/* NB: equivalent to hlist_del_init_rcu */ staticinlinebool __sk_del_node_init(struct sock *sk)
{ if (sk_hashed(sk)) {
__sk_del_node(sk);
sk_node_init(&sk->sk_node); returntrue;
} returnfalse;
}
/* Grab socket reference count. This operation is valid only whenskisALREADYgrabbedf.e.itisfoundinhashtable oralistandthelookupismadeunderlockpreventinghashtable modifications.
*/
staticinlinestruct user_namespace *sk_user_ns(conststruct sock *sk)
{ /* Careful only use this in a context where these parameters *cannotchangeandmustallbevalid,suchasrecvmsgfrom *userspace.
*/ return sk->sk_socket->file->f_cred->user_ns;
}
/* Sock flags */ enum sock_flags {
SOCK_DEAD,
SOCK_DONE,
SOCK_URGINLINE,
SOCK_KEEPOPEN,
SOCK_LINGER,
SOCK_DESTROY,
SOCK_BROADCAST,
SOCK_TIMESTAMP,
SOCK_ZAPPED,
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_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */
SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
SOCK_MEMALLOC, /* VM depends on this socket for swapping */
SOCK_TIMESTAMPING_RX_SOFTWARE, /* %SOF_TIMESTAMPING_RX_SOFTWARE */
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. *Willuselast4bytesofpacketsentfrom *user-spaceinstead.
*/
SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */
SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */
SOCK_TXTIME,
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 */
};
/* Note: If you think the test should be: *returnREAD_ONCE(sk->sk_ack_backlog)>=READ_ONCE(sk->sk_max_ack_backlog); *Thenpleasetakealookatcommit64a146513f8f("[NET]:Revertincorrectacceptqueuebacklogchanges.")
*/ staticinlinebool sk_acceptq_is_full(conststruct sock *sk)
{ return READ_ONCE(sk->sk_ack_backlog) > READ_ONCE(sk->sk_max_ack_backlog);
}
staticinlinevoid 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 */ staticinlinevoid __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
{ /* dont let skb dst not refcounted, we are going to leave rcu lock */
skb_dst_force(skb);
if (!sk->sk_backlog.tail)
WRITE_ONCE(sk->sk_backlog.head, skb); else
sk->sk_backlog.tail->next = skb;
/* The per-socket spinlock must be held here. */ staticinline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *skb, unsignedint limit)
{ if (sk_rcvqueues_full(sk, limit)) return -ENOBUFS;
staticinlinevoid sk_incoming_cpu_update(struct sock *sk)
{ int cpu = raw_smp_processor_id();
if (unlikely(READ_ONCE(sk->sk_incoming_cpu) != cpu))
WRITE_ONCE(sk->sk_incoming_cpu, cpu);
}
staticinlinevoid sock_rps_save_rxhash(struct sock *sk, conststruct sk_buff *skb)
{ #ifdef CONFIG_RPS /* The following WRITE_ONCE() is paired with the READ_ONCE() *here,andanotheroneinsock_rps_record_flow().
