Add tests for preallocated + musttail

[aeubanks]

Summary

Follow-up to https://reviews.llvm.org/D80581.
Turns out the codegen part already worked, so only needed to add tests.
I manually verified that in these tests the generated code for inalloca
and preallocated were identical.

[hans]

lgtm

llvm/test/CodeGen/X86/musttail-indirect.ll

 ; int  (B::*mp_g)(A, int, A) = &B::g;
 ; void (B::*mp_h)(A, int, A) = &B::h;
 ; A    (B::*mp_i)(A, int, A) = &B::i;
 ; A    (B::*mp_j)(int)       = &B::j;
 
 ; Each member pointer creates a thunk.  The ones with inalloca are required to
 ; tail calls by the ABI, even at O0.
 
-; TODO: add tests for preallocated/musttail once supported
-
 %struct.B = type { i32 (...)** }
 %struct.A = type { i32 }
 
 ; CHECK-LABEL: f_thunk:
 ; CHECK: jmpl
 ; CHECK-NOT: ret
 define x86_thiscallcc i32 @f_thunk(%struct.B* %this, i32) {
 entry:
entry:
   %1 = bitcast %struct.B* %this to i32 (%struct.B*, <{ %struct.A, i32, %struct.A }>*)***
   %vtable = load i32 (%struct.B*, <{ %struct.A, i32, %struct.A }>*)**, i32 (%struct.B*, <{ %struct.A, i32, %struct.A }>*)*** %1
   %vfn = getelementptr inbounds i32 (%struct.B*, <{ %struct.A, i32, %struct.A }>*)*, i32 (%struct.B*, <{ %struct.A, i32, %struct.A }>*)** %vtable, i32 1
   %2 = load i32 (%struct.B*, <{ %struct.A, i32, %struct.A }>*)*, i32 (%struct.B*, <{ %struct.A, i32, %struct.A }>*)** %vfn
   %3 = musttail call x86_thiscallcc i32 %2(%struct.B* %this, <{ %struct.A, i32, %struct.A }>* inalloca %0)
   ret i32 %3
 }
 
+; Preallocated thunks shouldn't require any stores to the stack.
+; CHECK-LABEL: g_thunk_preallocated:
+; CHECK-NOT: mov %{{.*}}, {{.*(.*esp.*)}}
+; CHECK: jmpl
+; CHECK-NOT: ret
+define x86_thiscallcc i32 @g_thunk_preallocated(%struct.B* %this, <{ %struct.A, i32, %struct.A }>* preallocated(<{ %struct.A, i32, %struct.A }>)) {
+entry:
+  %1 = bitcast %struct.B* %this to i32 (%struct.B*, <{ %struct.A, i32, %struct.A }>*)***
+  %vtable = load i32 (%struct.B*, <{ %struct.A, i32, %struct.A }>*)**, i32 (%struct.B*, <{ %struct.A, i32, %struct.A }>*)*** %1
+  %vfn = getelementptr inbounds i32 (%struct.B*, <{ %struct.A, i32, %struct.A }>*)*, i32 (%struct.B*, <{ %struct.A, i32, %struct.A }>*)** %vtable, i32 1
+  %2 = load i32 (%struct.B*, <{ %struct.A, i32, %struct.A }>*)*, i32 (%struct.B*, <{ %struct.A, i32, %struct.A }>*)** %vfn
+  %3 = musttail call x86_thiscallcc i32 %2(%struct.B* %this, <{ %struct.A, i32, %struct.A }>* preallocated(<{ %struct.A, i32, %struct.A }>) %0)
+  ret i32 %3
+}
+
 ; CHECK-LABEL: h_thunk:
 ; CHECK: jmpl
 ; CHECK-NOT: mov %{{.*}}, {{.*(.*esp.*)}}
 ; CHECK-NOT: ret
 define x86_thiscallcc void @h_thunk(%struct.B* %this, <{ %struct.A, i32, %struct.A }>* inalloca) {
 entry:
   %1 = bitcast %struct.B* %this to void (%struct.B*, <{ %struct.A, i32, %struct.A }>*)***
   %vtable = load void (%struct.B*, <{ %struct.A, i32, %struct.A }>*)**, void (%struct.B*, <{ %struct.A, i32, %struct.A }>*)*** %1
   %vfn = getelementptr inbounds void (%struct.B*, <{ %struct.A, i32, %struct.A }>*)*, void (%struct.B*, <{ %struct.A, i32, %struct.A }>*)** %vtable, i32 2
   %2 = load void (%struct.B*, <{ %struct.A, i32, %struct.A }>*)*, void (%struct.B*, <{ %struct.A, i32, %struct.A }>*)** %vfn
   musttail call x86_thiscallcc void %2(%struct.B* %this, <{ %struct.A, i32, %struct.A }>* inalloca %0)
   ret void
 }
 
