GH-139653: Only raise an exception (or fatal error) when the stack pointer is about...

Only raises if the stack pointer is both below the limit *and* above the stack base.
This prevents false positives for user-space threads, as the stack pointer will be outside those bounds
if the stack has been swapped.

diff --git a/Include/internal/pycore_ceval.h b/Include/internal/pycore_ceval.h
index 47c42fccdc2376a7da33ff83d50a6906cbdcee15..2ae84be7b33966d00f44d9faa25c6e155f61f9ff 100644 (file)
--- a/Include/internal/pycore_ceval.h
+++ b/Include/internal/pycore_ceval.h
@@ -217,10 +217,13 @@ extern void _PyEval_DeactivateOpCache(void);
 static inline int _Py_MakeRecCheck(PyThreadState *tstate)  {
     uintptr_t here_addr = _Py_get_machine_stack_pointer();
     _PyThreadStateImpl *_tstate = (_PyThreadStateImpl *)tstate;
+    // Overflow if stack pointer is between soft limit and the base of the hardware stack.
+    // If it is below the hardware stack base, assume that we have the wrong stack limits, and do nothing.
+    // We could have the wrong stack limits because of limited platform support, or user-space threads.
 #if _Py_STACK_GROWS_DOWN
-    return here_addr < _tstate->c_stack_soft_limit;
+    return here_addr < _tstate->c_stack_soft_limit && here_addr >= _tstate->c_stack_soft_limit - 2 * _PyOS_STACK_MARGIN_BYTES;
 #else
-    return here_addr > _tstate->c_stack_soft_limit;
+    return here_addr > _tstate->c_stack_soft_limit && here_addr <= _tstate->c_stack_soft_limit + 2 * _PyOS_STACK_MARGIN_BYTES;
 #endif
 }
 

diff --git a/InternalDocs/stack_protection.md b/InternalDocs/stack_protection.md
index fa025bd930f74ed2272cdc7cb7c0ed0176fc5d11..14802e57d095f4d17029eece371a565c421115c9 100644 (file)
--- a/InternalDocs/stack_protection.md
+++ b/InternalDocs/stack_protection.md
@@ -38,12 +38,19 @@ Recursion checks are performed by `_Py_EnterRecursiveCall()` or `_Py_EnterRecurs
 
 ```python
 kb_used = (stack_top - stack_pointer)>>10
-if stack_pointer < hard_limit:
+if stack_pointer < bottom_of_machine_stack:
+    pass # Our stack limits could be wrong so it is safest to do nothing.
+elif stack_pointer < hard_limit:
     FatalError(f"Unrecoverable stack overflow (used {kb_used} kB)")
 elif stack_pointer < soft_limit:
     raise RecursionError(f"Stack overflow (used {kb_used} kB)")
 ```
 
+### User space threads and other oddities
+
+Some libraries provide user-space threads. These will change the C stack at runtime.
+To guard against this we only raise if the stack pointer is in the window between the expected stack base and the soft limit.
+
 ### Diagnosing and fixing stack overflows
 
 For stack protection to work correctly the amount of stack consumed between calls to `_Py_EnterRecursiveCall()` must be less than `_PyOS_STACK_MARGIN_BYTES`.

diff --git a/Misc/NEWS.d/next/Core_and_Builtins/2025-11-17-14-40-45.gh-issue-139653.LzOy1M.rst b/Misc/NEWS.d/next/Core_and_Builtins/2025-11-17-14-40-45.gh-issue-139653.LzOy1M.rst
new file mode 100644 (file)
index 0000000..c3ae0e8
--- /dev/null
+++ b/Misc/NEWS.d/next/Core_and_Builtins/2025-11-17-14-40-45.gh-issue-139653.LzOy1M.rst
@@ -0,0 +1,4 @@
+Only raise a ``RecursionError`` or trigger a fatal error if the stack
+pointer is both below the limit pointer *and* above the stack base. If
+outside of these bounds assume that it is OK. This prevents false positives
+when user-space threads swap stacks.

