Momchil Velikov 50a97aacac [AArch64] Async unwind - function prologues
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
2022-03-24 16:16:44 +00:00

225 lines
8.4 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -verify-machineinstrs -mtriple=aarch64-unknown-linux < %s | FileCheck %s
; RUN: llc -verify-machineinstrs -mtriple=arm64-apple-ios < %s | FileCheck %s --check-prefix=CHECK-APPLE
; Check CSR split can work properly for tests below.
@a = common dso_local local_unnamed_addr global i32 0, align 4
define dso_local signext i32 @test1(i32* %b) local_unnamed_addr {
; CHECK-LABEL: test1:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: stp x30, x19, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w30, -16
; CHECK-NEXT: adrp x8, a
; CHECK-NEXT: ldrsw x8, [x8, :lo12:a]
; CHECK-NEXT: cmp x8, x0
; CHECK-NEXT: b.eq .LBB0_2
; CHECK-NEXT: // %bb.1: // %if.end
; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB0_2: // %if.then
; CHECK-NEXT: mov x19, x0
; CHECK-NEXT: bl callVoid
; CHECK-NEXT: mov x0, x19
; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: b callNonVoid
;
; CHECK-APPLE-LABEL: test1:
; CHECK-APPLE: ; %bb.0: ; %entry
; CHECK-APPLE-NEXT: stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
; CHECK-APPLE-NEXT: .cfi_def_cfa_offset 32
; CHECK-APPLE-NEXT: stp x29, x30, [sp, #16] ; 16-byte Folded Spill
; CHECK-APPLE-NEXT: .cfi_offset w30, -8
; CHECK-APPLE-NEXT: .cfi_offset w29, -16
; CHECK-APPLE-NEXT: .cfi_offset w19, -24
; CHECK-APPLE-NEXT: .cfi_offset w20, -32
; CHECK-APPLE-NEXT: Lloh0:
; CHECK-APPLE-NEXT: adrp x8, _a@PAGE
; CHECK-APPLE-NEXT: Lloh1:
; CHECK-APPLE-NEXT: ldrsw x8, [x8, _a@PAGEOFF]
; CHECK-APPLE-NEXT: cmp x8, x0
; CHECK-APPLE-NEXT: b.eq LBB0_2
; CHECK-APPLE-NEXT: ; %bb.1: ; %if.end
; CHECK-APPLE-NEXT: ldp x29, x30, [sp, #16] ; 16-byte Folded Reload
; CHECK-APPLE-NEXT: ldp x20, x19, [sp], #32 ; 16-byte Folded Reload
; CHECK-APPLE-NEXT: ret
; CHECK-APPLE-NEXT: LBB0_2: ; %if.then
; CHECK-APPLE-NEXT: mov x19, x0
; CHECK-APPLE-NEXT: bl _callVoid
; CHECK-APPLE-NEXT: ldp x29, x30, [sp, #16] ; 16-byte Folded Reload
; CHECK-APPLE-NEXT: mov x0, x19
; CHECK-APPLE-NEXT: ldp x20, x19, [sp], #32 ; 16-byte Folded Reload
; CHECK-APPLE-NEXT: b _callNonVoid
; CHECK-APPLE-NEXT: .loh AdrpLdr Lloh0, Lloh1
entry:
%0 = load i32, i32* @a, align 4, !tbaa !2
%conv = sext i32 %0 to i64
%1 = inttoptr i64 %conv to i32*
%cmp = icmp eq i32* %1, %b
br i1 %cmp, label %if.then, label %if.end
if.then: ; preds = %entry
%call = tail call signext i32 bitcast (i32 (...)* @callVoid to i32 ()*)()
%call2 = tail call signext i32 @callNonVoid(i32* %b)
br label %if.end
if.end: ; preds = %if.then, %entry
%retval.0 = phi i32 [ %call2, %if.then ], [ undef, %entry ]
ret i32 %retval.0
}
declare signext i32 @callVoid(...) local_unnamed_addr
declare signext i32 @callNonVoid(i32*) local_unnamed_addr
define dso_local signext i32 @test2(i32* %p1) local_unnamed_addr {
; CHECK-LABEL: test2:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: stp x30, x19, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w30, -16
; CHECK-NEXT: cbz x0, .LBB1_3
; CHECK-NEXT: // %bb.1: // %entry
; CHECK-NEXT: adrp x8, a
; CHECK-NEXT: mov x19, x0
; CHECK-NEXT: ldrsw x8, [x8, :lo12:a]
; CHECK-NEXT: cmp x8, x0
; CHECK-NEXT: b.ne .LBB1_3
; CHECK-NEXT: // %bb.2: // %if.then2
; CHECK-NEXT: bl callVoid
; CHECK-NEXT: mov x0, x19
; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: b callNonVoid
; CHECK-NEXT: .LBB1_3: // %return
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
;
; CHECK-APPLE-LABEL: test2:
; CHECK-APPLE: ; %bb.0: ; %entry
; CHECK-APPLE-NEXT: stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
; CHECK-APPLE-NEXT: .cfi_def_cfa_offset 32
; CHECK-APPLE-NEXT: stp x29, x30, [sp, #16] ; 16-byte Folded Spill
