[asan] Move memcpy, memmove, memset code out of asan_interceptors.cc

[mcgrathr]

Summary

This is a pure refactoring change. It simply moves all the code and
macros related to defining the ASan interceptor versions of memcpy,
memmove, and memset into a separate file. This makes it cleaner to
disable all the other interceptor code while still using these three,
for a port that defines these but not the other common interceptors.

[alekseyshl]

Can we rename them to asan_interceptors_memintrinsics.cc/.h? Other than that, lgtm.

[mcgrathr]

Renamed new files.

[mcgrathr]

Can you land it for me?

Thanks,
Roland

[alekseyshl]

Will do!

lib/asan/CMakeLists.txt

set(ASAN_SOURCES
   asan_globals.cc
   asan_globals_win.cc
   asan_interceptors.cc
   asan_linux.cc
   asan_mac.cc
   asan_malloc_linux.cc
   asan_malloc_mac.cc
   asan_malloc_win.cc
+  asan_memintrin.cc
   asan_memory_profile.cc
   asan_poisoning.cc
   asan_posix.cc
   asan_report.cc
   asan_rtl.cc
   asan_stack.cc
   asan_stats.cc
   asan_suppressions.cc

lib/asan/asan_interceptors.h

 // This file is a part of AddressSanitizer, an address sanity checker.
 //
 // ASan-private header for asan_interceptors.cc
 //===----------------------------------------------------------------------===//
 #ifndef ASAN_INTERCEPTORS_H
 #define ASAN_INTERCEPTORS_H
 
 #include "asan_internal.h"
+#include "asan_memintrin.h"
 #include "interception/interception.h"
 #include "sanitizer_common/sanitizer_platform_interceptors.h"
 
 // Use macro to describe if specific function should be
 // intercepted on a given platform.
 #if !SANITIZER_WINDOWS
 # define ASAN_INTERCEPT_ATOLL_AND_STRTOLL 1
 # define ASAN_INTERCEPT__LONGJMP 1

 
 #if SANITIZER_LINUX && !SANITIZER_ANDROID
 # define ASAN_INTERCEPT___STRDUP 1
 #else
 # define ASAN_INTERCEPT___STRDUP 0
 #endif
 
 DECLARE_REAL(int, memcmp, const void *a1, const void *a2, uptr size)
-DECLARE_REAL(void*, memcpy, void *to, const void *from, uptr size)
-DECLARE_REAL(void*, memset, void *block, int c, uptr size)
 DECLARE_REAL(char*, strchr, const char *str, int c)
 DECLARE_REAL(SIZE_T, strlen, const char *s)
 DECLARE_REAL(char*, strncpy, char *to, const char *from, uptr size)
 DECLARE_REAL(uptr, strnlen, const char *s, uptr maxlen)
 DECLARE_REAL(char*, strstr, const char *s1, const char *s2)
 struct sigaction;
 DECLARE_REAL(int, sigaction, int signum, const struct sigaction *act,
                              struct sigaction *oldact)

lib/asan/asan_interceptors.cc

 #if defined(__i386) && SANITIZER_LINUX
 #define ASAN_PTHREAD_CREATE_VERSION "GLIBC_2.1"
 #elif defined(__mips__) && SANITIZER_LINUX
 #define ASAN_PTHREAD_CREATE_VERSION "GLIBC_2.2"
 #endif
 
