[InstrProfiling] Make CountersPtr in __profd_ relative

MaskRay · MaskRay · commit a1532ed27582 · 2021-07-30T11:52:18.000-07:00
Change `CountersPtr` in `__profd_` to a label difference, which is a link-time constant. On ELF, when linking a shared object, this requires that `__profc_` is either private or linkonce/linkonce_odr hidden. On COFF, we need D104564 so that `.quad a-b` (64-bit label difference) can lower to a 32-bit PC-relative relocation. ``` # ELF: R_X86_64_PC64 (PC-relative) .quad .L__profc_foo-.L__profd_foo # Mach-O: a pair of 8-byte X86_64_RELOC_UNSIGNED and X86_64_RELOC_SUBTRACTOR .quad l___profc_foo-l___profd_foo # COFF: we actually use IMAGE_REL_AMD64_REL32/IMAGE_REL_ARM64_REL32 so # the high 32-bit value is zero even if .L__profc_foo < .L__profd_foo # As compensation, we truncate CountersDelta in the header so that # __llvm_profile_merge_from_buffer and llvm-profdata reader keep working. .quad .L__profc_foo-.L__profd_foo ``` (Note: link.exe sorts `.lprfc` before `.lprfd` even if the object writer has `.lprfd` before `.lprfc`, so we cannot work around by reordering `.lprfc` and `.lprfd`.) With this change, a stage 2 (`-DLLVM_TARGETS_TO_BUILD=X86 -DLLVM_BUILD_INSTRUMENTED=IR`) `ld -pie` linked clang is 1.74% smaller due to fewer R_X86_64_RELATIVE relocations. ``` % readelf -r pie | awk '$3~/R.*/{s[$3]++} END {for (k in s) print k, s[k]}' R_X86_64_JUMP_SLO 331 R_X86_64_TPOFF64 2 R_X86_64_RELATIVE 476059 # was: 607712 R_X86_64_64 2616 R_X86_64_GLOB_DAT 31 ``` The absolute function address (used by llvm-profdata to collect indirect call targets) can be converted to relative as well, but is not done in this patch. Differential Revision: https://reviews.llvm.org/D104556
diff --git a/clang/test/Profile/c-linkage-available_externally.c b/clang/test/Profile/c-linkage-available_externally.c
@@ -3,7 +3,7 @@
 // RUN: %clang_cc1 -O2 -triple x86_64-apple-macosx10.9 -main-file-name c-linkage-available_externally.c %s -o - -emit-llvm -fprofile-instrument=clang | FileCheck %s
 
 // CHECK: @__profc_foo = linkonce_odr hidden global [1 x i64] zeroinitializer, section "__DATA,__llvm_prf_cnts", align 8
-// CHECK: @__profd_foo = linkonce_odr hidden global {{.*}} i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__profc_foo, i32 0, i32 0){{.*}}, section "__DATA,__llvm_prf_data,regular,live_support", align 8
+// CHECK: @__profd_foo = linkonce_odr hidden global {{.*}} i64 sub (i64 ptrtoint ([1 x i64]* @__profc_foo to i64), i64 ptrtoint ({ i64, i64, i64, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i64)), {{.*}}, section "__DATA,__llvm_prf_data,regular,live_support", align 8
 inline int foo(void) { return 1; }
 
