diff mbox series

[2/3] Linux: Use rseq in sched_getcpu if available (v9)

Message ID 20200622180803.1449-3-mathieu.desnoyers@efficios.com
State Superseded
Commit 6e29cb3f61ff5432c78a1c84b0d9b123a350ab36
Headers show
Series Restartable Sequences enablement | expand

Commit Message

Mathieu Desnoyers June 22, 2020, 6:08 p.m. UTC
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)

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: 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.

Changes since v5:
- Use __ASSUME_RSEQ to detect rseq availability.

Changes since v6:
- Remove use of __ASSUME_RSEQ.

Changes since v7:
- Fix incorrect merge with commit d0def09ff6 ("linux: Fix vDSO macros
  build with time64 interfaces")

Changes since v8:
- Update patch title.
- Add /* RSEQ_SIG */ for #else and #endif.
---
 sysdeps/unix/sysv/linux/sched_getcpu.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/sysdeps/unix/sysv/linux/sched_getcpu.c b/sysdeps/unix/sysv/linux/sched_getcpu.c
index c019cfb3cf..c0f992e056 100644
--- 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 */