Date: Mon, 26 Aug 2002 13:29:58 -0400 (EDT) From: John Baldwin <jhb@FreeBSD.org> To: Maksim Yevmenkin <myevmenk@exodus.net> Cc: hackers@FreeBSD.ORG, "M. Warner Losh" <imp@bsdimp.com>, Bosko Milekic <bmilekic@unixdaemons.com> Subject: Re: Fast interrupts Message-ID: <XFMail.20020826132958.jhb@FreeBSD.org> In-Reply-To: <3D6A61F7.872038E5@exodus.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On 26-Aug-2002 Maksim Yevmenkin wrote: > Bosko Milekic wrote: >> >> On Mon, Aug 26, 2002 at 09:41:43AM -0700, Maksim Yevmenkin wrote: >> > John Baldwin wrote: >> > > >> > > On 26-Aug-2002 M. Warner Losh wrote: >> > > > can you call wakeup(9) from a fast interrupt handler? >> > >> > [ ...] >> > >> > > > The only reason I ask is because sio seems to go out of its way to >> > > > schedule a soft interrupt to deal with waking up processes, which then >> > > > calls wakeup... >> > > >> > > Since wakeup only needs a spin lock, it is probably ok. You just can't call >> > > anything that would sleep (in any interrupt handler) or block on a non-spin > ^^^^^^^^^^^^^^^^^^^^^^^^^^ > my understanding is that John was talking about any > interrupt handler. Not just fast interrupt hander. Yes. When you block on a MTX_DEF mutex, that is not considered "sleeping" for the purposes of that statement. Sleeping is when you are in SSLEEP (well, what used to be called SSLEEP). >> > > mutex. >> > >> > what is the general locking technique for interrupt handlers? >> > there must be some sort of locking, right? >> >> You are allowed to use mutex locks (both spin and MTX_DEF), only you >> are only allowed to user the former for fast interrupt handlers. > > thanks, > max -- John Baldwin <jhb@FreeBSD.org> <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?XFMail.20020826132958.jhb>