) return err; - skb->len += copy; - skb->data_len += copy; - skb->truesize += copy; + skb_len_add(skb, copy); sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); return 0; @@ -2131,9 +2391,12 @@ static inline void sock_poll_wait(struct file *filp, struct socket *sock, static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) { - if (sk->sk_txhash) { + /* This pairs with WRITE_ONCE() in sk_set_txhash() */ + u32 txhash = READ_ONCE(sk->sk_txhash); + + if (txhash) { skb->l4_hash = 1; - skb->hash = sk->sk_txhash; + skb->hash = txhash; } } @@ -2156,17 +2419,46 @@ static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk) sk_mem_charge(sk, skb->truesize); } +static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk) +{ + if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) { + skb_orphan(skb); + skb->destructor = sock_efree; + skb->sk = sk; + return true; + } + return false; +} + +static inline void skb_prepare_for_gro(struct sk_buff *skb) +{ + if (skb->destructor != sock_wfree) { + skb_orphan(skb); + return; + } + skb->slow_gro = 1; +} + void sk_reset_timer(struct sock *sk, struct timer_list *timer, unsigned long expires); void sk_stop_timer(struct sock *sk, struct timer_list *timer); +void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer); + int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, struct sk_buff *skb, unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb)); int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); -int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); + +int sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason *reason); + +static inline int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + return sock_queue_rcv_skb_reason(sk, skb, NULL); +} int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb); struct sk_buff *sock_dequeue_err_skb(struct sock *sk); @@ -2178,12 +2470,19 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk); static inline int sock_error(struct sock *sk) { int err; - if (likely(!sk->sk_err)) + + /* Avoid an atomic operation for the common case. + * This is racy since another cpu/thread can change sk_err under us. + */ + if (likely(data_race(!sk->sk_err))) return 0; + err = xchg(&sk->sk_err, 0); return -err; } +void sk_error_report(struct sock *sk); + static inline unsigned long sock_wspace(struct sock *sk) { int amt = 0; @@ -2245,31 +2544,32 @@ static inline void sk_stream_moderate_sndbuf(struct sock *sk) return; val = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1); + val = max_t(u32, val, sk_unused_reserved_mem(sk)); WRITE_ONCE(sk->sk_sndbuf, max_t(u32, val, SOCK_MIN_SNDBUF)); } -struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, - bool force_schedule); - /** * sk_page_frag - return an appropriate page_frag * @sk: socket * * Use the per task page_frag instead of the per socket one for - * optimization when we know that we're in the normal context and owns + * optimization when we know that we're in process context and own * everything that's associated with %current. * - * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest - * inside other socket operations and end up recursing into sk_page_frag() - * while it's already in use. + * 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. * * 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 (gfpflags_normal_context(sk->sk_allocation)) + if ((sk->sk_allocation & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC | __GFP_FS)) == + (__GFP_DIRECT_RECLAIM | __GFP_FS)) return ¤t->task_frag; return &sk->sk_frag; @@ -2290,6 +2590,11 @@ static inline gfp_t gfp_any(void) return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } +static inline gfp_t gfp_memcg_charge(void) +{ + return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; +} + static inline long sock_rcvtimeo(const struct sock *sk, bool noblock) { return noblock ? 0 : sk->sk_rcvtimeo; @@ -2404,20 +2709,21 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) __sock_recv_wifi_status(msg, sk, skb); } -void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, - struct sk_buff *skb); +void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb); #define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC) -static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, - struct sk_buff *skb) +static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) { -#define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL) | \ - (1UL << SOCK_RCVTSTAMP)) +#define FLAGS_RECV_CMSGS ((1UL << SOCK_RXQ_OVFL) | \ + (1UL << SOCK_RCVTSTAMP) | \ + (1UL << SOCK_RCVMARK)) #define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) - if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY) - __sock_recv_ts_and_drops(msg, sk, skb); + if (sk->sk_flags & FLAGS_RECV_CMSGS || sk->sk_tsflags & TSFLAGS_ANY) + __sock_recv_cmsgs(msg, sk, skb); else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP))) sock_write_timestamp(sk, skb->tstamp); else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP)) @@ -2442,7 +2748,7 @@ static inline void _sock_tx_timestamp(struct sock *sk, __u16 tsflags, __sock_tx_timestamp(tsflags, tx_flags); if (tsflags & SOF_TIMESTAMPING_OPT_ID && tskey && tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) - *tskey = sk->sk_tskey++; + *tskey = atomic_inc_return(&sk->sk_tskey) - 1; } if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS))) *tx_flags |= SKBTX_WIFI_STATUS; @@ -2460,7 +2766,11 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) &skb_shinfo(skb)->tskey); } -DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key); +static inline bool sk_is_tcp(const struct sock *sk) +{ + return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP; +} + /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from @@ -2472,47 +2782,56 @@ DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key); static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); - if (static_branch_unlikely(&tcp_rx_skb_cache_key) && - !sk->sk_rx_skb_cache) { - sk->sk_rx_skb_cache = skb; - skb_orphan(skb); - return; - } __kfree_skb(skb); } -static inline -struct net *sock_net(const struct sock *sk) +static inline bool +skb_sk_is_prefetched(struct sk_buff *skb) { - return read_pnet(&sk->sk_net); +#ifdef CONFIG_INET + return skb->destructor == sock_pfree; +#else + return false; +#endif /* CONFIG_INET */ } -static inline -void sock_net_set(struct sock *sk, struct net *net) +/* This helper checks if a socket is a full socket, + * ie _not_ a timewait or request socket. + */ +static inline bool sk_fullsock(const struct sock *sk) { - write_pnet(&sk->sk_net, net); + return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV); +} + +static inline bool +sk_is_refcounted(struct sock *sk) +{ + /* Only full sockets have sk->sk_flags. */ + return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE); } -static inline struct sock *skb_steal_sock(struct sk_buff *skb) +/** + * skb_steal_sock - steal a socket from an sk_buff + * @skb: sk_buff to steal the socket from + * @refcounted: is set to true if the socket is reference-counted + */ +static inline struct sock * +skb_steal_sock(struct sk_buff *skb, bool *refcounted) { if (skb->sk) { struct sock *sk = skb->sk; + *refcounted = true; + if (skb_sk_is_prefetched(skb)) + *refcounted = sk_is_refcounted(sk); skb->destructor = NULL; skb->sk = NULL; return sk; } + *refcounted = false; return NULL; } -/* This helper checks if a socket is a full socket, - * ie _not_ a timewait or request socket. - */ -static inline bool sk_fullsock(const struct sock *sk) -{ - return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV); -} - /* Checks if this SKB belongs to an HW offloaded socket * and whether any SW fallbacks are required based on dev. * Check decrypted mark in case skb_orphan() cleared socket. @@ -2575,24 +2894,25 @@ extern int sysctl_optmem_max; extern __u32 sysctl_wmem_default; extern __u32 sysctl_rmem_default; +#define SKB_FRAG_PAGE_ORDER get_order(32768) DECLARE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key); 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 READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset)); - return *proto->sysctl_wmem; + return READ_ONCE(*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 READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset)); - return *proto->sysctl_rmem; + return READ_ONCE(*proto->sysctl_rmem); } /* Default TCP Small queue budget is ~1 ms of data (1sec >> 10) @@ -2613,13 +2933,14 @@ static inline void sk_pacing_shift_update(struct sock *sk, int val) */ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif) { + int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); int mdif; - if (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif) + if (!bound_dev_if || bound_dev_if == dif) return true; mdif = l3mdev_master_ifindex_by_index(sock_net(sk), dif); - if (mdif && mdif == sk->sk_bound_dev_if) + if (mdif && mdif == bound_dev_if) return true; return false; @@ -2627,4 +2948,31 @@ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif) void sock_def_readable(struct sock *sk); +int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk); +void sock_set_timestamp(struct sock *sk, int optname, bool valbool); +int sock_set_timestamping(struct sock *sk, int optname, + struct so_timestamping timestamping); + +void sock_enable_timestamps(struct sock *sk); +void sock_no_linger(struct sock *sk); +void sock_set_keepalive(struct sock *sk); +void sock_set_priority(struct sock *sk, u32 priority); +void sock_set_rcvbuf(struct sock *sk, int val); +void sock_set_mark(struct sock *sk, u32 val); +void sock_set_reuseaddr(struct sock *sk); +void sock_set_reuseport(struct sock *sk); +void sock_set_sndtimeo(struct sock *sk, s64 secs); + +int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len); + +int sock_get_timeout(long timeo, void *optval, bool old_timeval); +int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, + sockptr_t optval, int optlen, bool old_timeval); + +static inline bool sk_is_readable(struct sock *sk) +{ + if (sk->sk_prot->sock_is_readable) + return sk->sk_prot->sock_is_readable(sk); + return false; +} #endif /* _SOCK_H */ |