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

# Conflicts:
#	fs/smb/server/smb2pdu.c
#	fs/smb/server/vfs.c
#	fs/smb/server/vfs.h

10 files changed, 74 insertions, 107 deletions

diff --git a/Documentation/filesystems/befs.rst b/Documentation/filesystems/befs.rst
index a22f603b2938..c1dbfe9c95d2 100644
--- a/Documentation/filesystems/befs.rst
+++ b/Documentation/filesystems/befs.rst
@@ -44,8 +44,8 @@ implementation.
 Which is it, BFS or BEFS?
 =========================
 Be, Inc said, "BeOS Filesystem is officially called BFS, not BeFS".
-But Unixware Boot Filesystem is called bfs, too. And they are already in
-the kernel. Because of this naming conflict, on Linux the BeOS
+But the UnixWare Boot Filesystem is called bfs, too, and it was already
+in the kernel. Because of this naming conflict, on Linux the BeOS
 filesystem is called befs.
 
 How to Install
diff --git a/Documentation/filesystems/bfs.rst b/Documentation/filesystems/bfs.rst
deleted file mode 100644
index ce14b9018807..000000000000
--- a/Documentation/filesystems/bfs.rst
+++ /dev/null
@@ -1,60 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0
-
-========================
-BFS Filesystem for Linux
-========================
-
-The BFS filesystem is used by SCO UnixWare OS for the /stand slice, which
-usually contains the kernel image and a few other files required for the
-boot process.
-
-In order to access /stand partition under Linux you obviously need to
-know the partition number and the kernel must support UnixWare disk slices
-(CONFIG_UNIXWARE_DISKLABEL config option). However BFS support does not
-depend on having UnixWare disklabel support because one can also mount
-BFS filesystem via loopback::
-
-    # losetup /dev/loop0 stand.img
-    # mount -t bfs /dev/loop0 /mnt/stand
-
-where stand.img is a file containing the image of BFS filesystem.
-When you have finished using it and umounted you need to also deallocate
-/dev/loop0 device by::
-
-    # losetup -d /dev/loop0
-
-You can simplify mounting by just typing::
-
-    # mount -t bfs -o loop stand.img /mnt/stand
-
-this will allocate the first available loopback device (and load loop.o
-kernel module if necessary) automatically. If the loopback driver is not
-loaded automatically, make sure that you have compiled the module and
-that modprobe is functioning. Beware that umount will not deallocate
-/dev/loopN device if /etc/mtab file on your system is a symbolic link to
-/proc/mounts. You will need to do it manually using "-d" switch of
-losetup(8). Read losetup(8) manpage for more info.
-
-To create the BFS image under UnixWare you need to find out first which
-slice contains it. The command prtvtoc(1M) is your friend::
-
-    # prtvtoc /dev/rdsk/c0b0t0d0s0
-
-(assuming your root disk is on target=0, lun=0, bus=0, controller=0). Then you
-look for the slice with tag "STAND", which is usually slice 10. With this
-information you can use dd(1) to create the BFS image::
-
-    # umount /stand
-    # dd if=/dev/rdsk/c0b0t0d0sa of=stand.img bs=512
-
-Just in case, you can verify that you have done the right thing by checking
-the magic number::
-
-    # od -Ad -tx4 stand.img | more
-
-The first 4 bytes should be 0x1badface.
-
-If you have any patches, questions or suggestions regarding this BFS
-implementation please contact the author:
-
-Tigran Aivazian <aivazian.tigran@gmail.com>
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index fbd55915a318..1100130ccf0a 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -75,7 +75,6 @@ Documentation for filesystem implementations.
    autofs
    autofs-mount-control
    befs
-   bfs
    btrfs
    ceph
    coda
diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index 844d65eb47a5..6330653287d5 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -61,23 +61,23 @@ inode_operations
 
 prototypes::
 
