Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs pile #3 from Al Viro:
 "Assorted fixes and patches from the last cycle"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  [regression] chunk lost from bd9b51
  vfs: make mounts and mountstats honor root dir like mountinfo does
  vfs: cleanup show_mountinfo
  init: fix read-write root mount
  unfuck binfmt_misc.c (broken by commit e6084d4)
  vm_area_operations: kill ->migrate()
  new helper: iter_is_iovec()
  move_extent_per_page(): get rid of unused w_flags
  lustre: get rid of playing with ->fs
  btrfs: filp_open() returns ERR_PTR() on failure, not NULL...

drivers/staging/lustre/lustre/include/linux/lustre_compat25.h

@@ -42,28 +42,6 @@
 
 #include "lustre_patchless_compat.h"
 
-# define LOCK_FS_STRUCT(fs)	spin_lock(&(fs)->lock)
-# define UNLOCK_FS_STRUCT(fs)	spin_unlock(&(fs)->lock)
-
-static inline void ll_set_fs_pwd(struct fs_struct *fs, struct vfsmount *mnt,
-				 struct dentry *dentry)
-{
-	struct path path;
-	struct path old_pwd;
-
-	path.mnt = mnt;
-	path.dentry = dentry;
-	LOCK_FS_STRUCT(fs);
-	old_pwd = fs->pwd;
-	path_get(&path);
-	fs->pwd = path;
-	UNLOCK_FS_STRUCT(fs);
-
-	if (old_pwd.dentry)
-		path_put(&old_pwd);
-}
-
-
 /*
  * set ATTR_BLOCKS to a high value to avoid any risk of collision with other
  * ATTR_* attributes (see bug 13828)
@@ -110,8 +88,6 @@ static inline void ll_set_fs_pwd(struct fs_struct *fs, struct vfsmount *mnt,
 #define cfs_bio_io_error(a, b)   bio_io_error((a))
 #define cfs_bio_endio(a, b, c)    bio_endio((a), (c))
 
-#define cfs_fs_pwd(fs)       ((fs)->pwd.dentry)
-#define cfs_fs_mnt(fs)       ((fs)->pwd.mnt)
 #define cfs_path_put(nd)     path_put(&(nd)->path)
 
 

drivers/staging/lustre/lustre/llite/dir.c

@@ -661,7 +661,7 @@ int ll_dir_setdirstripe(struct inode *dir, struct lmv_user_md *lump,
 	int mode;
 	int err;
 
-	mode = (0755 & (S_IRWXUGO|S_ISVTX) & ~current->fs->umask) | S_IFDIR;
+	mode = (0755 & ~current_umask()) | S_IFDIR;
 	op_data = ll_prep_md_op_data(NULL, dir, NULL, filename,
 				     strlen(filename), mode, LUSTRE_OPC_MKDIR,
 				     lump);

drivers/staging/lustre/lustre/llite/llite_lib.c

@@ -2372,21 +2372,6 @@ char *ll_get_fsname(struct super_block *sb, char *buf, int buflen)
 	return buf;
 }
 
-static char *ll_d_path(struct dentry *dentry, char *buf, int bufsize)
-{
-	char *path = NULL;
-
-	struct path p;
-
-	p.dentry = dentry;
-	p.mnt = current->fs->root.mnt;
-	path_get(&p);
-	path = d_path(&p, buf, bufsize);
-	path_put(&p);
-
-	return path;
-}
-
 void ll_dirty_page_discard_warn(struct page *page, int ioret)
 {
 	char *buf, *path = NULL;
@@ -2398,7 +2383,7 @@ void ll_dirty_page_discard_warn(struct page *page, int ioret)
 	if (buf != NULL) {
 		dentry = d_find_alias(page->mapping->host);
 		if (dentry != NULL)
-			path = ll_d_path(dentry, buf, PAGE_SIZE);
+			path = dentry_path_raw(dentry, buf, PAGE_SIZE);
 	}
 
 	CDEBUG(D_WARNING,

fs/binfmt_misc.c

@@ -254,6 +254,7 @@ static char *scanarg(char *s, char del)
 				return NULL;
 		}
 	}
+	s[-1] ='\0';
 	return s;
 }
 
@@ -378,8 +379,7 @@ static Node *create_entry(const char __user *buffer, size_t count)
 		p = scanarg(p, del);
 		if (!p)
 			goto einval;
-		p[-1] = '\0';
+		if (!e->magic[0])
-		if (p == e->magic)
 			goto einval;
 		if (USE_DEBUG)
 			print_hex_dump_bytes(
@@ -391,8 +391,7 @@ static Node *create_entry(const char __user *buffer, size_t count)
 		p = scanarg(p, del);
 		if (!p)
 			goto einval;
-		p[-1] = '\0';
+		if (!e->mask[0]) {
-		if (p == e->mask) {
 			e->mask = NULL;
 			pr_debug("register:  mask[raw]: none\n");
 		} else if (USE_DEBUG)

fs/btrfs/volumes.c

@@ -1485,7 +1485,7 @@ static void update_dev_time(char *path_name)
 	struct file *filp;
 
 	filp = filp_open(path_name, O_RDWR, 0);
-	if (!filp)
+	if (IS_ERR(filp))
 		return;
 	file_update_time(filp);
 	filp_close(filp, NULL);

fs/ext4/move_extent.c

@@ -267,7 +267,6 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
 	handle_t *handle;
 	ext4_lblk_t orig_blk_offset, donor_blk_offset;
 	unsigned long blocksize = orig_inode->i_sb->s_blocksize;
-	unsigned int w_flags = 0;
 	unsigned int tmp_data_size, data_size, replaced_size;
 	int err2, jblocks, retries = 0;
 	int replaced_count = 0;
@@ -288,9 +287,6 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
 		return 0;
 	}
 
