Linux: Use rseq in sched_getcpu if available

When available, use the cpu_id field from __rseq_abi on Linux to
implement sched_getcpu().  Fall-back on the vgetcpu vDSO if unavailable.

Benchmarks:

x86-64: Intel E5-2630 v3@2.40GHz, 16-core, hyperthreading

glibc sched_getcpu():                     13.7 ns (baseline)
glibc sched_getcpu() using rseq:           2.5 ns (speedup:  5.5x)
inline load cpuid from __rseq_abi TLS:     0.8 ns (speedup: 17.1x)

diff --git a/sysdeps/unix/sysv/linux/sched_getcpu.c b/sysdeps/unix/sysv/linux/sched_getcpu.c
index c019cfb3cfb74ae6a240707b63c1be23e4a99b03..c0f992e05629c40eafe1ece5a8c04a8a4db7fd41 100644 (file)
--- a/sysdeps/unix/sysv/linux/sched_getcpu.c
+++ b/sysdeps/unix/sysv/linux/sched_getcpu.c
@@ -18,10 +18,12 @@
 #include <errno.h>
 #include <sched.h>
 #include <sysdep.h>
+#include <atomic.h>
 #include <sysdep-vdso.h>
+#include <sys/rseq.h>
 
-int
-sched_getcpu (void)
+static int
+vsyscall_sched_getcpu (void)
 {
   unsigned int cpu;
   int r = -1;
@@ -32,3 +34,19 @@ sched_getcpu (void)
 #endif
   return r == -1 ? r : cpu;
 }
+
+#ifdef RSEQ_SIG
+int
+sched_getcpu (void)
+{
+  int cpu_id = atomic_load_relaxed (&__rseq_abi.cpu_id);
+
+  return cpu_id >= 0 ? cpu_id : vsyscall_sched_getcpu ();
+}
+#else /* RSEQ_SIG */
+int
+sched_getcpu (void)
+{
+  return vsyscall_sched_getcpu ();
+}
+#endif /* RSEQ_SIG */