-	int (*create) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t);
+	int (*create) (const struct mnt_idmap *, struct inode *,struct dentry *,umode_t);
 	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
 	int (*link) (struct dentry *,struct inode *,struct dentry *);
 	int (*unlink) (struct inode *,struct dentry *);
-	int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *,const char *);
-	struct dentry *(*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t);
+	int (*symlink) (const struct mnt_idmap *, struct inode *,struct dentry *,const char *);
+	struct dentry *(*mkdir) (const struct mnt_idmap *, struct inode *,struct dentry *,umode_t);
 	int (*rmdir) (struct inode *,struct dentry *);
-	int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t,dev_t);
-	int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *,
+	int (*mknod) (const struct mnt_idmap *, struct inode *,struct dentry *,umode_t,dev_t);
+	int (*rename) (const struct mnt_idmap *, struct inode *, struct dentry *,
 			struct inode *, struct dentry *, unsigned int);
 	int (*readlink) (struct dentry *, char __user *,int);
 	const char *(*get_link) (struct dentry *, struct inode *, struct delayed_call *);
 	void (*truncate) (struct inode *);
-	int (*permission) (struct mnt_idmap *, struct inode *, int, unsigned int);
+	int (*permission) (const struct mnt_idmap *, struct inode *, int, unsigned int);
 	struct posix_acl * (*get_inode_acl)(struct inode *, int, bool);
-	int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *);
-	int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int);
+	int (*setattr) (const struct mnt_idmap *, struct dentry *, struct iattr *);
+	int (*getattr) (const struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int);
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
 	void (*update_time)(struct inode *inode, enum fs_update_time type,
@@ -86,12 +86,12 @@ prototypes::
 	int (*atomic_open)(struct inode *, struct dentry *,
 				struct file *, unsigned open_flag,
 				umode_t create_mode);
-	int (*tmpfile) (struct mnt_idmap *, struct inode *,
+	int (*tmpfile) (const struct mnt_idmap *, struct inode *,
 			struct file *, umode_t);
-	int (*fileattr_set)(struct mnt_idmap *idmap,
+	int (*fileattr_set)(const struct mnt_idmap *idmap,
 			    struct dentry *dentry, struct file_kattr *fa);
 	int (*fileattr_get)(struct dentry *dentry, struct file_kattr *fa);
-	struct posix_acl * (*get_acl)(struct mnt_idmap *, struct dentry *, int);
+	struct posix_acl * (*get_acl)(const struct mnt_idmap *, struct dentry *, int);
 	struct offset_ctx *(*get_offset_ctx)(struct inode *inode);
 
 locking rules:
@@ -148,7 +148,7 @@ prototypes::
 		   struct inode *inode, const char *name, void *buffer,
 		   size_t size);
 	int (*set)(const struct xattr_handler *handler,
-                   struct mnt_idmap *idmap,
+                   const struct mnt_idmap *idmap,
                    struct dentry *dentry, struct inode *inode, const char *name,
                    const void *buffer, size_t size, int flags);
 
diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst
index ddd799df6ce3..0c9786ffe192 100644
--- a/Documentation/filesystems/netfs_library.rst
+++ b/Documentation/filesystems/netfs_library.rst
@@ -195,7 +195,7 @@ structure is defined::
 		struct inode inode;
 		const struct netfs_request_ops *ops;
 		struct fscache_cookie * cache;
-		loff_t remote_i_size;
+		loff_t _remote_i_size;
 		unsigned long flags;
 		...
 	};
@@ -229,11 +229,14 @@ filesystem:
    Local caching cookie, or NULL if no caching is enabled.  This field does not
    exist if fscache is disabled.
 
- * ``remote_i_size``
+ * ``_remote_i_size``
 
    The size of the file on the server.  This differs from inode->i_size if
    local modifications have been made but not yet written back.
 
+   Use netfs_read_remote_i_size() and netfs_write_remote_i_size() to access
+   this field.  Hold inode->i_lock when writing it.
+
  * ``flags``
 
    A set of flags, some of which the filesystem might be interested in:
diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst
index 60880eb0c49d..e666edab789f 100644
--- a/Documentation/filesystems/porting.rst
+++ b/Documentation/filesystems/porting.rst
@@ -348,7 +348,7 @@ simply of return 1.  Note that all actual eviction work is done by caller after
 As before, clear_inode() must be called exactly once on each call of
 ->evict_inode() (as it used to be for each call of ->delete_inode()).  Unlike
 before, if you are using inode-associated metadata buffers (i.e.
-mark_buffer_dirty_inode()), it's your responsibility to call
+mmb_mark_buffer_dirty()), it's your responsibility to call
 invalidate_inode_buffers() before clear_inode().
 
 NOTE: checking i_nlink in the beginning of ->write_inode() and bailing out
@@ -1203,16 +1203,16 @@ will fail-safe.
 
 ---
 
-** mandatory**
+**mandatory**
 
 lookup_one(), lookup_one_unlocked(), lookup_one_positive_unlocked() now
 take a qstr instead of a name and len.  These, not the "one_len"
 versions, should be used whenever accessing a filesystem from outside
-that filesysmtem, through a mount point - which will have a mnt_idmap.
+that filesystem, through a mount point - which will have a mnt_idmap.
 
