Merge tag 'topic/iomem-mmap-vs-gup-2021-02-22' of git://anongit.freedesktop.org/drm/drm

Pull follow_pfn() updates from Daniel Vetter:
 "Fixes around VM_FPNMAP and follow_pfn:

   - replace mm/frame_vector.c by get_user_pages in misc/habana and
     drm/exynos drivers, then move that into media as it's sole user

   - close race in generic_access_phys

   - s390 pci ioctl fix of this series landed in 5.11 already

   - properly revoke iomem mappings (/dev/mem, pci files)"

* tag 'topic/iomem-mmap-vs-gup-2021-02-22' of git://anongit.freedesktop.org/drm/drm:
  PCI: Revoke mappings like devmem
  PCI: Also set up legacy files only after sysfs init
  sysfs: Support zapping of binary attr mmaps
  resource: Move devmem revoke code to resource framework
  /dev/mem: Only set filp->f_mapping
  PCI: Obey iomem restrictions for procfs mmap
  mm: Close race in generic_access_phys
  media: videobuf2: Move frame_vector into media subsystem
  mm/frame-vector: Use FOLL_LONGTERM
  misc/habana: Use FOLL_LONGTERM for userptr
  misc/habana: Stop using frame_vector helpers
  drm/exynos: Use FOLL_LONGTERM for g2d cmdlists
  drm/exynos: Stop using frame_vector helpers

drivers/char/mem.c

@@ -31,9 +31,6 @@
 #include <linux/uio.h>
 #include <linux/uaccess.h>
 #include <linux/security.h>
-#include <linux/pseudo_fs.h>
-#include <uapi/linux/magic.h>
-#include <linux/mount.h>
 
 #ifdef CONFIG_IA64
 # include <linux/efi.h>
@@ -829,42 +826,6 @@ static loff_t memory_lseek(struct file *file, loff_t offset, int orig)
 	return ret;
 }
 
-static struct inode *devmem_inode;
-
-#ifdef CONFIG_IO_STRICT_DEVMEM
-void revoke_devmem(struct resource *res)
-{
-	/* pairs with smp_store_release() in devmem_init_inode() */
-	struct inode *inode = smp_load_acquire(&devmem_inode);
-
-	/*
-	 * Check that the initialization has completed. Losing the race
-	 * is ok because it means drivers are claiming resources before
-	 * the fs_initcall level of init and prevent /dev/mem from
-	 * establishing mappings.
-	 */
-	if (!inode)
-		return;
-
-	/*
-	 * The expectation is that the driver has successfully marked
-	 * the resource busy by this point, so devmem_is_allowed()
-	 * should start returning false, however for performance this
-	 * does not iterate the entire resource range.
-	 */
-	if (devmem_is_allowed(PHYS_PFN(res->start)) &&
-	    devmem_is_allowed(PHYS_PFN(res->end))) {
-		/*
-		 * *cringe* iomem=relaxed says "go ahead, what's the
-		 * worst that can happen?"
-		 */
-		return;
-	}
-
-	unmap_mapping_range(inode->i_mapping, res->start, resource_size(res), 1);
-}
-#endif
-
 static int open_port(struct inode *inode, struct file *filp)
 {
 	int rc;
@@ -884,8 +845,7 @@ static int open_port(struct inode *inode, struct file *filp)
 	 * revocations when drivers want to take over a /dev/mem mapped
 	 * range.
 	 */
-	inode->i_mapping = devmem_inode->i_mapping;
-	filp->f_mapping = inode->i_mapping;
+	filp->f_mapping = iomem_get_mapping();
 
 	return 0;
 }
@@ -1017,48 +977,6 @@ static char *mem_devnode(struct device *dev, umode_t *mode)
 
 static struct class *mem_class;
 
-static int devmem_fs_init_fs_context(struct fs_context *fc)
-{
-	return init_pseudo(fc, DEVMEM_MAGIC) ? 0 : -ENOMEM;
-}
-
-static struct file_system_type devmem_fs_type = {
-	.name		= "devmem",
-	.owner		= THIS_MODULE,
-	.init_fs_context = devmem_fs_init_fs_context,
-	.kill_sb	= kill_anon_super,
-};
-
-static int devmem_init_inode(void)
-{
-	static struct vfsmount *devmem_vfs_mount;
-	static int devmem_fs_cnt;
-	struct inode *inode;
-	int rc;
-
-	rc = simple_pin_fs(&devmem_fs_type, &devmem_vfs_mount, &devmem_fs_cnt);
-	if (rc < 0) {
-		pr_err("Cannot mount /dev/mem pseudo filesystem: %d\n", rc);
-		return rc;
-	}
-
-	inode = alloc_anon_inode(devmem_vfs_mount->mnt_sb);
-	if (IS_ERR(inode)) {
-		rc = PTR_ERR(inode);
-		pr_err("Cannot allocate inode for /dev/mem: %d\n", rc);
-		simple_release_fs(&devmem_vfs_mount, &devmem_fs_cnt);
-		return rc;
-	}
-
-	/*
-	 * Publish /dev/mem initialized.
-	 * Pairs with smp_load_acquire() in revoke_devmem().
-	 */
-	smp_store_release(&devmem_inode, inode);
-
-	return 0;
-}
-
 static int __init chr_dev_init(void)
 {
 	int minor;
@@ -1080,8 +998,6 @@ static int __init chr_dev_init(void)
 		 */
 		if ((minor == DEVPORT_MINOR) && !arch_has_dev_port())
 			continue;
-		if ((minor == DEVMEM_MINOR) && devmem_init_inode() != 0)
-			continue;
 
