diff --git a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
index c219f79b96ea01..53e0a581762d4a 100644
--- a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -4276,7 +4276,7 @@ AArch64FrameLowering::inlineStackProbeLoopExactMultiple(
   return ExitMBB->begin();
 }
 
-MachineBasicBlock::iterator AArch64FrameLowering::inlineStackProbeFixed(
+void AArch64FrameLowering::inlineStackProbeFixed(
     MachineBasicBlock::iterator MBBI, Register ScratchReg, int64_t FrameSize,
     StackOffset CFAOffset) const {
   MachineBasicBlock *MBB = MBBI->getParent();
@@ -4353,54 +4353,35 @@ MachineBasicBlock::iterator AArch64FrameLowering::inlineStackProbeFixed(
           .setMIFlags(MachineInstr::FrameSetup);
     }
   }
-
-  MachineBasicBlock::iterator Next = std::next(MBBI);
-  return Next;
-}
-
-MachineBasicBlock::iterator AArch64FrameLowering::inlineStackProbeFixed(
-    MachineBasicBlock::iterator MBBI) const {
-
-  Register ScratchReg = MBBI->getOperand(0).getReg();
-  int64_t FrameSize = MBBI->getOperand(1).getImm();
-  StackOffset CFAOffset = StackOffset::get(MBBI->getOperand(2).getImm(),
-                                           MBBI->getOperand(3).getImm());
-
-  MachineBasicBlock::iterator NextInst =
-      inlineStackProbeFixed(MBBI, ScratchReg, FrameSize, CFAOffset);
-
-  MBBI->eraseFromParent();
-  return NextInst;
-}
-
-MachineBasicBlock::iterator AArch64FrameLowering::inlineStackProbeVar(
-    MachineBasicBlock::iterator MBBI) const {
-  MachineBasicBlock &MBB = *MBBI->getParent();
-  MachineFunction &MF = *MBB.getParent();
-  const AArch64InstrInfo *TII =
-      MF.getSubtarget<AArch64Subtarget>().getInstrInfo();
-
-  DebugLoc DL = MBB.findDebugLoc(MBBI);
-  Register TargetReg = MBBI->getOperand(0).getReg();
-
-  MachineBasicBlock::iterator NextInst =
-      TII->probedStackAlloc(MBBI, TargetReg, true);
-
-  MBBI->eraseFromParent();
-  return NextInst;
 }
 
 void AArch64FrameLowering::inlineStackProbe(MachineFunction &MF,
                                             MachineBasicBlock &MBB) const {
-  for (auto MBBI = MBB.begin(), E = MBB.end(); MBBI != E;) {
-    if (MBBI->getOpcode() == AArch64::PROBED_STACKALLOC) {
-      MBBI = inlineStackProbeFixed(MBBI);
-      E = MBBI->getParent()->end();
-    } else if (MBBI->getOpcode() == AArch64::PROBED_STACKALLOC_VAR) {
-      MBBI = inlineStackProbeVar(MBBI);
-      E = MBBI->getParent()->end();
+  // Get the instructions that need to be replaced. We emit at most two of
+  // these. Remember them in order to avoid complications coming from the need
+  // to traverse the block while potentially creating more blocks.
