From nobody Sun May 19 12:26:34 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1696328320; cv=none; d=zohomail.com; s=zohoarc; b=K8zgNqD7fkFWTBUQ1/9C8Gxgju/KB9b2aeLXy28+tKAAROkt80WxEiGjWZcWblhcAmh76ED/DS71Rc3g1OgBkukDU68rKQU48ugZOvJU0WvVMaTDclq2ls1BZbp0FoIGfNNj3UPD6vTEc9VBuF5W8JdqFetnB3NWXPslJYW/ciw= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1696328320; h=Content-Transfer-Encoding:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=8DI5NJmnJVqiypvxLqxJOHBmBLc5QhQqY9Z4+f2hBow=; b=BmZFNBzK4gxkQDuJbthUxqq4zHb99u3yMPoCikjZYUFHauEK25Km0l+YakZlE2h511dTPo7Z+fK996r9MBXSXYTlwqmz8vvBPiDf6IMu1CR9omVlzGavTIKSxuaSbSIEb5lgAQm6PUvSaXlqT2C/4llDkMvt3ksB/BvE7baVzjg= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696328320724816.0980234070066; Tue, 3 Oct 2023 03:18:40 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qncRZ-0007Sm-Jh; Tue, 03 Oct 2023 06:15:57 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRY-0007SZ-Gi for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:15:56 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.133.124]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRW-0004QZ-MS for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:15:55 -0400 Received: from mimecast-mx02.redhat.com (mx-ext.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-562-zPR9EIqMO4WUE5U74gCw2g-1; Tue, 03 Oct 2023 06:15:49 -0400 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.rdu2.redhat.com [10.11.54.9]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 3D86F3803915; Tue, 3 Oct 2023 10:15:49 +0000 (UTC) Received: from laptop.redhat.com (unknown [10.39.192.172]) by smtp.corp.redhat.com (Postfix) with ESMTP id A1CB4492B16; Tue, 3 Oct 2023 10:15:46 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1696328153; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=8DI5NJmnJVqiypvxLqxJOHBmBLc5QhQqY9Z4+f2hBow=; b=OS0d4hTOZdcsIrV+vTLL/9rHN0YwDhZII9WkBFI/BWqCsX3Mf6H4NNoOT3xYcfnFpPoqAD XsK5bvZViAPrSlG/e1VLKr84ANqrQWN/p3ywmNghdvNcM+9eUggRp9OlLl8grbYuHpZjbU cumslzwz6FQzg0rJVkhN6THZMd0fnPU= X-MC-Unique: zPR9EIqMO4WUE5U74gCw2g-1 From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, zhenzhong.duan@intel.com, alex.williamson@redhat.com, clg@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com, joao.m.martins@oracle.com, peterx@redhat.com, kevin.tian@intel.com, yi.l.liu@intel.com, yi.y.sun@intel.com, chao.p.peng@intel.com, mjrosato@linux.ibm.com Subject: [PATCH v3 01/15] scripts/update-linux-headers: Add iommufd.h Date: Tue, 3 Oct 2023 12:13:58 +0200 Message-ID: <20231003101530.288864-2-eric.auger@redhat.com> In-Reply-To: <20231003101530.288864-1-eric.auger@redhat.com> References: <20231003101530.288864-1-eric.auger@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.1 on 10.11.54.9 Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=170.10.133.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H3=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=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: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @redhat.com) X-ZM-MESSAGEID: 1696328322408100001 Content-Type: text/plain; charset="utf-8" Update the script to import iommufd.h Signed-off-by: Eric Auger Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: C=C3=A9dric Le Goater --- scripts/update-linux-headers.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/scripts/update-linux-headers.sh b/scripts/update-linux-headers= .sh index 35a64bb501..34295c0fe5 100755 --- a/scripts/update-linux-headers.sh +++ b/scripts/update-linux-headers.sh @@ -161,7 +161,8 @@ done rm -rf "$output/linux-headers/linux" mkdir -p "$output/linux-headers/linux" for header in const.h stddef.h kvm.h vfio.h vfio_ccw.h vfio_zdev.h vhost.h= \ - psci.h psp-sev.h userfaultfd.h memfd.h mman.h nvme_ioctl.h v= duse.h; do + psci.h psp-sev.h userfaultfd.h memfd.h mman.h nvme_ioctl.h \ + vduse.h iommufd.h; do cp "$tmpdir/include/linux/$header" "$output/linux-headers/linux" done =20 --=20 2.41.0 From nobody Sun May 19 12:26:34 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1696328221; cv=none; d=zohomail.com; s=zohoarc; b=A21YN2TqALHzT5NE3xAR15Sm3Cy6mH8+hraRlboYx4pEYxdNMVfPqhEs9uoqAOmGsfRn/OrGgrZVvY85K01w+LnpvorzaFYX9v+62lrCgOxu3F1bhkNMsrF919cVO8ah0BDF/EQdt+6EmuX7TQxZEUv80d6UZaiPCxq08B2lTuA= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1696328221; h=Content-Type:Content-Transfer-Encoding:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=XAoEZOKmsn6TCtK7yUGPyzK0sl4iwrK4j5BWiCYC3l0=; b=GZs9UAvOHhpNPNS5ee32Qbnyj5d8iqJC4mAAbIkiF75AxYUrddWlmAJAqBI76M+Lqe40ytq+GpTVLbd1iB9fNmzElMJQ1AAZF7KI2ip3xHVaxb/484AXD+Gcil3xcWYFrV9TzPTGlIxiJ8R4w2fxyFCy2j7GyrOzgdG5Jecwypw= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696328221703891.3010263295024; Tue, 3 Oct 2023 03:17:01 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qncS1-0007XO-Va; Tue, 03 Oct 2023 06:16:26 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncS0-0007Wx-AU for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:24 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.133.124]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRx-0004UT-NA for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:24 -0400 Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-404-cFYYIRLlNCy_6UShQI1LlQ-1; Tue, 03 Oct 2023 06:16:07 -0400 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.rdu2.redhat.com [10.11.54.9]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 2AFA685A5BD; Tue, 3 Oct 2023 10:15:52 +0000 (UTC) Received: from laptop.redhat.com (unknown [10.39.192.172]) by smtp.corp.redhat.com (Postfix) with ESMTP id 8173A492B16; Tue, 3 Oct 2023 10:15:49 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1696328181; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=XAoEZOKmsn6TCtK7yUGPyzK0sl4iwrK4j5BWiCYC3l0=; b=iyWKqfYj5HHJxeZyJCns8kyOfom3YEL0KDZZqjhdBafBgjfzJ/n6Pya+vvDWVo+ac5tvGq Mv/hj1dc+qx4bmhXpAgiNI+e0bgeyz7gBBSq+aicUo31vlywBneHA9gSi5Z2RFKoQ2HIC3 leQnPxXWZq7J1JukxdlN4CwXIRCRhxY= X-MC-Unique: cFYYIRLlNCy_6UShQI1LlQ-1 From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, zhenzhong.duan@intel.com, alex.williamson@redhat.com, clg@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com, joao.m.martins@oracle.com, peterx@redhat.com, kevin.tian@intel.com, yi.l.liu@intel.com, yi.y.sun@intel.com, chao.p.peng@intel.com, mjrosato@linux.ibm.com Subject: [PATCH v3 02/15] linux-headers: Add iommufd.h Date: Tue, 3 Oct 2023 12:13:59 +0200 Message-ID: <20231003101530.288864-3-eric.auger@redhat.com> In-Reply-To: <20231003101530.288864-1-eric.auger@redhat.com> References: <20231003101530.288864-1-eric.auger@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.1 on 10.11.54.9 Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=170.10.133.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H3=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=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: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @redhat.com) X-ZM-MESSAGEID: 1696328222797100005 From: Zhenzhong Duan Since commit da3c22c74a3c ("linux-headers: Update to Linux v6.6-rc1"), linux-headers has been updated to v6.6-rc1. As previous patch added iommufd.h to update-linux-headers.sh, run the script again against TAG v6.6-rc1 to have iommufd.h included. Signed-off-by: Zhenzhong Duan Reviewed-by: C=C3=A9dric Le Goater --- linux-headers/linux/iommufd.h | 444 ++++++++++++++++++++++++++++++++++ 1 file changed, 444 insertions(+) create mode 100644 linux-headers/linux/iommufd.h diff --git a/linux-headers/linux/iommufd.h b/linux-headers/linux/iommufd.h new file mode 100644 index 0000000000..218bf7ac98 --- /dev/null +++ b/linux-headers/linux/iommufd.h @@ -0,0 +1,444 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES. + */ +#ifndef _IOMMUFD_H +#define _IOMMUFD_H + +#include +#include + +#define IOMMUFD_TYPE (';') + +/** + * DOC: General ioctl format + * + * The ioctl interface follows a general format to allow for extensibility= . Each + * ioctl is passed in a structure pointer as the argument providing the si= ze of + * the structure in the first u32. The kernel checks that any structure sp= ace + * beyond what it understands is 0. This allows userspace to use the backw= ard + * compatible portion while consistently using the newer, larger, structur= es. + * + * ioctls use a standard meaning for common errnos: + * + * - ENOTTY: The IOCTL number itself is not supported at all + * - E2BIG: The IOCTL number is supported, but the provided structure has + * non-zero in a part the kernel does not understand. + * - EOPNOTSUPP: The IOCTL number is supported, and the structure is + * understood, however a known field has a value the kernel does not + * understand or support. + * - EINVAL: Everything about the IOCTL was understood, but a field is not + * correct. + * - ENOENT: An ID or IOVA provided does not exist. + * - ENOMEM: Out of memory. + * - EOVERFLOW: Mathematics overflowed. + * + * As well as additional errnos, within specific ioctls. + */ +enum { + IOMMUFD_CMD_BASE =3D 0x80, + IOMMUFD_CMD_DESTROY =3D IOMMUFD_CMD_BASE, + IOMMUFD_CMD_IOAS_ALLOC, + IOMMUFD_CMD_IOAS_ALLOW_IOVAS, + IOMMUFD_CMD_IOAS_COPY, + IOMMUFD_CMD_IOAS_IOVA_RANGES, + IOMMUFD_CMD_IOAS_MAP, + IOMMUFD_CMD_IOAS_UNMAP, + IOMMUFD_CMD_OPTION, + IOMMUFD_CMD_VFIO_IOAS, + IOMMUFD_CMD_HWPT_ALLOC, + IOMMUFD_CMD_GET_HW_INFO, +}; + +/** + * struct iommu_destroy - ioctl(IOMMU_DESTROY) + * @size: sizeof(struct iommu_destroy) + * @id: iommufd object ID to destroy. Can be any destroyable object type. + * + * Destroy any object held within iommufd. + */ +struct iommu_destroy { + __u32 size; + __u32 id; +}; +#define IOMMU_DESTROY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_DESTROY) + +/** + * struct iommu_ioas_alloc - ioctl(IOMMU_IOAS_ALLOC) + * @size: sizeof(struct iommu_ioas_alloc) + * @flags: Must be 0 + * @out_ioas_id: Output IOAS ID for the allocated object + * + * Allocate an IO Address Space (IOAS) which holds an IO Virtual Address (= IOVA) + * to memory mapping. + */ +struct iommu_ioas_alloc { + __u32 size; + __u32 flags; + __u32 out_ioas_id; +}; +#define IOMMU_IOAS_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_ALLOC) + +/** + * struct iommu_iova_range - ioctl(IOMMU_IOVA_RANGE) + * @start: First IOVA + * @last: Inclusive last IOVA + * + * An interval in IOVA space. + */ +struct iommu_iova_range { + __aligned_u64 start; + __aligned_u64 last; +}; + +/** + * struct iommu_ioas_iova_ranges - ioctl(IOMMU_IOAS_IOVA_RANGES) + * @size: sizeof(struct iommu_ioas_iova_ranges) + * @ioas_id: IOAS ID to read ranges from + * @num_iovas: Input/Output total number of ranges in the IOAS + * @__reserved: Must be 0 + * @allowed_iovas: Pointer to the output array of struct iommu_iova_range + * @out_iova_alignment: Minimum alignment required for mapping IOVA + * + * Query an IOAS for ranges of allowed IOVAs. Mapping IOVA outside these r= anges + * is not allowed. num_iovas will be set to the total number of iovas and + * the allowed_iovas[] will be filled in as space permits. + * + * The allowed ranges are dependent on the HW path the DMA operation takes= , and + * can change during the lifetime of the IOAS. A fresh empty IOAS will hav= e a + * full range, and each attached device will narrow the ranges based on th= at + * device's HW restrictions. Detaching a device can widen the ranges. User= space + * should query ranges after every attach/detach to know what IOVAs are va= lid + * for mapping. + * + * On input num_iovas is the length of the allowed_iovas array. On output = it is + * the total number of iovas filled in. The ioctl will return -EMSGSIZE an= d set + * num_iovas to the required value if num_iovas is too small. In this case= the + * caller should allocate a larger output array and re-issue the ioctl. + * + * out_iova_alignment returns the minimum IOVA alignment that can be given + * to IOMMU_IOAS_MAP/COPY. IOVA's must satisfy:: + * + * starting_iova % out_iova_alignment =3D=3D 0 + * (starting_iova + length) % out_iova_alignment =3D=3D 0 + * + * out_iova_alignment can be 1 indicating any IOVA is allowed. It cannot + * be higher than the system PAGE_SIZE. + */ +struct iommu_ioas_iova_ranges { + __u32 size; + __u32 ioas_id; + __u32 num_iovas; + __u32 __reserved; + __aligned_u64 allowed_iovas; + __aligned_u64 out_iova_alignment; +}; +#define IOMMU_IOAS_IOVA_RANGES _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_IOVA_RAN= GES) + +/** + * struct iommu_ioas_allow_iovas - ioctl(IOMMU_IOAS_ALLOW_IOVAS) + * @size: sizeof(struct iommu_ioas_allow_iovas) + * @ioas_id: IOAS ID to allow IOVAs from + * @num_iovas: Input/Output total number of ranges in the IOAS + * @__reserved: Must be 0 + * @allowed_iovas: Pointer to array of struct iommu_iova_range + * + * Ensure a range of IOVAs are always available for allocation. If this ca= ll + * succeeds then IOMMU_IOAS_IOVA_RANGES will never return a list of IOVA r= anges + * that are narrower than the ranges provided here. This call will fail if + * IOMMU_IOAS_IOVA_RANGES is currently narrower than the given ranges. + * + * When an IOAS is first created the IOVA_RANGES will be maximally sized, = and as + * devices are attached the IOVA will narrow based on the device restricti= ons. + * When an allowed range is specified any narrowing will be refused, ie de= vice + * attachment can fail if the device requires limiting within the allowed = range. + * + * Automatic IOVA allocation is also impacted by this call. MAP will only + * allocate within the allowed IOVAs if they are present. + * + * This call replaces the entire allowed list with the given list. + */ +struct iommu_ioas_allow_iovas { + __u32 size; + __u32 ioas_id; + __u32 num_iovas; + __u32 __reserved; + __aligned_u64 allowed_iovas; +}; +#define IOMMU_IOAS_ALLOW_IOVAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_ALLOW_IO= VAS) + +/** + * enum iommufd_ioas_map_flags - Flags for map and copy + * @IOMMU_IOAS_MAP_FIXED_IOVA: If clear the kernel will compute an appropr= iate + * IOVA to place the mapping at + * @IOMMU_IOAS_MAP_WRITEABLE: DMA is allowed to write to this mapping + * @IOMMU_IOAS_MAP_READABLE: DMA is allowed to read from this mapping + */ +enum iommufd_ioas_map_flags { + IOMMU_IOAS_MAP_FIXED_IOVA =3D 1 << 0, + IOMMU_IOAS_MAP_WRITEABLE =3D 1 << 1, + IOMMU_IOAS_MAP_READABLE =3D 1 << 2, +}; + +/** + * struct iommu_ioas_map - ioctl(IOMMU_IOAS_MAP) + * @size: sizeof(struct iommu_ioas_map) + * @flags: Combination of enum iommufd_ioas_map_flags + * @ioas_id: IOAS ID to change the mapping of + * @__reserved: Must be 0 + * @user_va: Userspace pointer to start mapping from + * @length: Number of bytes to map + * @iova: IOVA the mapping was placed at. If IOMMU_IOAS_MAP_FIXED_IOVA is = set + * then this must be provided as input. + * + * Set an IOVA mapping from a user pointer. If FIXED_IOVA is specified the= n the + * mapping will be established at iova, otherwise a suitable location base= d on + * the reserved and allowed lists will be automatically selected and retur= ned in + * iova. + * + * If IOMMU_IOAS_MAP_FIXED_IOVA is specified then the iova range must curr= ently + * be unused, existing IOVA cannot be replaced. + */ +struct iommu_ioas_map { + __u32 size; + __u32 flags; + __u32 ioas_id; + __u32 __reserved; + __aligned_u64 user_va; + __aligned_u64 length; + __aligned_u64 iova; +}; +#define IOMMU_IOAS_MAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_MAP) + +/** + * struct iommu_ioas_copy - ioctl(IOMMU_IOAS_COPY) + * @size: sizeof(struct iommu_ioas_copy) + * @flags: Combination of enum iommufd_ioas_map_flags + * @dst_ioas_id: IOAS ID to change the mapping of + * @src_ioas_id: IOAS ID to copy from + * @length: Number of bytes to copy and map + * @dst_iova: IOVA the mapping was placed at. If IOMMU_IOAS_MAP_FIXED_IOVA= is + * set then this must be provided as input. + * @src_iova: IOVA to start the copy + * + * Copy an already existing mapping from src_ioas_id and establish it in + * dst_ioas_id. The src iova/length must exactly match a range used with + * IOMMU_IOAS_MAP. + * + * This may be used to efficiently clone a subset of an IOAS to another, o= r as a + * kind of 'cache' to speed up mapping. Copy has an efficiency advantage o= ver + * establishing equivalent new mappings, as internal resources are shared,= and + * the kernel will pin the user memory only once. + */ +struct iommu_ioas_copy { + __u32 size; + __u32 flags; + __u32 dst_ioas_id; + __u32 src_ioas_id; + __aligned_u64 length; + __aligned_u64 dst_iova; + __aligned_u64 src_iova; +}; +#define IOMMU_IOAS_COPY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_COPY) + +/** + * struct iommu_ioas_unmap - ioctl(IOMMU_IOAS_UNMAP) + * @size: sizeof(struct iommu_ioas_unmap) + * @ioas_id: IOAS ID to change the mapping of + * @iova: IOVA to start the unmapping at + * @length: Number of bytes to unmap, and return back the bytes unmapped + * + * Unmap an IOVA range. The iova/length must be a superset of a previously + * mapped range used with IOMMU_IOAS_MAP or IOMMU_IOAS_COPY. Splitting or + * truncating ranges is not allowed. The values 0 to U64_MAX will unmap + * everything. + */ +struct iommu_ioas_unmap { + __u32 size; + __u32 ioas_id; + __aligned_u64 iova; + __aligned_u64 length; +}; +#define IOMMU_IOAS_UNMAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_UNMAP) + +/** + * enum iommufd_option - ioctl(IOMMU_OPTION_RLIMIT_MODE) and + * ioctl(IOMMU_OPTION_HUGE_PAGES) + * @IOMMU_OPTION_RLIMIT_MODE: + * Change how RLIMIT_MEMLOCK accounting works. The caller must have pri= vilege + * to invoke this. Value 0 (default) is user based accouting, 1 uses pr= ocess + * based accounting. Global option, object_id must be 0 + * @IOMMU_OPTION_HUGE_PAGES: + * Value 1 (default) allows contiguous pages to be combined when genera= ting + * iommu mappings. Value 0 disables combining, everything is mapped to + * PAGE_SIZE. This can be useful for benchmarking. This is a per-IOAS + * option, the object_id must be the IOAS ID. + */ +enum iommufd_option { + IOMMU_OPTION_RLIMIT_MODE =3D 0, + IOMMU_OPTION_HUGE_PAGES =3D 1, +}; + +/** + * enum iommufd_option_ops - ioctl(IOMMU_OPTION_OP_SET) and + * ioctl(IOMMU_OPTION_OP_GET) + * @IOMMU_OPTION_OP_SET: Set the option's value + * @IOMMU_OPTION_OP_GET: Get the option's value + */ +enum iommufd_option_ops { + IOMMU_OPTION_OP_SET =3D 0, + IOMMU_OPTION_OP_GET =3D 1, +}; + +/** + * struct iommu_option - iommu option multiplexer + * @size: sizeof(struct iommu_option) + * @option_id: One of enum iommufd_option + * @op: One of enum iommufd_option_ops + * @__reserved: Must be 0 + * @object_id: ID of the object if required + * @val64: Option value to set or value returned on get + * + * Change a simple option value. This multiplexor allows controlling optio= ns + * on objects. IOMMU_OPTION_OP_SET will load an option and IOMMU_OPTION_OP= _GET + * will return the current value. + */ +struct iommu_option { + __u32 size; + __u32 option_id; + __u16 op; + __u16 __reserved; + __u32 object_id; + __aligned_u64 val64; +}; +#define IOMMU_OPTION _IO(IOMMUFD_TYPE, IOMMUFD_CMD_OPTION) + +/** + * enum iommufd_vfio_ioas_op - IOMMU_VFIO_IOAS_* ioctls + * @IOMMU_VFIO_IOAS_GET: Get the current compatibility IOAS + * @IOMMU_VFIO_IOAS_SET: Change the current compatibility IOAS + * @IOMMU_VFIO_IOAS_CLEAR: Disable VFIO compatibility + */ +enum iommufd_vfio_ioas_op { + IOMMU_VFIO_IOAS_GET =3D 0, + IOMMU_VFIO_IOAS_SET =3D 1, + IOMMU_VFIO_IOAS_CLEAR =3D 2, +}; + +/** + * struct iommu_vfio_ioas - ioctl(IOMMU_VFIO_IOAS) + * @size: sizeof(struct iommu_vfio_ioas) + * @ioas_id: For IOMMU_VFIO_IOAS_SET the input IOAS ID to set + * For IOMMU_VFIO_IOAS_GET will output the IOAS ID + * @op: One of enum iommufd_vfio_ioas_op + * @__reserved: Must be 0 + * + * The VFIO compatibility support uses a single ioas because VFIO APIs do = not + * support the ID field. Set or Get the IOAS that VFIO compatibility will = use. + * When VFIO_GROUP_SET_CONTAINER is used on an iommufd it will get the + * compatibility ioas, either by taking what is already set, or auto creat= ing + * one. From then on VFIO will continue to use that ioas and is not effect= ed by + * this ioctl. SET or CLEAR does not destroy any auto-created IOAS. + */ +struct iommu_vfio_ioas { + __u32 size; + __u32 ioas_id; + __u16 op; + __u16 __reserved; +}; +#define IOMMU_VFIO_IOAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VFIO_IOAS) + +/** + * struct iommu_hwpt_alloc - ioctl(IOMMU_HWPT_ALLOC) + * @size: sizeof(struct iommu_hwpt_alloc) + * @flags: Must be 0 + * @dev_id: The device to allocate this HWPT for + * @pt_id: The IOAS to connect this HWPT to + * @out_hwpt_id: The ID of the new HWPT + * @__reserved: Must be 0 + * + * Explicitly allocate a hardware page table object. This is the same obje= ct + * type that is returned by iommufd_device_attach() and represents the + * underlying iommu driver's iommu_domain kernel object. + * + * A HWPT will be created with the IOVA mappings from the given IOAS. + */ +struct iommu_hwpt_alloc { + __u32 size; + __u32 flags; + __u32 dev_id; + __u32 pt_id; + __u32 out_hwpt_id; + __u32 __reserved; +}; +#define IOMMU_HWPT_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_ALLOC) + +/** + * struct iommu_hw_info_vtd - Intel VT-d hardware information + * + * @flags: Must be 0 + * @__reserved: Must be 0 + * + * @cap_reg: Value of Intel VT-d capability register defined in VT-d spec + * section 11.4.2 Capability Register. + * @ecap_reg: Value of Intel VT-d capability register defined in VT-d spec + * section 11.4.3 Extended Capability Register. + * + * User needs to understand the Intel VT-d specification to decode the + * register value. + */ +struct iommu_hw_info_vtd { + __u32 flags; + __u32 __reserved; + __aligned_u64 cap_reg; + __aligned_u64 ecap_reg; +}; + +/** + * enum iommu_hw_info_type - IOMMU Hardware Info Types + * @IOMMU_HW_INFO_TYPE_NONE: Used by the drivers that do not report hardwa= re + * info + * @IOMMU_HW_INFO_TYPE_INTEL_VTD: Intel VT-d iommu info type + */ +enum iommu_hw_info_type { + IOMMU_HW_INFO_TYPE_NONE, + IOMMU_HW_INFO_TYPE_INTEL_VTD, +}; + +/** + * struct iommu_hw_info - ioctl(IOMMU_GET_HW_INFO) + * @size: sizeof(struct iommu_hw_info) + * @flags: Must be 0 + * @dev_id: The device bound to the iommufd + * @data_len: Input the length of a user buffer in bytes. Output the lengt= h of + * data that kernel supports + * @data_uptr: User pointer to a user-space buffer used by the kernel to f= ill + * the iommu type specific hardware information data + * @out_data_type: Output the iommu hardware info type as defined in the e= num + * iommu_hw_info_type. + * @__reserved: Must be 0 + * + * Query an iommu type specific hardware information data from an iommu be= hind + * a given device that has been bound to iommufd. This hardware info data = will + * be used to sync capabilities between the virtual iommu and the physical + * iommu, e.g. a nested translation setup needs to check the hardware info= , so + * a guest stage-1 page table can be compatible with the physical iommu. + * + * To capture an iommu type specific hardware information data, @data_uptr= and + * its length @data_len must be provided. Trailing bytes will be zeroed if= the + * user buffer is larger than the data that kernel has. Otherwise, kernel = only + * fills the buffer using the given length in @data_len. If the ioctl succ= eeds, + * @data_len will be updated to the length that kernel actually supports, + * @out_data_type will be filled to decode the data filled in the buffer + * pointed by @data_uptr. Input @data_len =3D=3D zero is allowed. + */ +struct iommu_hw_info { + __u32 size; + __u32 flags; + __u32 dev_id; + __u32 data_len; + __aligned_u64 data_uptr; + __u32 out_data_type; + __u32 __reserved; +}; +#define IOMMU_GET_HW_INFO _IO(IOMMUFD_TYPE, IOMMUFD_CMD_GET_HW_INFO) +#endif --=20 2.41.0 From nobody Sun May 19 12:26:34 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1696328359; cv=none; d=zohomail.com; s=zohoarc; b=DZk3GP1J3ICqFz7vDU92saW4GkCCQqiayn//vv6NNn+/aLPGW2LhAPC8WqZwXBDlWkhT0zYWCwdiBpqcVQIAzRwzT3QEOBmwEz9YM9ZjbUCmSIIBwXWlNeuasSXn7nKj90VwXZQpQIGAhCybiJOnsGVAkd60ezmmW9m5dHrCq/c= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1696328359; h=Content-Type:Content-Transfer-Encoding:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=XDpbe+mOxilwH/vaolTekL6XmlHMpnxDi8ih3JxfguM=; b=S87fwpb5ArSqDv4tV/BcpKD7IB/XqCte6On8XJaZ9ICxdtCz90xwaZph9Y0i6Ybcaya0kmcQO3XTL48Uhfu752kpn6YAyKOD7syqT9VsK+dsno/MWb2YZp5P58I0bvm/jLa6GImUiN0Rs+q1bVNfCzobvpEYXR2haWxoZ3SDM0U= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696328359322171.43693895914964; Tue, 3 Oct 2023 03:19:19 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qncRj-0007TI-6M; Tue, 03 Oct 2023 06:16:07 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRh-0007T9-PM for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:05 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.129.124]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRe-0004Rp-3n for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:05 -0400 Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-173-eFhXNDPOPduqAt8oiUsCEg-1; Tue, 03 Oct 2023 06:15:55 -0400 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.rdu2.redhat.com [10.11.54.9]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 3AE188007A4; Tue, 3 Oct 2023 10:15:55 +0000 (UTC) Received: from laptop.redhat.com (unknown [10.39.192.172]) by smtp.corp.redhat.com (Postfix) with ESMTP id 6F7A4492B16; Tue, 3 Oct 2023 10:15:52 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1696328161; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=XDpbe+mOxilwH/vaolTekL6XmlHMpnxDi8ih3JxfguM=; b=driCusO3yU4YjPGKUh4RBihsANZx1GalLIu0VddAjQ5alXbw1dnval5BeLltDjPG4gR6hd awkZr0fW/gx9k2fcXujvGik425PNkkcOnuKlMk0cHuPrguJCj8qDppPdzVaeZrQl+9aVcz FVm/DLKol5bozozh14IDpqdJPvt0jBU= X-MC-Unique: eFhXNDPOPduqAt8oiUsCEg-1 From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, zhenzhong.duan@intel.com, alex.williamson@redhat.com, clg@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com, joao.m.martins@oracle.com, peterx@redhat.com, kevin.tian@intel.com, yi.l.liu@intel.com, yi.y.sun@intel.com, chao.p.peng@intel.com, mjrosato@linux.ibm.com Subject: [PATCH v3 03/15] vfio/common: Move IOMMU agnostic helpers to a separate file Date: Tue, 3 Oct 2023 12:14:00 +0200 Message-ID: <20231003101530.288864-4-eric.auger@redhat.com> In-Reply-To: <20231003101530.288864-1-eric.auger@redhat.com> References: <20231003101530.288864-1-eric.auger@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.1 on 10.11.54.9 Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=170.10.129.