diff mbox

[v14,11/22] vfio iommu: Add blocking notifier to notify DMA_UNMAP

Message ID 1479329194-10247-12-git-send-email-kwankhede@nvidia.com (mailing list archive)
State New, archived
Headers show

Commit Message

Kirti Wankhede Nov. 16, 2016, 8:46 p.m. UTC
Added blocking notifier to IOMMU TYPE1 driver to notify vendor drivers
about DMA_UNMAP.
Exported two APIs vfio_register_notifier() and vfio_unregister_notifier().
Notifier should be registered, if external user wants to use
vfio_pin_pages()/vfio_unpin_pages() APIs to pin/unpin pages.
Vendor driver should use VFIO_IOMMU_NOTIFY_DMA_UNMAP action to invalidate
mappings.

Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
Signed-off-by: Neo Jia <cjia@nvidia.com>
Change-Id: I5910d0024d6be87f3e8d3e0ca0eaeaaa0b17f271
---
 drivers/vfio/vfio.c             | 73 ++++++++++++++++++++++++++++++++++++++
 drivers/vfio/vfio_iommu_type1.c | 77 +++++++++++++++++++++++++++++++++--------
 include/linux/vfio.h            | 12 +++++++
 3 files changed, 147 insertions(+), 15 deletions(-)

Comments

Alex Williamson Nov. 17, 2016, 12:02 a.m. UTC | #1
On Thu, 17 Nov 2016 02:16:23 +0530
Kirti Wankhede <kwankhede@nvidia.com> wrote:
> @@ -1321,12 +1350,11 @@ static void vfio_iommu_unmap_unpin_reaccount(struct vfio_iommu *iommu)
>  
>  static void vfio_sanity_check_pfn_list(struct vfio_iommu *iommu)
>  {
> -	struct rb_node *n, *p;
> +	struct rb_node *n;
>  
>  	n = rb_first(&iommu->dma_list);
>  	for (; n; n = rb_next(n)) {
>  		struct vfio_dma *dma;
> -		int unlocked = 0;
>  
>  		dma = rb_entry(n, struct vfio_dma, node);
>  

This chunk really should have been part of 10/22 as well.
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Jike Song Nov. 17, 2016, 2:53 a.m. UTC | #2
On 11/17/2016 04:46 AM, Kirti Wankhede wrote:
> Added blocking notifier to IOMMU TYPE1 driver to notify vendor drivers
> about DMA_UNMAP.
> Exported two APIs vfio_register_notifier() and vfio_unregister_notifier().
> Notifier should be registered, if external user wants to use
> vfio_pin_pages()/vfio_unpin_pages() APIs to pin/unpin pages.
> Vendor driver should use VFIO_IOMMU_NOTIFY_DMA_UNMAP action to invalidate
> mappings.
> 
> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
> Signed-off-by: Neo Jia <cjia@nvidia.com>
> Change-Id: I5910d0024d6be87f3e8d3e0ca0eaeaaa0b17f271
> ---
>  drivers/vfio/vfio.c             | 73 ++++++++++++++++++++++++++++++++++++++
>  drivers/vfio/vfio_iommu_type1.c | 77 +++++++++++++++++++++++++++++++++--------
>  include/linux/vfio.h            | 12 +++++++
>  3 files changed, 147 insertions(+), 15 deletions(-)
> 
> diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
> index bd36c16b0ef2..c850ba324be2 100644
> --- a/drivers/vfio/vfio.c
> +++ b/drivers/vfio/vfio.c
> @@ -1901,6 +1901,79 @@ err_unpin_pages:
>  }
>  EXPORT_SYMBOL(vfio_unpin_pages);
>  
> +int vfio_register_notifier(struct device *dev, struct notifier_block *nb)
> +{
> +	struct vfio_container *container;
> +	struct vfio_group *group;
> +	struct vfio_iommu_driver *driver;
> +	ssize_t ret;
> +

Any reason being 'ssize_t' here (and unregister)?

