From: Tim Northover <tnorthover@apple.com>
Date: Wed, 23 Sep 2015 22:21:09 +0000 (+0000)
Subject: ARM: fix folding stack adjustment (again again again...)
X-Git-Url: http://demsky.eecs.uci.edu/git/?a=commitdiff_plain;h=cdc6a8eab9d54c3b942ecc6eeabd6d4c8fff2ee7;p=oota-llvm.git

ARM: fix folding stack adjustment (again again again...)

This time, the issue is that we weren't accounting for the possibility that
aligned DPRs could have been stored after the final "push" in a prologue. When
that happened we effectively moved a "sub sp, #N" from below the aligned stores
to above them, and everything went to pot.

To make it worse, I'd actually committed something testing that we produced
wrong code, so the test update is tiny.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@248437 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Target/ARM/ARMFrameLowering.cpp b/lib/Target/ARM/ARMFrameLowering.cpp
index b52ca93c204..5b5b1b022f5 100644
--- a/lib/Target/ARM/ARMFrameLowering.cpp
+++ b/lib/Target/ARM/ARMFrameLowering.cpp
@@ -488,7 +488,8 @@ void ARMFrameLowering::emitPrologue(MachineFunction &MF,
 
   if (NumBytes) {
     // Adjust SP after all the callee-save spills.
-    if (tryFoldSPUpdateIntoPushPop(STI, MF, LastPush, NumBytes))
+    if (AFI->getNumAlignedDPRCS2Regs() == 0 &&
+        tryFoldSPUpdateIntoPushPop(STI, MF, LastPush, NumBytes))
       DefCFAOffsetCandidates.addExtraBytes(LastPush, NumBytes);
     else {
       emitSPUpdate(isARM, MBB, MBBI, dl, TII, -NumBytes,
diff --git a/test/CodeGen/ARM/fold-stack-adjust.ll b/test/CodeGen/ARM/fold-stack-adjust.ll
index 614966d4024..5bec6445560 100644
--- a/test/CodeGen/ARM/fold-stack-adjust.ll
+++ b/test/CodeGen/ARM/fold-stack-adjust.ll
@@ -67,11 +67,12 @@ define void @check_vfp_fold() minsize {
   ; iOS uses aligned NEON stores here, which is convenient since we
   ; want to make sure that works too.
 ; CHECK-IOS-LABEL: check_vfp_fold:
-; CHECK-IOS: push {r0, r1, r2, r3, r4, r7, lr}
+; CHECK-IOS: push {r4, r7, lr}
 ; CHECK-IOS: sub.w r4, sp, #16
 ; CHECK-IOS: bfc r4, #0, #4
 ; CHECK-IOS: mov sp, r4
 ; CHECK-IOS: vst1.64 {d8, d9}, [r4:128]
+; CHECK-IOS: sub sp, #16
 ; ...
 ; CHECK-IOS: add r4, sp, #16
 ; CHECK-IOS: vld1.64 {d8, d9}, [r4:128]