[DWARF] Fix a bug in line info handling

This fixes a bug in the line info handling in the dwarf code, based on a
problem I when implementing RelocVisitor support for MachO.
Since addr+size will give the first address past the end of the function,
we need to back up one line table entry. Fix this by looking up the
end_addr-1, which is the last address in the range. Note that this also
removes a duplicate output from the llvm-rtdyld line table dump. The
relevant line is the end_sequence one in the line table and has an offset
of the first address part the end of the range and hence should not be
included.
Also factor out the common functionality into a separate function.
This comes up on MachO much more than on ELF, since MachO
doesn't store the symbol size separately, hence making
said situation always occur.

Differential Revision: http://reviews.llvm.org/D9925

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@238699 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/DebugInfo/DWARF/DWARFDebugLine.h b/include/llvm/DebugInfo/DWARF/DWARFDebugLine.h
index 5f223d4dc4e681a864927a2fd72e8f2fc394bd3e..93e7c790ccf90b8fb362d409a4a6482a40d9ad55 100644 (file)
--- a/include/llvm/DebugInfo/DWARF/DWARFDebugLine.h
+++ b/include/llvm/DebugInfo/DWARF/DWARFDebugLine.h
@@ -171,6 +171,9 @@ public:
   struct LineTable {
     LineTable();
 
+    // Represents an invalid row
+    const uint32_t UnknownRowIndex = UINT32_MAX;
+
     void appendRow(const DWARFDebugLine::Row &R) {
       Rows.push_back(R);
     }
@@ -179,7 +182,7 @@ public:
     }
 
     // Returns the index of the row with file/line info for a given address,
-    // or -1 if there is no such row.
+    // or UnknownRowIndex if there is no such row.
     uint32_t lookupAddress(uint64_t address) const;
 
     bool lookupAddressRange(uint64_t address, uint64_t size,
@@ -211,6 +214,10 @@ public:
     typedef SequenceVector::const_iterator SequenceIter;
     RowVector Rows;
     SequenceVector Sequences;
+
+  private:
+    uint32_t findRowInSeq(const DWARFDebugLine::Sequence &seq,
+                          uint64_t address) const;
   };
 
   const LineTable *getLineTable(uint32_t offset) const;

diff --git a/lib/DebugInfo/DWARF/DWARFDebugLine.cpp b/lib/DebugInfo/DWARF/DWARFDebugLine.cpp
index 2a737ef788fc63e92872fe74050ac4e07ee4d883..a0bee0da17656422c1b921c59b110f13f9a83ff0 100644 (file)
--- a/lib/DebugInfo/DWARF/DWARFDebugLine.cpp
+++ b/lib/DebugInfo/DWARF/DWARFDebugLine.cpp
@@ -531,10 +531,36 @@ bool DWARFDebugLine::LineTable::parse(DataExtractor debug_line_data,
   return end_offset;
 }
 
+uint32_t
+DWARFDebugLine::LineTable::findRowInSeq(const DWARFDebugLine::Sequence &seq,
+                                        uint64_t address) const {
+  if (!seq.containsPC(address))
+    return UnknownRowIndex;
+  // Search for instruction address in the rows describing the sequence.
+  // Rows are stored in a vector, so we may use arithmetical operations with
+  // iterators.
+  DWARFDebugLine::Row row;
+  row.Address = address;
+  RowIter first_row = Rows.begin() + seq.FirstRowIndex;
+  RowIter last_row = Rows.begin() + seq.LastRowIndex;
+  LineTable::RowIter row_pos = std::lower_bound(
+      first_row, last_row, row, DWARFDebugLine::Row::orderByAddress);
+  if (row_pos == last_row) {
+    return seq.LastRowIndex - 1;
+  }
+  uint32_t index = seq.FirstRowIndex + (row_pos - first_row);
+  if (row_pos->Address > address) {
+    if (row_pos == first_row)
+      return UnknownRowIndex;
+    else
+      index--;
+  }
+  return index;
+}
+
 uint32_t DWARFDebugLine::LineTable::lookupAddress(uint64_t address) const {
-  uint32_t unknown_index = UINT32_MAX;
   if (Sequences.empty())
-    return unknown_index;
+    return UnknownRowIndex;
   // First, find an instruction sequence containing the given address.
   DWARFDebugLine::Sequence sequence;
   sequence.LowPC = address;
@@ -549,31 +575,10 @@ uint32_t DWARFDebugLine::LineTable::lookupAddress(uint64_t address) const {
     found_seq = *seq_pos;
   } else {
     if (seq_pos == first_seq)
-      return unknown_index;
+      return UnknownRowIndex;
     found_seq = *(seq_pos - 1);
   }
-  if (!found_seq.containsPC(address))
-    return unknown_index;
-  // Search for instruction address in the rows describing the sequence.
-  // Rows are stored in a vector, so we may use arithmetical operations with
-  // iterators.
-  DWARFDebugLine::Row row;
-  row.Address = address;
-  RowIter first_row = Rows.begin() + found_seq.FirstRowIndex;
-  RowIter last_row = Rows.begin() + found_seq.LastRowIndex;
-  RowIter row_pos = std::lower_bound(first_row, last_row, row,
-      DWARFDebugLine::Row::orderByAddress);
-  if (row_pos == last_row) {
-    return found_seq.LastRowIndex - 1;
-  }
-  uint32_t index = found_seq.FirstRowIndex + (row_pos - first_row);
-  if (row_pos->Address > address) {
-    if (row_pos == first_row)
-      return unknown_index;
-    else
-      index--;
-  }
-  return index;
+  return findRowInSeq(found_seq, address);
 }
 
