Eric Dumazet 989a297920 fasync: RCU and fine grained locking
kill_fasync() uses a central rwlock, candidate for RCU conversion, to
avoid cache line ping pongs on SMP.

fasync_remove_entry() and fasync_add_entry() can disable IRQS on a short
section instead during whole list scan.

Use a spinlock per fasync_struct to synchronize kill_fasync_rcu() and
fasync_{remove|add}_entry(). This spinlock is IRQ safe, so sock_fasync()
doesnt need its own implementation and can use fasync_helper(), to
reduce code size and complexity.

We can remove __kill_fasync() direct use in net/socket.c, and rename it
to kill_fasync_rcu().

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-21 16:19:29 -07:00
..
2010-04-12 07:55:15 -04:00
2010-01-26 22:22:26 -05:00
2010-04-08 15:35:20 +02:00
2010-03-12 15:52:35 -08:00
2009-12-16 07:20:13 -08:00
2010-03-06 11:26:29 -08:00
2010-03-06 11:26:29 -08:00
2010-03-19 08:05:10 +01:00
2010-03-03 14:13:08 -05:00
2009-12-17 04:52:13 -05:00
2010-04-21 16:19:29 -07:00
2010-03-06 11:26:29 -08:00
2010-03-03 14:07:59 -05:00
2010-03-08 16:55:37 +01:00
2009-12-17 10:51:40 -05:00
2010-03-12 15:52:32 -08:00
2010-03-03 14:08:00 -05:00
2009-12-16 12:16:49 -05:00