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H4=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=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: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @redhat.com) X-ZM-MESSAGEID: 1696328361279100002 From: Yi Liu Move low-level iommu agnostic helpers to a separate helpers.c file. They relate to regions, interrupts, device/region capabilities and etc. Signed-off-by: Eric Auger Signed-off-by: Yi Sun Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: C=C3=A9dric Le Goater --- include/hw/vfio/vfio-common.h | 9 + hw/vfio/common.c | 588 -------------------------------- hw/vfio/helpers.c | 611 ++++++++++++++++++++++++++++++++++ hw/vfio/meson.build | 1 + 4 files changed, 621 insertions(+), 588 deletions(-) create mode 100644 hw/vfio/helpers.c diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index e9b8954595..e0483893d1 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -196,6 +196,12 @@ typedef struct VFIODisplay { } dmabuf; } VFIODisplay; =20 +typedef struct { + unsigned long *bitmap; + hwaddr size; + hwaddr pages; +} VFIOBitmap; + void vfio_put_base_device(VFIODevice *vbasedev); void vfio_disable_irqindex(VFIODevice *vbasedev, int index); void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index); @@ -245,6 +251,8 @@ bool vfio_get_info_dma_avail(struct vfio_iommu_type1_in= fo *info, unsigned int *avail); struct vfio_info_cap_header * vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id); +struct vfio_info_cap_header * +vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id); #endif extern const MemoryListener vfio_prereg_listener; =20 @@ -257,4 +265,5 @@ int vfio_spapr_remove_window(VFIOContainer *container, bool vfio_migration_realize(VFIODevice *vbasedev, Error **errp); void vfio_migration_exit(VFIODevice *vbasedev); =20 +int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size); #endif /* HW_VFIO_VFIO_COMMON_H */ diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 134649226d..4e122fc4e4 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -62,84 +62,6 @@ static QLIST_HEAD(, VFIOAddressSpace) vfio_address_space= s =3D static int vfio_kvm_device_fd =3D -1; #endif =20 -/* - * Common VFIO interrupt disable - */ -void vfio_disable_irqindex(VFIODevice *vbasedev, int index) -{ - struct vfio_irq_set irq_set =3D { - .argsz =3D sizeof(irq_set), - .flags =3D VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER, - .index =3D index, - .start =3D 0, - .count =3D 0, - }; - - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); -} - -void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index) -{ - struct vfio_irq_set irq_set =3D { - .argsz =3D sizeof(irq_set), - .flags =3D VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK, - .index =3D index, - .start =3D 0, - .count =3D 1, - }; - - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); -} - -void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index) -{ - struct vfio_irq_set irq_set =3D { - .argsz =3D sizeof(irq_set), - .flags =3D VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_MASK, - .index =3D index, - .start =3D 0, - .count =3D 1, - }; - - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); -} - -static inline const char *action_to_str(int action) -{ - switch (action) { - case VFIO_IRQ_SET_ACTION_MASK: - return "MASK"; - case VFIO_IRQ_SET_ACTION_UNMASK: - return "UNMASK"; - case VFIO_IRQ_SET_ACTION_TRIGGER: - return "TRIGGER"; - default: - return "UNKNOWN ACTION"; - } -} - -static const char *index_to_str(VFIODevice *vbasedev, int index) -{ - if (vbasedev->type !=3D VFIO_DEVICE_TYPE_PCI) { - return NULL; - } - - switch (index) { - case VFIO_PCI_INTX_IRQ_INDEX: - return "INTX"; - case VFIO_PCI_MSI_IRQ_INDEX: - return "MSI"; - case VFIO_PCI_MSIX_IRQ_INDEX: - return "MSIX"; - case VFIO_PCI_ERR_IRQ_INDEX: - return "ERR"; - case VFIO_PCI_REQ_IRQ_INDEX: - return "REQ"; - default: - return NULL; - } -} - static int vfio_ram_block_discard_disable(VFIOContainer *container, bool s= tate) { switch (container->iommu_type) { @@ -163,183 +85,10 @@ static int vfio_ram_block_discard_disable(VFIOContain= er *container, bool state) } } =20 -int vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex, - int action, int fd, Error **errp) -{ - struct vfio_irq_set *irq_set; - int argsz, ret =3D 0; - const char *name; - int32_t *pfd; - - argsz =3D sizeof(*irq_set) + sizeof(*pfd); - - irq_set =3D g_malloc0(argsz); - irq_set->argsz =3D argsz; - irq_set->flags =3D VFIO_IRQ_SET_DATA_EVENTFD | action; - irq_set->index =3D index; - irq_set->start =3D subindex; - irq_set->count =3D 1; - pfd =3D (int32_t *)&irq_set->data; - *pfd =3D fd; - - if (ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set)) { - ret =3D -errno; - } - g_free(irq_set); - - if (!ret) { - return 0; - } - - error_setg_errno(errp, -ret, "VFIO_DEVICE_SET_IRQS failure"); - - name =3D index_to_str(vbasedev, index); - if (name) { - error_prepend(errp, "%s-%d: ", name, subindex); - } else { - error_prepend(errp, "index %d-%d: ", index, subindex); - } - error_prepend(errp, - "Failed to %s %s eventfd signaling for interrupt ", - fd < 0 ? "tear down" : "set up", action_to_str(action)); - return ret; -} - -/* - * IO Port/MMIO - Beware of the endians, VFIO is always little endian - */ -void vfio_region_write(void *opaque, hwaddr addr, - uint64_t data, unsigned size) -{ - VFIORegion *region =3D opaque; - VFIODevice *vbasedev =3D region->vbasedev; - union { - uint8_t byte; - uint16_t word; - uint32_t dword; - uint64_t qword; - } buf; - - switch (size) { - case 1: - buf.byte =3D data; - break; - case 2: - buf.word =3D cpu_to_le16(data); - break; - case 4: - buf.dword =3D cpu_to_le32(data); - break; - case 8: - buf.qword =3D cpu_to_le64(data); - break; - default: - hw_error("vfio: unsupported write size, %u bytes", size); - break; - } - - if (pwrite(vbasedev->fd, &buf, size, region->fd_offset + addr) !=3D si= ze) { - error_report("%s(%s:region%d+0x%"HWADDR_PRIx", 0x%"PRIx64 - ",%d) failed: %m", - __func__, vbasedev->name, region->nr, - addr, data, size); - } - - trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size); - - /* - * A read or write to a BAR always signals an INTx EOI. This will - * do nothing if not pending (including not in INTx mode). We assume - * that a BAR access is in response to an interrupt and that BAR - * accesses will service the interrupt. Unfortunately, we don't know - * which access will service the interrupt, so we're potentially - * getting quite a few host interrupts per guest interrupt. - */ - vbasedev->ops->vfio_eoi(vbasedev); -} - -uint64_t vfio_region_read(void *opaque, - hwaddr addr, unsigned size) -{ - VFIORegion *region =3D opaque; - VFIODevice *vbasedev =3D region->vbasedev; - union { - uint8_t byte; - uint16_t word; - uint32_t dword; - uint64_t qword; - } buf; - uint64_t data =3D 0; - - if (pread(vbasedev->fd, &buf, size, region->fd_offset + addr) !=3D siz= e) { - error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m", - __func__, vbasedev->name, region->nr, - addr, size); - return (uint64_t)-1; - } - switch (size) { - case 1: - data =3D buf.byte; - break; - case 2: - data =3D le16_to_cpu(buf.word); - break; - case 4: - data =3D le32_to_cpu(buf.dword); - break; - case 8: - data =3D le64_to_cpu(buf.qword); - break; - default: - hw_error("vfio: unsupported read size, %u bytes", size); - break; - } - - trace_vfio_region_read(vbasedev->name, region->nr, addr, size, data); - - /* Same as write above */ - vbasedev->ops->vfio_eoi(vbasedev); - - return data; -} - -const MemoryRegionOps vfio_region_ops =3D { - .read =3D vfio_region_read, - .write =3D vfio_region_write, - .endianness =3D DEVICE_LITTLE_ENDIAN, - .valid =3D { - .min_access_size =3D 1, - .max_access_size =3D 8, - }, - .impl =3D { - .min_access_size =3D 1, - .max_access_size =3D 8, - }, -}; - /* * Device state interfaces */ =20 -typedef struct { - unsigned long *bitmap; - hwaddr size; - hwaddr pages; -} VFIOBitmap; - -static int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size) -{ - vbmap->pages =3D REAL_HOST_PAGE_ALIGN(size) / qemu_real_host_page_size= (); - vbmap->size =3D ROUND_UP(vbmap->pages, sizeof(__u64) * BITS_PER_BYTE) / - BITS_PER_BYTE; - vbmap->bitmap =3D g_try_malloc0(vbmap->size); - if (!vbmap->bitmap) { - return -ENOMEM; - } - - return 0; -} - static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, uint64_t size, ram_addr_t ram_addr); =20 @@ -1994,30 +1743,6 @@ static void vfio_listener_release(VFIOContainer *con= tainer) } } =20 -static struct vfio_info_cap_header * -vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id) -{ - struct vfio_info_cap_header *hdr; - - for (hdr =3D ptr + cap_offset; hdr !=3D ptr; hdr =3D ptr + hdr->next) { - if (hdr->id =3D=3D id) { - return hdr; - } - } - - return NULL; -} - -struct vfio_info_cap_header * -vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id) -{ - if (!(info->flags & VFIO_REGION_INFO_FLAG_CAPS)) { - return NULL; - } - - return vfio_get_cap((void *)info, info->cap_offset, id); -} - static struct vfio_info_cap_header * vfio_get_iommu_type1_info_cap(struct vfio_iommu_type1_info *info, uint16_t= id) { @@ -2028,16 +1753,6 @@ vfio_get_iommu_type1_info_cap(struct vfio_iommu_type= 1_info *info, uint16_t id) return vfio_get_cap((void *)info, info->cap_offset, id); } =20 -struct vfio_info_cap_header * -vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id) -{ - if (!(info->flags & VFIO_DEVICE_FLAGS_CAPS)) { - return NULL; - } - - return vfio_get_cap((void *)info, info->cap_offset, id); -} - bool vfio_get_info_dma_avail(struct vfio_iommu_type1_info *info, unsigned int *avail) { @@ -2059,232 +1774,6 @@ bool vfio_get_info_dma_avail(struct vfio_iommu_type= 1_info *info, return true; } =20 -static int vfio_setup_region_sparse_mmaps(VFIORegion *region, - struct vfio_region_info *info) -{ - struct vfio_info_cap_header *hdr; - struct vfio_region_info_cap_sparse_mmap *sparse; - int i, j; - - hdr =3D vfio_get_region_info_cap(info, VFIO_REGION_INFO_CAP_SPARSE_MMA= P); - if (!hdr) { - return -ENODEV; - } - - sparse =3D container_of(hdr, struct vfio_region_info_cap_sparse_mmap, = header); - - trace_vfio_region_sparse_mmap_header(region->vbasedev->name, - region->nr, sparse->nr_areas); - - region->mmaps =3D g_new0(VFIOMmap, sparse->nr_areas); - - for (i =3D 0, j =3D 0; i < sparse->nr_areas; i++) { - if (sparse->areas[i].size) { - trace_vfio_region_sparse_mmap_entry(i, sparse->areas[i].offset, - sparse->areas[i].offset + - sparse->areas[i].size - 1); - region->mmaps[j].offset =3D sparse->areas[i].offset; - region->mmaps[j].size =3D sparse->areas[i].size; - j++; - } - } - - region->nr_mmaps =3D j; - region->mmaps =3D g_realloc(region->mmaps, j * sizeof(VFIOMmap)); - - return 0; -} - -int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *regio= n, - int index, const char *name) -{ - struct vfio_region_info *info; - int ret; - - ret =3D vfio_get_region_info(vbasedev, index, &info); - if (ret) { - return ret; - } - - region->vbasedev =3D vbasedev; - region->flags =3D info->flags; - region->size =3D info->size; - region->fd_offset =3D info->offset; - region->nr =3D index; - - if (region->size) { - region->mem =3D g_new0(MemoryRegion, 1); - memory_region_init_io(region->mem, obj, &vfio_region_ops, - region, name, region->size); - - if (!vbasedev->no_mmap && - region->flags & VFIO_REGION_INFO_FLAG_MMAP) { - - ret =3D vfio_setup_region_sparse_mmaps(region, info); - - if (ret) { - region->nr_mmaps =3D 1; - region->mmaps =3D g_new0(VFIOMmap, region->nr_mmaps); - region->mmaps[0].offset =3D 0; - region->mmaps[0].size =3D region->size; - } - } - } - - g_free(info); - - trace_vfio_region_setup(vbasedev->name, index, name, - region->flags, region->fd_offset, region->size= ); - return 0; -} - -static void vfio_subregion_unmap(VFIORegion *region, int index) -{ - trace_vfio_region_unmap(memory_region_name(®ion->mmaps[index].mem), - region->mmaps[index].offset, - region->mmaps[index].offset + - region->mmaps[index].size - 1); - memory_region_del_subregion(region->mem, ®ion->mmaps[index].mem); - munmap(region->mmaps[index].mmap, region->mmaps[index].size); - object_unparent(OBJECT(®ion->mmaps[index].mem)); - region->mmaps[index].mmap =3D NULL; -} - -int vfio_region_mmap(VFIORegion *region) -{ - int i, prot =3D 0; - char *name; - - if (!region->mem) { - return 0; - } - - prot |=3D region->flags & VFIO_REGION_INFO_FLAG_READ ? PROT_READ : 0; - prot |=3D region->flags & VFIO_REGION_INFO_FLAG_WRITE ? PROT_WRITE : 0; - - for (i =3D 0; i < region->nr_mmaps; i++) { - region->mmaps[i].mmap =3D mmap(NULL, region->mmaps[i].size, prot, - MAP_SHARED, region->vbasedev->fd, - region->fd_offset + - region->mmaps[i].offset); - if (region->mmaps[i].mmap =3D=3D MAP_FAILED) { - int ret =3D -errno; - - trace_vfio_region_mmap_fault(memory_region_name(region->mem), = i, - region->fd_offset + - region->mmaps[i].offset, - region->fd_offset + - region->mmaps[i].offset + - region->mmaps[i].size - 1, ret); - - region->mmaps[i].mmap =3D NULL; - - for (i--; i >=3D 0; i--) { - vfio_subregion_unmap(region, i); - } - - return ret; - } - - name =3D g_strdup_printf("%s mmaps[%d]", - memory_region_name(region->mem), i); - memory_region_init_ram_device_ptr(®ion->mmaps[i].mem, - memory_region_owner(region->mem), - name, region->mmaps[i].size, - region->mmaps[i].mmap); - g_free(name); - memory_region_add_subregion(region->mem, region->mmaps[i].offset, - ®ion->mmaps[i].mem); - - trace_vfio_region_mmap(memory_region_name(®ion->mmaps[i].mem), - region->mmaps[i].offset, - region->mmaps[i].offset + - region->mmaps[i].size - 1); - } - - return 0; -} - -void vfio_region_unmap(VFIORegion *region) -{ - int i; - - if (!region->mem) { - return; - } - - for (i =3D 0; i < region->nr_mmaps; i++) { - if (region->mmaps[i].mmap) { - vfio_subregion_unmap(region, i); - } - } -} - -void vfio_region_exit(VFIORegion *region) -{ - int i; - - if (!region->mem) { - return; - } - - for (i =3D 0; i < region->nr_mmaps; i++) { - if (region->mmaps[i].mmap) { - memory_region_del_subregion(region->mem, ®ion->mmaps[i].mem= ); - } - } - - trace_vfio_region_exit(region->vbasedev->name, region->nr); -} - -void vfio_region_finalize(VFIORegion *region) -{ - int i; - - if (!region->mem) { - return; - } - - for (i =3D 0; i < region->nr_mmaps; i++) { - if (region->mmaps[i].mmap) { - munmap(region->mmaps[i].mmap, region->mmaps[i].size); - object_unparent(OBJECT(®ion->mmaps[i].mem)); - } - } - - object_unparent(OBJECT(region->mem)); - - g_free(region->mem); - g_free(region->mmaps); - - trace_vfio_region_finalize(region->vbasedev->name, region->nr); - - region->mem =3D NULL; - region->mmaps =3D NULL; - region->nr_mmaps =3D 0; - region->size =3D 0; - region->flags =3D 0; - region->nr =3D 0; -} - -void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled) -{ - int i; - - if (!region->mem) { - return; - } - - for (i =3D 0; i < region->nr_mmaps; i++) { - if (region->mmaps[i].mmap) { - memory_region_set_enabled(®ion->mmaps[i].mem, enabled); - } - } - - trace_vfio_region_mmaps_set_enabled(memory_region_name(region->mem), - enabled); -} - void vfio_reset_handler(void *opaque) { VFIOGroup *group; @@ -2983,83 +2472,6 @@ void vfio_put_base_device(VFIODevice *vbasedev) close(vbasedev->fd); } =20 -int vfio_get_region_info(VFIODevice *vbasedev, int index, - struct vfio_region_info **info) -{ - size_t argsz =3D sizeof(struct vfio_region_info); - - *info =3D g_malloc0(argsz); - - (*info)->index =3D index; -retry: - (*info)->argsz =3D argsz; - - if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) { - g_free(*info); - *info =3D NULL; - return -errno; - } - - if ((*info)->argsz > argsz) { - argsz =3D (*info)->argsz; - *info =3D g_realloc(*info, argsz); - - goto retry; - } - - return 0; -} - -int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type, - uint32_t subtype, struct vfio_region_info **i= nfo) -{ - int i; - - for (i =3D 0; i < vbasedev->num_regions; i++) { - struct vfio_info_cap_header *hdr; - struct vfio_region_info_cap_type *cap_type; - - if (vfio_get_region_info(vbasedev, i, info)) { - continue; - } - - hdr =3D vfio_get_region_info_cap(*info, VFIO_REGION_INFO_CAP_TYPE); - if (!hdr) { - g_free(*info); - continue; - } - - cap_type =3D container_of(hdr, struct vfio_region_info_cap_type, h= eader); - - trace_vfio_get_dev_region(vbasedev->name, i, - cap_type->type, cap_type->subtype); - - if (cap_type->type =3D=3D type && cap_type->subtype =3D=3D subtype= ) { - return 0; - } - - g_free(*info); - } - - *info =3D NULL; - return -ENODEV; -} - -bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_ty= pe) -{ - struct vfio_region_info *info =3D NULL; - bool ret =3D false; - - if (!vfio_get_region_info(vbasedev, region, &info)) { - if (vfio_get_region_info_cap(info, cap_type)) { - ret =3D true; - } - g_free(info); - } - - return ret; -} - /* * Interfaces for IBM EEH (Enhanced Error Handling) */ diff --git a/hw/vfio/helpers.c b/hw/vfio/helpers.c new file mode 100644 index 0000000000..717930b9d8 --- /dev/null +++ b/hw/vfio/helpers.c @@ -0,0 +1,611 @@ +/* + * low level and IOMMU backend agnostic helpers used by VFIO devices, + * related to regions, interrupts, capabilities + * + * Copyright Red Hat, Inc. 2012 + * + * Authors: + * Alex Williamson + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Based on qemu-kvm device-assignment: + * Adapted for KVM by Qumranet. + * Copyright (c) 2007, Neocleus, Alex Novik (alex@neocleus.com) + * Copyright (c) 2007, Neocleus, Guy Zana (guy@neocleus.com) + * Copyright (C) 2008, Qumranet, Amit Shah (amit.shah@qumranet.com) + * Copyright (C) 2008, Red Hat, Amit Shah (amit.shah@redhat.com) + * Copyright (C) 2008, IBM, Muli Ben-Yehuda (muli@il.ibm.com) + */ + +#include "qemu/osdep.h" +#include + +#include "hw/vfio/vfio-common.h" +#include "hw/vfio/vfio.h" +#include "hw/hw.h" +#include "trace.h" +#include "qapi/error.h" + +/* + * Common VFIO interrupt disable + */ +void vfio_disable_irqindex(VFIODevice *vbasedev, int index) +{ + struct vfio_irq_set irq_set =3D { + .argsz =3D sizeof(irq_set), + .flags =3D VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER, + .index =3D index, + .start =3D 0, + .count =3D 0, + }; + + ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); +} + +void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index) +{ + struct vfio_irq_set irq_set =3D { + .argsz =3D sizeof(irq_set), + .flags =3D VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK, + .index =3D index, + .start =3D 0, + .count =3D 1, + }; + + ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); +} + +void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index) +{ + struct vfio_irq_set irq_set =3D { + .argsz =3D sizeof(irq_set), + .flags =3D VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_MASK, + .index =3D index, + .start =3D 0, + .count =3D 1, + }; + + ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); +} + +static inline const char *action_to_str(int action) +{ + switch (action) { + case VFIO_IRQ_SET_ACTION_MASK: + return "MASK"; + case VFIO_IRQ_SET_ACTION_UNMASK: + return "UNMASK"; + case VFIO_IRQ_SET_ACTION_TRIGGER: + return "TRIGGER"; + default: + return "UNKNOWN ACTION"; + } +} + +static const char *index_to_str(VFIODevice *vbasedev, int index) +{ + if (vbasedev->type !=3D VFIO_DEVICE_TYPE_PCI) { + return NULL; + } + + switch (index) { + case VFIO_PCI_INTX_IRQ_INDEX: + return "INTX"; + case VFIO_PCI_MSI_IRQ_INDEX: + return "MSI"; + case VFIO_PCI_MSIX_IRQ_INDEX: + return "MSIX"; + case VFIO_PCI_ERR_IRQ_INDEX: + return "ERR"; + case VFIO_PCI_REQ_IRQ_INDEX: + return "REQ"; + default: + return NULL; + } +} + +int vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex, + int action, int fd, Error **errp) +{ + struct vfio_irq_set *irq_set; + int argsz, ret =3D 0; + const char *name; + int32_t *pfd; + + argsz =3D sizeof(*irq_set) + sizeof(*pfd); + + irq_set =3D g_malloc0(argsz); + irq_set->argsz =3D argsz; + irq_set->flags =3D VFIO_IRQ_SET_DATA_EVENTFD | action; + irq_set->index =3D index; + irq_set->start =3D subindex; + irq_set->count =3D 1; + pfd =3D (int32_t *)&irq_set->data; + *pfd =3D fd; + + if (ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set)) { + ret =3D -errno; + } + g_free(irq_set); + + if (!ret) { + return 0; + } + + error_setg_errno(errp, -ret, "VFIO_DEVICE_SET_IRQS failure"); + + name =3D index_to_str(vbasedev, index); + if (name) { + error_prepend(errp, "%s-%d: ", name, subindex); + } else { + error_prepend(errp, "index %d-%d: ", index, subindex); + } + error_prepend(errp, + "Failed to %s %s eventfd signaling for interrupt ", + fd < 0 ? "tear down" : "set up", action_to_str(action)); + return ret; +} + +/* + * IO Port/MMIO - Beware of the endians, VFIO is always little endian + */ +void vfio_region_write(void *opaque, hwaddr addr, + uint64_t data, unsigned size) +{ + VFIORegion *region =3D opaque; + VFIODevice *vbasedev =3D region->vbasedev; + union { + uint8_t byte; + uint16_t word; + uint32_t dword; + uint64_t qword; + } buf; + + switch (size) { + case 1: + buf.byte =3D data; + break; + case 2: + buf.word =3D cpu_to_le16(data); + break; + case 4: + buf.dword =3D cpu_to_le32(data); + break; + case 8: + buf.qword =3D cpu_to_le64(data); + break; + default: + hw_error("vfio: unsupported write size, %u bytes", size); + break; + } + + if (pwrite(vbasedev->fd, &buf, size, region->fd_offset + addr) !=3D si= ze) { + error_report("%s(%s:region%d+0x%"HWADDR_PRIx", 0x%"PRIx64 + ",%d) failed: %m", + __func__, vbasedev->name, region->nr, + addr, data, size); + } + + trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size); + + /* + * A read or write to a BAR always signals an INTx EOI. This will + * do nothing if not pending (including not in INTx mode). We assume + * that a BAR access is in response to an interrupt and that BAR + * accesses will service the interrupt. Unfortunately, we don't know + * which access will service the interrupt, so we're potentially + * getting quite a few host interrupts per guest interrupt. + */ + vbasedev->ops->vfio_eoi(vbasedev); +} + +uint64_t vfio_region_read(void *opaque, + hwaddr addr, unsigned size) +{ + VFIORegion *region =3D opaque; + VFIODevice *vbasedev =3D region->vbasedev; + union { + uint8_t byte; + uint16_t word; + uint32_t dword; + uint64_t qword; + } buf; + uint64_t data =3D 0; + + if (pread(vbasedev->fd, &buf, size, region->fd_offset + addr) !=3D siz= e) { + error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m", + __func__, vbasedev->name, region->nr, + addr, size); + return (uint64_t)-1; + } + switch (size) { + case 1: + data =3D buf.byte; + break; + case 2: + data =3D le16_to_cpu(buf.word); + break; + case 4: + data =3D le32_to_cpu(buf.dword); + break; + case 8: + data =3D le64_to_cpu(buf.qword); + break; + default: + hw_error("vfio: unsupported read size, %u bytes", size); + break; + } + + trace_vfio_region_read(vbasedev->name, region->nr, addr, size, data); + + /* Same as write above */ + vbasedev->ops->vfio_eoi(vbasedev); + + return data; +} + +const MemoryRegionOps vfio_region_ops =3D { + .read =3D vfio_region_read, + .write =3D vfio_region_write, + .endianness =3D DEVICE_LITTLE_ENDIAN, + .valid =3D { + .min_access_size =3D 1, + .max_access_size =3D 8, + }, + .impl =3D { + .min_access_size =3D 1, + .max_access_size =3D 8, + }, +}; + +int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size) +{ + vbmap->pages =3D REAL_HOST_PAGE_ALIGN(size) / qemu_real_host_page_size= (); + vbmap->size =3D ROUND_UP(vbmap->pages, sizeof(__u64) * BITS_PER_BYTE) / + BITS_PER_BYTE; + vbmap->bitmap =3D g_try_malloc0(vbmap->size); + if (!vbmap->bitmap) { + return -ENOMEM; + } + + return 0; +} + +struct vfio_info_cap_header * +vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id) +{ + struct vfio_info_cap_header *hdr; + + for (hdr =3D ptr + cap_offset; hdr !=3D ptr; hdr =3D ptr + hdr->next) { + if (hdr->id =3D=3D id) { + return hdr; + } + } + + return NULL; +} + +struct vfio_info_cap_header * +vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id) +{ + if (!(info->flags & VFIO_REGION_INFO_FLAG_CAPS)) { + return NULL; + } + + return vfio_get_cap((void *)info, info->cap_offset, id); +} + +struct vfio_info_cap_header * +vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id) +{ + if (!