 int main(void) {
diff --git a/compiler-rt/include/profile/InstrProfData.inc b/compiler-rt/include/profile/InstrProfData.inc
@@ -75,9 +75,7 @@ INSTR_PROF_DATA(const uint64_t, llvm::Type::getInt64Ty(Ctx), NameRef, \
 INSTR_PROF_DATA(const uint64_t, llvm::Type::getInt64Ty(Ctx), FuncHash, \
                 ConstantInt::get(llvm::Type::getInt64Ty(Ctx), \
                 Inc->getHash()->getZExtValue()))
-INSTR_PROF_DATA(const IntPtrT, llvm::Type::getInt64PtrTy(Ctx), CounterPtr, \
-                ConstantExpr::getBitCast(CounterPtr, \
-                llvm::Type::getInt64PtrTy(Ctx)))
+INSTR_PROF_DATA(const IntPtrT, IntPtrTy, CounterPtr, RelativeCounterPtr)
 /* This is used to map function pointers for the indirect call targets to
  * function name hashes during the conversion from raw to merged profile
  * data.
@@ -134,7 +132,8 @@ INSTR_PROF_RAW_HEADER(uint64_t, PaddingBytesBeforeCounters, PaddingBytesBeforeCo
 INSTR_PROF_RAW_HEADER(uint64_t, CountersSize, CountersSize)
 INSTR_PROF_RAW_HEADER(uint64_t, PaddingBytesAfterCounters, PaddingBytesAfterCounters)
 INSTR_PROF_RAW_HEADER(uint64_t, NamesSize,  NamesSize)
-INSTR_PROF_RAW_HEADER(uint64_t, CountersDelta, (uintptr_t)CountersBegin)
+INSTR_PROF_RAW_HEADER(uint64_t, CountersDelta,
+                      (uintptr_t)CountersBegin - (uintptr_t)DataBegin)
 INSTR_PROF_RAW_HEADER(uint64_t, NamesDelta, (uintptr_t)NamesBegin)
 INSTR_PROF_RAW_HEADER(uint64_t, ValueKindLast, IPVK_Last)
 INSTR_PROF_RAW_HEADER(uint64_t, BinaryIdsSize, __llvm_write_binary_ids(NULL))
diff --git a/compiler-rt/lib/profile/InstrProfilingMerge.c b/compiler-rt/lib/profile/InstrProfilingMerge.c
@@ -81,6 +81,14 @@ int __llvm_profile_check_compatibility(const char *ProfileData,
   return 0;
 }
 
+static uintptr_t signextIfWin64(void *V) {
+#ifdef _WIN64
+  return (uintptr_t)(int32_t)(uintptr_t)V;
+#else
+  return (uintptr_t)V;
+#endif
+}
+
 COMPILER_RT_VISIBILITY
 int __llvm_profile_merge_from_buffer(const char *ProfileData,
                                      uint64_t ProfileSize) {
@@ -89,6 +97,7 @@ int __llvm_profile_merge_from_buffer(const char *ProfileData,
   uint64_t *SrcCountersStart;
   const char *SrcNameStart;
   const char *SrcValueProfDataStart, *SrcValueProfData;
+  uintptr_t CountersDelta = Header->CountersDelta;
 
   SrcDataStart =
       (__llvm_profile_data *)(ProfileData + sizeof(__llvm_profile_header));
@@ -105,15 +114,30 @@ int __llvm_profile_merge_from_buffer(const char *ProfileData,
       DstData = (__llvm_profile_data *)__llvm_profile_begin_data(),
       SrcValueProfData = SrcValueProfDataStart;
        SrcData < SrcDataEnd; ++SrcData, ++DstData) {
-    uint64_t *DstCounters = (uint64_t *)DstData->CounterPtr;
+    // For the in-memory destination, CounterPtr is the distance from the start
+    // address of the data to the start address of the counter. On WIN64,
+    // CounterPtr is a truncated 32-bit value due to COFF limitation. Sign
+    // extend CounterPtr to get the original value.
+    uint64_t *DstCounters =
+        (uint64_t *)((uintptr_t)DstData + signextIfWin64(DstData->CounterPtr));
     unsigned NVK = 0;
 