 namespace __asan {
 
-// Return true if we can quickly decide that the region is unpoisoned.
-// We assume that a redzone is at least 16 bytes.
-static inline bool QuickCheckForUnpoisonedRegion(uptr beg, uptr size) {
-  if (size == 0) return true;
-  if (size <= 32)
-    return !AddressIsPoisoned(beg) &&
-           !AddressIsPoisoned(beg + size - 1) &&
-           !AddressIsPoisoned(beg + size / 2);
-  if (size <= 64)
-    return !AddressIsPoisoned(beg) &&
-           !AddressIsPoisoned(beg + size / 4) &&
-           !AddressIsPoisoned(beg + size - 1) &&
-           !AddressIsPoisoned(beg + 3 * size / 4) &&
-           !AddressIsPoisoned(beg + size / 2);
-  return false;
-}
-
-struct AsanInterceptorContext {
-  const char *interceptor_name;
-};
-
-// We implement ACCESS_MEMORY_RANGE, ASAN_READ_RANGE,
-// and ASAN_WRITE_RANGE as macro instead of function so
-// that no extra frames are created, and stack trace contains
-// relevant information only.
-// We check all shadow bytes.
-#define ACCESS_MEMORY_RANGE(ctx, offset, size, isWrite) do {            \
-    uptr __offset = (uptr)(offset);                                     \
-    uptr __size = (uptr)(size);                                         \
-    uptr __bad = 0;                                                     \
-    if (__offset > __offset + __size) {                                 \
-      GET_STACK_TRACE_FATAL_HERE;                                       \
-      ReportStringFunctionSizeOverflow(__offset, __size, &stack);       \
-    }                                                                   \
-    if (!QuickCheckForUnpoisonedRegion(__offset, __size) &&             \
-        (__bad = __asan_region_is_poisoned(__offset, __size))) {        \
-      AsanInterceptorContext *_ctx = (AsanInterceptorContext *)ctx;     \
-      bool suppressed = false;                                          \
-      if (_ctx) {                                                       \
-        suppressed = IsInterceptorSuppressed(_ctx->interceptor_name);   \
-        if (!suppressed && HaveStackTraceBasedSuppressions()) {         \
-          GET_STACK_TRACE_FATAL_HERE;                                   \
-          suppressed = IsStackTraceSuppressed(&stack);                  \
-        }                                                               \
-      }                                                                 \
-      if (!suppressed) {                                                \
-        GET_CURRENT_PC_BP_SP;                                           \
-        ReportGenericError(pc, bp, sp, __bad, isWrite, __size, 0, false);\
-      }                                                                 \
-    }                                                                   \
-  } while (0)
-
-// memcpy is called during __asan_init() from the internals of printf(...).
-// We do not treat memcpy with to==from as a bug.
-// See http://llvm.org/bugs/show_bug.cgi?id=11763.
-#define ASAN_MEMCPY_IMPL(ctx, to, from, size)                           \
-  do {                                                                  \
-    if (UNLIKELY(!asan_inited)) return internal_memcpy(to, from, size); \
-    if (asan_init_is_running) {                                         \
-      return REAL(memcpy)(to, from, size);                              \
-    }                                                                   \
-    ENSURE_ASAN_INITED();                                               \
-    if (flags()->replace_intrin) {                                      \
-      if (to != from) {                                                 \
-        CHECK_RANGES_OVERLAP("memcpy", to, size, from, size);           \
-      }                                                                 \
-      ASAN_READ_RANGE(ctx, from, size);                                 \
-      ASAN_WRITE_RANGE(ctx, to, size);                                  \
-    }                                                                   \
-    return REAL(memcpy)(to, from, size);                                \
-  } while (0)
-
-// memset is called inside Printf.
-#define ASAN_MEMSET_IMPL(ctx, block, c, size)                           \
-  do {                                                                  \
-    if (UNLIKELY(!asan_inited)) return internal_memset(block, c, size); \
-    if (asan_init_is_running) {                                         \
-      return REAL(memset)(block, c, size);                              \
-    }                                                                   \
-    ENSURE_ASAN_INITED();                                               \
-    if (flags()->replace_intrin) {                                      \
-      ASAN_WRITE_RANGE(ctx, block, size);                               \
-    }                                                                   \
-    return REAL(memset)(block, c, size);                                \
-  } while (0)
-
-#define ASAN_MEMMOVE_IMPL(ctx, to, from, size)                           \
-  do {                                                                   \
-    if (UNLIKELY(!asan_inited)) return internal_memmove(to, from, size); \
-    ENSURE_ASAN_INITED();                                                \
-    if (flags()->replace_intrin) {                                       \
-      ASAN_READ_RANGE(ctx, from, size);                                  \
-      ASAN_WRITE_RANGE(ctx, to, size);                                   \
-    }                                                                    \
-    return internal_memmove(to, from, size);                             \
-  } while (0)
-
-#define ASAN_READ_RANGE(ctx, offset, size) \
-  ACCESS_MEMORY_RANGE(ctx, offset, size, false)
-#define ASAN_WRITE_RANGE(ctx, offset, size) \
-  ACCESS_MEMORY_RANGE(ctx, offset, size, true)
-
 #define ASAN_READ_STRING_OF_LEN(ctx, s, len, n)                 \
   ASAN_READ_RANGE((ctx), (s),                                   \
     common_flags()->strict_string_checks ? (len) + 1 : (n))
 
 #define ASAN_READ_STRING(ctx, s, n)                             \
   ASAN_READ_STRING_OF_LEN((ctx), (s), REAL(strlen)(s), (n))
 
-// Behavior of functions like "memcpy" or "strcpy" is undefined
-// if memory intervals overlap. We report error in this case.
-// Macro is used to avoid creation of new frames.
-static inline bool RangesOverlap(const char *offset1, uptr length1,
-                                 const char *offset2, uptr length2) {
-  return !((offset1 + length1 <= offset2) || (offset2 + length2 <= offset1));
-}
-#define CHECK_RANGES_OVERLAP(name, _offset1, length1, _offset2, length2) do { \
-  const char *offset1 = (const char*)_offset1; \
-  const char *offset2 = (const char*)_offset2; \
-  if (RangesOverlap(offset1, length1, offset2, length2)) { \
-    GET_STACK_TRACE_FATAL_HERE; \
-    ReportStringFunctionMemoryRangesOverlap(name, offset1, length1, \
-                                            offset2, length2, &stack); \
-  } \
-} while (0)
-
 static inline uptr MaybeRealStrnlen(const char *s, uptr maxlen) {
 #if SANITIZER_INTERCEPT_STRNLEN
   if (REAL(strnlen)) {
     return REAL(strnlen)(s, maxlen);
   }
 #endif
   return internal_strnlen(s, maxlen);
 }

