diff options
Diffstat (limited to 'include/net/sock.h')
| -rw-r--r-- | include/net/sock.h | 885 |
1 files changed, 515 insertions, 370 deletions
diff --git a/include/net/sock.h b/include/net/sock.h index 11d503417591..aafe8bdb2c0f 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -76,19 +76,6 @@ * the other protocols. */ -/* Define this to get the SOCK_DBG debugging facility. */ -#define SOCK_DEBUGGING -#ifdef SOCK_DEBUGGING -#define SOCK_DEBUG(sk, msg...) do { if ((sk) && sock_flag((sk), SOCK_DBG)) \ - printk(KERN_DEBUG msg); } while (0) -#else -/* Validate arguments and do nothing */ -static inline __printf(2, 3) -void SOCK_DEBUG(const struct sock *sk, const char *msg, ...) -{ -} -#endif - /* This is the per-socket lock. The spinlock provides a synchronization * between user contexts and software interrupt processing, whereas the * mini-semaphore synchronizes multiple users amongst themselves. @@ -131,6 +118,7 @@ typedef __u64 __bitwise __addrpair; * @skc_reuseport: %SO_REUSEPORT setting * @skc_ipv6only: socket is IPV6 only * @skc_net_refcnt: socket is using net ref counting + * @skc_bypass_prot_mem: bypass the per-protocol memory accounting for skb * @skc_bound_dev_if: bound device index if != 0 * @skc_bind_node: bind hash linkage for various protocol lookup tables * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol @@ -187,6 +175,7 @@ struct sock_common { unsigned char skc_reuseport:1; unsigned char skc_ipv6only:1; unsigned char skc_net_refcnt:1; + unsigned char skc_bypass_prot_mem:1; int skc_bound_dev_if; union { struct hlist_node skc_bind_node; @@ -262,6 +251,7 @@ struct sk_filter; * @sk_dst_cache: destination cache * @sk_dst_pending_confirm: need to confirm neighbour * @sk_policy: flow policy + * @psp_assoc: PSP association, if socket is PSP-secured * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed * @sk_tsq_flags: TCP Small Queues flags @@ -277,8 +267,6 @@ struct sk_filter; * @sk_pacing_status: Pacing status (requested, handled by sch_fq) * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE) * @sk_sndbuf: size of send buffer in bytes - * @__sk_flags_offset: empty field used to determine location of bitfield - * @sk_padding: unused element for alignment * @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) @@ -297,9 +285,11 @@ struct sk_filter; * @sk_err_soft: errors that don't cause failure but are the cause of a * persistent failure not just 'timed out' * @sk_drops: raw/udp drops counter + * @sk_drop_counters: optional pointer to numa_drop_counters * @sk_ack_backlog: current listen backlog * @sk_max_ack_backlog: listen backlog set in listen() * @sk_uid: user id of owner + * @sk_ino: inode number (zero if orphaned) * @sk_prefer_busy_poll: prefer busypolling over softirq processing * @sk_busy_poll_budget: napi processing budget when busypolling * @sk_priority: %SO_PRIORITY setting @@ -315,15 +305,19 @@ struct sk_filter; * @sk_txrehash: enable TX hash rethink * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer + * @tcp_retransmit_timer: tcp retransmit timer + * @mptcp_retransmit_timer: mptcp retransmit 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 flags + * @sk_bpf_cb_flags: used in bpf_setsockopt() * @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_tx_queue_mapping_jiffies: time in jiffies of last @sk_tx_queue_mapping refresh. * @sk_zckey: counter to order MSG_ZEROCOPY notifications * @sk_socket: Identd and reporting IO signals * @sk_user_data: RPC layer private data. Write-protected by @sk_callback_lock. @@ -336,7 +330,7 @@ struct sk_filter; * @sk_cgrp_data: cgroup data for this cgroup * @sk_memcg: this socket's memory cgroup association * @sk_write_pending: a write to stream socket waits to start - * @sk_wait_pending: number of threads blocked on this socket + * @sk_disconnects: number of disconnect operations performed on this sock * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed * @sk_write_space: callback to indicate there is bf sending space available @@ -351,8 +345,16 @@ struct sk_filter; * @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 + * @sk_scm_recv_flags: all flags used by scm_recv() + * @sk_scm_credentials: flagged by SO_PASSCRED to recv SCM_CREDENTIALS + * @sk_scm_security: flagged by SO_PASSSEC to recv SCM_SECURITY + * @sk_scm_pidfd: flagged by SO_PASSPIDFD to recv SCM_PIDFD + * @sk_scm_rights: flagged by SO_PASSRIGHTS to recv SCM_RIGHTS + * @sk_scm_unused: unused flags for scm_recv() * @ns_tracker: tracker for netns reference - * @sk_bind2_node: bind node in the bhash2 table + * @sk_user_frags: xarray of pages the user is holding a reference on. + * @sk_owner: reference to the real owner of the socket that calls + * sock_lock_init_class_and_name(). */ struct sock { /* @@ -383,6 +385,7 @@ struct sock { #define sk_reuseport __sk_common.skc_reuseport #define sk_ipv6only __sk_common.skc_ipv6only #define sk_net_refcnt __sk_common.skc_net_refcnt +#define sk_bypass_prot_mem __sk_common.skc_bypass_prot_mem #define sk_bound_dev_if __sk_common.skc_bound_dev_if #define sk_bind_node __sk_common.skc_bind_node #define sk_prot __sk_common.skc_prot @@ -394,14 +397,10 @@ 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; + __cacheline_group_begin(sock_write_rx); - socket_lock_t sk_lock; atomic_t sk_drops; - int sk_rcvlowat; + __s32 sk_peek_off; struct sk_buff_head sk_error_queue; struct sk_buff_head sk_receive_queue; /* @@ -418,18 +417,24 @@ 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; + __cacheline_group_end(sock_write_rx); + + __cacheline_group_begin(sock_read_rx); + /* early demux fields */ + struct dst_entry __rcu *sk_rx_dst; + int sk_rx_dst_ifindex; + u32 sk_rx_dst_cookie; + #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sk_ll_usec; - /* ===== mostly read cache line ===== */ unsigned int sk_napi_id; + u16 sk_busy_poll_budget; + u8 sk_prefer_busy_poll; #endif + u8 sk_userlocks; int sk_rcvbuf; - int sk_wait_pending; struct sk_filter __rcu *sk_filter; union { @@ -438,15 +443,38 @@ struct sock { struct socket_wq *sk_wq_raw; /* public: */ }; + + void (*sk_data_ready)(struct sock *sk); + long sk_rcvtimeo; + int sk_rcvlowat; + __cacheline_group_end(sock_read_rx); + + __cacheline_group_begin(sock_read_rxtx); + int sk_err; + struct socket *sk_socket; +#ifdef CONFIG_MEMCG + struct mem_cgroup *sk_memcg; +#endif #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; #endif +#if IS_ENABLED(CONFIG_INET_PSP) + struct psp_assoc __rcu *psp_assoc; +#endif + __cacheline_group_end(sock_read_rxtx); - struct dst_entry __rcu *sk_dst_cache; + __cacheline_group_begin(sock_write_rxtx); + socket_lock_t sk_lock; + u32 sk_reserved_mem; + int sk_forward_alloc; + u32 sk_tsflags; + __cacheline_group_end(sock_write_rxtx); + + __cacheline_group_begin(sock_write_tx); + int sk_write_pending; atomic_t sk_omem_alloc; - int sk_sndbuf; + int sk_err_soft; - /* ===== cache line for TX ===== */ int sk_wmem_queued; refcount_t sk_wmem_alloc; unsigned long sk_tsq_flags; @@ -455,22 +483,44 @@ struct sock { struct rb_root tcp_rtx_queue; }; struct sk_buff_head sk_write_queue; - __s32 sk_peek_off; - int sk_write_pending; - __u32 sk_dst_pending_confirm; - u32 sk_pacing_status; /* see enum sk_pacing */ - long sk_sndtimeo; - struct timer_list sk_timer; - __u32 sk_priority; - __u32 sk_mark; + struct page_frag sk_frag; + union { + struct timer_list sk_timer; + struct timer_list tcp_retransmit_timer; + struct timer_list mptcp_retransmit_timer; + }; unsigned long sk_pacing_rate; /* bytes per second */ + atomic_t sk_zckey; + atomic_t sk_tskey; + unsigned long sk_tx_queue_mapping_jiffies; + __cacheline_group_end(sock_write_tx); + + __cacheline_group_begin(sock_read_tx); + u32 sk_dst_pending_confirm; + u32 sk_pacing_status; /* see enum sk_pacing */ unsigned long sk_max_pacing_rate; - struct page_frag sk_frag; + long sk_sndtimeo; + u32 sk_priority; + u32 sk_mark; + kuid_t sk_uid; + u16 sk_protocol; + u16 sk_type; + struct dst_entry __rcu *sk_dst_cache; netdev_features_t sk_route_caps; - int sk_gso_type; +#ifdef CONFIG_SOCK_VALIDATE_XMIT + struct sk_buff* (*sk_validate_xmit_skb)(struct sock *sk, + struct net_device *dev, + struct sk_buff *skb); +#endif + u16 sk_gso_type; + u16 sk_gso_max_segs; unsigned int sk_gso_max_size; gfp_t sk_allocation; - __u32 sk_txhash; + u32 sk_txhash; + int sk_sndbuf; + u8 sk_pacing_shift; + bool sk_use_task_frag; + __cacheline_group_end(sock_read_tx); /* * Because of non atomicity rules, all @@ -479,72 +529,71 @@ struct sock { u8 sk_gso_disabled : 1, sk_kern_sock : 1, sk_no_check_tx : 1, - sk_no_check_rx : 1, - sk_userlocks : 4; - u8 sk_pacing_shift; - u16 sk_type; - u16 sk_protocol; - u16 sk_gso_max_segs; + sk_no_check_rx : 1; + u8 sk_shutdown; unsigned long sk_lingertime; struct proto *sk_prot_creator; rwlock_t sk_callback_lock; - int sk_err, - sk_err_soft; 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 + unsigned long sk_ino; 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 seqlock_t sk_stamp_seq; #endif - atomic_t sk_tskey; - atomic_t sk_zckey; - u32 sk_tsflags; - u8 sk_shutdown; + int sk_disconnects; + union { + u8 sk_txrehash; + u8 sk_scm_recv_flags; + struct { + u8 sk_scm_credentials : 1, + sk_scm_security : 1, + sk_scm_pidfd : 1, + sk_scm_rights : 1, + sk_scm_unused : 4; + }; + }; u8 sk_clockid; u8 sk_txtime_deadline_mode : 1, sk_txtime_report_errors : 1, sk_txtime_unused : 6; - bool sk_use_task_frag; +#define SK_BPF_CB_FLAG_TEST(SK, FLAG) ((SK)->sk_bpf_cb_flags & (FLAG)) + u8 sk_bpf_cb_flags; - struct socket *sk_socket; void *sk_user_data; #ifdef CONFIG_SECURITY void *sk_security; #endif struct sock_cgroup_data sk_cgrp_data; - struct mem_cgroup *sk_memcg; void (*sk_state_change)(struct sock *sk); - void (*sk_data_ready)(struct sock *sk); void (*sk_write_space)(struct sock *sk); void (*sk_error_report)(struct sock *sk); int (*sk_backlog_rcv)(struct sock *sk, struct sk_buff *skb); -#ifdef CONFIG_SOCK_VALIDATE_XMIT - struct sk_buff* (*sk_validate_xmit_skb)(struct sock *sk, - struct net_device *dev, - struct sk_buff *skb); -#endif void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; #ifdef CONFIG_BPF_SYSCALL struct bpf_local_storage __rcu *sk_bpf_storage; #endif + struct numa_drop_counters *sk_drop_counters; struct rcu_head sk_rcu; netns_tracker ns_tracker; - struct hlist_node sk_bind2_node; + struct xarray sk_user_frags; + +#if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES) + struct module *sk_owner; +#endif +}; + +struct sock_bh_locked { + struct sock *sock; + local_lock_t bh_lock; }; enum sk_pacing { @@ -789,11 +838,9 @@ static inline bool sk_del_node_init(struct sock *sk) { bool rc = __sk_del_node_init(sk); - if (rc) { - /* paranoid for a while -acme */ - WARN_ON(refcount_read(&sk->sk_refcnt) == 1); + if (rc) __sock_put(sk); - } + return rc; } #define sk_del_node_init_rcu(sk) sk_del_node_init(sk) @@ -811,14 +858,25 @@ static inline bool sk_nulls_del_node_init_rcu(struct sock *sk) { bool rc = __sk_nulls_del_node_init_rcu(sk); - if (rc) { - /* paranoid for a while -acme */ - WARN_ON(refcount_read(&sk->sk_refcnt) == 1); + if (rc) __sock_put(sk); - } + return rc; } +static inline bool sk_nulls_replace_node_init_rcu(struct sock *old, + struct sock *new) +{ + if (sk_hashed(old)) { + hlist_nulls_replace_init_rcu(&old->sk_nulls_node, + &new->sk_nulls_node); + __sock_put(old); + return true; + } + + return false; +} + static inline void __sk_add_node(struct sock *sk, struct hlist_head *list) { hlist_add_head(&sk->sk_node, list); @@ -873,16 +931,6 @@ 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) \ @@ -900,8 +948,8 @@ static inline void sk_add_bind2_node(struct sock *sk, struct hlist_head *list) 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) +#define sk_for_each_bound_safe(__sk, tmp, list) \ + hlist_for_each_entry_safe(__sk, tmp, list, sk_bind_node) /** * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset @@ -959,9 +1007,17 @@ enum sock_flags { SOCK_XDP, /* XDP is attached */ SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */ SOCK_RCVMARK, /* Receive SO_MARK ancillary data with packet */ + SOCK_RCVPRIORITY, /* Receive SO_PRIORITY ancillary data with packet */ + SOCK_TIMESTAMPING_ANY, /* Copy of sk_tsflags & TSFLAGS_ANY */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) +/* + * The highest bit of sk_tsflags is reserved for kernel-internal + * SOCKCM_FLAG_TS_OPT_ID. There is a check in core/sock.c to control that + * SOF_TIMESTAMPING* values do not reach this reserved area + */ +#define SOCKCM_FLAG_TS_OPT_ID BIT(31) static inline void sock_copy_flags(struct sock *nsk, const struct sock *osk) { @@ -1053,6 +1109,12 @@ static inline void sk_wmem_queued_add(struct sock *sk, int val) WRITE_ONCE(sk->sk_wmem_queued, sk->sk_wmem_queued + val); } +static inline void sk_forward_alloc_add(struct sock *sk, int val) +{ + /* Paired with lockless reads of sk->sk_forward_alloc */ + WRITE_ONCE(sk->sk_forward_alloc, sk->sk_forward_alloc + val); +} + void sk_stream_write_space(struct sock *sk); /* OOB backlog add */ @@ -1126,41 +1188,6 @@ static inline void sk_incoming_cpu_update(struct sock *sk) WRITE_ONCE(sk->sk_incoming_cpu, cpu); } -static inline void sock_rps_record_flow_hash(__u32 hash) -{ -#ifdef CONFIG_RPS - struct rps_sock_flow_table *sock_flow_table; - - rcu_read_lock(); - sock_flow_table = rcu_dereference(rps_sock_flow_table); - rps_record_sock_flow(sock_flow_table, hash); - rcu_read_unlock(); -#endif -} - -static inline void sock_rps_record_flow(const struct sock *sk) -{ -#ifdef CONFIG_RPS - if (static_branch_unlikely(&rfs_needed)) { - /* Reading sk->sk_rxhash might incur an expensive cache line - * miss. - * - * TCP_ESTABLISHED does cover almost all states where RFS - * might be useful, and is cheaper [1] than testing : - * IPv4: inet_sk(sk)->inet_daddr - * IPv6: ipv6_addr_any(&sk->sk_v6_daddr) - * OR an additional socket flag - * [1] : sk_state and sk_prot are in the same cache line. - */ - if (sk->sk_state == TCP_ESTABLISHED) { - /* This READ_ONCE() is paired with the WRITE_ONCE() - * from sock_rps_save_rxhash() and sock_rps_reset_rxhash(). - */ - sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash)); - } - } -#endif -} static inline void sock_rps_save_rxhash(struct sock *sk, const struct sk_buff *skb) @@ -1183,8 +1210,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk) } #define sk_wait_event(__sk, __timeo, __condition, __wait) \ - ({ int __rc; \ - __sk->sk_wait_pending++; \ + ({ int __rc, __dis = __sk->sk_disconnects; \ release_sock(__sk); \ __rc = __condition; \ if (!__rc) { \ @@ -1194,8 +1220,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk) } \ sched_annotate_sleep(); \ lock_sock(__sk); \ - __sk->sk_wait_pending--; \ - __rc = __condition; \ + __rc = __dis == __sk->sk_disconnects ? __condition : -EPIPE; \ __rc; \ }) @@ -1240,6 +1265,13 @@ static inline void sk_prot_clear_nulls(struct sock *sk, int size) size - offsetof(struct sock, sk_node.pprev)); } +struct proto_accept_arg { + int flags; + int err; + int is_empty; + bool kern; +}; + /* Networking protocol blocks we attach to sockets. * socket layer -> transport layer interface */ @@ -1247,15 +1279,15 @@ struct proto { void (*close)(struct sock *sk, long timeout); int (*pre_connect)(struct sock *sk, - struct sockaddr *uaddr, + struct sockaddr_unsized *uaddr, int addr_len); int (*connect)(struct sock *sk, - struct sockaddr *uaddr, + struct sockaddr_unsized *uaddr, int addr_len); int (*disconnect)(struct sock *sk, int flags); - struct sock * (*accept)(struct sock *sk, int flags, int *err, - bool kern); + struct sock * (*accept)(struct sock *sk, + struct proto_accept_arg *arg); int (*ioctl)(struct sock *sk, int cmd, int *karg); @@ -1279,9 +1311,9 @@ struct proto { size_t len, int flags, int *addr_len); void (*splice_eof)(struct socket *sock); int (*bind)(struct sock *sk, - struct sockaddr *addr, int addr_len); + struct sockaddr_unsized *addr, int addr_len); int (*bind_add)(struct sock *sk, - struct sockaddr *addr, int addr_len); + struct sockaddr_unsized *addr, int addr_len); int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); @@ -1307,10 +1339,6 @@ struct proto { 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 (*sock_is_readable)(struct sock *sk); /* Memory pressure */ @@ -1345,8 +1373,6 @@ struct proto { unsigned int useroffset; /* Usercopy region offset */ unsigned int usersize; /* Usercopy region size */ - unsigned int __percpu *orphan_count; - struct request_sock_ops *rsk_prot; struct