From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mout.web.de (mout.web.de [212.227.15.4]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 9CC39386C1E; Mon, 10 Aug 2026 18:08:45 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=212.227.15.4 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1786385328; cv=none; b=ew0R4LF2VLnmROfE0dDBXx4IRCF0G56juqduTUuwPfgtJgsqpZVJFKrvKrpmManwGWYK+mlYhDJ9jVQhzGNa5jUgspEF6+phkCa6VTcRX0mxOlmE/lw9OenJ6kti2lvPi2RZtUV7hSBHRgLaA0ZfU5FM0iN4ShxhMfuETT7zDE0= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1786385328; c=relaxed/simple; bh=CSt57JpgI+17xAo5V9C39r/T7YtE9Ld5077l6RUSWNY=; h=Message-ID:Subject:From:To:Cc:Date:In-Reply-To:References: Content-Type:MIME-Version; b=S4CS8lR9wXGwXGlU5t1b8un2kGToftSBUYdTsEciIs/7PI5qC/IPmrlWxBAo5So7AjZtRCLRldqmvS03+umPMm7+/TB3hmDYUX9SSa74vGAreCWVm7Ni5rTLBz80x0IsvS4m/VaXZlKKM9rbKJBTFYjNLW2VIxOVHwCVc6g6LhE= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=web.de; spf=pass smtp.mailfrom=web.de; dkim=pass (2048-bit key) header.d=web.de header.i=spasswolf@web.de header.b=O8tL8q4r; arc=none smtp.client-ip=212.227.15.4 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=web.de Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=web.de Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=web.de header.i=spasswolf@web.de header.b="O8tL8q4r" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=web.de; s=s29768273; t=1786385313; x=1786990113; i=spasswolf@web.de; bh=QYc+eF6/YnZt2VFVNOIwgjAZT9Yt1fgTfonhQovMzs0=; h=X-UI-Sender-Class:Message-ID:Subject:From:To:Cc:Date:In-Reply-To: References:Content-Type:MIME-Version:Content-Transfer-Encoding:cc: content-transfer-encoding:content-type:date:from:message-id: mime-version:reply-to:subject:to; b=O8tL8q4ranKHXQGRBDkW2153uX6AtJyfQXv9rkEvRwUq53HDa6kMmofKM3HCkRSK +k4EB5yXOiZJgHHzDo0QkpyXuTVwruDm9gkTeRSAUbbYnpHN8g7l0GyUHRyqvss9O crQnNHDorFWQNvHMhLhOzmUEJcBLc7dGNpMDvOWldGfgWt0DfM8dfqNW1kPLpYdLw 3JE0KppeKBNPwsCBlvo9lRxtNblvwWAdqDBmT6/4QWehLrD3Iwj4VBhRn9m/nLPR+ HkfYa+NDijiPBOggG/4dLBMhdvnF6Z3shpp1p8+WItFCTIFCbY/cwE8od1dWKOu2Q