Reapply "Enable LSan for arm Linux"

This patch reapplies r299923 with typo fixed in BLX macros.

llvm-svn: 299948

compiler-rt/cmake/config-ix.cmake

@@ -164,7 +164,12 @@ set(ALL_SANITIZER_COMMON_SUPPORTED_ARCH ${X86} ${X86_64} ${PPC64}
 set(ALL_ASAN_SUPPORTED_ARCH ${X86} ${X86_64} ${ARM32} ${ARM64}
     ${MIPS32} ${MIPS64} ${PPC64} ${S390X})
 set(ALL_DFSAN_SUPPORTED_ARCH ${X86_64} ${MIPS64} ${ARM64})
-set(ALL_LSAN_SUPPORTED_ARCH ${X86} ${X86_64} ${MIPS64} ${ARM64})
+
+if(APPLE)
+  set(ALL_LSAN_SUPPORTED_ARCH ${X86} ${X86_64} ${MIPS64} ${ARM64})
+else()
+  set(ALL_LSAN_SUPPORTED_ARCH ${X86} ${X86_64} ${MIPS64} ${ARM64} ${ARM32})
+endif()
 set(ALL_MSAN_SUPPORTED_ARCH ${X86_64} ${MIPS64} ${ARM64} ${PPC64})
 set(ALL_PROFILE_SUPPORTED_ARCH ${X86} ${X86_64} ${ARM32} ${ARM64} ${PPC64}
     ${MIPS32} ${MIPS64} ${S390X})

compiler-rt/lib/asan/tests/asan_test.cc

@@ -685,13 +685,15 @@ void *ThreadStackReuseFunc2(void *unused) {
   return 0;
 }
 
+#if !defined(__thumb__)
 TEST(AddressSanitizer, ThreadStackReuseTest) {
   pthread_t t;
   PTHREAD_CREATE(&t, 0, ThreadStackReuseFunc1, 0);
   PTHREAD_JOIN(t, 0);
   PTHREAD_CREATE(&t, 0, ThreadStackReuseFunc2, 0);
   PTHREAD_JOIN(t, 0);
 }
+#endif
 
 #if defined(__SSE2__)
 #include <emmintrin.h>
@@ -1091,6 +1093,11 @@ TEST(AddressSanitizer, ThreadedStressStackReuseTest) {
   }
 }
 
+// pthread_exit tries to perform unwinding stuff that leads to dlopen'ing
+// libgcc_s.so. dlopen in its turn calls malloc to store "libgcc_s.so" string
+// that confuses LSan on Thumb because it fails to understand that this
+// allocation happens in dynamic linker and should be ignored.
+#if !defined(__thumb__)
 static void *PthreadExit(void *a) {
   pthread_exit(0);
   return 0;
@@ -1103,6 +1110,7 @@ TEST(AddressSanitizer, PthreadExitTest) {
     PTHREAD_JOIN(t, 0);
   }
 }
+#endif
 
 // FIXME: Why does clang-cl define __EXCEPTIONS?
 #if defined(__EXCEPTIONS) && !defined(_WIN32)

compiler-rt/lib/lsan/lsan_allocator.cc

@@ -24,7 +24,7 @@
 extern "C" void *memset(void *ptr, int value, uptr num);
 
 namespace __lsan {
-#if defined(__i386__)
+#if defined(__i386__) || defined(__arm__)
 static const uptr kMaxAllowedMallocSize = 1UL << 30;
 #elif defined(__mips64) || defined(__aarch64__)
 static const uptr kMaxAllowedMallocSize = 4UL << 30;

compiler-rt/lib/lsan/lsan_allocator.h

@@ -48,7 +48,8 @@ struct ChunkMetadata {
   u32 stack_trace_id;
 };
 
