diff --git a/lld/ELF/Config.h b/lld/ELF/Config.h --- a/lld/ELF/Config.h +++ b/lld/ELF/Config.h @@ -242,6 +242,7 @@ bool ltoDebugPassManager; bool ltoEmitAsm; bool ltoUniqueBasicBlockSectionNames; + bool ltoValidateAllVtablesHaveTypeInfos; bool ltoWholeProgramVisibility; bool mergeArmExidx; bool mipsN32Abi = false; @@ -467,6 +468,9 @@ std::atomic hasTlsIe{false}; // True if we need to reserve two .got entries for local-dynamic TLS model. std::atomic needsTlsLd{false}; + // True if all native vtable symbols have corresponding type info symbols + // during LTO. + bool ltoAllVtablesHaveTypeInfos; void reset(); diff --git a/lld/ELF/Driver.cpp b/lld/ELF/Driver.cpp --- a/lld/ELF/Driver.cpp +++ b/lld/ELF/Driver.cpp @@ -1021,6 +1021,63 @@ } } +template +static void ltoValidateAllVtablesHaveTypeInfos(opt::InputArgList &args) { + llvm::DenseSet typeInfoSymbols; + llvm::DenseSet vtableSymbols; + auto processVtableAndTypeInfoSymbols = [&](StringRef name) { + if (name.consume_front("_ZTI")) + typeInfoSymbols.insert(name); + else if (name.consume_front("_ZTV")) + vtableSymbols.insert(name); + }; + + // Examine all native symbol tables + for (ELFFileBase *f : ctx.objectFiles) { + using Elf_Sym = typename ELFT::Sym; + for (const Elf_Sym &s : f->template getGlobalELFSyms()) { + if (s.st_shndx != SHN_UNDEF) { + StringRef name = check(s.getName(f->getStringTable())); + processVtableAndTypeInfoSymbols(name); + } + } + } + + for (SharedFile *f : ctx.sharedFiles) { + using Elf_Sym = typename ELFT::Sym; + for (const Elf_Sym &s : f->template getELFSyms()) { + if (s.st_shndx != SHN_UNDEF) { + StringRef name = check(s.getName(f->getStringTable())); + processVtableAndTypeInfoSymbols(name); + } + } + } + + SmallSetVector vtableSymbolsWithNoRTTI; + for (auto &s : vtableSymbols) + if (!typeInfoSymbols.count(s)) + vtableSymbolsWithNoRTTI.insert(s); + + // Remove known safe symbols. + for (auto *arg : args.filtered(OPT_lto_known_safe_vtables)) { + StringRef knownSafeName = arg->getValue(); + if (!knownSafeName.consume_front("_ZTV")) + error("--lto-known-safe-vtables=: expected symbol to start with _ZTV, " + "but got " + + knownSafeName); + vtableSymbolsWithNoRTTI.remove(knownSafeName); + } + + ctx.ltoAllVtablesHaveTypeInfos = vtableSymbolsWithNoRTTI.empty(); + // Check for unmatched RTTI symbols + for (StringRef s : vtableSymbolsWithNoRTTI) { + message( + "--lto-validate-all-vtables-have-type-infos: RTTI missing for vtable " + "_ZTV" + + s + ", --lto-whole-program-visibility disabled"); + } +} + static DebugCompressionType getCompressionType(StringRef s, StringRef option) { DebugCompressionType type = StringSwitch(s) .Case("zlib", DebugCompressionType::Zlib) @@ -1216,6 +1273,9 @@ config->ltoWholeProgramVisibility = args.hasFlag(OPT_lto_whole_program_visibility, OPT_no_lto_whole_program_visibility, false); + config->ltoValidateAllVtablesHaveTypeInfos = + args.hasFlag(OPT_lto_validate_all_vtables_have_type_infos, + OPT_no_lto_validate_all_vtables_have_type_infos, false); config->ltoo = args::getInteger(args, OPT_lto_O, 2); if (config->ltoo > 3) error("invalid optimization level for LTO: " + Twine(config->ltoo)); @@ -2784,6 +2844,10 @@ config->ltoEmitAsm || !config->thinLTOModulesToCompile.empty(); + // Handle -lto-validate-all-vtables-had-type-infos + if (config->ltoValidateAllVtablesHaveTypeInfos) + invokeELFT(ltoValidateAllVtablesHaveTypeInfos, args); + // Do link-time optimization if given files are LLVM bitcode files. // This compiles bitcode files into real object files. // diff --git a/lld/ELF/LTO.cpp b/lld/ELF/LTO.cpp --- a/lld/ELF/LTO.cpp +++ b/lld/ELF/LTO.cpp @@ -152,6 +152,9 @@ c.DwoDir = std::string(config->dwoDir); c.HasWholeProgramVisibility = config->ltoWholeProgramVisibility; + c.ValidateAllVtablesHaveTypeInfos = + config->ltoValidateAllVtablesHaveTypeInfos; + c.AllVtablesHaveTypeInfos = ctx.ltoAllVtablesHaveTypeInfos; c.AlwaysEmitRegularLTOObj = !config->ltoObjPath.empty(); for (const llvm::StringRef &name : config->thinLTOModulesToCompile) diff --git a/lld/ELF/Options.td b/lld/ELF/Options.td --- a/lld/ELF/Options.td +++ b/lld/ELF/Options.td @@ -598,9 +598,13 @@ defm lto_pgo_warn_mismatch: BB<"lto-pgo-warn-mismatch", "turn on warnings about profile cfg mismatch (default)", "turn off warnings about profile cfg mismatch">; +defm lto_known_safe_vtables : EEq<"lto-known-safe-vtables", "When --lto-validate-all-vtables-have-type-infos is enabled, skip validation on these vtables">; def lto_obj_path_eq: JJ<"lto-obj-path=">; def lto_sample_profile: JJ<"lto-sample-profile=">, HelpText<"Sample profile file path">; +defm lto_validate_all_vtables_have_type_infos: BB<"lto-validate-all-vtables-have-type-infos", + "Validate that all vtables have type infos for LTO link", + "Do not validate that all vtables have type infos for LTO link">; defm lto_whole_program_visibility: BB<"lto-whole-program-visibility", "Asserts that the LTO link has whole program visibility", "Asserts that the LTO link does not have whole program visibility">; diff --git a/lld/test/ELF/lto/Inputs/devirt_validate_vtable_typeinfos.ll b/lld/test/ELF/lto/Inputs/devirt_validate_vtable_typeinfos.ll new file mode 100644 --- /dev/null +++ b/lld/test/ELF/lto/Inputs/devirt_validate_vtable_typeinfos.ll @@ -0,0 +1,26 @@ +; REQUIRES: x86 + +target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-unknown-linux-gnu" + +%struct.A = type { ptr } +%struct.Native = type { %struct.A } + +@_ZTV6Native = linkonce_odr unnamed_addr constant { [4 x ptr] } { [4 x ptr] [ptr null, ptr @_ZTI6Native, ptr @_ZN1A1nEi, ptr @_ZN6Native1fEi] } +@_ZTS6Native = linkonce_odr constant [8 x i8] c"6Native\00" +@_ZTI6Native = linkonce_odr constant { ptr, ptr, ptr } { ptr null, ptr @_ZTS6Native, ptr @_ZTI1A } + +; Base type A does not need to emit a vtable if it's never instantiated. However, RTTI still gets generated +@_ZTS1A = linkonce_odr constant [3 x i8] c"1A\00" +@_ZTI1A = linkonce_odr constant { ptr, ptr } { ptr null, ptr @_ZTS1A } + + +define linkonce_odr i32 @_ZN6Native1fEi(ptr %this, i32 %a) #0 { + ret i32 1; +} + +define linkonce_odr i32 @_ZN1A1nEi(ptr %this, i32 %a) #0 { + ret i32 0; +} + +attributes #0 = { noinline optnone } diff --git a/lld/test/ELF/lto/Inputs/devirt_validate_vtable_typeinfos_no_rtti.ll b/lld/test/ELF/lto/Inputs/devirt_validate_vtable_typeinfos_no_rtti.ll new file mode 100644 --- /dev/null +++ b/lld/test/ELF/lto/Inputs/devirt_validate_vtable_typeinfos_no_rtti.ll @@ -0,0 +1,19 @@ +; REQUIRES: x86 + +target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-unknown-linux-gnu" + +%struct.A = type { ptr } +%struct.Native = type { %struct.A } + +@_ZTV6Native = linkonce_odr unnamed_addr constant { [4 x ptr] } { [4 x ptr] [ptr null, ptr null, ptr @_ZN1A1nEi, ptr @_ZN6Native1fEi] } + +define linkonce_odr i32 @_ZN6Native1fEi(ptr %this, i32 %a) #0 { + ret i32 1; +} + +define linkonce_odr i32 @_ZN1A1nEi(ptr %this, i32 %a) #0 { + ret i32 0; +} + +attributes #0 = { noinline optnone } diff --git a/lld/test/ELF/lto/Inputs/devirt_validate_vtable_typeinfos_ref.ll b/lld/test/ELF/lto/Inputs/devirt_validate_vtable_typeinfos_ref.ll new file mode 100644 --- /dev/null +++ b/lld/test/ELF/lto/Inputs/devirt_validate_vtable_typeinfos_ref.ll @@ -0,0 +1,68 @@ +;; Source code: +;; cat > a.h <<'eof' +;; struct A { virtual int foo(); }; +;; int bar(A *a); +;; eof +;; cat > b.cc <<'eof' +;; #include "a.h" +;; struct B : A { int foo() { return 2; } }; +;; int baz() { B b; return bar(&b); } +;; eof +;; clang++ -flto=thin b.cc -c + +target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-unknown-linux-gnu" + +%struct.B = type { %struct.A } +%struct.A = type { ptr } + +@_ZTV1B = linkonce_odr dso_local unnamed_addr constant { [3 x ptr] } { [3 x ptr] [ptr null, ptr @_ZTI1B, ptr @_ZN1B3fooEv] }, !type !0, !type !1, !type !2, !type !3 +@_ZTS1B = linkonce_odr dso_local constant [3 x i8] c"1B\00" +@_ZTI1A = external constant ptr +@_ZTI1B = linkonce_odr dso_local constant { ptr, ptr, ptr } { ptr null, ptr @_ZTS1B, ptr @_ZTI1A } +@_ZTV1A = external unnamed_addr constant { [3 x ptr] } + +define dso_local noundef i32 @_Z3bazv() #0 { +entry: + %b = alloca %struct.B + call void @_ZN1BC2Ev(ptr noundef nonnull align 8 dereferenceable(8) %b) + %call = call noundef i32 @_Z3barP1A(ptr noundef %b) + ret i32 %call +} + +define linkonce_odr dso_local void @_ZN1BC2Ev(ptr noundef nonnull align 8 dereferenceable(8) %this) #0 { +entry: + %this.addr = alloca ptr + store ptr %this, ptr %this.addr + %this1 = load ptr, ptr %this.addr + call void @_ZN1AC2Ev(ptr noundef nonnull align 8 dereferenceable(8) %this1) + store ptr getelementptr inbounds ({ [3 x ptr] }, ptr @_ZTV1B, i32 0, inrange i32 0, i32 2), ptr %this1 + ret void +} + +declare i32 @_Z3barP1A(ptr noundef) + +define linkonce_odr dso_local void @_ZN1AC2Ev(ptr noundef nonnull align 8 dereferenceable(8) %this) #0 { +entry: + %this.addr = alloca ptr + store ptr %this, ptr %this.addr + %this1 = load ptr, ptr %this.addr + store ptr getelementptr inbounds ({ [3 x ptr] }, ptr @_ZTV1A, i32 0, inrange i32 0, i32 2), ptr %this1 + ret void +} + +define linkonce_odr i32 @_ZN1B3fooEv(ptr noundef nonnull align 8 dereferenceable(8) %this) #0 { +entry: + %this.addr = alloca ptr + store ptr %this, ptr %this.addr + %this1 = load ptr, ptr %this.addr + ret i32 2 +} + +;; Make sure we don't inline or otherwise optimize out the direct calls. +attributes #0 = { noinline optnone } + +!0 = !{i64 16, !"_ZTS1A"} +!1 = !{i64 16, !"_ZTSM1AFivE.virtual"} +!2 = !{i64 16, !"_ZTS1B"} +!3 = !{i64 16, !"_ZTSM1BFivE.virtual"} diff --git a/lld/test/ELF/lto/Inputs/devirt_validate_vtable_typeinfos_undef.ll b/lld/test/ELF/lto/Inputs/devirt_validate_vtable_typeinfos_undef.ll new file mode 100644 --- /dev/null +++ b/lld/test/ELF/lto/Inputs/devirt_validate_vtable_typeinfos_undef.ll @@ -0,0 +1,16 @@ +; REQUIRES: x86 + +target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-unknown-linux-gnu" + +@_ZTV1B = external unnamed_addr constant { [4 x ptr] } + +define linkonce_odr void @_ZN1BC2Ev(ptr %this) #0 { + %this.addr = alloca ptr, align 8 + store ptr %this, ptr %this.addr, align 8 + %this1 = load ptr, ptr %this.addr, align 8 + store ptr getelementptr inbounds ({ [4 x ptr] }, ptr @_ZTV1B, i32 0, inrange i32 0, i32 2), ptr %this1, align 8 + ret void +} + +attributes #0 = { noinline optnone } diff --git a/lld/test/ELF/lto/devirt_validate_vtable_typeinfos.ll b/lld/test/ELF/lto/devirt_validate_vtable_typeinfos.ll new file mode 100644 --- /dev/null +++ b/lld/test/ELF/lto/devirt_validate_vtable_typeinfos.ll @@ -0,0 +1,263 @@ +; REQUIRES: x86 + +;; Common artifacts +; RUN: opt --thinlto-bc -o %t1.o %s +; RUN: opt --thinlto-bc --thinlto-split-lto-unit -o %t1_hybrid.o %s +; RUN: cp %s %t1_regular.ll +; RUN: echo '!llvm.module.flags = !{!12, !13}' >> %t1_regular.ll +; RUN: echo '!12 = !{i32 1, !"ThinLTO", i32 0}' >> %t1_regular.ll +; RUN: echo '!13 = !{i32 1, !"EnableSplitLTOUnit", i32 1}' >> %t1_regular.ll +; RUN: opt -module-summary -o %t1_regular.o %t1_regular.ll + +; RUN: llvm-as %S/Inputs/devirt_validate_vtable_typeinfos.ll -o %t2.bc +; RUN: llc -relocation-model=pic -filetype=obj %t2.bc -o %t2.o +; RUN: ld.lld %t2.o -o %t2.so -shared + +; RUN: llvm-as %S/Inputs/devirt_validate_vtable_typeinfos_no_rtti.ll -o %t2_nortti.bc +; RUN: llc -relocation-model=pic -filetype=obj %t2_nortti.bc -o %t2_nortti.o +; RUN: ld.lld %t2_nortti.o -o %t2_nortti.so -shared + +; RUN: llvm-as %S/Inputs/devirt_validate_vtable_typeinfos_undef.ll -o %t2_undef.bc +; RUN: llc -relocation-model=pic -filetype=obj %t2_undef.bc -o %t2_undef.o +; RUN: ld.lld %t2_undef.o -o %t2_undef.so -shared + +;; With --lto-whole-program-visibility, we assume no native types can interfere +;; and thus proceed with devirtualization even in the presence of native types + +;; Index based WPD +; RUN: ld.lld %t1.o %t2.o -o %t3_index -save-temps --lto-whole-program-visibility \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=REMARK +; RUN: llvm-dis %t1.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-IR + +;; Hybrid WPD +; RUN: ld.lld %t1_hybrid.o %t2.o -o %t3_hybrid -save-temps --lto-whole-program-visibility \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=REMARK +; RUN: llvm-dis %t1_hybrid.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-IR + +;; Regular LTO WPD +; RUN: ld.lld %t1_regular.o %t2.o -o %t3_regular -save-temps --lto-whole-program-visibility \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=REMARK +; RUN: llvm-dis %t3_regular.0.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-IR + +; REMARK-DAG: single-impl: devirtualized a call to _ZN1A1nEi +; REMARK-DAG: single-impl: devirtualized a call to _ZN1D1mEi + +;; With --lto-validate-all-vtables-have-type-infos, the linker checks for the presence of vtables +;; and RTTI in native files and blocks devirtualization to be conservative on correctness +;; for these types. + +;; Index based WPD +; RUN: ld.lld %t1.o %t2.o -o %t4_index -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=VALIDATE +; RUN: llvm-dis %t1.