[compiler-rt] 5ca2117 - [InstrProfiling] Use ELF section groups for counters, data and values
Petr Hosek via llvm-commits
llvm-commits at lists.llvm.org
Sun Feb 21 16:13:28 PST 2021
Author: Petr Hosek
Date: 2021-02-21T16:13:06-08:00
New Revision: 5ca21175e09fc7fb7dcaee9ebd6782d122a5688f
URL: https://github.com/llvm/llvm-project/commit/5ca21175e09fc7fb7dcaee9ebd6782d122a5688f
DIFF: https://github.com/llvm/llvm-project/commit/5ca21175e09fc7fb7dcaee9ebd6782d122a5688f.diff
LOG: [InstrProfiling] Use ELF section groups for counters, data and values
__start_/__stop_ references retain C identifier name sections such as
__llvm_prf_*. Putting these into a section group disables this logic.
The ELF section group semantics ensures that group members are retained
or discarded as a unit. When a function symbol is discarded, this allows
allows linker to discard counters, data and values associated with that
function symbol as well.
Note that `noduplicates` COMDAT is lowered to zero-flag section group in
ELF. We only set this for functions that aren't already in a COMDAT and
for those that don't have available_externally linkage since we already
use regular COMDAT groups for those.
Differential Revision: https://reviews.llvm.org/D96757
Added:
compiler-rt/test/profile/instrprof-gc-sections.c
Modified:
compiler-rt/test/CMakeLists.txt
compiler-rt/test/profile/CMakeLists.txt
llvm/lib/Transforms/Instrumentation/InstrProfiling.cpp
llvm/test/Instrumentation/InstrProfiling/icall.ll
llvm/test/Instrumentation/InstrProfiling/linkage.ll
llvm/test/Instrumentation/InstrProfiling/platform.ll
llvm/test/Transforms/PGOProfile/counter_promo.ll
llvm/test/Transforms/PGOProfile/counter_promo_mexits.ll
Removed:
################################################################################
diff --git a/compiler-rt/test/CMakeLists.txt b/compiler-rt/test/CMakeLists.txt
index 0836005e10db..4d2a6ec2be10 100644
--- a/compiler-rt/test/CMakeLists.txt
+++ b/compiler-rt/test/CMakeLists.txt
@@ -22,7 +22,7 @@ if(NOT ANDROID)
# Use LLVM utils and Clang from the same build tree.
list(APPEND SANITIZER_COMMON_LIT_TEST_DEPS
clang clang-resource-headers FileCheck count not llvm-config llvm-nm llvm-objdump
- llvm-readobj llvm-symbolizer compiler-rt-headers sancov)
+ llvm-readelf llvm-readobj llvm-symbolizer compiler-rt-headers sancov)
if (WIN32)
list(APPEND SANITIZER_COMMON_LIT_TEST_DEPS KillTheDoctor)
endif()
diff --git a/compiler-rt/test/profile/CMakeLists.txt b/compiler-rt/test/profile/CMakeLists.txt
index 4b031306594f..446e850a3bc1 100644
--- a/compiler-rt/test/profile/CMakeLists.txt
+++ b/compiler-rt/test/profile/CMakeLists.txt
@@ -5,6 +5,9 @@ set(PROFILE_TESTSUITES)
set(PROFILE_TEST_DEPS ${SANITIZER_COMMON_LIT_TEST_DEPS})
if(NOT COMPILER_RT_STANDALONE_BUILD)
list(APPEND PROFILE_TEST_DEPS profile llvm-profdata llvm-cov)
+ if(NOT APPLE AND COMPILER_RT_HAS_LLD AND TARGET lld)
+ list(APPEND PROFILE_TEST_DEPS lld)
+ endif()
endif()
set(PROFILE_TEST_ARCH ${PROFILE_SUPPORTED_ARCH})
