diff options
Diffstat (limited to 'Include')
| -rw-r--r-- | Include/Python.h | 13 | ||||
| -rw-r--r-- | Include/cpython/unicodeobject.h | 131 | ||||
| -rw-r--r-- | Include/internal/pycore_ceval.h | 3 | ||||
| -rw-r--r-- | Include/internal/pycore_crossinterp.h | 37 | ||||
| -rw-r--r-- | Include/internal/pycore_freelist_state.h | 2 | ||||
| -rw-r--r-- | Include/internal/pycore_interp_structs.h | 3 | ||||
| -rw-r--r-- | Include/internal/pycore_stackref.h | 68 | ||||
| -rw-r--r-- | Include/object.h | 9 | ||||
| -rw-r--r-- | Include/pymacro.h | 82 |
9 files changed, 220 insertions, 128 deletions
diff --git a/Include/Python.h b/Include/Python.h index f34d581f0b4..64be8014589 100644 --- a/Include/Python.h +++ b/Include/Python.h @@ -59,14 +59,6 @@ # include <intrin.h> // __readgsqword() #endif -// Suppress known warnings in Python header files. -#if defined(_MSC_VER) -// Warning that alignas behaviour has changed. Doesn't affect us, because we -// never relied on the old behaviour. -#pragma warning(push) -#pragma warning(disable: 5274) -#endif - // Include Python header files #include "pyport.h" #include "pymacro.h" @@ -146,9 +138,4 @@ #include "cpython/pyfpe.h" #include "cpython/tracemalloc.h" -// Restore warning filter -#ifdef _MSC_VER -#pragma warning(pop) -#endif - #endif /* !Py_PYTHON_H */ diff --git a/Include/cpython/unicodeobject.h b/Include/cpython/unicodeobject.h index 3d0414f5291..86c502730f4 100644 --- a/Include/cpython/unicodeobject.h +++ b/Include/cpython/unicodeobject.h @@ -47,6 +47,63 @@ static inline Py_UCS4 Py_UNICODE_LOW_SURROGATE(Py_UCS4 ch) { /* --- Unicode Type ------------------------------------------------------- */ +struct _PyUnicodeObject_state { + /* If interned is non-zero, the two references from the + dictionary to this object are *not* counted in ob_refcnt. + The possible values here are: + 0: Not Interned + 1: Interned + 2: Interned and Immortal + 3: Interned, Immortal, and Static + This categorization allows the runtime to determine the right + cleanup mechanism at runtime shutdown. */ +#ifdef Py_GIL_DISABLED + // Needs to be accessed atomically, so can't be a bit field. + unsigned char interned; +#else + unsigned int interned:2; +#endif + /* Character size: + + - PyUnicode_1BYTE_KIND (1): + + * character type = Py_UCS1 (8 bits, unsigned) + * all characters are in the range U+0000-U+00FF (latin1) + * if ascii is set, all characters are in the range U+0000-U+007F + (ASCII), otherwise at least one character is in the range + U+0080-U+00FF + + - PyUnicode_2BYTE_KIND (2): + + * character type = Py_UCS2 (16 bits, unsigned) + * all characters are in the range U+0000-U+FFFF (BMP) + * at least one character is in the range U+0100-U+FFFF + + - PyUnicode_4BYTE_KIND (4): + + * character type = Py_UCS4 (32 bits, unsigned) + * all characters are in the range U+0000-U+10FFFF + * at least one character is in the range U+10000-U+10FFFF + */ + unsigned int kind:3; + /* Compact is with respect to the allocation scheme. Compact unicode + objects only require one memory block while non-compact objects use + one block for the PyUnicodeObject struct and another for its data + buffer. */ + unsigned int compact:1; + /* The string only contains characters in the range U+0000-U+007F (ASCII) + and the kind is PyUnicode_1BYTE_KIND. If ascii is set and compact is + set, use the PyASCIIObject structure. */ + unsigned int ascii:1; + /* The object is statically allocated. */ + unsigned int statically_allocated:1; +#ifndef