diff --git a/Python/ceval.c b/Python/ceval.c
index 14fef42ea967d61fab063c717e743ce907b320dc..5381cd826dfd197693e27bfc68a915dd8f278a0d 100644 (file)
--- a/Python/ceval.c
+++ b/Python/ceval.c
@@ -362,9 +362,11 @@ _Py_ReachedRecursionLimitWithMargin(PyThreadState *tstate, int margin_count)
         _Py_InitializeRecursionLimits(tstate);
     }
 #if _Py_STACK_GROWS_DOWN
-    return here_addr <= _tstate->c_stack_soft_limit + margin_count * _PyOS_STACK_MARGIN_BYTES;
+    return here_addr <= _tstate->c_stack_soft_limit + margin_count * _PyOS_STACK_MARGIN_BYTES &&
+        here_addr >= _tstate->c_stack_soft_limit - 2 * _PyOS_STACK_MARGIN_BYTES;
 #else
-    return here_addr > _tstate->c_stack_soft_limit - margin_count * _PyOS_STACK_MARGIN_BYTES;
+    return here_addr > _tstate->c_stack_soft_limit - margin_count * _PyOS_STACK_MARGIN_BYTES &&
+        here_addr <= _tstate->c_stack_soft_limit + 2 * _PyOS_STACK_MARGIN_BYTES;
 #endif
 }
 
@@ -455,7 +457,7 @@ int pthread_attr_destroy(pthread_attr_t *a)
 #endif
 
 static void
-hardware_stack_limits(uintptr_t *base, uintptr_t *top)
+hardware_stack_limits(uintptr_t *base, uintptr_t *top, uintptr_t sp)
 {
 #ifdef WIN32
     ULONG_PTR low, high;
@@ -491,10 +493,19 @@ hardware_stack_limits(uintptr_t *base, uintptr_t *top)
         return;
     }
 #  endif
-    uintptr_t here_addr = _Py_get_machine_stack_pointer();
-    uintptr_t top_addr = _Py_SIZE_ROUND_UP(here_addr, 4096);
+    // Add some space for caller function then round to minimum page size
+    // This is a guess at the top of the stack, but should be a reasonably
+    // good guess if called from _PyThreadState_Attach when creating a thread.
+    // If the thread is attached deep in a call stack, then the guess will be poor.
+#if _Py_STACK_GROWS_DOWN
+    uintptr_t top_addr = _Py_SIZE_ROUND_UP(sp + 8*sizeof(void*), SYSTEM_PAGE_SIZE);
     *top = top_addr;
     *base = top_addr - Py_C_STACK_SIZE;
+#  else
+    uintptr_t base_addr = _Py_SIZE_ROUND_DOWN(sp - 8*sizeof(void*), SYSTEM_PAGE_SIZE);
+    *base = base_addr;
+    *top = base_addr + Py_C_STACK_SIZE;
+#endif
 #endif
 }
 
@@ -543,7 +554,8 @@ void
 _Py_InitializeRecursionLimits(PyThreadState *tstate)
 {
     uintptr_t base, top;
-    hardware_stack_limits(&base, &top);
+    uintptr_t here_addr = _Py_get_machine_stack_pointer();
+    hardware_stack_limits(&base, &top, here_addr);
     assert(top != 0);
 
     tstate_set_stack(tstate, base, top);
@@ -587,7 +599,7 @@ PyUnstable_ThreadState_ResetStackProtection(PyThreadState *tstate)
 
 
 /* The function _Py_EnterRecursiveCallTstate() only calls _Py_CheckRecursiveCall()
-   if the recursion_depth reaches recursion_limit. */
+   if the stack pointer is between the stack base and c_stack_hard_limit. */
 int
 _Py_CheckRecursiveCall(PyThreadState *tstate, const char *where)
 {
@@ -596,10 +608,12 @@ _Py_CheckRecursiveCall(PyThreadState *tstate, const char *where)
     assert(_tstate->c_stack_soft_limit != 0);
     assert(_tstate->c_stack_hard_limit != 0);
 #if _Py_STACK_GROWS_DOWN
+    assert(here_addr >= _tstate->c_stack_hard_limit - _PyOS_STACK_MARGIN_BYTES);
     if (here_addr < _tstate->c_stack_hard_limit) {
         /* Overflowing while handling an overflow. Give up. */
         int kbytes_used = (int)(_tstate->c_stack_top - here_addr)/1024;
 #else
+    assert(here_addr <= _tstate->c_stack_hard_limit + _PyOS_STACK_MARGIN_BYTES);
     if (here_addr > _tstate->c_stack_hard_limit) {
         /* Overflowing while handling an overflow. Give up. */
         int kbytes_used = (int)(here_addr - _tstate->c_stack_top)/1024;