diff --git a/compiler-rt/test/profile/instrprof-gc-sections.c b/compiler-rt/test/profile/instrprof-gc-sections.c
new file mode 100644
index 000000000000..8459fb70fd75
--- /dev/null
+++ b/compiler-rt/test/profile/instrprof-gc-sections.c
@@ -0,0 +1,86 @@
+// REQUIRES: linux, lld-available
+
+// RUN: %clang_profgen=%t.profraw -fuse-ld=lld -fcoverage-mapping -mllvm -enable-name-compression=false -DCODE=1 -ffunction-sections -fdata-sections -Wl,--gc-sections -o %t %s
+// RUN: %run %t
+// RUN: llvm-profdata merge -o %t.profdata %t.profraw
+// RUN: llvm-profdata show --all-functions %t.profdata | FileCheck %s -check-prefix=PROF
+// RUN: llvm-cov show %t -instr-profile %t.profdata | FileCheck %s -check-prefix=COV
+// RUN: llvm-nm %t | FileCheck %s -check-prefix=NM
+// RUN: llvm-readelf -x __llvm_prf_names %t | FileCheck %s -check-prefix=PRF_NAMES
+// RUN: llvm-readelf -x __llvm_prf_cnts %t | FileCheck %s -check-prefix=PRF_CNTS
+
+// RUN: %clang_lto_profgen=%t.lto.profraw -fuse-ld=lld -fcoverage-mapping -mllvm -enable-name-compression=false -DCODE=1 -ffunction-sections -fdata-sections -Wl,--gc-sections -flto -o %t.lto %s
+// RUN: %run %t.lto
+// RUN: llvm-profdata merge -o %t.lto.profdata %t.lto.profraw
+// RUN: llvm-profdata show --all-functions %t.lto.profdata | FileCheck %s -check-prefix=PROF
+// RUN: llvm-cov show %t.lto -instr-profile %t.lto.profdata | FileCheck %s -check-prefix=COV
+// RUN: llvm-nm %t.lto | FileCheck %s -check-prefix=NM
+// RUN: llvm-readelf -x __llvm_prf_names %t.lto | FileCheck %s -check-prefix=PRF_NAMES
+// RUN: llvm-readelf -x __llvm_prf_cnts %t.lto | FileCheck %s -check-prefix=PRF_CNTS
+
+// Note: We expect foo() and some of the profiling data associated with it to
+// be garbage collected.
+
+// Note: When there is no code in a program, we expect to see the exact same
+// set of external functions provided by the profile runtime.
+
+// Note: We also check the IR instrumentation and expect foo() to be garbage
+// collected as well.
+
+// RUN: %clang_pgogen=%t.pgo.profraw -fuse-ld=lld -DCODE=1 -ffunction-sections -fdata-sections -Wl,--gc-sections -o %t.pgo %s
+// RUN: %run %t.pgo
+// RUN: llvm-profdata merge -o %t.pgo.profdata %t.pgo.profraw
+// RUN: llvm-profdata show --all-functions %t.pgo.profdata | FileCheck %s -check-prefix=PGO
+// RUN: llvm-nm %t.pgo | FileCheck %s -check-prefix=NM
+
+#ifdef CODE
+
+// COV: [[@LINE+1]]{{ *}}|{{ *}}0|void foo()
+void foo() {}
+
+// COV: [[@LINE+1]]{{ *}}|{{ *}}1|int main
+int main() { return 0; }
+
+#endif // CODE
+
+// NM-NOT: foo
+
+// PROF: Counters:
+// PROF-NEXT: main:
+// PROF-NEXT: Hash:
+// PROF-NEXT: Counters: 1
+// PROF-NEXT: Function count: 1
+// PROF-NEXT: Instrumentation level: Front-end
+// PROF-NEXT: Functions shown: 1
+// PROF-NEXT: Total functions: 1
+// PROF-NEXT: Maximum function count:
+// PROF-NEXT: Maximum internal block count:
+
+// Note: We don't expect the names of garbage collected functions to disappear
+// from __llvm_prf_names, because collectPGOFuncNameStrings() glues the names
+// together.
