[Support] Add more context to DataExtractor getLEB128 errors

[jhenderson]

Summary

This patch adds the current offset to the error messages reported by getLEB128, so that clients don't have to add it themselves and can just report the error when they receive it.

[dblaikie]

Sounds good to me

[clayborg]

That will be a nice addition to the error text.

llvm/lib/Support/DataExtractor.cpp

if (isError(Err))
     return T();
 
   const char *error;
   unsigned bytes_read;
   T result =
       Decoder(Bytes.data() + *OffsetPtr, &bytes_read, Bytes.end(), &error);
   if (error) {
     if (Err)
-      *Err = createStringError(errc::illegal_byte_sequence, error);
+      *Err = createStringError(errc::illegal_byte_sequence,
+                               "unable to decode LEB128 at offset 0x%8.8" PRIx64
+                               ": %s",
+                               *OffsetPtr, error);
     return T();
   }
   *OffsetPtr += bytes_read;
   return result;
 }
 
 uint64_t DataExtractor::getULEB128(uint64_t *offset_ptr, Error *Err) const {
   return getLEB128(Data, offset_ptr, Err, decodeULEB128);

llvm/test/DebugInfo/X86/dwarfdump-debug-loclists-error-cases.s

 # RUN: llvm-mc %s -filetype obj -triple x86_64-pc-linux --defsym CASE1=0 -o %t1.o
-# RUN: not llvm-dwarfdump -debug-loclists %t1.o 2>&1 | FileCheck %s --check-prefix=ULEB
+# RUN: not llvm-dwarfdump -debug-loclists %t1.o 2>&1 | FileCheck %s --check-prefix=ULEB -DOFFSET=0x0000000d
 
 # RUN: llvm-mc %s -filetype obj -triple x86_64-pc-linux --defsym CASE2=0 -o %t2.o
-# RUN: not llvm-dwarfdump -debug-loclists %t2.o 2>&1 | FileCheck %s --check-prefix=ULEB
+# RUN: not llvm-dwarfdump -debug-loclists %t2.o 2>&1 | FileCheck %s --check-prefix=ULEB -DOFFSET=0x0000000e
 
 # RUN: llvm-mc %s -filetype obj -triple x86_64-pc-linux --defsym CASE3=0 -o %t3.o
-# RUN: not llvm-dwarfdump -debug-loclists %t3.o 2>&1 | FileCheck %s --check-prefix=ULEB
+# RUN: not llvm-dwarfdump -debug-loclists %t3.o 2>&1 | FileCheck %s --check-prefix=ULEB -DOFFSET=0x0000000f
 
 # RUN: llvm-mc %s -filetype obj -triple x86_64-pc-linux --defsym CASE4=0 -o %t4.o
 # RUN: not llvm-dwarfdump -debug-loclists %t4.o 2>&1 | FileCheck %s
 
 # RUN: llvm-mc %s -filetype obj -triple x86_64-pc-linux --defsym CASE5=0 -o %t5.o
 # RUN: not llvm-dwarfdump -debug-loclists %t5.o 2>&1 | FileCheck %s
 
 # RUN: llvm-mc %s -filetype obj -triple x86_64-pc-linux --defsym CASE6=0 -o %t6.o
 # RUN: not llvm-dwarfdump -debug-loclists %t6.o 2>&1 | FileCheck %s
 
 # RUN: llvm-mc %s -filetype obj -triple x86_64-pc-linux --defsym CASE7=0 -o %t7.o
 # RUN: not llvm-dwarfdump -debug-loclists %t7.o 2>&1 | FileCheck %s --check-prefix=UNIMPL
 
 # CHECK: error: unexpected end of data
-# ULEB: error: malformed uleb128, extends past end
+# ULEB: error: unable to decode LEB128 at offset [[OFFSET]]: malformed uleb128, extends past end
 # UNIMPL: error: LLE of kind 47 not supported
 
 .section  .debug_loclists,"",@progbits
   .long  .Ldebug_loclist_table_end0-.Ldebug_loclist_table_start0
 .Ldebug_loclist_table_start0:
  .short 5                        # Version.
  .byte 8                         # Address size.
  .byte 0                         # Segment selector size.

llvm/test/tools/llvm-dwarfdump/X86/debug_line_short_prologue.s

 
 # RUN: llvm-mc -triple x86_64-pc-linux %s -filetype=obj --defsym CASE=3 -o %t3
 # RUN: llvm-dwarfdump -debug-line %t3 2>&1 | FileCheck %s --check-prefixes=ALL,OK
 
 # ALL:      debug_line[0x00000000]
 # C0-NEXT:  warning: parsing line table prologue at 0x00000000 found an invalid directory or file table description at 0x00000027
 # C0-NEXT:  warning: failed to parse entry content descriptors: unexpected end of data at offset 0x27
 # C1-NEXT:  warning: parsing line table prologue at 0x00000000 found an invalid directory or file table description at 0x0000002a
-# C1-NEXT:  warning: failed to parse entry content descriptors: malformed uleb128, extends past end
+# C1-NEXT:  warning: failed to parse entry content descriptors: unable to decode LEB128 at offset 0x0000002a: malformed uleb128, extends past end
 # C2-NEXT:  warning: parsing line table prologue at 0x00000000 found an invalid directory or file table description at 0x0000002b
-# C2-NEXT:  warning: failed to parse entry content descriptors: malformed uleb128, extends past end
+# C2-NEXT:  warning: failed to parse entry content descriptors: unable to decode LEB128 at offset 0x0000002b: malformed uleb128, extends past end
 # ALL:      include_directories[  0] = "/tmp"
 # OK:       file_names[  0]:
 # OK-NEXT:             name: "foo"
 # OK-NEXT:        dir_index: 0
 
 .section .debug_line,"",@progbits
 .long   .Lend-.Lstart   # Length of Unit
 .Lstart:

llvm/unittests/Support/DataExtractorTest.cpp

TEST(DataExtractorTest, LEB128_error) {
   EXPECT_EQ(0U, Offset);
 
   Offset = 0;
   EXPECT_EQ(0U, DE.getSLEB128(&Offset));
   EXPECT_EQ(0U, Offset);
 
   DataExtractor::Cursor C(0);
   EXPECT_EQ(0U, DE.getULEB128(C));
-  EXPECT_THAT_ERROR(C.takeError(), Failed());
+  EXPECT_THAT_ERROR(
+      C.takeError(),
+      FailedWithMessage("unable to decode LEB128 at offset 0x00000000: "
+                        "malformed uleb128, extends past end"));
 
   C = DataExtractor::Cursor(0);
   EXPECT_EQ(0U, DE.getSLEB128(C));
-  EXPECT_THAT_ERROR(C.takeError(), Failed());
+  EXPECT_THAT_ERROR(
+      C.takeError(),
+      FailedWithMessage("unable to decode LEB128 at offset 0x00000000: "
+                        "malformed sleb128, extends past end"));
+
+  // Show non-zero offsets are reported appropriately.
+  C = DataExtractor::Cursor(1);
+  EXPECT_EQ(0U, DE.getULEB128(C));
+  EXPECT_THAT_ERROR(
+      C.takeError(),
+      FailedWithMessage("unable to decode LEB128 at offset 0x00000001: "
+                        "malformed uleb128, extends past end"));
 }
 
 TEST(DataExtractorTest, Cursor_tell) {
   DataExtractor DE(StringRef("AB"), false, 8);
   DataExtractor::Cursor C(0);
   // A successful read operation advances the cursor
   EXPECT_EQ('A', DE.getU8(C));
   EXPECT_EQ(1u, C.tell());