Re: Semantics of smp_mb() [was : Re: [PATCH] Fix RCU race in access of nohz_cpu_mask ]

[Srivatsa Vaddagiri <vatsa@in.ibm.com>]

On Mon, Dec 12, 2005 at 11:49:07AM +1100, Keith Owens wrote:
> >On the contrary.  I did some digging and asking and thinking about this
> >for the Unreliable Guide to Kernel Locking, years ago:
> >
> >wmb() means all writes preceeding will complete before any writes
> >following are started.
> >rmb() means all reads preceeding will complete before any reads
> >following are started.
> >mb() means all reads and writes preceeding will complete before any
> >reads and writes following are started.
> 
> FWIW, wmb() on IA64 does not require that preceding stores are flushed
> to main memory.  It only requires that they be "made visible to other
> processors in the coherence domain".  "visible" means that the updated
> value must reach (at least) an externally snooped cache.  There is no
> requirement that the preceding stores be flushed all the way to main
> memory, the updates only have to get as far as a cache level that other
> cpus can see.  The cache snooping takes care of flushing to main memory
> when necessary.

For the context of the problem that we are dealing with, I think this fact
that writes are made "visible" to other CPUs (before smp_mb() finishes and 
before other reads are started) is good enough.

Oleg, with all these inputs, I consider the patch I had sent to be correct.
Let me know if you still have some lingering doubts!

P.S :- Thanks to everybody who reponded clarifying this subject.


-- 


Thanks and Regards,
Srivatsa Vaddagiri,
Linux Technology Center,
IBM Software Labs,
Bangalore, INDIA - 560017