[PATCH v1 10/16] iommufd: Add mmap interface

[Nicolin Chen <nicolinc@nvidia.com>]

For vIOMMU passing through HW resources to user space (VMs), add an mmap
infrastructure to map a region of hardware MMIO pages. The addr and size
should be given previously via a prior IOMMU_VIOMMU_ALLOC ioctl in some
output fields of the structure.

Maintain an mt_mmap per ictx for validations. And give IOMMU drivers a
pair of helpers to add and delete mmap regions onto the mt_mmap.

Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
---
 drivers/iommu/iommufd/iommufd_private.h |  9 ++++++
 include/linux/iommufd.h                 | 15 ++++++++++
 drivers/iommu/iommufd/driver.c          | 40 +++++++++++++++++++++++++
 drivers/iommu/iommufd/main.c            | 35 ++++++++++++++++++++++
 4 files changed, 99 insertions(+)

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index da35ffcc212b..5be0248966aa 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 +57,13 @@ 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;
+	bool is_io;
+};
+
 /*
  * 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 4118eaece1a5..e9394e20c4dd 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -226,6 +226,9 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
 					     size_t size,
 					     enum iommufd_object_type type);
 void iommufd_object_abort(struct iommufd_ctx *ictx, struct iommufd_object *obj);
+int iommufd_ctx_alloc_mmap(struct iommufd_ctx *ictx, phys_addr_t base,
+			   size_t size, bool is_io, 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,
@@ -246,6 +249,18 @@ static inline void iommufd_object_abort(struct iommufd_ctx *ictx,
 {
 }
 
+static inline int iommufd_ctx_alloc_mmap(struct iommufd_ctx *ictx,
+					 phys_addr_t base, size_t size,
+					 bool is_io, unsigned long *immap_id)
+{
+	return -EOPNOTSUPP;
+}
+
+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 7980a09761c2..abe0bdc1e9a3 100644
--- a/drivers/iommu/iommufd/driver.c
+++ b/drivers/iommu/iommufd/driver.c
@@ -50,6 +50,46 @@ void iommufd_object_abort(struct iommufd_ctx *ictx, struct iommufd_object *obj)
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_object_abort, "IOMMUFD");
 
+/* Driver should report the immap_id to user space for mmap() syscalls */
+int iommufd_ctx_alloc_mmap(struct iommufd_ctx *ictx, phys_addr_t base,
+			   size_t size, bool is_io, 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;
+	immap->is_io = is_io;
+
+	rc = mtree_alloc_range(&ictx->mt_mmap, immap_id, immap, sizeof(immap),
+			       0, LONG_MAX >> PAGE_SHIFT, GFP_KERNEL);
+	if (rc < 0) {
+		kfree(immap);
+		return rc;
+	}
+
+	/* mmap() syscall would 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 27473aff150f..d3101c76fcb8 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 +411,45 @@ static long iommufd_fops_ioctl(struct file *filp, unsigned int cmd,
 	return ret;
 }
 
+/*
+ * The pfn and size carried in @vma from the user space mmap call should be
+ * previously given to user space via a prior ioctl output.
+ */
+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 of an mtree entry/immap */
+	immap = mtree_load(&ictx->mt_mmap, vma->vm_pgoff);
+	if (!immap)
+		return -EINVAL;
+	if (size >> PAGE_SHIFT > immap->pfn_end - immap->pfn_start + 1)
+		return -EINVAL;
+
+	vma->vm_pgoff = 0;
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
+	if (immap->is_io)
+		vm_flags_set(vma, 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,
 };
 
 /**
-- 
2.43.0