[{"id":3680783,"web_url":"http://patchwork.ozlabs.org/comment/3680783/","msgid":"","list_archive_url":null,"date":"2026-04-22T18:19:14","subject":"ACK: [SRU][N][PATCH 0/1] Revert \"iommu: disable SVA when CONFIG_X86\n is set\"","submitter":{"id":89903,"url":"http://patchwork.ozlabs.org/api/people/89903/","name":"Tim Whisonant","email":"tim.whisonant@canonical.com"},"content":"On Wed, Apr 22, 2026 at 09:06:15PM +0300, Mehmet Basaran wrote:\n> BugLink: https://bugs.launchpad.net/bugs/2149766\n> \n> [Impact]\n> \n> The issue has been brought to our attention when questing (6.17)\n> kernels were unable to load amd_xdna drivers. However, this commit,\n> in addition to NPUs, also affects PCIe cards which make use of\n> unified memory (GPUs, Accelerators, NICs). With this commit, PCIe\n> devices will revert to using legacy method (pinning) instead of\n> unified memory. As a result,\n> - arguably it will be less secure,\n> - there can be performance drops.\n> \n> Currently, this commit is part of an 8 commit patch series:\n> \"Fix stale IOTLB entries for kernel address space\", v7.\n> [PATCH v7 1/8] iommu: Disable SVA when CONFIG_X86 is set\n> [PATCH v7 2/8] mm: Add a ptdesc flag to mark kernel page tables\n> [PATCH v7 3/8] mm: Actually mark kernel page table pages\n> [PATCH v7 4/8] x86/mm: Use 'ptdesc' when freeing PMD pages\n> [PATCH v7 5/8] mm: Introduce pure page table freeing function\n> [PATCH v7 6/8] x86/mm: Use pagetable_free()\n> [PATCH v7 7/8] mm: Introduce deferred freeing for kernel page tables\n> [PATCH v7 8/8] iommu/sva: Invalidate stale IOTLB entries for kernel address space\n> \n> where \"iommu: disable SVA when CONFIG_X86 is set\" is undone by\n> the 8th commit. We only have this commit from the whole patchset.\n> Ideally we should have the whole patchset applied.\n> \n> [Fix]\n> \n> This commit fixes the following issue which is old,\n> 26b25a2b98e4 (\"iommu: Bind process address spaces to devices\")\n> and we applied this commit recently. So, reverting this commit\n> won't be introducing regressions. Affected kernel versions are:\n> - 6.8 due to the reasons above.\n> - 6.17 due to both the reasons above and the amd_xdna issue.\n> \n> [Test Plan]\n> \n> Our regression test suite doesn't catch this issue. However,\n> we will run it again to see it doesn't cause anything else.\n> \n> [Where problems could occur]\n> \n> Reverted commit is a fix for a security vulnerability related to\n> IOMMU Shared Virtual Addressing (SVA). In an SVA context, an \n> IOMMU can cache kernel page table entries. When a kernel page \n> table page is freed and reallocated for another purpose, the \n> IOMMU might still hold stale, incorrect entries. This can be \n> exploited to cause a use-after-free or write-after-free condition,\n> potentially leading to privilege escalation or data corruption.\n> \n> Mehmet Basaran (1):\n> Revert \"iommu: disable SVA when CONFIG_X86 is set\"\n> \n> drivers/iommu/iommu-sva.c | 3 ---\n> 1 file changed, 3 deletions(-)\n> \n> -- \n> 2.43.0\n> \n\nAcked-by: Tim Whisonant ","headers":{"Return-Path":"","X-Original-To":"incoming@patchwork.ozlabs.org","Delivered-To":"patchwork-incoming@legolas.ozlabs.org","Authentication-Results":["legolas.ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (4096-bit key;\n unprotected) header.d=canonical.com header.i=@canonical.com\n header.a=rsa-sha256 header.s=20251003 header.b=hHajlJKP;\n\tdkim-atps=neutral","legolas.ozlabs.org;\n spf=pass (sender SPF authorized) smtp.mailfrom=lists.ubuntu.com\n (client-ip=185.125.189.65; helo=lists.ubuntu.com;\n envelope-from=kernel-team-bounces@lists.ubuntu.com;\n receiver=patchwork.ozlabs.org)"],"Received":["from lists.ubuntu.com (lists.ubuntu.com [185.125.189.65])\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 4g16v566Gtz1yD5\n\tfor ; Thu, 23 Apr 2026 04:19:29 +1000 (AEST)","from localhost ([127.0.0.1] helo=lists.ubuntu.com)\n\tby lists.ubuntu.com with esmtp (Exim 4.86_2)\n\t(envelope-from )\n\tid 1wFcAS-0001C2-RV; Wed, 22 Apr 2026 18:19:20 +0000","from smtp-relay-internal-1.internal ([10.131.114.114]\n helo=smtp-relay-internal-1.canonical.com)\n by lists.ubuntu.com with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128)\n (Exim 4.86_2) (envelope-from )\n id 1wFcAR-0001BT-HP\n for kernel-team@lists.ubuntu.com; Wed, 22 Apr 2026 18:19:19 +0000","from mail-ot1-f72.google.com (mail-ot1-f72.google.com\n [209.85.210.72])\n (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)\n key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest\n SHA256)\n (No client certificate requested)\n by smtp-relay-internal-1.canonical.com (Postfix) with ESMTPS id 48DB13F206\n for ; Wed, 22 Apr 2026 18:19:19 +0000 (UTC)","by mail-ot1-f72.google.com with SMTP id\n 46e09a7af769-7de44ba64e7so466260a34.1\n for ; Wed, 22 Apr 2026 11:19:19 -0700 (PDT)","from localhost (104-6-108-11.lightspeed.frokca.sbcglobal.net.\n [104.6.108.11]) by smtp.gmail.com with ESMTPSA id\n 46e09a7af769-7dcc892c515sm7677129a34.21.2026.04.22.11.19.15\n for \n (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256);\n Wed, 22 Apr 2026 11:19:16 -0700 (PDT)"],"DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed; d=canonical.com;\n s=20251003; t=1776881959;\n bh=H8ipR1pYd3A0l/bQ/6/ZPalrvvHSBrMqaiD9WPxis4U=;\n h=Date:From:To:Subject:Message-ID:References:MIME-Version:\n Content-Type:In-Reply-To;\n b=hHajlJKPgMHmwYmiABqb4hyfqqd5y8UMkDJP4IiJ9IYptWpfmxhPs724eWdWSFxOq\n U4vBBj/rJj8OJvcvzDFMhiLj93v9tTQHCFjmb370CPB+7ssrf6tWrQnEPcq5yfpOZM\n SBJNkCyat2Bv2fSLicZEm+YtH6hP6w7hhMP02D4fgDeBZHJeoidCqx5mZBM4o4JUjL\n VlW7+1RsIkOyDuS026uWXlvIkGt1FdjKFRTFoHAq4T2pxAoIYcFPJ/M1nuTRU2oX2E\n vgqPD6ymn5eqJIrXHxfVl3xwtldI4B9fpTLyLeAYpFfiDDymYK9gMj4FZlw4we5JRG\n yCfSJ9EI7XKozfaswGwnHTBh4BB2lWkt2Bv0G761wGaGGzJPzcUdUNV+KszHgmlOw/\n s7rdN8oMgV2mzm4ZImjS3cn1QP838gSs+ykhjRhwnFa1pt/4zh3+87W3FduRiR7+Qh\n 1hWz7bGXsYoii07JSNLu7FZQXGn301a0YB7UUN1TpOqgvGllyWSNAqQzFSVu4nc6kY\n dEKL3sUnKpN0q5FNOHewOKZMqEQnXUiVZSqLa5ul+35jqXbeOimdt3GDn8lBRCjq6p\n duEvoGh0oi65u/vPg6nziHRIEM5Dme7aE18W8XurcHH+dvYtv00AVeEHJ2/YGRxsL+\n s+hgmXH0/MsshKLFQtc3NJrk=","X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=1e100.net; s=20251104; t=1776881957; x=1777486757;\n h=in-reply-to:content-disposition:mime-version:references:message-id\n :subject:to:from:date:x-gm-gg:x-gm-message-state:from:to:cc:subject\n :date:message-id:reply-to;\n bh=H8ipR1pYd3A0l/bQ/6/ZPalrvvHSBrMqaiD9WPxis4U=;\n b=XJ5izPi7sxj7M3gjxE/u4WDLsGqZJCMBUUFIn/lLWARUQiNhp6uJfze6sxOhs5GvgF\n sdu1j5RcDwJk80iG97eBKIEeZACWzaON8OP1pi/zXKxWH/TloAhcyl48N/0ZQScgHboz\n wF2z4Rd/mc4BwKWH00fCRd42LK5+KNwdO6TBdPmcp/eSAjzxpD+MEN+uMUJqK49Bfd8n\n YyTXWFLP4XtrQOpSCAuQ37pOa4ryR/MkcGUeRHxCXq47hMPV5wPrF9a/5rKrDIZtMKh7\n ULRbTceBvbovC1kwk/dUMOz82ynfARQ2OhF2hOk9B5Km00kFF2j5un/rB/QNjgXtgdqw\n zSeA==","X-Gm-Message-State":"AOJu0YzC4UGMee1uCJ5sj+7zpV2pNVbwFb6F8UESETaMi+WogWJS/iFE\n 47LsBy/i+3d+ze2eGuvgcI/dCPD5617rZmn7EK4z6ncaGqIY3mGz4cDIN2MXZjEI0im/PJcpU2Z\n xSLIECcYFwnA1itFkyehtZzu98Uwz6gsxLExv0iLHb0Ubm1cixzGq+6mwecCAk4u8YU9rGatAr7\n 8g/Q5AIMhXqIdG4w==","X-Gm-Gg":"AeBDietJwtuHUdxYz9v4RGBR3vpWUAUxGp53fpHJpFLxQI6odhsLic0tdsZlG0m3tRL\n W6mb1ktD9b0A0cURg4ojpW0xT2/VJxTFwGS6vokzg308zRkDjGpvEHhBNYWLtsCSr0d3IF67x75\n 9hmb4k2iccwWlaBr05xruUnhRKySyAS1gvv7DvoR1lMHnq0pcf4yfkdxK5MHQiarjl0KK8TF8Tn\n 1A/9GEw4f4jF7crZWvdWHBV5Ib1sNTCoKEG8TUT13+ws0F8A1Z2AiDYNcu8U+roB1i+bpWB4wki\n C5kNFNbHaRdjKSwYT1LDqCyVrViLnfp6RC1kzA+uYcNDKgciGtR3J/UNkXjTJeQ3icAA37t79mI\n Pl3vGGikDi/YBpfP68u9OHlWZQ4e1QKhzPz0UrOd4c5z+CvaoCQ58N7LsfjarZKX/siegyixJhf\n 76leQTB7P8/fxB","X-Received":["by 2002:a05:6830:3154:b0:7dc:da06:c0f0 with SMTP id\n 46e09a7af769-7dcda06d028mr5663000a34.4.1776881957197;\n Wed, 22 Apr 2026 11:19:17 -0700 (PDT)","by 2002:a05:6830:3154:b0:7dc:da06:c0f0 with SMTP id\n 46e09a7af769-7dcda06d028mr5662982a34.4.1776881956747;\n Wed, 22 Apr 2026 11:19:16 -0700 (PDT)"],"Date":"Wed, 22 Apr 2026 11:19:14 -0700","From":"Tim Whisonant ","To":"kernel-team@lists.ubuntu.com","Subject":"ACK: [SRU][N][PATCH 0/1] Revert \"iommu: disable SVA when CONFIG_X86\n is set\"","Message-ID":"","References":"<20260422180616.336474-1-mehmet.basaran@canonical.com>","MIME-Version":"1.0","Content-Disposition":"inline","In-Reply-To":"<20260422180616.336474-1-mehmet.basaran@canonical.com>","X-BeenThere":"kernel-team@lists.ubuntu.com","X-Mailman-Version":"2.1.20","Precedence":"list","List-Id":"Kernel team discussions ","List-Unsubscribe":",\n ","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n ","Content-Type":"text/plain; charset=\"utf-8\"","Content-Transfer-Encoding":"base64","Errors-To":"kernel-team-bounces@lists.ubuntu.com","Sender":"\"kernel-team\" "}},{"id":3680813,"web_url":"http://patchwork.ozlabs.org/comment/3680813/","msgid":"","list_archive_url":null,"date":"2026-04-22T18:38:27","subject":"ACK: [SRU][N][PATCH 0/1] Revert \"iommu: disable SVA when CONFIG_X86\n is set\"","submitter":{"id":91410,"url":"http://patchwork.ozlabs.org/api/people/91410/","name":"Alice C. Munduruca","email":"alice.munduruca@canonical.com"},"content":"On Wed Apr 22, 2026 at 2:06 PM EDT, Mehmet Basaran wrote:\n> BugLink: https://bugs.launchpad.net/bugs/2149766\n>\n> [Impact]\n> \n> The issue has been brought to our attention when questing (6.17)\n> kernels were unable to load amd_xdna drivers. However, this commit,\n> in addition to NPUs, also affects PCIe cards which make use of\n> unified memory (GPUs, Accelerators, NICs). With this commit, PCIe\n> devices will revert to using legacy method (pinning) instead of\n> unified memory. As a result,\n> - arguably it will be less secure,\n> - there can be performance drops.\n>\n> Currently, this commit is part of an 8 commit patch series:\n> \"Fix stale IOTLB entries for kernel address space\", v7.