[AArch64] Fix bug in prolog clobbering live reg when shrink wrapping.

This adapts r261349 to the release branch.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_38@261586 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/AArch64/AArch64FrameLowering.cpp b/lib/Target/AArch64/AArch64FrameLowering.cpp
index 11ae8005370d10326afb44f7e2d734ec8a2a74fe..3f63d049c34ed109fb8007a1103ef8bac6a2e294 100644 (file)
--- a/lib/Target/AArch64/AArch64FrameLowering.cpp
+++ b/lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -275,6 +275,18 @@ static bool isCSSave(MachineInstr *MBBI) {
          MBBI->getOpcode() == AArch64::STPDpre;
 }
 
+bool AArch64FrameLowering::canUseAsPrologue(
+    const MachineBasicBlock &MBB) const {
+  const MachineFunction *MF = MBB.getParent();
+  const AArch64Subtarget &Subtarget = MF->getSubtarget<AArch64Subtarget>();
+  const AArch64RegisterInfo *RegInfo = Subtarget.getRegisterInfo();
+
+  // Don't need a scratch register if we're not going to re-align the stack.
+  // Otherwise, we may need a scratch register to be available and we do not
+  // support that for now.
+  return !RegInfo->needsStackRealignment(*MF);
+}
+
 void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
                                         MachineBasicBlock &MBB) const {
   MachineBasicBlock::iterator MBBI = MBB.begin();

diff --git a/lib/Target/AArch64/AArch64FrameLowering.h b/lib/Target/AArch64/AArch64FrameLowering.h
index 427afdf4acbf0736dfea29551023b9264bb453c4..7d8354c38787c3f6d492e94a2b4fb7c324ec5f88 100644 (file)
--- a/lib/Target/AArch64/AArch64FrameLowering.h
+++ b/lib/Target/AArch64/AArch64FrameLowering.h
@@ -37,6 +37,8 @@ public:
   void emitPrologue(MachineFunction &MF, MachineBasicBlock &MBB) const override;
   void emitEpilogue(MachineFunction &MF, MachineBasicBlock &MBB) const override;
 
+  bool canUseAsPrologue(const MachineBasicBlock &MBB) const override;
+
   int getFrameIndexReference(const MachineFunction &MF, int FI,
                              unsigned &FrameReg) const override;
   int resolveFrameIndexReference(const MachineFunction &MF, int FI,

diff --git a/test/CodeGen/AArch64/aarch64-dynamic-stack-layout.ll b/test/CodeGen/AArch64/aarch64-dynamic-stack-layout.ll
index 1820b8163a9054fc603c507ac164d92e1da25a4b..90093f94d0ad985e156cc0e65b2a85dfb3fd10d8 100644 (file)
--- a/test/CodeGen/AArch64/aarch64-dynamic-stack-layout.ll
+++ b/test/CodeGen/AArch64/aarch64-dynamic-stack-layout.ll
@@ -522,10 +522,10 @@ bb1:
 
 ; CHECK-LABEL: realign_conditional2
 ; Extra realignment in the prologue (performance issue).
-; CHECK:  tbz  {{.*}} .[[LABEL:.*]]
 ; CHECK:  sub  x9, sp, #32            // =32
 ; CHECK:  and  sp, x9, #0xffffffffffffffe0
 ; CHECK:  mov   x19, sp
+; CHECK:  tbz  {{.*}} .[[LABEL:.*]]
 ; Stack is realigned in a non-entry BB.
 ; CHECK:  sub  [[REG:x[01-9]+]], sp, #64
 ; CHECK:  and  sp, [[REG]], #0xffffffffffffffe0

