linux_close.c 10.3 KB
Newer Older
D
duke 已提交
1
/*
X
xdono 已提交
2
 * Copyright 2001-2008 Sun Microsystems, Inc.  All Rights Reserved.
D
duke 已提交
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
 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
 *
 * This code is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 only, as
 * published by the Free Software Foundation.  Sun designates this
 * particular file as subject to the "Classpath" exception as provided
 * by Sun in the LICENSE file that accompanied this code.
 *
 * This code 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 General Public License
 * version 2 for more details (a copy is included in the LICENSE file that
 * accompanied this code).
 *
 * You should have received a copy of the GNU General Public License version
 * 2 along with this work; if not, write to the Free Software Foundation,
 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
 *
 * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
 * CA 95054 USA or visit www.sun.com if you need additional information or
 * have any questions.
 */

#include <stdio.h>
#include <stdlib.h>
#include <signal.h>
#include <pthread.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <sys/uio.h>
#include <unistd.h>
#include <errno.h>

#include <sys/poll.h>

/*
 * Stack allocated by thread when doing blocking operation
 */
typedef struct threadEntry {
    pthread_t thr;                      /* this thread */
    struct threadEntry *next;           /* next thread */
    int intr;                           /* interrupted */
} threadEntry_t;

/*
 * Heap allocated during initialized - one entry per fd
 */
typedef struct {
    pthread_mutex_t lock;               /* fd lock */
    threadEntry_t *threads;             /* threads blocked on fd */
} fdEntry_t;

/*
 * Signal to unblock thread
 */
static int sigWakeup = (__SIGRTMAX - 2);

/*
 * The fd table and the number of file descriptors
 */
static fdEntry_t *fdTable;
static int fdCount;

/*
 * Null signal handler
 */
static void sig_wakeup(int sig) {
}

/*
 * Initialization routine (executed when library is loaded)
 * Allocate fd tables and sets up signal handler.
 */
static void __attribute((constructor)) init() {
    struct rlimit nbr_files;
    sigset_t sigset;
    struct sigaction sa;

    /*
     * Allocate table based on the maximum number of
     * file descriptors.
     */
    getrlimit(RLIMIT_NOFILE, &nbr_files);
    fdCount = nbr_files.rlim_max;
    fdTable = (fdEntry_t *)calloc(fdCount, sizeof(fdEntry_t));
    if (fdTable == NULL) {
        fprintf(stderr, "library initialization failed - "
                "unable to allocate file descriptor table - out of memory");
        abort();
    }

    /*
     * Setup the signal handler
     */
    sa.sa_handler = sig_wakeup;
    sa.sa_flags   = 0;
    sigemptyset(&sa.sa_mask);
    sigaction(sigWakeup, &sa, NULL);

    sigemptyset(&sigset);
    sigaddset(&sigset, sigWakeup);
    sigprocmask(SIG_UNBLOCK, &sigset, NULL);
}

/*
 * Return the fd table for this fd or NULL is fd out
 * of range.
 */
static inline fdEntry_t *getFdEntry(int fd)
{
    if (fd < 0 || fd > fdCount) {
        return NULL;
    }
    return &fdTable[fd];
}

/*
 * Start a blocking operation :-
 *    Insert thread onto thread list for the fd.
 */
static inline void startOp(fdEntry_t *fdEntry, threadEntry_t *self)
{
    self->thr = pthread_self();
    self->intr = 0;

    pthread_mutex_lock(&(fdEntry->lock));
    {
        self->next = fdEntry->threads;
        fdEntry->threads = self;
    }
    pthread_mutex_unlock(&(fdEntry->lock));
}

/*
 * End a blocking operation :-
 *     Remove thread from thread list for the fd
 *     If fd has been interrupted then set errno to EBADF
 */
static inline void endOp
    (fdEntry_t *fdEntry, threadEntry_t *self)
{
    int orig_errno = errno;
    pthread_mutex_lock(&(fdEntry->lock));
    {
        threadEntry_t *curr, *prev=NULL;
        curr = fdEntry->threads;
        while (curr != NULL) {
            if (curr == self) {
                if (curr->intr) {
                    orig_errno = EBADF;
                }
                if (prev == NULL) {
                    fdEntry->threads = curr->next;
                } else {
                    prev->next = curr->next;
                }
                break;
            }
            prev = curr;
            curr = curr->next;
        }
    }
    pthread_mutex_unlock(&(fdEntry->lock));
    errno = orig_errno;
}

/*
 * Close or dup2 a file descriptor ensuring that all threads blocked on
 * the file descriptor are notified via a wakeup signal.
 *
 *      fd1 < 0    => close(fd2)
 *      fd1 >= 0   => dup2(fd1, fd2)
 *
 * Returns -1 with errno set if operation fails.
 */
static int closefd(int fd1, int fd2) {
    int rv, orig_errno;
    fdEntry_t *fdEntry = getFdEntry(fd2);
    if (fdEntry == NULL) {
        errno = EBADF;
        return -1;
    }

    /*
     * Lock the fd to hold-off additional I/O on this fd.
     */
    pthread_mutex_lock(&(fdEntry->lock));

    {
        /*
         * Send a wakeup signal to all threads blocked on this
         * file descriptor.
         */
        threadEntry_t *curr = fdEntry->threads;
        while (curr != NULL) {
            curr->intr = 1;
            pthread_kill( curr->thr, sigWakeup );
            curr = curr->next;
        }