--
Thanks,
Jike
> +	if (!dev || !nb)
> +		return -EINVAL;
> +
> +	group = vfio_group_get_from_dev(dev);
> +	if (IS_ERR(group))
> +		return PTR_ERR(group);
> +
> +	ret = vfio_group_add_container_user(group);
> +	if (ret)
> +		goto err_register_nb;
> +
> +	container = group->container;
> +	down_read(&container->group_lock);
> +
> +	driver = container->iommu_driver;
> +	if (likely(driver && driver->ops->register_notifier))
> +		ret = driver->ops->register_notifier(container->iommu_data, nb);
> +	else
> +		ret = -ENOTTY;
> +
> +	up_read(&container->group_lock);
> +	vfio_group_try_dissolve_container(group);
> +
> +err_register_nb:
> +	vfio_group_put(group);
> +	return ret;
> +}
> +EXPORT_SYMBOL(vfio_register_notifier);
> +
> +int vfio_unregister_notifier(struct device *dev, struct notifier_block *nb)
> +{
> +	struct vfio_container *container;
> +	struct vfio_group *group;
> +	struct vfio_iommu_driver *driver;
> +	ssize_t ret;
> +
> +	if (!dev || !nb)
> +		return -EINVAL;
> +
> +	group = vfio_group_get_from_dev(dev);
> +	if (IS_ERR(group))
> +		return PTR_ERR(group);
> +
> +	ret = vfio_group_add_container_user(group);
> +	if (ret)
> +		goto err_unregister_nb;
> +
> +	container = group->container;
> +	down_read(&container->group_lock);
> +
> +	driver = container->iommu_driver;
> +	if (likely(driver && driver->ops->unregister_notifier))
> +		ret = driver->ops->unregister_notifier(container->iommu_data,
> +						       nb);
> +	else
> +		ret = -ENOTTY;
> +
> +	up_read(&container->group_lock);
> +	vfio_group_try_dissolve_container(group);
> +
> +err_unregister_nb:
> +	vfio_group_put(group);
> +	return ret;
> +}
> +EXPORT_SYMBOL(vfio_unregister_notifier);
> +
>  /**
>   * Module/class support
>   */
> diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
> index 98191fc590f8..63fbc48a088f 100644
> --- a/drivers/vfio/vfio_iommu_type1.c
> +++ b/drivers/vfio/vfio_iommu_type1.c
> @@ -38,6 +38,7 @@
>  #include <linux/workqueue.h>
>  #include <linux/pid_namespace.h>
>  #include <linux/mdev.h>
> +#include <linux/notifier.h>
>  
>  #define DRIVER_VERSION  "0.2"
>  #define DRIVER_AUTHOR   "Alex Williamson <alex.williamson@redhat.com>"
> @@ -60,6 +61,7 @@ struct vfio_iommu {
>  	struct vfio_domain	*external_domain; /* domain for external user */
>  	struct mutex		lock;
>  	struct rb_root		dma_list;
> +	struct blocking_notifier_head notifier;
>  	bool			v2;
>  	bool			nesting;
>  };
> @@ -561,7 +563,8 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
>  
>  	mutex_lock(&iommu->lock);
>  
> -	if (!iommu->external_domain) {
> +	/* Fail if notifier list is empty */
> +	if ((!iommu->external_domain) || (!iommu->notifier.head)) {
>  		ret = -EINVAL;
>  		goto pin_done;
>  	}
> @@ -776,9 +779,9 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
>  			     struct vfio_iommu_type1_dma_unmap *unmap)
>  {
>  	uint64_t mask;
> -	struct vfio_dma *dma;
> +	struct vfio_dma *dma, *dma_last = NULL;
>  	size_t unmapped = 0;
> -	int ret = 0;
> +	int ret = 0, retries;
>  
>  	mask = ((uint64_t)1 << __ffs(vfio_pgsize_bitmap(iommu))) - 1;
>  
> @@ -788,7 +791,7 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
>  		return -EINVAL;
>  
>  	WARN_ON(mask & PAGE_MASK);
> -
> +again:
>  	mutex_lock(&iommu->lock);
>  
>  	/*
> @@ -844,6 +847,32 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
>  		 */
>  		if (dma->task->mm != current->mm)
>  			break;
> +
> +		if (!RB_EMPTY_ROOT(&dma->pfn_list)) {
> +			struct vfio_iommu_type1_dma_unmap nb_unmap;
> +
> +			if (dma_last == dma) {
> +				BUG_ON(++retries > 10);
> +			} else {
> +				dma_last = dma;
> +				retries = 0;
> +			}
> +
> +			nb_unmap.iova = dma->iova;
> +			nb_unmap.size = dma->size;
> +
> +			/*
> +			 * Notify anyone (mdev vendor drivers) to invalidate and
> +			 * unmap iovas within the range we're about to unmap.
> +			 * Vendor drivers MUST unpin pages in response to an
> +			 * invalidation.
> +			 */
> +			mutex_unlock(&iommu->lock);
> +			blocking_notifier_call_chain(&iommu->notifier,
> +						    VFIO_IOMMU_NOTIFY_DMA_UNMAP,
> +						    &nb_unmap);
> +			goto again;
> +		}
>  		unmapped += dma->size;
>  		vfio_remove_dma(iommu, dma);
>  	}
> @@ -1321,12 +1350,11 @@ static void vfio_iommu_unmap_unpin_reaccount(struct vfio_iommu *iommu)
>  
>  static void vfio_sanity_check_pfn_list(struct vfio_iommu *iommu)
>  {
> -	struct rb_node *n, *p;
> +	struct rb_node *n;
>  
>  	n = rb_first(&iommu->dma_list);
>  	for (; n; n = rb_next(n)) {
>  		struct vfio_dma *dma;
> -		int unlocked = 0;
>  
>  		dma = rb_entry(n, struct vfio_dma, node);
>  
> @@ -1419,6 +1447,7 @@ static void *vfio_iommu_type1_open(unsigned long arg)
>  	INIT_LIST_HEAD(&iommu->domain_list);
>  	iommu->dma_list = RB_ROOT;
>  	mutex_init(&iommu->lock);
> +	BLOCKING_INIT_NOTIFIER_HEAD(&iommu->notifier);
>  
>  	return iommu;
>  }
> @@ -1553,16 +1582,34 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
>  	return -ENOTTY;
>  }
>  
> +static int vfio_iommu_type1_register_notifier(void *iommu_data,
> +					      struct notifier_block *nb)
> +{
> +	struct vfio_iommu *iommu = iommu_data;
> +
> +	return blocking_notifier_chain_register(&iommu->notifier, nb);
> +}
> +
> +static int vfio_iommu_type1_unregister_notifier(void *iommu_data,
> +						struct notifier_block *nb)
> +{
> +	struct vfio_iommu *iommu = iommu_data;
> +
> +	return blocking_notifier_chain_unregister(&iommu->notifier, nb);
> +}
> +
>  static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
> -	.name		= "vfio-iommu-type1",
> -	.owner		= THIS_MODULE,
> -	.open		= vfio_iommu_type1_open,
> -	.release	= vfio_iommu_type1_release,
> -	.ioctl		= vfio_iommu_type1_ioctl,
> -	.attach_group	= vfio_iommu_type1_attach_group,
> -	.detach_group	= vfio_iommu_type1_detach_group,
> -	.pin_pages	= vfio_iommu_type1_pin_pages,
> -	.unpin_pages	= vfio_iommu_type1_unpin_pages,
> +	.name			= "vfio-iommu-type1",
> +	.owner			= THIS_MODULE,
> +	.open			= vfio_iommu_type1_open,
> +	.release		= vfio_iommu_type1_release,
> +	.ioctl			= vfio_iommu_type1_ioctl,
> +	.attach_group		= vfio_iommu_type1_attach_group,
> +	.detach_group		= vfio_iommu_type1_detach_group,
> +	.pin_pages		= vfio_iommu_type1_pin_pages,
> +	.unpin_pages		= vfio_iommu_type1_unpin_pages,
> +	.register_notifier	= vfio_iommu_type1_register_notifier,
> +	.unregister_notifier	= vfio_iommu_type1_unregister_notifier,
>  };
>  
>  static int __init vfio_iommu_type1_init(void)
> diff --git a/include/linux/vfio.h b/include/linux/vfio.h
> index 3c862a030029..6ab13f7e2920 100644
> --- a/include/linux/vfio.h
> +++ b/include/linux/vfio.h
> @@ -80,6 +80,10 @@ struct vfio_iommu_driver_ops {
>  				     unsigned long *phys_pfn);
>  	int		(*unpin_pages)(void *iommu_data,
>  				       unsigned long *user_pfn, int npage);
> +	int		(*register_notifier)(void *iommu_data,
> +					     struct notifier_block *nb);
> +	int		(*unregister_notifier)(void *iommu_data,
> +					       struct notifier_block *nb);
>  };
>  
>  extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops);
> @@ -103,6 +107,14 @@ 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);
>  
> +#define VFIO_IOMMU_NOTIFY_DMA_UNMAP	(1)
> +
> +extern int vfio_register_notifier(struct device *dev,
> +				  struct notifier_block *nb);
> +
> +extern int vfio_unregister_notifier(struct device *dev,
> +				    struct notifier_block *nb);
> +
>  /*
>   * Sub-module helpers
>   */
> 
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index bd36c16b0ef2..c850ba324be2 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1901,6 +1901,79 @@  err_unpin_pages:
 }
 EXPORT_SYMBOL(vfio_unpin_pages);
 
