mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 20:23:11 +01:00
8920d6a40a
Summary: First patch to support Safe Whole Program Devirtualization Enablement, see RFC here: http://lists.llvm.org/pipermail/llvm-dev/2019-December/137543.html Always emit !vcall_visibility metadata under -fwhole-program-vtables, and not just for -fvirtual-function-elimination. The vcall visibility metadata will (in a subsequent patch) be used to communicate to WPD which vtables are safe to devirtualize, and we will optionally convert the metadata to hidden visibility at link time. Subsequent follow on patches will help enable this by adding vcall_visibility metadata to the ThinLTO summaries, and always emit type test intrinsics under -fwhole-program-vtables (and not just for vtables with hidden visibility). In order to do this safely with VFE, since for VFE all vtable loads must be type checked loads which will no longer be the case, this patch adds a new "Virtual Function Elim" module flag to communicate to GlobalDCE whether to perform VFE using the vcall_visibility metadata. One additional advantage of using the vcall_visibility metadata to drive more WPD at LTO link time is that we can use the same mechanism to enable more aggressive VFE at LTO link time as well. The link time option proposed in the RFC will convert vcall_visibility metadata to hidden (aka linkage unit visibility), which combined with -fvirtual-function-elimination will allow it to be done more aggressively at LTO link time under the same conditions. Reviewers: pcc, ostannard, evgeny777, steven_wu Subscribers: mehdi_amini, Prazek, hiraditya, dexonsmith, davidxl, cfe-commits, llvm-commits Tags: #clang, #llvm Differential Revision: https://reviews.llvm.org/D71907
59 lines
2.6 KiB
LLVM
59 lines
2.6 KiB
LLVM
; RUN: opt < %s -globaldce -S | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
|
|
declare dso_local noalias nonnull i8* @_Znwm(i64)
|
|
declare { i8*, i1 } @llvm.type.checked.load(i8*, i32, metadata)
|
|
|
|
; %struct.A is a C++ struct with two virtual functions, A::foo and A::bar. The
|
|
; !vcall_visibility metadata is set on the vtable, so we know that all virtual
|
|
; calls through this vtable are visible and use the @llvm.type.checked.load
|
|
; intrinsic. Function test_A makes a call to A::foo, but there is no call to
|
|
; A::bar anywhere, so A::bar can be deleted, and its vtable slot replaced with
|
|
; null.
|
|
|
|
%struct.A = type { i32 (...)** }
|
|
|
|
; The pointer to A::bar in the vtable can be removed, because it will never be
|
|
; loaded. We replace it with null to keep the layout the same. Because it is at
|
|
; the end of the vtable we could potentially shrink the vtable, but don't
|
|
; currently do that.
|
|
; CHECK: @_ZTV1A = internal unnamed_addr constant { [4 x i8*] } { [4 x i8*] [i8* null, i8* null, i8* bitcast (i32 (%struct.A*)* @_ZN1A3fooEv to i8*), i8* null] }
|
|
@_ZTV1A = internal unnamed_addr constant { [4 x i8*] } { [4 x i8*] [i8* null, i8* null, i8* bitcast (i32 (%struct.A*)* @_ZN1A3fooEv to i8*), i8* bitcast (i32 (%struct.A*)* @_ZN1A3barEv to i8*)] }, align 8, !type !0, !type !1, !type !2, !vcall_visibility !3
|
|
|
|
; A::foo is called, so must be retained.
|
|
; CHECK: define internal i32 @_ZN1A3fooEv(
|
|
define internal i32 @_ZN1A3fooEv(%struct.A* nocapture readnone %this) {
|
|
entry:
|
|
ret i32 42
|
|
}
|
|
|
|
; A::bar is not used, so can be deleted.
|
|
; CHECK-NOT: define internal i32 @_ZN1A3barEv(
|
|
define internal i32 @_ZN1A3barEv(%struct.A* nocapture readnone %this) {
|
|
entry:
|
|
ret i32 1337
|
|
}
|
|
|
|
define dso_local i32 @test_A() {
|
|
entry:
|
|
%call = tail call i8* @_Znwm(i64 8)
|
|
%0 = bitcast i8* %call to %struct.A*
|
|
%1 = bitcast i8* %call to i32 (...)***
|
|
store i32 (...)** bitcast (i8** getelementptr inbounds ({ [4 x i8*] }, { [4 x i8*] }* @_ZTV1A, i64 0, inrange i32 0, i64 2) to i32 (...)**), i32 (...)*** %1, align 8
|
|
%2 = tail call { i8*, i1 } @llvm.type.checked.load(i8* bitcast (i8** getelementptr inbounds ({ [4 x i8*] }, { [4 x i8*] }* @_ZTV1A, i64 0, inrange i32 0, i64 2) to i8*), i32 0, metadata !"_ZTS1A"), !nosanitize !9
|
|
%3 = extractvalue { i8*, i1 } %2, 0, !nosanitize !9
|
|
%4 = bitcast i8* %3 to i32 (%struct.A*)*, !nosanitize !9
|
|
%call1 = tail call i32 %4(%struct.A* nonnull %0)
|
|
ret i32 %call1
|
|
}
|
|
|
|
!llvm.module.flags = !{!4}
|
|
|
|
!0 = !{i64 16, !"_ZTS1A"}
|
|
!1 = !{i64 16, !"_ZTSM1AFivE.virtual"}
|
|
!2 = !{i64 24, !"_ZTSM1AFivE.virtual"}
|
|
!3 = !{i64 2}
|
|
!4 = !{i32 1, !"Virtual Function Elim", i32 1}
|
|
!9 = !{}
|