Only scan global sections containing data in LSan on darwin

Summary:
__DATA segments on Darwin contain a large number of separate sections,
most of which cannot actually contain pointers, and contain const values or
objc metadata. Only scanning sections which can contain pointers greatly improves
performance.

On a medium-sized (~4000 files) internal project, I saw a speedup of about 50%
in standalone LSan's execution time (50% improvement in the time spent running
LSan, not the total program time).

Reviewers: kcc, kubamracek, alekseyshl

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D35432

git-svn-id: https://llvm.org/svn/llvm-project/compiler-rt/trunk@308231 91177308-0d34-0410-b5e6-96231b3b80d8

5 files changed, 28 insertions, 11 deletions

diff --git a/lib/lsan/lsan_common_mac.cc b/lib/lsan/lsan_common_mac.cc
index f87c6b7e0..c0fa36fd9 100644
--- a/lib/lsan/lsan_common_mac.cc
+++ b/lib/lsan/lsan_common_mac.cc
@@ -92,8 +92,15 @@ LoadedModule *GetLinker() { return nullptr; }
 // required on Darwin.
 void InitializePlatformSpecificModules() {}
 
+// Sections which may contain global variables
+static const char *kGlobalVarSecNames[] = {
+    "__DATA",      "__bss",         "__common",       "__data",
+    "__objc_data", "__objc_opt_rw", "__objc_opt_ptrs"};
+
 // Scans global variables for heap pointers.
 void ProcessGlobalRegions(Frontier *frontier) {
+  for (auto name : kGlobalVarSecNames) CHECK(ARRAY_SIZE(name) < kMaxSegName);
+
   MemoryMappingLayout memory_mapping(false);
   InternalMmapVector<LoadedModule> modules(/*initial_capacity*/ 128);
   memory_mapping.DumpListOfModules(&modules);
@@ -104,10 +111,10 @@ void ProcessGlobalRegions(Frontier *frontier) {
 
     for (const __sanitizer::LoadedModule::AddressRange &range :
          modules[i].ranges()) {
-      // Sections storing global variables are writable and non-executable
-      if (range.executable || !range.writable) continue;
-
-      ScanGlobalRange(range.beg, range.end, frontier);
+      for (auto name : kGlobalVarSecNames) {
+        if (!internal_strcmp(range.name, name))
+          ScanGlobalRange(range.beg, range.end, frontier);
+      }
     }
   }
 }
diff --git a/lib/sanitizer_common/sanitizer_common.cc b/lib/sanitizer_common/sanitizer_common.cc
index 7e6f8fce7..3868d5469 100644
--- a/lib/sanitizer_common/sanitizer_common.cc
+++ b/lib/sanitizer_common/sanitizer_common.cc
@@ -285,9 +285,10 @@ void LoadedModule::clear() {
 }
 
 void LoadedModule::addAddressRange(uptr beg, uptr end, bool executable,
-                                   bool writable) {
+                                   bool writable, const char *name) {
   void *mem = InternalAlloc(sizeof(AddressRange));
-  AddressRange *r = new(mem) AddressRange(beg, end, executable, writable);
+  AddressRange *r =
+      new(mem) AddressRange(beg, end, executable, writable, name);
   ranges_.push_back(r);
   if (executable && end > max_executable_address_)
     max_executable_address_ = end;
diff --git a/lib/sanitizer_common/sanitizer_common.h b/lib/sanitizer_common/sanitizer_common.h
index 89aae5798..f684271d4 100644
--- a/lib/sanitizer_common/sanitizer_common.h
+++ b/lib/sanitizer_common/sanitizer_common.h
@@ -702,6 +702,7 @@ inline const char *ModuleArchToString(ModuleArch arch) {
 }
 
 const uptr kModuleUUIDSize = 16;
+const uptr kMaxSegName = 16;
 
 // Represents a binary loaded into virtual memory (e.g. this can be an
 // executable or a shared object).
@@ -720,7 +721,8 @@ class LoadedModule {
   void set(const char *module_name, uptr base_address, ModuleArch arch,
            u8 uuid[kModuleUUIDSize], bool instrumented);
   void clear();
-  void addAddressRange(uptr beg, uptr end, bool executable, bool writable);
+  void addAddressRange(uptr beg, uptr end, bool executable, bool writable,
+                       const char *name = nullptr);
   bool containsAddress(uptr address) const;
 
   const char *full_name() const { return full_name_; }
@@ -736,13 +738,17 @@ class LoadedModule {
     uptr end;
     bool executable;
     bool writable;
+    char name[kMaxSegName];
 
-    AddressRange(uptr beg, uptr end, bool executable, bool writable)
+    AddressRange(uptr beg, uptr end, bool executable, bool writable,
+                 const char *name)
         : next(nullptr),
           beg(beg),
           end(end),
           executable(executable),
-          writable(writable) {}
+          writable(writable) {
+      internal_strncpy(this->name, (name ? name : ""), ARRAY_SIZE(this->name));
+    }
   };
 
   const IntrusiveList<AddressRange> &ranges() const { return ranges_; }
diff --git a/lib/sanitizer_common/sanitizer_procmaps.h b/lib/sanitizer_common/sanitizer_procmaps.h
index 76685661c..50753c4e6 100644
--- a/lib/sanitizer_common/sanitizer_procmaps.h
+++ b/lib/sanitizer_common/sanitizer_procmaps.h
@@ -58,6 +58,7 @@ class MemoryMappedSegment {
   u8 uuid[kModuleUUIDSize];
 
 #if SANITIZER_MAC
+  char name[kMaxSegName];
 
  private:
   friend class MemoryMappingLayout;
diff --git a/lib/sanitizer_common/sanitizer_procmaps_mac.cc b/lib/sanitizer_common/sanitizer_procmaps_mac.cc
index 411bbd39d..277d2b194 100644
--- a/lib/sanitizer_common/sanitizer_procmaps_mac.cc
+++ b/lib/sanitizer_common/sanitizer_procmaps_mac.cc
@@ -42,12 +42,13 @@ void MemoryMappedSegment::NextSectionLoad(LoadedModule *module) {
 
   uptr sec_start = sc->addr + base_virt_addr_;
   uptr sec_end = sec_start + sc->size;
-  module->addAddressRange(sec_start, sec_end, IsExecutable(), IsWritable());
+  module->addAddressRange(sec_start, sec_end, IsExecutable(), IsWritable(),
+                          sc->sectname);
 }
 
 void MemoryMappedSegment::AddAddressRanges(LoadedModule *module) {
   if (!nsects_) {
-    module->addAddressRange(start, end, IsExecutable(), IsWritable());
+    module->addAddressRange(start, end, IsExecutable(), IsWritable(), name);
     return;
   }
 
@@ -199,6 +200,7 @@ bool MemoryMappingLayout::NextSegmentLoad(MemoryMappedSegment *segment) {
                             : _dyld_get_image_name(current_image_);
       internal_strncpy(segment->filename, src, segment->filename_size);
     }
+    internal_strncpy(segment->name, sc->segname, ARRAY_SIZE(segment->name));
     segment->arch = current_arch_;
     internal_memcpy(segment->uuid, current_uuid_, kModuleUUIDSize);
     return true;