+    // SrcData is a serialized representation of the memory image. We need to
+    // compute the in-buffer counter offset from the in-memory address distance.
+    // The initial CountersDelta is the in-memory address difference
+    // start(__llvm_prf_cnts)-start(__llvm_prf_data), so SrcData->CounterPtr -
+    // CountersDelta computes the offset into the in-buffer counter section.
+    //
+    // On WIN64, CountersDelta is truncated as well, so no need for signext.
+    uint64_t *SrcCounters =
+        SrcCountersStart +
+        ((uintptr_t)SrcData->CounterPtr - CountersDelta) / sizeof(uint64_t);
+    // CountersDelta needs to be decreased as we advance to the next data
+    // record.
+    CountersDelta -= sizeof(*SrcData);
     unsigned NC = SrcData->NumCounters;
     if (NC == 0)
       return 1;
-    uint64_t *SrcCounters = SrcCountersStart + ((size_t)SrcData->CounterPtr -
-                                                Header->CountersDelta) /
-                                                   sizeof(uint64_t);
     if (SrcCounters < SrcCountersStart ||
         (const char *)SrcCounters >= SrcNameStart ||
         (const char *)(SrcCounters + NC) > SrcNameStart)
diff --git a/compiler-rt/lib/profile/InstrProfilingWriter.c b/compiler-rt/lib/profile/InstrProfilingWriter.c
@@ -283,6 +283,12 @@ lprofWriteDataImpl(ProfDataWriter *Writer, const __llvm_profile_data *DataBegin,
 #define INSTR_PROF_RAW_HEADER(Type, Name, Init) Header.Name = Init;
 #include "profile/InstrProfData.inc"
 
+  /* On WIN64, label differences are truncated 32-bit values. Truncate
+   * CountersDelta to match. */
+#ifdef _WIN64
+  Header.CountersDelta = (void *)(uint32_t)Header.CountersDelta;
+#endif
+
   /* Write the profile header. */
   ProfDataIOVec IOVec[] = {{&Header, sizeof(__llvm_profile_header), 1, 0}};
   if (Writer->Write(Writer, IOVec, sizeof(IOVec) / sizeof(*IOVec)))
diff --git a/llvm/include/llvm/ProfileData/InstrProfData.inc b/llvm/include/llvm/ProfileData/InstrProfData.inc
@@ -75,9 +75,7 @@ INSTR_PROF_DATA(const uint64_t, llvm::Type::getInt64Ty(Ctx), NameRef, \
 INSTR_PROF_DATA(const uint64_t, llvm::Type::getInt64Ty(Ctx), FuncHash, \
                 ConstantInt::get(llvm::Type::getInt64Ty(Ctx), \
                 Inc->getHash()->getZExtValue()))
-INSTR_PROF_DATA(const IntPtrT, llvm::Type::getInt64PtrTy(Ctx), CounterPtr, \
-                ConstantExpr::getBitCast(CounterPtr, \
-                llvm::Type::getInt64PtrTy(Ctx)))
+INSTR_PROF_DATA(const IntPtrT, IntPtrTy, CounterPtr, RelativeCounterPtr)
 /* This is used to map function pointers for the indirect call targets to
  * function name hashes during the conversion from raw to merged profile
  * data.
@@ -134,7 +132,8 @@ INSTR_PROF_RAW_HEADER(uint64_t, PaddingBytesBeforeCounters, PaddingBytesBeforeCo
 INSTR_PROF_RAW_HEADER(uint64_t, CountersSize, CountersSize)
 INSTR_PROF_RAW_HEADER(uint64_t, PaddingBytesAfterCounters, PaddingBytesAfterCounters)
 INSTR_PROF_RAW_HEADER(uint64_t, NamesSize,  NamesSize)
-INSTR_PROF_RAW_HEADER(uint64_t, CountersDelta, (uintptr_t)CountersBegin)
+INSTR_PROF_RAW_HEADER(uint64_t, CountersDelta,
+                      (uintptr_t)CountersBegin - (uintptr_t)DataBegin)
 INSTR_PROF_RAW_HEADER(uint64_t, NamesDelta, (uintptr_t)NamesBegin)
 INSTR_PROF_RAW_HEADER(uint64_t, ValueKindLast, IPVK_Last)
 INSTR_PROF_RAW_HEADER(uint64_t, BinaryIdsSize, __llvm_write_binary_ids(NULL))
diff --git a/llvm/lib/ProfileData/InstrProfReader.cpp b/llvm/lib/ProfileData/InstrProfReader.cpp
@@ -437,7 +437,15 @@ Error RawInstrProfReader<IntPtrT>::readRawCounts(
   // may itself be corrupt.
   if (MaxNumCounters < 0 || NumCounters > (uint32_t)MaxNumCounters)
     return error(instrprof_error::malformed);
+
+  // We need to compute the in-buffer counter offset from the in-memory address
+  // distance. The initial CountersDelta is the in-memory address difference
+  // start(__llvm_prf_cnts)-start(__llvm_prf_data), so SrcData->CounterPtr -
+  // CountersDelta computes the offset into the in-buffer counter section.
+  //
+  // CountersDelta decreases as we advance to the next data record.
   ptrdiff_t CounterOffset = getCounterOffset(CounterPtr);
+  CountersDelta -= sizeof(*Data);
   if (CounterOffset < 0 || CounterOffset > MaxNumCounters ||
       ((uint32_t)CounterOffset + NumCounters) > (uint32_t)MaxNumCounters)
     return error(instrprof_error::malformed);
diff --git a/llvm/lib/Transforms/Instrumentation/InstrProfiling.cpp b/llvm/lib/Transforms/Instrumentation/InstrProfiling.cpp
@@ -920,6 +920,7 @@ InstrProfiling::getOrCreateRegionCounters(InstrProfIncrementInst *Inc) {
   }
 
