From patchwork Wed Jan 15 03:53:03 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yan Zhao X-Patchwork-Id: 11333333 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 44B0D138D for ; Wed, 15 Jan 2020 04:03:14 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 225BB24671 for ; Wed, 15 Jan 2020 04:03:14 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729081AbgAOEDF (ORCPT ); Tue, 14 Jan 2020 23:03:05 -0500 Received: from mga04.intel.com ([192.55.52.120]:12750 "EHLO mga04.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1728884AbgAOEDE (ORCPT ); Tue, 14 Jan 2020 23:03:04 -0500 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga008.jf.intel.com ([10.7.209.65]) by fmsmga104.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 14 Jan 2020 20:03:03 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.70,321,1574150400"; d="scan'208";a="217983181" Received: from unknown (HELO joy-OptiPlex-7040.sh.intel.com) ([10.239.13.9]) by orsmga008.jf.intel.com with ESMTP; 14 Jan 2020 20:03:01 -0800 From: Yan Zhao To: alex.williamson@redhat.com Cc: zhenyuw@linux.intel.com, intel-gvt-dev@lists.freedesktop.org, kvm@vger.kernel.org, linux-kernel@vger.kernel.org, pbonzini@redhat.com, kevin.tian@intel.com, peterx@redhat.com, Yan Zhao Subject: [PATCH v2 1/2] vfio: introduce vfio_dma_rw to read/write a range of IOVAs Date: Tue, 14 Jan 2020 22:53:03 -0500 Message-Id: <20200115035303.12362-1-yan.y.zhao@intel.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20200115034132.2753-1-yan.y.zhao@intel.com> References: <20200115034132.2753-1-yan.y.zhao@intel.com> Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org vfio_dma_rw will read/write a range of user space memory pointed to by IOVA into/from a kernel buffer without pinning the user space memory. TODO: mark the IOVAs to user space memory dirty if they are written in vfio_dma_rw(). Cc: Kevin Tian Signed-off-by: Yan Zhao --- drivers/vfio/vfio.c | 45 +++++++++++++++++++ drivers/vfio/vfio_iommu_type1.c | 76 +++++++++++++++++++++++++++++++++ include/linux/vfio.h | 5 +++ 3 files changed, 126 insertions(+) diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index c8482624ca34..8bd52bc841cf 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -1961,6 +1961,51 @@ int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, int npage) } EXPORT_SYMBOL(vfio_unpin_pages); +/* + * Read/Write a range of IOVAs pointing to user space memory into/from a kernel + * buffer without pinning the user space memory + * @dev [in] : device + * @iova [in] : base IOVA of a user space buffer + * @data [in] : pointer to kernel buffer + * @len [in] : kernel buffer length + * @write : indicate read or write + * Return error code on failure or 0 on success. + */ +int vfio_dma_rw(struct device *dev, dma_addr_t iova, void *data, + size_t len, bool write) +{ + struct vfio_container *container; + struct vfio_group *group; + struct vfio_iommu_driver *driver; + int ret = 0; + + if (!dev || !data || len <= 0) + return -EINVAL; + + group = vfio_group_get_from_dev(dev); + if (!group) + return -ENODEV; + + ret = vfio_group_add_container_user(group); + if (ret) + goto out; + + container = group->container; + driver = container->iommu_driver; + + if (likely(driver && driver->ops->dma_rw)) + ret = driver->ops->dma_rw(container->iommu_data, + iova, data, len, write); + else + ret = -ENOTTY; + + vfio_group_try_dissolve_container(group); +out: + vfio_group_put(group); + return ret; +} +EXPORT_SYMBOL(vfio_dma_rw); + static int vfio_register_iommu_notifier(struct vfio_group *group, unsigned long *events, struct notifier_block *nb) diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 2ada8e6cdb88..a2d850b97ae6 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -2326,6 +2327,80 @@ static int vfio_iommu_type1_unregister_notifier(void *iommu_data, return blocking_notifier_chain_unregister(&iommu->notifier, nb); } +static size_t vfio_iommu_type1_rw_dma_nopin(struct vfio_iommu *iommu, + dma_addr_t iova, void *data, + size_t count, bool write) +{ + struct mm_struct *mm; + unsigned long vaddr; + struct vfio_dma *dma; + bool kthread = current->mm == NULL; + size_t done = 0; + size_t offset; + + dma = vfio_find_dma(iommu, iova, 1); + if (!dma) + return 0; + + if (write && !(dma->prot & IOMMU_WRITE)) + return 0; + + mm = get_task_mm(dma->task); + + if (!mm) + return 0; + + if (kthread) + use_mm(mm); + else if (current->mm != mm) + goto out; + + offset = iova - dma->iova; + + if (count > dma->size - offset) + count = dma->size - offset; + + vaddr = dma->vaddr + offset; + + if (write) + done = __copy_to_user((void __user *)vaddr, data, count) ? + 0 : count; + else + done = __copy_from_user(data, (void __user *)vaddr, count) ? + 0 : count; + + if (kthread) + unuse_mm(mm); +out: + mmput(mm); + return done; +} + +static int vfio_iommu_type1_dma_rw(void *iommu_data, dma_addr_t iova, + void *data, size_t count, bool write) +{ + struct vfio_iommu *iommu = iommu_data; + int ret = 0; + size_t done = 0; + + mutex_lock(&iommu->lock); + while (count > 0) { + done = vfio_iommu_type1_rw_dma_nopin(iommu, iova, data, + count, write); + if (!done) { + ret = -EFAULT; + break; + } + + count -= done; + data += done; + iova += done; + } + + mutex_unlock(&iommu->lock); + return ret; +} + static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = { .name = "vfio-iommu-type1", .owner = THIS_MODULE, @@ -2338,6 +2413,7 @@ static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = { .unpin_pages = vfio_iommu_type1_unpin_pages, .register_notifier = vfio_iommu_type1_register_notifier, .unregister_notifier = vfio_iommu_type1_unregister_notifier, + .dma_rw = vfio_iommu_type1_dma_rw, }; static int __init vfio_iommu_type1_init(void) diff --git a/include/linux/vfio.h b/include/linux/vfio.h index e42a711a2800..962f76a2d668 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -82,6 +82,8 @@ struct vfio_iommu_driver_ops { struct notifier_block *nb); int (*unregister_notifier)(void *iommu_data, struct notifier_block *nb); + int (*dma_rw)(void *iommu_data, dma_addr_t iova, + void *data, size_t count, bool write); }; extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops); @@ -107,6 +109,9 @@ extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, int npage); +extern int vfio_dma_rw(struct device *dev, dma_addr_t iova, void *data, + size_t len, bool write); + /* each type has independent events */ enum vfio_notify_type { VFIO_IOMMU_NOTIFY = 0, From patchwork Wed Jan 15 03:54:55 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yan Zhao X-Patchwork-Id: 11333335 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 9291A138D for ; Wed, 15 Jan 2020 04:04:16 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 7ABE42467D for ; Wed, 15 Jan 2020 04:04:16 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729052AbgAOEEM (ORCPT ); Tue, 14 Jan 2020 23:04:12 -0500 Received: from mga06.intel.com ([134.134.136.31]:26364 "EHLO mga06.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1728879AbgAOEEM (ORCPT ); Tue, 14 Jan 2020 23:04:12 -0500 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga008.jf.intel.com ([10.7.209.65]) by orsmga104.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 14 Jan 2020 20:04:11 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.70,321,1574150400"; d="scan'208";a="217983429" Received: from unknown (HELO joy-OptiPlex-7040.sh.intel.com) ([10.239.13.9]) by orsmga008.jf.intel.com with ESMTP; 14 Jan 2020 20:04:09 -0800 From: Yan Zhao To: zhenyuw@linux.intel.com Cc: alex.williamson@redhat.com, intel-gvt-dev@lists.freedesktop.org, kvm@vger.kernel.org, linux-kernel@vger.kernel.org, pbonzini@redhat.com, kevin.tian@intel.com, peterx@redhat.com, Yan Zhao Subject: [PATCH v2 2/2] drm/i915/gvt: subsitute kvm_read/write_guest with vfio_dma_rw Date: Tue, 14 Jan 2020 22:54:55 -0500 Message-Id: <20200115035455.12417-1-yan.y.zhao@intel.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20200115034132.2753-1-yan.y.zhao@intel.com> References: <20200115034132.2753-1-yan.y.zhao@intel.com> Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org As a device model, it is better to read/write guest memory using vfio interface, so that vfio is able to maintain dirty info of device IOVAs. Compared to kvm interfaces kvm_read/write_guest(), vfio_dma_rw() has ~600 cycles more overhead on average. ------------------------------------- | interface | avg cpu cycles | |-----------------------------------| | kvm_write_guest | 1554 | | ----------------------------------| | kvm_read_guest | 707 | |-----------------------------------| | vfio_dma_rw(w) | 2274 | |-----------------------------------| | vfio_dma_rw(r) | 1378 | ------------------------------------- Comparison of benchmarks scores are as blow: ------------------------------------------------------ | avg score | kvm_read/write_guest | vfio_dma_rw | |----------------------------------------------------| | Glmark2 | 1284 | 1296 | |----------------------------------------------------| | Lightsmark | 61.24 | 61.27 | |----------------------------------------------------| | OpenArena | 140.9 | 137.4 | |----------------------------------------------------| | Heaven | 671 | 670 | ------------------------------------------------------ No obvious performance downgrade found. Cc: Kevin Tian Signed-off-by: Yan Zhao --- drivers/gpu/drm/i915/gvt/kvmgt.c | 26 +++++++------------------- 1 file changed, 7 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index bd79a9718cc7..17edc9a7ff05 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -1966,31 +1966,19 @@ static int kvmgt_rw_gpa(unsigned long handle, unsigned long gpa, void *buf, unsigned long len, bool write) { struct kvmgt_guest_info *info; - struct kvm *kvm; - int idx, ret; - bool kthread = current->mm == NULL; + int ret; + struct intel_vgpu *vgpu; + struct device *dev; if (!handle_valid(handle)) return -ESRCH; info = (struct kvmgt_guest_info *)handle; - kvm = info->kvm; - - if (kthread) { - if (!mmget_not_zero(kvm->mm)) - return -EFAULT; - use_mm(kvm->mm); - } - - idx = srcu_read_lock(&kvm->srcu); - ret = write ? kvm_write_guest(kvm, gpa, buf, len) : - kvm_read_guest(kvm, gpa, buf, len); - srcu_read_unlock(&kvm->srcu, idx); + vgpu = info->vgpu; + dev = mdev_dev(vgpu->vdev.mdev); - if (kthread) { - unuse_mm(kvm->mm); - mmput(kvm->mm); - } + ret = write ? vfio_dma_rw(dev, gpa, buf, len, true) : + vfio_dma_rw(dev, gpa, buf, len, false); return ret; }