 		device_create(mem_class, NULL, MKDEV(MEM_MAJOR, minor),
 			      NULL, devlist[minor].name);

drivers/gpu/drm/exynos/Kconfig

@@ -89,7 +89,6 @@ comment "Sub-drivers"
 config DRM_EXYNOS_G2D
 	bool "G2D"
 	depends on VIDEO_SAMSUNG_S5P_G2D=n || COMPILE_TEST
-	select FRAME_VECTOR
 	help
 	  Choose this option if you want to use Exynos G2D for DRM.
 

drivers/gpu/drm/exynos/exynos_drm_g2d.c

@@ -205,7 +205,8 @@ struct g2d_cmdlist_userptr {
 	dma_addr_t		dma_addr;
 	unsigned long		userptr;
 	unsigned long		size;
-	struct frame_vector	*vec;
+	struct page		**pages;
+	unsigned int		npages;
 	struct sg_table		*sgt;
 	atomic_t		refcount;
 	bool			in_pool;
@@ -378,7 +379,6 @@ static void g2d_userptr_put_dma_addr(struct g2d_data *g2d,
 					bool force)
 {
 	struct g2d_cmdlist_userptr *g2d_userptr = obj;
-	struct page **pages;
 
 	if (!obj)
 		return;
@@ -398,15 +398,9 @@ static void g2d_userptr_put_dma_addr(struct g2d_data *g2d,
 	dma_unmap_sgtable(to_dma_dev(g2d->drm_dev), g2d_userptr->sgt,
 			  DMA_BIDIRECTIONAL, 0);
 
-	pages = frame_vector_pages(g2d_userptr->vec);
-	if (!IS_ERR(pages)) {
-		int i;
-
-		for (i = 0; i < frame_vector_count(g2d_userptr->vec); i++)
-			set_page_dirty_lock(pages[i]);
-	}
-	put_vaddr_frames(g2d_userptr->vec);
-	frame_vector_destroy(g2d_userptr->vec);
+	unpin_user_pages_dirty_lock(g2d_userptr->pages, g2d_userptr->npages,
+				    true);
+	kvfree(g2d_userptr->pages);
 
 	if (!g2d_userptr->out_of_list)
 		list_del_init(&g2d_userptr->list);
@@ -474,35 +468,35 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct g2d_data *g2d,
 	offset = userptr & ~PAGE_MASK;
 	end = PAGE_ALIGN(userptr + size);
 	npages = (end - start) >> PAGE_SHIFT;
-	g2d_userptr->vec = frame_vector_create(npages);
-	if (!g2d_userptr->vec) {
+	g2d_userptr->pages = kvmalloc_array(npages, sizeof(*g2d_userptr->pages),
+					    GFP_KERNEL);
+	if (!g2d_userptr->pages) {
 		ret = -ENOMEM;
 		goto err_free;
 	}
 
-	ret = get_vaddr_frames(start, npages, FOLL_FORCE | FOLL_WRITE,
-		g2d_userptr->vec);
+	ret = pin_user_pages_fast(start, npages,
+				  FOLL_FORCE | FOLL_WRITE | FOLL_LONGTERM,
+				  g2d_userptr->pages);
 	if (ret != npages) {
 		DRM_DEV_ERROR(g2d->dev,
 			      "failed to get user pages from userptr.\n");
 		if (ret < 0)
-			goto err_destroy_framevec;
-		ret = -EFAULT;
-		goto err_put_framevec;
-	}
-	if (frame_vector_to_pages(g2d_userptr->vec) < 0) {
+			goto err_destroy_pages;
+		npages = ret;
 		ret = -EFAULT;
-		goto err_put_framevec;
+		goto err_unpin_pages;
 	}
+	g2d_userptr->npages = npages;
 
 	sgt = kzalloc(sizeof(*sgt), GFP_KERNEL);
 	if (!sgt) {
 		ret = -ENOMEM;
-		goto err_put_framevec;
+		goto err_unpin_pages;
 	}
 
 	ret = sg_alloc_table_from_pages(sgt,
-					frame_vector_pages(g2d_userptr->vec),
+					g2d_userptr->pages,
 					npages, offset, size, GFP_KERNEL);
 	if (ret < 0) {
 		DRM_DEV_ERROR(g2d->dev, "failed to get sgt from pages.\n");
@@ -538,11 +532,11 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct g2d_data *g2d,
 err_free_sgt:
 	kfree(sgt);
 
