[VFS] Add support for handling path traversals

Handle ".", ".." and "./" with trailing slashes while collecting files
to be dumped into the vfs overlay directory.

Include the support for symlinks into components. Given the path:

/install-dir/bin/../lib/clang/3.8.0/include/altivec.h, if "bin"
component is a symlink, it's not safe to use `path::remove_dots` here,
and `realpath` is used to get the right answer. Since `realpath`
is expensive, we only do it at collecting time (which only happens
during the crash reproducer) and cache the base directory for fast lookups.

Overall, this makes the input to the VFS YAML file to be canonicalized
to never contain traversal components.

Differential Revision: http://reviews.llvm.org/D17104

rdar://problem/24499339

llvm-svn: 261551

2 files changed, 112 insertions, 23 deletions

diff --git a/clang/lib/Basic/VirtualFileSystem.cpp b/clang/lib/Basic/VirtualFileSystem.cpp
index 6977f400287..68ad428ec7e 100644
--- a/clang/lib/Basic/VirtualFileSystem.cpp
+++ b/clang/lib/Basic/VirtualFileSystem.cpp
@@ -111,6 +111,20 @@ bool FileSystem::exists(const Twine &Path) {
   return Status && Status->exists();
 }
 
+#ifndef NDEBUG
+static bool isTraversalComponent(StringRef Component) {
+  return Component.equals("..") || Component.equals(".");
+}
+
+static bool pathHasTraversal(StringRef Path) {
+  using namespace llvm::sys;
+  for (StringRef Comp : llvm::make_range(path::begin(Path), path::end(Path)))
+    if (isTraversalComponent(Comp))
+      return true;
+  return false;
+}
+#endif
+
 //===-----------------------------------------------------------------------===/
 // RealFileSystem implementation
 //===-----------------------------------------------------------------------===/
@@ -807,6 +821,9 @@ public:
 ///
 /// and inherit their attributes from the external contents.
 ///
+/// Virtual file paths and external files are expected to be canonicalized
+/// without "..", "." and "./" in their paths.
+///
 /// In both cases, the 'name' field may contain multiple path components (e.g.
 /// /path/to/file). However, any directory that contains more than one child
 /// must be uniquely represented by a directory entry.
@@ -1004,7 +1021,13 @@ class RedirectingFileSystemParser {
       if (Key == "name") {
         if (!parseScalarString(I->getValue(), Value, Buffer))
           return nullptr;
-        Name = Value;
+
+        SmallString<256> Path(Value);
+        // Guarantee that old YAML files containing paths with ".." and "." are
+        // properly canonicalized before read into the VFS.
+        Path = sys::path::remove_leading_dotslash(Path);
+        sys::path::remove_dots(Path, /*remove_dot_dot=*/true);
+        Name = Path.str();
       } else if (Key == "type") {
         if (!parseScalarString(I->getValue(), Value, Buffer))
           return nullptr;
@@ -1048,7 +1071,12 @@ class RedirectingFileSystemParser {
         HasContents = true;
         if (!parseScalarString(I->getValue(), Value, Buffer))
           return nullptr;
-        ExternalContentsPath = Value;
+        SmallString<256> Path(Value);
+        // Guarantee that old YAML files containing paths with ".." and "." are
+        // properly canonicalized before read into the VFS.
+        Path = sys::path::remove_leading_dotslash(Path);
+        sys::path::remove_dots(Path, /*remove_dot_dot=*/true);
+        ExternalContentsPath = Path.str();
       } else if (Key == "use-external-name") {
         bool Val;
         if (!parseScalarBool(I->getValue(), Val))
@@ -1238,6 +1266,12 @@ ErrorOr<Entry *> RedirectingFileSystem::lookupPath(const Twine &Path_) {
   if (std::error_code EC = makeAbsolute(Path))
     return EC;
 
+  // Canonicalize path by removing ".", "..", "./", etc components. This is
+  // a VFS request, do bot bother about symlinks in the path components
+  // but canonicalize in order to perform the correct entry search.
+  Path = sys::path::remove_leading_dotslash(Path);
+  sys::path::remove_dots(Path, /*remove_dot_dot=*/true);
+
   if (Path.empty())
     return make_error_code(llvm::errc::invalid_argument);
 
@@ -1254,10 +1288,10 @@ ErrorOr<Entry *> RedirectingFileSystem::lookupPath(const Twine &Path_) {
 ErrorOr<Entry *>
 RedirectingFileSystem::lookupPath(sys::path::const_iterator Start,
                                   sys::path::const_iterator End, Entry *From) {
-  if (Start->equals("."))
-    ++Start;
+  assert(!isTraversalComponent(*Start) &&
+         !isTraversalComponent(From->getName()) &&
+         "Paths should not contain traversal components");
 
-  // FIXME: handle ..
   if (CaseSensitive ? !Start->equals(From->getName())
                     : !Start->equals_lower(From->getName()))
     // failure to match
@@ -1376,16 +1410,6 @@ UniqueID vfs::getNextVirtualUniqueID() {
   return UniqueID(std::numeric_limits<uint64_t>::max(), ID);
 }
 
-#ifndef NDEBUG
-static bool pathHasTraversal(StringRef Path) {
-  using namespace llvm::sys;
-  for (StringRef Comp : llvm::make_range(path::begin(Path), path::end(Path)))
-    if (Comp == "." || Comp == "..")
-      return true;
-  return false;
-}
-#endif
-
 void YAMLVFSWriter::addFileMapping(StringRef VirtualPath, StringRef RealPath) {
   assert(sys::path::is_absolute(VirtualPath) && "virtual path not absolute");
   assert(sys::path::is_absolute(RealPath) && "real path not absolute");
diff --git a/clang/lib/Frontend/ModuleDependencyCollector.cpp b/clang/lib/Frontend/ModuleDependencyCollector.cpp
index 9768a164acb..df5e19df91d 100644
--- a/clang/lib/Frontend/ModuleDependencyCollector.cpp
+++ b/clang/lib/Frontend/ModuleDependencyCollector.cpp
@@ -13,8 +13,9 @@
 
