aboutsummaryrefslogtreecommitdiffstats
path: root/include/asm-alpha/socket.h
Commit message (Collapse)AuthorAge
* alpha: move include/asm-alpha to arch/alpha/include/asmLinus Torvalds2008-08-15
| | | | | | | | | | | | | | | | | Sam Ravnborg did the build-test that the direct header file move works, I'm just committing it. This is a pure move: mkdir arch/alpha/include git mv include/asm-alpha arch/alpha/include/asm with no other changes. Requested-and-tested-by: Sam Ravnborg <sam@ravnborg.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* flag parameters: pacceptUlrich Drepper2008-07-24
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch is by far the most complex in the series. It adds a new syscall paccept. This syscall differs from accept in that it adds (at the userlevel) two additional parameters: - a signal mask - a flags value The flags parameter can be used to set flag like SOCK_CLOEXEC. This is imlpemented here as well. Some people argued that this is a property which should be inherited from the file desriptor for the server but this is against POSIX. Additionally, we really want the signal mask parameter as well (similar to pselect, ppoll, etc). So an interface change in inevitable. The flag value is the same as for socket and socketpair. I think diverging here will only create confusion. Similar to the filesystem interfaces where the use of the O_* constants differs, it is acceptable here. The signal mask is handled as for pselect etc. The mask is temporarily installed for the thread and removed before the call returns. I modeled the code after pselect. If there is a problem it's likely also in pselect. For architectures which use socketcall I maintained this interface instead of adding a system call. The symmetry shouldn't be broken. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include <errno.h> #include <fcntl.h> #include <pthread.h> #include <signal.h> #include <stdio.h> #include <unistd.h> #include <netinet/in.h> #include <sys/socket.h> #include <sys/syscall.h> #ifndef __NR_paccept # ifdef __x86_64__ # define __NR_paccept 288 # elif defined __i386__ # define SYS_PACCEPT 18 # define USE_SOCKETCALL 1 # else # error "need __NR_paccept" # endif #endif #ifdef USE_SOCKETCALL # define paccept(fd, addr, addrlen, mask, flags) \ ({ long args[6] = { \ (long) fd, (long) addr, (long) addrlen, (long) mask, 8, (long) flags }; \ syscall (__NR_socketcall, SYS_PACCEPT, args); }) #else # define paccept(fd, addr, addrlen, mask, flags) \ syscall (__NR_paccept, fd, addr, addrlen, mask, 8, flags) #endif #define PORT 57392 #define SOCK_CLOEXEC O_CLOEXEC static pthread_barrier_t b; static void * tf (void *arg) { pthread_barrier_wait (&b); int s = socket (AF_INET, SOCK_STREAM, 0); struct sockaddr_in sin; sin.sin_family = AF_INET; sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK); sin.sin_port = htons (PORT); connect (s, (const struct sockaddr *) &sin, sizeof (sin)); close (s); pthread_barrier_wait (&b); s = socket (AF_INET, SOCK_STREAM, 0); sin.sin_port = htons (PORT); connect (s, (const struct sockaddr *) &sin, sizeof (sin)); close (s); pthread_barrier_wait (&b); pthread_barrier_wait (&b); sleep (2); pthread_kill ((pthread_t) arg, SIGUSR1); return NULL; } static void handler (int s) { } int main (void) { pthread_barrier_init (&b, NULL, 2); struct sockaddr_in sin; pthread_t th; if (pthread_create (&th, NULL, tf, (void *) pthread_self ()) != 0) { puts ("pthread_create failed"); return 1; } int s = socket (AF_INET, SOCK_STREAM, 0); int reuse = 1; setsockopt (s, SOL_SOCKET, SO_REUSEADDR, &reuse, sizeof (reuse)); sin.sin_family = AF_INET; sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK); sin.sin_port = htons (PORT); bind (s, (struct sockaddr *) &sin, sizeof (sin)); listen (s, SOMAXCONN); pthread_barrier_wait (&b); int s2 = paccept (s, NULL, 0, NULL, 0); if (s2 < 0) { puts ("paccept(0) failed"); return 1; } int coe = fcntl (s2, F_GETFD); if (coe & FD_CLOEXEC) { puts ("paccept(0) set close-on-exec-flag"); return 1; } close (s2); pthread_barrier_wait (&b); s2 = paccept (s, NULL, 0, NULL, SOCK_CLOEXEC); if (s2 < 0) { puts ("paccept(SOCK_CLOEXEC) failed"); return 1; } coe = fcntl (s2, F_GETFD); if ((coe & FD_CLOEXEC) == 0) { puts ("paccept(SOCK_CLOEXEC) does not set close-on-exec flag"); return 1; } close (s2); pthread_barrier_wait (&b); struct sigaction sa; sa.sa_handler = handler; sa.sa_flags = 0; sigemptyset (&sa.sa_mask); sigaction (SIGUSR1, &sa, NULL); sigset_t ss; pthread_sigmask (SIG_SETMASK, NULL, &ss); sigaddset (&ss, SIGUSR1); pthread_sigmask (SIG_SETMASK, &ss, NULL); sigdelset (&ss, SIGUSR1); alarm (4); pthread_barrier_wait (&b); errno = 0 ; s2 = paccept (s, NULL, 0, &ss, 0); if (s2 != -1 || errno != EINTR) { puts ("paccept did not fail with EINTR"); return 1; } close (s); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: make it compile] [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: <linux-arch@vger.kernel.