-#if defined(__mips64) || defined(__aarch64__) || defined(__i386__)
+#if defined(__mips64) || defined(__aarch64__) || defined(__i386__) || \
+    defined(__arm__)
 static const uptr kRegionSizeLog = 20;
 static const uptr kNumRegions = SANITIZER_MMAP_RANGE_SIZE >> kRegionSizeLog;
 typedef TwoLevelByteMap<(kNumRegions >> 12), 1 << 12> ByteMap;

compiler-rt/lib/lsan/lsan_common.h

@@ -37,6 +37,9 @@
 #elif defined(__i386__) && \
     (SANITIZER_LINUX && !SANITIZER_ANDROID || SANITIZER_MAC)
 #define CAN_SANITIZE_LEAKS 1
+#elif defined(__arm__) && \
+    SANITIZER_LINUX && !SANITIZER_ANDROID
+#define CAN_SANITIZE_LEAKS 1
 #else
 #define CAN_SANITIZE_LEAKS 0
 #endif
@@ -144,13 +147,36 @@ struct ScopedInterceptorDisabler {
   ~ScopedInterceptorDisabler() { EnableInThisThread(); }
 };
 
+// According to Itanium C++ ABI array cookie is a one word containing
+// size of allocated array.
+static inline bool IsItaniumABIArrayCookie(uptr chunk_beg, uptr chunk_size,
+                                           uptr addr) {
+  return chunk_size == sizeof(uptr) && chunk_beg + chunk_size == addr &&
+         *reinterpret_cast<uptr *>(chunk_beg) == 0;
+}
+
+// According to ARM C++ ABI array cookie consists of two words:
+// struct array_cookie {
+//   std::size_t element_size; // element_size != 0
+//   std::size_t element_count;
+// };
+static inline bool IsARMABIArrayCookie(uptr chunk_beg, uptr chunk_size,
+                                       uptr addr) {
+  return chunk_size == 2 * sizeof(uptr) && chunk_beg + chunk_size == addr &&
+         *reinterpret_cast<uptr *>(chunk_beg + sizeof(uptr)) == 0;
+}
+
 // Special case for "new T[0]" where T is a type with DTOR.
-// new T[0] will allocate one word for the array size (0) and store a pointer
-// to the end of allocated chunk.
+// new T[0] will allocate a cookie (one or two words) for the array size (0)
+// and store a pointer to the end of allocated chunk. The actual cookie layout
+// varies between platforms according to their C++ ABI implementation.
 inline bool IsSpecialCaseOfOperatorNew0(uptr chunk_beg, uptr chunk_size,
                                         uptr addr) {
-  return chunk_size == sizeof(uptr) && chunk_beg + chunk_size == addr &&
-         *reinterpret_cast<uptr *>(chunk_beg) == 0;
+#if defined(__arm__)
+  return IsARMABIArrayCookie(chunk_beg, chunk_size, addr);
+#else
+  return IsItaniumABIArrayCookie(chunk_beg, chunk_size, addr);
+#endif
 }
 
 // The following must be implemented in the parent tool.

