[llvm] x86: fix musttail sibcall miscompilation (PR #168956)

[Folkert de Vries via llvm-commits]

================
@@ -0,0 +1,88 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -x86-asm-syntax=intel | FileCheck %s
+; ; RUN: llc < %s -mtriple=i686-unknown-unknown | FileCheck %s
+
+; Test correct handling of a musttail call with a byval struct argument.
+
+%struct.1xi32 = type { [1 x i32] }
+%struct.3xi32 = type { [3 x i32] }
+%struct.5xi32 = type { [5 x i32] }
+
+declare dso_local i32 @Func1(ptr byval(%struct.1xi32) %0)
+declare dso_local i32 @Func3(ptr byval(%struct.3xi32) %0)
+declare dso_local i32 @Func5(ptr byval(%struct.5xi32) %0)
+declare dso_local i32 @FuncManyArgs(i32 %0, i32 %1, i32 %2, i32 %3, i32 %4, i32 %5, i8 %6, ptr byval(%struct.5xi32) %7)
+
+define dso_local i32 @test1(ptr byval(%struct.1xi32) %0) {
+; CHECK-LABEL: test1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    jmp Func1 # TAILCALL
+  %r = musttail call i32 @Func1(ptr byval(%struct.1xi32) %0)
+  ret i32 %r
+}
+
+define dso_local i32 @test3(ptr byval(%struct.3xi32) %0) {
+; CHECK-LABEL: test3:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    jmp Func3 # TAILCALL
+  %r = musttail call i32 @Func3(ptr byval(%struct.3xi32) %0)
+  ret i32 %r
+}
+
+; sizeof(%struct.5xi32) > 16, in x64 this is passed on stack.
+define dso_local i32 @test5(ptr byval(%struct.5xi32) %0) {
+; CHECK-LABEL: test5:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    jmp Func5 # TAILCALL
+  %r = musttail call i32 @Func5(ptr byval(%struct.5xi32) %0)
+  ret i32 %r
+}
+
+; Test passing multiple arguments with different sizes on stack. In x64 Linux
+; the first 6 are passed by register.
+define dso_local i32 @testManyArgs(i32 %0, i32 %1, i32 %2, i32 %3, i32 %4, i32 %5, i8 %6, ptr byval(%struct.5xi32) %7) {
+; CHECK-LABEL: testManyArgs:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    jmp FuncManyArgs # TAILCALL
+  %r = musttail call i32 @FuncManyArgs(i32 %0, i32 %1, i32 %2, i32 %3, i32 %4, i32 %5, i8 %6, ptr byval(%struct.5xi32) %7)
+  ret i32 %r
+}
+
+define dso_local i32 @testRecursion(i32 %0, i32 %1, i32 %2, i32 %3, i32 %4, i32 %5, i8 %6, ptr byval(%struct.5xi32) %7) {
+; CHECK-LABEL: testRecursion:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    jmp testRecursion # TAILCALL
+  %r = musttail call i32 @testRecursion(i32 %0, i32 %1, i32 %2, i32 %3, i32 %4, i32 %5, i8 %6, ptr byval(%struct.5xi32) %7)
+  ret i32 %r
+}
+
+define dso_local i32 @swap(ptr byval(%struct.1xi32) %0, ptr byval(%struct.1xi32) %1) noinline {
+; CHECK-LABEL: swap:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    mov eax, dword ptr [rsp + 8]
+; CHECK-NEXT:    add eax, dword ptr [rsp + 16]
+; CHECK-NEXT:    ret
+entry:
+  %a.ptr = getelementptr inbounds %struct.1xi32, ptr %0, i32 0, i32 0, i32 0
+  %a     = load i32, ptr %a.ptr, align 4
+  %b.ptr = getelementptr inbounds %struct.1xi32, ptr %1, i32 0, i32 0, i32 0
+  %b     = load i32, ptr %b.ptr, align 4
+  %sum   = add i32 %a, %b
+  ret i32 %sum
+}
+
+define dso_local i32 @swapByValArguments(ptr byval(%struct.1xi32) %0, ptr byval(%struct.1xi32) %1) {
+; CHECK-LABEL: swapArguments:
+; CHECK:       # %bb.0:
+
+; CHECK-NEXT:    mov eax, dword ptr [rsp + 8]
+; CHECK-NEXT:    mov dword ptr [rsp - 16], eax
+; CHECK-NEXT:    mov ecx, dword ptr [rsp + 16]
+; CHECK-NEXT:    mov dword ptr [rsp - 8], ecx
+
+; CHECK-NEXT:    mov dword ptr [rsp + 8], ecx
+; CHECK-NEXT:    mov dword ptr [rsp + 16], eax
+; CHECK-NEXT:    jmp swap # TAILCALL
+  %r = musttail call i32 @swap(ptr byval(%struct.1xi32) %1, ptr byval(%struct.1xi32) %0)
+  ret i32 %r
+}
----------------
folkertdev wrote:

in this case the copy to the stack is not needed, there is sufficient register space. The arm logic doesn't seem to consider that case (likely because in practice by-val parameters are larger, and it's unlikely that there is sufficient space in register?)

https://github.com/llvm/llvm-project/pull/168956