[committed] libstdc++: Add TSan annotations to std::atomic<shared_ptr<T>>

Message ID 20220914220449.276340-1-jwakely@redhat.com
State New, archived
Headers
Series [committed] libstdc++: Add TSan annotations to std::atomic<shared_ptr<T>> |

Commit Message

Jonathan Wakely Sept. 14, 2022, 10:04 p.m. UTC
  Tested powerpc64le-linux, pushed to trunk.

-- >8 --

This adds annotations to std::atomic<shared_ptr<T>> to enable TSan to
understand the custom locking. Without this, TSan reports data races for
accesses to the _M_ptr member, even though those are correctly
synchronized using atomic operations on the tagged pointer.

libstdc++-v3/ChangeLog:

	* include/bits/shared_ptr_atomic.h (_GLIBCXX_TSAN_MUTEX_DESTROY)
	(_GLIBCXX_TSAN_MUTEX_PRE_LOCK, _GLIBCXX_TSAN_MUTEX_POST_LOCK)
	(_GLIBCXX_TSAN_MUTEX_PRE_UNLOCK, _GLIBCXX_TSAN_MUTEX_POST_UNLOCK)
	(_GLIBCXX_TSAN_MUTEX_PRE_SIGNAL, _GLIBCXX_TSAN_MUTEX_POST_SIGNAL):
	Define macros for TSan annotation functions.
	(_Sp_atomic::_Atomic_count): Add annotations.
---
 libstdc++-v3/include/bits/shared_ptr_atomic.h | 38 +++++++++++++++++++
 1 file changed, 38 insertions(+)
  

Comments

Jonathan Wakely Sept. 14, 2022, 10:25 p.m. UTC | #1
On Wed, 14 Sept 2022 at 23:05, Jonathan Wakely via Libstdc++
<libstdc++@gcc.gnu.org> wrote:
>
> Tested powerpc64le-linux, pushed to trunk.
>
> -- >8 --
>
> This adds annotations to std::atomic<shared_ptr<T>> to enable TSan to
> understand the custom locking. Without this, TSan reports data races for
> accesses to the _M_ptr member, even though those are correctly
> synchronized using atomic operations on the tagged pointer.
>
> libstdc++-v3/ChangeLog:
>
>         * include/bits/shared_ptr_atomic.h (_GLIBCXX_TSAN_MUTEX_DESTROY)
>         (_GLIBCXX_TSAN_MUTEX_PRE_LOCK, _GLIBCXX_TSAN_MUTEX_POST_LOCK)
>         (_GLIBCXX_TSAN_MUTEX_PRE_UNLOCK, _GLIBCXX_TSAN_MUTEX_POST_UNLOCK)
>         (_GLIBCXX_TSAN_MUTEX_PRE_SIGNAL, _GLIBCXX_TSAN_MUTEX_POST_SIGNAL):
>         Define macros for TSan annotation functions.
>         (_Sp_atomic::_Atomic_count): Add annotations.
> ---
>  libstdc++-v3/include/bits/shared_ptr_atomic.h | 38 +++++++++++++++++++
>  1 file changed, 38 insertions(+)
>
> diff --git a/libstdc++-v3/include/bits/shared_ptr_atomic.h b/libstdc++-v3/include/bits/shared_ptr_atomic.h
> index d4bd712fc7d..4580807f42c 100644
> --- a/libstdc++-v3/include/bits/shared_ptr_atomic.h
> +++ b/libstdc++-v3/include/bits/shared_ptr_atomic.h
> @@ -32,6 +32,30 @@
>
>  #include <bits/atomic_base.h>
>
> +#if defined _GLIBCXX_TSAN && __has_include(<sanitizer/tsan_interface.h>)
> +#include <sanitizer/tsan_interface.h>
> +#define _GLIBCXX_TSAN_MUTEX_DESTROY(X) \
> +  __tsan_mutex_destroy(X, __tsan_mutex_not_static)
> +#define _GLIBCXX_TSAN_MUTEX_PRE_LOCK(X) \
> +  __tsan_mutex_pre_lock(X, __tsan_mutex_not_static)
> +#define _GLIBCXX_TSAN_MUTEX_POST_LOCK(X) \
> +  __tsan_mutex_post_lock(X, __tsan_mutex_not_static, 0)
> +#define _GLIBCXX_TSAN_MUTEX_PRE_UNLOCK(X) \
> +  __tsan_mutex_pre_unlock(X, __tsan_mutex_not_static)
> +#define _GLIBCXX_TSAN_MUTEX_POST_UNLOCK(X) \
> +  __tsan_mutex_post_unlock(X, __tsan_mutex_not_static)
> +#define _GLIBCXX_TSAN_MUTEX_PRE_SIGNAL(X) __tsan_mutex_pre_signal(X, 0)
> +#define _GLIBCXX_TSAN_MUTEX_POST_SIGNAL(X) __tsan_mutex_post_signal(X, 0)
> +#else
> +#define _GLIBCXX_TSAN_MUTEX_DESTROY(X)
> +#define _GLIBCXX_TSAN_MUTEX_PRE_LOCK(X)
> +#define _GLIBCXX_TSAN_MUTEX_POST_LOCK(X)
> +#define _GLIBCXX_TSAN_MUTEX_PRE_UNLOCK(X)
> +#define _GLIBCXX_TSAN_MUTEX_POST_UNLOCK(X)
> +#define _GLIBCXX_TSAN_MUTEX_PRE_SIGNAL(X)
> +#define _GLIBCXX_TSAN_MUTEX_POST_SIGNAL(X)
> +#endif
> +
>  namespace std _GLIBCXX_VISIBILITY(default)
>  {
>  _GLIBCXX_BEGIN_NAMESPACE_VERSION
> @@ -377,6 +401,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
>         ~_Atomic_count()
>         {
>           auto __val = _M_val.load(memory_order_relaxed);
> +         _GLIBCXX_TSAN_MUTEX_DESTROY(&_M_val);

