From eb2317b13b1884b07db23d986988620941b2f075 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 20 Sep 2021 17:09:04 -0400
Subject: [PATCH 01/67] nios2: _TIF_ALLWORK_MASK is unused

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/nios2/include/asm/thread_info.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/arch/nios2/include/asm/thread_info.h b/arch/nios2/include/asm/thread_info.h
index bcc0e9915ebd..5abac9893b32 100644
--- a/arch/nios2/include/asm/thread_info.h
+++ b/arch/nios2/include/asm/thread_info.h
@@ -96,9 +96,6 @@ static inline struct thread_info *current_thread_info(void)
 /* work to do on interrupt/exception return */
 #define _TIF_WORK_MASK		0x0000FFFE
 
-/* work to do on any return to u-space */
-# define _TIF_ALLWORK_MASK	0x0000FFFF
-
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_NIOS2_THREAD_INFO_H */

From 0aaf08de8426f823bd0e36797445222e6392e374 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 19 Jan 2023 19:22:22 -0500
Subject: [PATCH 02/67] __blockdev_direct_IO(): get rid of submit_io callback

always NULL...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/direct-io.c     | 9 ++-------
 fs/ocfs2/aops.c    | 2 +-
 include/linux/fs.h | 4 ++--
 3 files changed, 5 insertions(+), 10 deletions(-)

diff --git a/fs/direct-io.c b/fs/direct-io.c
index ab0d7ea89813..0b380bb8a81e 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -86,7 +86,6 @@ struct dio_submit {
 	sector_t final_block_in_request;/* doesn't change */
 	int boundary;			/* prev block is at a boundary */
 	get_block_t *get_block;		/* block mapping function */
-	dio_submit_t *submit_io;	/* IO submition function */
 
 	loff_t logical_offset_in_bio;	/* current first logical block in bio */
 	sector_t final_block_in_bio;	/* current final block in bio + 1 */
@@ -431,10 +430,7 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
 
 	dio->bio_disk = bio->bi_bdev->bd_disk;
 
-	if (sdio->submit_io)
-		sdio->submit_io(bio, dio->inode, sdio->logical_offset_in_bio);
-	else
-		submit_bio(bio);
+	submit_bio(bio);
 
 	sdio->bio = NULL;
 	sdio->boundary = 0;
@@ -1098,7 +1094,7 @@ static inline int drop_refcount(struct dio *dio)
 ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 		struct block_device *bdev, struct iov_iter *iter,
 		get_block_t get_block, dio_iodone_t end_io,
-		dio_submit_t submit_io, int flags)
+		int flags)
 {
 	unsigned i_blkbits = READ_ONCE(inode->i_blkbits);
 	unsigned blkbits = i_blkbits;
@@ -1215,7 +1211,6 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 
 	sdio.get_block = get_block;
 	dio->end_io = end_io;
-	sdio.submit_io = submit_io;
 	sdio.final_block_in_bio = -1;
 	sdio.next_block_for_io = -1;
 
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 1d65f6ef00ca..50448ba5fda8 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2448,7 +2448,7 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 
 	return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
 				    iter, get_block,
-				    ocfs2_dio_end_io, NULL, 0);
+				    ocfs2_dio_end_io, 0);
 }
 
 const struct address_space_operations ocfs2_aops = {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c85916e9f7db..b07d13e546d3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2778,7 +2778,7 @@ enum {
 ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 			     struct block_device *bdev, struct iov_iter *iter,
 			     get_block_t get_block,
-			     dio_iodone_t end_io, dio_submit_t submit_io,
+			     dio_iodone_t end_io,
 			     int flags);
 
 static inline ssize_t blockdev_direct_IO(struct kiocb *iocb,
@@ -2787,7 +2787,7 @@ static inline ssize_t blockdev_direct_IO(struct kiocb *iocb,
 					 get_block_t get_block)
 {
 	return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
-			get_block, NULL, NULL, DIO_LOCKING | DIO_SKIP_HOLES);
+			get_block, NULL, DIO_LOCKING | DIO_SKIP_HOLES);
 }
 #endif
 

From f2620f166e2a4db08f016b7b30b904ab28c265e4 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 1 Feb 2023 14:14:52 +0100
Subject: [PATCH 03/67] xattr: simplify listxattr helpers

The generic_listxattr() and simple_xattr_list() helpers list xattrs and
contain duplicated code. Add two helpers that both generic_listxattr()
and simple_xattr_list() can use.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
---
 fs/posix_acl.c            | 25 ++++++++++++
 fs/xattr.c                | 85 ++++++++++++++-------------------------
 include/linux/posix_acl.h |  7 ++++
 include/linux/xattr.h     |  1 +
 4 files changed, 64 insertions(+), 54 deletions(-)

diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 5a76fb35923a..b350e8396adb 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -957,6 +957,31 @@ set_posix_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 }
 EXPORT_SYMBOL(set_posix_acl);
 
+int posix_acl_listxattr(struct inode *inode, char **buffer,
+			ssize_t *remaining_size)
+{
+	int err;
+
+	if (!IS_POSIXACL(inode))
+		return 0;
+
+	if (inode->i_acl) {
+		err = xattr_list_one(buffer, remaining_size,
+				     XATTR_NAME_POSIX_ACL_ACCESS);
+		if (err)
+			return err;
+	}
+
+	if (inode->i_default_acl) {
+		err = xattr_list_one(buffer, remaining_size,
+				     XATTR_NAME_POSIX_ACL_DEFAULT);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static bool
 posix_acl_xattr_list(struct dentry *dentry)
 {
diff --git a/fs/xattr.c b/fs/xattr.c
index 14a7eb3c8fa8..1a35235ecc73 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -949,6 +949,21 @@ SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name)
 	return error;
 }
 
+int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name)
+{
+	size_t len;
+
+	len = strlen(name) + 1;
+	if (*buffer) {
+		if (*remaining_size < len)
+			return -ERANGE;
+		memcpy(*buffer, name, len);
+		*buffer += len;
+	}
+	*remaining_size -= len;
+	return 0;
+}
+
 /*
  * Combine the results of the list() operation from every xattr_handler in the
  * list.
@@ -957,33 +972,22 @@ ssize_t
 generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 {
 	const struct xattr_handler *handler, **handlers = dentry->d_sb->s_xattr;
-	unsigned int size = 0;
+	ssize_t remaining_size = buffer_size;
+	int err = 0;
 
-	if (!buffer) {
-		for_each_xattr_handler(handlers, handler) {
-			if (!handler->name ||
-			    (handler->list && !handler->list(dentry)))
-				continue;
-			size += strlen(handler->name) + 1;
-		}
-	} else {
-		char *buf = buffer;
-		size_t len;
+	err = posix_acl_listxattr(d_inode(dentry), &buffer, &remaining_size);
+	if (err)
+		return err;
 
-		for_each_xattr_handler(handlers, handler) {
-			if (!handler->name ||
-			    (handler->list && !handler->list(dentry)))
-				continue;
-			len = strlen(handler->name);
-			if (len + 1 > buffer_size)
-				return -ERANGE;
-			memcpy(buf, handler->name, len + 1);
-			buf += len + 1;
-			buffer_size -= len + 1;
-		}
-		size = buf - buffer;
+	for_each_xattr_handler(handlers, handler) {
+		if (!handler->name || (handler->list && !handler->list(dentry)))
+			continue;
+		err = xattr_list_one(&buffer, &remaining_size, handler->name);
+		if (err)
+			return err;
 	}
-	return size;
+
+	return err ? err : buffer_size - remaining_size;
 }
 EXPORT_SYMBOL(generic_listxattr);
 