+  SmallVector<MachineInstr *, 4> ToReplace;
+  for (MachineInstr &MI : MBB)
+    if (MI.getOpcode() == AArch64::PROBED_STACKALLOC ||
+        MI.getOpcode() == AArch64::PROBED_STACKALLOC_VAR)
+      ToReplace.push_back(&MI);
+
+  for (MachineInstr *MI : ToReplace) {
+    if (MI->getOpcode() == AArch64::PROBED_STACKALLOC) {
+      Register ScratchReg = MI->getOperand(0).getReg();
+      int64_t FrameSize = MI->getOperand(1).getImm();
+      StackOffset CFAOffset = StackOffset::get(MI->getOperand(2).getImm(),
+                                               MI->getOperand(3).getImm());
+      inlineStackProbeFixed(MI->getIterator(), ScratchReg, FrameSize,
+                            CFAOffset);
     } else {
-      ++MBBI;
+      assert(MI->getOpcode() == AArch64::PROBED_STACKALLOC_VAR &&
+             "Stack probe pseudo-instruction expected");
+      const AArch64InstrInfo *TII =
+          MI->getMF()->getSubtarget<AArch64Subtarget>().getInstrInfo();
+      Register TargetReg = MI->getOperand(0).getReg();
+      (void)TII->probedStackAlloc(MI->getIterator(), TargetReg, true);
     }
+    MI->eraseFromParent();
   }
 }
diff --git a/llvm/lib/Target/AArch64/AArch64FrameLowering.h b/llvm/lib/Target/AArch64/AArch64FrameLowering.h
index f0c3106cb7017b..941af03a78b738 100644
--- a/llvm/lib/Target/AArch64/AArch64FrameLowering.h
+++ b/llvm/lib/Target/AArch64/AArch64FrameLowering.h
@@ -164,15 +164,9 @@ class AArch64FrameLowering : public TargetFrameLowering {
   void inlineStackProbe(MachineFunction &MF,
                         MachineBasicBlock &PrologueMBB) const override;
 
-  MachineBasicBlock::iterator
-  inlineStackProbeFixed(MachineBasicBlock::iterator MBBI, Register ScratchReg,
-                        int64_t FrameSize, StackOffset CFAOffset) const;
-
-  MachineBasicBlock::iterator
-  inlineStackProbeFixed(MachineBasicBlock::iterator MBBI) const;
-
-  MachineBasicBlock::iterator
-  inlineStackProbeVar(MachineBasicBlock::iterator MBBI) const;
+  void inlineStackProbeFixed(MachineBasicBlock::iterator MBBI,
+                             Register ScratchReg, int64_t FrameSize,
+                             StackOffset CFAOffset) const;
 
   MachineBasicBlock::iterator
   inlineStackProbeLoopExactMultiple(MachineBasicBlock::iterator MBBI,
diff --git a/llvm/test/CodeGen/AArch64/stack-probing-last-in-block.mir b/llvm/test/CodeGen/AArch64/stack-probing-last-in-block.mir
new file mode 100644
index 00000000000000..6c8ec7e4c4fa92
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/stack-probing-last-in-block.mir
@@ -0,0 +1,146 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 4
+# RUN: llc -run-pass=prologepilog %s -o - | FileCheck %s
+# Regression test for a crash when the probing instruction
+# to replace is last in the block.
+--- |
+  source_filename = "tt.ll"
+  target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+  target triple = "aarch64-linux"
+
+  declare i1 @g(ptr)
+
+  define void @f(ptr %out) #0 {
+  entry:
+    %p = alloca i32, i32 50000, align 4
+    br label %loop
+
+  loop:                                             ; preds = %loop, %entry
+    %c = call i1 @g(ptr %p)
+    br i1 %c, label %loop, label %exit
+
+  exit:                                             ; preds = %loop
+    ret void
+  }
+
+  attributes #0 = { uwtable "frame-pointer"="none" "probe-stack"="inline-asm" "target-features"="+sve" }
+
+...