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-VALIDATE-IR + +;; Hybrid WPD +; RUN: ld.lld %t1_hybrid.o %t2.o -o %t4_hybrid -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=VALIDATE +; RUN: llvm-dis %t1_hybrid.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-VALIDATE-IR + +;; Regular LTO WPD +; RUN: ld.lld %t1_regular.o %t2.o -o %t4_regular -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=VALIDATE +; RUN: llvm-dis %t4_regular.0.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-VALIDATE-IR + +;; DSOs behave similarly + +;; Index based WPD +; RUN: ld.lld %t1.o %t2.so -o %t5_index -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=VALIDATE +; RUN: llvm-dis %t1.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-VALIDATE-IR + +;; Hybrid WPD +; RUN: ld.lld %t1_hybrid.o %t2.so -o %t5_hybrid -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=VALIDATE +; RUN: llvm-dis %t1_hybrid.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-VALIDATE-IR + +;; Regular LTO WPD +; RUN: ld.lld %t1_regular.o %t2.so -o %t5_regular -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=VALIDATE +; RUN: llvm-dis %t5_regular.0.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-VALIDATE-IR + +; VALIDATE-NOT: single-impl: +; VALIDATE: single-impl: devirtualized a call to _ZN1D1mEi +; VALIDATE-NOT: single-impl: + +;; When vtables without type infos are detected in native files, we have a hole in our knowledge so +;; --lto-validate-all-vtables-have-type-infos conservatively disables --lto-whole-program-visibility + +;; Index based WPD +; RUN: ld.lld %t1.o %t2_nortti.o -o %t6_index -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=NO-RTTI +; RUN: llvm-dis %t1.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-NO-RTTI-IR + +;; Hybrid WPD +; RUN: ld.lld %t1_hybrid.o %t2_nortti.o -o %t6_hybrid -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=NO-RTTI +; RUN: llvm-dis %t1_hybrid.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-NO-RTTI-IR + +;; Regular LTO WPD +; RUN: ld.lld %t1_regular.o %t2_nortti.o -o %t6_regular -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=NO-RTTI +; RUN: llvm-dis %t6_regular.0.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-NO-RTTI-IR + +;; DSOs behave similarly + +;; Index based WPD +; RUN: ld.lld %t1.o %t2_nortti.so -o %t7_index -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=NO-RTTI +; RUN: llvm-dis %t1.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-NO-RTTI-IR + +;; Hybrid WPD +; RUN: ld.lld %t1_hybrid.o %t2_nortti.so -o %t7_hybrid -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=NO-RTTI +; RUN: llvm-dis %t1_hybrid.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-NO-RTTI-IR + +;; Regular LTO WPD +; RUN: ld.lld %t1_regular.o %t2_nortti.so -o %t7_regular -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=NO-RTTI +; RUN: llvm-dis %t7_regular.0.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-NO-RTTI-IR + +; NO-RTTI-DAG: --lto-validate-all-vtables-have-type-infos: RTTI missing for vtable _ZTV6Native, --lto-whole-program-visibility disabled +; NO-RTTI-DAG: single-impl: devirtualized a call to _ZN1D1mEi + +;; --lto-known-safe-vtables=* can be used to specifically allow types to participate in WPD +;; even if they don't have corresponding RTTI + +;; Index based WPD +; RUN: ld.lld %t1.o %t2_nortti.o -o %t8_index -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: --lto-known-safe-vtables=_ZTV6Native -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=REMARK +; RUN: llvm-dis %t1.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-IR + +;; Hybrid WPD +; RUN: ld.lld %t1_hybrid.o %t2_nortti.o -o %t8_hybrid -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: --lto-known-safe-vtables=_ZTV6Native -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=REMARK +; RUN: llvm-dis %t1_hybrid.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-IR + +;; Regular LTO WPD +; RUN: ld.lld %t1_regular.o %t2_nortti.o -o %t8_regular -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: --lto-known-safe-vtables=_ZTV6Native -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=REMARK +; RUN: llvm-dis %t8_regular.0.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-IR + +;; Only check for definitions of vtables symbols, just having a reference does not allow a type to +;; be derived from + +;; Index based WPD +; RUN: ld.lld %t1.o %t2_undef.o -o %t9_index -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=REMARK +; RUN: llvm-dis %t1.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-IR + +;; Hybrid WPD +; RUN: ld.lld %t1_hybrid.o %t2_undef.o -o %t9_hybrid -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=REMARK +; RUN: llvm-dis %t1_hybrid.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-IR + +;; Regular LTO WPD +; RUN: ld.lld %t1_regular.o %t2_undef.o -o %t9_regular -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=REMARK +; RUN: llvm-dis %t9_regular.0.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-IR + +target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-unknown-linux-gnu" + +%struct.A = type { ptr } +%struct.B = type { %struct.A } +%struct.C = type { %struct.A } +%struct.D = type { ptr } + +@_ZTV1B = linkonce_odr constant { [4 x ptr] } { [4 x ptr] [ptr null, ptr @_ZTI1B, ptr @_ZN1B1fEi, ptr @_ZN1A1nEi] }, !type !0, !type !1, !type !2, !type !3, !type !4, !type !5 +@_ZTV1C = linkonce_odr constant { [4 x ptr] } { [4 x ptr] [ptr null, ptr @_ZTI1C, ptr @_ZN1C1fEi, ptr @_ZN1A1nEi] }, !type !0, !type !1, !type !2, !type !6, !type !7, !type !8 +@_ZTV1D = internal constant { [3 x ptr] } { [3 x ptr] [ptr null, ptr @_ZTI1D, ptr @_ZN1D1mEi] }, !type !9, !vcall_visibility !11 + +@_ZTS1A = linkonce_odr constant [3 x i8] c"1A\00" +@_ZTI1A = linkonce_odr constant { ptr, ptr } { ptr null, ptr @_ZTS1A } + +@_ZTS1B = linkonce_odr constant [3 x i8] c"1B\00" +@_ZTI1B = linkonce_odr constant { ptr, ptr, ptr } { ptr null, ptr @_ZTS1B, ptr @_ZTI1A } + +@_ZTS1C = linkonce_odr constant [3 x i8] c"1C\00" +@_ZTI1C = linkonce_odr constant { ptr, ptr, ptr } { ptr null, ptr @_ZTS1C, ptr @_ZTI1A } + +@_ZTS1D = internal constant [3 x i8] c"1D\00" +@_ZTI1D = internal constant { ptr, ptr } { ptr null, ptr @_ZTS1D } + +;; Prevent the vtables from being dead code eliminated. +@llvm.used = appending global [3 x ptr] [ ptr @_ZTV1B, ptr @_ZTV1C, ptr @_ZTV1D ] + +; CHECK-COMMON-IR-LABEL: define dso_local i32 @_start +define i32 @_start(ptr %obj, ptr %obj2, i32 %a) { +entry: + %vtable = load ptr, ptr %obj + %p = call i1 @llvm.type.test(ptr %vtable, metadata !"