 #if ASAN_INTERCEPT___CXA_THROW
 INTERCEPTOR(void, __cxa_throw, void *a, void *b, void *c) {
   CHECK(REAL(__cxa_throw));
   __asan_handle_no_return();
   REAL(__cxa_throw)(a, b, c);
 }
 #endif
 
-void *__asan_memcpy(void *to, const void *from, uptr size) {
-  ASAN_MEMCPY_IMPL(nullptr, to, from, size);
-}
-
-void *__asan_memset(void *block, int c, uptr size) {
-  ASAN_MEMSET_IMPL(nullptr, block, c, size);
-}
-
-void *__asan_memmove(void *to, const void *from, uptr size) {
-  ASAN_MEMMOVE_IMPL(nullptr, to, from, size);
-}
-
 #if ASAN_INTERCEPT_INDEX
 # if ASAN_USE_ALIAS_ATTRIBUTE_FOR_INDEX
 INTERCEPTOR(char*, index, const char *string, int c)
   ALIAS(WRAPPER_NAME(strchr));
 # else
 #  if SANITIZER_MAC
 DECLARE_REAL(char*, index, const char *string, int c)
 OVERRIDE_FUNCTION(index, strchr);

lib/asan/asan_memintrin.h

+//===-- asan_memintrin.h -------------------------------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===---------------------------------------------------------------------===//
+//
+// This file is a part of AddressSanitizer, an address sanity checker.
+//
+// ASan-private header for asan_memintrin.cc
+//===---------------------------------------------------------------------===//
+#ifndef ASAN_MEMINTRIN_H
+#define ASAN_MEMINTRIN_H
+
+#include "asan_interface_internal.h"
+#include "asan_internal.h"
+#include "asan_mapping.h"
+#include "interception/interception.h"
+
+DECLARE_REAL(void*, memcpy, void *to, const void *from, uptr size)
+DECLARE_REAL(void*, memset, void *block, int c, uptr size)
+
+namespace __asan {
+
+// Return true if we can quickly decide that the region is unpoisoned.
+// We assume that a redzone is at least 16 bytes.
+static inline bool QuickCheckForUnpoisonedRegion(uptr beg, uptr size) {
+  if (size == 0) return true;
+  if (size <= 32)
+    return !AddressIsPoisoned(beg) &&
+           !AddressIsPoisoned(beg + size - 1) &&
+           !AddressIsPoisoned(beg + size / 2);
+  if (size <= 64)
+    return !AddressIsPoisoned(beg) &&
+           !AddressIsPoisoned(beg + size / 4) &&
+           !AddressIsPoisoned(beg + size - 1) &&
+           !AddressIsPoisoned(beg + 3 * size / 4) &&
+           !AddressIsPoisoned(beg + size / 2);
+  return false;
+}
+
+struct AsanInterceptorContext {
+  const char *interceptor_name;
+};
+
+// We implement ACCESS_MEMORY_RANGE, ASAN_READ_RANGE,
+// and ASAN_WRITE_RANGE as macro instead of function so
+// that no extra frames are created, and stack trace contains
+// relevant information only.
+// We check all shadow bytes.
+#define ACCESS_MEMORY_RANGE(ctx, offset, size, isWrite) do {            \
+    uptr __offset = (uptr)(offset);                                     \
+    uptr __size = (uptr)(size);                                         \
+    uptr __bad = 0;                                                     \
+    if (__offset > __offset + __size) {                                 \
+      GET_STACK_TRACE_FATAL_HERE;                                       \
+      ReportStringFunctionSizeOverflow(__offset, __size, &stack);       \
+    }                                                                   \
+    if (!QuickCheckForUnpoisonedRegion(__offset, __size) &&             \
+        (__bad = __asan_region_is_poisoned(__offset, __size))) {        \
+      AsanInterceptorContext *_ctx = (AsanInterceptorContext *)ctx;     \
+      bool suppressed = false;                                          \
+      if (_ctx) {                                                       \
+        suppressed = IsInterceptorSuppressed(_ctx->interceptor_name);   \
+        if (!suppressed && HaveStackTraceBasedSuppressions()) {         \
+          GET_STACK_TRACE_FATAL_HERE;                                   \
+          suppressed = IsStackTraceSuppressed(&stack);                  \
+        }                                                               \
+      }                                                                 \
+      if (!suppressed) {                                                \
+        GET_CURRENT_PC_BP_SP;                                           \
+        ReportGenericError(pc, bp, sp, __bad, isWrite, __size, 0, false);\
+      }                                                                 \
+    }                                                                   \
+  } while (0)
+
+// memcpy is called during __asan_init() from the internals of printf(...).
+// We do not treat memcpy with to==from as a bug.
+// See http://llvm.org/bugs/show_bug.cgi?id=11763.
+#define ASAN_MEMCPY_IMPL(ctx, to, from, size)                           \