+---
+name:            f
+alignment:       4
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+callsEHReturn:   false
+callsUnwindInit: false
+hasEHCatchret:   false
+hasEHScopes:     false
+hasEHFunclets:   false
+isOutlined:      false
+debugInstrRef:   false
+failsVerification: false
+tracksDebugUserValues: true
+registers:       []
+liveins:         []
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    4
+  adjustsStack:    true
+  hasCalls:        true
+  stackProtector:  ''
+  functionContext: ''
+  maxCallFrameSize: 0
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  hasTailCall:     false
+  localFrameSize:  200000
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:
+  - { id: 0, name: p, type: default, offset: 0, size: 200000, alignment: 4,
+      stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+      local-offset: -200000, debug-info-variable: '', debug-info-expression: '',
+      debug-info-location: '' }
+entry_values:    []
+callSites:       []
+debugValueSubstitutions: []
+constants:       []
+machineFunctionInfo: {}
+body:             |
+  ; CHECK-LABEL: name: f
+  ; CHECK: bb.0.entry:
+  ; CHECK-NEXT:   successors: %bb.3(0x80000000)
+  ; CHECK-NEXT:   liveins: $lr, $fp
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   early-clobber $sp = frame-setup STPXpre killed $fp, killed $lr, $sp, -2 :: (store (s64) into %stack.2), (store (s64) into %stack.1)
+  ; CHECK-NEXT:   frame-setup CFI_INSTRUCTION def_cfa_offset 16
+  ; CHECK-NEXT:   frame-setup CFI_INSTRUCTION offset $w30, -8
+  ; CHECK-NEXT:   frame-setup CFI_INSTRUCTION offset $w29, -16
+  ; CHECK-NEXT:   $x9 = frame-setup SUBXri $sp, 48, 12
+  ; CHECK-NEXT:   frame-setup CFI_INSTRUCTION def_cfa $w9, 196624
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.3.entry:
+  ; CHECK-NEXT:   successors: %bb.4(0x40000000), %bb.3(0x40000000)
+  ; CHECK-NEXT:   liveins: $x9
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   $sp = frame-setup SUBXri $sp, 1, 12
+  ; CHECK-NEXT:   frame-setup STRXui $xzr, $sp, 0
+  ; CHECK-NEXT:   $xzr = frame-setup SUBSXrx64 $sp, $x9, 24, implicit-def $nzcv
+  ; CHECK-NEXT:   frame-setup Bcc 1, %bb.3, implicit $nzcv
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.4.entry:
+  ; CHECK-NEXT:   successors: %bb.1(0x80000000)
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   frame-setup CFI_INSTRUCTION def_cfa_register $wsp
+  ; CHECK-NEXT:   $sp = frame-setup SUBXri $sp, 3392, 0
+  ; CHECK-NEXT:   frame-setup CFI_INSTRUCTION def_cfa_offset 200016
+  ; CHECK-NEXT:   frame-setup STRXui $xzr, $sp, 0
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.1.loop:
+  ; CHECK-NEXT:   successors: %bb.1(0x7c000000), %bb.2(0x04000000)
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   $x0 = ADDXri $sp, 0, 0
+  ; CHECK-NEXT:   BL @g, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp, implicit-def $w0
+  ; CHECK-NEXT:   TBNZW killed renamable $w0, 0, %bb.1
+  ; CHECK-NEXT:   B %bb.2
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.2.exit:
+  ; CHECK-NEXT:   $sp = frame-destroy ADDXri $sp, 48, 12
+  ; CHECK-NEXT:   frame-destroy CFI_INSTRUCTION def_cfa_offset 3408
+  ; CHECK-NEXT:   $sp = frame-destroy ADDXri $sp, 3392, 0
+  ; CHECK-NEXT:   frame-destroy CFI_INSTRUCTION def_cfa_offset 16
+  ; CHECK-NEXT:   early-clobber $sp, $fp, $lr = frame-destroy LDPXpost $sp, 2 :: (load (s64) from %stack.2), (load (s64) from %stack.1)
+  ; CHECK-NEXT:   frame-destroy CFI_INSTRUCTION def_cfa_offset 0
+  ; CHECK-NEXT:   frame-destroy CFI_INSTRUCTION restore $w30
+  ; CHECK-NEXT:   frame-destroy CFI_INSTRUCTION restore $w29
+  ; CHECK-NEXT:   RET_ReallyLR
+  bb.0.entry:
+    successors: %bb.1(0x80000000)
+
+
+  bb.1.loop:
+    successors: %bb.1(0x7c000000), %bb.2(0x04000000)
+
+    ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp
+    $x0 = ADDXri %stack.0.p, 0, 0
+    BL @g, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp, implicit-def $w0
+    ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp
+    TBNZW killed renamable $w0, 0, %bb.1
+    B %bb.2
+
+  bb.2.exit:
+    RET_ReallyLR
+
+...