[PowerPC] Fix and(or(x, c1), c2) -> rlwimi generation

PPCISelDAGToDAG has a transformation that generates a rlwimi instruction from
an input pattern that looks like this:

  and(or(x, c1), c2)

but the associated logic does not work if there are bits that are 1 in c1 but 0
in c2 (these are normally canonicalized away, but that can't happen if the 'or'
has other users. Make sure we abort the transformation if such bits are
discovered.

Fixes PR24704.

llvm-svn: 246900

llvm/lib/Target/PowerPC/PPCISelDAGToDAG.cpp

@@ -2570,13 +2570,25 @@ SDNode *PPCDAGToDAGISel::Select(SDNode *N) {
       return nullptr;
     }
     // ISD::OR doesn't get all the bitfield insertion fun.
-    // (and (or x, c1), c2) where isRunOfOnes(~(c1^c2)) is a bitfield insert
+    // (and (or x, c1), c2) where isRunOfOnes(~(c1^c2)) might be a
+    // bitfield insert.
     if (isInt32Immediate(N->getOperand(1), Imm) &&
         N->getOperand(0).getOpcode() == ISD::OR &&
         isInt32Immediate(N->getOperand(0).getOperand(1), Imm2)) {
+      // The idea here is to check whether this is equivalent to:
+      //   (c1 & m) | (x & ~m)
+      // where m is a run-of-ones mask. The logic here is that, for each bit in
+      // c1 and c2:
+      //  - if both are 1, then the output will be 1.
+      //  - if both are 0, then the output will be 0.
+      //  - if the bit in c1 is 0, and the bit in c2 is 1, then the output will
+      //    come from x.
+      //  - if the bit in c1 is 1, and the bit in c2 is 0, then the output will
+      //    be 0.
+      //  If that last condition is never the case, then we can form m from the
+      //  bits that are the same between c1 and c2.
       unsigned MB, ME;
-      Imm = ~(Imm^Imm2);
-      if (isRunOfOnes(Imm, MB, ME)) {
+      if (isRunOfOnes(~(Imm^Imm2), MB, ME) && !(~Imm & Imm2)) {
         SDValue Ops[] = { N->getOperand(0).getOperand(0),
                             N->getOperand(0).getOperand(1),
                             getI32Imm(0, dl), getI32Imm(MB, dl),

llvm/test/CodeGen/PowerPC/rlwimi-and-or-bits.ll

@@ -0,0 +1,27 @@
+; RUN: llc < %s | FileCheck %s
+target datalayout = "E-m:e-i64:64-n32:64"
+target triple = "powerpc64-unknown-linux-gnu"
+
+@m = external global i32, align 4
+
+; Function Attrs: nounwind
+define signext i32 @main() #0 {
+entry:
+
+; CHECK-LABEL: @main
+; CHECK-NOT: rlwimi
+; CHECK: andi
+
+  %0 = load i32, i32* @m, align 4
+  %or = or i32 %0, 250
+  store i32 %or, i32* @m, align 4
+  %and = and i32 %or, 249
+  %sub.i = sub i32 %and, 0
+  %sext = shl i32 %sub.i, 24
+  %conv = ashr exact i32 %sext, 24
+  ret i32 %conv
+}
+
+attributes #0 = { nounwind "target-cpu"="pwr7" }
+attributes #1 = { nounwind }
+