From owner-cvs-all Sat Jul 14 17:28:41 2001 Delivered-To: cvs-all@freebsd.org Received: from mail5.speakeasy.net (mail5.speakeasy.net [216.254.0.205]) by hub.freebsd.org (Postfix) with SMTP id 04E6E37B406 for ; Sat, 14 Jul 2001 17:28:33 -0700 (PDT) (envelope-from jhb@FreeBSD.org) Received: (qmail 64557 invoked from network); 15 Jul 2001 00:28:31 -0000 Received: from unknown (HELO laptop.baldwin.cx) ([64.81.54.73]) (envelope-sender ) by mail5.speakeasy.net (qmail-ldap-1.03) with SMTP for ; 15 Jul 2001 00:28:31 -0000 Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <20010714171122.L29594-100000@wonky.feral.com> Date: Sat, 14 Jul 2001 17:28:35 -0700 (PDT) From: John Baldwin To: Matthew Jacob Subject: RE: cvs commit: src/sys/alpha/alpha machdep.c mp_machdep.c vm_ma Cc: cvs-committers@FreeBSD.org, cvs-all@FreeBSD.org, Matt Jacob Sender: owner-cvs-all@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG On 15-Jul-01 Matthew Jacob wrote: > > > What do you mean? You mean the 'cngect' dance? That'd work too if you'd like. No, the ugly rendezvous where we stop all the CPUs and then do a handshake to transfer control over to the boot CPU which then shuts down the CPU that just poked it and then performs the final halt so that the SRM console is on the boot CPU, for example. Alpha may not need this however. The 4100 at work doesn't hang on shutdowns and seems to work fine regardless of which CPU does the halt and drop to SRM. > On Sat, 14 Jul 2001, John Baldwin wrote: > >> >> On 14-Jul-01 Matt Jacob wrote: >> > mjacob 2001/07/14 14:37:58 PDT >> > >> > Modified files: >> > sys/alpha/alpha machdep.c mp_machdep.c vm_machdep.c >> > sys/alpha/include smp.h >> > Log: >> > Fix reboot hangs that have happened with multiple processors >> > on Alpha 4100s. >> > >> > Basically, if you're halting or you're rebooting, you should >> > tell all other processors to halt first. Define IPI_HALT- IPI_STOP >> > is not what we want for this purpose, which will call prom_halt(0) >> > on receipt. >> > >> > The processor running the halt or reboot wil send an IPI_HALT to all >> > other processors, delay a bit, then continue to do what what it was >> > planning on doing (prom_halt({0|1})). >> >> Are you sure we don't need to do the "real" halt on the boot processor like >> we >> have to do on the x86? >> >> -- >> >> John Baldwin -- http://www.FreeBSD.org/~jhb/ >> PGP Key: http://www.baldwin.cx/~john/pgpkey.asc >> "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ >> > -- John Baldwin -- http://www.FreeBSD.org/~jhb/ PGP Key: http://www.baldwin.cx/~john/pgpkey.asc "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe cvs-all" in the body of the message