Implement some TLS support for PowerPC64.

[foad]

Summary

This is enough to get the asan static_tls.cc test case working.

[samsonov]

LGTM

lib/sanitizer_common/sanitizer_linux_libcdep.cc

 #endif
 
 #ifdef __i386__
 # define DL_INTERNAL_FUNCTION __attribute__((regparm(3), stdcall))
 #else
 # define DL_INTERNAL_FUNCTION
 #endif
 
-#if defined(__mips__)
+#if defined(__mips__) || defined(__powerpc64__)
 // TlsPreTcbSize includes size of struct pthread_descr and size of tcb
 // head structure. It lies before the static tls blocks.
 static uptr TlsPreTcbSize() {
-  const uptr kTcbHead = 16;
+# if defined(__mips__)
+  const uptr kTcbHead = 16; // sizeof (tcbhead_t)
+# elif defined(__powerpc64__)
+  const uptr kTcbHead = 88; // sizeof (tcbhead_t)
+# endif
   const uptr kTlsAlign = 16;
   const uptr kTlsPreTcbSize =
     (ThreadDescriptorSize() + kTcbHead + kTlsAlign - 1) & ~(kTlsAlign - 1);
   InitTlsSize();
   g_tls_size = (g_tls_size + kTlsPreTcbSize + kTlsAlign -1) & ~(kTlsAlign - 1);
   return kTlsPreTcbSize;
 }
 #endif
// all current supported platforms have 16 bytes stack alignment
   get_tls(&tls_size, &tls_align);
   if (tls_align < kStackAlign)
     tls_align = kStackAlign;
   g_tls_size = RoundUpTo(tls_size, tls_align);
 #endif  // !SANITIZER_FREEBSD && !SANITIZER_ANDROID && !SANITIZER_GO
 }
 
 #if (defined(__x86_64__) || defined(__i386__) || defined(__mips__) \
-    || defined(__aarch64__)) \
+    || defined(__aarch64__) || defined(__powerpc64__)) \
     && SANITIZER_LINUX && !SANITIZER_ANDROID
-// sizeof(struct thread) from glibc.
+// 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__)
 #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 == '.')) {
-      /* sizeof(struct thread) values from various glibc versions.  */
+      /* sizeof(struct pthread) values from various glibc versions.  */
       if (SANITIZER_X32)
         val = 1728;  // Assume only one particular version for x32.
       else if (minor <= 3)
         val = FIRST_32_SECOND_64(1104, 1696);
       else if (minor == 4)
         val = FIRST_32_SECOND_64(1120, 1728);
       else if (minor == 5)
         val = FIRST_32_SECOND_64(1136, 1728);
#elif defined(__mips__)
   if (val)
     atomic_store(&kThreadDescriptorSize, val, memory_order_relaxed);
   return val;
 #elif defined(__aarch64__)
   // The sizeof (struct pthread) is the same from GLIBC 2.17 to 2.22.
   val = 1776;
   atomic_store(&kThreadDescriptorSize, val, memory_order_relaxed);
   return val;
+#elif defined(__powerpc64__)
+  val = 1776; // from glibc.ppc64le 2.20-8.fc21
+  atomic_store(&kThreadDescriptorSize, val, memory_order_relaxed);
+  return val;
 #endif
   return 0;
 }
 
 // The offset at which pointer to self is located in the thread descriptor.
 const uptr kThreadSelfOffset = FIRST_32_SECOND_64(8, 16);
 
 uptr ThreadSelfOffset() {
# elif defined(__mips__)
   uptr thread_pointer;
   asm volatile(".set push;\
                 .set mips64r2;\
                 rdhwr %0,$29;\
                 .set pop" : "=r" (thread_pointer));
   descr_addr = thread_pointer - kTlsTcbOffset - TlsPreTcbSize();
 # elif defined(__aarch64__)
   descr_addr = reinterpret_cast<uptr>(__builtin_thread_pointer());
+# elif defined(__powerpc64__)
+  // PPC64LE uses TLS variant I. The thread pointer (in GPR 13)
+  // points to the end of the TCB + 0x7000. The pthread_descr structure is
+  // immediately in front of the TCB. TlsPreTcbSize() includes the size of the
+  // TCB and the size of pthread_descr.
+  const uptr kTlsTcbOffset = 0x7000;
+  uptr thread_pointer;
+  asm("addi %0,13,%1" : "=r"(thread_pointer) : "I"(-kTlsTcbOffset));
+  descr_addr = thread_pointer - TlsPreTcbSize();
 # else
 #  error "unsupported CPU arch"
 # endif
   return descr_addr;
 }
 #endif  // (x86_64 || i386 || MIPS) && SANITIZER_LINUX
 
