From owner-freebsd-alpha Sun Apr 25 7: 2:54 1999 Delivered-To: freebsd-alpha@freebsd.org Received: from helios.dnttm.ru (dnttm-gw.rssi.ru [193.232.0.205]) by hub.freebsd.org (Postfix) with ESMTP id 56E311526D for ; Sun, 25 Apr 1999 07:02:51 -0700 (PDT) (envelope-from dima@tejblum.dnttm.rssi.ru) Received: (from uucp@localhost) by helios.dnttm.ru (8.9.1/8.9.1/IP-3) with UUCP id SAA29829 for freebsd-alpha@freebsd.org; Sun, 25 Apr 1999 18:01:01 +0400 Received: from tejblum.dnttm.rssi.ru (localhost [127.0.0.1]) by tejblum.dnttm.rssi.ru (8.9.3/8.9.1) with ESMTP id RAA02496 for ; Sun, 25 Apr 1999 17:59:36 +0400 (MSD) (envelope-from dima@tejblum.dnttm.rssi.ru) Message-Id: <199904251359.RAA02496@tejblum.dnttm.rssi.ru> X-Mailer: exmh version 2.0gamma 1/27/96 To: freebsd-alpha@freebsd.org Subject: "I-stream memory barrier" Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii From: Dmitrij Tejblum Date: Sun, 25 Apr 1999 17:59:36 +0400 Sender: owner-freebsd-alpha@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org It looks to me that our pmap take alpha_pal_imb() wrong. Our pmap apparently assume that I-cache like TLB is virtually indexed and tagged with the ASN. So we call alpha_pal_imb() only when start new ASN generation. NetBSD have completely different idea (I-cache is indexed by the physical address?) and call alpha_pal_imb() in every second pmap function. I suspect they are right... Comments? Dima To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-alpha" in the body of the message