DEfK40FATgDsmW183Q== X-UI-Sender-Class: 814a7b36-bfc1-4dae-8640-3722d8ec6cd6 Received: from client.hidden.invalid by smtp.web.de (mrweb006 [213.165.67.108]) with ESMTPSA (Nemesis) id 1MIL4K-1whPbJ2pUq-007NlK; Mon, 10 Aug 2026 20:08:33 +0200 Message-ID: <014e423f0ef7c8e7c4c3f208ec6c632c796b80a1.camel@web.de> Subject: Re: [Re] GPU reset when running the ROCm hsa runtime tests on gfx12 and next-20260701 From: Bert Karwatzki To: Alex Deucher , "Zhang, Jesse(Jie)" , Shaoyun Liu Cc: Alex Deucher , linux-kernel@vger.kernel.org, amd-gfx@lists.freedesktop.org, linux-next@vger.kernel.org, Amber Lin , Mario Limonciello , spasswolf@web.de Date: Mon, 10 Aug 2026 20:08:31 +0200 In-Reply-To: <5b571b7ce1c81d3757061a4378db0ced65a86b58.camel@web.de> References: <20260705003504.31425-1-spasswolf@web.de> <5b571b7ce1c81d3757061a4378db0ced65a86b58.camel@web.de> Content-Type: text/plain; charset="UTF-8" User-Agent: Evolution 3.56.2-10+b1 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Provags-ID: V03:K1:4yS5AfOhBBE95NhWAmoXoiJTQmCP/zycCxmWDWyBtX0PbBDLF6W 3UR+j3KJy8p/QQkvVcnKJZXa9DS2eyKoFKJGdJHrmdt81vkuVUsmV0qQf6uGuzvTzBG+Xxb FP/TzceCVJh3tQuX8EF72jFykoGUOqr9qb8tnI9hPRgMafghBaqx31uwLFKBKQhAb4xNpkC SUMIMc9gXuJlqFOWi4+Kw== X-Spam-Flag: NO UI-OutboundReport: notjunk:1;M01:P0:+HFxhJ6jx8M=;RAXKoxkXEL0ywXWY8KG5I9OR/IS nVMfdgc6Yh06NuXyOQJMRHfnpQ+0l1pbslRrCFLcZg/jrAeDQOED4Xll48qYUs/9W9Jg0GFbr MVaS0lgJ/wMoVUp5SIySXQ/k3F/xNyD99/n5nUyuxy/ncGV13rgmjHbldxzryr1KYDKE2hdJY T7FW4v0Nih9q6SXmRCw24y1pg72XyZFWe9rz+hyxlahD7hc+00f4f0NYzvhsGne9agV88DKPp VmnrjU+5egCX6G+RGjCjvuaiDaOqxp67F2+Oqy1MA9/i5nF77ogr4gruvjUAzMObqPb+Ny2RJ hkHm6TJFpftKW1EukTMxHvKJ9Ues60seqcGY/wSQ/SpOaK5wJ5MsmzPW+AvlIkKx9n6ZvraPp an9ETi4pxkAyfsReG96Wa2Mdiv7gaf5GP5vrG7yXPj381GLUcU9Uq5QpgC2whS+I62HbON8DL GdQoFwXTZa0zBlovSG3WRvEYvSEs6RrHPEZi9kCkaI5DBZ4tBrHSqIESgUty+XucNcV1+kNUz i+0L7PtIT5z1nrimmMyHoN8h8OKf2WnFniSdIthL6I6ZB1grP/U0QT6UQpUgxnm2EQ9YvtVq4 d1IXN6cMBk+JafjNkPyvCEnxaa5NO16faTncNPMgVyjMAT3yH4EBzdi+dI2gxz31jmykMW/3F P9FF+R9chtLUb2mWS4mZh3/cPZrIAGyuC8UMR0yFDjv5wNDthf1eTUcL/LXoM+mszlQiJRgQU