Re: [PATCH 3/4] rhashtable: use bit_spin_locks to protect hash bucket.

[Herbert Xu]

On Mon, Mar 25, 2019 at 04:05:39PM +1100, NeilBrown wrote:
>
> + * Sometimes we unlock a bucket by writing a new pointer there.  In that
> + * case we don't need to unlock, but we do need to reset state such as
> + * local_bh. For that we have rht_unlocked().  This doesn't include
> + * the memory barrier that bit_spin_unlock() provides, but rcu_assign_pointer()
> + * will have provided that.

Hmm, are you sure that's enough? IIRC rcu_assign_pointer only
provides a write barrier compared to the more complete (but one-way)
barrier that a spin-lock provides.

Cheers,
-- 
Email: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt