diff options
Diffstat (limited to 'include/net/sock.h')
| -rw-r--r-- | include/net/sock.h | 2031 |
1 files changed, 1447 insertions, 584 deletions
diff --git a/include/net/sock.h b/include/net/sock.h index 1806e5b6141..15635074570 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -40,21 +40,50 @@ #ifndef _SOCK_H #define _SOCK_H -#include <linux/config.h> +#include <linux/hardirq.h> +#include <linux/kernel.h> #include <linux/list.h> +#include <linux/list_nulls.h> #include <linux/timer.h> #include <linux/cache.h> -#include <linux/module.h> +#include <linux/bitops.h> +#include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/skbuff.h> /* struct sk_buff */ +#include <linux/mm.h> #include <linux/security.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/memcontrol.h> +#include <linux/res_counter.h> +#include <linux/static_key.h> +#include <linux/aio.h> +#include <linux/sched.h> #include <linux/filter.h> +#include <linux/rculist_nulls.h> +#include <linux/poll.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <net/dst.h> #include <net/checksum.h> +struct cgroup; +struct cgroup_subsys; +#ifdef CONFIG_NET +int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss); +void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg); +#else +static inline +int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) +{ + return 0; +} +static inline +void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg) +{ +} +#endif /* * This structure really needs to be cleaned up. * Most of it is for TCP, and not used by any of @@ -67,56 +96,126 @@ #define SOCK_DEBUG(sk, msg...) do { if ((sk) && sock_flag((sk), SOCK_DBG)) \ printk(KERN_DEBUG msg); } while (0) #else -#define SOCK_DEBUG(sk, msg...) do { } while (0) +/* 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. */ -struct sock_iocb; typedef struct { spinlock_t slock; - struct sock_iocb *owner; + int owned; wait_queue_head_t wq; + /* + * We express the mutex-alike socket_lock semantics + * to the lock validator by explicitly managing + * the slock as a lock variant (in addition to + * the slock itself): + */ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif } socket_lock_t; -#define sock_lock_init(__sk) \ -do { spin_lock_init(&((__sk)->sk_lock.slock)); \ - (__sk)->sk_lock.owner = NULL; \ - init_waitqueue_head(&((__sk)->sk_lock.wq)); \ -} while(0) - struct sock; struct proto; +struct net; + +typedef __u32 __bitwise __portpair; +typedef __u64 __bitwise __addrpair; /** * struct sock_common - minimal network layer representation of sockets + * @skc_daddr: Foreign IPv4 addr + * @skc_rcv_saddr: Bound local IPv4 addr + * @skc_hash: hash value used with various protocol lookup tables + * @skc_u16hashes: two u16 hash values used by UDP lookup tables + * @skc_dport: placeholder for inet_dport/tw_dport + * @skc_num: placeholder for inet_num/tw_num * @skc_family: network address family * @skc_state: Connection state * @skc_reuse: %SO_REUSEADDR setting + * @skc_reuseport: %SO_REUSEPORT setting * @skc_bound_dev_if: bound device index if != 0 - * @skc_node: main hash linkage for various protocol lookup tables * @skc_bind_node: bind hash linkage for various protocol lookup tables - * @skc_refcnt: reference count - * @skc_hash: hash value used with various protocol lookup tables + * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol * @skc_prot: protocol handlers inside a network family + * @skc_net: reference to the network namespace of this socket + * @skc_node: main hash linkage for various protocol lookup tables + * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol + * @skc_tx_queue_mapping: tx queue number for this connection + * @skc_refcnt: reference count * * This is the minimal network layer representation of sockets, the header * 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 { + __be32 skc_daddr; + __be32 skc_rcv_saddr; + }; + }; + union { + unsigned int skc_hash; + __u16 skc_u16hashes[2]; + }; + /* skc_dport && skc_num must be grouped as well */ + union { + __portpair skc_portpair; + struct { + __be16 skc_dport; + __u16 skc_num; + }; + }; + unsigned short skc_family; volatile unsigned char skc_state; - unsigned char skc_reuse; + unsigned char skc_reuse:4; + unsigned char skc_reuseport:4; int skc_bound_dev_if; - struct hlist_node skc_node; - struct hlist_node skc_bind_node; - atomic_t skc_refcnt; - unsigned int skc_hash; + union { + struct hlist_node skc_bind_node; + struct hlist_nulls_node skc_portaddr_node; + }; struct proto *skc_prot; +#ifdef CONFIG_NET_NS + struct net *skc_net; +#endif + +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr skc_v6_daddr; + struct in6_addr skc_v6_rcv_saddr; +#endif + + /* + * fields between dontcopy_begin/dontcopy_end + * are not copied in sock_copy() + */ + /* private: */ + int skc_dontcopy_begin[0]; + /* public: */ + union { + struct hlist_node skc_node; + struct hlist_nulls_node skc_nulls_node; + }; + int skc_tx_queue_mapping; + atomic_t skc_refcnt; + /* private: */ + int skc_dontcopy_end[0]; + /* public: */ }; +struct cg_proto; /** * struct sock - network layer representation of sockets * @__sk_common: shared layout with inet_timewait_sock @@ -124,48 +223,68 @@ struct sock_common { * @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings * @sk_lock: synchronizer * @sk_rcvbuf: size of receive buffer in bytes - * @sk_sleep: sock wait queue + * @sk_wq: sock wait queue and async head + * @sk_rx_dst: receive input route used by early demux * @sk_dst_cache: destination cache * @sk_dst_lock: destination cache lock * @sk_policy: flow policy - * @sk_rmem_alloc: receive queue bytes committed * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed * @sk_write_queue: Packet sending queue + * @sk_async_wait_queue: DMA copied packets * @sk_omem_alloc: "o" is "option" or "other" * @sk_wmem_queued: persistent queue size * @sk_forward_alloc: space allocated forward + * @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 + * @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler) + * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE) * @sk_sndbuf: size of send buffer in bytes - * @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, %SO_OOBINLINE settings - * @sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets + * @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, + * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings + * @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_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) + * @sk_gso_max_size: Maximum GSO segment size to build + * @sk_gso_max_segs: Maximum number of GSO segments * @sk_lingertime: %SO_LINGER l_linger setting * @sk_backlog: always used with the per-socket spinlock held * @sk_callback_lock: used with the callbacks in the end of this struct * @sk_error_queue: rarely used - * @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt, IPV6_ADDRFORM for instance) + * @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt, + * IPV6_ADDRFORM for instance) * @sk_err: last error - * @sk_err_soft: errors that don't cause failure but are the cause of a persistent failure not just 'timed out' + * @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_ack_backlog: current listen backlog * @sk_max_ack_backlog: listen backlog set in listen() * @sk_priority: %SO_PRIORITY setting + * @sk_cgrp_prioidx: socket group's priority map index * @sk_type: socket type (%SOCK_STREAM, etc) * @sk_protocol: which protocol this socket belongs in this network family - * @sk_peercred: %SO_PEERCRED setting + * @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_rxhash: flow hash received from netif layer * @sk_filter: socket filtering instructions * @sk_protinfo: private area, net family specific, when not using slab * @sk_timer: sock cleanup timer * @sk_stamp: time stamp of last packet received * @sk_socket: Identd and reporting IO signals * @sk_user_data: RPC layer private data - * @sk_sndmsg_page: cached page for sendmsg - * @sk_sndmsg_off: cached offset for sendmsg + * @sk_frag: cached page frag + * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit * @sk_security: used by security modules + * @sk_mark: generic packet mark + * @sk_classid: this socket's cgroup classid + * @sk_cgrp: this socket's cgroup-specific proto data * @sk_write_pending: a write to stream socket waits to start * @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 @@ -180,47 +299,96 @@ struct sock { * don't add nothing before this first member (__sk_common) --acme */ struct sock_common __sk_common; +#define sk_node __sk_common.skc_node +#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 + +#define sk_dontcopy_begin __sk_common.skc_dontcopy_begin +#define sk_dontcopy_end __sk_common.skc_dontcopy_end +#define sk_hash __sk_common.skc_hash +#define sk_portpair __sk_common.skc_portpair +#define sk_num __sk_common.skc_num +#define sk_dport __sk_common.skc_dport +#define sk_addrpair __sk_common.skc_addrpair +#define sk_daddr __sk_common.skc_daddr +#define sk_rcv_saddr __sk_common.skc_rcv_saddr #define sk_family __sk_common.skc_family #define sk_state __sk_common.skc_state #define sk_reuse __sk_common.skc_reuse +#define sk_reuseport __sk_common.skc_reuseport #define