Re: [PATCH v2] coroutine-ucontext: Save fake stack for pooled coroutine

2024-01-17 Thread Stefan Hajnoczi 
On Wed, Jan 17, 2024 at 04:06:02PM +0900, Akihiko Odaki wrote:
> Coroutine may be pooled even after COROUTINE_TERMINATE if
> CONFIG_COROUTINE_POOL is enabled and fake stack should be saved in
> such a case to keep AddressSanitizerUseAfterReturn working. Even worse,
> I'm seeing stack corruption without fake stack being saved.
> 
> Signed-off-by: Akihiko Odaki 
> ---
> Changes in v2:
> - Added missing set_current() (Marc-André Lureau)
> - Added G_STATIC_ASSERT(!IS_ENABLED(CONFIG_TSAN)) (Marc-André Lureau)
> - Renamed terminate() to terminate_asan() for clarity and consistency.
> - Changed terminate_asan() to call start_switch_fiber_asan() for
>   consistency.
> - Link to v1: 
> https://lore.kernel.org/r/20240112-asan-v1-1-e330f0d00...@daynix.com
> ---
>  util/coroutine-ucontext.c | 35 ++-
>  1 file changed, 26 insertions(+), 9 deletions(-)

Thanks, applied to my block tree:
https://gitlab.com/stefanha/qemu/commits/block

Stefan


signature.asc
Description: PGP signature

Re: [PATCH v2] coroutine-ucontext: Save fake stack for pooled coroutine

2024-01-16 Thread Marc-André Lureau 
Hi

On Wed, Jan 17, 2024 at 11:26 AM Marc-André Lureau
 wrote:
>
> Hi
>
> On Wed, Jan 17, 2024 at 11:06 AM Akihiko Odaki  
> wrote:
> >
> > Coroutine may be pooled even after COROUTINE_TERMINATE if
> > CONFIG_COROUTINE_POOL is enabled and fake stack should be saved in
> > such a case to keep AddressSanitizerUseAfterReturn working. Even worse,
> > I'm seeing stack corruption without fake stack being saved.
> >
> > Signed-off-by: Akihiko Odaki 
> > ---
> > Changes in v2:
> > - Added missing set_current() (Marc-André Lureau)
> > - Added G_STATIC_ASSERT(!IS_ENABLED(CONFIG_TSAN)) (Marc-André Lureau)
> > - Renamed terminate() to terminate_asan() for clarity and consistency.
> > - Changed terminate_asan() to call start_switch_fiber_asan() for
> >   consistency.
> > - Link to v1: 
> > https://lore.kernel.org/r/20240112-asan-v1-1-e330f0d00...@daynix.com
> > ---
> >  util/coroutine-ucontext.c | 35 ++-
> >  1 file changed, 26 insertions(+), 9 deletions(-)
> >
> > diff --git a/util/coroutine-ucontext.c b/util/coroutine-ucontext.c
> > index 7b304c79d942..8ef603d081ea 100644
> > --- a/util/coroutine-ucontext.c
> > +++ b/util/coroutine-ucontext.c
> > @@ -119,13 +119,11 @@ void finish_switch_fiber(void *fake_stack_save)
> >
> >  /* always_inline is required to avoid TSan runtime fatal errors. */
> >  static inline __attribute__((always_inline))
> > -void start_switch_fiber_asan(CoroutineAction action, void 
> > **fake_stack_save,