*/ if (unlikely(READ_ONCE(sk->sk_rxhash) != skb->hash))
WRITE_ONCE(sk->sk_rxhash, skb->hash); #endif
}
staticinlinevoid sock_rps_reset_rxhash(struct sock *sk)
{ #ifdef CONFIG_RPS /* Paired with READ_ONCE() in sock_rps_record_flow() */
WRITE_ONCE(sk->sk_rxhash, 0); #endif
}
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);
struct proto_accept_arg { int flags; int err; int is_empty; bool kern;
};
/* Networking protocol blocks we attach to sockets. *socketlayer->transportlayerinterface
*/ struct proto { void (*close)(struct sock *sk, long timeout); int (*pre_connect)(struct sock *sk, struct sockaddr *uaddr, int addr_len); int (*connect)(struct sock *sk, struct sockaddr *uaddr, int addr_len); int (*disconnect)(struct sock *sk, int flags);
int (*ioctl)(struct sock *sk, int cmd, int *karg); int (*init)(struct sock *sk); void (*destroy)(struct sock *sk); void (*shutdown)(struct sock *sk, int how); int (*setsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, unsignedint optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *option); void (*keepalive)(struct sock *sk, int valbool); #ifdef CONFIG_COMPAT int (*compat_ioctl)(struct sock *sk, unsignedint cmd, unsignedlong arg); #endif int (*sendmsg)(struct sock *sk, struct msghdr *msg,
size_t len); int (*recvmsg)(struct sock *sk, struct msghdr *msg,
size_t len, int flags, int *addr_len); void (*splice_eof)(struct socket *sock); int (*bind)(struct sock *sk, struct sockaddr *addr, int addr_len); int (*bind_add)(struct sock *sk, struct sockaddr *addr, int addr_len);
int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); bool (*bpf_bypass_getsockopt)(int level, int optname);
void (*release_cb)(struct sock *sk);
/* Keeping track of sk's, looking them up, and port selection methods. */ int (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsignedshort snum); void (*put_port)(struct sock *sk); #ifdef CONFIG_BPF_SYSCALL int (*psock_update_sk_prot)(struct sock *sk, struct sk_psock *psock, bool restore); #endif
/* Keeping track of sockets in use */ #ifdef CONFIG_PROC_FS unsignedint inuse_idx; #endif
bool (*stream_memory_free)(conststruct sock *sk, int wake); bool (*sock_is_readable)(struct sock *sk); /* Memory pressure */ void (*enter_memory_pressure)(struct sock *sk); void (*leave_memory_pressure)(struct sock *sk);
atomic_long_t *memory_allocated; /* Current allocated memory. */ int __percpu *per_cpu_fw_alloc; struct percpu_counter *sockets_allocated; /* Current number of sockets. */
struct list_head node; int (*diag_destroy)(struct sock *sk, int err);
} __randomize_layout;
int proto_register(struct proto *prot, int alloc_slab); void proto_unregister(struct proto *prot); int sock_load_diag_module(int family, int protocol);
INDIRECT_CALLABLE_DECLARE(bool tcp_stream_memory_free(conststruct sock *sk, int wake));
staticinlinebool __sk_stream_memory_free(conststruct sock *sk, int wake)
{ if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf)) returnfalse;
staticinlineint
proto_sockets_allocated_sum_positive(struct proto *prot)
{ return percpu_counter_sum_positive(prot->sockets_allocated);
}
#ifdef CONFIG_PROC_FS #define PROTO_INUSE_NR 64/* should be enough for the first time */ struct prot_inuse { int all; int val[PROTO_INUSE_NR];
};
staticinlinevoid sock_prot_inuse_add(conststruct net *net, conststruct proto *prot, int val)
{
this_cpu_add(net->core.prot_inuse->val[prot->inuse_idx], val);
}
staticinlinevoid sock_inuse_add(conststruct net *net, int val)
{
this_cpu_add(net->core.prot_inuse->all, val);
}
int sock_prot_inuse_get(struct net *net, struct proto *proto); int sock_inuse_get(struct net *net); #else staticinlinevoid sock_prot_inuse_add(conststruct net *net, conststruct proto *prot, int val)
{
}
staticinlinevoid sock_inuse_add(conststruct net *net, int val)
{
} #endif
/* With per-bucket locks this operation is not-atomic, so that *thisversionisnotworse.
