c - 警报处理程序中 swapcontext 后的段错误

Question

基本上，我正在尝试做的是在具有上下文切换的单个线程上模拟多线程。我每 10 微秒设置一个警报，然后将上下文从一个线程切换到另一个线程。问题是大约五分之一的运行在警报完成 swapcontext 后立即以段错误结束，至少这是我用 gdb 跟踪它的地方。

这是我的源文件主程序

    #include "umt.h"

void f()
{
    int x = 10;
    printf("starting thread\n");
    while(x)
    {
        printf("thread %d\n", x);
        sleep(1);
        x--;
    }

}

int main()
{
    int x = 0, y, z;
    umt_init();
    y = umt_thread_create(f);
    printf("starting main\n");
    if(y == 0)
    {
        printf("Problems with creating thread\n");
        return;
    }
    x = 10;
    z = 1;
    while(x)
    {
        printf("main\n");
        x--;
    }
    umt_thread_join(y);
    printf("done waiting\n");
    return 0;
}

UMT.h

    #include <sys/time.h>
#include <stdio.h>
#include <signal.h>
#include <ucontext.h>
#include <stdlib.h>

#define TRUE        1
#define FALSE       0

typedef struct _umt_thread
{
    int thread_id;
    ucontext_t context;
    void (*handler)(void);
    int hasFinished;
}umt_thread, *pumt_thread;

void umt_init();

int umt_thread_create(void (*handler)(void));

void umt_thread_join(int thr);

和 umt.c

    #include "umt.h"

#define MAIN_CONTEXT        0
#define STACK_SIZE          1638400

int currentThread;
char threadpool[15];

pumt_thread threads;

void signal_thread_finish();

void thread_handler()
{
    threads[currentThread].handler();
    signal_thread_finish();
}

void thread_scheduler();

void signal_thread_finish()
{
    threads[currentThread].hasFinished = TRUE;
    threadpool[currentThread] = 0;
    thread_scheduler();
}

void thread_scheduler()
{
    int nextThread = 0, curThread = 0;
    int x = 0;
    ucontext_t *con1, *con2;

    nextThread = currentThread + 1;
    while(1)
    {
        if(nextThread == 15)
            nextThread = 0;
        if(nextThread == currentThread)
            break;
        if(threadpool[nextThread] == 1)
            break;
        nextThread++;
    }

    if(nextThread == currentThread)
        return;
    curThread = currentThread;
    currentThread = nextThread;
    con1 = &(threads[curThread].context);
    con2 = &(threads[nextThread].context);
    x = swapcontext(con1, con2); 
}

void umt_init()
{
    ucontext_t context;
    struct itimerval mytimer;
    int i;
    stack_t new_stack;

    getcontext(&context);

    threads = (pumt_thread)malloc(sizeof(umt_thread) * 15);
    threads[MAIN_CONTEXT].thread_id = MAIN_CONTEXT;
    threads[MAIN_CONTEXT].context = context;

    threadpool[MAIN_CONTEXT] = 1;
    for(i = 1;i<15;i++)
    {
        threadpool[i] = 0;
    }

    currentThread = 0;

    new_stack.ss_sp = (char*)malloc(STACK_SIZE);
    new_stack.ss_size = STACK_SIZE;
    new_stack.ss_flags = 0;
    i = sigaltstack(&new_stack, NULL);
    if(i != 0)
    {
        printf("problems assigning new stack for signaling\n");
    }

    signal(SIGALRM, thread_scheduler);
    mytimer.it_interval.tv_sec = 0;
    mytimer.it_interval.tv_usec = 10;
    mytimer.it_value.tv_sec = 0;
    mytimer.it_value.tv_usec = 5;
    setitimer(ITIMER_REAL, &mytimer, 0);
}

int umt_thread_create(void (*handler)(void))
{
    ucontext_t context;
    int i, pos;

    for(i = 1;i<15;i++)
    {
        if(threadpool[i] == 0)
        {
            pos = i;
            break;
        }
    }
    if(i == 15)
    {
        printf("No empty space in the threadpool\n");
        return -1;
    }

    if(getcontext(&context) == -1)
    {
        printf("Problems getting context\n");
        return 0;
    }
    context.uc_link = 0;//&(threads[MAIN_CONTEXT].context);
    context.uc_stack.ss_sp = (char*)malloc(STACK_SIZE);
    if(context.uc_stack.ss_sp == NULL)
    {
        printf("Problems with allocating stack\n");
    }
    context.uc_stack.ss_size = STACK_SIZE;
    context.uc_stack.ss_flags = 0;
    makecontext(&context, thread_handler, 0);

    threads[pos].thread_id = pos;
    threads[pos].context = context;
    threads[pos].handler = handler;
    threads[pos].hasFinished = FALSE;

    threadpool[pos] = 1;

    printf("Created thread on pos %d\n", pos);

    return pos;
}

void umt_thread_join(int tid)
{
    while(!threads[tid].hasFinished)
    {
    }
}

我尝试了很多组合并尝试通过指令进行跟踪，但无法就可能导致此段错误的原因得出结论或想法。谢谢

Answer 1

我看到的问题很少(有些与段错误有关 + 一些其他评论)

1. 您的调度程序 (thread_scheduler) 应该位于临界区，例如您应该阻止任何警报信号(或忽略它们)，以便以不会破坏它的方式处理线程池。您可以使用 sigprocmask 或一个 volatile bool 变量来使警报静音(请注意，这与用户线程互斥量不同，只是与您的调度逻辑的内部同步)

2. 恕我直言，您的时钟走得太快了，这是以微秒为单位，而不是毫秒，因此 tv_usec 的 1000 微秒对于测试目的可能更有意义。

3. 较小的堆栈大小也可能导致段错误，但看起来您的堆栈足够大。

附注有一个更好的方法来处理连接，你目前在它上面浪费了很多 CPU 周期，为什么不简单地避免切换到调用连接的线程，直到它正在等待的线程终止？