\n> [PATCH v7 1/8] iommu: Disable SVA when CONFIG_X86 is set\n> [PATCH v7 2/8] mm: Add a ptdesc flag to mark kernel page tables\n> [PATCH v7 3/8] mm: Actually mark kernel page table pages\n> [PATCH v7 4/8] x86/mm: Use 'ptdesc' when freeing PMD pages\n> [PATCH v7 5/8] mm: Introduce pure page table freeing function\n> [PATCH v7 6/8] x86/mm: Use pagetable_free()\n> [PATCH v7 7/8] mm: Introduce deferred freeing for kernel page tables\n> [PATCH v7 8/8] iommu/sva: Invalidate stale IOTLB entries for kernel address space\n>\n> where \"iommu: disable SVA when CONFIG_X86 is set\" is undone by\n> the 8th commit. We only have this commit from the whole patchset.\n> Ideally we should have the whole patchset applied.\n>\n> [Fix]\n>\n> This commit fixes the following issue which is old,\n> 26b25a2b98e4 (\"iommu: Bind process address spaces to devices\")\n> and we applied this commit recently. So, reverting this commit\n> won't be introducing regressions. Affected kernel versions are:\n> - 6.8 due to the reasons above.\n> - 6.17 due to both the reasons above and the amd_xdna issue.\n>\n> [Test Plan]\n>\n> Our regression test suite doesn't catch this issue. However,\n> we will run it again to see it doesn't cause anything else.\n>\n> [Where problems could occur]\n>\n> Reverted commit is a fix for a security vulnerability related to\n> IOMMU Shared Virtual Addressing (SVA). In an SVA context, an \n> IOMMU can cache kernel page table entries. When a kernel page \n> table page is freed and reallocated for another purpose, the \n> IOMMU might still hold stale, incorrect entries. This can be \n> exploited to cause a use-after-free or write-after-free condition,\n> potentially leading to privilege escalation or data corruption.\n>\n> Mehmet Basaran (1):\n> Revert \"iommu: disable SVA when CONFIG_X86 is set\"\n>\n> drivers/iommu/iommu-sva.c | 3 ---\n> 1 file changed, 3 deletions(-)\n\nAcked-by: Alice C. Munduruca ","headers":{"Return-Path":"","X-Original-To":"incoming@patchwork.ozlabs.org","Delivered-To":"patchwork-incoming@legolas.ozlabs.org","Authentication-Results":["legolas.ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (4096-bit key;\n unprotected) header.d=canonical.com header.i=@canonical.com\n header.a=rsa-sha256 header.s=20251003 header.b=JSUH65aj;\n\tdkim-atps=neutral","legolas.ozlabs.org;\n spf=pass (sender SPF authorized) smtp.mailfrom=lists.ubuntu.com\n (client-ip=185.125.189.65; helo=lists.ubuntu.com;\n envelope-from=kernel-team-bounces@lists.ubuntu.com;\n receiver=patchwork.ozlabs.org)"],"Received":["from lists.ubuntu.com (lists.ubuntu.com [185.125.189.65])\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 4g17KM0sqJz1y2d\n\tfor ; Thu, 23 Apr 2026 04:38:47 +1000 (AEST)","from localhost ([127.0.0.1] helo=lists.ubuntu.com)\n\tby lists.ubuntu.com with esmtp (Exim 4.86_2)\n\t(envelope-from )\n\tid 1wFcTB-0001nr-8s; Wed, 22 Apr 2026 18:38:41 +0000","from smtp-relay-internal-0.internal ([10.131.114.225]\n helo=smtp-relay-internal-0.canonical.com)\n by lists.ubuntu.com with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128)\n (Exim 4.86_2) (envelope-from )\n id 1wFcTA-0001nH-Ms\n for