Re: [PATCH v2 13/22] iommufd: Add mmap interface

[Pranjal Shrivastava <praan@google.com>]

On Tue, Apr 29, 2025 at 08:24:33PM +0000, Pranjal Shrivastava wrote:
> On Fri, Apr 25, 2025 at 10:58:08PM -0700, Nicolin Chen wrote:
> > For vIOMMU passing through HW resources to user space (VMs), add an mmap
> > infrastructure to map a region of hardware MMIO pages.
> > 
> > Maintain an mt_mmap per ictx for validations. To allow IOMMU drivers to
> > add and delete mmappable regions to/from the mt_mmap, add a pair of new
> > helpers: iommufd_ctx_alloc_mmap() and iommufd_ctx_free_mmap().
> > 
> > Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
> > ---
> >  drivers/iommu/iommufd/iommufd_private.h |  8 +++++
> >  include/linux/iommufd.h                 | 15 ++++++++++
> >  drivers/iommu/iommufd/driver.c          | 39 +++++++++++++++++++++++++
> >  drivers/iommu/iommufd/main.c            | 39 +++++++++++++++++++++++++
> >  4 files changed, 101 insertions(+)
> > 
> > diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
> > index b974c207ae8a..db5b62ec4abb 100644
> > --- a/drivers/iommu/iommufd/iommufd_private.h
> > +++ b/drivers/iommu/iommufd/iommufd_private.h
> > @@ -7,6 +7,7 @@
> >  #include <linux/iommu.h>
> >  #include <linux/iommufd.h>
> >  #include <linux/iova_bitmap.h>
> > +#include <linux/maple_tree.h>
> >  #include <linux/rwsem.h>
> >  #include <linux/uaccess.h>
> >  #include <linux/xarray.h>
> > @@ -44,6 +45,7 @@ struct iommufd_ctx {
> >  	struct xarray groups;
> >  	wait_queue_head_t destroy_wait;
> >  	struct rw_semaphore ioas_creation_lock;
> > +	struct maple_tree mt_mmap;
> >  
> >  	struct mutex sw_msi_lock;
> >  	struct list_head sw_msi_list;
> > @@ -55,6 +57,12 @@ struct iommufd_ctx {
> >  	struct iommufd_ioas *vfio_ioas;
> >  };
> >  
> > +/* Entry for iommufd_ctx::mt_mmap */
> > +struct iommufd_mmap {
> > +	unsigned long pfn_start;
> > +	unsigned long pfn_end;
> > +};
> > +
> >  /*
> >   * The IOVA to PFN map. The map automatically copies the PFNs into multiple
> >   * domains and permits sharing of PFNs between io_pagetable instances. This
> > diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
> > index 5dff154e8ce1..d63e2d91be0d 100644
> > --- a/include/linux/iommufd.h
> > +++ b/include/linux/iommufd.h
> > @@ -236,6 +236,9 @@ int iommufd_object_depend(struct iommufd_object *obj_dependent,
> >  			  struct iommufd_object *obj_depended);
> >  void iommufd_object_undepend(struct iommufd_object *obj_dependent,
> >  			     struct iommufd_object *obj_depended);
> > +int iommufd_ctx_alloc_mmap(struct iommufd_ctx *ictx, phys_addr_t base,
> > +			   size_t size, unsigned long *immap_id);
> > +void iommufd_ctx_free_mmap(struct iommufd_ctx *ictx, unsigned long immap_id);
> >  struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu,
> >  				       unsigned long vdev_id);
> >  int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu,
> > @@ -262,11 +265,23 @@ static inline int iommufd_object_depend(struct iommufd_object *obj_dependent,
> >  	return -EOPNOTSUPP;
> >  }
> >  
> > +static inline int iommufd_ctx_alloc_mmap(struct iommufd_ctx *ictx,
> > +					 phys_addr_t base, size_t size,
> > +					 unsigned long *immap_id)
> > +{
> > +	return -EOPNOTSUPP;
> > +}
> > +
> >  static inline void iommufd_object_undepend(struct iommufd_object *obj_dependent,
> >  					   struct iommufd_object *obj_depended)
> >  {
> >  }
> >  
> > +static inline void iommufd_ctx_free_mmap(struct iommufd_ctx *ictx,
> > +					 unsigned long immap_id)
> > +{
> > +}
> > +
> >  static inline struct device *
> >  iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id)
> >  {
> > diff --git a/drivers/iommu/iommufd/driver.c b/drivers/iommu/iommufd/driver.c
> > index fb7f8fe40f95..c55336c580dc 100644
> > --- a/drivers/iommu/iommufd/driver.c
> > +++ b/drivers/iommu/iommufd/driver.c
> > @@ -78,6 +78,45 @@ void iommufd_object_undepend(struct iommufd_object *obj_dependent,
> >  }
> >  EXPORT_SYMBOL_NS_GPL(iommufd_object_undepend, "IOMMUFD");
> >  
> > +/* Driver should report the output @immap_id to user space for mmap() syscall */
> > +int iommufd_ctx_alloc_mmap(struct iommufd_ctx *ictx, phys_addr_t base,
> > +			   size_t size, unsigned long *immap_id)
> > +{
> > +	struct iommufd_mmap *immap;
> > +	int rc;
> > +
> > +	if (WARN_ON_ONCE(!immap_id))
> > +		return -EINVAL;
> > +	if (base & ~PAGE_MASK)
> > +		return -EINVAL;
> > +	if (!size || size & ~PAGE_MASK)
> > +		return -EINVAL;
> > +
> > +	immap = kzalloc(sizeof(*immap), GFP_KERNEL);
> > +	if (!immap)
> > +		return -ENOMEM;
> > +	immap->pfn_start = base >> PAGE_SHIFT;
> > +	immap->pfn_end = immap->pfn_start + (size >> PAGE_SHIFT) - 1;
> > +
> > +	rc = mtree_alloc_range(&ictx->mt_mmap, immap_id, immap, sizeof(immap),
> 
> I believe this should be sizeof(*immap) ?

