Add address ranges for individual macho sections on darwin

[fjricci]

Summary

This is a re-upload of the reverted commit r308644. It has changed quite
a bit to reflect post-commit comments by kcc, so I'm re-uploading as
a new review.

[fjricci]

Don't split executable segment into sections to avoid confusing libignore

compiler-rt/trunk/lib/sanitizer_common/sanitizer_procmaps.h

 #endif  // SANITIZER_FREEBSD || SANITIZER_LINUX || SANITIZER_NETBSD
 
 // Memory protection masks.
 static const uptr kProtectionRead = 1;
 static const uptr kProtectionWrite = 2;
 static const uptr kProtectionExecute = 4;
 static const uptr kProtectionShared = 8;
 
-struct MemoryMappedSegment {
+struct MemoryMappedSegmentData;
+
+class MemoryMappedSegment {
+ public:
   MemoryMappedSegment(char *buff = nullptr, uptr size = 0)
-      : filename(buff), filename_size(size) {}
+      : filename(buff), filename_size(size), data_(nullptr) {}
   ~MemoryMappedSegment() {}
 
   bool IsReadable() const { return protection & kProtectionRead; }
   bool IsWritable() const { return protection & kProtectionWrite; }
   bool IsExecutable() const { return protection & kProtectionExecute; }
   bool IsShared() const { return protection & kProtectionShared; }
 
+  void AddAddressRanges(LoadedModule *module);
+
   uptr start;
   uptr end;
   uptr offset;
   char *filename;  // owned by caller
   uptr filename_size;
   uptr protection;
   ModuleArch arch;
   u8 uuid[kModuleUUIDSize];
+
+ private:
+  friend class MemoryMappingLayout;
+
+  // This field is assigned and owned by MemoryMappingLayout if needed
+  MemoryMappedSegmentData *data_;
 };
 
 class MemoryMappingLayout {
  public:
   explicit MemoryMappingLayout(bool cache_enabled);
   ~MemoryMappingLayout();
   bool Next(MemoryMappedSegment *segment);
   void Reset();

compiler-rt/trunk/lib/sanitizer_common/sanitizer_procmaps_common.cc

bool IsHex(char c) {
   int d = TranslateDigit(c);
   return d >= 0 && d < 16;
 }
 
 uptr ParseHex(const char **p) {
   return ParseNumber(p, 16);
 }
 
+void MemoryMappedSegment::AddAddressRanges(LoadedModule *module) {
+  module->addAddressRange(start, end, IsExecutable(), IsWritable());
+}
+
 MemoryMappingLayout::MemoryMappingLayout(bool cache_enabled) {
   ReadProcMaps(&proc_self_maps_);
   if (cache_enabled) {
     if (proc_self_maps_.mmaped_size == 0) {
       LoadFromCache();
       CHECK_GT(proc_self_maps_.len, 0);
     }
   } else {
for (uptr i = 0; Next(&segment); i++) {
     //   is mapped to a fixed memory range).
     // * If a binary is compiled with -pie, all the modules are
     //   mapped high at address space (in particular, higher than
     //   shadow memory of the tool), so the module can't be the
     //   first entry.
     uptr base_address = (i ? segment.start : 0) - segment.offset;
     LoadedModule cur_module;
     cur_module.set(cur_name, base_address);
-    cur_module.addAddressRange(segment.start, segment.end,
-                               segment.IsExecutable(), segment.IsWritable());
+    segment.AddAddressRanges(&cur_module);
     modules->push_back(cur_module);
   }
 }
 
 void GetMemoryProfile(fill_profile_f cb, uptr *stats, uptr stats_size) {
   char *smaps = nullptr;
   uptr smaps_cap = 0;
   uptr smaps_len = 0;

compiler-rt/trunk/lib/sanitizer_common/sanitizer_procmaps_mac.cc

 #define CPU_SUBTYPE_ARM_V7K   ((cpu_subtype_t)12)
 #endif
 #ifndef CPU_TYPE_ARM64
 #define CPU_TYPE_ARM64        (CPU_TYPE_ARM | CPU_ARCH_ABI64)
 #endif
 