-err_put_framevec:
-	put_vaddr_frames(g2d_userptr->vec);
+err_unpin_pages:
+	unpin_user_pages(g2d_userptr->pages, npages);
 
-err_destroy_framevec:
-	frame_vector_destroy(g2d_userptr->vec);
+err_destroy_pages:
+	kvfree(g2d_userptr->pages);
 
 err_free:
 	kfree(g2d_userptr);

drivers/media/common/videobuf2/Kconfig

@@ -9,7 +9,6 @@ config VIDEOBUF2_V4L2
 
 config VIDEOBUF2_MEMOPS
 	tristate
-	select FRAME_VECTOR
 
 config VIDEOBUF2_DMA_CONTIG
 	tristate

drivers/media/common/videobuf2/Makefile

 # SPDX-License-Identifier: GPL-2.0
 videobuf2-common-objs := videobuf2-core.o
+videobuf2-common-objs += frame_vector.o
 
 ifeq ($(CONFIG_TRACEPOINTS),y)
   videobuf2-common-objs += vb2-trace.o

mm/frame_vector.c → drivers/media/common/videobuf2/frame_vector.c

@@ -8,6 +8,8 @@
 #include <linux/pagemap.h>
 #include <linux/sched.h>
 
+#include <media/frame_vector.h>
+
 /**
  * get_vaddr_frames() - map virtual addresses to pfns
  * @start:	starting user address
@@ -32,13 +34,12 @@
  * This function takes care of grabbing mmap_lock as necessary.
  */
 int get_vaddr_frames(unsigned long start, unsigned int nr_frames,
-		     unsigned int gup_flags, struct frame_vector *vec)
+		     struct frame_vector *vec)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	int ret = 0;
 	int err;
-	int locked;
 
 	if (nr_frames == 0)
 		return 0;
@@ -48,40 +49,26 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames,
 
 	start = untagged_addr(start);
 
-	mmap_read_lock(mm);
-	locked = 1;
-	vma = find_vma_intersection(mm, start, start + 1);
-	if (!vma) {
-		ret = -EFAULT;
-		goto out;
-	}
-
-	/*
-	 * While get_vaddr_frames() could be used for transient (kernel
-	 * controlled lifetime) pinning of memory pages all current
-	 * users establish long term (userspace controlled lifetime)
-	 * page pinning. Treat get_vaddr_frames() like
-	 * get_user_pages_longterm() and disallow it for filesystem-dax
-	 * mappings.
-	 */
-	if (vma_is_fsdax(vma)) {
-		ret = -EOPNOTSUPP;
-		goto out;
-	}
-
-	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) {
+	ret = pin_user_pages_fast(start, nr_frames,
+				  FOLL_FORCE | FOLL_WRITE | FOLL_LONGTERM,
+				  (struct page **)(vec->ptrs));
+	if (ret > 0) {
 		vec->got_ref = true;
 		vec->is_pfns = false;
-		ret = pin_user_pages_locked(start, nr_frames,
-			gup_flags, (struct page **)(vec->ptrs), &locked);
-		goto out;
+		goto out_unlocked;
 	}
 
+	mmap_read_lock(mm);
 	vec->got_ref = false;
 	vec->is_pfns = true;
+	ret = 0;
 	do {
 		unsigned long *nums = frame_vector_pfns(vec);
 
+		vma = find_vma_intersection(mm, start, start + 1);
+		if (!vma)
+			break;
+
 		while (ret < nr_frames && start + PAGE_SIZE <= vma->vm_end) {
 			err = follow_pfn(vma, start, &nums[ret]);
 			if (err) {
@@ -92,17 +79,13 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames,
 			start += PAGE_SIZE;
 			ret++;
 		}
-		/*
-		 * We stop if we have enough pages or if VMA doesn't completely
-		 * cover the tail page.
-		 */
-		if (ret >= nr_frames || start < vma->vm_end)
+		/* Bail out if VMA doesn't completely cover the tail page. */
+		if (start < vma->vm_end)
 			break;
-		vma = find_vma_intersection(mm, start, start + 1);
-	} while (vma && vma->vm_flags & (VM_IO | VM_PFNMAP));
+	} while (ret < nr_frames);
 out:
-	if (locked)
-		mmap_read_unlock(mm);
+	mmap_read_unlock(mm);
+out_unlocked:
 	if (!ret)
 		ret = -EFAULT;
 	if (ret > 0)