After further thought, I'm not sure this is right. This tells tsan
that the "mutex" at &_M_val cannot be locked or unlocked again after
this. But what happens if the address is reused by a different
atomic<shared_ptr<T>> which happens to be at the same memory address?
Will tsan think that's an invalid use of the original "mutex" after
its destruction?

I will investigate.

We might need to stop using the __tsan_mutex_destroy call, and if so,
we can stop using the __tsan_mutex_not_static flag too. The pre/post
lock/unlock/signal pairs are still valuable without the lifetime
checking.
  
Jonathan Wakely Sept. 14, 2022, 10:28 p.m. UTC | #2
On Wed, 14 Sept 2022 at 23:25, Jonathan Wakely wrote:
>
> On Wed, 14 Sept 2022 at 23:05, Jonathan Wakely via Libstdc++
> <libstdc++@gcc.gnu.org> wrote:
> >
> > Tested powerpc64le-linux, pushed to trunk.
> >
> > -- >8 --
> >
> > This adds annotations to std::atomic<shared_ptr<T>> to enable TSan to
> > understand the custom locking. Without this, TSan reports data races for
> > accesses to the _M_ptr member, even though those are correctly
> > synchronized using atomic operations on the tagged pointer.
> >
> > libstdc++-v3/ChangeLog:
> >
> >         * include/bits/shared_ptr_atomic.h (_GLIBCXX_TSAN_MUTEX_DESTROY)
> >         (_GLIBCXX_TSAN_MUTEX_PRE_LOCK, _GLIBCXX_TSAN_MUTEX_POST_LOCK)
> >         (_GLIBCXX_TSAN_MUTEX_PRE_UNLOCK, _GLIBCXX_TSAN_MUTEX_POST_UNLOCK)
> >         (_GLIBCXX_TSAN_MUTEX_PRE_SIGNAL, _GLIBCXX_TSAN_MUTEX_POST_SIGNAL):
> >         Define macros for TSan annotation functions.
> >         (_Sp_atomic::_Atomic_count): Add annotations.
> > ---
> >  libstdc++-v3/include/bits/shared_ptr_atomic.h | 38 +++++++++++++++++++
> >  1 file changed, 38 insertions(+)
> >
> > diff --git a/libstdc++-v3/include/bits/shared_ptr_atomic.h b/libstdc++-v3/include/bits/shared_ptr_atomic.h
> > index d4bd712fc7d..4580807f42c 100644
> > --- a/libstdc++-v3/include/bits/shared_ptr_atomic.h
> > +++ b/libstdc++-v3/include/bits/shared_ptr_atomic.h
> > @@ -32,6 +32,30 @@
> >
> >  #include <bits/atomic_base.h>
> >
> > +#if defined _GLIBCXX_TSAN && __has_include(<sanitizer/tsan_interface.h>)
> > +#include <sanitizer/tsan_interface.h>
> > +#define _GLIBCXX_TSAN_MUTEX_DESTROY(X) \
> > +  __tsan_mutex_destroy(X, __tsan_mutex_not_static)
> > +#define _GLIBCXX_TSAN_MUTEX_PRE_LOCK(X) \
> > +  __tsan_mutex_pre_lock(X, __tsan_mutex_not_static)
> > +#define _GLIBCXX_TSAN_MUTEX_POST_LOCK(X) \
> > +  __tsan_mutex_post_lock(X, __tsan_mutex_not_static, 0)
> > +#define _GLIBCXX_TSAN_MUTEX_PRE_UNLOCK(X) \
> > +  __tsan_mutex_pre_unlock(X, __tsan_mutex_not_static)
> > +#define _GLIBCXX_TSAN_MUTEX_POST_UNLOCK(X) \
> > +  __tsan_mutex_post_unlock(X, __tsan_mutex_not_static)
> > +#define _GLIBCXX_TSAN_MUTEX_PRE_SIGNAL(X) __tsan_mutex_pre_signal(X, 0)
> > +#define _GLIBCXX_TSAN_MUTEX_POST_SIGNAL(X) __tsan_mutex_post_signal(X, 0)
> > +#else
> > +#define _GLIBCXX_TSAN_MUTEX_DESTROY(X)
> > +#define _GLIBCXX_TSAN_MUTEX_PRE_LOCK(X)
> > +#define _GLIBCXX_TSAN_MUTEX_POST_LOCK(X)
> > +#define _GLIBCXX_TSAN_MUTEX_PRE_UNLOCK(X)
> > +#define _GLIBCXX_TSAN_MUTEX_POST_UNLOCK(X)
> > +#define _GLIBCXX_TSAN_MUTEX_PRE_SIGNAL(X)
> > +#define _GLIBCXX_TSAN_MUTEX_POST_SIGNAL(X)
> > +#endif
> > +
> >  namespace std _GLIBCXX_VISIBILITY(default)
> >  {
> >  _GLIBCXX_BEGIN_NAMESPACE_VERSION
> > @@ -377,6 +401,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
> >         ~_Atomic_count()
> >         {
> >           auto __val = _M_val.load(memory_order_relaxed);
> > +         _GLIBCXX_TSAN_MUTEX_DESTROY(&_M_val);
>
> After further thought, I'm not sure this is right. This tells tsan
> that the "mutex" at &_M_val cannot be locked or unlocked again after
> this. But what happens if the address is reused by a different
> atomic<shared_ptr<T>> which happens to be at the same memory address?
> Will tsan think that's an invalid use of the original "mutex" after
> its destruction?