_ZTS1A") + call void @llvm.assume(i1 %p) + %fptrptr = getelementptr ptr, ptr %vtable, i32 1 + %fptr1 = load ptr, ptr %fptrptr, align 8 + + ;; Check that the call was devirtualized. + ; CHECK-IR: %call = tail call i32 @_ZN1A1nEi + ;; --lto-whole-program-visibility disabled so no devirtualization + ; CHECK-VALIDATE-IR: %call = tail call i32 %fptr1 + ; CHECK-NO-RTTI-IR: %call = tail call i32 %fptr1 + %call = tail call i32 %fptr1(ptr nonnull %obj, i32 %a) + + %fptr22 = load ptr, ptr %vtable, align 8 + + ;; We still have to call it as virtual. + ; CHECK-IR: %call2 = tail call i32 %fptr22 + ; CHECK-VALIDATE-IR: %call2 = tail call i32 %fptr22 + ; CHECK-NO-RTTI-IR: %call2 = tail call i32 %fptr22 + %call2 = tail call i32 %fptr22(ptr nonnull %obj, i32 %call) + + %vtable2 = load ptr, ptr %obj2 + %p2 = call i1 @llvm.type.test(ptr %vtable2, metadata !10) + call void @llvm.assume(i1 %p2) + + %fptr33 = load ptr, ptr %vtable2, align 8 + + ;; Check that the call was devirtualized. + ; CHECK-IR: %call3 = tail call i32 @_ZN1D1mEi + ;; Types not present in native files can still be devirtualized + ; CHECK-VALIDATE-IR: %call3 = tail call i32 @_ZN1D1mEi + ;; --lto-whole-program-visibility disabled but being local this + ;; has VCallVisibilityTranslationUnit visibility so it's still devirtualized + ; CHECK-NO-RTTI-IR: %call3 = tail call i32 @_ZN1D1mEi + %call3 = tail call i32 %fptr33(ptr nonnull %obj2, i32 %call2) + + ret i32 %call3 +} +; CHECK-COMMON-IR-LABEL: ret i32 +; CHECK-COMMON-IR-LABEL: } + +declare i1 @llvm.type.test(ptr, metadata) +declare void @llvm.assume(i1) + +define linkonce_odr i32 @_ZN1B1fEi(ptr %this, i32 %a) #0 { + ret i32 0; +} + +define linkonce_odr i32 @_ZN1A1nEi(ptr %this, i32 %a) #0 { + ret i32 0; +} + +define linkonce_odr i32 @_ZN1C1fEi(ptr %this, i32 %a) #0 { + ret i32 0; +} + +define internal i32 @_ZN1D1mEi(ptr %this, i32 %a) #0 { + ret i32 0; +} + +;; Make sure we don't inline or otherwise optimize out the direct calls. +attributes #0 = { noinline optnone } + +!0 = !{i64 16, !"_ZTS1A"} +!1 = !{i64 16, !"_ZTSM1AFviE.virtual"} +!2 = !{i64 24, !"_ZTSM1AFviE.virtual"} +!3 = !{i64 16, !"_ZTS1B"} +!4 = !{i64 16, !"_ZTSM1BFviE.virtual"} +!5 = !{i64 24, !"_ZTSM1BFviE.virtual"} +!6 = !{i64 16, !"_ZTS1C"} +!7 = !{i64 16, !"_ZTSM1CFviE.virtual"} +!8 = !{i64 24, !"_ZTSM1CFviE.virtual"} +!9 = !{i64 16, !10} +!10 = distinct !{} +!11 = !{i64 2} diff --git a/lld/test/ELF/lto/devirt_validate_vtable_typeinfos_mixed_lto.ll b/lld/test/ELF/lto/devirt_validate_vtable_typeinfos_mixed_lto.ll new file mode 100644 --- /dev/null +++ b/lld/test/ELF/lto/devirt_validate_vtable_typeinfos_mixed_lto.ll @@ -0,0 +1,183 @@ +; REQUIRES: x86 + +; RUN: rm -rf %t.dir +; RUN: split-file %s %t.dir +; RUN: cd %t.dir + +;; Common artifacts +; RUN: opt --thinlto-bc --thinlto-split-lto-unit -o %t1.o ThinLTO.ll +; RUN: opt -module-summary -o %t2.o RegularLTO.ll + +;; --lto-whole-program-visibility when there's split ThinLTO and a RegularLTO with summary optimizes +;; using the combined index. +; RUN: ld.lld %t1.o %t2.o -o %t3 -save-temps --lto-whole-program-visibility \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=REMARK +; RUN: llvm-dis %t1.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-IR,CHECK-COMMON-IR +; RUN: llvm-dis %t3.0.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-REGULAR-IR,CHECK-COMMON-REGULAR-IR + +;; --lto-validate-all-vtables-have-type-infos when there's split ThinLTO and a RegularLTO with summary behaves the same +;; as everything is present in the combined index. +; RUN: ld.lld %t1.o %t2.o -o %t3 -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=REMARK +; RUN: llvm-dis %t1.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-IR,CHECK-COMMON-IR +; RUN: llvm-dis %t3.0.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-REGULAR-IR,CHECK-COMMON-REGULAR-IR + +; REMARK-DAG: single-impl: devirtualized a call to _ZN1D1mEi +; REMARK-DAG: single-impl: devirtualized a call to _ZN1A1nEi + +;--- ThinLTO.ll +target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-unknown-linux-gnu" + +%struct.A = type { ptr } +%struct.B = type { %struct.A } +%struct.C = type { %struct.A } +%struct.D = type { ptr } + +@_ZTV1B = linkonce_odr constant { [4 x ptr] } { [4 x ptr] [ptr null, ptr @_ZTI1B, ptr @_ZN1A1fEi, ptr @_ZN1A1nEi] }, !type !0, !type !1, !type !2, !type !3, !type !4, !type !5 +@_ZTV1C = linkonce_odr constant { [4 x ptr] } { [4 x ptr] [ptr null, ptr @_ZTI1C, ptr @_ZN1A1fEi, ptr @_ZN1A1nEi] }, !type !0, !type !1, !type !2, !type !6, !type !7, !type !8 +@_ZTV1D = internal constant { [3 x ptr] } { [3 x ptr] [ptr null, ptr @_ZTI1D, ptr @_ZN1D1mEi] }, !type !9, !vcall_visibility !11 + +@_ZTS1A = linkonce_odr constant [3 x i8] c"1A\00" +@_ZTI1A = linkonce_odr constant { ptr, ptr } { ptr null, ptr @_ZTS1A } + +@_ZTS1B = linkonce_odr constant [3 x i8] c"1B\00" +@_ZTI1B = linkonce_odr constant { ptr, ptr, ptr } { ptr null, ptr @_ZTS1B, ptr @_ZTI1A } + +@_ZTS1C = linkonce_odr constant [3 x i8] c"1C\00" +@_ZTI1C = linkonce_odr constant { ptr, ptr, ptr } { ptr null, ptr @_ZTS1C, ptr @_ZTI1A } + +@_ZTS1D = internal constant [3 x i8] c"1D\00" +@_ZTI1D = internal constant { ptr, ptr } { ptr null, ptr @_ZTS1D } + +;; Prevent the vtables from being dead code eliminated. +@llvm.used = appending global [3 x ptr] [ ptr @_ZTV1B, ptr @_ZTV1C, ptr @_ZTV1D ], section "llvm.metadata" + +; CHECK-COMMON-IR-LABEL: define dso_local i32 @_start +define i32 @_start(ptr %obj, ptr %obj2, i32 %a) { + ;; Call function built with RegularLTO + %RegularLTOResult = call i32 @RegularLTO(ptr %obj, i32 %a) + + ;; ThinLTO code starts here + %vtable = load ptr, ptr %obj + %p = call i1 @llvm.type.test(ptr %vtable, metadata !"_ZTS1A") + call void @llvm.assume(i1 %p) + %fptrptr = getelementptr ptr, ptr %vtable, i32 1 + %fptr1 = load ptr, ptr %fptrptr, align 8 + + ;; Check that the call was devirtualized. + ; CHECK-IR: %call = tail call i32 @_ZN1A1nEi + %call = tail call i32 %fptr1(ptr nonnull %obj, i32 %a) + + %fptr22 = load ptr, ptr %vtable, align 8 + + ;; Check that the call was not devirtualized. + ; CHECK-IR: %call2 = tail call i32 %fptr22 + %call2 = tail call i32 %fptr22(ptr nonnull %obj, i32 %call) + + %vtable2 = load ptr, ptr %obj2 + %p2 = call i1 @llvm.type.test(ptr %vtable2, metadata !10) + call void @llvm.assume(i1 %p2) + + %fptr33 = load ptr, ptr %vtable2, align 8 + + ;; Check that the call was devirtualized. + ; CHECK-IR: %call3 = tail call i32 @_ZN1D1mEi + %call3 = tail call i32 %fptr33(ptr nonnull %obj2, i32 %call2) + + ret i32 %call3 +} +; CHECK-COMMON-IR-LABEL: ret i32 +; CHECK-COMMON-IR-LABEL: } + +declare i32 @RegularLTO(ptr) +declare i1 @llvm.type.test(ptr, metadata) +declare void @llvm.assume(i1) + +define linkonce_odr i32 @_ZN1A1fEi(ptr %this, i32 %a) #0 { + ret i32 0; +} + +define linkonce_odr i32 @_ZN1A1nEi(ptr %this, i32 %a) #0 { + ret i32 0; +} + +define internal i32 @_ZN1D1mEi(ptr %this, i32 %a) #0 { + ret i32 0; +} + +;; Make sure we don't inline or otherwise optimize out the direct calls. +attributes #0 = { noinline optnone } + +!0 = !