sk_bound_dev_if __sk_common.skc_bound_dev_if -#define sk_node __sk_common.skc_node #define sk_bind_node __sk_common.skc_bind_node -#define sk_refcnt __sk_common.skc_refcnt -#define sk_hash __sk_common.skc_hash #define sk_prot __sk_common.skc_prot - unsigned char sk_shutdown : 2, - sk_no_check : 2, - sk_userlocks : 4; - unsigned char sk_protocol; - unsigned short sk_type; - int sk_rcvbuf; +#define sk_net __sk_common.skc_net +#define sk_v6_daddr __sk_common.skc_v6_daddr +#define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr + socket_lock_t sk_lock; - wait_queue_head_t *sk_sleep; - struct dst_entry *sk_dst_cache; - struct xfrm_policy *sk_policy[2]; - rwlock_t sk_dst_lock; - atomic_t sk_rmem_alloc; - atomic_t sk_wmem_alloc; - atomic_t sk_omem_alloc; struct sk_buff_head sk_receive_queue; - struct sk_buff_head sk_write_queue; - int sk_wmem_queued; - int sk_forward_alloc; - gfp_t sk_allocation; - int sk_sndbuf; - int sk_route_caps; - unsigned long sk_flags; - unsigned long sk_lingertime; /* * The backlog queue is special, it is always used with * the per-socket spinlock held and requires low latency * access. Therefore we special case it's implementation. + * Note : rmem_alloc is in this structure to fill a hole + * on 64bit arches, not because its logically part of + * backlog. */ struct { - struct sk_buff *head; - struct sk_buff *tail; + atomic_t rmem_alloc; + int len; + struct sk_buff *head; + struct sk_buff *tail; } sk_backlog; +#define sk_rmem_alloc sk_backlog.rmem_alloc + int sk_forward_alloc; +#ifdef CONFIG_RPS + __u32 sk_rxhash; +#endif +#ifdef CONFIG_NET_RX_BUSY_POLL + unsigned int sk_napi_id; + unsigned int sk_ll_usec; +#endif + atomic_t sk_drops; + int sk_rcvbuf; + + struct sk_filter __rcu *sk_filter; + struct socket_wq __rcu *sk_wq; + +#ifdef CONFIG_NET_DMA + struct sk_buff_head sk_async_wait_queue; +#endif + +#ifdef CONFIG_XFRM + struct xfrm_policy *sk_policy[2]; +#endif + unsigned long sk_flags; + struct dst_entry *sk_rx_dst; + struct dst_entry __rcu *sk_dst_cache; + spinlock_t sk_dst_lock; + atomic_t sk_wmem_alloc; + atomic_t sk_omem_alloc; + int sk_sndbuf; + struct sk_buff_head sk_write_queue; + kmemcheck_bitfield_begin(flags); + unsigned int sk_shutdown : 2, + sk_no_check_tx : 1, + sk_no_check_rx : 1, + sk_userlocks : 4, + sk_protocol : 8, + sk_type : 16; + kmemcheck_bitfield_end(flags); + int sk_wmem_queued; + gfp_t sk_allocation; + u32 sk_pacing_rate; /* bytes per second */ + u32 sk_max_pacing_rate; + netdev_features_t sk_route_caps; + netdev_features_t sk_route_nocaps; + int sk_gso_type; + unsigned int sk_gso_max_size; + u16 sk_gso_max_segs; + int sk_rcvlowat; + unsigned long sk_lingertime; struct sk_buff_head sk_error_queue; struct proto *sk_prot_creator; rwlock_t sk_callback_lock; @@ -229,33 +397,85 @@ struct sock { unsigned short sk_ack_backlog; unsigned short sk_max_ack_backlog; __u32 sk_priority; - struct ucred sk_peercred; - int sk_rcvlowat; +#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) + __u32 sk_cgrp_prioidx; +#endif + struct pid *sk_peer_pid; + const struct cred *sk_peer_cred; long sk_rcvtimeo; long sk_sndtimeo; - struct sk_filter *sk_filter; void *sk_protinfo; struct timer_list sk_timer; - struct timeval sk_stamp; + ktime_t sk_stamp; struct socket *sk_socket; void *sk_user_data; - struct page *sk_sndmsg_page; + struct page_frag sk_frag; struct sk_buff *sk_send_head; - __u32 sk_sndmsg_off; + __s32 sk_peek_off; int sk_write_pending; +#ifdef CONFIG_SECURITY void *sk_security; +#endif + __u32 sk_mark; + u32 sk_classid; + struct cg_proto *sk_cgrp; void (*sk_state_change)(struct sock *sk); - void (*sk_data_ready)(struct sock *sk, int bytes); + 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); + int (*sk_backlog_rcv)(struct sock *sk, + struct sk_buff *skb); void (*sk_destruct)(struct sock *sk); }; +#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) + +/* + * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK + * or not whether his port will be reused by someone else. SK_FORCE_REUSE + * on a socket means that the socket will reuse everybody else's port + * without looking at the other's sk_reuse value. + */ + +#define SK_NO_REUSE 0 +#define SK_CAN_REUSE 1 +#define SK_FORCE_REUSE 2 + +static inline int sk_peek_offset(struct sock *sk, int flags) +{ + if ((flags & MSG_PEEK) && (sk->sk_peek_off >= 0)) + return sk->sk_peek_off; + else + return 0; +} + +static inline void sk_peek_offset_bwd(struct sock *sk, int val) +{ + if (sk->sk_peek_off >= 0) { + if (sk->sk_peek_off >= val) + sk->sk_peek_off -= val; + else + sk->sk_peek_off = 0; + } +} + +static inline void sk_peek_offset_fwd(struct sock *sk, int val) +{ + if (sk->sk_peek_off >= 0) + sk->sk_peek_off += val; +} + /* * Hashed lists helper routines */ +static inline struct sock *sk_entry(const struct hlist_node *node) +{ + return hlist_entry(node, struct sock, sk_node); +} + static inline struct sock *__sk_head(const struct hlist_head *head) { return hlist_entry(head->first, struct sock, sk_node); @@ -266,40 +486,64 @@ static inline struct sock *sk_head(const struct hlist_head *head) return hlist_empty(head) ? NULL : __sk_head(head); } +static inline struct sock *__sk_nulls_head(const struct hlist_nulls_head *head) +{ + return hlist_nulls_entry(head->first, struct sock, sk_nulls_node); +} + +static inline struct sock *sk_nulls_head(const struct hlist_nulls_head *head) +{ + return hlist_nulls_empty(head) ? NULL : __sk_nulls_head(head); +} + static inline struct sock *sk_next(const struct sock *sk) { return sk->sk_node.next ? hlist_entry(sk->sk_node.next, struct sock, sk_node) : NULL; } -static inline int sk_unhashed(const struct sock *sk) +static inline struct sock *sk_nulls_next(const struct sock *sk) +{ + return (!is_a_nulls(sk->sk_nulls_node.next)) ? + hlist_nulls_entry(sk->sk_nulls_node.next, + struct sock, sk_nulls_node) : + NULL; +} + +static inline bool sk_unhashed(const struct sock *sk) { return hlist_unhashed(&sk->sk_node); } -static inline int sk_hashed(const struct sock *sk) +static inline bool sk_hashed(const struct sock *sk) { - return sk->sk_node.pprev != NULL; + return !sk_unhashed(sk); } -static __inline__ void sk_node_init(struct hlist_node *node) +static inline void sk_node_init(struct hlist_node *node) { node->pprev = NULL; } -static __inline__ void __sk_del_node(struct sock *sk) +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); } -static __inline__ int __sk_del_node_init(struct sock *sk) +/* NB: equivalent to hlist_del_init_rcu */ +static inline bool __sk_del_node_init(struct sock *sk) { if (sk_hashed(sk)) { __sk_del_node(sk); sk_node_init(&sk->sk_node); - return 1; + return true; } - return 0; + return false; } /* Grab socket reference count. This operation is valid only @@ -321,9 +565,31 @@ static inline void __sock_put(struct sock *sk) atomic_dec(&sk->sk_refcnt); } -static __inline__ int sk_del_node_init(struct sock *sk) +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(atomic_read(&sk->sk_refcnt) == 1); + __sock_put(sk); + } + return rc; +} +#define sk_del_node_init_rcu(sk) sk_del_node_init(sk) + +static inline bool __sk_nulls_del_node_init_rcu(struct sock *sk) +{ + if (sk_hashed(sk)) { + hlist_nulls_del_init_rcu(&sk->sk_nulls_node); + return true; + } + return false; +} + +static inline bool sk_nulls_del_node_init_rcu(struct sock *sk) { - int rc = __sk_del_node_init(sk); + bool rc = __sk_nulls_del_node_init_rcu(sk); if (rc) { /* paranoid for a while -acme */ @@ -333,40 +599,71 @@ static __inline__ int sk_del_node_init(struct sock *sk) return rc; } -static __inline__ void __sk_add_node(struct sock *sk, struct hlist_head *list) +static inline void __sk_add_node(struct sock *sk, struct hlist_head *list) { hlist_add_head(&sk->sk_node, list); } -static __inline__ void sk_add_node(struct sock *sk, struct hlist_head *list) +static inline void sk_add_node(struct sock *sk, struct hlist_head *list) { sock_hold(sk); __sk_add_node(sk, list); } -static __inline__ void __sk_del_bind_node(struct sock *sk) +static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list) +{ + sock_hold(sk); + hlist_add_head_rcu(&sk->sk_node, list); +} + +static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) +{ + hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); +} + +static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) +{ + sock_hold(sk); + __sk_nulls_add_node_rcu(sk, list); +} + +static inline void __sk_del_bind_node(struct sock *sk) { __hlist_del(&sk->sk_bind_node); } -static __inline__ void sk_add_bind_node(struct sock *sk, +static inline void sk_add_bind_node(struct sock *sk, struct hlist_head *list) { hlist_add_head(&sk->sk_bind_node, list); } -#define sk_for_each(__sk, node, list) \ - hlist_for_each_entry(__sk, node, list, sk_node) -#define sk_for_each_from(__sk, node) \ - if (__sk && ({ node = &(__sk)->sk_node; 1; })) \ - hlist_for_each_entry_from(__sk, node, sk_node) -#define sk_for_each_continue(__sk, node) \ - if (__sk && ({ node = &(__sk)->sk_node; 1; })) \ - hlist_for_each_entry_continue(__sk, node, sk_node) -#define sk_for_each_safe(__sk, node, tmp, list) \ - hlist_for_each_entry_safe(__sk, node, tmp, list, sk_node) -#define sk_for_each_bound(__sk, node, list) \ - hlist_for_each_entry(__sk, node, list, sk_bind_node) +#define sk_for_each(__sk, list) \ + hlist_for_each_entry(__sk, list, sk_node) +#define sk_for_each_rcu(__sk, list) \ + hlist_for_each_entry_rcu(__sk, list, sk_node) +#define sk_nulls_for_each(__sk, node, list) \ + hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node) +#define sk_nulls_for_each_rcu(__sk, node, list) \ + hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node) +#define sk_for_each_from(__sk) \ + hlist_for_each_entry_from(__sk, sk_node) +#define sk_nulls_for_each_from(__sk, node) \ + if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \ + hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node) +#define sk_for_each_safe(__sk, tmp, 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) + +static inline struct user_namespace *sk_user_ns(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 + * userspace. + */ + return sk->sk_socket->file->f_cred->user_ns; +} /* Sock flags */ enum sock_flags { @@ -382,9 +679,27 @@ enum sock_flags { SOCK_USE_WRITE_QUEUE, /* whether to call sk->sk_write_space in sock_wfree */ SOCK_DBG, /* %SO_DEBUG setting */ SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */ - SOCK_NO_LARGESEND, /* whether to sent large segments or not */ + 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_TX_HARDWARE, /* %SOF_TIMESTAMPING_TX_HARDWARE */ + SOCK_TIMESTAMPING_TX_SOFTWARE, /* %SOF_TIMESTAMPING_TX_SOFTWARE */ + SOCK_TIMESTAMPING_RX_HARDWARE, /* %SOF_TIMESTAMPING_RX_HARDWARE */ + SOCK_TIMESTAMPING_RX_SOFTWARE, /* %SOF_TIMESTAMPING_RX_SOFTWARE */ + SOCK_TIMESTAMPING_SOFTWARE, /* %SOF_TIMESTAMPING_SOFTWARE */ + SOCK_TIMESTAMPING_RAW_HARDWARE, /* %SOF_TIMESTAMPING_RAW_HARDWARE */ + SOCK_TIMESTAMPING_SYS_HARDWARE, /* %SOF_TIMESTAMPING_SYS_HARDWARE */ + SOCK_FASYNC, /* fasync() active */ + SOCK_RXQ_OVFL, + SOCK_ZEROCOPY, /* buffers from userspace */ + SOCK_WIFI_STATUS, /* push wifi status to userspace */ + SOCK_NOFCS, /* Tell NIC not to do the Ethernet FCS. + * Will use last 4 bytes of packet sent from + * user-space instead. + */ + SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */ + SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */ }; static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) @@ -402,11 +717,31 @@ static inline void sock_reset_flag(struct sock *sk, enum sock_flags flag) __clear_bit(flag, &sk->sk_flags); } -static inline int sock_flag(struct sock *sk, enum sock_flags flag) +static inline bool sock_flag(const struct sock *sk, enum sock_flags flag) { return test_bit(flag, &sk->sk_flags); } +#ifdef CONFIG_NET +extern struct static_key memalloc_socks; +static inline int sk_memalloc_socks(void) +{ + return static_key_false(&memalloc_socks); +} +#else + +static inline int sk_memalloc_socks(void) +{ + return 0; +} + +#endif + +static inline gfp_t sk_gfp_atomic(struct sock *sk, gfp_t gfp_mask) +{ + return GFP_ATOMIC | (sk->sk_allocation & __GFP_MEMALLOC); +} + static inline void sk_acceptq_removed(struct sock *sk) { sk->sk_ack_backlog--; @@ -417,7 +752,7 @@ static inline void sk_acceptq_added(struct sock *sk) sk->sk_ack_backlog++; } -static inline int sk_acceptq_is_full(struct sock *sk) +static inline bool sk_acceptq_is_full(const struct sock *sk) { return sk->sk_ack_backlog > sk->sk_max_ack_backlog; } @@ -425,144 +760,264 @@ static inline int sk_acceptq_is_full(struct sock *sk) /* * Compute minimal free write space needed to queue new packets. */ -static inline int sk_stream_min_wspace(struct sock *sk) +static inline int sk_stream_min_wspace(const struct sock *sk) { - return sk->sk_wmem_queued / 2; + return sk->sk_wmem_queued >> 1; } -static inline int sk_stream_wspace(struct sock *sk) +static inline int sk_stream_wspace(const struct sock *sk) { return sk->sk_sndbuf - sk->sk_wmem_queued; } -extern void sk_stream_write_space(struct sock *sk); +void sk_stream_write_space(struct sock *sk); -static inline int sk_stream_memory_free(struct sock *sk) +/* OOB backlog add */ +static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) { - return sk->sk_wmem_queued < sk->sk_sndbuf; + /* dont let skb dst not refcounted, we are going to leave rcu lock */ + skb_dst_force(skb); + + if (!sk->sk_backlog.tail) + sk->sk_backlog.head = skb; + else + sk->sk_backlog.tail->next = skb; + + sk->sk_backlog.tail = skb; + skb->next = NULL; } -extern void sk_stream_rfree(struct sk_buff *skb); +/* + * Take into account size of receive queue and backlog queue + * Do not take into account this skb truesize, + * to allow even a single big packet to come. + */ +static inline bool sk_rcvqueues_full(const struct sock *sk, const struct sk_buff *skb, + unsigned int limit) +{ + unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc); -static inline void sk_stream_set_owner_r(struct sk_buff *skb, struct sock *sk) + return qsize > limit; +} + +/* The per-socket spinlock must be held here. */ +static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *skb, + unsigned int limit) { - skb->sk = sk; - skb->destructor = sk_stream_rfree; - atomic_add(skb->truesize, &sk->sk_rmem_alloc); - sk->sk_forward_alloc -= skb->truesize; + if (sk_rcvqueues_full(sk, skb, limit)) + return -ENOBUFS; + + __sk_add_backlog(sk, skb); + sk->sk_backlog.len += skb->truesize; + return 0; } -static inline void sk_stream_free_skb(struct sock *sk, struct sk_buff *skb) +int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb); + +static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { - sock_set_flag(sk, SOCK_QUEUE_SHRUNK); - sk->sk_wmem_queued -= skb->truesize; - sk->sk_forward_alloc += skb->truesize; - __kfree_skb(skb); + if (sk_memalloc_socks() && skb_pfmemalloc(skb)) + return __sk_backlog_rcv(sk, skb); + + return sk->sk_backlog_rcv(sk, skb); } -/* The per-socket spinlock must be held here. */ -static inline void sk_add_backlog(struct sock *sk, struct sk_buff *skb) +static inline void sock_rps_record_flow_hash(__u32 hash) { - if (!sk->sk_backlog.tail) { - sk->sk_backlog.head = sk->sk_backlog.tail = skb; - } else { - sk->sk_backlog.tail->next = skb; - sk->sk_backlog.tail = skb; - } - skb->next = NULL; +#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 } -#define sk_wait_event(__sk, __timeo, __condition) \ -({ int rc; \ - release_sock(__sk); \ - rc = __condition; \ - if (!rc) { \ - *(__timeo) = schedule_timeout(*(__timeo)); \ - rc = __condition; \ - } \ - lock_sock(__sk); \ - rc; \ -}) +static inline void sock_rps_reset_flow_hash(__u32 hash) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *sock_flow_table; -extern int sk_stream_wait_connect(struct sock *sk, long *timeo_p); -extern int sk_stream_wait_memory(struct sock *sk, long *timeo_p); -extern void sk_stream_wait_close(struct sock *sk, long timeo_p); -extern int sk_stream_error(struct sock *sk, int flags, int err); -extern void sk_stream_kill_queues(struct sock *sk); + rcu_read_lock(); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + rps_reset_sock_flow(sock_flow_table, hash); + rcu_read_unlock(); +#endif +} -extern int sk_wait_data(struct sock *sk, long *timeo); +static inline void sock_rps_record_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + sock_rps_record_flow_hash(sk->sk_rxhash); +#endif +} + +static inline void sock_rps_reset_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + sock_rps_reset_flow_hash(sk->sk_rxhash); +#endif +} + +static inline void sock_rps_save_rxhash(struct sock *sk, + const struct sk_buff *skb) +{ +#ifdef CONFIG_RPS + if (unlikely(sk->sk_rxhash != skb->hash)) { + sock_rps_reset_flow(sk); + sk->sk_rxhash = skb->hash; + } +#endif +} + +static inline void sock_rps_reset_rxhash(struct sock *sk) +{ +#ifdef CONFIG_RPS + sock_rps_reset_flow(sk); + sk->sk_rxhash = 0; +#endif +} + +#define sk_wait_event(__sk, __timeo, __condition) \ + ({ int __rc; \ + release_sock(__sk); \ + __rc = __condition; \ + if (!__rc) { \ + *(__timeo) = schedule_timeout(*(__timeo)); \ + } \ + lock_sock(__sk); \ + __rc = __condition; \ + __rc; \ + }) + +int sk_stream_wait_connect(struct sock *sk, long *timeo_p); +int sk_stream_wait_memory(struct sock *sk, long *timeo_p); +void sk_stream_wait_close(struct sock *sk, long timeo_p); +int sk_stream_error(struct sock *sk, int flags, int err); +void sk_stream_kill_queues(struct sock *sk); +void sk_set_memalloc(struct sock *sk); +void sk_clear_memalloc(struct sock *sk); + +int sk_wait_data(struct sock *sk, long *timeo); struct request_sock_ops; struct timewait_sock_ops; +struct inet_hashinfo; +struct raw_hashinfo; +struct module; + +/* + * caches using SLAB_DESTROY_BY_RCU should let .next pointer from nulls nodes + * un-modified. Special care is taken when initializing object to zero. + */ +static inline void sk_prot_clear_nulls(struct sock *sk, int size) +{ + if (offsetof(struct sock, sk_node.next) != 0) + memset(sk, 0, offsetof(struct sock, sk_node.next)); + memset(&sk->sk_node.pprev, 0, + size - offsetof(struct sock, sk_node.pprev)); +} /* Networking protocol blocks we attach to sockets. * socket layer -> transport layer interface * transport -> network interface is defined by struct inet_proto */ struct proto { - void (*close)(struct sock *sk, + void (*close)(struct sock *sk, long timeout); int (*connect)(struct sock *sk, - struct sockaddr *uaddr, + struct