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Roland McGrath <roland@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* [NET]: Introducing socket mark socket option.Laszlo Attila Toth2008-01-31
| | | | | | | | | | | | A userspace program may wish to set the mark for each packets its send without using the netfilter MARK target. Changing the mark can be used for mark based routing without netfilter or for packet filtering. It requires CAP_NET_ADMIN capability. Signed-off-by: Laszlo Attila Toth <panther@balabit.hu> Acked-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
* [NET]: Adding SO_TIMESTAMPNS / SCM_TIMESTAMPNS supportEric Dumazet2007-04-26
| | | | | | | | | | | | | | | | | | | | | Now that network timestamps use ktime_t infrastructure, we can add a new SOL_SOCKET sockopt SO_TIMESTAMPNS. This command is similar to SO_TIMESTAMP, but permits transmission of a 'timespec struct' instead of a 'timeval struct' control message. (nanosecond resolution instead of microsecond) Control message is labelled SCM_TIMESTAMPNS instead of SCM_TIMESTAMP A socket cannot mix SO_TIMESTAMP and SO_TIMESTAMPNS : the two modes are mutually exclusive. sock_recv_timestamp() became too big to be fully inlined so I added a __sock_recv_timestamp() helper function. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> CC: linux-arch@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
* [AF_UNIX]: Datagram getpeersecCatherine Zhang2006-06-29
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch implements an API whereby an application can determine the label of its peer's Unix datagram sockets via the auxiliary data mechanism of recvmsg. Patch purpose: This patch enables a security-aware application to retrieve the security context of the peer of a Unix datagram socket. The application can then use this security context to determine the security context for processing on behalf of the peer who sent the packet. Patch design and implementation: The design and implementation is very similar to the UDP case for INET sockets. Basically we build upon the existing Unix domain socket API for retrieving user credentials. Linux offers the API for obtaining user credentials via ancillary messages (i.e., out of band/control messages that are bundled together with a normal message). To retrieve the security context, the application first indicates to the kernel such desire by setting the SO_PASSSEC option via getsockopt. Then the application retrieves the security context using the auxiliary data mechanism. An example server application for Unix datagram socket should look like this: toggle = 1; toggle_len = sizeof(toggle); setsockopt(sockfd, SOL_SOCKET, SO_PASSSEC, &toggle, &toggle_len); recvmsg(sockfd, &msg_hdr, 0); if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) { cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr); if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) && cmsg_hdr->cmsg_level == SOL_SOCKET && cmsg_hdr->cmsg_type == SCM_SECURITY) { memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext)); } } sock_setsockopt is enhanced with a new socket option SOCK_PASSSEC to allow a server socket to receive security context of the peer. Testing: We have tested the patch by setting up Unix datagram client and server applications. We verified that the server can retrieve the security context using the auxiliary data mechanism of recvmsg. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Acked-by: Acked-by: James Morris <jmorris@namei.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* [NET]: Introduce SO_{SND,RCV}BUFFORCE socket optionsPatrick McHardy2005-08-29
| | | | | | | Allows overriding of sysctl_{wmem,rmrm}_max Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
* Linux-2.6.12-rc2v2.6.12-rc2Linus Torvalds2005-04-16
Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
generated by cgit v1.2.2 (git 2.25.0) at 2025-09-16 23:38:29 -0400
apos;t do this for DEBUG_MUTEXES because that relies on wait_lock * to serialize everything. */ for (;;) { struct task_struct *owner; /* * If there's an owner, wait for it to either * release the lock or go to sleep. */ owner = ACCESS_ONCE(lock->owner); if (owner && !mutex_spin_on_owner(lock, owner)) break; if (atomic_cmpxchg(&lock->count, 1, 0) == 1) { lock_acquired(&lock->dep_map, ip); mutex_set_owner(lock); preempt_enable(); return 0; } /* * When there's no owner, we might have preempted between the * owner acquiring the lock and setting the owner field. If * we're an RT task that will live-lock because we won't let * the owner complete. */ if (!owner && (need_resched() || rt_task(task))) break; /* * The cpu_relax() call is a compiler barrier which forces * everything in this loop to be re-loaded. We don't need * memory barriers as we'll eventually observe the right * values at the cost of a few extra spins. */ arch_mutex_cpu_relax(); } #endif spin_lock_mutex(&lock->wait_lock, flags); debug_mutex_lock_common(lock, &waiter); debug_mutex_add_waiter(lock, &waiter, task_thread_info(task)); /* add waiting tasks to the end of the waitqueue (FIFO): */ list_add_tail(&waiter.list, &lock->wait_list); waiter.task = task; if (atomic_xchg(&lock->count, -1) == 1) goto done; lock_contended(&lock->dep_map, ip); for (;;) { /* * Lets try to take the lock again - this is needed even if * we get here for the first time (shortly after failing to * acquire the lock), to make sure that we get a wakeup once * it's unlocked. Later on, if we sleep, this is the * operation that gives us the lock. We xchg it to -1, so * that when we release the lock, we properly wake up the * other waiters: */ if (atomic_xchg(&lock->count, -1) == 1) break; /* * got a signal? (This code gets eliminated in the * TASK_UNINTERRUPTIBLE case.) */ if (unlikely(signal_pending_state(state, task))) { mutex_remove_waiter(lock, &waiter, task_thread_info(task)); mutex_release(&lock->dep_map, 1, ip); spin_unlock_mutex(&lock->wait_lock, flags); debug_mutex_free_waiter(&waiter); preempt_enable(); return -EINTR; } __set_task_state(task, state); /* didn't get the lock, go to sleep: */ spin_unlock_mutex(&lock->wait_lock, flags); preempt_enable_no_resched(); schedule(); preempt_disable(); spin_lock_mutex(&lock->wait_lock, flags); } done: lock_acquired(&lock->dep_map, ip); /* got the lock - rejoice! */ mutex_remove_waiter(lock, &waiter, current_thread_info()); mutex_set_owner(lock); /* set it to 0 if there are no waiters left: */ if (likely(list_empty(&lock->wait_list))) atomic_set(&lock->count, 0); spin_unlock_mutex(&lock->wait_lock, flags); debug_mutex_free_waiter(&waiter); preempt_enable(); return 0; } #ifdef CONFIG_DEBUG_LOCK_ALLOC void __sched mutex_lock_nested(struct mutex *lock, unsigned int subclass) { might_sleep(); __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_); } EXPORT_SYMBOL_GPL(mutex_lock_nested); void __sched _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) { might_sleep(); __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, nest, _RET_IP_); } EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock); int __sched mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass) { might_sleep(); return __mutex_lock_common(lock, TASK_KILLABLE, subclass, NULL, _RET_IP_); } EXPORT_SYMBOL_GPL(mutex_lock_killable_nested); int __sched mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass) { might_sleep(); return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, subclass, NULL, _RET_IP_); } EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested); #endif /* * Release the lock, slowpath: */ static inline void __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested) { struct mutex *lock = container_of(lock_count, struct mutex, count); unsigned long flags; spin_lock_mutex(&lock->wait_lock, flags); mutex_release(&lock->dep_map, nested, _RET_IP_); debug_mutex_unlock(lock); /* * some architectures leave the lock unlocked in the fastpath failure * case, others need to leave it locked. In the later case we have to * unlock it here */ if (__mutex_slowpath_needs_to_unlock()) atomic_set(&lock->count, 1); if (!list_empty(&lock->wait_list)) { /* get the first entry from