[compiler-rt] f0ab8d9 - [ASan] Use debuginfo for symbolization.

Mitch Phillips via llvm-commits llvm-commits at lists.llvm.org
Wed Jun 15 15:36:50 PDT 2022


Author: Mitch Phillips
Date: 2022-06-15T15:36:36-07:00
New Revision: f0ab8d90d47c4b1e0ea73e655777b4bc35e3f609

URL: https://github.com/llvm/llvm-project/commit/f0ab8d90d47c4b1e0ea73e655777b4bc35e3f609
DIFF: https://github.com/llvm/llvm-project/commit/f0ab8d90d47c4b1e0ea73e655777b4bc35e3f609.diff

LOG: [ASan] Use debuginfo for symbolization.

Hint: Looking here because your manual invocation of something in
'check-asan' broke? You need a new symbolizer (after D123538).

An upcoming patch will remove the internal metadata for global
variables. With D123534 and D123538, clang now emits DWARF debug info
for constant strings (the only global variable type it was missing), and
llvm-symbolizer is now able to symbolize all global variable addresses
(where previously it wouldn't give you the file:line information).

Move ASan's runtime over from the internal metadata to DWARF.

Differential Revision: https://reviews.llvm.org/D127552

Added: 
    

Modified: 
    compiler-rt/lib/asan/asan_globals.cpp
    compiler-rt/lib/asan/asan_interface_internal.h
    compiler-rt/lib/sanitizer_common/sanitizer_symbolizer_libcdep.cpp
    compiler-rt/test/asan/TestCases/Linux/odr-violation.cpp
    compiler-rt/test/asan/TestCases/global-location.cpp

Removed: 
    


################################################################################
diff  --git a/compiler-rt/lib/asan/asan_globals.cpp b/compiler-rt/lib/asan/asan_globals.cpp
index ecc2600f039a1..29eef6c68a516 100644
--- a/compiler-rt/lib/asan/asan_globals.cpp
+++ b/compiler-rt/lib/asan/asan_globals.cpp
@@ -86,10 +86,11 @@ static void ReportGlobal(const Global &g, const char *prefix) {
       "odr_indicator=%p\n",
       prefix, (void *)&g, (void *)g.beg, g.size, g.size_with_redzone, g.name,
       g.module_name, g.has_dynamic_init, (void *)g.odr_indicator);
-  if (g.location) {
-    Report("  location (%p): name=%s[%p], %d %d\n", (void *)g.location,
-           g.location->filename, (void *)g.location->filename,
-           g.location->line_no, g.location->column_no);
+
+  DataInfo info;
+  Symbolizer::GetOrInit()->SymbolizeData(g.beg, &info);
+  if (info.line != 0) {
+    Report("  location: name=%s, %d\n", info.file, info.line);
   }
 }
 
@@ -295,19 +296,15 @@ void PrintGlobalNameIfASCII(InternalScopedString *str, const __asan_global &g) {
               (char *)g.beg);
 }
 
-static const char *GlobalFilename(const __asan_global &g) {
-  const char *res = g.module_name;
-  // Prefer the filename from source location, if is available.
-  if (g.location) res = g.location->filename;
-  CHECK(res);
-  return res;
-}
-
 void PrintGlobalLocation(InternalScopedString *str, const __asan_global &g) {
-  str->append("%s", GlobalFilename(g));
-  if (!g.location) return;
-  if (g.location->line_no) str->append(":%d", g.location->line_no);
-  if (g.location->column_no) str->append(":%d", g.location->column_no);
+  DataInfo info;
+  Symbolizer::GetOrInit()->SymbolizeData(g.beg, &info);
+
+  if (info.line != 0) {
+    str->append("%s:%d", info.file, info.line);
+  } else {
+    str->append("%s", g.module_name);
+  }
 }
 
