Commit 8d46c0cc authored by Yan Zhao's avatar Yan Zhao Committed by Alex Williamson
Browse files

vfio: introduce vfio_dma_rw to read/write a range of IOVAs



vfio_dma_rw will read/write a range of user space memory pointed to by
IOVA into/from a kernel buffer without enforcing 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: default avatarYan Zhao <yan.y.zhao@intel.com>
Signed-off-by: default avatarAlex Williamson <alex.williamson@redhat.com>
parent c0560f51
Loading
Loading
Loading
Loading
+49 −0
Original line number Diff line number Diff line
@@ -1999,6 +1999,55 @@ err_unpin_pages:
}
EXPORT_SYMBOL(vfio_unpin_pages);


/*
 * This interface allows the CPUs to perform some sort of virtual DMA on
 * behalf of the device.
 *
 * CPUs read/write from/into a range of IOVAs pointing to user space memory
 * into/from a kernel buffer.
 *
 * As the read/write of user space memory is conducted via the CPUs and is
 * not a real device DMA, it is not necessary to pin the user space memory.
 *
 * The caller needs to call vfio_group_get_external_user() or
 * vfio_group_get_external_user_from_dev() prior to calling this interface,
 * so as to prevent the VFIO group from disposal in the middle of the call.
 * But it can keep the reference to the VFIO group for several calls into
 * this interface.
 * After finishing using of the VFIO group, the caller needs to release the
 * VFIO group by calling vfio_group_put_external_user().
 *
 * @group [in]		: VFIO group
 * @user_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 vfio_group *group, dma_addr_t user_iova,
		void *data, size_t len, bool write)
{
	struct vfio_container *container;
	struct vfio_iommu_driver *driver;
	int ret = 0;

	if (!group || !data || len <= 0)
		return -EINVAL;

	container = group->container;
	driver = container->iommu_driver;

	if (likely(driver && driver->ops->dma_rw))
		ret = driver->ops->dma_rw(container->iommu_data,
					  user_iova, data, len, write);
	else
		ret = -ENOTTY;

	return ret;
}
EXPORT_SYMBOL(vfio_dma_rw);

static int vfio_register_iommu_notifier(struct vfio_group *group,
					unsigned long *events,
					struct notifier_block *nb)
+76 −0
Original line number Diff line number Diff line
@@ -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>
@@ -2305,6 +2306,80 @@ static int vfio_iommu_type1_unregister_notifier(void *iommu_data,
	return blocking_notifier_chain_unregister(&iommu->notifier, nb);
}

static int vfio_iommu_type1_dma_rw_chunk(struct vfio_iommu *iommu,
					 dma_addr_t user_iova, void *data,
					 size_t count, bool write,
					 size_t *copied)
{
	struct mm_struct *mm;
	unsigned long vaddr;
	struct vfio_dma *dma;
	bool kthread = current->mm == NULL;
	size_t offset;

	*copied = 0;

	dma = vfio_find_dma(iommu, user_iova, 1);
	if (!dma)
		return -EINVAL;

	if ((write && !(dma->prot & IOMMU_WRITE)) ||
			!(dma->prot & IOMMU_READ))
		return -EPERM;

	mm = get_task_mm(dma->task);

	if (!mm)
		return -EPERM;

	if (kthread)
		use_mm(mm);
	else if (current->mm != mm)
		goto out;

	offset = user_iova - dma->iova;

	if (count > dma->size - offset)
		count = dma->size - offset;

	vaddr = dma->vaddr + offset;

	if (write)
		*copied = __copy_to_user((void __user *)vaddr, data,
					 count) ? 0 : count;
	else
		*copied = __copy_from_user(data, (void __user *)vaddr,
					   count) ? 0 : count;
	if (kthread)
		unuse_mm(mm);
out:
	mmput(mm);
	return *copied ? 0 : -EFAULT;
}

static int vfio_iommu_type1_dma_rw(void *iommu_data, dma_addr_t user_iova,
				   void *data, size_t count, bool write)
{
	struct vfio_iommu *iommu = iommu_data;
	int ret = 0;
	size_t done;

	mutex_lock(&iommu->lock);
	while (count > 0) {
		ret = vfio_iommu_type1_dma_rw_chunk(iommu, user_iova, data,
						    count, write, &done);
		if (ret)
			break;

		count -= done;
		data += done;
		user_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,
@@ -2317,6 +2392,7 @@ 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)
+5 −0
Original line number Diff line number Diff line
@@ -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 user_iova,
				  void *data, size_t count, bool write);
};

extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops);
@@ -109,6 +111,9 @@ 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 vfio_group *group, dma_addr_t user_iova,
		       void *data, size_t len, bool write);

/* each type has independent events */
enum vfio_notify_type {
	VFIO_IOMMU_NOTIFY = 0,