[llvm] 39b3c41 - [InstrProfiling] Use !associated metadata for counters, data and values
Petr Hosek via llvm-commits
llvm-commits at lists.llvm.org
Mon Jun 8 13:36:23 PDT 2020
Author: Petr Hosek
Date: 2020-06-08T13:35:56-07:00
New Revision: 39b3c41b65302a969fa5507402976a255a07c158
URL: https://github.com/llvm/llvm-project/commit/39b3c41b65302a969fa5507402976a255a07c158
DIFF: https://github.com/llvm/llvm-project/commit/39b3c41b65302a969fa5507402976a255a07c158.diff
LOG: [InstrProfiling] Use !associated metadata for counters, data and values
The !associated metadata may be attached to a global object declaration
with a single argument that references another global object. This
metadata prevents discarding of the global object in linker GC unless
the referenced object is also discarded.
Furthermore, when a function symbol is discarded by the linker, setting
up !associated metadata allows linker to discard counters, data and
values associated with that function symbol. This is not possible today
because there's metadata to guide the linker. This approach is also used
by other instrumentations like sanitizers.
Note that !associated metadata is only supported by ELF, it does not have
any effect on non-ELF targets.
Differential Revision: https://reviews.llvm.org/D76802
Added:
compiler-rt/test/profile/instrprof-gc-sections.c
llvm/test/Instrumentation/InstrProfiling/associated.ll
Modified:
compiler-rt/lib/profile/InstrProfilingPlatformLinux.c
llvm/lib/Transforms/Instrumentation/InstrProfiling.cpp
llvm/test/Transforms/PGOProfile/counter_promo.ll
llvm/test/Transforms/PGOProfile/counter_promo_mexits.ll
Removed:
################################################################################
diff --git a/compiler-rt/lib/profile/InstrProfilingPlatformLinux.c b/compiler-rt/lib/profile/InstrProfilingPlatformLinux.c
index becfe1fd9f5a..4e3230bfb24c 100644
--- a/compiler-rt/lib/profile/InstrProfilingPlatformLinux.c
+++ b/compiler-rt/lib/profile/InstrProfilingPlatformLinux.c
@@ -24,27 +24,21 @@
#define PROF_VNODES_STOP INSTR_PROF_SECT_STOP(INSTR_PROF_VNODES_COMMON)
/* Declare section start and stop symbols for various sections
- * generated by compiler instrumentation.
+ * generated by compiler instrumentation. These symbols are
+ * declared as weak, which means that they'll end up as NULL if
+ * those sections are empty, and any code that iterates over the
+ * content using __llvm_profile_begin_* and __llvm_profile_end_*
+ * functions defined below will be a no-op.
*/
-extern __llvm_profile_data PROF_DATA_START COMPILER_RT_VISIBILITY;
-extern __llvm_profile_data PROF_DATA_STOP COMPILER_RT_VISIBILITY;
-extern uint64_t PROF_CNTS_START COMPILER_RT_VISIBILITY;
-extern uint64_t PROF_CNTS_STOP COMPILER_RT_VISIBILITY;
-extern uint32_t PROF_ORDERFILE_START COMPILER_RT_VISIBILITY;
-extern char PROF_NAME_START COMPILER_RT_VISIBILITY;
-extern char PROF_NAME_STOP COMPILER_RT_VISIBILITY;
-extern ValueProfNode PROF_VNODES_START COMPILER_RT_VISIBILITY;
-extern ValueProfNode PROF_VNODES_STOP COMPILER_RT_VISIBILITY;
-
-/* Add dummy data to ensure the section is always created. */
-__llvm_profile_data
- __prof_data_sect_data[0] COMPILER_RT_SECTION(INSTR_PROF_DATA_SECT_NAME);
-uint64_t
- __prof_cnts_sect_data[0] COMPILER_RT_SECTION(INSTR_PROF_CNTS_SECT_NAME);
-uint32_t
- __prof_orderfile_sect_data[0] COMPILER_RT_SECTION(INSTR_PROF_ORDERFILE_SECT_NAME);
-char __prof_nms_sect_data[0] COMPILER_RT_SECTION(INSTR_PROF_NAME_SECT_NAME);
-ValueProfNode __prof_vnodes_sect_data[0] COMPILER_RT_SECTION(INSTR_PROF_VNODES_SECT_NAME);
+extern __llvm_profile_data PROF_DATA_START COMPILER_RT_VISIBILITY COMPILER_RT_WEAK;
+extern __llvm_profile_data PROF_DATA_STOP COMPILER_RT_VISIBILITY COMPILER_RT_WEAK;
+extern uint64_t PROF_CNTS_START COMPILER_RT_VISIBILITY COMPILER_RT_WEAK;
+extern uint64_t PROF_CNTS_STOP COMPILER_RT_VISIBILITY COMPILER_RT_WEAK;
+extern uint32_t PROF_ORDERFILE_START COMPILER_RT_VISIBILITY COMPILER_RT_WEAK;
+extern char PROF_NAME_START COMPILER_RT_VISIBILITY COMPILER_RT_WEAK;
+extern char PROF_NAME_STOP COMPILER_RT_VISIBILITY COMPILER_RT_WEAK;
+extern ValueProfNode PROF_VNODES_START COMPILER_RT_VISIBILITY COMPILER_RT_WEAK;
+extern ValueProfNode PROF_VNODES_STOP COMPILER_RT_VISIBILITY COMPILER_RT_WEAK;
COMPILER_RT_VISIBILITY const __llvm_profile_data *
__llvm_profile_begin_data(void) {
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..a3d0fa466c30
--- /dev/null
+++ b/compiler-rt/test/profile/instrprof-gc-sections.c
@@ -0,0 +1,91 @@
+// 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.
