diff --git a/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp b/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp
--- a/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp
+++ b/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp
@@ -999,6 +999,11 @@
 
 void RISCVInsertVSETVLI::emitVSETVLIs(MachineBasicBlock &MBB) {
   VSETVLIInfo CurInfo;
+  // BBLocalInfo tracks the VL/VTYPE state way BBInfo.Change was calculated in
+  // computeIncomingVLVTYPE. We need this to apply canSkipVSETVLIForLoadStore
+  // the same way computeIncomingVLVTYPE did. We can't include predecessor
+  // information in that decision to avoid disagreeing with the global analysis.
+  VSETVLIInfo BBLocalInfo;
   // Only be set if current VSETVLIInfo is from an explicit VSET(I)VLI.
   MachineInstr *PrevVSETVLIMI = nullptr;
 
@@ -1014,6 +1019,7 @@
       MI.getOperand(3).setIsDead(false);
       MI.getOperand(4).setIsDead(false);
       CurInfo = getInfoForVSETVLI(MI);
+      BBLocalInfo = getInfoForVSETVLI(MI);
       PrevVSETVLIMI = &MI;
       continue;
     }
@@ -1043,12 +1049,22 @@
         // use the predecessor information.
         assert(BlockInfo[MBB.getNumber()].Pred.isValid() &&
                "Expected a valid predecessor state.");
-        if (needVSETVLI(NewInfo, BlockInfo[MBB.getNumber()].Pred) &&
+        // Don't use predecessor information if there was an earlier instruction
+        // in this block that allowed a vsetvli to be skipped for load/store.
+        if (!(BBLocalInfo.isValid() &&
+              canSkipVSETVLIForLoadStore(MI, NewInfo, BBLocalInfo)) &&
+            needVSETVLI(NewInfo, BlockInfo[MBB.getNumber()].Pred) &&
             needVSETVLIPHI(NewInfo, MBB)) {
           insertVSETVLI(MBB, MI, NewInfo, BlockInfo[MBB.getNumber()].Pred);
           CurInfo = NewInfo;
+          BBLocalInfo = NewInfo;
         }
+
+        // We must update BBLocalInfo for every vector instruction.
+        if (!BBLocalInfo.isValid())
+          BBLocalInfo = NewInfo;
       } else {
+        assert(BBLocalInfo.isValid());
         // If this instruction isn't compatible with the previous VL/VTYPE
         // we need to insert a VSETVLI.
         // If this is a unit-stride or strided load/store, we may be able to use
@@ -1084,6 +1100,7 @@
           if (NeedInsertVSETVLI)
             insertVSETVLI(MBB, MI, NewInfo, CurInfo);
           CurInfo = NewInfo;
+          BBLocalInfo = NewInfo;
         }
       }
       PrevVSETVLIMI = nullptr;
@@ -1094,6 +1111,7 @@
     if (MI.isCall() || MI.isInlineAsm() || MI.modifiesRegister(RISCV::VL) ||
         MI.modifiesRegister(RISCV::VTYPE)) {
       CurInfo = VSETVLIInfo::getUnknown();
+      BBLocalInfo = VSETVLIInfo::getUnknown();
       PrevVSETVLIMI = nullptr;
     }
   }
diff --git a/llvm/test/CodeGen/RISCV/rvv/vsetvli-insert-crossbb.mir b/llvm/test/CodeGen/RISCV/rvv/vsetvli-insert-crossbb.mir
--- a/llvm/test/CodeGen/RISCV/rvv/vsetvli-insert-crossbb.mir
+++ b/llvm/test/CodeGen/RISCV/rvv/vsetvli-insert-crossbb.mir
@@ -567,10 +567,6 @@
   ; CHECK-NEXT:   [[PseudoVADD_VX_M1_:%[0-9]+]]:vr = PseudoVADD_VX_M1 [[PseudoVID_V_M1_]], [[PHI]], -1, 6, implicit $vl, implicit $vtype
   ; CHECK-NEXT:   [[MUL:%[0-9]+]]:gpr = MUL [[PHI]], [[SRLI]]
   ; CHECK-NEXT:   [[ADD:%[0-9]+]]:gpr = ADD [[COPY]], [[MUL]]
-  ; FIXME: We insert a SEW=32,LMUL=1/2 VSETVLI here but no SEW=64,LMUL=1
-  ; VSETVLI before the VADD above. This misconfigures the VADD in the case that
-  ; the loop takes its backedge.
-  ; CHECK-NEXT:   dead $x0 = PseudoVSETVLIX0 killed $x0, 87, implicit-def $vl, implicit-def $vtype, implicit $vl
   ; CHECK-NEXT:   PseudoVSE32_V_MF2 killed [[PseudoVADD_VX_M1_]], killed [[ADD]], -1, 5, implicit $vl, implicit $vtype
   ; CHECK-NEXT:   [[ADDI:%[0-9]+]]:gpr = ADDI [[PHI]], 1
   ; CHECK-NEXT:   BLTU [[ADDI]], [[COPY1]], %bb.1