{i64 16, !"_ZTS1A"} +!1 = !{i64 16, !"_ZTSM1AFviE.virtual"} +!2 = !{i64 24, !"_ZTSM1AFviE.virtual"} +!3 = !{i64 16, !"_ZTS1B"} +!4 = !{i64 16, !"_ZTSM1BFviE.virtual"} +!5 = !{i64 24, !"_ZTSM1BFviE.virtual"} +!6 = !{i64 16, !"_ZTS1C"} +!7 = !{i64 16, !"_ZTSM1CFviE.virtual"} +!8 = !{i64 24, !"_ZTSM1CFviE.virtual"} +!9 = !{i64 16, !10} +!10 = distinct !{} +!11 = !{i64 2} + +;--- RegularLTO.ll +; REQUIRES: x86 + +target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-unknown-linux-gnu" + +%struct.A = type { ptr } +%struct.Native = type { %struct.A } + +@_ZTV7Regular = linkonce_odr unnamed_addr constant { [4 x ptr] } { [4 x ptr] [ptr null, ptr @_ZTI7Regular, ptr @_ZN7Regular1fEi, ptr @_ZN1A1nEi] } , !type !0, !type !1, !type !2, !type !3, !type !4, !type !5 +@_ZTS7Regular = linkonce_odr constant [9 x i8] c"7Regular\00" +@_ZTI7Regular = linkonce_odr constant { ptr, ptr, ptr } { ptr null, ptr @_ZTS7Regular, ptr @_ZTI1A } + +; Base type A does not need to emit a vtable if it's never instantiated. However, RTTI still gets generated +@_ZTS1A = linkonce_odr constant [3 x i8] c"1A\00" +@_ZTI1A = linkonce_odr constant { ptr, ptr } { ptr null, ptr @_ZTS1A } + +;; Prevent the vtables from being dead code eliminated. +@llvm.used = appending global [1 x ptr] [ ptr @_ZTV7Regular ], section "llvm.metadata" + +; CHECK-COMMON-REGULAR-IR-LABEL: define dso_local i32 @RegularLTO +define i32 @RegularLTO(ptr %obj, i32 %a) #0 { +entry: + %vtable = load ptr, ptr %obj + %p = call i1 @llvm.type.test(ptr %vtable, metadata !"_ZTS1A") + call void @llvm.assume(i1 %p) + %fptr1 = load ptr, ptr %vtable, align 8 + + ;; Check that the call was not devirtualized. + ; CHECK-REGULAR-IR: %call = tail call i32 %fptr1 + %call = tail call i32 %fptr1(ptr nonnull %obj, i32 %a) + + ret i32 %call +} +; CHECK-COMMON-REGULAR-IR-LABEL: ret i32 +; CHECK-COMMON-REGULAR-IR-LABEL: } + +declare i1 @llvm.type.test(ptr, metadata) +declare void @llvm.assume(i1) + +define linkonce_odr i32 @_ZN7Regular1fEi(ptr %this, i32 %a) #0 { + ret i32 1; +} + +define linkonce_odr i32 @_ZN1A1nEi(ptr %this, i32 %a) #0 { + ret i32 0; +} + +attributes #0 = { noinline optnone } +!llvm.module.flags = !{!6, !7} + +!0 = !{i64 16, !"_ZTS1A"} +!1 = !{i64 16, !"_ZTSM1AFviE.virtual"} +!2 = !{i64 24, !"_ZTSM1AFviE.virtual"} +!3 = !{i64 16, !"_ZTS7Regular"} +!4 = !{i64 16, !"_ZTSM7RegularFviE.virtual"} +!5 = !{i64 24, !"_ZTSM7RegularFviE.virtual"} +!6 = !{i32 1, !"ThinLTO", i32 0} +!7 = !{i32 1, !"EnableSplitLTOUnit", i32 1} diff --git a/lld/test/ELF/lto/devirt_validate_vtable_typeinfos_no_rtti.ll b/lld/test/ELF/lto/devirt_validate_vtable_typeinfos_no_rtti.ll new file mode 100644 --- /dev/null +++ b/lld/test/ELF/lto/devirt_validate_vtable_typeinfos_no_rtti.ll @@ -0,0 +1,136 @@ +; REQUIRES: x86 + +;; Common artifacts +; RUN: opt --thinlto-bc -o %t1.o %s +; RUN: opt --thinlto-bc --thinlto-split-lto-unit -o %t1_hybrid.o %s +; RUN: cp %s %t1_regular.ll +; RUN: echo '!llvm.module.flags = !{!6, !7}' >> %t1_regular.ll +; RUN: echo '!6 = !{i32 1, !"ThinLTO", i32 0}' >> %t1_regular.ll +; RUN: echo '!7 = !{i32 1, !"EnableSplitLTOUnit", i32 1}' >> %t1_regular.ll +; RUN: opt -module-summary -o %t1_regular.o %t1_regular.ll + +;; With --lto-whole-program-visibility, we assume no native types can interfere +;; and thus proceed with devirtualization even in the presence of native types + +;; Index based WPD +; RUN: ld.lld %t1.o -o %t3_index -save-temps --lto-whole-program-visibility \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=REMARK +; RUN: llvm-dis %t1.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-IR + +;; Hybrid WPD +; RUN: ld.lld %t1_hybrid.o -o %t3_hybrid -save-temps --lto-whole-program-visibility \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=REMARK +; RUN: llvm-dis %t1_hybrid.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-IR + +;; Regular LTO WPD +; RUN: ld.lld %t1_regular.o -o %t3_regular -save-temps --lto-whole-program-visibility \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=REMARK +; RUN: llvm-dis %t3_regular.0.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-IR + +; REMARK-DAG: single-impl: devirtualized a call to _ZN1A1nEi +; REMARK-DAG: single-impl: devirtualized a call to _ZN1D1mEi + +;; With --lto-whole-program-visibility and --lto-validate-all-vtables-have-type-infos +;; we rely on resolutions on the typename symbol to inform us of what's outside the summary. +;; Without the typename symbol in the LTO unit (e.g. RTTI disabled) this causes +;; conservative disablement of WPD on these types unless it's local + +;; Index based WPD +; RUN: ld.lld %t1.o -o %t3_index -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=VALIDATE +; RUN: llvm-dis %t1.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-VALIDATE-IR + +;; Hybrid WPD +; RUN: ld.lld %t1_hybrid.o -o %t3_hybrid -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=VALIDATE +; RUN: llvm-dis %t1_hybrid.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-VALIDATE-IR + +;; Regular LTO WPD +; RUN: ld.lld %t1_regular.o -o %t3_regular -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s --check-prefix=VALIDATE +; RUN: llvm-dis %t3_regular.0.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-COMMON-IR-LABEL,CHECK-VALIDATE-IR + +; VALIDATE-DAG: single-impl: devirtualized a call to _ZN1D1mEi + +target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-unknown-linux-gnu" + +%struct.A = type { ptr } +%struct.B = type { %struct.A } +%struct.C = type { %struct.A } +%struct.D = type { ptr } + +@_ZTV1B = linkonce_odr constant { [4 x ptr] } { [4 x ptr] [ptr null, ptr null, ptr @_ZN1B1fEi, ptr @_ZN1A1nEi] }, !type !0, !type !1 +@_ZTV1C = linkonce_odr constant { [4 x ptr] } { [4 x ptr] [ptr null, ptr null, ptr @_ZN1C1fEi, ptr @_ZN1A1nEi] }, !type !0, !type !2 +@_ZTV1D = internal constant { [3 x ptr] } { [3 x ptr] [ptr null, ptr null, ptr @_ZN1D1mEi] }, !type !3, !vcall_visibility !5 + +;; Prevent the vtables from being dead code eliminated. +@llvm.used = appending global [3 x ptr] [ ptr @_ZTV1B, ptr @_ZTV1C, ptr @_ZTV1D ] + +; CHECK-COMMON-IR-LABEL: define dso_local i32 @_start +define i32 @_start(ptr %obj, ptr %obj2, i32 %a) { +entry: + %vtable = load ptr, ptr %obj + %p = call i1 @llvm.type.test(ptr %vtable, metadata !"