SUcQMXkQHmUtfs6h6uiu6BSuCRAqKbErPfJybrz7A32FbuUry9d/RoaNhNNnaOH/kn2hPA1pS LrC/VCYezlFSmAOHoVxskT3hSzofpk0PkHftRgIPzP5cpKh/uJ2FroTNO04V7KCAkB889++RA PxU91h6Yse0Y+YU+D0LIXg6Fix8a9hd5TsNjhrULbMpbWwNqnwEASz9u+OLJrahO8vbNws+n9 DCPs8+ssIDCLjMWaRqWabsUDPpWteiCKSCvA6QSuOpNwpv9v30s+bT6pq8pJ0dTpqRv7W+Rpd 9Qk0Y66RBylKHvzMrHybTp/QKu+iFsZ0oYANMTTMAlScSE0k2KJiy1jEPoc29psOcKdhQDq3m Vv1mcm+FqgHjxxRA0Vio40XVhWlWU3Ef+nuIh64jES3irKenufgH+Yvf1QRCJ46WtqQdC/Cic EtnDkAIczVXK5Z7OU7jOZmZssM3xmA80QM1qHZ4clqMtToq7yGgemR+JIWOluenyrSw1/7dOE /EZpSzpdShM3x6oDROCzoyMJGsysbtInA0gbct01QljlnHD+lmRvTdCbk2wauD/MXaBKiQ6Qt MeXp8KiuIoA5jsz+adptuZB5hDMO3EufeQBLDYg87DOdkP6+t/TCpauPgAi+mjHsUaob0Jq9n 0G1Fps5ARs/H9qtFJSvt8XyASnnldrm59/3+/xkVd4piTKZBdlnAR7TqF9QSceZ71WDyGD+E+ 67pgepIcSHbwrMu1j8o44Wooq+dGUGWKVumQGovqgvWlMjr7ErghO613HxgHcOR/T2LcvrSPT 7YyP76/FtYjvRmJnHdfpX3YJRXYbRt4W3jT99MzMJMEJsyji8ItgkkD3drmhc1ITmaEpFg09h sDUIYzXbt2QihTRMwWD0NwSBgKdgpKR4lGFpzVFbSoVRiZASarc2VqQMbQatm03oF0m67+V8x M2upns/kRpjI2rpoYvE0tCLsP679fZnK0zQhsqwF4FRs6jz8iu+YHCoWNLaeE7Ov1N1RqhvEY Bp8oVnd62vvM4+/1ovakckYsUT/ctF8ZqR8BkGrlD6j1QHDZI0Ojm1bzhMi+3bB0WOL83fmEG iHIc7SAPGeUDeqAbuw8XPaZNI2lJI373ivi9fwWB1ld8+okihoYqrXvaG6y5w5cyKCGN9ICPf vnnL/xyc4C+13exP4Z/t0nIksOatHzsCDaf49CYF3fnzbCly/GANOGGaWRVBF1gd+k6BMjqPd sVQm9i9ALc2VlaTeVPUqwguExsWaHbLUiapsoHF2tXiCowHEiVX2XQKicurTu6vLqDNLLHHBU 8pvxk7AnKNsEuqeIvUuutYRMS6upP+CsjIR5JSs5Y2tvDHffHR5/OVDi5QTHjB7DgOC26i7yx FuFga1sCNuL69bGZLSkCKBRCVLmQDvppY/6nda2AiiFmZDU70jX395mofJYe7F1hmZEhjfkj6 TIh3Rcq4BadgRJZmUA3UFnEb/rx2VvAY7vTBqwLSSe6gaOrefBWSUPEPjTWYgSYhYmo0CCJnQ nmbXcr20sjqyjE92oJZWsIVJvUUnX5uZyEPjHQGYV8vd1QYoOQQCAXusBwrTp3dvSoq+SnzSq byczhyYxaah7/B7JCsYhmadvTDe1tpJwWiANw52Uer10nIuTuT2tcbtQIsIddbjrN7gQgXI2V 0VFC8UeiXnPNhlKfhVBaB5oMB0vJN6UeNmkCtg6w1U+lJnc1qeRHhxoLQyt7FI3YshQGbJvJ9 rjdzJwuhX6xiXN/6itwX/XLSVjUXJDhf5SzErU/HebYheuxaGUsWlcePQS8/J4IHtxzpf6Nx7 IInArg9XGbG30DYe0tUtwwkUb2LSoCK8B6aRhQZQ+UYFgs9D3QAFBxobgTeOwRwn0ZtC7Vl4R PB8ooY9pqOlZuQ5UDmaOZFndD8+RVelKSiPC/mr4+u8dD+u7envzQgxGD5BQUXea/xmi18Yx9 U3OwUGftvVOxIJKHeLaRkCI+s2T/1yy/pgO9lA5X6iscvZ73VkUhfBvxb6a0XeAZRrKpahryx