kernel-team@lists.ubuntu.com; Wed, 22 Apr 2026 18:38:40 +0000","from mail-qv1-f72.google.com (mail-qv1-f72.google.com\n [209.85.219.72])\n (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)\n key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest\n SHA256)\n (No client certificate requested)\n by smtp-relay-internal-0.canonical.com (Postfix) with ESMTPS id 872BF3F2A0\n for ; Wed, 22 Apr 2026 18:38:40 +0000 (UTC)","by mail-qv1-f72.google.com with SMTP id\n 6a1803df08f44-8a3bc7f5d43so132692036d6.2\n for ; Wed, 22 Apr 2026 11:38:40 -0700 (PDT)","from localhost ([69.157.253.239]) by smtp.gmail.com with ESMTPSA id\n 6a1803df08f44-8b02ac77546sm129876726d6.17.2026.04.22.11.38.38\n (version=TLS1_3 cipher=TLS_AES_128_GCM_SHA256 bits=128/128);\n Wed, 22 Apr 2026 11:38:38 -0700 (PDT)"],"DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed; d=canonical.com;\n s=20251003; t=1776883120;\n bh=5YcEQxk410mgqXZAVTeDh8WqNTjBLZppFSRm3fPpM6w=;\n h=Mime-Version:Content-Type:Date:Message-Id:Subject:From:To:\n References:In-Reply-To;\n b=JSUH65ajCbyukT9nSRlQoUjm0GbTzzym0iwpJcp1gl8HnbN6TIzkqyGhdH49Z9f7a\n NZNwOx22pBaFt5tr8xl77NTKVEeTcdc95ucnXjiEX45OOD6f2npEUMpTCQsuYhAUrY\n D4CMGrdw0PHzjkMQKXKkAo+h6I1GF01OKWWye9fJ661WRJynNYqOwl8q1EJli670MT\n FmWgTgWcjAZGdqj4fhOucl9K9BRlh2NUOJPPClp+QpAIn4Qw/aKvxPoVTiGv3mQFca\n YvLBEV+8U8K52dQ1F66cjuz5FU9w0xnsnXWa0yfU6uWGDw/OA0BoUB6S6xQ84qKCuJ\n LUgKUG22ZYGcBzQPyWfvuwvHUTZzcDAiA3NxGmeovgCeV2lVa8h0c8pq4uf8elHTLd\n TWyRkwPeaS+rnples3Xs6W2fJgq3eSsSXJbwQ0gzWtqGkSI4D+5AYuJ8ei11Ksy5GS\n viCTTImziWBMX6izSg7+XR51I2J0OvG1qB6PNcMudvly/F6UOASXdwysOCh0gMTaEA\n V7wQjPadul1XU2O5gNVd1ck7IXJIeDmVzdar8ZZwESBIFhSvtgerPwVjTHI/fk6pY/\n GnDbtZ0wkES/DfFlg6WR2tTqlfpW9Cwdq6lQtBl6goc1w0Q3pOPN5xSlB4XrL6OsKF\n 7OmTFbiEHTjq/240jbHJEYYI=","X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=1e100.net; s=20251104; t=1776883119; x=1777487919;\n h=in-reply-to:references:to:from:subject:message-id:date\n :content-transfer-encoding:mime-version:x-gm-gg:x-gm-message-state\n :from:to:cc:subject:date:message-id:reply-to;\n bh=5YcEQxk410mgqXZAVTeDh8WqNTjBLZppFSRm3fPpM6w=;\n b=sJ7c8sJfgjie0357ls4nYAiIlhbtkIffa4BuHEaYwAoDo/f0STJxTIWZ83G/JPNdwO\n vqo/yJFGx9noV5GoXif+4N2t8NzRqOxGIe3DYmIWttYUQ0596/Nd0V/+qgkRbpn//P8C\n Ftrw11xGZO55LeAFnZmNrolTuUvvyXM+Xv47j+1N23+zfpQJl72Xhiympc+WwUHuPTNN\n HEw+ZUS3e29h3HjA2QdLBU/VBUOihMB2OTslELFpaRWs+p1RlwlCgB+1MDdnsTeMCE0p\n EOQazrnWX98MebZA8NvUhlbkYMOEq8BtrcrD4d7Kb5K6xAMfmYlb4HMCzKDao0zl892d\n 1W/g==","X-Forwarded-Encrypted":"i=1;\n AFNElJ/yVv2rJl/wl6KmSMm2kqNhfdjTBMZa+gI5M07Ub/rUZy7zr3or222qWZlZyuEZTewXh3wEG0Ey2obHJg==@lists.ubuntu.com","X-Gm-Message-State":"AOJu0YxBssCrAg5l0cpLTzsPuvmXJLgL3CEYFmoMayUz5H0fV73cNVmc\n Q0qZMpTnTBso4Kp6F8TNd6ECrf/PBHSXQvHSzH3/dN7b8j6Oc26r6qJCJiUsilWAM2aDGgk5hLV\n BF7sPtz0gm0REouqY2yKHH66fDHE0Ypu0vhE31d9EapzFBtrH9Avh3+e8YSLsN0VhI/1OGDLHmZ\n 1s/+yGByo3IUV/jQ==","X-Gm-Gg":"AeBDieunkidKzFdT3ibcwHh4mbfsRZJg2VwN7C+MdWJytM8O825lKjFEeEdNQ+qLUYN\n Acu1jSvN2flh/87+CaBlSGhfUUTn1lYAfzaE8i2TgG8ByQFcrVoTIXINRAZyuWYvK1xMt92Gfgf\n Fu9lO0Pne5LPC9PJnYSQG5t5Qwm9b1/MoacCjtujGE4TDsFZMIB0FeaJS0bB6C8anzXRwX4nw2a\n AD3pz6URz1ek1pV83ILOGcs1QGMXtJ+Ew+P2wMvjLjLvL4w+S0ddZAmRHE6d/pZnWmXdq21fx2Y\n otJdQFIIXmT7n+pMHt3pVNtKNP1zd3TUdVduzHO/Wh6lz9mr+pSIB06mrjdV7WL++PANozBkW/L\n