 ---
 
-** mandatory**
+**mandatory**
 
 Functions try_lookup_one_len(), lookup_one_len(),
 lookup_one_len_unlocked() and lookup_positive_unlocked() have been
@@ -1229,7 +1229,7 @@ already been performed such as after vfs_path_parent_lookup()
 
 ---
 
-** mandatory**
+**mandatory**
 
 d_hash_and_lookup() is no longer exported or available outside the VFS.
 Use try_lookup_noperm() instead.  This adds name validation and takes
@@ -1370,7 +1370,7 @@ similar.
 
 ---
 
-** mandatory**
+**mandatory**
 
 lock_rename(), lock_rename_child(), unlock_rename() are no
 longer available.  Use start_renaming() or similar.
@@ -1409,3 +1409,16 @@ use only if you have no alternative.
 The .create inode_operation no longer receives the 'excl' arg.  It must
 always assume the file does not already exist.  If the filesystem needs
 to be involved in non-exclusive create, it should provide atomic_open.
+
+---
+
+**mandatory**
+
+All struct mnt_idmap pointers handed to filesystems are const now.
+->create(), ->mkdir(), ->mknod(), ->symlink(), ->rename(), ->setattr(),
+->getattr(), ->permission(), ->tmpfile(), ->get_acl(), ->set_acl() and
+->fileattr_set() as well as the xattr ->set() handler and the vfs_*()
+helpers take a const struct mnt_idmap *. mnt_idmap() and file_mnt_idmap()
+return one. The idmapping is immutable so nothing should have modified it
+anyway. References are taken and dropped via mnt_idmap_get() and
+mnt_idmap_put() as before, both accept a const pointer.
diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index c102b62023cd..fc59c98acca1 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -1963,6 +1963,10 @@ For example::
   $ echo 0x7 > /proc/self/coredump_filter
   $ ./some_program
 
+If the coredump socket protocol is used a coredump server can select memory
+types to include dynamically. See COREDUMP_MEMORY_TYPES in
+include/uapi/linux/coredump.h.
+
 3.5	/proc/<pid>/mountinfo - Information about mounts
 --------------------------------------------------------
 
diff --git a/Documentation/filesystems/sharedsubtree.rst b/Documentation/filesystems/sharedsubtree.rst
index 8b7dc9159083..8bae6d9a7e04 100644
--- a/Documentation/filesystems/sharedsubtree.rst
+++ b/Documentation/filesystems/sharedsubtree.rst
@@ -564,8 +564,8 @@ f) Unmount semantics
    where 'A' is a mount mounted on mount 'B' at dentry 'b'.
 
    If mount 'B' is shared, then all most-recently-mounted mounts at dentry
-   'b' on mounts that receive propagation from mount 'B' and does not have
-   sub-mounts within them are unmounted.
+   'b' on mounts that receive propagation from mount 'B' are unmounted as
+   well, if every mount below them is also unmounted.
 
    Example: Let's say 'B1', 'B2', 'B3' are shared mounts that propagate to
    each other.
@@ -584,10 +584,18 @@ f) Unmount semantics
 
    So all 'C1', 'C2' and 'C3' should be unmounted.
 
-   If any of 'C2' or 'C3' has some child mounts, then that mount is not
-   unmounted, but all other mounts are unmounted. However if 'C1' is told
-   to be unmounted and 'C1' has some sub-mounts, the umount operation is
-   failed entirely.
+   If any of 'C2' or 'C3' has a child mount that cannot be unmounted
+   then that mount is not unmounted. But all other mounts are unmounted.
+   A child mount that is itself unmounted by the same unmount
+   propagation does not keep its parent mounted. However if 'C1' is
+   supposed to be unmounted and 'C1' has some sub-mounts, the unmount
+   fails.
+
+   A lazy umount (MNT_DETACH) takes a whole tree. Every mount of the
+   tree then propagates its unmount from its own parent as described
+   above, so the mounts that receive propagation lose the corresponding
+   trees as well. Documentation/filesystems/propagate_umount.txt has the
+   precise rules, including the ones for locked mounts.
 
 g) Clone Namespace
 
diff --git a/Documentation/filesystems/squashfs.rst b/Documentation/filesystems/squashfs.rst
index 45653b3228f9..d6397961d16b 100644
--- a/Documentation/filesystems/squashfs.rst
+++ b/Documentation/filesystems/squashfs.rst
@@ -177,9 +177,9 @@ or if the compressed block was larger than the uncompressed block.
 
