@@ -1,3 +1,8 @@
+2019-12-17 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+
+ * sysdeps/unix/sysv/linux/sched_getcpu.c: use rseq cpu_id TLS on
+ Linux.
+
2019-12-17 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
* NEWS: Add Restartable Sequences feature description.
@@ -18,14 +18,15 @@
#include <errno.h>
#include <sched.h>
#include <sysdep.h>
+#include <atomic.h>
#ifdef HAVE_GETCPU_VSYSCALL
# define HAVE_VSYSCALL
#endif
#include <sysdep-vdso.h>
-int
-sched_getcpu (void)
+static int
+vsyscall_sched_getcpu (void)
{
#ifdef __NR_getcpu
unsigned int cpu;
@@ -37,3 +38,23 @@ sched_getcpu (void)
return -1;
#endif
}
+
+#ifdef __NR_rseq
+#include <sys/rseq.h>
+#endif
+
+#if defined __NR_rseq && defined 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
+int
+sched_getcpu (void)
+{
+ return vsyscall_sched_getcpu ();
+}
+#endif
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) Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> CC: Carlos O'Donell <carlos@redhat.com> CC: Florian Weimer <fweimer@redhat.com> CC: Joseph Myers <joseph@codesourcery.com> CC: Szabolcs Nagy <szabolcs.nagy@arm.com> CC: Thomas Gleixner <tglx@linutronix.de> CC: Ben Maurer <bmaurer@fb.com> CC: Peter Zijlstra <peterz@infradead.org> CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> CC: Boqun Feng <boqun.feng@gmail.com> CC: Will Deacon <will.deacon@arm.com> CC: Dave Watson <davejwatson@fb.com> CC: Paul Turner <pjt@google.com> CC: libc-alpha@sourceware.org CC: linux-kernel@vger.kernel.org CC: linux-api@vger.kernel.org --- Changes since v1: - rseq is only used if both __NR_rseq and RSEQ_SIG are defined. Changes since v2: - remove duplicated __rseq_abi extern declaration. Changes since v3: - update ChangeLog. Changes since v4: - Use atomic_load_relaxed to load the __rseq_abi.cpu_id field, a consequence of the fact that __rseq_abi is not volatile anymore. - Include atomic.h which provides atomic_load_relaxed. --- ChangeLog.old/ChangeLog.19 | 5 +++++ sysdeps/unix/sysv/linux/sched_getcpu.c | 25 +++++++++++++++++++++++-- 2 files changed, 28 insertions(+), 2 deletions(-)