49

是否有一种可移植的方式(POSIX)来获取当前进程的最高分配文件描述符编号?

例如,我知道有一种在 AIX 上获取号码的好方法,但我正在寻找一种可移植的方法。

我问的原因是我想关闭所有打开的文件描述符。我的程序是一个服务器,它以 root 身份运行,并为非 root 用户分叉和执行子程序。让特权文件描述符在子进程中打开是一个安全问题。一些文件描述符可能被我无法控制的代码(C 库、第三方库等)打开,所以我不能依赖FD_CLOEXEC任何一个。

4

6 回答 6

70

虽然可移植,但关闭所有文件描述符sysconf(_SC_OPEN_MAX)并不可靠,因为在大多数系统上,此调用返回当前文件描述符软限制,该限制可能已低于使用的最高文件描述符。另一个问题是在许多系统上sysconf(_SC_OPEN_MAX)可能会返回INT_MAX,这可能会导致这种方法速度慢得令人无法接受。不幸的是,没有可靠的、可移植的替代方案不涉及迭代每个可能的非负 int 文件描述符。

尽管不可移植,但当今常用的大多数操作系统都提供了以下一种或多种解决方案来解决此问题:

  1. 关闭所有打开的文件描述符>= fd或在一个范围内的库函数。对于关闭所有文件描述符的常见情况,这是最简单的解决方案,尽管它不能用于其他很多情况。要关闭除特定集合之外的所有文件描述符,dup2可用于预先将它们移动到低端,并在必要时将它们向后移动。

    • closefrom(fd) (Linux 与 glibc 2.34+、Solaris 9+、FreeBSD 7.3+、NetBSD 3.0+、OpenBSD 3.5+)

    • fcntl(fd, F_CLOSEM, 0) (AIX、IRIX、NetBSD)

    • close_range(lowfd, highfd, 0) (Linux 内核 5.9+ 和 glibc 2.34+,FreeBSD 12.2+)

  2. 提供进程当前使用的最大文件描述符的库函数。要关闭某个数量以上的所有文件描述符,要么将它们全部关闭到此最大值,要么在循环中不断获取并关闭最高文件描述符,直到达到下限。哪个更有效取决于文件描述符密度。

    • fcntl(0, F_MAXFD) (NetBSD)

    • pstat_getproc(&ps, sizeof(struct pst_status), (size_t)0, (int)getpid())
      返回有关进程的信息,包括当前在 中打开的最高文件描述符ps.pst_highestfd。(HP-UX)

  3. 列出进程当前使用的所有文件描述符的库函数。这更灵活,因为它允许关闭所有文件描述符,查找最高文件描述符,或者对每个打开的文件描述符执行任何其他操作,甚至可能是另一个进程的描述符。 示例(OpenSSH)

    • proc_pidinfo(getpid(), PROC_PIDLISTFDS, 0, fdinfo_buf, sz) (苹果系统)
  4. 当前为进程分配的文件描述符插槽数提供了当前使用的文件描述符数的上限。 示例(红宝石)

    • /proc/pid/status/proc/self/status (Linux)中的“FDSize:”行
  5. 包含每个打开文件描述符的条目的目录。这类似于#3,只是它不是库函数。对于常见用途,这可能比其他方法更复杂,并且可能由于各种原因而失败,例如未安装 proc/fdescfs、chroot 环境或没有可用于打开目录的文件描述符(进程或系统限制)。因此,这种方法的使用通常与回退机制结合使用。 示例(OpenSSH)另一个示例(glib)

    • /proc/pid/fd//proc/self/fd/ (Linux、Solaris、AIX、Cygwin、NetBSD)
      (AIX 不支持“ self”)

    • /dev/fd/ (FreeBSD, macOS)