   // Create data variable.
+  auto *IntPtrTy = M->getDataLayout().getIntPtrType(M->getContext());
   auto *Int16Ty = Type::getInt16Ty(Ctx);
   auto *Int16ArrayTy = ArrayType::get(Int16Ty, IPVK_Last + 1);
   Type *DataTypes[] = {
@@ -936,10 +937,6 @@ InstrProfiling::getOrCreateRegionCounters(InstrProfIncrementInst *Inc) {
   for (uint32_t Kind = IPVK_First; Kind <= IPVK_Last; ++Kind)
     Int16ArrayVals[Kind] = ConstantInt::get(Int16Ty, PD.NumValueSites[Kind]);
 
-  Constant *DataVals[] = {
-#define INSTR_PROF_DATA(Type, LLVMType, Name, Init) Init,
-#include "llvm/ProfileData/InstrProfData.inc"
-  };
   // If the data variable is not referenced by code (if we don't emit
   // @llvm.instrprof.value.profile, NS will be 0), and the counter keeps the
   // data variable live under linker GC, the data variable can be private. This
@@ -953,8 +950,19 @@ InstrProfiling::getOrCreateRegionCounters(InstrProfIncrementInst *Inc) {
     Visibility = GlobalValue::DefaultVisibility;
   }
   auto *Data =
-      new GlobalVariable(*M, DataTy, false, Linkage,
-                         ConstantStruct::get(DataTy, DataVals), DataVarName);
+      new GlobalVariable(*M, DataTy, false, Linkage, nullptr, DataVarName);
+  // Reference the counter variable with a label difference (link-time
+  // constant).
+  auto *RelativeCounterPtr =
+      ConstantExpr::getSub(ConstantExpr::getPtrToInt(CounterPtr, IntPtrTy),
+                           ConstantExpr::getPtrToInt(Data, IntPtrTy));
+
+  Constant *DataVals[] = {
+#define INSTR_PROF_DATA(Type, LLVMType, Name, Init) Init,
+#include "llvm/ProfileData/InstrProfData.inc"
+  };
+  Data->setInitializer(ConstantStruct::get(DataTy, DataVals));
+
   Data->setVisibility(Visibility);
   Data->setSection(getInstrProfSectionName(IPSK_data, TT.getObjectFormat()));
   Data->setAlignment(Align(INSTR_PROF_DATA_ALIGNMENT));
diff --git a/llvm/test/Instrumentation/InstrProfiling/icall.ll b/llvm/test/Instrumentation/InstrProfiling/icall.ll
@@ -56,9 +56,9 @@ attributes #0 = { nounwind }
 ; STATIC-SAME:   @__llvm_prf_vnodes
 ; STATIC-SAME:   @__llvm_prf_nm
 