(info->flags & VFIO_DEVICE_FLAGS_CAPS)) { + return NULL; + } + + return vfio_get_cap((void *)info, info->cap_offset, id); +} + +static int vfio_setup_region_sparse_mmaps(VFIORegion *region, + struct vfio_region_info *info) +{ + struct vfio_info_cap_header *hdr; + struct vfio_region_info_cap_sparse_mmap *sparse; + int i, j; + + hdr =3D vfio_get_region_info_cap(info, VFIO_REGION_INFO_CAP_SPARSE_MMA= P); + if (!hdr) { + return -ENODEV; + } + + sparse =3D container_of(hdr, struct vfio_region_info_cap_sparse_mmap, = header); + + trace_vfio_region_sparse_mmap_header(region->vbasedev->name, + region->nr, sparse->nr_areas); + + region->mmaps =3D g_new0(VFIOMmap, sparse->nr_areas); + + for (i =3D 0, j =3D 0; i < sparse->nr_areas; i++) { + if (sparse->areas[i].size) { + trace_vfio_region_sparse_mmap_entry(i, sparse->areas[i].offset, + sparse->areas[i].offset + + sparse->areas[i].size - 1); + region->mmaps[j].offset =3D sparse->areas[i].offset; + region->mmaps[j].size =3D sparse->areas[i].size; + j++; + } + } + + region->nr_mmaps =3D j; + region->mmaps =3D g_realloc(region->mmaps, j * sizeof(VFIOMmap)); + + return 0; +} + +int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *regio= n, + int index, const char *name) +{ + struct vfio_region_info *info; + int ret; + + ret =3D vfio_get_region_info(vbasedev, index, &info); + if (ret) { + return ret; + } + + region->vbasedev =3D vbasedev; + region->flags =3D info->flags; + region->size =3D info->size; + region->fd_offset =3D info->offset; + region->nr =3D index; + + if (region->size) { + region->mem =3D g_new0(MemoryRegion, 1); + memory_region_init_io(region->mem, obj, &vfio_region_ops, + region, name, region->size); + + if (!vbasedev->no_mmap && + region->flags & VFIO_REGION_INFO_FLAG_MMAP) { + + ret =3D vfio_setup_region_sparse_mmaps(region, info); + + if (ret) { + region->nr_mmaps =3D 1; + region->mmaps =3D g_new0(VFIOMmap, region->nr_mmaps); + region->mmaps[0].offset =3D 0; + region->mmaps[0].size =3D region->size; + } + } + } + + g_free(info); + + trace_vfio_region_setup(vbasedev->name, index, name, + region->flags, region->fd_offset, region->size= ); + return 0; +} + +static void vfio_subregion_unmap(VFIORegion *region, int index) +{ + trace_vfio_region_unmap(memory_region_name(®ion->mmaps[index].mem), + region->mmaps[index].offset, + region->mmaps[index].offset + + region->mmaps[index].size - 1); + memory_region_del_subregion(region->mem, ®ion->mmaps[index].mem); + munmap(region->mmaps[index].mmap, region->mmaps[index].size); + object_unparent(OBJECT(®ion->mmaps[index].mem)); + region->mmaps[index].mmap =3D NULL; +} + +int vfio_region_mmap(VFIORegion *region) +{ + int i, prot =3D 0; + char *name; + + if (!region->mem) { + return 0; + } + + prot |=3D region->flags & VFIO_REGION_INFO_FLAG_READ ? PROT_READ : 0; + prot |=3D region->flags & VFIO_REGION_INFO_FLAG_WRITE ? PROT_WRITE : 0; + + for (i =3D 0; i < region->nr_mmaps; i++) { + region->mmaps[i].mmap =3D mmap(NULL, region->mmaps[i].size, prot, + MAP_SHARED, region->vbasedev->fd, + region->fd_offset + + region->mmaps[i].offset); + if (region->mmaps[i].mmap =3D=3D MAP_FAILED) { + int ret =3D -errno; + + trace_vfio_region_mmap_fault(memory_region_name(region->mem), = i, + region->fd_offset + + region->mmaps[i].offset, + region->fd_offset + + region->mmaps[i].offset + + region->mmaps[i].size - 1, ret); + + region->mmaps[i].mmap =3D NULL; + + for (i--; i >=3D 0; i--) { + vfio_subregion_unmap(region, i); + } + + return ret; + } + + name =3D g_strdup_printf("%s mmaps[%d]", + memory_region_name(region->mem), i); + memory_region_init_ram_device_ptr(®ion->mmaps[i].mem, + memory_region_owner(region->mem), + name, region->mmaps[i].size, + region->mmaps[i].mmap); + g_free(name); + memory_region_add_subregion(region->mem, region->mmaps[i].offset, + ®ion->mmaps[i].mem); + + trace_vfio_region_mmap(memory_region_name(®ion->mmaps[i].mem), + region->mmaps[i].offset, + region->mmaps[i].offset + + region->mmaps[i].size - 1); + } + + return 0; +} + +void vfio_region_unmap(VFIORegion *region) +{ + int i; + + if (!region->mem) { + return; + } + + for (i =3D 0; i < region->nr_mmaps; i++) { + if (region->mmaps[i].mmap) { + vfio_subregion_unmap(region, i); + } + } +} + +void vfio_region_exit(VFIORegion *region) +{ + int i; + + if (!region->mem) { + return; + } + + for (i =3D 0; i < region->nr_mmaps; i++) { + if (region->mmaps[i].mmap) { + memory_region_del_subregion(region->mem, ®ion->mmaps[i].mem= ); + } + } + + trace_vfio_region_exit(region->vbasedev->name, region->nr); +} + +void vfio_region_finalize(VFIORegion *region) +{ + int i; + + if (!region->mem) { + return; + } + + for (i =3D 0; i < region->nr_mmaps; i++) { + if (region->mmaps[i].mmap) { + munmap(region->mmaps[i].mmap, region->mmaps[i].size); + object_unparent(OBJECT(®ion->mmaps[i].mem)); + } + } + + object_unparent(OBJECT(region->mem)); + + g_free(region->mem); + g_free(region->mmaps); + + trace_vfio_region_finalize(region->vbasedev->name, region->nr); + + region->mem =3D NULL; + region->mmaps =3D NULL; + region->nr_mmaps =3D 0; + region->size =3D 0; + region->flags =3D 0; + region->nr =3D 0; +} + +void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled) +{ + int i; + + if (!region->mem) { + return; + } + + for (i =3D 0; i < region->nr_mmaps; i++) { + if (region->mmaps[i].mmap) { + memory_region_set_enabled(®ion->mmaps[i].mem, enabled); + } + } + + trace_vfio_region_mmaps_set_enabled(memory_region_name(region->mem), + enabled); +} + +int vfio_get_region_info(VFIODevice *vbasedev, int index, + struct vfio_region_info **info) +{ + size_t argsz =3D sizeof(struct vfio_region_info); + + *info =3D g_malloc0(argsz); + + (*info)->index =3D index; +retry: + (*info)->argsz =3D argsz; + + if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) { + g_free(*info); + *info =3D NULL; + return -errno; + } + + if ((*info)->argsz > argsz) { + argsz =3D (*info)->argsz; + *info =3D g_realloc(*info, argsz); + + goto retry; + } + + return 0; +} + +int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type, + uint32_t subtype, struct vfio_region_info **i= nfo) +{ + int i; + + for (i =3D 0; i < vbasedev->num_regions; i++) { + struct vfio_info_cap_header *hdr; + struct vfio_region_info_cap_type *cap_type; + + if (vfio_get_region_info(vbasedev, i, info)) { + continue; + } + + hdr =3D vfio_get_region_info_cap(*info, VFIO_REGION_INFO_CAP_TYPE); + if (!hdr) { + g_free(*info); + continue; + } + + cap_type =3D container_of(hdr, struct vfio_region_info_cap_type, h= eader); + + trace_vfio_get_dev_region(vbasedev->name, i, + cap_type->type, cap_type->subtype); + + if (cap_type->type =3D=3D type && cap_type->subtype =3D=3D subtype= ) { + return 0; + } + + g_free(*info); + } + + *info =3D NULL; + return -ENODEV; +} + +bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_ty= pe) +{ + struct vfio_region_info *info =3D NULL; + bool ret =3D false; + + if (!vfio_get_region_info(vbasedev, region, &info)) { + if (vfio_get_region_info_cap(info, cap_type)) { + ret =3D true; + } + g_free(info); + } + + return ret; +} diff --git a/hw/vfio/meson.build b/hw/vfio/meson.build index da9af297a0..3746c9f984 100644 --- a/hw/vfio/meson.build +++ b/hw/vfio/meson.build @@ -1,5 +1,6 @@ vfio_ss =3D ss.source_set() vfio_ss.add(files( + 'helpers.c', 'common.c', 'spapr.c', 'migration.c', --=20 2.41.0 From nobody Sun May 19 12:26:34 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1696328221; cv=none; d=zohomail.com; s=zohoarc; b=X794kg1ur82pZkv7ODSfIib7VIEL7POhFYeoM6vz2xFLujhs4Br/3AMKD20cr2B1DKJt9ME6groCxWI9iFwtmAvJVf0pJj23BiVyeylaobTgcN5aP9zOQCn2UAWzu6TnsV3h6OLMFk7MF7zioqHqc8KBxd0BOd0axHrJ1CpMBWM= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1696328221; h=Content-Transfer-Encoding:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=mKfdLlzvVRTQw0TCz+PbqKZGFM1dkOMT3xzK8NlQLZg=; b=cr9K/yEYQonb8QSLAiQStX3kO6DIPclEo7qaz7geReHglY8p7nuX21PEZ8m9DU/IcouFC200N6gsIYQR+h98TwbCzZPTKKqHJVDD00GSZHK1peQ+e700Py0eYxPSdRPxpocT9Rhl5RRny3DqvBkILMc18F/qoyNxPnyLImRCGXc= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696328221977565.4075632211096; Tue, 3 Oct 2023 03:17:01 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qncRl-0007UH-Mj; Tue, 03 Oct 2023 06:16:09 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRk-0007Tm-5Q for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:08 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.129.124]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRe-0004Rt-U3 for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:07 -0400 Received: from mimecast-mx02.redhat.com (mx-ext.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-349-pcfzqXyBPSGWXMUps8ArhQ-1; Tue, 03 Oct 2023 06:15:58 -0400 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.rdu2.redhat.com [10.11.54.9]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 1C09E29AB454; Tue, 3 Oct 2023 10:15:58 +0000 (UTC) Received: from laptop.redhat.com (unknown [10.39.192.172]) by smtp.corp.redhat.com (Postfix) with ESMTP id 80831492B16; Tue, 3 Oct 2023 10:15:55 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1696328162; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=mKfdLlzvVRTQw0TCz+PbqKZGFM1dkOMT3xzK8NlQLZg=; b=IZC6RvvWI0tBkWFFbFvTywvgN83dLr3s/zSknXvd8iW0MZMiECjX9+fa2Mp7K4EIQQCKef MZSwqp6yWaUgP3uRL4wWaO+tSd2ATVggP+inRXxBNCHjfwFi8DQKLP5/sxhlTwOUGWI9S6 vZyUCnQk+U6RYNf/IkJHWqLY1CQ0Yus= X-MC-Unique: pcfzqXyBPSGWXMUps8ArhQ-1 From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, zhenzhong.duan@intel.com, alex.williamson@redhat.com, clg@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com, joao.m.martins@oracle.com, peterx@redhat.com, kevin.tian@intel.com, yi.l.liu@intel.com, yi.y.sun@intel.com, chao.p.peng@intel.com, mjrosato@linux.ibm.com Subject: [PATCH v3 04/15] vfio/common: Propagate KVM_SET_DEVICE_ATTR error if any Date: Tue, 3 Oct 2023 12:14:01 +0200 Message-ID: <20231003101530.288864-5-eric.auger@redhat.com> In-Reply-To: <20231003101530.288864-1-eric.auger@redhat.com> References: <20231003101530.288864-1-eric.auger@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.1 on 10.11.54.9 Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=170.10.129.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H4=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=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: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @redhat.com) X-ZM-MESSAGEID: 1696328223113100009 Content-Type: text/plain; charset="utf-8" In the VFIO_SPAPR_TCE_v2_IOMMU container case, when KVM_SET_DEVICE_ATTR fails, we currently don't propagate the error as we do on the vfio_spapr_create_window() failure case. Let's align the code. Take the opportunity to reword the error message and make it more explicit. Signed-off-by: Eric Auger Reviewed-by: C=C3=A9dric Le Goater --- I think thise should end up in the if (!container->initialized) { if (!container->error) { path and call the error_propagate_prepend() --- hw/vfio/common.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 4e122fc4e4..c54a72ec80 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -878,11 +878,11 @@ static void vfio_listener_region_add(MemoryListener *= listener, QLIST_FOREACH(group, &container->group_list, container_nex= t) { param.groupfd =3D group->fd; if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &at= tr)) { - error_report("vfio: failed to setup fd %d " - "for a group with fd %d: %s", - param.tablefd, param.groupfd, - strerror(errno)); - return; + error_setg_errno(&err, errno, + "vfio: failed GROUP_SET_SPAPR_TCE= for " + "KVM VFIO device %d and group fd = %d", + param.tablefd, param.groupfd); + goto fail; } trace_vfio_spapr_group_attach(param.groupfd, param.tab= lefd); } --=20 2.41.0 From nobody Sun May 19 12:26:34 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1696328320; cv=none; d=zohomail.com; s=zohoarc; b=PgVXUkBoAKbEod+70ncHqW8rCwe5qAmNnsN0j62eZJFLdXxJY6BOw6Ts+r0MNwjCA3De+6bTRxmdTuzbqDKOi87e2bxKabvzsTVNQcq0SFeLVDIq0HzfOsw5RzJfLHZsefica73cca0RB2yY7I8HtfFub1/JZs623XplmAT6lUE= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1696328320; h=Content-Type:Content-Transfer-Encoding:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=850XWWEcM6vFOOAJCQ78JgSWAMqdDK6wLWc6c6eWiIY=; b=IdXFaSVQ4pAkXH5LmDwerRcThhosNDlCBYC4bK3lxCAIG/g9DxCJB/FWuH0Z02wy2uCoAtMVLXunFBkNBUSJqP7UG3nJqaSMHOAjx0nFUG8or88ADmJzzB3zKgHi5xH59SHECQJt1ckQXIzBnxPDZDNBtLvmRXNPMRXx07IDWPw= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696328320729865.2362646912205; Tue, 3 Oct 2023 03:18:40 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qncRo-0007V2-V2; Tue, 03 Oct 2023 06:16:12 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRm-0007UZ-6t for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:11 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.133.124]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRk-0004Sh-C4 for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:09 -0400 Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-654-EL3wgxkhPxexApZigGhxOQ-1; Tue, 03 Oct 2023 06:16:01 -0400 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.rdu2.redhat.com [10.11.54.9]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id EFE3C8015AB; Tue, 3 Oct 2023 10:16:00 +0000 (UTC) Received: from laptop.redhat.com (unknown [10.39.192.172]) by smtp.corp.redhat.com (Postfix) with ESMTP id 5F41D492B16; Tue, 3 Oct 2023 10:15:58 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1696328166; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=850XWWEcM6vFOOAJCQ78JgSWAMqdDK6wLWc6c6eWiIY=; b=f1rhZjPYROUartM8Kbs3f1nDv8fVRkpvsDQ20GoICkMzDgU7f/IAev9Omw6/N18A+iE09q g2Su1H4dCRBXmgUW2lPoZycJsnxOAIMLD/ObfxRe0pDTNFbFrNFLDjpaZXeAAhaQpyo85P zcPt8ho/5D8e7doAKi4KURAj6/hjDkY= X-MC-Unique: EL3wgxkhPxexApZigGhxOQ-1 From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, zhenzhong.duan@intel.com, alex.williamson@redhat.com, clg@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com, joao.m.martins@oracle.com, peterx@redhat.com, kevin.tian@intel.com, yi.l.liu@intel.com, yi.y.sun@intel.com, chao.p.peng@intel.com, mjrosato@linux.ibm.com Subject: [PATCH v3 05/15] vfio/common: Introduce vfio_container_add|del_section_window() Date: Tue, 3 Oct 2023 12:14:02 +0200 Message-ID: <20231003101530.288864-6-eric.auger@redhat.com> In-Reply-To: <20231003101530.288864-1-eric.auger@redhat.com> References: <20231003101530.288864-1-eric.auger@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.1 on 10.11.54.9 Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=170.10.133.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H3=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=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: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @redhat.com) X-ZM-MESSAGEID: 1696328322437100002 Introduce helper functions that isolate the code used for VFIO_SPAPR_TCE_v2_IOMMU. Those helpers hide implementation details beneath the container object and make the vfio_listener_region_add/del() implementations more readable. No code change intended. Signed-off-by: Eric Auger Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: C=C3=A9dric Le Goater --- hw/vfio/common.c | 156 +++++++++++++++++++++++++++-------------------- 1 file changed, 89 insertions(+), 67 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index c54a72ec80..0397788aa5 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -807,6 +807,92 @@ static bool vfio_get_section_iova_range(VFIOContainer = *container, return true; } =20 +static int vfio_container_add_section_window(VFIOContainer *container, + MemoryRegionSection *section, + Error **errp) +{ + VFIOHostDMAWindow *hostwin; + hwaddr pgsize =3D 0; + int ret; + + if (container->iommu_type !=3D VFIO_SPAPR_TCE_v2_IOMMU) { + return 0; + } + + /* For now intersections are not allowed, we may relax this later */ + QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { + if (ranges_overlap(hostwin->min_iova, + hostwin->max_iova - hostwin->min_iova + 1, + section->offset_within_address_space, + int128_get64(section->size))) { + error_setg(errp, + "region [0x%"PRIx64",0x%"PRIx64"] overlaps with existing" + "host DMA window [0x%"PRIx64",0x%"PRIx64"]", + section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(section->size) - 1, + hostwin->min_iova, hostwin->max_iova); + return -EINVAL; + } + } + + ret =3D vfio_spapr_create_window(container, section, &pgsize); + if (ret) { + error_setg_errno(errp, -ret, "Failed to create SPAPR window"); + return ret; + } + + vfio_host_win_add(container, section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(section->size) - 1, pgsize); +#ifdef CONFIG_KVM + if (kvm_enabled()) { + VFIOGroup *group; + IOMMUMemoryRegion *iommu_mr =3D IOMMU_MEMORY_REGION(section->mr); + struct kvm_vfio_spapr_tce param; + struct kvm_device_attr attr =3D { + .group =3D KVM_DEV_VFIO_GROUP, + .attr =3D KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE, + .addr =3D (uint64_t)(unsigned long)¶m, + }; + + if (!memory_region_iommu_get_attr(iommu_mr, IOMMU_ATTR_SPAPR_TCE_F= D, + ¶m.tablefd)) { + QLIST_FOREACH(group, &container->group_list, container_next) { + param.groupfd =3D group->fd; + if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr))= { + error_setg_errno(errp, errno, + "vfio: failed GROUP_SET_SPAPR_TCE for= " + "KVM VFIO device %d and group fd %d", + param.tablefd, param.groupfd); + return -errno; + } + trace_vfio_spapr_group_attach(param.groupfd, param.tablefd= ); + } + } + } +#endif + return 0; +} + +static void vfio_container_del_section_window(VFIOContainer *container, + MemoryRegionSection *section) +{ + if (container->iommu_type !=3D VFIO_SPAPR_TCE_v2_IOMMU) { + return; + } + + vfio_spapr_remove_window(container, + section->offset_within_address_space); + if (vfio_host_win_del(container, + section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(section->size) - 1) < 0) { + hw_error("%s: Cannot delete missing window at %"HWADDR_PRIx, + __func__, section->offset_within_address_space); + } +} + static void vfio_listener_region_add(MemoryListener *listener, MemoryRegionSection *section) { @@ -833,62 +919,8 @@ static void vfio_listener_region_add(MemoryListener *l= istener, return; } =20 - if (container->iommu_type =3D=3D VFIO_SPAPR_TCE_v2_IOMMU) { - hwaddr pgsize =3D 0; - - /* For now intersections are not allowed, we may relax this later = */ - QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { - if (ranges_overlap(hostwin->min_iova, - hostwin->max_iova - hostwin->min_iova + 1, - section->offset_within_address_space, - int128_get64(section->size))) { - error_setg(&err, - "region [0x%"PRIx64",0x%"PRIx64"] overlaps with existi= ng" - "host DMA window [0x%"PRIx64",0x%"PRIx64"]", - section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1, - hostwin->min_iova, hostwin->max_iova); - goto fail; - } - } - - ret =3D vfio_spapr_create_window(container, section, &pgsize); - if (ret) { - error_setg_errno(&err, -ret, "Failed to create SPAPR window"); - goto fail; - } - - vfio_host_win_add(container, section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1, pgsize); -#ifdef CONFIG_KVM - if (kvm_enabled()) { - VFIOGroup *group; - IOMMUMemoryRegion *iommu_mr =3D IOMMU_MEMORY_REGION(section->m= r); - struct kvm_vfio_spapr_tce param; - struct kvm_device_attr attr =3D { - .group =3D KVM_DEV_VFIO_GROUP, - .attr =3D KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE, - .addr =3D (uint64_t)(unsigned long)¶m, - }; - - if (!memory_region_iommu_get_attr(iommu_mr, IOMMU_ATTR_SPAPR_T= CE_FD, - ¶m.tablefd)) { - QLIST_FOREACH(group, &container->group_list, container_nex= t) { - param.groupfd =3D group->fd; - if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &at= tr)) { - error_setg_errno(&err, errno, - "vfio: failed GROUP_SET_SPAPR_TCE= for " - "KVM VFIO device %d and group fd = %d", - param.tablefd, param.groupfd); - goto fail; - } - trace_vfio_spapr_group_attach(param.groupfd, param.tab= lefd); - } - } - } -#endif + if (vfio_container_add_section_window(container, section, &err)) { + goto fail; } =20 hostwin =3D vfio_find_hostwin(container, iova, end); @@ -1105,17 +1137,7 @@ static void vfio_listener_region_del(MemoryListener = *listener, =20 memory_region_unref(section->mr); =20 - if (container->iommu_type =3D=3D VFIO_SPAPR_TCE_v2_IOMMU) { - vfio_spapr_remove_window(container, - section->offset_within_address_space); - if (vfio_host_win_del(container, - section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1) < 0) { - hw_error("%s: Cannot delete missing window at %"HWADDR_PRIx, - __func__, section->offset_within_address_space); - } - } + vfio_container_del_section_window(container, section); } =20 static int vfio_set_dirty_page_tracking(VFIOContainer *container, bool sta= rt) --=20 2.41.0 From nobody Sun May 19 12:26:34 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1696328325; cv=none; d=zohomail.com; s=zohoarc; b=K+SFfFysI4HS/hsLCTPMtlswOb2nYYYi0RWrfY55/l8UKrETK+EYkCnKhKR7RYYCzDdTK1KDZI14/Lf38x3/4miJTvjQPOYQAB6VP12SAgnZn8XxvOsn7xSbGRmzxx0MrGyfJHNwqysw4jE/XLMzBsuEsE3UmKNyAYY/gwdSuuQ= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1696328325; h=Content-Transfer-Encoding:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=L5b1eeQIjjRAhWFnzCyKsWFZNP/zYHrb3/4/DrZj/g0=; b=MsllWgAzeKQFXh6q6gl1uQzmP5DXt9v41EqHikKKUhd6KQ2IBIJFhMVEDb7FqOxr0G8a2A8SDSbPH8FDOEthexe/HDG8dpmedG8paeANAbJfox1nt2aqCmChteUWzmO6iMEG/LUIVKLNrWiACfDLDXswWRc0R12JdjDLtZr5LIM= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696328325573578.5356798443705; Tue, 3 Oct 2023 03:18:45 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qncRo-0007V3-Vh; Tue, 03 Oct 2023 06:16:13 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRk-0007Tu-Ln for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:08 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.133.124]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRi-0004SZ-Bv for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:08 -0400 Received: from mimecast-mx02.redhat.com (mx-ext.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-226-IfkyqlepNaavHeZGpjkqcA-1; Tue, 03 Oct 2023 06:16:04 -0400 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.rdu2.redhat.com [10.11.54.9]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id D0C4A3C11A0B; Tue, 3 Oct 2023 10:16:03 +0000 (UTC) Received: from laptop.redhat.com (unknown [10.39.192.172]) by smtp.corp.redhat.com (Postfix) with ESMTP id 3E82A492B16; Tue, 3 Oct 2023 10:16:01 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1696328165; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=L5b1eeQIjjRAhWFnzCyKsWFZNP/zYHrb3/4/DrZj/g0=; b=F+WcErinnitIjyUy3Jjo91s74MjpxtjCUtj/dsVzRF2eIQclBgTp+r49Wc1bD/sqD3hVrA qfgxQHqh3PF1jrDNccyBJEUqB5eHsFq5twBrL9EdmRKeE+AonTzgoJ+/Pq/SXNsgXLG0CU 7gjtjt+OYbbwcWZrMeGaYYXPHUavVPw= X-MC-Unique: IfkyqlepNaavHeZGpjkqcA-1 From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, zhenzhong.duan@intel.com, alex.williamson@redhat.com, clg@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com, joao.m.martins@oracle.com, peterx@redhat.com, kevin.tian@intel.com, yi.l.liu@intel.com, yi.y.sun@intel.com, chao.p.peng@intel.com, mjrosato@linux.ibm.com Subject: [PATCH v3 06/15] vfio/common: Extract out vfio_kvm_device_[add/del]_fd Date: Tue, 3 Oct 2023 12:14:03 +0200 Message-ID: <20231003101530.288864-7-eric.auger@redhat.com> In-Reply-To: <20231003101530.288864-1-eric.auger@redhat.com> References: <20231003101530.288864-1-eric.auger@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.1 on 10.11.54.9 Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=170.10.133.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H3=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=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: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @redhat.com) X-ZM-MESSAGEID: 1696328326800100003 Content-Type: text/plain; charset="utf-8" From: Zhenzhong Duan Introduce two new helpers, vfio_kvm_device_[add/del]_fd which take as input a file descriptor which can be either a group fd or a cdev fd. This uses the new KVM_DEV_VFIO_FILE VFIO KVM device group, which aliases to the legacy KVM_DEV_VFIO_GROUP. vfio_kvm_device_[add/del]_group then call those new helpers. Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: Eric Auger --- include/hw/vfio/vfio-common.h | 3 ++ hw/vfio/common.c | 69 +++++++++++++++++++++++------------ 2 files changed, 49 insertions(+), 23 deletions(-) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index e0483893d1..c4e7c3b4a7 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -226,6 +226,9 @@ struct vfio_device_info *vfio_get_device_info(int fd); int vfio_get_device(VFIOGroup *group, const char *name, VFIODevice *vbasedev, Error **errp); =20 +int vfio_kvm_device_add_fd(int fd, Error **errp); +int vfio_kvm_device_del_fd(int fd, Error **errp); + extern const MemoryRegionOps vfio_region_ops; typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList; extern VFIOGroupList vfio_group_list; diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 0397788aa5..d8ed432cb6 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -1818,17 +1818,17 @@ void vfio_reset_handler(void *opaque) } } =20 -static void vfio_kvm_device_add_group(VFIOGroup *group) +int vfio_kvm_device_add_fd(int fd, Error **errp) { #ifdef CONFIG_KVM struct kvm_device_attr attr =3D { - .group =3D KVM_DEV_VFIO_GROUP, - .attr =3D KVM_DEV_VFIO_GROUP_ADD, - .addr =3D (uint64_t)(unsigned long)&group->fd, + .group =3D KVM_DEV_VFIO_FILE, + .attr =3D KVM_DEV_VFIO_FILE_ADD, + .addr =3D (uint64_t)(unsigned long)&fd, }; =20 if (!kvm_enabled()) { - return; + return 0; } =20 if (vfio_kvm_device_fd < 0) { @@ -1837,38 +1837,61 @@ static void vfio_kvm_device_add_group(VFIOGroup *gr= oup) }; =20 if (kvm_vm_ioctl(kvm_state, KVM_CREATE_DEVICE, &cd)) { - error_report("Failed to create KVM VFIO device: %m"); - return; + error_setg_errno(errp, errno, "Failed to create KVM VFIO devic= e"); + return -errno; } =20 vfio_kvm_device_fd =3D cd.fd; } =20 if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { - error_report("Failed to add group %d to KVM VFIO device: %m", - group->groupid); + error_setg_errno(errp, errno, "Failed to add fd %d to KVM VFIO dev= ice", + fd); + return -errno; } #endif + return 0; +} + +int vfio_kvm_device_del_fd(int fd, Error **errp) +{ +#ifdef CONFIG_KVM + struct kvm_device_attr attr =3D { + .group =3D KVM_DEV_VFIO_FILE, + .attr =3D KVM_DEV_VFIO_FILE_DEL, + .addr =3D (uint64_t)(unsigned long)&fd, + }; + + if (vfio_kvm_device_fd < 0) { + error_setg(errp, "KVM VFIO device isn't created yet"); + return -EINVAL; + } + + if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { + error_setg_errno(errp, errno, + "Failed to remove fd %d from KVM VFIO device", fd= ); + return -errno; + } +#endif + return 0; +} + +static void vfio_kvm_device_add_group(VFIOGroup *group) +{ + Error *err =3D NULL; + + if (vfio_kvm_device_add_fd(group->fd, &err)) { + error_reportf_err(err, "group ID %d: ", group->groupid); + } } =20 static void vfio_kvm_device_del_group(VFIOGroup *group) { -#ifdef CONFIG_KVM - struct kvm_device_attr attr =3D { - .group =3D KVM_DEV_VFIO_GROUP, - .attr =3D KVM_DEV_VFIO_GROUP_DEL, - .addr =3D (uint64_t)(unsigned long)&group->fd, - }; + Error *err =3D NULL; =20 - if (vfio_kvm_device_fd < 0) { - return; + if (vfio_kvm_device_del_fd(group->fd, &err)) { + error_reportf_err(err, "group ID %d: ", group->groupid); } - - if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { - error_report("Failed to remove group %d from KVM VFIO device: %m", - group->groupid); - } -#endif } =20 static VFIOAddressSpace *vfio_get_address_space(AddressSpace *as) --=20 2.41.0 From nobody Sun May 19 12:26:34 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1696328235; cv=none; d=zohomail.com; s=zohoarc; b=mX7hWic1I9c7zLjs5lRJQV/jrCTUbewWjuV0RqwSOcnr0Uf/h+LAQ+CGa1+EVl1NQ4Lqg0nwOLAbzeKwQMmdKq0RubaZgaMoh8eQwypsdgrxy2P1dGi0V8wyAoo2PXB2XxgvM336GFxO/CpFNM0ukQN0jBiSMSIjKKcD8A7dli4= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1696328235; h=Content-Transfer-Encoding:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=IPoJcgI+jCf7Vo1qLO+xwE+xDSc3GVsZU7BpbCeoKUQ=; b=Jg/ZFjke52UnPYkePoVwVYp2vj4FKrwC3xJHHA6mV0YTBweJe/H5plSVbQI5rsjHRBf3SdaFdYrTb1Q1YtK8ri8ONMeXYo7/YYZpT4T1X9kW6hk2SaE8BFoY9MPFAgjsfeikW/0aHw2YwxGfzHpc2ssCWoShEp/BZE9xCKIsDyw= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696328235827159.62529357398887; Tue, 3 Oct 2023 03:17:15 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qncRr-0007Vv-1r; Tue, 03 Oct 2023 06:16:15 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRp-0007VK-N0 for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:13 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.129.124]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRn-0004TQ-M8 for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:13 -0400 Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-3-leCInF_aPnqpAXhsBSQYdA-1; Tue, 03 Oct 2023 06:16:07 -0400 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.rdu2.redhat.com [10.11.54.9]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id E8CB8185A790; Tue, 3 Oct 2023 10:16:06 +0000 (UTC) Received: from laptop.redhat.com (unknown [10.39.192.172]) by smtp.corp.redhat.com (Postfix) with ESMTP id 23411492B16; Tue, 3 Oct 2023 10:16:03 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1696328170; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=IPoJcgI+jCf7Vo1qLO+xwE+xDSc3GVsZU7BpbCeoKUQ=; b=Se2jW0n95L3rDTXlwFcyX0u11k0V+LVs5HacPBgSU9rcIpyuAIFWliw5I4x41z53VW2q0Z OVrn84paMy9cr9cCnBIB44Pk+CV6n9I1R+2BHr4aQ7uYqvsmajCkumKikRsPH1KFR4QLtQ Ehmuk3iXyA+O0ex7Tjx+K8Hch2RBjxo= X-MC-Unique: leCInF_aPnqpAXhsBSQYdA-1 From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, zhenzhong.duan@intel.com, alex.williamson@redhat.com, clg@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com, joao.m.martins@oracle.com, peterx@redhat.com, kevin.tian@intel.com, yi.l.liu@intel.com, yi.y.sun@intel.com, chao.p.peng@intel.com, mjrosato@linux.ibm.com Subject: [PATCH v3 07/15] vfio/pci: Introduce vfio_[attach/detach]_device Date: Tue, 3 Oct 2023 12:14:04 +0200 Message-ID: <20231003101530.288864-8-eric.auger@redhat.com> In-Reply-To: <20231003101530.288864-1-eric.auger@redhat.com> References: <20231003101530.288864-1-eric.auger@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.1 on 10.11.54.9 Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=170.10.129.