• Olaf Mandel's avatar
    Remove duplicate poller decision making · 48b50cef
    Olaf Mandel authored
    The decision about the poller mechanism to use (select, poll, ...)
    was done twice: once by the build system and once by the code in
    poller.hpp. As the build-system can actually detect the mechanisms
    available, prefer that result to the hard coded defaults in
    poller.hpp.
    
    At the same time, remove the duplicate detection of select() vs.
    poll()-variant from proxy.cpp, signaler.cpp and zmq.cpp.
    
    This patch has not been tested on many build platforms: especially
    the cmake build needs testing / patching. For the other builds,
    hard code the result as these these are all Windows platforms.
    48b50cef
signaler.cpp 14.3 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503
/*
    Copyright (c) 2007-2014 Contributors as noted in the AUTHORS file

    This file is part of 0MQ.

    0MQ is free software; you can redistribute it and/or modify it under
    the terms of the GNU Lesser General Public License as published by
    the Free Software Foundation; either version 3 of the License, or
    (at your option) any later version.

    0MQ is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    GNU Lesser General Public License for more details.

    You should have received a copy of the GNU Lesser General Public License
    along with this program.  If not, see <http://www.gnu.org/licenses/>.
*/

#include "poller.hpp"

//  On AIX, poll.h has to be included before zmq.h to get consistent
//  definition of pollfd structure (AIX uses 'reqevents' and 'retnevents'
//  instead of 'events' and 'revents' and defines macros to map from POSIX-y
//  names to AIX-specific names).
#if defined ZMQ_POLL_BASED_ON_POLL
#include <poll.h>
#elif defined ZMQ_POLL_BASED_ON_SELECT
#if defined ZMQ_HAVE_WINDOWS
#include "windows.hpp"
#elif defined ZMQ_HAVE_HPUX
#include <sys/param.h>
#include <sys/types.h>
#include <sys/time.h>
#elif defined ZMQ_HAVE_OPENVMS
#include <sys/types.h>
#include <sys/time.h>
#else
#include <sys/select.h>
#endif
#endif

#include "signaler.hpp"
#include "likely.hpp"
#include "stdint.hpp"
#include "config.hpp"
#include "err.hpp"
#include "fd.hpp"
#include "ip.hpp"

#if defined ZMQ_HAVE_EVENTFD
#include <sys/eventfd.h>
#endif

#if defined ZMQ_HAVE_WINDOWS
#include "windows.hpp"
#include <tchar.h>
#else
#include <unistd.h>
#include <netinet/tcp.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/socket.h>
#endif

zmq::signaler_t::signaler_t ()
{
    //  Create the socketpair for signaling.
    if (make_fdpair (&r, &w) == 0) {
        unblock_socket (w);
        unblock_socket (r);
    }
#ifdef HAVE_FORK
    pid = getpid();
#endif
}

zmq::signaler_t::~signaler_t ()
{
#if defined ZMQ_HAVE_EVENTFD
    int rc = close (r);
    errno_assert (rc == 0);
#elif defined ZMQ_HAVE_WINDOWS
    struct linger so_linger = { 1, 0 };
    int rc = setsockopt (w, SOL_SOCKET, SO_LINGER,
        (char *)&so_linger, sizeof (so_linger));
    wsa_assert (rc != SOCKET_ERROR);
    rc = closesocket (w);
    wsa_assert (rc != SOCKET_ERROR);
    rc = closesocket (r);
    wsa_assert (rc != SOCKET_ERROR);
#else
    int rc = close (w);
    errno_assert (rc == 0);
    rc = close (r);
    errno_assert (rc == 0);
#endif
}

zmq::fd_t zmq::signaler_t::get_fd ()
{
    return r;
}

void zmq::signaler_t::send ()
{
#if HAVE_FORK
    if (unlikely(pid != getpid())) {
        //printf("Child process %d signaler_t::send returning without sending #1\n", getpid());
        return; // do not send anything in forked child context
    }
#endif
#if defined ZMQ_HAVE_EVENTFD
    const uint64_t inc = 1;
    ssize_t sz = write (w, &inc, sizeof (inc));
    errno_assert (sz == sizeof (inc));
#elif defined ZMQ_HAVE_WINDOWS
    unsigned char dummy = 0;
    int nbytes = ::send (w, (char*) &dummy, sizeof (dummy), 0);
    wsa_assert (nbytes != SOCKET_ERROR);
    zmq_assert (nbytes == sizeof (dummy));
#else
    unsigned char dummy = 0;
    while (true) {
        ssize_t nbytes = ::send (w, &dummy, sizeof (dummy), 0);
        if (unlikely (nbytes == -1 && errno == EINTR))
            continue;
#if HAVE_FORK
        if (unlikely(pid != getpid())) {
            //printf("Child process %d signaler_t::send returning without sending #2\n", getpid());
            errno = EINTR;
            break;
        }
#endif
        zmq_assert (nbytes == sizeof (dummy));
        break;
    }
#endif
}

