[MemCpyOpt] Add additional call slot tests (NFC)

The case of a destination read between call and memcpy was not
covered anywhere (but is handled correctly).

However, a potentially throwing call between the call and the
memcpy appears to be miscompiled.

Author: nikic

llvm/test/Transforms/MemCpyOpt/callslot.ll

@@ -0,0 +1,91 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -S -memcpyopt < %s | FileCheck %s
+
+define i8 @read_dest_between_call_and_memcpy() {
+; CHECK-LABEL: @read_dest_between_call_and_memcpy(
+; CHECK-NEXT:    [[DEST:%.*]] = alloca i8, i64 16, align 1
+; CHECK-NEXT:    [[SRC:%.*]] = alloca i8, i64 16, align 1
+; CHECK-NEXT:    store i8 1, i8* [[DEST]], align 1
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* [[SRC]], i8 0, i64 16, i1 false)
+; CHECK-NEXT:    [[X:%.*]] = load i8, i8* [[DEST]], align 1
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* [[DEST]], i8 0, i64 16, i1 false)
+; CHECK-NEXT:    ret i8 [[X]]
+;
+  %dest = alloca i8, i64 16
+  %src = alloca i8, i64 16
+  store i8 1, i8* %dest
+  call void @llvm.memset.p0i8.i64(i8* %src, i8 0, i64 16, i1 false)
+  %x = load i8, i8* %dest
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dest, i8* %src, i64 16, i1 false)
+  ret i8 %x
+}
+
+define i8 @read_src_between_call_and_memcpy() {
+; CHECK-LABEL: @read_src_between_call_and_memcpy(
+; CHECK-NEXT:    [[DEST:%.*]] = alloca i8, i64 16, align 1
+; CHECK-NEXT:    [[SRC:%.*]] = alloca i8, i64 16, align 1
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* [[SRC]], i8 0, i64 16, i1 false)
+; CHECK-NEXT:    [[X:%.*]] = load i8, i8* [[SRC]], align 1
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[DEST]], i8* [[SRC]], i64 16, i1 false)
+; CHECK-NEXT:    ret i8 [[X]]
+;
+  %dest = alloca i8, i64 16
+  %src = alloca i8, i64 16
+  call void @llvm.memset.p0i8.i64(i8* %src, i8 0, i64 16, i1 false)
+  %x = load i8, i8* %src
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dest, i8* %src, i64 16, i1 false)
+  ret i8 %x
+}
+
+define void @write_dest_between_call_and_memcpy() {
+; CHECK-LABEL: @write_dest_between_call_and_memcpy(
+; CHECK-NEXT:    [[DEST:%.*]] = alloca i8, i64 16, align 1
+; CHECK-NEXT:    [[SRC:%.*]] = alloca i8, i64 16, align 1
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* [[SRC]], i8 0, i64 16, i1 false)
+; CHECK-NEXT:    store i8 1, i8* [[DEST]], align 1
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* [[DEST]], i8 0, i64 16, i1 false)
+; CHECK-NEXT:    ret void
+;
+  %dest = alloca i8, i64 16
+  %src = alloca i8, i64 16
+  call void @llvm.memset.p0i8.i64(i8* %src, i8 0, i64 16, i1 false)
+  store i8 1, i8* %dest
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dest, i8* %src, i64 16, i1 false)
+  ret void
+}
+
+define void @write_src_between_call_and_memcpy() {
+; CHECK-LABEL: @write_src_between_call_and_memcpy(
+; CHECK-NEXT:    [[DEST:%.*]] = alloca i8, i64 16, align 1
+; CHECK-NEXT:    [[SRC:%.*]] = alloca i8, i64 16, align 1
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* [[SRC]], i8 0, i64 16, i1 false)
+; CHECK-NEXT:    store i8 1, i8* [[SRC]], align 1
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[DEST]], i8* [[SRC]], i64 16, i1 false)
+; CHECK-NEXT:    ret void
+;
+  %dest = alloca i8, i64 16
+  %src = alloca i8, i64 16
+  call void @llvm.memset.p0i8.i64(i8* %src, i8 0, i64 16, i1 false)
+  store i8 1, i8* %src
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dest, i8* %src, i64 16, i1 false)
+  ret void
+}
+
+; TODO: This is a miscompile.
+define void @throw_between_call_and_mempy(i8* dereferenceable(16) %dest) {
+; CHECK-LABEL: @throw_between_call_and_mempy(
+; CHECK-NEXT:    [[SRC:%.*]] = alloca i8, i64 16, align 1
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* [[DEST:%.*]], i8 0, i64 16, i1 false)
+; CHECK-NEXT:    call void @may_throw() [[ATTR2:#.*]]
+; CHECK-NEXT:    ret void
+;
+  %src = alloca i8, i64 16
+  call void @llvm.memset.p0i8.i64(i8* %src, i8 0, i64 16, i1 false)
+  call void @may_throw() readnone
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dest, i8* %src, i64 16, i1 false)
+  ret void
+}
+
+declare void @may_throw()
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8*, i8*, i64, i1)
+declare void @llvm.memset.p0i8.i64(i8*, i8, i64, i1)