Merge branch 'vfs.all' of https://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs.git

14 files changed, 57 insertions, 132 deletions

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 8808ee76e73c..5a725a0cd35f 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -66,7 +66,7 @@ struct block_device {
 	int			bd_holders;
 	struct kobject		*bd_holder_dir;
 
-	atomic_t		bd_fsfreeze_count; /* number of freeze requests */
+	atomic_t		bd_fsfreeze_count; /* >0 freeze requests, <0 freeze deniers */
 	struct mutex		bd_fsfreeze_mutex; /* serialize freeze/thaw */
 
 	struct partition_meta_info *bd_meta_info;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 9213a5716f95..dbb549cdfb77 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -126,8 +126,6 @@ struct blk_integrity {
 	unsigned char				pi_tuple_size;
 };
 
-typedef unsigned int __bitwise blk_mode_t;
-
 /* open for reading */
 #define BLK_OPEN_READ		((__force blk_mode_t)(1 << 0))
 /* open for writing */
@@ -1771,13 +1769,6 @@ struct blk_holder_ops {
 };
 
 /*
- * For filesystems using @fs_holder_ops, the @holder argument passed to
- * helpers used to open and claim block devices via
- * bd_prepare_to_claim() must point to a superblock.
- */
-extern const struct blk_holder_ops fs_holder_ops;
-
-/*
  * Return the correct open flags for blkdev_get_by_* for super block flags
  * as stored in sb->s_flags.
  */
@@ -1837,7 +1828,10 @@ static inline int early_lookup_bdev(const char *pathname, dev_t *dev)
 
 int bdev_freeze(struct block_device *bdev);
 int bdev_thaw(struct block_device *bdev);
+int bdev_deny_freeze(struct block_device *bdev);
+void bdev_allow_freeze(struct block_device *bdev);
 void bdev_fput(struct file *bdev_file);
+void bdev_yield_claim(struct file *bdev_file);
 
 struct io_comp_batch {
 	struct rq_list req_list;
diff --git a/include/linux/efs_vh.h b/include/linux/efs_vh.h
deleted file mode 100644
index 206c5270f7b8..000000000000
--- a/include/linux/efs_vh.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * efs_vh.h
- *
- * Copyright (c) 1999 Al Smith
- *
- * Portions derived from IRIX header files (c) 1985 MIPS Computer Systems, Inc.
- */
-
-#ifndef __EFS_VH_H__
-#define __EFS_VH_H__
-
-#define VHMAGIC		0xbe5a941	/* volume header magic number */
-#define NPARTAB		16		/* 16 unix partitions */
-#define NVDIR		15		/* max of 15 directory entries */
-#define BFNAMESIZE	16		/* max 16 chars in boot file name */
-#define VDNAMESIZE	8
-
-struct volume_directory {
-	char	vd_name[VDNAMESIZE];	/* name */
-	__be32	vd_lbn;			/* logical block number */
-	__be32	vd_nbytes;		/* file length in bytes */
-};
-
-struct partition_table {	/* one per logical partition */
-	__be32	pt_nblks;	/* # of logical blks in partition */
-	__be32	pt_firstlbn;	/* first lbn of partition */
-	__be32	pt_type;	/* use of partition */
-};
-
-struct volume_header {
-	__be32	vh_magic;			/* identifies volume header */
-	__be16	vh_rootpt;			/* root partition number */
-	__be16	vh_swappt;			/* swap partition number */
-	char	vh_bootfile[BFNAMESIZE];	/* name of file to boot */
-	char	pad[48];			/* device param space */
-	struct volume_directory vh_vd[NVDIR];	/* other vol hdr contents */
-	struct partition_table  vh_pt[NPARTAB];	/* device partition layout */
-	__be32	vh_csum;			/* volume header checksum */
-	__be32	vh_fill;			/* fill out to 512 bytes */
-};
-
-/* partition type sysv is used for EFS format CD-ROM partitions */
-#define SGI_SYSV	0x05
-#define SGI_EFS		0x07
-#define IS_EFS(x)	(((x) == SGI_EFS) || ((x) == SGI_SYSV))
-
-struct pt_types {
-	int	pt_type;
-	char	*pt_name;
-};
-
-#endif /* __EFS_VH_H__ */
-
diff --git a/include/linux/fs.h b/include/linux/fs.h
index d10897b3a1e3..30e0f54d8828 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1916,8 +1916,6 @@ struct dir_context {
 struct io_uring_cmd;
 struct offset_ctx;
 
-typedef unsigned int __bitwise fop_flags_t;
-
 struct file_operations {
 	struct module *owner;
 	fop_flags_t fop_flags;
@@ -2002,7 +2000,7 @@ struct inode_operations {
 	int (*readlink) (struct dentry *, char __user *,int);
 
 	int (*create) (struct mnt_idmap *, struct inode *,struct dentry *,
-		       umode_t, bool);
+		       umode_t);
 	int (*link) (struct dentry *,struct inode *,struct dentry *);
 	int (*unlink) (struct inode *,struct dentry *);
 	int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *,
diff --git a/include/linux/fs/super.h b/include/linux/fs/super.h
index 405612678115..733d439f01ed 100644
--- a/include/linux/fs/super.h
+++ b/include/linux/fs/super.h
@@ -237,4 +237,12 @@ int thaw_super(struct super_block *super, enum freeze_holder who,
 
 int sb_init_dio_done_wq(struct super_block *sb);
 