w9+2EMMcsAhDengqN2zbk9UR7gF8HdzvHnNcMpQzIXfs=","X-Received":["by 2002:a05:6214:2024:b0:89c:8671:10a with SMTP id\n 6a1803df08f44-8b027e833d2mr365866156d6.0.1776883119292;\n Wed, 22 Apr 2026 11:38:39 -0700 (PDT)","by 2002:a05:6214:2024:b0:89c:8671:10a with SMTP id\n 6a1803df08f44-8b027e833d2mr365865766d6.0.1776883118888;\n Wed, 22 Apr 2026 11:38:38 -0700 (PDT)"],"Mime-Version":"1.0","Date":"Wed, 22 Apr 2026 14:38:27 -0400","Message-Id":"","Subject":"ACK: [SRU][N][PATCH 0/1] Revert \"iommu: disable SVA when CONFIG_X86\n is set\"","From":"\"Alice C. Munduruca\" ","To":"\"Mehmet Basaran\" ,\n ","X-Mailer":"aerc 0.21.0","References":"<20260422180616.336474-1-mehmet.basaran@canonical.com>","In-Reply-To":"<20260422180616.336474-1-mehmet.basaran@canonical.com>","X-BeenThere":"kernel-team@lists.ubuntu.com","X-Mailman-Version":"2.1.20","Precedence":"list","List-Id":"Kernel team discussions ","List-Unsubscribe":",\n ","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n ","Content-Type":"text/plain; charset=\"utf-8\"","Content-Transfer-Encoding":"base64","Errors-To":"kernel-team-bounces@lists.ubuntu.com","Sender":"\"kernel-team\" "}},{"id":3680918,"web_url":"http://patchwork.ozlabs.org/comment/3680918/","msgid":"<87zf2urdoo.fsf@gmail.com>","list_archive_url":null,"date":"2026-04-22T19:35:19","subject":"APPLIED: [SRU][N][PATCH 0/1] Revert \"iommu: disable SVA when\n CONFIG_X86 is set\"","submitter":{"id":89305,"url":"http://patchwork.ozlabs.org/api/people/89305/","name":"Mehmet Basaran","email":"mehmet.basaran@canonical.com"},"content":"Applied to noble:linux master-next branch. Thanks.\nMehmet Basaran writes:\n\n> BugLink: https://bugs.launchpad.net/bugs/2149766\n>\n> [Impact]\n> \n> The issue has been brought to our attention when questing (6.17)\n> kernels were unable to load amd_xdna drivers. However, this commit,\n> in addition to NPUs, also affects PCIe cards which make use of\n> unified memory (GPUs, Accelerators, NICs). With this commit, PCIe\n> devices will revert to using legacy method (pinning) instead of\n> unified memory. As a result,\n> - arguably it will be less secure,\n> - there can be performance drops.\n>\n> Currently, this commit is part of an 8 commit patch series:\n> \"Fix stale IOTLB entries for kernel address space\", v7.\n> [PATCH v7 1/8] iommu: Disable SVA when CONFIG_X86 is set\n> [PATCH v7 2/8] mm: Add a ptdesc flag to mark kernel page tables\n> [PATCH v7 3/8] mm: Actually mark kernel page table pages\n> [PATCH v7 4/8] x86/mm: Use 'ptdesc' when freeing PMD pages\n> [PATCH v7 5/8] mm: Introduce pure page table freeing function\n> [PATCH v7 6/8] x86/mm: Use pagetable_free()\n> [PATCH v7 7/8] mm: Introduce deferred freeing for kernel page tables\n> [PATCH v7 8/8] iommu/sva: Invalidate stale IOTLB entries for kernel address space\n>\n> where \"iommu: disable SVA when CONFIG_X86 is set\" is undone by\n> the 8th commit. We only have this commit from the whole patchset.\n> Ideally we should have the whole patchset applied.\n>\n> [Fix]\n>\n> This commit fixes the following issue which is old,\n> 26b25a2b98e4 (\"iommu: Bind process address spaces to devices\")\n> and we applied this commit recently. So, reverting this commit\n> won't be introducing regressions. Affected kernel versions are:\n> - 6.8 due to the reasons above.