[BUG] 2.6.37-rc3 massive interactivity regression on ARM

[Eric Dumazet]

Le vendredi 10 décembre 2010 à 21:39 +0100, Eric Dumazet a écrit :

> This was exactly my suggestion Christoph.
> 
> I am glad you understand it now.
> 
> 

By the way, we need smp_wmb(), not barrier(), even only the "owner cpu"
can write into its 'percpu' seqcount.

There is nothing special about a seqcount being percpu or a 'global'
one. We must have same memory barrier semantics.

	this_cpu_write_seqcount_begin(&myseqcount);
	this_cpu_add(mydata1, add1);
	this_cpu_add(mydata2, add2);
	this_cpu_inc(mydata3);
	this_cpu_write_seqcount_end(&myseqcount);

We protect the data[1,2,3] set with a seqcount, so need smp_wmb() in
both _begin() and _end()