From patchwork Fri Sep 25 13:48:43 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Eric Auger X-Patchwork-Id: 304404 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.6 required=3.0 tests=BAYES_00,DKIM_INVALID, DKIM_SIGNED, HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH, MAILING_LIST_MULTI, SIGNED_OFF_BY, SPF_HELO_NONE, SPF_PASS autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 89DD0C4363D for ; Fri, 25 Sep 2020 13:51:33 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 16F282086A for ; Fri, 25 Sep 2020 13:51:33 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=fail reason="signature verification failed" (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="NWzEfWii" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 16F282086A Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=redhat.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Received: from localhost ([::1]:42372 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1kLo8K-00053g-1B for qemu-devel@archiver.kernel.org; Fri, 25 Sep 2020 09:51:32 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:35230) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1kLo6A-0002cB-S6 for qemu-devel@nongnu.org; Fri, 25 Sep 2020 09:49:18 -0400 Received: from us-smtp-delivery-124.mimecast.com ([216.205.24.124]:39023) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_CBC_SHA1:256) (Exim 4.90_1) (envelope-from ) id 1kLo67-0000kx-J3 for qemu-devel@nongnu.org; Fri, 25 Sep 2020 09:49:18 -0400 Dkim-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1601041751; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=n7WJt6aP9FRh7ANbQTFO8w3xDn6Lth8lc2RIhYZlSKE=; b=NWzEfWiiI6daTCpIPL7YdhqEXFibsdYsYnLCVOvY/KthbnGWcq+MZ2q6b5PjnCY1KqajgX kY5vuhvaf1YAr6FAEe//SwvS32FG7H2OPcI9btqxMNJK059VOJ3O0dGsTAJntn3l5aQWi0 vZfYi9ulg9wowq2usJWY/GmlxvIEt2w= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-443-C6CLpOndPY-6i44u3Gc0uw-1; Fri, 25 Sep 2020 09:49:07 -0400 X-MC-Unique: C6CLpOndPY-6i44u3Gc0uw-1 Received: from smtp.corp.redhat.com (int-mx04.intmail.prod.int.phx2.redhat.com [10.5.11.14]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 5FB10640A1; Fri, 25 Sep 2020 13:49:06 +0000 (UTC) Received: from laptop.redhat.com (ovpn-113-81.ams2.redhat.com [10.36.113.81]) by smtp.corp.redhat.com (Postfix) with ESMTP id 30E975D9DC; Fri, 25 Sep 2020 13:49:01 +0000 (UTC) From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, qemu-arm@nongnu.org, stefanha@redhat.com, fam@euphon.net, philmd@redhat.com, alex.williamson@redhat.com Subject: [RFC 1/3] util/vfio-helpers: Collect IOVA reserved regions Date: Fri, 25 Sep 2020 15:48:43 +0200 Message-Id: <20200925134845.21053-2-eric.auger@redhat.com> In-Reply-To: <20200925134845.21053-1-eric.auger@redhat.com> References: <20200925134845.21053-1-eric.auger@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.14 Authentication-Results: relay.mimecast.com; auth=pass smtp.auth=CUSA124A263 smtp.mailfrom=eric.auger@redhat.com X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Received-SPF: pass client-ip=216.205.24.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-detected-operating-system: by eggs.gnu.org: First seen = 2020/09/25 02:48:20 X-ACL-Warn: Detected OS = Linux 2.2.x-3.x [generic] [fuzzy] X-Spam_score_int: -32 X-Spam_score: -3.3 X-Spam_bar: --- X-Spam_report: (-3.3 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-1.199, 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_H5=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001 autolearn=unavailable autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: lvivier@redhat.com, kwolf@redhat.com, cohuck@redhat.com, mreitz@redhat.com Errors-To: qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Sender: "Qemu-devel" The IOVA allocator currently