-; STATIC: call void @__llvm_profile_instrument_target(i64 %3, i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*), i32 0)
-; STATIC-EXT: call void @__llvm_profile_instrument_target(i64 %3, i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*), i32 zeroext 0)
-; STATIC-SEXT: call void @__llvm_profile_instrument_target(i64 %3, i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*), i32 signext 0)
+; STATIC: call void @__llvm_profile_instrument_target(i64 %3, i8* bitcast ({ i64, i64, i64, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*), i32 0)
+; STATIC-EXT: call void @__llvm_profile_instrument_target(i64 %3, i8* bitcast ({ i64, i64, i64, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*), i32 zeroext 0)
+; STATIC-SEXT: call void @__llvm_profile_instrument_target(i64 %3, i8* bitcast ({ i64, i64, i64, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*), i32 signext 0)
 
 ; STATIC: declare void @__llvm_profile_instrument_target(i64, i8*, i32)
 ; STATIC-EXT: declare void @__llvm_profile_instrument_target(i64, i8*, i32 zeroext)
diff --git a/llvm/test/Instrumentation/InstrProfiling/profiling.ll b/llvm/test/Instrumentation/InstrProfiling/profiling.ll
@@ -18,7 +18,7 @@
 ; CHECK-NOT: __profn_baz
 
 ; ELF:   @__profc_foo = private global [1 x i64] zeroinitializer, section "__llvm_prf_cnts", comdat, align 8
-; ELF:   @__profd_foo = private {{.*}}, section "__llvm_prf_data", comdat($__profc_foo), align 8
+; ELF:   @__profd_foo = private global { i64, i64, i64, i8*, i8*, i32, [2 x i16] } { i64 [[#]], i64 0, i64 sub (i64 ptrtoint ([1 x i64]* @__profc_foo to i64), i64 ptrtoint ({ i64, i64, i64, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i64)), i8* null, i8* null, i32 1, [2 x i16] zeroinitializer }, section "__llvm_prf_data", comdat($__profc_foo), align 8
 ; MACHO: @__profc_foo = private global [1 x i64] zeroinitializer, section "__DATA,__llvm_prf_cnts", align 8
 ; MACHO: @__profd_foo = private {{.*}}, section "__DATA,__llvm_prf_data,regular,live_support", align 8
 ; WIN:   @__profc_foo = private global [1 x i64] zeroinitializer, section ".lprfc$M", align 8
@@ -59,9 +59,9 @@ declare void @llvm.instrprof.increment(i8*, i64, i32, i32)
 ; WIN:   @llvm.compiler.used = appending global {{.*}} @__llvm_profile_runtime_user {{.*}} @__profd_foo {{.*}} @__profd_bar {{.*}} @__profd_baz
 
