[Internalize] Support glob patterns for API lists

[jhuber6]

Summary

The internalize pass supports an option to provide a list of symbols
that should not be internalized. THis is useful retaining certain
defintions that should be kept alive. However, this interface is
somewhat difficult to use as it requires knowing every single symbol's
name and specifying it. Many APIs provide common prefixes for the
symbols exported by the library, so it would make sense to be able to
match these using a simple glob pattern. This patch changes the handling
from a simple string comparison to a glob pattern match.

[MaskRay]

llvm/lib/Transforms/IPO/Internalize.cpp

53

Update comment

llvm/test/Transforms/Internalize/globs.ll

1

to avoid gotcha when a user runs the command in a shell.

You can drop <

llvm/lib/Transforms/IPO/Internalize.cpp

 #include "llvm/ADT/StringSet.h"
 #include "llvm/ADT/Triple.h"
 #include "llvm/Analysis/CallGraph.h"
 #include "llvm/IR/Module.h"
 #include "llvm/InitializePasses.h"
 #include "llvm/Pass.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
+#include "llvm/Support/GlobPattern.h"
 #include "llvm/Support/LineIterator.h"
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/raw_ostream.h"
 #include "llvm/Transforms/IPO.h"
 using namespace llvm;
 
 #define DEBUG_TYPE "internalize"
 
 STATISTIC(NumAliases, "Number of aliases internalized");
 STATISTIC(NumFunctions, "Number of functions internalized");
 STATISTIC(NumGlobals, "Number of global vars internalized");
 
 // APIFile - A file which contains a list of symbols that should not be marked
 // external.
 static cl::opt<std::string>
     APIFile("internalize-public-api-file", cl::value_desc("filename"),
             cl::desc("A file containing list of symbol names to preserve"));
 
 // APIList - A list of symbols that should not be marked internal.
 static cl::list<std::string>
     APIList("internalize-public-api-list", cl::value_desc("list"),
             cl::desc("A list of symbol names to preserve"), cl::CommaSeparated);
 
 namespace {
 // Helper to load an API list to preserve from file and expose it as a functor
 // for internalization.
 class PreserveAPIList {
 public:
   PreserveAPIList() {
     if (!APIFile.empty())
       LoadFile(APIFile);
-    ExternalNames.insert(APIList.begin(), APIList.end());
+    for (StringRef Pattern : APIList)
+      addGlob(Pattern);
   }
 
   bool operator()(const GlobalValue &GV) {
-    return ExternalNames.count(GV.getName());
+    return llvm::any_of(
+        ExternalNames, [&](GlobPattern &GP) { return GP.match(GV.getName()); });
   }
 
 private:
   // Contains the set of symbols loaded from file
-  StringSet<> ExternalNames;
+  SmallVector<GlobPattern> ExternalNames;
+
+  void addGlob(StringRef Pattern) {
+    auto GlobOrErr = GlobPattern::create(Pattern);
+    if (!GlobOrErr) {
+      errs() << "WARNING: when loading pattern: '"
+             << toString(GlobOrErr.takeError()) << "' ignoring";
+      return;
+    }
+    ExternalNames.emplace_back(std::move(*GlobOrErr));
+  }
 
   void LoadFile(StringRef Filename) {
     // Load the APIFile...
-    ErrorOr<std::unique_ptr<MemoryBuffer>> Buf =
+    ErrorOr<std::unique_ptr<MemoryBuffer>> BufOrErr =
         MemoryBuffer::getFile(Filename);
-    if (!Buf) {
+    if (!BufOrErr) {
       errs() << "WARNING: Internalize couldn't load file '" << Filename
              << "'! Continuing as if it's empty.\n";
       return; // Just continue as if the file were empty
     }
-    for (line_iterator I(*Buf->get(), true), E; I != E; ++I)
-      ExternalNames.insert(*I);
+    Buf = std::move(*BufOrErr);
+    for (line_iterator I(*Buf, true), E; I != E; ++I)
+      addGlob(*I);
   }
+
+  std::shared_ptr<MemoryBuffer> Buf;
 };
 } // end anonymous namespace
 
 bool InternalizePass::shouldPreserveGV(const GlobalValue &GV) {
   // Function must be defined here
   if (GV.isDeclaration())
     return true;
 

llvm/test/Transforms/Internalize/globs.ll

+; RUN: opt < %s -internalize -internalize-public-api-list bar?,_*,*_,[ab] -S | FileCheck %s
+
+; CHECK: @foo = internal global
+@foo = global i32 0
+
+; CHECK: @bar_ = global
+@bar_ = global i32 0
+
+; CHECK: @_foo = global
+@_foo = global i32 0
+
+; CHECK: @foo_ = global
+@foo_ = global i32 0
+
+; CHECK: @a = global
+@a = global i32 0
+
+; CHECK: @b = global
+@b = global i32 0
+
+; CHECK: @c = internal global
+@c = global i32 0