aboutsummaryrefslogtreecommitdiff
path: root/coroutine-ucontext.c
diff options
context:
space:
mode:
authorPaolo Bonzini <pbonzini@redhat.com>2014-12-02 12:05:44 +0100
committerStefan Hajnoczi <stefanha@redhat.com>2015-01-13 13:43:28 +0000
commitd1d1b206b07977fe0e75b0254e5b50c215c97803 (patch)
tree2926e9c04304e3ef1d016a84152a3e27cd486fc1 /coroutine-ucontext.c
parentbc521696607c5348fcd8a9e57b408d0ac0dbe2f8 (diff)
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>
Diffstat (limited to 'coroutine-ucontext.c')
-rw-r--r--coroutine-ucontext.c69
1 files changed, 19 insertions, 50 deletions
diff --git a/coroutine-ucontext.c b/coroutine-ucontext.c
index 4bf2cde279..259fcb48a4 100644
--- a/coroutine-ucontext.c
+++ b/coroutine-ucontext.c
@@ -25,7 +25,6 @@
#include <stdlib.h>
#include <setjmp.h>
#include <stdint.h>
-#include <pthread.h>
#include <ucontext.h>
#include "qemu-common.h"
#include "block/coroutine_int.h"
@@ -48,15 +47,8 @@ typedef struct {
/**
* 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
@@ -68,36 +60,6 @@ union cc_arg {
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)
{
union cc_arg arg;
@@ -193,15 +155,23 @@ void qemu_coroutine_delete(Coroutine *co_)
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 = sigsetjmp(from->env, 0);
if (ret == 0) {
@@ -212,14 +182,13 @@ CoroutineAction qemu_coroutine_switch(Coroutine *from_, Coroutine *to_,
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;
}