 #if SANITIZER_FREEBSD

 #if !SANITIZER_GO
 static void GetTls(uptr *addr, uptr *size) {
 #if SANITIZER_LINUX && !SANITIZER_ANDROID
 # if defined(__x86_64__) || defined(__i386__)
   *addr = ThreadSelf();
   *size = GetTlsSize();
   *addr -= *size;
   *addr += ThreadDescriptorSize();
-# elif defined(__mips__) || defined(__aarch64__)
+# elif defined(__mips__) || defined(__aarch64__) || defined(__powerpc64__)
   *addr = ThreadSelf();
   *size = GetTlsSize();
 # else
   *addr = 0;
   *size = 0;
 # endif
 #elif SANITIZER_FREEBSD
   void** segbase = ThreadSelfSegbase();

lib/sanitizer_common/sanitizer_tls_get_addr.cc

 void DTLS_Destroy() {
   if (!common_flags()->intercept_tls_get_addr) return;
   VPrintf(2, "__tls_get_addr: DTLS_Destroy %p %zd\n", &dtls, dtls.dtv_size);
   uptr s = dtls.dtv_size;
   dtls.dtv_size = kDestroyedThread;  // Do this before unmap for AS-safety.
   DTLS_Deallocate(dtls.dtv, s);
 }
 
+#if defined(__powerpc64__)
+// This is glibc's TLS_DTV_OFFSET:
+// "Dynamic thread vector pointers point 0x8000 past the start of each
+//  TLS block."
+static const uptr kDtvOffset = 0x8000;
+#else
+static const uptr kDtvOffset = 0;
+#endif
+
 DTLS::DTV *DTLS_on_tls_get_addr(void *arg_void, void *res,
                                 uptr static_tls_begin, uptr static_tls_end) {
   if (!common_flags()->intercept_tls_get_addr) return 0;
   TlsGetAddrParam *arg = reinterpret_cast<TlsGetAddrParam *>(arg_void);
   uptr dso_id = arg->dso_id;
   if (dtls.dtv_size == kDestroyedThread) return 0;
   DTLS_Resize(dso_id + 1);
   if (dtls.dtv[dso_id].beg) return 0;
   uptr tls_size = 0;
-  uptr tls_beg = reinterpret_cast<uptr>(res) - arg->offset;
+  uptr tls_beg = reinterpret_cast<uptr>(res) - arg->offset - kDtvOffset;
   VPrintf(2, "__tls_get_addr: %p {%p,%p} => %p; tls_beg: %p; sp: %p "
              "num_live_dtls %zd\n",
           arg, arg->dso_id, arg->offset, res, tls_beg, &tls_beg,
           atomic_load(&number_of_live_dtls, memory_order_relaxed));
   if (dtls.last_memalign_ptr == tls_beg) {
     tls_size = dtls.last_memalign_size;
     VPrintf(2, "__tls_get_addr: glibc <=2.18 suspected; tls={%p,%p}\n",
         tls_beg, tls_size);

test/asan/TestCases/Linux/static_tls.cc

 // REQUIRES: asan-64-bits
 // Regression test: __tls_get_addr interceptor must recognize static TLS.
 //
 // RUN: %clangxx_asan -DSHARED %s -shared -o %t-so.so -fPIC
 // RUN: %clangxx_asan %s -ldl -pthread -o %t %t-so.so
 // RUN: %env_asan_opts=verbosity=2 %run %t 2>&1 | FileCheck %s
 
 // CHECK: before
 // CHECK: __tls_get_addr: static tls
 // CHECK: after
 
-// XFAIL: powerpc64, aarch64
+// XFAIL: aarch64
 
 #ifndef SHARED
 #include <stdio.h>
 
 unsigned *f();
 int main(int argc, char *argv[]) {
   fprintf(stderr, "before\n");
   f();