data race when resizing unicode objects

[kumaraditya303]

When running ctypes tests in parallel, the following data race is detected:

env TSAN_OPTIONS="suppressions=Tools/tsan/suppressions_free_threading.txt halt_on_error=1" ./python -m test test_ctypes --parallel-threads 4

==================
WARNING: ThreadSanitizer: data race (pid=19492)
  Atomic read of size 8 at 0x7f1b0a230680 by thread T1323:
    #0 _Py_atomic_load_uintptr_relaxed /home/realkumaraditya/cpython/./Include/cpython/pyatomic_gcc.h:375:10 (python+0x271055) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #1 _Py_IsOwnedByCurrentThread /home/realkumaraditya/cpython/./Include/object.h:254:12 (python+0x271055)
    #2 _Py_TryIncrefFast /home/realkumaraditya/cpython/./Include/internal/pycore_object.h:558:9 (python+0x271055)
    #3 _Py_TryIncrefCompare /home/realkumaraditya/cpython/./Include/internal/pycore_object.h:597:9 (python+0x271055)
    #4 compare_unicode_unicode_threadsafe /home/realkumaraditya/cpython/Objects/dictobject.c:1432:18 (python+0x271055)
    #5 do_lookup /home/realkumaraditya/cpython/Objects/dictobject.c:1013:23 (python+0x271055)
    #6 unicodekeys_lookup_unicode_threadsafe /home/realkumaraditya/cpython/Objects/dictobject.c:1449:12 (python+0x271055)
    #7 _Py_dict_lookup_threadsafe /home/realkumaraditya/cpython/Objects/dictobject.c:1504:18 (python+0x270757) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #8 _PyDict_GetItemRef_KnownHash /home/realkumaraditya/cpython/Objects/dictobject.c:2353:21 (python+0x272c0e) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #9 PyDict_GetItemRef /home/realkumaraditya/cpython/Objects/dictobject.c:2389:12 (python+0x272c0e)
    #10 cache_struct_converter /home/realkumaraditya/cpython/./Modules/_struct.c:2524:9 (_struct.cpython-314t-x86_64-linux-gnu.so+0x5338) (BuildId: cd844f32564aba7a2b18bdb1e258a78c397c8ebc)
    #11 calcsize /home/realkumaraditya/cpython/./Modules/clinic/_struct.c.h:266:10 (_struct.cpython-314t-x86_64-linux-gnu.so+0x4ac7) (BuildId: cd844f32564aba7a2b18bdb1e258a78c397c8ebc)
    #12 _PyEval_EvalFrameDefault /home/realkumaraditya/cpython/Python/generated_cases.c.h:2225:35 (python+0x3fef50) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #13 _PyEval_EvalFrame /home/realkumaraditya/cpython/./Include/internal/pycore_ceval.h:119:16 (python+0x3f7150) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #14 _PyEval_Vector /home/realkumaraditya/cpython/Python/ceval.c:1908:12 (python+0x3f7150)
    #15 _PyFunction_Vectorcall /home/realkumaraditya/cpython/Objects/call.c (python+0x1f1cdf) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #16 _PyObject_VectorcallTstate /home/realkumaraditya/cpython/./Include/internal/pycore_call.h:169:11 (python+0x1f66b0) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #17 method_vectorcall /home/realkumaraditya/cpython/Objects/classobject.c:94:18 (python+0x1f66b0)
    #18 _PyVectorcall_Call /home/realkumaraditya/cpython/Objects/call.c:273:16 (python+0x1f196f) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #19 _PyObject_Call /home/realkumaraditya/cpython/Objects/call.c:348:16 (python+0x1f196f)
    #20 PyObject_Call /home/realkumaraditya/cpython/Objects/call.c:373:12 (python+0x1f19d5) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #21 _PyEval_EvalFrameDefault /home/realkumaraditya/cpython/Python/generated_cases.c.h:2411:32 (python+0x3ff399) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #22 _PyEval_EvalFrame /home/realkumaraditya/cpython/./Include/internal/pycore_ceval.h:119:16 (python+0x3f7150) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #23 _PyEval_Vector /home/realkumaraditya/cpython/Python/ceval.c:1908:12 (python+0x3f7150)
    #24 _PyFunction_Vectorcall /home/realkumaraditya/cpython/Objects/call.c (python+0x1f1cdf) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #25 _PyObject_VectorcallTstate /home/realkumaraditya/cpython/./Include/internal/pycore_call.h:169:11 (python+0x1f65ff) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #26 method_vectorcall /home/realkumaraditya/cpython/Objects/classobject.c:72:20 (python+0x1f65ff)
    #27 _PyVectorcall_Call /home/realkumaraditya/cpython/Objects/call.c:273:16 (python+0x1f196f) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #28 _PyObject_Call /home/realkumaraditya/cpython/Objects/call.c:348:16 (python+0x1f196f)
    #29 PyObject_Call /home/realkumaraditya/cpython/Objects/call.c:373:12 (python+0x1f19d5) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #30 thread_run /home/realkumaraditya/cpython/./Modules/_threadmodule.c:353:21 (python+0x5998d2) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #31 pythread_wrapper /home/realkumaraditya/cpython/Python/thread_pthread.h:242:5 (python+0x4f4157) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)