+  do {                                                                  \
+    if (UNLIKELY(!asan_inited)) return internal_memcpy(to, from, size); \
+    if (asan_init_is_running) {                                         \
+      return REAL(memcpy)(to, from, size);                              \
+    }                                                                   \
+    ENSURE_ASAN_INITED();                                               \
+    if (flags()->replace_intrin) {                                      \
+      if (to != from) {                                                 \
+        CHECK_RANGES_OVERLAP("memcpy", to, size, from, size);           \
+      }                                                                 \
+      ASAN_READ_RANGE(ctx, from, size);                                 \
+      ASAN_WRITE_RANGE(ctx, to, size);                                  \
+    }                                                                   \
+    return REAL(memcpy)(to, from, size);                                \
+  } while (0)
+
+// memset is called inside Printf.
+#define ASAN_MEMSET_IMPL(ctx, block, c, size)                           \
+  do {                                                                  \
+    if (UNLIKELY(!asan_inited)) return internal_memset(block, c, size); \
+    if (asan_init_is_running) {                                         \
+      return REAL(memset)(block, c, size);                              \
+    }                                                                   \
+    ENSURE_ASAN_INITED();                                               \
+    if (flags()->replace_intrin) {                                      \
+      ASAN_WRITE_RANGE(ctx, block, size);                               \
+    }                                                                   \
+    return REAL(memset)(block, c, size);                                \
+  } while (0)
+
+#define ASAN_MEMMOVE_IMPL(ctx, to, from, size)                           \
+  do {                                                                   \
+    if (UNLIKELY(!asan_inited)) return internal_memmove(to, from, size); \
+    ENSURE_ASAN_INITED();                                                \
+    if (flags()->replace_intrin) {                                       \
+      ASAN_READ_RANGE(ctx, from, size);                                  \
+      ASAN_WRITE_RANGE(ctx, to, size);                                   \
+    }                                                                    \
+    return internal_memmove(to, from, size);                             \
+  } while (0)
+
+#define ASAN_READ_RANGE(ctx, offset, size) \
+  ACCESS_MEMORY_RANGE(ctx, offset, size, false)
+#define ASAN_WRITE_RANGE(ctx, offset, size) \
+  ACCESS_MEMORY_RANGE(ctx, offset, size, true)
+
+// Behavior of functions like "memcpy" or "strcpy" is undefined
+// if memory intervals overlap. We report error in this case.
+// Macro is used to avoid creation of new frames.
+static inline bool RangesOverlap(const char *offset1, uptr length1,
+                                 const char *offset2, uptr length2) {
+  return !((offset1 + length1 <= offset2) || (offset2 + length2 <= offset1));
+}
+#define CHECK_RANGES_OVERLAP(name, _offset1, length1, _offset2, length2) do { \
+  const char *offset1 = (const char*)_offset1; \
+  const char *offset2 = (const char*)_offset2; \
+  if (RangesOverlap(offset1, length1, offset2, length2)) { \
+    GET_STACK_TRACE_FATAL_HERE; \
+    ReportStringFunctionMemoryRangesOverlap(name, offset1, length1, \
+                                            offset2, length2, &stack); \
+  } \
+} while (0)
+
+}  // namespace __asan
+
+#endif  // ASAN_MEMINTRIN_H

lib/asan/asan_memintrin.cc

+//===-- asan_memintrin.cc ----------------------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===---------------------------------------------------------------------===//
+//
+// This file is a part of AddressSanitizer, an address sanity checker.
+//
+// ASan versions of memcpy, memmove, and memset.
+//===---------------------------------------------------------------------===//
+
+#include "asan_memintrin.h"
+#include "asan_report.h"
+#include "asan_stack.h"
+#include "asan_suppressions.h"
+
+using namespace __asan;  // NOLINT
+
+void *__asan_memcpy(void *to, const void *from, uptr size) {
+  ASAN_MEMCPY_IMPL(nullptr, to, from, size);
+}
+
+void *__asan_memset(void *block, int c, uptr size) {
+  ASAN_MEMSET_IMPL(nullptr, block, c, size);
+}
+
+void *__asan_memmove(void *to, const void *from, uptr size) {
+  ASAN_MEMMOVE_IMPL(nullptr, to, from, size);
+}