{"id":2227434,"url":"http://patchwork.ozlabs.org/api/patches/2227434/?format=json","web_url":"http://patchwork.ozlabs.org/project/linux-pci/patch/20260423173051.1999679-1-mattev@meta.com/","project":{"id":28,"url":"http://patchwork.ozlabs.org/api/projects/28/?format=json","name":"Linux PCI development","link_name":"linux-pci","list_id":"linux-pci.vger.kernel.org","list_email":"linux-pci@vger.kernel.org","web_url":null,"scm_url":null,"webscm_url":null,"list_archive_url":"","list_archive_url_format":"","commit_url_format":""},"msgid":"<20260423173051.1999679-1-mattev@meta.com>","list_archive_url":null,"date":"2026-04-23T17:30:51","name":"[v2] PCI/P2PDMA: Avoid returning a provider for non_mappable_bars","commit_ref":null,"pull_url":null,"state":"new","archived":false,"hash":"0a6362aed2a5d3c44c352f3a68b52c8023adac68","submitter":{"id":93208,"url":"http://patchwork.ozlabs.org/api/people/93208/?format=json","name":"Matt Evans","email":"mattev@meta.com"},"delegate":null,"mbox":"http://patchwork.ozlabs.org/project/linux-pci/patch/20260423173051.1999679-1-mattev@meta.com/mbox/","series":[{"id":501226,"url":"http://patchwork.ozlabs.org/api/series/501226/?format=json","web_url":"http://patchwork.ozlabs.org/project/linux-pci/list/?series=501226","date":"2026-04-23T17:30:51","name":"[v2] PCI/P2PDMA: Avoid returning a provider for non_mappable_bars","version":2,"mbox":"http://patchwork.ozlabs.org/series/501226/mbox/"}],"comments":"http://patchwork.ozlabs.org/api/patches/2227434/comments/","check":"pending","checks":"http://patchwork.ozlabs.org/api/patches/2227434/checks/","tags":{},"related":[],"headers":{"Return-Path":"\n ","X-Original-To":["incoming@patchwork.ozlabs.org","linux-pci@vger.kernel.org"],"Delivered-To":"patchwork-incoming@legolas.ozlabs.org","Authentication-Results":["legolas.ozlabs.org;\n\tdkim=pass (2048-bit key;\n unprotected) header.d=meta.com header.i=@meta.com header.a=rsa-sha256\n header.s=s2048-2025-q2 header.b=KoSQJ4QE;\n\tdkim-atps=neutral","legolas.ozlabs.org;\n spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org\n (client-ip=2600:3c0a:e001:db::12fc:5321; helo=sea.lore.kernel.org;\n envelope-from=linux-pci+bounces-53059-incoming=patchwork.ozlabs.org@vger.kernel.org;\n receiver=patchwork.ozlabs.org)","smtp.subspace.kernel.org;\n\tdkim=pass (2048-bit key) header.d=meta.com header.i=@meta.com\n header.b=\"KoSQJ4QE\"","smtp.subspace.kernel.org;\n arc=none smtp.client-ip=67.231.145.42","smtp.subspace.kernel.org;\n dmarc=pass (p=reject dis=none) header.from=meta.com","smtp.subspace.kernel.org;\n spf=pass smtp.mailfrom=meta.com"],"Received":["from sea.lore.kernel.org (sea.lore.kernel.org\n [IPv6:2600:3c0a:e001:db::12fc:5321])\n\t(using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)\n\t key-exchange x25519)\n\t(No client certificate requested)\n\tby legolas.ozlabs.org (Postfix) with ESMTPS id 4g1jnQ3nmTz1yCv\n\tfor ; Fri, 24 Apr 2026 03:31:38 +1000 (AEST)","from smtp.subspace.kernel.org (conduit.subspace.kernel.org\n [100.90.174.1])\n\tby sea.lore.kernel.org (Postfix) with ESMTP id 3C5D8300A623\n\tfor ; Thu, 23 Apr 2026 17:31:36 +0000 (UTC)","from localhost.localdomain (localhost.localdomain [127.0.0.1])\n\tby smtp.subspace.kernel.org (Postfix) with ESMTP id B4E971E7C12;\n\tThu, 23 Apr 2026 17:31:35 +0000 (UTC)","from mx0a-00082601.pphosted.com (mx0a-00082601.pphosted.com\n [67.231.145.42])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits))\n\t(No client certificate requested)\n\tby smtp.subspace.kernel.org (Postfix) with