+
+// PRF_NAMES: Hex dump of section '__llvm_prf_names':
+// PRF_NAMES-NEXT: {{.*}} 0800666f 6f016d61 696e{{.*$}}
+// | | f o o # m a i n
+// | |___________|
+// | |
+// UncompressedLen = 8 |
+// |
+// CompressedLen = 0
+
+// Note: We expect the profile counters for garbage collected functions to also
+// be garbage collected.
+
+// PRF_CNTS: Hex dump of section '__llvm_prf_cnts':
+// PRF_CNTS-NEXT: {{.*}} 00000000 00000000 {{.*$}}
+
+// PGO: Counters:
+// PGO-NEXT: main:
+// PGO-NEXT: Hash:
+// PGO-NEXT: Counters: 1
+// PGO-NEXT: Instrumentation level: IR
+// PGO-NEXT: Functions shown: 1
+// PGO-NEXT: Total functions: 1
+// PGO-NEXT: Maximum function count:
+// PGO-NEXT: Maximum internal block count:
diff --git a/llvm/lib/Transforms/Instrumentation/InstrProfiling.cpp b/llvm/lib/Transforms/Instrumentation/InstrProfiling.cpp
index 9efc7d1ac500..5aa8a1513817 100644
--- a/llvm/lib/Transforms/Instrumentation/InstrProfiling.cpp
+++ b/llvm/lib/Transforms/Instrumentation/InstrProfiling.cpp
@@ -830,9 +830,18 @@ InstrProfiling::getOrCreateRegionCounters(InstrProfIncrementInst *Inc) {
}
std::string DataVarName = getVarName(Inc, getInstrProfDataVarPrefix());
auto MaybeSetComdat = [=](GlobalVariable *GV) {
- if (NeedComdat)
- GV->setComdat(M->getOrInsertComdat(TT.isOSBinFormatCOFF() ? GV->getName()
- : DataVarName));
+ // For ELF, when not using COMDAT, put counters, data and values into
+ // a noduplicates COMDAT which is lowered to a zero-flag section group.
+ // This allows linker GC to discard the entire group when the function
+ // is discarded.
+ bool UseComdat = (NeedComdat || TT.isOSBinFormatELF());
+ if (UseComdat) {
+ auto GroupName = TT.isOSBinFormatCOFF() ? GV->getName() : DataVarName;
+ Comdat *C = M->getOrInsertComdat(GroupName);
+ if (!NeedComdat)
+ C->setSelectionKind(Comdat::NoDuplicates);
+ GV->setComdat(C);
+ }
};
uint64_t NumCounters = Inc->getNumCounters()->getZExtValue();
diff --git a/llvm/test/Instrumentation/InstrProfiling/icall.ll b/llvm/test/Instrumentation/InstrProfiling/icall.ll
index 9d45d7cd5635..311770ae5707 100644
--- a/llvm/test/Instrumentation/InstrProfiling/icall.ll
+++ b/llvm/test/Instrumentation/InstrProfiling/icall.ll
@@ -43,8 +43,8 @@ declare void @llvm.instrprof.value.profile(i8*, i64, i64, i32, i32) #0
attributes #0 = { nounwind }
-; STATIC: @__profvp_foo = private global [1 x i64] zeroinitializer, section "{{[^"]+}}", align 8
-; STATIC: @__profvp_bar = private global [1 x i64] zeroinitializer, section "{{[^"]+}}", comdat($__profd_bar), align 8
+; STATIC: @__profvp_foo = private global [1 x i64] zeroinitializer, section "{{[^"]+}}"
+; STATIC: @__profvp_bar = private global [1 x i64] zeroinitializer, section "{{[^"]+}}", comdat($__profd_bar)
; STATIC: @__llvm_prf_vnodes
; DYN-NOT: @__profvp_foo
diff --git a/llvm/test/Instrumentation/InstrProfiling/linkage.ll b/llvm/test/Instrumentation/InstrProfiling/linkage.ll
index 6320060afe42..8de6a2ec6f0b 100644
--- a/llvm/test/Instrumentation/InstrProfiling/linkage.ll
+++ b/llvm/test/Instrumentation/InstrProfiling/linkage.ll
@@ -1,16 +1,22 @@
;; Check that runtime symbols get appropriate linkage.