@@ -1245,20 +1249,6 @@ static bool xattr_is_trusted(const char *name)
 	return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
 }
 
-static int xattr_list_one(char **buffer, ssize_t *remaining_size,
-			  const char *name)
-{
-	size_t len = strlen(name) + 1;
-	if (*buffer) {
-		if (*remaining_size < len)
-			return -ERANGE;
-		memcpy(*buffer, name, len);
-		*buffer += len;
-	}
-	*remaining_size -= len;
-	return 0;
-}
-
 /**
  * simple_xattr_list - list all xattr objects
  * @inode: inode from which to get the xattrs
@@ -1287,22 +1277,9 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
 	ssize_t remaining_size = size;
 	int err = 0;
 
-#ifdef CONFIG_FS_POSIX_ACL
-	if (IS_POSIXACL(inode)) {
-		if (inode->i_acl) {
-			err = xattr_list_one(&buffer, &remaining_size,
-					     XATTR_NAME_POSIX_ACL_ACCESS);
-			if (err)
-				return err;
-		}
-		if (inode->i_default_acl) {
-			err = xattr_list_one(&buffer, &remaining_size,
-					     XATTR_NAME_POSIX_ACL_DEFAULT);
-			if (err)
-				return err;
-		}
-	}
-#endif
+	err = posix_acl_listxattr(inode, &buffer, &remaining_size);
+	if (err)
+		return err;
 
 	read_lock(&xattrs->lock);
 	for (rbp = rb_first(&xattrs->rb_root); rbp; rbp = rb_next(rbp)) {
diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h
index 21cc29b8a9e8..0e65b3d634d9 100644
--- a/include/linux/posix_acl.h
+++ b/include/linux/posix_acl.h
@@ -106,6 +106,8 @@ struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap,
 			      struct dentry *dentry, const char *acl_name);
 int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 		   const char *acl_name);
+int posix_acl_listxattr(struct inode *inode, char **buffer,
+			ssize_t *remaining_size);
 #else
 static inline int posix_acl_chmod(struct mnt_idmap *idmap,
 				  struct dentry *dentry, umode_t mode)
@@ -153,6 +155,11 @@ static inline int vfs_remove_acl(struct mnt_idmap *idmap,
 {
 	return -EOPNOTSUPP;
 }
+static inline int posix_acl_listxattr(struct inode *inode, char **buffer,
+				      ssize_t *remaining_size)
+{
+	return 0;
+}
 #endif /* CONFIG_FS_POSIX_ACL */
 
 struct posix_acl *get_inode_acl(struct inode *inode, int type);
diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index 6af72461397d..ce8fb0bd56c6 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -109,5 +109,6 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
 			  char *buffer, size_t size);
 void simple_xattr_add(struct simple_xattrs *xattrs,
 		      struct simple_xattr *new_xattr);
+int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name);
 
 #endif	/* _LINUX_XATTR_H */

From 2db8a948046cab3a2f707561592906a3d096972f Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 1 Feb 2023 14:14:53 +0100
Subject: [PATCH 04/67] xattr: add listxattr helper

Add a tiny helper to determine whether an xattr handler given a specific
dentry supports listing the requested xattr. We will use this helper in
various filesystems in later commits.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
---
 include/linux/xattr.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index ce8fb0bd56c6..7adf768d4396 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -47,6 +47,22 @@ struct xattr_handler {
 		   size_t size, int flags);
 };
 
+/**
+ * xattr_handler_can_list - check whether xattr can be listed
+ * @handler: handler for this type of xattr
+ * @dentry: dentry whose inode xattr to list
+ *
+ * Determine whether the xattr associated with @dentry can be listed given
+ * @handler.
+ *
+ * Return: true if xattr can be listed, false if not.
+ */
+static inline bool xattr_handler_can_list(const struct xattr_handler *handler,
+					  struct dentry *dentry)
+{
+	return handler && (!handler->list || handler->list(dentry));
+}
+
 const char *xattr_full_name(const struct xattr_handler *, const char *);
 
 struct xattr {

From 831be973aa21d1cf8948bf4b1d4e73e6d5d028c0 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 1 Feb 2023 14:14:54 +0100
Subject: [PATCH 05/67] xattr: remove unused argument

his helpers is really just used to check for user.* xattr support so
don't make it pointlessly generic.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
---
 fs/nfsd/nfs4xdr.c     |  3 +--
 fs/xattr.c            | 10 ++++------
 include/linux/xattr.h |  2 +-
 3 files changed, 6 insertions(+), 9 deletions(-)

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index e12e5a4ad502..e30c0746305b 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3444,8 +3444,7 @@ out_acl:
 		p = xdr_reserve_space(xdr, 4);
 		if (!p)
 			goto out_resource;
-		err = xattr_supported_namespace(d_inode(dentry),
-						XATTR_USER_PREFIX);
+		err = xattr_supports_user_prefix(d_inode(dentry));
 		*p++ = cpu_to_be32(err == 0);
 	}
 
diff --git a/fs/xattr.c b/fs/xattr.c
index 1a35235ecc73..95bb6b30ab13 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -160,11 +160,10 @@ xattr_permission(struct mnt_idmap *idmap, struct inode *inode,
  * Look for any handler that deals with the specified namespace.
  */
 int
-xattr_supported_namespace(struct inode *inode, const char *prefix)
+xattr_supports_user_prefix(struct inode *inode)
 {
 	const struct xattr_handler **handlers = inode->i_sb->s_xattr;
 	const struct xattr_handler *handler;
-	size_t preflen;
 
 	if (!(inode->i_opflags & IOP_XATTR)) {
 		if (unlikely(is_bad_inode(inode)))
@@ -172,16 +171,15 @@ xattr_supported_namespace(struct inode *inode, const char *prefix)
 		return -EOPNOTSUPP;
 	}
 
-	preflen = strlen(prefix);
-
 	for_each_xattr_handler(handlers, handler) {
-		if (!strncmp(xattr_prefix(handler), prefix, preflen))
+		if (!strncmp(xattr_prefix(handler), XATTR_USER_PREFIX,
+			     XATTR_USER_PREFIX_LEN))
 			return 0;
 	}
 
 	return -EOPNOTSUPP;
 }
-EXPORT_SYMBOL(xattr_supported_namespace);
+EXPORT_SYMBOL(xattr_supports_user_prefix);
 
 int
 __vfs_setxattr(struct mnt_idmap *idmap, struct dentry *dentry,
diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index 7adf768d4396..d591ef59aa98 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -94,7 +94,7 @@ int vfs_getxattr_alloc(struct mnt_idmap *idmap,
 		       struct dentry *dentry, const char *name,
 		       char **xattr_value, size_t size, gfp_t flags);
 
-int xattr_supported_namespace(struct inode *inode, const char *prefix);
+int xattr_supports_user_prefix(struct inode *inode);
 
 static inline const char *xattr_prefix(const struct xattr_handler *handler)
 {

From 0c95c025a02e477b2d112350e1c78bb0cc994c51 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 1 Feb 2023 14:14:55 +0100
Subject: [PATCH 06/67] fs: drop unused posix acl handlers

