Merge branch 'master' into sh_merge_master

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -6,7 +6,8 @@ body:
   - type: markdown
     attributes:
       value: |
-        Maintainers will only make a best effort to triage PRs. Please do your best to make the issue as easy to act on as possible, and only open if clearly a problem with pybind11 (ask first if unsure).
+        Please do your best to make the issue as easy to act on as possible, and only submit here if there is clearly a problem with pybind11 (ask first if unsure). **Note that a reproducer in a PR is much more likely to get immediate attention.**
+
   - type: checkboxes
     id: steps
     attributes:
@@ -20,6 +21,12 @@ body:
         - label: Consider asking first in the [Gitter chat room](https://gitter.im/pybind/Lobby) or in a [Discussion](https:/pybind/pybind11/discussions/new).
           required: false
 
+  - type: Input
+    id: version
+    attributes:
+      label: What version (or hash if on master) of pybind11 are you using?
+      required: true
+
   - type: textarea
     id: description
     attributes:
@@ -40,6 +47,14 @@ body:
         The code should be minimal, have no external dependencies, isolate the
         function(s) that cause breakage. Submit matched and complete C++ and
         Python snippets that can be easily compiled and run to diagnose the
-        issue. If possible, make a PR with a new, failing test to give us a
+        issue. — Note that a reproducer in a PR is much more likely to get
-        starting point to work on!
+        immediate attention: failing tests in the pybind11 CI are the best
+        starting point for working out fixes.
       render: text
+
+  - type: Input
+    id: regression
+    attributes:
+      label: Is this a regression? Put the last known working version here if it is.
+      description: Put the last known working version here if this is a regression.
+      value: Not a regression

.github/workflows/ci.yml

@@ -31,7 +31,7 @@ jobs:
         - '3.6'
         - '3.9'
         - '3.10'
-        - '3.11-dev'
+        - '3.11'
         - 'pypy-3.7'
         - 'pypy-3.8'
         - 'pypy-3.9'
@@ -103,10 +103,12 @@ jobs:
       run: python -m pip install pytest-github-actions-annotate-failures
 
     # First build - C++11 mode and inplace
+    # More-or-less randomly adding -DPYBIND11_SIMPLE_GIL_MANAGEMENT=ON here.
     - name: Configure C++11 ${{ matrix.args }}
       run: >
         cmake -S . -B .
         -DPYBIND11_WERROR=ON
+        -DPYBIND11_SIMPLE_GIL_MANAGEMENT=ON
         -DDOWNLOAD_CATCH=ON
         -DDOWNLOAD_EIGEN=ON
         -DCMAKE_CXX_STANDARD=11
@@ -120,7 +122,7 @@ jobs:
 
     - name: C++11 tests
       # TODO: Figure out how to load the DLL on Python 3.8+
-      if: "!(runner.os == 'Windows' && (matrix.python == 3.8 || matrix.python == 3.9 || matrix.python == '3.10' || matrix.python == '3.11-dev' || matrix.python == 'pypy-3.8'))"
+      if: "!(runner.os == 'Windows' && (matrix.python == 3.8 || matrix.python == 3.9 || matrix.python == '3.10' || matrix.python == '3.11' || matrix.python == 'pypy-3.8'))"
       run: cmake --build .  --target cpptest -j 2
 
     - name: Interface test C++11
@@ -130,10 +132,12 @@ jobs:
       run: git clean -fdx
 
     # Second build - C++17 mode and in a build directory
+    # More-or-less randomly adding -DPYBIND11_SIMPLE_GIL_MANAGEMENT=OFF here.
     - name: Configure C++17
       run: >
         cmake -S . -B build2
         -DPYBIND11_WERROR=ON
+        -DPYBIND11_SIMPLE_GIL_MANAGEMENT=OFF
         -DDOWNLOAD_CATCH=ON
         -DDOWNLOAD_EIGEN=ON
         -DCMAKE_CXX_STANDARD=17
@@ -147,7 +151,7 @@ jobs:
 
     - name: C++ tests
       # TODO: Figure out how to load the DLL on Python 3.8+
-      if: "!(runner.os == 'Windows' && (matrix.python == 3.8 || matrix.python == 3.9 || matrix.python == '3.10' || matrix.python == '3.11-dev' || matrix.python == 'pypy-3.8'))"
+      if: "!(runner.os == 'Windows' && (matrix.python == 3.8 || matrix.python == 3.9 || matrix.python == '3.10' || matrix.python == '3.11' || matrix.python == 'pypy-3.8'))"
       run: cmake --build build2 --target cpptest
 
     # Third build - C++17 mode with unstable ABI
@@ -187,7 +191,7 @@ jobs:
         - python-version: "3.9"
           python-debug: true
           valgrind: true
-        - python-version: "3.11-dev"
+        - python-version: "3.11"
           python-debug: false
 
     name: "🐍 ${{ matrix.python-version }}${{ matrix.python-debug && '-dbg' || '' }} (deadsnakes)${{ matrix.valgrind && ' • Valgrind' || '' }} • x64"
@@ -392,7 +396,7 @@ jobs:
   # Testing on CentOS 7 + PGI compilers, which seems to require more workarounds
   centos-nvhpc7:
     runs-on: ubuntu-latest
-    name: "🐍 3 • CentOS7 / PGI 22.3 • x64"
+    name: "🐍 3 • CentOS7 / PGI 22.9 • x64"
     container: centos:7
 
     steps:
@@ -402,7 +406,7 @@ jobs:
       run: yum update -y && yum install -y epel-release && yum install -y git python3-devel make environment-modules cmake3 yum-utils
 
     - name: Install NVidia HPC SDK
-      run: yum-config-manager --add-repo https://developer.download.nvidia.com/hpc-sdk/rhel/nvhpc.repo && yum -y install nvhpc-22.3
+      run: yum-config-manager --add-repo https://developer.download.nvidia.com/hpc-sdk/rhel/nvhpc.repo && yum -y install nvhpc-22.9
 
     # On CentOS 7, we have to filter a few tests (compiler internal error)
     # and allow deeper template recursion (not needed on CentOS 8 with a newer
@@ -412,12 +416,12 @@ jobs:
       shell: bash
       run: |
         source /etc/profile.d/modules.sh
-        module load /opt/nvidia/hpc_sdk/modulefiles/nvhpc/22.3
+        module load /opt/nvidia/hpc_sdk/modulefiles/nvhpc/22.9
         cmake3 -S . -B build -DDOWNLOAD_CATCH=ON \
                             -DCMAKE_CXX_STANDARD=11 \
                             -DPYTHON_EXECUTABLE=$(python3 -c "import sys; print(sys.executable)") \
                             -DCMAKE_CXX_FLAGS="-Wc,--pending_instantiations=0" \
-                            -DPYBIND11_TEST_FILTER="test_smart_ptr.cpp;test_virtual_functions.cpp"
+                            -DPYBIND11_TEST_FILTER="test_smart_ptr.cpp"
 
     # Building before installing Pip should produce a warning but not an error
     - name: Build

.github/workflows/labeler.yml

@@ -10,7 +10,11 @@ jobs:
     steps:
 
     - uses: actions/labeler@main
-      if: github.event.pull_request.merged == true
+      if: >
+        github.event.pull_request.merged == true &&
+        !startsWith(github.event.pull_request.title, 'chore(deps):') &&
+        !startsWith(github.event.pull_request.title, 'ci(fix):') &&
+        !startsWith(github.event.pull_request.title, 'docs(changelog):')
       with:
         repo-token: ${{ secrets.GITHUB_TOKEN }}
         configuration-path: .github/labeler_merged.yml

CMakeLists.txt

@@ -91,10 +91,16 @@ endif()
 option(PYBIND11_INSTALL "Install pybind11 header files?" ${PYBIND11_MASTER_PROJECT})
 option(PYBIND11_TEST "Build pybind11 test suite?" ${PYBIND11_MASTER_PROJECT})
 option(PYBIND11_NOPYTHON "Disable search for Python" OFF)
+option(PYBIND11_SIMPLE_GIL_MANAGEMENT
+       "Use simpler GIL management logic that does not support disassociation" OFF)
 set(PYBIND11_INTERNALS_VERSION
     ""
     CACHE STRING "Override the ABI version, may be used to enable the unstable ABI.")
 
