From owner-freebsd-amd64@FreeBSD.ORG Sat Feb 4 18:14:24 2012 Return-Path: Delivered-To: freebsd-amd64@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 91B331065688 for ; Sat, 4 Feb 2012 18:14:24 +0000 (UTC) (envelope-from freebsd@pki2.com) Received: from btw.pki2.com (btw.pki2.com [IPv6:2001:470:a:6fd::2]) by mx1.freebsd.org (Postfix) with ESMTP id 514D88FC13 for ; Sat, 4 Feb 2012 18:14:24 +0000 (UTC) Received: from [127.0.0.1] (localhost [127.0.0.1]) by btw.pki2.com (8.14.5/8.14.5) with ESMTP id q14IEIXc017675; Sat, 4 Feb 2012 10:14:18 -0800 (PST) (envelope-from freebsd@pki2.com) From: Dennis Glatting To: Konstantin Belousov In-Reply-To: <20120204180401.GV3283@deviant.kiev.zoral.com.ua> References: <4F2CFFC3.30909@gurgelmail.com> <20120204124952.GK3283@deviant.kiev.zoral.com.ua> <7e0e01cc2b957c417a3f69232b33ebe0@antiszoc.hu> <1328372906.15339.98.camel@btw.pki2.com> <20120204163303.GR3283@deviant.kiev.zoral.com.ua> <1328373505.14163.8.camel@btw.pki2.com> <1328373948.14163.13.camel@btw.pki2.com> <20120204170431.GT3283@deviant.kiev.zoral.com.ua> <1328375448.14163.14.camel@btw.pki2.com> <1328377314.14163.21.camel@btw.pki2.com> <20120204180401.GV3283@deviant.kiev.zoral.com.ua> Content-Type: text/plain; charset="ISO-8859-1" Date: Sat, 04 Feb 2012 10:14:18 -0800 Message-ID: <1328379258.14163.28.camel@btw.pki2.com> Mime-Version: 1.0 X-Mailer: Evolution 2.32.1 FreeBSD GNOME Team Port Content-Transfer-Encoding: 7bit X-yoursite-MailScanner-Information: Dennis Glatting X-yoursite-MailScanner-ID: q14IEIXc017675 X-yoursite-MailScanner: Found to be clean X-MailScanner-From: freebsd@pki2.com Cc: freebsd-amd64@freebsd.org Subject: Re: aesni module with AMD CPUs? X-BeenThere: freebsd-amd64@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Porting FreeBSD to the AMD64 platform List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 04 Feb 2012 18:14:24 -0000 On Sat, 2012-02-04 at 20:04 +0200, Konstantin Belousov wrote: > On Sat, Feb 04, 2012 at 09:41:54AM -0800, Dennis Glatting wrote: > > On Sat, 2012-02-04 at 09:10 -0800, Dennis Glatting wrote: > > > > What is written into dmesg after the load ? > > > > Try to restart sshd and log into the system over ssh after aesni(4) > > > and > > > > cryptodev(4) modules are loaded. > > > > > > > Sorry, BD3 is in the process of being updated to pick up the LSI patches > > (Thank you LSI and others). > > > > > > On BD3: > > > > > > bd3# kldload aesni > > bd3# kldstat | grep -i aesni > > 8 1 0xffffffff81768000 1a2b aesni.ko > > bd3# /etc/rc.d/sshd restart > > Stopping sshd. > > Waiting for PIDS: 1832. > > Starting sshd. > > bd3# > > > > > > > > On BTW: > > > > > > btw> ssh -v dennisg@bd3 > > OpenSSH_5.4p1_hpn13v11 FreeBSD-20100308, OpenSSL 0.9.8q 2 Dec 2010 > > debug1: Reading configuration data /etc/ssh/ssh_config > > debug1: Connecting to bd3.pki2.com [192.168.23.22] port 22. > > debug1: Connection established. > > debug1: identity file /home/dennis_glatting/.ssh/id_rsa type -1 > > debug1: identity file /home/dennis_glatting/.ssh/id_rsa-cert type -1 > > debug1: identity file /home/dennis_glatting/.ssh/id_dsa type -1 > > debug1: identity file /home/dennis_glatting/.ssh/id_dsa-cert type -1 > > debug1: Remote protocol version 2.0, remote software version > > OpenSSH_5.8p2_hpn13v11 FreeBSD-20110503 > > debug1: match: OpenSSH_5.8p2_hpn13v11 FreeBSD-20110503 pat OpenSSH* > > debug1: Enabling compatibility mode for protocol 2.0 > > debug1: Local version