 } // namespace __asan

diff  --git a/compiler-rt/lib/asan/asan_interface_internal.h b/compiler-rt/lib/asan/asan_interface_internal.h
index 3e6e660288746..b0802a89ddbde 100644
--- a/compiler-rt/lib/asan/asan_interface_internal.h
+++ b/compiler-rt/lib/asan/asan_interface_internal.h
@@ -53,8 +53,9 @@ extern "C" {
     const char *module_name; // Module name as a C string. This pointer is a
                              // unique identifier of a module.
     uptr has_dynamic_init;   // Non-zero if the global has dynamic initializer.
-    __asan_global_source_location *location;  // Source location of a global,
-                                              // or NULL if it is unknown.
+    uptr windows_padding;    // TODO: Figure out how to remove this padding
+                             // that's simply here to make the MSVC incremental
+                             // linker happy...
     uptr odr_indicator;      // The address of the ODR indicator symbol.
   };
 

diff  --git a/compiler-rt/lib/sanitizer_common/sanitizer_symbolizer_libcdep.cpp b/compiler-rt/lib/sanitizer_common/sanitizer_symbolizer_libcdep.cpp
index 16cb65e1aac96..461fe96613688 100644
--- a/compiler-rt/lib/sanitizer_common/sanitizer_symbolizer_libcdep.cpp
+++ b/compiler-rt/lib/sanitizer_common/sanitizer_symbolizer_libcdep.cpp
@@ -363,14 +363,21 @@ void ParseSymbolizePCOutput(const char *str, SymbolizedStack *res) {
   }
 }
 
-// Parses a two-line string in the following format:
+// Parses a two- or three-line string in the following format:
 //   <symbol_name>
 //   <start_address> <size>
-// Used by LLVMSymbolizer and InternalSymbolizer.
+//   <filename>:<column>
+// Used by LLVMSymbolizer and InternalSymbolizer. LLVMSymbolizer added support
+// for symbolizing the third line in D123538, but we support the older two-line
+// information as well.
 void ParseSymbolizeDataOutput(const char *str, DataInfo *info) {
   str = ExtractToken(str, "\n", &info->name);
   str = ExtractUptr(str, " ", &info->start);
   str = ExtractUptr(str, "\n", &info->size);
+  // Note: If the third line isn't present, these calls will set info.{file,
+  // line} to empty strings.
+  str = ExtractToken(str, ":", &info->file);
+  str = ExtractUptr(str, "\n", &info->line);
 }
 
 static void ParseSymbolizeFrameOutput(const char *str,

diff  --git a/compiler-rt/test/asan/TestCases/Linux/odr-violation.cpp b/compiler-rt/test/asan/TestCases/Linux/odr-violation.cpp
index 478568cd122c2..1c8ea99430df2 100644
--- a/compiler-rt/test/asan/TestCases/Linux/odr-violation.cpp
+++ b/compiler-rt/test/asan/TestCases/Linux/odr-violation.cpp
@@ -7,15 +7,15 @@
 // pointers. This setting is not on by default because it's too expensive.
 //
 // Different size: detect a bug if detect_odr_violation>=1
-// RUN: %clangxx_asan -DBUILD_SO=1 -fPIC -shared %s -o %dynamiclib
-// RUN: %clangxx_asan %s %ld_flags_rpath_exe -o %t-ODR-EXE
+// RUN: %clangxx_asan -g -DBUILD_SO=1 -fPIC -shared %s -o %dynamiclib
+// RUN: %clangxx_asan -g %s %ld_flags_rpath_exe -o %t-ODR-EXE
 // RUN: %env_asan_opts=fast_unwind_on_malloc=0:detect_odr_violation=1 not %run %t-ODR-EXE 2>&1 | FileCheck %s
 // RUN: %env_asan_opts=fast_unwind_on_malloc=0:detect_odr_violation=2 not %run %t-ODR-EXE 2>&1 | FileCheck %s
 // RUN: %env_asan_opts=fast_unwind_on_malloc=0:detect_odr_violation=0     %run %t-ODR-EXE 2>&1 | FileCheck %s --check-prefix=DISABLED
 // RUN: %env_asan_opts=fast_unwind_on_malloc=0                        not %run %t-ODR-EXE 2>&1 | FileCheck %s
 //
 // Same size: report a bug only if detect_odr_violation>=2.
-// RUN: %clangxx_asan -DBUILD_SO=1 -fPIC -shared %s -o %dynamiclib -DSZ=100
+// RUN: %clangxx_asan -g -DBUILD_SO=1 -fPIC -shared %s -o %dynamiclib -DSZ=100
 // RUN: %env_asan_opts=fast_unwind_on_malloc=0:detect_odr_violation=1     %run %t-ODR-EXE 2>&1 | FileCheck %s --check-prefix=DISABLED
 // RUN: %env_asan_opts=fast_unwind_on_malloc=0:detect_odr_violation=2 not %run %t-ODR-EXE 2>&1 | FileCheck %s
 // RUN: %env_asan_opts=fast_unwind_on_malloc=0                        not %run %t-ODR-EXE 2>&1 | FileCheck %s
@@ -26,18 +26,18 @@
 // RUN: rm -f %t.supp
 //
 // Use private aliases for global variables without indicator symbol.
-// RUN: %clangxx_asan -DBUILD_SO=1 -fPIC -shared -mllvm -asan-use-private-alias %s -o %dynamiclib -DSZ=100
-// RUN: %clangxx_asan -mllvm -asan-use-private-alias %s %ld_flags_rpath_exe -o %t-ODR-EXE
+// RUN: %clangxx_asan -g -DBUILD_SO=1 -fPIC -shared -mllvm -asan-use-private-alias %s -o %dynamiclib -DSZ=100
+// RUN: %clangxx_asan -g -mllvm -asan-use-private-alias %s %ld_flags_rpath_exe -o %t-ODR-EXE
 // RUN: %env_asan_opts=fast_unwind_on_malloc=0 %run %t-ODR-EXE 2>&1 | FileCheck %s --check-prefix=DISABLED
 