+if(PYBIND11_SIMPLE_GIL_MANAGEMENT)
+  add_compile_definitions(PYBIND11_SIMPLE_GIL_MANAGEMENT)
+endif()
+
 cmake_dependent_option(
   USE_PYTHON_INCLUDE_DIR
   "Install pybind11 headers in Python include directory instead of default installation prefix"

docs/changelog.rst

@@ -16,6 +16,104 @@ IN DEVELOPMENT
 
 Changes will be summarized here periodically.
 
+Version 2.10.1 (Oct 2?, 2022)
+-----------------------------
+
+
+Changes:
+
+
+* Allow ``pybind11::capsule`` constructor to take null destructor pointers.
+  `#4221 <https://github.com/pybind/pybind11/pull/4221>`_
+
+* ``embed.h`` was changed so that ``PYTHONPATH`` is used also with Python 3.11
+  (established behavior).
+  `#4119 <https://github.com/pybind/pybind11/pull/4119>`_
+
+Bug fixes:
+
+* Fix MSVC 2019 v.1924 & C++14 mode error for ``overload_cast``.
+  `#4188 <https://github.com/pybind/pybind11/pull/4188>`_
+
+* Make augmented assignment operators non-const for the object-api. Behavior
+  was previously broken for augmented assignment operators.
+  `#4065 <https://github.com/pybind/pybind11/pull/4065>`_
+
+* Add proper error checking to C++ bindings for Python list append and insert.
+  `#4208 <https://github.com/pybind/pybind11/pull/4208>`_
+
+* Work-around for Nvidia's CUDA nvcc compiler in versions 11.4.0 - 11.8.0.
+  `#4220 <https://github.com/pybind/pybind11/pull/4220>`_
+
+* A workaround for PyPy was added in the ``py::error_already_set``
+  implementation, related to PR `#1895 <https://github.com/pybind/pybind11/pull/1895>`_
+  released with v2.10.0.
+  `#4079 <https://github.com/pybind/pybind11/pull/4079>`_
+
+* Fixed compiler errors when C++23 ``std::forward_like`` is available.
+  `#4136 <https://github.com/pybind/pybind11/pull/4136>`_
+
+* Properly raise exceptions in contains methods (like when an object in unhashable).
+  `#4209 <https://github.com/pybind/pybind11/pull/4209>`_
+
+* Further improve another error in exception handling.
+  `#4232 <https://github.com/pybind/pybind11/pull/4232>`_
+
+* ``get_local_internals()`` was made compatible with
+  ``finalize_interpreter()``, fixing potential freezes during interpreter
+  finalization.
+  `#4192 <https://github.com/pybind/pybind11/pull/4192>`_
+
+
+Performance and style:
+
+* Reserve space in set and STL map casters if possible. This will prevent
+  unnecessary rehashing / resizing by knowing the number of keys ahead of time
+  for Python to C++ casting. This improvement will greatly speed up the casting
+  of large unordered maps and sets.
+  `#4194 <https://github.com/pybind/pybind11/pull/4194>`_
+
+* GIL RAII scopes are non-copyable to avoid potential bugs.
+  `#4183 <https://github.com/pybind/pybind11/pull/4183>`_
+
+* Explicitly default all relevant ctors for pytypes in the ``PYBIND11_OBJECT``
+  macros and enforce the clang-tidy checks ``modernize-use-equals-default`` in
+  macros as well.
+  `#4017 <https://github.com/pybind/pybind11/pull/4017>`_
+
+* Optimize iterator advancement in C++ bindings.
+  `#4237 <https://github.com/pybind/pybind11/pull/4237>`_
+
+* Use the modern ``PyObject_GenericGetDict`` and ``PyObject_GenericSetDict``
+  for handling dynamic attribute dictionaries.
+  `#4106 <https://github.com/pybind/pybind11/pull/4106>`_
+
+* Document that users should use ``PYBIND11_NAMESPACE`` instead of using ``pybind11`` when
+  opening namespaces. Using namespace declarations and namespace qualification
+  remain the same as ``pybind11``. This is done to ensure consistent symbol
+  visibility.
+  `#4098 <https://github.com/pybind/pybind11/pull/4098>`_
+
+* Mark ``detail::forward_like`` as constexpr.
+  `#4147 <https://github.com/pybind/pybind11/pull/4147>`_
+
+* Optimize unpacking_collector when processing ``arg_v`` arguments.
+  `#4219 <https://github.com/pybind/pybind11/pull/4219>`_
+
+
+Build system improvements:
+
+* Include a pkg-config file when installing pybind11, such as in the Python
+  package.
+  `#4077 <https://github.com/pybind/pybind11/pull/4077>`_
+
+* Avoid stripping debug symbols when ``CMAKE_BUILD_TYPE`` is set to ``DEBUG``
+  instead of ``Debug``.
+  `#4078 <https://github.com/pybind/pybind11/pull/4078>`_
+
+* Followup to `#3948 <https://github.com/pybind/pybind11/pull/3948>`_, fixing vcpkg again.
+  `#4123 <https://github.com/pybind/pybind11/pull/4123>`_
+
 Version 2.10.0 (Jul 15, 2022)
 -----------------------------
 

include/pybind11/cast.h

@@ -278,7 +278,7 @@ public:
         return false;
     }
     static handle cast(T, return_value_policy /* policy */, handle /* parent */) {
-        return none().inc_ref();
+        return none().release();
     }
     PYBIND11_TYPE_CASTER(T, const_name("None"));
 };
@@ -321,7 +321,7 @@ public:
         if (ptr) {
             return capsule(ptr).release();
         }
-        return none().inc_ref();
+        return none().release();
     }
 
     template <typename T>
@@ -571,7 +571,7 @@ public:
 
     static handle cast(const CharT *src, return_value_policy policy, handle parent) {
         if (src == nullptr) {
-            return pybind11::none().inc_ref();
+            return pybind11::none().release();
         }
         return StringCaster::cast(StringType(src), policy, parent);
     }
@@ -1220,11 +1220,9 @@ enable_if_t<cast_is_temporary_value_reference<T>::value, T> cast_safe(object &&)
     pybind11_fail("Internal error: cast_safe fallback invoked");
 }
 template <typename T>
-enable_if_t<std::is_same<void, intrinsic_t<T>>::value, void> cast_safe(object &&) {}
+enable_if_t<std::is_void<T>::value, void> cast_safe(object &&) {}
 template <typename T>
-enable_if_t<detail::none_of<cast_is_temporary_value_reference<T>,
+enable_if_t<detail::none_of<cast_is_temporary_value_reference<T>, std::is_void<T>>::value, T>
-                            std::is_same<void, intrinsic_t<T>>>::value,
-            T>
 cast_safe(object &&o) {
     return pybind11::cast<T>(std::move(o));
 }

include/pybind11/detail/common.h

@@ -205,11 +205,8 @@
 #    endif
 #endif
 
-#if defined(__cpp_lib_char8_t) && __cpp_lib_char8_t >= 201811L
-#    define PYBIND11_HAS_U8STRING
-#endif
-
 #include <Python.h>
+// Reminder: WITH_THREAD is always defined if PY_VERSION_HEX >= 0x03070000
 #if PY_VERSION_HEX < 0x03060000
 #    error "PYTHON < 3.6 IS UNSUPPORTED. pybind11 v2.9 was the last to support Python 2 and 3.5."
 #endif
@@ -233,6 +230,10 @@
 #    undef copysign
 #endif
 