\n> - 6.17 due to both the reasons above and the amd_xdna issue.\n>\n> [Test Plan]\n>\n> Our regression test suite doesn't catch this issue. However,\n> we will run it again to see it doesn't cause anything else.\n>\n> [Where problems could occur]\n>\n> Reverted commit is a fix for a security vulnerability related to\n> IOMMU Shared Virtual Addressing (SVA). In an SVA context, an \n> IOMMU can cache kernel page table entries. When a kernel page \n> table page is freed and reallocated for another purpose, the \n> IOMMU might still hold stale, incorrect entries. This can be \n> exploited to cause a use-after-free or write-after-free condition,\n> potentially leading to privilege escalation or data corruption.\n>\n> Mehmet Basaran (1):\n> Revert \"iommu: disable SVA when CONFIG_X86 is set\"\n>\n> drivers/iommu/iommu-sva.c | 3 ---\n> 1 file changed, 3 deletions(-)\n>\n> -- \n> 2.43.0","headers":{"Return-Path":"","X-Original-To":"incoming@patchwork.ozlabs.org","Delivered-To":"patchwork-incoming@legolas.ozlabs.org","Authentication-Results":["legolas.ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (4096-bit key;\n unprotected) header.d=canonical.com header.i=@canonical.com\n header.a=rsa-sha256 header.s=20251003 header.b=ZmURrAxM;\n\tdkim-atps=neutral","legolas.ozlabs.org;\n spf=pass (sender SPF authorized) smtp.mailfrom=lists.ubuntu.com\n (client-ip=185.125.189.65; helo=lists.ubuntu.com;\n envelope-from=kernel-team-bounces@lists.ubuntu.com;\n receiver=patchwork.ozlabs.org)"],"Received":["from lists.ubuntu.com (lists.ubuntu.com [185.125.189.65])\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 4g18Zp0Z86z1y2d\n\tfor ; Thu, 23 Apr 2026 05:35:30 +1000 (AEST)","from localhost ([127.0.0.1] helo=lists.ubuntu.com)\n\tby lists.ubuntu.com with esmtp (Exim 4.86_2)\n\t(envelope-from )\n\tid 1wFdM4-0007WA-IO; Wed, 22 Apr 2026 19:35:24 +0000","from smtp-relay-internal-0.internal ([10.131.114.225]\n helo=smtp-relay-internal-0.canonical.com)\n by lists.ubuntu.com with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128)\n (Exim 4.86_2) (envelope-from )\n id 1wFdM3-0007Vl-MX\n for kernel-team@lists.ubuntu.com; Wed, 22 Apr 2026 19:35:23 +0000","from mail-wm1-f72.google.com (mail-wm1-f72.google.com\n [209.85.128.72])\n (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)\n key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest\n SHA256)\n (No client certificate requested)\n by smtp-relay-internal-0.canonical.com (Postfix) with ESMTPS id 8BC7A3F221\n for ; Wed, 22 Apr 2026 19:35:23 +0000 (UTC)","by mail-wm1-f72.google.com with SMTP id\n 5b1f17b1804b1-486fa07f2bbso42647015e9.2\n for ; Wed, 22 Apr 2026 12:35:23 -0700 (PDT)","from localhost ([149.86.141.144]) by smtp.gmail.com with ESMTPSA id\n 5b1f17b1804b1-48a52583fe7sm178886475e9.13.2026.04.22.12.35.20\n for \n (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256);\n Wed, 22 Apr 2026 12:35:21 -0700 (PDT)"],"DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed; d=canonical.com;\n s=20251003; t=1776886523;\n bh=S+p1o/wgOHpa4Vb81WS56kGKpKZh3ti3eQ2GzCQGTz4=;\n h=From:To:Subject:In-Reply-To:References:Date:Message-ID:\n