[DWARF parser] Fix broken address ranges construction.

Previous algorithm for constructing [Address ranges]->[Compile Units]
mapping was wrong. It somewhat relied on the assumption that address ranges
for different compile units may not overlap. It is not so.
For example, two compile units may contain the definition of the same
linkonce_odr function. These definitions will be merged at link-time,
resulting in equivalent .debug_ranges entries for both these units

Instead of sorting and merging original address ranges (from .debug_ranges
and .debug_aranges), implement a different approach: save endpoints
of all ranges, and then use a sweep-line approach to construct
the desired mapping. If we find that certain address maps to
several compilation units, we just pick any of them.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@210860 91177308-0d34-0410-b5e6-96231b3b80d8

lib/DebugInfo/DWARFDebugAranges.cpp

@@ -15,6 +15,7 @@
 #include "llvm/Support/raw_ostream.h"
 #include <algorithm>
 #include <cassert>
+#include <set>
 using namespace llvm;
 
 void DWARFDebugAranges::extract(DataExtractor DebugArangesData) {
@@ -30,6 +31,7 @@ void DWARFDebugAranges::extract(DataExtractor DebugArangesData) {
       uint64_t HighPC = Desc.getEndAddress();
       appendRange(CUOffset, LowPC, HighPC);
     }
+    ParsedCUOffsets.insert(CUOffset);
   }
 }
 
@@ -56,69 +58,55 @@ void DWARFDebugAranges::generate(DWARFContext *CTX) {
     }
   }
 
-  sortAndMinimize();
+  construct();
 }
 
 void DWARFDebugAranges::clear() {
+  Endpoints.clear();
   Aranges.clear();
   ParsedCUOffsets.clear();
 }
 
 void DWARFDebugAranges::appendRange(uint32_t CUOffset, uint64_t LowPC,
                                     uint64_t HighPC) {
-  if (!Aranges.empty()) {
-    if (Aranges.back().CUOffset == CUOffset &&
-        Aranges.back().HighPC() == LowPC) {
-      Aranges.back().setHighPC(HighPC);
-      return;
-    }
-  }
-  Aranges.push_back(Range(LowPC, HighPC, CUOffset));
+  if (LowPC >= HighPC)
+    return;
+  Endpoints.emplace_back(LowPC, CUOffset, true);
+  Endpoints.emplace_back(HighPC, CUOffset, false);
 }
 
-void DWARFDebugAranges::sortAndMinimize() {
-  const size_t orig_arange_size = Aranges.size();
-  // Size of one? If so, no sorting is needed
-  if (orig_arange_size <= 1)
-    return;
-  // Sort our address range entries
-  std::stable_sort(Aranges.begin(), Aranges.end());
-
-  // Most address ranges are contiguous from function to function
-  // so our new ranges will likely be smaller. We calculate the size
-  // of the new ranges since although std::vector objects can be resized,
-  // the will never reduce their allocated block size and free any excesss
-  // memory, so we might as well start a brand new collection so it is as
-  // small as possible.
-
-  // First calculate the size of the new minimal arange vector
-  // so we don't have to do a bunch of re-allocations as we
-  // copy the new minimal stuff over to the new collection.
-  size_t minimal_size = 1;
-  for (size_t i = 1; i < orig_arange_size; ++i) {
-    if (!Range::SortedOverlapCheck(Aranges[i-1], Aranges[i]))
-      ++minimal_size;
-  }
-
-  // Else, make a new RangeColl that _only_ contains what we need.
-  RangeColl minimal_aranges;
-  minimal_aranges.resize(minimal_size);
-  uint32_t j = 0;
-  minimal_aranges[j] = Aranges[0];
-  for (size_t i = 1; i < orig_arange_size; ++i) {
-    if (Range::SortedOverlapCheck(minimal_aranges[j], Aranges[i])) {
-      minimal_aranges[j].setHighPC(Aranges[i].HighPC());
-    } else {
-      // Only increment j if we aren't merging
-      minimal_aranges[++j] = Aranges[i];
+void DWARFDebugAranges::construct() {
+  std::multiset<uint32_t> ValidCUs;  // Maintain the set of CUs describing
+                                     // a current address range.
+  std::sort(Endpoints.begin(), Endpoints.end());
+  uint64_t PrevAddress = -1ULL;
+  for (const auto &E : Endpoints) {
+    if (PrevAddress < E.Address && ValidCUs.size() > 0) {
+      // If the address range between two endpoints is described by some
+      // CU, first try to extend the last range in Aranges. If we can't
+      // do it, start a new range.
+      if (!Aranges.empty() && Aranges.back().HighPC() == PrevAddress &&
+          ValidCUs.find(Aranges.back().CUOffset) != ValidCUs.end()) {
+        Aranges.back().setHighPC(E.Address);
+      } else {
+        Aranges.emplace_back(PrevAddress, E.Address, *ValidCUs.begin());
+      }
     }
+    // Update the set of valid CUs.
+    if (E.IsRangeStart) {
+      ValidCUs.insert(E.CUOffset);
+    } else {
+      auto CUPos = ValidCUs.find(E.CUOffset);
+      assert(CUPos != ValidCUs.end());
+      ValidCUs.erase(CUPos);
+    }
+    PrevAddress = E.Address;
   }
-  assert(j+1 == minimal_size);
+  assert(ValidCUs.empty());
 
