[{"id":3676843,"web_url":"http://patchwork.ozlabs.org/comment/3676843/","msgid":"<8c51c77e-b496-4e99-a35c-364d224d1b3c@redhat.com>","list_archive_url":null,"date":"2026-04-13T16:09:15","subject":"Re: [PATCH 00/14] migration/vfio: Fix a few issues on API misuse or\n statistic reports","submitter":{"id":85406,"url":"http://patchwork.ozlabs.org/api/people/85406/","name":"Cédric Le Goater","email":"clg@redhat.com"},"content":"On 4/8/26 18:55, Peter Xu wrote:\n> CI: https://gitlab.com/peterx/qemu/-/pipelines/2437886506\n> rfc: https://lore.kernel.org/r/20260319231302.123135-1-peterx@redhat.com\n> \n> This is v1 of this series. I dropped RFC because I feel like I collected\n> enough feedback on previous version on what is uncertain, meanwhile I also\n> managed to borrow a system with nVidia RTX6000 2GB vGPU and tested it.\n> \n> There're too many trivial things changed since RFC->v1 here, let me only\n> mention what majorly has changed:\n> \n> - This version will assume both VFIO ioctls (reporting either precopy or\n> stopcopy size) may report anything (say, garbage), and it shouldn't crash\n> QEMU. It will affect what got reported with downtime or remaining data,\n> but that's best effort so it's expected. With that in mind, I dropped\n> patch 3 as Avihai suggested. IOW, I expect no concern on either overflow\n> / underflow or atomicity on reading these values from the VFIO drivers.\n> \n> - The cached stopcopy_bytes for VFIO reflects always the total size\n> (includes precopy sizes).\n> \n> - Introduced one new patch to report \"system-wide\" remaining data, which\n> will start to include VFIO remaining device data. We can't squash that\n> directly into \"ram\" section of query-migrate QMP results, so I introduced\n> a new \"remaining\" field in query-migrate result for it.\n> \n> - One more patch \"migration: Make qemu_savevm_query_pending() available\n> anytime\" trying to fix a very hard to hit race condition I found when\n> testing against virtio-net-failover tests. I can only hit it if I run\n> tens of concurrent tests, but it will be needed to fix a crash.\n> \n> Otherwise the major things should be kept almost as-is. I should also\n> addressed all comments I received from rfc version. Please shoot if I\n> missed something.\n> \n> Overview\n> ========\n> \n> VFIO migration was merged quite a while, but we do still see things off\n> here and there. This series tries to address some of them, but only based\n> on my limited understandings.