drivers/media/common/videobuf2/videobuf2-memops.c

@@ -40,7 +40,6 @@ struct frame_vector *vb2_create_framevec(unsigned long start,
 	unsigned long first, last;
 	unsigned long nr;
 	struct frame_vector *vec;
-	unsigned int flags = FOLL_FORCE | FOLL_WRITE;
 
 	first = start >> PAGE_SHIFT;
 	last = (start + length - 1) >> PAGE_SHIFT;
@@ -48,7 +47,7 @@ struct frame_vector *vb2_create_framevec(unsigned long start,
 	vec = frame_vector_create(nr);
 	if (!vec)
 		return ERR_PTR(-ENOMEM);
-	ret = get_vaddr_frames(start & PAGE_MASK, nr, flags, vec);
+	ret = get_vaddr_frames(start & PAGE_MASK, nr, vec);
 	if (ret < 0)
 		goto out_destroy;
 	/* We accept only complete set of PFNs */

drivers/media/platform/omap/Kconfig

@@ -12,6 +12,5 @@ config VIDEO_OMAP2_VOUT
 	depends on VIDEO_V4L2
 	select VIDEOBUF2_DMA_CONTIG
 	select OMAP2_VRFB if ARCH_OMAP2 || ARCH_OMAP3
-	select FRAME_VECTOR
 	help
 	  V4L2 Display driver support for OMAP2/3 based boards.

drivers/misc/habanalabs/Kconfig

@@ -6,7 +6,6 @@
 config HABANA_AI
 	tristate "HabanaAI accelerators (habanalabs)"
 	depends on PCI && HAS_IOMEM
-	select FRAME_VECTOR
 	select GENERIC_ALLOCATOR
 	select HWMON
 	help

drivers/misc/habanalabs/common/habanalabs.h

@@ -1089,7 +1089,8 @@ struct hl_ctx_mgr {
  * struct hl_userptr - memory mapping chunk information
  * @vm_type: type of the VM.
  * @job_node: linked-list node for hanging the object on the Job's list.
- * @vec: pointer to the frame vector.
+ * @pages: pointer to struct page array
+ * @npages: size of @pages array
  * @sgt: pointer to the scatter-gather table that holds the pages.
  * @dir: for DMA unmapping, the direction must be supplied, so save it.
  * @debugfs_list: node in debugfs list of command submissions.
@@ -1100,7 +1101,8 @@ struct hl_ctx_mgr {
 struct hl_userptr {
 	enum vm_type_t		vm_type; /* must be first */
 	struct list_head	job_node;
-	struct frame_vector	*vec;
+	struct page		**pages;
+	unsigned int		npages;
 	struct sg_table		*sgt;
 	enum dma_data_direction dir;
 	struct list_head	debugfs_list;

drivers/misc/habanalabs/common/memory.c

@@ -1436,45 +1436,40 @@ static int get_user_memory(struct hl_device *hdev, u64 addr, u64 size,
 		return -EFAULT;
 	}
 
-	userptr->vec = frame_vector_create(npages);
-	if (!userptr->vec) {
-		dev_err(hdev->dev, "Failed to create frame vector\n");
+	userptr->pages = kvmalloc_array(npages, sizeof(*userptr->pages),
+					GFP_KERNEL);
+	if (!userptr->pages)
 		return -ENOMEM;
-	}
 
-	rc = get_vaddr_frames(start, npages, FOLL_FORCE | FOLL_WRITE,
-				userptr->vec);
+	rc = pin_user_pages_fast(start, npages,
+				 FOLL_FORCE | FOLL_WRITE | FOLL_LONGTERM,
+				 userptr->pages);
 
 	if (rc != npages) {
 		dev_err(hdev->dev,
 			"Failed to map host memory, user ptr probably wrong\n");
 		if (rc < 0)
-			goto destroy_framevec;
-		rc = -EFAULT;
-		goto put_framevec;
-	}
-
-	if (frame_vector_to_pages(userptr->vec) < 0) {
-		dev_err(hdev->dev,
-			"Failed to translate frame vector to pages\n");
+			goto destroy_pages;
+		npages = rc;
 		rc = -EFAULT;
-		goto put_framevec;
+		goto put_pages;
 	}
+	userptr->npages = npages;
 
 	rc = sg_alloc_table_from_pages(userptr->sgt,
-					frame_vector_pages(userptr->vec),
-					npages, offset, size, GFP_ATOMIC);
+				       userptr->pages,
+				       npages, offset, size, GFP_ATOMIC);
 	if (rc < 0) {
 		dev_err(hdev->dev, "failed to create SG table from pages\n");
-		goto put_framevec;
+		goto put_pages;
 	}
 
 	return 0;
 