*/ staticinlineint __sk_prot_rehash(struct sock *sk)
{
sk->sk_prot->unhash(sk); return sk->sk_prot->hash(sk);
}
/* About 10 seconds */ #define SOCK_DESTROY_TIME (10*HZ)
/* Sockets 0-1023 can't be bound to unless you are superuser */ #define PROT_SOCK 1024
/* *Functionsformemoryaccounting
*/ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind); int __sk_mem_schedule(struct sock *sk, int size, int kind); void __sk_mem_reduce_allocated(struct sock *sk, int amount); void __sk_mem_reclaim(struct sock *sk, int amount);
#define SK_MEM_SEND 0 #define SK_MEM_RECV 1
/* sysctl_mem values are in pages */ staticinlinelong sk_prot_mem_limits(conststruct sock *sk, int index)
{ return READ_ONCE(sk->sk_prot->sysctl_mem[index]);
}
/* 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))
/* Used by processes to "lock" a socket state, so that *interruptsandbottomhalfhandlerswon'tchangeit *fromunderus.Itessentiallyblocksanyincoming *packets,sothatwewon'tgetanynewdataorany *packetsthatchangethestateofthesocket. * *Whilelocked,BHprocessingwilladdnewpacketsto *thebacklogqueue.Thisqueueisprocessedbythe *ownerofthesocketlockrightbeforeitisreleased. * *Since~2.3.5itisalsoexclusivesleeplockserializing *accessesfromuserprocesscontext.
*/
/* The sk_lock has mutex_unlock() semantics: */
mutex_release(&sk->sk_lock.dep_map, _RET_IP_);
}
/* no reclassification while locks are held */ staticinlinebool sock_allow_reclassification(conststruct sock *csk)
{ struct sock *sk = (struct sock *)csk;
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_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,
unsigned long data_len, int noblock,
int *errcode, int max_page_order);
static inline struct sk_buff *sock_alloc_send_skb(struct sock *sk,
unsigned long size,
int noblock, int *errcode)
{
return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0);
}
void *sock_kmalloc(struct sock *sk, int size, gfp_t priority);
void *sock_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);
static inline void sock_replace_proto(struct sock *sk, struct proto *proto)
{
if (sk->sk_socket)
clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
WRITE_ONCE(sk->sk_prot, proto);
}
int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
struct sockcm_cookie *sockc);
int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
struct sockcm_cookie *sockc);
/*
* 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_socketpair(struct socket *, struct socket *);
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);
int sock_no_shutdown(struct socket *, int);
int sock_no_sendmsg(struct socket *, struct msghdr *, size_t);
int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t len);
int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int);
int sock_no_mmap(struct file *file, struct socket *sock,
struct vm_area_struct *vma);
/*
* Functions to fill in entries in struct proto_ops when a protocol
* uses the inet style.
*/
int sock_common_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen);
int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int flags);
int sock_common_setsockopt(struct socket *sock, int level, int optname,
sockptr_t optval, unsigned int optlen);
void sk_common_release(struct sock *sk);
/*
* Default socket callbacks and setup code
*/
/* Initialise core socket variables using an explicit uid. */
void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid);
/* Initialise core socket variables.
* Assumes struct socket *sock is embedded in a struct socket_alloc.
*/
void sock_init_data(struct socket *sock, struct sock *sk);
/*
* Socket reference counting postulates.
*
* * Each user of socket SHOULD hold a reference count.
* * Each access point to socket (an hash table bucket, reference from a list,
* running timer, skb in flight MUST hold a reference count.
* * When reference count hits 0, it means it will never increase back.
* * When reference count hits 0, it means that no references from
* outside exist to this socket and current process on current CPU
* is last user and may/should destroy this socket.
* * sk_free is called from any context: process, BH, IRQ. When
* it is called, socket has no references from outside -> sk_free
* may release descendant resources allocated by the socket, but
* to the time when it is called, socket is NOT referenced by any
* hash tables, lists etc.
* * Packets, delivered from outside (from network or from another process)
* and enqueued on receive/error queues SHOULD NOT grab reference count,
* when they sit in queue. Otherwise, packets will leak to hole, when
* socket is looked up by one cpu and unhasing is made by another CPU.
* It is true for udp/raw, netlink (leak to receive and error queues), tcp
* (leak to backlog). Packet socket does all the processing inside
* BR_NETPROTO_LOCK, so that it has not this race condition. UNIX sockets
* use separate SMP lock, so that they are prone too.
*/
/* Ungrab socket and destroy it, if it was the last reference. */
static inline void sock_put(struct sock *sk)
{
if (refcount_dec_and_test(&sk->sk_refcnt))
sk_free(sk);
}
/* Generic version of sock_put(), dealing with all sockets
* (TCP_TIMEWAIT, TCP_NEW_SYN_RECV, ESTABLISHED...)