I29/BPZnD8wxxNzN8Wdaf5+pVu3KMGTyxglDucXL3t/PpURRkESYLimEJJ6PEBaOOS8h42XLj oBPExdbEP8aUg1dwiVedYTSI+KejLw6Oyu8mB2iH3Mzj05hq4ydncJ8wLKVCyX3lt5XlZh0x5 MyGP/3Hvx8rjSZTzUrBJQLngFsJNS+gv4MGFD6Eg7dwAAt8aQXBjPP9Z/9q8n/kbsHvJHU4jR t6j4lpztfZtvYQVe81swOw5Y1At/BkXqHWgj/laUVulSrxuVdwSkZc/Sry+OfQP4FmwffnMJj x5pVUV4fOFLKYwW8sya4uhPMLi8KqYMAW3QJDZ4DmydLqlp3gwGXrUwiactB1Y1nPZeM2Pqw9 YNr0/Z0mXY8Ho8jecexs0kDBeIGx2gCmKDWjjKzF+H3u+JG2Aw8Ao8q7Fv04l315qenJX1IGd gbuLms0V/533DqAOeuLLKVNh2uCrfCud/zNdwrgkdrOKJTy5Xgk7R8BvvH6IxRe0aj5oVaOa+ 3+jh9cRm5sAPk3M1v/AiARD8Dg0cSukFYdknzplooGbzcLzezryDD6UYT6V30CtV9MJ1qNuEO eFRAdjTsaprlZvDx7bw2C3GBfX3mBZN0GVV7d77PahhD6oi0+lgoa+SObFwfdTiduYMAcHD8m jl2KWJrWBbP7Ua0c664BTw4JVwKUVMUJTT7n5fI3K3g/5omb5xqLwK8CJdpZuOa71QFp2NjN9 5MUcGPv2ZoVY6IslS8Ipt/o8u24dwNoGuswgpmzeMMDmc7i66gtDzTmS+mbCiihr8KebrdOCg XpOYNo7gqvHKkMDstqBMKRPqPv/yFuxPFuOhUkRk/B81T8mtI/Eegf9pC0g5iHnhhde+hpA8y +JO4sQDlt7yK0Rp4T0hTrAGO8EL5+5UlNRtKYYO6uvF2qJj1fqkUiJQTOvdikXh343L6Pl2t1 wcbk8mklNLbLwnXS6L3hAtK5/AHjyaA/87AtdNkhIEctl2wxdjgKvmlItIw+loccq3t/4WkSP RKGrLs3DMBsenAMbWRmpD0rTLe/uWVvVVIte9pEP2ZS0UijzEGVCcY+vfx4Er7dqJyj0JOBg2 9F6fI8JED+Tke4jBXdNvTOFcH7P5gyU/bEgejSF5EumyQTuNN7feYBoC0/yqoVft4naiC8Omy aGEtj07pJY9WUSnz2u6O/0AbVrHmcI9Wqhk6e+jX5QQf6i0oSchntaYtBpi/Ixcrlpb/NXvdL m1SC7RmkV/EZL6jXF6XOONtMTgWG7NOqhQhBrWrcp0vgZo2da9lFQ4gYfGmiqKiOAm/bGO2rq /vLOJm+T0gJvLszSOGkgfFCQk2ENGgydpHWjP3/vjmxo4TsFfxAnwtt/eX+zkPgTrPz7WgI1k UO7Gl17VUGSxa8M1LMXtkxsQS38QxGAANivQh9d398YdjyT2UbMr4LvtfPbTBxTg2R7XLEXCB 7ctpUq5ufQEqCeZKlry3XJXPFIWe5ro7kIVUcxctd8GHSuvDXeQUNFzfEs8Y7zBqXZMPDFw52 dWyeP/laD3Uz7c42K+zND3itPzvVuiGjPzTi0szNnSYh9l7QSdZ36wLTtqxbwSE+dUwuRlEUm 2x/RMB4ToHo3r/lm2lm3OPoIJOTPpFIiqQI9rg+j7kHPqj++kctA2YikR0sVjRYxGHih15hwS EHWVyy/5XGyuypB/uSKIQe9mRdjhKbys4RKind0+UHmLgl/D21Rbfzfqi7dQL8AkrQEoDuhx7 2NENtRGXTfan9xnURpGaiXHZiG9UjZ6+8+cOBdiPbLTEMLXza+ufMwhCLiHgi77MNFR6zKVLf KOjTVm57+4bOCEV2vnWZIUwsFgE/h/WUdLmiJDYeZJhcSX3MFyH6JmTgScck1k5iVig9E1vEV g+ptytznhLRgm6KDJRCj+blZh26Ce/GbqjAwYNtz7149c8iSNpWUyWs9yqC7yyf9KZcPIeQPz 2hFPrdmYuxIkvuhZf2QOSXaNvFg0zDjAPb5FcC2rHpfvYbYUGviYiqgV6PVUKUVyvRvALGUm0 