_ZTS1A") + call void @llvm.assume(i1 %p) + %fptrptr = getelementptr ptr, ptr %vtable, i32 1 + %fptr1 = load ptr, ptr %fptrptr, align 8 + + ;; Check that the call was devirtualized. + ; CHECK-IR: %call = tail call i32 @_ZN1A1nEi + ;; No resolution for _ZTS1A means we don't devirtualize + ; CHECK-VALIDATE-IR: %call = tail call i32 %fptr1 + %call = tail call i32 %fptr1(ptr nonnull %obj, i32 %a) + + %fptr22 = load ptr, ptr %vtable, align 8 + + ;; We still have to call it as virtual. + ; CHECK-IR: %call3 = tail call i32 %fptr22 + ; CHECK-VALIDATE-IR: %call3 = tail call i32 %fptr22 + %call3 = tail call i32 %fptr22(ptr nonnull %obj, i32 %call) + + %vtable2 = load ptr, ptr %obj2 + %p2 = call i1 @llvm.type.test(ptr %vtable2, metadata !4) + call void @llvm.assume(i1 %p2) + + %fptr33 = load ptr, ptr %vtable2, align 8 + + ;; Check that the call was devirtualized. + ; CHECK-IR: %call4 = tail call i32 @_ZN1D1mEi + ;; Being local this has VCallVisibilityTranslationUnit + ;; visibility so it's still devirtualized + ; CHECK-VALIDATE-IR: %call4 = tail call i32 @_ZN1D1mEi + %call4 = tail call i32 %fptr33(ptr nonnull %obj2, i32 %call3) + ret i32 %call4 +} +; CHECK-COMMON-IR-LABEL: ret i32 +; CHECK-COMMON-IR-LABEL: } + +declare i1 @llvm.type.test(ptr, metadata) +declare void @llvm.assume(i1) + +define linkonce_odr i32 @_ZN1B1fEi(ptr %this, i32 %a) #0 { + ret i32 0; +} + +define linkonce_odr i32 @_ZN1A1nEi(ptr %this, i32 %a) #0 { + ret i32 0; +} + +define linkonce_odr i32 @_ZN1C1fEi(ptr %this, i32 %a) #0 { + ret i32 0; +} + +define internal i32 @_ZN1D1mEi(ptr %this, i32 %a) #0 { + ret i32 0; +} + +;; Make sure we don't inline or otherwise optimize out the direct calls. +attributes #0 = { noinline optnone } + +!0 = !{i64 16, !"_ZTS1A"} +!1 = !{i64 16, !"_ZTS1B"} +!2 = !{i64 16, !"_ZTS1C"} +!3 = !{i64 16, !4} +!4 = distinct !{} +!5 = !{i64 2} diff --git a/lld/test/ELF/lto/devirt_validate_vtable_typeinfos_ref.ll b/lld/test/ELF/lto/devirt_validate_vtable_typeinfos_ref.ll new file mode 100644 --- /dev/null +++ b/lld/test/ELF/lto/devirt_validate_vtable_typeinfos_ref.ll @@ -0,0 +1,130 @@ +; REQUIRES: x86 + +;; Common artifacts +; RUN: opt --thinlto-bc -o %t1.o %s +; RUN: opt --thinlto-bc --thinlto-split-lto-unit -o %t1_hybrid.o %s +; RUN: cp %s %t1_regular.ll +; RUN: echo '!llvm.module.flags = !{!2, !3}' >> %t1_regular.ll +; RUN: echo '!2 = !{i32 1, !"ThinLTO", i32 0}' >> %t1_regular.ll +; RUN: echo '!3 = !{i32 1, !"EnableSplitLTOUnit", i32 1}' >> %t1_regular.ll +; RUN: opt -module-summary -o %t1_regular.o %t1_regular.ll + +; RUN: llvm-as %S/Inputs/devirt_validate_vtable_typeinfos_ref.ll -o %t2.bc +; RUN: llc -relocation-model=pic -filetype=obj %t2.bc -o %t2.o + +;; Native objects can contain only a reference to the base type infos if the base declaration has no key functions. +;; Because of that, --lto-validate-all-vtables-have-type-infos needs to query for the type info symbol inside native files rather than the +;; type name symbol that's used as the key in !type metadata to correctly stop devirtualization on the native type. + +;; Index based WPD +; RUN: ld.lld %t1.o %t2.o -o %t3_index -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s +; RUN: llvm-dis %t1.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-IR + +;; Hybrid WPD +; RUN: ld.lld %t1_hybrid.o %t2.o -o %t3_hybrid -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s +; RUN: llvm-dis %t1_hybrid.o.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-IR + +;; Regular LTO WPD +; RUN: ld.lld %t1_regular.o %t2.o -o %t3_regular -save-temps --lto-whole-program-visibility --lto-validate-all-vtables-have-type-infos \ +; RUN: -mllvm -pass-remarks=. 2>&1 | FileCheck %s +; RUN: llvm-dis %t3_regular.0.4.opt.bc -o - | FileCheck %s --check-prefixes=CHECK-IR + +; CHECK-NOT: single-impl: devirtualized a call to _ZN1A3fooEv + +;; Source code: +;; cat > a.h <<'eof' +;; struct A { virtual int foo(); }; +;; int bar(A *a); +;; eof +;; cat > main.cc <<'eof' +;; #include "a.h" +;; +;; int A::foo() { return 1; } +;; int bar(A *a) { return a->foo(); } +;; +;; extern int baz(); +;; int main() { +;; A a; +;; int i = bar(&a); +;; int j = baz(); +;; return i + j; +;; } +;; eof +;; clang++ -fwhole-program-vtables -fno-split-lto-unit -flto=thin main.cc -c + +target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-unknown-linux-gnu" + +%struct.A = type { %struct.Abase } +%struct.Abase = type { ptr } + +@_ZTV1A = dso_local unnamed_addr constant { [3 x ptr] } { [3 x ptr] [ptr null, ptr @_ZTI1A, ptr @_ZN1A3fooEv] }, align 8, !type !0, !type !1 +@_ZTS1A = dso_local constant [3 x i8] c"1A\00", align 1 +@_ZTI1A = dso_local constant { ptr, ptr } { ptr null, ptr @_ZTS1A }, align 8 + +define dso_local noundef i32 @_ZN1A3fooEv(ptr noundef nonnull align 8 dereferenceable(8) %this) #0 align 2 { +entry: + %this.addr = alloca ptr + store ptr %this, ptr %this.addr + %this1 = load ptr, ptr %this.addr + ret i32 1 +} + +; CHECK-IR: define dso_local noundef i32 @_Z3barP1A +define dso_local noundef i32 @_Z3barP1A(ptr noundef %a) #0 { +entry: + %a.addr = alloca ptr + store ptr %a, ptr %a.addr + %0 = load ptr, ptr %a.addr + %vtable = load ptr, ptr %0 + %1 = call i1 @llvm.public.type.test(ptr %vtable, metadata !"_ZTS1A") + call void @llvm.assume(i1 %1) + %vfn = getelementptr inbounds ptr, ptr %vtable, i64 0 + %fptr = load ptr, ptr %vfn + ;; Check that the call was not devirtualized. + ; CHECK-IR: %call = call noundef i32 %fptr + %call = call noundef i32 %fptr(ptr noundef nonnull align 8 dereferenceable(8) %0) + ret i32 %call +} +; CHECK-IR: ret i32 +; CHECK-IR: } + +declare i1 @llvm.public.type.test(ptr, metadata) +declare void @llvm.assume(i1 noundef) + +define dso_local noundef i32 @main() #0 { +entry: + %retval = alloca i32, align 4 + %a = alloca %struct.A, align 8 + %i = alloca i32, align 4 + %j = alloca i32, align 4 + store i32 0, ptr %retval, align 4 + call void @_ZN1AC2Ev(ptr noundef nonnull align 8 dereferenceable(8) %a) + %call = call noundef i32 @_Z3barP1A(ptr noundef %a) + store i32 %call, ptr %i, align 4 + %call1 = call noundef i32 @_Z3bazv() + store i32 %call1, ptr %j, align 4 + %0 = load i32, ptr %i, align 4 + %1 = load i32, ptr %j, align 4 + %add = add nsw i32 %0, %1 + ret i32 %add +} + +define linkonce_odr dso_local void @_ZN1AC2Ev(ptr noundef nonnull align 8 dereferenceable(8) %this) #0 align 2 { +entry: + %this.addr = alloca ptr, align 8 + store ptr %this, ptr %this.addr, align 8 + %this1 = load ptr, ptr %this.addr, align 8 + store ptr getelementptr inbounds ({ [3 x ptr] }, ptr @_ZTV1A, i32 0, inrange i32 0, i32 2), ptr %this1, align 8 + ret void +} + +declare noundef i32 @_Z3bazv() + +;; Make sure we don't inline or otherwise optimize out the direct calls. +attributes #0 = { noinline optnone } + +!0 = !