+int vfio_register_notifier(struct device *dev, struct notifier_block *nb)
+{
+	struct vfio_container *container;
+	struct vfio_group *group;
+	struct vfio_iommu_driver *driver;
+	ssize_t ret;
+
+	if (!dev || !nb)
+		return -EINVAL;
+
+	group = vfio_group_get_from_dev(dev);
+	if (IS_ERR(group))
+		return PTR_ERR(group);
+
+	ret = vfio_group_add_container_user(group);
+	if (ret)
+		goto err_register_nb;
+
+	container = group->container;
+	down_read(&container->group_lock);
+
+	driver = container->iommu_driver;
+	if (likely(driver && driver->ops->register_notifier))
+		ret = driver->ops->register_notifier(container->iommu_data, nb);
+	else
+		ret = -ENOTTY;
+
+	up_read(&container->group_lock);
+	vfio_group_try_dissolve_container(group);
+
+err_register_nb:
+	vfio_group_put(group);
+	return ret;
+}
+EXPORT_SYMBOL(vfio_register_notifier);
+
+int vfio_unregister_notifier(struct device *dev, struct notifier_block *nb)
+{
+	struct vfio_container *container;
+	struct vfio_group *group;
+	struct vfio_iommu_driver *driver;
+	ssize_t ret;
+
+	if (!dev || !nb)
+		return -EINVAL;
+
+	group = vfio_group_get_from_dev(dev);
+	if (IS_ERR(group))
+		return PTR_ERR(group);
+
+	ret = vfio_group_add_container_user(group);
+	if (ret)
+		goto err_unregister_nb;
+
+	container = group->container;
+	down_read(&container->group_lock);
+
+	driver = container->iommu_driver;
+	if (likely(driver && driver->ops->unregister_notifier))
+		ret = driver->ops->unregister_notifier(container->iommu_data,
+						       nb);
+	else
+		ret = -ENOTTY;
+
+	up_read(&container->group_lock);
+	vfio_group_try_dissolve_container(group);
+
+err_unregister_nb:
+	vfio_group_put(group);
+	return ret;
+}
+EXPORT_SYMBOL(vfio_unregister_notifier);
+
 /**
  * Module/class support
  */
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 98191fc590f8..63fbc48a088f 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -38,6 +38,7 @@ 
 #include <linux/workqueue.h>
 #include <linux/pid_namespace.h>
 #include <linux/mdev.h>
+#include <linux/notifier.h>
 
