KVM Archive on lore.kernel.org
 help / color / Atom feed
From: Yan Zhao <yan.y.zhao@intel.com>
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 <yan.y.zhao@intel.com>
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> (raw)
In-Reply-To: <20200115034132.2753-1-yan.y.zhao@intel.com>

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 <kevin.tian@intel.com>
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
---
 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 <linux/iommu.h>
 #include <linux/module.h>
 #include <linux/mm.h>
+#include <linux/mmu_context.h>
 #include <linux/rbtree.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
@@ -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,
-- 
2.17.1


  reply index

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-01-15  3:41 [PATCH v2 0/2] use vfio_dma_rw to read/write IOVAs from CPU side Yan Zhao
2020-01-15  3:53 ` Yan Zhao [this message]
2020-01-15 20:06   ` [PATCH v2 1/2] vfio: introduce vfio_dma_rw to read/write a range of IOVAs Alex Williamson
2020-01-16  2:30     ` Mika Penttilä
2020-01-16  2:59       ` Alex Williamson
2020-01-16  3:15         ` Mika Penttilä
2020-01-16  3:58           ` Alex Williamson
2020-01-16  5:32     ` Yan Zhao
2020-01-15  3:54 ` [PATCH v2 2/2] drm/i915/gvt: subsitute kvm_read/write_guest with vfio_dma_rw Yan Zhao
2020-01-15 20:06   ` Alex Williamson
2020-01-16  5:49     ` Yan Zhao
2020-01-16 15:37       ` Alex Williamson
2020-01-19 10:06         ` Yan Zhao
2020-01-20 20:01           ` Alex Williamson
2020-01-21  8:12             ` Yan Zhao
2020-01-21 16:51               ` Alex Williamson
2020-01-21 22:10                 ` Yan Zhao
2020-01-22  3:07                   ` Yan Zhao
2020-01-23 10:02                     ` Yan Zhao

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200115035303.12362-1-yan.y.zhao@intel.com \
    --to=yan.y.zhao@intel.com \
    --cc=alex.williamson@redhat.com \
    --cc=intel-gvt-dev@lists.freedesktop.org \
    --cc=kevin.tian@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=zhenyuw@linux.intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

KVM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/kvm/0 kvm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 kvm kvm/ https://lore.kernel.org/kvm \
		kvm@vger.kernel.org
	public-inbox-index kvm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.kvm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git