5ae8575296
* x64: Take SIGFPE signals for divide traps Prior to this commit Wasmtime would configure `avoid_div_traps=true` unconditionally for Cranelift. This, for the division-based instructions, would change emitted code to explicitly trap on trap conditions instead of letting the `div` x86 instruction trap. There's no specific reason for Wasmtime, however, to specifically avoid traps in the `div` instruction. This means that the extra generated branches on x86 aren't necessary since the `div` and `idiv` instructions already trap for similar conditions as wasm requires. This commit instead disables the `avoid_div_traps` setting for Wasmtime's usage of Cranelift. Subsequently the codegen rules were updated slightly: * When `avoid_div_traps=true`, traps are no longer emitted for `div` instructions. * The `udiv`/`urem` instructions now list their trap as divide-by-zero instead of integer overflow. * The lowering for `sdiv` was updated to still explicitly check for zero but the integer overflow case is deferred to the instruction itself. * The lowering of `srem` no longer checks for zero and the listed trap for the `div` instruction is a divide-by-zero. This means that the codegen for `udiv` and `urem` no longer have any branches. The codegen for `sdiv` removes one branch but keeps the zero-check to differentiate the two kinds of traps. The codegen for `srem` removes one branch but keeps the -1 check since the semantics of `srem` mismatch with the semantics of `idiv` with a -1 divisor (specifically for INT_MIN). This is unlikely to have really all that much of a speedup but was something I noticed during #6008 which seemed like it'd be good to clean up. Plus Wasmtime's signal handling was already set up to catch `SIGFPE`, it was just never firing. * Remove the `avoid_div_traps` cranelift setting With no known users currently removing this should be possible and helps simplify the x64 backend. * x64: GC more support for avoid_div_traps Remove the `validate_sdiv_divisor*` pseudo-instructions and clean up some of the ISLE rules now that `div` is allowed to itself trap unconditionally. * x64: Store div trap code in instruction itself * Keep divisors in registers, not in memory Don't accidentally fold multiple traps together * Handle EXC_ARITHMETIC on macos * Update emit tests * Update winch and tests
140 lines
2.4 KiB
Plaintext
140 lines
2.4 KiB
Plaintext
test compile precise-output
|
|
target x86_64
|
|
|
|
function %f1(i8, i8) -> i8 {
|
|
block0(v0: i8, v1: i8):
|
|
v2 = sdiv v0, v1
|
|
return v2
|
|
}
|
|
|
|
; VCode:
|
|
; pushq %rbp
|
|
; movq %rsp, %rbp
|
|
; block0:
|
|
; movq %rdi, %rax
|
|
; cbw %al, %al
|
|
; testb %sil, %sil
|
|
; jnz ; ud2 int_divz ;
|
|
; idiv %al, %sil, %al ; trap=int_ovf
|
|
; movq %rbp, %rsp
|
|
; popq %rbp
|
|
; ret
|
|
;
|
|
; Disassembled:
|
|
; block0: ; offset 0x0
|
|
; pushq %rbp
|
|
; movq %rsp, %rbp
|
|
; block1: ; offset 0x4
|
|
; movq %rdi, %rax
|
|
; cbtw
|
|
; testb %sil, %sil
|
|
; jne 0x14
|
|
; ud2 ; trap: int_divz
|
|
; idivb %sil ; trap: int_ovf
|
|
; movq %rbp, %rsp
|
|
; popq %rbp
|
|
; retq
|
|
|
|
function %f2(i16, i16) -> i16 {
|
|
block0(v0: i16, v1: i16):
|
|
v2 = sdiv v0, v1
|
|
return v2
|
|
}
|
|
|
|
; VCode:
|
|
; pushq %rbp
|
|
; movq %rsp, %rbp
|
|
; block0:
|
|
; movq %rdi, %rax
|
|
; cwd %ax, %dx
|
|
; testw %si, %si
|
|
; jnz ; ud2 int_divz ;
|
|
; idiv %ax, %dx, %si, %ax, %dx ; trap=int_ovf
|
|
; movq %rbp, %rsp
|
|
; popq %rbp
|
|
; ret
|
|
;
|
|
; Disassembled:
|
|
; block0: ; offset 0x0
|
|
; pushq %rbp
|
|
; movq %rsp, %rbp
|
|
; block1: ; offset 0x4
|
|
; movq %rdi, %rax
|
|
; cwtd
|
|
; testw %si, %si
|
|
; jne 0x14
|
|
; ud2 ; trap: int_divz
|
|
; idivw %si ; trap: int_ovf
|
|
; movq %rbp, %rsp
|
|
; popq %rbp
|
|
; retq
|
|
|
|
function %f3(i32, i32) -> i32 {
|
|
block0(v0: i32, v1: i32):
|
|
v2 = sdiv v0, v1
|
|
return v2
|
|
}
|
|
|
|
; VCode:
|
|
; pushq %rbp
|
|
; movq %rsp, %rbp
|
|
; block0:
|
|
; movq %rdi, %rax
|
|
; cdq %eax, %edx
|
|
; testl %esi, %esi
|
|
; jnz ; ud2 int_divz ;
|
|
; idiv %eax, %edx, %esi, %eax, %edx ; trap=int_ovf
|
|
; movq %rbp, %rsp
|
|
; popq %rbp
|
|
; ret
|
|
;
|
|
; Disassembled:
|
|
; block0: ; offset 0x0
|
|
; pushq %rbp
|
|
; movq %rsp, %rbp
|
|
; block1: ; offset 0x4
|
|
; movq %rdi, %rax
|
|
; cltd
|
|
; testl %esi, %esi
|
|
; jne 0x12
|
|
; ud2 ; trap: int_divz
|
|
; idivl %esi ; trap: int_ovf
|
|
; movq %rbp, %rsp
|
|
; popq %rbp
|
|
; retq
|
|
|
|
function %f4(i64, i64) -> i64 {
|
|
block0(v0: i64, v1: i64):
|
|
v2 = sdiv v0, v1
|
|
return v2
|
|
}
|
|
|
|
; VCode:
|
|
; pushq %rbp
|
|
; movq %rsp, %rbp
|
|
; block0:
|
|
; movq %rdi, %rax
|
|
; cqo %rax, %rdx
|
|
; testq %rsi, %rsi
|
|
; jnz ; ud2 int_divz ;
|
|
; idiv %rax, %rdx, %rsi, %rax, %rdx ; trap=int_ovf
|
|
; movq %rbp, %rsp
|
|
; popq %rbp
|
|
; ret
|
|
;
|
|
; Disassembled:
|
|
; block0: ; offset 0x0
|
|
; pushq %rbp
|
|
; movq %rsp, %rbp
|
|
; block1: ; offset 0x4
|
|
; movq %rdi, %rax
|
|
; cqto
|
|
; testq %rsi, %rsi
|
|
; jne 0x14
|
|
; ud2 ; trap: int_divz
|
|
; idivq %rsi ; trap: int_ovf
|
|
; movq %rbp, %rsp
|
|
; popq %rbp
|
|
; retq
|
|
|