c - 交换到ucontext_t的uc_link时，swapcontext segfaults

我正在使用常规的makecontext / swapcontext例程在C语言中编写一个小型的概念证明光纤库，但这给我带来了麻烦（我的平台是使用clang-503.0.40的OSX 10.9 Mavericks）。

这是我要处理的数据结构：

typedef enum {
    /// Fiber is waiting to start execution
    FIBER_PENDING,

    /// Fiber is in the midst of executing
    FIBER_EXECUTING,

    /// Fiber has finished executing
    FIBER_FINISHED,

    /// Fiber is in the process of yielding
    FIBER_YIELDING
} fiber_state;

typedef struct {
    char *stack;
    fiber_state state;
    ucontext_t context;
} fiber;

这是小型库（三个功能，fiber_init，fiber_run和fiber_yield：

#include <string.h>
#include <stdlib.h>
#include <signal.h>
#include <assert.h>
#include <stdio.h>

// Generic log w/ file name and line number
#define LOG(x) fprintf(stderr, "%s:%d |-> %s\n", __FILE__, __LINE__, x)

// the current executing fiber in this thread (or NULL of none are executing)
// (TODO: make this TLS)
static fiber *current_fiber = NULL;

/// prepare fiber 'f' to be run
void fiber_init(fiber *f, void(* fiber_func)()) {
    // zero out the fiber
    memset(f, 0, sizeof(fiber));

    f->state = FIBER_PENDING;
    f->stack = (char*) malloc(SIGSTKSZ);

    // init stack config of the fiber context
    ucontext_t *f_context = &(f->context);

    getcontext(f_context);
    f_context->uc_stack.ss_sp    = f->stack;
    f_context->uc_stack.ss_size  = SIGSTKSZ;
    f_context->uc_stack.ss_flags = 0;

    // initialize the context
    makecontext(f_context, fiber_func, 0);
}

/// Deallocate resources associated with 'f'
void fiber_destroy(fiber *f) {
    free(f->stack);
}

/// Start or resume fiber 'f'
void fiber_run(fiber *f) {
    // context to switch back to when yielding, or when the fiber returns
    ucontext_t return_context;
    f->context.uc_link = &return_context;

    // save the fiber being swapped away from (or NULL)
    fiber *old_fiber = current_fiber;
    current_fiber = f;

    LOG("Swapping into fiber context");

    getcontext(&return_context);
    int status = swapcontext(
        &return_context,
        &(f->context));
    assert(status == 0 && "Failed to swap to fiber context");

    LOG("Back to parent context from swap");

    if(f->state == FIBER_YIELDING) {
        f->state = FIBER_EXECUTING;
        LOG("Fiber yielded");
    }
    else {
        LOG("Fiber done executing; marking as finished");
        current_fiber->state = FIBER_FINISHED;
    }

    // restore old fiber
    current_fiber = old_fiber;
}

/// from witin a fiber, yield control to the caller's context
void fiber_yield() {
    assert(current_fiber && "No fiber is currently running!");

    current_fiber->state = FIBER_YIELDING;

    LOG("Yielding back to caller context");
    int status = swapcontext(
        &(current_fiber->context),
        current_fiber->context.uc_link);
    assert(status == 0 && "Failed to swap to parent context");
    LOG("Swapped back into fiber context (post-yield)");
}

/// query fiber state
int fiber_is_pending(const fiber *const f) {
    return f->state == FIBER_PENDING;
}
int fiber_is_finished(const fiber *const f) {
    return f->state == FIBER_FINISHED;
}
int fiber_is_executing(const fiber *const f) {
    return f->state == FIBER_EXECUTING;
}

不过，似乎在光纤中调用fiber_yield（）不能正确地将上下文与调用者的上下文交换（其引用存储在光纤上下文的uc_link中，请参见current_fiber->context.uc_link中的fiber_yield）

运行该程序的痕迹：

void my_func() {
    LOG(" ------- I'm the fiber function! yielding");
    fiber_yield();
    LOG(" ------- End of my_func");
}

int main() {
    fiber f;
    fiber_init(&f, my_func);

    while(!fiber_is_finished(&f)) {
        fiber_run(&f);
        LOG("Back in main run loop");
    }

    fiber_destroy(&f);
    return 0;
}

产生输出：

fibers.c:70 |-> Swapping into fiber context
test_harness.c:5 |->  ------- I'm the fiber function! yielding
fibers.c:99 |-> Yielding back to caller context
Segmentation fault: 11

我已经了解到OSX具有堆栈对齐限制（限制为16个字节的边界），但是我正在使用malloc分配堆栈，这将返回一个与16字节边界对齐的块（或者我已经阅读了） 。也就是说，似乎重新排列声明的顺序有时可能会导致段错误发生，但这是非常虚假的，并且难以复制。

在调用swapcontext之前检查fiber_yield会显示current_fiber->context具有非常大的堆栈大小。比应该的大得多。也许这是腐败的征兆：

(lldb) p current_fiber->context
(ucontext_t) $3 = {
  uc_onstack = 0
  uc_sigmask = 0
  uc_stack = (ss_sp = 0x00007fff5fbff720, ss_size = 140734799804176, ss_flags = 0)
  uc_link = 0x00007fff5fbff780
  uc_mcsize = 0
  uc_mcontext = 0x00007fff5fbff828
}
(lldb) p *(current_fiber->context.uc_link)
(__darwin_ucontext) $4 = {
  uc_onstack = -541067328
  uc_sigmask = 0
  uc_stack = (ss_sp = 0x00007fff5fbff700, ss_size = 8388608, ss_flags = 0)
  uc_link = 0x0000000000000000
  uc_mcsize = 140734799804400
  uc_mcontext = 0x00007fff5fbff7b8
}

任何线索可能会发生什么？谢谢！

最佳答案

我能够使用您的代码在OS X 10.6.8上使用Apple的gcc-4.2.1进行编译，从而重现相同的问题。

我注意到您不包含ucontext.h。使用-Wall进行编译会使编译器警告ucontext函数的隐式声明。

添加#include <ucontext.h>导致错误：

In file included from foo.c:6:
/usr/include/ucontext.h:42:2: error: #error ucontext routines are deprecated, and require _XOPEN_SOURCE to be defined

首先添加#define _XOPEN_SOURCE包括修复该问题以及该程序的行为。显然，该宏更改了相关结构的布局，以匹配这些功能的期望和要求。

对于这些功能已被弃用，我不确定该如何告诉您。我知道没有支持的替代品。

关于c - 交换到ucontext_t的uc_link时，swapcontext segfaults，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/23852522/