ignores host reserved regions. As a result some chosen IOVAs may collide with some of them, resulting in VFIO MAP_DMA errors later on. This happens on ARM where the MSI reserved window quickly is encountered: [0x8000000, 0x8100000]. since 5.4 kernel, VFIO returns the usable IOVA regions. So let's enumerate them in the prospect to avoid them, later on. Signed-off-by: Eric Auger --- util/vfio-helpers.c | 75 +++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 73 insertions(+), 2 deletions(-) diff --git a/util/vfio-helpers.c b/util/vfio-helpers.c index 583bdfb36f..8e91beba95 100644 --- a/util/vfio-helpers.c +++ b/util/vfio-helpers.c @@ -40,6 +40,11 @@ typedef struct { uint64_t iova; } IOVAMapping; +struct IOVARange { + uint64_t start; + uint64_t end; +}; + struct QEMUVFIOState { QemuMutex lock; @@ -49,6 +54,8 @@ struct QEMUVFIOState { int device; RAMBlockNotifier ram_notifier; struct vfio_region_info config_region_info, bar_region_info[6]; + struct IOVARange *usable_iova_ranges; + uint8_t nb_iova_ranges; /* These fields are protected by @lock */ /* VFIO's IO virtual address space is managed by splitting into a few @@ -236,6 +243,36 @@ static int qemu_vfio_pci_write_config(QEMUVFIOState *s, void *buf, int size, int return ret == size ? 0 : -errno; } +static void collect_usable_iova_ranges(QEMUVFIOState *s, void *first_cap) +{ + struct vfio_iommu_type1_info_cap_iova_range *cap_iova_range; + struct vfio_info_cap_header *cap = first_cap; + void *offset = first_cap; + int i; + + while (cap->id != VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE) { + if (cap->next) { + return; + } + offset += cap->next; + cap = (struct vfio_info_cap_header *)cap; + } + + cap_iova_range = (struct vfio_iommu_type1_info_cap_iova_range *)cap; + + s->nb_iova_ranges = cap_iova_range->nr_iovas; + if (s->nb_iova_ranges > 1) { + s->usable_iova_ranges = + g_realloc(s->usable_iova_ranges, + s->nb_iova_ranges * sizeof(struct IOVARange)); + } + + for (i = 0; i < s->nb_iova_ranges; i++) { + s->usable_iova_ranges[i].start = cap_iova_range->iova_ranges[i].start; + s->usable_iova_ranges[i].end = cap_iova_range->iova_ranges[i].end; + } +} + static int qemu_vfio_init_pci(QEMUVFIOState *s, const char *device, Error **errp) { @@ -243,10 +280,13 @@ static int qemu_vfio_init_pci(QEMUVFIOState *s, const char *device, int i; uint16_t pci_cmd; struct vfio_group_status group_status = { .argsz = sizeof(group_status) }; - struct vfio_iommu_type1_info iommu_info = { .argsz = sizeof(iommu_info) }; + struct vfio_iommu_type1_info *iommu_info = NULL; + size_t iommu_info_size = sizeof(*iommu_info); struct vfio_device_info device_info = { .argsz = sizeof(device_info) }; char *group_file = NULL; + s->usable_iova_ranges = NULL; + /* Create a new container */ s->container = open("/dev/vfio/vfio", O_RDWR); @@ -310,13 +350,38 @@ static int qemu_vfio_init_pci(QEMUVFIOState *s, const char *device, goto fail; } + iommu_info = g_malloc0(iommu_info_size); + iommu_info->argsz = iommu_info_size; + /* Get additional IOMMU info */ - if (ioctl(s->container, VFIO_IOMMU_GET_INFO, &iommu_info)) { + if (ioctl(s->container, VFIO_IOMMU_GET_INFO, iommu_info)) { error_setg_errno(errp, errno, "Failed to get IOMMU info"); ret = -errno; goto fail; } + /* + * if the kernel does not report usable IOVA regions, choose + * the legacy [QEMU_VFIO_IOVA_MIN, QEMU_VFIO_IOVA_MAX -1] region + */ + s->nb_iova_ranges = 1; + s->usable_iova_ranges = g_new0(struct IOVARange, 1); + s->usable_iova_ranges[0].start = QEMU_VFIO_IOVA_MIN; + s->usable_iova_ranges[0].end = QEMU_VFIO_IOVA_MAX - 1; + + if (iommu_info->argsz > iommu_info_size) { + void *first_cap; + + iommu_info_size = iommu_info->argsz; + iommu_info = g_realloc(iommu_info, iommu_info_size); + if (ioctl(s->container, VFIO_IOMMU_GET_INFO, iommu_info)) { + ret = -errno; + goto fail; + } + first_cap = (void *)iommu_info + iommu_info->cap_offset; + collect_usable_iova_ranges(s, first_cap); + } + s->device = ioctl(s->group, VFIO_GROUP_GET_DEVICE_FD, device); if (s->device < 0) { @@ -365,8 +430,12 @@ static int qemu_vfio_init_pci(QEMUVFIOState *s, const char *device, if (ret) { goto fail; } + g_free(iommu_info); return 0; fail: + g_free(s->usable_iova_ranges); + s->nb_iova_ranges = 0; + g_free(iommu_info); close(s->group); fail_container: close(s->container); @@ -716,6 +785,8 @@ void qemu_vfio_close(QEMUVFIOState *s) qemu_vfio_undo_mapping(s, &s->mappings[i], NULL); } ram_block_notifier_remove(&s->ram_notifier); + g_free(s->usable_iova_ranges); + s->nb_iova_ranges = 0; qemu_vfio_reset(s); close(s->device); close(s->group); From patchwork Fri Sep 25 13:48:44 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Eric Auger X-Patchwork-Id: 272719 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.6 required=3.0 tests=BAYES_00,DKIM_INVALID, DKIM_SIGNED, HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH, MAILING_LIST_MULTI, SIGNED_OFF_BY, SPF_HELO_NONE, SPF_PASS autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 9EA2EC4363D for ; Fri, 25 Sep 2020 13:59:56 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id A487B2086A for ; Fri, 25 Sep 2020 13:59:55 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=fail reason="signature verification failed" (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="MfHEKkxN" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org A487B2086A Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=redhat.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Received: from localhost ([::1]:42478 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1kLoGQ-00007W-I6 for qemu-devel@archiver.kernel.org; Fri, 25 Sep 2020 09:59:54 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:35236) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1kLo6B-0002ca-2P for qemu-devel@nongnu.org; Fri, 25 Sep 2020 09:49:19 -0400 Received: from us-smtp-delivery-124.mimecast.com ([63.128.21.124]:37477) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_CBC_SHA1:256) (Exim 4.90_1) (envelope-from ) id 1kLo67-0000l7-K3 for qemu-devel@nongnu.org; Fri, 25 Sep 2020 09:49:18 -0400 Dkim-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1601041751; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=MhsjaAvcc2A8rxRwS3aD1ncZ7PrT1QP4PmosGTDO3t8=; b=MfHEKkxNkuLrZve9tO+3ivk5KhVeSqle9Fe7Wvn+AF4Edy5MgJLG+jAkm5Ba7W3p8r1LIc dunyc3GlgvrXOIeL3XQXsuobTYccYWJuBUT2et4tz4mSJGeGNue81ZfKE3z3braO2qc+3y z5UvHkFRv56gU1QPP+Dr9kIA0jRjUvI= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-244-eiyasU3IM82UTT2iBI4_eA-1; Fri, 25 Sep 2020 09:49:10 -0400 X-MC-Unique: eiyasU3IM82UTT2iBI4_eA-1 Received: from smtp.corp.redhat.com (int-mx04.intmail.prod.int.phx2.redhat.com [10.5.11.14]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 2417881F00F; Fri, 25 Sep 2020 13:49:09 +0000 (UTC) Received: from laptop.redhat.com (ovpn-113-81.ams2.redhat.com [10.36.113.81]) by smtp.corp.redhat.com (Postfix) with ESMTP id AEF625D9DC; Fri, 25 Sep 2020 13:49:06 +0000 (UTC) From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, qemu-arm@nongnu.org, stefanha@redhat.com, fam@euphon.net, philmd@redhat.com, alex.williamson@redhat.com Subject: [RFC 2/3] util/vfio-helpers: Dynamically compute the min/max IOVA Date: Fri, 25 Sep 2020 15:48:44 +0200 Message-Id: <20200925134845.21053-3-eric.auger@redhat.com> In-Reply-To: <20200925134845.21053-1-eric.auger@redhat.com> References: <20200925134845.21053-1-eric.auger@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.14 Authentication-Results: relay.mimecast.com; auth=pass smtp.auth=CUSA124A263 smtp.mailfrom=eric.auger@redhat.com X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Received-SPF: pass client-ip=63.128.21.