*/
void sock_gen_put(struct sock *sk);
int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested,
unsigned int trim_cap, bool refcounted);
static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb,
const int nested)
{
return __sk_receive_skb(sk, skb, nested, 1, true);
}
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;
/* 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, tx_queue);
}
#define NO_QUEUE_MAPPING USHRT_MAX
static inline void sk_tx_queue_clear(struct sock *sk)
{
/* 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) {
/* Paired with WRITE_ONCE() in sk_tx_queue_clear()
* and sk_tx_queue_set().
*/
int val = READ_ONCE(sk->sk_tx_queue_mapping);
if (val != NO_QUEUE_MAPPING)
return val;
}
return -1;
}
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,
* we do not release it in this function, because protocol
* probably wants some additional cleanups or even continuing
* to work with this socket (TCP).
*/
static inline void sock_orphan(struct sock *sk)
{
write_lock_bh(&sk->sk_callback_lock);
sock_set_flag(sk, SOCK_DEAD);
sk_set_socket(sk, NULL);
sk->sk_wq = NULL;
write_unlock_bh(&sk->sk_callback_lock);
}
/**
* sk_has_allocations - check if allocations are outstanding
* @sk: socket
*
* Return: 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);
}
/**
* skwq_has_sleeper - check if there are any waiting processes
* @wq: struct socket_wq
*
* Return: true if socket_wq has waiting processes
*
* The purpose of the skwq_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 skwq_has_sleeper(struct socket_wq *wq)
{
return wq && wq_has_sleeper(&wq->wait);
}
/**
* sock_poll_wait - wrapper for the poll_wait call.
* @filp: file
* @sock: socket to wait on
* @p: poll_table
*
* See the comments in the wq_has_sleeper function.
*/
static inline void sock_poll_wait(struct file *filp, struct socket *sock,
poll_table *p)
{
/* 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)
{
/* This pairs with WRITE_ONCE() in sk_set_txhash() */
u32 txhash = READ_ONCE(sk->sk_txhash);
/*
* 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
* packet ever received.
*/
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);
}
/*
* Recover an error report and clear atomically
*/
static inline int sock_error(struct sock *sk)
{
int err;
/* Avoid an atomic operation for the common case.
* This is racy since another cpu/thread can change sk_err under us.
*/
if (likely(data_race(!sk->sk_err)))
return 0;
err = xchg(&sk->sk_err, 0);
return -err;
}
void sk_error_report(struct sock *sk);
static inline unsigned long sock_wspace(struct sock *sk)
{
int amt = 0;
if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
amt = sk->sk_sndbuf - refcount_read(&sk->sk_wmem_alloc);
if (amt < 0)
amt = 0;
}
return amt;
}
/* Note:
* We use sk->sk_wq_raw, from contexts knowing this
* pointer is not NULL and cannot disappear/change.
*/
static inline void sk_set_bit(int nr, struct sock *sk)
{
if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) &&
!sock_flag(sk, SOCK_FASYNC))
return;
static inline void sk_wake_async(const struct sock *sk, int how, int band)
{
if (sock_flag(sk, SOCK_FASYNC)) {
rcu_read_lock();
sock_wake_async(rcu_dereference(sk->sk_wq), how, band);
rcu_read_unlock();
}
}
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
* minimum.
*/
#define TCP_SKB_MIN_TRUESIZE (2048 + SKB_DATA_ALIGN(sizeof(struct sk_buff)))
/**
* sk_page_frag - return an appropriate page_frag
* @sk: socket
*
* Use the per task page_frag instead of the per socket one for
* optimization when we know that we're in process context and own
* everything that's associated with %current.
*
* Both direct reclaim and page faults can nest inside other
* socket operations and end up recursing into sk_page_frag()
* while it's already in use: explicitly avoid task page_frag
* when users disable sk_use_task_frag.
*
* Return: a per task page_frag if context allows that,
* otherwise a per socket one.
