diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -8441,6 +8441,11 @@
     if (!CM.blockNeedsPredicationForAnyReason(BB))
       return BlockMaskCache[BB] = BlockMask; // Loop incoming mask is all-one.
 
+    auto NewInsertionPoint = Builder.getInsertBlock()->getFirstNonPhi();
+    // Create the block in mask as the first non-phi instruction in the block.
+    VPBuilder::InsertPointGuard Guard(Builder);
+    Builder.setInsertPoint(Builder.getInsertBlock(), NewInsertionPoint);
+
     // Introduce the early-exit compare IV <= BTC to form header block mask.
     // This is used instead of IV < TC because TC may wrap, unlike BTC.
     // Start by constructing the desired canonical IV in the header block.
@@ -8454,13 +8459,7 @@
       IV = IVRecipe;
     }
 
-    // Create the block in mask as the first non-phi instruction in the block.
-    VPBuilder::InsertPointGuard Guard(Builder);
-    auto NewInsertionPoint = Builder.getInsertBlock()->getFirstNonPhi();
-    Builder.setInsertPoint(Builder.getInsertBlock(), NewInsertionPoint);
-
     assert(CM.foldTailByMasking() && "must fold the tail");
-
     if (CM.TTI.emitGetActiveLaneMask()) {
       VPValue *TC = Plan->getOrCreateTripCount();
       BlockMask = Builder.createNaryOp(VPInstruction::ActiveLaneMask, {IV, TC});
diff --git a/llvm/lib/Transforms/Vectorize/VPlanValue.h b/llvm/lib/Transforms/Vectorize/VPlanValue.h
--- a/llvm/lib/Transforms/Vectorize/VPlanValue.h
+++ b/llvm/lib/Transforms/Vectorize/VPlanValue.h
@@ -96,6 +96,7 @@
     VPVReplicateSC,
     VPVWidenSC,
     VPVWidenCallSC,
+    VPVWidenCanonicalIVSC,
     VPVWidenGEPSC,
     VPVWidenSelectSC,
 
@@ -103,7 +104,6 @@
     VPVBlendSC,
     VPVFirstOrderRecurrencePHISC,
     VPVWidenPHISC,
-    VPVWidenCanonicalIVSC,
     VPVWidenIntOrFpInductionSC,
     VPVPredInstPHI,
     VPVReductionPHISC,
@@ -325,6 +325,7 @@
     VPReductionSC,
     VPReplicateSC,
     VPWidenCallSC,
+    VPWidenCanonicalIVSC,
     VPWidenGEPSC,
     VPWidenMemoryInstructionSC,
     VPWidenSC,
@@ -334,7 +335,6 @@
     VPBlendSC,
     VPFirstOrderRecurrencePHISC,
     VPWidenPHISC,
-    VPWidenCanonicalIVSC,
     VPWidenIntOrFpInductionSC,
     VPPredInstPHISC,
     VPReductionPHISC,
diff --git a/llvm/test/Transforms/LoopVectorize/pr46525-expander-insertpoint.ll b/llvm/test/Transforms/LoopVectorize/pr46525-expander-insertpoint.ll
--- a/llvm/test/Transforms/LoopVectorize/pr46525-expander-insertpoint.ll
+++ b/llvm/test/Transforms/LoopVectorize/pr46525-expander-insertpoint.ll
@@ -39,20 +39,20 @@
 ; CHECK-NEXT:    [[INDUCTION:%.*]] = add <2 x i64> [[BROADCAST_SPLAT2]], [[TMP3]]
 ; CHECK-NEXT:    [[TMP4:%.*]] = mul i64 0, [[INC]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[OFFSET_IDX]], [[TMP4]]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <2 x i64> poison, i64 [[INDEX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT4:%.*]] = shufflevector <2 x i64> [[BROADCAST_SPLATINSERT3]], <2 x i64> poison, <2 x i32> zeroinitializer
-; CHECK-NEXT:    [[VEC_IV:%.*]] = add <2 x i64> [[BROADCAST_SPLAT4]], <i64 0, i64 1>
-; CHECK-NEXT:    [[OFFSET_IDX5:%.*]] = mul i64 [[INDEX]], [[INC]]
-; CHECK-NEXT:    [[TMP6:%.*]] = trunc i64 [[OFFSET_IDX5]] to i8
+; CHECK-NEXT:    [[OFFSET_IDX3:%.*]] = mul i64 [[INDEX]], [[INC]]
+; CHECK-NEXT:    [[TMP6:%.*]] = trunc i64 [[OFFSET_IDX3]] to i8
 ; CHECK-NEXT:    [[TMP7:%.*]] = trunc i64 [[INC]] to i8
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT6:%.*]] = insertelement <2 x i8> poison, i8 [[TMP6]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT7:%.*]] = shufflevector <2 x i8> [[BROADCAST_SPLATINSERT6]], <2 x i8> poison, <2 x i32> zeroinitializer
-; CHECK-NEXT:    [[DOTSPLATINSERT8:%.*]] = insertelement <2 x i8> poison, i8 [[TMP7]], i32 0
-; CHECK-NEXT:    [[DOTSPLAT9:%.*]] = shufflevector <2 x i8> [[DOTSPLATINSERT8]], <2 x i8> poison, <2 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP8:%.*]] = mul <2 x i8> <i8 0, i8 1>, [[DOTSPLAT9]]
-; CHECK-NEXT:    [[INDUCTION10:%.*]] = add <2 x i8> [[BROADCAST_SPLAT7]], [[TMP8]]
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT4:%.*]] = insertelement <2 x i8> poison, i8 [[TMP6]], i32 0
+; CHECK-NEXT:    [[BROADCAST_SPLAT5:%.*]] = shufflevector <2 x i8> [[BROADCAST_SPLATINSERT4]], <2 x i8> poison, <2 x i32> zeroinitializer
+; CHECK-NEXT:    [[DOTSPLATINSERT6:%.*]] = insertelement <2 x i8> poison, i8 [[TMP7]], i32 0
+; CHECK-NEXT:    [[DOTSPLAT7:%.*]] = shufflevector <2 x i8> [[DOTSPLATINSERT6]], <2 x i8> poison, <2 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP8:%.*]] = mul <2 x i8> <i8 0, i8 1>, [[DOTSPLAT7]]
+; CHECK-NEXT:    [[INDUCTION8:%.*]] = add <2 x i8> [[BROADCAST_SPLAT5]], [[TMP8]]
 ; CHECK-NEXT:    [[TMP9:%.*]] = mul i8 0, [[TMP7]]
 ; CHECK-NEXT:    [[TMP10:%.*]] = add i8 [[TMP6]], [[TMP9]]
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT9:%.*]] = insertelement <2 x i64> poison, i64 [[INDEX]], i32 0
+; CHECK-NEXT:    [[BROADCAST_SPLAT10:%.*]] = shufflevector <2 x i64> [[BROADCAST_SPLATINSERT9]], <2 x i64> poison, <2 x i32> zeroinitializer
+; CHECK-NEXT:    [[VEC_IV:%.*]] = add <2 x i64> [[BROADCAST_SPLAT10]], <i64 0, i64 1>
 ; CHECK-NEXT:    [[TMP11:%.*]] = icmp ule <2 x i64> [[VEC_IV]], [[BROADCAST_SPLAT]]
 ; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <2 x i1> [[TMP11]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP12]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]