micropython/py/pystack.h

124 lines
4.0 KiB
C
Raw Normal View History

py: Introduce a Python stack for scoped allocation. This patch introduces the MICROPY_ENABLE_PYSTACK option (disabled by default) which enables a "Python stack" that allows to allocate and free memory in a scoped, or Last-In-First-Out (LIFO) way, similar to alloca(). A new memory allocation API is introduced along with this Py-stack. It includes both "local" and "nonlocal" LIFO allocation. Local allocation is intended to be equivalent to using alloca(), whereby the same function must free the memory. Nonlocal allocation is where another function may free the memory, so long as it's still LIFO. Follow-up patches will convert all uses of alloca() and VLA to the new scoped allocation API. The old behaviour (using alloca()) will still be available, but when MICROPY_ENABLE_PYSTACK is enabled then alloca() is no longer required or used. The benefits of enabling this option are (or will be once subsequent patches are made to convert alloca()/VLA): - Toolchains without alloca() can use this feature to obtain correct and efficient scoped memory allocation (compared to using the heap instead of alloca(), which is slower). - Even if alloca() is available, enabling the Py-stack gives slightly more efficient use of stack space when calling nested Python functions, due to the way that compilers implement alloca(). - Enabling the Py-stack with the stackless mode allows for even more efficient stack usage, as well as retaining high performance (because the heap is no longer used to build and destroy stackless code states). - With Py-stack and stackless enabled, Python-calling-Python is no longer recursive in the C mp_execute_bytecode function. The micropython.pystack_use() function is included to measure usage of the Python stack.
2017-11-26 12:28:40 +00:00
/*
* This file is part of the MicroPython project, http://micropython.org/
*
* The MIT License (MIT)
*
* Copyright (c) 2017 Damien P. George
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#ifndef MICROPY_INCLUDED_PY_PYSTACK_H
#define MICROPY_INCLUDED_PY_PYSTACK_H
#include "py/mpstate.h"
// Enable this debugging option to check that the amount of memory freed is
// consistent with amounts that were previously allocated.
#define MP_PYSTACK_DEBUG (0)
#if MICROPY_ENABLE_PYSTACK
void mp_pystack_init(void *start, void *end);
void *mp_pystack_alloc(size_t n_bytes);
// This function can free multiple continuous blocks at once: just pass the
// pointer to the block that was allocated first and it and all subsequently
// allocated blocks will be freed.
static inline void mp_pystack_free(void *ptr) {
assert((uint8_t *)ptr >= MP_STATE_THREAD(pystack_start));
assert((uint8_t *)ptr <= MP_STATE_THREAD(pystack_cur));
py: Introduce a Python stack for scoped allocation. This patch introduces the MICROPY_ENABLE_PYSTACK option (disabled by default) which enables a "Python stack" that allows to allocate and free memory in a scoped, or Last-In-First-Out (LIFO) way, similar to alloca(). A new memory allocation API is introduced along with this Py-stack. It includes both "local" and "nonlocal" LIFO allocation. Local allocation is intended to be equivalent to using alloca(), whereby the same function must free the memory. Nonlocal allocation is where another function may free the memory, so long as it's still LIFO. Follow-up patches will convert all uses of alloca() and VLA to the new scoped allocation API. The old behaviour (using alloca()) will still be available, but when MICROPY_ENABLE_PYSTACK is enabled then alloca() is no longer required or used. The benefits of enabling this option are (or will be once subsequent patches are made to convert alloca()/VLA): - Toolchains without alloca() can use this feature to obtain correct and efficient scoped memory allocation (compared to using the heap instead of alloca(), which is slower). - Even if alloca() is available, enabling the Py-stack gives slightly more efficient use of stack space when calling nested Python functions, due to the way that compilers implement alloca(). - Enabling the Py-stack with the stackless mode allows for even more efficient stack usage, as well as retaining high performance (because the heap is no longer used to build and destroy stackless code states). - With Py-stack and stackless enabled, Python-calling-Python is no longer recursive in the C mp_execute_bytecode function. The micropython.pystack_use() function is included to measure usage of the Python stack.