sockaddr *uaddr, int addr_len); int (*disconnect)(struct sock *sk, int flags); - struct sock * (*accept) (struct sock *sk, int flags, int *err); + struct sock * (*accept)(struct sock *sk, int flags, int *err); int (*ioctl)(struct sock *sk, int cmd, unsigned long arg); int (*init)(struct sock *sk); - int (*destroy)(struct sock *sk); + void (*destroy)(struct sock *sk); void (*shutdown)(struct sock *sk, int how); - int (*setsockopt)(struct sock *sk, int level, + int (*setsockopt)(struct sock *sk, int level, + int optname, char __user *optval, + unsigned int optlen); + int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, - int optlen); - int (*getsockopt)(struct sock *sk, int level, - int optname, char __user *optval, - int __user *option); + int __user *option); +#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 kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len); int (*recvmsg)(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int noblock, int flags, - int *addr_len); + size_t len, int noblock, 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, + int (*bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len); - int (*backlog_rcv) (struct sock *sk, + int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); + void (*release_cb)(struct sock *sk); + void (*mtu_reduced)(struct sock *sk); + /* Keeping track of sk's, looking them up, and port selection methods. */ void (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); + void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); + void (*clear_sk)(struct sock *sk, int size); + /* Keeping track of sockets in use */ +#ifdef CONFIG_PROC_FS + unsigned int inuse_idx; +#endif + + bool (*stream_memory_free)(const struct sock *sk); /* Memory pressure */ - void (*enter_memory_pressure)(void); - atomic_t *memory_allocated; /* Current allocated memory. */ - atomic_t *sockets_allocated; /* Current number of sockets. */ + void (*enter_memory_pressure)(struct sock *sk); + atomic_long_t *memory_allocated; /* Current allocated memory. */ + struct percpu_counter *sockets_allocated; /* Current number of sockets. */ /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. - * All the sk_stream_mem_schedule() is of this nature: accounting + * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ int *memory_pressure; - int *sysctl_mem; + long *sysctl_mem; int *sysctl_wmem; int *sysctl_rmem; int max_header; + bool no_autobind; - kmem_cache_t *slab; + struct kmem_cache *slab; unsigned int obj_size; + int slab_flags; - atomic_t *orphan_count; + struct percpu_counter *orphan_count; struct request_sock_ops *rsk_prot; struct timewait_sock_ops *twsk_prot; + union { + struct inet_hashinfo *hashinfo; + struct udp_table *udp_table; + struct raw_hashinfo *raw_hash; + } h; + struct module *owner; char name[32]; @@ -571,14 +1026,60 @@ struct proto { #ifdef SOCK_REFCNT_DEBUG atomic_t socks; #endif - struct { - int inuse; - u8 __pad[SMP_CACHE_BYTES - sizeof(int)]; - } stats[NR_CPUS]; +#ifdef CONFIG_MEMCG_KMEM + /* + * cgroup specific init/deinit functions. Called once for all + * protocols that implement it, from cgroups populate function. + * This function has to setup any files the protocol want to + * appear in the kmem cgroup filesystem. + */ + int (*init_cgroup)(struct mem_cgroup *memcg, + struct cgroup_subsys *ss); + void (*destroy_cgroup)(struct mem_cgroup *memcg); + struct cg_proto *(*proto_cgroup)(struct mem_cgroup *memcg); +#endif }; -extern int proto_register(struct proto *prot, int alloc_slab); -extern void proto_unregister(struct proto *prot); +/* + * Bits in struct cg_proto.flags + */ +enum cg_proto_flags { + /* Currently active and new sockets should be assigned to cgroups */ + MEMCG_SOCK_ACTIVE, + /* It was ever activated; we must disarm static keys on destruction */ + MEMCG_SOCK_ACTIVATED, +}; + +struct cg_proto { + struct res_counter memory_allocated; /* Current allocated memory. */ + struct percpu_counter sockets_allocated; /* Current number of sockets. */ + int memory_pressure; + long sysctl_mem[3]; + unsigned long flags; + /* + * memcg field is used to find which memcg we belong directly + * Each memcg struct can hold more than one cg_proto, so container_of + * won't really cut. + * + * The elegant solution would be having an inverse function to + * proto_cgroup in struct proto, but that means polluting the structure + * for everybody, instead of just for memcg users. + */ + struct mem_cgroup *memcg; +}; + +int proto_register(struct proto *prot, int alloc_slab); +void proto_unregister(struct proto *prot); + +static inline bool memcg_proto_active(struct cg_proto *cg_proto) +{ + return test_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); +} + +static inline bool memcg_proto_activated(struct cg_proto *cg_proto) +{ + return test_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags); +} #ifdef SOCK_REFCNT_DEBUG static inline void sk_refcnt_debug_inc(struct sock *sk) @@ -605,17 +1106,233 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) #define sk_refcnt_debug_release(sk) do { } while (0) #endif /* SOCK_REFCNT_DEBUG */ -/* Called with local bh disabled */ -static __inline__ void sock_prot_inc_use(struct proto *prot) +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_NET) +extern struct static_key memcg_socket_limit_enabled; +static inline struct cg_proto *parent_cg_proto(struct proto *proto, + struct cg_proto *cg_proto) +{ + return proto->proto_cgroup(parent_mem_cgroup(cg_proto->memcg)); +} +#define mem_cgroup_sockets_enabled static_key_false(&memcg_socket_limit_enabled) +#else +#define mem_cgroup_sockets_enabled 0 +static inline struct cg_proto *parent_cg_proto(struct proto *proto, + struct cg_proto *cg_proto) +{ + return NULL; +} +#endif + +static inline bool sk_stream_memory_free(const struct sock *sk) +{ + if (sk->sk_wmem_queued >= sk->sk_sndbuf) + return false; + + return sk->sk_prot->stream_memory_free ? + sk->sk_prot->stream_memory_free(sk) : true; +} + +static inline bool sk_stream_is_writeable(const struct sock *sk) +{ + return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && + sk_stream_memory_free(sk); +} + + +static inline bool sk_has_memory_pressure(const struct sock *sk) +{ + return sk->sk_prot->memory_pressure != NULL; +} + +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_cgrp) + return !!sk->sk_cgrp->memory_pressure; + + return !!*sk->sk_prot->memory_pressure; +} + +static inline void sk_leave_memory_pressure(struct sock *sk) +{ + int *memory_pressure = sk->sk_prot->memory_pressure; + + if (!memory_pressure) + return; + + if (*memory_pressure) + *memory_pressure = 0; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { + struct cg_proto *cg_proto = sk->sk_cgrp; + struct proto *prot = sk->sk_prot; + + for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) + cg_proto->memory_pressure = 0; + } + +} + +static inline void sk_enter_memory_pressure(struct sock *sk) +{ + if (!sk->sk_prot->enter_memory_pressure) + return; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { + struct cg_proto *cg_proto = sk->sk_cgrp; + struct proto *prot = sk->sk_prot; + + for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) + cg_proto->memory_pressure = 1; + } + + sk->sk_prot->enter_memory_pressure(sk); +} + +static inline long sk_prot_mem_limits(const struct sock *sk, int index) +{ + long *prot = sk->sk_prot->sysctl_mem; + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + prot = sk->sk_cgrp->sysctl_mem; + return prot[index]; +} + +static inline void memcg_memory_allocated_add(struct cg_proto *prot, + unsigned long amt, + int *parent_status) +{ + struct res_counter *fail; + int ret; + + ret = res_counter_charge_nofail(&prot->memory_allocated, + amt << PAGE_SHIFT, &fail); + if (ret < 0) + *parent_status = OVER_LIMIT; +} + +static inline void memcg_memory_allocated_sub(struct cg_proto *prot, + unsigned long amt) +{ + res_counter_uncharge(&prot->memory_allocated, amt << PAGE_SHIFT); +} + +static inline u64 memcg_memory_allocated_read(struct cg_proto *prot) +{ + u64 ret; + ret = res_counter_read_u64(&prot->memory_allocated, RES_USAGE); + return ret >> PAGE_SHIFT; +} + +static inline long +sk_memory_allocated(const struct sock *sk) +{ + struct proto *prot = sk->sk_prot; + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + return memcg_memory_allocated_read(sk->sk_cgrp); + + return atomic_long_read(prot->memory_allocated); +} + +static inline long +sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status) +{ + struct proto *prot = sk->sk_prot; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { + memcg_memory_allocated_add(sk->sk_cgrp, amt, parent_status); + /* update the root cgroup regardless */ + atomic_long_add_return(amt, prot->memory_allocated); + return memcg_memory_allocated_read(sk->sk_cgrp); + } + + return atomic_long_add_return(amt, prot->memory_allocated); +} + +static inline void +sk_memory_allocated_sub(struct sock *sk, int amt) { - prot->stats[smp_processor_id()].inuse++; + struct proto *prot = sk->sk_prot; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + memcg_memory_allocated_sub(sk->sk_cgrp, amt); + + atomic_long_sub(amt, prot->memory_allocated); } -static __inline__ void sock_prot_dec_use(struct proto *prot) +static inline void sk_sockets_allocated_dec(struct sock *sk) { - prot->stats[smp_processor_id()].inuse--; + struct proto *prot = sk->sk_prot; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { + struct cg_proto *cg_proto = sk->sk_cgrp; + + for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) + percpu_counter_dec(&cg_proto->sockets_allocated); + } + + percpu_counter_dec(prot->sockets_allocated); } +static inline void sk_sockets_allocated_inc(struct sock *sk) +{ + struct proto *prot = sk->sk_prot; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { + struct cg_proto *cg_proto = sk->sk_cgrp; + + for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) + percpu_counter_inc(&cg_proto->sockets_allocated); + } + + percpu_counter_inc(prot->sockets_allocated); +} + +static inline int +sk_sockets_allocated_read_positive(struct sock *sk) +{ + struct proto *prot = sk->sk_prot; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + return percpu_counter_read_positive(&sk->sk_cgrp->sockets_allocated); + + return percpu_counter_read_positive(prot->sockets_allocated); +} + +static inline int +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) +{ + if (!prot->memory_pressure) + return false; + return !!