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-detected-operating-system: by eggs.gnu.org: First seen = 2020/09/25 01:07:33 X-ACL-Warn: Detected OS = Linux 2.2.x-3.x [generic] [fuzzy] X-Spam_score_int: -32 X-Spam_score: -3.3 X-Spam_bar: --- X-Spam_report: (-3.3 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-1.199, 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_H5=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001 autolearn=unavailable autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: lvivier@redhat.com, kwolf@redhat.com, cohuck@redhat.com, mreitz@redhat.com Errors-To: qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Sender: "Qemu-devel" Currently the min/max IOVA are hardcoded to [0x10000, 1 << 39]. Now we dynamically fetch the info from VFIO, if the kernel supports it, let's use the dynamically retrieved value. Signed-off-by: Eric Auger --- util/vfio-helpers.c | 34 ++++++++++++++++++++-------------- 1 file changed, 20 insertions(+), 14 deletions(-) diff --git a/util/vfio-helpers.c b/util/vfio-helpers.c index 8e91beba95..567bcf1ded 100644 --- a/util/vfio-helpers.c +++ b/util/vfio-helpers.c @@ -26,11 +26,11 @@ #define QEMU_VFIO_DEBUG 0 +/* + * Min/Max IOVA addresses, only used if VFIO does not report + * the usable IOVA ranges + */ #define QEMU_VFIO_IOVA_MIN 0x10000ULL -/* XXX: Once VFIO exposes the iova bit width in the IOMMU capability interface, - * we can use a runtime limit; alternatively it's also possible to do platform - * specific detection by reading sysfs entries. Until then, 39 is a safe bet. - **/ #define QEMU_VFIO_IOVA_MAX (1ULL << 39) typedef struct { @@ -56,6 +56,8 @@ struct QEMUVFIOState { struct vfio_region_info config_region_info, bar_region_info[6]; struct IOVARange *usable_iova_ranges; uint8_t nb_iova_ranges; + uint64_t max_iova; + uint64_t min_iova; /* These fields are protected by @lock */ /* VFIO's IO virtual address space is managed by splitting into a few @@ -63,7 +65,7 @@ struct QEMUVFIOState { * * --------------- <= 0 * |xxxxxxxxxxxxx| - * |-------------| <= QEMU_VFIO_IOVA_MIN + * |-------------| <= min_iova * | | * | Fixed | * | | @@ -75,20 +77,20 @@ struct QEMUVFIOState { * | | * | Temp | * | | - * |-------------| <= QEMU_VFIO_IOVA_MAX + * |-------------| <= max_iova * |xxxxxxxxxxxxx| * |xxxxxxxxxxxxx| * --------------- * - * - Addresses lower than QEMU_VFIO_IOVA_MIN are reserved as invalid; + * - Addresses lower than min_iova are reserved as invalid; * * - Fixed mappings of HVAs are assigned "low" IOVAs in the range of - * [QEMU_VFIO_IOVA_MIN, low_water_mark). Once allocated they will not be + * [min_iova, low_water_mark). Once allocated they will not be * reclaimed - low_water_mark never shrinks; * * - IOVAs in range [low_water_mark, high_water_mark) are free; * - * - IOVAs in range [high_water_mark, QEMU_VFIO_IOVA_MAX) are volatile + * - IOVAs in range [high_water_mark, max_iova) are volatile * mappings. At each qemu_vfio_dma_reset_temporary() call, the whole area * is recycled. The caller should make sure I/O's depending on these * mappings are completed before calling. @@ -271,6 +273,8 @@ static void collect_usable_iova_ranges(QEMUVFIOState *s, void *first_cap) s->usable_iova_ranges[i].start = cap_iova_range->iova_ranges[i].start; s->usable_iova_ranges[i].end = cap_iova_range->iova_ranges[i].end; } + s->min_iova = s->usable_iova_ranges[0].start; + s->max_iova = s->usable_iova_ranges[i - 1].end + 1; } static int qemu_vfio_init_pci(QEMUVFIOState *s, const char *device, @@ -362,12 +366,14 @@ static int qemu_vfio_init_pci(QEMUVFIOState *s, const char *device, /* * if the kernel does not report usable IOVA regions, choose - * the legacy [QEMU_VFIO_IOVA_MIN, QEMU_VFIO_IOVA_MAX -1] region + * the legacy [QEMU_VFIO_IOVA_MIN, QEMU_VFIO_IOVA_MAX - 1] region */ s->nb_iova_ranges = 1; s->usable_iova_ranges = g_new0(struct IOVARange, 1); s->usable_iova_ranges[0].start = QEMU_VFIO_IOVA_MIN; s->usable_iova_ranges[0].end = QEMU_VFIO_IOVA_MAX - 1; + s->min_iova = QEMU_VFIO_IOVA_MIN; + s->max_iova = QEMU_VFIO_IOVA_MAX; if (iommu_info->argsz > iommu_info_size) { void *first_cap; @@ -484,8 +490,8 @@ static void qemu_vfio_open_common(QEMUVFIOState *s) s->ram_notifier.ram_block_added = qemu_vfio_ram_block_added; s->ram_notifier.ram_block_removed = qemu_vfio_ram_block_removed; ram_block_notifier_add(&s->ram_notifier); - s->low_water_mark = QEMU_VFIO_IOVA_MIN; - s->high_water_mark = QEMU_VFIO_IOVA_MAX; + s->low_water_mark = s->min_iova; + s->high_water_mark = s->max_iova; qemu_ram_foreach_block(qemu_vfio_init_ramblock, s); } @@ -734,7 +740,7 @@ int qemu_vfio_dma_reset_temporary(QEMUVFIOState *s) .argsz = sizeof(unmap), .flags = 0, .iova = s->high_water_mark, - .size = QEMU_VFIO_IOVA_MAX - s->high_water_mark, + .size = s->max_iova - s->high_water_mark, }; trace_qemu_vfio_dma_reset_temporary(s); QEMU_LOCK_GUARD(&s->lock); @@ -742,7 +748,7 @@ int qemu_vfio_dma_reset_temporary(QEMUVFIOState *s) error_report("VFIO_UNMAP_DMA failed: %s", strerror(errno)); return -errno; } - s->high_water_mark = QEMU_VFIO_IOVA_MAX; + s->high_water_mark = s->max_iova; return 0; } From patchwork Fri Sep 25 13:48:45 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Eric Auger X-Patchwork-Id: 304403 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.6 required=3.0 tests=BAYES_00,DKIM_INVALID, DKIM_SIGNED, HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH, MAILING_LIST_MULTI, SIGNED_OFF_BY, SPF_HELO_NONE, SPF_PASS autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 3D4EDC4363D for ; Fri, 25 Sep 2020 13:55:46 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id BBF14206C9 for ; Fri, 25 Sep 2020 13:55:45 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=fail reason="signature verification failed" (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="ir8IhASS" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org BBF14206C9 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=redhat.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Received: from localhost ([::1]:54572 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1kLoCO-0001h2-EF for qemu-devel@archiver.kernel.org; Fri, 25 Sep 2020 09:55:44 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:35366) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1kLo6w-0003tm-1n for qemu-devel@nongnu.org; Fri, 25 Sep 2020 09:50:07 -0400 Received: from us-smtp-delivery-124.mimecast.com ([216.205.24.124]:43617) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_CBC_SHA1:256) (Exim 4.90_1) (envelope-from ) id 1kLo6s-0000ps-0u for qemu-devel@nongnu.org; Fri, 25 Sep 2020 09:50:04 -0400 Dkim-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1601041798; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=fLvjjbnseEvWZyZlxkrX+W1Hx+rNQ9Jg98KLgwjIUh0=; b=ir8IhASSfIG71X7ZkLp8wJzrmpD7klhPzoOvKNpE5GerdxbH8gp/RxQbD2lYJjGLE+wYuG Z65D3ifu8JFOnQe1MXCBo0Jvnr+U2ht6VdY3BUIv8C6oTEoIaDD2WUfiXq6o392tOuGY8l izfQpDhJqKVEiEd1aVFi+HBI1WnDh40= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-557-_u9TE8skM56EMqOW5PgM4Q-1; Fri, 25 Sep 2020 09:49:57 -0400 X-MC-Unique: _u9TE8skM56EMqOW5PgM4Q-1 Received: from smtp.corp.redhat.com (int-mx04.intmail.prod.int.phx2.redhat.com [10.5.11.14]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id C183F1084C9E; Fri, 25 Sep 2020 13:49:55 +0000 (UTC) Received: from laptop.redhat.com (ovpn-113-81.ams2.redhat.com [10.36.113.81]) by smtp.corp.redhat.com (Postfix) with ESMTP id 742DE5D9DC; Fri, 25 Sep 2020 13:49:09 +0000 (UTC) From: Eric Auger