2017-11-26 12:28:40 +00:00
#if MP_PYSTACK_DEBUG
size_t n_bytes_to_free = MP_STATE_THREAD(pystack_cur) - (uint8_t *)ptr;
size_t n_bytes = *(size_t *)(MP_STATE_THREAD(pystack_cur) - MICROPY_PYSTACK_ALIGN);
py: Introduce a Python stack for scoped allocation. This patch introduces the MICROPY_ENABLE_PYSTACK option (disabled by default) which enables a "Python stack" that allows to allocate and free memory in a scoped, or Last-In-First-Out (LIFO) way, similar to alloca(). A new memory allocation API is introduced along with this Py-stack. It includes both "local" and "nonlocal" LIFO allocation. Local allocation is intended to be equivalent to using alloca(), whereby the same function must free the memory. Nonlocal allocation is where another function may free the memory, so long as it's still LIFO. Follow-up patches will convert all uses of alloca() and VLA to the new scoped allocation API. The old behaviour (using alloca()) will still be available, but when MICROPY_ENABLE_PYSTACK is enabled then alloca() is no longer required or used. The benefits of enabling this option are (or will be once subsequent patches are made to convert alloca()/VLA): - Toolchains without alloca() can use this feature to obtain correct and efficient scoped memory allocation (compared to using the heap instead of alloca(), which is slower). - Even if alloca() is available, enabling the Py-stack gives slightly more efficient use of stack space when calling nested Python functions, due to the way that compilers implement alloca(). - Enabling the Py-stack with the stackless mode allows for even more efficient stack usage, as well as retaining high performance (because the heap is no longer used to build and destroy stackless code states). - With Py-stack and stackless enabled, Python-calling-Python is no longer recursive in the C mp_execute_bytecode function. The micropython.pystack_use() function is included to measure usage of the Python stack.
2017-11-26 12:28:40 +00:00
while (n_bytes < n_bytes_to_free) {
n_bytes += *(size_t *)(MP_STATE_THREAD(pystack_cur) - n_bytes - MICROPY_PYSTACK_ALIGN);
py: Introduce a Python stack for scoped allocation. This patch introduces the MICROPY_ENABLE_PYSTACK option (disabled by default) which enables a "Python stack" that allows to allocate and free memory in a scoped, or Last-In-First-Out (LIFO) way, similar to alloca(). A new memory allocation API is introduced along with this Py-stack. It includes both "local" and "nonlocal" LIFO allocation. Local allocation is intended to be equivalent to using alloca(), whereby the same function must free the memory. Nonlocal allocation is where another function may free the memory, so long as it's still LIFO. Follow-up patches will convert all uses of alloca() and VLA to the new scoped allocation API. The old behaviour (using alloca()) will still be available, but when MICROPY_ENABLE_PYSTACK is enabled then alloca() is no longer required or used. The benefits of enabling this option are (or will be once subsequent patches are made to convert alloca()/VLA): - Toolchains without alloca() can use this feature to obtain correct and efficient scoped memory allocation (compared to using the heap instead of alloca(), which is slower). - Even if alloca() is available, enabling the Py-stack gives slightly more efficient use of stack space when calling nested Python functions, due to the way that compilers implement alloca(). - Enabling the Py-stack with the stackless mode allows for even more efficient stack usage, as well as retaining high performance (because the heap is no longer used to build and destroy stackless code states). - With Py-stack and stackless enabled, Python-calling-Python is no longer recursive in the C mp_execute_bytecode function. The micropython.pystack_use() function is included to measure usage of the Python stack.
2017-11-26 12:28:40 +00:00
}
if (n_bytes != n_bytes_to_free) {
mp_printf(&mp_plat_print, "mp_pystack_free() failed: %u != %u\n", (uint)n_bytes_to_free,
(uint)*(size_t *)(MP_STATE_THREAD(pystack_cur) - MICROPY_PYSTACK_ALIGN));
py: Introduce a Python stack for scoped allocation. This patch introduces the MICROPY_ENABLE_PYSTACK option (disabled by default) which enables a "Python stack" that allows to allocate and free memory in a scoped, or Last-In-First-Out (LIFO) way, similar to alloca(). A new memory allocation API is introduced along with this Py-stack. It includes both "local" and "nonlocal" LIFO allocation. Local allocation is intended to be equivalent to using alloca(), whereby the same function must free the memory. Nonlocal allocation is where another function may free the memory, so long as it's still LIFO. Follow-up patches will convert all uses of alloca() and VLA to the new scoped allocation API. The old behaviour (using alloca()) will still be available, but when MICROPY_ENABLE_PYSTACK is enabled then alloca() is no longer required or used. The benefits of enabling this option are (or will be once subsequent patches are made to convert alloca()/VLA): - Toolchains without alloca() can use this feature to obtain correct and efficient scoped memory allocation (compared to using the heap instead of alloca(), which is slower). - Even if alloca() is available, enabling the Py-stack gives slightly more efficient use of stack space when calling nested Python functions, due to the way that compilers implement alloca(). - Enabling the Py-stack with the stackless mode allows for even more efficient stack usage, as well as retaining high performance (because the heap is no longer used to build and destroy stackless code states). - With Py-stack and stackless enabled, Python-calling-Python is no longer recursive in the C mp_execute_bytecode function. The micropython.pystack_use() function is included to measure usage of the Python stack.