 namespace __sanitizer {
 
+// Contains information used to iterate through sections.
+struct MemoryMappedSegmentData {
+  uptr nsects;
+  char *current_load_cmd_addr;
+  u32 lc_type;
+  uptr base_virt_addr;
+  uptr addr_mask;
+};
+
+template <typename Section>
+static void NextSectionLoad(LoadedModule *module, MemoryMappedSegmentData *data,
+                            bool isWritable) {
+  const Section *sc = (const Section *)data->current_load_cmd_addr;
+  data->current_load_cmd_addr += sizeof(Section);
+
+  uptr sec_start = (sc->addr & data->addr_mask) + data->base_virt_addr;
+  uptr sec_end = sec_start + sc->size;
+  module->addAddressRange(sec_start, sec_end, /*executable=*/false, isWritable);
+}
+
+void MemoryMappedSegment::AddAddressRanges(LoadedModule *module) {
+  // Don't iterate over sections when the caller hasn't set up the
+  // data pointer, when there are no sections, or when the segment
+  // is executable. Avoid iterating over executable sections because
+  // it will confuse libignore, and because the extra granularity
+  // of information is not needed by any sanitizers.
+  if (!data_ || !data_->nsects || IsExecutable()) {
+    module->addAddressRange(start, end, IsExecutable(), IsWritable());
+    return;
+  }
+
+  do {
+    if (data_->lc_type == LC_SEGMENT) {
+      NextSectionLoad<struct section>(module, data_, IsWritable());
+#ifdef MH_MAGIC_64
+    } else if (data_->lc_type == LC_SEGMENT_64) {
+      NextSectionLoad<struct section_64>(module, data_, IsWritable());
+#endif
+    }
+  } while (--data_->nsects);
+}
+
 MemoryMappingLayout::MemoryMappingLayout(bool cache_enabled) {
   Reset();
 }
 
 MemoryMappingLayout::~MemoryMappingLayout() {
 }
 
 // More information about Mach-O headers can be found in mach-o/loader.h

 // Note that the segment addresses are not necessarily sorted.
 template <u32 kLCSegment, typename SegmentCommand>
 bool MemoryMappingLayout::NextSegmentLoad(MemoryMappedSegment *segment) {
   const char *lc = current_load_cmd_addr_;
   current_load_cmd_addr_ += ((const load_command *)lc)->cmdsize;
   if (((const load_command *)lc)->cmd == kLCSegment) {
     const SegmentCommand* sc = (const SegmentCommand *)lc;
 
+    uptr base_virt_addr, addr_mask;
     if (current_image_ == kDyldImageIdx) {
+      base_virt_addr = (uptr)get_dyld_hdr();
       // vmaddr is masked with 0xfffff because on macOS versions < 10.12,
       // it contains an absolute address rather than an offset for dyld.
       // To make matters even more complicated, this absolute address
       // isn't actually the absolute segment address, but the offset portion
       // of the address is accurate when combined with the dyld base address,
       // and the mask will give just this offset.
-      segment->start = (sc->vmaddr & 0xfffff) + (uptr)get_dyld_hdr();
-      segment->end = (sc->vmaddr & 0xfffff) + sc->vmsize + (uptr)get_dyld_hdr();
+      addr_mask = 0xfffff;
     } else {
-      const sptr dlloff = _dyld_get_image_vmaddr_slide(current_image_);
-      segment->start = sc->vmaddr + dlloff;
-      segment->end = sc->vmaddr + sc->vmsize + dlloff;
+      base_virt_addr = (uptr)_dyld_get_image_vmaddr_slide(current_image_);
+      addr_mask = ~0;
+    }
+    segment->start = (sc->vmaddr & addr_mask) + base_virt_addr;
+    segment->end = segment->start + sc->vmsize;
+
+    // Most callers don't need section information, so only fill this struct
+    // when required.
+    if (segment->data_) {
+      segment->data_->nsects = sc->nsects;
+      segment->data_->current_load_cmd_addr =
+          (char *)lc + sizeof(SegmentCommand);
+      segment->data_->lc_type = kLCSegment;
+      segment->data_->base_virt_addr = base_virt_addr;
+      segment->data_->addr_mask = addr_mask;
     }
 
     // Return the initial protection.
     segment->protection = sc->initprot;
     segment->offset =
         (current_filetype_ == /*MH_EXECUTE*/ 0x2) ? sc->vmaddr : sc->fileoff;
     if (segment->filename) {
       const char *src = (current_image_ == kDyldImageIdx)
#endif
   return false;
 }
 
 void MemoryMappingLayout::DumpListOfModules(
     InternalMmapVector<LoadedModule> *modules) {
   Reset();
   InternalScopedString module_name(kMaxPathLength);
   MemoryMappedSegment segment(module_name.data(), kMaxPathLength);
-  for (uptr i = 0; Next(&segment); i++) {
+  MemoryMappedSegmentData data;
+  segment.data_ = &data;
+  while (Next(&segment)) {
     if (segment.filename[0] == '\0') continue;
     LoadedModule *cur_module = nullptr;
     if (!modules->empty() &&
         0 == internal_strcmp(segment.filename, modules->back().full_name())) {
       cur_module = &modules->back();
     } else {
       modules->push_back(LoadedModule());
       cur_module = &modules->back();
       cur_module->set(segment.filename, segment.start, segment.arch,
                       segment.uuid, current_instrumented_);
     }
-    cur_module->addAddressRange(segment.start, segment.end,
-                                segment.IsExecutable(), segment.IsWritable());
+    segment.AddAddressRanges(cur_module);
   }
 }
 
 }  // namespace __sanitizer
 
 #endif  // SANITIZER_MAC