+; CHECK-LABEL: h_thunk_preallocated:
+; CHECK: jmpl
+; CHECK-NOT: mov %{{.*}}, {{.*(.*esp.*)}}
+; CHECK-NOT: ret
+define x86_thiscallcc void @h_thunk_preallocated(%struct.B* %this, <{ %struct.A, i32, %struct.A }>* preallocated(<{ %struct.A, i32, %struct.A }>)) {
+entry:
+  %1 = bitcast %struct.B* %this to void (%struct.B*, <{ %struct.A, i32, %struct.A }>*)***
+  %vtable = load void (%struct.B*, <{ %struct.A, i32, %struct.A }>*)**, void (%struct.B*, <{ %struct.A, i32, %struct.A }>*)*** %1
+  %vfn = getelementptr inbounds void (%struct.B*, <{ %struct.A, i32, %struct.A }>*)*, void (%struct.B*, <{ %struct.A, i32, %struct.A }>*)** %vtable, i32 2
+  %2 = load void (%struct.B*, <{ %struct.A, i32, %struct.A }>*)*, void (%struct.B*, <{ %struct.A, i32, %struct.A }>*)** %vfn
+  musttail call x86_thiscallcc void %2(%struct.B* %this, <{ %struct.A, i32, %struct.A }>* preallocated(<{ %struct.A, i32, %struct.A }>) %0)
+  ret void
+}
+
 ; CHECK-LABEL: i_thunk:
 ; CHECK-NOT: mov %{{.*}}, {{.*(.*esp.*)}}
 ; CHECK: jmpl
 ; CHECK-NOT: ret
 define x86_thiscallcc %struct.A* @i_thunk(%struct.B* %this, <{ %struct.A*, %struct.A, i32, %struct.A }>* inalloca) {
 entry:
   %1 = bitcast %struct.B* %this to %struct.A* (%struct.B*, <{ %struct.A*, %struct.A, i32, %struct.A }>*)***
   %vtable = load %struct.A* (%struct.B*, <{ %struct.A*, %struct.A, i32, %struct.A }>*)**, %struct.A* (%struct.B*, <{ %struct.A*, %struct.A, i32, %struct.A }>*)*** %1
   %vfn = getelementptr inbounds %struct.A* (%struct.B*, <{ %struct.A*, %struct.A, i32, %struct.A }>*)*, %struct.A* (%struct.B*, <{ %struct.A*, %struct.A, i32, %struct.A }>*)** %vtable, i32 3
   %2 = load %struct.A* (%struct.B*, <{ %struct.A*, %struct.A, i32, %struct.A }>*)*, %struct.A* (%struct.B*, <{ %struct.A*, %struct.A, i32, %struct.A }>*)** %vfn
   %3 = musttail call x86_thiscallcc %struct.A* %2(%struct.B* %this, <{ %struct.A*, %struct.A, i32, %struct.A }>* inalloca %0)
   ret %struct.A* %3
 }
 