Ugh, Sorry, shouldn't this be size >> PAGE_SHIFT (num_indices to alloc) ?

> 
> > +			       0, LONG_MAX >> PAGE_SHIFT, GFP_KERNEL);
> > +	if (rc < 0) {
> > +		kfree(immap);
> > +		return rc;
> > +	}
> > +
> > +	/* mmap() syscall will right-shift the immap_id to vma->vm_pgoff */
> > +	*immap_id <<= PAGE_SHIFT;
> > +	return 0;
> > +}
> > +EXPORT_SYMBOL_NS_GPL(iommufd_ctx_alloc_mmap, "IOMMUFD");
> > +
> > +void iommufd_ctx_free_mmap(struct iommufd_ctx *ictx, unsigned long immap_id)
> > +{
> > +	kfree(mtree_erase(&ictx->mt_mmap, immap_id >> PAGE_SHIFT));
> > +}
> > +EXPORT_SYMBOL_NS_GPL(iommufd_ctx_free_mmap, "IOMMUFD");
> > +
> >  /* Caller should xa_lock(&viommu->vdevs) to protect the return value */
> >  struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu,
> >  				       unsigned long vdev_id)
> > diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
> > index ac51d5cfaa61..4b46ea47164d 100644
> > --- a/drivers/iommu/iommufd/main.c
> > +++ b/drivers/iommu/iommufd/main.c
> > @@ -213,6 +213,7 @@ static int iommufd_fops_open(struct inode *inode, struct file *filp)
> >  	xa_init_flags(&ictx->objects, XA_FLAGS_ALLOC1 | XA_FLAGS_ACCOUNT);
> >  	xa_init(&ictx->groups);
> >  	ictx->file = filp;
> > +	mt_init_flags(&ictx->mt_mmap, MT_FLAGS_ALLOC_RANGE);
> >  	init_waitqueue_head(&ictx->destroy_wait);
> >  	mutex_init(&ictx->sw_msi_lock);
> >  	INIT_LIST_HEAD(&ictx->sw_msi_list);
> > @@ -410,11 +411,49 @@ static long iommufd_fops_ioctl(struct file *filp, unsigned int cmd,
> >  	return ret;
> >  }
> >  
> > +/*
> > + * Kernel driver must first do iommufd_ctx_alloc_mmap() to register an mmappable
> > + * MMIO region to the iommufd core to receive an "immap_id". Then, driver should
> > + * report to user space this immap_id and the size of the registered MMIO region
> > + * for @vm_pgoff and @size of an mmap() call, via an IOMMU_VIOMMU_ALLOC ioctl in
> > + * the output fields of its driver-type data structure.
> > + *
> > + * Note the @size is allowed to be smaller than the registered size as a partial
> > + * mmap starting from the registered base address.
> > + */
> > +static int iommufd_fops_mmap(struct file *filp, struct vm_area_struct *vma)
> > +{
> > +	struct iommufd_ctx *ictx = filp->private_data;
> > +	size_t size = vma->vm_end - vma->vm_start;
> > +	struct iommufd_mmap *immap;
> > +
> > +	if (size & ~PAGE_MASK)
> > +		return -EINVAL;
> > +	if (!(vma->vm_flags & VM_SHARED))
> > +		return -EINVAL;
> > +	if (vma->vm_flags & VM_EXEC)
> > +		return -EPERM;
> > +
> > +	/* vm_pgoff carries an index (immap_id) to an mtree entry (immap) */
> > +	immap = mtree_load(&ictx->mt_mmap, vma->vm_pgoff);
> > +	if (!immap)
> > +		return -ENXIO;
> > +	if (size >> PAGE_SHIFT > immap->pfn_end - immap->pfn_start + 1)
> > +		return -ENXIO;
> > +
> > +	vma->vm_pgoff = 0;
> > +	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
> > +	vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO);
> > +	return remap_pfn_range(vma, vma->vm_start, immap->pfn_start, size,
> > +			       vma->vm_page_prot);
> > +}
> > +
> >  static const struct file_operations iommufd_fops = {
> >  	.owner = THIS_MODULE,
> >  	.open = iommufd_fops_open,
> >  	.release = iommufd_fops_release,
> >  	.unlocked_ioctl = iommufd_fops_ioctl,
> > +	.mmap = iommufd_fops_mmap,
> >  };
> >  
> >  /**
> 
> Thanks,
> Praan
> 
> > -- 
> > 2.43.0
> >