[IA64] Slim-down __clear_bit_unlock
authorZoltan Menyhart <Zoltan.Menyhart@bull.net>
Mon, 4 Feb 2008 23:19:16 +0000 (15:19 -0800)
committerTony Luck <tony.luck@intel.com>
Mon, 4 Feb 2008 23:19:16 +0000 (15:19 -0800)
commit5302ac5019367470e123cb91844a28d6941e6912
tree33b7ede4df3f5c476cec45b997471ef7a1567f9c
parent97075c4b3b7fdd6a083eea075c3a4a601f0d64d8
[IA64] Slim-down __clear_bit_unlock

- I removed the unnecessary barrier() from __clear_bit_unlock().
  ia64_st4_rel_nta() makes sure all the modifications are globally
  seen before the bit is seen to be off.
- I made __clear_bit() modeled after __set_bit() and __change_bit().
- I corrected some comments sating that a memory barrier is provided,
  yet in reality, it is the acquisition side of the memory barrier only.
- I corrected some comments, e.g. test_and_clear_bit() was peaking
  about "bit to set".

Signed-off-by: Zoltan Menyhart, <Zoltan.Menyhart@bull.net>
Acked-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Tony Luck <tony.luck@intel.com>
include/asm-ia64/bitops.h