Cache getpid.

In practice, with this implementation we never need to make a system call.
We get the main thread's tid (which is the same as our pid) back from
the set_tid_address system call we have to make during initialization.
A new pthread will have the same pid as its parent, and a fork child's
main (and only) thread will have a pid equal to its tid, which we get for
free from the kernel before clone returns.

The only time we'd actually have to make a getpid system call now is if
we take a signal during fork and the signal handler calls getpid. (That,
or we call getpid in the dynamic linker while it's still dealing with its
own relocations and hasn't even set up the main thread yet.)

Bug: 15387103
Change-Id: I6d4718ed0a5c912fc75b5f738c49a023dbed5189

benchmarks/unistd_benchmark.cpp

@@ -30,6 +30,17 @@ static void BM_unistd_getpid(int iters) {
 }
 BENCHMARK(BM_unistd_getpid);
 
+static void BM_unistd_getpid_syscall(int iters) {
+  StartBenchmarkTiming();
+
+  for (int i = 0; i < iters; ++i) {
+    syscall(__NR_getpid);
+  }
+
+  StopBenchmarkTiming();
+}
+BENCHMARK(BM_unistd_getpid_syscall);
+
 // Stop GCC optimizing out our pure function.
 /* Must not be static! */ pid_t (*gettid_fp)() = gettid;