 ; ELF_GENERIC:      define internal void @__llvm_profile_register_functions() unnamed_addr {
-; ELF_GENERIC-NEXT:   call void @__llvm_profile_register_function(i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*))
-; ELF_GENERIC-NEXT:   call void @__llvm_profile_register_function(i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_bar to i8*))
-; ELF_GENERIC-NEXT:   call void @__llvm_profile_register_function(i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_baz to i8*))
+; ELF_GENERIC-NEXT:   call void @__llvm_profile_register_function(i8* bitcast ({ i64, i64, i64, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*))
+; ELF_GENERIC-NEXT:   call void @__llvm_profile_register_function(i8* bitcast ({ i64, i64, i64, i8*, i8*, i32, [2 x i16] }* @__profd_bar to i8*))
+; ELF_GENERIC-NEXT:   call void @__llvm_profile_register_function(i8* bitcast ({ i64, i64, i64, i8*, i8*, i32, [2 x i16] }* @__profd_baz to i8*))
 ; ELF_GENERIC-NEXT:   call void @__llvm_profile_register_names_function(i8* getelementptr inbounds {{.*}} @__llvm_prf_nm
 ; ELF_GENERIC-NEXT:   ret void
 ; ELF_GENERIC-NEXT: }
diff --git a/llvm/test/Transforms/PGOProfile/comdat_internal.ll b/llvm/test/Transforms/PGOProfile/comdat_internal.ll
@@ -14,7 +14,7 @@ $foo = comdat any
 ; CHECK: @__llvm_profile_raw_version = constant i64 {{[0-9]+}}, comdat
 ; CHECK-NOT: __profn__stdin__foo
 ; CHECK: @__profc__stdin__foo.[[#FOO_HASH]] = private global [1 x i64] zeroinitializer, section "__llvm_prf_cnts", comdat, align 8
-; CHECK: @__profd__stdin__foo.[[#FOO_HASH]] = private global { i64, i64, i64*, i8*, i8*, i32, [2 x i16] } { i64 -5640069336071256030, i64 [[#FOO_HASH]], i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__profc__stdin__foo.[[#FOO_HASH]], i32 0, i32 0), i8* null
+; CHECK: @__profd__stdin__foo.[[#FOO_HASH]] = private global { i64, i64, i64, i8*, i8*, i32, [2 x i16] } { i64 -5640069336071256030, i64 [[#FOO_HASH]], i64 sub (i64 ptrtoint ([1 x i64]* @__profc__stdin__foo.742261418966908927 to i64), i64 ptrtoint ({ i64, i64, i64, i8*, i8*, i32, [2 x i16] }* @__profd__stdin__foo.742261418966908927 to i64)), i8* null
 ; CHECK-NOT: bitcast (i32 ()* @foo to i8*)
 ; CHECK-SAME: , i8* null, i32 1, [2 x i16] zeroinitializer }, section "__llvm_prf_data", comdat($__profc__stdin__foo.[[#FOO_HASH]]), align 8
 ; CHECK: @__llvm_prf_nm
diff --git a/llvm/test/Transforms/PGOProfile/indirect_call_profile.ll b/llvm/test/Transforms/PGOProfile/indirect_call_profile.ll
@@ -39,7 +39,7 @@ entry:
   %tmp = load void ()*, void ()** @bar, align 8
 ; GEN: [[ICALL_TARGET:%[0-9]+]] = ptrtoint void ()* %tmp to i64
 ; GEN-NEXT: call void @llvm.instrprof.value.profile(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @__profn_foo, i32 0, i32 0), i64 [[#FOO_HASH]], i64 [[ICALL_TARGET]], i32 0, i32 0)
-; LOWER: call void @__llvm_profile_instrument_target(i64 %1, i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*), i32 0)
+; LOWER: call void @__llvm_profile_instrument_target(i64 %1, i8* bitcast ({ i64, i64, i64, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*), i32 0)
   call void %tmp()
   ret void
 }
@@ -52,7 +52,7 @@ entry:
   %tmp = load void ()*, void ()** @bar, align 8
 ; GEN: [[ICALL_TARGET:%[0-9]+]] = ptrtoint void ()* %tmp to i64
 ; GEN-NEXT: call void @llvm.instrprof.value.profile(i8* getelementptr inbounds ([9 x i8], [9 x i8]* @__profn_vp_inline, i32 0, i32 0), i64 [[#FOO_HASH]], i64 [[ICALL_TARGET]], i32 0, i32 0)
-; LOWER: call void @__llvm_profile_instrument_target(i64 %1, i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_vp_inline.[[#]] to i8*), i32 0)
+; LOWER: call void @__llvm_profile_instrument_target(i64 %1, i8* bitcast ({ i64, i64, i64, i8*, i8*, i32, [2 x i16] }* @__profd_vp_inline.[[#]] to i8*), i32 0)
   call void %tmp()
   ret void
 }
diff --git a/llvm/test/Transforms/PGOProfile/memcpy.ll b/llvm/test/Transforms/PGOProfile/memcpy.ll
@@ -23,7 +23,7 @@ for.cond1:
 
