fs: replace mmap hook with .mmap_prepare for simple mappings

Since commit c84bf6dd2b83 ("mm: introduce new .mmap_prepare() file
callback"), the f_op->mmap() hook has been deprecated in favour of
f_op->mmap_prepare().

This callback is invoked in the mmap() logic far earlier, so error handling
can be performed more safely without complicated and bug-prone state
unwinding required should an error arise.

This hook also avoids passing a pointer to a not-yet-correctly-established
VMA avoiding any issues with referencing this data structure.

It rather provides a pointer to the new struct vm_area_desc descriptor type
which contains all required state and allows easy setting of required
parameters without any consideration needing to be paid to locking or
reference counts.

Note that nested filesystems like overlayfs are compatible with an
.mmap_prepare() callback since commit bb666b7c2707 ("mm: add mmap_prepare()
compatibility layer for nested file systems").

In this patch we apply this change to file systems with relatively simple
mmap() hook logic - exfat, ceph, f2fs, bcachefs, zonefs, btrfs, ocfs2,
orangefs, nilfs2, romfs, ramfs and aio.

Signed-off-by: Lorenzo Stoakes <[e-mail]>
Link: https://lore.kernel.org/f528ac4[e-mail]
Acked-by: Damien Le Moal <[e-mail]>
Reviewed-by: Jan Kara <[e-mail]>
Reviewed-by: Viacheslav Dubeyko <[e-mail]>
Signed-off-by: Christian Brauner <[e-mail]>

fs/aio.c

···
 #endif
 };
 
-static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma)
+static int aio_ring_mmap_prepare(struct vm_area_desc *desc)
 {
-	vm_flags_set(vma, VM_DONTEXPAND);
-	vma->vm_ops = &aio_ring_vm_ops;
+	desc->vm_flags |= VM_DONTEXPAND;
+	desc->vm_ops = &aio_ring_vm_ops;
 	return 0;
 }
 
 static const struct file_operations aio_ring_fops = {
-	.mmap = aio_ring_mmap,
+	.mmap_prepare = aio_ring_mmap_prepare,
 };
 
 #if IS_ENABLED(CONFIG_MIGRATION)

fs/bcachefs/fs.c

···
 	.page_mkwrite   = bch2_page_mkwrite,
 };
 
-static int bch2_mmap(struct file *file, struct vm_area_struct *vma)
+static int bch2_mmap_prepare(struct vm_area_desc *desc)
 {
-	file_accessed(file);
+	file_accessed(desc->file);
 
-	vma->vm_ops = &bch_vm_ops;
+	desc->vm_ops = &bch_vm_ops;
 	return 0;
 }
 
···
 	.llseek		= bch2_llseek,
 	.read_iter	= bch2_read_iter,
 	.write_iter	= bch2_write_iter,
-	.mmap		= bch2_mmap,
+	.mmap_prepare	= bch2_mmap_prepare,
 	.get_unmapped_area = thp_get_unmapped_area,
 	.fsync		= bch2_fsync,
 	.splice_read	= filemap_splice_read,

fs/btrfs/file.c

···
 	.page_mkwrite	= btrfs_page_mkwrite,
 };
 
-static int btrfs_file_mmap(struct file	*filp, struct vm_area_struct *vma)
+static int btrfs_file_mmap_prepare(struct vm_area_desc *desc)
 {
+	struct file *filp = desc->file;
 	struct address_space *mapping = filp->f_mapping;
 
 	if (!mapping->a_ops->read_folio)
 		return -ENOEXEC;
 
 	file_accessed(filp);
-	vma->vm_ops = &btrfs_file_vm_ops;
+	desc->vm_ops = &btrfs_file_vm_ops;
 
 	return 0;
 }
···
 	.splice_read	= filemap_splice_read,
 	.write_iter	= btrfs_file_write_iter,
 	.splice_write	= iter_file_splice_write,
-	.mmap		= btrfs_file_mmap,
+	.mmap_prepare	= btrfs_file_mmap_prepare,
 	.open		= btrfs_file_open,
 	.release	= btrfs_release_file,
 	.get_unmapped_area = thp_get_unmapped_area,

fs/ceph/addr.c

···
 	.page_mkwrite	= ceph_page_mkwrite,
 };
 
-int ceph_mmap(struct file *file, struct vm_area_struct *vma)
+int ceph_mmap_prepare(struct vm_area_desc *desc)
 {
-	struct address_space *mapping = file->f_mapping;
+	struct address_space *mapping = desc->file->f_mapping;
 
 	if (!mapping->a_ops->read_folio)
 		return -ENOEXEC;
-	vma->vm_ops = &ceph_vmops;
+	desc->vm_ops = &ceph_vmops;
 	return 0;
 }
 

fs/ceph/file.c

···
 	.llseek = ceph_llseek,
 	.read_iter = ceph_read_iter,
 	.write_iter = ceph_write_iter,
-	.mmap = ceph_mmap,
+	.mmap_prepare = ceph_mmap_prepare,
 	.fsync = ceph_fsync,
 	.lock = ceph_lock,
 	.setlease = simple_nosetlease,

fs/ceph/super.h

···
 /* addr.c */
 extern const struct address_space_operations ceph_aops;
 extern const struct netfs_request_ops ceph_netfs_ops;
-extern int ceph_mmap(struct file *file, struct vm_area_struct *vma);
+int ceph_mmap_prepare(struct vm_area_desc *desc);
 extern int ceph_uninline_data(struct file *file);
 extern int ceph_pool_perm_check(struct inode *inode, int need);
 extern void ceph_pool_perm_destroy(struct ceph_mds_client* mdsc);

fs/exfat/file.c

···
 	.page_mkwrite	= exfat_page_mkwrite,
 };
 