-	if (segment_eq(get_fs(), KERNEL_DS))
-		w_flags |= AOP_FLAG_UNINTERRUPTIBLE;
-
 	orig_blk_offset = orig_page_offset * blocks_per_page +
 		data_offset_in_page;
 

fs/kernfs/file.c

@@ -448,27 +448,6 @@ static struct mempolicy *kernfs_vma_get_policy(struct vm_area_struct *vma,
 	return pol;
 }
 
-static int kernfs_vma_migrate(struct vm_area_struct *vma,
-			      const nodemask_t *from, const nodemask_t *to,
-			      unsigned long flags)
-{
-	struct file *file = vma->vm_file;
-	struct kernfs_open_file *of = kernfs_of(file);
-	int ret;
-
-	if (!of->vm_ops)
-		return 0;
-
-	if (!kernfs_get_active(of->kn))
-		return 0;
-
-	ret = 0;
-	if (of->vm_ops->migrate)
-		ret = of->vm_ops->migrate(vma, from, to, flags);
-
-	kernfs_put_active(of->kn);
-	return ret;
-}
 #endif
 
 static const struct vm_operations_struct kernfs_vm_ops = {
@@ -479,7 +458,6 @@ static const struct vm_operations_struct kernfs_vm_ops = {
 #ifdef CONFIG_NUMA
 	.set_policy	= kernfs_vma_set_policy,
 	.get_policy	= kernfs_vma_get_policy,
-	.migrate	= kernfs_vma_migrate,
 #endif
 };
 

fs/proc_namespace.c

@@ -91,6 +91,7 @@ static void show_type(struct seq_file *m, struct super_block *sb)
 
 static int show_vfsmnt(struct seq_file *m, struct vfsmount *mnt)
 {
+	struct proc_mounts *p = proc_mounts(m);
 	struct mount *r = real_mount(mnt);
 	int err = 0;
 	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
@@ -104,7 +105,10 @@ static int show_vfsmnt(struct seq_file *m, struct vfsmount *mnt)
 		mangle(m, r->mnt_devname ? r->mnt_devname : "none");
 	}
 	seq_putc(m, ' ');
-	seq_path(m, &mnt_path, " \t\n\\");
+	/* mountpoints outside of chroot jail will give SEQ_SKIP on this */
+	err = seq_path_root(m, &mnt_path, &p->root, " \t\n\\");
+	if (err)
+		goto out;
 	seq_putc(m, ' ');
 	show_type(m, sb);
 	seq_puts(m, __mnt_is_readonly(mnt) ? " ro" : " rw");
@@ -125,7 +129,6 @@ static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt)
 	struct mount *r = real_mount(mnt);
 	struct super_block *sb = mnt->mnt_sb;
 	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
-	struct path root = p->root;
 	int err = 0;
 
 	seq_printf(m, "%i %i %u:%u ", r->mnt_id, r->mnt_parent->mnt_id,
@@ -139,7 +142,7 @@ static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt)
 	seq_putc(m, ' ');
 
 	/* mountpoints outside of chroot jail will give SEQ_SKIP on this */
-	err = seq_path_root(m, &mnt_path, &root, " \t\n\\");
+	err = seq_path_root(m, &mnt_path, &p->root, " \t\n\\");
 	if (err)
 		goto out;
 
@@ -182,6 +185,7 @@ static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt)
 
 static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt)
 {
+	struct proc_mounts *p = proc_mounts(m);
 	struct mount *r = real_mount(mnt);
 	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
 	struct super_block *sb = mnt_path.dentry->d_sb;
@@ -201,7 +205,10 @@ static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt)
 
 	/* mount point */
 	seq_puts(m, " mounted on ");
-	seq_path(m, &mnt_path, " \t\n\\");
+	/* mountpoints outside of chroot jail will give SEQ_SKIP on this */
+	err = seq_path_root(m, &mnt_path, &p->root, " \t\n\\");
+	if (err)
+		goto out;
 	seq_putc(m, ' ');
 