+struct file;
+struct file *fs_bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
+				      struct super_block *sb);
+struct file *fs_bdev_file_open_by_path(const char *path, blk_mode_t mode,
+				       void *holder, struct super_block *sb);
+void fs_bdev_unregister(struct file *bdev_file, struct super_block *sb);
+void fs_bdev_file_release(struct file *bdev_file, struct super_block *sb);
+
 #endif /* _LINUX_FS_SUPER_H */
diff --git a/include/linux/fs/super_types.h b/include/linux/fs/super_types.h
index ef7941e9dc79..c8172558750f 100644
--- a/include/linux/fs/super_types.h
+++ b/include/linux/fs/super_types.h
@@ -30,6 +30,7 @@ struct mount;
 struct mtd_info;
 struct quotactl_ops;
 struct shrinker;
+struct super_dev;
 struct unicode_map;
 struct user_namespace;
 struct workqueue_struct;
@@ -132,6 +133,7 @@ struct super_operations {
 struct super_block {
 	struct list_head			s_list;		/* Keep this first */
 	dev_t					s_dev;		/* search index; _not_ kdev_t */
+	struct super_dev			*s_super_dev;	/* sget_fc()'s device table claim */
 	unsigned char				s_blocksize_bits;
 	unsigned long				s_blocksize;
 	loff_t					s_maxbytes;	/* Max file size */
@@ -145,7 +147,7 @@ struct super_block {
 	unsigned long				s_magic;
 	struct dentry				*s_root;
 	struct rw_semaphore			s_umount;
-	int					s_count;
+	refcount_t				s_passive;
 	atomic_t				s_active;
 #ifdef CONFIG_SECURITY
 	void					*s_security;
diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h
index 0070764b790a..97eef8d3863d 100644
--- a/include/linux/fs_struct.h
+++ b/include/linux/fs_struct.h
@@ -6,6 +6,7 @@
 #include <linux/path.h>
 #include <linux/spinlock.h>
 #include <linux/seqlock.h>
+#include <linux/vfsdebug.h>
 
 struct fs_struct {
 	int users;
@@ -16,6 +17,7 @@ struct fs_struct {
 } __randomize_layout;
 
 extern struct kmem_cache *fs_cachep;
+extern struct fs_struct *userspace_init_fs;
 
 extern void exit_fs(struct task_struct *);
 extern void set_fs_root(struct fs_struct *, const struct path *);
@@ -40,6 +42,8 @@ static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd)
 	read_sequnlock_excl(&fs->seq);
 }
 
+struct fs_struct *switch_fs_struct(struct fs_struct *new_fs);
+
 extern bool current_chrooted(void);
 
 static inline int current_umask(void)
@@ -47,4 +51,34 @@ static inline int current_umask(void)
 	return current->fs->umask;
 }
 
+/*
+ * Temporarily use userspace_init_fs for path resolution in kthreads.
+ * Callers should use scoped_with_init_fs() which automatically
+ * restores the original fs_struct at scope exit.
+ */
+static inline struct fs_struct *__override_init_fs(void)
+{
+	struct fs_struct *old_fs;
+
+	old_fs = current->fs;
+	WRITE_ONCE(current->fs, userspace_init_fs);
+	return old_fs;
+}
+
+static inline void __revert_init_fs(struct fs_struct *old_fs)
+{
+	VFS_WARN_ON_ONCE(current->fs != userspace_init_fs);
+	WRITE_ONCE(current->fs, old_fs);
+}
+
+DEFINE_CLASS(__override_init_fs,
+	     struct fs_struct *,
+	     __revert_init_fs(_T),
+	     __override_init_fs(), void)
+
+#define scoped_with_init_fs() \
+	scoped_class(__override_init_fs, __UNIQUE_ID(label))
+
+void __init init_userspace_fs(void);
+
 #endif /* _LINUX_FS_STRUCT_H */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index a6cb241ea00c..61536be773f5 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -24,6 +24,7 @@
 
 extern struct files_struct init_files;
 extern struct fs_struct init_fs;
+extern struct fs_struct *userspace_init_fs;
 extern struct nsproxy init_nsproxy;
 
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
diff --git a/include/linux/net.h b/include/linux/net.h
index f268f395ce47..fdcf9956805c 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -285,6 +285,7 @@ int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags);
 struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname);
 struct socket *sockfd_lookup(int fd, int *err);
 struct socket *sock_from_file(struct file *file);
+int sock_read_xattr(struct socket *sock, const char *name, void *value, size_t size);
 #define		     sockfd_put(sock) fput(sock->file)
 int net_ratelimit(void);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 373bcc0598d1..1e4136c2b2a3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1191,6 +1191,7 @@ struct task_struct {
 	unsigned long			last_switch_time;
 #endif
 	/* Filesystem information: */
+	struct fs_struct		*real_fs;
 	struct fs_struct		*fs;
 