Py_GIL_DISABLED + /* Historical: padding to ensure that PyUnicode_DATA() is always aligned to + 4 bytes (see issue gh-63736 on m68k) */ + unsigned int :24; +#endif +}; + /* ASCII-only strings created through PyUnicode_New use the PyASCIIObject structure. state.ascii and state.compact are set, and the data immediately follow the structure. utf8_length can be found @@ -99,67 +156,8 @@ typedef struct { PyObject_HEAD Py_ssize_t length; /* Number of code points in the string */ Py_hash_t hash; /* Hash value; -1 if not set */ -#ifdef Py_GIL_DISABLED - /* Ensure 4 byte alignment for PyUnicode_DATA(), see gh-63736 on m68k. - In the non-free-threaded build, we'll use explicit padding instead */ - _Py_ALIGN_AS(4) -#endif - struct { - /* If interned is non-zero, the two references from the - dictionary to this object are *not* counted in ob_refcnt. - The possible values here are: - 0: Not Interned - 1: Interned - 2: Interned and Immortal - 3: Interned, Immortal, and Static - This categorization allows the runtime to determine the right - cleanup mechanism at runtime shutdown. */ -#ifdef Py_GIL_DISABLED - // Needs to be accessed atomically, so can't be a bit field. - unsigned char interned; -#else - unsigned int interned:2; -#endif - /* Character size: - - - PyUnicode_1BYTE_KIND (1): - - * character type = Py_UCS1 (8 bits, unsigned) - * all characters are in the range U+0000-U+00FF (latin1) - * if ascii is set, all characters are in the range U+0000-U+007F - (ASCII), otherwise at least one character is in the range - U+0080-U+00FF - - - PyUnicode_2BYTE_KIND (2): - - * character type = Py_UCS2 (16 bits, unsigned) - * all characters are in the range U+0000-U+FFFF (BMP) - * at least one character is in the range U+0100-U+FFFF - - - PyUnicode_4BYTE_KIND (4): - - * character type = Py_UCS4 (32 bits, unsigned) - * all characters are in the range U+0000-U+10FFFF - * at least one character is in the range U+10000-U+10FFFF - */ - unsigned int kind:3; - /* Compact is with respect to the allocation scheme. Compact unicode - objects only require one memory block while non-compact objects use - one block for the PyUnicodeObject struct and another for its data - buffer. */ - unsigned int compact:1; - /* The string only contains characters in the range U+0000-U+007F (ASCII) - and the kind is PyUnicode_1BYTE_KIND. If ascii is set and compact is - set, use the PyASCIIObject structure. */ - unsigned int ascii:1; - /* The object is statically allocated. */ - unsigned int statically_allocated:1; -#ifndef Py_GIL_DISABLED - /* Padding to ensure that PyUnicode_DATA() is always aligned to - 4 bytes (see issue gh-63736 on m68k) */ - unsigned int :24; -#endif - } state; + /* Ensure 4 byte alignment for PyUnicode_DATA(), see gh-63736 on m68k. */ + _Py_ALIGNED_DEF(4, struct _PyUnicodeObject_state) state; } PyASCIIObject; /* Non-ASCII strings allocated through PyUnicode_New use the @@ -300,6 +298,17 @@ static inline Py_ssize_t PyUnicode_GET_LENGTH(PyObject *op) { } #define PyUnicode_GET_LENGTH(op) PyUnicode_GET_LENGTH(_PyObject_CAST(op)) +/* Returns the cached hash, or -1 if not cached yet. */ +static inline Py_hash_t +PyUnstable_Unicode_GET_CACHED_HASH(PyObject *op) { + assert(PyUnicode_Check(op)); +#ifdef Py_GIL_DISABLED + return _Py_atomic_load_ssize_relaxed(&_PyASCIIObject_CAST(op)->hash); +#else + return _PyASCIIObject_CAST(op)->hash; +#endif +} + /* Write into the canonical representation, this function does not do any sanity checks and is