Date: Mon, 17 Oct 2011 00:20:47 +0800 From: Adrian Chadd <adrian@freebsd.org> To: Warner Losh <imp@bsdimp.com> Cc: freebsd-arch@freebsd.org Subject: Re: newbus bus access routines and bus_space_barrier() Message-ID: <CAJ-Vmom_ujHNytAmRN76Ww1jTnLUO2b4CsbH6Tph2jcdv94c-g@mail.gmail.com> In-Reply-To: <4EEA1F8B-9854-4C5C-A397-95AD454D3680@bsdimp.com> References: <CAJ-VmonJnHyLQJ-kVtMV=X7mq7=wq2MGn9wUqdbEtZ6qXd52rg@mail.gmail.com> <4EEA1F8B-9854-4C5C-A397-95AD454D3680@bsdimp.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On 16 October 2011 11:45, Warner Losh <imp@bsdimp.com> wrote: > Usually they are needed, but we get away without them often because they are needed in a limited set of circumstances and we have memory barriers in our locking primitives. Hm, so should this actively be fixed for drivers? I note iwn(4) does its own (correct looking?) barrier stuff. A few other drivers do. ath doesn't (yet). wi(4) doesn't yet do barriers, but someone supplied a patch that may work better on ppc if said barriers are included. Thanks, Adrian
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAJ-Vmom_ujHNytAmRN76Ww1jTnLUO2b4CsbH6Tph2jcdv94c-g>