50a97aacac
Re-commit of 32e8b550e5439c7e4aafa73894faffd5f25d0d05 This patch rearranges emission of CFI instructions, so the resulting DWARF and `.eh_frame` information is precise at every instruction. The current state is that the unwind info is emitted only after the function prologue. This is fine for synchronous (e.g. C++) exceptions, but the information is generally incorrect when the program counter is at an instruction in the prologue or the epilogue, for example: ``` stp x29, x30, [sp, #-16]! // 16-byte Folded Spill mov x29, sp .cfi_def_cfa w29, 16 ... ``` after the `stp` is executed the (initial) rule for the CFA still says the CFA is in the `sp`, even though it's already offset by 16 bytes A correct unwind info could look like: ``` stp x29, x30, [sp, #-16]! // 16-byte Folded Spill .cfi_def_cfa_offset 16 mov x29, sp .cfi_def_cfa w29, 16 ... ``` Having this information precise up to an instruction is useful for sampling profilers that would like to get a stack backtrace. The end goal (towards this patch is just a step) is to have fully working `-fasynchronous-unwind-tables`. Reviewed By: danielkiss, MaskRay Differential Revision: https://reviews.llvm.org/D111411
66 lines
2.1 KiB
LLVM
66 lines
2.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=aarch64-linux-gnu -verify-machineinstrs -o - %s | FileCheck %s
|
|
; LSR used to pick a sub-optimal solution due to the target responding
|
|
; conservatively to isLegalAddImmediate for negative values.
|
|
|
|
declare void @foo(i32)
|
|
|
|
define void @test(i32 %px) {
|
|
; CHECK-LABEL: test:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: str x30, [sp, #-32]! // 8-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_offset w19, -8
|
|
; CHECK-NEXT: .cfi_offset w20, -16
|
|
; CHECK-NEXT: .cfi_offset w30, -32
|
|
; CHECK-NEXT: subs w8, w0, #1
|
|
; CHECK-NEXT: mov w19, w0
|
|
; CHECK-NEXT: csel w20, wzr, w8, lt
|
|
; CHECK-NEXT: b .LBB0_2
|
|
; CHECK-NEXT: .LBB0_1: // %for.inc
|
|
; CHECK-NEXT: // in Loop: Header=BB0_2 Depth=1
|
|
; CHECK-NEXT: add w8, w20, #1
|
|
; CHECK-NEXT: cmp w20, w19
|
|
; CHECK-NEXT: mov w20, w8
|
|
; CHECK-NEXT: b.gt .LBB0_4
|
|
; CHECK-NEXT: .LBB0_2: // %for.body
|
|
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: cmp w19, w20
|
|
; CHECK-NEXT: b.eq .LBB0_1
|
|
; CHECK-NEXT: // %bb.3: // %if.then3
|
|
; CHECK-NEXT: // in Loop: Header=BB0_2 Depth=1
|
|
; CHECK-NEXT: mov w0, w20
|
|
; CHECK-NEXT: bl foo
|
|
; CHECK-NEXT: b .LBB0_1
|
|
; CHECK-NEXT: .LBB0_4: // %for.cond.cleanup
|
|
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldr x30, [sp], #32 // 8-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%sub = add nsw i32 %px, -1
|
|
%cmp = icmp slt i32 %px, 1
|
|
%.sub = select i1 %cmp, i32 0, i32 %sub
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%x.015 = phi i32 [ %inc, %for.inc ], [ %.sub, %entry ]
|
|
%cmp2 = icmp eq i32 %x.015, %px
|
|
br i1 %cmp2, label %for.inc, label %if.then3
|
|
|
|
if.then3:
|
|
tail call void @foo(i32 %x.015)
|
|
br label %for.inc
|
|
|
|
for.inc:
|
|
%inc = add nsw i32 %x.015, 1
|
|
%cmp1 = icmp sgt i32 %x.015, %px
|
|
br i1 %cmp1, label %for.cond.cleanup.loopexit, label %for.body
|
|
|
|
for.cond.cleanup.loopexit:
|
|
br label %for.cond.cleanup
|
|
|
|
for.cond.cleanup:
|
|
ret void
|
|
}
|