\n> \n> Two major issues I wanted to resolve:\n> \n> (1) VFIO reports state_pending_{exact|estimate}() differently\n> \n> It reports stop-only sizes in exact() only (which includes both precopy and\n> stopcopy data), while in estimate() it only reports precopy data. This is\n> violating the API. It was done like it to trigger proper sync on the VFIO\n> ioctls only but it was only a workaround. This series should fix it by\n> introducing stopcopy size reporting facility for vmstate handlers.\n> \n> (2) expected_downtime / remaining doesn't take VFIO devices into account\n> \n> When query migration, QEMU reports one field called \"expected-downtime\".\n> The document was phrasing this almost from RAM perspective, but ideally it\n> should be about an estimated blackout window (in milliseconds) if we\n> switchover anytime, based on known information.\n> \n> This didn't yet took VFIO into account, especially in the case of VFIO\n> devices that may contain a large amount of device states (like GPUs).\n> \n> For problem (2), the use case should be that an mgmt app when migrating a\n> VFIO GPU device needs to always adjust downtime for migration to converge,\n> because when it's involved normal downtime like 300ms will normally not\n> suffice.\n> \n> Now the issue with that is the mgmt doesn't have a good way to know exactly\n> how well the precopy goes with the whole system and the GPU device.\n> \n> The hope is fixed expected_downtime will provide one way for the mgmt app\n> to have a reasonable hint for downtime to setup to converge a migration.\n> \n> Meanwhile, with a system-wise \"remaining\" field introduced, mgmt can query\n> this results at beginning of each iteration to know if a stall is\n> happening, IOW, if it's likely that this migration will not converge at\n> all. When detected, mgmt can start to consider the expected_downtime value\n> reported above for converging this migration. See more on testing below.\n> \n> Tests\n> =====\n> \n> Tested this series with an assigned VFIO device GRID RTX6000-2B, FB memory\n> 2GB.\n> \n> The test covers both correct reporting of system-wise remaining data (which\n> used to only cover RAM), and the expected downtime. I verified that using\n> the expected downtime I can converge a VFIO migration immediately according\n> to the value reported. Test process as below:\n> \n> Start the VM and kick off migration until it spins at the end, not\n> converging with default 300ms downtime. It's common for a 2GB vGPU device\n> due to both huge stopsize reported and dramally small mbps reported.\n> \n> As a start, update avail-switchover (I chose 1GB over a real 10Gbps port):\n> \n> This will stablize bandwidth.