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H4=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=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: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @redhat.com) X-ZM-MESSAGEID: 1696328236631100001 Content-Type: text/plain; charset="utf-8" We want the VFIO devices to be able to use two different IOMMU backends, the legacy VFIO one and the new iommufd one. Introduce vfio_[attach/detach]_device which aim at hiding the underlying IOMMU backend (IOCTLs, datatypes, ...). Once vfio_attach_device completes, the device is attached to a security context and its fd can be used. Conversely When vfio_detach_device completes, the device has been detached from the security context. At the moment only the implementation based on the legacy container/group exists. Let's use it from the vfio-pci device. Subsequent patches will handle other devices. We also take benefit of this patch to properly free vbasedev->name on failure. Signed-off-by: Eric Auger Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: C=C3=A9dric Le Goater --- v2 -> v3: - added trace_vfio_detach_device - added a comment explaining why we pass @name to vfio_attach_device although vbasedev->name is populated - free vbasedev->name and detach_device if needed --- include/hw/vfio/vfio-common.h | 3 ++ hw/vfio/common.c | 74 +++++++++++++++++++++++++++++++++++ hw/vfio/pci.c | 67 +++++++------------------------ hw/vfio/trace-events | 3 +- 4 files changed, 94 insertions(+), 53 deletions(-) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index c4e7c3b4a7..12fbfbc37d 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -225,6 +225,9 @@ void vfio_put_group(VFIOGroup *group); struct vfio_device_info *vfio_get_device_info(int fd); int vfio_get_device(VFIOGroup *group, const char *name, VFIODevice *vbasedev, Error **errp); +int vfio_attach_device(char *name, VFIODevice *vbasedev, + AddressSpace *as, Error **errp); +void vfio_detach_device(VFIODevice *vbasedev); =20 int vfio_kvm_device_add_fd(int fd, Error **errp); int vfio_kvm_device_del_fd(int fd, Error **errp); diff --git a/hw/vfio/common.c b/hw/vfio/common.c index d8ed432cb6..f4c33c9858 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -2611,3 +2611,77 @@ int vfio_eeh_as_op(AddressSpace *as, uint32_t op) } return vfio_eeh_container_op(container, op); } + +static int vfio_device_groupid(VFIODevice *vbasedev, Error **errp) +{ + char *tmp, group_path[PATH_MAX], *group_name; + int ret, groupid; + ssize_t len; + + tmp =3D g_strdup_printf("%s/iommu_group", vbasedev->sysfsdev); + len =3D readlink(tmp, group_path, sizeof(group_path)); + g_free(tmp); + + if (len <=3D 0 || len >=3D sizeof(group_path)) { + ret =3D len < 0 ? -errno : -ENAMETOOLONG; + error_setg_errno(errp, -ret, "no iommu_group found"); + return ret; + } + + group_path[len] =3D 0; + + group_name =3D basename(group_path); + if (sscanf(group_name, "%d", &groupid) !=3D 1) { + error_setg_errno(errp, errno, "failed to read %s", group_path); + return -errno; + } + return groupid; +} + +/* + * vfio_attach_device: attach a device to a security context + * @name and @vbasedev->name are likely to be different depending + * on the type of the device, hence the need for passing @name + */ +int vfio_attach_device(char *name, VFIODevice *vbasedev, + AddressSpace *as, Error **errp) +{ + int groupid =3D vfio_device_groupid(vbasedev, errp); + VFIODevice *vbasedev_iter; + VFIOGroup *group; + int ret; + + if (groupid < 0) { + return groupid; + } + + trace_vfio_attach_device(vbasedev->name, groupid); + + group =3D vfio_get_group(groupid, as, errp); + if (!group) { + return -ENOENT; + } + + QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { + if (strcmp(vbasedev_iter->name, vbasedev->name) =3D=3D 0) { + error_setg(errp, "device is already attached"); + vfio_put_group(group); + return -EBUSY; + } + } + ret =3D vfio_get_device(group, name, vbasedev, errp); + if (ret) { + vfio_put_group(group); + } + + return ret; +} + +void vfio_detach_device(VFIODevice *vbasedev) +{ + VFIOGroup *group =3D vbasedev->group; + + trace_vfio_detach_device(vbasedev->name, group->groupid); + vfio_put_base_device(vbasedev); + vfio_put_group(group); +} diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 898296fd54..60e10d0eee 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -2895,10 +2895,10 @@ static void vfio_populate_device(VFIOPCIDevice *vde= v, Error **errp) =20 static void vfio_pci_put_device(VFIOPCIDevice *vdev) { + vfio_detach_device(&vdev->vbasedev); + g_free(vdev->vbasedev.name); g_free(vdev->msix); - - vfio_put_base_device(&vdev->vbasedev); } =20 static void vfio_err_notifier_handler(void *opaque) @@ -3045,13 +3045,9 @@ static void vfio_realize(PCIDevice *pdev, Error **er= rp) { VFIOPCIDevice *vdev =3D VFIO_PCI(pdev); VFIODevice *vbasedev =3D &vdev->vbasedev; - VFIODevice *vbasedev_iter; - VFIOGroup *group; - char *tmp, *subsys, group_path[PATH_MAX], *group_name; + char *tmp, *subsys; Error *err =3D NULL; - ssize_t len; struct stat st; - int groupid; int i, ret; bool is_mdev; char uuid[UUID_FMT_LEN]; @@ -3082,39 +3078,6 @@ static void vfio_realize(PCIDevice *pdev, Error **er= rp) vbasedev->type =3D VFIO_DEVICE_TYPE_PCI; vbasedev->dev =3D DEVICE(vdev); =20 - tmp =3D g_strdup_printf("%s/iommu_group", vbasedev->sysfsdev); - len =3D readlink(tmp, group_path, sizeof(group_path)); - g_free(tmp); - - if (len <=3D 0 || len >=3D sizeof(group_path)) { - error_setg_errno(errp, len < 0 ? errno : ENAMETOOLONG, - "no iommu_group found"); - goto error; - } - - group_path[len] =3D 0; - - group_name =3D basename(group_path); - if (sscanf(group_name, "%d", &groupid) !=3D 1) { - error_setg_errno(errp, errno, "failed to read %s", group_path); - goto error; - } - - trace_vfio_realize(vbasedev->name, groupid); - - group =3D vfio_get_group(groupid, pci_device_iommu_address_space(pdev)= , errp); - if (!group) { - goto error; - } - - QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { - if (strcmp(vbasedev_iter->name, vbasedev->name) =3D=3D 0) { - error_setg(errp, "device is already attached"); - vfio_put_group(group); - goto error; - } - } - /* * Mediated devices *might* operate compatibly with discarding of RAM,= but * we cannot know for certain, it depends on whether the mdev vendor d= river @@ -3132,7 +3095,6 @@ static void vfio_realize(PCIDevice *pdev, Error **err= p) if (vbasedev->ram_block_discard_allowed && !is_mdev) { error_setg(errp, "x-balloon-allowed only potentially compatible " "with mdev devices"); - vfio_put_group(group); goto error; } =20 @@ -3143,17 +3105,17 @@ static void vfio_realize(PCIDevice *pdev, Error **e= rrp) name =3D g_strdup(vbasedev->name); } =20 - ret =3D vfio_get_device(group, name, vbasedev, errp); + ret =3D vfio_attach_device(name, vbasedev, + pci_device_iommu_address_space(pdev), errp); g_free(name); if (ret) { - vfio_put_group(group); goto error; } =20 vfio_populate_device(vdev, &err); if (err) { error_propagate(errp, err); - goto error; + goto out_detach; } =20 /* Get a copy of config space */ @@ -3163,7 +3125,7 @@ static void vfio_realize(PCIDevice *pdev, Error **err= p) if (ret < (int)MIN(pci_config_size(&vdev->pdev), vdev->config_size)) { ret =3D ret < 0 ? -errno : -EFAULT; error_setg_errno(errp, -ret, "failed to read device config space"); - goto error; + goto out_detach; } =20 /* vfio emulates a lot for us, but some bits need extra love */ @@ -3182,7 +3144,7 @@ static void vfio_realize(PCIDevice *pdev, Error **err= p) if (vdev->vendor_id !=3D PCI_ANY_ID) { if (vdev->vendor_id >=3D 0xffff) { error_setg(errp, "invalid PCI vendor ID provided"); - goto error; + goto out_detach; } vfio_add_emulated_word(vdev, PCI_VENDOR_ID, vdev->vendor_id, ~0); trace_vfio_pci_emulated_vendor_id(vbasedev->name, vdev->vendor_id); @@ -3193,7 +3155,7 @@ static void vfio_realize(PCIDevice *pdev, Error **err= p) if (vdev->device_id !=3D PCI_ANY_ID) { if (vdev->device_id > 0xffff) { error_setg(errp, "invalid PCI device ID provided"); - goto error; + goto out_detach; } vfio_add_emulated_word(vdev, PCI_DEVICE_ID, vdev->device_id, ~0); trace_vfio_pci_emulated_device_id(vbasedev->name, vdev->device_id); @@ -3204,7 +3166,7 @@ static void vfio_realize(PCIDevice *pdev, Error **err= p) if (vdev->sub_vendor_id !=3D PCI_ANY_ID) { if (vdev->sub_vendor_id > 0xffff) { error_setg(errp, "invalid PCI subsystem vendor ID provided"); - goto error; + goto out_detach; } vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_VENDOR_ID, vdev->sub_vendor_id, ~0); @@ -3215,7 +3177,7 @@ static void vfio_realize(PCIDevice *pdev, Error **err= p) if (vdev->sub_device_id !=3D PCI_ANY_ID) { if (vdev->sub_device_id > 0xffff) { error_setg(errp, "invalid PCI subsystem device ID provided"); - goto error; + goto out_detach; } vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_ID, vdev->sub_device_id= , ~0); trace_vfio_pci_emulated_sub_device_id(vbasedev->name, @@ -3248,7 +3210,7 @@ static void vfio_realize(PCIDevice *pdev, Error **err= p) vfio_msix_early_setup(vdev, &err); if (err) { error_propagate(errp, err); - goto error; + goto out_detach; } =20 vfio_bars_register(vdev); @@ -3364,14 +3326,16 @@ out_deregister: out_teardown: vfio_teardown_msi(vdev); vfio_bars_exit(vdev); +out_detach: + vfio_detach_device(vbasedev); error: error_prepend(errp, VFIO_MSG_PREFIX, vbasedev->name); + g_free(vbasedev->name); } =20 static void vfio_instance_finalize(Object *obj) { VFIOPCIDevice *vdev =3D VFIO_PCI(obj); - VFIOGroup *group =3D vdev->vbasedev.group; =20 vfio_display_finalize(vdev); vfio_bars_finalize(vdev); @@ -3385,7 +3349,6 @@ static void vfio_instance_finalize(Object *obj) * g_free(vdev->igd_opregion); */ vfio_pci_put_device(vdev); - vfio_put_group(group); } =20 static void vfio_exitfn(PCIDevice *pdev) diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index 0ba3c5a0e2..8ac13eb106 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -37,7 +37,8 @@ vfio_pci_hot_reset_dep_devices(int domain, int bus, int s= lot, int function, int vfio_pci_hot_reset_result(const char *name, const char *result) "%s hot re= set: %s" vfio_populate_device_config(const char *name, unsigned long size, unsigned= long offset, unsigned long flags) "Device %s config:\n size: 0x%lx, offse= t: 0x%lx, flags: 0x%lx" vfio_populate_device_get_irq_info_failure(const char *errstr) "VFIO_DEVICE= _GET_IRQ_INFO failure: %s" -vfio_realize(const char *name, int group_id) " (%s) group %d" +vfio_attach_device(const char *name, int group_id) " (%s) group %d" +vfio_detach_device(const char *name, int group_id) " (%s) group %d" vfio_mdev(const char *name, bool is_mdev) " (%s) is_mdev %d" vfio_add_ext_cap_dropped(const char *name, uint16_t cap, uint16_t offset) = "%s 0x%x@0x%x" vfio_pci_reset(const char *name) " (%s)" --=20 2.41.0 From nobody Sun May 19 12:26:34 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1696328299; cv=none; d=zohomail.com; s=zohoarc; b=GgIaZ4Lgk1nVeQo+yS8bnIojD4D4lkLNTng0Uqdy7lwI2umAoA8w3olQfjcQRqZypHmocIvG2u9YyZG1weN8+FMKzj/wE1JfYZmifWi0gp0n2nSrryrXOeB9yIZUxjcuIc8gAw7Nc8Kv/Z3kNO3JSoMqkSPjVtr+Ui5XeRkuKFA= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1696328299; h=Content-Transfer-Encoding:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=UFggz0IZIZHL+e/Y7lXZHgjy/eJs0Ir+JTDyvWOWpPs=; b=hsIybaDZji/A7Vhmw/KN8lrFyifCD2DQDIpcBcNsQNMUrJnqp7yswbL5Vy0Va65+KuQRcJYLja0wfzjJE/M4waaSVRMlKpyHJNUSd40BZgObps99m0PBUVJkEQBr2J3ipTmsvGncb2veFgmPEBe6zZDeepSNZSNvaoLoWzRTVqA= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696328299431489.27465730896836; Tue, 3 Oct 2023 03:18:19 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qncRt-0007WX-NO; Tue, 03 Oct 2023 06:16:17 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRr-0007Vz-Nh for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:15 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.133.124]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRq-0004Ti-6N for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:15 -0400 Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-584-QtP-R9IFM9SARbeYBWv7cQ-1; Tue, 03 Oct 2023 06:16:10 -0400 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.rdu2.redhat.com [10.11.54.9]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id CC82C800B35; Tue, 3 Oct 2023 10:16:09 +0000 (UTC) Received: from laptop.redhat.com (unknown [10.39.192.172]) by smtp.corp.redhat.com (Postfix) with ESMTP id 3B594492B16; Tue, 3 Oct 2023 10:16:07 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1696328173; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=UFggz0IZIZHL+e/Y7lXZHgjy/eJs0Ir+JTDyvWOWpPs=; b=KkPBLbdZRU6Y5ncrM+dwPAXso/FIX3TTB998CbcTX3LFJxYwCOZgp1xdfWLAza9taXKL/3 MUIAAadlf6vKfjIN3pb9KnvlYRTHRIUYU5VUSyauL8Vm1bN5PeCvoRsTAS8+rl1vNd71Qh HHZHsSEqwnffsSy5XtVqJ/Apu4Kwv8Y= X-MC-Unique: QtP-R9IFM9SARbeYBWv7cQ-1 From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, zhenzhong.duan@intel.com, alex.williamson@redhat.com, clg@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com, joao.m.martins@oracle.com, peterx@redhat.com, kevin.tian@intel.com, yi.l.liu@intel.com, yi.y.sun@intel.com, chao.p.peng@intel.com, mjrosato@linux.ibm.com Subject: [PATCH v3 08/15] vfio/platform: Use vfio_[attach/detach]_device Date: Tue, 3 Oct 2023 12:14:05 +0200 Message-ID: <20231003101530.288864-9-eric.auger@redhat.com> In-Reply-To: <20231003101530.288864-1-eric.auger@redhat.com> References: <20231003101530.288864-1-eric.auger@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.1 on 10.11.54.9 Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=170.10.133.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H3=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=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: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @redhat.com) X-ZM-MESSAGEID: 1696328300347100001 Content-Type: text/plain; charset="utf-8" Let the vfio-platform device use vfio_attach_device() and vfio_detach_device(), hence hiding the details of the used IOMMU backend. Drop the trace event for vfio-platform as we have similar one in vfio_attach_device. Signed-off-by: Eric Auger Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: C=C3=A9dric Le Goater --- hw/vfio/platform.c | 43 +++---------------------------------------- hw/vfio/trace-events | 1 - 2 files changed, 3 insertions(+), 41 deletions(-) diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c index 5af73f9287..8e3d4ac458 100644 --- a/hw/vfio/platform.c +++ b/hw/vfio/platform.c @@ -529,12 +529,7 @@ static VFIODeviceOps vfio_platform_ops =3D { */ static int vfio_base_device_init(VFIODevice *vbasedev, Error **errp) { - VFIOGroup *group; - VFIODevice *vbasedev_iter; - char *tmp, group_path[PATH_MAX], *group_name; - ssize_t len; struct stat st; - int groupid; int ret; =20 /* @sysfsdev takes precedence over @host */ @@ -557,47 +552,15 @@ static int vfio_base_device_init(VFIODevice *vbasedev= , Error **errp) return -errno; } =20 - tmp =3D g_strdup_printf("%s/iommu_group", vbasedev->sysfsdev); - len =3D readlink(tmp, group_path, sizeof(group_path)); - g_free(tmp); - - if (len < 0 || len >=3D sizeof(group_path)) { - ret =3D len < 0 ? -errno : -ENAMETOOLONG; - error_setg_errno(errp, -ret, "no iommu_group found"); - return ret; - } - - group_path[len] =3D 0; - - group_name =3D basename(group_path); - if (sscanf(group_name, "%d", &groupid) !=3D 1) { - error_setg_errno(errp, errno, "failed to read %s", group_path); - return -errno; - } - - trace_vfio_platform_base_device_init(vbasedev->name, groupid); - - group =3D vfio_get_group(groupid, &address_space_memory, errp); - if (!group) { - return -ENOENT; - } - - QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { - if (strcmp(vbasedev_iter->name, vbasedev->name) =3D=3D 0) { - error_setg(errp, "device is already attached"); - vfio_put_group(group); - return -EBUSY; - } - } - ret =3D vfio_get_device(group, vbasedev->name, vbasedev, errp); + ret =3D vfio_attach_device(vbasedev->name, vbasedev, + &address_space_memory, errp); if (ret) { - vfio_put_group(group); return ret; } =20 ret =3D vfio_populate_device(vbasedev, errp); if (ret) { - vfio_put_group(group); + vfio_detach_device(vbasedev); } =20 return ret; diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index 8ac13eb106..0eb2387cf2 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -121,7 +121,6 @@ vfio_get_dirty_bitmap(int fd, uint64_t iova, uint64_t s= ize, uint64_t bitmap_size vfio_iommu_map_dirty_notify(uint64_t iova_start, uint64_t iova_end) "iommu= dirty @ 0x%"PRIx64" - 0x%"PRIx64 =20 # platform.c -vfio_platform_base_device_init(char *name, int groupid) "%s belongs to gro= up #%d" vfio_platform_realize(char *name, char *compat) "vfio device %s, compat = =3D %s" vfio_platform_eoi(int pin, int fd) "EOI IRQ pin %d (fd=3D%d)" vfio_platform_intp_mmap_enable(int pin) "IRQ #%d still active, stay in slo= w path" --=20 2.41.0 From nobody Sun May 19 12:26:34 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1696328228; cv=none; d=zohomail.com; s=zohoarc; b=ldiomgsgzZeBY0kt6e6qRTHxKXeUY8aO8Yw2p+OBkLjIDs8KQZ9lt9Hdk1Hhw2ONCr8VzaanF93JV6OVP96YFu4QWARf7OJB/cVNkXA84SfFnHBpimQz+ah+lkJiUI9JCXAusWwR0pBPBrUjbdagGVG86lDqDudriMGtMBh5lkU= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1696328228; h=Content-Transfer-Encoding:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=8Ha2YcahuKguXOu+iE4becfZ8BtWLkSQ+T0GPkBk3uM=; b=oGNMGQ8WrFpLCo9fSg5ln775cdy54Y0mBZ1v009MhDmty7/NV4lusclQ8pfv7avni1cAZbzYQuuSLqcY07dXqVO+XINGMd+5b+hYlElhwaWISfHw+X0PwV65RFX30VfBsJf9DkbjKnqItwlSPcmxumBSqYOQ3S9g4y23ngRITuU= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696328228511907.4044092611817; Tue, 3 Oct 2023 03:17:08 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qncS2-0007Xs-M3; Tue, 03 Oct 2023 06:16:26 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRz-0007Wp-UW for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:23 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.129.124]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRy-0004Ud-2N for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:23 -0400 Received: from mimecast-mx02.redhat.com (mx-ext.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-175-CsMJO4V5NL2HFlCdalgdUQ-1; Tue, 03 Oct 2023 06:16:13 -0400 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.rdu2.redhat.com [10.11.54.9]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id AECB93C11A07; Tue, 3 Oct 2023 10:16:12 +0000 (UTC) Received: from laptop.redhat.com (unknown [10.39.192.172]) by smtp.corp.redhat.com (Postfix) with ESMTP id 1E4DB492B16; Tue, 3 Oct 2023 10:16:09 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1696328181; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=8Ha2YcahuKguXOu+iE4becfZ8BtWLkSQ+T0GPkBk3uM=; b=AuT925Ex5GnBA9Ramq3k/wdgM1pkPNMgDKyzZ6SKgJUmc4Pz0uEltdUZehG4QNKuBtBDpi iS56btjj/rRgo/WgnjcpdPsEOi+WZk7k3WzrxZLpM7q0iCqYq8PHQc6U0tQzyIcPpLEryw wLnmGb7d7r6KM1JrAb7a5tlESIrmReI= X-MC-Unique: CsMJO4V5NL2HFlCdalgdUQ-1 From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, zhenzhong.duan@intel.com, alex.williamson@redhat.com, clg@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com, joao.m.martins@oracle.com, peterx@redhat.com, kevin.tian@intel.com, yi.l.liu@intel.com, yi.y.sun@intel.com, chao.p.peng@intel.com, mjrosato@linux.ibm.com Subject: [PATCH v3 09/15] vfio/ap: Use vfio_[attach/detach]_device Date: Tue, 3 Oct 2023 12:14:06 +0200 Message-ID: <20231003101530.288864-10-eric.auger@redhat.com> In-Reply-To: <20231003101530.288864-1-eric.auger@redhat.com> References: <20231003101530.288864-1-eric.auger@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.1 on 10.11.54.9 Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=170.10.129.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H4=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=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: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @redhat.com) X-ZM-MESSAGEID: 1696328229087100002 Content-Type: text/plain; charset="utf-8" Let the vfio-ap device use vfio_attach_device() and vfio_detach_device(), hence hiding the details of the used IOMMU backend. We take the opportunity to use g_path_get_basename() which is prefered, as suggested by 3e015d815b ("use g_path_get_basename instead of basename") Signed-off-by: Eric Auger Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: C=C3=A9dric Le Goater Reviewed-by: Matthew Rosato --- v2 -> v3: - Mention g_path_get_basename in commit message and properly free vbasedev->name, call vfio_detach_device --- hw/vfio/ap.c | 70 ++++++++++------------------------------------------ 1 file changed, 13 insertions(+), 57 deletions(-) diff --git a/hw/vfio/ap.c b/hw/vfio/ap.c index 6e21d1da5a..d0b587b3b1 100644 --- a/hw/vfio/ap.c +++ b/hw/vfio/ap.c @@ -53,40 +53,6 @@ struct VFIODeviceOps vfio_ap_ops =3D { .vfio_compute_needs_reset =3D vfio_ap_compute_needs_reset, }; =20 -static void vfio_ap_put_device(VFIOAPDevice *vapdev) -{ - g_free(vapdev->vdev.name); - vfio_put_base_device(&vapdev->vdev); -} - -static VFIOGroup *vfio_ap_get_group(VFIOAPDevice *vapdev, Error **errp) -{ - GError *gerror =3D NULL; - char *symlink, *group_path; - int groupid; - - symlink =3D g_strdup_printf("%s/iommu_group", vapdev->vdev.sysfsdev); - group_path =3D g_file_read_link(symlink, &gerror); - g_free(symlink); - - if (!group_path) { - error_setg(errp, "%s: no iommu_group found for %s: %s", - TYPE_VFIO_AP_DEVICE, vapdev->vdev.sysfsdev, gerror->mes= sage); - g_error_free(gerror); - return NULL; - } - - if (sscanf(basename(group_path), "%d", &groupid) !=3D 1) { - error_setg(errp, "vfio: failed to read %s", group_path); - g_free(group_path); - return NULL; - } - - g_free(group_path); - - return vfio_get_group(groupid, &address_space_memory, errp); -} - static void vfio_ap_req_notifier_handler(void *opaque) { VFIOAPDevice *vapdev =3D opaque; @@ -189,22 +155,15 @@ static void vfio_ap_unregister_irq_notifier(VFIOAPDev= ice *vapdev, static void vfio_ap_realize(DeviceState *dev, Error **errp) { int ret; - char *mdevid; Error *err =3D NULL; - VFIOGroup *vfio_group; APDevice *apdev =3D AP_DEVICE(dev); VFIOAPDevice *vapdev =3D VFIO_AP_DEVICE(apdev); + VFIODevice *vbasedev =3D &vapdev->vdev; =20 - vfio_group =3D vfio_ap_get_group(vapdev, errp); - if (!vfio_group) { - return; - } - - vapdev->vdev.ops =3D &vfio_ap_ops; - vapdev->vdev.type =3D VFIO_DEVICE_TYPE_AP; - mdevid =3D basename(vapdev->vdev.sysfsdev); - vapdev->vdev.name =3D g_strdup_printf("%s", mdevid); - vapdev->vdev.dev =3D dev; + vbasedev->name =3D g_path_get_basename(vbasedev->sysfsdev); + vbasedev->ops =3D &vfio_ap_ops; + vbasedev->type =3D VFIO_DEVICE_TYPE_AP; + vbasedev->dev =3D dev; =20 /* * vfio-ap devices operate in a way compatible with discarding of @@ -214,9 +173,11 @@ static void vfio_ap_realize(DeviceState *dev, Error **= errp) */ vapdev->vdev.ram_block_discard_allowed =3D true; =20 - ret =3D vfio_get_device(vfio_group, mdevid, &vapdev->vdev, errp); + ret =3D vfio_attach_device(vbasedev->name, vbasedev, + &address_space_memory, errp); if (ret) { - goto out_get_dev_err; + g_free(vbasedev->name); + return; } =20 vfio_ap_register_irq_notifier(vapdev, VFIO_AP_REQ_IRQ_INDEX, &err); @@ -225,25 +186,20 @@ static void vfio_ap_realize(DeviceState *dev, Error *= *errp) * Report this error, but do not make it a failing condition. * Lack of this IRQ in the host does not prevent normal operation. */ + vfio_detach_device(vbasedev); error_report_err(err); + g_free(vbasedev->name); } - - return; - -out_get_dev_err: - vfio_ap_put_device(vapdev); - vfio_put_group(vfio_group); } =20 static void vfio_ap_unrealize(DeviceState *dev) { APDevice *apdev =3D AP_DEVICE(dev); VFIOAPDevice *vapdev =3D VFIO_AP_DEVICE(apdev); - VFIOGroup *group =3D vapdev->vdev.group; =20 vfio_ap_unregister_irq_notifier(vapdev, VFIO_AP_REQ_IRQ_INDEX); - vfio_ap_put_device(vapdev); - vfio_put_group(group); + vfio_detach_device(&vapdev->vdev); + g_free(vapdev->vdev.name); } =20 static Property vfio_ap_properties[] =3D { --=20 2.41.0 From nobody Sun May 19 12:26:34 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1696328291; cv=none; d=zohomail.com; s=zohoarc; b=MVNrV4vHFMBUJOXBUIwgMgyqe99TlISP5qHaRMBPe+AO+RkJJl/LrssicaB9Ep0eRn0MLvGwv7zoHeS+zGKNw8eLDsfXm0BRZWqn3rxC6Z5xQptEA/wzP5SJAGU134d0UeVfBrgj0ftMfVy7A1sOe6uudlb11uLFnN0pMLa/0iI= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1696328291; h=Content-Transfer-Encoding:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=JSId7hJ0P/pfV87hOdGsmRXamFRjFDlrbrHHQNjGa7Y=; b=QOY/BFqvcPUgXviK1czIPzUUkvrTC0TTFn9jDyaJSlM53dAZpkjoc1S1SXFZDqEThBK9BzxH7bkzTcwgRbh+O3NG250evyKghB7STcEouA2WJMh6ft+XtHAh4If3xoMMceTNiCCrGC3PvWdsguX1kJvOuoBV6cX3qC8OJFHy7QU= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 169632829101454.16309660572972; Tue, 3 Oct 2023 03:18:11 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qncS1-0007XL-BV; Tue, 03 Oct 2023 06:16:25 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRy-0007Wc-0n for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:23 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.133.124]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncRv-0004U8-Q6 for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:21 -0400 Received: from mimecast-mx02.redhat.com (mx-ext.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-368-fuYVlayCMe-t-u9HYY9-LQ-1; Tue, 03 Oct 2023 06:16:16 -0400 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.rdu2.redhat.com [10.11.54.9]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 8E3BA1C0CCA7; Tue, 3 Oct 2023 10:16:15 +0000 (UTC) Received: from laptop.redhat.com (unknown [10.39.192.172]) by smtp.corp.redhat.com (Postfix) with ESMTP id F2591492B16; Tue, 3 Oct 2023 10:16:12 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1696328178; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=JSId7hJ0P/pfV87hOdGsmRXamFRjFDlrbrHHQNjGa7Y=; b=Yw4J1jw+hlWJS16wEXV4bAMr7fD1k7DapNyP7FAPQMjL5ZvT9FFjjy1Oq7Mfri1Bhv8en8 JMx0pRqFD2lUE+9+NBQKV9bzAg+0qfXK2+ieEy8HXy5VVwE26LyyxM3IfrolNynZeEoJ51 /jvIdqAueD9r6IcKMe0bTjuhmg2iUG4= X-MC-Unique: fuYVlayCMe-t-u9HYY9-LQ-1 From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, zhenzhong.duan@intel.com, alex.williamson@redhat.com, clg@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com, joao.m.martins@oracle.com, peterx@redhat.com, kevin.tian@intel.com, yi.l.liu@intel.com, yi.y.sun@intel.com, chao.p.peng@intel.com, mjrosato@linux.ibm.com Subject: [PATCH v3 10/15] vfio/ccw: Use vfio_[attach/detach]_device Date: Tue, 3 Oct 2023 12:14:07 +0200 Message-ID: <20231003101530.288864-11-eric.auger@redhat.com> In-Reply-To: <20231003101530.288864-1-eric.auger@redhat.com> References: <20231003101530.288864-1-eric.auger@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.1 on 10.11.54.9 Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=170.10.133.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H3=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=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: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @redhat.com) X-ZM-MESSAGEID: 1696328292863100001 Content-Type: text/plain; charset="utf-8" Let the vfio-ccw device use vfio_attach_device() and vfio_detach_device(), hence hiding the details of the used IOMMU backend. Note that the migration reduces the following trace "vfio: subchannel %s has already been attached" (featuring cssid.ssid.devid) into "device is already attached" Also now all the devices have been migrated to use the new vfio_attach_device/vfio_detach_device API, let's turn the legacy functions into static functions, local to container.c. Signed-off-by: Eric Auger Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: Matthew Rosato --- v2 -> v3: - Hopefully fix confusion beteen vbasedev->name, mdevid and sysfsdev while keeping into account Matthew's comment https://lore.kernel.org/qemu-devel/6e04ab8f-dc84-e9c2-deea-2b6b31678b53@l= inux.ibm.com/ --- include/hw/vfio/vfio-common.h | 5 -- hw/vfio/ccw.c | 122 +++++++++------------------------- hw/vfio/common.c | 10 +-- 3 files changed, 37 insertions(+), 100 deletions(-) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index 12fbfbc37d..c486bdef2a 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -202,7 +202,6 @@ typedef struct { hwaddr pages; } VFIOBitmap; =20 -void vfio_put_base_device(VFIODevice *vbasedev); void vfio_disable_irqindex(VFIODevice *vbasedev, int index); void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index); void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index); @@ -220,11 +219,7 @@ void vfio_region_unmap(VFIORegion *region); void vfio_region_exit(VFIORegion *region); void vfio_region_finalize(VFIORegion *region); void vfio_reset_handler(void *opaque); -VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp); -void vfio_put_group(VFIOGroup *group); struct vfio_device_info *vfio_get_device_info(int fd); -int vfio_get_device(VFIOGroup *group, const char *name, - VFIODevice *vbasedev, Error **errp); int vfio_attach_device(char *name, VFIODevice *vbasedev, AddressSpace *as, Error **errp); void vfio_detach_device(VFIODevice *vbasedev); diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c index 1e2fce83b0..84eafb2e87 100644 --- a/hw/vfio/ccw.c +++ b/hw/vfio/ccw.c @@ -572,88 +572,15 @@ static void vfio_ccw_put_region(VFIOCCWDevice *vcdev) g_free(vcdev->io_region); } =20 -static void vfio_ccw_put_device(VFIOCCWDevice *vcdev) -{ - g_free(vcdev->vdev.name); - vfio_put_base_device(&vcdev->vdev); -} - -static void vfio_ccw_get_device(VFIOGroup *group, VFIOCCWDevice *vcdev, - Error **errp) -{ - S390CCWDevice *cdev =3D S390_CCW_DEVICE(vcdev); - char *name =3D g_strdup_printf("%x.