int zmq::signaler_t::wait (int timeout_)
{
#ifdef HAVE_FORK
    if (unlikely(pid != getpid()))
    {
        // we have forked and the file descriptor is closed. Emulate an interupt
        // response.
        //printf("Child process %d signaler_t::wait returning simulating interrupt #1\n", getpid());
        errno = EINTR;
        return -1;
    }
#endif

#ifdef ZMQ_POLL_BASED_ON_POLL

    struct pollfd pfd;
    pfd.fd = r;
    pfd.events = POLLIN;
    int rc = poll (&pfd, 1, timeout_);
    if (unlikely (rc < 0)) {
        errno_assert (errno == EINTR);
        return -1;
    }
    else
    if (unlikely (rc == 0)) {
        errno = EAGAIN;
        return -1;
    }
#ifdef HAVE_FORK
    if (unlikely(pid != getpid())) {
        // we have forked and the file descriptor is closed. Emulate an interupt
        // response.
        //printf("Child process %d signaler_t::wait returning simulating interrupt #2\n", getpid());
        errno = EINTR;
        return -1;
    }
#endif
    zmq_assert (rc == 1);
    zmq_assert (pfd.revents & POLLIN);
    return 0;

#elif defined ZMQ_POLL_BASED_ON_SELECT

    fd_set fds;
    FD_ZERO (&fds);
    FD_SET (r, &fds);
    struct timeval timeout;
    if (timeout_ >= 0) {
        timeout.tv_sec = timeout_ / 1000;
        timeout.tv_usec = timeout_ % 1000 * 1000;
    }
#ifdef ZMQ_HAVE_WINDOWS
    int rc = select (0, &fds, NULL, NULL,
        timeout_ >= 0 ? &timeout : NULL);
    wsa_assert (rc != SOCKET_ERROR);
#else
    int rc = select (r + 1, &fds, NULL, NULL,
        timeout_ >= 0 ? &timeout : NULL);
    if (unlikely (rc < 0)) {
        errno_assert (errno == EINTR);
        return -1;
    }
#endif
    if (unlikely (rc == 0)) {
        errno = EAGAIN;
        return -1;
    }
    zmq_assert (rc == 1);
    return 0;

#else
#error
#endif
}

void zmq::signaler_t::recv ()
{
    //  Attempt to read a signal.
#if defined ZMQ_HAVE_EVENTFD
    uint64_t dummy;
    ssize_t sz = read (r, &dummy, sizeof (dummy));
    errno_assert (sz == sizeof (dummy));

    //  If we accidentally grabbed the next signal along with the current
    //  one, return it back to the eventfd object.
    if (unlikely (dummy == 2)) {
        const uint64_t inc = 1;
        ssize_t sz2 = write (w, &inc, sizeof (inc));
        errno_assert (sz2 == sizeof (inc));
        return;
    }

    zmq_assert (dummy == 1);
#else
    unsigned char dummy;
#if defined ZMQ_HAVE_WINDOWS
    int nbytes = ::recv (r, (char*) &dummy, sizeof (dummy), 0);
    wsa_assert (nbytes != SOCKET_ERROR);
#else
    ssize_t nbytes = ::recv (r, &dummy, sizeof (dummy), 0);
    errno_assert (nbytes >= 0);
#endif
    zmq_assert (nbytes == sizeof (dummy));
    zmq_assert (dummy == 0);
#endif
}

#ifdef HAVE_FORK
void zmq::signaler_t::forked()
{
    //  Close file descriptors created in the parent and create new pair
    close (r);
    close (w);
    make_fdpair (&r, &w);
}
#endif

//  Returns -1 if we could not make the socket pair successfully
int zmq::signaler_t::make_fdpair (fd_t *r_, fd_t *w_)
{
#if defined ZMQ_HAVE_EVENTFD
    fd_t fd = eventfd (0, 0);
    if (fd == -1) {
        errno_assert (errno == ENFILE || errno == EMFILE);
        *w_ = *r_ = -1;
        return -1;
    }
    else {
        *w_ = *r_ = fd;
        return 0;
    }