\n> \n> Libvirt's domjobinfo won't be able to see the real remaining data because\n> libvirt still doesn't support the new \"remaining\" field, however we can\n> still see expected_downtime will be reported correctly now (instead of\n> reporting zero, before this patch applied):\n> \n> Data remaining: 0.000 B\n> Memory remaining: 0.000 B\n> Expected downtime: 1910 ms\n> \n> If we peek through QEMU monitor, we'll see with the change the system-wise\n> remaining data to be 1.9GB (even if RAM keeps reporting 0), and expected\n> downtime keeps the same as what domjobinfo reports as 1.9 seconds:\n> \n> Status: active\n> Time (ms): total=336919, setup=10, exp_down=1910\n> Remaining (bytes): 1.91 GiB\n> RAM info:\n> Throughput (Mbps): 460.09\n> Sizes: pagesize=4 KiB, total=32 GiB\n> Transfers: transferred=12.7 GiB, remain=0 B\n> Channels: precopy=12.7 GiB, multifd=0 B, postcopy=0 B, vfio=0 B\n> Page Types: normal=3306906, zero=7745576\n> Page Rates (pps): transfer=14010, dirty=8039\n> Others: dirty_syncs=247045\n> \n> It means 1.91 seconds are required as lowest downtime per math.\n> \n> We can try to set something lower than that, migration will not converge:\n> \n> ...\n> ...\n> \n> Then if we update downtime_limit to be slightly larger than expected downtime:\n> \n> Migration will complete almost immediately.\n\n\nI tested the series by performing a migration of a RHEL9 VM with a vGPU\n(NVIDIA L4-2B) and an MLX5 VF, from a RHEL9 host (vGPU mdev) to a RHEL10\nhost (vGPU VF), with the vGPU under load.\n\nThe expected downtime was fluctuating around 2600 ms. Bandwidth was\naround 950 Mbps. Setting downtime to 3000ms made the migration\nconverge quickly.\n\nTested-by: Cédric Le Goater \n\nThanks,\n\nC.\n\n\n> \n> Peter Xu (14):\n> migration: Fix low possibility downtime violation\n> migration/qapi: Rename MigrationStats to MigrationRAMStats\n> vfio/migration: Cache stop size in VFIOMigration\n> migration/treewide: Merge @state_pending_{exact|estimate} APIs\n> migration: Use the new save_query_pending() API directly\n> migration: Introduce stopcopy_bytes in save_query_pending()\n> vfio/migration: Fix incorrect reporting for VFIO pending data\n> migration: Make qemu_savevm_query_pending() available anytime\n> migration: Move iteration counter out of RAM\n> migration: Introduce a helper to return switchover bw estimate\n> migration: Calculate expected downtime on demand\n> migration: Fix calculation of expected_downtime to take VFIO info\n> migration/qapi: Introduce system-wise \"remaining\" reports\n> migration/qapi: Update unit for avail-switchover-bandwidth\n> \n> docs/about/removed-features.rst | 2 +-\n> docs/devel/migration/main.rst | 9 +-\n> docs/devel/migration/vfio.rst | 9 +-\n> qapi/migration.json | 32 +++---\n> hw/vfio/vfio-migration-internal.h | 8 ++\n> include/migration/register.h | 59 ++++------\n> migration/migration-stats.h | 13 ++-\n> migration/migration.h | 10 +-\n> migration/savevm.h | 9 +-\n> hw/s390x/s390-stattrib.c | 9 +-\n> hw/vfio/migration.c | 92 +++++++++-------\n> migration/block-dirty-bitmap.c | 10 +-\n> migration/migration-hmp-cmds.c | 5 +\n> migration/migration.c | 172 +++++++++++++++++++++---------\n> migration/ram.c | 40 ++-----\n> migration/savevm.c | 73 +++++++------\n> hw/vfio/trace-events | 3 +-\n> migration/trace-events | 3 +-\n> 18 files changed, 313 insertions(+), 245 deletions(-)\n>","headers":{"Return-Path":"","X-Original-To":"incoming@patchwork.ozlabs.org","Delivered-To":"patchwork-incoming@legolas.ozlabs.org","Authentication-Results":["legolas.ozlabs.org;\n\tdkim=pass (1024-bit key;\n unprotected) header.d=redhat.com header.i=@redhat.com header.a=rsa-sha256\n header.s=mimecast20190719 header.b=SZOMLVJJ;\n\tdkim=pass (2048-bit key;\n unprotected) header.d=redhat.com header.i=@redhat.com header.a=rsa-sha256\n header.s=google header.b=DvApUaje;\n\tdkim-atps=neutral","legolas.ozlabs.org;\n spf=pass (sender SPF authorized) smtp.mailfrom=nongnu.org\n (client-ip=209.51.188.17; helo=lists1p.gnu.org;\n envelope-from=qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org;\n receiver=patchwork.ozlabs.org)"],"Received":["from lists1p.gnu.org (lists1p.gnu.org [209.51.188.17])\n\t(using TLSv1.2 with cipher ECDHE-ECDSA-AES256-GCM-SHA384 (256/256 bits))\n\t(No client certificate requested)\n\tby legolas.ozlabs.org (Postfix) with ESMTPS id 4fvXSQ2kX9z1xtJ\n\tfor ; Tue, 14 Apr 2026 02:10:27 +1000 (AEST)","from localhost ([::1] helo=lists1p.gnu.org)\n\tby lists1p.gnu.org with esmtp (Exim 4.90_1)\n\t(envelope-from )\n\tid 1wCJrK-0000wB-Gu; Mon, 13 Apr 2026 12:09:58 -0400","from eggs.gnu.org ([2001:470:142:3::10])\n by lists1p.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256)\n (Exim 4.90_1) (envelope-from ) id 1wCJqz-0000uV-JP\n for qemu-devel@nongnu.org; Mon, 13 Apr 2026 12:09:39 -0400","from us-smtp-delivery-124.mimecast.com ([170.10.133.124])\n by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256)\n (Exim 4.90_1) (envelope-from ) id 1wCJqp-0003da-Cm\n for qemu-devel@nongnu.org; Mon, 13 Apr 2026 12:09:29 -0400","from mail-wm1-f70.google.com (mail-wm1-f70.google.com\n [209.85.128.70]) by relay.mimecast.com with ESMTP with STARTTLS\n (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id\n us-mta-538-BdGCubX1P8aq5ot0r0H0Dw-1; Mon, 13 Apr 2026 12:09:19 -0400","by mail-wm1-f70.google.com with SMTP id\n 5b1f17b1804b1-488c82b4701so27755775e9.0\n for ; Mon, 13 Apr 2026 09:09:19 -0700 (PDT)","from ?IPV6:2a01:e0a:280:24f0:9db0:474c:ff43:9f5c?