+#if defined(PYPY_VERSION) && !defined(PYBIND11_SIMPLE_GIL_MANAGEMENT)
+#    define PYBIND11_SIMPLE_GIL_MANAGEMENT
+#endif
+
 #if defined(_MSC_VER)
 #    if defined(PYBIND11_DEBUG_MARKER)
 #        define _DEBUG
@@ -259,6 +260,11 @@
 #    endif
 #endif
 
+// Must be after including <version> or one of the other headers specified by the standard
+#if defined(__cpp_lib_char8_t) && __cpp_lib_char8_t >= 201811L
+#    define PYBIND11_HAS_U8STRING
+#endif
+
 // #define PYBIND11_STR_LEGACY_PERMISSIVE
 // If DEFINED, pybind11::str can hold PyUnicodeObject or PyBytesObject
 //             (probably surprising and never documented, but this was the

include/pybind11/detail/internals.h

@@ -9,6 +9,12 @@
 
 #pragma once
 
+#include "common.h"
+
+#if defined(WITH_THREAD) && defined(PYBIND11_SIMPLE_GIL_MANAGEMENT)
+#    include "../gil.h"
+#endif
+
 #include "../pytypes.h"
 #include "smart_holder_sfinae_hooks_only.h"
 
@@ -50,7 +56,7 @@ inline PyObject *make_object_base_type(PyTypeObject *metaclass);
 // `Py_LIMITED_API` anyway.
 #    if PYBIND11_INTERNALS_VERSION > 4
 #        define PYBIND11_TLS_KEY_REF Py_tss_t &
-#        ifdef __GNUC__
+#        if defined(__GNUC__) && !defined(__INTEL_COMPILER)
 // Clang on macOS warns due to `Py_tss_NEEDS_INIT` not specifying an initializer
 // for every field.
 #            define PYBIND11_TLS_KEY_INIT(var)                                                    \
@@ -170,10 +176,12 @@ struct internals {
     PyTypeObject *default_metaclass;
     PyObject *instance_base;
 #if defined(WITH_THREAD)
+    // Unused if PYBIND11_SIMPLE_GIL_MANAGEMENT is defined:
     PYBIND11_TLS_KEY_INIT(tstate)
 #    if PYBIND11_INTERNALS_VERSION > 4
     PYBIND11_TLS_KEY_INIT(loader_life_support_tls_key)
 #    endif // PYBIND11_INTERNALS_VERSION > 4
+    // Unused if PYBIND11_SIMPLE_GIL_MANAGEMENT is defined:
     PyInterpreterState *istate = nullptr;
     ~internals() {
 #    if PYBIND11_INTERNALS_VERSION > 4
@@ -419,6 +427,10 @@ PYBIND11_NOINLINE internals &get_internals() {
         return **internals_pp;
     }
 
+#if defined(WITH_THREAD)
+#    if defined(PYBIND11_SIMPLE_GIL_MANAGEMENT)
+    gil_scoped_acquire gil;
+#    else
     // Ensure that the GIL is held since we will need to make Python calls.
     // Cannot use py::gil_scoped_acquire here since that constructor calls get_internals.
     struct gil_scoped_acquire_local {
@@ -428,6 +440,8 @@ PYBIND11_NOINLINE internals &get_internals() {
         ~gil_scoped_acquire_local() { PyGILState_Release(state); }
         const PyGILState_STATE state;
     } gil;
+#    endif
+#endif
     error_scope err_scope;
 
     PYBIND11_STR_TYPE id(PYBIND11_INTERNALS_ID);

include/pybind11/eigen/matrix.h

@@ -11,7 +11,6 @@
 
 #include "../numpy.h"
 
-// Similar to comments & pragma block in eigen_tensor.h. PLEASE KEEP IN SYNC.
 /* HINT: To suppress warnings originating from the Eigen headers, use -isystem.
    See also:
        https://stackoverflow.com/questions/2579576/i-dir-vs-isystem-dir

include/pybind11/functional.h

@@ -110,7 +110,7 @@ public:
     template <typename Func>
     static handle cast(Func &&f_, return_value_policy policy, handle /* parent */) {
         if (!f_) {
-            return none().inc_ref();
+            return none().release();
         }
 
         auto result = f_.template target<function_type>();

include/pybind11/gil.h

@@ -10,7 +10,10 @@
 #pragma once
 
 #include "detail/common.h"
-#include "detail/internals.h"
+
+#if defined(WITH_THREAD) && !defined(PYBIND11_SIMPLE_GIL_MANAGEMENT)
+#    include "detail/internals.h"
+#endif
 
 PYBIND11_NAMESPACE_BEGIN(PYBIND11_NAMESPACE)
 
@@ -21,7 +24,9 @@ PyThreadState *get_thread_state_unchecked();
 
 PYBIND11_NAMESPACE_END(detail)
 
-#if defined(WITH_THREAD) && !defined(PYPY_VERSION)
+#if defined(WITH_THREAD)
+
+#    if !defined(PYBIND11_SIMPLE_GIL_MANAGEMENT)
 
 /* The functions below essentially reproduce the PyGILState_* API using a RAII
  * pattern, but there are a few important differences:
@@ -62,11 +67,11 @@ public:
 
         if (!tstate) {
             tstate = PyThreadState_New(internals.istate);
-#    if defined(PYBIND11_DETAILED_ERROR_MESSAGES)
+#        if defined(PYBIND11_DETAILED_ERROR_MESSAGES)
             if (!tstate) {
                 pybind11_fail("scoped_acquire: could not create thread state!");
             }
-#    endif
+#        endif
             tstate->gilstate_counter = 0;
             PYBIND11_TLS_REPLACE_VALUE(internals.tstate, tstate);
         } else {
@@ -87,20 +92,20 @@ public:
 
