falso
/
qemu-irix
mirror of https://github.com/n64decomp/qemu-irix.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

coroutine-ucontext: use __thread 

ELF thread local storage is about 10% faster on tests/test-coroutine's
perf/cost test.  The timing on my machine is 190ns per iteration with
pthread TLS, 170 with ELF TLS.

Based on a patch by Kevin Wolf and Peter Lieven, but redone to follow
the model of coroutine-win32.c (including the important "noinline"
attribute!).

Platforms without thread-local storage (OpenBSD probably?) will need
a new-enough GCC for this to compile, in order to use the same emutls
support that Windows already relies on.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Message-id: 1417518350-6167-2-git-send-email-pbonzini@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
This commit is contained in:
Paolo Bonzini 2014-12-02 12:05:44 +01:00 committed by Stefan Hajnoczi
parent bc52169660
commit d1d1b206b0
1 changed files with 19 additions and 50 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

69
coroutine-ucontext.c
View File

@ -25,7 +25,6 @@
#include <stdlib.h> #include <stdlib.h>
#include <setjmp.h> #include <setjmp.h>
#include <stdint.h> #include <stdint.h>
#include <pthread.h>
#include <ucontext.h> #include <ucontext.h>
#include "qemu-common.h" #include "qemu-common.h"
#include "block/coroutine_int.h" #include "block/coroutine_int.h"
@ -48,15 +47,8 @@ typedef struct {
/** /**
* Per-thread coroutine bookkeeping * Per-thread coroutine bookkeeping
*/ */
typedef struct { static __thread CoroutineUContext leader;
/** Currently executing coroutine */ static __thread Coroutine *current;
Coroutine *current;
/** The default coroutine */
CoroutineUContext leader;
} CoroutineThreadState;
static pthread_key_t thread_state_key;
/* /*
* va_args to makecontext() must be type 'int', so passing * va_args to makecontext() must be type 'int', so passing
@ -68,36 +60,6 @@ union cc_arg {
int i[2]; 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__((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) static void coroutine_trampoline(int i0, int i1)
{ {
union cc_arg arg; union cc_arg arg;
@ -193,15 +155,23 @@ void qemu_coroutine_delete(Coroutine *co_)
g_free(co); g_free(co);
} }
CoroutineAction qemu_coroutine_switch(Coroutine *from_, Coroutine *to_, /* This function is marked noinline to prevent GCC from inlining it
CoroutineAction action) * 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 *from = DO_UPCAST(CoroutineUContext, base, from_);
CoroutineUContext *to = DO_UPCAST(CoroutineUContext, base, to_); CoroutineUContext *to = DO_UPCAST(CoroutineUContext, base, to_);
CoroutineThreadState *s = coroutine_get_thread_state();
int ret; int ret;
s->current = to_; current = to_;
ret = sigsetjmp(from->env, 0); ret = sigsetjmp(from->env, 0);
if (ret == 0) { if (ret == 0) {
@ -212,14 +182,13 @@ CoroutineAction qemu_coroutine_switch(Coroutine *from_, Coroutine *to_,
Coroutine *qemu_coroutine_self(void) Coroutine *qemu_coroutine_self(void)
{ {
CoroutineThreadState *s = coroutine_get_thread_state(); if (!current) {
current = &leader.base;
return s->current; }
return current;
} }
bool qemu_in_coroutine(void) bool qemu_in_coroutine(void)
{ {
CoroutineThreadState *s = pthread_getspecific(thread_state_key); return current && current->caller;
return s && s->current->caller;
} }