iommufd: Add IOMMU_IOAS_MAP_FILE

Define the IOMMU_IOAS_MAP_FILE ioctl interface, which allows a user to
register memory by passing a memfd plus offset and length.  Implement it
using the memfd_pin_folios() kAPI.

Link: https://patch.msgid.link/r/[email protected]
Suggested-by: Jason Gunthorpe <[email protected]>
Signed-off-by: Steve Sistare <[email protected]>
Reviewed-by: Jason Gunthorpe <[email protected]>
Reviewed-by: Kevin Tian <[email protected]>
Signed-off-by: Jason Gunthorpe <[email protected]>

Author: Steve Sistare

drivers/iommu/iommufd/io_pagetable.c

@@ -268,7 +268,14 @@ static int iopt_alloc_area_pages(struct io_pagetable *iopt,
 		/* Use the first entry to guess the ideal IOVA alignment */
 		elm = list_first_entry(pages_list, struct iopt_pages_list,
 				       next);
-		start = elm->start_byte + (uintptr_t)elm->pages->uptr;
+		switch (elm->pages->type) {
+		case IOPT_ADDRESS_USER:
+			start = elm->start_byte + (uintptr_t)elm->pages->uptr;
+			break;
+		case IOPT_ADDRESS_FILE:
+			start = elm->start_byte + elm->pages->start;
+			break;
+		}
 		rc = iopt_alloc_iova(iopt, dst_iova, start, length);
 		if (rc)
 			goto out_unlock;
@@ -446,6 +453,33 @@ int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt,
 			       uptr - pages->uptr, iommu_prot, flags);
 }
 
+/**
+ * iopt_map_file_pages() - Like iopt_map_user_pages, but map a file.
+ * @ictx: iommufd_ctx the iopt is part of
+ * @iopt: io_pagetable to act on
+ * @iova: If IOPT_ALLOC_IOVA is set this is unused on input and contains
+ *        the chosen iova on output. Otherwise is the iova to map to on input
+ * @file: file to map
+ * @start: map file starting at this byte offset
+ * @length: Number of bytes to map
+ * @iommu_prot: Combination of IOMMU_READ/WRITE/etc bits for the mapping
+ * @flags: IOPT_ALLOC_IOVA or zero
+ */
+int iopt_map_file_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt,
+			unsigned long *iova, struct file *file,
+			unsigned long start, unsigned long length,
+			int iommu_prot, unsigned int flags)
+{
+	struct iopt_pages *pages;
+
+	pages = iopt_alloc_file_pages(file, start, length,
+				      iommu_prot & IOMMU_WRITE);
+	if (IS_ERR(pages))
+		return PTR_ERR(pages);
+	return iopt_map_common(ictx, iopt, pages, iova, length,
+			       start - pages->start, iommu_prot, flags);
+}
+
 struct iova_bitmap_fn_arg {
 	unsigned long flags;
 	struct io_pagetable *iopt;

drivers/iommu/iommufd/io_pagetable.h

@@ -220,6 +220,8 @@ struct iopt_pages {
 
 struct iopt_pages *iopt_alloc_user_pages(void __user *uptr,
 					 unsigned long length, bool writable);
+struct iopt_pages *iopt_alloc_file_pages(struct file *file, unsigned long start,
+					 unsigned long length, bool writable);
 void iopt_release_pages(struct kref *kref);
 static inline void iopt_put_pages(struct iopt_pages *pages)
 {

drivers/iommu/iommufd/ioas.c

@@ -2,6 +2,7 @@
 /*
  * Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES
  */
+#include <linux/file.h>
 #include <linux/interval_tree.h>
 #include <linux/iommu.h>
 #include <linux/iommufd.h>
@@ -197,6 +198,52 @@ static int conv_iommu_prot(u32 map_flags)
 	return iommu_prot;
 }
 
+int iommufd_ioas_map_file(struct iommufd_ucmd *ucmd)
+{
+	struct iommu_ioas_map_file *cmd = ucmd->cmd;
+	unsigned long iova = cmd->iova;
+	struct iommufd_ioas *ioas;
+	unsigned int flags = 0;
+	struct file *file;
+	int rc;
+
+	if (cmd->flags &
+	     ~(IOMMU_IOAS_MAP_FIXED_IOVA | IOMMU_IOAS_MAP_WRITEABLE |
+	       IOMMU_IOAS_MAP_READABLE))
+		return -EOPNOTSUPP;
+
+	if (cmd->iova >= ULONG_MAX || cmd->length >= ULONG_MAX)
+		return -EOVERFLOW;
+
+	if (!(cmd->flags &
+	      (IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)))
+		return -EINVAL;
+
+	ioas = iommufd_get_ioas(ucmd->ictx, cmd->ioas_id);
+	if (IS_ERR(ioas))
+		return PTR_ERR(ioas);
+
+	if (!(cmd->flags & IOMMU_IOAS_MAP_FIXED_IOVA))
+		flags = IOPT_ALLOC_IOVA;
+
+	file = fget(cmd->fd);
+	if (!file)
+		return -EBADF;
+
+	rc = iopt_map_file_pages(ucmd->ictx, &ioas->iopt, &iova, file,
+				 cmd->start, cmd->length,
+				 conv_iommu_prot(cmd->flags), flags);
+	if (rc)
+		goto out_put;
+
+	cmd->iova = iova;
+	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
+out_put:
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
+	fput(file);
+	return rc;
+}
+
 int iommufd_ioas_map(struct iommufd_ucmd *ucmd)
 {
 	struct iommu_ioas_map *cmd = ucmd->cmd;