+
+// RUN: %clang_profgen -fcoverage-mapping -ffunction-sections -fdata-sections -Wl,--gc-sections -shared -o %t.nocode.so %s
+// RUN: llvm-nm -jgU %t.nocode.so | grep -vE "__start_.*|__stop_.*" > %t.nocode.syms
+// RUN: llvm-nm -jgU %t | grep -vE "main|foo|_start|__libc_.*" > %t.code.syms
+// RUN:
diff %t.nocode.syms %t.code.syms
+
+// 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 ceceafa86030..06ccf439501a 100644
--- a/llvm/lib/Transforms/Instrumentation/InstrProfiling.cpp
+++ b/llvm/lib/Transforms/Instrumentation/InstrProfiling.cpp
@@ -844,6 +844,8 @@ InstrProfiling::getOrCreateRegionCounters(InstrProfIncrementInst *Inc) {
CounterPtr->setAlignment(Align(8));
MaybeSetComdat(CounterPtr);
CounterPtr->setLinkage(Linkage);
+ CounterPtr->setMetadata(LLVMContext::MD_associated,
+ MDNode::get(Ctx, ValueAsMetadata::get(CounterPtr)));
auto *Int8PtrTy = Type::getInt8PtrTy(Ctx);
// Allocate statically the array of pointers to value profile nodes for
@@ -865,6 +867,8 @@ InstrProfiling::getOrCreateRegionCounters(InstrProfIncrementInst *Inc) {
getInstrProfSectionName(IPSK_vals, TT.getObjectFormat()));
ValuesVar->setAlignment(Align(8));
MaybeSetComdat(ValuesVar);
+ ValuesVar->setMetadata(LLVMContext::MD_associated,
+ MDNode::get(Ctx, ValueAsMetadata::get(CounterPtr)));
ValuesPtrExpr =
ConstantExpr::getBitCast(ValuesVar, Type::getInt8PtrTy(Ctx));
}
@@ -899,6 +903,8 @@ InstrProfiling::getOrCreateRegionCounters(InstrProfIncrementInst *Inc) {
Data->setAlignment(Align(INSTR_PROF_DATA_ALIGNMENT));
MaybeSetComdat(Data);
Data->setLinkage(Linkage);
+ Data->setMetadata(LLVMContext::MD_associated,
+ MDNode::get(Ctx, ValueAsMetadata::get(CounterPtr)));
PD.RegionCounters = CounterPtr;
PD.DataVar = Data;
diff --git a/llvm/test/Instrumentation/InstrProfiling/associated.ll b/llvm/test/Instrumentation/InstrProfiling/associated.ll
new file mode 100644
index 000000000000..9ee2d0c7e301
--- /dev/null
+++ b/llvm/test/Instrumentation/InstrProfiling/associated.ll
@@ -0,0 +1,18 @@
+; RUN: opt < %s -mtriple=x86_64-unknown-linux -instrprof -S | FileCheck %s
+; RUN: opt < %s -mtriple=x86_64-unknown-linux -passes=instrprof -S | FileCheck %s
+; RUN: opt < %s -mtriple=x86_64-unknown-linux -pgo-instr-gen -S | FileCheck %s
+; RUN: opt < %s -mtriple=x86_64-unknown-linux -passes=pgo-instr-gen -S | FileCheck %s
+
+ at __profn_foo = hidden constant [3 x i8] c"foo"
+
+; CHECK: @__profc_foo = hidden global [1 x i64] zeroinitializer, section "__llvm_prf_cnts", align 8, !associated !0
+; CHECK: @__profd_foo = hidden global {{.*}}, section "__llvm_prf_data", align 8, !associated !0
+
+define void @foo() {
+ call void @llvm.instrprof.increment(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @__profn_foo, i32 0, i32 0), i64 0, i32 1, i32 0)
+ ret void
+}
+
+declare void @llvm.instrprof.increment(i8*, i64, i32, i32)
+
+; CHECK: !0 = !{[1 x i64]* @__profc_foo}
diff --git a/llvm/test/Transforms/PGOProfile/counter_promo.ll b/llvm/test/Transforms/PGOProfile/counter_promo.ll
index 812d0fefaa79..da08ace84933 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