Index: docs/LangRef.rst
===================================================================
--- docs/LangRef.rst
+++ docs/LangRef.rst
@@ -1561,6 +1561,8 @@
     inlined into a function that has no ``"stack-probe-size"`` attribute
     at all, the resulting function has the ``"stack-probe-size"`` attribute
     of the callee.
+``"no-stack-arg-probe"``
+    This attribute disables ABI-required stack probes, if any.
 ``writeonly``
     On a function, this attribute indicates that the function may write to but
     does not read from memory.
Index: lib/Target/AArch64/AArch64FrameLowering.cpp
===================================================================
--- lib/Target/AArch64/AArch64FrameLowering.cpp
+++ lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -369,7 +369,8 @@
     F.getFnAttribute("stack-probe-size")
         .getValueAsString()
         .getAsInteger(0, StackProbeSize);
-  return StackSizeInBytes >= StackProbeSize;
+  return (StackSizeInBytes >= StackProbeSize) &&
+         !F.hasFnAttribute("no-stack-arg-probe");
 }
 
 bool AArch64FrameLowering::shouldCombineCSRLocalStackBump(
Index: lib/Target/ARM/ARMFrameLowering.cpp
===================================================================
--- lib/Target/ARM/ARMFrameLowering.cpp
+++ lib/Target/ARM/ARMFrameLowering.cpp
@@ -209,7 +209,8 @@
     F.getFnAttribute("stack-probe-size")
         .getValueAsString()
         .getAsInteger(0, StackProbeSize);
-  return StackSizeInBytes >= StackProbeSize;
+  return (StackSizeInBytes >= StackProbeSize) &&
+         !F.hasFnAttribute("no-stack-arg-probe");
 }
 
 namespace {
Index: lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- lib/Target/X86/X86ISelLowering.cpp
+++ lib/Target/X86/X86ISelLowering.cpp
@@ -38919,7 +38919,8 @@
 
   // Generally, if we aren't on Windows, the platform ABI does not include
   // support for stack probes, so don't emit them.
-  if (!Subtarget.isOSWindows() || Subtarget.isTargetMachO())
+  if (!Subtarget.isOSWindows() || Subtarget.isTargetMachO() ||
+      MF.getFunction()->hasFnAttribute("no-stack-arg-probe"))
     return "";
 
   // We need a stack probe to conform to the Windows ABI. Choose the right
Index: lib/Target/X86/X86WinAllocaExpander.cpp
===================================================================
--- lib/Target/X86/X86WinAllocaExpander.cpp
+++ lib/Target/X86/X86WinAllocaExpander.cpp
@@ -62,6 +62,7 @@
   unsigned StackPtr;
   unsigned SlotSize;
   int64_t StackProbeSize;
+  bool NoStackArgProbe;
 
   StringRef getPassName() const override { return "X86 WinAlloca Expander"; }
   static char ID;
@@ -240,13 +241,21 @@
     }
     break;
   case Probe:
-    // The probe lowering expects the amount in RAX/EAX.
-    BuildMI(*MBB, MI, DL, TII->get(TargetOpcode::COPY), RegA)
-        .addReg(MI->getOperand(0).getReg());
-
-    // Do the probe.
-    STI->getFrameLowering()->emitStackProbe(*MBB->getParent(), *MBB, MI, DL,
-                                            /*InPrologue=*/false);
+    if (!NoStackArgProbe) {
+      // The probe lowering expects the amount in RAX/EAX.
+      BuildMI(*MBB, MI, DL, TII->get(TargetOpcode::COPY), RegA)
+          .addReg(MI->getOperand(0).getReg());
+
+      // Do the probe.
+      STI->getFrameLowering()->emitStackProbe(*MBB->getParent(), *MBB, MI, DL,
+                                              /*InPrologue=*/false);
+    } else {
+      // Sub
+      BuildMI(*MBB, I, DL, TII->get(Is64Bit ? X86::SUB64rr : X86::SUB32rr),
+              StackPtr)
+          .addReg(StackPtr)
+          .addReg(MI->getOperand(0).getReg());
+    }
     break;
   }
 
@@ -278,6 +287,7 @@
   StackPtr = TRI->getStackRegister();
   SlotSize = TRI->getSlotSize();
 
+  NoStackArgProbe = MF.getFunction()->hasFnAttribute("no-stack-arg-probe");
   StackProbeSize = 4096;
   if (MF.getFunction().hasFnAttribute("stack-probe-size")) {
     MF.getFunction()