diff options
Diffstat (limited to 'linux/302stack_allocate.subx')
-rw-r--r-- | linux/302stack_allocate.subx | 61 |
1 files changed, 61 insertions, 0 deletions
diff --git a/linux/302stack_allocate.subx b/linux/302stack_allocate.subx new file mode 100644 index 00000000..cd51d5ff --- /dev/null +++ b/linux/302stack_allocate.subx @@ -0,0 +1,61 @@ +# A function which pushes n zeros on the stack. +# Really only intended to be called from code generated by mu.subx (for array +# vars on the stack). + +== code + +#? Entry: +#? # . prologue +#? 89/<- %ebp 4/r32/esp +#? # +#? 68/push 0xfcfdfeff/imm32 +#? b8/copy-to-eax 0x34353637/imm32 +#? $dump-stack0: +#? (push-n-zero-bytes 4) +#? 68/push 0x20/imm32 +#? $dump-stack9: +#? b8/copy-to-eax 1/imm32/exit +#? cd/syscall 0x80/imm8 + +# This is not a regular function, so it won't be idiomatic. +# Registers must be properly restored. +# Registers can be spilled, but that modifies the stack and needs to be +# cleaned up. + +# Overhead: +# 62 + n*6 instructions to push n bytes. +# If we just emitted code to push n zeroes, it would be: +# 5 bytes for 4 zero bytes, so 1.25 bytes per zero. And that's not even +# instructions. +# But on the other hand it would destroy the instruction cache, where this +# approach requires 15 instructions, fixed. + +# n must be positive +push-n-zero-bytes: # n: int +$push-n-zero-bytes:prologue: + 89/<- *Push-n-zero-bytes-ebp 5/r32/ebp # spill ebp without affecting stack + 89/<- %ebp 4/r32/esp +$push-n-zero-bytes:copy-ra: + # -- esp = ebp + 89/<- *Push-n-zero-bytes-eax 0/r32/eax + 8b/-> *esp 0/r32/eax + 2b/subtract *(ebp+4) 4/r32/esp + # -- esp+n = ebp + 89/<- *esp 0/r32/eax + 8b/-> *Push-n-zero-bytes-eax 0/r32/eax +$push-n-zero-bytes:bulk-cleaning: + 89/<- *Push-n-zero-bytes-esp 4/r32/esp + 81 0/subop/add *Push-n-zero-bytes-esp 4/imm32 + 81 0/subop/add *(ebp+4) 4/imm32 + (zero-out *Push-n-zero-bytes-esp *(ebp+4)) # n+4 +$push-n-zero-bytes:epilogue: + 8b/-> *Push-n-zero-bytes-ebp 5/r32/ebp # restore spill + c3/return + +== data +Push-n-zero-bytes-ebp: # (addr int) + 0/imm32 +Push-n-zero-bytes-esp: # (addr int) + 0/imm32 +Push-n-zero-bytes-eax: + 0/imm32 |