 // Use private aliases for global variables: use indicator symbol to detect ODR violation.
-// RUN: %clangxx_asan -DBUILD_SO=1 -fPIC -shared -mllvm -asan-use-private-alias -mllvm -asan-use-odr-indicator  %s -o %dynamiclib -DSZ=100
-// RUN: %clangxx_asan -mllvm -asan-use-private-alias -mllvm -asan-use-odr-indicator %s %ld_flags_rpath_exe -o %t-ODR-EXE
+// RUN: %clangxx_asan -g -DBUILD_SO=1 -fPIC -shared -mllvm -asan-use-private-alias -mllvm -asan-use-odr-indicator  %s -o %dynamiclib -DSZ=100
+// RUN: %clangxx_asan -g -mllvm -asan-use-private-alias -mllvm -asan-use-odr-indicator %s %ld_flags_rpath_exe -o %t-ODR-EXE
 // RUN: %env_asan_opts=fast_unwind_on_malloc=0 not %run %t-ODR-EXE 2>&1 | FileCheck %s
 
 // Same as above but with clang switches.
-// RUN: %clangxx_asan -DBUILD_SO=1 -fPIC -shared -fsanitize-address-use-odr-indicator %s -o %dynamiclib -DSZ=100
-// RUN: %clangxx_asan -fsanitize-address-use-odr-indicator %s %ld_flags_rpath_exe -o %t-ODR-EXE
+// RUN: %clangxx_asan -g -DBUILD_SO=1 -fPIC -shared -fsanitize-address-use-odr-indicator %s -o %dynamiclib -DSZ=100
+// RUN: %clangxx_asan -g -fsanitize-address-use-odr-indicator %s %ld_flags_rpath_exe -o %t-ODR-EXE
 // RUN: %env_asan_opts=fast_unwind_on_malloc=0 not %run %t-ODR-EXE 2>&1 | FileCheck %s
 
 // GNU driver doesn't handle .so files properly.
@@ -55,7 +55,7 @@ namespace foo { char G[SZ]; }
 #include <stdio.h>
 namespace foo { char G[100]; }
 // CHECK: ERROR: AddressSanitizer: odr-violation
-// CHECK: size=100 'foo::G' {{.*}}odr-violation.cpp:[[@LINE-2]]:22
+// CHECK: size=100 'foo::G' {{.*}}odr-violation.cpp:[[@LINE-2]]
 // CHECK: size={{4|100}} 'foo::G'
 int main(int argc, char **argv) {
   printf("PASS: %p\n", &foo::G);

