1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 04:02:41 +01:00
llvm-mirror/test/CodeGen/X86/pr32241.ll
Petar Jovanovic 9686e666ef Correct dwarf unwind information in function epilogue
This patch aims to provide correct dwarf unwind information in function
epilogue for X86.
It consists of two parts. The first part inserts CFI instructions that set
appropriate cfa offset and cfa register in emitEpilogue() in
X86FrameLowering. This part is X86 specific.

The second part is platform independent and ensures that:

* CFI instructions do not affect code generation (they are not counted as
  instructions when tail duplicating or tail merging)
* Unwind information remains correct when a function is modified by
  different passes. This is done in a late pass by analyzing information
  about cfa offset and cfa register in BBs and inserting additional CFI
  directives where necessary.

Added CFIInstrInserter pass:

* analyzes each basic block to determine cfa offset and register are valid
  at its entry and exit
* verifies that outgoing cfa offset and register of predecessor blocks match
  incoming values of their successors
* inserts additional CFI directives at basic block beginning to correct the
  rule for calculating CFA

Having CFI instructions in function epilogue can cause incorrect CFA
calculation rule for some basic blocks. This can happen if, due to basic
block reordering, or the existence of multiple epilogue blocks, some of the
blocks have wrong cfa offset and register values set by the epilogue block
above them.
CFIInstrInserter is currently run only on X86, but can be used by any target
that implements support for adding CFI instructions in epilogue.

Patch by Violeta Vukobrat.

Differential Revision: https://reviews.llvm.org/D42848

llvm-svn: 330706
2018-04-24 10:32:08 +00:00

88 lines
3.2 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -fast-isel-sink-local-values < %s -fast-isel -mtriple=i686-unknown-unknown -O0 -mcpu=skx | FileCheck %s
define i32 @_Z3foov() {
; CHECK-LABEL: _Z3foov:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: subl $16, %esp
; CHECK-NEXT: .cfi_def_cfa_offset 20
; CHECK-NEXT: movw $10959, {{[0-9]+}}(%esp) # imm = 0x2ACF
; CHECK-NEXT: movw $-15498, {{[0-9]+}}(%esp) # imm = 0xC376
; CHECK-NEXT: movw $19417, {{[0-9]+}}(%esp) # imm = 0x4BD9
; CHECK-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: cmpw $0, {{[0-9]+}}(%esp)
; CHECK-NEXT: movb $1, %cl
; CHECK-NEXT: movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
; CHECK-NEXT: movb %cl, {{[0-9]+}}(%esp) # 1-byte Spill
; CHECK-NEXT: jne .LBB0_2
; CHECK-NEXT: # %bb.1: # %lor.rhs
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: movb %al, %cl
; CHECK-NEXT: movb %cl, {{[0-9]+}}(%esp) # 1-byte Spill
; CHECK-NEXT: jmp .LBB0_2
; CHECK-NEXT: .LBB0_2: # %lor.end
; CHECK-NEXT: movb {{[0-9]+}}(%esp), %al # 1-byte Reload
; CHECK-NEXT: andb $1, %al
; CHECK-NEXT: movzbl %al, %ecx
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
; CHECK-NEXT: cmpl %ecx, %edx
; CHECK-NEXT: setl %al
; CHECK-NEXT: andb $1, %al
; CHECK-NEXT: movzbl %al, %ecx
; CHECK-NEXT: xorl $-1, %ecx
; CHECK-NEXT: cmpl $0, %ecx
; CHECK-NEXT: movb $1, %al
; CHECK-NEXT: movb %al, {{[0-9]+}}(%esp) # 1-byte Spill
; CHECK-NEXT: jne .LBB0_4
; CHECK-NEXT: # %bb.3: # %lor.rhs4
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: movb %al, %cl
; CHECK-NEXT: movb %cl, {{[0-9]+}}(%esp) # 1-byte Spill
; CHECK-NEXT: jmp .LBB0_4
; CHECK-NEXT: .LBB0_4: # %lor.end5
; CHECK-NEXT: movb {{[0-9]+}}(%esp), %al # 1-byte Reload
; CHECK-NEXT: andb $1, %al
; CHECK-NEXT: movzbl %al, %ecx
; CHECK-NEXT: movw %cx, %dx
; CHECK-NEXT: movw %dx, {{[0-9]+}}(%esp)
; CHECK-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: addl $16, %esp
; CHECK-NEXT: .cfi_def_cfa_offset 4
; CHECK-NEXT: retl
entry:
%aa = alloca i16, align 2
%bb = alloca i16, align 2
%cc = alloca i16, align 2
store i16 10959, i16* %aa, align 2
store i16 -15498, i16* %bb, align 2
store i16 19417, i16* %cc, align 2
%0 = load i16, i16* %aa, align 2
%conv = zext i16 %0 to i32
%1 = load i16, i16* %cc, align 2
%tobool = icmp ne i16 %1, 0
br i1 %tobool, label %lor.end, label %lor.rhs
lor.rhs: ; preds = %entry
br label %lor.end
lor.end: ; preds = %lor.rhs, %entry
%2 = phi i1 [ true, %entry ], [ false, %lor.rhs ]
%conv1 = zext i1 %2 to i32
%cmp = icmp slt i32 %conv, %conv1
%conv2 = zext i1 %cmp to i32
%neg = xor i32 %conv2, -1
%tobool3 = icmp ne i32 %neg, 0
br i1 %tobool3, label %lor.end5, label %lor.rhs4
lor.rhs4: ; preds = %lor.end
br label %lor.end5
lor.end5: ; preds = %lor.rhs4, %lor.end
%3 = phi i1 [ true, %lor.end ], [ false, %lor.rhs4 ]
%conv6 = zext i1 %3 to i16
store i16 %conv6, i16* %bb, align 2
%4 = load i16, i16* %bb, align 2
%conv7 = zext i16 %4 to i32
ret i32 %conv7
}