 	/* Open file information: */
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 41ed884cffc9..e0c1ca8c6a18 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -31,6 +31,7 @@ struct kernel_clone_args {
 	u32 io_thread:1;
 	u32 user_worker:1;
 	u32 no_files:1;
+	u32 umh:1;
 	unsigned long stack;
 	unsigned long stack_size;
 	unsigned long tls;
diff --git a/include/linux/types.h b/include/linux/types.h
index 93166b0b0617..bc5dda2a3d86 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -163,6 +163,8 @@ typedef u32 dma_addr_t;
 typedef unsigned int __bitwise gfp_t;
 typedef unsigned int __bitwise slab_flags_t;
 typedef unsigned int __bitwise fmode_t;
+typedef unsigned int __bitwise blk_mode_t;
+typedef unsigned int __bitwise fop_flags_t;
 
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
 typedef u64 phys_addr_t;
diff --git a/include/uapi/asm-generic/errno.h b/include/uapi/asm-generic/errno.h
index bd78e69e0a43..c84ebf89c8b6 100644
--- a/include/uapi/asm-generic/errno.h
+++ b/include/uapi/asm-generic/errno.h
@@ -76,7 +76,7 @@
 #define	ENOPROTOOPT	92	/* Protocol not available */
 #define	EPROTONOSUPPORT	93	/* Protocol not supported */
 #define	ESOCKTNOSUPPORT	94	/* Socket type not supported */
-#define	EOPNOTSUPP	95	/* Operation not supported on transport endpoint */
+#define	EOPNOTSUPP	95	/* Operation not supported */
 #define	EPFNOSUPPORT	96	/* Protocol family not supported */
 #define	EAFNOSUPPORT	97	/* Address family not supported by protocol */
 #define	EADDRINUSE	98	/* Address already in use */
diff --git a/include/uapi/linux/efs_fs_sb.h b/include/uapi/linux/efs_fs_sb.h
deleted file mode 100644
index 6bad29a10faa..000000000000
--- a/include/uapi/linux/efs_fs_sb.h
+++ /dev/null
@@ -1,63 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * efs_fs_sb.h
- *
- * Copyright (c) 1999 Al Smith
- *
- * Portions derived from IRIX header files (c) 1988 Silicon Graphics
- */
-
-#ifndef __EFS_FS_SB_H__
-#define __EFS_FS_SB_H__
-
-#include <linux/types.h>
-#include <linux/magic.h>
-
-/* EFS superblock magic numbers */
-#define EFS_MAGIC	0x072959
-#define EFS_NEWMAGIC	0x07295a
-
-#define IS_EFS_MAGIC(x)	((x == EFS_MAGIC) || (x == EFS_NEWMAGIC))
-
-#define EFS_SUPER		1
-#define EFS_ROOTINODE		2
-
-/* efs superblock on disk */
-struct efs_super {
-	__be32		fs_size;        /* size of filesystem, in sectors */
-	__be32		fs_firstcg;     /* bb offset to first cg */
-	__be32		fs_cgfsize;     /* size of cylinder group in bb's */
-	__be16		fs_cgisize;     /* bb's of inodes per cylinder group */
-	__be16		fs_sectors;     /* sectors per track */
-	__be16		fs_heads;       /* heads per cylinder */
-	__be16		fs_ncg;         /* # of cylinder groups in filesystem */
-	__be16		fs_dirty;       /* fs needs to be fsck'd */
-	__be32		fs_time;        /* last super-block update */
-	__be32		fs_magic;       /* magic number */
-	char		fs_fname[6];    /* file system name */
-	char		fs_fpack[6];    /* file system pack name */
-	__be32		fs_bmsize;      /* size of bitmap in bytes */
-	__be32		fs_tfree;       /* total free data blocks */
-	__be32		fs_tinode;      /* total free inodes */
-	__be32		fs_bmblock;     /* bitmap location. */
-	__be32		fs_replsb;      /* Location of replicated superblock. */
-	__be32		fs_lastialloc;  /* last allocated inode */
-	char		fs_spare[20];   /* space for expansion - MUST BE ZERO */
-	__be32		fs_checksum;    /* checksum of volume portion of fs */
-};
-
-/* efs superblock information in memory */
-struct efs_sb_info {
-	__u32	fs_magic;	/* superblock magic number */
-	__u32	fs_start;	/* first block of filesystem */
-	__u32	first_block;	/* first data block in filesystem */
-	__u32	total_blocks;	/* total number of blocks in filesystem */
-	__u32	group_size;	/* # of blocks a group consists of */ 
-	__u32	data_free;	/* # of free data blocks */
-	__u32	inode_free;	/* # of free inodes */
-	__u16	inode_blocks;	/* # of blocks used for inodes in every grp */
-	__u16	total_groups;	/* # of groups */
-};
-
-#endif /* __EFS_FS_SB_H__ */
-