Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

[Jason Gunthorpe <jgg@nvidia.com>]

On Thu, May 19, 2022 at 03:20:40PM +0800, Lu Baolu wrote:
> The iommu_sva_domain represents a hardware pagetable that the IOMMU
> hardware could use for SVA translation. This adds some infrastructure
> to support SVA domain in the iommu common layer. It includes:
> 
> - Add a new struct iommu_sva_domain and new IOMMU_DOMAIN_SVA domain
>   type.
> - Add a new domain ops pointer in iommu_ops. The IOMMU drivers that
>   support SVA should provide the callbacks.
> - Add helpers to allocate and free an SVA domain.
> - Add helpers to set an SVA domain to a device and the reverse
>   operation.
> 
> Some buses, like PCI, route packets without considering the PASID value.
> Thus a DMA target address with PASID might be treated as P2P if the
> address falls into the MMIO BAR of other devices in the group. To make
> things simple, the attach/detach interfaces only apply to devices
> belonging to the singleton groups, and the singleton is immutable in
> fabric i.e. not affected by hotplug.
> 
> The iommu_set/block_device_pasid() can be used for other purposes,
> such as kernel DMA with pasid, mediation device, etc. Hence, it is put
> in the iommu.c.
> 
> Suggested-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
> Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
> Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
>  include/linux/iommu.h         | 51 +++++++++++++++++++++++++
>  drivers/iommu/iommu-sva-lib.h | 15 ++++++++
>  drivers/iommu/iommu-sva-lib.c | 48 +++++++++++++++++++++++
>  drivers/iommu/iommu.c         | 71 +++++++++++++++++++++++++++++++++++
>  4 files changed, 185 insertions(+)
> 
> diff --git a/include/linux/iommu.h b/include/linux/iommu.h
> index 0c358b7c583b..e8cf82d46ce1 100644
> +++ b/include/linux/iommu.h
> @@ -64,6 +64,9 @@ struct iommu_domain_geometry {
>  #define __IOMMU_DOMAIN_PT	(1U << 2)  /* Domain is identity mapped   */
>  #define __IOMMU_DOMAIN_DMA_FQ	(1U << 3)  /* DMA-API uses flush queue    */
>  
> +#define __IOMMU_DOMAIN_SHARED	(1U << 4)  /* Page table shared from CPU  */
> +#define __IOMMU_DOMAIN_HOST_VA	(1U << 5)  /* Host CPU virtual address */
> +
>  /*
>   * This are the possible domain-types
>   *
> @@ -86,6 +89,8 @@ struct iommu_domain_geometry {
>  #define IOMMU_DOMAIN_DMA_FQ	(__IOMMU_DOMAIN_PAGING |	\
>  				 __IOMMU_DOMAIN_DMA_API |	\
>  				 __IOMMU_DOMAIN_DMA_FQ)
> +#define IOMMU_DOMAIN_SVA	(__IOMMU_DOMAIN_SHARED |	\
> +				 __IOMMU_DOMAIN_HOST_VA)
>  
>  struct iommu_domain {
>  	unsigned type;
> @@ -254,6 +259,7 @@ struct iommu_ops {
>  	int (*def_domain_type)(struct device *dev);
>  
>  	const struct iommu_domain_ops *default_domain_ops;
> +	const struct iommu_domain_ops *sva_domain_ops;
>  	unsigned long pgsize_bitmap;
>  	struct module *owner;
>  };
> @@ -262,6 +268,8 @@ struct iommu_ops {
>   * struct iommu_domain_ops - domain specific operations
>   * @attach_dev: attach an iommu domain to a device
>   * @detach_dev: detach an iommu domain from a device
> + * @set_dev_pasid: set an iommu domain to a pasid of device
> + * @block_dev_pasid: block pasid of device from using iommu domain
>   * @map: map a physically contiguous memory region to an iommu domain
>   * @map_pages: map a physically contiguous set of pages of the same size to
>   *             an iommu domain.
> @@ -282,6 +290,10 @@ struct iommu_ops {
>  struct iommu_domain_ops {
>  	int (*attach_dev)(struct iommu_domain *domain, struct device *dev);
>  	void (*detach_dev)(struct iommu_domain *domain, struct device *dev);
> +	int (*set_dev_pasid)(struct iommu_domain *domain, struct device *dev,
> +			     ioasid_t pasid);
> +	void (*block_dev_pasid)(struct iommu_domain *domain, struct device *dev,
> +				ioasid_t pasid);
>  
>  	int (*map)(struct iommu_domain *domain, unsigned long iova,
>  		   phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
> @@ -677,6 +689,10 @@ int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner);
>  void iommu_group_release_dma_owner(struct iommu_group *group);
>  bool iommu_group_dma_owner_claimed(struct iommu_group *group);
>  
> +int iommu_set_device_pasid(struct iommu_domain *domain, struct device *dev,
> +			   ioasid_t pasid);
> +void iommu_block_device_pasid(struct iommu_domain *domain, struct device *dev,
> +			      ioasid_t pasid);
>  #else /* CONFIG_IOMMU_API */
>  
>  struct iommu_ops {};
> @@ -1050,6 +1066,17 @@ static inline bool iommu_group_dma_owner_claimed(struct iommu_group *group)
>  {
>  	return false;
>  }
> +
> +static inline int iommu_set_device_pasid(struct iommu_domain *domain,
> +					 struct device *dev, ioasid_t pasid)
> +{
> +	return -ENODEV;
> +}
> +
> +static inline void iommu_block_device_pasid(struct iommu_domain *domain,
> +					    struct device *dev, ioasid_t pasid)
> +{
> +}
>  #endif /* CONFIG_IOMMU_API */
>  
>  /**
> @@ -1075,4 +1102,28 @@ void iommu_debugfs_setup(void);
>  static inline void iommu_debugfs_setup(void) {}
>  #endif
>  
> +#ifdef CONFIG_IOMMU_SVA
> +struct iommu_domain *
> +iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm);
> +void iommu_sva_free_domain(struct iommu_domain *domain);
> +int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev,
> +			 ioasid_t pasid);
> +#else /* CONFIG_IOMMU_SVA */
> +static inline struct iommu_domain *
> +iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm)
> +{
> +	return ERR_PTR(-EINVAL);
> +}
> +
> +static inline void iommu_sva_free_domain(struct iommu_domain *domain)
> +{
> +}
> +
> +static inline int iommu_sva_set_domain(struct iommu_domain *domain,
> +				       struct device *dev, ioasid_t pasid)
> +{
> +	return -EINVAL;
> +}
> +#endif /* CONFIG_IOMMU_SVA */
> +
>  #endif /* __LINUX_IOMMU_H */
> diff --git a/drivers/iommu/iommu-sva-lib.h b/drivers/iommu/iommu-sva-lib.h
> index 8909ea1094e3..1be21e6b93ec 100644
> +++ b/drivers/iommu/iommu-sva-lib.h
> @@ -7,6 +7,7 @@
>  
>  #include <linux/ioasid.h>
>  #include <linux/mm_types.h>
> +#include <linux/iommu.h>
>  
>  int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max);
>  struct mm_struct *iommu_sva_find(ioasid_t pasid);
> @@ -16,6 +17,20 @@ struct device;
>  struct iommu_fault;
>  struct iopf_queue;
>  
> +struct iommu_sva_domain {
> +	struct iommu_domain	domain;
> +	struct mm_struct	*mm;
> +};
> +
> +#define to_sva_domain(d) container_of_safe(d, struct iommu_sva_domain, domain)
> +
> +static inline struct mm_struct *domain_to_mm(struct iommu_domain *domain)
> +{
> +	struct iommu_sva_domain *sva_domain = to_sva_domain(domain);
> +
> +	return sva_domain->mm;
> +}
> +
>  #ifdef CONFIG_IOMMU_SVA
>  int iommu_queue_iopf(struct iommu_fault *fault, void *cookie);
>  
> diff --git a/drivers/iommu/iommu-sva-lib.c b/drivers/iommu/iommu-sva-lib.c
> index 106506143896..210c376f6043 100644
> +++ b/drivers/iommu/iommu-sva-lib.c
> @@ -69,3 +69,51 @@ struct mm_struct *iommu_sva_find(ioasid_t pasid)
>  	return ioasid_find(&iommu_sva_pasid, pasid, __mmget_not_zero);
>  }
>  EXPORT_SYMBOL_GPL(iommu_sva_find);
> +
> +/*
> + * IOMMU SVA driver-oriented interfaces
> + */
> +struct iommu_domain *
> +iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm)

