[UBSan] Implement src:*=sanitize for UBSan

clang/docs/ReleaseNotes.rst

@@ -1013,6 +1013,7 @@ Sanitizers
 ----------
 
 - ``-fsanitize=vptr`` is no longer a part of ``-fsanitize=undefined``.
+- Sanitizer ignorelists now support the syntax ``src:*=sanitize``.
 
 Python Binding Changes
 ----------------------

clang/docs/SanitizerSpecialCaseList.rst

@@ -58,7 +58,7 @@ Usage with UndefinedBehaviorSanitizer
 ability to adjust instrumentation based on type.
 
 By default, supported sanitizers will have their instrumentation disabled for
-types specified within an ignorelist.
+entries specified within an ignorelist.
 
 .. code-block:: bash
 
@@ -77,10 +77,9 @@ For example, supplying the above ``ignorelist.txt`` to
 ``-fsanitize-ignorelist=ignorelist.txt`` disables overflow sanitizer
 instrumentation for arithmetic operations containing values of type ``int``.
 
-The ``=sanitize`` category is also supported. Any types assigned to the
-``sanitize`` category will have their sanitizer instrumentation remain. If the
-same type appears within or across ignorelists with different categories the
-``sanitize`` category takes precedence -- regardless of order.
+The ``=sanitize`` category is also supported. Any ``=sanitize`` category
+entries enable sanitizer instrumentation, even if it was ignored by entries
+before.
 
 With this, one may disable instrumentation for some or all types and
 specifically allow instrumentation for one or many types -- including types
@@ -103,6 +102,23 @@ supported sanitizers.
     char c = toobig; // also not instrumented
   }
 
+If multiple entries match the source, than the latest entry takes the
+precedence.
+
+.. code-block:: bash
+
+  $ cat ignorelist1.txt
+  # test.cc will be instrumented.
+  src:*
+  src:*/mylib/*=sanitize
+  src:*/mylib/test.cc
+
+  $ cat ignorelist2.txt
+  # test.cc will not be instrumented.
+  src:*
+  src:*/mylib/test.cc
+  src:*/mylib/*=sanitize
+
 Format
 ======
 

clang/include/clang/Basic/SanitizerSpecialCaseList.h

@@ -43,13 +43,18 @@ class SanitizerSpecialCaseList : public llvm::SpecialCaseList {
   bool inSection(SanitizerMask Mask, StringRef Prefix, StringRef Query,
                  StringRef Category = StringRef()) const;
 
+  // Query ignorelisted entries if any bit in Mask matches the entry's section.
+  // Return 0 if not found. If found, return the line number (starts with 1).
+  unsigned inSectionBlame(SanitizerMask Mask, StringRef Prefix, StringRef Query,
+                          StringRef Category = StringRef()) const;
+
 protected:
   // Initialize SanitizerSections.
   void createSanitizerSections();
 
   struct SanitizerSection {
     SanitizerSection(SanitizerMask SM, SectionEntries &E)
-        : Mask(SM), Entries(E){};
+        : Mask(SM), Entries(E) {};
 
     SanitizerMask Mask;
     SectionEntries &Entries;

clang/lib/Basic/NoSanitizeList.cpp

@@ -44,7 +44,13 @@ bool NoSanitizeList::containsFunction(SanitizerMask Mask,
 
 bool NoSanitizeList::containsFile(SanitizerMask Mask, StringRef FileName,
                                   StringRef Category) const {
-  return SSCL->inSection(Mask, "src", FileName, Category);
+  unsigned NoSanLine = SSCL->inSectionBlame(Mask, "src", FileName, Category);
+  if (NoSanLine == 0)
+    return false;
+  unsigned SanLine = SSCL->inSectionBlame(Mask, "src", FileName, "sanitize");
+  // If we have two cases such as `src:a.cpp=sanitize` and `src:a.cpp`, the
+  // current entry override the previous entry.
+  return !SanLine || NoSanLine > SanLine;
 }
 
 bool NoSanitizeList::containsMainFile(SanitizerMask Mask, StringRef FileName,

clang/lib/Basic/SanitizerSpecialCaseList.cpp

@@ -11,6 +11,7 @@
 //
 //===----------------------------------------------------------------------===//
 #include "clang/Basic/SanitizerSpecialCaseList.h"
+#include "llvm/ADT/STLExtras.h"
 
 using namespace clang;
 
@@ -56,10 +57,20 @@ void SanitizerSpecialCaseList::createSanitizerSections() {
 bool SanitizerSpecialCaseList::inSection(SanitizerMask Mask, StringRef Prefix,
                                          StringRef Query,
                                          StringRef Category) const {
-  for (auto &S : SanitizerSections)
-    if ((S.Mask & Mask) &&
-        SpecialCaseList::inSectionBlame(S.Entries, Prefix, Query, Category))
-      return true;
+  return inSectionBlame(Mask, Prefix, Query, Category);
+}
 
-  return false;
+unsigned SanitizerSpecialCaseList::inSectionBlame(SanitizerMask Mask,
+                                                  StringRef Prefix,
+                                                  StringRef Query,
+                                                  StringRef Category) const {
+  for (const auto &S : llvm::reverse(SanitizerSections)) {
+    if (S.Mask & Mask) {
+      unsigned lineNum =
+          SpecialCaseList::inSectionBlame(S.Entries, Prefix, Query, Category);
+      if (lineNum > 0)
+        return lineNum;
+    }
+  }
+  return 0;
 }

clang/test/CodeGen/ubsan-src-ignorelist-category.test

@@ -3,14 +3,15 @@
 
 // RUN: %clang_cc1 -triple x86_64-linux-gnu -fsanitize=signed-integer-overflow -fsanitize-ignorelist=%t/src.ignorelist -emit-llvm %t/test2.c -o -             | FileCheck %s --check-prefixes=CHECK2
 
