Index: llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp
===================================================================
--- llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp
+++ llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp
@@ -1833,20 +1833,40 @@
   return V;
 }
 
-/// Check whether value has nuw/nsw/exact set but SCEV does not.
-/// TODO: In reality it is better to check the poison recursively
-/// but this is better than nothing.
-static bool SCEVLostPoisonFlags(const SCEV *S, const Instruction *I) {
+/// Return true if we can reuse instruction 'I' for all users of 'S' without
+/// introducing uses of 'I' which propagate poison in more cases.
+static bool canReuseInstructionForAllUsers(const SCEV *S,
+                                           const Instruction *I) {
   if (isa<OverflowingBinaryOperator>(I)) {
+    if (!I->hasNoSignedWrap() && !I->hasNoUnsignedWrap())
+      // 'I' never introduces new poison
+      return true;
     if (auto *NS = dyn_cast<SCEVNAryExpr>(S)) {
+      // We have a SCEV with flags we can check, are the instructions
+      // flags strictly weaker than the SCEVs?
       if (I->hasNoSignedWrap() && !NS->hasNoSignedWrap())
-        return true;
+        return false;
       if (I->hasNoUnsignedWrap() && !NS->hasNoUnsignedWrap())
-        return true;
+        return false;
+      return true;
     }
+    // In general, we may have used flags to optimize a binop into an
+    // alternate form.  Thus, we must conclude that S conceptually has
+    // some unknown set of flags and thus that I must contradict them.
+    return false;
   } else if (isa<PossiblyExactOperator>(I) && I->isExact())
+    return false;
+  else if (const auto *GEP = dyn_cast<GEPOperator>(I)) {
+    if (!GEP->isInBounds())
+      return false;
+    // TODO: SCEV models as an add in most cases, we could duplicate
+    // logic from above for this.
     return true;
-  return false;
+  }
+
+  // We have enumerated the instructions which have poison generating flags
+  // while also being SCEVable.  Thus, if we get here, we can reuse.
+  return true;
 }
 
 ScalarEvolution::ValueOffsetPair
@@ -1873,7 +1893,7 @@
             SE.DT.dominates(EntInst, InsertPt) &&
             (SE.LI.getLoopFor(EntInst->getParent()) == nullptr ||
              SE.LI.getLoopFor(EntInst->getParent())->contains(InsertPt)) &&
-            !SCEVLostPoisonFlags(S, EntInst))
+            canReuseInstructionForAllUsers(S, EntInst))
           return {V, Offset};
       }
     }
Index: llvm/test/CodeGen/PowerPC/common-chain.ll
===================================================================
--- llvm/test/CodeGen/PowerPC/common-chain.ll
+++ llvm/test/CodeGen/PowerPC/common-chain.ll
@@ -786,158 +786,154 @@
 ; CHECK-NEXT:    cmpldi r8, 3
 ; CHECK-NEXT:    blt cr0, .LBB7_4
 ; CHECK-NEXT:  # %bb.2: # %for.body.preheader.new
+; CHECK-NEXT:    ld r17, -176(r1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld r18, -168(r1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld r19, -160(r1) # 8-byte Folded Reload