2017-11-26 12:28:40 +00:00
assert(0);
}
#endif
MP_STATE_THREAD(pystack_cur) = (uint8_t *)ptr;
py: Introduce a Python stack for scoped allocation. This patch introduces the MICROPY_ENABLE_PYSTACK option (disabled by default) which enables a "Python stack" that allows to allocate and free memory in a scoped, or Last-In-First-Out (LIFO) way, similar to alloca(). A new memory allocation API is introduced along with this Py-stack. It includes both "local" and "nonlocal" LIFO allocation. Local allocation is intended to be equivalent to using alloca(), whereby the same function must free the memory. Nonlocal allocation is where another function may free the memory, so long as it's still LIFO. Follow-up patches will convert all uses of alloca() and VLA to the new scoped allocation API. The old behaviour (using alloca()) will still be available, but when MICROPY_ENABLE_PYSTACK is enabled then alloca() is no longer required or used. The benefits of enabling this option are (or will be once subsequent patches are made to convert alloca()/VLA): - Toolchains without alloca() can use this feature to obtain correct and efficient scoped memory allocation (compared to using the heap instead of alloca(), which is slower). - Even if alloca() is available, enabling the Py-stack gives slightly more efficient use of stack space when calling nested Python functions, due to the way that compilers implement alloca(). - Enabling the Py-stack with the stackless mode allows for even more efficient stack usage, as well as retaining high performance (because the heap is no longer used to build and destroy stackless code states). - With Py-stack and stackless enabled, Python-calling-Python is no longer recursive in the C mp_execute_bytecode function. The micropython.pystack_use() function is included to measure usage of the Python stack.
2017-11-26 12:28:40 +00:00
}
static inline void mp_pystack_realloc(void *ptr, size_t n_bytes) {
mp_pystack_free(ptr);
mp_pystack_alloc(n_bytes);
}
static inline size_t mp_pystack_usage(void) {
return MP_STATE_THREAD(pystack_cur) - MP_STATE_THREAD(pystack_start);
}
static inline size_t mp_pystack_limit(void) {
return MP_STATE_THREAD(pystack_end) - MP_STATE_THREAD(pystack_start);
}
#endif
#if !MICROPY_ENABLE_PYSTACK
#define mp_local_alloc(n_bytes) alloca(n_bytes)
static inline void mp_local_free(void *ptr) {
(void)ptr;
}
static inline void *mp_nonlocal_alloc(size_t n_bytes) {
return m_new(uint8_t, n_bytes);
}
static inline void *mp_nonlocal_realloc(void *ptr, size_t old_n_bytes, size_t new_n_bytes) {
return m_renew(uint8_t, ptr, old_n_bytes, new_n_bytes);
}
static inline void mp_nonlocal_free(void *ptr, size_t n_bytes) {
m_del(uint8_t, ptr, n_bytes);
}
#else
static inline void *mp_local_alloc(size_t n_bytes) {
return mp_pystack_alloc(n_bytes);
}
static inline void mp_local_free(void *ptr) {
mp_pystack_free(ptr);
}
static inline void *mp_nonlocal_alloc(size_t n_bytes) {
return mp_pystack_alloc(n_bytes);
}
static inline void *mp_nonlocal_realloc(void *ptr, size_t old_n_bytes, size_t new_n_bytes) {
(void)old_n_bytes;
mp_pystack_realloc(ptr, new_n_bytes);
return ptr;
}
static inline void mp_nonlocal_free(void *ptr, size_t n_bytes) {
(void)n_bytes;
mp_pystack_free(ptr);
}
#endif
#endif // MICROPY_INCLUDED_PY_PYSTACK_H