{i64 16, !"_ZTS1A"} +!1 = !{i64 16, !"_ZTSM1AFivE.virtual"} diff --git a/llvm/include/llvm/LTO/Config.h b/llvm/include/llvm/LTO/Config.h --- a/llvm/include/llvm/LTO/Config.h +++ b/llvm/include/llvm/LTO/Config.h @@ -80,6 +80,12 @@ /// link. bool HasWholeProgramVisibility = false; + /// We're validating that all native vtables have corresponding type infos. + bool ValidateAllVtablesHaveTypeInfos = false; + /// If all native vtables have corresponding type infos, allow + /// usage of RTTI to block devirtualization on types used in native files. + bool AllVtablesHaveTypeInfos = false; + /// Always emit a Regular LTO object even when it is empty because no Regular /// LTO modules were linked. This option is useful for some build system which /// want to know a priori all possible output files. diff --git a/llvm/include/llvm/Transforms/IPO/WholeProgramDevirt.h b/llvm/include/llvm/Transforms/IPO/WholeProgramDevirt.h --- a/llvm/include/llvm/Transforms/IPO/WholeProgramDevirt.h +++ b/llvm/include/llvm/Transforms/IPO/WholeProgramDevirt.h @@ -243,10 +243,18 @@ bool WholeProgramVisibilityEnabledInLTO); void updateVCallVisibilityInModule( Module &M, bool WholeProgramVisibilityEnabledInLTO, - const DenseSet &DynamicExportSymbols); + const DenseSet &DynamicExportSymbols, + bool ValidateAllVtablesHaveTypeInfos, + function_ref IsVisibleToRegularObj); void updateVCallVisibilityInIndex( ModuleSummaryIndex &Index, bool WholeProgramVisibilityEnabledInLTO, - const DenseSet &DynamicExportSymbols); + const DenseSet &DynamicExportSymbols, + const DenseSet &VisibleToRegularObjSymbols); + +void getVisibleToRegularObjVtableGUIDs( + ModuleSummaryIndex &Index, + DenseSet &VisibleToRegularObjSymbols, + function_ref IsVisibleToRegularObj); /// Perform index-based whole program devirtualization on the \p Summary /// index. Any devirtualized targets used by a type test in another module diff --git a/llvm/lib/LTO/LTO.cpp b/llvm/lib/LTO/LTO.cpp --- a/llvm/lib/LTO/LTO.cpp +++ b/llvm/lib/LTO/LTO.cpp @@ -1286,13 +1286,28 @@ updateMemProfAttributes(*RegularLTO.CombinedModule, ThinLTO.CombinedIndex); + bool WholeProgramVisibilityEnabledInLTO = + Conf.HasWholeProgramVisibility && + // If validation is enabled, upgrade visibility only when all vtables + // have typeinfos. + (!Conf.ValidateAllVtablesHaveTypeInfos || Conf.AllVtablesHaveTypeInfos); + + // This returns true when the name is local or not defined. Locals are + // expected to be handled separately. + auto IsVisibleToRegularObj = [&](StringRef name) { + return GlobalResolutions.count(name) + ? GlobalResolutions[name].VisibleOutsideSummary + : true; + }; + // If allowed, upgrade public vcall visibility metadata to linkage unit // visibility before whole program devirtualization in the optimizer. - updateVCallVisibilityInModule(*RegularLTO.CombinedModule, - Conf.HasWholeProgramVisibility, - DynamicExportSymbols); + updateVCallVisibilityInModule( + *RegularLTO.CombinedModule, WholeProgramVisibilityEnabledInLTO, + DynamicExportSymbols, Conf.ValidateAllVtablesHaveTypeInfos, + IsVisibleToRegularObj); updatePublicTypeTestCalls(*RegularLTO.CombinedModule, - Conf.HasWholeProgramVisibility); + WholeProgramVisibilityEnabledInLTO); if (Conf.PreOptModuleHook && !Conf.PreOptModuleHook(0, *RegularLTO.CombinedModule)) @@ -1694,13 +1709,38 @@ std::set ExportedGUIDs; - if (hasWholeProgramVisibility(Conf.HasWholeProgramVisibility)) + bool WholeProgramVisibilityEnabledInLTO = + Conf.HasWholeProgramVisibility && + // If validation is enabled, upgrade visibility only when all vtables + // have typeinfos. + (!Conf.ValidateAllVtablesHaveTypeInfos || Conf.AllVtablesHaveTypeInfos); + if (hasWholeProgramVisibility(WholeProgramVisibilityEnabledInLTO)) ThinLTO.CombinedIndex.setWithWholeProgramVisibility(); + + // If we're validating, get the vtable symbols that should not be + // upgraded because they correspond to typeIDs outside of index-based + // WPD info. + DenseSet VisibleToRegularObjSymbols; + if (WholeProgramVisibilityEnabledInLTO && + Conf.ValidateAllVtablesHaveTypeInfos) { + // This returns true when the name is local or not defined. Locals are + // expected to be handled separately. + auto IsVisibleToRegularObj = [&](StringRef name) { + return GlobalResolutions.count(name) + ? GlobalResolutions[name].VisibleOutsideSummary + : true; + }; + + getVisibleToRegularObjVtableGUIDs(ThinLTO.CombinedIndex, + VisibleToRegularObjSymbols, + IsVisibleToRegularObj); + } + // If allowed, upgrade public vcall visibility to linkage unit visibility in // the summaries before whole program devirtualization below. - updateVCallVisibilityInIndex(ThinLTO.CombinedIndex, - Conf.HasWholeProgramVisibility, - DynamicExportSymbols); + updateVCallVisibilityInIndex( + ThinLTO.CombinedIndex, WholeProgramVisibilityEnabledInLTO, + DynamicExportSymbols, VisibleToRegularObjSymbols); // Perform index-based WPD. This will return immediately if there are // no index entries in the typeIdMetadata map (e.g. if we are instead diff --git a/llvm/lib/LTO/LTOCodeGenerator.cpp b/llvm/lib/LTO/LTOCodeGenerator.cpp --- a/llvm/lib/LTO/LTOCodeGenerator.cpp +++ b/llvm/lib/LTO/LTOCodeGenerator.cpp @@ -604,11 +604,14 @@ // pipeline run below. updatePublicTypeTestCalls(*MergedModule, /* WholeProgramVisibilityEnabledInLTO */ false); - updateVCallVisibilityInModule(*MergedModule, - /* WholeProgramVisibilityEnabledInLTO */ false, - // FIXME: This needs linker information via a - // TBD new interface. - /* DynamicExportSymbols */ {}); + updateVCallVisibilityInModule( + *MergedModule, + /* WholeProgramVisibilityEnabledInLTO */ false, + // FIXME: These need linker information via a + // TBD new interface. + /*DynamicExportSymbols=*/{}, + /*ValidateAllVtablesHaveTypeInfos=*/false, + /*IsVisibleToRegularObj=*/[](StringRef) { return true; }); // We always run the verifier once on the merged module, the `DisableVerify` // parameter only applies to subsequent verify. diff --git a/llvm/lib/LTO/ThinLTOCodeGenerator.cpp