*/
static inline struct page_frag *sk_page_frag(struct sock *sk)
{
if (sk->sk_use_task_frag)
return ¤t->task_frag;
static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len)
{
int v = waitall ? len : min_t(int, READ_ONCE(sk->sk_rcvlowat), len);
return v ?: 1;
}
/* Alas, with timeout socket operations are not restartable.
* Compare this to poll().
*/
static inline int sock_intr_errno(long timeo)
{
return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR;
}
struct sock_skb_cb {
u32 dropcount;
};
/* Store sock_skb_cb at the end of skb->cb[] so protocol families
* using skb->cb[] would keep using it directly and utilize its
* alignment guarantee.
*/
#define SOCK_SKB_CB_OFFSET (sizeof_field(struct sk_buff, cb) - \
sizeof(struct sock_skb_cb))
/**
* _sock_tx_timestamp - checks whether the outgoing packet is to be time stamped
* @sk: socket sending this packet
* @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,
const struct sockcm_cookie *sockc,
__u8 *tx_flags, __u32 *tskey)
{
__u32 tsflags = sockc->tsflags;
/**
* sk_eat_skb - Release a skb if it is no longer needed
* @sk: socket to eat this skb from
* @skb: socket buffer to eat
*
* 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)
{
__skb_unlink(skb, &sk->sk_receive_queue);
__kfree_skb(skb);
}
/* This helper checks if a socket is a full socket,
* ie _not_ a timewait or request socket.
*/
static inline bool sk_fullsock(const struct sock *sk)
{
return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV);
}
static inline bool
sk_is_refcounted(struct sock *sk)
{
/* Only full sockets have sk->sk_flags. */
return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE);
}
/* 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)
{
#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);
} else if (unlikely(skb_is_decrypted(skb))) {
pr_warn_ratelimited("unencrypted skb with no associated socket - dropping\n");
kfree_skb(skb);
skb = NULL;
}
#endif
return skb;
}
/* This helper checks if a socket is a LISTEN or NEW_SYN_RECV
* SYNACK messages can be attached to either ones (depending on SYNCOOKIE)
*/
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);
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);
/* Take into consideration the size of the struct sk_buff overhead in the
* determination of these values, since that is non-constant across
* platforms. This makes socket queueing behavior and performance
* not depend upon such differences.
*/
#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)
static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto)
{
/* Does this proto have per netns sysctl_wmem ? */
if (proto->sysctl_wmem_offset)
return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset));
return READ_ONCE(*proto->sysctl_wmem);
}
static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto)
{
/* Does this proto have per netns sysctl_rmem ? */
if (proto->sysctl_rmem_offset)
return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset));
return READ_ONCE(*proto->sysctl_rmem);
}
/* Default TCP Small queue budget is ~1 ms of data (1sec >> 10)
* Some wifi drivers need to tweak it to get more chunks.
* They can use this helper from their ndo_start_xmit()
*/
static inline void sk_pacing_shift_update(struct sock *sk, int val)
{
if (!sk || !sk_fullsock(sk) || READ_ONCE(sk->sk_pacing_shift) == val)
return;
WRITE_ONCE(sk->sk_pacing_shift, val);
}
/* if a socket is bound to a device, check that the given device
* index is either the same or that the socket is bound to an L3
* master device and the given device index is also enslaved to
* that L3 master
*/
static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif)
{
int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
int mdif;
if (!bound_dev_if || bound_dev_if == dif)
return true;
int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk);
void sock_set_timestamp(struct sock *sk, int optname, bool valbool);
int sock_set_timestamping(struct sock *sk, int optname,
struct so_timestamping timestamping);
int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len);
int sock_get_timeout(long timeo, void *optval, bool old_timeval);
int sock_copy_user_timeval(struct __kernel_sock_timeval *tv,
sockptr_t optval, int optlen, bool old_timeval);
int sock_ioctl_inout(struct sock *sk, unsigned int cmd,
void __user *arg, void *karg, size_t size);
int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
static inline bool sk_is_readable(struct sock *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 */
Messung V0.5 in Prozent
¤ Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.0.138Bemerkung:
¤
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.