-static int exfat_file_mmap(struct file *file, struct vm_area_struct *vma)
+static int exfat_file_mmap_prepare(struct vm_area_desc *desc)
 {
-	if (unlikely(exfat_forced_shutdown(file_inode(file)->i_sb)))
+	struct file *file = desc->file;
+
+	if (unlikely(exfat_forced_shutdown(file_inode(desc->file)->i_sb)))
 		return -EIO;
 
 	file_accessed(file);
-	vma->vm_ops = &exfat_file_vm_ops;
+	desc->vm_ops = &exfat_file_vm_ops;
 	return 0;
 }
 
···
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = exfat_compat_ioctl,
 #endif
-	.mmap		= exfat_file_mmap,
+	.mmap_prepare	= exfat_file_mmap_prepare,
 	.fsync		= exfat_file_fsync,
 	.splice_read	= exfat_splice_read,
 	.splice_write	= iter_file_splice_write,

fs/f2fs/file.c

···
 	return -EINVAL;
 }
 
-static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
+static int f2fs_file_mmap_prepare(struct vm_area_desc *desc)
 {
+	struct file *file = desc->file;
 	struct inode *inode = file_inode(file);
 
 	if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
···
 		return -EOPNOTSUPP;
 
 	file_accessed(file);
-	vma->vm_ops = &f2fs_file_vm_ops;
+	desc->vm_ops = &f2fs_file_vm_ops;
 
 	f2fs_down_read(&F2FS_I(inode)->i_sem);
 	set_inode_flag(inode, FI_MMAP_FILE);
···
 	.iopoll		= iocb_bio_iopoll,
 	.open		= f2fs_file_open,
 	.release	= f2fs_release_file,
-	.mmap		= f2fs_file_mmap,
+	.mmap_prepare	= f2fs_file_mmap_prepare,
 	.flush		= f2fs_file_flush,
 	.fsync		= f2fs_sync_file,
 	.fallocate	= f2fs_fallocate,

fs/nilfs2/file.c

···
 	.page_mkwrite	= nilfs_page_mkwrite,
 };
 
-static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma)
+static int nilfs_file_mmap_prepare(struct vm_area_desc *desc)
 {
-	file_accessed(file);
-	vma->vm_ops = &nilfs_file_vm_ops;
+	file_accessed(desc->file);
+	desc->vm_ops = &nilfs_file_vm_ops;
 	return 0;
 }
 
···
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= nilfs_compat_ioctl,
 #endif	/* CONFIG_COMPAT */
-	.mmap		= nilfs_file_mmap,
+	.mmap_prepare	= nilfs_file_mmap_prepare,
 	.open		= generic_file_open,
 	/* .release	= nilfs_release_file, */
 	.fsync		= nilfs_sync_file,

fs/ocfs2/file.c

···
  */
 const struct file_operations ocfs2_fops = {
 	.llseek		= ocfs2_file_llseek,
-	.mmap		= ocfs2_mmap,
+	.mmap_prepare	= ocfs2_mmap_prepare,
 	.fsync		= ocfs2_sync_file,
 	.release	= ocfs2_file_release,
 	.open		= ocfs2_file_open,
···
  */
 const struct file_operations ocfs2_fops_no_plocks = {
 	.llseek		= ocfs2_file_llseek,
-	.mmap		= ocfs2_mmap,
+	.mmap_prepare	= ocfs2_mmap_prepare,
 	.fsync		= ocfs2_sync_file,
 	.release	= ocfs2_file_release,
 	.open		= ocfs2_file_open,

fs/ocfs2/mmap.c

···
 	.page_mkwrite	= ocfs2_page_mkwrite,
 };
 
-int ocfs2_mmap(struct file *file, struct vm_area_struct *vma)
+int ocfs2_mmap_prepare(struct vm_area_desc *desc)
 {
+	struct file *file = desc->file;
 	int ret = 0, lock_level = 0;
 
 	ret = ocfs2_inode_lock_atime(file_inode(file),
···
 	}
 	ocfs2_inode_unlock(file_inode(file), lock_level);
 out:
-	vma->vm_ops = &ocfs2_file_vm_ops;
+	desc->vm_ops = &ocfs2_file_vm_ops;
 	return 0;
 }
 

fs/ocfs2/mmap.h

···
 #ifndef OCFS2_MMAP_H
 #define OCFS2_MMAP_H
 
-int ocfs2_mmap(struct file *file, struct vm_area_struct *vma);
+int ocfs2_mmap_prepare(struct vm_area_desc *desc);
 