-// RUN: %clang_cc1 -triple x86_64-linux-gnu -fsanitize=signed-integer-overflow -fsanitize-ignorelist=%t/src.ignorelist -emit-llvm %t/test1.c -o -             | FileCheck %s --check-prefixes=CHECK1,IGNORE
+// RUN: %clang_cc1 -triple x86_64-linux-gnu -fsanitize=signed-integer-overflow -fsanitize-ignorelist=%t/src.ignorelist -emit-llvm %t/test1.c -o -             | FileCheck %s --check-prefixes=CHECK1,SANITIZE
 // RUN: %clang_cc1 -triple x86_64-linux-gnu -fsanitize=signed-integer-overflow -fsanitize-ignorelist=%t/src.ignorelist.contradict1 -emit-llvm %t/test1.c -o - | FileCheck %s --check-prefixes=CHECK1,IGNORE
-// RUN: %clang_cc1 -triple x86_64-linux-gnu -fsanitize=signed-integer-overflow -fsanitize-ignorelist=%t/src.ignorelist.contradict2 -emit-llvm %t/test1.c -o - | FileCheck %s --check-prefixes=CHECK1,IGNORE
+// RUN: %clang_cc1 -triple x86_64-linux-gnu -fsanitize=signed-integer-overflow -fsanitize-ignorelist=%t/src.ignorelist.contradict2 -emit-llvm %t/test1.c -o - | FileCheck %s --check-prefixes=CHECK1,SANITIZE
 // RUN: %clang_cc1 -triple x86_64-linux-gnu -fsanitize=signed-integer-overflow -fsanitize-ignorelist=%t/src.ignorelist.contradict3 -emit-llvm %t/test1.c -o - | FileCheck %s --check-prefixes=CHECK1,IGNORE
-// RUN: %clang_cc1 -triple x86_64-linux-gnu -fsanitize=signed-integer-overflow -fsanitize-ignorelist=%t/src.ignorelist.contradict4 -emit-llvm %t/test1.c -o - | FileCheck %s --check-prefixes=CHECK1,IGNORE
+// RUN: %clang_cc1 -triple x86_64-linux-gnu -fsanitize=signed-integer-overflow -fsanitize-ignorelist=%t/src.ignorelist.contradict4 -emit-llvm %t/test1.c -o - | FileCheck %s --check-prefixes=CHECK1,SANITIZE
 // RUN: %clang_cc1 -triple x86_64-linux-gnu -fsanitize=signed-integer-overflow -fsanitize-ignorelist=%t/src.ignorelist.contradict5 -emit-llvm %t/test1.c -o - | FileCheck %s --check-prefixes=CHECK1,IGNORE
-// RUN: %clang_cc1 -triple x86_64-linux-gnu -fsanitize=signed-integer-overflow -fsanitize-ignorelist=%t/src.ignorelist.contradict6 -emit-llvm %t/test1.c -o - | FileCheck %s --check-prefixes=CHECK1,IGNORE
-
+// RUN: %clang_cc1 -triple x86_64-linux-gnu -fsanitize=signed-integer-overflow -fsanitize-ignorelist=%t/src.ignorelist.contradict6 -emit-llvm %t/test1.c -o - | FileCheck %s --check-prefixes=CHECK1,SANITIZE
+// RUN: %clang_cc1 -triple x86_64-linux-gnu -fsanitize=signed-integer-overflow -fsanitize-ignorelist=%t/src.ignorelist.contradict7 -emit-llvm %t/test1.c -o - | FileCheck %s --check-prefixes=CHECK1,IGNORE
+// RUN: %clang_cc1 -triple x86_64-linux-gnu -fsanitize=signed-integer-overflow -fsanitize-ignorelist=%t/src.ignorelist.contradict8 -emit-llvm %t/test1.c -o - | FileCheck %s --check-prefixes=CHECK1,SANITIZE
 
 // Verify ubsan only emits checks for files in the allowlist
 
@@ -52,6 +53,31 @@ src:*/tes*1.c=sanitize
 src:*/te*t1.c
 src:*/t*st1.c=sanitize
 
+//--- src.ignorelist.contradict7
+[{unsigned-integer-overflow,signed-integer-overflow}]
+src:*
+src:*/tes*1.c=sanitize
+src:*/te*t1.c
+src:*/t*st1.c=sanitize
+[{unsigned-integer-overflow,signed-integer-overflow}]
+src:*
+src:*/te*t1.c
+src:*/tes*1.c=sanitize
+src:*/test1.c
+
+//--- src.ignorelist.contradict8
+[{unsigned-integer-overflow,signed-integer-overflow}]
+src:*
+src:*/te*t1.c
+src:*/tes*1.c=sanitize
+src:*/test1.c
+[{unsigned-integer-overflow,signed-integer-overflow}]
+src:*
+src:*/tes*1.c=sanitize
+src:*/te*t1.c
+src:*/t*st1.c=sanitize
+
+
 //--- test1.c
 // CHECK1-LABEL: define dso_local i32 @add
 int add(int a, int b) {