%x.%04x", cdev->hostid.cssid, - cdev->hostid.ssid, - cdev->hostid.devid); - VFIODevice *vbasedev; - - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (strcmp(vbasedev->name, name) =3D=3D 0) { - error_setg(errp, "vfio: subchannel %s has already been attache= d", - name); - goto out_err; - } - } - - /* - * All vfio-ccw devices are believed to operate in a way compatible wi= th - * discarding of memory in RAM blocks, ie. pages pinned in the host are - * in the current working set of the guest driver and therefore never - * overlap e.g., with pages available to the guest balloon driver. Th= is - * needs to be set before vfio_get_device() for vfio common to handle - * ram_block_discard_disable(). - */ - vcdev->vdev.ram_block_discard_allowed =3D true; - - if (vfio_get_device(group, cdev->mdevid, &vcdev->vdev, errp)) { - goto out_err; - } - - vcdev->vdev.ops =3D &vfio_ccw_ops; - vcdev->vdev.type =3D VFIO_DEVICE_TYPE_CCW; - vcdev->vdev.name =3D name; - vcdev->vdev.dev =3D DEVICE(vcdev); - - return; - -out_err: - g_free(name); -} - -static VFIOGroup *vfio_ccw_get_group(S390CCWDevice *cdev, Error **errp) -{ - char *tmp, group_path[PATH_MAX]; - ssize_t len; - int groupid; - - tmp =3D g_strdup_printf("/sys/bus/css/devices/%x.%x.%04x/%s/iommu_grou= p", - cdev->hostid.cssid, cdev->hostid.ssid, - cdev->hostid.devid, cdev->mdevid); - len =3D readlink(tmp, group_path, sizeof(group_path)); - g_free(tmp); - - if (len <=3D 0 || len >=3D sizeof(group_path)) { - error_setg(errp, "vfio: no iommu_group found"); - return NULL; - } - - group_path[len] =3D 0; - - if (sscanf(basename(group_path), "%d", &groupid) !=3D 1) { - error_setg(errp, "vfio: failed to read %s", group_path); - return NULL; - } - - return vfio_get_group(groupid, &address_space_memory, errp); -} - static void vfio_ccw_realize(DeviceState *dev, Error **errp) { - VFIOGroup *group; S390CCWDevice *cdev =3D S390_CCW_DEVICE(dev); VFIOCCWDevice *vcdev =3D VFIO_CCW(cdev); S390CCWDeviceClass *cdc =3D S390_CCW_DEVICE_GET_CLASS(cdev); + VFIODevice *vbasedev =3D &vcdev->vdev; Error *err =3D NULL; + char *name; + int ret; =20 /* Call the class init function for subchannel. */ if (cdc->realize) { @@ -663,14 +590,31 @@ static void vfio_ccw_realize(DeviceState *dev, Error = **errp) } } =20 - group =3D vfio_ccw_get_group(cdev, &err); - if (!group) { - goto out_group_err; - } + name =3D g_strdup_printf("%x.%x.%04x", vcdev->cdev.hostid.cssid, + vcdev->cdev.hostid.ssid, + vcdev->cdev.hostid.devid); + vbasedev->sysfsdev =3D g_strdup_printf("/sys/bus/css/devices/%s/%s", + name, + cdev->mdevid); + vbasedev->ops =3D &vfio_ccw_ops; + vbasedev->type =3D VFIO_DEVICE_TYPE_CCW; + vbasedev->name =3D name; + vbasedev->dev =3D &vcdev->cdev.parent_obj.parent_obj; =20 - vfio_ccw_get_device(group, vcdev, &err); - if (err) { - goto out_device_err; + /* + * All vfio-ccw devices are believed to operate in a way compatible wi= th + * discarding of memory in RAM blocks, ie. pages pinned in the host are + * in the current working set of the guest driver and therefore never + * overlap e.g., with pages available to the guest balloon driver. Th= is + * needs to be set before vfio_get_device() for vfio common to handle + * ram_block_discard_disable(). + */ + vbasedev->ram_block_discard_allowed =3D true; + + ret =3D vfio_attach_device(cdev->mdevid, vbasedev, + &address_space_memory, errp); + if (ret) { + goto out_attach_dev_err; } =20 vfio_ccw_get_region(vcdev, &err); @@ -708,10 +652,9 @@ out_irq_notifier_err: out_io_notifier_err: vfio_ccw_put_region(vcdev); out_region_err: - vfio_ccw_put_device(vcdev); -out_device_err: - vfio_put_group(group); -out_group_err: + vfio_detach_device(vbasedev); +out_attach_dev_err: + g_free(vbasedev->name); if (cdc->unrealize) { cdc->unrealize(cdev); } @@ -724,14 +667,13 @@ static void vfio_ccw_unrealize(DeviceState *dev) S390CCWDevice *cdev =3D S390_CCW_DEVICE(dev); VFIOCCWDevice *vcdev =3D VFIO_CCW(cdev); S390CCWDeviceClass *cdc =3D S390_CCW_DEVICE_GET_CLASS(cdev); - VFIOGroup *group =3D vcdev->vdev.group; =20 vfio_ccw_unregister_irq_notifier(vcdev, VFIO_CCW_REQ_IRQ_INDEX); vfio_ccw_unregister_irq_notifier(vcdev, VFIO_CCW_CRW_IRQ_INDEX); vfio_ccw_unregister_irq_notifier(vcdev, VFIO_CCW_IO_IRQ_INDEX); vfio_ccw_put_region(vcdev); - vfio_ccw_put_device(vcdev); - vfio_put_group(group); + vfio_detach_device(&vcdev->vdev); + g_free(vcdev->vdev.name); =20 if (cdc->unrealize) { cdc->unrealize(cdev); diff --git a/hw/vfio/common.c b/hw/vfio/common.c index f4c33c9858..56cfe94d97 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -2335,7 +2335,7 @@ static void vfio_disconnect_container(VFIOGroup *grou= p) } } =20 -VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp) +static VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **er= rp) { VFIOGroup *group; char path[32]; @@ -2402,7 +2402,7 @@ free_group_exit: return NULL; } =20 -void vfio_put_group(VFIOGroup *group) +static void vfio_put_group(VFIOGroup *group) { if (!group || !QLIST_EMPTY(&group->device_list)) { return; @@ -2447,8 +2447,8 @@ retry: return info; } =20 -int vfio_get_device(VFIOGroup *group, const char *name, - VFIODevice *vbasedev, Error **errp) +static int vfio_get_device(VFIOGroup *group, const char *name, + VFIODevice *vbasedev, Error **errp) { g_autofree struct vfio_device_info *info =3D NULL; int fd; @@ -2506,7 +2506,7 @@ int vfio_get_device(VFIOGroup *group, const char *nam= e, return 0; } =20 -void vfio_put_base_device(VFIODevice *vbasedev) +static void vfio_put_base_device(VFIODevice *vbasedev) { if (!vbasedev->group) { return; --=20 2.41.0 From nobody Sun May 19 12:26:34 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1696328250; cv=none; d=zohomail.com; s=zohoarc; b=UKv83EfPbScNNVudbRT1r+AUglrLRwIlGukHfaIt3bawzELhXzbplEclrcxRY8mcSoFKDOQl4AOgiqT56UL3q2qIoXAP6EFmeEM1UKvj+cNjN5QlEGaq5OqyHz4FckUst20BpF2IYBwb6hPt9An+okI3+PC6a6/UkZvNHReaG88= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1696328250; h=Content-Transfer-Encoding:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=tRJLV4Vl2D0Bi54mZ0oxWnMjC54OT+8seLr//XsauoY=; b=BNE8py8SadlRDm5CRrAo2pWsfTbNOY+E1RZ2Um51VOlEdMkXdE7pcV4MazqVnMJwZJCtAQ5fnd8orUZGInyqOGGKODS+6K/yjgzZBq+wRGX2heffr8N9nRz4qyDHK3shZRTV2FsL7Sidf5j+s/ZuS4jQPS2lHkW5kHppYoBvP74= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696328250704691.3044252951672; Tue, 3 Oct 2023 03:17:30 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qncS6-0007YQ-IJ; Tue, 03 Oct 2023 06:16:30 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncS4-0007Y1-ER for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:28 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.133.124]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncS2-0004VW-Ta for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:28 -0400 Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-614-bdU1Lke_PreMsu-7bp9Q7g-1; Tue, 03 Oct 2023 06:16:19 -0400 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.rdu2.redhat.com [10.11.54.9]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 71F41185A78E; Tue, 3 Oct 2023 10:16:18 +0000 (UTC) Received: from laptop.redhat.com (unknown [10.39.192.172]) by smtp.corp.redhat.com (Postfix) with ESMTP id D2215492B16; Tue, 3 Oct 2023 10:16:15 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1696328186; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=tRJLV4Vl2D0Bi54mZ0oxWnMjC54OT+8seLr//XsauoY=; b=fcQnPSRfNd+DC9PzCJp2VeBdJ5GA9fP3avYcZT5bb1NCJd4TDXYAafCfYK8nrNsg9XKN1P 3o1rLTycz3tKX9Z0cEaGocAwuTY8HA+bscFWZeRlFXGRheQSjEbkGpYawzMClgou0QAtvK Gx9SpqaUzI921yS8XteC8jQCeqzbYhM= X-MC-Unique: bdU1Lke_PreMsu-7bp9Q7g-1 From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, zhenzhong.duan@intel.com, alex.williamson@redhat.com, clg@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com, joao.m.martins@oracle.com, peterx@redhat.com, kevin.tian@intel.com, yi.l.liu@intel.com, yi.y.sun@intel.com, chao.p.peng@intel.com, mjrosato@linux.ibm.com Subject: [PATCH v3 11/15] vfio/common: Move VFIO reset handler registration to a group agnostic function Date: Tue, 3 Oct 2023 12:14:08 +0200 Message-ID: <20231003101530.288864-12-eric.auger@redhat.com> In-Reply-To: <20231003101530.288864-1-eric.auger@redhat.com> References: <20231003101530.288864-1-eric.auger@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.1 on 10.11.54.9 Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=170.10.133.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H3=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=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: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @redhat.com) X-ZM-MESSAGEID: 1696328251199100001 Content-Type: text/plain; charset="utf-8" From: Zhenzhong Duan Move the reset handler registration/unregistration to a place that is not group specific. vfio_[get/put]_address_space are the best places for that purpose. Signed-off-by: Eric Auger Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: C=C3=A9dric Le Goater --- hw/vfio/common.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 56cfe94d97..019da387d2 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -1909,6 +1909,10 @@ static VFIOAddressSpace *vfio_get_address_space(Addr= essSpace *as) space->as =3D as; QLIST_INIT(&space->containers); =20 + if (QLIST_EMPTY(&vfio_address_spaces)) { + qemu_register_reset(vfio_reset_handler, NULL); + } + QLIST_INSERT_HEAD(&vfio_address_spaces, space, list); =20 return space; @@ -1920,6 +1924,9 @@ static void vfio_put_address_space(VFIOAddressSpace *= space) QLIST_REMOVE(space, list); g_free(space); } + if (QLIST_EMPTY(&vfio_address_spaces)) { + qemu_unregister_reset(vfio_reset_handler, NULL); + } } =20 /* @@ -2385,10 +2392,6 @@ static VFIOGroup *vfio_get_group(int groupid, Addres= sSpace *as, Error **errp) goto close_fd_exit; } =20 - if (QLIST_EMPTY(&vfio_group_list)) { - qemu_register_reset(vfio_reset_handler, NULL); - } - QLIST_INSERT_HEAD(&vfio_group_list, group, next); =20 return group; @@ -2417,10 +2420,6 @@ static void vfio_put_group(VFIOGroup *group) trace_vfio_put_group(group->fd); close(group->fd); g_free(group); - - if (QLIST_EMPTY(&vfio_group_list)) { - qemu_unregister_reset(vfio_reset_handler, NULL); - } } =20 struct vfio_device_info *vfio_get_device_info(int fd) --=20 2.41.0 From nobody Sun May 19 12:26:34 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1696328307; cv=none; d=zohomail.com; s=zohoarc; b=Okv6H+ZtWJ9P7AYkgGI1ZLbOukVSb/nbMfJGQ3CaXpcNte7Wg3PTEx6q5mIiVITJc9zk/bbzV/NYxkdMdAMeM4w0WrnKHTs2VQygEYfYiZpAJH0Q8oF2fZANFbOl+BOMjWFHVZVGjQd4UE9nvP3a420CiEWYGg29druEGQBgqc0= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1696328307; h=Content-Transfer-Encoding:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=LycLW0xYuBoFANoBrU9we+I27Pg3w09s3IXHksuliyk=; b=TlZj8bIaKVLLZ1oO9hWxNdPjyNStUOhxDdmgzk9x1vQrdN/MsgE2SwLIRUh07VxEQhnDgjVsO2SVem2lgGyJpKE/ro4H8dqTq92SoA6CUl20Mtadr40jselqXQ0QtEsIP7Dz28E0V5y2l9zw71TVYCyijTK5Mtg7vgTnOxKMSfM= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696328306819564.8614608300478; Tue, 3 Oct 2023 03:18:26 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qncSO-0007c5-2s; Tue, 03 Oct 2023 06:16:48 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncSH-0007b7-S7 for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:42 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.133.124]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncSE-0004Xi-Uj for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:41 -0400 Received: from mimecast-mx02.redhat.com (mx-ext.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-626-n-oGaqmYN3e1IocRyX6WrA-1; Tue, 03 Oct 2023 06:16:22 -0400 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.rdu2.redhat.com [10.11.54.9]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 01B7D29AA383; Tue, 3 Oct 2023 10:16:22 +0000 (UTC) Received: from laptop.redhat.com (unknown [10.39.192.172]) by smtp.corp.redhat.com (Postfix) with ESMTP id B65C3492B16; Tue, 3 Oct 2023 10:16:18 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1696328198; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=LycLW0xYuBoFANoBrU9we+I27Pg3w09s3IXHksuliyk=; b=FaZd0qmdDeyfTVST/PPO1LYkNXdGqhxLWDpE9LT/7J2lLrBzng2RLPdyuLqZ3llunuGIX6 wfdod9iiRoDTIlWCoslCX74yUMHdk5b9sm5O2b8ApAaNZHG/haWWBrv+jOa3W8KOEu5J7h mh8P1mPhxBqj5GMNPSZjwfwX4TS7bpo= X-MC-Unique: n-oGaqmYN3e1IocRyX6WrA-1 From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, zhenzhong.duan@intel.com, alex.williamson@redhat.com, clg@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com, joao.m.martins@oracle.com, peterx@redhat.com, kevin.tian@intel.com, yi.l.liu@intel.com, yi.y.sun@intel.com, chao.p.peng@intel.com, mjrosato@linux.ibm.com Subject: [PATCH v3 12/15] vfio/common: Introduce a per container device list Date: Tue, 3 Oct 2023 12:14:09 +0200 Message-ID: <20231003101530.288864-13-eric.auger@redhat.com> In-Reply-To: <20231003101530.288864-1-eric.auger@redhat.com> References: <20231003101530.288864-1-eric.auger@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.1 on 10.11.54.9 Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=170.10.133.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H3=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=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: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @redhat.com) X-ZM-MESSAGEID: 1696328308561100003 Content-Type: text/plain; charset="utf-8" From: Zhenzhong Duan Several functions need to iterate over the VFIO devices attached to a given container. This is currently achieved by iterating over the groups attached to the container and then over the devices in the group. Let's introduce a per container device list that simplifies this search. Per container list is used in below functions: vfio_devices_all_dirty_tracking vfio_devices_all_device_dirty_tracking vfio_devices_all_running_and_mig_active vfio_devices_dma_logging_stop vfio_devices_dma_logging_start vfio_devices_query_dirty_bitmap This will also ease the migration of IOMMUFD by hiding the group specificity. Suggested-by: Alex Williamson Signed-off-by: Zhenzhong Duan Signed-off-by: Eric Auger Reviewed-by: C=C3=A9dric Le Goater --- include/hw/vfio/vfio-common.h | 2 + hw/vfio/common.c | 145 +++++++++++++++------------------- 2 files changed, 67 insertions(+), 80 deletions(-) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index c486bdef2a..8ca70dd821 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -98,6 +98,7 @@ typedef struct VFIOContainer { QLIST_HEAD(, VFIOGroup) group_list; QLIST_HEAD(, VFIORamDiscardListener) vrdl_list; QLIST_ENTRY(VFIOContainer) next; + QLIST_HEAD(, VFIODevice) device_list; } VFIOContainer; =20 typedef struct VFIOGuestIOMMU { @@ -129,6 +130,7 @@ typedef struct VFIODeviceOps VFIODeviceOps; =20 typedef struct VFIODevice { QLIST_ENTRY(VFIODevice) next; + QLIST_ENTRY(VFIODevice) container_next; struct VFIOGroup *group; char *sysfsdev; char *name; diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 019da387d2..ef9dc7c747 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -218,7 +218,6 @@ bool vfio_device_state_is_precopy(VFIODevice *vbasedev) =20 static bool vfio_devices_all_dirty_tracking(VFIOContainer *container) { - VFIOGroup *group; VFIODevice *vbasedev; MigrationState *ms =3D migrate_get_current(); =20 @@ -227,19 +226,17 @@ static bool vfio_devices_all_dirty_tracking(VFIOConta= iner *container) return false; } =20 - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - VFIOMigration *migration =3D vbasedev->migration; + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + VFIOMigration *migration =3D vbasedev->migration; =20 - if (!migration) { - return false; - } + if (!migration) { + return false; + } =20 - if (vbasedev->pre_copy_dirty_page_tracking =3D=3D ON_OFF_AUTO_= OFF && - (vfio_device_state_is_running(vbasedev) || - vfio_device_state_is_precopy(vbasedev))) { - return false; - } + if (vbasedev->pre_copy_dirty_page_tracking =3D=3D ON_OFF_AUTO_OFF = && + (vfio_device_state_is_running(vbasedev) || + vfio_device_state_is_precopy(vbasedev))) { + return false; } } return true; @@ -247,14 +244,11 @@ static bool vfio_devices_all_dirty_tracking(VFIOConta= iner *container) =20 static bool vfio_devices_all_device_dirty_tracking(VFIOContainer *containe= r) { - VFIOGroup *group; VFIODevice *vbasedev; =20 - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (!vbasedev->dirty_pages_supported) { - return false; - } + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + if (!vbasedev->dirty_pages_supported) { + return false; } } =20 @@ -267,27 +261,24 @@ static bool vfio_devices_all_device_dirty_tracking(VF= IOContainer *container) */ static bool vfio_devices_all_running_and_mig_active(VFIOContainer *contain= er) { - VFIOGroup *group; VFIODevice *vbasedev; =20 if (!migration_is_active(migrate_get_current())) { return false; } =20 - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - VFIOMigration *migration =3D vbasedev->migration; + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + VFIOMigration *migration =3D vbasedev->migration; =20 - if (!migration) { - return false; - } + if (!migration) { + return false; + } =20 - if (vfio_device_state_is_running(vbasedev) || - vfio_device_state_is_precopy(vbasedev)) { - continue; - } else { - return false; - } + if (vfio_device_state_is_running(vbasedev) || + vfio_device_state_is_precopy(vbasedev)) { + continue; + } else { + return false; } } return true; @@ -1187,20 +1178,17 @@ static bool vfio_section_is_vfio_pci(MemoryRegionSe= ction *section, { VFIOPCIDevice *pcidev; VFIODevice *vbasedev; - VFIOGroup *group; Object *owner; =20 owner =3D memory_region_owner(section->mr); =20 - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->type !=3D VFIO_DEVICE_TYPE_PCI) { - continue; - } - pcidev =3D container_of(vbasedev, VFIOPCIDevice, vbasedev); - if (OBJECT(pcidev) =3D=3D owner) { - return true; - } + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + if (vbasedev->type !=3D VFIO_DEVICE_TYPE_PCI) { + continue; + } + pcidev =3D container_of(vbasedev, VFIOPCIDevice, vbasedev); + if (OBJECT(pcidev) =3D=3D owner) { + return true; } } =20 @@ -1296,24 +1284,21 @@ static void vfio_devices_dma_logging_stop(VFIOConta= iner *container) sizeof(uint64_t))] =3D {}; struct vfio_device_feature *feature =3D (struct vfio_device_feature *)= buf; VFIODevice *vbasedev; - VFIOGroup *group; =20 feature->argsz =3D sizeof(buf); feature->flags =3D VFIO_DEVICE_FEATURE_SET | VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP; =20 - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (!vbasedev->dirty_tracking) { - continue; - } - - if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) { - warn_report("%s: Failed to stop DMA logging, err %d (%s)", - vbasedev->name, -errno, strerror(errno)); - } - vbasedev->dirty_tracking =3D false; + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + if (!vbasedev->dirty_tracking) { + continue; } + + if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) { + warn_report("%s: Failed to stop DMA logging, err %d (%s)", + vbasedev->name, -errno, strerror(errno)); + } + vbasedev->dirty_tracking =3D false; } } =20 @@ -1396,7 +1381,6 @@ static int vfio_devices_dma_logging_start(VFIOContain= er *container) struct vfio_device_feature *feature; VFIODirtyRanges ranges; VFIODevice *vbasedev; - VFIOGroup *group; int ret =3D 0; =20 vfio_dirty_tracking_init(container, &ranges); @@ -1406,21 +1390,19 @@ static int vfio_devices_dma_logging_start(VFIOConta= iner *container) return -errno; } =20 - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->dirty_tracking) { - continue; - } - - ret =3D ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature); - if (ret) { - ret =3D -errno; - error_report("%s: Failed to start DMA logging, err %d (%s)= ", - vbasedev->name, ret, strerror(errno)); - goto out; - } - vbasedev->dirty_tracking =3D true; + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + if (vbasedev->dirty_tracking) { + continue; } + + ret =3D ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature); + if (ret) { + ret =3D -errno; + error_report("%s: Failed to start DMA logging, err %d (%s)", + vbasedev->name, ret, strerror(errno)); + goto out; + } + vbasedev->dirty_tracking =3D true; } =20 out: @@ -1500,21 +1482,18 @@ static int vfio_devices_query_dirty_bitmap(VFIOCont= ainer *container, hwaddr size) { VFIODevice *vbasedev; - VFIOGroup *group; int ret; =20 - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - ret =3D vfio_device_dma_logging_report(vbasedev, iova, size, - vbmap->bitmap); - if (ret) { - error_report("%s: Failed to get DMA logging report, iova: " - "0x%" HWADDR_PRIx ", size: 0x%" HWADDR_PRIx - ", err: %d (%s)", - vbasedev->name, iova, size, ret, strerror(-re= t)); + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + ret =3D vfio_device_dma_logging_report(vbasedev, iova, size, + vbmap->bitmap); + if (ret) { + error_report("%s: Failed to get DMA logging report, iova: " + "0x%" HWADDR_PRIx ", size: 0x%" HWADDR_PRIx + ", err: %d (%s)", + vbasedev->name, iova, size, ret, strerror(-ret)); =20 - return ret; - } + return ret; } } =20 @@ -2648,6 +2627,7 @@ int vfio_attach_device(char *name, VFIODevice *vbased= ev, int groupid =3D vfio_device_groupid(vbasedev, errp); VFIODevice *vbasedev_iter; VFIOGroup *group; + VFIOContainer *container; int ret; =20 if (groupid < 0) { @@ -2671,8 +2651,12 @@ int vfio_attach_device(char *name, VFIODevice *vbase= dev, ret =3D vfio_get_device(group, name, vbasedev, errp); if (ret) { vfio_put_group(group); + return ret; } =20 + container =3D group->container; + QLIST_INSERT_HEAD(&container->device_list, vbasedev, container_next); + return ret; } =20 @@ -2680,6 +2664,7 @@ void vfio_detach_device(VFIODevice *vbasedev) { VFIOGroup *group =3D vbasedev->group; =20 + QLIST_REMOVE(vbasedev, container_next); trace_vfio_detach_device(vbasedev->name, group->groupid); vfio_put_base_device(vbasedev); vfio_put_group(group); --=20 2.41.0 From nobody Sun May 19 12:26:34 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1696328221; cv=none; d=zohomail.com; s=zohoarc; b=JCu8mkb9gFLht64Z434Tlip1k+54BbdClxYdQq/v49OFAOkhN4Gg7aE/H9qPIQayH+zfm5/PAc2De+/VE23kdmml1LmOragGvJw4H/4SN5VZH4JPjXZkF7WeNpifB/2ntflb/JjJSFgh7MvBMewfleAtXB3+KyOcOBLXTdfpfRg= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1696328221; h=Content-Transfer-Encoding:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=wcBmqIuyPnHgedmKy2ossbRkzFHL6LIyAEHIzIUz0Ak=; b=DOcULZznICEylUYGdaXFZWIqM+Bm7i/NNswUIc7kPF6NKmWxfEk6w1EKaBN4fLP5HngTU7pVJkYqlnBz1NZpNrZmdUXhPG25UVBsZBYNzyuNN6EZL1oMSInsasdNAqhqSOCQfH2AR1g2XUrCyXmwJ4Tb7SBHIjboJrB/MyhigCo= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696328221467429.7403599577518; Tue, 3 Oct 2023 03:17:01 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qncSK-0007ba-GB; Tue, 03 Oct 2023 06:16:44 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncSG-0007aq-Aj for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:40 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.129.124]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncS3-0004Vf-Nv for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:39 -0400 Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-385-kVWM-PYGO8WA_2_Kg6D07g-1; Tue, 03 Oct 2023 06:16:25 -0400 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.rdu2.redhat.com [10.11.54.9]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id DA2C985A5BE; Tue, 3 Oct 2023 10:16:24 +0000 (UTC) Received: from laptop.redhat.com (unknown [10.39.192.172]) by smtp.corp.redhat.com (Postfix) with ESMTP id 4BCC4492B16; Tue, 3 Oct 2023 10:16:22 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1696328187; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=wcBmqIuyPnHgedmKy2ossbRkzFHL6LIyAEHIzIUz0Ak=; b=BTW/ck8MWexBZGMjjJFxv85YCzT9WpJzpiVNHohtWJM4gnEn8TEdHMkhNbhKOEVxYbGwGH R9fWB1spEbMvCfaNUUZrhEZYfudHzCKbUYfd8uHUmJqkiDcGuuVOqJrU1BLFaBowa72Y6O JsOy7oIDwzw+g8bSgqvvWGjzVYax4i4= X-MC-Unique: kVWM-PYGO8WA_2_Kg6D07g-1 From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, zhenzhong.duan@intel.com, alex.williamson@redhat.com, clg@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com, joao.m.martins@oracle.com, peterx@redhat.com, kevin.tian@intel.com, yi.l.liu@intel.com, yi.y.sun@intel.com, chao.p.peng@intel.com, mjrosato@linux.ibm.com Subject: [PATCH v3 13/15] vfio/common: Store the parent container in VFIODevice Date: Tue, 3 Oct 2023 12:14:10 +0200 Message-ID: <20231003101530.288864-14-eric.auger@redhat.com> In-Reply-To: <20231003101530.288864-1-eric.auger@redhat.com> References: <20231003101530.288864-1-eric.auger@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.1 on 10.11.54.9 Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=170.10.129.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, SPF_HELO_NONE=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: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @redhat.com) X-ZM-MESSAGEID: 1696328222850100006 Content-Type: text/plain; charset="utf-8" From: Zhenzhong Duan let's store the parent contaienr within the VFIODevice. This simplifies the logic in vfio_viommu_preset() and brings the benefice to hide the group specificity which is useful for IOMMUFD migration. Signed-off-by: Eric Auger Signed-off-by: Zhenzhong Duan --- include/hw/vfio/vfio-common.h | 1 + hw/vfio/common.c | 8 +++++++- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index 8ca70dd821..bf12e40667 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -132,6 +132,7 @@ typedef struct VFIODevice { QLIST_ENTRY(VFIODevice) next; QLIST_ENTRY(VFIODevice) container_next; struct VFIOGroup *group; + VFIOContainer *container; char *sysfsdev; char *name; DeviceState *dev; diff --git a/hw/vfio/common.c b/hw/vfio/common.c index ef9dc7c747..55f8a113ea 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -184,7 +184,7 @@ void vfio_unblock_multiple_devices_migration(void) =20 bool vfio_viommu_preset(VFIODevice *vbasedev) { - return vbasedev->group->container->space->as !=3D &address_space_memor= y; + return vbasedev->container->space->as !