Remove struct posix_acl_{access,default}_handler for all filesystems
that don't depend on the xattr handler in their inode->i_op->listxattr()
method in any way. There's nothing more to do than to simply remove the
handler. It's been effectively unused ever since we introduced the new
posix acl api.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
---
 fs/9p/xattr.c        | 4 ----
 fs/btrfs/xattr.c     | 4 ----
 fs/ceph/xattr.c      | 4 ----
 fs/cifs/xattr.c      | 4 ----
 fs/ecryptfs/inode.c  | 4 ----
 fs/erofs/xattr.c     | 4 ----
 fs/ext2/xattr.c      | 4 ----
 fs/ext4/xattr.c      | 4 ----
 fs/f2fs/xattr.c      | 4 ----
 fs/gfs2/xattr.c      | 2 --
 fs/jffs2/xattr.c     | 4 ----
 fs/jfs/xattr.c       | 4 ----
 fs/nfs/nfs3_fs.h     | 1 -
 fs/nfs/nfs3acl.c     | 6 ------
 fs/nfs/nfs3super.c   | 3 ---
 fs/ntfs3/xattr.c     | 4 ----
 fs/ocfs2/xattr.c     | 2 --
 fs/orangefs/xattr.c  | 2 --
 fs/overlayfs/super.c | 8 --------
 fs/xfs/xfs_xattr.c   | 4 ----
 mm/shmem.c           | 4 ----
 21 files changed, 80 deletions(-)

diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c
index 50f7f3f6b55e..a0fcc2ce2e2e 100644
--- a/fs/9p/xattr.c
+++ b/fs/9p/xattr.c
@@ -183,10 +183,6 @@ static struct xattr_handler v9fs_xattr_security_handler = {
 const struct xattr_handler *v9fs_xattr_handlers[] = {
 	&v9fs_xattr_user_handler,
 	&v9fs_xattr_trusted_handler,
-#ifdef CONFIG_FS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
 #ifdef CONFIG_9P_FS_SECURITY
 	&v9fs_xattr_security_handler,
 #endif
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 0ebeaf4e81f9..fc4b20c2688a 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -444,10 +444,6 @@ static const struct xattr_handler btrfs_btrfs_xattr_handler = {
 
 const struct xattr_handler *btrfs_xattr_handlers[] = {
 	&btrfs_security_xattr_handler,
-#ifdef CONFIG_BTRFS_FS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
 	&btrfs_trusted_xattr_handler,
 	&btrfs_user_xattr_handler,
 	&btrfs_btrfs_xattr_handler,
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index f65b07cc33a2..1fe1b62abebd 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -1411,10 +1411,6 @@ void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx)
  * attributes are handled directly.
  */
 const struct xattr_handler *ceph_xattr_handlers[] = {
-#ifdef CONFIG_CEPH_FS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
 	&ceph_other_xattr_handler,
 	NULL,
 };
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 50e762fa1a14..4ad5531686d8 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -487,9 +487,5 @@ const struct xattr_handler *cifs_xattr_handlers[] = {
 	&smb3_ntsd_xattr_handler, /* alias for above since avoiding "cifs" */
 	&cifs_cifs_ntsd_full_xattr_handler,
 	&smb3_ntsd_full_xattr_handler, /* alias for above since avoiding "cifs" */
-#ifdef CONFIG_FS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
 	NULL
 };
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 144ace9e0dd9..83274915ba6d 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -1210,10 +1210,6 @@ static const struct xattr_handler ecryptfs_xattr_handler = {
 };
 
 const struct xattr_handler *ecryptfs_xattr_handlers[] = {
-#ifdef CONFIG_FS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
 	&ecryptfs_xattr_handler,
 	NULL
 };
diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c
index 60729b1220b6..3de058f17428 100644
--- a/fs/erofs/xattr.c
+++ b/fs/erofs/xattr.c
@@ -463,10 +463,6 @@ const struct xattr_handler __maybe_unused erofs_xattr_security_handler = {
 
 const struct xattr_handler *erofs_xattr_handlers[] = {
 	&erofs_xattr_user_handler,
-#ifdef CONFIG_EROFS_FS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
 	&erofs_xattr_trusted_handler,
 #ifdef CONFIG_EROFS_FS_SECURITY
 	&erofs_xattr_security_handler,
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index 641abfa4b718..262951ffe8d0 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -113,10 +113,6 @@ static const struct xattr_handler *ext2_xattr_handler_map[] = {
 const struct xattr_handler *ext2_xattr_handlers[] = {
 	&ext2_xattr_user_handler,
 	&ext2_xattr_trusted_handler,
-#ifdef CONFIG_EXT2_FS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
 #ifdef CONFIG_EXT2_FS_SECURITY
 	&ext2_xattr_security_handler,
 #endif
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 62f2ec599218..abe659e948b8 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -101,10 +101,6 @@ static const struct xattr_handler * const ext4_xattr_handler_map[] = {
 const struct xattr_handler *ext4_xattr_handlers[] = {
 	&ext4_xattr_user_handler,
 	&ext4_xattr_trusted_handler,
-#ifdef CONFIG_EXT4_FS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
 #ifdef CONFIG_EXT4_FS_SECURITY
 	&ext4_xattr_security_handler,
 #endif
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index d92edbbdc30e..37cfc0302251 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -204,10 +204,6 @@ static const struct xattr_handler *f2fs_xattr_handler_map[] = {
 
 const struct xattr_handler *f2fs_xattr_handlers[] = {
 	&f2fs_xattr_user_handler,
-#ifdef CONFIG_F2FS_FS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
 	&f2fs_xattr_trusted_handler,
 #ifdef CONFIG_F2FS_FS_SECURITY
 	&f2fs_xattr_security_handler,
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index adf6d17cf033..93b36d026bb4 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -1501,8 +1501,6 @@ const struct xattr_handler *gfs2_xattr_handlers_max[] = {
 	/* GFS2_FS_FORMAT_MIN */
 	&gfs2_xattr_user_handler,
 	&gfs2_xattr_security_handler,
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
 	NULL,
 };
 
diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c
index da3e18503c65..0eaec4a0f3b1 100644
--- a/fs/jffs2/xattr.c
+++ b/fs/jffs2/xattr.c
@@ -919,10 +919,6 @@ const struct xattr_handler *jffs2_xattr_handlers[] = {
 	&jffs2_user_xattr_handler,
 #ifdef CONFIG_JFFS2_FS_SECURITY
 	&jffs2_security_xattr_handler,
-#endif
-#ifdef CONFIG_JFFS2_FS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
 #endif
 	&jffs2_trusted_xattr_handler,
 	NULL
diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c
index f817798fa1eb..931e50018f88 100644
--- a/fs/jfs/xattr.c
+++ b/fs/jfs/xattr.c
@@ -986,10 +986,6 @@ static const struct xattr_handler jfs_trusted_xattr_handler = {
 };
 
 const struct xattr_handler *jfs_xattr_handlers[] = {
-#ifdef CONFIG_JFS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
 	&jfs_os2_xattr_handler,
 	&jfs_user_xattr_handler,
 	&jfs_security_xattr_handler,
diff --git a/fs/nfs/nfs3_fs.h b/fs/nfs/nfs3_fs.h
index 4fa37dc038b5..b333ea119ef5 100644
--- a/fs/nfs/nfs3_fs.h
+++ b/fs/nfs/nfs3_fs.h
@@ -17,7 +17,6 @@ extern int nfs3_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 extern int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 		struct posix_acl *dfacl);
 extern ssize_t nfs3_listxattr(struct dentry *, char *, size_t);
-extern const struct xattr_handler *nfs3_xattr_handlers[];
 #else
 static inline int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 		struct posix_acl *dfacl)
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 1247f544a440..349cc4f60a28 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -300,12 +300,6 @@ fail:
 	goto out;
 }
 
