[PATCH 0/4 V2] rcu: implement call_srcu()

[Lai Jiangshan]

These patches are the second version of the
"[RFC PATCH 5/5 single-thread-version] implement per-domain single-thread state machine call_srcu()"

These patches are on the top of paulmck/linux-rcu.git/rcu/srcu
(3c8975b51a7bed5dd993c5c4eab245a121bdc728)

I noticed this branch has patch "implement Peter's checking algorithm"
applied, so the pathes are rebased on 3c8975b51 and are tested based on
Peter's algorithm.

Except the rebasing, only 2 changes:
	Refactor the srcu_advance_batches() as Peter's suggestion.
	Impletement synchronize_srcu() with fast path awared.
	- old version just calls call_srcu() and waits.
	- Ftrace shows new synchronize_srcu() cost 6us when fast path.

Lai Jiangshan (4):
  fix for peter's algorithm
  use "int trycount" instead of "bool expedited"
  add call_srcu()
  add srcu torture

 include/linux/srcu.h |   25 ++++-
 kernel/rcutorture.c  |   44 ++++++-
 kernel/srcu.c        |  322 +++++++++++++++++++++++++++++++++++++++-----------
 3 files changed, 314 insertions(+), 77 deletions(-)

-- 
1.7.4.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/