-  // Now swap our new minimal aranges into place. The local
-  // minimal_aranges will then contian the old big collection
-  // which will get freed.
-  minimal_aranges.swap(Aranges);
+  // Endpoints are not needed now.
+  std::vector<RangeEndpoint> EmptyEndpoints;
+  EmptyEndpoints.swap(Endpoints);
 }
 
 uint32_t DWARFDebugAranges::findAddress(uint64_t Address) const {

lib/DebugInfo/DWARFDebugAranges.h

@@ -27,9 +27,9 @@ private:
   void clear();
   void extract(DataExtractor DebugArangesData);
 
-  // Use appendRange multiple times and then call sortAndMinimize.
+  // Call appendRange multiple times and then call construct.
   void appendRange(uint32_t CUOffset, uint64_t LowPC, uint64_t HighPC);
-  void sortAndMinimize();
+  void construct();
 
   struct Range {
     explicit Range(uint64_t LowPC = -1ULL, uint64_t HighPC = -1ULL,
@@ -47,31 +47,39 @@ private:
         return LowPC + Length;
       return -1ULL;
     }
+
     bool containsAddress(uint64_t Address) const {
       return LowPC <= Address && Address < HighPC();
     }
-
-    bool operator <(const Range &other) const {
+    bool operator<(const Range &other) const {
       return LowPC < other.LowPC;
     }
 
-    static bool SortedOverlapCheck(const Range &Left, const Range &Right) {
-      if (Left.CUOffset != Right.CUOffset)
-        return false;
-      return Left.HighPC() >= Right.LowPC;
-    }
-
     uint64_t LowPC; // Start of address range.
     uint32_t Length; // End of address range (not including this address).
     uint32_t CUOffset; // Offset of the compile unit or die.
   };
 
+  struct RangeEndpoint {
+    uint64_t Address;
+    uint32_t CUOffset;
+    bool IsRangeStart;
+
+    RangeEndpoint(uint64_t Address, uint32_t CUOffset, bool IsRangeStart)
+        : Address(Address), CUOffset(CUOffset), IsRangeStart(IsRangeStart) {}
+
+    bool operator<(const RangeEndpoint &Other) const {
+      return Address < Other.Address;
+    }
+  };
+
+
   typedef std::vector<Range>              RangeColl;
   typedef RangeColl::const_iterator       RangeCollIterator;
-  typedef DenseSet<uint32_t>              ParsedCUOffsetColl;
 
+  std::vector<RangeEndpoint> Endpoints;
   RangeColl Aranges;
-  ParsedCUOffsetColl ParsedCUOffsets;
+  DenseSet<uint32_t> ParsedCUOffsets;
 };
 
 }

test/DebugInfo/Inputs/arange-overlap.cc

@@ -0,0 +1,26 @@
+void call();
+
+struct S {
+  static void foo() { call(); call(); }
+  static void bar() { call(); call(); }
+  static void baz() {}
+};
+
+#ifdef FILE1
+# define FUNC_NAME func1
+# define FUNC_BODY \
+    S::foo(); S::bar(); S::baz();
+#else
+# define FUNC_NAME func2
+# define FUNC_BODY \
+    S::bar();
+#endif
+
+void FUNC_NAME() {
+  FUNC_BODY
+}
+
+// Build instructions:
+// $ clang -g -fPIC -c -DFILE1 arange-overlap.cc -o obj1.o
+// $ clang -g -fPIC -c arange-overlap.cc -o obj2.o
+// $ clang -shared obj1.o obj2.o -o <output>

test/DebugInfo/llvm-symbolizer.test

@@ -18,6 +18,7 @@ RUN: echo "%p/Inputs/macho-universal:i386 0x1f67" >> %t.input
 RUN: echo "%p/Inputs/macho-universal:x86_64 0x100000f05" >> %t.input
 RUN: echo "%p/Inputs/llvm-symbolizer-dwo-test 0x400514" >> %t.input
 RUN: echo "%p/Inputs/fission-ranges.elf-x86_64 0x720" >> %t.input
+RUN: echo "%p/Inputs/arange-overlap.elf-x86_64 0x714" >> %t.input
 
 RUN: llvm-symbolizer --functions=linkage --inlining --demangle=false \
 RUN:    --default-arch=i386 < %t.input | FileCheck %s
@@ -94,6 +95,9 @@ CHECK-NEXT: llvm-symbolizer-dwo-test.cc:11
 CHECK: main
 CHECK-NEXT: {{.*}}fission-ranges.cc:6
 
+CHECK: _ZN1S3bazEv
+CHECK-NEXT: {{.*}}arange-overlap.cc:6
+
 RUN: echo "unexisting-file 0x1234" > %t.input2
 RUN: llvm-symbolizer < %t.input2