+; CHECK-NEXT:    sldi r11, r12, 1
+; CHECK-NEXT:    add r0, r12, r11
 ; CHECK-NEXT:    rldicl r7, r7, 62, 2
 ; CHECK-NEXT:    sldi r10, r12, 2
-; CHECK-NEXT:    ld r2, -168(r1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld r31, -160(r1) # 8-byte Folded Reload
-; CHECK-NEXT:    std r7, -184(r1) # 8-byte Folded Spill
-; CHECK-NEXT:    mr r7, r4
-; CHECK-NEXT:    ld r4, -176(r1) # 8-byte Folded Reload
-; CHECK-NEXT:    add r8, r4, r10
-; CHECK-NEXT:    sldi r8, r8, 3
-; CHECK-NEXT:    add r9, r5, r8
-; CHECK-NEXT:    add r8, r2, r10
-; CHECK-NEXT:    add r10, r31, r10
-; CHECK-NEXT:    sldi r10, r10, 3
+; CHECK-NEXT:    rldicl r7, r7, 2, 1
+; CHECK-NEXT:    add r29, r17, r0
+; CHECK-NEXT:    add r28, r18, r0
+; CHECK-NEXT:    add r0, r19, r0
+; CHECK-NEXT:    addi r7, r7, -4
+; CHECK-NEXT:    add r8, r17, r10
+; CHECK-NEXT:    sldi r31, r0, 3
+; CHECK-NEXT:    add r0, r17, r11
 ; CHECK-NEXT:    sldi r8, r8, 3
-; CHECK-NEXT:    add r30, r5, r10
-; CHECK-NEXT:    add r29, r7, r10
-; CHECK-NEXT:    add r28, r3, r10
-; CHECK-NEXT:    sldi r10, r12, 1
-; CHECK-NEXT:    add r8, r5, r8
-; CHECK-NEXT:    add r11, r12, r10
-; CHECK-NEXT:    add r0, r4, r11
-; CHECK-NEXT:    sldi r0, r0, 3
-; CHECK-NEXT:    add r27, r5, r0
-; CHECK-NEXT:    add r0, r2, r11
-; CHECK-NEXT:    add r11, r31, r11
-; CHECK-NEXT:    sldi r11, r11, 3
+; CHECK-NEXT:    rldicl r7, r7, 62, 2
+; CHECK-NEXT:    sldi r29, r29, 3
+; CHECK-NEXT:    sldi r28, r28, 3
 ; CHECK-NEXT:    sldi r0, r0, 3
-; CHECK-NEXT:    add r25, r5, r11
-; CHECK-NEXT:    add r24, r7, r11
-; CHECK-NEXT:    add r23, r3, r11
-; CHECK-NEXT:    add r11, r4, r10
+; CHECK-NEXT:    addi r7, r7, 1
+; CHECK-NEXT:    add r9, r5, r8
+; CHECK-NEXT:    add r8, r18, r10
+; CHECK-NEXT:    add r10, r19, r10
+; CHECK-NEXT:    add r29, r5, r29
+; CHECK-NEXT:    add r28, r5, r28
+; CHECK-NEXT:    add r27, r5, r31
 ; CHECK-NEXT:    add r26, r5, r0
-; CHECK-NEXT:    sldi r11, r11, 3
-; CHECK-NEXT:    add r22, r5, r11
-; CHECK-NEXT:    add r11, r2, r10
-; CHECK-NEXT:    add r10, r31, r10
+; CHECK-NEXT:    add r0, r18, r11
+; CHECK-NEXT:    add r11, r19, r11
+; CHECK-NEXT:    sldi r8, r8, 3
 ; CHECK-NEXT:    sldi r10, r10, 3
+; CHECK-NEXT:    mtctr r7
+; CHECK-NEXT:    sldi r7, r12, 5
+; CHECK-NEXT:    sldi r0, r0, 3
 ; CHECK-NEXT:    sldi r11, r11, 3
-; CHECK-NEXT:    add r20, r5, r10
-; CHECK-NEXT:    add r19, r7, r10
-; CHECK-NEXT:    add r18, r3, r10
-; CHECK-NEXT:    add r10, r12, r4
-; CHECK-NEXT:    add r21, r5, r11
-; CHECK-NEXT:    sldi r11, r2, 3
-; CHECK-NEXT:    sldi r10, r10, 3
-; CHECK-NEXT:    add r17, r5, r10
-; CHECK-NEXT:    add r10, r12, r2
-; CHECK-NEXT:    sldi r10, r10, 3
-; CHECK-NEXT:    add r16, r5, r10
-; CHECK-NEXT:    add r10, r12, r31
-; CHECK-NEXT:    sldi r31, r31, 3
-; CHECK-NEXT:    sub r0, r11, r31
-; CHECK-NEXT:    sldi r11, r4, 3
-; CHECK-NEXT:    mr r4, r7
-; CHECK-NEXT:    ld r7, -184(r1) # 8-byte Folded Reload
-; CHECK-NEXT:    sldi r10, r10, 3
