diff --git a/llvm/lib/Target/AArch64/AArch64CallingConvention.td b/llvm/lib/Target/AArch64/AArch64CallingConvention.td
--- a/llvm/lib/Target/AArch64/AArch64CallingConvention.td
+++ b/llvm/lib/Target/AArch64/AArch64CallingConvention.td
@@ -384,6 +384,10 @@
                                            D8,  D9,  D10, D11,
                                            D12, D13, D14, D15)>;
 
+// A variant for treating X18 as callee saved, when interfacing with
+// code that needs X18 to be preserved.
+def CSR_AArch64_AAPCS_X18 : CalleeSavedRegs<(add X18, CSR_AArch64_AAPCS)>;
+
 // Win64 has unwinding codes for an (FP,LR) pair, save_fplr and save_fplr_x.
 // We put FP before LR, so that frame lowering logic generates (FP,LR) pairs,
 // and not (LR,FP) pairs.
diff --git a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
--- a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -2389,6 +2389,7 @@
   TargetFrameLowering::determineCalleeSaves(MF, SavedRegs, RS);
   const AArch64RegisterInfo *RegInfo = static_cast<const AArch64RegisterInfo *>(
       MF.getSubtarget().getRegisterInfo());
+  const AArch64Subtarget &Subtarget = MF.getSubtarget<AArch64Subtarget>();
   AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
   unsigned UnspilledCSGPR = AArch64::NoRegister;
   unsigned UnspilledCSGPRPaired = AArch64::NoRegister;
@@ -2437,6 +2438,16 @@
     }
   }
 
+  if (MF.getFunction().getCallingConv() == CallingConv::Win64 &&
+      !Subtarget.isTargetWindows()) {
+    // For Windows calling convention on a non-windows OS, where X18 is treated
+    // as reserved, back up X18 when entering non-windows code (marked with the
+    // Windows calling convention) and restore when returning regardless of
+    // whether the individual function uses it - it might call other functions
+    // that clobber it.
+    SavedRegs.set(AArch64::X18);
+  }
+
   // Calculates the callee saved stack size.
   unsigned CSStackSize = 0;
   unsigned SVECSStackSize = 0;
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -3958,6 +3958,13 @@
   CallingConv::ID CallerCC = CallerF.getCallingConv();
   bool CCMatch = CallerCC == CalleeCC;
 
+  // When using the Windows calling convention on a non-windows OS, we want
+  // to back up and restore X18 in such functions; we can't do a tail call
+  // from those functions.
+  if (CallerCC == CallingConv::Win64 && !Subtarget->isTargetWindows() &&
+      CalleeCC != CallingConv::Win64)
+    return false;
+
   // Byval parameters hand the function a pointer directly into the stack area
   // we want to reuse during a tail call. Working around this *is* possible (see
   // X86) but less efficient and uglier in LowerCall.
diff --git a/llvm/lib/Target/AArch64/AArch64RegisterInfo.cpp b/llvm/lib/Target/AArch64/AArch64RegisterInfo.cpp
--- a/llvm/lib/Target/AArch64/AArch64RegisterInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64RegisterInfo.cpp
@@ -71,6 +71,10 @@
     return CSR_AArch64_AAPCS_SwiftError_SaveList;
   if (MF->getFunction().getCallingConv() == CallingConv::PreserveMost)
     return CSR_AArch64_RT_MostRegs_SaveList;
+  if (MF->getFunction().getCallingConv() == CallingConv::Win64)
+    // This is for OSes other than Windows; Windows is a separate case further
+    // above.
+    return CSR_AArch64_AAPCS_X18_SaveList;
   return CSR_AArch64_AAPCS_SaveList;
 }
 
diff --git a/llvm/test/CodeGen/AArch64/aarch64_win64cc_vararg.ll b/llvm/test/CodeGen/AArch64/aarch64_win64cc_vararg.ll
--- a/llvm/test/CodeGen/AArch64/aarch64_win64cc_vararg.ll
+++ b/llvm/test/CodeGen/AArch64/aarch64_win64cc_vararg.ll
@@ -2,16 +2,18 @@
 