-const struct xattr_handler *nfs3_xattr_handlers[] = {
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-	NULL,
-};
-
 static int
 nfs3_list_one_acl(struct inode *inode, int type, const char *name, void *data,
 		size_t size, ssize_t *result)
diff --git a/fs/nfs/nfs3super.c b/fs/nfs/nfs3super.c
index 7c5809431e61..8a9be9e47f76 100644
--- a/fs/nfs/nfs3super.c
+++ b/fs/nfs/nfs3super.c
@@ -14,9 +14,6 @@ struct nfs_subversion nfs_v3 = {
 	.rpc_vers = &nfs_version3,
 	.rpc_ops  = &nfs_v3_clientops,
 	.sops     = &nfs_sops,
-#ifdef CONFIG_NFS_V3_ACL
-	.xattr    = nfs3_xattr_handlers,
-#endif
 };
 
 static int __init init_nfs_v3(void)
diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c
index ff64302e87e5..7324cf924932 100644
--- a/fs/ntfs3/xattr.c
+++ b/fs/ntfs3/xattr.c
@@ -1033,10 +1033,6 @@ static const struct xattr_handler ntfs_other_xattr_handler = {
 };
 
 const struct xattr_handler *ntfs_xattr_handlers[] = {
-#ifdef CONFIG_NTFS3_FS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
 	&ntfs_other_xattr_handler,
 	NULL,
 };
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 389308efe854..10dab2a7b2e2 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -89,8 +89,6 @@ static struct ocfs2_xattr_def_value_root def_xv = {
 
 const struct xattr_handler *ocfs2_xattr_handlers[] = {
 	&ocfs2_xattr_user_handler,
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
 	&ocfs2_xattr_trusted_handler,
 	&ocfs2_xattr_security_handler,
 	NULL
diff --git a/fs/orangefs/xattr.c b/fs/orangefs/xattr.c
index 6ecad4f94ae6..68b62689a63e 100644
--- a/fs/orangefs/xattr.c
+++ b/fs/orangefs/xattr.c
@@ -555,8 +555,6 @@ static const struct xattr_handler orangefs_xattr_default_handler = {
 };
 
 const struct xattr_handler *orangefs_xattr_handlers[] = {
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
 	&orangefs_xattr_default_handler,
 	NULL
 };
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index f1d9f75f8786..f97ad8b40dbb 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1055,20 +1055,12 @@ static const struct xattr_handler ovl_other_xattr_handler = {
 };
 
 static const struct xattr_handler *ovl_trusted_xattr_handlers[] = {
-#ifdef CONFIG_FS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
 	&ovl_own_trusted_xattr_handler,
 	&ovl_other_xattr_handler,
 	NULL
 };
 
 static const struct xattr_handler *ovl_user_xattr_handlers[] = {
-#ifdef CONFIG_FS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
 	&ovl_own_user_xattr_handler,
 	&ovl_other_xattr_handler,
 	NULL
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 7b9a0ed1b11f..43e5c219aaed 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -179,10 +179,6 @@ const struct xattr_handler *xfs_xattr_handlers[] = {
 	&xfs_xattr_user_handler,
 	&xfs_xattr_trusted_handler,
 	&xfs_xattr_security_handler,
-#ifdef CONFIG_XFS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
 	NULL
 };
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 448f393d8ab2..b76521ed372d 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3339,10 +3339,6 @@ static const struct xattr_handler shmem_trusted_xattr_handler = {
 };
 
 static const struct xattr_handler *shmem_xattr_handlers[] = {
-#ifdef CONFIG_TMPFS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
 	&shmem_security_xattr_handler,
 	&shmem_trusted_xattr_handler,
 	NULL

From a5488f29835c0eb5561b46e71c23f6c39aab6c83 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 1 Feb 2023 14:14:56 +0100
Subject: [PATCH 07/67] fs: simplify ->listxattr() implementation

The ext{2,4}, erofs, f2fs, and jffs2 filesystems use the same logic to
check whether a given xattr can be listed. Simplify them and avoid
open-coding the same check by calling the helper we introduced earlier.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: linux-f2fs-devel@lists.sourceforge.net
Cc: linux-erofs@lists.ozlabs.org
Cc: linux-ext4@vger.kernel.org
Cc: linux-mtd@lists.infradead.org
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
---
 fs/erofs/xattr.c |  8 ++------
 fs/erofs/xattr.h | 14 +++++++++++---
 fs/ext2/xattr.c  | 17 ++++++++++-------
 fs/ext4/xattr.c  | 17 ++++++++++-------
 fs/f2fs/xattr.c  | 16 ++++++++++------
 fs/jffs2/xattr.c | 21 ++++++++++++---------
 6 files changed, 55 insertions(+), 38 deletions(-)

diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c
index 3de058f17428..015462763bdd 100644
--- a/fs/erofs/xattr.c
+++ b/fs/erofs/xattr.c
@@ -486,13 +486,9 @@ static int xattr_entrylist(struct xattr_iter *_it,
 	unsigned int prefix_len;
 	const char *prefix;
 
-	const struct xattr_handler *h =
-		erofs_xattr_handler(entry->e_name_index);
-
-	if (!h || (h->list && !h->list(it->dentry)))
+	prefix = erofs_xattr_prefix(entry->e_name_index, it->dentry);
+	if (!prefix)
 		return 1;
-
-	prefix = xattr_prefix(h);
 	prefix_len = strlen(prefix);
 
 	if (!it->buffer) {
diff --git a/fs/erofs/xattr.h b/fs/erofs/xattr.h
index 0a43c9ee9f8f..08658e414c33 100644
--- a/fs/erofs/xattr.h
+++ b/fs/erofs/xattr.h
@@ -41,8 +41,11 @@ extern const struct xattr_handler erofs_xattr_user_handler;
 extern const struct xattr_handler erofs_xattr_trusted_handler;
 extern const struct xattr_handler erofs_xattr_security_handler;
 
-static inline const struct xattr_handler *erofs_xattr_handler(unsigned int idx)
+static inline const char *erofs_xattr_prefix(unsigned int idx,
+					     struct dentry *dentry)
 {
+	const struct xattr_handler *handler = NULL;
+
 	static const struct xattr_handler *xattr_handler_map[] = {
 		[EROFS_XATTR_INDEX_USER] = &erofs_xattr_user_handler,
 #ifdef CONFIG_EROFS_FS_POSIX_ACL
@@ -57,8 +60,13 @@ static inline const struct xattr_handler *erofs_xattr_handler(unsigned int idx)
 #endif
 	};
 
-	return idx && idx < ARRAY_SIZE(xattr_handler_map) ?
-		xattr_handler_map[idx] : NULL;
+	if (idx && idx < ARRAY_SIZE(xattr_handler_map))
+		handler = xattr_handler_map[idx];
+
+	if (!xattr_handler_can_list(handler, dentry))
+		return NULL;
+
+	return xattr_prefix(handler);
 }
 
 extern const struct xattr_handler *erofs_xattr_handlers[];
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index 262951ffe8d0..958976f809f5 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -121,14 +121,18 @@ const struct xattr_handler *ext2_xattr_handlers[] = {
 
 #define EA_BLOCK_CACHE(inode)	(EXT2_SB(inode->i_sb)->s_ea_block_cache)
 
