[AArch64] Fix variadic tail-calls on ARM64EC

ARM64EC varargs calls expect that x4 = sp at entry, special handling is
needed to ensure this with tail calls since they occur after the
epilogue and the X4 write happens before.

Author: bylaws

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

@@ -7991,11 +7991,22 @@ AArch64TargetLowering::LowerCall(CallLoweringInfo &CLI,
   }
 
   if (IsVarArg && Subtarget->isWindowsArm64EC()) {
+    SDValue ParamPtr = StackPtr;
+    if (IsTailCall) {
+      const AArch64FrameLowering *TFI =
+          MF.getSubtarget<AArch64Subtarget>().getFrameLowering();
+
+      // Create a dummy object at the top of the stack that can be used to get
+      // the SP after the epilogue
+      int FI = MF.getFrameInfo().CreateFixedObject(1, FPDiff, true);
+      ParamPtr = DAG.getFrameIndex(FI, PtrVT);
+    }
+
     // For vararg calls, the Arm64EC ABI requires values in x4 and x5
     // describing the argument list.  x4 contains the address of the
     // first stack parameter. x5 contains the size in bytes of all parameters
     // passed on the stack.
-    RegsToPass.emplace_back(AArch64::X4, StackPtr);
+    RegsToPass.emplace_back(AArch64::X4, ParamPtr);
     RegsToPass.emplace_back(AArch64::X5,
                             DAG.getConstant(NumBytes, DL, MVT::i64));
   }

llvm/test/CodeGen/AArch64/vararg-tallcall.ll

@@ -1,5 +1,6 @@
 ; RUN: llc -mtriple=aarch64-windows-msvc %s -o - | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnu %s -o - | FileCheck %s
+; RUN: llc -mtriple=arm64ec-windows-msvc %s -o - | FileCheck %s --check-prefixes=CHECK-EC
 ; RUN: llc -global-isel -global-isel-abort=2 -verify-machineinstrs -mtriple=aarch64-windows-msvc %s -o - | FileCheck %s
 ; RUN: llc -global-isel -global-isel-abort=2 -verify-machineinstrs -mtriple=aarch64-linux-gnu %s -o - | FileCheck %s
 
@@ -32,3 +33,10 @@ attributes #1 = { noinline optnone "thunk" }
 ; CHECK: ldr     x9, [x9]
 ; CHECK: mov     v0.16b, v16.16b
 ; CHECK: br      x9
+; CHECK-EC: mov     v7.16b, v0.16b
+; CHECK-EC: ldr     x9, [x0]
+; CHECK-EC: ldr     x11, [x9]
+; CHECK-EC: mov     v0.16b, v7.16b
+; CHECK-EC: add     x4, sp, #64
+; CHECK-EC: add     sp, sp, #64
+; CHECK-EC: br      x11