     PYBIND11_NOINLINE void dec_ref() {
         --tstate->gilstate_counter;
-#    if defined(PYBIND11_DETAILED_ERROR_MESSAGES)
+#        if defined(PYBIND11_DETAILED_ERROR_MESSAGES)
         if (detail::get_thread_state_unchecked() != tstate) {
             pybind11_fail("scoped_acquire::dec_ref(): thread state must be current!");
         }
         if (tstate->gilstate_counter < 0) {
             pybind11_fail("scoped_acquire::dec_ref(): reference count underflow!");
         }
-#    endif
+#        endif
         if (tstate->gilstate_counter == 0) {
-#    if defined(PYBIND11_DETAILED_ERROR_MESSAGES)
+#        if defined(PYBIND11_DETAILED_ERROR_MESSAGES)
             if (!release) {
                 pybind11_fail("scoped_acquire::dec_ref(): internal error!");
             }
-#    endif
+#        endif
             PyThreadState_Clear(tstate);
             if (active) {
                 PyThreadState_DeleteCurrent();
@@ -178,12 +183,14 @@ private:
     bool disassoc;
     bool active = true;
 };
-#elif defined(PYPY_VERSION)
+
+#    else // PYBIND11_SIMPLE_GIL_MANAGEMENT
+
 class gil_scoped_acquire {
     PyGILState_STATE state;
 
 public:
-    gil_scoped_acquire() { state = PyGILState_Ensure(); }
+    gil_scoped_acquire() : state{PyGILState_Ensure()} {}
     gil_scoped_acquire(const gil_scoped_acquire &) = delete;
     gil_scoped_acquire &operator=(const gil_scoped_acquire &) = delete;
     ~gil_scoped_acquire() { PyGILState_Release(state); }
@@ -194,19 +201,39 @@ class gil_scoped_release {
     PyThreadState *state;
 
 public:
-    gil_scoped_release() { state = PyEval_SaveThread(); }
+    gil_scoped_release() : state{PyEval_SaveThread()} {}
     gil_scoped_release(const gil_scoped_release &) = delete;
     gil_scoped_release &operator=(const gil_scoped_acquire &) = delete;
     ~gil_scoped_release() { PyEval_RestoreThread(state); }
     void disarm() {}
 };
-#else
+
+#    endif // PYBIND11_SIMPLE_GIL_MANAGEMENT
+
+#else // WITH_THREAD
+
 class gil_scoped_acquire {
+public:
+    gil_scoped_acquire() {
+        // Trick to suppress `unused variable` error messages (at call sites).
+        (void) (this != (this + 1));
+    }
+    gil_scoped_acquire(const gil_scoped_acquire &) = delete;
+    gil_scoped_acquire &operator=(const gil_scoped_acquire &) = delete;
     void disarm() {}
 };
+
 class gil_scoped_release {
+public:
+    gil_scoped_release() {
+        // Trick to suppress `unused variable` error messages (at call sites).
+        (void) (this != (this + 1));
+    }
+    gil_scoped_release(const gil_scoped_release &) = delete;
+    gil_scoped_release &operator=(const gil_scoped_acquire &) = delete;
     void disarm() {}
 };
-#endif
+
+#endif // WITH_THREAD
 
 PYBIND11_NAMESPACE_END(PYBIND11_NAMESPACE)

include/pybind11/pybind11.h

@@ -2588,7 +2588,7 @@ template <typename Access,
           typename Sentinel,
           typename ValueType,
           typename... Extra>
-iterator make_iterator_impl(Iterator &&first, Sentinel &&last, Extra &&...extra) {
+iterator make_iterator_impl(Iterator first, Sentinel last, Extra &&...extra) {
     using state = detail::iterator_state<Access, Policy, Iterator, Sentinel, ValueType, Extra...>;
     // TODO: state captures only the types of Extra, not the values
 
@@ -2614,7 +2614,7 @@ iterator make_iterator_impl(Iterator &&first, Sentinel &&last, Extra &&...extra)
                 Policy);
     }
 
-    return cast(state{std::forward<Iterator>(first), std::forward<Sentinel>(last), true});
+    return cast(state{first, last, true});
 }
 
 PYBIND11_NAMESPACE_END(detail)
@@ -2625,15 +2625,13 @@ template <return_value_policy Policy = return_value_policy::reference_internal,
           typename Sentinel,
           typename ValueType = typename detail::iterator_access<Iterator>::result_type,
           typename... Extra>
-iterator make_iterator(Iterator &&first, Sentinel &&last, Extra &&...extra) {
+iterator make_iterator(Iterator first, Sentinel last, Extra &&...extra) {
     return detail::make_iterator_impl<detail::iterator_access<Iterator>,
                                       Policy,
                                       Iterator,
                                       Sentinel,
                                       ValueType,
-                                      Extra...>(std::forward<Iterator>(first),
+                                      Extra...>(first, last, std::forward<Extra>(extra)...);
-                                                std::forward<Sentinel>(last),
-                                                std::forward<Extra>(extra)...);
 }
 
 /// Makes a python iterator over the keys (`.first`) of a iterator over pairs from a
@@ -2643,15 +2641,13 @@ template <return_value_policy Policy = return_value_policy::reference_internal,
           typename Sentinel,
           typename KeyType = typename detail::iterator_key_access<Iterator>::result_type,
           typename... Extra>
-iterator make_key_iterator(Iterator &&first, Sentinel &&last, Extra &&...extra) {
+iterator make_key_iterator(Iterator first, Sentinel last, Extra &&...extra) {
     return detail::make_iterator_impl<detail::iterator_key_access<Iterator>,
                                       Policy,
                                       Iterator,
                                       Sentinel,
                                       KeyType,
-                                      Extra...>(std::forward<Iterator>(first),
+                                      Extra...>(first, last, std::forward<Extra>(extra)...);
-                                                std::forward<Sentinel>(last),
-                                                std::forward<Extra>(extra)...);
 }
 
 /// Makes a python iterator over the values (`.second`) of a iterator over pairs from a
@@ -2661,15 +2657,13 @@ template <return_value_policy Policy = return_value_policy::reference_internal,
           typename Sentinel,
           typename ValueType = typename detail::iterator_value_access<Iterator>::result_type,
           typename... Extra>
-iterator make_value_iterator(Iterator &&first, Sentinel &&last, Extra &&...extra) {
+iterator make_value_iterator(Iterator first, Sentinel last, Extra &&...extra) {
     return detail::make_iterator_impl<detail::iterator_value_access<Iterator>,
                                       Policy,
                                       Iterator,
                                       Sentinel,
                                       ValueType,
-                                      Extra...>(std::forward<Iterator>(first),
+                                      Extra...>(first, last, std::forward<Extra>(extra)...);
-                                                std::forward<Sentinel>(last),
-                                                std::forward<Extra>(extra)...);
 }
 
 /// Makes an iterator over values of an stl container or other container supporting

include/pybind11/pytypes.h

@@ -1432,6 +1432,9 @@ public:
     str(const char *c, const SzType &n)
         : object(PyUnicode_FromStringAndSize(c, ssize_t_cast(n)), stolen_t{}) {
         if (!m_ptr) {
+            if (PyErr_Occurred()) {
+                throw error_already_set();
+            }
             pybind11_fail("Could not allocate string object!");
         }
     }
@@ -1441,6 +1444,9 @@ public:
     // NOLINTNEXTLINE(google-explicit-constructor)
     str(const char *c = "") : object(PyUnicode_FromString(c), stolen_t{}) {
         if (!m_ptr) {
+            if (PyErr_Occurred()) {
+                throw error_already_set();
+            }
             pybind11_fail("Could not allocate string object!");
         }
     }
@@ -1598,6 +1604,9 @@ inline str::str(const bytes &b) {
     }
     auto obj = reinterpret_steal<object>(PyUnicode_FromStringAndSize(buffer, length));
     if (!obj) {
+        if (PyErr_Occurred()) {
+            throw error_already_set();
+        }
         pybind11_fail("Could not allocate string object!");
     }
     m_ptr = obj.release().ptr();

include/pybind11/stl.h

@@ -311,7 +311,7 @@ struct optional_caster {
     template <typename T>
     static handle cast(T &&src, return_value_policy policy, handle parent) {
         if (!src) {
-            return none().inc_ref();
+            return none().release();
         }
         if (!std::is_lvalue_reference<T>::value) {
             policy = return_value_policy_override<Value>::policy(policy);

tests/conftest.py

@@ -210,4 +210,5 @@ def pytest_report_header(config):
         f" {pybind11_tests.compiler_info}"
         f" {pybind11_tests.cpp_std}"
         f" {pybind11_tests.PYBIND11_INTERNALS_ID}"
+        f" PYBIND11_SIMPLE_GIL_MANAGEMENT={pybind11_tests.PYBIND11_SIMPLE_GIL_MANAGEMENT}"
     )

tests/cross_module_gil_utils.cpp

@@ -6,9 +6,15 @@
     All rights reserved. Use of this source code is governed by a
     BSD-style license that can be found in the LICENSE file.
 */
+#if defined(PYBIND11_INTERNALS_VERSION)
+#    undef PYBIND11_INTERNALS_VERSION
+#endif
+#define PYBIND11_INTERNALS_VERSION 21814642 // Ensure this module has its own `internals` instance.
 #include <pybind11/pybind11.h>
 