*prot->memory_pressure; +} + + +#ifdef CONFIG_PROC_FS +/* Called with local bh disabled */ +void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc); +int sock_prot_inuse_get(struct net *net, struct proto *proto); +#else +static inline void sock_prot_inuse_add(struct net *net, struct proto *prot, + int inc) +{ +} +#endif + + /* With per-bucket locks this operation is not-atomic, so that * this version is not worse. */ @@ -625,6 +1342,8 @@ static inline void __sk_prot_rehash(struct sock *sk) sk->sk_prot->hash(sk); } +void sk_prot_clear_portaddr_nulls(struct sock *sk, int size); + /* About 10 seconds */ #define SOCK_DESTROY_TIME (10*HZ) @@ -650,7 +1369,6 @@ struct sock_iocb { struct sock *sk; struct scm_cookie *scm; struct msghdr *msg, async_msg; - struct iovec async_iov; struct kiocb *kiocb; }; @@ -679,41 +1397,82 @@ static inline struct inode *SOCK_INODE(struct socket *socket) return &container_of(socket, struct socket_alloc, socket)->vfs_inode; } -extern void __sk_stream_mem_reclaim(struct sock *sk); -extern int sk_stream_mem_schedule(struct sock *sk, int size, int kind); +/* + * Functions for memory accounting + */ +int __sk_mem_schedule(struct sock *sk, int size, int kind); +void __sk_mem_reclaim(struct sock *sk); -#define SK_STREAM_MEM_QUANTUM ((int)PAGE_SIZE) +#define SK_MEM_QUANTUM ((int)PAGE_SIZE) +#define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM) +#define SK_MEM_SEND 0 +#define SK_MEM_RECV 1 -static inline int sk_stream_pages(int amt) +static inline int sk_mem_pages(int amt) { - return (amt + SK_STREAM_MEM_QUANTUM - 1) / SK_STREAM_MEM_QUANTUM; + return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT; } -static inline void sk_stream_mem_reclaim(struct sock *sk) +static inline bool sk_has_account(struct sock *sk) { - if (sk->sk_forward_alloc >= SK_STREAM_MEM_QUANTUM) - __sk_stream_mem_reclaim(sk); + /* return true if protocol supports memory accounting */ + return !!sk->sk_prot->memory_allocated; } -static inline void sk_stream_writequeue_purge(struct sock *sk) +static inline bool sk_wmem_schedule(struct sock *sk, int size) { - struct sk_buff *skb; + if (!sk_has_account(sk)) + return true; + return size <= sk->sk_forward_alloc || + __sk_mem_schedule(sk, size, SK_MEM_SEND); +} - while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) - sk_stream_free_skb(sk, skb); - sk_stream_mem_reclaim(sk); +static inline bool +sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) +{ + if (!sk_has_account(sk)) + return true; + return size<= sk->sk_forward_alloc || + __sk_mem_schedule(sk, size, SK_MEM_RECV) || + skb_pfmemalloc(skb); } -static inline int sk_stream_rmem_schedule(struct sock *sk, struct sk_buff *skb) +static inline void sk_mem_reclaim(struct sock *sk) { - return (int)skb->truesize <= sk->sk_forward_alloc || - sk_stream_mem_schedule(sk, skb->truesize, 1); + if (!sk_has_account(sk)) + return; + if (sk->sk_forward_alloc >= SK_MEM_QUANTUM) + __sk_mem_reclaim(sk); } -static inline int sk_stream_wmem_schedule(struct sock *sk, int size) +static inline void sk_mem_reclaim_partial(struct sock *sk) { - return size <= sk->sk_forward_alloc || - sk_stream_mem_schedule(sk, size, 0); + if (!sk_has_account(sk)) + return; + if (sk->sk_forward_alloc > SK_MEM_QUANTUM) + __sk_mem_reclaim(sk); +} + +static inline void sk_mem_charge(struct sock *sk, int size) +{ + if (!sk_has_account(sk)) + return; + sk->sk_forward_alloc -= size; +} + +static inline void sk_mem_uncharge(struct sock *sk, int size) +{ + if (!sk_has_account(sk)) + return; + sk->sk_forward_alloc += size; +} + +static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb) +{ + sock_set_flag(sk, SOCK_QUEUE_SHRUNK); + sk->sk_wmem_queued -= skb->truesize; + sk_mem_uncharge(sk, skb->truesize); + __kfree_skb(skb); } /* Used by processes to "lock" a socket state, so that @@ -729,170 +1488,140 @@ static inline int sk_stream_wmem_schedule(struct sock *sk, int size) * Since ~2.3.5 it is also exclusive sleep lock serializing * accesses from user process context. */ -#define sock_owned_by_user(sk) ((sk)->sk_lock.owner) +#define sock_owned_by_user(sk) ((sk)->sk_lock.owned) + +static inline void sock_release_ownership(struct sock *sk) +{ + sk->sk_lock.owned = 0; +} + +/* + * Macro so as to not evaluate some arguments when + * lockdep is not enabled. + * + * Mark both the sk_lock and the sk_lock.slock as a + * per-address-family lock class. + */ +#define sock_lock_init_class_and_name(sk, sname, skey, name, key) \ +do { \ + 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)); \ + lockdep_set_class_and_name(&(sk)->sk_lock.slock, \ + (skey), (sname)); \ + lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \ +} while (0) + +void lock_sock_nested(struct sock *sk, int subclass); + +static inline void lock_sock(struct sock *sk) +{ + lock_sock_nested(sk, 0); +} -extern void FASTCALL(lock_sock(struct sock *sk)); -extern void FASTCALL(release_sock(struct sock *sk)); +void release_sock(struct sock *sk); /* BH context may only use the following locking interface. */ #define bh_lock_sock(__sk) spin_lock(&((__sk)->sk_lock.slock)) +#define bh_lock_sock_nested(__sk) \ + spin_lock_nested(&((__sk)->sk_lock.slock), \ + SINGLE_DEPTH_NESTING) #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock)) -extern struct sock *sk_alloc(int family, - gfp_t priority, - struct proto *prot, int zero_it); -extern void sk_free(struct sock *sk); -extern struct sock *sk_clone(const struct sock *sk, - const gfp_t priority); - -extern struct sk_buff *sock_wmalloc(struct sock *sk, - unsigned long size, int force, - gfp_t priority); -extern struct sk_buff *sock_rmalloc(struct sock *sk, - unsigned long size, int force, - gfp_t priority); -extern void sock_wfree(struct sk_buff *skb); -extern void sock_rfree(struct sk_buff *skb); - -extern int sock_setsockopt(struct socket *sock, int level, - int op, char __user *optval, - int optlen); - -extern int sock_getsockopt(struct socket *sock, int level, - int op, char __user *optval, - int __user *optlen); -extern struct sk_buff *sock_alloc_send_skb(struct sock *sk, - unsigned long size, - int noblock, - int *errcode); -extern void *sock_kmalloc(struct sock *sk, int size, - gfp_t priority); -extern void sock_kfree_s(struct sock *sk, void *mem, int size); -extern void sk_send_sigurg(struct sock *sk); +bool lock_sock_fast(struct sock *sk); +/** + * unlock_sock_fast - complement of lock_sock_fast + * @sk: socket + * @slow: slow mode + * + * fast unlock socket for user context. + * If slow mode is on, we call regular release_sock() + */ +static inline void unlock_sock_fast(struct sock *sk, bool slow) +{ + if (slow) + release_sock(sk); + else + spin_unlock_bh(&sk->sk_lock.slock); +} + + +struct sock *sk_alloc(struct net *net, int family, gfp_t priority, + struct proto *prot); +void sk_free(struct sock *sk); +void sk_release_kernel(struct sock *sk); +struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority); + +struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, + gfp_t priority); +void sock_wfree(struct sk_buff *skb); +void skb_orphan_partial(struct sk_buff *skb); +void sock_rfree(struct sk_buff *skb); +void sock_edemux(struct sk_buff *skb); + +int sock_setsockopt(struct socket *sock, int level, int op, + char __user *optval, unsigned int optlen); + +int sock_getsockopt(struct socket *sock, int level, int op, + char __user *optval, int __user *optlen); +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); +void *sock_kmalloc(struct sock *sk, int size, gfp_t priority); +void sock_kfree_s(struct sock *sk, void *mem, int size); +void sk_send_sigurg(struct sock *sk); /* * Functions to fill in entries in struct proto_ops when a protocol * does not implement a particular function. */ -extern int sock_no_bind(struct socket *, - struct sockaddr *, int); -extern int sock_no_connect(struct socket *, - struct sockaddr *, int, int); -extern int sock_no_socketpair(struct socket *, - struct socket *); -extern int