 #endif  /* OCFS2_MMAP_H */

fs/orangefs/file.c

···
 /*
  * Memory map a region of a file.
  */
-static int orangefs_file_mmap(struct file *file, struct vm_area_struct *vma)
+static int orangefs_file_mmap_prepare(struct vm_area_desc *desc)
 {
+	struct file *file = desc->file;
 	int ret;
 
 	ret = orangefs_revalidate_mapping(file_inode(file));
···
 		     "orangefs_file_mmap: called on %pD\n", file);
 
 	/* set the sequential readahead hint */
-	vm_flags_mod(vma, VM_SEQ_READ, VM_RAND_READ);
+	desc->vm_flags |= VM_SEQ_READ;
+	desc->vm_flags &= ~VM_RAND_READ;
 
 	file_accessed(file);
-	vma->vm_ops = &orangefs_file_vm_ops;
+	desc->vm_ops = &orangefs_file_vm_ops;
 	return 0;
 }
 
···
 	.read_iter	= orangefs_file_read_iter,
 	.write_iter	= orangefs_file_write_iter,
 	.lock		= orangefs_lock,
-	.mmap		= orangefs_file_mmap,
+	.mmap_prepare	= orangefs_file_mmap_prepare,
 	.open		= generic_file_open,
 	.splice_read    = orangefs_file_splice_read,
 	.splice_write   = iter_file_splice_write,

fs/ramfs/file-nommu.c

···
 						   unsigned long len,
 						   unsigned long pgoff,
 						   unsigned long flags);
-static int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma);
+static int ramfs_nommu_mmap_prepare(struct vm_area_desc *desc);
 
 static unsigned ramfs_mmap_capabilities(struct file *file)
 {
···
 
 const struct file_operations ramfs_file_operations = {
 	.mmap_capabilities	= ramfs_mmap_capabilities,
-	.mmap			= ramfs_nommu_mmap,
+	.mmap_prepare		= ramfs_nommu_mmap_prepare,
 	.get_unmapped_area	= ramfs_nommu_get_unmapped_area,
 	.read_iter		= generic_file_read_iter,
 	.write_iter		= generic_file_write_iter,
···
 /*
  * set up a mapping for shared memory segments
  */
-static int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma)
+static int ramfs_nommu_mmap_prepare(struct vm_area_desc *desc)
 {
-	if (!is_nommu_shared_mapping(vma->vm_flags))
+	if (!is_nommu_shared_mapping(desc->vm_flags))
 		return -ENOSYS;
 
-	file_accessed(file);
-	vma->vm_ops = &generic_file_vm_ops;
+	file_accessed(desc->file);
+	desc->vm_ops = &generic_file_vm_ops;
 	return 0;
 }

fs/romfs/mmap-nommu.c

···
  * permit a R/O mapping to be made directly through onto an MTD device if
  * possible
  */
-static int romfs_mmap(struct file *file, struct vm_area_struct *vma)
+static int romfs_mmap_prepare(struct vm_area_desc *desc)
 {
-	return is_nommu_shared_mapping(vma->vm_flags) ? 0 : -ENOSYS;
+	return is_nommu_shared_mapping(desc->vm_flags) ? 0 : -ENOSYS;
 }
 
 static unsigned romfs_mmap_capabilities(struct file *file)
···
 	.llseek			= generic_file_llseek,
 	.read_iter		= generic_file_read_iter,
 	.splice_read		= filemap_splice_read,
-	.mmap			= romfs_mmap,
+	.mmap_prepare		= romfs_mmap_prepare,
 	.get_unmapped_area	= romfs_get_unmapped_area,
 	.mmap_capabilities	= romfs_mmap_capabilities,
 };

fs/zonefs/file.c

···
 	.page_mkwrite	= zonefs_filemap_page_mkwrite,
 };
 
-static int zonefs_file_mmap(struct file *file, struct vm_area_struct *vma)
+static int zonefs_file_mmap_prepare(struct vm_area_desc *desc)
 {
+	struct file *file = desc->file;
+
 	/*
 	 * Conventional zones accept random writes, so their files can support
 	 * shared writable mappings. For sequential zone files, only read
···
 	 * ordering between msync() and page cache writeback.
 	 */
 	if (zonefs_inode_is_seq(file_inode(file)) &&
-	    (vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
+	    (desc->vm_flags & VM_SHARED) && (desc->vm_flags & VM_MAYWRITE))
 		return -EINVAL;
 
 	file_accessed(file);
-	vma->vm_ops = &zonefs_file_vm_ops;
+	desc->vm_ops = &zonefs_file_vm_ops;
 
 	return 0;
 }
···
 	.open		= zonefs_file_open,
 	.release	= zonefs_file_release,
 	.fsync		= zonefs_file_fsync,
-	.mmap		= zonefs_file_mmap,
+	.mmap_prepare	= zonefs_file_mmap_prepare,
 	.llseek		= zonefs_file_llseek,
 	.read_iter	= zonefs_file_read_iter,
 	.write_iter	= zonefs_file_write_iter,