 for.body3:
   %conv = sext i32 %add to i64
-; CHECK: call void @__llvm_profile_instrument_memop(i64 %conv, i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*), i32 0)
+; CHECK: call void @__llvm_profile_instrument_memop(i64 %conv, i8* bitcast ({ i64, i64, i64, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*), i32 0)
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i1 false)
   %inc = add nsw i32 %j.0, 1
   br label %for.cond1
diff --git a/llvm/test/tools/llvm-profdata/Inputs/c-general.profraw b/llvm/test/tools/llvm-profdata/Inputs/c-general.profraw
diff --git a/llvm/test/tools/llvm-profdata/raw-32-bits-be.test b/llvm/test/tools/llvm-profdata/raw-32-bits-be.test
@@ -20,7 +20,7 @@ RUN: printf '\0\0\0\0\0\0\0\0' >> %t
 
 RUN: printf '\344\023\165\112\031\035\265\067' >> %t
 RUN: printf '\0\0\0\0\0\0\0\2' >> %t
-RUN: printf '\1\0\0\10' >> %t
+RUN: printf '\0\xff\xff\xe0' >> %t
 RUN: printf '\0\0\0\0' >> %t
 RUN: printf '\0\0\0\0' >> %t
 RUN: printf '\0\0\0\2' >> %t
diff --git a/llvm/test/tools/llvm-profdata/raw-32-bits-le.test b/llvm/test/tools/llvm-profdata/raw-32-bits-le.test
@@ -20,7 +20,7 @@ RUN: printf '\0\0\0\0\0\0\0\0' >> %t
 
 RUN: printf '\067\265\035\031\112\165\023\344' >> %t
 RUN: printf '\02\0\0\0\0\0\0\0' >> %t
-RUN: printf '\10\0\0\1' >> %t
+RUN: printf '\xe0\xff\xff\0' >> %t
 RUN: printf '\0\0\0\0' >> %t
 RUN: printf '\0\0\0\0' >> %t
 RUN: printf '\2\0\0\0' >> %t
diff --git a/llvm/test/tools/llvm-profdata/raw-64-bits-be.test b/llvm/test/tools/llvm-profdata/raw-64-bits-be.test
@@ -19,7 +19,7 @@ RUN: printf '\0\0\0\1\0\0\0\0' >> %t
 
 RUN: printf '\344\023\165\112\031\035\265\067' >> %t
 RUN: printf '\0\0\0\0\0\0\0\02' >> %t
-RUN: printf '\0\0\0\1\0\4\0\10' >> %t
+RUN: printf '\0\0\0\1\0\3\xff\xd8' >> %t
 RUN: printf '\0\0\0\0\0\0\0\0' >> %t
 RUN: printf '\0\0\0\0\0\0\0\0' >> %t
 RUN: printf '\0\0\0\02\0\0\0\0' >> %t
diff --git a/llvm/test/tools/llvm-profdata/raw-64-bits-le.test b/llvm/test/tools/llvm-profdata/raw-64-bits-le.test
@@ -19,7 +19,7 @@ RUN: printf '\1\0\0\0\0\0\0\0' >> %t
 
 RUN: printf '\067\265\035\031\112\165\023\344' >> %t
 RUN: printf '\02\0\0\0\0\0\0\0' >> %t
-RUN: printf '\10\0\4\0\1\0\0\0' >> %t
+RUN: printf '\xd8\xff\3\0\1\0\0\0' >> %t
 RUN: printf '\0\0\0\0\0\0\0\0' >> %t
 RUN: printf '\0\0\0\0\0\0\0\0' >> %t
 RUN: printf '\02\0\0\0\0\0\0\0' >> %t