+; CHECK-LABEL: i_thunk_preallocated:
+; CHECK-NOT: mov %{{.*}}, {{.*(.*esp.*)}}
+; CHECK: jmpl
+; CHECK-NOT: ret
+define x86_thiscallcc %struct.A* @i_thunk_preallocated(%struct.B* %this, <{ %struct.A*, %struct.A, i32, %struct.A }>* preallocated(<{ %struct.A*, %struct.A, i32, %struct.A }>)) {
+entry:
+  %1 = bitcast %struct.B* %this to %struct.A* (%struct.B*, <{ %struct.A*, %struct.A, i32, %struct.A }>*)***
+  %vtable = load %struct.A* (%struct.B*, <{ %struct.A*, %struct.A, i32, %struct.A }>*)**, %struct.A* (%struct.B*, <{ %struct.A*, %struct.A, i32, %struct.A }>*)*** %1
+  %vfn = getelementptr inbounds %struct.A* (%struct.B*, <{ %struct.A*, %struct.A, i32, %struct.A }>*)*, %struct.A* (%struct.B*, <{ %struct.A*, %struct.A, i32, %struct.A }>*)** %vtable, i32 3
+  %2 = load %struct.A* (%struct.B*, <{ %struct.A*, %struct.A, i32, %struct.A }>*)*, %struct.A* (%struct.B*, <{ %struct.A*, %struct.A, i32, %struct.A }>*)** %vfn
+  %3 = musttail call x86_thiscallcc %struct.A* %2(%struct.B* %this, <{ %struct.A*, %struct.A, i32, %struct.A }>* preallocated(<{ %struct.A*, %struct.A, i32, %struct.A }>) %0)
+  ret %struct.A* %3
+}
+
 ; CHECK-LABEL: j_thunk:
 ; CHECK: jmpl
 ; CHECK-NOT: ret
 define x86_thiscallcc void @j_thunk(%struct.A* noalias sret %agg.result, %struct.B* %this, i32) {
 entry:
   %1 = bitcast %struct.B* %this to void (%struct.A*, %struct.B*, i32)***
   %vtable = load void (%struct.A*, %struct.B*, i32)**, void (%struct.A*, %struct.B*, i32)*** %1
   %vfn = getelementptr inbounds void (%struct.A*, %struct.B*, i32)*, void (%struct.A*, %struct.B*, i32)** %vtable, i32 4
entry:
   %1 = bitcast %struct.B* %this to i32 (<{ %struct.B*, %struct.A }>*)***
   %vtable = load i32 (<{ %struct.B*, %struct.A }>*)**, i32 (<{ %struct.B*, %struct.A }>*)*** %1
   %vfn = getelementptr inbounds i32 (<{ %struct.B*, %struct.A }>*)*, i32 (<{ %struct.B*, %struct.A }>*)** %vtable, i32 1
   %2 = load i32 (<{ %struct.B*, %struct.A }>*)*, i32 (<{ %struct.B*, %struct.A }>*)** %vfn
   %3 = musttail call x86_stdcallcc i32 %2(<{ %struct.B*, %struct.A }>* inalloca %0)
   ret i32 %3
 }
 