 Inodes are packed into the metadata blocks, and are not aligned to block
 boundaries, therefore inodes overlap compressed blocks.  Inodes are identified
-by a 48-bit number which encodes the location of the compressed metadata block
-containing the inode, and the byte offset into that block where the inode is
-placed (<block, offset>).
+by a 64-bit number: the upper 48 bits encode the location of the compressed
+metadata block containing the inode, and the lower 16 bits give the byte offset
+into that block where the inode is placed (<block, offset>).
 
 To maximise compression there are different inodes for each file type
 (regular file, directory, device, etc.), the inode contents and length
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index d3a93eec3945..99495497ea6d 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -117,7 +117,7 @@ members are defined:
 		const struct fs_parameter_spec *parameters;
 		void (*kill_sb) (struct super_block *);
 		struct module *owner;
-		struct file_system_type * next;
+		struct hlist_node list;
 		struct hlist_head fs_supers;
 
 		struct lock_class_key s_lock_key;
@@ -415,33 +415,33 @@ As of kernel 2.6.22, the following members are defined:
 .. code-block:: c
 
 	struct inode_operations {
-		int (*create) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t);
+		int (*create) (const struct mnt_idmap *, struct inode *,struct dentry *, umode_t);
 		struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
 		int (*link) (struct dentry *,struct inode *,struct dentry *);
 		int (*unlink) (struct inode *,struct dentry *);
-		int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *,const char *);
-		struct dentry *(*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t);
+		int (*symlink) (const struct mnt_idmap *, struct inode *,struct dentry *,const char *);
+		struct dentry *(*mkdir) (const struct mnt_idmap *, struct inode *,struct dentry *,umode_t);
 		int (*rmdir) (struct inode *,struct dentry *);
-		int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t,dev_t);
-		int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *,
+		int (*mknod) (const struct mnt_idmap *, struct inode *,struct dentry *,umode_t,dev_t);
+		int (*rename) (const struct mnt_idmap *, struct inode *, struct dentry *,
 			       struct inode *, struct dentry *, unsigned int);
 		int (*readlink) (struct dentry *, char __user *,int);
 		const char *(*get_link) (struct dentry *, struct inode *,
 					 struct delayed_call *);
-		int (*permission) (struct mnt_idmap *, struct inode *, int);
+		int (*permission) (const struct mnt_idmap *, struct inode *, int);
 		struct posix_acl * (*get_inode_acl)(struct inode *, int, bool);
-		int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *);
-		int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int);
+		int (*setattr) (const struct mnt_idmap *, struct dentry *, struct iattr *);
+		int (*getattr) (const struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int);
 		ssize_t (*listxattr) (struct dentry *, char *, size_t);
 		void (*update_time)(struct inode *inode, enum fs_update_time type,
 				    int flags);
 		void (*sync_lazytime)(struct inode *inode);
 		int (*atomic_open)(struct inode *, struct dentry *, struct file *,
 				   unsigned open_flag, umode_t create_mode);
-		int (*tmpfile) (struct mnt_idmap *, struct inode *, struct file *, umode_t);
-		struct posix_acl * (*get_acl)(struct mnt_idmap *, struct dentry *, int);
-	        int (*set_acl)(struct mnt_idmap *, struct dentry *, struct posix_acl *, int);
-		int (*fileattr_set)(struct mnt_idmap *idmap,
+		int (*tmpfile) (const struct mnt_idmap *, struct inode *, struct file *, umode_t);
+		struct posix_acl * (*get_acl)(const struct mnt_idmap *, struct dentry *, int);
+	        int (*set_acl)(const struct mnt_idmap *, struct dentry *, struct posix_acl *, int);
+		int (*fileattr_set)(const struct mnt_idmap *idmap,
 				    struct dentry *dentry, struct file_kattr *fa);
 		int (*fileattr_get)(struct dentry *dentry, struct file_kattr *fa);
 	        struct offset_ctx *(*get_offset_ctx)(struct inode *inode);
@@ -507,8 +507,8 @@ otherwise noted.
 	dentry before the first mkdir returns.
 
 	If there is any chance this could happen, then the new inode
-	should be d_drop()ed and attached with d_splice_alias().  The
-	returned dentry (if any) should be returned by ->mkdir().
+	should be attached with d_splice_alias().  The returned
+	dentry (if any) should be returned by ->mkdir().
 
 ``rmdir``
 	called by the rmdir(2) system call.  Only required if you want