; CHECK-APPLE-NEXT: .cfi_offset w30, -8
; CHECK-APPLE-NEXT: .cfi_offset w29, -16
; CHECK-APPLE-NEXT: .cfi_offset w19, -24
; CHECK-APPLE-NEXT: .cfi_offset w20, -32
; CHECK-APPLE-NEXT: cbz x0, LBB1_3
; CHECK-APPLE-NEXT: ; %bb.1: ; %entry
; CHECK-APPLE-NEXT: Lloh2:
; CHECK-APPLE-NEXT: adrp x8, _a@PAGE
; CHECK-APPLE-NEXT: mov x19, x0
; CHECK-APPLE-NEXT: Lloh3:
; CHECK-APPLE-NEXT: ldrsw x8, [x8, _a@PAGEOFF]
; CHECK-APPLE-NEXT: cmp x8, x0
; CHECK-APPLE-NEXT: b.ne LBB1_3
; CHECK-APPLE-NEXT: ; %bb.2: ; %if.then2
; CHECK-APPLE-NEXT: bl _callVoid
; CHECK-APPLE-NEXT: ldp x29, x30, [sp, #16] ; 16-byte Folded Reload
; CHECK-APPLE-NEXT: mov x0, x19
; CHECK-APPLE-NEXT: ldp x20, x19, [sp], #32 ; 16-byte Folded Reload
; CHECK-APPLE-NEXT: b _callNonVoid
; CHECK-APPLE-NEXT: LBB1_3: ; %return
; CHECK-APPLE-NEXT: ldp x29, x30, [sp, #16] ; 16-byte Folded Reload
; CHECK-APPLE-NEXT: mov w0, wzr
; CHECK-APPLE-NEXT: ldp x20, x19, [sp], #32 ; 16-byte Folded Reload
; CHECK-APPLE-NEXT: ret
; CHECK-APPLE-NEXT: .loh AdrpLdr Lloh2, Lloh3
entry:
%tobool = icmp eq i32* %p1, null
br i1 %tobool, label %return, label %if.end
if.end: ; preds = %entry
%0 = load i32, i32* @a, align 4, !tbaa !2
%conv = sext i32 %0 to i64
%1 = inttoptr i64 %conv to i32*
%cmp = icmp eq i32* %1, %p1
br i1 %cmp, label %if.then2, label %return
if.then2: ; preds = %if.end
%call = tail call signext i32 bitcast (i32 (...)* @callVoid to i32 ()*)()
%call3 = tail call signext i32 @callNonVoid(i32* nonnull %p1)
br label %return
return: ; preds = %if.end, %entry, %if.then2
%retval.0 = phi i32 [ %call3, %if.then2 ], [ 0, %entry ], [ 0, %if.end ]
ret i32 %retval.0
}
define dso_local i8* @test3(i8** nocapture %p1, i8 zeroext %p2) local_unnamed_addr {
; CHECK-LABEL: test3:
; 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: ldr x19, [x0]
; CHECK-NEXT: cbz x19, .LBB2_2
; CHECK-NEXT: // %bb.1: // %land.rhs
; CHECK-NEXT: mov x20, x0
; CHECK-NEXT: mov x0, x19
; CHECK-NEXT: bl bar
; CHECK-NEXT: str x0, [x20]
; CHECK-NEXT: .LBB2_2: // %land.end
; CHECK-NEXT: mov x0, x19
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x30, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ret
;
; CHECK-APPLE-LABEL: test3:
; CHECK-APPLE: ; %bb.0: ; %entry
; CHECK-APPLE-NEXT: stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
; CHECK-APPLE-NEXT: .cfi_def_cfa_offset 32
; CHECK-APPLE-NEXT: stp x29, x30, [sp, #16] ; 16-byte Folded Spill
; CHECK-APPLE-NEXT: .cfi_offset w30, -8
; CHECK-APPLE-NEXT: .cfi_offset w29, -16
; CHECK-APPLE-NEXT: .cfi_offset w19, -24
; CHECK-APPLE-NEXT: .cfi_offset w20, -32
; CHECK-APPLE-NEXT: ldr x19, [x0]
; CHECK-APPLE-NEXT: cbz x19, LBB2_2
; CHECK-APPLE-NEXT: ; %bb.1: ; %land.rhs
; CHECK-APPLE-NEXT: mov x20, x0
; CHECK-APPLE-NEXT: mov x0, x19
; CHECK-APPLE-NEXT: bl _bar
; CHECK-APPLE-NEXT: str x0, [x20]
; CHECK-APPLE-NEXT: LBB2_2: ; %land.end
; CHECK-APPLE-NEXT: ldp x29, x30, [sp, #16] ; 16-byte Folded Reload
; CHECK-APPLE-NEXT: mov x0, x19
; CHECK-APPLE-NEXT: ldp x20, x19, [sp], #32 ; 16-byte Folded Reload
; CHECK-APPLE-NEXT: ret
entry:
%0 = load i8*, i8** %p1, align 8, !tbaa !6
%tobool = icmp eq i8* %0, null
br i1 %tobool, label %land.end, label %land.rhs
land.rhs: ; preds = %entry
%call = tail call i8* @bar(i8* nonnull %0, i8 zeroext %p2)
store i8* %call, i8** %p1, align 8, !tbaa !6
br label %land.end
land.end: ; preds = %entry, %land.rhs
ret i8* %0
}
declare i8* @bar(i8*, i8 zeroext) local_unnamed_addr
!llvm.module.flags = !{!0}
!llvm.ident = !{!1}
!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{!"clang version 10.0.0 (trunk 367381) (llvm/trunk 367388)"}
!2 = !{!3, !3, i64 0}
!3 = !{!"int", !4, i64 0}
!4 = !{!"omnipotent char", !5, i64 0}
!5 = !{!"Simple C/C++ TBAA"}
!6 = !{!7, !7, i64 0}
!7 = !{!"any pointer", !4, i64 0}