#elif defined ZMQ_HAVE_WINDOWS
#   if !defined _WIN32_WCE
    // Windows CE does not manage security attributes
    SECURITY_DESCRIPTOR sd;
    SECURITY_ATTRIBUTES sa;
    memset (&sd, 0, sizeof (sd));
    memset (&sa, 0, sizeof (sa));

    InitializeSecurityDescriptor(&sd, SECURITY_DESCRIPTOR_REVISION);
    SetSecurityDescriptorDacl(&sd, TRUE, 0, FALSE);

    sa.nLength = sizeof(SECURITY_ATTRIBUTES);
    sa.lpSecurityDescriptor = &sd;
#   endif

    //  This function has to be in a system-wide critical section so that
    //  two instances of the library don't accidentally create signaler
    //  crossing the process boundary.
    //  We'll use named event object to implement the critical section.
    //  Note that if the event object already exists, the CreateEvent requests
    //  EVENT_ALL_ACCESS access right. If this fails, we try to open
    //  the event object asking for SYNCHRONIZE access only.
    HANDLE sync = NULL;

    //  Create critical section only if using fixed signaler port
    //  Use problematic Event implementation for compatibility if using old port 5905.
    //  Otherwise use Mutex implementation.
    int event_signaler_port = 5905;

    if (signaler_port == event_signaler_port) {
#       if !defined _WIN32_WCE
        sync = CreateEvent (&sa, FALSE, TRUE, TEXT ("Global\\zmq-signaler-port-sync"));
#       else
        sync = CreateEvent (NULL, FALSE, TRUE, TEXT ("Global\\zmq-signaler-port-sync"));
#       endif
        if (sync == NULL && GetLastError () == ERROR_ACCESS_DENIED)
            sync = OpenEvent (SYNCHRONIZE | EVENT_MODIFY_STATE,
                              FALSE, TEXT ("Global\\zmq-signaler-port-sync"));

        win_assert (sync != NULL);
    }
    else if (signaler_port != 0) {
        TCHAR mutex_name[64];
        _stprintf (mutex_name, TEXT ("Global\\zmq-signaler-port-%d"), signaler_port);

#       if !defined _WIN32_WCE
        sync = CreateMutex (&sa, FALSE, mutex_name);
#       else
        sync = CreateMutex (NULL, FALSE, mutex_name);
#       endif
        if (sync == NULL && GetLastError () == ERROR_ACCESS_DENIED)
            sync = OpenMutex (SYNCHRONIZE, FALSE, mutex_name);

        win_assert (sync != NULL);
    }

    //  Windows has no 'socketpair' function. CreatePipe is no good as pipe
    //  handles cannot be polled on. Here we create the socketpair by hand.
    *w_ = INVALID_SOCKET;
    *r_ = INVALID_SOCKET;

    //  Create listening socket.
    SOCKET listener;
    listener = open_socket (AF_INET, SOCK_STREAM, 0);
    wsa_assert (listener != INVALID_SOCKET);

    //  Set SO_REUSEADDR and TCP_NODELAY on listening socket.
    BOOL so_reuseaddr = 1;
    int rc = setsockopt (listener, SOL_SOCKET, SO_REUSEADDR,
        (char *)&so_reuseaddr, sizeof (so_reuseaddr));
    wsa_assert (rc != SOCKET_ERROR);
    BOOL tcp_nodelay = 1;
    rc = setsockopt (listener, IPPROTO_TCP, TCP_NODELAY,
        (char *)&tcp_nodelay, sizeof (tcp_nodelay));
    wsa_assert (rc != SOCKET_ERROR);

    //  Init sockaddr to signaler port.
    struct sockaddr_in addr;
    memset (&addr, 0, sizeof (addr));
    addr.sin_family = AF_INET;
    addr.sin_addr.s_addr = htonl (INADDR_LOOPBACK);
    addr.sin_port = htons (signaler_port);

    //  Create the writer socket.
    *w_ = open_socket (AF_INET, SOCK_STREAM, 0);
    wsa_assert (*w_ != INVALID_SOCKET);

    //  Set TCP_NODELAY on writer socket.
    rc = setsockopt (*w_, IPPROTO_TCP, TCP_NODELAY,
        (char *)&tcp_nodelay, sizeof (tcp_nodelay));
    wsa_assert (rc != SOCKET_ERROR);

    if (sync != NULL) {
        //  Enter the critical section.
        DWORD dwrc = WaitForSingleObject (sync, INFINITE);
        zmq_assert (dwrc == WAIT_OBJECT_0 || dwrc == WAIT_ABANDONED);
    }