\n ([2a01:e0a:280:24f0:9db0:474c:ff43:9f5c])\n by smtp.gmail.com with ESMTPSA id\n 5b1f17b1804b1-488d532ef00sm345910925e9.5.2026.04.13.09.09.16\n (version=TLS1_3 cipher=TLS_AES_128_GCM_SHA256 bits=128/128);\n Mon, 13 Apr 2026 09:09:17 -0700 (PDT)"],"DKIM-Signature":["v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com;\n s=mimecast20190719; t=1776096562;\n h=from:from:reply-to:subject:subject:date:date:message-id:message-id:\n to:to:cc:cc:mime-version:mime-version:content-type:content-type:\n content-transfer-encoding:content-transfer-encoding:\n in-reply-to:in-reply-to:references:references:autocrypt:autocrypt;\n bh=XsHRlgIainPvA0VAWBxDYR7CbZ9e2tbHl18JznsYMZM=;\n b=SZOMLVJJUkOD1k0Q0K3hsa+aSUa6N+6fIDuZuzER7VpuGeFloazLyBKOnigZiiwL857az5\n FlI+M5XxPIb6nyjPBce/gXHPbzSheAe+jdy2YLTX9et4//Rb6AmulOWgle8BmsXSwmjoPm\n 0M+6xb45jSExUASUUxmDlTPjI/fx7dg=","v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=redhat.com; s=google; t=1776096558; x=1776701358; darn=nongnu.org;\n h=content-transfer-encoding:in-reply-to:autocrypt:from\n :content-language:references:cc:to:subject:user-agent:mime-version\n :date:message-id:from:to:cc:subject:date:message-id:reply-to;\n bh=XsHRlgIainPvA0VAWBxDYR7CbZ9e2tbHl18JznsYMZM=;\n b=DvApUajeJf3Il51oKQp/OCjiayRVFcJ1+yNzkXSfH1UeXWlUDsiCOS36fr8GliihKy\n hVTuuoJ68rxzqfGW0PyrWmDg2YD4g96ghnjSbR93Fyi/nlun3ieMa/PUfNgMmPljanLq\n 3GbpDUIDdP16LnzMHhKCusdKoQRhUABd0JVTEZOiMKcbjUSLd8FlZs6HWjFRxv3T2k3d\n TKarEJLXz9/o2R8CSVa4J9nojoIBfYT2zFoD3Fww5bF+FBNDkSTXvN0CHgG6jsNDiWY9\n QMGA8M7zjDzUDuMES6cynhCycRyyIGb22mgKkj/B61lpdYTsvGcwV8GC7qjI0TFkoQGd\n 5fiA=="],"X-MC-Unique":"BdGCubX1P8aq5ot0r0H0Dw-1","X-Mimecast-MFC-AGG-ID":"BdGCubX1P8aq5ot0r0H0Dw_1776096558","X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=1e100.net; s=20251104; t=1776096558; x=1776701358;\n h=content-transfer-encoding:in-reply-to:autocrypt:from\n :content-language:references:cc:to:subject:user-agent:mime-version\n :date:message-id:x-gm-gg:x-gm-message-state:from:to:cc:subject:date\n :message-id:reply-to;\n bh=XsHRlgIainPvA0VAWBxDYR7CbZ9e2tbHl18JznsYMZM=;\n b=SDfCUWp8m1Hx5zr5CLKR5uwRstCO4LkUTywIYoHHTfB1pJ0Mv9bgWb69Dn3RPeUUp5\n Gh8TPzNCLGNKOJuQi78dqIkhHRRn91ClFIfCcjox1AhMu9c/wi2SGnp4qSzUPoLnuqCQ\n RmKTzo0VoHZlPucns6AFLUKgoltZmS6eq1FYYPsqg35UPhePkM4OZ5+fx6OYcJuXVfVF\n N+706rmyNM+qOgVgfn8mnp4V4f1I//LseLstib+adwe6bZqqq0JRKn7rKXmaDsxEXlqM\n 319/VnT/GLdnL5TtCM8aWikm3Ng9x1Qsnm9AEDguZsrdi2s2lZAtXm2XPIFBnJdXHvCF\n DMJw==","X-Forwarded-Encrypted":"i=1;\n AFNElJ+wAc99EVm0S0YLJb8//514FfaeSaHTXoD4RqJ/vqKhaAaEQbcAVSR1YsM88QGD8qZg20dC7bc8pCkg@nongnu.org","X-Gm-Message-State":"AOJu0Yy11LuYHCzi1V84w2es3NtUkdX2ejw8LsB4VVb7f9oOUcWZy6EQ\n mm25LkXh51cU/bhoboGJQiAiAaoVNPF2gYfEmVI/LWcwMzuXncQhlNm+zV5VG6wFUQyzND5WlI2\n cWhHDRED/PfzkTV9aiWC6CPsj0x0DMstoUmB/9mKQ6Rts0sQTYEw+t/+N","X-Gm-Gg":"AeBDieuVCCCViKrUVtWsPm3Mz6pgYblsn9+WahYBoMaywez0hNa9wJ/8uzYHoBAe8qo\n qprcGr5g+XMAmgOEDeqF5vWSTPr6kJDy825EP24QKehB9NOxvW15LiTngXN+iHdopehwm/ddH52\n gf+oDk+MiJwZdlmxivtsmGIjmFeQ6NMhIrXVbTwfz2pMexoKlKK0ls2xhsdKq9veWsiWxyPDFpn\n