=3D &address_space_memory; } =20 static void vfio_set_migration_error(int err) @@ -2655,6 +2655,7 @@ int vfio_attach_device(char *name, VFIODevice *vbased= ev, } =20 container =3D group->container; + vbasedev->container =3D container; QLIST_INSERT_HEAD(&container->device_list, vbasedev, container_next); =20 return ret; @@ -2664,7 +2665,12 @@ void vfio_detach_device(VFIODevice *vbasedev) { VFIOGroup *group =3D vbasedev->group; =20 + if (!vbasedev->container) { + return; + } + QLIST_REMOVE(vbasedev, container_next); + vbasedev->container =3D NULL; trace_vfio_detach_device(vbasedev->name, group->groupid); vfio_put_base_device(vbasedev); vfio_put_group(group); --=20 2.41.0 From nobody Sun May 19 12:26:34 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1696328362; cv=none; d=zohomail.com; s=zohoarc; b=JCzgkxEAO40uLUgPEU8uKjTB/oTIIzf1H/diiv6CcaUvwiPLc3ltGy1YJlScMgxbaSoGLfLUvwF1FzLreVFLM4nKOSg6D18Onpa2A+vCKeAilzheNvyh1S4AmcS0sFDDh/iyeiKIXGh4SzhwUp/VHgDWSSeRINgJq+ZLlkDC6xc= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1696328362; h=Content-Transfer-Encoding:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=wDAgD80h/8hNhmZQaLliEb+4nAAT1dJ41MljGKC5/HY=; b=JnuHxiBlUf3fDirqODSPo4F9KW+fFLjOqIo4Bej1C6BVwhCH4B3NF4/HQi9n8K9x5VCddn0AI/VPWJKWeoq7PR1HhzhzgC91SfZFhVstTEJH8UoAFF7JqpTLI+ufkCk2P1Ts5NJNt+Gc+X2GsxjKgbDYMLerMPkfa4ITG80dq/o= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696328362015442.7140846520175; Tue, 3 Oct 2023 03:19:22 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qncSj-000864-2W; Tue, 03 Oct 2023 06:17:09 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncSR-0007ch-QH for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:52 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.133.124]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncSQ-0004ZU-4B for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:51 -0400 Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-624-fjDJccJVNn6-w5sQAASLfQ-1; Tue, 03 Oct 2023 06:16:28 -0400 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.rdu2.redhat.com [10.11.54.9]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id B6A08185A790; Tue, 3 Oct 2023 10:16:27 +0000 (UTC) Received: from laptop.redhat.com (unknown [10.39.192.172]) by smtp.corp.redhat.com (Postfix) with ESMTP id 29A2A492B16; Tue, 3 Oct 2023 10:16:25 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1696328209; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=wDAgD80h/8hNhmZQaLliEb+4nAAT1dJ41MljGKC5/HY=; b=D9c3fvZ6Wf5DEI+KkjQNVuFTBOeLvEoxFoyL2iXvtnKbiQv13LlYDDOty/X8ugz35ap6O1 gybS8yZ4D6kRz3Jws14ji6JjLc1XGkyltnxX9a5SCgOj5KxixITMM31R1gHyVM7yS06YxM hOA1XKz0HCU+z4uXKOEB4rSClu5rJd4= X-MC-Unique: fjDJccJVNn6-w5sQAASLfQ-1 From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, zhenzhong.duan@intel.com, alex.williamson@redhat.com, clg@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com, joao.m.martins@oracle.com, peterx@redhat.com, kevin.tian@intel.com, yi.l.liu@intel.com, yi.y.sun@intel.com, chao.p.peng@intel.com, mjrosato@linux.ibm.com Subject: [PATCH v3 14/15] vfio/common: Introduce a global VFIODevice list Date: Tue, 3 Oct 2023 12:14:11 +0200 Message-ID: <20231003101530.288864-15-eric.auger@redhat.com> In-Reply-To: <20231003101530.288864-1-eric.auger@redhat.com> References: <20231003101530.288864-1-eric.auger@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.1 on 10.11.54.9 Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=170.10.133.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H3=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=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: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @redhat.com) X-ZM-MESSAGEID: 1696328363198100005 Content-Type: text/plain; charset="utf-8" From: Zhenzhong Duan Some functions iterate over all the VFIODevices. This is currently achieved by iterating over all groups/devices. Let's introduce a global list of VFIODevices simplifying that scan. This will also be useful while migrating to IOMMUFD by hiding the group specificity. Signed-off-by: Eric Auger Signed-off-by: Zhenzhong Duan Suggested-by: Alex Williamson --- include/hw/vfio/vfio-common.h | 2 ++ hw/vfio/common.c | 45 +++++++++++++++-------------------- 2 files changed, 21 insertions(+), 26 deletions(-) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index bf12e40667..54905b9dd4 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -131,6 +131,7 @@ typedef struct VFIODeviceOps VFIODeviceOps; typedef struct VFIODevice { QLIST_ENTRY(VFIODevice) next; QLIST_ENTRY(VFIODevice) container_next; + QLIST_ENTRY(VFIODevice) global_next; struct VFIOGroup *group; VFIOContainer *container; char *sysfsdev; @@ -232,6 +233,7 @@ int vfio_kvm_device_del_fd(int fd, Error **errp); =20 extern const MemoryRegionOps vfio_region_ops; typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList; +typedef QLIST_HEAD(VFIODeviceList, VFIODevice) VFIODeviceList; extern VFIOGroupList vfio_group_list; =20 bool vfio_mig_active(void); diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 55f8a113ea..95bc50bcda 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -48,6 +48,8 @@ =20 VFIOGroupList vfio_group_list =3D QLIST_HEAD_INITIALIZER(vfio_group_list); +static VFIODeviceList vfio_device_list =3D + QLIST_HEAD_INITIALIZER(vfio_device_list); static QLIST_HEAD(, VFIOAddressSpace) vfio_address_spaces =3D QLIST_HEAD_INITIALIZER(vfio_address_spaces); =20 @@ -94,18 +96,15 @@ static int vfio_get_dirty_bitmap(VFIOContainer *contain= er, uint64_t iova, =20 bool vfio_mig_active(void) { - VFIOGroup *group; VFIODevice *vbasedev; =20 - if (QLIST_EMPTY(&vfio_group_list)) { + if (QLIST_EMPTY(&vfio_device_list)) { return false; } =20 - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->migration_blocker) { - return false; - } + QLIST_FOREACH(vbasedev, &vfio_device_list, next) { + if (vbasedev->migration_blocker) { + return false; } } return true; @@ -120,19 +119,16 @@ static Error *multiple_devices_migration_blocker; */ static bool vfio_multiple_devices_migration_is_supported(void) { - VFIOGroup *group; VFIODevice *vbasedev; unsigned int device_num =3D 0; bool all_support_p2p =3D true; =20 - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->migration) { - device_num++; + QLIST_FOREACH(vbasedev, &vfio_device_list, next) { + if (vbasedev->migration) { + device_num++; =20 - if (!(vbasedev->migration->mig_flags & VFIO_MIGRATION_P2P)= ) { - all_support_p2p =3D false; - } + if (!(vbasedev->migration->mig_flags & VFIO_MIGRATION_P2P)) { + all_support_p2p =3D false; } } } @@ -1777,22 +1773,17 @@ bool vfio_get_info_dma_avail(struct vfio_iommu_type= 1_info *info, =20 void vfio_reset_handler(void *opaque) { - VFIOGroup *group; VFIODevice *vbasedev; =20 - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->dev->realized) { - vbasedev->ops->vfio_compute_needs_reset(vbasedev); - } + QLIST_FOREACH(vbasedev, &vfio_device_list, next) { + if (vbasedev->dev->realized) { + vbasedev->ops->vfio_compute_needs_reset(vbasedev); } } =20 - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->dev->realized && vbasedev->needs_reset) { - vbasedev->ops->vfio_hot_reset_multi(vbasedev); - } + QLIST_FOREACH(vbasedev, &vfio_device_list, next) { + if (vbasedev->dev->realized && vbasedev->needs_reset) { + vbasedev->ops->vfio_hot_reset_multi(vbasedev); } } } @@ -2657,6 +2648,7 @@ int vfio_attach_device(char *name, VFIODevice *vbased= ev, container =3D group->container; vbasedev->container =3D container; QLIST_INSERT_HEAD(&container->device_list, vbasedev, container_next); + QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next); =20 return ret; } @@ -2669,6 +2661,7 @@ void vfio_detach_device(VFIODevice *vbasedev) return; } =20 + QLIST_REMOVE(vbasedev, global_next); QLIST_REMOVE(vbasedev, container_next); vbasedev->container =3D NULL; trace_vfio_detach_device(vbasedev->name, group->groupid); --=20 2.41.0 From nobody Sun May 19 12:26:34 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1696328283; cv=none; d=zohomail.com; s=zohoarc; b=RXTzXFdX20L9iUrh68gHa+5gQDCRlOr/pTr9eEwbXgXl7S4GzDGCbXZkTeWw536ixHX+Mf3qkJY1Ui69GhzR7wXQzJLzHWoOpKiEOIelQrAxhCfgiVQ1bboW5oqUGzW6vc1T2sWCwE53zQI0YFX14x1GgS8+2bPR5tM/m5q9fvE= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1696328283; h=Content-Transfer-Encoding:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=N2zEE/UpuEAS7EswfWZUKL6qJFSbfh8dCPM10w33HYQ=; b=C5MXY6/7BQV+TYpPbwkDTdzbMyfHMjqKwKxMRPMNEszx1duByptoFncOs+I0HNTJX5G6KWratxOgkL11tvWCvDLz1voNAYiyu+/hdaeOE2KYACC+j5QA6gCfc0S1Mgwdyw9Qx0h3PT+Qb6cMn49MFpnCv3pTwuiOCjuJ7s6qH30= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696328283718176.33454673264146; Tue, 3 Oct 2023 03:18:03 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qncSZ-0007tf-E0; Tue, 03 Oct 2023 06:17:01 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncSH-0007b6-SB for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:42 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.133.124]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qncSC-0004XS-4c for qemu-devel@nongnu.org; Tue, 03 Oct 2023 06:16:41 -0400 Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-248-vo55P8F-OoS9qPQo7Wa5wg-1; Tue, 03 Oct 2023 06:16:33 -0400 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.rdu2.redhat.com [10.11.54.9]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 8D981811E7B; Tue, 3 Oct 2023 10:16:32 +0000 (UTC) Received: from laptop.redhat.com (unknown [10.39.192.172]) by smtp.corp.redhat.com (Postfix) with ESMTP id 07E56492B16; Tue, 3 Oct 2023 10:16:27 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1696328195; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=N2zEE/UpuEAS7EswfWZUKL6qJFSbfh8dCPM10w33HYQ=; b=Vgce9iQAtmJGIEyBzbaPh3/t48vk5edbvIyJ11lwuHOudJrfVVWmipUb9J4SR4syDbZzG/ WxHdzFK0hVlf9yxVQ6a6KAsrpQ40sZTVusqln2ZAtQaLGl/EwLUYjksm4HHlgCQ49gnkz+ pqdL6oXiJitva6rxEnHGqPegm77ojIE= X-MC-Unique: vo55P8F-OoS9qPQo7Wa5wg-1 From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, zhenzhong.duan@intel.com, alex.williamson@redhat.com, clg@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com, joao.m.martins@oracle.com, peterx@redhat.com, kevin.tian@intel.com, yi.l.liu@intel.com, yi.y.sun@intel.com, chao.p.peng@intel.com, mjrosato@linux.ibm.com Subject: [PATCH v3 15/15] vfio/common: Move legacy VFIO backend code into separate container.c Date: Tue, 3 Oct 2023 12:14:12 +0200 Message-ID: <20231003101530.288864-16-eric.auger@redhat.com> In-Reply-To: <20231003101530.288864-1-eric.auger@redhat.com> References: <20231003101530.288864-1-eric.auger@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.1 on 10.11.54.9 Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=170.10.133.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H3=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=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: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @redhat.com) X-ZM-MESSAGEID: 1696328284892100001 Content-Type: text/plain; charset="utf-8" From: Yi Liu Move all the code really dependent on the legacy VFIO container/group into a separate file: container.c. What does remain in common.c is the code related to VFIOAddressSpace, MemoryListeners, migration and all other general operations. Signed-off-by: Eric Auger Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: C=C3=A9dric Le Goater --- include/hw/vfio/vfio-common.h | 35 + hw/vfio/common.c | 1155 +------------------------------- hw/vfio/container.c | 1156 +++++++++++++++++++++++++++++++++ hw/vfio/meson.build | 1 + 4 files changed, 1208 insertions(+), 1139 deletions(-) create mode 100644 hw/vfio/container.c diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index 54905b9dd4..7780b9073a 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -206,6 +206,30 @@ typedef struct { hwaddr pages; } VFIOBitmap; =20 +void vfio_host_win_add(VFIOContainer *container, + hwaddr min_iova, hwaddr max_iova, + uint64_t iova_pgsizes); +int vfio_host_win_del(VFIOContainer *container, hwaddr min_iova, + hwaddr max_iova); +VFIOAddressSpace *vfio_get_address_space(AddressSpace *as); +void vfio_put_address_space(VFIOAddressSpace *space); +bool vfio_devices_all_running_and_saving(VFIOContainer *container); + +/* container->fd */ +int vfio_dma_unmap(VFIOContainer *container, hwaddr iova, + ram_addr_t size, IOMMUTLBEntry *iotlb); +int vfio_dma_map(VFIOContainer *container, hwaddr iova, + ram_addr_t size, void *vaddr, bool readonly); +int vfio_set_dirty_page_tracking(VFIOContainer *container, bool start); +int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *vbmap, + hwaddr iova, hwaddr size); + +int vfio_container_add_section_window(VFIOContainer *container, + MemoryRegionSection *section, + Error **errp); +void vfio_container_del_section_window(VFIOContainer *container, + MemoryRegionSection *section); + void vfio_disable_irqindex(VFIODevice *vbasedev, int index); void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index); void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index); @@ -235,6 +259,10 @@ extern const MemoryRegionOps vfio_region_ops; typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList; typedef QLIST_HEAD(VFIODeviceList, VFIODevice) VFIODeviceList; extern VFIOGroupList vfio_group_list; +extern VFIODeviceList vfio_device_list; + +extern const MemoryListener vfio_memory_listener; +extern int vfio_kvm_device_fd; =20 bool vfio_mig_active(void); int vfio_block_multiple_devices_migration(VFIODevice *vbasedev, Error **er= rp); @@ -272,4 +300,11 @@ bool vfio_migration_realize(VFIODevice *vbasedev, Erro= r **errp); void vfio_migration_exit(VFIODevice *vbasedev); =20 int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size); +bool vfio_devices_all_running_and_mig_active(VFIOContainer *container); +bool vfio_devices_all_device_dirty_tracking(VFIOContainer *container); +int vfio_devices_query_dirty_bitmap(VFIOContainer *container, + VFIOBitmap *vbmap, hwaddr iova, + hwaddr size); +int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, + uint64_t size, ram_addr_t ram_addr); #endif /* HW_VFIO_VFIO_COMMON_H */ diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 95bc50bcda..9e61de03ee 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -46,9 +46,7 @@ #include "migration/qemu-file.h" #include "sysemu/tpm.h" =20 -VFIOGroupList vfio_group_list =3D - QLIST_HEAD_INITIALIZER(vfio_group_list); -static VFIODeviceList vfio_device_list =3D +VFIODeviceList vfio_device_list =3D QLIST_HEAD_INITIALIZER(vfio_device_list); static QLIST_HEAD(, VFIOAddressSpace) vfio_address_spaces =3D QLIST_HEAD_INITIALIZER(vfio_address_spaces); @@ -61,39 +59,13 @@ static QLIST_HEAD(, VFIOAddressSpace) vfio_address_spac= es =3D * initialized, this file descriptor is only released on QEMU exit and * we'll re-use it should another vfio device be attached before then. */ -static int vfio_kvm_device_fd =3D -1; +int vfio_kvm_device_fd =3D -1; #endif =20 -static int vfio_ram_block_discard_disable(VFIOContainer *container, bool s= tate) -{ - switch (container->iommu_type) { - case VFIO_TYPE1v2_IOMMU: - case VFIO_TYPE1_IOMMU: - /* - * We support coordinated discarding of RAM via the RamDiscardMana= ger. - */ - return ram_block_uncoordinated_discard_disable(state); - default: - /* - * VFIO_SPAPR_TCE_IOMMU most probably works just fine with - * RamDiscardManager, however, it is completely untested. - * - * VFIO_SPAPR_TCE_v2_IOMMU with "DMA memory preregistering" does - * completely the opposite of managing mapping/pinning dynamically= as - * required by RamDiscardManager. We would have to special-case se= ctions - * with a RamDiscardManager. - */ - return ram_block_discard_disable(state); - } -} - /* * Device state interfaces */ =20 -static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, - uint64_t size, ram_addr_t ram_addr); - bool vfio_mig_active(void) { VFIODevice *vbasedev; @@ -238,7 +210,7 @@ static bool vfio_devices_all_dirty_tracking(VFIOContain= er *container) return true; } =20 -static bool vfio_devices_all_device_dirty_tracking(VFIOContainer *containe= r) +bool vfio_devices_all_device_dirty_tracking(VFIOContainer *container) { VFIODevice *vbasedev; =20 @@ -255,7 +227,7 @@ static bool vfio_devices_all_device_dirty_tracking(VFIO= Container *container) * Check if all VFIO devices are running and migration is active, which is * essentially equivalent to the migration being in pre-copy phase. */ -static bool vfio_devices_all_running_and_mig_active(VFIOContainer *contain= er) +bool vfio_devices_all_running_and_mig_active(VFIOContainer *container) { VFIODevice *vbasedev; =20 @@ -280,150 +252,8 @@ static bool vfio_devices_all_running_and_mig_active(V= FIOContainer *container) return true; } =20 -static int vfio_dma_unmap_bitmap(VFIOContainer *container, - hwaddr iova, ram_addr_t size, - IOMMUTLBEntry *iotlb) -{ - struct vfio_iommu_type1_dma_unmap *unmap; - struct vfio_bitmap *bitmap; - VFIOBitmap vbmap; - int ret; - - ret =3D vfio_bitmap_alloc(&vbmap, size); - if (ret) { - return ret; - } - - unmap =3D g_malloc0(sizeof(*unmap) + sizeof(*bitmap)); - - unmap->argsz =3D sizeof(*unmap) + sizeof(*bitmap); - unmap->iova =3D iova; - unmap->size =3D size; - unmap->flags |=3D VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP; - bitmap =3D (struct vfio_bitmap *)&unmap->data; - - /* - * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of - * qemu_real_host_page_size to mark those dirty. Hence set bitmap_pgsi= ze - * to qemu_real_host_page_size. - */ - bitmap->pgsize =3D qemu_real_host_page_size(); - bitmap->size =3D vbmap.size; - bitmap->data =3D (__u64 *)vbmap.bitmap; - - if (vbmap.size > container->max_dirty_bitmap_size) { - error_report("UNMAP: Size of bitmap too big 0x%"PRIx64, vbmap.size= ); - ret =3D -E2BIG; - goto unmap_exit; - } - - ret =3D ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap); - if (!ret) { - cpu_physical_memory_set_dirty_lebitmap(vbmap.bitmap, - iotlb->translated_addr, vbmap.pages); - } else { - error_report("VFIO_UNMAP_DMA with DIRTY_BITMAP : %m"); - } - -unmap_exit: - g_free(unmap); - g_free(vbmap.bitmap); - - return ret; -} - -/* - * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86 - */ -static int vfio_dma_unmap(VFIOContainer *container, - hwaddr iova, ram_addr_t size, - IOMMUTLBEntry *iotlb) -{ - struct vfio_iommu_type1_dma_unmap unmap =3D { - .argsz =3D sizeof(unmap), - .flags =3D 0, - .iova =3D iova, - .size =3D size, - }; - bool need_dirty_sync =3D false; - int ret; - - if (iotlb && vfio_devices_all_running_and_mig_active(container)) { - if (!vfio_devices_all_device_dirty_tracking(container) && - container->dirty_pages_supported) { - return vfio_dma_unmap_bitmap(container, iova, size, iotlb); - } - - need_dirty_sync =3D true; - } - - while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) { - /* - * The type1 backend has an off-by-one bug in the kernel (71a7d3d7= 8e3c - * v4.15) where an overflow in its wrap-around check prevents us f= rom - * unmapping the last page of the address space. Test for the err= or - * condition and re-try the unmap excluding the last page. The - * expectation is that we've never mapped the last page anyway and= this - * unmap request comes via vIOMMU support which also makes it unli= kely - * that this page is used. This bug was introduced well after typ= e1 v2 - * support was introduced, so we shouldn't need to test for v1. A= fix - * is queued for kernel v5.0 so this workaround can be removed once - * affected kernels are sufficiently deprecated. - */ - if (errno =3D=3D EINVAL && unmap.size && !(unmap.iova + unmap.size= ) && - container->iommu_type =3D=3D VFIO_TYPE1v2_IOMMU) { - trace_vfio_dma_unmap_overflow_workaround(); - unmap.size -=3D 1ULL << ctz64(container->pgsizes); - continue; - } - error_report("VFIO_UNMAP_DMA failed: %s", strerror(errno)); - return -errno; - } - - if (need_dirty_sync) { - ret =3D vfio_get_dirty_bitmap(container, iova, size, - iotlb->translated_addr); - if (ret) { - return ret; - } - } - - return 0; -} - -static int vfio_dma_map(VFIOContainer *container, hwaddr iova, - ram_addr_t size, void *vaddr, bool readonly) -{ - struct vfio_iommu_type1_dma_map map =3D { - .argsz =3D sizeof(map), - .flags =3D VFIO_DMA_MAP_FLAG_READ, - .vaddr =3D (__u64)(uintptr_t)vaddr, - .iova =3D iova, - .size =3D size, - }; - - if (!readonly) { - map.flags |=3D VFIO_DMA_MAP_FLAG_WRITE; - } - - /* - * Try the mapping, if it fails with EBUSY, unmap the region and try - * again. This shouldn't be necessary, but we sometimes see it in - * the VGA ROM space. - */ - if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) =3D=3D 0 || - (errno =3D=3D EBUSY && vfio_dma_unmap(container, iova, size, NULL)= =3D=3D 0 && - ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) =3D=3D 0)) { - return 0; - } - - error_report("VFIO_MAP_DMA failed: %s", strerror(errno)); - return -errno; -} - -static void vfio_host_win_add(VFIOContainer *container, - hwaddr min_iova, hwaddr max_iova, - uint64_t iova_pgsizes) +void vfio_host_win_add(VFIOContainer *container, hwaddr min_iova, + hwaddr max_iova, uint64_t iova_pgsizes) { VFIOHostDMAWindow *hostwin; =20 @@ -444,8 +274,8 @@ static void vfio_host_win_add(VFIOContainer *container, QLIST_INSERT_HEAD(&container->hostwin_list, hostwin, hostwin_next); } =20 -static int vfio_host_win_del(VFIOContainer *container, hwaddr min_iova, - hwaddr max_iova) +int vfio_host_win_del(VFIOContainer *container, + hwaddr min_iova, hwaddr max_iova) { VFIOHostDMAWindow *hostwin; =20 @@ -794,92 +624,6 @@ static bool vfio_get_section_iova_range(VFIOContainer = *container, return true; } =20 -static int vfio_container_add_section_window(VFIOContainer *container, - MemoryRegionSection *section, - Error **errp) -{ - VFIOHostDMAWindow *hostwin; - hwaddr pgsize =3D 0; - int ret; - - if (container->iommu_type !=3D VFIO_SPAPR_TCE_v2_IOMMU) { - return 0; - } - - /* For now intersections are not allowed, we may relax this later */ - QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { - if (ranges_overlap(hostwin->min_iova, - hostwin->max_iova - hostwin->min_iova + 1, - section->offset_within_address_space, - int128_get64(section->size))) { - error_setg(errp, - "region [0x%"PRIx64",0x%"PRIx64"] overlaps with existing" - "host DMA window [0x%"PRIx64",0x%"PRIx64"]", - section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1, - hostwin->min_iova, hostwin->max_iova); - return -EINVAL; - } - } - - ret =3D vfio_spapr_create_window(container, section, &pgsize); - if (ret) { - error_setg_errno(errp, -ret, "Failed to create SPAPR window"); - return ret; - } - - vfio_host_win_add(container, section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1, pgsize); -#ifdef CONFIG_KVM - if (kvm_enabled()) { - VFIOGroup *group; - IOMMUMemoryRegion *iommu_mr =3D IOMMU_MEMORY_REGION(section->mr); - struct kvm_vfio_spapr_tce param; - struct kvm_device_attr attr =3D { - .group =3D KVM_DEV_VFIO_GROUP, - .attr =3D KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE, - .addr =3D (uint64_t)(unsigned long)¶m, - }; - - if (!memory_region_iommu_get_attr(iommu_mr, IOMMU_ATTR_SPAPR_TCE_F= D, - ¶m.tablefd)) { - QLIST_FOREACH(group, &container->group_list, container_next) { - param.groupfd =3D group->fd; - if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr))= { - error_setg_errno(errp, errno, - "vfio: failed GROUP_SET_SPAPR_TCE for= " - "KVM VFIO device %d and group fd %d", - param.tablefd, param.groupfd); - return -errno; - } - trace_vfio_spapr_group_attach(param.groupfd, param.tablefd= ); - } - } - } -#endif - return 0; -} - -static void vfio_container_del_section_window(VFIOContainer *container, - MemoryRegionSection *section) -{ - if (container->iommu_type !=3D VFIO_SPAPR_TCE_v2_IOMMU) { - return; - } - - vfio_spapr_remove_window(container, - section->offset_within_address_space); - if (vfio_host_win_del(container, - section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1) < 0) { - hw_error("%s: Cannot delete missing window at %"HWADDR_PRIx, - __func__, section->offset_within_address_space); - } -} - static void vfio_listener_region_add(MemoryListener *listener, MemoryRegionSection *section) { @@ -1127,33 +871,6 @@ static void vfio_listener_region_del(MemoryListener *= listener, vfio_container_del_section_window(container, section); } =20 -static int vfio_set_dirty_page_tracking(VFIOContainer *container, bool sta= rt) -{ - int ret; - struct vfio_iommu_type1_dirty_bitmap dirty =3D { - .argsz =3D sizeof(dirty), - }; - - if (!container->dirty_pages_supported) { - return 0; - } - - if (start) { - dirty.flags =3D VFIO_IOMMU_DIRTY_PAGES_FLAG_START; - } else { - dirty.flags =3D VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP; - } - - ret =3D ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, &dirty); - if (ret) { - ret =3D -errno; - error_report("Failed to set dirty tracking flag 0x%x errno: %d", - dirty.flags, errno); - } - - return ret; -} - typedef struct VFIODirtyRanges { hwaddr min32; hwaddr max32; @@ -1473,9 +1190,9 @@ static int vfio_device_dma_logging_report(VFIODevice = *vbasedev, hwaddr iova, return 0; } =20 -static int vfio_devices_query_dirty_bitmap(VFIOContainer *container, - VFIOBitmap *vbmap, hwaddr iova, - hwaddr size) +int vfio_devices_query_dirty_bitmap(VFIOContainer *container, + VFIOBitmap *vbmap, hwaddr iova, + hwaddr size) { VFIODevice *vbasedev; int ret; @@ -1496,45 +1213,8 @@ static int vfio_devices_query_dirty_bitmap(VFIOConta= iner *container, return 0; } =20 -static int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *v= bmap, - hwaddr iova, hwaddr size) -{ - struct vfio_iommu_type1_dirty_bitmap *dbitmap; - struct vfio_iommu_type1_dirty_bitmap_get *range; - int ret; - - dbitmap =3D g_malloc0(sizeof(*dbitmap) + sizeof(*range)); - - dbitmap->argsz =3D sizeof(*dbitmap) + sizeof(*range); - dbitmap->flags =3D VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP; - range =3D (struct vfio_iommu_type1_dirty_bitmap_get *)&dbitmap->data; - range->iova =3D iova; - range->size =3D size; - - /* - * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of - * qemu_real_host_page_size to mark those dirty. Hence set bitmap's pg= size - * to qemu_real_host_page_size. - */ - range->bitmap.pgsize =3D qemu_real_host_page_size(); - range->bitmap.size =3D vbmap->size; - range->bitmap.data =3D (__u64 *)vbmap->bitmap; - - ret =3D ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, dbitmap); - if (ret) { - ret =3D -errno; - error_report("Failed to get dirty bitmap for iova: 0x%"PRIx64 - " size: 0x%"PRIx64" err: %d", (uint64_t)range->iova, - (uint64_t)range->size, errno); - } - - g_free(dbitmap); - - return ret; -} - -static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, - uint64_t size, ram_addr_t ram_addr) +int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, + uint64_t size, ram_addr_t ram_addr) { bool all_device_dirty_tracking =3D vfio_devices_all_device_dirty_tracking(container); @@ -1723,7 +1403,7 @@ static void vfio_listener_log_sync(MemoryListener *li= stener, } } =20 -static const MemoryListener vfio_memory_listener =3D { +const MemoryListener vfio_memory_listener =3D { .name =3D "vfio", .region_add =3D vfio_listener_region_add, .region_del =3D vfio_listener_region_del, @@ -1732,45 +1412,6 @@ static const MemoryListener vfio_memory_listener =3D= { .log_sync =3D vfio_listener_log_sync, }; =20 -static void vfio_listener_release(VFIOContainer *container) -{ - memory_listener_unregister(&container->listener); - if (container->iommu_type =3D=3D VFIO_SPAPR_TCE_v2_IOMMU) { - memory_listener_unregister(&container->prereg_listener); - } -} - -static struct vfio_info_cap_header * -vfio_get_iommu_type1_info_cap(struct vfio_iommu_type1_info *info, uint16_t= id) -{ - if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) { - return NULL; - } - - return vfio_get_cap((void *)info, info->cap_offset, id); -} - -bool vfio_get_info_dma_avail(struct vfio_iommu_type1_info *info, - unsigned int *avail) -{ - struct vfio_info_cap_header *hdr; - struct vfio_iommu_type1_info_dma_avail *cap; - - /* If the capability cannot be found, assume no DMA limiting */ - hdr =3D vfio_get_iommu_type1_info_cap(info, - VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL); - if (hdr =3D=3D NULL) { - return false; - } - - if (avail !