Re: [PATCH v11 05/22] vfio iommu: Added pin and unpin callback functions to vfio_iommu_driver_ops

[Alex Williamson <alex.williamson@redhat.com>]

On Sat, 5 Nov 2016 02:40:39 +0530
Kirti Wankhede <kwankhede@nvidia.com> wrote:

> Added two new callback functions to struct vfio_iommu_driver_ops. Backend
> IOMMU module that supports pining and unpinning pages for mdev devices
> should provide these functions.
> Added APIs for pining and unpining pages to VFIO module. These calls back
> into backend iommu module to actually pin and unpin pages.
> Renamed static functions in vfio_type1_iommu.c to resolve conflicts
> 
> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
> Signed-off-by: Neo Jia <cjia@nvidia.com>
> Change-Id: Ia7417723aaae86bec2959ad9ae6c2915ddd340e0
> ---
>  drivers/vfio/vfio.c             | 96 +++++++++++++++++++++++++++++++++++++++++
>  drivers/vfio/vfio_iommu_type1.c | 20 ++++-----
>  include/linux/vfio.h            | 14 +++++-
>  3 files changed, 119 insertions(+), 11 deletions(-)
> 
> diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
> index 2e83bdf007fe..76d260e98930 100644
> --- a/drivers/vfio/vfio.c
> +++ b/drivers/vfio/vfio.c
> @@ -1799,6 +1799,102 @@ void vfio_info_cap_shift(struct vfio_info_cap *caps, size_t offset)
>  }
>  EXPORT_SYMBOL_GPL(vfio_info_cap_shift);
>  
> +
> +/*
> + * Pin a set of guest PFNs and return their associated host PFNs for local
> + * domain only.
> + * @dev [in] : device
> + * @user_pfn [in]: array of user/guest PFNs
> + * @npage [in]: count of array elements
> + * @prot [in] : protection flags
> + * @phys_pfn[out] : array of host PFNs
> + * Return error or number of pages pinned.
> + */
> +int vfio_pin_pages(struct device *dev, unsigned long *user_pfn,
> +		   int npage, int prot, unsigned long *phys_pfn)
> +{
> +	struct vfio_container *container;
> +	struct vfio_group *group;
> +	struct vfio_iommu_driver *driver;
> +	int ret;
> +
> +	if (!dev || !user_pfn || !phys_pfn)
> +		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_pin_pages;
> +
> +	container = group->container;
> +	down_read(&container->group_lock);
> +
> +	driver = container->iommu_driver;
> +	if (likely(driver && driver->ops->pin_pages))
> +		ret = driver->ops->pin_pages(container->iommu_data, user_pfn,
> +					     npage, prot, phys_pfn);
> +	else
> +		ret = -EINVAL;

-ENOTTY might be a more appropriate error return here and below since
we're not signaling invalid argument, we're signaling lack of support.

> +
> +	up_read(&container->group_lock);
> +	vfio_group_try_dissolve_container(group);
> +
> +err_pin_pages:
> +	vfio_group_put(group);
> +	return ret;
> +

Unnecessary extra line

> +}
> +EXPORT_SYMBOL(vfio_pin_pages);
> +
> +/*
> + * Unpin set of host PFNs for local domain only.
> + * @dev [in] : device
> + * @user_pfn [in]: array of user/guest PFNs to be unpinned
> + * @pfn [in] : array of host PFNs to be unpinned.
> + * @npage [in] :count of elements in array, that is number of pages.
> + * Return error or number of pages unpinned.
> + */
> +int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn,
> +		     unsigned long *pfn, int npage)
> +{
> +	struct vfio_container *container;
> +	struct vfio_group *group;
> +	struct vfio_iommu_driver *driver;
> +	int ret;
> +
> +	if (!dev || !pfn)
> +		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_unpin_pages;
> +
> +	container = group->container;
> +	down_read(&container->group_lock);
> +
> +	driver = container->iommu_driver;
> +	if (likely(driver && driver->ops->unpin_pages))
> +		ret = driver->ops->unpin_pages(container->iommu_data, user_pfn,
> +					       pfn, npage);
> +	else
> +		ret = -EINVAL;
> +
> +	up_read(&container->group_lock);
> +	vfio_group_try_dissolve_container(group);
> +
> +err_unpin_pages:
> +	vfio_group_put(group);
> +	return ret;
> +}
> +EXPORT_SYMBOL(vfio_unpin_pages);
> +
>  /**
>   * Module/class support
>   */
> diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
> index 2ba19424e4a1..7fb87f008e0a 100644
> --- a/drivers/vfio/vfio_iommu_type1.c
> +++ b/drivers/vfio/vfio_iommu_type1.c
> @@ -259,8 +259,8 @@ static int vaddr_get_pfn(unsigned long vaddr, int prot, unsigned long *pfn)
>   * the iommu can only map chunks of consecutive pfns anyway, so get the
>   * first page and all consecutive pages with the same locking.
>   */
> -static long vfio_pin_pages(unsigned long vaddr, long npage,
> -			   int prot, unsigned long *pfn_base)
> +static long __vfio_pin_pages_remote(unsigned long vaddr, long npage,
> +				    int prot, unsigned long *pfn_base)