 #include <cstdint>
+#include <string>
+#include <thread>
 
 // This file mimics a DSO that makes pybind11 calls but does not define a
 // PYBIND11_MODULE. The purpose is to test that such a DSO can create a
@@ -21,8 +27,54 @@
 namespace {
 
 namespace py = pybind11;
+
 void gil_acquire() { py::gil_scoped_acquire gil; }
 
+std::string gil_multi_acquire_release(unsigned bits) {
+    if ((bits & 0x1u) != 0u) {
+        py::gil_scoped_acquire gil;
+    }
+    if ((bits & 0x2u) != 0u) {
+        py::gil_scoped_release gil;
+    }
+    if ((bits & 0x4u) != 0u) {
+        py::gil_scoped_acquire gil;
+    }
+    if ((bits & 0x8u) != 0u) {
+        py::gil_scoped_release gil;
+    }
+    return PYBIND11_INTERNALS_ID;
+}
+
+struct CustomAutoGIL {
+    CustomAutoGIL() : gstate(PyGILState_Ensure()) {}
+    ~CustomAutoGIL() { PyGILState_Release(gstate); }
+
+    PyGILState_STATE gstate;
+};
+struct CustomAutoNoGIL {
+    CustomAutoNoGIL() : save(PyEval_SaveThread()) {}
+    ~CustomAutoNoGIL() { PyEval_RestoreThread(save); }
+
+    PyThreadState *save;
+};
+
+template <typename Acquire, typename Release>
+void gil_acquire_inner() {
+    Acquire acquire_outer;
+    Acquire acquire_inner;
+    Release release;
+}
+
+template <typename Acquire, typename Release>
+void gil_acquire_nested() {
+    Acquire acquire_outer;
+    Acquire acquire_inner;
+    Release release;
+    auto thread = std::thread(&gil_acquire_inner<Acquire, Release>);
+    thread.join();
+}
+
 constexpr char kModuleName[] = "cross_module_gil_utils";
 
 struct PyModuleDef moduledef = {
@@ -30,6 +82,9 @@ struct PyModuleDef moduledef = {
 
 } // namespace
 
+#define ADD_FUNCTION(Name, ...)                                                                   \
+    PyModule_AddObject(m, Name, PyLong_FromVoidPtr(reinterpret_cast<void *>(&__VA_ARGS__)));
+
 extern "C" PYBIND11_EXPORT PyObject *PyInit_cross_module_gil_utils() {
 
     PyObject *m = PyModule_Create(&moduledef);
@@ -37,8 +92,16 @@ extern "C" PYBIND11_EXPORT PyObject *PyInit_cross_module_gil_utils() {
     if (m != nullptr) {
         static_assert(sizeof(&gil_acquire) == sizeof(void *),
                       "Function pointer must have the same size as void*");
-        PyModule_AddObject(
+        ADD_FUNCTION("gil_acquire_funcaddr", gil_acquire)
-            m, "gil_acquire_funcaddr", PyLong_FromVoidPtr(reinterpret_cast<void *>(&gil_acquire)));
+        ADD_FUNCTION("gil_multi_acquire_release_funcaddr", gil_multi_acquire_release)
+        ADD_FUNCTION("gil_acquire_inner_custom_funcaddr",
+                     gil_acquire_inner<CustomAutoGIL, CustomAutoNoGIL>)
+        ADD_FUNCTION("gil_acquire_nested_custom_funcaddr",
+                     gil_acquire_nested<CustomAutoGIL, CustomAutoNoGIL>)
+        ADD_FUNCTION("gil_acquire_inner_pybind11_funcaddr",
+                     gil_acquire_inner<py::gil_scoped_acquire, py::gil_scoped_release>)
+        ADD_FUNCTION("gil_acquire_nested_pybind11_funcaddr",
+                     gil_acquire_nested<py::gil_scoped_acquire, py::gil_scoped_release>)
     }
 
     return m;

tests/pybind11_tests.cpp

@@ -89,6 +89,12 @@ PYBIND11_MODULE(pybind11_tests, m) {
 #endif
     m.attr("cpp_std") = cpp_std();
     m.attr("PYBIND11_INTERNALS_ID") = PYBIND11_INTERNALS_ID;
+    m.attr("PYBIND11_SIMPLE_GIL_MANAGEMENT") =
+#if defined(PYBIND11_SIMPLE_GIL_MANAGEMENT)
+        true;
+#else
+        false;
+#endif
 
     bind_ConstructorStats(m);
 

tests/test_class.cpp

@@ -398,6 +398,8 @@ TEST_SUBMODULE(class_, m) {
 
     protected:
         virtual int foo() const { return value; }
+        virtual void *void_foo() { return static_cast<void *>(&value); }
+        virtual void *get_self() { return static_cast<void *>(this); }
 
     private:
         int value = 42;
@@ -406,6 +408,8 @@ TEST_SUBMODULE(class_, m) {
     class TrampolineB : public ProtectedB {
     public:
         int foo() const override { PYBIND11_OVERRIDE(int, ProtectedB, foo, ); }
+        void *void_foo() override { PYBIND11_OVERRIDE(void *, ProtectedB, void_foo, ); }
+        void *get_self() override { PYBIND11_OVERRIDE(void *, ProtectedB, get_self, ); }
     };
 
     class PublicistB : public ProtectedB {
@@ -415,11 +419,23 @@ TEST_SUBMODULE(class_, m) {
         // (in Debug builds only, tested with icpc (ICC) 2021.1 Beta 20200827)
         ~PublicistB() override{}; // NOLINT(modernize-use-equals-default)
         using ProtectedB::foo;
+        using ProtectedB::get_self;
+        using ProtectedB::void_foo;
     };
 
+    m.def("read_foo", [](const void *original) {
+        const int *ptr = reinterpret_cast<const int *>(original);
+        return *ptr;
+    });
+
+    m.def("pointers_equal",
+          [](const void *original, const void *comparison) { return original == comparison; });
+
     py::class_<ProtectedB, TrampolineB>(m, "ProtectedB")
         .def(py::init<>())
-        .def("foo", &PublicistB::foo);
+        .def("foo", &PublicistB::foo)
+        .def("void_foo", &PublicistB::void_foo)
+        .def("get_self", &PublicistB::get_self);
 