-put_framevec:
-	put_vaddr_frames(userptr->vec);
-destroy_framevec:
-	frame_vector_destroy(userptr->vec);
+put_pages:
+	unpin_user_pages(userptr->pages, npages);
+destroy_pages:
+	kvfree(userptr->pages);
 	return rc;
 }
 
@@ -1560,8 +1555,6 @@ int hl_pin_host_memory(struct hl_device *hdev, u64 addr, u64 size,
  */
 void hl_unpin_host_memory(struct hl_device *hdev, struct hl_userptr *userptr)
 {
-	struct page **pages;
-
 	hl_debugfs_remove_userptr(hdev, userptr);
 
 	if (userptr->dma_mapped)
@@ -1569,15 +1562,8 @@ void hl_unpin_host_memory(struct hl_device *hdev, struct hl_userptr *userptr)
 							userptr->sgt->nents,
 							userptr->dir);
 
-	pages = frame_vector_pages(userptr->vec);
-	if (!IS_ERR(pages)) {
-		int i;
-
-		for (i = 0; i < frame_vector_count(userptr->vec); i++)
-			set_page_dirty_lock(pages[i]);
-	}
-	put_vaddr_frames(userptr->vec);
-	frame_vector_destroy(userptr->vec);
+	unpin_user_pages_dirty_lock(userptr->pages, userptr->npages, true);
+	kvfree(userptr->pages);
 
 	list_del(&userptr->job_node);
 

drivers/pci/pci-sysfs.c

@@ -927,6 +927,9 @@ void pci_create_legacy_files(struct pci_bus *b)
 {
 	int error;
 
+	if (!sysfs_initialized)
+		return;
+
 	b->legacy_io = kcalloc(2, sizeof(struct bin_attribute),
 			       GFP_ATOMIC);
 	if (!b->legacy_io)
@@ -939,6 +942,7 @@ void pci_create_legacy_files(struct pci_bus *b)
 	b->legacy_io->read = pci_read_legacy_io;
 	b->legacy_io->write = pci_write_legacy_io;
 	b->legacy_io->mmap = pci_mmap_legacy_io;
+	b->legacy_io->mapping = iomem_get_mapping();
 	pci_adjust_legacy_attr(b, pci_mmap_io);
 	error = device_create_bin_file(&b->dev, b->legacy_io);
 	if (error)
@@ -951,6 +955,7 @@ void pci_create_legacy_files(struct pci_bus *b)
 	b->legacy_mem->size = 1024*1024;
 	b->legacy_mem->attr.mode = 0600;
 	b->legacy_mem->mmap = pci_mmap_legacy_mem;
+	b->legacy_io->mapping = iomem_get_mapping();
 	pci_adjust_legacy_attr(b, pci_mmap_mem);
 	error = device_create_bin_file(&b->dev, b->legacy_mem);
 	if (error)
@@ -1166,6 +1171,8 @@ static int pci_create_attr(struct pci_dev *pdev, int num, int write_combine)
 			res_attr->mmap = pci_mmap_resource_uc;
 		}
 	}
+	if (res_attr->mmap)
+		res_attr->mapping = iomem_get_mapping();
 	res_attr->attr.name = res_attr_name;
 	res_attr->attr.mode = 0600;
 	res_attr->size = pci_resource_len(pdev, num);
@@ -1448,6 +1455,7 @@ void pci_remove_sysfs_dev_files(struct pci_dev *pdev)
 static int __init pci_sysfs_init(void)
 {
 	struct pci_dev *pdev = NULL;
+	struct pci_bus *pbus = NULL;
 	int retval;
 
 	sysfs_initialized = 1;
@@ -1459,6 +1467,9 @@ static int __init pci_sysfs_init(void)
 		}
 	}
 
+	while ((pbus = pci_find_next_bus(pbus)))
+		pci_create_legacy_files(pbus);
+
 	return 0;
 }
 late_initcall(pci_sysfs_init);

drivers/pci/proc.c

@@ -274,6 +274,11 @@ static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma)
 		else
 			return -EINVAL;
 	}
+
+	if (dev->resource[i].flags & IORESOURCE_MEM &&
+	    iomem_is_exclusive(dev->resource[i].start))
+		return -EINVAL;
+
 	ret = pci_mmap_page_range(dev, i, vma,
 				  fpriv->mmap_state, write_combine);
 	if (ret < 0)
@@ -293,6 +298,7 @@ static int proc_bus_pci_open(struct inode *inode, struct file *file)
 	fpriv->write_combine = 0;
 
 	file->private_data = fpriv;
+	file->f_mapping = iomem_get_mapping();
 
 	return 0;
 }

fs/sysfs/file.c

@@ -170,6 +170,16 @@ static int sysfs_kf_bin_mmap(struct kernfs_open_file *of,
 	return battr->mmap(of->file, kobj, battr, vma);
 }
 
