Messages in this thread | | | Date | Tue, 17 Aug 2010 07:35:14 -0700 | From | "Paul E. McKenney" <> | Subject | Re: [PATCH tip/core/rcu 08/10] rcu: Add a TINY_PREEMPT_RCU |
| |
On Tue, Aug 17, 2010 at 05:36:13PM +0800, Lai Jiangshan wrote: > On 08/17/2010 06:24 AM, Paul E. McKenney wrote: > > >> --(t->rcu_read_lock_nesting) > >> > >> could be split in two distinct operations: > >> > >> read t->rcu_read_lock_nesting > >> decrement t->rcu_read_lock_nesting > >> > >> Note that in order to know the result required to pass the sequence > >> point "&&" (the test), we only need to perform the read, not the > >> decrement. AFAIU, gcc would be in its rights to move the > >> t->rcu_read_lock_nesting update after the volatile access. > > > > I will run this by some compiler experts. > > We can just use "read and decrement statements" instead of "--" to > avoid dependency from compilers.
You mean something like local_add_return()? This turns into atomic_add_return() on many platforms, including x86 as it turns out, so I am reluctant to use it.
If you had something else in mind, please don't keep it a secret!
Thanx, Paul
| |