cRT2oxbpnZ5V0vEAUYvYFQpek6hfAKAte3xcx+adJFVAPN8bf5vsI8D+wtBj0IcS9x1VcQ+3rNg\n N6ND7firC2pmx10vyDSNH5/YuLpN/S0iu4NLIAbYCLjcrJQ9iQG2SBURkwAlp/VUkJSiwhg+0eo\n yCSLpO11tFQF5V5g9vUsALLRiOzE0ZgZ4SJxf5E5PUpWQLqinan3TxHh6Uv4q","X-Received":["by 2002:a05:600c:8717:b0:477:9890:9ab8 with SMTP id\n 5b1f17b1804b1-488d6816f5amr192575395e9.3.1776096558236;\n Mon, 13 Apr 2026 09:09:18 -0700 (PDT)","by 2002:a05:600c:8717:b0:477:9890:9ab8 with SMTP id\n 5b1f17b1804b1-488d6816f5amr192574685e9.3.1776096557681;\n Mon, 13 Apr 2026 09:09:17 -0700 (PDT)"],"Message-ID":"<8c51c77e-b496-4e99-a35c-364d224d1b3c@redhat.com>","Date":"Mon, 13 Apr 2026 18:09:15 +0200","MIME-Version":"1.0","User-Agent":"Mozilla Thunderbird","Subject":"Re: [PATCH 00/14] migration/vfio: Fix a few issues on API misuse or\n statistic reports","To":"Peter Xu , qemu-devel@nongnu.org","Cc":"\"Maciej S . Szmigiero\" , =?utf-8?q?Daniel_P_?=\n\t=?utf-8?q?=2E_Berrang=C3=A9?= ,\n Zhiyi Guo , Juraj Marcin ,\n Prasad Pandit , Avihai Horon ,\n Kirti Wankhede , Fabiano Rosas ,\n Joao Martins ,\n Markus Armbruster , Alex Williamson ","References":"<20260408165559.157108-1-peterx@redhat.com>","Content-Language":"en-US, fr","From":"=?utf-8?q?C=C3=A9dric_Le_Goater?= ","Autocrypt":"addr=clg@redhat.com; keydata=\n xsFNBFu8o3UBEADP+oJVJaWm5vzZa/iLgpBAuzxSmNYhURZH+guITvSySk30YWfLYGBWQgeo\n 8NzNXBY3cH7JX3/a0jzmhDc0U61qFxVgrPqs1PQOjp7yRSFuDAnjtRqNvWkvlnRWLFq4+U5t\n yzYe4SFMjFb6Oc0xkQmaK2flmiJNnnxPttYwKBPd98WfXMmjwAv7QfwW+OL3VlTPADgzkcqj\n 53bfZ4VblAQrq6Ctbtu7JuUGAxSIL3XqeQlAwwLTfFGrmpY7MroE7n9Rl+hy/kuIrb/TO8n0\n ZxYXvvhT7OmRKvbYuc5Jze6o7op/bJHlufY+AquYQ4dPxjPPVUT/DLiUYJ3oVBWFYNbzfOrV\n RxEwNuRbycttMiZWxgflsQoHF06q/2l4ttS3zsV4TDZudMq0TbCH/uJFPFsbHUN91qwwaN/+\n gy1j7o6aWMz+Ib3O9dK2M/j/O/Ube95mdCqN4N/uSnDlca3YDEWrV9jO1mUS/ndOkjxa34ia\n 70FjwiSQAsyIwqbRO3CGmiOJqDa9qNvd2TJgAaS2WCw/TlBALjVQ7AyoPEoBPj31K74Wc4GS\n Rm+FSch32ei61yFu6ACdZ12i5Edt+To+hkElzjt6db/UgRUeKfzlMB7PodK7o8NBD8outJGS\n tsL2GRX24QvvBuusJdMiLGpNz3uqyqwzC5w0Fd34E6G94806fwARAQABzSJDw6lkcmljIExl\n IEdvYXRlciA8Y2xnQHJlZGhhdC5jb20+wsGRBBMBCAA7FiEEoPZlSPBIlev+awtgUaNDx8/7\n 7KEFAmTLlVECGwMFCwkIBwICIgIGFQoJCAsCBBYCAwECHgcCF4AACgkQUaNDx8/77KG0eg//\n S0zIzTcxkrwJ/9XgdcvVTnXLVF9V4/tZPfB7sCp8rpDCEseU6O0TkOVFoGWM39sEMiQBSvyY\n lHrP7p7E/JYQNNLh441MfaX8RJ5Ul3btluLapm8oHp/vbHKV2IhLcpNCfAqaQKdfk8yazYhh\n EdxTBlzxPcu+78uE5fF4wusmtutK0JG0sAgq0mHFZX7qKG6LIbdLdaQalZ8CCFMKUhLptW71\n xe+aNrn7hScBoOj2kTDRgf9CE7svmjGToJzUxgeh9mIkxAxTu7XU+8lmL28j2L5uNuDOq9vl\n hM30OT+pfHmyPLtLK8+GXfFDxjea5hZLF+2yolE/ATQFt9AmOmXC+YayrcO2ZvdnKExZS1o8\n VUKpZgRnkwMUUReaF/mTauRQGLuS4lDcI4DrARPyLGNbvYlpmJWnGRWCDguQ/LBPpbG7djoy\n k3NlvoeA757c4DgCzggViqLm0Bae320qEc6z9o0X0ePqSU2f7vcuWN49Uhox5kM5L86DzjEQ\n