This should return the proper type

> +{
> +	struct iommu_sva_domain *sva_domain;
> +	struct iommu_domain *domain;
> +
> +	if (!bus->iommu_ops || !bus->iommu_ops->sva_domain_ops)
> +		return ERR_PTR(-ENODEV);
> +
> +	sva_domain = kzalloc(sizeof(*sva_domain), GFP_KERNEL);
> +	if (!sva_domain)
> +		return ERR_PTR(-ENOMEM);
> +
> +	mmgrab(mm);
> +	sva_domain->mm = mm;
> +
> +	domain = &sva_domain->domain;
> +	domain->type = IOMMU_DOMAIN_SVA;
> +	domain->ops = bus->iommu_ops->sva_domain_ops;
> +
> +	return domain;
> +}
> +
> +void iommu_sva_free_domain(struct iommu_domain *domain)
> +{
> +	struct iommu_sva_domain *sva_domain = to_sva_domain(domain);
> +
> +	mmdrop(sva_domain->mm);
> +	kfree(sva_domain);
> +}

No callback to the driver?

> +int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev,
> +			 ioasid_t pasid)
> +{

Why does this function exist? Just call iommu_set_device_pasid()

> +int iommu_set_device_pasid(struct iommu_domain *domain, struct device *dev,
> +			   ioasid_t pasid)
> +{

Here you can continue to use attach/detach language as at this API
level we expect strict pairing..


> +void iommu_block_device_pasid(struct iommu_domain *domain, struct device *dev,
> +			      ioasid_t pasid)
> +{
> +	struct iommu_group *group = iommu_group_get(dev);
> +
> +	mutex_lock(&group->mutex);
> +	domain->ops->block_dev_pasid(domain, dev, pasid);
> +	xa_erase(&group->pasid_array, pasid);
> +	mutex_unlock(&group->mutex);

Should be the blocking domain.

Jason