From nobody Fri Oct 3 20:51:26 2025 X-Original-To: freebsd-virtualization@mlmmj.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mlmmj.nyi.freebsd.org (Postfix) with ESMTP id 4cdgnN61Zrz69BNl for ; Fri, 03 Oct 2025 20:51:36 +0000 (UTC) (envelope-from jon@xyinn.org) Received: from mail-4323.protonmail.ch (mail-4323.protonmail.ch [185.70.43.23]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256 client-signature RSA-PSS (4096 bits) client-digest SHA256) (Client CN "protonmail.com", Issuer "R10" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 4cdgnL3Bycz42Bv for ; Fri, 03 Oct 2025 20:51:33 +0000 (UTC) (envelope-from jon@xyinn.org) Authentication-Results: mx1.freebsd.org; dkim=pass header.d=xyinn.org header.s=protonmail3 header.b=WAbohS9h; dmarc=pass (policy=none) header.from=xyinn.org; spf=pass (mx1.freebsd.org: domain of jon@xyinn.org designates 185.70.43.23 as permitted sender) smtp.mailfrom=jon@xyinn.org DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=xyinn.org; s=protonmail3; t=1759524691; x=1759783891; bh=fiieQe2PTFWj4GKCuAj4AR2Ig9AY5PRkJCErnsoCZJI=; h=Date:To:From:Cc:Subject:Message-ID:In-Reply-To:References: Feedback-ID:From:To:Cc:Date:Subject:Reply-To:Feedback-ID: Message-ID:BIMI-Selector; b=WAbohS9hiKpEKozEN8pdhbJFqJ8pKALrDdWdWQWTNBjLO1RrZN1qgaJiWC90dlMbq mxmBmG0NFDNFMiZum7nt7syWHSX+2sUQIZ1+FFVkitz/HePSySPQGpbQWgGYQe2pvO EPHOokPNd1DvDYqZPle0UuVI8kg0un7WGC1PkP+29l72LDxDjAGbrbpMplJROwM2L9 rrmSywBzVCtMv+kniIgKg8tFdwi3UtR9MCs2N3E3RVMTAxC9GItSfXPPB2yFdOrQSe xfcbUU+6e5Nf2BrQjLp0nDe8M9aIj0T+mckSfFe5MU9853UNMJhLMNwCuuBIJMm21J aT0rRZj/amcLA== Date: Fri, 03 Oct 2025 20:51:26 +0000 To: Jonathan Vasquez From: Jonathan Vasquez Cc: "freebsd-virtualization@freebsd.org" Subject: Re: GPU Passthrough on FreeBSD 14.3 (AMD Radeon RX 6900 XT and Windows 10 Pro) Message-ID: In-Reply-To: References: <6CV-OY6BcErrWRit9jSpi6fWsYBG3E_Z3u6eTLPcz6foPAZV1gQpZYaZTR7JA_1ot5RQVqrWQaLxJFySXjspIhSbBJGxmckcDQyzxhALNus=@xyinn.org> <77221679b528434788d667441d1a32a2@userve.net> <44d9286c-0866-4805-827d-5cb91511800b@tilda.center> <3HATaLlOogPiMZWbxSnWPCnJC11_unXloaoQzyF8Ek01s9gZGVqnKKruZgFTrqHQBCi5xWNEzLzK37xiNdn3yCwXG8U7NfXKRmwY8_5xCLw=@xyinn.org> <7CNs3oS07TqJcWsTrJCZmDlAypBuy9yh4xr_iAgGnUOGjqAP5iRl1JMkuna8LwFSNIvphQLojKi214B4w6ef2q2IRgvjdolLwUD8KCnXaSQ=@xyinn.org> <9c53f1805e22fcf2c9eb878e0c7cc9a723c30dd8.camel@FreeBSD.org> <-rzPcOUnhEy7jFcu7cF7V_kjAVPV_2deuhv7EY-eJl536fUllXK-3SSnWq13HStABMZuphkRAysMMhDXvd_MWIlH4QaMGU-8l2nXKeOY-Eo=@xyinn.org> Feedback-ID: 12351801:user:proton X-Pm-Message-ID: 118b860c753131a058cae18b48abbae192df55a8 List-Id: Discussion List-Archive: https://lists.freebsd.org/archives/freebsd-virtualization List-Help: List-Post: List-Subscribe: List-Unsubscribe: X-BeenThere: freebsd-virtualization@freebsd.org Sender: owner-freebsd-virtualization@FreeBSD.org MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable X-Spamd-Bar: ---- X-Spamd-Result: default: False [-4.39 / 