-static inline const struct xattr_handler *
-ext2_xattr_handler(int name_index)
+static inline const char *ext2_xattr_prefix(int name_index,
+					    struct dentry *dentry)
 {
 	const struct xattr_handler *handler = NULL;
 
 	if (name_index > 0 && name_index < ARRAY_SIZE(ext2_xattr_handler_map))
 		handler = ext2_xattr_handler_map[name_index];
-	return handler;
+
+	if (!xattr_handler_can_list(handler, dentry))
+		return NULL;
+
+	return xattr_prefix(handler);
 }
 
 static bool
@@ -329,11 +333,10 @@ bad_block:
 	/* list the attribute names */
 	for (entry = FIRST_ENTRY(bh); !IS_LAST_ENTRY(entry);
 	     entry = EXT2_XATTR_NEXT(entry)) {
-		const struct xattr_handler *handler =
-			ext2_xattr_handler(entry->e_name_index);
+		const char *prefix;
 
-		if (handler && (!handler->list || handler->list(dentry))) {
-			const char *prefix = handler->prefix ?: handler->name;
+		prefix = ext2_xattr_prefix(entry->e_name_index, dentry);
+		if (prefix) {
 			size_t prefix_len = strlen(prefix);
 			size_t size = prefix_len + entry->e_name_len + 1;
 
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index abe659e948b8..09a9fade2053 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -169,14 +169,18 @@ static void ext4_xattr_block_csum_set(struct inode *inode,
 						bh->b_blocknr, BHDR(bh));
 }
 
-static inline const struct xattr_handler *
-ext4_xattr_handler(int name_index)
+static inline const char *ext4_xattr_prefix(int name_index,
+					    struct dentry *dentry)
 {
 	const struct xattr_handler *handler = NULL;
 
 	if (name_index > 0 && name_index < ARRAY_SIZE(ext4_xattr_handler_map))
 		handler = ext4_xattr_handler_map[name_index];
-	return handler;
+
+	if (!xattr_handler_can_list(handler, dentry))
+		return NULL;
+
+	return xattr_prefix(handler);
 }
 
 static int
@@ -736,11 +740,10 @@ ext4_xattr_list_entries(struct dentry *dentry, struct ext4_xattr_entry *entry,
 	size_t rest = buffer_size;
 
 	for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
-		const struct xattr_handler *handler =
-			ext4_xattr_handler(entry->e_name_index);
+		const char *prefix;
 
-		if (handler && (!handler->list || handler->list(dentry))) {
-			const char *prefix = handler->prefix ?: handler->name;
+		prefix = ext4_xattr_prefix(entry->e_name_index, dentry);
+		if (prefix) {
 			size_t prefix_len = strlen(prefix);
 			size_t size = prefix_len + entry->e_name_len + 1;
 
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 37cfc0302251..c8a265966a6c 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -212,13 +212,18 @@ const struct xattr_handler *f2fs_xattr_handlers[] = {
 	NULL,
 };
 
-static inline const struct xattr_handler *f2fs_xattr_handler(int index)
+static inline const char *f2fs_xattr_prefix(int index,
+					    struct dentry *dentry)
 {
 	const struct xattr_handler *handler = NULL;
 
 	if (index > 0 && index < ARRAY_SIZE(f2fs_xattr_handler_map))
 		handler = f2fs_xattr_handler_map[index];
-	return handler;
+
+	if (!xattr_handler_can_list(handler, dentry))
+		return NULL;
+
+	return xattr_prefix(handler);
 }
 
 static struct f2fs_xattr_entry *__find_xattr(void *base_addr,
@@ -569,12 +574,12 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 	last_base_addr = (void *)base_addr + XATTR_SIZE(inode);
 
 	list_for_each_xattr(entry, base_addr) {
-		const struct xattr_handler *handler =
-			f2fs_xattr_handler(entry->e_name_index);
 		const char *prefix;
 		size_t prefix_len;
 		size_t size;
 
+		prefix = f2fs_xattr_prefix(entry->e_name_index, dentry);
+
 		if ((void *)(entry) + sizeof(__u32) > last_base_addr ||
 			(void *)XATTR_NEXT_ENTRY(entry) > last_base_addr) {
 			f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr",
@@ -586,10 +591,9 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 			goto cleanup;
 		}
 
-		if (!handler || (handler->list && !handler->list(dentry)))
+		if (!prefix)
 			continue;
 
-		prefix = xattr_prefix(handler);
 		prefix_len = strlen(prefix);
 		size = prefix_len + entry->e_name_len + 1;
 		if (buffer) {
diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c
index 0eaec4a0f3b1..1189a70d2007 100644
--- a/fs/jffs2/xattr.c
+++ b/fs/jffs2/xattr.c
@@ -924,8 +924,9 @@ const struct xattr_handler *jffs2_xattr_handlers[] = {
 	NULL
 };
 
-static const struct xattr_handler *xprefix_to_handler(int xprefix) {
-	const struct xattr_handler *ret;
+static const char *jffs2_xattr_prefix(int xprefix, struct dentry *dentry)
+{
+	const struct xattr_handler *ret = NULL;
 
 	switch (xprefix) {
 	case JFFS2_XPREFIX_USER:
@@ -948,10 +949,13 @@ static const struct xattr_handler *xprefix_to_handler(int xprefix) {
 		ret = &jffs2_trusted_xattr_handler;
 		break;
 	default:
-		ret = NULL;
-		break;
+		return NULL;
 	}
-	return ret;
+
+	if (!xattr_handler_can_list(ret, dentry))
+		return NULL;
+
+	return xattr_prefix(ret);
 }
 
 ssize_t jffs2_listxattr(struct dentry *dentry, char *buffer, size_t size)
@@ -962,7 +966,6 @@ ssize_t jffs2_listxattr(struct dentry *dentry, char *buffer, size_t size)
 	struct jffs2_inode_cache *ic = f->inocache;
 	struct jffs2_xattr_ref *ref, **pref;
 	struct jffs2_xattr_datum *xd;
-	const struct xattr_handler *xhandle;
 	const char *prefix;
 	ssize_t prefix_len, len, rc;
 	int retry = 0;
@@ -994,10 +997,10 @@ ssize_t jffs2_listxattr(struct dentry *dentry, char *buffer, size_t size)
 					goto out;
 			}
 		}
-		xhandle = xprefix_to_handler(xd->xprefix);
-		if (!xhandle || (xhandle->list && !xhandle->list(dentry)))
+
+		prefix = jffs2_xattr_prefix(xd->xprefix, dentry);
+		if (!prefix)
 			continue;
-		prefix = xhandle->prefix ?: xhandle->name;
 		prefix_len = strlen(prefix);
 		rc = prefix_len + xd->name_len + 1;
 

From 387b96a5891c075986afbf13e84cba357710068e Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 1 Feb 2023 14:14:57 +0100
Subject: [PATCH 08/67] reiserfs: rework ->listxattr() implementation

Rework reiserfs so it doesn't have to rely on the dummy xattr handlers
in its s_xattr list anymore as this is completely unused for setting and
getting posix acls.

Cc: reiserfs-devel@vger.kernel.org
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
---
 fs/reiserfs/xattr.c | 48 ++++++++++++++++++++++++---------------------
 1 file changed, 26 insertions(+), 22 deletions(-)

diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 06d810c72c52..354b74bc8072 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -52,6 +52,7 @@
 #include <linux/quotaops.h>
 #include <linux/security.h>
 #include <linux/posix_acl_xattr.h>
+#include <linux/xattr.h>
 
 #define PRIVROOT_NAME ".reiserfs_priv"
 #define XAROOT_NAME   "xattrs"
@@ -770,23 +771,34 @@ out:
 			(handler) != NULL;			\
 			(handler) = *(handlers)++)
 
-/* This is the implementation for the xattr plugin infrastructure */
-static inline const struct xattr_handler *
-find_xattr_handler_prefix(const struct xattr_handler **handlers,
-			   const char *name)
+static inline bool reiserfs_posix_acl_list(const char *name,
+					   struct dentry *dentry)
 {
-	const struct xattr_handler *xah;
+	return (posix_acl_type(name) >= 0) &&
+	       IS_POSIXACL(d_backing_inode(dentry));
+}
 
-	if (!handlers)
-		return NULL;
+/* This is the implementation for the xattr plugin infrastructure */
+static inline bool reiserfs_xattr_list(const struct xattr_handler **handlers,
+				       const char *name, struct dentry *dentry)
+{
+	if (handlers) {
+		const struct xattr_handler *xah = NULL;
 
-	for_each_xattr_handler(handlers, xah) {
-		const char *prefix = xattr_prefix(xah);
-		if (strncmp(prefix, name, strlen(prefix)) == 0)
-			break;
+		for_each_xattr_handler(handlers, xah) {
+			const char *prefix = xattr_prefix(xah);
+
+			if (strncmp(prefix, name, strlen(prefix)))
+				continue;
+
+			if (!xattr_handler_can_list(xah, dentry))
+				return false;
+
+			return true;
+		}
 	}
 
-	return xah;
+	return reiserfs_posix_acl_list(name, dentry);
 }
 
 struct listxattr_buf {
@@ -807,12 +819,8 @@ static bool listxattr_filler(struct dir_context *ctx, const char *name,
 
 	if (name[0] != '.' ||
 	    (namelen != 1 && (name[1] != '.' || namelen != 2))) {
-		const struct xattr_handler *handler;
-
-		handler = find_xattr_handler_prefix(b->dentry->d_sb->s_xattr,
-						    name);
-		if (!handler /* Unsupported xattr name */ ||
-		    (handler->list && !handler->list(b->dentry)))
+		if (!reiserfs_xattr_list(b->dentry->d_sb->s_xattr, name,
+					 b->dentry))
 			return true;
 		size = namelen + 1;
 		if (b->buf) {
@@ -910,10 +918,6 @@ const struct xattr_handler *reiserfs_xattr_handlers[] = {
 #endif
 #ifdef CONFIG_REISERFS_FS_SECURITY
 	&reiserfs_xattr_security_handler,
-#endif
-#ifdef CONFIG_REISERFS_FS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
 #endif
 	NULL
 };

From d549b741740e63e87e661754e2d1b336fdc51d50 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 1 Feb 2023 14:14:58 +0100
Subject: [PATCH 09/67] fs: rename generic posix acl handlers

Reflect in their naming and document that they are kept around for
legacy reasons and shouldn't be used anymore by new code.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
---
 fs/erofs/xattr.h                |  6 ++----
 fs/ext2/xattr.c                 |  4 ++--
 fs/ext4/xattr.c                 |  4 ++--
 fs/f2fs/xattr.c                 |  4 ++--
 fs/jffs2/xattr.c                |  4 ++--
 fs/ocfs2/xattr.c                | 12 +++++-------
 fs/posix_acl.c                  | 24 ++++++++++++++++++------
 include/linux/posix_acl_xattr.h |  5 +++--
 8 files changed, 36 insertions(+), 27 deletions(-)

diff --git a/fs/erofs/xattr.h b/fs/erofs/xattr.h
index 08658e414c33..97185cb649b6 100644
--- a/fs/erofs/xattr.h
+++ b/fs/erofs/xattr.h
@@ -49,10 +49,8 @@ static inline const char *erofs_xattr_prefix(unsigned int idx,
 	static const struct xattr_handler *xattr_handler_map[] = {
 		[EROFS_XATTR_INDEX_USER] = &erofs_xattr_user_handler,
 #ifdef CONFIG_EROFS_FS_POSIX_ACL
-		[EROFS_XATTR_INDEX_POSIX_ACL_ACCESS] =
-			&posix_acl_access_xattr_handler,
-		[EROFS_XATTR_INDEX_POSIX_ACL_DEFAULT] =
-			&posix_acl_default_xattr_handler,
+		[EROFS_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access,
+		[EROFS_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default,
 #endif
 		[EROFS_XATTR_INDEX_TRUSTED] = &erofs_xattr_trusted_handler,
 #ifdef CONFIG_EROFS_FS_SECURITY
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index 958976f809f5..b126af5f8b15 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -101,8 +101,8 @@ static void ext2_xattr_rehash(struct ext2_xattr_header *,
 static const struct xattr_handler *ext2_xattr_handler_map[] = {
 	[EXT2_XATTR_INDEX_USER]		     = &ext2_xattr_user_handler,
 #ifdef CONFIG_EXT2_FS_POSIX_ACL
-	[EXT2_XATTR_INDEX_POSIX_ACL_ACCESS]  = &posix_acl_access_xattr_handler,
-	[EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT] = &posix_acl_default_xattr_handler,
+	[EXT2_XATTR_INDEX_POSIX_ACL_ACCESS]  = &nop_posix_acl_access,
+	[EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default,
 #endif
 	[EXT2_XATTR_INDEX_TRUSTED]	     = &ext2_xattr_trusted_handler,
 #ifdef CONFIG_EXT2_FS_SECURITY
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 09a9fade2053..839020b7a222 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -88,8 +88,8 @@ static void ext4_xattr_rehash(struct ext4_xattr_header *);
 static const struct xattr_handler * const ext4_xattr_handler_map[] = {
 	[EXT4_XATTR_INDEX_USER]		     = &ext4_xattr_user_handler,
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
-	[EXT4_XATTR_INDEX_POSIX_ACL_ACCESS]  = &posix_acl_access_xattr_handler,
-	[EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &posix_acl_default_xattr_handler,
+	[EXT4_XATTR_INDEX_POSIX_ACL_ACCESS]  = &nop_posix_acl_access,
+	[EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default,
 #endif
 	[EXT4_XATTR_INDEX_TRUSTED]	     = &ext4_xattr_trusted_handler,
 #ifdef CONFIG_EXT4_FS_SECURITY
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index c8a265966a6c..213805d3592c 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -192,8 +192,8 @@ const struct xattr_handler f2fs_xattr_security_handler = {
 static const struct xattr_handler *f2fs_xattr_handler_map[] = {
 	[F2FS_XATTR_INDEX_USER] = &f2fs_xattr_user_handler,
 #ifdef CONFIG_F2FS_FS_POSIX_ACL
-	[F2FS_XATTR_INDEX_POSIX_ACL_ACCESS] = &posix_acl_access_xattr_handler,
-	[F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT] = &posix_acl_default_xattr_handler,
+	[F2FS_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access,
+	[F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default,
 #endif
 	[F2FS_XATTR_INDEX_TRUSTED] = &f2fs_xattr_trusted_handler,
 #ifdef CONFIG_F2FS_FS_SECURITY
diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c
index 1189a70d2007..aa4048a27f31 100644
--- a/fs/jffs2/xattr.c
+++ b/fs/jffs2/xattr.c
@@ -939,10 +939,10 @@ static const char *jffs2_xattr_prefix(int xprefix, struct dentry *dentry)
 #endif
 #ifdef CONFIG_JFFS2_FS_POSIX_ACL
 	case JFFS2_XPREFIX_ACL_ACCESS:
-		ret = &posix_acl_access_xattr_handler;
+		ret = &nop_posix_acl_access;
 		break;
 	case JFFS2_XPREFIX_ACL_DEFAULT:
-		ret = &posix_acl_default_xattr_handler;
+		ret = &nop_posix_acl_default;
 		break;
 #endif
 	case JFFS2_XPREFIX_TRUSTED:
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 10dab2a7b2e2..83881bb4eace 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -95,13 +95,11 @@ const struct xattr_handler *ocfs2_xattr_handlers[] = {
 };
 