b/llvm/lib/LTO/ThinLTOCodeGenerator.cpp --- a/llvm/lib/LTO/ThinLTOCodeGenerator.cpp +++ b/llvm/lib/LTO/ThinLTOCodeGenerator.cpp @@ -1058,11 +1058,14 @@ // via the internal option. Must be done before WPD below. if (hasWholeProgramVisibility(/* WholeProgramVisibilityEnabledInLTO */ false)) Index->setWithWholeProgramVisibility(); + + // FIXME: This needs linker information via a TBD new interface updateVCallVisibilityInIndex(*Index, - /* WholeProgramVisibilityEnabledInLTO */ false, - // FIXME: This needs linker information via a + /*WholeProgramVisibilityEnabledInLTO=*/false, + // FIXME: These need linker information via a // TBD new interface. - /* DynamicExportSymbols */ {}); + /*DynamicExportSymbols=*/{}, + /*VisibleToRegularObjSymbols=*/{}); // Perform index-based WPD. This will return immediately if there are // no index entries in the typeIdMetadata map (e.g. if we are instead diff --git a/llvm/lib/Transforms/IPO/WholeProgramDevirt.cpp b/llvm/lib/Transforms/IPO/WholeProgramDevirt.cpp --- a/llvm/lib/Transforms/IPO/WholeProgramDevirt.cpp +++ b/llvm/lib/Transforms/IPO/WholeProgramDevirt.cpp @@ -784,12 +784,51 @@ !DisableWholeProgramVisibility; } +bool TypeIDVisibleToRegularObj( + StringRef TypeID, function_ref IsVisibleToRegularObj) { + // TypeID for member function pointer type is an internal construct + // and won't exist in IsVisibleToRegularObj. The full TypeID + // will be present and participate in invalidation. + if (TypeID.ends_with(".virtual")) + return false; + + // TypeID that doesn't start with Itanium mangling (_ZTS) will be + // non-externally visible types which cannot interact with + // external native files. See CodeGenModule::CreateMetadataIdentifierImpl. + if (!TypeID.starts_with("_ZTS")) + return false; + + // TypeID is keyed off the type name symbol (_ZTS). However, the native + // object may not contain this symbol if it does not contain a key + // function for the base type and thus only contains a reference to the + // type info (_ZTI). To catch this case we query using the type info + // symbol corresponding to the TypeID. + TypeID.consume_front("_ZTS"); + std::string typeInfo = "_ZTI" + TypeID.str(); + return IsVisibleToRegularObj(typeInfo); +} + +bool SkipUpdateDueToValidation( + GlobalVariable &GV, function_ref IsVisibleToRegularObj) { + SmallVector Types; + GV.getMetadata(LLVMContext::MD_type, Types); + + for (auto Type : Types) + if (auto *TypeID = dyn_cast(Type->getOperand(1).get())) + return TypeIDVisibleToRegularObj(TypeID->getString(), + IsVisibleToRegularObj); + + return false; +} + /// If whole program visibility asserted, then upgrade all public vcall /// visibility metadata on vtable definitions to linkage unit visibility in /// Module IR (for regular or hybrid LTO). void updateVCallVisibilityInModule( Module &M, bool WholeProgramVisibilityEnabledInLTO, - const DenseSet &DynamicExportSymbols) { + const DenseSet &DynamicExportSymbols, + bool ValidateAllVtablesHaveTypeInfos, + function_ref IsVisibleToRegularObj) { if (!hasWholeProgramVisibility(WholeProgramVisibilityEnabledInLTO)) return; for (GlobalVariable &GV : M.globals()) { @@ -800,7 +839,11 @@ GV.getVCallVisibility() == GlobalObject::VCallVisibilityPublic && // Don't upgrade the visibility for symbols exported to the dynamic // linker, as we have no information on their eventual use. - !DynamicExportSymbols.count(GV.getGUID())) + !DynamicExportSymbols.count(GV.getGUID()) && + // Don't upgrade the visibility for symbols if validation is on + // and their types are visible to regular object files + !(ValidateAllVtablesHaveTypeInfos && + SkipUpdateDueToValidation(GV, IsVisibleToRegularObj))) GV.setVCallVisibilityMetadata(GlobalObject::VCallVisibilityLinkageUnit); } } @@ -832,12 +875,26 @@ } } +/// Based on typeID string, get all associated vtable GUIDS that are +/// visible to regular objects. +void getVisibleToRegularObjVtableGUIDs( + ModuleSummaryIndex &Index, + DenseSet &VisibleToRegularObjSymbols, + function_ref IsVisibleToRegularObj) { + for (const auto &typeID : Index.typeIdCompatibleVtableMap()) { + if (TypeIDVisibleToRegularObj(typeID.first, IsVisibleToRegularObj)) + for (const TypeIdOffsetVtableInfo &P : typeID.second) + VisibleToRegularObjSymbols.insert(P.VTableVI.getGUID()); + } +} + /// If whole program visibility asserted, then upgrade all public vcall /// visibility metadata on vtable definition summaries to linkage unit /// visibility in Module summary index (for ThinLTO). void updateVCallVisibilityInIndex( ModuleSummaryIndex &Index, bool WholeProgramVisibilityEnabledInLTO, - const DenseSet &DynamicExportSymbols) { + const DenseSet &DynamicExportSymbols, + const DenseSet &VisibleToRegularObjSymbols) { if (!hasWholeProgramVisibility(WholeProgramVisibilityEnabledInLTO)) return; for (auto &P : Index) { @@ -850,6 +907,11 @@ if (!GVar || GVar->getVCallVisibility() != GlobalObject::VCallVisibilityPublic) continue; + // With validation enabled, we want to exclude symbols populated in + // VisibleToRegularObjSymbols. However, locals are also captured because + // of the current implementation so don't exclude them. + if (VisibleToRegularObjSymbols.count(P.first)) + continue; GVar->setVCallVisibility(GlobalObject::VCallVisibilityLinkageUnit); } } @@ -1045,8 +1107,8 @@ } bool DevirtIndex::tryFindVirtualCallTargets( - std::vector &TargetsForSlot, const TypeIdCompatibleVtableInfo TIdInfo, - uint64_t ByteOffset) { + std::vector &TargetsForSlot, + const TypeIdCompatibleVtableInfo TIdInfo, uint64_t ByteOffset) { for (const TypeIdOffsetVtableInfo &P : TIdInfo) { // Find a representative copy of the vtable initializer. // We can have multiple available_externally, linkonce_odr and weak_odr diff --git a/llvm/tools/opt/opt.cpp b/llvm/tools/opt/opt.cpp --- a/llvm/tools/opt/opt.cpp +++ b/llvm/tools/opt/opt.cpp @@ -570,9 +570,14 @@ // the facility for updating public visibility to linkage unit visibility when // specified by an internal option. This is normally done during LTO which is // not performed via opt. - updateVCallVisibilityInModule(*M, - /* WholeProgramVisibilityEnabledInLTO */ false, - /* DynamicExportSymbols */ {}); + updateVCallVisibilityInModule( + *M, + /*WholeProgramVisibilityEnabledInLTO=*/false, + // FIXME: These need linker information via a + // TBD new interface. + /*DynamicExportSymbols=*/{}, + /*ValidateAllVtablesHaveTypeInfos=*/false, + /*IsVisibleToRegularObj=*/[](StringRef) { return true; }); // Figure out what stream we are supposed to write to... std::unique_ptr Out;