> > +void start_switch_fiber_asan(void **fake_stack_save,
> >   const void *bottom, size_t size)
> >  {
> >  #ifdef CONFIG_ASAN
> > -__sanitizer_start_switch_fiber(
> > -action == COROUTINE_TERMINATE ? NULL : fake_stack_save,
> > -bottom, size);
> > +__sanitizer_start_switch_fiber(fake_stack_save, bottom, size);
> >  #endif
> >  }
> >
> > @@ -165,7 +163,7 @@ static void coroutine_trampoline(int i0, int i1)
> >  if (!sigsetjmp(self->env, 0)) {
> >  CoroutineUContext *leaderp = get_ptr_leader();
> >
> > -start_switch_fiber_asan(COROUTINE_YIELD, _stack_save,
> > +start_switch_fiber_asan(_stack_save,
> >  leaderp->stack, leaderp->stack_size);
> >  start_switch_fiber_tsan(_stack_save, self, true); /* 
> > true=caller */
> >  siglongjmp(*(sigjmp_buf *)co->entry_arg, 1);
> > @@ -226,8 +224,7 @@ Coroutine *qemu_coroutine_new(void)
> >
> >  /* swapcontext() in, siglongjmp() back out */
> >  if (!sigsetjmp(old_env, 0)) {
> > -start_switch_fiber_asan(COROUTINE_YIELD, _stack_save, 
> > co->stack,
> > -co->stack_size);
> > +start_switch_fiber_asan(_stack_save, co->stack, 
> > co->stack_size);
> >  start_switch_fiber_tsan(_stack_save,
> >  co, false); /* false=not caller */
> >
> > @@ -269,10 +266,28 @@ static inline void 
> > valgrind_stack_deregister(CoroutineUContext *co)
> >  #endif
> >  #endif
> >
> > +#if defined(CONFIG_ASAN) && defined(CONFIG_COROUTINE_POOL)
> > +static void coroutine_fn terminate_asan(void *opaque)
> > +{
> > +CoroutineUContext *to = DO_UPCAST(CoroutineUContext, base, opaque);
> > +
> > +set_current(opaque);
> > +start_switch_fiber_asan(NULL, to->stack, to->stack_size);
> > +G_STATIC_ASSERT(!IS_ENABLED(CONFIG_TSAN));
> > +siglongjmp(to->env, COROUTINE_ENTER);
> > +}
> > +#endif
> > +
> >  void qemu_coroutine_delete(Coroutine *co_)
> >  {
> >  CoroutineUContext *co = DO_UPCAST(CoroutineUContext, base, co_);
> >
> > +#if defined(CONFIG_ASAN) && defined(CONFIG_COROUTINE_POOL)
> > +co_->entry_arg = qemu_coroutine_self();
> > +co_->entry = terminate_asan;
> > +qemu_coroutine_switch(co_->entry_arg, co_, COROUTINE_ENTER);
> > +#endif
> > +
> >  #ifdef CONFIG_VALGRIND_H
> >  valgrind_stack_deregister(co);
> >  #endif
> > @@ -305,8 +320,10 @@ qemu_coroutine_switch(Coroutine *from_, Coroutine *to_,
> >
> >  ret = sigsetjmp(from->env, 0);
> >  if (ret == 0) {
> > -start_switch_fiber_asan(action, _stack_save, to->stack,
> > -to->stack_size);
> > +start_switch_fiber_asan(IS_ENABLED(CONFIG_COROUTINE_POOL) ||
> > +action != COROUTINE_TERMINATE ?
> > +_stack_save : NULL,
> > +to->stack, to->stack_size);
>
> given that the coroutine is reentered on delete to clear the fake
> stack, can we just pass _stack_save here?
>