-; RUN: opt < %s -mtriple=x86_64-apple-macosx10.10.0 -instrprof -S | FileCheck %s --check-prefixes=POSIX,MACHO
-; RUN: opt < %s -mtriple=x86_64-unknown-linux -instrprof -S | FileCheck %s --check-prefixes=POSIX,LINUX
-; RUN: opt < %s -mtriple=x86_64-unknown-fuchsia -instrprof -S | FileCheck %s --check-prefixes=POSIX,LINUX
+; RUN: opt < %s -mtriple=x86_64-apple-macosx10.10.0 -instrprof -S | FileCheck %s --check-prefixes=MACHO
+; RUN: opt < %s -mtriple=x86_64-unknown-linux -instrprof -S | FileCheck %s --check-prefixes=ELF
+; RUN: opt < %s -mtriple=x86_64-unknown-fuchsia -instrprof -S | FileCheck %s --check-prefixes=ELF
; RUN: opt < %s -mtriple=x86_64-pc-win32-coff -instrprof -S | FileCheck %s --check-prefixes=COFF
-; RUN: opt < %s -mtriple=x86_64-apple-macosx10.10.0 -passes=instrprof -S | FileCheck %s --check-prefixes=POSIX,MACHO
-; RUN: opt < %s -mtriple=x86_64-unknown-linux -passes=instrprof -S | FileCheck %s --check-prefixes=POSIX,LINUX
-; RUN: opt < %s -mtriple=x86_64-unknown-fuchsia -passes=instrprof -S | FileCheck %s --check-prefixes=POSIX,LINUX
+; RUN: opt < %s -mtriple=x86_64-apple-macosx10.10.0 -passes=instrprof -S | FileCheck %s --check-prefixes=MACHO
+; RUN: opt < %s -mtriple=x86_64-unknown-linux -passes=instrprof -S | FileCheck %s --check-prefixes=ELF
+; RUN: opt < %s -mtriple=x86_64-unknown-fuchsia -passes=instrprof -S | FileCheck %s --check-prefixes=ELF
; RUN: opt < %s -mtriple=x86_64-pc-win32-coff -passes=instrprof -S | FileCheck %s --check-prefixes=COFF
; MACHO: @__llvm_profile_runtime = external global i32
-; LINUX-NOT: @__llvm_profile_runtime = external global i32
+; ELF-NOT: @__llvm_profile_runtime = external global i32
+
+; ELF: $__profd_foo = comdat noduplicates
+; ELF: $__profd_foo_weak = comdat noduplicates
+; ELF: $"__profd_linkage.ll:foo_internal" = comdat noduplicates
+; ELF: $__profd_foo_inline = comdat noduplicates
+; ELF: $__profd_foo_extern = comdat any
@__profn_foo = hidden constant [3 x i8] c"foo"
@__profn_foo_weak = weak hidden constant [8 x i8] c"foo_weak"
@@ -18,8 +24,10 @@
@__profn_foo_inline = linkonce_odr hidden constant [10 x i8] c"foo_inline"
@__profn_foo_extern = linkonce_odr hidden constant [10 x i8] c"foo_extern"
-; POSIX: @__profc_foo = hidden global
-; POSIX: @__profd_foo = hidden global
+; ELF: @__profc_foo = hidden global{{.*}}section "__llvm_prf_cnts", comdat($__profd_foo)
+; ELF: @__profd_foo = hidden global{{.*}}section "__llvm_prf_data", comdat
+; MACHO: @__profc_foo = hidden global
+; MACHO: @__profd_foo = hidden global
; COFF: @__profc_foo = internal global
; COFF-NOT: comdat
; COFF: @__profd_foo = internal global
@@ -28,8 +36,10 @@ define void @foo() {
ret void
}
-; POSIX: @__profc_foo_weak = weak hidden global
-; POSIX: @__profd_foo_weak = weak hidden global