 static const struct xattr_handler *ocfs2_xattr_handler_map[OCFS2_XATTR_MAX] = {
-	[OCFS2_XATTR_INDEX_USER]	= &ocfs2_xattr_user_handler,
-	[OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS]
-					= &posix_acl_access_xattr_handler,
-	[OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT]
-					= &posix_acl_default_xattr_handler,
-	[OCFS2_XATTR_INDEX_TRUSTED]	= &ocfs2_xattr_trusted_handler,
-	[OCFS2_XATTR_INDEX_SECURITY]	= &ocfs2_xattr_security_handler,
+	[OCFS2_XATTR_INDEX_USER]		= &ocfs2_xattr_user_handler,
+	[OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS]	= &nop_posix_acl_access,
+	[OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT]	= &nop_posix_acl_default,
+	[OCFS2_XATTR_INDEX_TRUSTED]		= &ocfs2_xattr_trusted_handler,
+	[OCFS2_XATTR_INDEX_SECURITY]		= &ocfs2_xattr_security_handler,
 };
 
 struct ocfs2_xattr_info {
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index b350e8396adb..e262c428f869 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -988,19 +988,31 @@ posix_acl_xattr_list(struct dentry *dentry)
 	return IS_POSIXACL(d_backing_inode(dentry));
 }
 
-const struct xattr_handler posix_acl_access_xattr_handler = {
+/*
+ * nop_posix_acl_access - legacy xattr handler for access POSIX ACLs
+ *
+ * This is the legacy POSIX ACL access xattr handler. It is used by some
+ * filesystems to implement their ->listxattr() inode operation. New code
+ * should never use them.
+ */
+const struct xattr_handler nop_posix_acl_access = {
 	.name = XATTR_NAME_POSIX_ACL_ACCESS,
-	.flags = ACL_TYPE_ACCESS,
 	.list = posix_acl_xattr_list,
 };
-EXPORT_SYMBOL_GPL(posix_acl_access_xattr_handler);
+EXPORT_SYMBOL_GPL(nop_posix_acl_access);
 
-const struct xattr_handler posix_acl_default_xattr_handler = {
+/*
+ * nop_posix_acl_default - legacy xattr handler for default POSIX ACLs
+ *
+ * This is the legacy POSIX ACL default xattr handler. It is used by some
+ * filesystems to implement their ->listxattr() inode operation. New code
+ * should never use them.
+ */
+const struct xattr_handler nop_posix_acl_default = {
 	.name = XATTR_NAME_POSIX_ACL_DEFAULT,
-	.flags = ACL_TYPE_DEFAULT,
 	.list = posix_acl_xattr_list,
 };
-EXPORT_SYMBOL_GPL(posix_acl_default_xattr_handler);
+EXPORT_SYMBOL_GPL(nop_posix_acl_default);
 
 int simple_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 		   struct posix_acl *acl, int type)
diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h
index 54cd7a14330d..e86f3b731da2 100644
--- a/include/linux/posix_acl_xattr.h
+++ b/include/linux/posix_acl_xattr.h
@@ -68,7 +68,8 @@ static inline int posix_acl_type(const char *name)
 	return -1;
 }
 
-extern const struct xattr_handler posix_acl_access_xattr_handler;
-extern const struct xattr_handler posix_acl_default_xattr_handler;
+/* These are legacy handlers. Don't use them for new code. */
+extern const struct xattr_handler nop_posix_acl_access;
+extern const struct xattr_handler nop_posix_acl_default;
 
 #endif	/* _POSIX_ACL_XATTR_H */

From d9f892b9bdc22b12bc960837a09f014d5a324975 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 1 Feb 2023 14:14:59 +0100
Subject: [PATCH 10/67] reiserfs: rework priv inode handling

Reiserfs is the only filesystem that removes IOP_XATTR without also
using a set of dedicated inode operations at the same time that nop all
xattr related inode operations. This means we need to have a IOP_XATTR
check in vfs_listxattr() instead of just being able to check for
->listxatt() being implemented.

Introduce a dedicated set of nop inode operations that are used when
IOP_XATTR is removed, allowing us to remove that check from
vfs_listxattr(). This in turn allows us to completely decouple POSIX ACLs from
IOP_XATTR.

Cc: reiserfs-devel@vger.kernel.org
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
---
 fs/reiserfs/file.c     |  7 ++++++
 fs/reiserfs/inode.c    |  6 ++---
 fs/reiserfs/namei.c    | 50 +++++++++++++++++++++++++++++++++++++-----
 fs/reiserfs/reiserfs.h |  2 ++
 fs/reiserfs/xattr.c    |  9 +++-----
 5 files changed, 59 insertions(+), 15 deletions(-)

diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 467d13da198f..b54cc7048f02 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -261,3 +261,10 @@ const struct inode_operations reiserfs_file_inode_operations = {
 	.fileattr_get = reiserfs_fileattr_get,
 	.fileattr_set = reiserfs_fileattr_set,
 };
+
+const struct inode_operations reiserfs_priv_file_inode_operations = {
+	.setattr = reiserfs_setattr,
+	.permission = reiserfs_permission,
+	.fileattr_get = reiserfs_fileattr_get,
+	.fileattr_set = reiserfs_fileattr_set,
+};
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index d54cab854f60..d8debbb6105f 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -2087,10 +2087,8 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 	 * Mark it private if we're creating the privroot
 	 * or something under it.
 	 */
-	if (IS_PRIVATE(dir) || dentry == REISERFS_SB(sb)->priv_root) {
-		inode->i_flags |= S_PRIVATE;
-		inode->i_opflags &= ~IOP_XATTR;
-	}
+	if (IS_PRIVATE(dir) || dentry == REISERFS_SB(sb)->priv_root)
+		reiserfs_init_priv_inode(inode);
 
 	if (reiserfs_posixacl(inode->i_sb)) {
 		reiserfs_write_unlock(inode->i_sb);
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index 42d2c20e1345..52240cc891cf 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -378,13 +378,11 @@ static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry,
 
 		/*
 		 * Propagate the private flag so we know we're
-		 * in the priv tree.  Also clear IOP_XATTR
+		 * in the priv tree.  Also clear xattr support
 		 * since we don't have xattrs on xattr files.
 		 */
-		if (IS_PRIVATE(dir)) {
-			inode->i_flags |= S_PRIVATE;
-			inode->i_opflags &= ~IOP_XATTR;
-		}
+		if (IS_PRIVATE(dir))
+			reiserfs_init_priv_inode(inode);
 	}
 	reiserfs_write_unlock(dir->i_sb);
 	if (retval == IO_ERROR) {
@@ -1649,6 +1647,48 @@ static int reiserfs_rename(struct mnt_idmap *idmap,
 	return retval;
 }
 