 bool DWARFDebugLine::LineTable::lookupAddressRange(
@@ -602,45 +607,21 @@ bool DWARFDebugLine::LineTable::lookupAddressRange(
   // index we just calculated
 
   while (seq_pos != last_seq && seq_pos->LowPC < end_addr) {
-    DWARFDebugLine::Sequence cur_seq = *seq_pos;
-    uint32_t first_row_index;
-    uint32_t last_row_index;
-    if (seq_pos == start_pos) {
-      // For the first sequence, we need to find which row in the sequence is the
-      // first in our range. Rows are stored in a vector, so we may use
-      // arithmetical operations with iterators.
-      DWARFDebugLine::Row row;
-      row.Address = address;
-      RowIter first_row = Rows.begin() + cur_seq.FirstRowIndex;
-      RowIter last_row = Rows.begin() + cur_seq.LastRowIndex;
-      RowIter row_pos = std::upper_bound(first_row, last_row, row,
-                                         DWARFDebugLine::Row::orderByAddress);
-      // The 'row_pos' iterator references the first row that is greater than
-      // our start address. Unless that's the first row, we want to start at
-      // the row before that.
-      first_row_index = cur_seq.FirstRowIndex + (row_pos - first_row);
-      if (row_pos != first_row)
-        --first_row_index;
-    } else
-      first_row_index = cur_seq.FirstRowIndex;
-
-    // For the last sequence in our range, we need to figure out the last row in
-    // range.  For all other sequences we can go to the end of the sequence.
-    if (cur_seq.HighPC > end_addr) {
-      DWARFDebugLine::Row row;
-      row.Address = end_addr;
-      RowIter first_row = Rows.begin() + cur_seq.FirstRowIndex;
-      RowIter last_row = Rows.begin() + cur_seq.LastRowIndex;
-      RowIter row_pos = std::upper_bound(first_row, last_row, row,
-                                         DWARFDebugLine::Row::orderByAddress);
-      // The 'row_pos' iterator references the first row that is greater than
-      // our end address.  The row before that is the last row we want.
-      last_row_index = cur_seq.FirstRowIndex + (row_pos - first_row) - 1;
-    } else
-      // Contrary to what you might expect, DWARFDebugLine::SequenceLastRowIndex
-      // isn't a valid index within the current sequence.  It's that plus one.
+    const DWARFDebugLine::Sequence &cur_seq = *seq_pos;
+    // For the first sequence, we need to find which row in the sequence is the
+    // first in our range.
+    uint32_t first_row_index = cur_seq.FirstRowIndex;
+    if (seq_pos == start_pos)
+      first_row_index = findRowInSeq(cur_seq, address);
+
+    // Figure out the last row in the range.
+    uint32_t last_row_index = findRowInSeq(cur_seq, end_addr - 1);
+    if (last_row_index == UnknownRowIndex)
       last_row_index = cur_seq.LastRowIndex - 1;
 
+    assert(first_row_index != UnknownRowIndex);
+    assert(last_row_index != UnknownRowIndex);
+
     for (uint32_t i = first_row_index; i <= last_row_index; ++i) {
       result.push_back(i);
     }

diff --git a/test/DebugInfo/debuglineinfo-macho.test b/test/DebugInfo/debuglineinfo-macho.test
index ac292d997ff3684ecb44c6e7782a4f6b8574f513..0c63dd6e8b0db3d6e3222ac3d097da82e973198f 100644 (file)
--- a/test/DebugInfo/debuglineinfo-macho.test
+++ b/test/DebugInfo/debuglineinfo-macho.test
@@ -1,12 +1,43 @@
 # Check that relocations get applied
 RUN: llvm-dwarfdump %p/Inputs/test-simple-macho.o | FileCheck %s
 RUN: llvm-dwarfdump %p/Inputs/test-multiple-macho.o | FileCheck %s
-RUN: llvm-rtdyld -printline %p/Inputs/test-multiple-macho.o | \
-RUN:   FileCheck --check-prefix=SIZE %s
+RUN: llvm-rtdyld -printline %p/Inputs/test-multiple-macho.o | FileCheck %s
 RUN: llvm-rtdyld -printobjline %p/Inputs/test-multiple-macho.o | FileCheck %s
 