We can't easily add a call to __tsan_mutex_create, which would begin
the lifetime of a new object at that address, because the default
constructor is constexpr, and the create function isn't.

>
> I will investigate.
>
> We might need to stop using the __tsan_mutex_destroy call, and if so,
> we can stop using the __tsan_mutex_not_static flag too. The pre/post
> lock/unlock/signal pairs are still valuable without the lifetime
> checking.
  

Patch

diff --git a/libstdc++-v3/include/bits/shared_ptr_atomic.h b/libstdc++-v3/include/bits/shared_ptr_atomic.h
index d4bd712fc7d..4580807f42c 100644
--- a/libstdc++-v3/include/bits/shared_ptr_atomic.h
+++ b/libstdc++-v3/include/bits/shared_ptr_atomic.h
@@ -32,6 +32,30 @@ 
 
 #include <bits/atomic_base.h>
 
+#if defined _GLIBCXX_TSAN && __has_include(<sanitizer/tsan_interface.h>)
+#include <sanitizer/tsan_interface.h>
+#define _GLIBCXX_TSAN_MUTEX_DESTROY(X) \
+  __tsan_mutex_destroy(X, __tsan_mutex_not_static)
+#define _GLIBCXX_TSAN_MUTEX_PRE_LOCK(X) \
+  __tsan_mutex_pre_lock(X, __tsan_mutex_not_static)
+#define _GLIBCXX_TSAN_MUTEX_POST_LOCK(X) \
+  __tsan_mutex_post_lock(X, __tsan_mutex_not_static, 0)
+#define _GLIBCXX_TSAN_MUTEX_PRE_UNLOCK(X) \
+  __tsan_mutex_pre_unlock(X, __tsan_mutex_not_static)
+#define _GLIBCXX_TSAN_MUTEX_POST_UNLOCK(X) \
+  __tsan_mutex_post_unlock(X, __tsan_mutex_not_static)
+#define _GLIBCXX_TSAN_MUTEX_PRE_SIGNAL(X) __tsan_mutex_pre_signal(X, 0)
+#define _GLIBCXX_TSAN_MUTEX_POST_SIGNAL(X) __tsan_mutex_post_signal(X, 0)
+#else
+#define _GLIBCXX_TSAN_MUTEX_DESTROY(X)
+#define _GLIBCXX_TSAN_MUTEX_PRE_LOCK(X)
+#define _GLIBCXX_TSAN_MUTEX_POST_LOCK(X)
+#define _GLIBCXX_TSAN_MUTEX_PRE_UNLOCK(X)
+#define _GLIBCXX_TSAN_MUTEX_POST_UNLOCK(X)
+#define _GLIBCXX_TSAN_MUTEX_PRE_SIGNAL(X)
+#define _GLIBCXX_TSAN_MUTEX_POST_SIGNAL(X)
+#endif
+
 namespace std _GLIBCXX_VISIBILITY(default)
 {
 _GLIBCXX_BEGIN_NAMESPACE_VERSION
@@ -377,6 +401,7 @@  _GLIBCXX_BEGIN_NAMESPACE_VERSION
 	~_Atomic_count()
 	{