  Previous write of size 8 at 0x7f1b0a230680 by thread T1321:
    #0 __tsan_memcpy <null> (python+0xdd10f) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #1 _mi_memcpy /home/realkumaraditya/cpython/./Include/internal/mimalloc/mimalloc/internal.h:929:3 (python+0x2af9bf) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #2 _mi_heap_realloc_zero /home/realkumaraditya/cpython/Objects/mimalloc/alloc.c:745:7 (python+0x2af9bf)
    #3 mi_heap_realloc /home/realkumaraditya/cpython/Objects/mimalloc/alloc.c:753:10 (python+0x2cce30) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #4 _PyObject_MiRealloc /home/realkumaraditya/cpython/Objects/obmalloc.c:276:12 (python+0x2cce30)
    #5 PyObject_Realloc /home/realkumaraditya/cpython/Objects/obmalloc.c:1416:12 (python+0x2cfc12) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #6 resize_compact /home/realkumaraditya/cpython/Objects/unicodeobject.c:1178:31 (python+0x359915) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #7 _PyUnicodeWriter_Finish /home/realkumaraditya/cpython/Objects/unicodeobject.c:14157:16 (python+0x33162a) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #8 PyUnicode_Format /home/realkumaraditya/cpython/Objects/unicodeobject.c:15361:12 (python+0x35e728) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #9 unicode_mod /home/realkumaraditya/cpython/Objects/unicodeobject.c:14332:12 (python+0x36df71) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #10 binary_op1 /home/realkumaraditya/cpython/Objects/abstract.c:964:13 (python+0x1bdb83) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #11 binary_op /home/realkumaraditya/cpython/Objects/abstract.c:1003:24 (python+0x1be2a8) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #12 PyNumber_Remainder /home/realkumaraditya/cpython/Objects/abstract.c:1187:1 (python+0x1be2a8)
    #13 _PyEval_EvalFrameDefault /home/realkumaraditya/cpython/Python/generated_cases.c.h:62:35 (python+0x3f7ae5) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #14 _PyEval_EvalFrame /home/realkumaraditya/cpython/./Include/internal/pycore_ceval.h:119:16 (python+0x3f7150) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #15 _PyEval_Vector /home/realkumaraditya/cpython/Python/ceval.c:1908:12 (python+0x3f7150)
    #16 _PyFunction_Vectorcall /home/realkumaraditya/cpython/Objects/call.c (python+0x1f1cdf) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #17 _PyObject_VectorcallTstate /home/realkumaraditya/cpython/./Include/internal/pycore_call.h:169:11 (python+0x1f66b0) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #18 method_vectorcall /home/realkumaraditya/cpython/Objects/classobject.c:94:18 (python+0x1f66b0)
    #19 _PyVectorcall_Call /home/realkumaraditya/cpython/Objects/call.c:273:16 (python+0x1f196f) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #20 _PyObject_Call /home/realkumaraditya/cpython/Objects/call.c:348:16 (python+0x1f196f)
    #21 PyObject_Call /home/realkumaraditya/cpython/Objects/call.c:373:12 (python+0x1f19d5) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #22 _PyEval_EvalFrameDefault /home/realkumaraditya/cpython/Python/generated_cases.c.h:2411:32 (python+0x3ff399) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #23 _PyEval_EvalFrame /home/realkumaraditya/cpython/./Include/internal/pycore_ceval.h:119:16 (python+0x3f7150) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #24 _PyEval_Vector /home/realkumaraditya/cpython/Python/ceval.c:1908:12 (python+0x3f7150)
    #25 _PyFunction_Vectorcall /home/realkumaraditya/cpython/Objects/call.c (python+0x1f1cdf) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #26 _PyObject_VectorcallTstate /home/realkumaraditya/cpython/./Include/internal/pycore_call.h:169:11 (python+0x1f65ff) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #27 method_vectorcall /home/realkumaraditya/cpython/Objects/classobject.c:72:20 (python+0x1f65ff)
    #28 _PyVectorcall_Call /home/realkumaraditya/cpython/Objects/call.c:273:16 (python+0x1f196f) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #29 _PyObject_Call /home/realkumaraditya/cpython/Objects/call.c:348:16 (python+0x1f196f)
    #30 PyObject_Call /home/realkumaraditya/cpython/Objects/call.c:373:12 (python+0x1f19d5) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #31 thread_run /home/realkumaraditya/cpython/./Modules/_threadmodule.c:353:21 (python+0x5998d2) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)
    #32 pythread_wrapper /home/realkumaraditya/cpython/Python/thread_pthread.h:242:5 (python+0x4f4157) (BuildId: 27b79e16bbd11b196a3f4a8232b4b09ecf4e18ee)

Linked PRs

• gh-132070: use _PyObject_IsUniquelyReferenced in unicodeobject #132091

[kumaraditya303]

I think in free-threading Py_REFCNT(op)==1 should be replaced by PyObject_IsUniquelyReferenced in such functions in unicodeobject.c:

cpython/Objects/unicodeobject.c

Lines 1197 to 1202 in a126cef

	static int
	resize_inplace(PyObject *unicode, Py_ssize_t length)
	{
	assert(!PyUnicode_IS_COMPACT(unicode));
	assert(Py_REFCNT(unicode) == 1);

[colesbury]

We should leave the assertions as is. I don't think that's related to this.

The race is because PyObject_Realloc() calls memcpy to fill in the new allocation, if the existing allocation can't be reused. The memcpy doesn't use relaxed atomic writes, so it can race with an one of the optimistic, non-locking reads.

For now, we should just add a suppression.

[colesbury]

We should change Py_REFCNT(op)==1 to PyObject_IsUniquelyReferenced for places where it controls behaviors, such as in if-statements, but the uses in assertions don't really matter.