        /*
         * And close/dup the file descriptor
         * (restart if interrupted by signal)
         */
        do {
            if (fd1 < 0) {
                rv = close(fd2);
            } else {
                rv = dup2(fd1, fd2);
            }
        } while (rv == -1 && errno == EINTR);

    }

    /*
     * Unlock without destroying errno
     */
    orig_errno = errno;
    pthread_mutex_unlock(&(fdEntry->lock));
    errno = orig_errno;

    return rv;
}

/*
 * Wrapper for dup2 - same semantics as dup2 system call except
 * that any threads blocked in an I/O system call on fd2 will be
 * preempted and return -1/EBADF;
 */
int NET_Dup2(int fd, int fd2) {
    if (fd < 0) {
        errno = EBADF;
        return -1;
    }
    return closefd(fd, fd2);
}

/*
 * Wrapper for close - same semantics as close system call
 * except that any threads blocked in an I/O on fd will be
 * preempted and the I/O system call will return -1/EBADF.
 */
int NET_SocketClose(int fd) {
    return closefd(-1, fd);
}

/************** Basic I/O operations here ***************/

/*
 * Macro to perform a blocking IO operation. Restarts
 * automatically if interrupted by signal (other than
 * our wakeup signal)
 */
#define BLOCKING_IO_RETURN_INT(FD, FUNC) {      \
    int ret;                                    \
    threadEntry_t self;                         \
    fdEntry_t *fdEntry = getFdEntry(FD);        \
    if (fdEntry == NULL) {                      \
        errno = EBADF;                          \
        return -1;                              \
    }                                           \
    do {                                        \
        startOp(fdEntry, &self);                \
        ret = FUNC;                             \
        endOp(fdEntry, &self);                  \
    } while (ret == -1 && errno == EINTR);      \
    return ret;                                 \
}

int NET_Read(int s, void* buf, size_t len) {
    BLOCKING_IO_RETURN_INT( s, recv(s, buf, len, 0) );
}

int NET_ReadV(int s, const struct iovec * vector, int count) {
    BLOCKING_IO_RETURN_INT( s, readv(s, vector, count) );
}

int NET_RecvFrom(int s, void *buf, int len, unsigned int flags,
       struct sockaddr *from, int *fromlen) {
284 285 286
    socklen_t socklen = *fromlen;
    BLOCKING_IO_RETURN_INT( s, recvfrom(s, buf, len, flags, from, &socklen) );
    *fromlen = socklen;
D
duke 已提交
287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302
}

int NET_Send(int s, void *msg, int len, unsigned int flags) {
    BLOCKING_IO_RETURN_INT( s, send(s, msg, len, flags) );
}

int NET_WriteV(int s, const struct iovec * vector, int count) {
    BLOCKING_IO_RETURN_INT( s, writev(s, vector, count) );
}

int NET_SendTo(int s, const void *msg, int len,  unsigned  int
       flags, const struct sockaddr *to, int tolen) {
    BLOCKING_IO_RETURN_INT( s, sendto(s, msg, len, flags, to, tolen) );
}

int NET_Accept(int s, struct sockaddr *addr, int *addrlen) {
303 304 305
    socklen_t socklen = *addrlen;
    BLOCKING_IO_RETURN_INT( s, accept(s, addr, &socklen) );
    *addrlen = socklen;
D
duke 已提交
306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329
}

int NET_Connect(int s, struct sockaddr *addr, int addrlen) {
    BLOCKING_IO_RETURN_INT( s, connect(s, addr, addrlen) );
}

#ifndef USE_SELECT
int NET_Poll(struct pollfd *ufds, unsigned int nfds, int timeout) {
    BLOCKING_IO_RETURN_INT( ufds[0].fd, poll(ufds, nfds, timeout) );
}
#else
int NET_Select(int s, fd_set *readfds, fd_set *writefds,
               fd_set *exceptfds, struct timeval *timeout) {
    BLOCKING_IO_RETURN_INT( s-1,
                            select(s, readfds, writefds, exceptfds, timeout) );
}
#endif

/*
 * Wrapper for poll(s, timeout).
 * Auto restarts with adjusted timeout if interrupted by
 * signal other than our wakeup signal.
 */
int NET_Timeout(int s, long timeout) {
330
    long prevtime = 0, newtime;
D
duke 已提交
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
    struct timeval t;
    fdEntry_t *fdEntry = getFdEntry(s);

    /*
     * Check that fd hasn't been closed.
     */
    if (fdEntry == NULL) {
        errno = EBADF;
        return -1;
    }

    /*
     * Pick up current time as may need to adjust timeout
     */
    if (timeout > 0) {
        gettimeofday(&t, NULL);
        prevtime = t.tv_sec * 1000  +  t.tv_usec / 1000;
    }

    for(;;) {
        struct pollfd pfd;
        int rv;
        threadEntry_t self;

        /*
         * Poll the fd. If interrupted by our wakeup signal
         * errno will be set to EBADF.
         */
        pfd.fd = s;
        pfd.events = POLLIN | POLLERR;

        startOp(fdEntry, &self);
        rv = poll(&pfd, 1, timeout);
        endOp(fdEntry, &self);

        /*
         * If interrupted then adjust timeout. If timeout
         * has expired return 0 (indicating timeout expired).
         */
        if (rv < 0 && errno == EINTR) {
            if (timeout > 0) {
                gettimeofday(&t, NULL);
                newtime = t.tv_sec * 1000  +  t.tv_usec / 1000;
                timeout -= newtime - prevtime;
                if (timeout <= 0) {
                    return 0;
                }
                prevtime = newtime;
            }
        } else {
            return rv;
        }

    }
}