ESMTPS id 381EB1D6DB5;\n\tThu, 23 Apr 2026 17:31:33 +0000 (UTC)","from pps.filterd (m0044010.ppops.net [127.0.0.1])\n\tby mx0a-00082601.pphosted.com (8.18.1.11/8.18.1.11) with ESMTP id\n 63NH8qht1825687;\n\tThu, 23 Apr 2026 10:31:19 -0700","from mail.thefacebook.com ([163.114.134.16])\n\tby mx0a-00082601.pphosted.com (PPS) with ESMTPS id 4dpeph6ax8-1\n\t(version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128 verify=NOT);\n\tThu, 23 Apr 2026 10:31:19 -0700 (PDT)","from localhost (2620:10d:c085:108::4) by mail.thefacebook.com\n (2620:10d:c08b:78::2ac9) with Microsoft SMTP Server (version=TLS1_2,\n cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.2.2562.37; Thu, 23 Apr\n 2026 17:31:18 +0000"],"ARC-Seal":"i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116;\n\tt=1776965495; cv=none;\n b=p9lMwTwUxeqdSejlP3X0ha/PdyfY/k/hfd24JSM19sQjjUyHm62taZiggPO3ITdCRHI47dnYQpzd2NChqzB9u73GlA0aMYuWEGTox3wNvhZ7shlcmeTJmjwYlHXS7AUFI6Na8sV/fAw+EWJQ5NY+irzXfXOxhPJf4U7v3EC9c/U=","ARC-Message-Signature":"i=1; a=rsa-sha256; d=subspace.kernel.org;\n\ts=arc-20240116; t=1776965495; c=relaxed/simple;\n\tbh=5laPpylFZGIAGK4ze8/dFHPrMTjfLQovup6TursfZhU=;\n\th=From:To:CC:Subject:Date:Message-ID:MIME-Version:Content-Type;\n b=PX7T2+hCx3PvQShbZMKBIVQQHPLOk3O//yxhjdAxyXXGT2W2CCv2fngP6+VNixJL8vEfRV2kTSHHNFyQ3/BHtX/HZQ6lxE8UNQAt/68J/ZY6fRKWoGkkxRmp959jTMZvZGRP3/kxs7IwNxuc3t6uVV3XWao2zR4LL5mzvAr9ioQ=","ARC-Authentication-Results":"i=1; smtp.subspace.kernel.org;\n dmarc=pass (p=reject dis=none) header.from=meta.com;\n spf=pass smtp.mailfrom=meta.com;\n dkim=pass (2048-bit key) header.d=meta.com header.i=@meta.com\n header.b=KoSQJ4QE; arc=none smtp.client-ip=67.231.145.42","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed; d=meta.com; h=cc\n\t:content-transfer-encoding:content-type:date:from:message-id\n\t:mime-version:subject:to; s=s2048-2025-q2; bh=sl1X8lIyZ3uvIcv5XJ\n\tvNWiGMZFCkwqvQySCiFqrT/0w=; b=KoSQJ4QEmGtB+n0P5xENqiYPrxCLhFMRI1\n\tb1A4enVbbap7ZbKwFWzjGKnc9FQFu19txKMkiMQyunBlKa7iD8GZEiCO1WsOZ2a8\n\tFPnyYAKDrOu80K/cOYp4RMMm+Ee87Btgw6AP4z1juLix+q9FxCe8VlwNQrbbA86r\n\tVq3EiKsRDCQsTgBSCt55Cc0zjbvWa4XAa7UUX9sh2hSBvSJtsP/7v2ReVv4H5kuE\n\tlC/pbQu9AEDU2Vdg5ejS2EeAt+oZ1Lm6+dcUdVrClWDRtf2SstJlo48HHNIEZfhr\n\tZ30F6Z4hReOFE56dvYn5t/aw9JvQXeQQWMg19tTiCqQaQXHCEulg==","From":"Matt Evans ","To":"Bjorn Helgaas ,\n Logan Gunthorpe\n\t,\n Ankit Agrawal , Leon Romanovsky\n\t,\n Alex Williamson ,\n Niklas Schnelle\n\t","CC":", ","Subject":"[PATCH v2] PCI/P2PDMA: Avoid returning a provider for\n non_mappable_bars","Date":"Thu, 23 Apr 2026 10:30:51 -0700","Message-ID":"<20260423173051.1999679-1-mattev@meta.com>","X-Mailer":"git-send-email 2.52.0","Precedence":"bulk","X-Mailing-List":"linux-pci@vger.kernel.org","List-Id":"","List-Subscribe":"","List-Unsubscribe":"","MIME-Version":"1.0","Content-Transfer-Encoding":"8bit","Content-Type":"text/plain","X-Proofpoint-Spam-Details-Enc":"AW1haW4tMjYwNDIzMDE3MSBTYWx0ZWRfX78pEYXaywXR9\n 7nUdyoFEINho7IZ7lY2PU3MjFhjYqRRJFZ9HCp91oRwTbzzNRD036sEoAxiu5Sv+lsKlpeVA11W\n AZOqCFULlN0OQ3aqnAr16atEVlJuXxyHLgq1INxhdHrD+bqZansyiPNAE8F7Kn3qZngJlzqrsI9\n QozlFoRTEVaP80zReuei4g3r484p03S+fM5wujsDt5vuxaxSuFZqenZV0H/M1R5NwHocwRlYPTn\n NR6+LghgvIuB8W4YKUTgVMV2ZW+HuolNns0Ex1y7JC8+BaIMx64hEz67TlVwpc3UpHoLE/ZKfzI\n O2DUqYUauU5hgKqmzOqaZoVKYQBwuff0gxP0xQvYSmJyur3gIIhoALJw5VdbUainbM34IoKmZDi\n fENtAG/hoRmAvf8t3AqYfBbmNwh8gGtSWQjAd1QrzgRDhnrgg5VzseS98JtbMZCug2uBq/Szy2a\n zgmj8PtP87y0sMNo8kA==","X-Proofpoint-GUID":"pr6pS-6pK0FJE7T4pft87PD_cUfgwYoM","X-Proofpoint-ORIG-GUID":"pr6pS-6pK0FJE7T4pft87PD_cUfgwYoM","X-Authority-Analysis":"v=2.4 