Add inline stack streaming to binary sample profiles.

With this patch we can now read and write inline stacks in sample
profiles to the binary encoded profiles.

In a subsequent patch, I will add a string table to the binary encoding.
Right now function names are emitted as strings every time we find them.
This is too bloated and will produce large files in applications with
lots of inlining.

llvm-svn: 249861

6 files changed, 137 insertions, 43 deletions

diff --git a/llvm/include/llvm/ProfileData/SampleProfReader.h b/llvm/include/llvm/ProfileData/SampleProfReader.h
index 9f4d53902e1..e2976e2efab 100644
--- a/llvm/include/llvm/ProfileData/SampleProfReader.h
+++ b/llvm/include/llvm/ProfileData/SampleProfReader.h
@@ -157,6 +157,9 @@ protected:
   /// \brief Return true if we've reached the end of file.
   bool at_eof() const { return Data >= End; }
 
+  /// Read the contents of the given profile instance.
+  std::error_code readProfile(FunctionSamples &FProfile);
+
   /// \brief Points to the current location in the buffer.
   const uint8_t *Data;
 
diff --git a/llvm/lib/ProfileData/SampleProfReader.cpp b/llvm/lib/ProfileData/SampleProfReader.cpp
index 6d7d182e46c..c620d4ca84a 100644
--- a/llvm/lib/ProfileData/SampleProfReader.cpp
+++ b/llvm/lib/ProfileData/SampleProfReader.cpp
@@ -378,62 +378,94 @@ ErrorOr<StringRef> SampleProfileReaderBinary::readString() {
   return Str;
 }
 
-std::error_code SampleProfileReaderBinary::read() {
-  while (!at_eof()) {
-    auto FName(readString());
-    if (std::error_code EC = FName.getError())
-      return EC;
+std::error_code
+SampleProfileReaderBinary::readProfile(FunctionSamples &FProfile) {
+  auto Val = readNumber<unsigned>();
+  if (std::error_code EC = Val.getError())
+    return EC;
+  FProfile.addTotalSamples(*Val);
 
-    Profiles[*FName] = FunctionSamples();
-    FunctionSamples &FProfile = Profiles[*FName];
+  Val = readNumber<unsigned>();
+  if (std::error_code EC = Val.getError())
+    return EC;
+  FProfile.addHeadSamples(*Val);
+
+  // Read the samples in the body.
+  auto NumRecords = readNumber<unsigned>();
+  if (std::error_code EC = NumRecords.getError())
+    return EC;
 
-    auto Val = readNumber<unsigned>();
-    if (std::error_code EC = Val.getError())
+  for (unsigned I = 0; I < *NumRecords; ++I) {
+    auto LineOffset = readNumber<uint64_t>();
+    if (std::error_code EC = LineOffset.getError())
       return EC;
-    FProfile.addTotalSamples(*Val);
 
-    Val = readNumber<unsigned>();
-    if (std::error_code EC = Val.getError())
+    auto Discriminator = readNumber<uint64_t>();
+    if (std::error_code EC = Discriminator.getError())
       return EC;
-    FProfile.addHeadSamples(*Val);
 
-    // Read the samples in the body.
-    auto NumRecords = readNumber<unsigned>();
-    if (std::error_code EC = NumRecords.getError())
+    auto NumSamples = readNumber<uint64_t>();
+    if (std::error_code EC = NumSamples.getError())
       return EC;
-    for (unsigned I = 0; I < *NumRecords; ++I) {
-      auto LineOffset = readNumber<uint64_t>();
-      if (std::error_code EC = LineOffset.getError())
-        return EC;
 
-      auto Discriminator = readNumber<uint64_t>();
-      if (std::error_code EC = Discriminator.getError())
-        return EC;
+    auto NumCalls = readNumber<unsigned>();
+    if (std::error_code EC = NumCalls.getError())
+      return EC;
 
