Date: Tue, 27 Apr 1999 09:45:53 +0100 (BST) From: Doug Rabson <dfr@nlsystems.com> To: Dmitrij Tejblum <tejblum@arc.hq.cti.ru> Cc: Dmitrij Tejblum <dima@tejblum.dnttm.rssi.ru>, freebsd-alpha@freebsd.org Subject: Re: "I-stream memory barrier" Message-ID: <Pine.BSF.4.05.9904270943200.36113-100000@herring.nlsystems.com> In-Reply-To: <199904262024.AAA38299@arc.hq.cti.ru>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, 27 Apr 1999, Dmitrij Tejblum wrote: > > I'm pretty sure that I-cache lines are tagged with ASNs. The Linux kernel > > only calls imb() when it runs out of ASNs > > Well, you are right, even comments in the NetBSD pmap say so. Nevertheles, > they call alpha_pal_imb() a lot - there should be a reason for that. > Also, take a look at Linux' ev5_flush_tlb_current_page() - it flush whole ASN > when it have to flush something executable, rather than do a TBIS. > > > and if it didn't work properly, > > I doubt that a system could survive even a single threaded make world, let > > alone -j20. > > This is not very convincing :-). I have seen as single threaded make world fail > mysteriously. (That is exactly why I started to look at the issue :-). I think you are right. If you want to tackle fixing this, I would suggest modifying pmap_invalidate_page to take the old pte value as an extra argument and using the NetBSD trick of a software PG_EXEC bit in the pte to mark executable pages. -- Doug Rabson Mail: dfr@nlsystems.com Nonlinear Systems Ltd. Phone: +44 181 442 9037 To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-alpha" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.4.05.9904270943200.36113-100000>