     // test_brace_initialization
     struct BraceInitialization {

tests/test_class.py

@@ -313,6 +313,8 @@ def test_bind_protected_functions():
 
     b = m.ProtectedB()
     assert b.foo() == 42
+    assert m.read_foo(b.void_foo()) == 42
+    assert m.pointers_equal(b.get_self(), b)
 
     class C(m.ProtectedB):
         def __init__(self):

tests/test_eigen_tensor.py

@@ -9,8 +9,16 @@ try:
     from pybind11_tests import eigen_tensor_avoid_stl_array as avoid
 
     submodules += [avoid.c_style, avoid.f_style]
-except ImportError:
+except ImportError as e:
-    pass
+    # Ensure config, build, toolchain, etc. issues are not masked here:
+    raise RuntimeError(
+        "import pybind11_tests.eigen_tensor_avoid_stl_array FAILED, while "
+        "import pybind11_tests.eigen_tensor succeeded. "
+        "Please ensure that "
+        "test_eigen_tensor.cpp & "
+        "test_eigen_tensor_avoid_stl_array.cpp "
+        "are built together (or both are not built if Eigen is not available)."
+    ) from e
 
 tensor_ref = np.empty((3, 5, 2), dtype=np.int64)
 

tests/test_embed/test_interpreter.cpp

@@ -293,7 +293,6 @@ TEST_CASE("Threads") {
 
     {
         py::gil_scoped_release gil_release{};
-        REQUIRE(has_pybind11_internals_static());
 
         auto threads = std::vector<std::thread>();
         for (auto i = 0; i < num_threads; ++i) {

tests/test_gil_scoped.cpp

@@ -11,6 +11,13 @@
 
 #include "pybind11_tests.h"
 
+#include <string>
+#include <thread>
+
+#define CROSS_MODULE(Function)                                                                    \
+    auto cm = py::module_::import("cross_module_gil_utils");                                      \
+    auto target = reinterpret_cast<void (*)()>(PyLong_AsVoidPtr(cm.attr(Function).ptr()));
+
 class VirtClass {
 public:
     virtual ~VirtClass() = default;
@@ -28,6 +35,16 @@ class PyVirtClass : public VirtClass {
 };
 
 TEST_SUBMODULE(gil_scoped, m) {
+    m.attr("defined_THREAD_SANITIZER") =
+#if defined(THREAD_SANITIZER)
+        true;
+#else
+        false;
+#endif
+
+    m.def("intentional_deadlock",
+          []() { std::thread([]() { py::gil_scoped_acquire gil_acquired; }).join(); });
+
     py::class_<VirtClass, PyVirtClass>(m, "VirtClass")
         .def(py::init<>())
         .def("virtual_func", &VirtClass::virtual_func)
@@ -37,11 +54,91 @@ TEST_SUBMODULE(gil_scoped, m) {
     m.def("test_callback_std_func", [](const std::function<void()> &func) { func(); });
     m.def("test_callback_virtual_func", [](VirtClass &virt) { virt.virtual_func(); });
     m.def("test_callback_pure_virtual_func", [](VirtClass &virt) { virt.pure_virtual_func(); });
-    m.def("test_cross_module_gil", []() {
+    m.def("test_cross_module_gil_released", []() {
-        auto cm = py::module_::import("cross_module_gil_utils");
+        CROSS_MODULE("gil_acquire_funcaddr")
-        auto gil_acquire = reinterpret_cast<void (*)()>(
-            PyLong_AsVoidPtr(cm.attr("gil_acquire_funcaddr").ptr()));
         py::gil_scoped_release gil_release;
-        gil_acquire();
+        target();
+    });
+    m.def("test_cross_module_gil_acquired", []() {
+        CROSS_MODULE("gil_acquire_funcaddr")
+        py::gil_scoped_acquire gil_acquire;
+        target();
+    });
+    m.def("test_cross_module_gil_inner_custom_released", []() {
+        CROSS_MODULE("gil_acquire_inner_custom_funcaddr")
+        py::gil_scoped_release gil_release;
+        target();
+    });
+    m.def("test_cross_module_gil_inner_custom_acquired", []() {
+        CROSS_MODULE("gil_acquire_inner_custom_funcaddr")
+        py::gil_scoped_acquire gil_acquire;
+        target();
+    });
+    m.def("test_cross_module_gil_inner_pybind11_released", []() {
+        CROSS_MODULE("gil_acquire_inner_pybind11_funcaddr")
+        py::gil_scoped_release gil_release;
+        target();
+    });
+    m.def("test_cross_module_gil_inner_pybind11_acquired", []() {
+        CROSS_MODULE("gil_acquire_inner_pybind11_funcaddr")
+        py::gil_scoped_acquire gil_acquire;
+        target();
+    });
+    m.def("test_cross_module_gil_nested_custom_released", []() {
+        CROSS_MODULE("gil_acquire_nested_custom_funcaddr")
+        py::gil_scoped_release gil_release;
+        target();
+    });
+    m.def("test_cross_module_gil_nested_custom_acquired", []() {
+        CROSS_MODULE("gil_acquire_nested_custom_funcaddr")
+        py::gil_scoped_acquire gil_acquire;
+        target();
+    });
+    m.def("test_cross_module_gil_nested_pybind11_released", []() {
+        CROSS_MODULE("gil_acquire_nested_pybind11_funcaddr")
+        py::gil_scoped_release gil_release;
+        target();
+    });
+    m.def("test_cross_module_gil_nested_pybind11_acquired", []() {
+        CROSS_MODULE("gil_acquire_nested_pybind11_funcaddr")
+        py::gil_scoped_acquire gil_acquire;
+        target();
+    });
+    m.def("test_release_acquire", [](const py::object &obj) {
+        py::gil_scoped_release gil_released;
+        py::gil_scoped_acquire gil_acquired;
+        return py::str(obj);
+    });
+    m.def("test_nested_acquire", [](const py::object &obj) {
+        py::gil_scoped_release gil_released;
+        py::gil_scoped_acquire gil_acquired_outer;
+        py::gil_scoped_acquire gil_acquired_inner;
+        return py::str(obj);
+    });
+    m.def("test_multi_acquire_release_cross_module", [](unsigned bits) {
+        py::set internals_ids;
+        internals_ids.add(PYBIND11_INTERNALS_ID);
+        {
+            py::gil_scoped_release gil_released;
+            auto thread_f = [bits, &internals_ids]() {
+                py::gil_scoped_acquire gil_acquired;
+                auto cm = py::module_::import("cross_module_gil_utils");
+                auto target = reinterpret_cast<std::string (*)(unsigned)>(
+                    PyLong_AsVoidPtr(cm.attr("gil_multi_acquire_release_funcaddr").ptr()));
+                std::string cm_internals_id = target(bits >> 3);
+                internals_ids.add(cm_internals_id);
+            };
+            if ((bits & 0x1u) != 0u) {
+                thread_f();
+            }
+            if ((bits & 0x2u) != 0u) {
+                std::thread non_python_thread(thread_f);
+                non_python_thread.join();
+            }
+            if ((bits & 0x4u) != 0u) {
+                thread_f();
+            }
+        }
+        return internals_ids;
     });
 }

tests/test_gil_scoped.py

@@ -1,45 +1,199 @@
 import multiprocessing
+import sys
 import threading
+import time
+
+import pytest
 