Ah, terminate_asan() is only called when the pool is enabled.

Reviewed-by: Marc-André Lureau 




-- 
Marc-André Lureau

Re: [PATCH v2] coroutine-ucontext: Save fake stack for pooled coroutine

2024-01-16 Thread Marc-André Lureau 
Hi

On Wed, Jan 17, 2024 at 11:06 AM Akihiko Odaki  wrote:
>
> Coroutine may be pooled even after COROUTINE_TERMINATE if
> CONFIG_COROUTINE_POOL is enabled and fake stack should be saved in
> such a case to keep AddressSanitizerUseAfterReturn working. Even worse,
> I'm seeing stack corruption without fake stack being saved.
>
> Signed-off-by: Akihiko Odaki 
> ---
> Changes in v2:
> - Added missing set_current() (Marc-André Lureau)
> - Added G_STATIC_ASSERT(!IS_ENABLED(CONFIG_TSAN)) (Marc-André Lureau)
> - Renamed terminate() to terminate_asan() for clarity and consistency.
> - Changed terminate_asan() to call start_switch_fiber_asan() for
>   consistency.
> - Link to v1: 
> https://lore.kernel.org/r/20240112-asan-v1-1-e330f0d00...@daynix.com
> ---
>  util/coroutine-ucontext.c | 35 ++-
>  1 file changed, 26 insertions(+), 9 deletions(-)
>
> diff --git a/util/coroutine-ucontext.c b/util/coroutine-ucontext.c
> index 7b304c79d942..8ef603d081ea 100644
> --- a/util/coroutine-ucontext.c
> +++ b/util/coroutine-ucontext.c
> @@ -119,13 +119,11 @@ void finish_switch_fiber(void *fake_stack_save)
>
>  /* always_inline is required to avoid TSan runtime fatal errors. */
>  static inline __attribute__((always_inline))
> -void start_switch_fiber_asan(CoroutineAction action, void **fake_stack_save,
> +void start_switch_fiber_asan(void **fake_stack_save,
>   const void *bottom, size_t size)
>  {
>  #ifdef CONFIG_ASAN
> -__sanitizer_start_switch_fiber(
> -action == COROUTINE_TERMINATE ? NULL : fake_stack_save,
> -bottom, size);
> +__sanitizer_start_switch_fiber(fake_stack_save, bottom, size);
>  #endif
>  }
>
> @@ -165,7 +163,7 @@ static void coroutine_trampoline(int i0, int i1)
>  if (!sigsetjmp(self->env, 0)) {
>  CoroutineUContext *leaderp = get_ptr_leader();
>
> -start_switch_fiber_asan(COROUTINE_YIELD, _stack_save,
> +start_switch_fiber_asan(_stack_save,
>  leaderp->stack, leaderp->stack_size);
>  start_switch_fiber_tsan(_stack_save, self, true); /* 
> true=caller */
>  siglongjmp(*(sigjmp_buf *)co->entry_arg, 1);
> @@ -226,8 +224,7 @@ Coroutine *qemu_coroutine_new(void)
>
>  /* swapcontext() in, siglongjmp() back out */
>  if (!sigsetjmp(old_env, 0)) {
> -start_switch_fiber_asan(COROUTINE_YIELD, _stack_save, co->stack,
> -co->stack_size);
> +start_switch_fiber_asan(_stack_save, co->stack, co->stack_size);
>  start_switch_fiber_tsan(_stack_save,
>  co, false); /* false=not caller */
>
> @@ -269,10 +266,28 @@ static inline void 
> valgrind_stack_deregister(CoroutineUContext *co)
>  #endif
>  #endif
>
> +#if defined(CONFIG_ASAN) && defined(CONFIG_COROUTINE_POOL)
> +static void coroutine_fn terminate_asan(void *opaque)
> +{
> +CoroutineUContext *to = DO_UPCAST(CoroutineUContext, base, opaque);
> +
> +set_current(opaque);
> +start_switch_fiber_asan(NULL, to->stack, to->stack_size);
> +G_STATIC_ASSERT(!IS_ENABLED(CONFIG_TSAN));
> +siglongjmp(to->env, COROUTINE_ENTER);
> +}
> +#endif
> +
>  void qemu_coroutine_delete(Coroutine *co_)
>  {
>  CoroutineUContext *co = DO_UPCAST(CoroutineUContext, base, co_);
>
> +#if defined(CONFIG_ASAN) && defined(CONFIG_COROUTINE_POOL)
> +co_->entry_arg = qemu_coroutine_self();
> +co_->entry = terminate_asan;
> +qemu_coroutine_switch(co_->entry_arg, co_, COROUTINE_ENTER);
> +#endif
> +
>  #ifdef CONFIG_VALGRIND_H
>  valgrind_stack_deregister(co);
>  #endif
> @@ -305,8 +320,10 @@ qemu_coroutine_switch(Coroutine *from_, Coroutine *to_,
>
>  ret = sigsetjmp(from->env, 0);
>  if (ret == 0) {
> -start_switch_fiber_asan(action, _stack_save, to->stack,
> -to->stack_size);
> +start_switch_fiber_asan(IS_ENABLED(CONFIG_COROUTINE_POOL) ||
> +action != COROUTINE_TERMINATE ?
> +_stack_save : NULL,
> +to->stack, to->stack_size);

given that the coroutine is reentered on delete to clear the fake
stack, can we just pass _stack_save here?

otherwise, looks ok to me

>  start_switch_fiber_tsan(_stack_save,
>  to, false); /* false=not caller */
>  siglongjmp(to->env, action);
>
> ---
> base-commit: f614acb7450282a119d85d759f27eae190476058
> change-id: 20240112-asan-eb695c769f40
>
> Best regards,
> --
> Akihiko Odaki 
>


-- 
Marc-André Lureau

[PATCH v2] coroutine-ucontext: Save fake stack for pooled coroutine

2024-01-16 Thread Akihiko Odaki 
Coroutine may be pooled even after COROUTINE_TERMINATE if
CONFIG_COROUTINE_POOL is enabled and fake stack should be saved in
such a case to keep AddressSanitizerUseAfterReturn working. Even worse,
I'm seeing stack corruption without fake stack being saved.