sock_no_accept(struct socket *, - struct socket *, int); -extern int sock_no_getname(struct socket *, - struct sockaddr *, int *, int); -extern unsigned int sock_no_poll(struct file *, struct socket *, - struct poll_table_struct *); -extern int sock_no_ioctl(struct socket *, unsigned int, - unsigned long); -extern int sock_no_listen(struct socket *, int); -extern int sock_no_shutdown(struct socket *, int); -extern int sock_no_getsockopt(struct socket *, int , int, - char __user *, int __user *); -extern int sock_no_setsockopt(struct socket *, int, int, - char __user *, int); -extern int sock_no_sendmsg(struct kiocb *, struct socket *, - struct msghdr *, size_t); -extern int sock_no_recvmsg(struct kiocb *, struct socket *, - struct msghdr *, size_t, int); -extern int sock_no_mmap(struct file *file, - struct socket *sock, - struct vm_area_struct *vma); -extern ssize_t sock_no_sendpage(struct socket *sock, - struct page *page, - int offset, size_t size, - int flags); +int sock_no_bind(struct socket *, struct sockaddr *, int); +int sock_no_connect(struct socket *, struct sockaddr *, int, int); +int sock_no_socketpair(struct socket *, struct socket *); +int sock_no_accept(struct socket *, struct socket *, int); +int sock_no_getname(struct socket *, struct sockaddr *, int *, int); +unsigned int sock_no_poll(struct file *, struct socket *, + struct poll_table_struct *); +int sock_no_ioctl(struct socket *, unsigned int, unsigned long); +int sock_no_listen(struct socket *, int); +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 kiocb *, struct socket *, struct msghdr *, size_t); +int sock_no_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t, + int); +int sock_no_mmap(struct file *file, struct socket *sock, + struct vm_area_struct *vma); +ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, + size_t size, int flags); /* * Functions to fill in entries in struct proto_ops when a protocol * uses the inet style. */ -extern int sock_common_getsockopt(struct socket *sock, int level, int optname, +int sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); -extern int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock, +int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size, int flags); -extern int sock_common_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen); +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); -extern void sk_common_release(struct sock *sk); +void sk_common_release(struct sock *sk); /* * Default socket callbacks and setup code */ - -/* Initialise core socket variables */ -extern void sock_init_data(struct socket *sock, struct sock *sk); - -/** - * sk_filter - run a packet through a socket filter - * @sk: sock associated with &sk_buff - * @skb: buffer to filter - * @needlock: set to 1 if the sock is not locked by caller. - * - * Run the filter code and then cut skb->data to correct size returned by - * sk_run_filter. If pkt_len is 0 we toss packet. If skb->len is smaller - * than pkt_len we keep whole skb->data. This is the socket level - * wrapper to sk_run_filter. It returns 0 if the packet should - * be accepted or -EPERM if the packet should be tossed. - * - */ - -static inline int sk_filter(struct sock *sk, struct sk_buff *skb, int needlock) -{ - int err; - - err = security_sock_rcv_skb(sk, skb); - if (err) - return err; - - if (sk->sk_filter) { - struct sk_filter *filter; - - if (needlock) - bh_lock_sock(sk); - - filter = sk->sk_filter; - if (filter) { - unsigned int pkt_len = sk_run_filter(skb, filter->insns, - filter->len); - if (!pkt_len) - err = -EPERM; - else - skb_trim(skb, pkt_len); - } - - if (needlock) - bh_unlock_sock(sk); - } - return err; -} - -/** - * sk_filter_release: Release a socket filter - * @sk: socket - * @fp: filter to remove - * - * Remove a filter from a socket and release its resources. - */ - -static inline void sk_filter_release(struct sock *sk, struct sk_filter *fp) -{ - unsigned int size = sk_filter_len(fp); - atomic_sub(size, &sk->sk_omem_alloc); - - if (atomic_dec_and_test(&fp->refcnt)) - kfree(fp); -} - -static inline void sk_filter_charge(struct sock *sk, struct sk_filter *fp) -{ - atomic_inc(&fp->refcnt); - atomic_add(sk_filter_len(fp), &sk->sk_omem_alloc); -} +/* Initialise core socket variables */ +void sock_init_data(struct socket *sock, struct sock *sk); /* * Socket reference counting postulates. @@ -925,30 +1654,39 @@ static inline void sock_put(struct sock *sk) if (atomic_dec_and_test(&sk->sk_refcnt)) sk_free(sk); } +/* Generic version of sock_put(), dealing with all sockets + * (TCP_TIMEWAIT, ESTABLISHED...) + */ +void sock_gen_put(struct sock *sk); -static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb) +int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested); + +static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) { - int rc = NET_RX_SUCCESS; + sk->sk_tx_queue_mapping = tx_queue; +} - if (sk_filter(sk, skb, 0)) - goto discard_and_relse; +static inline void sk_tx_queue_clear(struct sock *sk) +{ + sk->sk_tx_queue_mapping = -1; +} - skb->dev = NULL; +static inline int sk_tx_queue_get(const struct sock *sk) +{ + return sk ? sk->sk_tx_queue_mapping : -1; +} - bh_lock_sock(sk); - if (!sock_owned_by_user(sk)) - rc = sk->sk_backlog_rcv(sk, skb); - else - sk_add_backlog(sk, skb); - bh_unlock_sock(sk); -out: - sock_put(sk); - return rc; -discard_and_relse: - kfree_skb(skb); - goto out; +static inline void sk_set_socket(struct sock *sk, struct socket *sock) +{ + sk_tx_queue_clear(sk); + sk->sk_socket = sock; } +static inline wait_queue_head_t *sk_sleep(struct sock *sk) +{ + BUILD_BUG_ON(offsetof(struct socket_wq, wait) != 0); + return &rcu_dereference_raw(sk->sk_wq)->wait; +} /* Detach socket from process context. * Announce socket dead, detach it from wait queue and inode. * Note that parent inode held reference count on this struct sock, @@ -960,27 +1698,29 @@ static inline void sock_orphan(struct sock *sk) { write_lock_bh(&sk->sk_callback_lock); sock_set_flag(sk, SOCK_DEAD); - sk->sk_socket = NULL; - sk->sk_sleep = NULL; + sk_set_socket(sk, NULL); + sk->sk_wq = NULL; write_unlock_bh(&sk->sk_callback_lock); } static inline void sock_graft(struct sock *sk, struct socket *parent) { write_lock_bh(&sk->sk_callback_lock); - sk->sk_sleep = &parent->wait; + sk->sk_wq = parent->wq; parent->sk = sk; - sk->sk_socket = parent; + sk_set_socket(sk, parent); + security_sock_graft(sk, parent); write_unlock_bh(&sk->sk_callback_lock); } -extern int sock_i_uid(struct sock *sk); -extern unsigned long sock_i_ino(struct sock *sk); +kuid_t sock_i_uid(struct sock *sk); +unsigned long sock_i_ino(struct sock *sk); static inline struct dst_entry * __sk_dst_get(struct sock *sk) { - return sk->sk_dst_cache; + return rcu_dereference_check(sk->sk_dst_cache, sock_owned_by_user(sk) || + lockdep_is_held(&sk->sk_lock.slock)); } static inline struct dst_entry * @@ -988,92 +1728,133 @@ sk_dst_get(struct sock *sk) { struct dst_entry *dst; - read_lock(&sk->sk_dst_lock); - dst = sk->sk_dst_cache; - if (dst) - dst_hold(dst); - read_unlock(&sk->sk_dst_lock); + rcu_read_lock(); + dst = rcu_dereference(sk->sk_dst_cache); + if (dst && !atomic_inc_not_zero(&dst->__refcnt)) + dst = NULL; + rcu_read_unlock(); return dst; } +static inline void dst_negative_advice(struct sock *sk) +{ + struct dst_entry *ndst, *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); + } + } +} + static inline void __sk_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old_dst; - old_dst = sk->sk_dst_cache; - sk->sk_dst_cache = dst; + sk_tx_queue_clear(sk); + /* + * This can be called while sk is owned by the caller only, + * with no state that can be checked in a rcu_dereference_check() cond + */ + old_dst = rcu_dereference_raw(sk->sk_dst_cache); + rcu_assign_pointer(sk->sk_dst_cache, dst); dst_release(old_dst); } static inline void sk_dst_set(struct sock *sk, struct dst_entry *dst) { - write_lock(&sk->sk_dst_lock); - __sk_dst_set(sk, dst); - write_unlock(&sk->sk_dst_lock); + struct dst_entry *old_dst; + + sk_tx_queue_clear(sk); + old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst); + dst_release(old_dst); } static inline void __sk_dst_reset(struct sock *sk) { - struct dst_entry *old_dst; - - old_dst = sk->sk_dst_cache; - sk->sk_dst_cache = NULL; - dst_release(old_dst); + __sk_dst_set(sk, NULL); } static inline void sk_dst_reset(struct sock *sk) { - write_lock(&sk->sk_dst_lock); - __sk_dst_reset(sk); - write_unlock(&sk->sk_dst_lock); + sk_dst_set(sk, NULL); } -static inline struct dst_entry * -__sk_dst_check(struct sock *sk, u32 cookie) -{ - struct dst_entry *dst = sk->sk_dst_cache; +struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie); - if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { - sk->sk_dst_cache = NULL; - dst_release(dst); - return NULL; - } +struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie); - return dst; +static inline bool sk_can_gso(const struct sock *sk) +{ + return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type); } -static inline struct dst_entry * -sk_dst_check(struct sock *sk, u32 cookie) +void sk_setup_caps(struct sock *sk, struct dst_entry *dst); + +static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags) { - struct