 from pybind11_tests import gil_scoped as m
 
 
+class ExtendedVirtClass(m.VirtClass):
+    def virtual_func(self):
+        pass
+
+    def pure_virtual_func(self):
+        pass
+
+
+def test_callback_py_obj():
+    m.test_callback_py_obj(lambda: None)
+
+
+def test_callback_std_func():
+    m.test_callback_std_func(lambda: None)
+
+
+def test_callback_virtual_func():
+    extended = ExtendedVirtClass()
+    m.test_callback_virtual_func(extended)
+
+
+def test_callback_pure_virtual_func():
+    extended = ExtendedVirtClass()
+    m.test_callback_pure_virtual_func(extended)
+
+
+def test_cross_module_gil_released():
+    """Makes sure that the GIL can be acquired by another module from a GIL-released state."""
+    m.test_cross_module_gil_released()  # Should not raise a SIGSEGV
+
+
+def test_cross_module_gil_acquired():
+    """Makes sure that the GIL can be acquired by another module from a GIL-acquired state."""
+    m.test_cross_module_gil_acquired()  # Should not raise a SIGSEGV
+
+
+def test_cross_module_gil_inner_custom_released():
+    """Makes sure that the GIL can be acquired/released by another module
+    from a GIL-released state using custom locking logic."""
+    m.test_cross_module_gil_inner_custom_released()
+
+
+def test_cross_module_gil_inner_custom_acquired():
+    """Makes sure that the GIL can be acquired/acquired by another module
+    from a GIL-acquired state using custom locking logic."""
+    m.test_cross_module_gil_inner_custom_acquired()
+
+
+def test_cross_module_gil_inner_pybind11_released():
+    """Makes sure that the GIL can be acquired/released by another module
+    from a GIL-released state using pybind11 locking logic."""
+    m.test_cross_module_gil_inner_pybind11_released()
+
+
+def test_cross_module_gil_inner_pybind11_acquired():
+    """Makes sure that the GIL can be acquired/acquired by another module
+    from a GIL-acquired state using pybind11 locking logic."""
+    m.test_cross_module_gil_inner_pybind11_acquired()
+
+
+def test_cross_module_gil_nested_custom_released():
+    """Makes sure that the GIL can be nested acquired/released by another module
+    from a GIL-released state using custom locking logic."""
+    m.test_cross_module_gil_nested_custom_released()
+
+
+def test_cross_module_gil_nested_custom_acquired():
+    """Makes sure that the GIL can be nested acquired/acquired by another module
+    from a GIL-acquired state using custom locking logic."""
+    m.test_cross_module_gil_nested_custom_acquired()
+
+
+def test_cross_module_gil_nested_pybind11_released():
+    """Makes sure that the GIL can be nested acquired/released by another module
+    from a GIL-released state using pybind11 locking logic."""
+    m.test_cross_module_gil_nested_pybind11_released()
+
+
+def test_cross_module_gil_nested_pybind11_acquired():
+    """Makes sure that the GIL can be nested acquired/acquired by another module
+    from a GIL-acquired state using pybind11 locking logic."""
+    m.test_cross_module_gil_nested_pybind11_acquired()
+
+
+def test_release_acquire():
+    assert m.test_release_acquire(0xAB) == "171"
+
+
+def test_nested_acquire():
+    assert m.test_nested_acquire(0xAB) == "171"
+
+
+def test_multi_acquire_release_cross_module():
+    for bits in range(16 * 8):
+        internals_ids = m.test_multi_acquire_release_cross_module(bits)
+        assert len(internals_ids) == 2 if bits % 8 else 1
+
+
+# Intentionally putting human review in the loop here, to guard against accidents.
+VARS_BEFORE_ALL_BASIC_TESTS = dict(vars())  # Make a copy of the dict (critical).
+ALL_BASIC_TESTS = (
+    test_callback_py_obj,
+    test_callback_std_func,
+    test_callback_virtual_func,
+    test_callback_pure_virtual_func,
+    test_cross_module_gil_released,
+    test_cross_module_gil_acquired,
+    test_cross_module_gil_inner_custom_released,
+    test_cross_module_gil_inner_custom_acquired,
+    test_cross_module_gil_inner_pybind11_released,
+    test_cross_module_gil_inner_pybind11_acquired,
+    test_cross_module_gil_nested_custom_released,
+    test_cross_module_gil_nested_custom_acquired,
+    test_cross_module_gil_nested_pybind11_released,
+    test_cross_module_gil_nested_pybind11_acquired,
+    test_release_acquire,
+    test_nested_acquire,
+    test_multi_acquire_release_cross_module,
+)
+
+
+def test_all_basic_tests_completeness():
+    num_found = 0
+    for key, value in VARS_BEFORE_ALL_BASIC_TESTS.items():
+        if not key.startswith("test_"):
+            continue
+        assert value in ALL_BASIC_TESTS
+        num_found += 1
+    assert len(ALL_BASIC_TESTS) == num_found
+
+
+def _intentional_deadlock():
+    m.intentional_deadlock()
+
+
+ALL_BASIC_TESTS_PLUS_INTENTIONAL_DEADLOCK = ALL_BASIC_TESTS + (_intentional_deadlock,)
+SKIP_IF_DEADLOCK = True  # See PR #4216
+
+
 def _run_in_process(target, *args, **kwargs):
-    """Runs target in process and returns its exitcode after 10s (None if still alive)."""
+    if len(args) == 0:
+        test_fn = target
+    else:
+        test_fn = args[0]
+    # Do not need to wait much, 10s should be more than enough.
+    timeout = 0.1 if test_fn is _intentional_deadlock else 10
     process = multiprocessing.Process(target=target, args=args, kwargs=kwargs)
     process.daemon = True
     try:
+        t_start = time.time()
         process.start()
-        # Do not need to wait much, 10s should be more than enough.
+        if timeout >= 100:  # For debugging.
-        process.join(timeout=10)
+            print(
+                "\nprocess.pid STARTED", process.pid, (sys.argv, target, args, kwargs)
+            )
+            print(f"COPY-PASTE-THIS: gdb {sys.argv[0]} -p {process.pid}", flush=True)
+        process.join(timeout=timeout)
+        if timeout >= 100:
+            print("\nprocess.pid JOINED", process.pid, flush=True)
+        t_delta = time.time() - t_start
+        if process.exitcode == 66 and m.defined_THREAD_SANITIZER:  # Issue #2754
+            # WOULD-BE-NICE-TO-HAVE: Check that the message below is actually in the output.
+            # Maybe this could work:
+            # https://gist.github.com/alexeygrigorev/01ce847f2e721b513b42ea4a6c96905e
+            pytest.skip(
+                "ThreadSanitizer: starting new threads after multi-threaded fork is not supported."
+            )
+        elif test_fn is _intentional_deadlock:
+            assert process.exitcode is None
+            return 0
+        elif process.exitcode is None:
+            assert t_delta > 0.9 * timeout
+            msg = "DEADLOCK, most likely, exactly what this test is meant to detect."
+            if SKIP_IF_DEADLOCK:
+                pytest.skip(msg)
+            raise RuntimeError(msg)
         return process.exitcode
     finally:
         if process.is_alive():
             process.terminate()
 
 
-def _python_to_cpp_to_python():
+def _run_in_threads(test_fn, num_threads, parallel):
-    """Calls different C++ functions that come back to Python."""
-
-    class ExtendedVirtClass(m.VirtClass):
-        def virtual_func(self):
-            pass
-
-        def pure_virtual_func(self):
-            pass
-
-    extended = ExtendedVirtClass()
-    m.test_callback_py_obj(lambda: None)
-    m.test_callback_std_func(lambda: None)
-    m.test_callback_virtual_func(extended)
-    m.test_callback_pure_virtual_func(extended)
-
-
-def _python_to_cpp_to_python_from_threads(num_threads, parallel=False):
-    """Calls different C++ functions that come back to Python, from Python threads."""
     threads = []
     for _ in range(num_threads):
-        thread = threading.Thread(target=_python_to_cpp_to_python)
+        thread = threading.Thread(target=test_fn)
         thread.daemon = True
         thread.start()
         if parallel:
@@ -51,43 +205,40 @@ def _python_to_cpp_to_python_from_threads(num_threads, parallel=False):
 
 
 # TODO: FIXME, sometimes returns -11 (segfault) instead of 0 on macOS Python 3.9
-def test_python_to_cpp_to_python_from_thread():
+@pytest.mark.parametrize("test_fn", ALL_BASIC_TESTS_PLUS_INTENTIONAL_DEADLOCK)
+def test_run_in_process_one_thread(test_fn):
     """Makes sure there is no GIL deadlock when running in a thread.
 