-SIZE: Function: _bar, Size = 48
-SIZE: Function: _foo, Size = 16
-SIZE: Function: _fubar, Size = 46
-
 CHECK-NOT: error: failed to compute relocation: X86_64_RELOC_UNSIGNED
+
+# Check that relocations get applied correctly
+RUN: llvm-rtdyld -printobjline %p/Inputs/test-simple-macho.o \
+RUN:   | FileCheck %s -check-prefix TEST_SIMPLE
+RUN: llvm-rtdyld -printline %p/Inputs/test-simple-macho.o \
+RUN:   | FileCheck %s -check-prefix TEST_SIMPLE
+RUN: llvm-rtdyld -printobjline %p/Inputs/test-multiple-macho.o \
+RUN:   | FileCheck %s -check-prefix TEST_MULTIPLE
+RUN: llvm-rtdyld -printline %p/Inputs/test-multiple-macho.o \
+RUN:   | FileCheck %s -check-prefix TEST_MULTIPLE
+
+TEST_SIMPLE:      Function: _foo, Size = 11
+TEST_SIMPLE-NEXT:  Line info @ 0: simple.c, line:1
+TEST_SIMPLE-NEXT:  Line info @ 7: simple.c, line:2
+TEST_SIMPLE-NOT:   Line info @ 11: simple.c, line:2
+
+TEST_MULTIPLE:      Function: _bar, Size = 48
+TEST_MULTIPLE-NEXT:   Line info @ 0: multiple.c, line:5
+TEST_MULTIPLE-NEXT:   Line info @ 7: multiple.c, line:6
+TEST_MULTIPLE-NEXT:   Line info @ 16: multiple.c, line:9
+TEST_MULTIPLE-NEXT:   Line info @ 21: multiple.c, line:9
+TEST_MULTIPLE-NEXT:   Line info @ 26: multiple.c, line:7
+TEST_MULTIPLE-NEXT:   Line info @ 33: multiple.c, line:10
+TEST_MULTIPLE-NOT:    Line info @ 48: multiple.c, line:12
+TEST_MULTIPLE-NEXT: Function: _foo, Size = 16
+TEST_MULTIPLE-NEXT:   Line info @ 0: multiple.c, line:1
+TEST_MULTIPLE-NEXT:   Line info @ 7: multiple.c, line:2
+TEST_MULTIPLE-NOT:    Line info @ 16: multiple.c, line:5
+TEST_MULTIPLE-NEXT: Function: _fubar, Size = 46
+TEST_MULTIPLE-NEXT:   Line info @ 0: multiple.c, line:12
+TEST_MULTIPLE-NEXT:   Line info @ 7: multiple.c, line:13
+TEST_MULTIPLE-NEXT:   Line info @ 12: multiple.c, line:17
+TEST_MULTIPLE-NEXT:   Line info @ 25: multiple.c, line:15
+TEST_MULTIPLE-NEXT:   Line info @ 34: multiple.c, line:19
+TEST_MULTIPLE-NEXT:   Line info @ 41: multiple.c, line:21
+TEST_MULTIPLE-NOT:    Line info @ 46: multiple.c, line:21

diff --git a/test/DebugInfo/debuglineinfo.test b/test/DebugInfo/debuglineinfo.test
index 96a32285be46baedc952c63784d962eefbf661e9..720ba12ed7614b481e5d8054b8224ae1a8f11872 100644 (file)
--- a/test/DebugInfo/debuglineinfo.test
+++ b/test/DebugInfo/debuglineinfo.test
@@ -18,7 +18,6 @@ TEST_INLINE-NEXT: Line info @ 165: test-inline.cpp, line:35
 TEST_INLINE-NEXT: Function: _Z3foov, Size = 3
 TEST_INLINE-NEXT: Line info @ 0: test-inline.cpp, line:28
 TEST_INLINE-NEXT: Line info @ 2: test-inline.cpp, line:29
-TEST_INLINE-NEXT: Line info @ 3: test-inline.cpp, line:29
 TEST_INLINE-NEXT: Function: main, Size = 146
 TEST_INLINE-NEXT: Line info @ 0: test-inline.cpp, line:39
 TEST_INLINE-NEXT: Line info @ 21: test-inline.cpp, line:41
@@ -29,7 +28,6 @@ TEST_INLINE-NEXT: Line info @ 90: test-inline.cpp, line:45
 TEST_INLINE-NEXT: Line info @ 95: test-inline.cpp, line:46
 TEST_INLINE-NEXT: Line info @ 114: test-inline.cpp, line:48 
 TEST_INLINE-NEXT: Line info @ 141: test-inline.cpp, line:49
-TEST_INLINE-NEXT: Line info @ 146: test-inline.cpp, line:49
 
 ; This test checks the case where all code is in a single section.
 TEST_PARAMETERS:      Function: _Z15test_parametersPfPA2_dR11char_structPPitm, Size = 170
@@ -49,5 +47,4 @@ TEST_PARAMETERS-NEXT: Line info @ 90: test-parameters.cpp, line:45
 TEST_PARAMETERS-NEXT: Line info @ 95: test-parameters.cpp, line:46
 TEST_PARAMETERS-NEXT: Line info @ 114: test-parameters.cpp, line:48 
 TEST_PARAMETERS-NEXT: Line info @ 141: test-parameters.cpp, line:49
-TEST_PARAMETERS-NEXT: Line info @ 146: test-parameters.cpp, line:49