MIME-Version:Content-Type;\n b=ZmURrAxMC37t0bCy99+n71ZTGhNuU34EZKqpews+5OiukPSJIH5BYe/VpJEY4GFbE\n odgi4/H2qNrlqHPixcsnDRLdC7Ao78vx/V0keTQfxLC7ovy8fDwLfwqnHd8kq6K6Gv\n tv22b1gbSxGC5p1qalascpsxslo67XFAxuAKVDAPbHzVcXl3iSLZBXbHCcWufLOCSy\n DQ7k01whT8AFjz47r+qAgKB3IgjYSu7xZBFHRb74uJ8YWcztfEK2U2C1HOhP54dZ5a\n 5XMzy/r375Gsc7bD8N+dRN2T6Xtj5SImMtkh7+5eS2UtXWlw/ON8zcHb9vgiLEslFU\n Cmj491gKw9IenhKBYZfZE5AUohmN4GhR12TySV6Nn2xcOHcivD6GArvPNwHT53//Be\n V+iw06DGTVkOw3UlfJIFqbhY057RSo+v9fOeDIpTdSX6SIVh+4Bn4uuMmZO6OY9FQW\n oWqU52T4yIOccTss+477I22lHiSrO0PFrqFsoLtsK/5EVw5sc/no1xZJ9CiB2KGCxm\n /mUDUYOCvE7wWQUa/Ji2jIxmKBj0z7r6virk3yF6bNWzCyi7yMrge26psuLAWDhSox\n k83FqQjIIpT1p6ccC8i3h7icW8vsveRzQ3CZbvPbDSj2uXolXQ8kz14/2nn8+TTs4o\n QaZ071PNf6wx/mTDWAasUVxc=","X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=1e100.net; s=20251104; t=1776886523; x=1777491323;\n h=mime-version:message-id:date:references:in-reply-to:subject:to:from\n :x-gm-gg:x-gm-message-state:from:to:cc:subject:date:message-id\n :reply-to;\n bh=S+p1o/wgOHpa4Vb81WS56kGKpKZh3ti3eQ2GzCQGTz4=;\n b=jelEPwsKORmET88+3/+DAQvzCFdlpX1so+h8z5Rm06rUBM3uFofJTm83/7EZjBSDjq\n SUhimu3Q9/fDA3fnZzesZTu2okiZ9PI/YiaQARRLEkwHAd4YE32ckXQ9XncCiBCYgwhF\n Pkx2uFdB6iQAG/Mp0YIgbr1nksShjTvQ1dblUJ/Hg93OVeCzaq670hxmYsBs+B4U1evO\n /ovX2Y9ri3Ar9ElYKQjWKcpTgU1uM88QUqMe6BFhF0tuiIvmpGett3QMI02UI6E87v4A\n /CCwjVHbuM7b2CQMnH/xd9KSnTcrr/T4794ZmiWiYjZU7oR/vYuHpvdkC5iAgFVALwQv\n c/bw==","X-Gm-Message-State":"AOJu0YyewO0LTZCccjZ2MsT5+Up5NivxfpoYkmW1RH27qbLUSDFaRNn0\n yRx/T/Sii+Lg8zBh4JYvGQ+2XbBM5zWPO+M5OE26xcy3pN+4SgJMAFB4VKIaXlEn+9hmK2BralZ\n LvKJLWBs9S063BFjxRExij+wj0OG80fGEWPcPWd+W/jLm2t/0V1nIhD98Bu9e9tfndErjZ0JtSU\n rW9eFda/ClfyjPQBOr","X-Gm-Gg":"AeBDietEBup4kmwUIeCSg5wErmjvxNrPEXo7V0/qU7Wi2A3QFCCEQRm6aV1oMTKb9fU\n +FPrbH9/GigBQFnftSUfCnFi/sY+ompPuH+faEPA4OkuWyGkd4hjmfBznlhmyOKuAuNC4Rp8IBm\n fA2RHPMLoAdwzFEEngC09B/FrP3KG+DILx+xq3lpbj4uDxjlbfoz6ev5VMWYXNg6wWTLKJc4LZ7\n yNV8kj15Hd0rrOIu3WisgSaF6nfJP2Gej1F45TWi0/jnFz4MmJ1W/w2PJK3xNWp9byHm1EXEAnC\n /WAgJPV9DPP5dVqv2xZEf6diSYE6nitUhLQg8hvvpi55IPSeo1dTFAG2gFOTw+qAM7L7ZqVmVl8\n XW7gGQFgh6EQwvx3ul7AAlgJefMg4JXpVjfa7oIs22g==","X-Received":["by 2002:a05:600d:8451:b0:48a:599a:36fe with SMTP id\n 5b1f17b1804b1-48a599a4413mr56629895e9.24.1776886522842;\n Wed, 22 Apr 2026 12:35:22 -0700 (PDT)","by 2002:a05:600d:8451:b0:48a:599a:36fe with SMTP id\n 5b1f17b1804b1-48a599a4413mr56629615e9.24.1776886522402;\n Wed, 22 Apr 2026 12:35:22 -0700 (PDT)"],"From":"Mehmet Basaran ","To":"kernel-team@lists.ubuntu.com","Subject":"APPLIED: [SRU][N][PATCH 0/1] Revert \"iommu: disable SVA when\n CONFIG_X86 is set\"","In-Reply-To":"<20260422180616.336474-1-mehmet.basaran@canonical.com>","References":"<20260422180616.336474-1-mehmet.basaran@canonical.com>","Date":"Wed, 22 Apr 2026 22:35:19 +0300","Message-ID":"<87zf2urdoo.fsf@gmail.com>","MIME-Version":"1.0","Content-Type":"multipart/mixed; boundary=\"=-=-=\"","X-BeenThere":"kernel-team@lists.ubuntu.com","X-Mailman-Version":"2.1.20","Precedence":"list","List-Id":"Kernel team discussions ","List-Unsubscribe":",\n ","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n ","Errors-To":"kernel-team-bounces@lists.ubuntu.com","Sender":"\"kernel-team\" "}}]