+; ELF: @__profc_foo_weak = weak hidden global{{.*}}section "__llvm_prf_cnts", comdat($__profd_foo_weak)
+; ELF: @__profd_foo_weak = weak hidden global{{.*}}section "__llvm_prf_data", comdat
+; MACHO: @__profc_foo_weak = weak hidden global
+; MACHO: @__profd_foo_weak = weak hidden global
; COFF: @__profc_foo_weak = internal global
; COFF: @__profd_foo_weak = internal global
define weak void @foo_weak() {
@@ -37,8 +47,10 @@ define weak void @foo_weak() {
ret void
}
-; POSIX: @"__profc_linkage.ll:foo_internal" = internal global
-; POSIX: @"__profd_linkage.ll:foo_internal" = internal global
+; ELF: @"__profc_linkage.ll:foo_internal" = internal global{{.*}}section "__llvm_prf_cnts", comdat($"__profd_linkage.ll:foo_internal")
+; ELF: @"__profd_linkage.ll:foo_internal" = internal global{{.*}}section "__llvm_prf_data", comdat
+; MACHO: @"__profc_linkage.ll:foo_internal" = internal global
+; MACHO: @"__profd_linkage.ll:foo_internal" = internal global
; COFF: @"__profc_linkage.ll:foo_internal" = internal global
; COFF: @"__profd_linkage.ll:foo_internal" = internal global
define internal void @foo_internal() {
@@ -46,8 +58,10 @@ define internal void @foo_internal() {
ret void
}
-; POSIX: @__profc_foo_inline = linkonce_odr hidden global
-; POSIX: @__profd_foo_inline = linkonce_odr hidden global
+; ELF: @__profc_foo_inline = linkonce_odr hidden global{{.*}}section "__llvm_prf_cnts", comdat($__profd_foo_inline)
+; ELF: @__profd_foo_inline = linkonce_odr hidden global{{.*}}section "__llvm_prf_data", comdat
+; MACHO: @__profc_foo_inline = linkonce_odr hidden global
+; MACHO: @__profd_foo_inline = linkonce_odr hidden global
; COFF: @__profc_foo_inline = internal global{{.*}} section ".lprfc$M", align 8
; COFF: @__profd_foo_inline = internal global{{.*}} section ".lprfd$M", align 8
define linkonce_odr void @foo_inline() {
@@ -55,8 +69,8 @@ define linkonce_odr void @foo_inline() {
ret void
}
-; LINUX: @__profc_foo_extern = linkonce_odr hidden global {{.*}}section "__llvm_prf_cnts", comdat($__profd_foo_extern), align 8
-; LINUX: @__profd_foo_extern = linkonce_odr hidden global {{.*}}section "__llvm_prf_data", comdat, align 8
+; ELF: @__profc_foo_extern = linkonce_odr hidden global {{.*}}section "__llvm_prf_cnts", comdat($__profd_foo_extern), align 8
+; ELF: @__profd_foo_extern = linkonce_odr hidden global {{.*}}section "__llvm_prf_data", comdat, align 8
; MACHO: @__profc_foo_extern = linkonce_odr hidden global
; MACHO: @__profd_foo_extern = linkonce_odr hidden global
; COFF: @__profc_foo_extern = linkonce_odr hidden global {{.*}}section ".lprfc$M", comdat, align 8
@@ -73,5 +87,5 @@ declare void @llvm.instrprof.increment(i8*, i64, i32, i32)
; MACHO: ret i32 %[[REG]]
; MACHO: }
; COFF: define linkonce_odr hidden i32 @__llvm_profile_runtime_user() {{.*}} comdat {
