mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* [PATCH 9/9] jrcu: introduce alternate implementation of rcu_cpu
@ 2011-03-14  3:50 Joe Korty
  0 siblings, 0 replies; only message in thread
From: Joe Korty @ 2011-03-14  3:50 UTC (permalink / raw)
  To: paulmck
  Cc: fweisbec, peterz, laijs, mathieu.desnoyers, dhowells,
	loic.minier, dhaval.giani, tglx, josh, houston.jim, andi,
	linux-kernel

jrcu: introduce an alternate implementation of rcu_cpu().

This new implementation is based on smp_processor_id().
It is for those architectures which do not have
thread_info->cpu.

(We prefer the thread_info version as it works in early
boot where smp_processor_id() has not yet been set up).

Signed-off-by: Joe Korty <joe.korty@ccur.com>

Index: b/kernel/jrcu.c
===================================================================
--- a/kernel/jrcu.c
+++ b/kernel/jrcu.c
@@ -140,11 +140,27 @@ static u64 rcu_timestamp;
  * know what that is.  For RCU to work correctly, a cpu named '0' must
  * eventually be present (but need not ever be online).
  */
+#ifdef HAVE_THREAD_INFO_CPU
 static inline int rcu_cpu(void)
 {
 	return current_thread_info()->cpu;
 }
 
+#else
+
+static unsigned rcu_cpu_early_flag __read_mostly = 1;
+
+static inline int rcu_cpu(void)
+{
+	if (unlikely(rcu_cpu_early_flag)) {
+		if (!(rcu_scheduler_active && nr_cpu_ids > 1))
+			return 0;
+		rcu_cpu_early_flag = 0;
+	}
+	return raw_smp_processor_id();
+}
+#endif /* HAVE_THREAD_INFO_CPU */
+
 /*
  * Invoke whenever the calling CPU consents to end-of-batch.  All CPUs
  * must so consent before the batch is truly ended.
Index: b/arch/x86/include/asm/thread_info.h
===================================================================
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -29,6 +29,7 @@ struct thread_info {
 	__u32			flags;		/* low level flags */
 	__u32			status;		/* thread synchronous flags */
 	__u32			cpu;		/* current CPU */
+#define HAVE_THREAD_INFO_CPU	1
 	int			preempt_count;	/* 0 => preemptable,
 						   <0 => BUG */
 	mm_segment_t		addr_limit;

^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2011-03-14  3:51 UTC | newest]

Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2011-03-14  3:50 [PATCH 9/9] jrcu: introduce alternate implementation of rcu_cpu Joe Korty

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®