[X86] Fix RegAlloc issue by implementing TRI::getCustomEHPadPreservedMask

llvm/lib/Target/X86/X86RegisterInfo.cpp

@@ -525,6 +525,13 @@ X86RegisterInfo::getNoPreservedMask() const {
   return CSR_NoRegs_RegMask;
 }
 
+const uint32_t *
+X86RegisterInfo::getCustomEHPadPreservedMask(const MachineFunction &MF) const {
+  if (MF.getTarget().Options.ExceptionModel == ExceptionHandling::SjLj)
+    return getNoPreservedMask();
+  return TargetRegisterInfo::getCustomEHPadPreservedMask(MF);
+}
+
 const uint32_t *X86RegisterInfo::getDarwinTLSCallPreservedMask() const {
   return CSR_64_TLS_Darwin_RegMask;
 }

llvm/lib/Target/X86/X86RegisterInfo.h

@@ -102,6 +102,8 @@ class X86RegisterInfo final : public X86GenRegisterInfo {
   const uint32_t *getCallPreservedMask(const MachineFunction &MF,
                                        CallingConv::ID) const override;
   const uint32_t *getNoPreservedMask() const override;
+  const uint32_t *
+  getCustomEHPadPreservedMask(const MachineFunction &MF) const override;
 
   // Calls involved in thread-local variable lookup save more registers than
   // normal calls, so they need a different mask to represent this.

llvm/test/CodeGen/X86/sjlj-unwind-clobber.ll

@@ -0,0 +1,86 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc -mtriple=x86_64 -exception-model=sjlj -o - %s | FileCheck %s
+
+declare i32 @__gxx_personality_sj0(...)
+declare preserve_allcc void @foo(ptr)
+
+; Check that register allocator splits live ranges of loop invariant virtual
+; registers as they don't survive the unwind edge of an invoke.
+; The argument of `foo` (passed in %rdi) and the address of the jump table
+; (base register of `jmpq`) are loop invariant. They survive the call to `foo`,
+; but are clobbered by the unwinder when `foo` throws an exception, and so
+; their live ranges must be split around the unwind edge `callq foo` -> LBB0_3.
+; This is achieved by recalculating their values before each use rather than
+; once before the loop as was the case before register allocation.
+
+define void @test() personality ptr @__gxx_personality_sj0 {
+; CHECK-LABEL: test:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    pushq %rbp
+; CHECK-NEXT:    movq %rsp, %rbp
+; CHECK-NEXT:    pushq %r15
+; CHECK-NEXT:    pushq %r14
+; CHECK-NEXT:    pushq %r13
+; CHECK-NEXT:    pushq %r12
+; CHECK-NEXT:    pushq %rbx
+; CHECK-NEXT:    subq $104, %rsp
+; CHECK-NEXT:    movq __gxx_personality_sj0@GOTPCREL(%rip), %rax
+; CHECK-NEXT:    movq %rax, -104(%rbp)
+; CHECK-NEXT:    movq $GCC_except_table0, -96(%rbp)
+; CHECK-NEXT:    movq %rbp, -88(%rbp)
+; CHECK-NEXT:    movq %rsp, -72(%rbp)
+; CHECK-NEXT:    movq $.LBB0_3, -80(%rbp)
+; CHECK-NEXT:    leaq -136(%rbp), %rdi
+; CHECK-NEXT:    callq _Unwind_SjLj_Register@PLT
+; CHECK-NEXT:    leaq -44(%rbp), %rcx
+; CHECK-NEXT:  .LBB0_1: # %while.cond
+; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    movl $1, -128(%rbp)
+; CHECK-NEXT:  .Ltmp0:
+; CHECK-NEXT:    movq %rcx, %rdi
+; CHECK-NEXT:    callq foo@PLT
+; CHECK-NEXT:  .Ltmp1:
+; CHECK-NEXT:    jmp .LBB0_2
+; CHECK-NEXT:  .LBB0_3: # in Loop: Header=BB0_1 Depth=1
+; CHECK-NEXT:    leaq -44(%rbp), %rcx
+; CHECK-NEXT:    movl -128(%rbp), %eax
+; CHECK-NEXT:    cmpl $1, %eax
+; CHECK-NEXT:    jae .LBB0_5
+; CHECK-NEXT:  # %bb.4: # in Loop: Header=BB0_1 Depth=1
+; CHECK-NEXT:    leaq .LJTI0_0(%rip), %rdx
+; CHECK-NEXT:    jmpq *(%rdx,%rax,8)
+; CHECK-NEXT:  .LBB0_6: # %lpad
+; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
+; CHECK-NEXT:  .Ltmp2:
+; CHECK-NEXT:    movl -124(%rbp), %eax
+; CHECK-NEXT:    movl -120(%rbp), %eax
+; CHECK-NEXT:    jmp .LBB0_1
+; CHECK-NEXT:  .LBB0_2: # %while.end
+; CHECK-NEXT:    leaq -136(%rbp), %rdi
+; CHECK-NEXT:    callq _Unwind_SjLj_Unregister@PLT
+; CHECK-NEXT:    addq $104, %rsp
+; CHECK-NEXT:    popq %rbx
+; CHECK-NEXT:    popq %r12
+; CHECK-NEXT:    popq %r13
+; CHECK-NEXT:    popq %r14
+; CHECK-NEXT:    popq %r15
+; CHECK-NEXT:    popq %rbp
+; CHECK-NEXT:    retq
+; CHECK-NEXT:  .LBB0_5:
+; CHECK-NEXT:    ud2
+entry:
+  %ptr = alloca i32, align 4
+  br label %while.cond
+
+while.cond:
+  invoke preserve_allcc void @foo(ptr %ptr)
+          to label %while.end unwind label %lpad
+
+lpad:
+  %lp = landingpad { ptr, i32 }
+          catch ptr null
+  br label %while.cond
+
+while.end:
+  ret void
+}