Signed-off-by: Akihiko Odaki 
---
Changes in v2:
- Added missing set_current() (Marc-André Lureau)
- Added G_STATIC_ASSERT(!IS_ENABLED(CONFIG_TSAN)) (Marc-André Lureau)
- Renamed terminate() to terminate_asan() for clarity and consistency.
- Changed terminate_asan() to call start_switch_fiber_asan() for
  consistency.
- Link to v1: 
https://lore.kernel.org/r/20240112-asan-v1-1-e330f0d00...@daynix.com
---
 util/coroutine-ucontext.c | 35 ++-
 1 file changed, 26 insertions(+), 9 deletions(-)

diff --git a/util/coroutine-ucontext.c b/util/coroutine-ucontext.c
index 7b304c79d942..8ef603d081ea 100644
--- a/util/coroutine-ucontext.c
+++ b/util/coroutine-ucontext.c
@@ -119,13 +119,11 @@ void finish_switch_fiber(void *fake_stack_save)
 
 /* always_inline is required to avoid TSan runtime fatal errors. */
 static inline __attribute__((always_inline))
-void start_switch_fiber_asan(CoroutineAction action, void **fake_stack_save,
+void start_switch_fiber_asan(void **fake_stack_save,
  const void *bottom, size_t size)
 {
 #ifdef CONFIG_ASAN
-__sanitizer_start_switch_fiber(
-action == COROUTINE_TERMINATE ? NULL : fake_stack_save,
-bottom, size);
+__sanitizer_start_switch_fiber(fake_stack_save, bottom, size);
 #endif
 }
 
@@ -165,7 +163,7 @@ static void coroutine_trampoline(int i0, int i1)
 if (!sigsetjmp(self->env, 0)) {
 CoroutineUContext *leaderp = get_ptr_leader();
 
-start_switch_fiber_asan(COROUTINE_YIELD, _stack_save,
+start_switch_fiber_asan(_stack_save,
 leaderp->stack, leaderp->stack_size);
 start_switch_fiber_tsan(_stack_save, self, true); /* true=caller 
*/
 siglongjmp(*(sigjmp_buf *)co->entry_arg, 1);
@@ -226,8 +224,7 @@ Coroutine *qemu_coroutine_new(void)
 
 /* swapcontext() in, siglongjmp() back out */
 if (!sigsetjmp(old_env, 0)) {
-start_switch_fiber_asan(COROUTINE_YIELD, _stack_save, co->stack,
-co->stack_size);
+start_switch_fiber_asan(_stack_save, co->stack, co->stack_size);
 start_switch_fiber_tsan(_stack_save,
 co, false); /* false=not caller */
 
@@ -269,10 +266,28 @@ static inline void 
valgrind_stack_deregister(CoroutineUContext *co)
 #endif
 #endif
 
+#if defined(CONFIG_ASAN) && defined(CONFIG_COROUTINE_POOL)
+static void coroutine_fn terminate_asan(void *opaque)
+{
+CoroutineUContext *to = DO_UPCAST(CoroutineUContext, base, opaque);
+
+set_current(opaque);
+start_switch_fiber_asan(NULL, to->stack, to->stack_size);
+G_STATIC_ASSERT(!IS_ENABLED(CONFIG_TSAN));
+siglongjmp(to->env, COROUTINE_ENTER);
+}
+#endif
+
 void qemu_coroutine_delete(Coroutine *co_)
 {
 CoroutineUContext *co = DO_UPCAST(CoroutineUContext, base, co_);
 
+#if defined(CONFIG_ASAN) && defined(CONFIG_COROUTINE_POOL)
+co_->entry_arg = qemu_coroutine_self();
+co_->entry = terminate_asan;
+qemu_coroutine_switch(co_->entry_arg, co_, COROUTINE_ENTER);
+#endif
+
 #ifdef CONFIG_VALGRIND_H
 valgrind_stack_deregister(co);
 #endif
@@ -305,8 +320,10 @@ qemu_coroutine_switch(Coroutine *from_, Coroutine *to_,
 
 ret = sigsetjmp(from->env, 0);
 if (ret == 0) {
-start_switch_fiber_asan(action, _stack_save, to->stack,
-to->stack_size);
+start_switch_fiber_asan(IS_ENABLED(CONFIG_COROUTINE_POOL) ||
+action != COROUTINE_TERMINATE ?
+_stack_save : NULL,
+to->stack, to->stack_size);
 start_switch_fiber_tsan(_stack_save,
 to, false); /* false=not caller */
 siglongjmp(to->env, action);

---
base-commit: f614acb7450282a119d85d759f27eae190476058
change-id: 20240112-asan-eb695c769f40

Best regards,
-- 
Akihiko Odaki