使用这种方法可能难以可靠地处理所有极端情况。例如考虑关闭所有文件描述符 >= fd的情况,但是所有文件描述符 < fd都被使用,当前进程资源限制为fd,并且有文件描述符 >= fd正在使用中。由于已达到进程资源限制,无法打开目录。如果通过资源限制从fd关闭每个文件描述符或sysconf(_SC_OPEN_MAX)用作后备,则不会关闭任何内容。

于 2009-05-27T23:25:07.737 回答
13

POSIX方式是:

int maxfd=sysconf(_SC_OPEN_MAX);
for(int fd=3; fd<maxfd; fd++)
    close(fd);

(注意从 3 开始关闭,以保持标准输入/标准输出/标准错误打开)

如果文件描述符未打开,close() 会无害地返回 EBADF。没有必要浪费另一个系统调用检查。

一些 Unix 支持 closefrom()。这避免了对 close() 的过多调用,具体取决于最大可能的文件描述符数。虽然我知道最好的解决方案,但它是完全不可移植的。

于 2009-05-22T19:15:58.133 回答
6

我编写了代码来处理所有特定于平台的功能。所有功能都是异步信号安全的。认为人们可能会发现这很有用。目前仅在 OS X 上测试,请随时改进/修复。

// Async-signal safe way to get the current process's hard file descriptor limit.
static int
getFileDescriptorLimit() {
    long long sysconfResult = sysconf(_SC_OPEN_MAX);

    struct rlimit rl;
    long long rlimitResult;
    if (getrlimit(RLIMIT_NOFILE, &rl) == -1) {
        rlimitResult = 0;
    } else {
        rlimitResult = (long long) rl.rlim_max;
    }

    long result;
    if (sysconfResult > rlimitResult) {
        result = sysconfResult;
    } else {
        result = rlimitResult;
    }
    if (result < 0) {
        // Both calls returned errors.
        result = 9999;
    } else if (result < 2) {
        // The calls reported broken values.
        result = 2;
    }
    return result;
}

// Async-signal safe function to get the highest file
// descriptor that the process is currently using.
// See also http://stackoverflow.com/questions/899038/getting-the-highest-allocated-file-descriptor
static int
getHighestFileDescriptor() {
#if defined(F_MAXFD)
    int ret;

    do {
        ret = fcntl(0, F_MAXFD);
    } while (ret == -1 && errno == EINTR);
    if (ret == -1) {
        ret = getFileDescriptorLimit();
    }
    return ret;

#else
    int p[2], ret, flags;
    pid_t pid = -1;
    int result = -1;

    /* Since opendir() may not be async signal safe and thus may lock up
     * or crash, we use it in a child process which we kill if we notice
     * that things are going wrong.
     */

    // Make a pipe.
    p[0] = p[1] = -1;
    do {
        ret = pipe(p);
    } while (ret == -1 && errno == EINTR);
    if (ret == -1) {
        goto done;
    }

    // Make the read side non-blocking.
    do {
        flags = fcntl(p[0], F_GETFL);
    } while (flags == -1 && errno == EINTR);
    if (flags == -1) {
        goto done;
    }
    do {
        fcntl(p[0], F_SETFL, flags | O_NONBLOCK);
    } while (ret == -1 && errno == EINTR);
    if (ret == -1) {
        goto done;
    }

    do {
        pid = fork();
    } while (pid == -1 && errno == EINTR);

    if (pid == 0) {
        // Don't close p[0] here or it might affect the result.

        resetSignalHandlersAndMask();

        struct sigaction action;
        action.sa_handler = _exit;
        action.sa_flags   = SA_RESTART;
        sigemptyset(&action.sa_mask);
        sigaction(SIGSEGV, &action, NULL);
        sigaction(SIGPIPE, &action, NULL);
        sigaction(SIGBUS, &action, NULL);
        sigaction(SIGILL, &action, NULL);
        sigaction(SIGFPE, &action, NULL);
        sigaction(SIGABRT, &action, NULL);