cv=B8SJFutM c=1 sm=1 tr=0 ts=69ea5767 cx=c_pps\n a=CB4LiSf2rd0gKozIdrpkBw==:117 a=CB4LiSf2rd0gKozIdrpkBw==:17\n a=A5OVakUREuEA:10 a=VkNPw1HP01LnGYTKEx00:22 a=7x6HtfJdh03M6CCDgxCd:22\n a=8elwO82fXORLTBIkMd32:22 a=VwQbUJbxAAAA:8 a=VabnemYjAAAA:8\n a=LxoKb0BkxeglHS5Ch2kA:9 a=gKebqoRLp9LExxC7YDUY:22","X-Proofpoint-Virus-Version":"vendor=baseguard\n engine=ICAP:2.0.293,Aquarius:18.0.1143,Hydra:6.1.51,FMLib:17.12.100.49\n definitions=2026-04-23_03,2026-04-21_02,2025-10-01_01"},"content":"Extend the checks in pcim_p2pdma_init() and pcim_p2pdma_provider() to\nexclude functions that have pdev->non_mappable_bars set.\n\nConsumers such as VFIO were previously able to map these for access by\nthe CPU or P2P. Update the comment on non_mappable_bars to show it\nrefers to any access, not just userspace CPU access.\n\nFixes: 372d6d1b8ae3c (\"PCI/P2PDMA: Refactor to separate core P2P functionality from memory allocation\")\nSigned-off-by: Matt Evans \n---\n\nThis arises from Alex Williamson's suggestion to test\nnon_mappable_bars when getting the provider, with discussion here:\n\n https://lore.kernel.org/kvm/20260415181623.1021090-1-mattev@meta.com/\n\nThe goal was to prevent a hole where VFIO could export DMABUFs for\nBARs marked non-mappable, and to fix for all users of the provider\nrather than just VFIO. Alex observed that non_mappable_bars should be\ntaken to mean BARs weren't usable by the CPU _or_ peers and,\nconsidering that, its comment about userspace access wasn't quite\nright.\n\n== Changes ==\n\nv2:\n - Also test non_mappable_bars in pcim_p2pdma_init(), as\n otherwise pci_p2pdma_add_resource() will WARN_ON\n pcim_p2pdma_provider() failing.\n\nNiklas and Logan, I didn't re-add your R-B from v1 as (splitting\nhairs...) the code's changed.\n\nv1:\n https://lore.kernel.org/linux-pci/20260421174351.3897842-1-mattev@meta.com/\n\n\n drivers/pci/p2pdma.c | 6 +++++-\n include/linux/pci.h | 2 +-\n 2 files changed, 6 insertions(+), 2 deletions(-)","diff":"diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c\nindex 7c898542af8d..adb17a4f6939 100644\n--- a/drivers/pci/p2pdma.c\n+++ b/drivers/pci/p2pdma.c\n@@ -262,6 +262,9 @@ int pcim_p2pdma_init(struct pci_dev *pdev)\n \tstruct pci_p2pdma *p2p;\n \tint i, ret;\n \n+\tif (pdev->non_mappable_bars)\n+\t\treturn -EOPNOTSUPP;\n+\n \tp2p = rcu_dereference_protected(pdev->p2pdma, 1);\n \tif (p2p)\n \t\treturn 0;\n@@ -318,7 +321,8 @@ struct p2pdma_provider *pcim_p2pdma_provider(struct pci_dev *pdev, int bar)\n {\n \tstruct pci_p2pdma *p2p;\n \n-\tif (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM))\n+\tif (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM) ||\n+\t pdev->non_mappable_bars)\n \t\treturn NULL;\n \n \tp2p = rcu_dereference_protected(pdev->p2pdma, 1);\ndiff --git a/include/linux/pci.h b/include/linux/pci.h\nindex 2c4454583c11..1e6802017d6b 100644\n--- a/include/linux/pci.h\n+++ b/include/linux/pci.h\n@@ -508,7 +508,7 @@ struct pci_dev {\n \tunsigned int\tno_command_memory:1;\t/* No PCI_COMMAND_MEMORY */\n \tunsigned int\trom_bar_overlap:1;\t/* ROM BAR disable broken */\n \tunsigned int\trom_attr_enabled:1;\t/* Display of ROM attribute enabled? */\n-\tunsigned int\tnon_mappable_bars:1;\t/* BARs can't be mapped to user-space */\n+\tunsigned int\tnon_mappable_bars:1;\t/* BARs can't be mapped by CPU or peers */\n \tpci_dev_flags_t dev_flags;\n \tatomic_t\tenable_cnt;\t/* pci_enable_device has been called */\n \n","prefixes":["v2"]}