diff  --git a/compiler-rt/test/asan/TestCases/global-location.cpp b/compiler-rt/test/asan/TestCases/global-location.cpp
index 42711f97c21b9..8869ac5227843 100644
--- a/compiler-rt/test/asan/TestCases/global-location.cpp
+++ b/compiler-rt/test/asan/TestCases/global-location.cpp
@@ -1,21 +1,30 @@
-// RUN: %clangxx_asan -O2 %s -o %t
+// RUN: %clangxx_asan -g -O2 %s -o %t
 // RUN: not %run %t g 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=GLOB
 // RUN: not %run %t c 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=CLASS_STATIC
 // RUN: not %run %t f 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=FUNC_STATIC
 // RUN: not %run %t l 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=LITERAL
 
+// RUN: %clangxx_asan -O2 %s -o %t
+// RUN: llvm-strip -s %t
+// RUN: not %run %t g 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=GLOB-NO-G
+// RUN: not %run %t c 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=CLASS_STATIC-NO-G
+// RUN: not %run %t f 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=FUNC_STATIC-NO-G
+// RUN: not %run %t l 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=LITERAL-NO-G
+
 // CHECK: AddressSanitizer: global-buffer-overflow
 
 #include <string.h>
 
 struct C {
   static int array[10];
+  // CLASS_STATIC:      0x{{.*}} is located 4 bytes to the right of global variable 'C::array' defined in '{{.*}}global-location.cpp:[[@LINE-1]]' {{.*}} of size 40
+  // CLASS_STATIC-NO-G: 0x{{.*}} is located 4 bytes to the right of global variable 'C::array' defined in '{{.*}}global-location.cpp' {{.*}} of size 40
 };
 
 int global[10];
-// GLOB: 0x{{.*}} is located 4 bytes to the right of global variable 'global' defined in '{{.*}}global-location.cpp:[[@LINE-1]]:5' {{.*}} of size 40
+// GLOB:      0x{{.*}} is located 4 bytes to the right of global variable 'global' defined in '{{.*}}global-location.cpp:[[@LINE-1]]' {{.*}} of size 40
+// GLOB-NO-G: 0x{{.*}} is located 4 bytes to the right of global variable 'global' defined in '{{.*}}global-location.cpp' {{.*}} of size 40
 int C::array[10];
-// CLASS_STATIC: 0x{{.*}} is located 4 bytes to the right of global variable 'C::array' defined in '{{.*}}global-location.cpp:[[@LINE-1]]:8' {{.*}} of size 40
 
 int main(int argc, char **argv) {
   int one = argc - 1;
@@ -24,12 +33,14 @@ int main(int argc, char **argv) {
   case 'c': return C::array[one * 11];
   case 'f':
     static int array[10];
-    // FUNC_STATIC: 0x{{.*}} is located 4 bytes to the right of global variable 'array' defined in '{{.*}}global-location.cpp:[[@LINE-1]]:16' {{.*}} of size 40
+    // FUNC_STATIC:      0x{{.*}} is located 4 bytes to the right of global variable 'array' defined in '{{.*}}global-location.cpp:[[@LINE-1]]' {{.*}} of size 40
+    // FUNC_STATIC-NO-G: 0x{{.*}} is located 4 bytes to the right of global variable 'array' defined in '{{.*}}global-location.cpp' {{.*}} of size 40
     memset(array, 0, 10);
     return array[one * 11];
   case 'l':
     const char *str = "0123456789";
-    // LITERAL: 0x{{.*}} is located 0 bytes to the right of global variable {{.*}} defined in '{{.*}}global-location.cpp:[[@LINE-1]]:23' {{.*}} of size 11
+    // LITERAL:      0x{{.*}} is located 0 bytes to the right of global variable {{.*}} defined in '{{.*}}global-location.cpp:[[@LINE-1]]' {{.*}} of size 11
+    // LITERAL-NO-G: 0x{{.*}} is located 0 bytes to the right of global variable {{.*}} defined in '{{.*}}global-location.cpp' {{.*}} of size 11
     return str[one * 11];
   }
   return 0;


        


More information about the llvm-commits mailing list