     It runs in a separate process to be able to stop and assert if it deadlocks.
     """
-    assert _run_in_process(_python_to_cpp_to_python_from_threads, 1) == 0
+    assert _run_in_process(_run_in_threads, test_fn, num_threads=1, parallel=False) == 0
 
 
 # TODO: FIXME on macOS Python 3.9
-def test_python_to_cpp_to_python_from_thread_multiple_parallel():
+@pytest.mark.parametrize("test_fn", ALL_BASIC_TESTS_PLUS_INTENTIONAL_DEADLOCK)
+def test_run_in_process_multiple_threads_parallel(test_fn):
     """Makes sure there is no GIL deadlock when running in a thread multiple times in parallel.
 
     It runs in a separate process to be able to stop and assert if it deadlocks.
     """
-    assert _run_in_process(_python_to_cpp_to_python_from_threads, 8, parallel=True) == 0
+    assert _run_in_process(_run_in_threads, test_fn, num_threads=8, parallel=True) == 0
 
 
 # TODO: FIXME on macOS Python 3.9
-def test_python_to_cpp_to_python_from_thread_multiple_sequential():
+@pytest.mark.parametrize("test_fn", ALL_BASIC_TESTS_PLUS_INTENTIONAL_DEADLOCK)
+def test_run_in_process_multiple_threads_sequential(test_fn):
     """Makes sure there is no GIL deadlock when running in a thread multiple times sequentially.
 
     It runs in a separate process to be able to stop and assert if it deadlocks.
     """
-    assert (
+    assert _run_in_process(_run_in_threads, test_fn, num_threads=8, parallel=False) == 0
-        _run_in_process(_python_to_cpp_to_python_from_threads, 8, parallel=False) == 0
-    )
 
 
 # TODO: FIXME on macOS Python 3.9
-def test_python_to_cpp_to_python_from_process():
+@pytest.mark.parametrize("test_fn", ALL_BASIC_TESTS_PLUS_INTENTIONAL_DEADLOCK)
+def test_run_in_process_direct(test_fn):
     """Makes sure there is no GIL deadlock when using processes.
 
     This test is for completion, but it was never an issue.
     """
-    assert _run_in_process(_python_to_cpp_to_python) == 0
+    assert _run_in_process(test_fn) == 0
-
-
-def test_cross_module_gil():
-    """Makes sure that the GIL can be acquired by another module from a GIL-released state."""
-    m.test_cross_module_gil()  # Should not raise a SIGSEGV

tests/test_pytypes.cpp

@@ -206,7 +206,12 @@ TEST_SUBMODULE(pytypes, m) {
     m.def("str_from_char_ssize_t", []() { return py::str{"red", (py::ssize_t) 3}; });
     m.def("str_from_char_size_t", []() { return py::str{"blue", (py::size_t) 4}; });
     m.def("str_from_string", []() { return py::str(std::string("baz")); });
+    m.def("str_from_std_string_input", [](const std::string &stri) { return py::str(stri); });
+    m.def("str_from_cstr_input", [](const char *c_str) { return py::str(c_str); });
     m.def("str_from_bytes", []() { return py::str(py::bytes("boo", 3)); });
+    m.def("str_from_bytes_input",
+          [](const py::bytes &encoded_str) { return py::str(encoded_str); });
+
     m.def("str_from_object", [](const py::object &obj) { return py::str(obj); });
     m.def("repr_from_object", [](const py::object &obj) { return py::repr(obj); });
     m.def("str_from_handle", [](py::handle h) { return py::str(h); });

tests/test_pytypes.py

@@ -244,6 +244,20 @@ def test_str(doc):
         m.str_from_string_from_str(ucs_surrogates_str)
 
 
+@pytest.mark.parametrize(
+    "func",
+    [
+        m.str_from_bytes_input,
+        m.str_from_cstr_input,
+        m.str_from_std_string_input,
+    ],
+)
+def test_surrogate_pairs_unicode_error(func):
+    input_str = "\ud83d\ude4f".encode("utf-8", "surrogatepass")
+    with pytest.raises(UnicodeDecodeError):
+        func(input_str)
+
+
 def test_bytes(doc):
     assert m.bytes_from_char_ssize_t().decode() == "green"
     assert m.bytes_from_char_size_t().decode() == "purple"

tests/test_sequences_and_iterators.cpp

@@ -559,4 +559,23 @@ TEST_SUBMODULE(sequences_and_iterators, m) {
           []() { return py::make_iterator<py::return_value_policy::copy>(list); });
     m.def("make_iterator_2",
           []() { return py::make_iterator<py::return_value_policy::automatic>(list); });
+
+    // test_iterator on c arrays
+    // #4100: ensure lvalue required as increment operand
+    class CArrayHolder {
+    public:
+        CArrayHolder(double x, double y, double z) {
+            values[0] = x;
+            values[1] = y;
+            values[2] = z;
+        };
+        double values[3];
+    };
+
+    py::class_<CArrayHolder>(m, "CArrayHolder")
+        .def(py::init<double, double, double>())
+        .def(
+            "__iter__",
+            [](const CArrayHolder &v) { return py::make_iterator(v.values, v.values + 3); },
+            py::keep_alive<0, 1>());
 }

tests/test_sequences_and_iterators.py

@@ -241,3 +241,11 @@ def test_iterator_rvp():
     assert list(m.make_iterator_1()) == [1, 2, 3]
     assert list(m.make_iterator_2()) == [1, 2, 3]
     assert not isinstance(m.make_iterator_1(), type(m.make_iterator_2()))
+
+
+def test_carray_iterator():
+    """#4100: Check for proper iterator overload with C-Arrays"""
+    args_gt = list(float(i) for i in range(3))
+    arr_h = m.CArrayHolder(*args_gt)
+    args = list(arr_h)
+    assert args_gt == args

tools/FindPythonLibsNew.cmake

@@ -151,9 +151,13 @@ if(NOT _PYTHON_SUCCESS MATCHES 0)
   return()
 endif()
 
+option(
+  PYBIND11_PYTHONLIBS_OVERWRITE
+  "Overwrite cached values read from Python library (classic search). Turn off if cross-compiling and manually setting these values."
+  ON)
 # Can manually set values when cross-compiling
 macro(_PYBIND11_GET_IF_UNDEF lst index name)
-  if(NOT DEFINED "${name}")
+  if(PYBIND11_PYTHONLIBS_OVERWRITE OR NOT DEFINED "${name}")
     list(GET "${lst}" "${index}" "${name}")
   endif()
 endmacro()