compiler-rt/lib/sanitizer_common/sanitizer_linux.cc

@@ -1283,6 +1283,72 @@ uptr internal_clone(int (*fn)(void *), void *child_stack, int flags, void *arg,
                        : "memory");
   return res;
 }
+#elif defined(__arm__) && SANITIZER_LINUX
+uptr internal_clone(int (*fn)(void *), void *child_stack, int flags, void *arg,
+                    int *parent_tidptr, void *newtls, int *child_tidptr) {
+  unsigned int res;
+  if (!fn || !child_stack)
+    return -EINVAL;
+  child_stack = (char *)child_stack - 2 * sizeof(unsigned int);
+  ((unsigned int *)child_stack)[0] = (uptr)fn;
+  ((unsigned int *)child_stack)[1] = (uptr)arg;
+  register int r0 __asm__("r0") = flags;
+  register void *r1 __asm__("r1") = child_stack;
+  register int *r2 __asm__("r2") = parent_tidptr;
+  register void *r3 __asm__("r3") = newtls;
+  register int *r4 __asm__("r4") = child_tidptr;
+  register int r7 __asm__("r7") = __NR_clone;
+
+#if __ARM_ARCH > 4 || defined (__ARM_ARCH_4T__)
+# define ARCH_HAS_BX
+#endif
+#if __ARM_ARCH > 4
+# define ARCH_HAS_BLX
+#endif
+
+#ifdef ARCH_HAS_BX
+# ifdef ARCH_HAS_BLX
+#  define BLX(R) "blx "  #R "\n"
+# else
+#  define BLX(R) "mov lr, pc; bx " #R "\n"
+# endif
+#else
+# define BLX(R)  "mov lr, pc; mov pc," #R "\n"
+#endif
+
+  __asm__ __volatile__(
+                       /* %r0 = syscall(%r7 = SYSCALL(clone),
+                        *               %r0 = flags,
+                        *               %r1 = child_stack,
+                        *               %r2 = parent_tidptr,
+                        *               %r3  = new_tls,
+                        *               %r4 = child_tidptr)
+                        */
+
+                       /* Do the system call */
+                       "swi 0x0\n"
+
+                       /* if (%r0 != 0)
+                        *   return %r0;
+                        */
+                       "cmp r0, #0\n"
+                       "bne 1f\n"
+
+                       /* In the child, now. Call "fn(arg)". */
+                       "ldr r0, [sp, #4]\n"
+                       "ldr ip, [sp], #8\n"
+                       BLX(ip)
+                       /* Call _exit(%r0). */
+                       "mov r7, %7\n"
+                       "swi 0x0\n"
+                       "1:\n"
+                       "mov %0, r0\n"
+                       : "=r"(res)
+                       : "r"(r0), "r"(r1), "r"(r2), "r"(r3), "r"(r4), "r"(r7),
+                         "i"(__NR_exit)
+                       : "memory");
+  return res;
+}
 #endif  // defined(__x86_64__) && SANITIZER_LINUX
 
 #if SANITIZER_ANDROID

compiler-rt/lib/sanitizer_common/sanitizer_linux.h

@@ -48,7 +48,8 @@ int internal_sigaction_syscall(int signum, const void *act, void *oldact);
 #endif
 void internal_sigdelset(__sanitizer_sigset_t *set, int signum);
 #if defined(__x86_64__) || defined(__mips__) || defined(__aarch64__) \
-  || defined(__powerpc64__) || defined(__s390__) || defined(__i386__)
+  || defined(__powerpc64__) || defined(__s390__) || defined(__i386__) \
+  || defined(__arm__)
 uptr internal_clone(int (*fn)(void *), void *child_stack, int flags, void *arg,
                     int *parent_tidptr, void *newtls, int *child_tidptr);
 #endif

compiler-rt/lib/sanitizer_common/sanitizer_linux_libcdep.cc

@@ -183,23 +183,23 @@ void InitTlsSize() { }
 #endif  // !SANITIZER_FREEBSD && !SANITIZER_ANDROID && !SANITIZER_GO
 
 #if (defined(__x86_64__) || defined(__i386__) || defined(__mips__) \
-    || defined(__aarch64__) || defined(__powerpc64__) || defined(__s390__)) \
-    && SANITIZER_LINUX && !SANITIZER_ANDROID
+    || defined(__aarch64__) || defined(__powerpc64__) || defined(__s390__) \
+    || defined(__arm__)) && SANITIZER_LINUX && !SANITIZER_ANDROID
 // sizeof(struct pthread) from glibc.
 static atomic_uintptr_t kThreadDescriptorSize;
 