timewait_sock_ops *twsk_prot; @@ -1371,15 +1397,6 @@ int sock_load_diag_module(int family, int protocol); 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)) @@ -1417,72 +1434,6 @@ static inline int sk_under_cgroup_hierarchy(struct sock *sk, #endif } -static inline bool sk_has_memory_pressure(const struct sock *sk) -{ - return sk->sk_prot->memory_pressure != NULL; -} - -static inline bool sk_under_global_memory_pressure(const struct sock *sk) -{ - return sk->sk_prot->memory_pressure && - !!READ_ONCE(*sk->sk_prot->memory_pressure); -} - -static inline bool sk_under_memory_pressure(const struct sock *sk) -{ - if (!sk->sk_prot->memory_pressure) - return false; - - if (mem_cgroup_sockets_enabled && sk->sk_memcg && - mem_cgroup_under_socket_pressure(sk->sk_memcg)) - return true; - - return !!READ_ONCE(*sk->sk_prot->memory_pressure); -} - -static inline long -proto_memory_allocated(const struct proto *prot) -{ - 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) -{ - 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) -{ - 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) @@ -1509,15 +1460,6 @@ proto_sockets_allocated_sum_positive(struct proto *prot) return percpu_counter_sum_positive(prot->sockets_allocated); } -static inline bool -proto_memory_pressure(struct proto *prot) -{ - if (!prot->memory_pressure) - return false; - return !!READ_ONCE(*prot->memory_pressure); -} - - #ifdef CONFIG_PROC_FS #define PROTO_INUSE_NR 64 /* should be enough for the first time */ struct prot_inuse { @@ -1571,6 +1513,10 @@ static inline int __sk_prot_rehash(struct sock *sk) #define SOCK_BINDADDR_LOCK 4 #define SOCK_BINDPORT_LOCK 8 +/** + * define SOCK_CONNECT_BIND - &sock->sk_userlocks flag for auto-bind at connect() time + */ +#define SOCK_CONNECT_BIND 16 struct socket_alloc { struct socket socket; @@ -1626,7 +1572,7 @@ static inline bool sk_wmem_schedule(struct sock *sk, int size) } static inline bool -sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) +__sk_rmem_schedule(struct sock *sk, int size, bool pfmemalloc) { int delta; @@ -1634,7 +1580,13 @@ sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) return true; delta = size - sk->sk_forward_alloc; return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) || - skb_pfmemalloc(skb); + pfmemalloc; +} + +static inline bool +sk_rmem_schedule(struct sock *sk, const struct sk_buff *skb, int size) +{ + return __sk_rmem_schedule(sk, size, skb_pfmemalloc(skb)); } static inline int sk_unused_reserved_mem(const struct sock *sk) @@ -1673,17 +1625,48 @@ static inline void sk_mem_charge(struct sock *sk, int size) { if (!sk_has_account(sk)) return; - sk->sk_forward_alloc -= size; + sk_forward_alloc_add(sk, -size); } static inline void sk_mem_uncharge(struct sock *sk, int size) { if (!sk_has_account(sk)) return; - sk->sk_forward_alloc += size; + sk_forward_alloc_add(sk, size); sk_mem_reclaim(sk); } +void __sk_charge(struct sock *sk, gfp_t gfp); + +#if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES) +static inline void sk_owner_set(struct sock *sk, struct module *owner) +{ + __module_get(owner); + sk->sk_owner = owner; +} + +static inline void sk_owner_clear(struct sock *sk) +{ + sk->sk_owner = NULL; +} + +static inline void sk_owner_put(struct sock *sk) +{ + module_put(sk->sk_owner); +} +#else +static inline void sk_owner_set(struct sock *sk, struct module *owner) +{ +} + +static inline void sk_owner_clear(struct sock *sk) +{ +} + +static inline void sk_owner_put(struct sock *sk) +{ +} +#endif /* * Macro so as to not evaluate some arguments when * lockdep is not enabled. @@ -1693,13 +1676,14 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) */ #define sock_lock_init_class_and_name(sk, sname, skey, name, key) \ do { \ + sk_owner_set(sk, THIS_MODULE); \ sk->sk_lock.owned = 0; \ init_waitqueue_head(&sk->sk_lock.wq); \ spin_lock_init(&(sk)->sk_lock.slock); \ debug_check_no_locks_freed((void *)&(sk)->sk_lock, \ - sizeof((sk)->sk_lock)); \ + sizeof((sk)->sk_lock)); \ lockdep_set_class_and_name(&(sk)->sk_lock.slock, \ - (skey), (sname)); \ + (skey), (sname)); \ lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \ } while (0) @@ -1733,7 +1717,7 @@ 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 + * This version should be used for very small section, where process won't block * return false if fast path is taken: * * sk_lock.slock locked, owned = 0, BH disabled @@ -1804,6 +1788,13 @@ static inline void sock_owned_by_me(const struct sock *sk) #endif } +static inline void sock_not_owned_by_me(const struct sock *sk) +{ +#ifdef CONFIG_LOCKDEP + WARN_ON_ONCE(lockdep_sock_is_held(sk) && debug_locks); +#endif +} + static inline bool sock_owned_by_user(const struct sock *sk) { sock_owned_by_me(sk); @@ -1817,12 +1808,11 @@ static inline bool sock_owned_by_user_nocheck(const struct sock *sk) static inline void sock_release_ownership(struct sock *sk) { - if (sock_owned_by_user_nocheck(sk)) { - sk->sk_lock.owned = 0; + DEBUG_NET_WARN_ON_ONCE(!