75mO/Lu669nDvfnP0QRhbWrTia7lD5otwEA9USXq3imSQa8KOpvBI56kSR0KvMlWWMQ7zQgVq orkGaV41Qe5wAiYg6E1ikOFWlRgH6oAfMlQlGF87iBt3B+yqmMig/elXpQ31noe6iUJbdv6Gy 1Yg4rjSNHJ8+uy81etrLiudVYsWc6fRf11wyZCAM+46hAbQVFRRIJ+1SeHEfqngReRn41h2Rz 0+WoCmTVRxu3ZCW2T3dezK+n30cZBHOt2vpg1ZImKRfp9xc+IdFcLSf7fIoZ4d2U4+8gWFhX9 Vx0YI/UYelzcVNSTc+/dNQqlCG66yOM/K4Pc3BYd4M2t6JSFZnWe7Zr03NKui2Q6o8PDCp4cy sytn33qGjecUY1aXwzo4qb96+1ZJNJ5dyePaIetWgQIGvy7rBEoG0A4SrIKy77tC8B0YKTnMK z6L/FOF7FqYVDjNwd/QjzZLAmMllA02LeE4gCEE0yTwFg81HVyyCTKlzoa0bxm1fFbDwxdPXC yhiFc2CRWFUllpyM3VpqtIzn/0Ih8ff0cjBzifQYO70AiR8vLV0DcpBMoU/SQH2xOKcMUsNLe 4iecWkyiXBPEbNglyth7pWADGxo7nhfgiEkTs05FQXZh933f24bpYFTq/8z+5S/kqvPfdEOGD 5BG4l4sg1x3N3mFcpG0UfwEnfoL90vyo1XNUEljVv9/utAkUoPGNwSnPc+Wq6fGWW/gkWSjco cK8970cvS9XQNa7FvydUl34SvETzqV3aSk1oFBHl9xUX4JL0+Egl+ye4kj3VZMEOVuK+fmjYA YzW+FllpWoyRwDQGHznCn0FEQZ5BqoO6peVlu3tWTjgX37npDkXicWHo5hzi5IQOz6x5RurQC su54gKUthb9sonStFey8Pgp4y5vWFvKyKs93U9WzyF5H+LdRRKlYcPevjzOll5bJkNyFJhoTN 4kzsD2eBRC1cdtU0VB6S/Dgpo3rbb8bFc2WWoQ54Au+fLtXA0M2bOW0+/1PWkAKvhvEXU3D+9 BAloA8XJPMsyPFGzRehW37H8MgBFl4Mbsu1eJ7VlPGWfZfr1yY8BhyYevPdN68Vs= Am Montag, dem 10.08.2026 um 18:24 +0200 schrieb Bert Karwatzki: > Am Montag, dem 10.08.2026 um 10:15 -0400 schrieb Alex Deucher: > > @Amber Lin > > , @Zhang, Jesse(Jie), @Shaoyun Liu Can you take a look at the firmwar= e version? > >=20 > > Alex > >=20 >=20 > These are the firmware version reported in sysfs: >=20 > # find /sys/class/drm/card0/device/fw_version/ -print -type f -exec cat = {} \; > /sys/class/drm/card0/device/fw_version/ > /sys/class/drm/card0/device/fw_version/pfp_fw_version > 0x00000c12 > /sys/class/drm/card0/device/fw_version/vcn_fw_version > 0x0910c01a > /sys/class/drm/card0/device/fw_version/mec_fw_version > 0x00000d0c > /sys/class/drm/card0/device/fw_version/mes_fw_version > 0x0000008b > /sys/class/drm/card0/device/fw_version/dmcub_fw_version > 0x0a000c00 > /sys/class/drm/card0/device/fw_version/me_fw_version > 0x00000bc2 > /sys/class/drm/card0/device/fw_version/asd_fw_version > 0x21000110 > /sys/class/drm/card0/device/fw_version/sdma2_fw_version > 