+; CHECK-LABEL: _stdcall_thunk_preallocated@8:
+; CHECK-NOT: mov %{{.*}}, {{.*(.*esp.*)}}
+; CHECK: jmpl
+; CHECK-NOT: ret
+define x86_stdcallcc i32 @stdcall_thunk_preallocated(<{ %struct.B*, %struct.A }>* preallocated(<{ %struct.B*, %struct.A }>)) {
+entry:
+  %this_ptr = getelementptr inbounds <{ %struct.B*, %struct.A }>, <{ %struct.B*, %struct.A }>* %0, i32 0, i32 0
+  %this = load %struct.B*, %struct.B** %this_ptr
+  %1 = bitcast %struct.B* %this to i32 (<{ %struct.B*, %struct.A }>*)***
+  %vtable = load i32 (<{ %struct.B*, %struct.A }>*)**, i32 (<{ %struct.B*, %struct.A }>*)*** %1
+  %vfn = getelementptr inbounds i32 (<{ %struct.B*, %struct.A }>*)*, i32 (<{ %struct.B*, %struct.A }>*)** %vtable, i32 1
+  %2 = load i32 (<{ %struct.B*, %struct.A }>*)*, i32 (<{ %struct.B*, %struct.A }>*)** %vfn
+  %3 = musttail call x86_stdcallcc i32 %2(<{ %struct.B*, %struct.A }>* preallocated(<{ %struct.B*, %struct.A }>) %0)
+  ret i32 %3
+}
+
 ; CHECK-LABEL: @fastcall_thunk@8:
 ; CHECK-NOT: mov %{{.*}}, {{.*(.*esp.*)}}
 ; CHECK: jmpl
 ; CHECK-NOT: ret
 define x86_fastcallcc i32 @fastcall_thunk(%struct.B* inreg %this, <{ %struct.A }>* inalloca) {
 entry:
   %1 = bitcast %struct.B* %this to i32 (%struct.B*, <{ %struct.A }>*)***
   %vtable = load i32 (%struct.B*, <{ %struct.A }>*)**, i32 (%struct.B*, <{ %struct.A }>*)*** %1
   %vfn = getelementptr inbounds i32 (%struct.B*, <{ %struct.A }>*)*, i32 (%struct.B*, <{ %struct.A }>*)** %vtable, i32 1
   %2 = load i32 (%struct.B*, <{ %struct.A }>*)*, i32 (%struct.B*, <{ %struct.A }>*)** %vfn
   %3 = musttail call x86_fastcallcc i32 %2(%struct.B* inreg %this, <{ %struct.A }>* inalloca %0)
   ret i32 %3
 }
+
+; CHECK-LABEL: @fastcall_thunk_preallocated@8:
+; CHECK-NOT: mov %{{.*}}, {{.*(.*esp.*)}}
+; CHECK: jmpl
+; CHECK-NOT: ret
+define x86_fastcallcc i32 @fastcall_thunk_preallocated(%struct.B* inreg %this, <{ %struct.A }>* preallocated(<{ %struct.A }>)) {
+entry:
+  %1 = bitcast %struct.B* %this to i32 (%struct.B*, <{ %struct.A }>*)***
+  %vtable = load i32 (%struct.B*, <{ %struct.A }>*)**, i32 (%struct.B*, <{ %struct.A }>*)*** %1
+  %vfn = getelementptr inbounds i32 (%struct.B*, <{ %struct.A }>*)*, i32 (%struct.B*, <{ %struct.A }>*)** %vtable, i32 1
+  %2 = load i32 (%struct.B*, <{ %struct.A }>*)*, i32 (%struct.B*, <{ %struct.A }>*)** %vfn
+  %3 = musttail call x86_fastcallcc i32 %2(%struct.B* inreg %this, <{ %struct.A }>* preallocated(<{ %struct.A }>) %0)
+  ret i32 %3
+}

llvm/test/CodeGen/X86/musttail-thiscall.ll

 ; RUN: llc -verify-machineinstrs -mtriple=i686-- < %s | FileCheck %s
 ; RUN: llc -verify-machineinstrs -mtriple=i686-- -O0 < %s | FileCheck %s
 
-; TODO: add tests for preallocated/musttail once supported
-
 ; CHECK-LABEL: t1:
 ; CHECK: jmp {{_?}}t1_callee
 define x86_thiscallcc void @t1(i8* %this) {
   %adj = getelementptr i8, i8* %this, i32 4
   musttail call x86_thiscallcc void @t1_callee(i8* %adj)
   ret void
 }
 declare x86_thiscallcc void @t1_callee(i8* %this)

 define x86_thiscallcc i8* @t3(i8* %this, <{ i8*, i32 }>* inalloca %args) {
   %adj = getelementptr i8, i8* %this, i32 4
   %a_ptr = getelementptr <{ i8*, i32 }>, <{ i8*, i32 }>* %args, i32 0, i32 1
   store i32 0, i32* %a_ptr
   %rv = musttail call x86_thiscallcc i8* @t3_callee(i8* %adj, <{ i8*, i32 }>* inalloca %args)
   ret i8* %rv
 }
 declare x86_thiscallcc i8* @t3_callee(i8* %this, <{ i8*, i32 }>* inalloca %args);
+
+; CHECK-LABEL: t4:
+; CHECK: jmp {{_?}}t4_callee
+define x86_thiscallcc i8* @t4(i8* %this, <{ i8*, i32 }>* preallocated(<{ i8*, i32 }>) %args) {
+  %adj = getelementptr i8, i8* %this, i32 4
+  %a_ptr = getelementptr <{ i8*, i32 }>, <{ i8*, i32 }>* %args, i32 0, i32 1
+  store i32 0, i32* %a_ptr
+  %rv = musttail call x86_thiscallcc i8* @t4_callee(i8* %adj, <{ i8*, i32 }>* preallocated(<{ i8*, i32 }>) %args)
+  ret i8* %rv
+}
+declare x86_thiscallcc i8* @t4_callee(i8* %this, <{ i8*, i32 }>* preallocated(<{ i8*, i32 }>) %args);