 #define DRIVER_VERSION  "0.2"
 #define DRIVER_AUTHOR   "Alex Williamson <alex.williamson@redhat.com>"
@@ -60,6 +61,7 @@  struct vfio_iommu {
 	struct vfio_domain	*external_domain; /* domain for external user */
 	struct mutex		lock;
 	struct rb_root		dma_list;
+	struct blocking_notifier_head notifier;
 	bool			v2;
 	bool			nesting;
 };
@@ -561,7 +563,8 @@  static int vfio_iommu_type1_pin_pages(void *iommu_data,
 
 	mutex_lock(&iommu->lock);
 
-	if (!iommu->external_domain) {
+	/* Fail if notifier list is empty */
+	if ((!iommu->external_domain) || (!iommu->notifier.head)) {
 		ret = -EINVAL;
 		goto pin_done;
 	}
@@ -776,9 +779,9 @@  static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
 			     struct vfio_iommu_type1_dma_unmap *unmap)
 {
 	uint64_t mask;
-	struct vfio_dma *dma;
+	struct vfio_dma *dma, *dma_last = NULL;
 	size_t unmapped = 0;
-	int ret = 0;
+	int ret = 0, retries;
 
 	mask = ((uint64_t)1 << __ffs(vfio_pgsize_bitmap(iommu))) - 1;
 
@@ -788,7 +791,7 @@  static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
 		return -EINVAL;
 
 	WARN_ON(mask & PAGE_MASK);
-
+again:
 	mutex_lock(&iommu->lock);
 