RHXndoJkeL8LmHx8DM+kx4aZt0zVfCHwmKTkSTQoAQakLpLte7tWXIio9ZKhUGPv/eHxXEoS\n 0rOOAZ6np1U/xNR82QbF9qr9TrTVI3GtVe7Vxmff+qoSAxJiZQCo5kt0YlWwti2fFI4xvkOi\n V7lyhOA3+/3oRKpZYQ86Frlo61HU3r6d9wzOwU0EW7yjdQEQALyDNNMw/08/fsyWEWjfqVhW\n pOOrX2h+z4q0lOHkjxi/FRIRLfXeZjFfNQNLSoL8j1y2rQOs1j1g+NV3K5hrZYYcMs0xhmrZ\n KXAHjjDx7FW3sG3jcGjFW5Xk4olTrZwFsZVUcP8XZlArLmkAX3UyrrXEWPSBJCXxDIW1hzwp\n bV/nVbo/K9XBptT/wPd+RPiOTIIRptjypGY+S23HYBDND3mtfTz/uY0Jytaio9GETj+fFis6\n TxFjjbZNUxKpwftu/4RimZ7qL+uM1rG1lLWc9SPtFxRQ8uLvLOUFB1AqHixBcx7LIXSKZEFU\n CSLB2AE4wXQkJbApye48qnZ09zc929df5gU6hjgqV9Gk1rIfHxvTsYltA1jWalySEScmr0iS\n YBZjw8Nbd7SxeomAxzBv2l1Fk8fPzR7M616dtb3Z3HLjyvwAwxtfGD7VnvINPbzyibbe9c6g\n LxYCr23c2Ry0UfFXh6UKD83d5ybqnXrEJ5n/t1+TLGCYGzF2erVYGkQrReJe8Mld3iGVldB7\n JhuAU1+d88NS3aBpNF6TbGXqlXGF6Yua6n1cOY2Yb4lO/mDKgjXd3aviqlwVlodC8AwI0Sdu\n jWryzL5/AGEU2sIDQCHuv1QgzmKwhE58d475KdVX/3Vt5I9kTXpvEpfW18TjlFkdHGESM/Jx\n IqVsqvhAJkalABEBAAHCwV8EGAECAAkFAlu8o3UCGwwACgkQUaNDx8/77KEhwg//WqVopd5k\n 8hQb9VVdk6RQOCTfo6wHhEqgjbXQGlaxKHoXywEQBi8eULbeMQf5l4+tHJWBxswQ93IHBQjK\n yKyNr4FXseUI5O20XVNYDJZUrhA4yn0e/Af0IX25d94HXQ5sMTWr1qlSK6Zu79lbH3R57w9j\n hQm9emQEp785ui3A5U2Lqp6nWYWXz0eUZ0Tad2zC71Gg9VazU9MXyWn749s0nXbVLcLS0yop\n s302Gf3ZmtgfXTX/W+M25hiVRRKCH88yr6it+OMJBUndQVAA/fE9hYom6t/zqA248j0QAV/p\n LHH3hSirE1mv+7jpQnhMvatrwUpeXrOiEw1nHzWCqOJUZ4SY+HmGFW0YirWV2mYKoaGO2YBU\n wYF7O9TI3GEEgRMBIRT98fHa0NPwtlTktVISl73LpgVscdW8yg9Gc82oe8FzU1uHjU8b10lU\n XOMHpqDDEV9//r4ZhkKZ9C4O+YZcTFu+mvAY3GlqivBNkmYsHYSlFsbxc37E1HpTEaSWsGfA\n HQoPn9qrDJgsgcbBVc1gkUT6hnxShKPp4PlsZVMNjvPAnr5TEBgHkk54HQRhhwcYv1T2QumQ\n izDiU6iOrUzBThaMhZO3i927SG2DwWDVzZltKrCMD1aMPvb3NU8FOYRhNmIFR3fcalYr+9gD\n uVKe8BVz4atMOoktmt0GWTOC8P4=","In-Reply-To":"<20260408165559.157108-1-peterx@redhat.com>","Content-Type":"text/plain; charset=UTF-8; format=flowed","Content-Transfer-Encoding":"8bit","Received-SPF":"pass client-ip=170.10.133.124; envelope-from=clg@redhat.com;\n helo=us-smtp-delivery-124.mimecast.com","X-Spam_score_int":"-25","X-Spam_score":"-2.6","X-Spam_bar":"--","X-Spam_report":"(-2.6 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.54,\n DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1,\n RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H2=0.001,\n RCVD_IN_VALIDITY_RPBL_BLOCKED=0.001, RCVD_IN_VALIDITY_SAFE_BLOCKED=0.001,\n SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=ham autolearn_force=no","X-Spam_action":"no action","X-BeenThere":"qemu-devel@nongnu.org","X-Mailman-Version":"2.1.29","Precedence":"list","List-Id":"qemu development ","List-Unsubscribe":",\n ","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n ","Errors-To":"qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org","Sender":"qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org"}}]