-; CHECK-NEXT:    add r15, r5, r10
-; CHECK-NEXT:    add r14, r3, r10
-; CHECK-NEXT:    sub r31, r11, r31
+; CHECK-NEXT:    add r8, r5, r8
+; CHECK-NEXT:    add r30, r5, r10
+; CHECK-NEXT:    add r16, r3, r10
 ; CHECK-NEXT:    add r2, r4, r10
-; CHECK-NEXT:    li r11, 0
 ; CHECK-NEXT:    mr r10, r12
-; CHECK-NEXT:    rldicl r7, r7, 2, 1
-; CHECK-NEXT:    addi r7, r7, -4
-; CHECK-NEXT:    rldicl r7, r7, 62, 2
-; CHECK-NEXT:    addi r7, r7, 1
-; CHECK-NEXT:    mtctr r7
-; CHECK-NEXT:    sldi r7, r12, 5
+; CHECK-NEXT:    add r25, r5, r0
+; CHECK-NEXT:    add r0, r12, r17
+; CHECK-NEXT:    add r24, r5, r11
+; CHECK-NEXT:    add r14, r4, r11
+; CHECK-NEXT:    sldi r0, r0, 3
+; CHECK-NEXT:    add r23, r5, r0
+; CHECK-NEXT:    add r0, r12, r18
+; CHECK-NEXT:    sldi r0, r0, 3
+; CHECK-NEXT:    add r22, r5, r0
+; CHECK-NEXT:    add r0, r12, r19
+; CHECK-NEXT:    sldi r19, r19, 3
+; CHECK-NEXT:    sldi r15, r0, 3
+; CHECK-NEXT:    sldi r0, r18, 3
+; CHECK-NEXT:    sldi r18, r17, 3
+; CHECK-NEXT:    add r17, r3, r31
+; CHECK-NEXT:    add r31, r4, r31
+; CHECK-NEXT:    add r21, r5, r15
+; CHECK-NEXT:    add r20, r3, r15
+; CHECK-NEXT:    sub r0, r0, r19
+; CHECK-NEXT:    sub r19, r18, r19
+; CHECK-NEXT:    add r18, r3, r11
+; CHECK-NEXT:    add r15, r4, r15
+; CHECK-NEXT:    li r11, 0
 ; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB7_3: # %for.body
 ; CHECK-NEXT:    #
-; CHECK-NEXT:    lfd f0, 0(r14)
-; CHECK-NEXT:    lfd f1, 0(r2)
+; CHECK-NEXT:    lfd f0, 0(r20)
+; CHECK-NEXT:    lfd f1, 0(r15)
 ; CHECK-NEXT:    add r10, r10, r12
 ; CHECK-NEXT:    add r10, r10, r12
 ; CHECK-NEXT:    xsmuldp f0, f0, f1
-; CHECK-NEXT:    lfd f1, 0(r15)
+; CHECK-NEXT:    lfd f1, 0(r21)
 ; CHECK-NEXT:    add r10, r10, r12
 ; CHECK-NEXT:    add r10, r10, r12
 ; CHECK-NEXT:    xsadddp f0, f1, f0
-; CHECK-NEXT:    stfd f0, 0(r15)
-; CHECK-NEXT:    add r15, r15, r7
-; CHECK-NEXT:    lfdx f0, r14, r0
-; CHECK-NEXT:    lfdx f1, r2, r0
+; CHECK-NEXT:    stfd f0, 0(r21)
+; CHECK-NEXT:    add r21, r21, r7
+; CHECK-NEXT:    lfdx f0, r20, r0
+; CHECK-NEXT:    lfdx f1, r15, r0
 ; CHECK-NEXT:    xsmuldp f0, f0, f1
-; CHECK-NEXT:    lfdx f1, r16, r11
+; CHECK-NEXT:    lfdx f1, r22, r11
 ; CHECK-NEXT:    xsadddp f0, f1, f0
-; CHECK-NEXT:    stfdx f0, r16, r11
-; CHECK-NEXT:    lfdx f0, r14, r31
-; CHECK-NEXT:    lfdx f1, r2, r31
-; CHECK-NEXT:    add r14, r14, r7
-; CHECK-NEXT:    add r2, r2, r7
+; CHECK-NEXT:    stfdx f0, r22, r11
+; CHECK-NEXT:    lfdx f0, r20, r19
+; CHECK-NEXT:    lfdx f1, r15, r19
+; CHECK-NEXT:    add r20, r20, r7
+; CHECK-NEXT:    add r15, r15, r7
 ; CHECK-NEXT:    xsmuldp f0, f0, f1
-; CHECK-NEXT:    lfdx f1, r17, r11
+; CHECK-NEXT:    lfdx f1, r23, r11
 ; CHECK-NEXT:    xsadddp f0, f1, f0
-; CHECK-NEXT:    stfdx f0, r17, r11
+; CHECK-NEXT:    stfdx f0, r23, r11
 ; CHECK-NEXT:    lfd f0, 0(r18)
-; CHECK-NEXT:    lfd f1, 0(r19)
+; CHECK-NEXT:    lfd f1, 0(r14)
 ; CHECK-NEXT:    xsmuldp f0, f0, f1
-; CHECK-NEXT:    lfdx f1, r20, r11
+; CHECK-NEXT:    lfdx f1, r24, r11
 ; CHECK-NEXT:    xsadddp f0, f1, f0