-; LINUX-NOT: define linkonce_odr hidden i32 @__llvm_profile_runtime_user() {{.*}} {
-; LINUX-NOT: %[[REG:.*]] = load i32, i32* @__llvm_profile_runtime
+; ELF-NOT: define linkonce_odr hidden i32 @__llvm_profile_runtime_user() {{.*}} {
+; ELF-NOT: %[[REG:.*]] = load i32, i32* @__llvm_profile_runtime
diff --git a/llvm/test/Instrumentation/InstrProfiling/platform.ll b/llvm/test/Instrumentation/InstrProfiling/platform.ll
index 8c546075963b..a440c3e54d23 100644
--- a/llvm/test/Instrumentation/InstrProfiling/platform.ll
+++ b/llvm/test/Instrumentation/InstrProfiling/platform.ll
@@ -19,11 +19,11 @@
; WINDOWS-NOT: __profn_foo
; MACHO: @__profc_foo = hidden global [1 x i64] zeroinitializer, section "__DATA,__llvm_prf_cnts", align 8
-; ELF: @__profc_foo = hidden global [1 x i64] zeroinitializer, section "__llvm_prf_cnts", align 8
+; ELF: @__profc_foo = hidden global [1 x i64] zeroinitializer, section "__llvm_prf_cnts", comdat($__profd_foo), align 8
; WINDOWS: @__profc_foo = internal global [1 x i64] zeroinitializer, section ".lprfc$M", align 8
; MACHO: @__profd_foo = hidden {{.*}}, section "__DATA,__llvm_prf_data,regular,live_support", align 8
-; ELF: @__profd_foo = hidden {{.*}}, section "__llvm_prf_data", align 8
+; ELF: @__profd_foo = hidden {{.*}}, section "__llvm_prf_data", comdat, align 8
; WINDOWS: @__profd_foo = internal global {{.*}}, section ".lprfd$M", align 8
; ELF: @__llvm_prf_nm = private constant [{{.*}} x i8] c"{{.*}}", section "{{.*}}__llvm_prf_names", align 1
diff --git a/llvm/test/Transforms/PGOProfile/counter_promo.ll b/llvm/test/Transforms/PGOProfile/counter_promo.ll
index 55930c1be166..a477970830be 100644
--- a/llvm/test/Transforms/PGOProfile/counter_promo.ll
+++ b/llvm/test/Transforms/PGOProfile/counter_promo.ll
@@ -60,7 +60,7 @@ bb12: ; preds = %bb9
; ATOMIC_PROMO: atomicrmw add {{.*}} @__profc_foo{{.*}}0), i64 %[[LIVEOUT1]] seq_cst
; ATOMIC_PROMO-NEXT: atomicrmw add {{.*}} @__profc_foo{{.*}}1), i64 %[[LIVEOUT2]] seq_cst
; ATOMIC_PROMO-NEXT: atomicrmw add {{.*}} @__profc_foo{{.*}}2), i64 %[[LIVEOUT3]] seq_cst
-; PROMO-NOT: @__profc_foo
+; PROMO-NOT: @__profc_foo{{.*}})
}
diff --git a/llvm/test/Transforms/PGOProfile/counter_promo_mexits.ll b/llvm/test/Transforms/PGOProfile/counter_promo_mexits.ll
index bb799757a47c..8e907acb34da 100644
--- a/llvm/test/Transforms/PGOProfile/counter_promo_mexits.ll
+++ b/llvm/test/Transforms/PGOProfile/counter_promo_mexits.ll
@@ -69,7 +69,7 @@ bb15_0: ; preds = %bb11
; PROMO-NEXT: %pgocount{{.*}} = load {{.*}} @__profc_foo{{.*}} 4)
; PROMO-NEXT: add
; PROMO-NEXT: store {{.*}}@__profc_foo{{.*}}4)
-; PROMO-NOT: @__profc_foo
+; PROMO-NOT: @__profc_foo{{.*}})
bb15: ; preds = %bb14, %bb4
More information about the llvm-commits
mailing list