string SSH-2.0-OpenSSH_5.4p1_hpn13v11 > > FreeBSD-20100308 > > debug1: SSH2_MSG_KEXINIT sent > > debug1: SSH2_MSG_KEXINIT received > > debug1: kex: server->client aes128-ctr hmac-sha1 none > > debug1: kex: client->server aes128-ctr hmac-sha1 none > > debug1: SSH2_MSG_KEX_DH_GEX_REQUEST(1024<2048<8192) sent > > debug1: expecting SSH2_MSG_KEX_DH_GEX_GROUP > > debug1: SSH2_MSG_KEX_DH_GEX_INIT sent > > debug1: expecting SSH2_MSG_KEX_DH_GEX_REPLY > > debug1: Host 'bd3.pki2.com' is known and matches the RSA host key. > > debug1: Found key in /home/dennis_glatting/.ssh/known_hosts:41 > > debug1: ssh_rsa_verify: signature correct > > debug1: SSH2_MSG_NEWKEYS sent > > debug1: expecting SSH2_MSG_NEWKEYS > > debug1: SSH2_MSG_NEWKEYS received > > debug1: Roaming not allowed by server > > debug1: SSH2_MSG_SERVICE_REQUEST sent > > debug1: SSH2_MSG_SERVICE_ACCEPT received > > debug1: Authentications that can continue: > > publickey,keyboard-interactive > > debug1: Next authentication method: publickey > > debug1: Trying private key: /home/dennis_glatting/.ssh/id_rsa > > debug1: Trying private key: /home/dennis_glatting/.ssh/id_dsa > > debug1: Next authentication method: keyboard-interactive > > Password: > > debug1: Authentication succeeded (keyboard-interactive). > > debug1: Final hpn_buffer_size = 2097152 > > debug1: HPN Disabled: 0, HPN Buffer Size: 2097152 > > debug1: channel 0: new [client-session] > > debug1: Enabled Dynamic Window Scaling > > > > debug1: Requesting no-more-sessions@openssh.com > > debug1: Entering interactive session. > > Last login: Sat Feb 4 09:38:12 2012 from btw.pki2.com > > FreeBSD 9.0-STABLE (SMUNI) #2: Sat Feb 4 09:15:42 PST 2012 > > > > bd3> > > > > > > Back to BD3: > > > > bd3# dmesg|tail > > da9 at mps2 bus 0 scbus4 target 0 lun 0 > > da9: Fixed Direct Access SCSI-6 device > > da9: 300.000MB/s transfers > > da9: Command Queueing enabled > > da9: 2384658MB (4883781168 512 byte sectors: 255H 63S/T 304001C) > > Trying to mount root from ufs:/dev/gpt/disk0 [rw]... > > ZFS filesystem version 5 > > ZFS storage pool version 28 > > cryptosoft0: on motherboard > > aesni0: on motherboard > > bd3# > > > > > > bd3# tail /var/log/messages > > (snip -- sorry) > > Feb 4 09:38:18 bd3 su: dennisg to root on /dev/pts/0 > > Feb 4 09:38:22 bd3 kernel: cryptosoft0: on > > motherboard > > Feb 4 09:38:22 bd3 kernel: aesni0: on motherboard > > bd3# > > > > > > > > I /assume/ sshd is using the driver. How would I know? > > Without reading the code and possibly adding some printfs or logs, you > cannot. But I do know that sshd prefer /dev/crypto when available, over > the usermode algorithm implementation. > > You can also look at the users of /dev/crypto, using "fuser /dev/crypto" > command, and see what that pids are. > Check that. At this point I would have to do some reading but there is no /dev/crypto. Whatever AESNI is doing, apparently creating /dev/crypto isn't one of them. I loaded and looked on three machines: Two 8150s and the 6274. All RELENG_9. bd3# fuser /dev/crypto fuser: /dev/crypto: No such file or directory fuser: files not accessible bd3# > Overall, from logs you have provide, I think it is safe to claim that > AESNI properly attached and working on bulldozer. > > Also, there is src/tools/tools/crypto, in particular, cryptotest, which > I used while developing aesni(4). You would need to learn how to use it, > but it would make you 100% certain that AESNI driver working.