#include <stdlib.h>
#include <setjmp.h>
#include <stdint.h>
-#include <pthread.h>
#include <ucontext.h>
#include "qemu-common.h"
-#include "qemu-coroutine-int.h"
+#include "block/coroutine_int.h"
-enum {
- /* Maximum free pool size prevents holding too many freed coroutines */
- POOL_MAX_SIZE = 64,
-};
-
-/** Free list to speed up creation */
-static QLIST_HEAD(, Coroutine) pool = QLIST_HEAD_INITIALIZER(pool);
-static unsigned int pool_size;
+#ifdef CONFIG_VALGRIND_H
+#include <valgrind/valgrind.h>
+#endif
typedef struct {
Coroutine base;
void *stack;
- jmp_buf env;
+ sigjmp_buf env;
+
+#ifdef CONFIG_VALGRIND_H
+ unsigned int valgrind_stack_id;
+#endif
+
} CoroutineUContext;
/**
* Per-thread coroutine bookkeeping
*/
-typedef struct {
- /** Currently executing coroutine */
- Coroutine *current;
-
- /** The default coroutine */
- CoroutineUContext leader;
-} CoroutineThreadState;
-
-static pthread_key_t thread_state_key;
+static __thread CoroutineUContext leader;
+static __thread Coroutine *current;
/*
* va_args to makecontext() must be type 'int', so passing
int i[2];
};
-static CoroutineThreadState *coroutine_get_thread_state(void)
-{
- CoroutineThreadState *s = pthread_getspecific(thread_state_key);
-
- if (!s) {
- s = g_malloc0(sizeof(*s));
- s->current = &s->leader.base;
- pthread_setspecific(thread_state_key, s);
- }
- return s;
-}
-
-static void qemu_coroutine_thread_cleanup(void *opaque)
-{
- CoroutineThreadState *s = opaque;
-
- g_free(s);
-}
-
-static void __attribute__((destructor)) coroutine_cleanup(void)
-{
- Coroutine *co;
- Coroutine *tmp;
-
- QLIST_FOREACH_SAFE(co, &pool, pool_next, tmp) {
- g_free(DO_UPCAST(CoroutineUContext, base, co)->stack);
- g_free(co);
- }
-}
-
-static void __attribute__((constructor)) coroutine_init(void)
-{
- int ret;
-
- ret = pthread_key_create(&thread_state_key, qemu_coroutine_thread_cleanup);
- if (ret != 0) {
- fprintf(stderr, "unable to create leader key: %s\n", strerror(errno));
- abort();
- }
-}
-
static void coroutine_trampoline(int i0, int i1)
{
union cc_arg arg;
co = &self->base;
/* Initialize longjmp environment and switch back the caller */
- if (!setjmp(self->env)) {
- longjmp(*(jmp_buf *)co->entry_arg, 1);
+ if (!sigsetjmp(self->env, 0)) {
+ siglongjmp(*(sigjmp_buf *)co->entry_arg, 1);
}
while (true) {
}
}
-static Coroutine *coroutine_new(void)
+Coroutine *qemu_coroutine_new(void)
{
const size_t stack_size = 1 << 20;
CoroutineUContext *co;
ucontext_t old_uc, uc;
- jmp_buf old_env;
+ sigjmp_buf old_env;
union cc_arg arg = {0};
- /* The ucontext functions preserve signal masks which incurs a system call
- * overhead. setjmp()/longjmp() does not preserve signal masks but only
- * works on the current stack. Since we need a way to create and switch to
- * a new stack, use the ucontext functions for that but setjmp()/longjmp()
- * for everything else.
+ /* The ucontext functions preserve signal masks which incurs a
+ * system call overhead. sigsetjmp(buf, 0)/siglongjmp() does not
+ * preserve signal masks but only works on the current stack.
+ * Since we need a way to create and switch to a new stack, use
+ * the ucontext functions for that but sigsetjmp()/siglongjmp() for
+ * everything else.
*/
if (getcontext(&uc) == -1) {
uc.uc_stack.ss_size = stack_size;
uc.uc_stack.ss_flags = 0;
+#ifdef CONFIG_VALGRIND_H
+ co->valgrind_stack_id =
+ VALGRIND_STACK_REGISTER(co->stack, co->stack + stack_size);
+#endif
+
arg.p = co;
makecontext(&uc, (void (*)(void))coroutine_trampoline,
2, arg.i[0], arg.i[1]);
- /* swapcontext() in, longjmp() back out */
- if (!setjmp(old_env)) {
+ /* swapcontext() in, siglongjmp() back out */
+ if (!sigsetjmp(old_env, 0)) {
swapcontext(&old_uc, &uc);
}
return &co->base;
}
-Coroutine *qemu_coroutine_new(void)
+#ifdef CONFIG_VALGRIND_H
+#ifdef CONFIG_PRAGMA_DIAGNOSTIC_AVAILABLE
+/* Work around an unused variable in the valgrind.h macro... */
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wunused-but-set-variable"
+#endif
+static inline void valgrind_stack_deregister(CoroutineUContext *co)
{
- Coroutine *co;
-
- co = QLIST_FIRST(&pool);
- if (co) {
- QLIST_REMOVE(co, pool_next);
- pool_size--;
- } else {
- co = coroutine_new();
- }
- return co;
+ VALGRIND_STACK_DEREGISTER(co->valgrind_stack_id);
}
+#ifdef CONFIG_PRAGMA_DIAGNOSTIC_AVAILABLE
+#pragma GCC diagnostic pop
+#endif
+#endif
void qemu_coroutine_delete(Coroutine *co_)
{
CoroutineUContext *co = DO_UPCAST(CoroutineUContext, base, co_);
- if (pool_size < POOL_MAX_SIZE) {
- QLIST_INSERT_HEAD(&pool, &co->base, pool_next);
- co->base.caller = NULL;
- pool_size++;
- return;
- }
+#ifdef CONFIG_VALGRIND_H
+ valgrind_stack_deregister(co);
+#endif
g_free(co->stack);
g_free(co);
}
-CoroutineAction qemu_coroutine_switch(Coroutine *from_, Coroutine *to_,
- CoroutineAction action)
+/* This function is marked noinline to prevent GCC from inlining it
+ * into coroutine_trampoline(). If we allow it to do that then it
+ * hoists the code to get the address of the TLS variable "current"
+ * out of the while() loop. This is an invalid transformation because
+ * the sigsetjmp() call may be called when running thread A but
+ * return in thread B, and so we might be in a different thread
+ * context each time round the loop.
+ */
+CoroutineAction __attribute__((noinline))
+qemu_coroutine_switch(Coroutine *from_, Coroutine *to_,
+ CoroutineAction action)
{
CoroutineUContext *from = DO_UPCAST(CoroutineUContext, base, from_);
CoroutineUContext *to = DO_UPCAST(CoroutineUContext, base, to_);
- CoroutineThreadState *s = coroutine_get_thread_state();
int ret;
- s->current = to_;
+ current = to_;
- ret = setjmp(from->env);
+ ret = sigsetjmp(from->env, 0);
if (ret == 0) {
- longjmp(to->env, action);
+ siglongjmp(to->env, action);
}
return ret;
}
Coroutine *qemu_coroutine_self(void)
{
- CoroutineThreadState *s = coroutine_get_thread_state();
-
- return s->current;
+ if (!current) {
+ current = &leader.base;
+ }
+ return current;
}
bool qemu_in_coroutine(void)
{
- CoroutineThreadState *s = pthread_getspecific(thread_state_key);
-
- return s && s->current->caller;
+ return current && current->caller;
}