 uptr ThreadDescriptorSize() {
   uptr val = atomic_load(&kThreadDescriptorSize, memory_order_relaxed);
   if (val)
     return val;
-#if defined(__x86_64__) || defined(__i386__)
+#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
 #ifdef _CS_GNU_LIBC_VERSION
   char buf[64];
   uptr len = confstr(_CS_GNU_LIBC_VERSION, buf, sizeof(buf));
   if (len < sizeof(buf) && internal_strncmp(buf, "glibc 2.", 8) == 0) {
     char *end;
     int minor = internal_simple_strtoll(buf + 8, &end, 10);
-    if (end != buf + 8 && (*end == '\0' || *end == '.')) {
+    if (end != buf + 8 && (*end == '\0' || *end == '.' || *end == '-')) {
       int patch = 0;
       if (*end == '.')
         // strtoll will return 0 if no valid conversion could be performed
@@ -208,6 +208,9 @@ uptr ThreadDescriptorSize() {
       /* sizeof(struct pthread) values from various glibc versions.  */
       if (SANITIZER_X32)
         val = 1728;  // Assume only one particular version for x32.
+      // For ARM sizeof(struct pthread) changed in Glibc 2.23.
+      else if (SANITIZER_ARM)
+        val = minor <= 22 ? 1120 : 1216;
       else if (minor <= 3)
         val = FIRST_32_SECOND_64(1104, 1696);
       else if (minor == 4)
@@ -293,7 +296,7 @@ uptr ThreadSelf() {
                 rdhwr %0,$29;\
                 .set pop" : "=r" (thread_pointer));
   descr_addr = thread_pointer - kTlsTcbOffset - TlsPreTcbSize();
-# elif defined(__aarch64__)
+# elif defined(__aarch64__) || defined(__arm__)
   descr_addr = reinterpret_cast<uptr>(__builtin_thread_pointer()) -
                                       ThreadDescriptorSize();
 # elif defined(__s390__)
@@ -342,7 +345,8 @@ static void GetTls(uptr *addr, uptr *size) {
   *size = GetTlsSize();
   *addr -= *size;
   *addr += ThreadDescriptorSize();
-# elif defined(__mips__) || defined(__aarch64__) || defined(__powerpc64__)
+# elif defined(__mips__) || defined(__aarch64__) || defined(__powerpc64__) \
+    || defined(__arm__)
   *addr = ThreadSelf();
   *size = GetTlsSize();
 # else

compiler-rt/lib/sanitizer_common/sanitizer_platform.h

@@ -162,6 +162,12 @@
 # define SANITIZER_PPC64V2 0
 #endif
 
+#if defined(__arm__)
+# define SANITIZER_ARM 1
+#else
+# define SANITIZER_ARM 0
+#endif
+
 // By default we allow to use SizeClassAllocator64 on 64-bit platform.
 // But in some cases (e.g. AArch64's 39-bit address space) SizeClassAllocator64
 // does not work well and we need to fallback to SizeClassAllocator32.

compiler-rt/lib/sanitizer_common/sanitizer_stoptheworld_linux_libcdep.cc

@@ -16,7 +16,8 @@
 
 #if SANITIZER_LINUX && (defined(__x86_64__) || defined(__mips__) || \
                         defined(__aarch64__) || defined(__powerpc64__) || \
-                        defined(__s390__) || defined(__i386__))
+                        defined(__s390__) || defined(__i386__) || \
+                        defined(__arm__))
 
 #include "sanitizer_stoptheworld.h"
 
@@ -532,4 +533,4 @@ uptr SuspendedThreadsList::RegisterCount() {
 
 #endif  // SANITIZER_LINUX && (defined(__x86_64__) || defined(__mips__)
         // || defined(__aarch64__) || defined(__powerpc64__)
-        // || defined(__s390__) || defined(__i386__)
+        // || defined(__s390__) || defined(__i386__) || defined(__arm__)

compiler-rt/test/asan/TestCases/Linux/clang_gcc_abi.cc

@@ -3,7 +3,7 @@
 // RUN: %clangxx_asan -O2 -x c %s -o %t && not %run %t 2>&1 | FileCheck %s
 // RUN: %clangxx_asan -O3 -x c %s -o %t && not %run %t 2>&1 | FileCheck %s
 
-// REQUIRES: arm-target-arch
+// REQUIRES: arm-target-arch, fast-unwinder-works
 // XFAIL: armv7l-unknown-linux-gnueabihf
 
 #include <stdlib.h>

compiler-rt/test/asan/lit.cfg

@@ -2,6 +2,7 @@
 
 import os
 import platform
+import re
 
 import lit.formats
 
@@ -211,6 +212,10 @@ config.substitutions.append( ("%xdynamiclib_namespec", '%basename_t.dynamic') )
 if config.target_arch != 'arm' and config.target_arch != 'armhf' and config.target_arch != 'aarch64':
   config.available_features.add('stable-runtime')
 