15.00]; NEURAL_HAM_LONG(-1.00)[-1.000]; NEURAL_HAM_MEDIUM(-1.00)[-1.000]; NEURAL_HAM_SHORT(-0.99)[-0.995]; DMARC_POLICY_ALLOW(-0.50)[xyinn.org,none]; RWL_MAILSPIKE_EXCELLENT(-0.40)[185.70.43.23:from]; R_DKIM_ALLOW(-0.20)[xyinn.org:s=protonmail3]; R_SPF_ALLOW(-0.20)[+ip4:185.70.43.0/24]; MIME_GOOD(-0.10)[text/plain]; TO_DN_EQ_ADDR_SOME(0.00)[]; MISSING_XM_UA(0.00)[]; FREEFALL_USER(0.00)[jon]; MIME_TRACE(0.00)[0:+]; TO_DN_SOME(0.00)[]; ARC_NA(0.00)[]; RCVD_COUNT_ZERO(0.00)[0]; MID_RHS_MATCH_FROM(0.00)[]; FROM_EQ_ENVFROM(0.00)[]; FROM_HAS_DN(0.00)[]; RCVD_IN_DNSWL_NONE(0.00)[185.70.43.23:from]; TO_MATCH_ENVRCPT_SOME(0.00)[]; RCPT_COUNT_TWO(0.00)[2]; MLMMJ_DEST(0.00)[freebsd-virtualization@freebsd.org]; DKIM_TRACE(0.00)[xyinn.org:+] X-Rspamd-Queue-Id: 4cdgnL3Bycz42Bv Hello everyone, I hope you are all doing well. Since the last time I sent a= message, I've been able to collect a bit more data. After I sent that mess= age, my VM actually started having issues with it turning off, it took many= reboots for it to get stabilized again. There were different error codes, = usually related to 0x77 and 0x78, which seem to be related to power managem= ent or potentially cpu related. I eventually decided to try to see if I cou= ld turn the VM on, and immediately open up a game (like cyberpunk 2077) and= just leave it running in the main menu. Essentially I was trying to force = the VM to always stay running so that any power management optimizations th= at bhyve is doing don't run or are reduced. Leaving Cyberpunk 2077 running = for 3 days had no issues. I then decided to close the game and just leave i= t running on idle to see if it crashed, it still hasn't crashed in another = 2 days. So I have 5 days of uptime so far, and I've played a few sessions f= or at least 1-2 hours each session. Every once in a while there would be ma= ssive lag spike and I see my CPU (and I think GPU) cores going a bit crazy,= after a little bit things calm down a bit. I wonder if that would have bee= n a situation where the VM would have crashed, but didn't due to the game b= eing running. I have no idea. I've also was able to finally get Windows 11 Pro installed in bhyve and I w= as able to bypass all of the install and online requirements. I was reading jbo and other people's success at this thread: https://forums= .freebsd.org/threads/bhyve-vm-stuck-when-passthru-enabled.92854/page-2#post= -719569 so that inspired me to try and work through the issues I was receiving befo= re (I wanted to find a way to bypass everything using a clean Microsoft ISO= and now have to use Rufus to modify the install.. plus Rufus doesn't seem = to generate an ISO, and I'm trying to install this in bhyve). I documented = all we need here: https://xyinn.org/blog/freebsd/install_windows_11_bhyve Now that it's documented and I have a VM running, I'm going to upgrade my s= erver from FreeBSD 14.3-RELEASE to the stable branch so I can take advantag= e of this new commit that seems to have fixed the vCPU issues/crashes on Wi= ndows 11.. that issue seems to be very similar to what I've been experienci= ng on Windows 10 so I feel there may be a relationship there. Once I upgrad= e and have that fix running, I'm gonna do more experiments in my Windows 10= VM and see how stable it runs. I also will try out GPU passthrough on Wind= ows 11 as well and I'll probably make a smaller length video showing the pe= rformance of the AMD Radeon RX 6900 XT on Windows 11 Pro as well, and of co= urse, test the patch's stability since my Windows 11 Pro VM already crashed= a few times when I use it with 2 cores (and no passthrough). When I use it= with 1 core it hasn't crashed so far. - Jonathan