intended for usage in loops. The caller should cache the kind and data pointers obtained from other function calls. diff --git a/Include/internal/pycore_ceval.h b/Include/internal/pycore_ceval.h index 092feeb40b0..239177deb4a 100644 --- a/Include/internal/pycore_ceval.h +++ b/Include/internal/pycore_ceval.h @@ -353,7 +353,8 @@ PyAPI_FUNC(_PyStackRef) _PyFloat_FromDouble_ConsumeInputs(_PyStackRef left, _PyS extern int _PyRunRemoteDebugger(PyThreadState *tstate); #endif -_PyStackRef _PyForIter_NextWithIndex(PyObject *seq, _PyStackRef index); +PyAPI_FUNC(_PyStackRef) +_PyForIter_VirtualIteratorNext(PyThreadState* tstate, struct _PyInterpreterFrame* frame, _PyStackRef iter, _PyStackRef *index_ptr); #ifdef __cplusplus } diff --git a/Include/internal/pycore_crossinterp.h b/Include/internal/pycore_crossinterp.h index 713ddc66ba7..81faffac194 100644 --- a/Include/internal/pycore_crossinterp.h +++ b/Include/internal/pycore_crossinterp.h @@ -303,10 +303,10 @@ typedef struct _excinfo { const char *errdisplay; } _PyXI_excinfo; -PyAPI_FUNC(int) _PyXI_InitExcInfo(_PyXI_excinfo *info, PyObject *exc); +PyAPI_FUNC(_PyXI_excinfo *) _PyXI_NewExcInfo(PyObject *exc); +PyAPI_FUNC(void) _PyXI_FreeExcInfo(_PyXI_excinfo *info); PyAPI_FUNC(PyObject *) _PyXI_FormatExcInfo(_PyXI_excinfo *info); PyAPI_FUNC(PyObject *) _PyXI_ExcInfoAsObject(_PyXI_excinfo *info); -PyAPI_FUNC(void) _PyXI_ClearExcInfo(_PyXI_excinfo *info); typedef enum error_code { @@ -322,19 +322,20 @@ typedef enum error_code { _PyXI_ERR_NOT_SHAREABLE = -9, } _PyXI_errcode; +typedef struct xi_failure _PyXI_failure; -typedef struct _sharedexception { - // The originating interpreter. - PyInterpreterState *interp; - // The kind of error to propagate. - _PyXI_errcode code; - // The exception information to propagate, if applicable. - // This is populated only for some error codes, - // but always for _PyXI_ERR_UNCAUGHT_EXCEPTION. - _PyXI_excinfo uncaught; -} _PyXI_error; +PyAPI_FUNC(_PyXI_failure *) _PyXI_NewFailure(void); +PyAPI_FUNC(void) _PyXI_FreeFailure(_PyXI_failure *); +PyAPI_FUNC(_PyXI_errcode) _PyXI_GetFailureCode(_PyXI_failure *); +PyAPI_FUNC(int) _PyXI_InitFailure(_PyXI_failure *, _PyXI_errcode, PyObject *); +PyAPI_FUNC(void) _PyXI_InitFailureUTF8( + _PyXI_failure *, + _PyXI_errcode, + const char *); -PyAPI_FUNC(PyObject *) _PyXI_ApplyError(_PyXI_error *err); +PyAPI_FUNC(int) _PyXI_UnwrapNotShareableError( + PyThreadState *, + _PyXI_failure *); // A cross-interpreter session involves entering an interpreter @@ -366,19 +367,21 @@ PyAPI_FUNC(int) _PyXI_Enter( _PyXI_session_result *); PyAPI_FUNC(int) _PyXI_Exit( _PyXI_session *, - _PyXI_errcode, + _PyXI_failure *, _PyXI_session_result *); PyAPI_FUNC(PyObject *) _PyXI_GetMainNamespace( _PyXI_session *, - _PyXI_errcode *); + _PyXI_failure *); PyAPI_FUNC(int) _PyXI_Preserve( _PyXI_session *, const char *, PyObject *, - _PyXI_errcode *); -PyAPI_FUNC(PyObject *) _PyXI_GetPreserved(_PyXI_session_result *, const char *); + _PyXI_failure *); +PyAPI_FUNC(PyObject *) _PyXI_GetPreserved( + _PyXI_session_result *, + const char *); /*************/ diff --git a/Include/internal/pycore_freelist_state.h b/Include/internal/pycore_freelist_state.h index 4828dfd948f..59beb92f3f7 100644 --- a/Include/internal/pycore_freelist_state.h +++ b/Include/internal/pycore_freelist_state.h @@ -16,6 +16,7 @@ extern "C" { # define Py_dicts_MAXFREELIST 80 # define Py_dictkeys_MAXFREELIST 80 # define Py_floats_MAXFREELIST 100 +# define Py_complexes_MAXFREELIST 