=3D NULL) { - cap =3D (void *) hdr; - *avail =3D cap->avail; - } - - return true; -} - void vfio_reset_handler(void *opaque) { VFIODevice *vbasedev; @@ -1846,25 +1487,7 @@ int vfio_kvm_device_del_fd(int fd, Error **errp) return 0; } =20 -static void vfio_kvm_device_add_group(VFIOGroup *group) -{ - Error *err =3D NULL; - - if (vfio_kvm_device_add_fd(group->fd, &err)) { - error_reportf_err(err, "group ID %d: ", group->groupid); - } -} - -static void vfio_kvm_device_del_group(VFIOGroup *group) -{ - Error *err =3D NULL; - - if (vfio_kvm_device_del_fd(group->fd, &err)) { - error_reportf_err(err, "group ID %d: ", group->groupid); - } -} - -static VFIOAddressSpace *vfio_get_address_space(AddressSpace *as) +VFIOAddressSpace *vfio_get_address_space(AddressSpace *as) { VFIOAddressSpace *space; =20 @@ -1888,7 +1511,7 @@ static VFIOAddressSpace *vfio_get_address_space(Addre= ssSpace *as) return space; } =20 -static void vfio_put_address_space(VFIOAddressSpace *space) +void vfio_put_address_space(VFIOAddressSpace *space) { if (QLIST_EMPTY(&space->containers)) { QLIST_REMOVE(space, list); @@ -1899,499 +1522,6 @@ static void vfio_put_address_space(VFIOAddressSpace= *space) } } =20 -/* - * vfio_get_iommu_type - selects the richest iommu_type (v2 first) - */ -static int vfio_get_iommu_type(VFIOContainer *container, - Error **errp) -{ - int iommu_types[] =3D { VFIO_TYPE1v2_IOMMU, VFIO_TYPE1_IOMMU, - VFIO_SPAPR_TCE_v2_IOMMU, VFIO_SPAPR_TCE_IOMMU }; - int i; - - for (i =3D 0; i < ARRAY_SIZE(iommu_types); i++) { - if (ioctl(container->fd, VFIO_CHECK_EXTENSION, iommu_types[i])) { - return iommu_types[i]; - } - } - error_setg(errp, "No available IOMMU models"); - return -EINVAL; -} - -static int vfio_init_container(VFIOContainer *container, int group_fd, - Error **errp) -{ - int iommu_type, ret; - - iommu_type =3D vfio_get_iommu_type(container, errp); - if (iommu_type < 0) { - return iommu_type; - } - - ret =3D ioctl(group_fd, VFIO_GROUP_SET_CONTAINER, &container->fd); - if (ret) { - error_setg_errno(errp, errno, "Failed to set group container"); - return -errno; - } - - while (ioctl(container->fd, VFIO_SET_IOMMU, iommu_type)) { - if (iommu_type =3D=3D VFIO_SPAPR_TCE_v2_IOMMU) { - /* - * On sPAPR, despite the IOMMU subdriver always advertises v1 = and - * v2, the running platform may not support v2 and there is no - * way to guess it until an IOMMU group gets added to the cont= ainer. - * So in case it fails with v2, try v1 as a fallback. - */ - iommu_type =3D VFIO_SPAPR_TCE_IOMMU; - continue; - } - error_setg_errno(errp, errno, "Failed to set iommu for container"); - return -errno; - } - - container->iommu_type =3D iommu_type; - return 0; -} - -static int vfio_get_iommu_info(VFIOContainer *container, - struct vfio_iommu_type1_info **info) -{ - - size_t argsz =3D sizeof(struct vfio_iommu_type1_info); - - *info =3D g_new0(struct vfio_iommu_type1_info, 1); -again: - (*info)->argsz =3D argsz; - - if (ioctl(container->fd, VFIO_IOMMU_GET_INFO, *info)) { - g_free(*info); - *info =3D NULL; - return -errno; - } - - if (((*info)->argsz > argsz)) { - argsz =3D (*info)->argsz; - *info =3D g_realloc(*info, argsz); - goto again; - } - - return 0; -} - -static struct vfio_info_cap_header * -vfio_get_iommu_info_cap(struct vfio_iommu_type1_info *info, uint16_t id) -{ - struct vfio_info_cap_header *hdr; - void *ptr =3D info; - - if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) { - return NULL; - } - - for (hdr =3D ptr + info->cap_offset; hdr !=3D ptr; hdr =3D ptr + hdr->= next) { - if (hdr->id =3D=3D id) { - return hdr; - } - } - - return NULL; -} - -static void vfio_get_iommu_info_migration(VFIOContainer *container, - struct vfio_iommu_type1_info *inf= o) -{ - struct vfio_info_cap_header *hdr; - struct vfio_iommu_type1_info_cap_migration *cap_mig; - - hdr =3D vfio_get_iommu_info_cap(info, VFIO_IOMMU_TYPE1_INFO_CAP_MIGRAT= ION); - if (!hdr) { - return; - } - - cap_mig =3D container_of(hdr, struct vfio_iommu_type1_info_cap_migrati= on, - header); - - /* - * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of - * qemu_real_host_page_size to mark those dirty. - */ - if (cap_mig->pgsize_bitmap & qemu_real_host_page_size()) { - container->dirty_pages_supported =3D true; - container->max_dirty_bitmap_size =3D cap_mig->max_dirty_bitmap_siz= e; - container->dirty_pgsizes =3D cap_mig->pgsize_bitmap; - } -} - -static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, - Error **errp) -{ - VFIOContainer *container; - int ret, fd; - VFIOAddressSpace *space; - - space =3D vfio_get_address_space(as); - - /* - * VFIO is currently incompatible with discarding of RAM insofar as the - * madvise to purge (zap) the page from QEMU's address space does not - * interact with the memory API and therefore leaves stale virtual to - * physical mappings in the IOMMU if the page was previously pinned. = We - * therefore set discarding broken for each group added to a container, - * whether the container is used individually or shared. This provides - * us with options to allow devices within a group to opt-in and allow - * discarding, so long as it is done consistently for a group (for ins= tance - * if the device is an mdev device where it is known that the host ven= dor - * driver will never pin pages outside of the working set of the guest - * driver, which would thus not be discarding candidates). - * - * The first opportunity to induce pinning occurs here where we attemp= t to - * attach the group to existing containers within the AddressSpace. I= f any - * pages are already zapped from the virtual address space, such as fr= om - * previous discards, new pinning will cause valid mappings to be - * re-established. Likewise, when the overall MemoryListener for a new - * container is registered, a replay of mappings within the AddressSpa= ce - * will occur, re-establishing any previously zapped pages as well. - * - * Especially virtio-balloon is currently only prevented from discardi= ng - * new memory, it will not yet set ram_block_discard_set_required() and - * therefore, neither stops us here or deals with the sudden memory - * consumption of inflated memory. - * - * We do support discarding of memory coordinated via the RamDiscardMa= nager - * with some IOMMU types. vfio_ram_block_discard_disable() handles the - * details once we know which type of IOMMU we are using. - */ - - QLIST_FOREACH(container, &space->containers, next) { - if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) { - ret =3D vfio_ram_block_discard_disable(container, true); - if (ret) { - error_setg_errno(errp, -ret, - "Cannot set discarding of RAM broken"); - if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, - &container->fd)) { - error_report("vfio: error disconnecting group %d from" - " container", group->groupid); - } - return ret; - } - group->container =3D container; - QLIST_INSERT_HEAD(&container->group_list, group, container_nex= t); - vfio_kvm_device_add_group(group); - return 0; - } - } - - fd =3D qemu_open_old("/dev/vfio/vfio", O_RDWR); - if (fd < 0) { - error_setg_errno(errp, errno, "failed to open /dev/vfio/vfio"); - ret =3D -errno; - goto put_space_exit; - } - - ret =3D ioctl(fd, VFIO_GET_API_VERSION); - if (ret !=3D VFIO_API_VERSION) { - error_setg(errp, "supported vfio version: %d, " - "reported version: %d", VFIO_API_VERSION, ret); - ret =3D -EINVAL; - goto close_fd_exit; - } - - container =3D g_malloc0(sizeof(*container)); - container->space =3D space; - container->fd =3D fd; - container->error =3D NULL; - container->dirty_pages_supported =3D false; - container->dma_max_mappings =3D 0; - QLIST_INIT(&container->giommu_list); - QLIST_INIT(&container->hostwin_list); - QLIST_INIT(&container->vrdl_list); - - ret =3D vfio_init_container(container, group->fd, errp); - if (ret) { - goto free_container_exit; - } - - ret =3D vfio_ram_block_discard_disable(container, true); - if (ret) { - error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken"= ); - goto free_container_exit; - } - - switch (container->iommu_type) { - case VFIO_TYPE1v2_IOMMU: - case VFIO_TYPE1_IOMMU: - { - struct vfio_iommu_type1_info *info; - - ret =3D vfio_get_iommu_info(container, &info); - if (ret) { - error_setg_errno(errp, -ret, "Failed to get VFIO IOMMU info"); - goto enable_discards_exit; - } - - if (info->flags & VFIO_IOMMU_INFO_PGSIZES) { - container->pgsizes =3D info->iova_pgsizes; - } else { - container->pgsizes =3D qemu_real_host_page_size(); - } - - if (!vfio_get_info_dma_avail(info, &container->dma_max_mappings)) { - container->dma_max_mappings =3D 65535; - } - vfio_get_iommu_info_migration(container, info); - g_free(info); - - /* - * FIXME: We should parse VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE - * information to get the actual window extent rather than assume - * a 64-bit IOVA address space. - */ - vfio_host_win_add(container, 0, (hwaddr)-1, container->pgsizes); - - break; - } - case VFIO_SPAPR_TCE_v2_IOMMU: - case VFIO_SPAPR_TCE_IOMMU: - { - struct vfio_iommu_spapr_tce_info info; - bool v2 =3D container->iommu_type =3D=3D VFIO_SPAPR_TCE_v2_IOMMU; - - /* - * The host kernel code implementing VFIO_IOMMU_DISABLE is called - * when container fd is closed so we do not call it explicitly - * in this file. - */ - if (!v2) { - ret =3D ioctl(fd, VFIO_IOMMU_ENABLE); - if (ret) { - error_setg_errno(errp, errno, "failed to enable container"= ); - ret =3D -errno; - goto enable_discards_exit; - } - } else { - container->prereg_listener =3D vfio_prereg_listener; - - memory_listener_register(&container->prereg_listener, - &address_space_memory); - if (container->error) { - memory_listener_unregister(&container->prereg_listener); - ret =3D -1; - error_propagate_prepend(errp, container->error, - "RAM memory listener initialization failed: "); - goto enable_discards_exit; - } - } - - info.argsz =3D sizeof(info); - ret =3D ioctl(fd, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info); - if (ret) { - error_setg_errno(errp, errno, - "VFIO_IOMMU_SPAPR_TCE_GET_INFO failed"); - ret =3D -errno; - if (v2) { - memory_listener_unregister(&container->prereg_listener); - } - goto enable_discards_exit; - } - - if (v2) { - container->pgsizes =3D info.ddw.pgsizes; - /* - * There is a default window in just created container. - * To make region_add/del simpler, we better remove this - * window now and let those iommu_listener callbacks - * create/remove them when needed. - */ - ret =3D vfio_spapr_remove_window(container, info.dma32_window_= start); - if (ret) { - error_setg_errno(errp, -ret, - "failed to remove existing window"); - goto enable_discards_exit; - } - } else { - /* The default table uses 4K pages */ - container->pgsizes =3D 0x1000; - vfio_host_win_add(container, info.dma32_window_start, - info.dma32_window_start + - info.dma32_window_size - 1, - 0x1000); - } - } - } - - vfio_kvm_device_add_group(group); - - QLIST_INIT(&container->group_list); - QLIST_INSERT_HEAD(&space->containers, container, next); - - group->container =3D container; - QLIST_INSERT_HEAD(&container->group_list, group, container_next); - - container->listener =3D vfio_memory_listener; - - memory_listener_register(&container->listener, container->space->as); - - if (container->error) { - ret =3D -1; - error_propagate_prepend(errp, container->error, - "memory listener initialization failed: "); - goto listener_release_exit; - } - - container->initialized =3D true; - - return 0; -listener_release_exit: - QLIST_REMOVE(group, container_next); - QLIST_REMOVE(container, next); - vfio_kvm_device_del_group(group); - vfio_listener_release(container); - -enable_discards_exit: - vfio_ram_block_discard_disable(container, false); - -free_container_exit: - g_free(container); - -close_fd_exit: - close(fd); - -put_space_exit: - vfio_put_address_space(space); - - return ret; -} - -static void vfio_disconnect_container(VFIOGroup *group) -{ - VFIOContainer *container =3D group->container; - - QLIST_REMOVE(group, container_next); - group->container =3D NULL; - - /* - * Explicitly release the listener first before unset container, - * since unset may destroy the backend container if it's the last - * group. - */ - if (QLIST_EMPTY(&container->group_list)) { - vfio_listener_release(container); - } - - if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, &container->fd)) { - error_report("vfio: error disconnecting group %d from container", - group->groupid); - } - - if (QLIST_EMPTY(&container->group_list)) { - VFIOAddressSpace *space =3D container->space; - VFIOGuestIOMMU *giommu, *tmp; - VFIOHostDMAWindow *hostwin, *next; - - QLIST_REMOVE(container, next); - - QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, t= mp) { - memory_region_unregister_iommu_notifier( - MEMORY_REGION(giommu->iommu_mr), &giommu->n); - QLIST_REMOVE(giommu, giommu_next); - g_free(giommu); - } - - QLIST_FOREACH_SAFE(hostwin, &container->hostwin_list, hostwin_next, - next) { - QLIST_REMOVE(hostwin, hostwin_next); - g_free(hostwin); - } - - trace_vfio_disconnect_container(container->fd); - close(container->fd); - g_free(container); - - vfio_put_address_space(space); - } -} - -static VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **er= rp) -{ - VFIOGroup *group; - char path[32]; - struct vfio_group_status status =3D { .argsz =3D sizeof(status) }; - - QLIST_FOREACH(group, &vfio_group_list, next) { - if (group->groupid =3D=3D groupid) { - /* Found it. Now is it already in the right context? */ - if (group->container->space->as =3D=3D as) { - return group; - } else { - error_setg(errp, "group %d used in multiple address spaces= ", - group->groupid); - return NULL; - } - } - } - - group =3D g_malloc0(sizeof(*group)); - - snprintf(path, sizeof(path), "/dev/vfio/%d", groupid); - group->fd =3D qemu_open_old(path, O_RDWR); - if (group->fd < 0) { - error_setg_errno(errp, errno, "failed to open %s", path); - goto free_group_exit; - } - - if (ioctl(group->fd, VFIO_GROUP_GET_STATUS, &status)) { - error_setg_errno(errp, errno, "failed to get group %d status", gro= upid); - goto close_fd_exit; - } - - if (!(status.flags & VFIO_GROUP_FLAGS_VIABLE)) { - error_setg(errp, "group %d is not viable", groupid); - error_append_hint(errp, - "Please ensure all devices within the iommu_grou= p " - "are bound to their vfio bus driver.\n"); - goto close_fd_exit; - } - - group->groupid =3D groupid; - QLIST_INIT(&group->device_list); - - if (vfio_connect_container(group, as, errp)) { - error_prepend(errp, "failed to setup container for group %d: ", - groupid); - goto close_fd_exit; - } - - QLIST_INSERT_HEAD(&vfio_group_list, group, next); - - return group; - -close_fd_exit: - close(group->fd); - -free_group_exit: - g_free(group); - - return NULL; -} - -static void vfio_put_group(VFIOGroup *group) -{ - if (!group || !QLIST_EMPTY(&group->device_list)) { - return; - } - - if (!group->ram_block_discard_allowed) { - vfio_ram_block_discard_disable(group->container, false); - } - vfio_kvm_device_del_group(group); - vfio_disconnect_container(group); - QLIST_REMOVE(group, next); - trace_vfio_put_group(group->fd); - close(group->fd); - g_free(group); -} - struct vfio_device_info *vfio_get_device_info(int fd) { struct vfio_device_info *info; @@ -2415,256 +1545,3 @@ retry: =20 return info; } - -static int vfio_get_device(VFIOGroup *group, const char *name, - VFIODevice *vbasedev, Error **errp) -{ - g_autofree struct vfio_device_info *info =3D NULL; - int fd; - - fd =3D ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name); - if (fd < 0) { - error_setg_errno(errp, errno, "error getting device from group %d", - group->groupid); - error_append_hint(errp, - "Verify all devices in group %d are bound to vfio- " - "or pci-stub and not already in use\n", group->group= id); - return fd; - } - - info =3D vfio_get_device_info(fd); - if (!info) { - error_setg_errno(errp, errno, "error getting device info"); - close(fd); - return -1; - } - - /* - * Set discarding of RAM as not broken for this group if the driver kn= ows - * the device operates compatibly with discarding. Setting must be - * consistent per group, but since compatibility is really only possib= le - * with mdev currently, we expect singleton groups. - */ - if (vbasedev->ram_block_discard_allowed !=3D - group->ram_block_discard_allowed) { - if (!QLIST_EMPTY(&group->device_list)) { - error_setg(errp, "Inconsistent setting of support for discardi= ng " - "RAM (e.g., balloon) within group"); - close(fd); - return -1; - } - - if (!group->ram_block_discard_allowed) { - group->ram_block_discard_allowed =3D true; - vfio_ram_block_discard_disable(group->container, false); - } - } - - vbasedev->fd =3D fd; - vbasedev->group =3D group; - QLIST_INSERT_HEAD(&group->device_list, vbasedev, next); - - vbasedev->num_irqs =3D info->num_irqs; - vbasedev->num_regions =3D info->num_regions; - vbasedev->flags =3D info->flags; - - trace_vfio_get_device(name, info->flags, info->num_regions, info->num_= irqs); - - vbasedev->reset_works =3D !!(info->flags & VFIO_DEVICE_FLAGS_RESET); - - return 0; -} - -static void vfio_put_base_device(VFIODevice *vbasedev) -{ - if (!vbasedev->group) { - return; - } - QLIST_REMOVE(vbasedev, next); - vbasedev->group =3D NULL; - trace_vfio_put_base_device(vbasedev->fd); - close(vbasedev->fd); -} - -/* - * Interfaces for IBM EEH (Enhanced Error Handling) - */ -static bool vfio_eeh_container_ok(VFIOContainer *container) -{ - /* - * As of 2016-03-04 (linux-4.5) the host kernel EEH/VFIO - * implementation is broken if there are multiple groups in a - * container. The hardware works in units of Partitionable - * Endpoints (=3D=3D IOMMU groups) and the EEH operations naively - * iterate across all groups in the container, without any logic - * to make sure the groups have their state synchronized. For - * certain operations (ENABLE) that might be ok, until an error - * occurs, but for others (GET_STATE) it's clearly broken. - */ - - /* - * XXX Once fixed kernels exist, test for them here - */ - - if (QLIST_EMPTY(&container->group_list)) { - return false; - } - - if (QLIST_NEXT(QLIST_FIRST(&container->group_list), container_next)) { - return false; - } - - return true; -} - -static int vfio_eeh_container_op(VFIOContainer *container, uint32_t op) -{ - struct vfio_eeh_pe_op pe_op =3D { - .argsz =3D sizeof(pe_op), - .op =3D op, - }; - int ret; - - if (!vfio_eeh_container_ok(container)) { - error_report("vfio/eeh: EEH_PE_OP 0x%x: " - "kernel requires a container with exactly one group",= op); - return -EPERM; - } - - ret =3D ioctl(container->fd, VFIO_EEH_PE_OP, &pe_op); - if (ret < 0) { - error_report("vfio/eeh: EEH_PE_OP 0x%x failed: %m", op); - return -errno; - } - - return ret; -} - -static VFIOContainer *vfio_eeh_as_container(AddressSpace *as) -{ - VFIOAddressSpace *space =3D vfio_get_address_space(as); - VFIOContainer *container =3D NULL; - - if (QLIST_EMPTY(&space->containers)) { - /* No containers to act on */ - goto out; - } - - container =3D QLIST_FIRST(&space->containers); - - if (QLIST_NEXT(container, next)) { - /* We don't yet have logic to synchronize EEH state across - * multiple containers */ - container =3D NULL; - goto out; - } - -out: - vfio_put_address_space(space); - return container; -} - -bool vfio_eeh_as_ok(AddressSpace *as) -{ - VFIOContainer *container =3D vfio_eeh_as_container(as); - - return (container !=3D NULL) && vfio_eeh_container_ok(container); -} - -int vfio_eeh_as_op(AddressSpace *as, uint32_t op) -{ - VFIOContainer *container =3D vfio_eeh_as_container(as); - - if (!container) { - return -ENODEV; - } - return vfio_eeh_container_op(container, op); -} - -static int vfio_device_groupid(VFIODevice *vbasedev, Error **errp) -{ - char *tmp, group_path[PATH_MAX], *group_name; - int ret, groupid; - ssize_t len; - - tmp =3D g_strdup_printf("%s/iommu_group", vbasedev->sysfsdev); - len =3D readlink(tmp, group_path, sizeof(group_path)); - g_free(tmp); - - if (len <=3D 0 || len >=3D sizeof(group_path)) { - ret =3D len < 0 ? -errno : -ENAMETOOLONG; - error_setg_errno(errp, -ret, "no iommu_group found"); - return ret; - } - - group_path[len] =3D 0; - - group_name =3D basename(group_path); - if (sscanf(group_name, "%d", &groupid) !=3D 1) { - error_setg_errno(errp, errno, "failed to read %s", group_path); - return -errno; - } - return groupid; -} - -/* - * vfio_attach_device: attach a device to a security context - * @name and @vbasedev->name are likely to be different depending - * on the type of the device, hence the need for passing @name - */ -int vfio_attach_device(char *name, VFIODevice *vbasedev, - AddressSpace *as, Error **errp) -{ - int groupid =3D vfio_device_groupid(vbasedev, errp); - VFIODevice *vbasedev_iter; - VFIOGroup *group; - VFIOContainer *container; - int ret; - - if (groupid < 0) { - return groupid; - } - - trace_vfio_attach_device(vbasedev->name, groupid); - - group =3D vfio_get_group(groupid, as, errp); - if (!group) { - return -ENOENT; - } - - QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { - if (strcmp(vbasedev_iter->name, vbasedev->name) =3D=3D 0) { - error_setg(errp, "device is already attached"); - vfio_put_group(group); - return -EBUSY; - } - } - ret =3D vfio_get_device(group, name, vbasedev, errp); - if (ret) { - vfio_put_group(group); - return ret; - } - - container =3D group->container; - vbasedev->container =3D container; - QLIST_INSERT_HEAD(&container->device_list, vbasedev, container_next); - QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next); - - return ret; -} - -void vfio_detach_device(VFIODevice *vbasedev) -{ - VFIOGroup *group =3D vbasedev->group; - - if (!vbasedev->container) { - return; - } - - QLIST_REMOVE(vbasedev, global_next); - QLIST_REMOVE(vbasedev, container_next); - vbasedev->container =3D NULL; - trace_vfio_detach_device(vbasedev->name, group->groupid); - vfio_put_base_device(vbasedev); - vfio_put_group(group); -} diff --git a/hw/vfio/container.c b/hw/vfio/container.c new file mode 100644 index 0000000000..2527a263cc --- /dev/null +++ b/hw/vfio/container.c @@ -0,0 +1,1156 @@ +/* + * generic functions used by VFIO devices + * + * Copyright Red Hat, Inc. 2012 + * + * Authors: + * Alex Williamson + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Based on qemu-kvm device-assignment: + * Adapted for KVM by Qumranet. + * Copyright (c) 2007, Neocleus, Alex Novik (alex@neocleus.com) + * Copyright (c) 2007, Neocleus, Guy Zana (guy@neocleus.com) + * Copyright (C) 2008, Qumranet, Amit Shah (amit.shah@qumranet.com) + * Copyright (C) 2008, Red Hat, Amit Shah (amit.shah@redhat.com) + * Copyright (C) 2008, IBM, Muli Ben-Yehuda (muli@il.ibm.com) + */ + +#include "qemu/osdep.h" +#include +#ifdef CONFIG_KVM +#include +#endif +#include + +#include "hw/vfio/vfio-common.h" +#include "hw/vfio/vfio.h" +#include "exec/address-spaces.h" +#include "exec/memory.h" +#include "exec/ram_addr.h" +#include "hw/hw.h" +#include "qemu/error-report.h" +#include "qemu/range.h" +#include "sysemu/kvm.h" +#include "sysemu/reset.h" +#include "trace.h" +#include "qapi/error.h" +#include "migration/migration.h" + +VFIOGroupList vfio_group_list =3D + QLIST_HEAD_INITIALIZER(vfio_group_list); + +static int vfio_ram_block_discard_disable(VFIOContainer *container, bool s= tate) +{ + switch (container->iommu_type) { + case VFIO_TYPE1v2_IOMMU: + case VFIO_TYPE1_IOMMU: + /* + * We support coordinated discarding of RAM via the RamDiscardMana= ger. + */ + return ram_block_uncoordinated_discard_disable(state); + default: + /* + * VFIO_SPAPR_TCE_IOMMU most probably works just fine with + * RamDiscardManager, however, it is completely untested. + * + * VFIO_SPAPR_TCE_v2_IOMMU with "DMA memory preregistering" does + * completely the opposite of managing mapping/pinning dynamically= as + * required by RamDiscardManager. We would have to special-case se= ctions + * with a RamDiscardManager. + */ + return ram_block_discard_disable(state); + } +} + +static int vfio_dma_unmap_bitmap(VFIOContainer *container, + hwaddr iova, ram_addr_t size, + IOMMUTLBEntry *iotlb) +{ + struct vfio_iommu_type1_dma_unmap *unmap; + struct vfio_bitmap *bitmap; + VFIOBitmap vbmap; + int ret; + + ret =3D vfio_bitmap_alloc(&vbmap, size); + if (ret) { + return ret; + } + + unmap =3D g_malloc0(sizeof(*unmap) + sizeof(*bitmap)); + + unmap->argsz =3D sizeof(*unmap) + sizeof(*bitmap); + unmap->iova =3D iova; + unmap->size =3D size; + unmap->flags |=3D VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP; + bitmap =3D (struct vfio_bitmap *)&unmap->data; + + /* + * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of + * qemu_real_host_page_size to mark those dirty. Hence set bitmap_pgsi= ze + * to qemu_real_host_page_size. + */ + bitmap->pgsize =3D qemu_real_host_page_size(); + bitmap->size =3D vbmap.size; + bitmap->data =3D (__u64 *)vbmap.bitmap; + + if (vbmap.size > container->max_dirty_bitmap_size) { + error_report("UNMAP: Size of bitmap too big 0x%"PRIx64, vbmap.size= ); + ret =3D -E2BIG; + goto unmap_exit; + } + + ret =3D ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap); + if (!ret) { + cpu_physical_memory_set_dirty_lebitmap(vbmap.bitmap, + iotlb->translated_addr, vbmap.pages); + } else { + error_report("VFIO_UNMAP_DMA with DIRTY_BITMAP : %m"); + } + +unmap_exit: + g_free(unmap); + g_free(vbmap.bitmap); + + return ret; +} + +/* + * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86 + */ +int vfio_dma_unmap(VFIOContainer *container, hwaddr iova, + ram_addr_t size, IOMMUTLBEntry *iotlb) +{ + struct vfio_iommu_type1_dma_unmap unmap =3D { + .argsz =3D sizeof(unmap), + .flags =3D 0, + .iova =3D iova, + .size =3D size, + }; + bool need_dirty_sync =3D false; + int ret; + + if (iotlb && vfio_devices_all_running_and_mig_active(container)) { + if (!vfio_devices_all_device_dirty_tracking(container) && + container->dirty_pages_supported) { + return vfio_dma_unmap_bitmap(container, iova, size, iotlb); + } + + need_dirty_sync =3D true; + } + + while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) { + /* + * The type1 backend has an off-by-one bug in the kernel (71a7d3d7= 8e3c + * v4.15) where an overflow in its wrap-around check prevents us f= rom + * unmapping the last page of the address space. Test for the err= or + * condition and re-try the unmap excluding the last page. The + * expectation is that we've never mapped the last page anyway and= this + * unmap request comes via vIOMMU support which also makes it unli= kely + * that this page is used. This bug was introduced well after typ= e1 v2 + * support was introduced, so we shouldn't need to test for v1. A= fix + * is queued for kernel v5.0 so this workaround can be removed once + * affected kernels are sufficiently deprecated. + */ + if (errno =3D=3D EINVAL && unmap.size && !