the wait-list: */ struct mutex_waiter *waiter = list_entry(lock->wait_list.next, struct mutex_waiter, list); debug_mutex_wake_waiter(lock, waiter); wake_up_process(waiter->task); } spin_unlock_mutex(&lock->wait_lock, flags); } /* * Release the lock, slowpath: */ static __used noinline void __mutex_unlock_slowpath(atomic_t *lock_count) { __mutex_unlock_common_slowpath(lock_count, 1); } #ifndef CONFIG_DEBUG_LOCK_ALLOC /* * Here come the less common (and hence less performance-critical) APIs: * mutex_lock_interruptible() and mutex_trylock(). */ static noinline int __sched __mutex_lock_killable_slowpath(atomic_t *lock_count); static noinline int __sched __mutex_lock_interruptible_slowpath(atomic_t *lock_count); /** * mutex_lock_interruptible - acquire the mutex, interruptible * @lock: the mutex to be acquired * * Lock the mutex like mutex_lock(), and return 0 if the mutex has * been acquired or sleep until the mutex becomes available. If a * signal arrives while waiting for the lock then this function * returns -EINTR. * * This function is similar to (but not equivalent to) down_interruptible(). */ int __sched mutex_lock_interruptible(struct mutex *lock) { int ret; might_sleep(); ret = __mutex_fastpath_lock_retval (&lock->count, __mutex_lock_interruptible_slowpath); if (!ret) mutex_set_owner(lock); return ret; } EXPORT_SYMBOL(mutex_lock_interruptible); int __sched mutex_lock_killable(struct mutex *lock) { int ret; might_sleep(); ret = __mutex_fastpath_lock_retval (&lock->count, __mutex_lock_killable_slowpath); if (!ret) mutex_set_owner(lock); return ret; } EXPORT_SYMBOL(mutex_lock_killable); static __used noinline void __sched __mutex_lock_slowpath(atomic_t *lock_count) { struct mutex *lock = container_of(lock_count, struct mutex, count); __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_); } static noinline int __sched __mutex_lock_killable_slowpath(atomic_t *lock_count) { struct mutex *lock = container_of(lock_count, struct mutex, count); return __mutex_lock_common(lock, TASK_KILLABLE, 0, NULL, _RET_IP_); } static noinline int __sched __mutex_lock_interruptible_slowpath(atomic_t *lock_count) { struct mutex *lock = container_of(lock_count, struct mutex, count); return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, NULL, _RET_IP_); } #endif /* * Spinlock based trylock, we take the spinlock and check whether we * can get the lock: */ static inline int __mutex_trylock_slowpath(atomic_t *lock_count) { struct mutex *lock = container_of(lock_count, struct mutex, count); unsigned long flags; int prev; spin_lock_mutex(&lock->wait_lock, flags); prev = atomic_xchg(&lock->count, -1); if (likely(prev == 1)) { mutex_set_owner(lock); mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); } /* Set it back to 0 if there are no waiters: */ if (likely(list_empty(&lock->wait_list))) atomic_set(&lock->count, 0); spin_unlock_mutex(&lock->wait_lock, flags); return prev == 1; } /** * mutex_trylock - try to acquire the mutex, without waiting * @lock: the mutex to be acquired * * Try to acquire the mutex atomically. Returns 1 if the mutex * has been acquired successfully, and 0 on contention. * * NOTE: this function follows the spin_trylock() convention, so * it is negated from the down_trylock() return values! Be careful * about this when converting semaphore users to mutexes. * * This function must not be used in interrupt context. The * mutex must be released by the same task that acquired it. */ int __sched mutex_trylock(struct mutex *lock) { int ret; ret = __mutex_fastpath_trylock(&lock->count, __mutex_trylock_slowpath); if (ret) mutex_set_owner(lock); return ret; } EXPORT_SYMBOL(mutex_trylock); /** * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0 * @cnt: the atomic which we are to dec * @lock: the mutex to return holding if we dec to 0 * * return true and hold lock if we dec to 0, return false otherwise */ int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock) { /* dec if we can't possibly hit 0 */ if (atomic_add_unless(cnt, -1, 1)) return 0; /* we might hit 0, so take the lock */ mutex_lock(lock); if (!atomic_dec_and_test(cnt)) { /* when we actually did the dec, we didn't hit 0 */ mutex_unlock(lock); return 0; } /* we hit 0, and we hold the lock */ return 1; } EXPORT_SYMBOL(atomic_dec_and_mutex_lock);
generated by cgit v1.2.2 (git 2.25.0) at 2025-09-16 23:38:25 -0400