[sanitizer] Add strlen to the common interceptors

Summary:
Adds strlen to the common interceptors, under a new common flag
intercept_strlen.  This provides better sharing of interception code among
sanitizers and cleans up the inconsistent type declarations of the
previously duplicated interceptors.

Removes the now-duplicate strlen interceptor from asan, msan, and tsan.
The entry check semantics are normalized now for msan and asan, whose
private strlen interceptors contained multiple layers of checks that
included impossible-to-reach code.  The new semantics are identical to the
old: bypass interception if in the middle of init or if both on Mac and not
initialized; else, call the init routine and proceed.

Patch by Derek Bruening!

Reviewers: samsonov, vitalybuka

Subscribers: llvm-commits, kcc, zhaoqin

Differential Revision: http://reviews.llvm.org/D18020

git-svn-id: https://llvm.org/svn/llvm-project/compiler-rt/trunk@263177 91177308-0d34-0410-b5e6-96231b3b80d8

7 files changed, 26 insertions, 37 deletions

diff --git a/lib/asan/asan_flags.cc b/lib/asan/asan_flags.cc
index 363ee67e7..135341fc0 100644
--- a/lib/asan/asan_flags.cc
+++ b/lib/asan/asan_flags.cc
@@ -159,6 +159,10 @@ void InitializeFlags() {
         (ASAN_LOW_MEMORY) ? 1UL << 6 : 1UL << 8;
     f->quarantine_size_mb = kDefaultQuarantineSizeMb;
   }
+  if (!f->replace_str && common_flags()->intercept_strlen) {
+    Report("WARNING: strlen interceptor is enabled even though replace_str=0. "
+           "Use intercept_strlen=0 to disable it.");
+  }
 }
 
 }  // namespace __asan
diff --git a/lib/asan/asan_interceptors.cc b/lib/asan/asan_interceptors.cc
index faac15b32..4a10afcc1 100644
--- a/lib/asan/asan_interceptors.cc
+++ b/lib/asan/asan_interceptors.cc
@@ -580,23 +580,6 @@ INTERCEPTOR(char*, strdup, const char *s) {
 }
 #endif
 
-INTERCEPTOR(SIZE_T, strlen, const char *s) {
-  void *ctx;
-  ASAN_INTERCEPTOR_ENTER(ctx, strlen);
-  if (UNLIKELY(!asan_inited)) return internal_strlen(s);
-  // strlen is called from malloc_default_purgeable_zone()
-  // in __asan::ReplaceSystemAlloc() on Mac.
-  if (asan_init_is_running) {
-    return REAL(strlen)(s);
-  }
-  ENSURE_ASAN_INITED();
-  SIZE_T length = REAL(strlen)(s);
-  if (flags()->replace_str) {
-    ASAN_READ_RANGE(ctx, s, length + 1);
-  }
-  return length;
-}
-
 INTERCEPTOR(SIZE_T, wcslen, const wchar_t *s) {
   void *ctx;
   ASAN_INTERCEPTOR_ENTER(ctx, wcslen);
@@ -763,7 +746,6 @@ void InitializeAsanInterceptors() {
   ASAN_INTERCEPT_FUNC(strcat);  // NOLINT
   ASAN_INTERCEPT_FUNC(strchr);
   ASAN_INTERCEPT_FUNC(strcpy);  // NOLINT
-  ASAN_INTERCEPT_FUNC(strlen);
   ASAN_INTERCEPT_FUNC(wcslen);
   ASAN_INTERCEPT_FUNC(strncat);
   ASAN_INTERCEPT_FUNC(strncpy);
diff --git a/lib/msan/msan_interceptors.cc b/lib/msan/msan_interceptors.cc
index 1683a886e..1b97cb117 100644
--- a/lib/msan/msan_interceptors.cc
+++ b/lib/msan/msan_interceptors.cc
@@ -43,6 +43,8 @@ using __sanitizer::atomic_load;
 using __sanitizer::atomic_store;
 using __sanitizer::atomic_uintptr_t;
 
+DECLARE_REAL(SIZE_T, strlen, const char *s)
+
 #if SANITIZER_FREEBSD
 #define __errno_location __error
 #endif
@@ -280,15 +282,6 @@ INTERCEPTOR(void, malloc_stats, void) {
 #define MSAN_MAYBE_INTERCEPT_MALLOC_STATS
 #endif
 