+static int sysfs_kf_bin_open(struct kernfs_open_file *of)
+{
+	struct bin_attribute *battr = of->kn->priv;
+
+	if (battr->mapping)
+		of->file->f_mapping = battr->mapping;
+
+	return 0;
+}
+
 void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr)
 {
 	struct kernfs_node *kn = kobj->sd, *tmp;
@@ -241,6 +251,7 @@ static const struct kernfs_ops sysfs_bin_kfops_mmap = {
 	.read		= sysfs_kf_bin_read,
 	.write		= sysfs_kf_bin_write,
 	.mmap		= sysfs_kf_bin_mmap,
+	.open		= sysfs_kf_bin_open,
 };
 
 int sysfs_add_file_mode_ns(struct kernfs_node *parent,

include/linux/ioport.h

@@ -334,11 +334,7 @@ static inline void irqresource_disabled(struct resource *res, u32 irq)
 	res->flags = IORESOURCE_IRQ | IORESOURCE_DISABLED | IORESOURCE_UNSET;
 }
 
-#ifdef CONFIG_IO_STRICT_DEVMEM
-void revoke_devmem(struct resource *res);
-#else
-static inline void revoke_devmem(struct resource *res) { };
-#endif
+extern struct address_space *iomem_get_mapping(void);
 
 #endif /* __ASSEMBLY__ */
 #endif	/* _LINUX_IOPORT_H */

include/linux/mm.h

@@ -593,7 +593,8 @@ struct vm_operations_struct {
 	vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf);
 
 	/* called by access_process_vm when get_user_pages() fails, typically
-	 * for use by special VMAs that can switch between memory and hardware
+	 * for use by special VMAs. See also generic_access_phys() for a generic
+	 * implementation useful for any iomem mapping.
 	 */
 	int (*access)(struct vm_area_struct *vma, unsigned long addr,
 		      void *buf, int len, int write);
@@ -1761,48 +1762,6 @@ int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc);
 int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
 			struct task_struct *task, bool bypass_rlim);
 
-/* Container for pinned pfns / pages */
-struct frame_vector {
-	unsigned int nr_allocated;	/* Number of frames we have space for */
-	unsigned int nr_frames;	/* Number of frames stored in ptrs array */
-	bool got_ref;		/* Did we pin pages by getting page ref? */
-	bool is_pfns;		/* Does array contain pages or pfns? */
-	void *ptrs[];		/* Array of pinned pfns / pages. Use
-				 * pfns_vector_pages() or pfns_vector_pfns()
-				 * for access */
-};
-
-struct frame_vector *frame_vector_create(unsigned int nr_frames);
-void frame_vector_destroy(struct frame_vector *vec);
-int get_vaddr_frames(unsigned long start, unsigned int nr_pfns,
-		     unsigned int gup_flags, struct frame_vector *vec);
-void put_vaddr_frames(struct frame_vector *vec);
-int frame_vector_to_pages(struct frame_vector *vec);
-void frame_vector_to_pfns(struct frame_vector *vec);
-
-static inline unsigned int frame_vector_count(struct frame_vector *vec)
-{
-	return vec->nr_frames;
-}
-
-static inline struct page **frame_vector_pages(struct frame_vector *vec)
-{
-	if (vec->is_pfns) {
-		int err = frame_vector_to_pages(vec);
-
-		if (err)
-			return ERR_PTR(err);
-	}
-	return (struct page **)(vec->ptrs);
-}
-
-static inline unsigned long *frame_vector_pfns(struct frame_vector *vec)
-{
-	if (!vec->is_pfns)
-		frame_vector_to_pfns(vec);
-	return (unsigned long *)(vec->ptrs);
-}
-
 struct kvec;
 int get_kernel_pages(const struct kvec *iov, int nr_pages, int write,
 			struct page **pages);

include/linux/sysfs.h

@@ -164,11 +164,13 @@ __ATTRIBUTE_GROUPS(_name)
 
 struct file;
 struct vm_area_struct;
+struct address_space;
 
 struct bin_attribute {
 	struct attribute	attr;
 	size_t			size;
 	void			*private;
+	struct address_space	*mapping;
 	ssize_t (*read)(struct file *, struct kobject *, struct bin_attribute *,
 			char *, loff_t, size_t);
 	ssize_t (*write)(struct file *, struct kobject *, struct bin_attribute *,