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_); - } + /* The sk_lock has mutex_unlock() semantics: */ + mutex_release(&sk->sk_lock.dep_map, _RET_IP_); } /* no reclassification while locks are held */ @@ -1837,9 +1827,14 @@ static inline bool sock_allow_reclassification(const struct sock *csk) struct sock *sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern); void sk_free(struct sock *sk); +void sk_net_refcnt_upgrade(struct sock *sk); void sk_destruct(struct sock *sk); -struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority); -void sk_free_unlock_clone(struct sock *sk); +struct sock *sk_clone(const struct sock *sk, const gfp_t priority, bool lock); + +static inline struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) +{ + return sk_clone(sk, priority, true); +} struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority); @@ -1853,6 +1848,15 @@ void sock_efree(struct sk_buff *skb); #ifdef CONFIG_INET void sock_edemux(struct sk_buff *skb); void sock_pfree(struct sk_buff *skb); + +static inline void skb_set_owner_edemux(struct sk_buff *skb, struct sock *sk) +{ + skb_orphan(skb); + if (refcount_inc_not_zero(&sk->sk_refcnt)) { + skb->sk = sk; + skb->destructor = sock_edemux; + } +} #else #define sock_edemux sock_efree #endif @@ -1861,11 +1865,13 @@ 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 do_sock_setsockopt(struct socket *sock, bool compat, int level, + int optname, sockptr_t optval, int optlen); +int do_sock_getsockopt(struct socket *sock, bool compat, int level, + int optname, sockptr_t optval, sockptr_t 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_pskb(struct sock *sk, unsigned long header_len, @@ -1880,6 +1886,8 @@ static inline struct sk_buff *sock_alloc_send_skb(struct sock *sk, } void *sock_kmalloc(struct sock *sk, int size, gfp_t priority); +void *sock_kmemdup(struct sock *sk, const void *src, + 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); @@ -1895,12 +1903,19 @@ struct sockcm_cookie { u64 transmit_time; u32 mark; u32 tsflags; + u32 ts_opt_id; + u32 priority; + u32 dmabuf_id; }; static inline void sockcm_init(struct sockcm_cookie *sockc, const struct sock *sk) { - *sockc = (struct sockcm_cookie) { .tsflags = sk->sk_tsflags }; + *sockc = (struct sockcm_cookie) { + .mark = READ_ONCE(sk->sk_mark), + .tsflags = READ_ONCE(sk->sk_tsflags), + .priority = READ_ONCE(sk->sk_priority), + }; } int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, @@ -1912,10 +1927,10 @@ int sock_cmsg_send(struct sock *sk, struct msghdr *msg, * Functions to fill in entries in struct proto_ops when a protocol * does not implement a particular function. */ -int sock_no_bind(struct socket *, struct sockaddr *, int); -int sock_no_connect(struct socket *, struct sockaddr *, int, int); +int sock_no_bind(struct socket *sock, struct sockaddr_unsized *saddr, int len); +int sock_no_connect(struct socket *sock, struct sockaddr_unsized *saddr, int len, int flags); int sock_no_socketpair(struct socket *, struct socket *); -int sock_no_accept(struct socket *, struct socket *, int, bool); +int sock_no_accept(struct socket *, struct socket *, struct proto_accept_arg *); 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); @@ -2000,23 +2015,31 @@ static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) /* sk_tx_queue_mapping accept only upto a 16-bit value */ if (WARN_ON_ONCE((unsigned short)tx_queue >= USHRT_MAX)) return; - sk->sk_tx_queue_mapping = tx_queue; + /* Paired with READ_ONCE() in sk_tx_queue_get() and + * other WRITE_ONCE() because socket lock might be not held. + */ + if (READ_ONCE(sk->sk_tx_queue_mapping) != tx_queue) { + WRITE_ONCE(sk->sk_tx_queue_mapping, tx_queue); + WRITE_ONCE(sk->sk_tx_queue_mapping_jiffies, jiffies); + return; + } + + /* Refresh sk_tx_queue_mapping_jiffies if too old. */ + if (time_is_before_jiffies(READ_ONCE(sk->sk_tx_queue_mapping_jiffies) + HZ)) + WRITE_ONCE(sk->sk_tx_queue_mapping_jiffies, jiffies); } #define NO_QUEUE_MAPPING USHRT_MAX static inline void sk_tx_queue_clear(struct sock *sk) { - sk->sk_tx_queue_mapping = NO_QUEUE_MAPPING; + /* Paired with READ_ONCE() in sk_tx_queue_get() and + * other WRITE_ONCE() because socket lock might be not held. + */ + WRITE_ONCE(sk->sk_tx_queue_mapping, NO_QUEUE_MAPPING); } -static inline int sk_tx_queue_get(const struct sock *sk) -{ - if (sk && sk->sk_tx_queue_mapping != NO_QUEUE_MAPPING) - return sk->sk_tx_queue_mapping; - - return -1; -} +int sk_tx_queue_get(const struct sock *sk); static inline void __sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb, @@ -2067,6 +2090,13 @@ static inline int sk_rx_queue_get(const struct sock *sk) static inline void sk_set_socket(struct sock *sk, struct socket *sock) { sk->sk_socket = sock; + if (sock) { + WRITE_ONCE(sk->sk_uid, SOCK_INODE(sock)->i_uid); + WRITE_ONCE(sk->sk_ino, SOCK_INODE(sock)->i_ino); + } else { + /* Note: sk_uid is unchanged. */ + WRITE_ONCE(sk->sk_ino, 0); + } } static inline wait_queue_head_t *sk_sleep(struct sock *sk) @@ -2097,18 +2127,25 @@ static inline void sock_graft(struct sock *sk, struct socket *parent) rcu_assign_pointer(sk->sk_wq, &parent->wq); parent->sk = sk; sk_set_socket(sk, parent); - sk->sk_uid = SOCK_INODE(parent)->i_uid; security_sock_graft(sk, parent); write_unlock_bh(&sk->sk_callback_lock); } -kuid_t sock_i_uid(struct sock *sk); -unsigned long __sock_i_ino(struct sock *sk); -unsigned long sock_i_ino(struct sock *sk); +static inline unsigned long sock_i_ino(const struct sock *sk) +{ + /* Paired with WRITE_ONCE() in sock_graft() and sock_orphan() */ + return READ_ONCE(sk->sk_ino); +} + +static inline kuid_t sk_uid(const struct sock *sk) +{ + /* Paired with WRITE_ONCE() in sockfs_setattr() */ + return READ_ONCE(sk->sk_uid); +} static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk) { - return sk ? sk->sk_uid : make_kuid(net->user_ns, 0); + return sk ? sk_uid(sk) : make_kuid(net->user_ns, 0); } static inline u32 net_tx_rndhash(void) @@ -2134,14 +2171,14 @@ static inline bool sk_rethink_txhash(struct sock *sk) } static inline struct dst_entry * -__sk_dst_get(struct sock *sk) +__sk_dst_get(const struct sock *sk) { return rcu_dereference_check(sk->sk_dst_cache, lockdep_sock_is_held(sk)); } static inline struct dst_entry * -sk_dst_get(struct sock *sk) +sk_dst_get(const struct sock *sk) { struct dst_entry *dst; @@ -2155,17 +2192,10 @@ sk_dst_get(struct sock *sk) static inline void __dst_negative_advice(struct sock *sk) { - struct dst_entry *ndst, *dst = __sk_dst_get(sk); + struct dst_entry *dst = __sk_dst_get(sk); - if (dst && dst->ops->negative_advice) { - ndst = dst->ops->negative_advice(dst); - - if (ndst != dst) { - rcu_assign_pointer(sk->sk_dst_cache, ndst); - sk_tx_queue_clear(sk); - sk->sk_dst_pending_confirm = 0; - } - } + if (dst && dst->ops->negative_advice) + dst->ops->negative_advice(sk, dst); } static inline void dst_negative_advice(struct sock *sk) @@ -2180,7 +2210,7 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst) struct dst_entry *old_dst; sk_tx_queue_clear(sk); - sk->sk_dst_pending_confirm = 0; + WRITE_ONCE(sk->sk_dst_pending_confirm, 0); old_dst = rcu_dereference_protected(sk->sk_dst_cache, lockdep_sock_is_held(sk)); rcu_assign_pointer(sk->sk_dst_cache, dst); @@ -2193,8 +2223,8 @@ sk_dst_set(struct sock *sk, struct dst_entry *dst) struct dst_entry *old_dst; sk_tx_queue_clear(sk); - sk->sk_dst_pending_confirm = 0; - old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst); + WRITE_ONCE(sk->sk_dst_pending_confirm, 0); + old_dst = unrcu_pointer(xchg(&sk->sk_dst_cache, RCU_INITIALIZER(dst))); dst_release(old_dst); } @@ -2231,7 +2261,7 @@ static inline void sock_confirm_neigh(struct sk_buff *skb, struct neighbour *n) } } -bool sk_mc_loop(struct sock *sk); +bool sk_mc_loop(const struct sock *sk); static inline bool sk_can_gso(const struct sock *sk) { @@ -2295,6 +2325,7 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *fro return 0; } +#define SK_WMEM_ALLOC_BIAS 1 /** * sk_wmem_alloc_get - returns write allocations * @sk: socket @@ -2303,7 +2334,7 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *fro */ static inline int sk_wmem_alloc_get(const struct sock *sk) { - return refcount_read(&sk->sk_wmem_alloc) - 1; + return refcount_read(&sk->sk_wmem_alloc) - SK_WMEM_ALLOC_BIAS; } /** @@ -2365,7 +2396,7 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) } /** - * sock_poll_wait - place memory barrier behind the poll_wait call. + * sock_poll_wait - wrapper for the poll_wait call. * @filp: file * @sock: socket to wait on * @p: poll_table @@ -2375,15 +2406,12 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) static inline void sock_poll_wait(struct file *filp, struct socket *sock, poll_table *p) { - if (!poll_does_not_wait(p)) { - poll_wait(filp, &sock->wq.wait, p); - /* We need to be sure we are in sync with the - * socket flags modification. - * - * This memory barrier is paired in the wq_has_sleeper. - */ - smp_mb(); - } + /* Provides a barrier we need to be sure we are in sync + * with the socket flags modification. + * + * This memory barrier is paired in the wq_has_sleeper. + */ + poll_wait(filp, &sock->wq.wait, p); } static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) @@ -2536,6 +2564,12 @@ static inline void sk_wake_async(const struct sock *sk, int how, int band) } } +static inline void sk_wake_async_rcu(const struct sock *sk, int how, int band) +{ + if (unlikely(sock_flag(sk, SOCK_FASYNC))) + sock_wake_async(rcu_dereference(sk->sk_wq), how, band); +} + /* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might * need sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak. * Note: for send buffers, TCP works better if we can build two skbs at @@ -2585,12 +2619,16 @@ static inline struct page_frag *sk_page_frag(struct sock *sk) bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag); +static inline bool __sock_writeable(const struct sock *sk, int wmem_alloc) +{ + return wmem_alloc < (READ_ONCE(sk->sk_sndbuf) >> 1); +} /* * Default write policy as shown to user space via poll/select/SIGIO */ static inline bool sock_writeable(const struct sock *sk) { - return refcount_read(&sk->sk_wmem_alloc) < (READ_ONCE(sk->sk_sndbuf) >> 1); + return __sock_writeable(sk, refcount_read(&sk->sk_wmem_alloc)); } static inline gfp_t gfp_any(void) @@ -2603,14 +2641,62 @@ static inline gfp_t gfp_memcg_charge(void) return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } +#ifdef CONFIG_MEMCG +static inline struct mem_cgroup *mem_cgroup_from_sk(const struct sock *sk) +{ + return sk->sk_memcg; +} + +static inline bool mem_cgroup_sk_enabled(const struct sock *sk) +{ + return mem_cgroup_sockets_enabled && mem_cgroup_from_sk(sk); +} + +static inline bool mem_cgroup_sk_under_memory_pressure(const struct sock *sk) +{ + struct mem_cgroup *memcg = mem_cgroup_from_sk(sk); + +#ifdef CONFIG_MEMCG_V1 + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return !!memcg->tcpmem_pressure; +#endif /* CONFIG_MEMCG_V1 */ + + do { + if (time_before64(get_jiffies_64(), + mem_cgroup_get_socket_pressure(memcg))) { + memcg_memory_event(mem_cgroup_from_sk(sk), + MEMCG_SOCK_THROTTLED); + return true; + } + } while ((memcg = parent_mem_cgroup(memcg))); + + return false; +} +#else +static inline struct mem_cgroup *mem_cgroup_from_sk(const struct sock *sk) +{ + return NULL; +} + +static inline bool mem_cgroup_sk_enabled(const struct sock *sk) +{ + return false; +} + +static inline bool mem_cgroup_sk_under_memory_pressure(const struct sock *sk) +{ + return false; +} +#endif + static inline long sock_rcvtimeo(const struct sock *sk, bool noblock) { - return noblock ? 