-; CHECK-NEXT:    stfdx f0, r20, r11
+; CHECK-NEXT:    stfdx f0, r24, r11
 ; CHECK-NEXT:    lfdx f0, r18, r0
-; CHECK-NEXT:    lfdx f1, r19, r0
-; CHECK-NEXT:    xsmuldp f0, f0, f1
-; CHECK-NEXT:    lfdx f1, r21, r11
-; CHECK-NEXT:    xsadddp f0, f1, f0
-; CHECK-NEXT:    stfdx f0, r21, r11
-; CHECK-NEXT:    lfdx f0, r18, r31
-; CHECK-NEXT:    lfdx f1, r19, r31
-; CHECK-NEXT:    add r18, r18, r7
-; CHECK-NEXT:    add r19, r19, r7
-; CHECK-NEXT:    xsmuldp f0, f0, f1
-; CHECK-NEXT:    lfdx f1, r22, r11
-; CHECK-NEXT:    xsadddp f0, f1, f0
-; CHECK-NEXT:    stfdx f0, r22, r11
-; CHECK-NEXT:    lfd f0, 0(r23)
-; CHECK-NEXT:    lfd f1, 0(r24)
+; CHECK-NEXT:    lfdx f1, r14, r0
 ; CHECK-NEXT:    xsmuldp f0, f0, f1
 ; CHECK-NEXT:    lfdx f1, r25, r11
 ; CHECK-NEXT:    xsadddp f0, f1, f0
 ; CHECK-NEXT:    stfdx f0, r25, r11
-; CHECK-NEXT:    lfdx f0, r23, r0
-; CHECK-NEXT:    lfdx f1, r24, r0
+; CHECK-NEXT:    lfdx f0, r18, r19
+; CHECK-NEXT:    lfdx f1, r14, r19
+; CHECK-NEXT:    add r18, r18, r7
+; CHECK-NEXT:    add r14, r14, r7
 ; CHECK-NEXT:    xsmuldp f0, f0, f1
 ; CHECK-NEXT:    lfdx f1, r26, r11
 ; CHECK-NEXT:    xsadddp f0, f1, f0
 ; CHECK-NEXT:    stfdx f0, r26, r11
-; CHECK-NEXT:    lfdx f0, r23, r31
-; CHECK-NEXT:    lfdx f1, r24, r31
-; CHECK-NEXT:    add r23, r23, r7
-; CHECK-NEXT:    add r24, r24, r7
+; CHECK-NEXT:    lfd f0, 0(r17)
+; CHECK-NEXT:    lfd f1, 0(r31)
 ; CHECK-NEXT:    xsmuldp f0, f0, f1
 ; CHECK-NEXT:    lfdx f1, r27, r11
 ; CHECK-NEXT:    xsadddp f0, f1, f0
 ; CHECK-NEXT:    stfdx f0, r27, r11
-; CHECK-NEXT:    lfd f0, 0(r28)
-; CHECK-NEXT:    lfd f1, 0(r29)
+; CHECK-NEXT:    lfdx f0, r17, r0
+; CHECK-NEXT:    lfdx f1, r31, r0
+; CHECK-NEXT:    xsmuldp f0, f0, f1
+; CHECK-NEXT:    lfdx f1, r28, r11
+; CHECK-NEXT:    xsadddp f0, f1, f0
+; CHECK-NEXT:    stfdx f0, r28, r11
+; CHECK-NEXT:    lfdx f0, r17, r19
+; CHECK-NEXT:    lfdx f1, r31, r19
+; CHECK-NEXT:    add r17, r17, r7
+; CHECK-NEXT:    add r31, r31, r7
+; CHECK-NEXT:    xsmuldp f0, f0, f1
+; CHECK-NEXT:    lfdx f1, r29, r11
+; CHECK-NEXT:    xsadddp f0, f1, f0
+; CHECK-NEXT:    stfdx f0, r29, r11
+; CHECK-NEXT:    lfd f0, 0(r16)
+; CHECK-NEXT:    lfd f1, 0(r2)
 ; CHECK-NEXT:    xsmuldp f0, f0, f1
 ; CHECK-NEXT:    lfdx f1, r30, r11
 ; CHECK-NEXT:    xsadddp f0, f1, f0
 ; CHECK-NEXT:    stfdx f0, r30, r11
-; CHECK-NEXT:    lfdx f0, r28, r0
-; CHECK-NEXT:    lfdx f1, r29, r0
+; CHECK-NEXT:    lfdx f0, r16, r0
+; CHECK-NEXT:    lfdx f1, r2, r0
 ; CHECK-NEXT:    xsmuldp f0, f0, f1
 ; CHECK-NEXT:    lfdx f1, r8, r11
 ; CHECK-NEXT:    xsadddp f0, f1, f0
 ; CHECK-NEXT:    stfdx f0, r8, r11
-; CHECK-NEXT:    lfdx f0, r28, r31
-; CHECK-NEXT:    lfdx f1, r29, r31
-; CHECK-NEXT:    add r28, r28, r7
-; CHECK-NEXT:    add r29, r29, r7
+; CHECK-NEXT:    lfdx f0, r16, r19
+; CHECK-NEXT:    lfdx f1, r2, r19
+; CHECK-NEXT:    add r16, r16, r7
+; CHECK-NEXT:    add r2, r2, r7
 ; CHECK-NEXT:    xsmuldp f0, f0, f1
 ; CHECK-NEXT:    lfdx f1, r9, r11
 ; CHECK-NEXT:    xsadddp f0, f1, f0