    //  Bind listening socket to signaler port.
    rc = bind (listener, (const struct sockaddr*) &addr, sizeof (addr));

    if (rc != SOCKET_ERROR && signaler_port == 0) {
        //  Retrieve ephemeral port number
        int addrlen = sizeof (addr);
        rc = getsockname (listener, (struct sockaddr*) &addr, &addrlen);
    }

    //  Listen for incoming connections.
    if (rc != SOCKET_ERROR)
        rc = listen (listener, 1);

    //  Connect writer to the listener.
    if (rc != SOCKET_ERROR)
        rc = connect (*w_, (struct sockaddr*) &addr, sizeof (addr));

    //  Accept connection from writer.
    if (rc != SOCKET_ERROR)
        *r_ = accept (listener, NULL, NULL);

    //  Save errno if error occurred in bind/listen/connect/accept.
    int saved_errno = 0;
    if (*r_ == INVALID_SOCKET)
        saved_errno = WSAGetLastError ();

    //  We don't need the listening socket anymore. Close it.
    closesocket (listener);

    if (sync != NULL) {
        //  Exit the critical section.
        BOOL brc;
        if (signaler_port == event_signaler_port)
            brc = SetEvent (sync);
        else
            brc = ReleaseMutex (sync);
        win_assert (brc != 0);

        //  Release the kernel object
        brc = CloseHandle (sync);
        win_assert (brc != 0);
    }

    if (*r_ != INVALID_SOCKET) {
#   if !defined _WIN32_WCE
        //  On Windows, preventing sockets to be inherited by child processes.
        BOOL brc = SetHandleInformation ((HANDLE) *r_, HANDLE_FLAG_INHERIT, 0);
        win_assert (brc);
#   endif
        return 0;
    }
    else {
        //  Cleanup writer if connection failed
        if (*w_ != INVALID_SOCKET) {
            rc = closesocket (*w_);
            wsa_assert (rc != SOCKET_ERROR);
            *w_ = INVALID_SOCKET;
        }
        //  Set errno from saved value
        errno = wsa_error_to_errno (saved_errno);
        return -1;
    }

#elif defined ZMQ_HAVE_OPENVMS

    //  Whilst OpenVMS supports socketpair - it maps to AF_INET only.  Further,
    //  it does not set the socket options TCP_NODELAY and TCP_NODELACK which
    //  can lead to performance problems.
    //
    //  The bug will be fixed in V5.6 ECO4 and beyond.  In the meantime, we'll
    //  create the socket pair manually.
    struct sockaddr_in lcladdr;
    memset (&lcladdr, 0, sizeof (lcladdr));
    lcladdr.sin_family = AF_INET;
    lcladdr.sin_addr.s_addr = htonl (INADDR_LOOPBACK);
    lcladdr.sin_port = 0;

    int listener = open_socket (AF_INET, SOCK_STREAM, 0);
    errno_assert (listener != -1);

    int on = 1;
    int rc = setsockopt (listener, IPPROTO_TCP, TCP_NODELAY, &on, sizeof (on));
    errno_assert (rc != -1);

    rc = setsockopt (listener, IPPROTO_TCP, TCP_NODELACK, &on, sizeof (on));
    errno_assert (rc != -1);

    rc = bind (listener, (struct sockaddr*) &lcladdr, sizeof (lcladdr));
    errno_assert (rc != -1);

    socklen_t lcladdr_len = sizeof (lcladdr);

    rc = getsockname (listener, (struct sockaddr*) &lcladdr, &lcladdr_len);
    errno_assert (rc != -1);

    rc = listen (listener, 1);
    errno_assert (rc != -1);

    *w_ = open_socket (AF_INET, SOCK_STREAM, 0);
    errno_assert (*w_ != -1);

    rc = setsockopt (*w_, IPPROTO_TCP, TCP_NODELAY, &on, sizeof (on));
    errno_assert (rc != -1);

    rc = setsockopt (*w_, IPPROTO_TCP, TCP_NODELACK, &on, sizeof (on));
    errno_assert (rc != -1);

    rc = connect (*w_, (struct sockaddr*) &lcladdr, sizeof (lcladdr));
    errno_assert (rc != -1);

    *r_ = accept (listener, NULL, NULL);
    errno_assert (*r_ != -1);

    close (listener);

    return 0;

#else
    // All other implementations support socketpair()
    int sv [2];
    int rc = socketpair (AF_UNIX, SOCK_STREAM, 0, sv);
    if (rc == -1) {
        errno_assert (errno == ENFILE || errno == EMFILE);
        *w_ = *r_ = -1;
        return -1;
    }
    else {
        *w_ = sv [0];
        *r_ = sv [1];
        return 0;
    }
#endif
}