mirror of
https://github.com/python/cpython.git
synced 2025-07-12 13:55:34 +00:00
5535482d2a
gh-136541: Fix several problems of perf trampolines in x86_64 and aarch64 (GH-136500)
This commit fixes the following problems:
* The x86_64 trampolines are not preserving frame pointers
* The hardcoded offsets to the code segment from the FDE only worked properly for x64_64
* The CIE data was not following conventions of aarch64
* The eh_frame for aarch64 was not fully correct
(cherry picked from commit 236f733d8f)
Co-authored-by: Pablo Galindo Salgado <Pablogsal@gmail.com>
59 lines
1.3 KiB
ArmAsm
59 lines
1.3 KiB
ArmAsm
.text
|
|
.globl _Py_trampoline_func_start
|
|
# The following assembly is equivalent to:
|
|
# PyObject *
|
|
# trampoline(PyThreadState *ts, _PyInterpreterFrame *f,
|
|
# int throwflag, py_evaluator evaluator)
|
|
# {
|
|
# return evaluator(ts, f, throwflag);
|
|
# }
|
|
_Py_trampoline_func_start:
|
|
#ifdef __x86_64__
|
|
#if defined(__CET__) && (__CET__ & 1)
|
|
endbr64
|
|
#endif
|
|
push %rbp
|
|
mov %rsp, %rbp
|
|
call *%rcx
|
|
pop %rbp
|
|
ret
|
|
#endif // __x86_64__
|
|
#if defined(__aarch64__) && defined(__AARCH64EL__) && !defined(__ILP32__)
|
|
// ARM64 little endian, 64bit ABI
|
|
// generate with aarch64-linux-gnu-gcc 12.1
|
|
stp x29, x30, [sp, -16]!
|
|
mov x29, sp
|
|
blr x3
|
|
ldp x29, x30, [sp], 16
|
|
ret
|
|
#endif
|
|
#ifdef __riscv
|
|
addi sp,sp,-16
|
|
sd ra,8(sp)
|
|
jalr a3
|
|
ld ra,8(sp)
|
|
addi sp,sp,16
|
|
jr ra
|
|
#endif
|
|
.globl _Py_trampoline_func_end
|
|
_Py_trampoline_func_end:
|
|
.section .note.GNU-stack,"",@progbits
|
|
# Note for indicating the assembly code supports CET
|
|
#if defined(__x86_64__) && defined(__CET__) && (__CET__ & 1)
|
|
.section .note.gnu.property,"a"
|
|
.align 8
|
|
.long 1f - 0f
|
|
.long 4f - 1f
|
|
.long 5
|
|
0:
|
|
.string "GNU"
|
|
1:
|
|
.align 8
|
|
.long 0xc0000002
|
|
.long 3f - 2f
|
|
2:
|
|
.long 0x3
|
|
3:
|
|
.align 8
|
|
4:
|
|
#endif // __x86_64__
|