 	/*
@@ -844,6 +847,32 @@  static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
 		 */
 		if (dma->task->mm != current->mm)
 			break;
+
+		if (!RB_EMPTY_ROOT(&dma->pfn_list)) {
+			struct vfio_iommu_type1_dma_unmap nb_unmap;
+
+			if (dma_last == dma) {
+				BUG_ON(++retries > 10);
+			} else {
+				dma_last = dma;
+				retries = 0;
+			}
+
+			nb_unmap.iova = dma->iova;
+			nb_unmap.size = dma->size;
+
+			/*
+			 * Notify anyone (mdev vendor drivers) to invalidate and
+			 * unmap iovas within the range we're about to unmap.
+			 * Vendor drivers MUST unpin pages in response to an
+			 * invalidation.
+			 */
+			mutex_unlock(&iommu->lock);
+			blocking_notifier_call_chain(&iommu->notifier,
+						    VFIO_IOMMU_NOTIFY_DMA_UNMAP,
+						    &nb_unmap);
+			goto again;
+		}
 		unmapped += dma->size;
 		vfio_remove_dma(iommu, dma);
 	}
@@ -1321,12 +1350,11 @@  static void vfio_iommu_unmap_unpin_reaccount(struct vfio_iommu *iommu)
 
 static void vfio_sanity_check_pfn_list(struct vfio_iommu *iommu)
 {
-	struct rb_node *n, *p;
+	struct rb_node *n;
 
 	n = rb_first(&iommu->dma_list);
 	for (; n; n = rb_next(n)) {
 		struct vfio_dma *dma;
-		int unlocked = 0;
 
 		dma = rb_entry(n, struct vfio_dma, node);
 
@@ -1419,6 +1447,7 @@  static void *vfio_iommu_type1_open(unsigned long arg)
 	INIT_LIST_HEAD(&iommu->domain_list);
 	iommu->dma_list = RB_ROOT;
 	mutex_init(&iommu->lock);
+	BLOCKING_INIT_NOTIFIER_HEAD(&iommu->notifier);
 
 	return iommu;
 }
@@ -1553,16 +1582,34 @@  static long vfio_iommu_type1_ioctl(void *iommu_data,
 	return -ENOTTY;
 }
 
+static int vfio_iommu_type1_register_notifier(void *iommu_data,
+					      struct notifier_block *nb)
+{
+	struct vfio_iommu *iommu = iommu_data;
+
+	return blocking_notifier_chain_register(&iommu->notifier, nb);
+}
+
+static int vfio_iommu_type1_unregister_notifier(void *iommu_data,
+						struct notifier_block *nb)
+{
+	struct vfio_iommu *iommu = iommu_data;
+
+	return blocking_notifier_chain_unregister(&iommu->notifier, nb);
+}
+
 static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
-	.name		= "vfio-iommu-type1",
-	.owner		= THIS_MODULE,
-	.open		= vfio_iommu_type1_open,
-	.release	= vfio_iommu_type1_release,
-	.ioctl		= vfio_iommu_type1_ioctl,
-	.attach_group	= vfio_iommu_type1_attach_group,
-	.detach_group	= vfio_iommu_type1_detach_group,
-	.pin_pages	= vfio_iommu_type1_pin_pages,
-	.unpin_pages	= vfio_iommu_type1_unpin_pages,
+	.name			= "vfio-iommu-type1",
+	.owner			= THIS_MODULE,
+	.open			= vfio_iommu_type1_open,
+	.release		= vfio_iommu_type1_release,
+	.ioctl			= vfio_iommu_type1_ioctl,
+	.attach_group		= vfio_iommu_type1_attach_group,
+	.detach_group		= vfio_iommu_type1_detach_group,
+	.pin_pages		= vfio_iommu_type1_pin_pages,
+	.unpin_pages		= vfio_iommu_type1_unpin_pages,
+	.register_notifier	= vfio_iommu_type1_register_notifier,
+	.unregister_notifier	= vfio_iommu_type1_unregister_notifier,
 };
 
 static int __init vfio_iommu_type1_init(void)
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 3c862a030029..6ab13f7e2920 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -80,6 +80,10 @@  struct vfio_iommu_driver_ops {
 				     unsigned long *phys_pfn);
 	int		(*unpin_pages)(void *iommu_data,
 				       unsigned long *user_pfn, int npage);
+	int		(*register_notifier)(void *iommu_data,
+					     struct notifier_block *nb);
+	int		(*unregister_notifier)(void *iommu_data,
+					       struct notifier_block *nb);
 };
 
 extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops);
@@ -103,6 +107,14 @@  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);
 
+#define VFIO_IOMMU_NOTIFY_DMA_UNMAP	(1)
+
+extern int vfio_register_notifier(struct device *dev,
+				  struct notifier_block *nb);
+
+extern int vfio_unregister_notifier(struct device *dev,
+				    struct notifier_block *nb);
+
 /*
  * Sub-module helpers
  */