0 : sk->sk_rcvtimeo; + return noblock ? 0 : READ_ONCE(sk->sk_rcvtimeo); } static inline long sock_sndtimeo(const struct sock *sk, bool noblock) { - return noblock ? 0 : sk->sk_sndtimeo; + return noblock ? 0 : READ_ONCE(sk->sk_sndtimeo); } static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len) @@ -2634,10 +2720,10 @@ struct sock_skb_cb { /* Store sock_skb_cb at the end of skb->cb[] so protocol families * using skb->cb[] would keep using it directly and utilize its - * alignement guarantee. + * alignment guarantee. */ -#define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \ - sizeof(struct sock_skb_cb))) +#define SOCK_SKB_CB_OFFSET (sizeof_field(struct sk_buff, cb) - \ + sizeof(struct sock_skb_cb)) #define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \ SOCK_SKB_CB_OFFSET)) @@ -2645,18 +2731,53 @@ struct sock_skb_cb { #define sock_skb_cb_check_size(size) \ BUILD_BUG_ON((size) > SOCK_SKB_CB_OFFSET) +static inline void sk_drops_add(struct sock *sk, int segs) +{ + struct numa_drop_counters *ndc = sk->sk_drop_counters; + + if (ndc) + numa_drop_add(ndc, segs); + else + atomic_add(segs, &sk->sk_drops); +} + +static inline void sk_drops_inc(struct sock *sk) +{ + sk_drops_add(sk, 1); +} + +static inline int sk_drops_read(const struct sock *sk) +{ + const struct numa_drop_counters *ndc = sk->sk_drop_counters; + + if (ndc) { + DEBUG_NET_WARN_ON_ONCE(atomic_read(&sk->sk_drops)); + return numa_drop_read(ndc); + } + return atomic_read(&sk->sk_drops); +} + +static inline void sk_drops_reset(struct sock *sk) +{ + struct numa_drop_counters *ndc = sk->sk_drop_counters; + + if (ndc) + numa_drop_reset(ndc); + atomic_set(&sk->sk_drops, 0); +} + static inline void sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb) { SOCK_SKB_CB(skb)->dropcount = sock_flag(sk, SOCK_RXQ_OVFL) ? - atomic_read(&sk->sk_drops) : 0; + sk_drops_read(sk) : 0; } -static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb) +static inline void sk_drops_skbadd(struct sock *sk, const struct sk_buff *skb) { int segs = max_t(u16, 1, skb_shinfo(skb)->gso_segs); - atomic_add(segs, &sk->sk_drops); + sk_drops_add(sk, segs); } static inline ktime_t sock_read_timestamp(struct sock *sk) @@ -2692,12 +2813,16 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); +bool skb_has_tx_timestamp(struct sk_buff *skb, const struct sock *sk); +int skb_get_tx_timestamp(struct sk_buff *skb, struct sock *sk, + struct timespec64 *ts); + static inline void sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { - ktime_t kt = skb->tstamp; struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb); - + u32 tsflags = READ_ONCE(sk->sk_tsflags); + ktime_t kt = skb->tstamp; /* * generate control messages if * - receive time stamping in software requested @@ -2705,10 +2830,10 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) * - hardware time stamps available and wanted */ if (sock_flag(sk, SOCK_RCVTSTAMP) || - (sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) || - (kt && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) || + (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) || + (kt && tsflags & SOF_TIMESTAMPING_SOFTWARE) || (hwtstamps->hwtstamp && - (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE))) + (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE))) __sock_recv_timestamp(msg, sk, skb); else sock_write_timestamp(sk, kt); @@ -2726,11 +2851,13 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, { #define FLAGS_RECV_CMSGS ((1UL << SOCK_RXQ_OVFL) | \ (1UL << SOCK_RCVTSTAMP) | \ - (1UL << SOCK_RCVMARK)) + (1UL << SOCK_RCVMARK) | \ + (1UL << SOCK_RCVPRIORITY) | \ + (1UL << SOCK_TIMESTAMPING_ANY)) #define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) - if (sk->sk_flags & FLAGS_RECV_CMSGS || sk->sk_tsflags & TSFLAGS_ANY) + if (READ_ONCE(sk->sk_flags) & FLAGS_RECV_CMSGS) __sock_recv_cmsgs(msg, sk, skb); else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP))) sock_write_timestamp(sk, skb->tstamp); @@ -2738,45 +2865,90 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, sock_write_timestamp(sk, 0); } -void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags); +void __sock_tx_timestamp(__u32 tsflags, __u8 *tx_flags); /** * _sock_tx_timestamp - checks whether the outgoing packet is to be time stamped * @sk: socket sending this packet - * @tsflags: timestamping flags to use + * @sockc: pointer to socket cmsg cookie to get timestamping info * @tx_flags: completed with instructions for time stamping * @tskey: filled in with next sk_tskey (not for TCP, which uses seqno) * * Note: callers should take care of initial ``*tx_flags`` value (usually 0) */ -static inline void _sock_tx_timestamp(struct sock *sk, __u16 tsflags, +static inline void _sock_tx_timestamp(struct sock *sk, + const struct sockcm_cookie *sockc, __u8 *tx_flags, __u32 *tskey) { + __u32 tsflags = sockc->tsflags; + if (unlikely(tsflags)) { __sock_tx_timestamp(tsflags, tx_flags); if (tsflags & SOF_TIMESTAMPING_OPT_ID && tskey && - tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) - *tskey = atomic_inc_return(&sk->sk_tskey) - 1; + tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) { + if (tsflags & SOCKCM_FLAG_TS_OPT_ID) + *tskey = sockc->ts_opt_id; + else + *tskey = atomic_inc_return(&sk->sk_tskey) - 1; + } } - if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS))) - *tx_flags |= SKBTX_WIFI_STATUS; } -static inline void sock_tx_timestamp(struct sock *sk, __u16 tsflags, +static inline void sock_tx_timestamp(struct sock *sk, + const struct sockcm_cookie *sockc, __u8 *tx_flags) { - _sock_tx_timestamp(sk, tsflags, tx_flags, NULL); + _sock_tx_timestamp(sk, sockc, tx_flags, NULL); } -static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) +static inline void skb_setup_tx_timestamp(struct sk_buff *skb, + const struct sockcm_cookie *sockc) { - _sock_tx_timestamp(skb->sk, tsflags, &skb_shinfo(skb)->tx_flags, + _sock_tx_timestamp(skb->sk, sockc, &skb_shinfo(skb)->tx_flags, &skb_shinfo(skb)->tskey); } +static inline bool sk_is_inet(const struct sock *sk) +{ + int family = READ_ONCE(sk->sk_family); + + return family == AF_INET || family == AF_INET6; +} + static inline bool sk_is_tcp(const struct sock *sk) { - return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP; + return sk_is_inet(sk) && + sk->sk_type == SOCK_STREAM && + sk->sk_protocol == IPPROTO_TCP; +} + +static inline bool sk_is_udp(const struct sock *sk) +{ + return sk_is_inet(sk) && + sk->sk_type == SOCK_DGRAM && + sk->sk_protocol == IPPROTO_UDP; +} + +static inline bool sk_is_unix(const struct sock *sk) +{ + return sk->sk_family == AF_UNIX; +} + +static inline bool sk_is_stream_unix(const struct sock *sk) +{ + return sk_is_unix(sk) && sk->sk_type == SOCK_STREAM; +} + +static inline bool sk_is_vsock(const struct sock *sk) +{ + return sk->sk_family == AF_VSOCK; +} + +static inline bool sk_may_scm_recv(const struct sock *sk) +{ + return (IS_ENABLED(CONFIG_UNIX) && sk->sk_family == AF_UNIX) || + sk->sk_family == AF_NETLINK || + (IS_ENABLED(CONFIG_BT) && sk->sk_family == AF_BLUETOOTH); } /** @@ -2818,53 +2990,10 @@ sk_is_refcounted(struct sock *sk) return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE); } -/** - * 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 - * @prefetched: is set to true if the socket was assigned from bpf - */ -static inline struct sock * -skb_steal_sock(struct sk_buff *skb, bool *refcounted, bool *prefetched) -{ - if (skb->sk) { - struct sock *sk = skb->sk; - - *refcounted = true; - *prefetched = skb_sk_is_prefetched(skb); - if (*prefetched) - *refcounted = sk_is_refcounted(sk); - skb->destructor = NULL; - skb->sk = NULL; - return sk; - } - *prefetched = false; - *refcounted = false; - return NULL; -} - -/* 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. - */ -static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb, - struct net_device *dev) +static inline bool +sk_requests_wifi_status(struct sock *sk) { -#ifdef CONFIG_SOCK_VALIDATE_XMIT - struct sock *sk = skb->sk; - - if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb) { - skb = sk->sk_validate_xmit_skb(sk, dev, skb); -#ifdef CONFIG_TLS_DEVICE - } else if (unlikely(skb->decrypted)) { - pr_warn_ratelimited("unencrypted skb with no associated socket - dropping\n"); - kfree_skb(skb); - skb = NULL; -#endif - } -#endif - - return skb; + return sk && sk_fullsock(sk) && sock_flag(sk, SOCK_WIFI_STATUS); } /* This helper checks if a socket is a LISTEN or NEW_SYN_RECV @@ -2875,6 +3004,16 @@ static inline bool sk_listener(const struct sock *sk) return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); } +/* This helper checks if a socket is a LISTEN or NEW_SYN_RECV or TIME_WAIT + * TCP SYNACK messages can be attached to LISTEN or NEW_SYN_RECV (depending on SYNCOOKIE) + * TCP RST and ACK can be attached to TIME_WAIT. + */ +static inline bool sk_listener_or_tw(const struct sock *sk) +{ + return (1 << READ_ONCE(sk->sk_state)) & + (TCPF_LISTEN | TCPF_NEW_SYN_RECV | TCPF_TIME_WAIT); +} + void sock_enable_timestamp(struct sock *sk, enum sock_flags flag); int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type); @@ -2893,15 +3032,12 @@ void sk_get_meminfo(const struct sock *sk, u32 *meminfo); */ #define _SK_MEM_PACKETS 256 #define _SK_MEM_OVERHEAD SKB_TRUESIZE(256) -#define SK_WMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) -#define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) +#define SK_WMEM_DEFAULT (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) +#define SK_RMEM_DEFAULT (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) extern __u32 sysctl_wmem_max; extern __u32 sysctl_rmem_max; -extern int sysctl_tstamp_allow_data; -extern int sysctl_optmem_max; - extern __u32 sysctl_wmem_default; extern __u32 sysctl_rmem_default; @@ -2964,7 +3100,13 @@ 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); +#if defined(CONFIG_CGROUP_BPF) +void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op); +#else +static inline void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op) +{ +} +#endif void sock_no_linger(struct sock *sk); void sock_set_keepalive(struct sock *sk); void sock_set_priority(struct sock *sk, u32 priority); @@ -2974,7 +3116,7 @@ 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_bind_add(struct sock *sk, struct sockaddr_unsized *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, @@ -2985,8 +3127,11 @@ int sock_ioctl_inout(struct sock *sk, unsigned int cmd, int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); static inline bool sk_is_readable(struct sock *sk) { - if (sk->sk_prot->sock_is_readable) - return sk->sk_prot->sock_is_readable(sk); + const struct proto *prot = READ_ONCE(sk->sk_prot); + + if (prot->sock_is_readable) + return prot->sock_is_readable(sk); + return false; } #endif /* _SOCK_H */ |