r185380: [PowerPC] Fix alignment bug with addressing peephole optimization.

[Bill Schmidt]

I screwed up on my commit log message, so herewith is what I meant to
send:

PowerPC has an optimization in the DAG post-processing phase to
simplify addressing expressions.  One example would be:

  addis 3,2,var at toc@ha             addis 3,2,var at toc@ha
  addi  3,3,var at toc@l       =>     ld    4,var at toc@l(3)
  ld    4,0(3)

This optimization can be performed for a variety of loads and stores,
not just for ld.  However, for ld, std, and lwa, the instruction
encoding requires the offset (represented by var at toc@l) to be
divisible by 4.  A relocation enforcing this will be generated.

Before this patch, there was no check whether "var" is aligned on at
least a 4-byte boundary, so it is possible for an incorrect load with
an invalid relocation to be generated.

Besides fixing this problem, the patch also adds an assertion check
prior to emitting code for an ld, std, or lwa instruction, verifying
the alignment for global variables is correct.  This should help us
catch similar issues should they be introduced in the future.

Unfortunately, there appear to be some issues with the Darwin
subtargets in this regard.  Five of the tests in the test suite, all
of them specific to powerpc64-darwin-apple*, fail if the test is
enabled.  I don't have time to investigate problems for Darwin, so for
now I have disabled the test for those subtargets.  If anyone is
interested in investigating, I'd be happy to review patches.


Index: test/CodeGen/PowerPC/reloc-align.ll
===================================================================
--- test/CodeGen/PowerPC/reloc-align.ll	(revision 0)
+++ test/CodeGen/PowerPC/reloc-align.ll	(revision 0)
@@ -0,0 +1,34 @@
+; RUN: llc -mcpu=pwr7 -O1 < %s | FileCheck %s
+
+; This test verifies that the peephole optimization of address accesses
+; does not produce a load or store with a relocation that can't be
+; satisfied for a given instruction encoding.  Reduced from a test supplied
+; by Hal Finkel.
+
+target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f128:128:128-v128:128:128-n32:64"
+target triple = "powerpc64-unknown-linux-gnu"
+
+%struct.S1 = type { [8 x i8] }
+
+ at main.l_1554 = internal global { i8, i8, i8, i8, i8, i8, i8, i8 } { i8 -1, i8 -6, i8 57, i8 62, i8 -48, i8 0, i8 58, i8 80 }, align 1
+
+; Function Attrs: nounwind readonly
+define signext i32 @main() #0 {
+entry:
+  %call = tail call fastcc signext i32 @func_90(%struct.S1* byval bitcast ({ i8, i8, i8, i8, i8, i8, i8, i8 }* @main.l_1554 to %struct.S1*))
+; CHECK-NOT: ld {{[0-9]+}}, main.l_1554 at toc@l
+  ret i32 %call
+}
+
+; Function Attrs: nounwind readonly
+define internal fastcc signext i32 @func_90(%struct.S1* byval nocapture %p_91) #0 {
+entry:
+  %0 = bitcast %struct.S1* %p_91 to i64*
+  %bf.load = load i64* %0, align 1
+  %bf.shl = shl i64 %bf.load, 26
+  %bf.ashr = ashr i64 %bf.shl, 54
+  %bf.cast = trunc i64 %bf.ashr to i32
+  ret i32 %bf.cast
+}
+
+attributes #0 = { nounwind readonly "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf"="true" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
Index: lib/Target/PowerPC/PPCAsmPrinter.cpp
===================================================================
--- lib/Target/PowerPC/PPCAsmPrinter.cpp	(revision 185327)
+++ lib/Target/PowerPC/PPCAsmPrinter.cpp	(working copy)
@@ -679,7 +679,26 @@ void PPCAsmPrinter::EmitInstruction(const MachineI
       OutStreamer.EmitRawText(StringRef("\tmsync"));
       return;
     }
+    break;
+  case PPC::LD:
+  case PPC::STD:
+  case PPC::LWA: {
+    // Verify alignment is legal, so we don't create relocations
+    // that can't be supported.
+    // FIXME:  This test is currently disabled for Darwin.  The test
+    // suite shows a handful of test cases that fail this check for
+    // Darwin.  Those need to be investigated before this sanity test
+    // can be enabled for those subtargets.
+    if (!Subtarget.isDarwin()) {
+      unsigned OpNum = (MI->getOpcode() == PPC::STD) ? 2 : 1;
+      const MachineOperand &MO = MI->getOperand(OpNum);
+      if (MO.isGlobal() && MO.getGlobal()->getAlignment() < 4)
+        llvm_unreachable("Global must be word-aligned for LD, STD, LWA!");
+    }
+    // Now process the instruction normally.
+    break;
   }
+  }
 
   LowerPPCMachineInstrToMCInst(MI, TmpInst, *this);
   OutStreamer.EmitInstruction(TmpInst);
Index: lib/Target/PowerPC/PPCISelDAGToDAG.cpp
===================================================================
--- lib/Target/PowerPC/PPCISelDAGToDAG.cpp	(revision 185327)
+++ lib/Target/PowerPC/PPCISelDAGToDAG.cpp	(working copy)
@@ -1530,6 +1530,14 @@ void PPCDAGToDAGISel::PostprocessISelDAG() {
       if (GlobalAddressSDNode *GA = dyn_cast<GlobalAddressSDNode>(ImmOpnd)) {
         SDLoc dl(GA);
         const GlobalValue *GV = GA->getGlobal();
+        // We can't perform this optimization for data whose alignment
+        // is insufficient for the instruction encoding.
+        if (GV->getAlignment() < 4 &&
+            (StorageOpcode == PPC::LD || StorageOpcode == PPC::STD ||
+             StorageOpcode == PPC::LWA)) {
+          DEBUG(dbgs() << "Rejected this candidate for alignment.\n\n");
+          continue;
+        }
         ImmOpnd = CurDAG->getTargetGlobalAddress(GV, dl, MVT::i64, 0, Flags);
       } else if (ConstantPoolSDNode *CP =
                  dyn_cast<ConstantPoolSDNode>(ImmOpnd)) {