To: eric.auger.pro@gmail.com, eric.auger@redhat.com, qemu-devel@nongnu.org, qemu-arm@nongnu.org, stefanha@redhat.com, fam@euphon.net, philmd@redhat.com, alex.williamson@redhat.com Subject: [RFC 3/3] util/vfio-helpers: Rework the IOVA allocator to avoid IOVA reserved regions Date: Fri, 25 Sep 2020 15:48:45 +0200 Message-Id: <20200925134845.21053-4-eric.auger@redhat.com> In-Reply-To: <20200925134845.21053-1-eric.auger@redhat.com> References: <20200925134845.21053-1-eric.auger@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.14 Authentication-Results: relay.mimecast.com; auth=pass smtp.auth=CUSA124A263 smtp.mailfrom=eric.auger@redhat.com X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Received-SPF: pass client-ip=216.205.24.124; envelope-from=eric.auger@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-detected-operating-system: by eggs.gnu.org: First seen = 2020/09/25 02:48:20 X-ACL-Warn: Detected OS = Linux 2.2.x-3.x [generic] [fuzzy] X-Spam_score_int: -32 X-Spam_score: -3.3 X-Spam_bar: --- X-Spam_report: (-3.3 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-1.199, 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_H5=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: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: lvivier@redhat.com, kwolf@redhat.com, cohuck@redhat.com, mreitz@redhat.com Errors-To: qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Sender: "Qemu-devel" Signed-off-by: Eric Auger --- util/vfio-helpers.c | 55 +++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 51 insertions(+), 4 deletions(-) diff --git a/util/vfio-helpers.c b/util/vfio-helpers.c index 567bcf1ded..c98d0d882e 100644 --- a/util/vfio-helpers.c +++ b/util/vfio-helpers.c @@ -676,6 +676,48 @@ static bool qemu_vfio_verify_mappings(QEMUVFIOState *s) return true; } +static int +qemu_vfio_find_fixed_iova(QEMUVFIOState *s, size_t size, uint64_t *iova) +{ + int i; + + for (i = 0; i < s->nb_iova_ranges; i++) { + if (s->usable_iova_ranges[i].end < s->low_water_mark) { + continue; + } + s->low_water_mark = + MAX(s->low_water_mark, s->usable_iova_ranges[i].start); + + if (s->usable_iova_ranges[i].end - s->low_water_mark + 1 >= size) { + *iova = s->low_water_mark; + s->low_water_mark += size; + return 0; + } + } + return -ENOMEM; +} + +static int +qemu_vfio_find_temp_iova(QEMUVFIOState *s, size_t size, uint64_t *iova) +{ + int i; + + for (i = s->nb_iova_ranges - 1; i >= 0; i--) { + if (s->usable_iova_ranges[i].start > s->high_water_mark) { + continue; + } + s->high_water_mark = + MIN(s->high_water_mark, s->usable_iova_ranges[i].end + 1); + + if (s->high_water_mark - s->usable_iova_ranges[i].start + 1 >= size) { + *iova = s->high_water_mark - size; + s->high_water_mark = *iova; + return 0; + } + } + return -ENOMEM; +} + /* Map [host, host + size) area into a contiguous IOVA address space, and store * the result in @iova if not NULL. The caller need to make sure the area is * aligned to page size, and mustn't overlap with existing mapping areas (split @@ -702,7 +744,11 @@ int qemu_vfio_dma_map(QEMUVFIOState *s, void *host, size_t size, goto out; } if (!temporary) { - iova0 = s->low_water_mark; + if (qemu_vfio_find_fixed_iova(s, size, &iova0)) { + ret = -ENOMEM; + goto out; + } + mapping = qemu_vfio_add_mapping(s, host, size, index + 1, iova0); if (!mapping) { ret = -ENOMEM; @@ -714,15 +760,16 @@ int qemu_vfio_dma_map(QEMUVFIOState *s, void *host, size_t size, qemu_vfio_undo_mapping(s, mapping, NULL); goto out; } - s->low_water_mark += size; qemu_vfio_dump_mappings(s); } else { - iova0 = s->high_water_mark - size; + if (qemu_vfio_find_temp_iova(s, size, &iova0)) { + ret = -ENOMEM; + goto out; + } ret = qemu_vfio_do_mapping(s, host, size, iova0); if (ret) { goto out; } - s->high_water_mark -= size; } } if (iova) {