100 # define Py_ints_MAXFREELIST 100 # define Py_slices_MAXFREELIST 1 # define Py_ranges_MAXFREELIST 6 @@ -43,6 +44,7 @@ struct _Py_freelist { struct _Py_freelists { struct _Py_freelist floats; + struct _Py_freelist complexes; struct _Py_freelist ints; struct _Py_freelist tuples[PyTuple_MAXSAVESIZE]; struct _Py_freelist lists; diff --git a/Include/internal/pycore_interp_structs.h b/Include/internal/pycore_interp_structs.h index f25f5847b3b..f1f427d99de 100644 --- a/Include/internal/pycore_interp_structs.h +++ b/Include/internal/pycore_interp_structs.h @@ -159,10 +159,11 @@ struct atexit_state { typedef struct { // Tagged pointer to next object in the list. // 0 means the object is not tracked - uintptr_t _gc_next; + _Py_ALIGNED_DEF(_PyObject_MIN_ALIGNMENT, uintptr_t) _gc_next; // Tagged pointer to previous object in the list. // Lowest two bits are used for flags documented later. + // Those bits are made available by the struct's minimum alignment. uintptr_t _gc_prev; } PyGC_Head; diff --git a/Include/internal/pycore_stackref.h b/Include/internal/pycore_stackref.h index f2ecc30b053..10e7199269e 100644 --- a/Include/internal/pycore_stackref.h +++ b/Include/internal/pycore_stackref.h @@ -62,14 +62,15 @@ PyAPI_FUNC(void) _Py_stackref_record_borrow(_PyStackRef ref, const char *filenam extern void _Py_stackref_associate(PyInterpreterState *interp, PyObject *obj, _PyStackRef ref); static const _PyStackRef PyStackRef_NULL = { .index = 0 }; +static const _PyStackRef PyStackRef_ERROR = { .index = 2 }; // Use the first 3 even numbers for None, True and False. // Odd numbers are reserved for (tagged) integers -#define PyStackRef_None ((_PyStackRef){ .index = 2 } ) -#define PyStackRef_False ((_PyStackRef){ .index = 4 }) -#define PyStackRef_True ((_PyStackRef){ .index = 6 }) +#define PyStackRef_None ((_PyStackRef){ .index = 4 } ) +#define PyStackRef_False ((_PyStackRef){ .index = 6 }) +#define PyStackRef_True ((_PyStackRef){ .index = 8 }) -#define INITIAL_STACKREF_INDEX 8 +#define INITIAL_STACKREF_INDEX 10 static inline int PyStackRef_IsNull(_PyStackRef ref) @@ -77,6 +78,19 @@ PyStackRef_IsNull(_PyStackRef ref) return ref.index == 0; } +static inline bool +PyStackRef_IsError(_PyStackRef ref) +{ + return ref.index == 2; +} + +static inline bool +PyStackRef_IsValid(_PyStackRef ref) +{ + /* Invalid values are ERROR and NULL */ + return !PyStackRef_IsError(ref) && !PyStackRef_IsNull(ref); +} + static inline int PyStackRef_IsTrue(_PyStackRef ref) { @@ -104,6 +118,7 @@ PyStackRef_IsTaggedInt(_PyStackRef ref) static inline PyObject * _PyStackRef_AsPyObjectBorrow(_PyStackRef ref, const char *filename, int linenumber) { + assert(!PyStackRef_IsError(ref)); assert(!PyStackRef_IsTaggedInt(ref)); _Py_stackref_record_borrow(ref, filename, linenumber); return _Py_stackref_get_object(ref); @@ -155,6 +170,7 @@ _PyStackRef_CLOSE(_PyStackRef ref, const char *filename, int linenumber) static inline void _PyStackRef_XCLOSE(_PyStackRef ref, const char *filename, int linenumber) { + assert(!PyStackRef_IsError(ref)); if (PyStackRef_IsNull(ref)) { return; } @@ -165,6 +181,7 @@ _PyStackRef_XCLOSE(_PyStackRef ref, const char *filename, int linenumber) static inline _PyStackRef _PyStackRef_DUP(_PyStackRef ref, const char *filename, int linenumber) { + assert(!PyStackRef_IsError(ref)); if (PyStackRef_IsTaggedInt(ref)) { return ref; } @@ -241,9 +258,51 @@ PyStackRef_IsNullOrInt(_PyStackRef ref); #else #define Py_INT_TAG 3 +#define Py_TAG_INVALID 2 #define