include/media/frame_vector.h

+// SPDX-License-Identifier: GPL-2.0
+#ifndef _MEDIA_FRAME_VECTOR_H
+#define _MEDIA_FRAME_VECTOR_H
+
+/* Container for pinned pfns / pages in frame_vector.c */
+struct frame_vector {
+	unsigned int nr_allocated;	/* Number of frames we have space for */
+	unsigned int nr_frames;	/* Number of frames stored in ptrs array */
+	bool got_ref;		/* Did we pin pages by getting page ref? */
+	bool is_pfns;		/* Does array contain pages or pfns? */
+	void *ptrs[];		/* Array of pinned pfns / pages. Use
+				 * pfns_vector_pages() or pfns_vector_pfns()
+				 * for access */
+};
+
+struct frame_vector *frame_vector_create(unsigned int nr_frames);
+void frame_vector_destroy(struct frame_vector *vec);
+int get_vaddr_frames(unsigned long start, unsigned int nr_pfns,
+		     struct frame_vector *vec);
+void put_vaddr_frames(struct frame_vector *vec);
+int frame_vector_to_pages(struct frame_vector *vec);
+void frame_vector_to_pfns(struct frame_vector *vec);
+
+static inline unsigned int frame_vector_count(struct frame_vector *vec)
+{
+	return vec->nr_frames;
+}
+
+static inline struct page **frame_vector_pages(struct frame_vector *vec)
+{
+	if (vec->is_pfns) {
+		int err = frame_vector_to_pages(vec);
+
+		if (err)
+			return ERR_PTR(err);
+	}
+	return (struct page **)(vec->ptrs);
+}
+
+static inline unsigned long *frame_vector_pfns(struct frame_vector *vec)
+{
+	if (!vec->is_pfns)
+		frame_vector_to_pfns(vec);
+	return (unsigned long *)(vec->ptrs);
+}
+
+#endif /* _MEDIA_FRAME_VECTOR_H */

include/media/videobuf2-core.h

@@ -18,6 +18,7 @@
 #include <linux/dma-buf.h>
 #include <linux/bitops.h>
 #include <media/media-request.h>
+#include <media/frame_vector.h>
 
 #define VB2_MAX_FRAME	(32)
 #define VB2_MAX_PLANES	(8)

kernel/resource.c

@@ -18,12 +18,15 @@
 #include <linux/spinlock.h>
 #include <linux/fs.h>
 #include <linux/proc_fs.h>
+#include <linux/pseudo_fs.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
 #include <linux/device.h>
 #include <linux/pfn.h>
 #include <linux/mm.h>
+#include <linux/mount.h>
 #include <linux/resource_ext.h>
+#include <uapi/linux/magic.h>
 #include <asm/io.h>
 
 
@@ -1119,6 +1122,55 @@ resource_size_t resource_alignment(struct resource *res)
 
 static DECLARE_WAIT_QUEUE_HEAD(muxed_resource_wait);
 
+static struct inode *iomem_inode;
+
+#ifdef CONFIG_IO_STRICT_DEVMEM
+static void revoke_iomem(struct resource *res)
+{
+	/* pairs with smp_store_release() in iomem_init_inode() */
+	struct inode *inode = smp_load_acquire(&iomem_inode);
+
+	/*
+	 * Check that the initialization has completed. Losing the race
+	 * is ok because it means drivers are claiming resources before
+	 * the fs_initcall level of init and prevent iomem_get_mapping users
+	 * from establishing mappings.
+	 */
+	if (!inode)
+		return;
+
+	/*
+	 * The expectation is that the driver has successfully marked
+	 * the resource busy by this point, so devmem_is_allowed()
+	 * should start returning false, however for performance this
+	 * does not iterate the entire resource range.
+	 */
+	if (devmem_is_allowed(PHYS_PFN(res->start)) &&
+	    devmem_is_allowed(PHYS_PFN(res->end))) {
+		/*
+		 * *cringe* iomem=relaxed says "go ahead, what's the
+		 * worst that can happen?"
+		 */
+		return;
+	}
+
+	unmap_mapping_range(inode->i_mapping, res->start, resource_size(res), 1);
+}
+#else
+static void revoke_iomem(struct resource *res) {}
+#endif
+
+struct address_space *iomem_get_mapping(void)
+{
+	/*
+	 * This function is only called from file open paths, hence guaranteed
+	 * that fs_initcalls have completed and no need to check for NULL. But
+	 * since revoke_iomem can be called before the initcall we still need
+	 * the barrier to appease checkers.
+	 */
+	return smp_load_acquire(&iomem_inode)->i_mapping;
+}
+
 /**
  * __request_region - create a new busy resource region
  * @parent: parent resource descriptor
@@ -1186,7 +1238,7 @@ struct resource * __request_region(struct resource *parent,
 	write_unlock(&resource_lock);
 
 	if (res && orig_parent == &iomem_resource)
-		revoke_devmem(res);
+		revoke_iomem(res);
 
 	return res;
 }
@@ -1786,4 +1838,48 @@ static int __init strict_iomem(char *str)
 	return 1;
 }
 