diff --git a/test/CodeGen/AArch64/arm64-shrink-wrapping.ll b/test/CodeGen/AArch64/arm64-shrink-wrapping.ll
index 2ecd66ddf5d4276bb28aa34f5936a2ef03e337cb..4d751f501d4ade25c00240a30c2b80a89a86c3bd 100644 (file)
--- a/test/CodeGen/AArch64/arm64-shrink-wrapping.ll
+++ b/test/CodeGen/AArch64/arm64-shrink-wrapping.ll
@@ -630,3 +630,88 @@ loop2b:                                           ; preds = %loop1
 end:
   ret void
 }
+
+; Don't do shrink-wrapping when we need to re-align the stack pointer.
+; See bug 26642.
+; CHECK-LABEL: stack_realign:
+; CHECK-NOT: lsl w[[LSL1:[0-9]+]], w0, w1
+; CHECK-NOT: lsl w[[LSL2:[0-9]+]], w1, w0
+; CHECK: stp x29, x30, [sp, #-16]!
+; CHECK: mov x29, sp
+; CHECK: sub x{{[0-9]+}}, sp, #16
+; CHECK-DAG: lsl w[[LSL1:[0-9]+]], w0, w1
+; CHECK-DAG: lsl w[[LSL2:[0-9]+]], w1, w0
+; CHECK-DAG: str w[[LSL1]],
+; CHECK-DAG: str w[[LSL2]],
+
+define i32 @stack_realign(i32 %a, i32 %b, i32* %ptr1, i32* %ptr2) {
+  %tmp = alloca i32, align 32
+  %shl1 = shl i32 %a, %b
+  %shl2 = shl i32 %b, %a
+  %tmp2 = icmp slt i32 %a, %b
+  br i1 %tmp2, label %true, label %false
+
+true:
+  store i32 %a, i32* %tmp, align 4
+  %tmp4 = load i32, i32* %tmp
+  br label %false
+
+false:
+  %tmp.0 = phi i32 [ %tmp4, %true ], [ %a, %0 ]
+  store i32 %shl1, i32* %ptr1
+  store i32 %shl2, i32* %ptr2
+  ret i32 %tmp.0
+}
+
+; Re-aligned stack pointer with all caller-save regs live.  See bug
+; 26642.  In this case we currently avoid shrink wrapping because
+; ensuring we have a scratch register to re-align the stack pointer is
+; too complicated.  Output should be the same for both enabled and
+; disabled shrink wrapping.
+; CHECK-LABEL: stack_realign2:
+; CHECK: stp {{x[0-9]+}}, {{x[0-9]+}}, [sp, #-{{[0-9]+}}]!
+; CHECK: add x29, sp, #{{[0-9]+}}
+; CHECK: lsl {{w[0-9]+}}, w0, w1
+
+define void @stack_realign2(i32 %a, i32 %b, i32* %ptr1, i32* %ptr2, i32* %ptr3, i32* %ptr4, i32* %ptr5, i32* %ptr6) {
+  %tmp = alloca i32, align 32
+  %tmp1 = shl i32 %a, %b
+  %tmp2 = shl i32 %b, %a
+  %tmp3 = lshr i32 %a, %b
+  %tmp4 = lshr i32 %b, %a
+  %tmp5 = add i32 %b, %a
+  %tmp6 = sub i32 %b, %a
+  %tmp7 = add i32 %tmp1, %tmp2
+  %tmp8 = sub i32 %tmp2, %tmp3
+  %tmp9 = add i32 %tmp3, %tmp4
+  %tmp10 = add i32 %tmp4, %tmp5
+  %cmp = icmp slt i32 %a, %b
+  br i1 %cmp, label %true, label %false
+
+true:
+  store i32 %a, i32* %tmp, align 4
+  call void asm sideeffect "nop", "~{x19},~{x20},~{x21},~{x22},~{x23},~{x24},~{x25},~{x26},~{x27},~{x28}"() nounwind
+  br label %false
+
+false:
+  store i32 %tmp1, i32* %ptr1, align 4
+  store i32 %tmp2, i32* %ptr2, align 4
+  store i32 %tmp3, i32* %ptr3, align 4
+  store i32 %tmp4, i32* %ptr4, align 4
+  store i32 %tmp5, i32* %ptr5, align 4
+  store i32 %tmp6, i32* %ptr6, align 4
+  %idx1 = getelementptr inbounds i32, i32* %ptr1, i64 1
+  store i32 %a, i32* %idx1, align 4
+  %idx2 = getelementptr inbounds i32, i32* %ptr1, i64 2
+  store i32 %b, i32* %idx2, align 4
+  %idx3 = getelementptr inbounds i32, i32* %ptr1, i64 3
+  store i32 %tmp7, i32* %idx3, align 4
+  %idx4 = getelementptr inbounds i32, i32* %ptr1, i64 4
+  store i32 %tmp8, i32* %idx4, align 4
+  %idx5 = getelementptr inbounds i32, i32* %ptr1, i64 5
+  store i32 %tmp9, i32* %idx5, align 4
+  %idx6 = getelementptr inbounds i32, i32* %ptr1, i64 6
+  store i32 %tmp10, i32* %idx6, align 4
+
+  ret void
+}