Py_TAG_REFCNT 1 #define Py_TAG_BITS 3 +static const _PyStackRef PyStackRef_ERROR = { .bits = Py_TAG_INVALID }; + +/* Wrap a pointer in a stack ref. + * The resulting stack reference is not safe and should only be used + * in the interpreter to pass values from one uop to another. + * The GC should never see one of these stack refs. */ +static inline _PyStackRef +PyStackRef_Wrap(void *ptr) +{ + assert(ptr != NULL); +#ifdef Py_DEBUG + return (_PyStackRef){ .bits = ((uintptr_t)ptr) | Py_TAG_INVALID }; +#else + return (_PyStackRef){ .bits = (uintptr_t)ptr }; +#endif +} + +static inline void * +PyStackRef_Unwrap(_PyStackRef ref) +{ +#ifdef Py_DEBUG + assert ((ref.bits & Py_TAG_BITS) == Py_TAG_INVALID); + return (void *)(ref.bits & ~Py_TAG_BITS); +#else + return (void *)(ref.bits); +#endif +} + +static inline bool +PyStackRef_IsError(_PyStackRef ref) +{ + return ref.bits == Py_TAG_INVALID; +} + +static inline bool +PyStackRef_IsValid(_PyStackRef ref) +{ + /* Invalid values are ERROR and NULL */ + return ref.bits >= Py_INT_TAG; +} + static inline bool PyStackRef_IsTaggedInt(_PyStackRef i) { @@ -284,6 +343,7 @@ PyStackRef_IncrementTaggedIntNoOverflow(_PyStackRef ref) static const _PyStackRef PyStackRef_NULL = { .bits = Py_TAG_DEFERRED}; + #define PyStackRef_IsNull(stackref) ((stackref).bits == PyStackRef_NULL.bits) #define PyStackRef_True ((_PyStackRef){.bits = ((uintptr_t)&_Py_TrueStruct) | Py_TAG_DEFERRED }) #define PyStackRef_False ((_PyStackRef){.bits = ((uintptr_t)&_Py_FalseStruct) | Py_TAG_DEFERRED }) diff --git a/Include/object.h b/Include/object.h index 42aed614d4a..c75e9db0cbd 100644 --- a/Include/object.h +++ b/Include/object.h @@ -101,6 +101,12 @@ whose size is determined when the object is allocated. #define PyObject_VAR_HEAD PyVarObject ob_base; #define Py_INVALID_SIZE (Py_ssize_t)-1 +/* PyObjects are given a minimum alignment so that the least significant bits + * of an object pointer become available for other purposes. + * This must be an integer literal with the value (1 << _PyGC_PREV_SHIFT), number of bytes. + */ +#define _PyObject_MIN_ALIGNMENT 4 + /* Nothing is actually declared to be a PyObject, but every pointer to * a Python object can be cast to a PyObject*. This is inheritance built * by hand. Similarly every pointer to a variable-size Python object can, @@ -136,6 +142,7 @@ struct _object { #else Py_ssize_t ob_refcnt; #endif + _Py_ALIGNED_DEF(_PyObject_MIN_ALIGNMENT, char) _aligner; }; #ifdef _MSC_VER __pragma(warning(pop)) @@ -153,7 +160,7 @@ struct _object { // ob_tid stores the thread id (or zero). It is also used by the GC and the // trashcan mechanism as a linked list pointer and by the GC to store the // computed "gc_refs" refcount. - uintptr_t ob_tid; + _Py_ALIGNED_DEF(_PyObject_MIN_ALIGNMENT, uintptr_t) ob_tid; uint16_t ob_flags; PyMutex ob_mutex; // per-object lock uint8_t ob_gc_bits; // gc-related state diff --git a/Include/pymacro.h b/Include/pymacro.h index d410645034d..bfe660e8303 100644 --- a/Include/pymacro.h +++ b/Include/pymacro.h @@ -24,44 +24,66 @@ #endif -// _Py_ALIGN_AS: this compiler's spelling of `alignas` keyword, -// We currently use alignas for free-threaded builds only; additional compat -// checking would be great before we add it to the default build. -// Standards/compiler support: +// _Py_ALIGNED_DEF(N, T): Define a variable/member with increased alignment +// +// `N`: the desired minimum alignment, an integer literal, number of bytes +// `T`: the type of the defined