drivers/iommu/iommufd/iommufd_private.h

@@ -69,6 +69,10 @@ int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt,
 			unsigned long *iova, void __user *uptr,
 			unsigned long length, int iommu_prot,
 			unsigned int flags);
+int iopt_map_file_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt,
+			unsigned long *iova, struct file *file,
+			unsigned long start, unsigned long length,
+			int iommu_prot, unsigned int flags);
 int iopt_map_pages(struct io_pagetable *iopt, struct list_head *pages_list,
 		   unsigned long length, unsigned long *dst_iova,
 		   int iommu_prot, unsigned int flags);
@@ -276,6 +280,7 @@ void iommufd_ioas_destroy(struct iommufd_object *obj);
 int iommufd_ioas_iova_ranges(struct iommufd_ucmd *ucmd);
 int iommufd_ioas_allow_iovas(struct iommufd_ucmd *ucmd);
 int iommufd_ioas_map(struct iommufd_ucmd *ucmd);
+int iommufd_ioas_map_file(struct iommufd_ucmd *ucmd);
 int iommufd_ioas_copy(struct iommufd_ucmd *ucmd);
 int iommufd_ioas_unmap(struct iommufd_ucmd *ucmd);
 int iommufd_ioas_option(struct iommufd_ucmd *ucmd);

drivers/iommu/iommufd/main.c

@@ -378,6 +378,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = {
 		 struct iommu_ioas_iova_ranges, out_iova_alignment),
 	IOCTL_OP(IOMMU_IOAS_MAP, iommufd_ioas_map, struct iommu_ioas_map,
 		 iova),
+	IOCTL_OP(IOMMU_IOAS_MAP_FILE, iommufd_ioas_map_file,
+		 struct iommu_ioas_map_file, iova),
 	IOCTL_OP(IOMMU_IOAS_UNMAP, iommufd_ioas_unmap, struct iommu_ioas_unmap,
 		 length),
 	IOCTL_OP(IOMMU_OPTION, iommufd_option, struct iommu_option,

drivers/iommu/iommufd/pages.c

@@ -45,6 +45,7 @@
  * last_iova + 1 can overflow. An iopt_pages index will always be much less than
  * ULONG_MAX so last_index + 1 cannot overflow.
  */
+#include <linux/file.h>
 #include <linux/highmem.h>
 #include <linux/iommu.h>
 #include <linux/iommufd.h>
@@ -1340,6 +1341,26 @@ struct iopt_pages *iopt_alloc_user_pages(void __user *uptr,
 	return pages;
 }
 
+struct iopt_pages *iopt_alloc_file_pages(struct file *file, unsigned long start,
+					 unsigned long length, bool writable)
+
+{
+	struct iopt_pages *pages;
+	unsigned long start_down = ALIGN_DOWN(start, PAGE_SIZE);
+	unsigned long end;
+
+	if (length && check_add_overflow(start, length - 1, &end))
+		return ERR_PTR(-EOVERFLOW);
+
+	pages = iopt_alloc_pages(start - start_down, length, writable);
+	if (IS_ERR(pages))
+		return pages;
+	pages->file = get_file(file);
+	pages->start = start_down;
+	pages->type = IOPT_ADDRESS_FILE;
+	return pages;
+}
+
 void iopt_release_pages(struct kref *kref)
 {
 	struct iopt_pages *pages = container_of(kref, struct iopt_pages, kref);
@@ -1352,6 +1373,8 @@ void iopt_release_pages(struct kref *kref)
 	mutex_destroy(&pages->mutex);
 	put_task_struct(pages->source_task);
 	free_uid(pages->source_user);
+	if (pages->type == IOPT_ADDRESS_FILE)
+		fput(pages->file);
 	kfree(pages);
 }
 

include/uapi/linux/iommufd.h

@@ -51,6 +51,7 @@ enum {
 	IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP = 0x8c,
 	IOMMUFD_CMD_HWPT_INVALIDATE = 0x8d,
 	IOMMUFD_CMD_FAULT_QUEUE_ALLOC = 0x8e,
+	IOMMUFD_CMD_IOAS_MAP_FILE = 0x8f,
 };
 
 /**
@@ -213,6 +214,30 @@ struct iommu_ioas_map {
 };
 #define IOMMU_IOAS_MAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_MAP)
 
+/**
+ * struct iommu_ioas_map_file - ioctl(IOMMU_IOAS_MAP_FILE)
+ * @size: sizeof(struct iommu_ioas_map_file)
+ * @flags: same as for iommu_ioas_map
+ * @ioas_id: same as for iommu_ioas_map
+ * @fd: the memfd to map
+ * @start: byte offset from start of file to map from
+ * @length: same as for iommu_ioas_map
+ * @iova: same as for iommu_ioas_map
+ *
+ * Set an IOVA mapping from a memfd file.  All other arguments and semantics
+ * match those of IOMMU_IOAS_MAP.
+ */
+struct iommu_ioas_map_file {
+	__u32 size;
+	__u32 flags;
+	__u32 ioas_id;
+	__s32 fd;
+	__aligned_u64 start;
+	__aligned_u64 length;
+	__aligned_u64 iova;
+};
+#define IOMMU_IOAS_MAP_FILE _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_MAP_FILE)
+
 /**
  * struct iommu_ioas_copy - ioctl(IOMMU_IOAS_COPY)
  * @size: sizeof(struct iommu_ioas_copy)