+# Fast unwinder doesn't work with Thumb
+if not re.match('-mthumb', config.target_cflags):
+  config.available_features.add('fast-unwinder-works')
+
 # Turn on leak detection on 64-bit Linux.
 if config.host_os == 'Linux' and (config.target_arch == 'x86_64' or config.target_arch == 'i386'):
   config.available_features.add('leak-detection')

compiler-rt/test/lsan/TestCases/large_allocation_leak.cc

@@ -5,7 +5,7 @@
 
 // For 32 bit LSan it's pretty likely that large chunks are "reachable" from some
 // internal data structures (e.g. Glibc global data).
-// UNSUPPORTED: x86
+// UNSUPPORTED: x86, arm
 
 #include <stdio.h>
 #include <stdlib.h>

compiler-rt/test/lsan/TestCases/swapcontext.cc

@@ -2,8 +2,10 @@
 // memory. Make sure we don't report these leaks.
 
 // RUN: %clangxx_lsan %s -o %t
-// RUN: %run %t 2>&1
-// RUN: not %run %t foo 2>&1 | FileCheck %s
+// RUN: LSAN_BASE="detect_leaks=1"
+// RUN: LSAN_OPTIONS=$LSAN_BASE %run %t 2>&1
+// RUN: LSAN_OPTIONS=$LSAN_BASE not %run %t foo 2>&1 | FileCheck %s
+// UNSUPPORTED: arm
 
 #include <stdio.h>
 #if defined(__APPLE__)
@@ -23,7 +25,7 @@ void Child() {
 }
 
 int main(int argc, char *argv[]) {
-  char stack_memory[kStackSize + 1];
+  char stack_memory[kStackSize + 1] __attribute__((aligned(16)));
   char *heap_memory = new char[kStackSize + 1];
   char *child_stack = (argc > 1) ? stack_memory : heap_memory;
 

compiler-rt/test/lsan/TestCases/use_registers.cc

@@ -33,6 +33,11 @@ void *registers_thread_func(void *arg) {
       :
       : "r" (p)
       );
+#elif defined(__arm__)
+  asm ( "mov r5, %0"
+      :
+      : "r" (p)
+      );
 #else
 #error "Test is not supported on this architecture."
 #endif

compiler-rt/test/lsan/TestCases/use_tls_dynamic.cc

@@ -5,7 +5,7 @@
 // RUN: LSAN_OPTIONS=$LSAN_BASE:"use_tls=0" not %run %t 2>&1 | FileCheck %s
 // RUN: LSAN_OPTIONS=$LSAN_BASE:"use_tls=1" %run %t 2>&1
 // RUN: LSAN_OPTIONS="" %run %t 2>&1
-// UNSUPPORTED: i386-linux,i686-linux
+// UNSUPPORTED: i386-linux,i686-linux,arm
 
 #ifndef BUILD_DSO
 #include <assert.h>

compiler-rt/test/lsan/lit.common.cfg

@@ -3,6 +3,7 @@
 # Common configuration for running leak detection tests under LSan/ASan.
 
 import os
+import re
 
 import lit.util
 
@@ -51,8 +52,12 @@ config.substitutions.append( ("%clangxx ", build_invocation(clang_cxxflags)) )
 config.substitutions.append( ("%clang_lsan ", build_invocation(clang_lsan_cflags)) )
 config.substitutions.append( ("%clangxx_lsan ", build_invocation(clang_lsan_cxxflags)) )
 
-# LeakSanitizer tests are currently supported on x86-64 Linux and mips64 Linux only.
-if config.host_os not in ['Linux'] or config.host_arch not in ['x86_64', 'mips64']:
+# LeakSanitizer tests are currently supported on x86-64 Linux, arm Linux and mips64 Linux only.
+if config.host_os not in ['Linux'] or config.host_arch not in ['x86_64', 'mips64', 'arm', 'armhf', armv7l]:
+  config.unsupported = True
+
+# Don't support Thumb due to broken fast unwinder
+if re.match('-mthumb', config.target_cflags):
   config.unsupported = True
 
 config.suffixes = ['.c', '.cc', '.cpp']