diff --git a/compiler-rt/lib/sanitizer_common/sanitizer_stacktrace.h b/compiler-rt/lib/sanitizer_common/sanitizer_stacktrace.h
--- a/compiler-rt/lib/sanitizer_common/sanitizer_stacktrace.h
+++ b/compiler-rt/lib/sanitizer_common/sanitizer_stacktrace.h
@@ -196,5 +196,26 @@
   uptr local_stack;                           \
   uptr sp = (uptr)&local_stack
 
+// GET_CURRENT_PC() is equivalent to StackTrace::GetCurrentPc().
+// Optimized x86 version is faster than GetCurrentPc because
+// it does not involve a function call, instead it reads RIP register.
+// Reads of RIP by an instruction return RIP pointing to the next
+// instruction, which is exactly what we want here, thus 0 offset.
+// It needs to be a macro because otherwise we will get the name
+// of this function on the top of most stacks. Attribute artificial
+// does not do what it claims to do, unfortunatley. And attribute
+// __nodebug__ is clang-only. If we would have an attribute that
+// would remove this function from debug info, we could simply make
+// StackTrace::GetCurrentPc() faster.
+#if defined(__x86_64__)
+#  define GET_CURRENT_PC()                \
+    ({                                    \
+      uptr pc;                            \
+      asm("lea 0(%%rip), %0" : "=r"(pc)); \
+      pc;                                 \
+    })
+#else
+#  define GET_CURRENT_PC() StackTrace::GetCurrentPc()
+#endif
 
 #endif  // SANITIZER_STACKTRACE_H
diff --git a/compiler-rt/lib/sanitizer_common/tests/sanitizer_stacktrace_test.cpp b/compiler-rt/lib/sanitizer_common/tests/sanitizer_stacktrace_test.cpp
--- a/compiler-rt/lib/sanitizer_common/tests/sanitizer_stacktrace_test.cpp
+++ b/compiler-rt/lib/sanitizer_common/tests/sanitizer_stacktrace_test.cpp
@@ -271,6 +271,30 @@
   EXPECT_EQ(bp, stack.top_frame_bp);
 }
 
+TEST(GetCurrentPc, Basic) {
+  // Test that PCs obtained via GET_CURRENT_PC()
+  // and StackTrace::GetCurrentPc() are all different
+  // and are close to the function start.
+  struct Local {
+    static NOINLINE void Test() {
+      const uptr pcs[] = {
+          (uptr)&Local::Test,
+          GET_CURRENT_PC(),
+          StackTrace::GetCurrentPc(),
+          StackTrace::GetCurrentPc(),
+      };
+      for (uptr i = 0; i < ARRAY_SIZE(pcs); i++)
+        Printf("pc%zu: %p\n", i, pcs[i]);
+      for (uptr i = 1; i < ARRAY_SIZE(pcs); i++) {
+        EXPECT_GT(pcs[i], pcs[0]);
+        EXPECT_LT(pcs[i], pcs[0] + 1000);
+        for (uptr j = 0; j < i; j++) EXPECT_NE(pcs[i], pcs[j]);
+      }
+    }
+  };
+  Local::Test();
+}
+
 // Dummy implementation. This should never be called, but is required to link
 // non-optimized builds of this test.
 void BufferedStackTrace::UnwindImpl(uptr pc, uptr bp, void *context,
diff --git a/compiler-rt/lib/tsan/rtl/tsan_interceptors.h b/compiler-rt/lib/tsan/rtl/tsan_interceptors.h
--- a/compiler-rt/lib/tsan/rtl/tsan_interceptors.h
+++ b/compiler-rt/lib/tsan/rtl/tsan_interceptors.h
@@ -30,14 +30,14 @@
 
 }  // namespace __tsan
 
-#define SCOPED_INTERCEPTOR_RAW(func, ...) \
-    cur_thread_init(); \
-    ThreadState *thr = cur_thread(); \
-    const uptr caller_pc = GET_CALLER_PC(); \
-    ScopedInterceptor si(thr, #func, caller_pc); \
-    const uptr pc = StackTrace::GetCurrentPc(); \
-    (void)pc; \
-/**/
+#define SCOPED_INTERCEPTOR_RAW(func, ...)      \
+  cur_thread_init();                           \
+  ThreadState *thr = cur_thread();             \
+  const uptr caller_pc = GET_CALLER_PC();      \
+  ScopedInterceptor si(thr, #func, caller_pc); \
+  const uptr pc = GET_CURRENT_PC();            \
+  (void)pc;                                    \
+  /**/
 
 #define SCOPED_TSAN_INTERCEPTOR(func, ...) \
     SCOPED_INTERCEPTOR_RAW(func, __VA_ARGS__); \