[PATCH] D126110: [BOLT] Fix AND evaluation bug in shrink wrapping

[Rafael Auler via Phabricator via llvm-commits]

rafauler created this revision.
rafauler added reviewers: Amir, maksfb, yota9, ayermolo, zr33.
Herald added a subscriber: pengfei.
Herald added a project: All.
rafauler requested review of this revision.
Herald added a project: LLVM.
Herald added a subscriber: llvm-commits.

Fix a bug where shrink-wrapping would use wrong stack offsets
because the stack was being aligned with an AND instruction, hence,
making its true offsets only available during runtime (we can't
statically determine where are the stack elements and we must give up
on this case).


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D126110

Files:
  bolt/lib/Target/X86/X86MCPlusBuilder.cpp
  bolt/test/X86/shrinkwrapping-and-rsp.s


Index: bolt/test/X86/shrinkwrapping-and-rsp.s
===================================================================
--- /dev/null
+++ bolt/test/X86/shrinkwrapping-and-rsp.s
@@ -0,0 +1,55 @@
+# This checks that shrink wrapping does attempt at accessing stack elements
+# using RSP when the function is aligning RSP and changing offsets.
+
+# REQUIRES: system-linux
+
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown \
+# RUN:   %s -o %t.o
+# RUN: link_fdata %s %t.o %t.fdata
+# RUN: llvm-strip --strip-unneeded %t.o
+# RUN: %clang %cflags %t.o -o %t.exe -Wl,-q -nostdlib
+# RUN: llvm-bolt %t.exe -o %t.out -data %t.fdata \
+# RUN:     -frame-opt=all -simplify-conditional-tail-calls=false \
+# RUN:     -eliminate-unreachable=false | FileCheck %s
+
+# Here we have a function that aligns the stack at prologue. Stack pointer
+# analysis can't try to infer offset positions after AND because that depends
+# on the runtime value of the stack pointer of callee (whether it is misaligned
+# or not).
+  .globl _start
+  .type _start, %function
+_start:
+  .cfi_startproc
+# FDATA: 0 [unknown] 0 1 _start 0 0 1
+  push  %rbp
+  mov   %rsp, %rbp
+  push  %rbx
+  push  %r14
+  and    $0xffffffffffffffe0,%rsp
+  subq  $0x20, %rsp
+b:  je  hot_path
+# FDATA: 1 _start #b# 1 _start #hot_path# 0 1
+cold_path:
+  mov %r14, %rdi
+  #mov %rbx, %rdi
+  # Block push-pop mode by using an instruction that requires the
+  # stack to be aligned to 128B. This will force the pass
+  # to try to index stack elements by using RSP +offset directly, but
+  # we do not know how to access individual elements of the stack thanks
+  # to the alignment.
+  movdqa	%xmm8, (%rsp)
+  addq  $0x20, %rsp
+  pop %r14
+  pop %rbx
+  pop %rbp
+  ret
+hot_path:
+  addq  $0x20, %rsp
+  pop %r14
+  pop %rbx
+  pop %rbp
+  ret
+  .cfi_endproc
+  .size _start, .-_start
+
+# CHECK:   BOLT-INFO: Shrink wrapping moved 0 spills inserting load/stores and 0 spills inserting push/pops
Index: bolt/lib/Target/X86/X86MCPlusBuilder.cpp
===================================================================
--- bolt/lib/Target/X86/X86MCPlusBuilder.cpp
+++ bolt/lib/Target/X86/X86MCPlusBuilder.cpp
@@ -1260,16 +1260,6 @@
     default:
       return false;
 
-    case X86::AND64ri32:
-    case X86::AND64ri8:
-      if (!Inst.getOperand(2).isImm())
-        return false;
-      if (ErrorOr<int64_t> InputVal =
-              getOperandVal(Inst.getOperand(1).getReg()))
-        Output = *InputVal & Inst.getOperand(2).getImm();
-      else
-        return false;
-      break;
     case X86::SUB64ri32:
     case X86::SUB64ri8:
       if (!Inst.getOperand(2).isImm())


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D126110.431115.patch
Type: text/x-patch
Size: 2635 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220521/5e89fd5d/attachment.bin>