-      auto NumSamples = readNumber<uint64_t>();
-      if (std::error_code EC = NumSamples.getError())
+    for (unsigned J = 0; J < *NumCalls; ++J) {
+      auto CalledFunction(readString());
+      if (std::error_code EC = CalledFunction.getError())
         return EC;
 
-      auto NumCalls = readNumber<unsigned>();
-      if (std::error_code EC = NumCalls.getError())
+      auto CalledFunctionSamples = readNumber<uint64_t>();
+      if (std::error_code EC = CalledFunctionSamples.getError())
         return EC;
 
-      for (unsigned J = 0; J < *NumCalls; ++J) {
-        auto CalledFunction(readString());
-        if (std::error_code EC = CalledFunction.getError())
-          return EC;
+      FProfile.addCalledTargetSamples(*LineOffset, *Discriminator,
+                                      *CalledFunction, *CalledFunctionSamples);
+    }
 
-        auto CalledFunctionSamples = readNumber<uint64_t>();
-        if (std::error_code EC = CalledFunctionSamples.getError())
-          return EC;
+    FProfile.addBodySamples(*LineOffset, *Discriminator, *NumSamples);
+  }
 
-        FProfile.addCalledTargetSamples(*LineOffset, *Discriminator,
-                                        *CalledFunction,
-                                        *CalledFunctionSamples);
-      }
+  // Read all the samples for inlined function calls.
+  auto NumCallsites = readNumber<unsigned>();
+  if (std::error_code EC = NumCallsites.getError())
+    return EC;
 
-      FProfile.addBodySamples(*LineOffset, *Discriminator, *NumSamples);
-    }
+  for (unsigned J = 0; J < *NumCallsites; ++J) {
+    auto LineOffset = readNumber<uint64_t>();
+    if (std::error_code EC = LineOffset.getError())
+      return EC;
+
+    auto Discriminator = readNumber<uint64_t>();
+    if (std::error_code EC = Discriminator.getError())
+      return EC;
+
+    auto FName(readString());
+    if (std::error_code EC = FName.getError())
+      return EC;
+
+    FunctionSamples &CalleeProfile = FProfile.functionSamplesAt(
+        CallsiteLocation(*LineOffset, *Discriminator, *FName));
+    if (std::error_code EC = readProfile(CalleeProfile))
+      return EC;
+  }
+
+  return sampleprof_error::success;
+}
+
+std::error_code SampleProfileReaderBinary::read() {
+  while (!at_eof()) {
+    auto FName(readString());
+    if (std::error_code EC = FName.getError())
+      return EC;
+
+    Profiles[*FName] = FunctionSamples();
+    FunctionSamples &FProfile = Profiles[*FName];
+
+    if (std::error_code EC = readProfile(FProfile))
+      return EC;
   }
 
   return sampleprof_error::success;
diff --git a/llvm/lib/ProfileData/SampleProfWriter.cpp b/llvm/lib/ProfileData/SampleProfWriter.cpp
index e6a4d7d1321..6be884b13e0 100644
--- a/llvm/lib/ProfileData/SampleProfWriter.cpp
+++ b/llvm/lib/ProfileData/SampleProfWriter.cpp
@@ -84,14 +84,13 @@ SampleProfileWriterBinary::SampleProfileWriterBinary(StringRef F,
 /// \returns true if the samples were written successfully, false otherwise.
 bool SampleProfileWriterBinary::write(StringRef FName,
                                       const FunctionSamples &S) {
-  if (S.empty())
-    return true;
-
   OS << FName;
   encodeULEB128(0, OS);
   encodeULEB128(S.getTotalSamples(), OS);
   encodeULEB128(S.getHeadSamples(), OS);
   encodeULEB128(S.getBodySamples().size(), OS);
+
+  // Emit all the body samples.
   for (const auto &I : S.getBodySamples()) {
     LineLocation Loc = I.first;
     const SampleRecord &Sample = I.second;
@@ -108,6 +107,16 @@ bool SampleProfileWriterBinary::write(StringRef FName,
     }
   }
 