        DIR *dir = NULL;
        #ifdef __APPLE__
            /* /dev/fd can always be trusted on OS X. */
            dir = opendir("/dev/fd");
        #else
            /* On FreeBSD and possibly other operating systems, /dev/fd only
             * works if fdescfs is mounted. If it isn't mounted then /dev/fd
             * still exists but always returns [0, 1, 2] and thus can't be
             * trusted. If /dev and /dev/fd are on different filesystems
             * then that probably means fdescfs is mounted.
             */
            struct stat dirbuf1, dirbuf2;
            if (stat("/dev", &dirbuf1) == -1
             || stat("/dev/fd", &dirbuf2) == -1) {
                _exit(1);
            }
            if (dirbuf1.st_dev != dirbuf2.st_dev) {
                dir = opendir("/dev/fd");
            }
        #endif
        if (dir == NULL) {
            dir = opendir("/proc/self/fd");
            if (dir == NULL) {
                _exit(1);
            }
        }

        struct dirent *ent;
        union {
            int highest;
            char data[sizeof(int)];
        } u;
        u.highest = -1;

        while ((ent = readdir(dir)) != NULL) {
            if (ent->d_name[0] != '.') {
                int number = atoi(ent->d_name);
                if (number > u.highest) {
                    u.highest = number;
                }
            }
        }
        if (u.highest != -1) {
            ssize_t ret, written = 0;
            do {
                ret = write(p[1], u.data + written, sizeof(int) - written);
                if (ret == -1) {
                    _exit(1);
                }
                written += ret;
            } while (written < (ssize_t) sizeof(int));
        }
        closedir(dir);
        _exit(0);

    } else if (pid == -1) {
        goto done;

    } else {
        do {
            ret = close(p[1]);
        } while (ret == -1 && errno == EINTR);
        p[1] = -1;

        union {
            int highest;
            char data[sizeof(int)];
        } u;
        ssize_t ret, bytesRead = 0;
        struct pollfd pfd;
        pfd.fd = p[0];
        pfd.events = POLLIN;

        do {
            do {
                // The child process must finish within 30 ms, otherwise
                // we might as well query sysconf.
                ret = poll(&pfd, 1, 30);
            } while (ret == -1 && errno == EINTR);
            if (ret <= 0) {
                goto done;
            }

            do {
                ret = read(p[0], u.data + bytesRead, sizeof(int) - bytesRead);
            } while (ret == -1 && ret == EINTR);
            if (ret == -1) {
                if (errno != EAGAIN) {
                    goto done;
                }
            } else if (ret == 0) {
                goto done;
            } else {
                bytesRead += ret;
            }
        } while (bytesRead < (ssize_t) sizeof(int));

        result = u.highest;
        goto done;
    }

done:
    if (p[0] != -1) {
        do {
            ret = close(p[0]);
        } while (ret == -1 && errno == EINTR);
    }
    if (p[1] != -1) {
        do {
            close(p[1]);
        } while (ret == -1 && errno == EINTR);
    }
    if (pid != -1) {
        do {
            ret = kill(pid, SIGKILL);
        } while (ret == -1 && errno == EINTR);
        do {
            ret = waitpid(pid, NULL, 0);
        } while (ret == -1 && errno == EINTR);
    }

    if (result == -1) {
        result = getFileDescriptorLimit();
    }
    return result;
#endif
}

void
closeAllFileDescriptors(int lastToKeepOpen) {
    #if defined(F_CLOSEM)
        int ret;
        do {
            ret = fcntl(lastToKeepOpen + 1, F_CLOSEM);
        } while (ret == -1 && errno == EINTR);
        if (ret != -1) {
            return;
        }
    #elif defined(HAS_CLOSEFROM)
        closefrom(lastToKeepOpen + 1);
        return;
    #endif

    for (int i = getHighestFileDescriptor(); i > lastToKeepOpen; i--) {
        int ret;
        do {
            ret = close(i);
        } while (ret == -1 && errno == EINTR);
    }
}
于 2010-10-09T16:09:20.707 回答
1