+static int iomem_fs_init_fs_context(struct fs_context *fc)
+{
+	return init_pseudo(fc, DEVMEM_MAGIC) ? 0 : -ENOMEM;
+}
+
+static struct file_system_type iomem_fs_type = {
+	.name		= "iomem",
+	.owner		= THIS_MODULE,
+	.init_fs_context = iomem_fs_init_fs_context,
+	.kill_sb	= kill_anon_super,
+};
+
+static int __init iomem_init_inode(void)
+{
+	static struct vfsmount *iomem_vfs_mount;
+	static int iomem_fs_cnt;
+	struct inode *inode;
+	int rc;
+
+	rc = simple_pin_fs(&iomem_fs_type, &iomem_vfs_mount, &iomem_fs_cnt);
+	if (rc < 0) {
+		pr_err("Cannot mount iomem pseudo filesystem: %d\n", rc);
+		return rc;
+	}
+
+	inode = alloc_anon_inode(iomem_vfs_mount->mnt_sb);
+	if (IS_ERR(inode)) {
+		rc = PTR_ERR(inode);
+		pr_err("Cannot allocate inode for iomem: %d\n", rc);
+		simple_release_fs(&iomem_vfs_mount, &iomem_fs_cnt);
+		return rc;
+	}
+
+	/*
+	 * Publish iomem revocation inode initialized.
+	 * Pairs with smp_load_acquire() in revoke_iomem().
+	 */
+	smp_store_release(&iomem_inode, inode);
+
+	return 0;
+}
+
+fs_initcall(iomem_init_inode);
+
 __setup("iomem=", strict_iomem);

mm/Kconfig

@@ -804,9 +804,6 @@ config DEVICE_PRIVATE
 config VMAP_PFN
 	bool
 
-config FRAME_VECTOR
-	bool
-
 config ARCH_USES_HIGH_VMA_FLAGS
 	bool
 config ARCH_HAS_PKEYS

mm/Makefile

@@ -110,7 +110,6 @@ obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o
 obj-$(CONFIG_CMA_DEBUGFS) += cma_debug.o
 obj-$(CONFIG_USERFAULTFD) += userfaultfd.o
 obj-$(CONFIG_IDLE_PAGE_TRACKING) += page_idle.o
-obj-$(CONFIG_FRAME_VECTOR) += frame_vector.o
 obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o
 obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o
 obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o

mm/memory.c

@@ -4798,28 +4798,68 @@ int follow_phys(struct vm_area_struct *vma,
 	return ret;
 }
 
+/**
+ * generic_access_phys - generic implementation for iomem mmap access
+ * @vma: the vma to access
+ * @addr: userspace addres, not relative offset within @vma
+ * @buf: buffer to read/write
+ * @len: length of transfer
+ * @write: set to FOLL_WRITE when writing, otherwise reading
+ *
+ * This is a generic implementation for &vm_operations_struct.access for an
+ * iomem mapping. This callback is used by access_process_vm() when the @vma is
+ * not page based.
+ */
 int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
 			void *buf, int len, int write)
 {
 	resource_size_t phys_addr;
 	unsigned long prot = 0;
 	void __iomem *maddr;
-	int offset = addr & (PAGE_SIZE-1);
+	pte_t *ptep, pte;
+	spinlock_t *ptl;
+	int offset = offset_in_page(addr);
+	int ret = -EINVAL;
+
+	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+		return -EINVAL;
+
+retry:
+	if (follow_pte(vma->vm_mm, addr, &ptep, &ptl))
+		return -EINVAL;
+	pte = *ptep;
+	pte_unmap_unlock(ptep, ptl);
 
-	if (follow_phys(vma, addr, write, &prot, &phys_addr))
+	prot = pgprot_val(pte_pgprot(pte));
+	phys_addr = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT;
+
+	if ((write & FOLL_WRITE) && !pte_write(pte))
 		return -EINVAL;
 
 	maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot);
 	if (!maddr)
 		return -ENOMEM;
 
+	if (follow_pte(vma->vm_mm, addr, &ptep, &ptl))
+		goto out_unmap;
+
+	if (!pte_same(pte, *ptep)) {
+		pte_unmap_unlock(ptep, ptl);
+		iounmap(maddr);
+
+		goto retry;
+	}
+
 	if (write)
 		memcpy_toio(maddr + offset, buf, len);
 	else
 		memcpy_fromio(buf, maddr + offset, len);
+	ret = len;
+	pte_unmap_unlock(ptep, ptl);
+out_unmap:
 	iounmap(maddr);
 
-	return len;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(generic_access_phys);
 #endif