+  // Recursively emit all the callsite samples.
+  encodeULEB128(S.getCallsiteSamples().size(), OS);
+  for (const auto &J : S.getCallsiteSamples()) {
+    CallsiteLocation Loc = J.first;
+    const FunctionSamples &CalleeSamples = J.second;
+    encodeULEB128(Loc.LineOffset, OS);
+    encodeULEB128(Loc.Discriminator, OS);
+    write(Loc.CalleeName, CalleeSamples);
+  }
+
   return true;
 }
 
diff --git a/llvm/test/Transforms/SampleProfile/Inputs/fnptr.binprof b/llvm/test/Transforms/SampleProfile/Inputs/fnptr.binprof
index 14d7fd555da..8cbe646c16e 100644
--- a/llvm/test/Transforms/SampleProfile/Inputs/fnptr.binprof
+++ b/llvm/test/Transforms/SampleProfile/Inputs/fnptr.binprof
diff --git a/llvm/test/tools/llvm-profdata/Inputs/inline-samples.afdo b/llvm/test/tools/llvm-profdata/Inputs/inline-samples.afdo
new file mode 100644
index 00000000000..f8680d86fcb
--- /dev/null
+++ b/llvm/test/tools/llvm-profdata/Inputs/inline-samples.afdo
@@ -0,0 +1,20 @@
+main:366846:0
+ 2.1: 60401
+ 4: 0
+ 3: 0
+ 0: 0
+ 2.3: 60401
+ 1: 0
+ 2.3: _Z3fool:246044
+  1.2: 39280
+  1.4: 46871
+  1: 60401
+  1.3: _Z3bari:0
+   1.2: 0
+   1.1: 0
+  1.8: _Z3bari:0
+   1.2: 0
+   1.1: 0
+  1.7: _Z3bari:99492
+   1.2: 46732
+   1.1: 52760
diff --git a/llvm/test/tools/llvm-profdata/inline-samples.test b/llvm/test/tools/llvm-profdata/inline-samples.test
new file mode 100644
index 00000000000..b16ac488234
--- /dev/null
+++ b/llvm/test/tools/llvm-profdata/inline-samples.test
@@ -0,0 +1,30 @@
+Tests for conversion between text and binary encoded sample profiles.
+
+1- Encode the original profile into binary form. All the tests below will use
+   the binary profile.
+RUN: llvm-profdata merge --sample %p/Inputs/inline-samples.afdo -o %t.profbin
+
+2- Show all functions. This profile has a single main() function with several
+   inlined callees.
+RUN: llvm-profdata show --sample %t.profbin | FileCheck %s --check-prefix=SHOW1
+SHOW1: Function: main: 366846, 0, 6 sampled lines
+SHOW1: line offset: 2, discriminator: 3, inlined callee: _Z3fool: 246044, 0, 3 sampled lines
+SHOW1:   line offset: 1, discriminator: 3, inlined callee: _Z3bari: 0, 0, 2 sampled lines
+SHOW1:   line offset: 1, discriminator: 8, inlined callee: _Z3bari: 0, 0, 2 sampled lines
+SHOW1:   line offset: 1, discriminator: 7, inlined callee: _Z3bari: 99492, 0, 2 sampled lines
+SHOW1:     line offset: 1, discriminator: 2, number of samples: 46732
+
+3- Convert the binary profile to text encoding and check that they are both
+   identical.
+RUN: llvm-profdata merge --sample %t.profbin --text -o - | llvm-profdata show --sample - -o %t-bintext
+RUN: llvm-profdata show --sample %p/Inputs/inline-samples.afdo -o %t-text
+RUN: diff %t-bintext %t-text
+
+4- Merge the binary and text encodings of the profile and check that the
+   counters have doubled.
+RUN: llvm-profdata merge --sample --text %t.profbin %p/Inputs/inline-samples.afdo -o - | FileCheck %s --check-prefix=MERGE1
+MERGE1: main:733692:0
+MERGE1: 2.3: 120802
+MERGE1: 2.3: _Z3fool:492088
+MERGE1: 1.7: _Z3bari:198984
+MERGE1: 1.1: 105520