[Stack realignment] Handling of aligned allocas.

This patch implements dynamic realignment of stack objects for targets
with a non-realigned stack pointer. Behaviour in FunctionLoweringInfo
is changed so that for a target that has StackRealignable set to
false, over-aligned static allocas are considered to be variable-sized
objects and are handled with DYNAMIC_STACKALLOC nodes.

It would be good to group aligned allocas into a single big alloca as
an optimization, but this is yet todo.

SystemZ benefits from this, due to its stack frame layout.

New tests SystemZ/alloca-03.ll for aligned allocas, and
SystemZ/alloca-04.ll for "no-realign-stack" attribute on functions.

Review and help from Ulrich Weigand and Hal Finkel.

llvm-svn: 254227

2 files changed, 33 insertions, 2 deletions

diff --git a/llvm/lib/Target/SystemZ/SystemZFrameLowering.cpp b/llvm/lib/Target/SystemZ/SystemZFrameLowering.cpp
index 9eeb0466446..e1b20d0536d 100644
--- a/llvm/lib/Target/SystemZ/SystemZFrameLowering.cpp
+++ b/llvm/lib/Target/SystemZ/SystemZFrameLowering.cpp
@@ -48,7 +48,8 @@ static const TargetFrameLowering::SpillSlot SpillOffsetTable[] = {
 
 SystemZFrameLowering::SystemZFrameLowering()
     : TargetFrameLowering(TargetFrameLowering::StackGrowsDown, 8,
-                          -SystemZMC::CallFrameSize, 8) {
+                          -SystemZMC::CallFrameSize, 8,
+                          false /* StackRealignable */) {
   // Create a mapping from register number to save slot offset.
   RegSpillOffsets.grow(SystemZ::NUM_TARGET_REGS);
   for (unsigned I = 0, E = array_lengthof(SpillOffsetTable); I != E; ++I)
diff --git a/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp b/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp
index fa9ee6e2eeb..5959e90d2f6 100644
--- a/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp
+++ b/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp
@@ -2739,17 +2739,37 @@ SDValue SystemZTargetLowering::lowerVACOPY(SDValue Op,
 
 SDValue SystemZTargetLowering::
 lowerDYNAMIC_STACKALLOC(SDValue Op, SelectionDAG &DAG) const {
+  const TargetFrameLowering *TFI = Subtarget.getFrameLowering();
+  bool RealignOpt = !DAG.getMachineFunction().getFunction()->
+    hasFnAttribute("no-realign-stack");
+
   SDValue Chain = Op.getOperand(0);
   SDValue Size  = Op.getOperand(1);
+  SDValue Align = Op.getOperand(2);
   SDLoc DL(Op);
 
+  // If user has set the no alignment function attribute, ignore
+  // alloca alignments.
+  uint64_t AlignVal = (RealignOpt ?
+                       dyn_cast<ConstantSDNode>(Align)->getZExtValue() : 0);
+
+  uint64_t StackAlign = TFI->getStackAlignment();
+  uint64_t RequiredAlign = std::max(AlignVal, StackAlign);
+  uint64_t ExtraAlignSpace = RequiredAlign - StackAlign;
+
   unsigned SPReg = getStackPointerRegisterToSaveRestore();
+  SDValue NeededSpace = Size;
 
   // Get a reference to the stack pointer.
   SDValue OldSP = DAG.getCopyFromReg(Chain, DL, SPReg, MVT::i64);
 
+  // Add extra space for alignment if needed.
+  if (ExtraAlignSpace)
+    NeededSpace = DAG.getNode(ISD::ADD, DL, MVT::i64, NeededSpace,
+                              DAG.getConstant(ExtraAlignSpace, DL, MVT::i64)); 
+
   // Get the new stack pointer value.
-  SDValue NewSP = DAG.getNode(ISD::SUB, DL, MVT::i64, OldSP, Size);
+  SDValue NewSP = DAG.getNode(ISD::SUB, DL, MVT::i64, OldSP, NeededSpace);
 
   // Copy the new stack pointer back.
   Chain = DAG.getCopyToReg(Chain, DL, SPReg, NewSP);
@@ -2760,6 +2780,16 @@ lowerDYNAMIC_STACKALLOC(SDValue Op, SelectionDAG &DAG) const {
   SDValue ArgAdjust = DAG.getNode(SystemZISD::ADJDYNALLOC, DL, MVT::i64);
   SDValue Result = DAG.getNode(ISD::ADD, DL, MVT::i64, NewSP, ArgAdjust);
 
+  // Dynamically realign if needed.
+  if (RequiredAlign > StackAlign) {
+    Result =
+      DAG.getNode(ISD::ADD, DL, MVT::i64, Result,
+                  DAG.getConstant(ExtraAlignSpace, DL, MVT::i64));
+    Result =
+      DAG.getNode(ISD::AND, DL, MVT::i64, Result,
+                  DAG.getConstant(~(RequiredAlign - 1), DL, MVT::i64));
+  }
+
   SDValue Ops[2] = { Result, Chain };
   return DAG.getMergeValues(Ops, DL);
 }