0x00798e96 > /sys/class/drm/card0/device/fw_version/sdma_fw_version > 0x00798e96 > /sys/class/drm/card0/device/fw_version/smc_fw_version > 0x00664600 > /sys/class/drm/card0/device/fw_version/sos_fw_version > 0x003b0f0d > /sys/class/drm/card0/device/fw_version/imu_fw_version > 0x0c2c2500 > /sys/class/drm/card0/device/fw_version/rlc_fw_version > 0x00bde160 > /sys/class/drm/card0/device/fw_version/mes_kiq_fw_version > 0x0000008b >=20 > In addition dmesg reports a problem with the mes version: >=20 > [ 4.353074] [ T489] amdgpu 0000:03:00.0: MES firmware reports inco= rrect version in ucode binary (0x1 vs 0x8b) >=20 > Both these result use the firmware package shipped by debian sid: > ii firmware-amd-graphics 20260622-1 all Binary firmwar= e for AMD/ATI graphics and NPU chips >=20 > The earlier result of mes_sched =3D 0x76 is probably from the old firmwa= re (debian stable version 20250410), but > the gpu resets also occur with the new firmware from debian sid. >=20 > Bert Karwatzki I just tried the amdgpu firmware from the master branch of https://gitlab.com/kernel-firmware/linux-firmware and the result is the same (i.e. same firmware versions, same gpu reset). At least the mes firmware binaries are identical: bert@homer:/lib/firmware/amdgpu$ ls | grep gc_12 | grep mes | xargs md5sum e50b66d9d8cae78ddf76ea27cca5a051 gc_12_0_0_mes1.bin ed07c8a5a307bc882d42fe89441d1da9 gc_12_0_0_mes.bin 3284fd6f8269d020190d5e11075bbf6a gc_12_0_0_uni_mes.bin 99c60afc75c11cb47007c40db29121d3 gc_12_0_1_mes1.bin c1c9b01f5dd171906e7beefca32ebb9a gc_12_0_1_mes.bin 3284fd6f8269d020190d5e11075bbf6a gc_12_0_1_uni_mes.bin This is the backed up firmware from debian: bert@homer:/lib/firmware/amdgpu.debian$ ls | grep gc_12 | grep mes | xargs= md5sum e50b66d9d8cae78ddf76ea27cca5a051 gc_12_0_0_mes1.bin ed07c8a5a307bc882d42fe89441d1da9 gc_12_0_0_mes.bin 3284fd6f8269d020190d5e11075bbf6a gc_12_0_0_uni_mes.bin 99c60afc75c11cb47007c40db29121d3 gc_12_0_1_mes1.bin c1c9b01f5dd171906e7beefca32ebb9a gc_12_0_1_mes.bin 3284fd6f8269d020190d5e11075bbf6a gc_12_0_1_uni_mes.bin Bert Karwatzki