在 MacOS 上,您可以使用posix_spawn带有.POSIX_SPAWN_CLOEXEC_DEFAULTposix_spawnattr_setflags

这将只留下在调用中显式设置的文件描述符posix_spawn打开,关闭调用其他。

于 2021-08-03T12:55:12.990 回答
0

就在您的程序启动并且没有打开任何东西的时候。例如像 main() 的开始。pipe 和 fork 立即启动执行服务器。这样它的内存和其他细节是干净的,你可以把东西交给 fork & exec。

#include <unistd.h>
#include <stdio.h>
#include <memory.h>
#include <stdlib.h>

struct PipeStreamHandles {
    /** Write to this */
    int output;
    /** Read from this */
    int input;

    /** true if this process is the child after a fork */
    bool isChild;
    pid_t childProcessId;
};

PipeStreamHandles forkFullDuplex(){
    int childInput[2];
    int childOutput[2];

    pipe(childInput);
    pipe(childOutput);

    pid_t pid = fork();
    PipeStreamHandles streams;
    if(pid == 0){
        // child
        close(childInput[1]);
        close(childOutput[0]);

        streams.output = childOutput[1];
        streams.input = childInput[0];
        streams.isChild = true;
        streams.childProcessId = getpid();
    } else {
        close(childInput[0]);
        close(childOutput[1]);

        streams.output = childInput[1];
        streams.input = childOutput[0];
        streams.isChild = false;
        streams.childProcessId = pid;
    }

    return streams;
}


struct ExecuteData {
    char command[2048];
    bool shouldExit;
};

ExecuteData getCommand() {
    // maybe use json or semething to read what to execute
    // environment if any and etc..        
    // you can read via stdin because of the dup setup we did
    // in setupExecutor
    ExecuteData data;
    memset(&data, 0, sizeof(data));
    data.shouldExit = fgets(data.command, 2047, stdin) == NULL;
    return data;
}

void executorServer(){

    while(true){
        printf("executor server waiting for command\n");
        // maybe use json or semething to read what to execute
        // environment if any and etc..        
        ExecuteData command = getCommand();
        // one way is for getCommand() to check if stdin is gone
        // that way you can set shouldExit to true
        if(command.shouldExit){
            break;
        }
        printf("executor server doing command %s", command.command);
        system(command.command);
        // free command resources.
    }
}

static PipeStreamHandles executorStreams;
void setupExecutor(){
    PipeStreamHandles handles = forkFullDuplex();

    if(handles.isChild){
        // This simplifies so we can just use standard IO 
        dup2(handles.input, 0);
        // we comment this out so we see output.
        // dup2(handles.output, 1);
        close(handles.input);
        // we uncomment this one so we can see hello world
        // if you want to capture the output you will want this.
        //close(handles.output);
        handles.input = 0;
        handles.output = 1;
        printf("started child\n");
        executorServer();
        printf("exiting executor\n");
        exit(0);
    }

    executorStreams = handles;
}

/** Only has 0, 1, 2 file descriptiors open */
pid_t cleanForkAndExecute(const char *command) {
    // You can do json and use a json parser might be better
    // so you can pass other data like environment perhaps.
    // and also be able to return details like new proccess id so you can
    // wait if it's done and ask other relevant questions.
    write(executorStreams.output, command, strlen(command));
    write(executorStreams.output, "\n", 1);
}

int main () {
    // needs to be done early so future fds do not get open
    setupExecutor();

    // run your program as usual.
    cleanForkAndExecute("echo hello world");
    sleep(3);
}

如果你想在执行的程序上做 IO,执行器服务器将不得不做套接字重定向,你可以使用 unix 套接字。

于 2016-06-11T22:02:30.757 回答
-2

为什么不关闭从 0 到 10000 的所有描述符。

这会很快,最糟糕的事情就是 EBADF。

于 2009-05-22T17:54:45.110 回答