 define win64cc void @pass_va(i32 %count, ...) nounwind {
 entry:
-; CHECK: str     x30, [sp, #-80]!
-; CHECK: add     x8, sp, #24
-; CHECK: add     x0, sp, #24
-; CHECK: stp     x1, x2, [sp, #24]
-; CHECK: stp     x3, x4, [sp, #40]
-; CHECK: stp     x5, x6, [sp, #56]
-; CHECK: str     x7, [sp, #72]
+; CHECK: sub     sp, sp, #96
+; CHECK: add     x8, sp, #40
+; CHECK: add     x0, sp, #40
+; CHECK: stp     x30, x18, [sp, #16]
+; CHECK: stp     x1, x2, [sp, #40]
+; CHECK: stp     x3, x4, [sp, #56]
+; CHECK: stp     x5, x6, [sp, #72]
+; CHECK: str     x7, [sp, #88]
 ; CHECK: str     x8, [sp, #8]
 ; CHECK: bl      other_func
-; CHECK: ldr     x30, [sp], #80
+; CHECK: ldp     x30, x18, [sp, #16]
+; CHECK: add     sp, sp, #96
 ; CHECK: ret
   %ap = alloca i8*, align 8
   %ap1 = bitcast i8** %ap to i8*
@@ -27,11 +29,11 @@
 declare void @llvm.va_copy(i8*, i8*) nounwind
 
 ; CHECK-LABEL: f9:
-; CHECK: sub     sp, sp, #16
+; CHECK: str     x18, [sp, #-16]!
 ; CHECK: add     x8, sp, #24
 ; CHECK: add     x0, sp, #24
 ; CHECK: str     x8, [sp, #8]
-; CHECK: add     sp, sp, #16
+; CHECK: ldr     x18, [sp], #16
 ; CHECK: ret
 define win64cc i8* @f9(i64 %a0, i64 %a1, i64 %a2, i64 %a3, i64 %a4, i64 %a5, i64 %a6, i64 %a7, i64 %a8, ...) nounwind {
 entry:
@@ -43,11 +45,11 @@
 }
 
 ; CHECK-LABEL: f8:
-; CHECK: sub     sp, sp, #16
+; CHECK: str     x18, [sp, #-16]!
 ; CHECK: add     x8, sp, #16
 ; CHECK: add     x0, sp, #16
 ; CHECK: str     x8, [sp, #8]
-; CHECK: add     sp, sp, #16
+; CHECK: ldr     x18, [sp], #16
 ; CHECK: ret
 define win64cc i8* @f8(i64 %a0, i64 %a1, i64 %a2, i64 %a3, i64 %a4, i64 %a5, i64 %a6, i64 %a7, ...) nounwind {
 entry:
@@ -59,12 +61,12 @@
 }
 
 ; CHECK-LABEL: f7:
-; CHECK: sub     sp, sp, #32
+; CHECK: str     x18, [sp, #-32]!
 ; CHECK: add     x8, sp, #24
 ; CHECK: str     x7, [sp, #24]
 ; CHECK: add     x0, sp, #24
 ; CHECK: str     x8, [sp, #8]
-; CHECK: add     sp, sp, #32
+; CHECK: ldr     x18, [sp], #32
 ; CHECK: ret
 define win64cc i8* @f7(i64 %a0, i64 %a1, i64 %a2, i64 %a3, i64 %a4, i64 %a5, i64 %a6, ...) nounwind {
 entry:
diff --git a/llvm/test/CodeGen/AArch64/win64cc-backup-x18.ll b/llvm/test/CodeGen/AArch64/win64cc-backup-x18.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/win64cc-backup-x18.ll
@@ -0,0 +1,26 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+
+;; Testing that x18 is backed up and restored, and that x29 (if used) still
+;; points to the x29,x30 pair on the stack.
+
+; RUN: llc < %s -mtriple=aarch64-linux-gnu --frame-pointer=non-leaf | FileCheck %s
+; RUN: llc < %s -mtriple=aarch64-linux-gnu --frame-pointer=non-leaf -mattr=+reserve-x18 | FileCheck %s
+
+declare dso_local void @other()
+
+define dso_local win64cc void @func() #0 {
+; CHECK-LABEL: func:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
+; CHECK-NEXT:    str x18, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    mov x29, sp
+; CHECK-NEXT:    bl other
+; CHECK-NEXT:    ldr x18, [sp, #16] // 8-byte Folded Reload
+; CHECK-NEXT:    ldp x29, x30, [sp], #32 // 16-byte Folded Reload
+; CHECK-NEXT:    ret
+entry:
+  tail call void @other()
+  ret void
+}
+
+attributes #0 = { nounwind }