-INTERCEPTOR(SIZE_T, strlen, const char *s) {
-  if (msan_init_is_running)
-    return REAL(strlen)(s);
-  ENSURE_MSAN_INITED();
-  SIZE_T res = REAL(strlen)(s);
-  CHECK_UNPOISONED(s, res + 1);
-  return res;
-}
-
 INTERCEPTOR(SIZE_T, strnlen, const char *s, SIZE_T n) {
   ENSURE_MSAN_INITED();
   SIZE_T res = REAL(strnlen)(s, n);
@@ -1562,7 +1555,6 @@ void InitializeInterceptors() {
   INTERCEPT_FUNCTION(strndup);
   MSAN_MAYBE_INTERCEPT___STRNDUP;
   INTERCEPT_FUNCTION(strncpy);  // NOLINT
-  INTERCEPT_FUNCTION(strlen);
   INTERCEPT_FUNCTION(strnlen);
   INTERCEPT_FUNCTION(gcvt);
   INTERCEPT_FUNCTION(strcat);  // NOLINT
diff --git a/lib/sanitizer_common/sanitizer_common_interceptors.inc b/lib/sanitizer_common/sanitizer_common_interceptors.inc
index 2e630232a..560dd3e11 100644
--- a/lib/sanitizer_common/sanitizer_common_interceptors.inc
+++ b/lib/sanitizer_common/sanitizer_common_interceptors.inc
@@ -11,7 +11,7 @@
 // ThreadSanitizer, MemorySanitizer, etc.
 //
 // This file should be included into the tool's interceptor file,
-// which has to define it's own macros:
+// which has to define its own macros:
 //   COMMON_INTERCEPTOR_ENTER
 //   COMMON_INTERCEPTOR_ENTER_NOIGNORE
 //   COMMON_INTERCEPTOR_READ_RANGE
@@ -200,6 +200,20 @@ UNUSED static void DeleteInterceptorMetadata(void *addr) {
 }
 #endif  // SI_NOT_WINDOWS
 
+#if SANITIZER_INTERCEPT_STRLEN
+INTERCEPTOR(SIZE_T, strlen, const char *s) {
+  void *ctx;
+  COMMON_INTERCEPTOR_ENTER(ctx, strlen, s);
+  SIZE_T result = REAL(strlen)(s);
+  if (common_flags()->intercept_strlen)
+    COMMON_INTERCEPTOR_READ_RANGE(ctx, s, result + 1);
+  return result;
+}
+#define INIT_STRLEN COMMON_INTERCEPT_FUNCTION(strlen)
+#else
+#define INIT_STRLEN
+#endif
+
 #if SANITIZER_INTERCEPT_TEXTDOMAIN
 INTERCEPTOR(char*, textdomain, const char *domainname) {
   void *ctx;
@@ -5376,6 +5390,7 @@ static void InitializeCommonInterceptors() {
   interceptor_metadata_map = new((void *)&metadata_mem) MetadataHashMap();
 
   INIT_TEXTDOMAIN;
+  INIT_STRLEN;
   INIT_STRCMP;
   INIT_STRNCMP;
   INIT_STRCASECMP;
diff --git a/lib/sanitizer_common/sanitizer_flags.inc b/lib/sanitizer_common/sanitizer_flags.inc
index e983c0c76..7fbebf129 100644
--- a/lib/sanitizer_common/sanitizer_flags.inc
+++ b/lib/sanitizer_common/sanitizer_flags.inc
@@ -182,6 +182,9 @@ COMMON_FLAG(bool, intercept_strspn, true,
 COMMON_FLAG(bool, intercept_strpbrk, true,
             "If set, uses custom wrappers for strpbrk function "
             "to find more errors.")
+COMMON_FLAG(bool, intercept_strlen, true,
+            "If set, uses custom wrappers for strlen function "
+            "to find more errors.")
 COMMON_FLAG(bool, intercept_memcmp, true,
             "If set, uses custom wrappers for memcmp function "
             "to find more errors.")
diff --git a/lib/sanitizer_common/sanitizer_platform_interceptors.h b/lib/sanitizer_common/sanitizer_platform_interceptors.h
index f9c07a196..09fa1d944 100644
--- a/lib/sanitizer_common/sanitizer_platform_interceptors.h
+++ b/lib/sanitizer_common/sanitizer_platform_interceptors.h
@@ -53,6 +53,7 @@
 # define SI_IOS 0
 #endif
 
+#define SANITIZER_INTERCEPT_STRLEN 1
 #define SANITIZER_INTERCEPT_STRCMP 1
 #define SANITIZER_INTERCEPT_STRSTR 1
 #define SANITIZER_INTERCEPT_STRCASESTR SI_NOT_WINDOWS
diff --git a/lib/tsan/rtl/tsan_interceptors.cc b/lib/tsan/rtl/tsan_interceptors.cc
index 5e541f264..3b7361f13 100644
--- a/lib/tsan/rtl/tsan_interceptors.cc
+++ b/lib/tsan/rtl/tsan_interceptors.cc
@@ -668,13 +668,6 @@ TSAN_INTERCEPTOR(uptr, malloc_usable_size, void *p) {
 }
 #endif
 
-TSAN_INTERCEPTOR(uptr, strlen, const char *s) {
-  SCOPED_TSAN_INTERCEPTOR(strlen, s);
-  uptr len = internal_strlen(s);
-  MemoryAccessRange(thr, pc, (uptr)s, len + 1, false);
-  return len;
-}
-
 TSAN_INTERCEPTOR(void*, memset, void *dst, int v, uptr size) {
   // On FreeBSD we get here from libthr internals on thread initialization.
   if (!COMMON_INTERCEPTOR_NOTHING_IS_INITIALIZED) {
@@ -2618,7 +2611,6 @@ void InitializeInterceptors() {
   TSAN_MAYBE_INTERCEPT_PVALLOC;
   TSAN_INTERCEPT(posix_memalign);
 
-  TSAN_INTERCEPT(strlen);
   TSAN_INTERCEPT(memset);
   TSAN_INTERCEPT(memcpy);
   TSAN_INTERCEPT(memmove);