From owner-freebsd-hackers@freebsd.org Tue May 28 18:17:38 2019 Return-Path: Delivered-To: freebsd-hackers@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 1628415A7AE4 for ; Tue, 28 May 2019 18:17:38 +0000 (UTC) (envelope-from cperciva@freebsd.org) Received: from mail.tarsnap.com (mail.tarsnap.com [54.86.246.204]) by mx1.freebsd.org (Postfix) with ESMTP id 783AE8B785 for ; Tue, 28 May 2019 18:17:37 +0000 (UTC) (envelope-from cperciva@freebsd.org) Received: (qmail 15625 invoked from network); 28 May 2019 18:21:02 -0000 Received: from unknown (HELO ?127.0.0.1?) (127.0.0.1) by ec2-107-20-205-189.compute-1.amazonaws.com with ESMTP; 28 May 2019 18:21:02 -0000 Subject: Re: Amazon AMIs To: Andriy Gapon , Warner Losh , Matthew Seaman Cc: "freebsd-hackers@freebsd.org" , Alex Dupre , Jonathan Anderson References: <8a139c9c-b98b-4a54-1d7c-0ea1e3dc7a72@freebsd.org> <53a0bd68-a6ba-e8ad-4af2-abeb22e92c03@FreeBSD.org> <74ed9ad5-58d9-db02-2e20-b053ba5eeb87@FreeBSD.org> From: Colin Percival Openpgp: preference=signencrypt Autocrypt: addr=cperciva@freebsd.org; prefer-encrypt=mutual; keydata= mQGhBElrAAcRBACDfDys4ZtK+ErCJ1HAzYeteKpm3OEsvT/49AjUTLihkF79HhIKrCQU+1KC zv7BwHCMLb6hq30As9L7iFKG7n5QFLFC4Te/VcITUnWHMG/c3ViLOfJGvi+9/nOEHaM1dVJY D6tEp5yM1nHmVQpo9932j4KGuGFR0LhOK5IHXOSfGwCgxSFDPdgxe2OEjWxjGgY+oV3EafcD +JROXCTjlcQiG/OguQH4Vks3mhHfFnEppLxTkDuYgHZQiUtpcT9ssH5khgqoTyMar05OUdAj ZIhNbWDh4LgTj+7ZmvLhXT5Zxw8LX9d7T36aTB8XDQSenDqEtinMWOb0TCBBLbsB8EFG1WTT ESbZci9jJS5yhtktuZoY/eM8uXMD/3k4FWFO80VRRkELSp+XSy/VlSQjyi/rhl2nQq/oOA9F oJbDaB0yq9VNhxP+uFBzBWSqeIX0t1ZWLtNfVFr4TRP5hihI5ICrg/0OpqgisKsU2NFe9xyO hyJLYmfD8ebpDJ/9k30C7Iju9pVrwLm1QgS4S2fqJRcR+U4WbjvP7CgStCVDb2xpbiBQZXJj aXZhbCA8Y3BlcmNpdmFAdGFyc25hcC5jb20+iGEEExECACEFAklrALYCGwMHCwkIBwMCAQQV AggDBBYCAwECHgECF4AACgkQOM7KaQxqam6/igCgn+z2k3V5ggNppmWrZstt1U2lugsAoL7L wS9V9yLtil3oWmHtwpUqYruEuQINBElrAAcQCAD3ZLMIsP4CIDoJORg+YY0lqLVBgcnF7pFb 4Uy2+KvdWofN+DKH61rZLjgXXkNE9M4EQC1B4lGttBP8IY2gs41y3AUogGdyFbidq99rCBz7 LTsgARHwFxZoaHmXyiZLEU1QZuMqwPZV1mCviRhN5E3rRqYNXVcrnXAAuhBpvNyj/ntHvcDN 2/m+ochiuBYueU4kX3lHya7sOj+mTsndcWmQ9soOUyr8O0r/BG088bMn4qqtUw4dl5/pglXk jbl7uOOPinKf0WVd2r6M0wLPJCD4NPHrCWRLLLAjwfjrtoSRvXxDbXhCdgGBa72+K8eYLzVs hgq7tJOoBWzjVK6XRxR7AAMGB/9Mo3iJ2DxqDecd02KCB5BsFDICbJGhPltU7FwrtbC7djSb XUrwsEVLHi4st4cbdGNCWCrp0BRezXZKohKnNAPFOTK++ZfgeKxrV2sJod+Q9RILF86tQ4XF 7A7Yme5hy92t/WgiU4vc/fWbgP8gV/19f8nunaT2E9NSa70mZFjZNu4iuwThoUUO5CV3Wo0Y UISsnRK8XD1+LR3A2qVyLiFRwh/miC1hgLFCTGCQ3GLxZeZzIpYSlGdQJ0L5lixW5ZQD9r1I 8i/8zhE6qRFAM0upUMI3Gt1Oq2w03DiXrZU0Fu/R8Rm8rlnkQKA+95mRTUq1xL5P5NZIi4gJ Z569OPMFiEkEGBECAAkFAklrAAcCGwwACgkQOM7KaQxqam41igCfbaldnFTu5uAdrnrghESv EI3CAo8AoLkNMks1pThl2BJNRm4CtTK9xZeH Message-ID: <79d5cdad-3a95-de88-25ee-0dd8d27a442e@freebsd.org> Date: Tue, 28 May 2019 11:19:07 -0700 User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:60.0) Gecko/20100101 Thunderbird/60.5.0 MIME-Version: 1.0 In-Reply-To: <74ed9ad5-58d9-db02-2e20-b053ba5eeb87@FreeBSD.org> Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: 7bit X-Rspamd-Queue-Id: 783AE8B785 X-Spamd-Bar: -- Authentication-Results: mx1.freebsd.org X-Spamd-Result: default: False [-2.97 / 15.00]; local_wl_from(0.00)[freebsd.org]; NEURAL_HAM_MEDIUM(-1.00)[-1.000,0]; NEURAL_HAM_LONG(-1.00)[-1.000,0]; NEURAL_HAM_SHORT(-0.97)[-0.970,0]; ASN(0.00)[asn:14618, ipnet:54.86.0.0/16, country:US] X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 28 May 2019 18:17:38 -0000 On 5/28/19 5:52 AM, Andriy Gapon wrote: > On 21/02/2019 18:17, Warner Losh wrote: >> It's hot-unplug that doesn't work quite right. Hotplug works, I believe, if >> you have PCI_HP in your kernel, I believe. >> >> What's needed is about a solid week of cleanup and testing in this area, >> however. > > I am not sure about the context of the latest question... whether it was about > NVMe hot-plug on real modern hardware or whether it was still about AWS. > In the latter case, as Colin pointed out earlier[*], PCI_HP would not help at > all, because the emulated bridge is not a PCIe bridge. > It seems that they use a mechanism based on an older specification, PCI Standard > Hot-Plug Controller and Subsystem Specification. Right, these EC2 instances look like they have NVMe devices being hotplugged on a legacy PCI bus attached to an Intel 440FX chipset. There is no real hardware which behaves the same way as these VMs. -- Colin Percival Security Officer Emeritus, FreeBSD | The power to serve Founder, Tarsnap | www.tarsnap.com | Online backups for the truly paranoid