rcu: simplify the usage of percpu data
authorLai Jiangshan <laijs@cn.fujitsu.com>
Mon, 28 Jun 2010 08:25:04 +0000 (16:25 +0800)
committerPaul E. McKenney <paulmck@linux.vnet.ibm.com>
Fri, 20 Aug 2010 00:18:01 +0000 (17:18 -0700)
commit394f99a9007d4274f7076bb8553ab0ff9707688b
tree7d379f91321cec58b87fd5f5089947872689d591
parente546f485e1d7520ca0200502cdcc11b503f4805c
rcu: simplify the usage of percpu data

&percpu_data is compatible with allocated percpu data.

And we use it and remove the "->rda[NR_CPUS]" array, saving significant
storage on systems with large numbers of CPUs.  This does add an additional
level of indirection and thus an additional cache line referenced, but
because ->rda is not used on the read side, this is OK.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Reviewed-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
kernel/rcutree.c
kernel/rcutree.h
kernel/rcutree_plugin.h
kernel/rcutree_trace.c