 	  auto __val = _M_val.load(memory_order_relaxed);
+	  _GLIBCXX_TSAN_MUTEX_DESTROY(&_M_val);
 	  __glibcxx_assert(!(__val & _S_lock_bit));
 	  if (auto __pi = reinterpret_cast<pointer>(__val))
 	    {
@@ -406,6 +431,8 @@  _GLIBCXX_BEGIN_NAMESPACE_VERSION
 	      __current = _M_val.load(memory_order_relaxed);
 	    }
 
+	  _GLIBCXX_TSAN_MUTEX_PRE_LOCK(&_M_val);
+
 	  while (!_M_val.compare_exchange_strong(__current,
 						 __current | _S_lock_bit,
 						 __o,
@@ -416,6 +443,7 @@  _GLIBCXX_BEGIN_NAMESPACE_VERSION
 #endif
 	      __current = __current & ~_S_lock_bit;
 	    }
+	  _GLIBCXX_TSAN_MUTEX_POST_LOCK(&_M_val);
 	  return reinterpret_cast<pointer>(__current);
 	}
 
@@ -423,7 +451,9 @@  _GLIBCXX_BEGIN_NAMESPACE_VERSION
 	void
 	unlock(memory_order __o) const noexcept
 	{
+	  _GLIBCXX_TSAN_MUTEX_PRE_UNLOCK(&_M_val);
 	  _M_val.fetch_sub(1, __o);
+	  _GLIBCXX_TSAN_MUTEX_POST_UNLOCK(&_M_val);
 	}
 
 	// Swaps the values of *this and __c, and unlocks *this.
@@ -434,7 +464,9 @@  _GLIBCXX_BEGIN_NAMESPACE_VERSION
 	  if (__o != memory_order_seq_cst)
 	    __o = memory_order_release;
 	  auto __x = reinterpret_cast<uintptr_t>(__c._M_pi);
+	  _GLIBCXX_TSAN_MUTEX_PRE_UNLOCK(&_M_val);
 	  __x = _M_val.exchange(__x, __o);
+	  _GLIBCXX_TSAN_MUTEX_POST_UNLOCK(&_M_val);
 	  __c._M_pi = reinterpret_cast<pointer>(__x & ~_S_lock_bit);
 	}
 
@@ -443,20 +475,26 @@  _GLIBCXX_BEGIN_NAMESPACE_VERSION
 	void
 	_M_wait_unlock(memory_order __o) const noexcept
 	{
+	  _GLIBCXX_TSAN_MUTEX_PRE_UNLOCK(&_M_val);
 	  auto __v = _M_val.fetch_sub(1, memory_order_relaxed);
+	  _GLIBCXX_TSAN_MUTEX_POST_UNLOCK(&_M_val);
 	  _M_val.wait(__v & ~_S_lock_bit, __o);
 	}
 
 	void
 	notify_one() noexcept
 	{
+	  _GLIBCXX_TSAN_MUTEX_PRE_SIGNAL(&_M_val);
 	  _M_val.notify_one();
+	  _GLIBCXX_TSAN_MUTEX_POST_SIGNAL(&_M_val);
 	}
 
 	void
 	notify_all() noexcept
 	{
+	  _GLIBCXX_TSAN_MUTEX_PRE_SIGNAL(&_M_val);
 	  _M_val.notify_all();
+	  _GLIBCXX_TSAN_MUTEX_POST_SIGNAL(&_M_val);
 	}
 #endif