(unmap.iova + unmap.size= ) && + container->iommu_type =3D=3D VFIO_TYPE1v2_IOMMU) { + trace_vfio_dma_unmap_overflow_workaround(); + unmap.size -=3D 1ULL << ctz64(container->pgsizes); + continue; + } + error_report("VFIO_UNMAP_DMA failed: %s", strerror(errno)); + return -errno; + } + + if (need_dirty_sync) { + ret =3D vfio_get_dirty_bitmap(container, iova, size, + iotlb->translated_addr); + if (ret) { + return ret; + } + } + + return 0; +} + +int vfio_dma_map(VFIOContainer *container, hwaddr iova, + ram_addr_t size, void *vaddr, bool readonly) +{ + struct vfio_iommu_type1_dma_map map =3D { + .argsz =3D sizeof(map), + .flags =3D VFIO_DMA_MAP_FLAG_READ, + .vaddr =3D (__u64)(uintptr_t)vaddr, + .iova =3D iova, + .size =3D size, + }; + + if (!readonly) { + map.flags |=3D VFIO_DMA_MAP_FLAG_WRITE; + } + + /* + * Try the mapping, if it fails with EBUSY, unmap the region and try + * again. This shouldn't be necessary, but we sometimes see it in + * the VGA ROM space. + */ + if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) =3D=3D 0 || + (errno =3D=3D EBUSY && vfio_dma_unmap(container, iova, size, NULL)= =3D=3D 0 && + ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) =3D=3D 0)) { + return 0; + } + + error_report("VFIO_MAP_DMA failed: %s", strerror(errno)); + return -errno; +} + +int vfio_container_add_section_window(VFIOContainer *container, + MemoryRegionSection *section, + Error **errp) +{ + VFIOHostDMAWindow *hostwin; + hwaddr pgsize =3D 0; + int ret; + + if (container->iommu_type !=3D VFIO_SPAPR_TCE_v2_IOMMU) { + return 0; + } + + /* For now intersections are not allowed, we may relax this later */ + QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { + if (ranges_overlap(hostwin->min_iova, + hostwin->max_iova - hostwin->min_iova + 1, + section->offset_within_address_space, + int128_get64(section->size))) { + error_setg(errp, + "region [0x%"PRIx64",0x%"PRIx64"] overlaps with existing" + "host DMA window [0x%"PRIx64",0x%"PRIx64"]", + section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(section->size) - 1, + hostwin->min_iova, hostwin->max_iova); + return -EINVAL; + } + } + + ret =3D vfio_spapr_create_window(container, section, &pgsize); + if (ret) { + error_setg_errno(errp, -ret, "Failed to create SPAPR window"); + return ret; + } + + vfio_host_win_add(container, section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(section->size) - 1, pgsize); +#ifdef CONFIG_KVM + if (kvm_enabled()) { + VFIOGroup *group; + IOMMUMemoryRegion *iommu_mr =3D IOMMU_MEMORY_REGION(section->mr); + struct kvm_vfio_spapr_tce param; + struct kvm_device_attr attr =3D { + .group =3D KVM_DEV_VFIO_GROUP, + .attr =3D KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE, + .addr =3D (uint64_t)(unsigned long)¶m, + }; + + if (!memory_region_iommu_get_attr(iommu_mr, IOMMU_ATTR_SPAPR_TCE_F= D, + ¶m.tablefd)) { + QLIST_FOREACH(group, &container->group_list, container_next) { + param.groupfd =3D group->fd; + if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr))= { + error_setg_errno(errp, errno, + "vfio: failed GROUP_SET_SPAPR_TCE for= " + "KVM VFIO device %d and group fd %d", + param.tablefd, param.groupfd); + return -errno; + } + trace_vfio_spapr_group_attach(param.groupfd, param.tablefd= ); + } + } + } +#endif + return 0; +} + +void vfio_container_del_section_window(VFIOContainer *container, + MemoryRegionSection *section) +{ + if (container->iommu_type !=3D VFIO_SPAPR_TCE_v2_IOMMU) { + return; + } + + vfio_spapr_remove_window(container, + section->offset_within_address_space); + if (vfio_host_win_del(container, + section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(section->size) - 1) < 0) { + hw_error("%s: Cannot delete missing window at %"HWADDR_PRIx, + __func__, section->offset_within_address_space); + } +} + +int vfio_set_dirty_page_tracking(VFIOContainer *container, bool start) +{ + int ret; + struct vfio_iommu_type1_dirty_bitmap dirty =3D { + .argsz =3D sizeof(dirty), + }; + + if (!container->dirty_pages_supported) { + return 0; + } + + if (start) { + dirty.flags =3D VFIO_IOMMU_DIRTY_PAGES_FLAG_START; + } else { + dirty.flags =3D VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP; + } + + ret =3D ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, &dirty); + if (ret) { + ret =3D -errno; + error_report("Failed to set dirty tracking flag 0x%x errno: %d", + dirty.flags, errno); + } + + return ret; +} + +int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *vbmap, + hwaddr iova, hwaddr size) +{ + struct vfio_iommu_type1_dirty_bitmap *dbitmap; + struct vfio_iommu_type1_dirty_bitmap_get *range; + int ret; + + dbitmap =3D g_malloc0(sizeof(*dbitmap) + sizeof(*range)); + + dbitmap->argsz =3D sizeof(*dbitmap) + sizeof(*range); + dbitmap->flags =3D VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP; + range =3D (struct vfio_iommu_type1_dirty_bitmap_get *)&dbitmap->data; + range->iova =3D iova; + range->size =3D size; + + /* + * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of + * qemu_real_host_page_size to mark those dirty. Hence set bitmap's pg= size + * to qemu_real_host_page_size. + */ + range->bitmap.pgsize =3D qemu_real_host_page_size(); + range->bitmap.size =3D vbmap->size; + range->bitmap.data =3D (__u64 *)vbmap->bitmap; + + ret =3D ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, dbitmap); + if (ret) { + ret =3D -errno; + error_report("Failed to get dirty bitmap for iova: 0x%"PRIx64 + " size: 0x%"PRIx64" err: %d", (uint64_t)range->iova, + (uint64_t)range->size, errno); + } + + g_free(dbitmap); + + return ret; +} + +static void vfio_listener_release(VFIOContainer *container) +{ + memory_listener_unregister(&container->listener); + if (container->iommu_type =3D=3D VFIO_SPAPR_TCE_v2_IOMMU) { + memory_listener_unregister(&container->prereg_listener); + } +} + +static struct vfio_info_cap_header * +vfio_get_iommu_type1_info_cap(struct vfio_iommu_type1_info *info, uint16_t= id) +{ + if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) { + return NULL; + } + + return vfio_get_cap((void *)info, info->cap_offset, id); +} + +bool vfio_get_info_dma_avail(struct vfio_iommu_type1_info *info, + unsigned int *avail) +{ + struct vfio_info_cap_header *hdr; + struct vfio_iommu_type1_info_dma_avail *cap; + + /* If the capability cannot be found, assume no DMA limiting */ + hdr =3D vfio_get_iommu_type1_info_cap(info, + VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL); + if (hdr =3D=3D NULL) { + return false; + } + + if (avail !=3D NULL) { + cap =3D (void *) hdr; + *avail =3D cap->avail; + } + + return true; +} + +static void vfio_kvm_device_add_group(VFIOGroup *group) +{ + Error *err =3D NULL; + + if (vfio_kvm_device_add_fd(group->fd, &err)) { + error_reportf_err(err, "group ID %d: ", group->groupid); + } +} + +static void vfio_kvm_device_del_group(VFIOGroup *group) +{ + Error *err =3D NULL; + + if (vfio_kvm_device_del_fd(group->fd, &err)) { + error_reportf_err(err, "group ID %d: ", group->groupid); + } +} + +/* + * vfio_get_iommu_type - selects the richest iommu_type (v2 first) + */ +static int vfio_get_iommu_type(VFIOContainer *container, + Error **errp) +{ + int iommu_types[] =3D { VFIO_TYPE1v2_IOMMU, VFIO_TYPE1_IOMMU, + VFIO_SPAPR_TCE_v2_IOMMU, VFIO_SPAPR_TCE_IOMMU }; + int i; + + for (i =3D 0; i < ARRAY_SIZE(iommu_types); i++) { + if (ioctl(container->fd, VFIO_CHECK_EXTENSION, iommu_types[i])) { + return iommu_types[i]; + } + } + error_setg(errp, "No available IOMMU models"); + return -EINVAL; +} + +static int vfio_init_container(VFIOContainer *container, int group_fd, + Error **errp) +{ + int iommu_type, ret; + + iommu_type =3D vfio_get_iommu_type(container, errp); + if (iommu_type < 0) { + return iommu_type; + } + + ret =3D ioctl(group_fd, VFIO_GROUP_SET_CONTAINER, &container->fd); + if (ret) { + error_setg_errno(errp, errno, "Failed to set group container"); + return -errno; + } + + while (ioctl(container->fd, VFIO_SET_IOMMU, iommu_type)) { + if (iommu_type =3D=3D VFIO_SPAPR_TCE_v2_IOMMU) { + /* + * On sPAPR, despite the IOMMU subdriver always advertises v1 = and + * v2, the running platform may not support v2 and there is no + * way to guess it until an IOMMU group gets added to the cont= ainer. + * So in case it fails with v2, try v1 as a fallback. + */ + iommu_type =3D VFIO_SPAPR_TCE_IOMMU; + continue; + } + error_setg_errno(errp, errno, "Failed to set iommu for container"); + return -errno; + } + + container->iommu_type =3D iommu_type; + return 0; +} + +static int vfio_get_iommu_info(VFIOContainer *container, + struct vfio_iommu_type1_info **info) +{ + + size_t argsz =3D sizeof(struct vfio_iommu_type1_info); + + *info =3D g_new0(struct vfio_iommu_type1_info, 1); +again: + (*info)->argsz =3D argsz; + + if (ioctl(container->fd, VFIO_IOMMU_GET_INFO, *info)) { + g_free(*info); + *info =3D NULL; + return -errno; + } + + if (((*info)->argsz > argsz)) { + argsz =3D (*info)->argsz; + *info =3D g_realloc(*info, argsz); + goto again; + } + + return 0; +} + +static struct vfio_info_cap_header * +vfio_get_iommu_info_cap(struct vfio_iommu_type1_info *info, uint16_t id) +{ + struct vfio_info_cap_header *hdr; + void *ptr =3D info; + + if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) { + return NULL; + } + + for (hdr =3D ptr + info->cap_offset; hdr !=3D ptr; hdr =3D ptr + hdr->= next) { + if (hdr->id =3D=3D id) { + return hdr; + } + } + + return NULL; +} + +static void vfio_get_iommu_info_migration(VFIOContainer *container, + struct vfio_iommu_type1_info *in= fo) +{ + struct vfio_info_cap_header *hdr; + struct vfio_iommu_type1_info_cap_migration *cap_mig; + + hdr =3D vfio_get_iommu_info_cap(info, VFIO_IOMMU_TYPE1_INFO_CAP_MIGRAT= ION); + if (!hdr) { + return; + } + + cap_mig =3D container_of(hdr, struct vfio_iommu_type1_info_cap_migrati= on, + header); + + /* + * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of + * qemu_real_host_page_size to mark those dirty. + */ + if (cap_mig->pgsize_bitmap & qemu_real_host_page_size()) { + container->dirty_pages_supported =3D true; + container->max_dirty_bitmap_size =3D cap_mig->max_dirty_bitmap_siz= e; + container->dirty_pgsizes =3D cap_mig->pgsize_bitmap; + } +} + +static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, + Error **errp) +{ + VFIOContainer *container; + int ret, fd; + VFIOAddressSpace *space; + + space =3D vfio_get_address_space(as); + + /* + * VFIO is currently incompatible with discarding of RAM insofar as the + * madvise to purge (zap) the page from QEMU's address space does not + * interact with the memory API and therefore leaves stale virtual to + * physical mappings in the IOMMU if the page was previously pinned. = We + * therefore set discarding broken for each group added to a container, + * whether the container is used individually or shared. This provides + * us with options to allow devices within a group to opt-in and allow + * discarding, so long as it is done consistently for a group (for ins= tance + * if the device is an mdev device where it is known that the host ven= dor + * driver will never pin pages outside of the working set of the guest + * driver, which would thus not be discarding candidates). + * + * The first opportunity to induce pinning occurs here where we attemp= t to + * attach the group to existing containers within the AddressSpace. I= f any + * pages are already zapped from the virtual address space, such as fr= om + * previous discards, new pinning will cause valid mappings to be + * re-established. Likewise, when the overall MemoryListener for a new + * container is registered, a replay of mappings within the AddressSpa= ce + * will occur, re-establishing any previously zapped pages as well. + * + * Especially virtio-balloon is currently only prevented from discardi= ng + * new memory, it will not yet set ram_block_discard_set_required() and + * therefore, neither stops us here or deals with the sudden memory + * consumption of inflated memory. + * + * We do support discarding of memory coordinated via the RamDiscardMa= nager + * with some IOMMU types. vfio_ram_block_discard_disable() handles the + * details once we know which type of IOMMU we are using. + */ + + QLIST_FOREACH(container, &space->containers, next) { + if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) { + ret =3D vfio_ram_block_discard_disable(container, true); + if (ret) { + error_setg_errno(errp, -ret, + "Cannot set discarding of RAM broken"); + if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, + &container->fd)) { + error_report("vfio: error disconnecting group %d from" + " container", group->groupid); + } + return ret; + } + group->container =3D container; + QLIST_INSERT_HEAD(&container->group_list, group, container_nex= t); + vfio_kvm_device_add_group(group); + return 0; + } + } + + fd =3D qemu_open_old("/dev/vfio/vfio", O_RDWR); + if (fd < 0) { + error_setg_errno(errp, errno, "failed to open /dev/vfio/vfio"); + ret =3D -errno; + goto put_space_exit; + } + + ret =3D ioctl(fd, VFIO_GET_API_VERSION); + if (ret !=3D VFIO_API_VERSION) { + error_setg(errp, "supported vfio version: %d, " + "reported version: %d", VFIO_API_VERSION, ret); + ret =3D -EINVAL; + goto close_fd_exit; + } + + container =3D g_malloc0(sizeof(*container)); + container->space =3D space; + container->fd =3D fd; + container->error =3D NULL; + container->dirty_pages_supported =3D false; + container->dma_max_mappings =3D 0; + QLIST_INIT(&container->giommu_list); + QLIST_INIT(&container->hostwin_list); + QLIST_INIT(&container->vrdl_list); + + ret =3D vfio_init_container(container, group->fd, errp); + if (ret) { + goto free_container_exit; + } + + ret =3D vfio_ram_block_discard_disable(container, true); + if (ret) { + error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken"= ); + goto free_container_exit; + } + + switch (container->iommu_type) { + case VFIO_TYPE1v2_IOMMU: + case VFIO_TYPE1_IOMMU: + { + struct vfio_iommu_type1_info *info; + + ret =3D vfio_get_iommu_info(container, &info); + if (ret) { + error_setg_errno(errp, -ret, "Failed to get VFIO IOMMU info"); + goto enable_discards_exit; + } + + if (info->flags & VFIO_IOMMU_INFO_PGSIZES) { + container->pgsizes =3D info->iova_pgsizes; + } else { + container->pgsizes =3D qemu_real_host_page_size(); + } + + if (!vfio_get_info_dma_avail(info, &container->dma_max_mappings)) { + container->dma_max_mappings =3D 65535; + } + vfio_get_iommu_info_migration(container, info); + g_free(info); + + /* + * FIXME: We should parse VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE + * information to get the actual window extent rather than assume + * a 64-bit IOVA address space. + */ + vfio_host_win_add(container, 0, (hwaddr)-1, container->pgsizes); + + break; + } + case VFIO_SPAPR_TCE_v2_IOMMU: + case VFIO_SPAPR_TCE_IOMMU: + { + struct vfio_iommu_spapr_tce_info info; + bool v2 =3D container->iommu_type =3D=3D VFIO_SPAPR_TCE_v2_IOMMU; + + /* + * The host kernel code implementing VFIO_IOMMU_DISABLE is called + * when container fd is closed so we do not call it explicitly + * in this file. + */ + if (!v2) { + ret =3D ioctl(fd, VFIO_IOMMU_ENABLE); + if (ret) { + error_setg_errno(errp, errno, "failed to enable container"= ); + ret =3D -errno; + goto enable_discards_exit; + } + } else { + container->prereg_listener =3D vfio_prereg_listener; + + memory_listener_register(&container->prereg_listener, + &address_space_memory); + if (container->error) { + memory_listener_unregister(&container->prereg_listener); + ret =3D -1; + error_propagate_prepend(errp, container->error, + "RAM memory listener initialization failed: "); + goto enable_discards_exit; + } + } + + info.argsz =3D sizeof(info); + ret =3D ioctl(fd, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info); + if (ret) { + error_setg_errno(errp, errno, + "VFIO_IOMMU_SPAPR_TCE_GET_INFO failed"); + ret =3D -errno; + if (v2) { + memory_listener_unregister(&container->prereg_listener); + } + goto enable_discards_exit; + } + + if (v2) { + container->pgsizes =3D info.ddw.pgsizes; + /* + * There is a default window in just created container. + * To make region_add/del simpler, we better remove this + * window now and let those iommu_listener callbacks + * create/remove them when needed. + */ + ret =3D vfio_spapr_remove_window(container, info.dma32_window_= start); + if (ret) { + error_setg_errno(errp, -ret, + "failed to remove existing window"); + goto enable_discards_exit; + } + } else { + /* The default table uses 4K pages */ + container->pgsizes =3D 0x1000; + vfio_host_win_add(container, info.dma32_window_start, + info.dma32_window_start + + info.dma32_window_size - 1, + 0x1000); + } + } + } + + vfio_kvm_device_add_group(group); + + QLIST_INIT(&container->group_list); + QLIST_INSERT_HEAD(&space->containers, container, next); + + group->container =3D container; + QLIST_INSERT_HEAD(&container->group_list, group, container_next); + + container->listener =3D vfio_memory_listener; + + memory_listener_register(&container->listener, container->space->as); + + if (container->error) { + ret =3D -1; + error_propagate_prepend(errp, container->error, + "memory listener initialization failed: "); + goto listener_release_exit; + } + + container->initialized =3D true; + + return 0; +listener_release_exit: + QLIST_REMOVE(group, container_next); + QLIST_REMOVE(container, next); + vfio_kvm_device_del_group(group); + vfio_listener_release(container); + +enable_discards_exit: + vfio_ram_block_discard_disable(container, false); + +free_container_exit: + g_free(container); + +close_fd_exit: + close(fd); + +put_space_exit: + vfio_put_address_space(space); + + return ret; +} + +static void vfio_disconnect_container(VFIOGroup *group) +{ + VFIOContainer *container =3D group->container; + + QLIST_REMOVE(group, container_next); + group->container =3D NULL; + + /* + * Explicitly release the listener first before unset container, + * since unset may destroy the backend container if it's the last + * group. + */ + if (QLIST_EMPTY(&container->group_list)) { + vfio_listener_release(container); + } + + if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, &container->fd)) { + error_report("vfio: error disconnecting group %d from container", + group->groupid); + } + + if (QLIST_EMPTY(&container->group_list)) { + VFIOAddressSpace *space =3D container->space; + VFIOGuestIOMMU *giommu, *tmp; + VFIOHostDMAWindow *hostwin, *next; + + QLIST_REMOVE(container, next); + + QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, t= mp) { + memory_region_unregister_iommu_notifier( + MEMORY_REGION(giommu->iommu_mr), &giommu->n); + QLIST_REMOVE(giommu, giommu_next); + g_free(giommu); + } + + QLIST_FOREACH_SAFE(hostwin, &container->hostwin_list, hostwin_next, + next) { + QLIST_REMOVE(hostwin, hostwin_next); + g_free(hostwin); + } + + trace_vfio_disconnect_container(container->fd); + close(container->fd); + g_free(container); + + vfio_put_address_space(space); + } +} + +static VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **er= rp) +{ + VFIOGroup *group; + char path[32]; + struct vfio_group_status status =3D { .argsz =3D sizeof(status) }; + + QLIST_FOREACH(group, &vfio_group_list, next) { + if (group->groupid =3D=3D groupid) { + /* Found it. Now is it already in the right context? */ + if (group->container->space->as =3D=3D as) { + return group; + } else { + error_setg(errp, "group %d used in multiple address spaces= ", + group->groupid); + return NULL; + } + } + } + + group =3D g_malloc0(sizeof(*group)); + + snprintf(path, sizeof(path), "/dev/vfio/%d", groupid); + group->fd =3D qemu_open_old(path, O_RDWR); + if (group->fd < 0) { + error_setg_errno(errp, errno, "failed to open %s", path); + goto free_group_exit; + } + + if (ioctl(group->fd, VFIO_GROUP_GET_STATUS, &status)) { + error_setg_errno(errp, errno, "failed to get group %d status", gro= upid); + goto close_fd_exit; + } + + if (!(status.flags & VFIO_GROUP_FLAGS_VIABLE)) { + error_setg(errp, "group %d is not viable", groupid); + error_append_hint(errp, + "Please ensure all devices within the iommu_grou= p " + "are bound to their vfio bus driver.\n"); + goto close_fd_exit; + } + + group->groupid =3D groupid; + QLIST_INIT(&group->device_list); + + if (vfio_connect_container(group, as, errp)) { + error_prepend(errp, "failed to setup container for group %d: ", + groupid); + goto close_fd_exit; + } + + QLIST_INSERT_HEAD(&vfio_group_list, group, next); + + return group; + +close_fd_exit: + close(group->fd); + +free_group_exit: + g_free(group); + + return NULL; +} + +static void vfio_put_group(VFIOGroup *group) +{ + if (!group || !QLIST_EMPTY(&group->device_list)) { + return; + } + + if (!group->ram_block_discard_allowed) { + vfio_ram_block_discard_disable(group->container, false); + } + vfio_kvm_device_del_group(group); + vfio_disconnect_container(group); + QLIST_REMOVE(group, next); + trace_vfio_put_group(group->fd); + close(group->fd); + g_free(group); +} + +static int vfio_get_device(VFIOGroup *group, const char *name, + VFIODevice *vbasedev, Error **errp) +{ + g_autofree struct vfio_device_info *info =3D NULL; + int fd; + + fd =3D ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name); + if (fd < 0) { + error_setg_errno(errp, errno, "error getting device from group %d", + group->groupid); + error_append_hint(errp, + "Verify all devices in group %d are bound to vfio- " + "or pci-stub and not already in use\n", group->group= id); + return fd; + } + + info =3D vfio_get_device_info(fd); + if (!info) { + error_setg_errno(errp, errno, "error getting device info"); + close(fd); + return -1; + } + + /* + * Set discarding of RAM as not broken for this group if the driver kn= ows + * the device operates compatibly with discarding. Setting must be + * consistent per group, but since compatibility is really only possib= le + * with mdev currently, we expect singleton groups. + */ + if (vbasedev->ram_block_discard_allowed !=3D + group->ram_block_discard_allowed) { + if (!QLIST_EMPTY(&group->device_list)) { + error_setg(errp, "Inconsistent setting of support for discardi= ng " + "RAM (e.g., balloon) within group"); + close(fd); + return -1; + } + + if (!group->ram_block_discard_allowed) { + group->ram_block_discard_allowed =3D true; + vfio_ram_block_discard_disable(group->container, false); + } + } + + vbasedev->fd =3D fd; + vbasedev->group =3D group; + QLIST_INSERT_HEAD(&group->device_list, vbasedev, next); + + vbasedev->num_irqs =3D info->num_irqs; + vbasedev->num_regions =3D info->num_regions; + vbasedev->flags =3D info->flags; + + trace_vfio_get_device(name, info->flags, info->num_regions, info->num_= irqs); + + vbasedev->reset_works =3D !!(info->flags & VFIO_DEVICE_FLAGS_RESET); + + return 0; +} + +static void vfio_put_base_device(VFIODevice *vbasedev) +{ + if (!vbasedev->group) { + return; + } + QLIST_REMOVE(vbasedev, next); + vbasedev->group =3D NULL; + trace_vfio_put_base_device(vbasedev->fd); + close(vbasedev->fd); +} + +/* + * Interfaces for IBM EEH (Enhanced Error Handling) + */ +static bool vfio_eeh_container_ok(VFIOContainer *container) +{ + /* + * As of 2016-03-04 (linux-4.5) the host kernel EEH/VFIO + * implementation is broken if there are multiple groups in a + * container. The hardware works in units of Partitionable + * Endpoints (=3D=3D IOMMU groups) and the EEH operations naively + * iterate across all groups in the container, without any logic + * to make sure the groups have their state synchronized. For + * certain operations (ENABLE) that might be ok, until an error + * occurs, but for others (GET_STATE) it's clearly broken. + */ + + /* + * XXX Once fixed kernels exist, test for them here + */ + + if (QLIST_EMPTY(&container->group_list)) { + return false; + } + + if (QLIST_NEXT(QLIST_FIRST(&container->group_list), container_next)) { + return false; + } + + return true; +} + +static int vfio_eeh_container_op(VFIOContainer *container, uint32_t op) +{ + struct vfio_eeh_pe_op pe_op =3D { + .argsz =3D sizeof(pe_op), + .op =3D op, + }; + int ret; + + if (!vfio_eeh_container_ok(container)) { + error_report("vfio/eeh: EEH_PE_OP 0x%x: " + "kernel requires a container with exactly one group",= op); + return -EPERM; + } + + ret =3D ioctl(container->fd, VFIO_EEH_PE_OP, &pe_op); + if (ret < 0) { + error_report("vfio/eeh: EEH_PE_OP 0x%x failed: %m", op); + return -errno; + } + + return ret; +} + +static VFIOContainer *vfio_eeh_as_container(AddressSpace *as) +{ + VFIOAddressSpace *space =3D vfio_get_address_space(as); + VFIOContainer *container =3D NULL; + + if (QLIST_EMPTY(&space->containers)) { + /* No containers to act on */ + goto out; + } + + container =3D QLIST_FIRST(&space->containers); + + if (QLIST_NEXT(container, next)) { + /* + * We don't yet have logic to synchronize EEH state across + * multiple containers + */ + container =3D NULL; + goto out; + } + +out: + vfio_put_address_space(space); + return container; +} + +bool vfio_eeh_as_ok(AddressSpace *as) +{ + VFIOContainer *container =3D vfio_eeh_as_container(as); + + return (container !=3D NULL) && vfio_eeh_container_ok(container); +} + +int vfio_eeh_as_op(AddressSpace *as, uint32_t op) +{ + VFIOContainer *container =3D vfio_eeh_as_container(as); + + if (!container) { + return -ENODEV; + } + return vfio_eeh_container_op(container, op); +} + +static int vfio_device_groupid(VFIODevice *vbasedev, Error **errp) +{ + char *tmp, group_path[PATH_MAX], *group_name; + int ret, groupid; + ssize_t len; + + tmp =3D g_strdup_printf("%s/iommu_group", vbasedev->sysfsdev); + len =3D readlink(tmp, group_path, sizeof(group_path)); + g_free(tmp); + + if (len <=3D 0 || len >=3D sizeof(group_path)) { + ret =3D len < 0 ? -errno : -ENAMETOOLONG; + error_setg_errno(errp, -ret, "no iommu_group found"); + return ret; + } + + group_path[len] =3D 0; + + group_name =3D basename(group_path); + if (sscanf(group_name, "%d", &groupid) !=3D 1) { + error_setg_errno(errp, errno, "failed to read %s", group_path); + return -errno; + } + return groupid; +} + +int vfio_attach_device(char *name, VFIODevice *vbasedev, + AddressSpace *as, Error **errp) +{ + int groupid =3D vfio_device_groupid(vbasedev, errp); + VFIODevice *vbasedev_iter; + VFIOGroup *group; + VFIOContainer *container; + int ret; + + if (groupid < 0) { + return groupid; + } + + trace_vfio_attach_device(vbasedev->name, groupid); + + group =3D vfio_get_group(groupid, as, errp); + if (!group) { + return -ENOENT; + } + + QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { + if (strcmp(vbasedev_iter->name, vbasedev->name) =3D=3D 0) { + error_setg(errp, "device is already attached"); + vfio_put_group(group); + return -EBUSY; + } + } + ret =3D vfio_get_device(group, name, vbasedev, errp); + if (ret) { + vfio_put_group(group); + return ret; + } + + container =3D group->container; + vbasedev->container =3D container; + QLIST_INSERT_HEAD(&container->device_list, vbasedev, container_next); + QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next); + + return ret; +} + +void vfio_detach_device(VFIODevice *vbasedev) +{ + VFIOGroup *group =3D vbasedev->group; + + if (!vbasedev->container) { + return; + } + + QLIST_REMOVE(vbasedev, global_next); + QLIST_REMOVE(vbasedev, container_next); + vbasedev->container =3D NULL; + trace_vfio_detach_device(vbasedev->name, group->groupid); + vfio_put_base_device(vbasedev); + vfio_put_group(group); +} diff --git a/hw/vfio/meson.build b/hw/vfio/meson.build index 3746c9f984..2a6912c940 100644 --- a/hw/vfio/meson.build +++ b/hw/vfio/meson.build @@ -2,6 +2,7 @@ vfio_ss =3D ss.source_set() vfio_ss.add(files( 'helpers.c', 'common.c', + 'container.c', 'spapr.c', 'migration.c', )) --=20 2.41.0