nit, what is the additional underscore prefix intended to imply?
Appending _remote is sufficient to avoid the symbol conflict.

>  {
>  	unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
>  	bool lock_cap = capable(CAP_IPC_LOCK);
> @@ -318,8 +318,8 @@ static long vfio_pin_pages(unsigned long vaddr, long npage,
>  	return i;
>  }
>  
> -static long vfio_unpin_pages(unsigned long pfn, long npage,
> -			     int prot, bool do_accounting)
> +static long __vfio_unpin_pages_remote(unsigned long pfn, long npage,
> +				      int prot, bool do_accounting)
>  {
>  	unsigned long unlocked = 0;
>  	long i;
> @@ -382,9 +382,9 @@ static void vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma)
>  		if (WARN_ON(!unmapped))
>  			break;
>  
> -		unlocked += vfio_unpin_pages(phys >> PAGE_SHIFT,
> -					     unmapped >> PAGE_SHIFT,
> -					     dma->prot, false);
> +		unlocked += __vfio_unpin_pages_remote(phys >> PAGE_SHIFT,
> +						      unmapped >> PAGE_SHIFT,
> +						      dma->prot, false);
>  		iova += unmapped;
>  
>  		cond_resched();
> @@ -613,8 +613,8 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
>  
>  	while (size) {
>  		/* Pin a contiguous chunk of memory */
> -		npage = vfio_pin_pages(vaddr + dma->size,
> -				       size >> PAGE_SHIFT, prot, &pfn);
> +		npage = __vfio_pin_pages_remote(vaddr + dma->size,
> +						size >> PAGE_SHIFT, prot, &pfn);
>  		if (npage <= 0) {
>  			WARN_ON(!npage);
>  			ret = (int)npage;
> @@ -624,7 +624,7 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
>  		/* Map it! */
>  		ret = vfio_iommu_map(iommu, iova + dma->size, pfn, npage, prot);
>  		if (ret) {
> -			vfio_unpin_pages(pfn, npage, prot, true);
> +			__vfio_unpin_pages_remote(pfn, npage, prot, true);
>  			break;
>  		}
>  
> diff --git a/include/linux/vfio.h b/include/linux/vfio.h
> index 0ecae0b1cd34..ba1b64cb7d4b 100644
> --- a/include/linux/vfio.h
> +++ b/include/linux/vfio.h
> @@ -75,7 +75,13 @@ struct vfio_iommu_driver_ops {
>  					struct iommu_group *group);
>  	void		(*detach_group)(void *iommu_data,
>  					struct iommu_group *group);
> -
> +	int		(*pin_pages)(void *iommu_data, unsigned long *user_pfn,
> +				     int npage, int prot,
> +				     unsigned long *phys_pfn);
> +	int		(*unpin_pages)(void *iommu_data,

Are we changing from long to int here simply because of the absurdity
in passing in more than a 2^31 entry array, that would already consume
more than 16GB itself?

> +				       unsigned long *user_pfn,
> +				       unsigned long *pfn,

nit, use phys_pfn so as to match the pin function?

> +				       int npage);
>  };
>  
>  extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops);
> @@ -127,6 +133,12 @@ static inline long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group,
>  }
>  #endif /* CONFIG_EEH */
>  
> +extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn,
> +			  int npage, int prot, unsigned long *phys_pfn);
> +
> +extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn,
> +			    unsigned long *pfn, int npage);
> +
>  /*
>   * IRQfd - generic
>   */