Better handle alignment requirements for local objects in pre-regalloc frame

mapping. Have the local block track its alignment requirement, and then
apply that when the block itself is allocated. Previously, offsets could
get adjusted in PEI to be different, relative to one another, than the
block allocation thought they would be, which defeats the point of doing
the allocation this way. Continuing rdar://8277890

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@111197 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/CodeGen/MachineFrameInfo.h b/include/llvm/CodeGen/MachineFrameInfo.h
index c99b5f59c1d5d616755063da3909e3e8d102b244..ba5d6ba97ebf00d8e0163c894113ca992c55e2cd 100644 (file)
--- a/include/llvm/CodeGen/MachineFrameInfo.h
+++ b/include/llvm/CodeGen/MachineFrameInfo.h
@@ -212,6 +212,10 @@ class MachineFrameInfo {
   /// target in eliminateFrameIndex().
   int64_t LocalFrameBaseOffset;
 
+  /// Required alignment of the local object blob, which is the strictest
+  /// alignment of any object in it.
+  unsigned LocalFrameMaxAlign;
+
 public:
     explicit MachineFrameInfo(const TargetFrameInfo &tfi) : TFI(tfi) {
     StackSize = NumFixedObjects = OffsetAdjustment = MaxAlignment = 0;
@@ -225,6 +229,7 @@ public:
     CSIValid = false;
     LocalFrameSize = 0;
     LocalFrameBaseOffset = 0;
+    LocalFrameMaxAlign = 0;
   }
 
   /// hasStackObjects - Return true if there are any stack objects in this
@@ -302,6 +307,15 @@ public:
   /// getLocalFrameSize - Get the size of the local object blob.
   int64_t getLocalFrameSize() const { return LocalFrameSize; }
 
+  /// setLocalFrameMaxAlign - Required alignment of the local object blob,
+  /// which is the strictest alignment of any object in it.
+  void setLocalFrameMaxAlign(unsigned Align) { LocalFrameMaxAlign = Align; }
+
+  /// getLocalFrameMaxAlign - Return the required alignment of the local
+  /// object blob.
+  unsigned getLocalFrameMaxAlign() { return LocalFrameMaxAlign; }
+
+
   /// isObjectPreAllocated - Return true if the object was pre-allocated into
   /// the local block.
   bool isObjectPreAllocated(int ObjectIdx) const {

diff --git a/lib/CodeGen/LocalStackSlotAllocation.cpp b/lib/CodeGen/LocalStackSlotAllocation.cpp
index 8cacc179fa04a3083fecd7071837cadd5e0d4dac..75498ed8e5ac32624f03fc00f293449248f6bd9f 100644 (file)
--- a/lib/CodeGen/LocalStackSlotAllocation.cpp
+++ b/lib/CodeGen/LocalStackSlotAllocation.cpp
@@ -99,7 +99,7 @@ void LocalStackSlotPass::calculateFrameObjectOffsets(MachineFunction &Fn) {
   // Loop over all of the stack objects, assigning sequential addresses...
   MachineFrameInfo *MFI = Fn.getFrameInfo();
   int64_t Offset = 0;
-  unsigned MaxAlign = MFI->getMaxAlignment();
+  unsigned MaxAlign = 0;
 
   // Make sure that the stack protector comes before the local variables on the
   // stack.
@@ -134,33 +134,7 @@ void LocalStackSlotPass::calculateFrameObjectOffsets(MachineFunction &Fn) {
     AdjustStackOffset(MFI, i, Offset, MaxAlign);
   }
 
-  const TargetRegisterInfo *RegInfo = Fn.getTarget().getRegisterInfo();
-  if (!RegInfo->targetHandlesStackFrameRounding()) {
-    // If we have reserved argument space for call sites in the function
-    // immediately on entry to the current function, count it as part of the
-    // overall stack size.
-    if (MFI->adjustsStack() && RegInfo->hasReservedCallFrame(Fn))
-      Offset += MFI->getMaxCallFrameSize();
-
-    // Round up the size to a multiple of the alignment.  If the function has
-    // any calls or alloca's, align to the target's StackAlignment value to
-    // ensure that the callee's frame or the alloca data is suitably aligned;
-    // otherwise, for leaf functions, align to the TransientStackAlignment
-    // value.
-    unsigned StackAlign;
-    if (MFI->adjustsStack() || MFI->hasVarSizedObjects() ||
-        (RegInfo->needsStackRealignment(Fn) && MFI->getObjectIndexEnd() != 0))
-      StackAlign = TFI.getStackAlignment();
-    else
-      StackAlign = TFI.getTransientStackAlignment();
-
-    // If the frame pointer is eliminated, all frame offsets will be relative to
-    // SP not FP. Align to MaxAlign so this works.
-    StackAlign = std::max(StackAlign, MaxAlign);
-    unsigned AlignMask = StackAlign - 1;
-    Offset = (Offset + AlignMask) & ~uint64_t(AlignMask);
-  }
-
   // Remember how big this blob of stack space is
   MFI->setLocalFrameSize(Offset);
+  MFI->setLocalFrameMaxAlign(MaxAlign);
 }

diff --git a/lib/CodeGen/PrologEpilogInserter.cpp b/lib/CodeGen/PrologEpilogInserter.cpp
index 8f1d3a6da612f6a4faa5aee16e6756afd4a47cd9..83aa0c44d781cd620201bd7d845266e750d4a7c6 100644 (file)
--- a/lib/CodeGen/PrologEpilogInserter.cpp
+++ b/lib/CodeGen/PrologEpilogInserter.cpp
@@ -556,10 +556,20 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) {
       AdjustStackOffset(MFI, SFI, StackGrowsDown, Offset, MaxAlign);
   }
 
-  // Store the offset of the start of the local allocation block. This
-  // will be used later when resolving frame base virtual register pseudos.
-  MFI->setLocalFrameBaseOffset(Offset);
+  // FIXME: Once this is working, then enable flag will change to a target
+  // check for whether the frame is large enough to want to use virtual
+  // frame index registers. Functions which don't want/need this optimization
+  // will continue to use the existing code path.
   if (EnableLocalStackAlloc) {
+    unsigned Align = MFI->getLocalFrameMaxAlign();
+
+    // Adjust to alignment boundary.
+    Offset = (Offset + Align - 1) / Align * Align;
+
+    // Store the offset of the start of the local allocation block. This
+    // will be used later when resolving frame base virtual register pseudos.
+    MFI->setLocalFrameBaseOffset(Offset);
+
     // Allocate the local block
     Offset += MFI->getLocalFrameSize();
 
@@ -571,10 +581,6 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) {
       AdjustStackOffset(MFI, Entry.first, StackGrowsDown, FIOffset, MaxAlign);
     }
   }
-  // FIXME: Allocate locals. Once the block allocation pass is turned on,
-  // this simplifies to just the second loop, since all of the large objects
-  // will have already been handled. The second loop can also simplify a
-  // bit, as the conditionals inside aren't all necessary.
 
   // Make sure that the stack protector comes before the local variables on the
   // stack.