variable +// (or a type with at least the defined variable's alignment) +// +// May not be used on a struct definition. +// +// Standards/compiler support for `alignas` alternatives: // - `alignas` is a keyword in C23 and C++11. // - `_Alignas` is a keyword in C11 // - GCC & clang has __attribute__((aligned)) // (use that for older standards in pedantic mode) // - MSVC has __declspec(align) // - `_Alignas` is common C compiler extension -// Older compilers may name it differently; to allow compilation on such -// unsupported platforms, we don't redefine _Py_ALIGN_AS if it's already +// Older compilers may name `alignas` differently; to allow compilation on such +// unsupported platforms, we don't redefine _Py_ALIGNED_DEF if it's already // defined. Note that defining it wrong (including defining it to nothing) will // cause ABI incompatibilities. -#ifdef Py_GIL_DISABLED -# ifndef _Py_ALIGN_AS -# ifdef __cplusplus -# if __cplusplus >= 201103L -# define _Py_ALIGN_AS(V) alignas(V) -# elif defined(__GNUC__) || defined(__clang__) -# define _Py_ALIGN_AS(V) __attribute__((aligned(V))) -# elif defined(_MSC_VER) -# define _Py_ALIGN_AS(V) __declspec(align(V)) -# else -# define _Py_ALIGN_AS(V) alignas(V) -# endif -# elif defined(__STDC_VERSION__) && __STDC_VERSION__ >= 202311L -# define _Py_ALIGN_AS(V) alignas(V) -# elif defined(__STDC_VERSION__) && __STDC_VERSION__ >= 201112L -# define _Py_ALIGN_AS(V) _Alignas(V) -# elif (defined(__GNUC__) || defined(__clang__)) -# define _Py_ALIGN_AS(V) __attribute__((aligned(V))) -# elif defined(_MSC_VER) -# define _Py_ALIGN_AS(V) __declspec(align(V)) -# else -# define _Py_ALIGN_AS(V) _Alignas(V) -# endif -# endif +// +// Behavior of `alignas` alternatives: +// - `alignas` & `_Alignas`: +// - Can be used multiple times; the greatest alignment applies. +// - It is an *error* if the combined effect of all `alignas` modifiers would +// decrease the alignment. +// - Takes types or numbers. +// - May not be used on a struct definition, unless also defining a variable. +// - `__declspec(align)`: +// - Has no effect if it would decrease alignment. +// - Only takes an integer literal. +// - May be used on struct or variable definitions. +// However, when defining both the struct and the variable at once, +// `declspec(aligned)` causes compiler warning 5274 and possible ABI +// incompatibility. +// - ` __attribute__((aligned))`: +// - Has no effect if it would decrease alignment. +// - Takes types or numbers +// - May be used on struct or variable definitions. +#ifndef _Py_ALIGNED_DEF +# ifdef __cplusplus +# if __cplusplus >= 201103L +# define _Py_ALIGNED_DEF(N, T) alignas(N) alignas(T) T +# elif defined(__GNUC__) || defined(__clang__) +# define _Py_ALIGNED_DEF(N, T) __attribute__((aligned(N))) T +# elif defined(_MSC_VER) +# define _Py_ALIGNED_DEF(N, T) __declspec(align(N)) T +# else +# define _Py_ALIGNED_DEF(N, T) alignas(N) alignas(T) T +# endif +# elif defined(__STDC_VERSION__) && __STDC_VERSION__ >= 202311L +# define _Py_ALIGNED_DEF(N, T) alignas(N) alignas(T) T +# elif defined(__STDC_VERSION__) && __STDC_VERSION__ >= 201112L +# define _Py_ALIGNED_DEF(N, T) _Alignas(N) _Alignas(T) T +# elif (defined(__GNUC__) || defined(__clang__)) +# define _Py_ALIGNED_DEF(N, T) __attribute__((aligned(N))) T +# elif defined(_MSC_VER) +# define _Py_ALIGNED_DEF(N, T) __declspec(align(N)) T +# else +# define _Py_ALIGNED_DEF(N, T) _Alignas(N) _Alignas(T) T +# endif #endif /* Minimum value between x and y */ |