dst_entry *dst = sk_dst_get(sk); + sk->sk_route_nocaps |= flags; + sk->sk_route_caps &= ~flags; +} - if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { - sk_dst_reset(sk); - dst_release(dst); - return NULL; - } +static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb, + char __user *from, char *to, + int copy, int offset) +{ + if (skb->ip_summed == CHECKSUM_NONE) { + int err = 0; + __wsum csum = csum_and_copy_from_user(from, to, copy, 0, &err); + if (err) + return err; + skb->csum = csum_block_add(skb->csum, csum, offset); + } else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) { + if (!access_ok(VERIFY_READ, from, copy) || + __copy_from_user_nocache(to, from, copy)) + return -EFAULT; + } else if (copy_from_user(to, from, copy)) + return -EFAULT; - return dst; + return 0; } -static inline void sk_setup_caps(struct sock *sk, struct dst_entry *dst) +static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb, + char __user *from, int copy) { - __sk_dst_set(sk, dst); - sk->sk_route_caps = dst->dev->features; - if (sk->sk_route_caps & NETIF_F_TSO) { - if (sock_flag(sk, SOCK_NO_LARGESEND) || dst->header_len) - sk->sk_route_caps &= ~NETIF_F_TSO; - } + int err, offset = skb->len; + + err = skb_do_copy_data_nocache(sk, skb, from, skb_put(skb, copy), + copy, offset); + if (err) + __skb_trim(skb, offset); + + return err; } -static inline void sk_charge_skb(struct sock *sk, struct sk_buff *skb) +static inline int skb_copy_to_page_nocache(struct sock *sk, char __user *from, + struct sk_buff *skb, + struct page *page, + int off, int copy) { - sk->sk_wmem_queued += skb->truesize; - sk->sk_forward_alloc -= skb->truesize; + int err; + + err = skb_do_copy_data_nocache(sk, skb, from, page_address(page) + off, + copy, skb->len); + if (err) + return err; + + skb->len += copy; + skb->data_len += copy; + skb->truesize += copy; + sk->sk_wmem_queued += copy; + sk_mem_charge(sk, copy); + return 0; } static inline int skb_copy_to_page(struct sock *sk, char __user *from, @@ -1082,7 +1863,7 @@ static inline int skb_copy_to_page(struct sock *sk, char __user *from, { if (skb->ip_summed == CHECKSUM_NONE) { int err = 0; - unsigned int csum = csum_and_copy_from_user(from, + __wsum csum = csum_and_copy_from_user(from, page_address(page) + off, copy, 0, &err); if (err) @@ -1095,98 +1876,152 @@ static inline int skb_copy_to_page(struct sock *sk, char __user *from, skb->data_len += copy; skb->truesize += copy; sk->sk_wmem_queued += copy; - sk->sk_forward_alloc -= copy; + sk_mem_charge(sk, copy); return 0; } +/** + * sk_wmem_alloc_get - returns write allocations + * @sk: socket + * + * Returns sk_wmem_alloc minus initial offset of one + */ +static inline int sk_wmem_alloc_get(const struct sock *sk) +{ + return atomic_read(&sk->sk_wmem_alloc) - 1; +} + +/** + * sk_rmem_alloc_get - returns read allocations + * @sk: socket + * + * Returns sk_rmem_alloc + */ +static inline int sk_rmem_alloc_get(const struct sock *sk) +{ + return atomic_read(&sk->sk_rmem_alloc); +} + +/** + * sk_has_allocations - check if allocations are outstanding + * @sk: socket + * + * Returns true if socket has write or read allocations + */ +static inline bool sk_has_allocations(const struct sock *sk) +{ + return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk); +} + +/** + * wq_has_sleeper - check if there are any waiting processes + * @wq: struct socket_wq + * + * Returns true if socket_wq has waiting processes + * + * The purpose of the wq_has_sleeper and sock_poll_wait is to wrap the memory + * barrier call. They were added due to the race found within the tcp code. + * + * Consider following tcp code paths: + * + * CPU1 CPU2 + * + * sys_select receive packet + * ... ... + * __add_wait_queue update tp->rcv_nxt + * ... ... + * tp->rcv_nxt check sock_def_readable + * ... { + * schedule rcu_read_lock(); + * wq = rcu_dereference(sk->sk_wq); + * if (wq && waitqueue_active(&wq->wait)) + * wake_up_interruptible(&wq->wait) + * ... + * } + * + * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay + * in its cache, and so does the tp->rcv_nxt update on CPU2 side. The CPU1 + * could then endup calling schedule and sleep forever if there are no more + * data on the socket. + * + */ +static inline bool wq_has_sleeper(struct socket_wq *wq) +{ + /* We need to be sure we are in sync with the + * add_wait_queue modifications to the wait queue. + * + * This memory barrier is paired in the sock_poll_wait. + */ + smp_mb(); + return wq && waitqueue_active(&wq->wait); +} + +/** + * sock_poll_wait - place memory barrier behind the poll_wait call. + * @filp: file + * @wait_address: socket wait queue + * @p: poll_table + * + * See the comments in the wq_has_sleeper function. + */ +static inline void sock_poll_wait(struct file *filp, + wait_queue_head_t *wait_address, poll_table *p) +{ + if (!poll_does_not_wait(p) && wait_address) { + poll_wait(filp, wait_address, 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(); + } +} + /* - * Queue a received datagram if it will fit. Stream and sequenced + * Queue a received datagram if it will fit. Stream and sequenced * protocols can't normally use this as they need to fit buffers in * and play with them. * - * Inlined as it's very short and called for pretty much every + * Inlined as it's very short and called for pretty much every * packet ever received. */ static inline void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) { - sock_hold(sk); + skb_orphan(skb); skb->sk = sk; skb->destructor = sock_wfree; + /* + * We used to take a refcount on sk, but following operation + * is enough to guarantee sk_free() wont free this sock until + * all in-flight packets are completed + */ atomic_add(skb->truesize, &sk->sk_wmem_alloc); } static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk) { + skb_orphan(skb); skb->sk = sk; skb->destructor = sock_rfree; atomic_add(skb->truesize, &sk->sk_rmem_alloc); + sk_mem_charge(sk, skb->truesize); } -extern void sk_reset_timer(struct sock *sk, struct timer_list* timer, - unsigned long expires); - -extern void sk_stop_timer(struct sock *sk, struct timer_list* timer); - -static inline int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) -{ - int err = 0; - int skb_len; - - /* Cast skb->rcvbuf to unsigned... It's pointless, but reduces - number of warnings when compiling with -W --ANK - */ - if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned)sk->sk_rcvbuf) { - err = -ENOMEM; - goto out; - } - - /* It would be deadlock, if sock_queue_rcv_skb is used - with socket lock! We assume that users of this - function are lock free. - */ - err = sk_filter(sk, skb, 1); - if (err) - goto out; - - skb->dev = NULL; - skb_set_owner_r(skb, sk); - - /* Cache the SKB length before we tack it onto the receive - * queue. Once it is added it no longer belongs to us and - * may be freed by other threads of control pulling packets - * from the queue. - */ - skb_len = skb->len; +void sk_reset_timer(struct sock *sk, struct timer_list *timer, + unsigned long expires); - skb_queue_tail(&sk->sk_receive_queue, skb); +void sk_stop_timer(struct sock *sk, struct timer_list *timer); - if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, skb_len); -out: - return err; -} +int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); -static inline int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) -{ - /* Cast skb->rcvbuf to unsigned... It's pointless, but reduces - number of warnings when compiling with -W --ANK - */ - if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned)sk->sk_rcvbuf) - return -ENOMEM; - skb_set_owner_r(skb, sk); - skb_queue_tail(&sk->sk_error_queue, skb); - if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, skb->len); - return 0; -} +int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb); /* * Recover an error report and clear atomically */ - + static inline int sock_error(struct sock *sk) { int err; @@ -1202,7 +2037,7 @@ static inline unsigned long sock_wspace(struct sock *sk) if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { amt = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc); - if (amt < 0) + if (amt < 0) amt = 0; } return amt; @@ -1210,81 +2045,53 @@ static inline unsigned long sock_wspace(struct sock *sk) static inline void sk_wake_async(struct sock *sk, int how, int band) { - if (sk->sk_socket && sk->sk_socket->fasync_list) + if (sock_flag(sk, SOCK_FASYNC)) sock_wake_async(sk->sk_socket, how, band); } -#define SOCK_MIN_SNDBUF 2048 -#define SOCK_MIN_RCVBUF 256 +/* 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 + * minimum. + */ +#define TCP_SKB_MIN_TRUESIZE (2048 + SKB_DATA_ALIGN(sizeof(struct sk_buff))) + +#define SOCK_MIN_SNDBUF (TCP_SKB_MIN_TRUESIZE * 2) +#define SOCK_MIN_RCVBUF TCP_SKB_MIN_TRUESIZE static inline void sk_stream_moderate_sndbuf(struct sock *sk) { if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) { - sk->sk_sndbuf = min(sk->sk_sndbuf, sk->sk_wmem_queued / 2); - sk->sk_sndbuf = max(sk->sk_sndbuf, SOCK_MIN_SNDBUF); - } -} - -static inline struct sk_buff *sk_stream_alloc_pskb(struct sock *sk, - int size, int mem, - gfp_t gfp) -{ - struct sk_buff *skb; - int hdr_len; - - hdr_len = SKB_DATA_ALIGN(sk->sk_prot->max_header); - skb = alloc_skb_fclone(size + hdr_len, gfp); - if (skb) { - skb->truesize += mem; - if (sk_stream_wmem_schedule(sk, skb->truesize)) { - skb_reserve(skb, hdr_len); - return skb; - } - __kfree_skb(skb); - } else { - sk->sk_prot->enter_memory_pressure(); - sk_stream_moderate_sndbuf(sk); + sk->sk_sndbuf = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1); + sk->sk_sndbuf = max_t(u32, sk->sk_sndbuf, SOCK_MIN_SNDBUF); } - return NULL; } -static inline struct sk_buff *sk_stream_alloc_skb(struct sock *sk, - int size, - gfp_t gfp) -{ - return sk_stream_alloc_pskb(sk, size, 0, gfp); -} +struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp); -static inline struct page *sk_stream_alloc_page(struct sock *sk) +/** + * sk_page_frag - return an appropriate page_frag + * @sk: socket + * + * If socket allocation mode allows current thread to sleep, it means its + * safe to use the per task page_frag instead of the per socket one. + */ +static inline struct page_frag *sk_page_frag(struct sock *sk) { - struct page *page = NULL; + if (sk->sk_allocation & __GFP_WAIT) + return ¤t->task_frag; - page = alloc_pages(sk->sk_allocation, 0); - if (!page) { - sk->sk_prot->enter_memory_pressure(); - sk_stream_moderate_sndbuf(sk); - } - return page; + return &sk->sk_frag; } -#define sk_stream_for_retrans_queue(skb, sk) \ - for (skb = (sk)->sk_write_queue.next; \ - (skb != (sk)->sk_send_head) && \ - (skb != (struct sk_buff *)&(sk)->sk_write_queue); \ - skb = skb->next) - -/*from STCP for fast SACK Process*/ -#define sk_stream_for_retrans_queue_from(skb, sk) \ - for (; (skb != (sk)->sk_send_head) && \ - (skb != (struct sk_buff *)&(sk)->sk_write_queue); \ - skb = skb->next) +bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag); /* * Default write policy as shown to user space via poll/select/SIGIO */ -static inline int sock_writeable(const struct sock *sk) +static inline bool sock_writeable(const struct sock *sk) { - return atomic_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf / 2); + return atomic_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf >> 1); } static inline gfp_t gfp_any(void) @@ -1292,12 +2099,12 @@ static inline gfp_t gfp_any(void) return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } -static inline long sock_rcvtimeo(const struct sock *sk, int noblock) +static inline long sock_rcvtimeo(const struct sock *sk, bool noblock) { return noblock ? 0 : sk->sk_rcvtimeo; } -static inline long sock_sndtimeo(const struct sock *sk, int noblock) +static inline long sock_sndtimeo(const struct sock *sk, bool noblock) { return noblock ? 0 : sk->sk_sndtimeo; } @@ -1315,102 +2122,158 @@ static inline int sock_intr_errno(long timeo) return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR; } -static __inline__ void +void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb); +void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb); + +static inline void sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { - struct timeval stamp; + ktime_t kt = skb->tstamp; + struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb); + + /* + * generate control messages if + * - receive time stamping in software requested (SOCK_RCVTSTAMP + * or SOCK_TIMESTAMPING_RX_SOFTWARE) + * - software time stamp available and wanted + * (SOCK_TIMESTAMPING_SOFTWARE) + * - hardware time stamps available and wanted + * (SOCK_TIMESTAMPING_SYS_HARDWARE or + * SOCK_TIMESTAMPING_RAW_HARDWARE) + */ + if (sock_flag(sk, SOCK_RCVTSTAMP) || + sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE) || + (kt.tv64 && sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) || + (hwtstamps->hwtstamp.tv64 && + sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE)) || + (hwtstamps->syststamp.tv64 && + sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE))) + __sock_recv_timestamp(msg, sk, skb); + else + sk->sk_stamp = kt; + + if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid) + __sock_recv_wifi_status(msg, sk, skb); +} + +void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb); + +static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) +{ +#define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL) | \ + (1UL << SOCK_RCVTSTAMP) | \ + (1UL << SOCK_TIMESTAMPING_SOFTWARE) | \ + (1UL << SOCK_TIMESTAMPING_RAW_HARDWARE) | \ + (1UL << SOCK_TIMESTAMPING_SYS_HARDWARE)) - skb_get_timestamp(skb, &stamp); - if (sock_flag(sk, SOCK_RCVTSTAMP)) { - /* Race occurred between timestamp enabling and packet - receiving. Fill in the current time for now. */ - if (stamp.tv_sec == 0) - do_gettimeofday(&stamp); - skb_set_timestamp(skb, &stamp); - put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP, sizeof(struct timeval), - &stamp); - } else - sk->sk_stamp = stamp; + if (sk->sk_flags & FLAGS_TS_OR_DROPS) + __sock_recv_ts_and_drops(msg, sk, skb); + else + sk->sk_stamp = skb->tstamp; } /** + * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped + * @sk: socket sending this packet + * @tx_flags: filled with instructions for time stamping + * + * Currently only depends on SOCK_TIMESTAMPING* flags. + */ +void sock_tx_timestamp(struct sock *sk, __u8 *tx_flags); + +/** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from * @skb: socket buffer to eat + * @copied_early: flag indicating whether DMA operations copied this data early * * This routine must be called with interrupts disabled or with the socket * locked so that the sk_buff queue operation is ok. */ -static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) +#ifdef CONFIG_NET_DMA +static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, bool copied_early) +{ + __skb_unlink(skb, &sk->sk_receive_queue); + if (!copied_early) + __kfree_skb(skb); + else + __skb_queue_tail(&sk->sk_async_wait_queue, skb); +} +#else +static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, bool copied_early) { __skb_unlink(skb, &sk->sk_receive_queue); __kfree_skb(skb); } +#endif -extern void sock_enable_timestamp(struct sock *sk); -extern int sock_get_timestamp(struct sock *, struct timeval __user *); - -/* - * Enable debug/info messages - */ +static inline +struct net *sock_net(const struct sock *sk) +{ + return read_pnet(&sk->sk_net); +} -#if 0 -#define NETDEBUG(fmt, args...) do { } while (0) -#define LIMIT_NETDEBUG(fmt, args...) do { } while(0) -#else -#define NETDEBUG(fmt, args...) printk(fmt,##args) -#define LIMIT_NETDEBUG(fmt, args...) do { if (net_ratelimit()) printk(fmt,##args); } while(0) -#endif +static inline +void sock_net_set(struct sock *sk, struct net *net) +{ + write_pnet(&sk->sk_net, net); +} /* - * Macros for sleeping on a socket. Use them like this: - * - * SOCK_SLEEP_PRE(sk) - * if (condition) - * schedule(); - * SOCK_SLEEP_POST(sk) - * - * N.B. These are now obsolete and were, afaik, only ever used in DECnet - * and when the last use of them in DECnet has gone, I'm intending to - * remove them. + * Kernel sockets, f.e. rtnl or icmp_socket, are a part of a namespace. + * They should not hold a reference to a namespace in order to allow + * to stop it. + * Sockets after sk_change_net should be released using sk_release_kernel */ +static inline void sk_change_net(struct sock *sk, struct net *net) +{ + struct net *current_net = sock_net(sk); -#define SOCK_SLEEP_PRE(sk) { struct task_struct *tsk = current; \ - DECLARE_WAITQUEUE(wait, tsk); \ - tsk->state = TASK_INTERRUPTIBLE; \ - add_wait_queue((sk)->sk_sleep, &wait); \ - release_sock(sk); - -#define SOCK_SLEEP_POST(sk) tsk->state = TASK_RUNNING; \ - remove_wait_queue((sk)->sk_sleep, &wait); \ - lock_sock(sk); \ - } + if (!net_eq(current_net, net)) { + put_net(current_net); + sock_net_set(sk, hold_net(net)); + } +} -static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool) +static inline struct sock *skb_steal_sock(struct sk_buff *skb) { - if (valbool) - sock_set_flag(sk, bit); - else - sock_reset_flag(sk, bit); + if (skb->sk) { + struct sock *sk = skb->sk; + + skb->destructor = NULL; + skb->sk = NULL; + return sk; + } + return NULL; } -extern __u32 sysctl_wmem_max; -extern __u32 sysctl_rmem_max; +void sock_enable_timestamp(struct sock *sk, int flag); +int sock_get_timestamp(struct sock *, struct timeval __user *); +int sock_get_timestampns(struct sock *, struct timespec __user *); +int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, + int type); -#ifdef CONFIG_NET -int siocdevprivate_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); -#else -static inline int siocdevprivate_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg) -{ - return -ENODEV; -} -#endif +bool sk_ns_capable(const struct sock *sk, + struct user_namespace *user_ns, int cap); +bool sk_capable(const struct sock *sk, int cap); +bool sk_net_capable(const struct sock *sk, int cap); -extern void sk_init(void); +/* + * Enable debug/info messages + */ +extern int net_msg_warn; +#define NETDEBUG(fmt, args...) \ + do { if (net_msg_warn) printk(fmt,##args); } while (0) -#ifdef CONFIG_SYSCTL -extern struct ctl_table core_table[]; -#endif +#define LIMIT_NETDEBUG(fmt, args...) \ + do { if (net_msg_warn && net_ratelimit()) printk(fmt,##args); } while(0) + +extern __u32 sysctl_wmem_max; +extern __u32 sysctl_rmem_max; extern int sysctl_optmem_max; |