 #include "clang/Frontend/Utils.h"
 #include "clang/Serialization/ASTReader.h"
-#include "llvm/ADT/StringSet.h"
+#include "llvm/ADT/StringMap.h"
 #include "llvm/ADT/iterator_range.h"
+#include "llvm/Config/config.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/Path.h"
 #include "llvm/Support/raw_ostream.h"
@@ -25,7 +26,9 @@ namespace {
 /// Private implementation for ModuleDependencyCollector
 class ModuleDependencyListener : public ASTReaderListener {
   ModuleDependencyCollector &Collector;
+  llvm::StringMap<std::string> SymLinkMap;
 
+  bool getRealPath(StringRef SrcPath, SmallVectorImpl<char> &Result);
   std::error_code copyToRoot(StringRef Src);
 public:
   ModuleDependencyListener(ModuleDependencyCollector &Collector)
@@ -57,6 +60,48 @@ void ModuleDependencyCollector::writeFileMap() {
   VFSWriter.write(OS);
 }
 
+// TODO: move this to Support/Path.h?
+static bool real_path(StringRef SrcPath, SmallVectorImpl<char> &RealPath) {
+#ifdef HAVE_REALPATH
+  char CanonicalPath[PATH_MAX];
+
+  // TODO: emit a warning in case this fails...?
+  if (!realpath(SrcPath.str().c_str(), CanonicalPath))
+    return false;
+
+  SmallString<256> RPath(CanonicalPath);
+  RealPath.swap(RPath);
+  return true;
+#else
+  // FIXME: Add support for systems without realpath.
+  return false;
+#endif
+}
+
+bool ModuleDependencyListener::getRealPath(StringRef SrcPath,
+                                           SmallVectorImpl<char> &Result) {
+  using namespace llvm::sys;
+  SmallString<256> RealPath;
+  StringRef FileName = path::filename(SrcPath);
+  std::string Dir = path::parent_path(SrcPath).str();
+  auto DirWithSymLink = SymLinkMap.find(Dir);
+
+  // Use real_path to fix any symbolic link component present in a path.
+  // Computing the real path is expensive, cache the search through the
+  // parent path directory.
+  if (DirWithSymLink == SymLinkMap.end()) {
+    if (!real_path(Dir, RealPath))
+      return false;
+    SymLinkMap[Dir] = RealPath.str();
+  } else {
+    RealPath = DirWithSymLink->second;
+  }
+
+  path::append(RealPath, FileName);
+  Result.swap(RealPath);
+  return true;
+}
+
 std::error_code ModuleDependencyListener::copyToRoot(StringRef Src) {
   using namespace llvm::sys;
 
@@ -65,22 +110,42 @@ std::error_code ModuleDependencyListener::copyToRoot(StringRef Src) {
   fs::make_absolute(AbsoluteSrc);
   // Canonicalize to a native path to avoid mixed separator styles.
   path::native(AbsoluteSrc);
-  // TODO: We probably need to handle .. as well as . in order to have valid
-  // input to the YAMLVFSWriter.
-  path::remove_dots(AbsoluteSrc);
+  // Remove redundant leading "./" pieces and consecutive separators.
+  AbsoluteSrc = path::remove_leading_dotslash(AbsoluteSrc);
+
+  // Canonicalize path by removing "..", "." components.
+  SmallString<256> CanonicalPath = AbsoluteSrc;
+  path::remove_dots(CanonicalPath, /*remove_dot_dot=*/true);
+
+  // If a ".." component is present after a symlink component, remove_dots may
+  // lead to the wrong real destination path. Let the source be canonicalized
+  // like that but make sure the destination uses the real path.
+  bool HasDotDotInPath =
+      std::count(path::begin(AbsoluteSrc), path::end(AbsoluteSrc), "..") > 0;
+  SmallString<256> RealPath;
+  bool HasRemovedSymlinkComponent = HasDotDotInPath &&
+                             getRealPath(AbsoluteSrc, RealPath) &&
+                             !StringRef(CanonicalPath).equals(RealPath);
 
   // Build the destination path.
   SmallString<256> Dest = Collector.getDest();
-  path::append(Dest, path::relative_path(AbsoluteSrc));
+  path::append(Dest, path::relative_path(HasRemovedSymlinkComponent ? RealPath
+                                                             : CanonicalPath));
 
   // Copy the file into place.
   if (std::error_code EC = fs::create_directories(path::parent_path(Dest),
                                                    /*IgnoreExisting=*/true))
     return EC;
-  if (std::error_code EC = fs::copy_file(AbsoluteSrc, Dest))
+  if (std::error_code EC = fs::copy_file(
+          HasRemovedSymlinkComponent ? RealPath : CanonicalPath, Dest))
     return EC;
-  // Use the absolute path under the root for the file mapping.
-  Collector.addFileMapping(AbsoluteSrc, Dest);
+
+  // Use the canonical path under the root for the file mapping. Also create
+  // an additional entry for the real path.
+  Collector.addFileMapping(CanonicalPath, Dest);
+  if (HasRemovedSymlinkComponent)
+    Collector.addFileMapping(RealPath, Dest);
+
   return std::error_code();
 }