 	/* file system type */
@@ -216,6 +223,7 @@ static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt)
 	}
 
 	seq_putc(m, '\n');
+out:
 	return err;
 }
 

include/linux/migrate.h

@@ -36,9 +36,6 @@ extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free,
 
 extern int migrate_prep(void);
 extern int migrate_prep_local(void);
-extern int migrate_vmas(struct mm_struct *mm,
-		const nodemask_t *from, const nodemask_t *to,
-		unsigned long flags);
 extern void migrate_page_copy(struct page *newpage, struct page *page);
 extern int migrate_huge_page_move_mapping(struct address_space *mapping,
 				  struct page *newpage, struct page *page);
@@ -57,13 +54,6 @@ static inline int migrate_pages(struct list_head *l, new_page_t new,
 static inline int migrate_prep(void) { return -ENOSYS; }
 static inline int migrate_prep_local(void) { return -ENOSYS; }
 
-static inline int migrate_vmas(struct mm_struct *mm,
-		const nodemask_t *from, const nodemask_t *to,
-		unsigned long flags)
-{
-	return -ENOSYS;
-}
-
 static inline void migrate_page_copy(struct page *newpage,
 				     struct page *page) {}
 

include/linux/mm.h

@@ -286,8 +286,6 @@ struct vm_operations_struct {
 	 */
 	struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
 					unsigned long addr);
-	int (*migrate)(struct vm_area_struct *vma, const nodemask_t *from,
-		const nodemask_t *to, unsigned long flags);
 #endif
 	/* called by sys_remap_file_pages() to populate non-linear mapping */
 	int (*remap_pages)(struct vm_area_struct *vma, unsigned long addr,

include/linux/uio.h

@@ -101,6 +101,11 @@ static inline size_t iov_iter_count(struct iov_iter *i)
 	return i->count;
 }
 
+static inline bool iter_is_iovec(struct iov_iter *i)
+{
+	return !(i->type & (ITER_BVEC | ITER_KVEC));
+}
+
 /*
  * Cap the iov_iter by given limit; note that the second argument is
  * *not* the new size - it's upper limit for such.  Passing it a value

init/do_mounts.c

@@ -395,8 +395,6 @@ void __init mount_block_root(char *name, int flags)
 			case 0:
 				goto out;
 			case -EACCES:
-				flags |= MS_RDONLY;
-				goto retry;
 			case -EINVAL:
 				continue;
 		}
@@ -419,6 +417,10 @@ void __init mount_block_root(char *name, int flags)
 #endif
 		panic("VFS: Unable to mount root fs on %s", b);
 	}
+	if (!(flags & MS_RDONLY)) {
+		flags |= MS_RDONLY;
+		goto retry;
+	}
 
 	printk("List of all partitions:\n");
 	printk_all_partitions();

mm/filemap.c

@@ -2464,7 +2464,7 @@ ssize_t generic_perform_write(struct file *file,
 	/*
 	 * Copies from kernel address space cannot fail (NFSD is a big user).
 	 */
-	if (segment_eq(get_fs(), KERNEL_DS))
+	if (!iter_is_iovec(i))
 		flags |= AOP_FLAG_UNINTERRUPTIBLE;
 
 	do {

mm/mempolicy.c

@@ -1041,10 +1041,6 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 
 	down_read(&mm->mmap_sem);
 
-	err = migrate_vmas(mm, from, to, flags);
-	if (err)
-		goto out;
-
 	/*
 	 * Find a 'source' bit set in 'tmp' whose corresponding 'dest'
 	 * bit in 'to' is not also set in 'tmp'.  Clear the found 'source'
@@ -1124,7 +1120,6 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 		if (err < 0)
 			break;
 	}
-out:
 	up_read(&mm->mmap_sem);
 	if (err < 0)
 		return err;

mm/migrate.c

@@ -1536,27 +1536,6 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
 	return err;
 }
 
-/*
- * Call migration functions in the vma_ops that may prepare
- * memory in a vm for migration. migration functions may perform
- * the migration for vmas that do not have an underlying page struct.
- */
-int migrate_vmas(struct mm_struct *mm, const nodemask_t *to,
-	const nodemask_t *from, unsigned long flags)
-{
- 	struct vm_area_struct *vma;
- 	int err = 0;
-
-	for (vma = mm->mmap; vma && !err; vma = vma->vm_next) {
- 		if (vma->vm_ops && vma->vm_ops->migrate) {
- 			err = vma->vm_ops->migrate(vma, to, from, flags);
- 			if (err)
- 				break;
- 		}
- 	}
- 	return err;
-}
-
 #ifdef CONFIG_NUMA_BALANCING
 /*
  * Returns true if this is a safe migration target node for misplaced NUMA

mm/shmem.c

@@ -1536,7 +1536,7 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	 * holes of a sparse file, we actually need to allocate those pages,
 	 * and even mark them dirty, so it cannot exceed the max_blocks limit.
 	 */
-	if (segment_eq(get_fs(), KERNEL_DS))
+	if (!iter_is_iovec(to))
 		sgp = SGP_DIRTY;
 
 	index = *ppos >> PAGE_CACHE_SHIFT;

net/socket.c

@@ -372,7 +372,6 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
 	path.mnt = mntget(sock_mnt);
 
 	d_instantiate(path.dentry, SOCK_INODE(sock));
-	SOCK_INODE(sock)->i_fop = &socket_file_ops;
 
 	file = alloc_file(&path, FMODE_READ | FMODE_WRITE,
 		  &socket_file_ops);