+static const struct inode_operations reiserfs_priv_dir_inode_operations = {
+	.create = reiserfs_create,
+	.lookup = reiserfs_lookup,
+	.link = reiserfs_link,
+	.unlink = reiserfs_unlink,
+	.symlink = reiserfs_symlink,
+	.mkdir = reiserfs_mkdir,
+	.rmdir = reiserfs_rmdir,
+	.mknod = reiserfs_mknod,
+	.rename = reiserfs_rename,
+	.setattr = reiserfs_setattr,
+	.permission = reiserfs_permission,
+	.fileattr_get = reiserfs_fileattr_get,
+	.fileattr_set = reiserfs_fileattr_set,
+};
+
+static const struct inode_operations reiserfs_priv_symlink_inode_operations = {
+	.get_link	= page_get_link,
+	.setattr = reiserfs_setattr,
+	.permission = reiserfs_permission,
+};
+
+static const struct inode_operations reiserfs_priv_special_inode_operations = {
+	.setattr = reiserfs_setattr,
+	.permission = reiserfs_permission,
+};
+
+void reiserfs_init_priv_inode(struct inode *inode)
+{
+	inode->i_flags |= S_PRIVATE;
+	inode->i_opflags &= ~IOP_XATTR;
+
+	if (S_ISREG(inode->i_mode))
+		inode->i_op = &reiserfs_priv_file_inode_operations;
+	else if (S_ISDIR(inode->i_mode))
+		inode->i_op = &reiserfs_priv_dir_inode_operations;
+	else if (S_ISLNK(inode->i_mode))
+		inode->i_op = &reiserfs_priv_symlink_inode_operations;
+	else
+		inode->i_op = &reiserfs_priv_special_inode_operations;
+}
+
 /* directories can handle most operations...  */
 const struct inode_operations reiserfs_dir_inode_operations = {
 	.create = reiserfs_create,
diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h
index 98e6f53c2fe0..1bccf6a2e908 100644
--- a/fs/reiserfs/reiserfs.h
+++ b/fs/reiserfs/reiserfs.h
@@ -3106,6 +3106,7 @@ int reiserfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 int __reiserfs_write_begin(struct page *page, unsigned from, unsigned len);
 
 /* namei.c */
+void reiserfs_init_priv_inode(struct inode *inode);
 void set_de_name_and_namelen(struct reiserfs_dir_entry *de);
 int search_by_entry_key(struct super_block *sb, const struct cpu_key *key,
 			struct treepath *path, struct reiserfs_dir_entry *de);
@@ -3175,6 +3176,7 @@ void reiserfs_unmap_buffer(struct buffer_head *);
 
 /* file.c */
 extern const struct inode_operations reiserfs_file_inode_operations;
+extern const struct inode_operations reiserfs_priv_file_inode_operations;
 extern const struct file_operations reiserfs_file_operations;
 extern const struct address_space_operations reiserfs_address_space_operations;
 
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 354b74bc8072..651027967159 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -896,8 +896,7 @@ static int create_privroot(struct dentry *dentry)
 		return -EOPNOTSUPP;
 	}
 
-	d_inode(dentry)->i_flags |= S_PRIVATE;
-	d_inode(dentry)->i_opflags &= ~IOP_XATTR;
+	reiserfs_init_priv_inode(d_inode(dentry));
 	reiserfs_info(dentry->d_sb, "Created %s - reserved for xattr "
 		      "storage.\n", PRIVROOT_NAME);
 
@@ -979,10 +978,8 @@ int reiserfs_lookup_privroot(struct super_block *s)
 	if (!IS_ERR(dentry)) {
 		REISERFS_SB(s)->priv_root = dentry;
 		d_set_d_op(dentry, &xattr_lookup_poison_ops);
-		if (d_really_is_positive(dentry)) {
-			d_inode(dentry)->i_flags |= S_PRIVATE;
-			d_inode(dentry)->i_opflags &= ~IOP_XATTR;
-		}
+		if (d_really_is_positive(dentry))
+			reiserfs_init_priv_inode(d_inode(dentry));
 	} else
 		err = PTR_ERR(dentry);
 	inode_unlock(d_inode(s->s_root));

From a1fbb607340d49f208e90cc0d7bdfff2141cce8d Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 1 Feb 2023 14:15:00 +0100
Subject: [PATCH 11/67] ovl: check for ->listxattr() support

We have decoupled vfs_listxattr() from IOP_XATTR. Instead we just need
to check whether inode->i_op->listxattr is implemented.

Cc: linux-unionfs@vger.kernel.org
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
---
 fs/overlayfs/copy_up.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index c14e90764e35..f658cc8ea492 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -81,8 +81,7 @@ int ovl_copy_xattr(struct super_block *sb, const struct path *oldpath, struct de
 	int error = 0;
 	size_t slen;
 
-	if (!(old->d_inode->i_opflags & IOP_XATTR) ||
-	    !(new->d_inode->i_opflags & IOP_XATTR))
+	if (!old->d_inode->i_op->listxattr || !new->d_inode->i_op->listxattr)
 		return 0;
 
 	list_size = vfs_listxattr(old, NULL, 0);

From e499214ce3ef50c50522719e753a1ffc928c2ec1 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 1 Feb 2023 14:15:01 +0100
Subject: [PATCH 12/67] acl: don't depend on IOP_XATTR

All codepaths that don't want to implement POSIX ACLs should simply not
implement the associated inode operations instead of relying on
IOP_XATTR. That's the case for all filesystems today.

For vfs_listxattr() all filesystems that explicitly turn of xattrs for a
given inode all set inode->i_op to a dedicated set of inode operations
that doesn't implement ->listxattr().  We can remove the dependency of
vfs_listxattr() on IOP_XATTR.

Removing this dependency will allow us to decouple POSIX ACLs from
IOP_XATTR and they can still be listed even if no other xattr handlers
are implemented. Otherwise we would have to implement elaborate schemes
to raise IOP_XATTR even if sb->s_xattr is set to NULL.

Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
---
 fs/posix_acl.c | 12 ++++--------
 fs/xattr.c     | 25 ++++++++++++++++++++++++-
 2 files changed, 28 insertions(+), 9 deletions(-)

diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index e262c428f869..7fa1b738bbab 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -1131,12 +1131,10 @@ retry_deleg:
 	if (error)
 		goto out_inode_unlock;
 
-	if (inode->i_opflags & IOP_XATTR)
+	if (likely(!is_bad_inode(inode)))
 		error = set_posix_acl(idmap, dentry, acl_type, kacl);
-	else if (unlikely(is_bad_inode(inode)))
-		error = -EIO;
 	else
-		error = -EOPNOTSUPP;
+		error = -EIO;
 	if (!error) {
 		fsnotify_xattr(dentry);
 		evm_inode_post_set_acl(dentry, acl_name, kacl);
@@ -1241,12 +1239,10 @@ retry_deleg:
 	if (error)
 		goto out_inode_unlock;
 
-	if (inode->i_opflags & IOP_XATTR)
+	if (likely(!is_bad_inode(inode)))
 		error = set_posix_acl(idmap, dentry, acl_type, NULL);
-	else if (unlikely(is_bad_inode(inode)))
-		error = -EIO;
 	else
-		error = -EOPNOTSUPP;
+		error = -EIO;
 	if (!error) {
 		fsnotify_xattr(dentry);
 		evm_inode_post_remove_acl(idmap, dentry, acl_name);
diff --git a/fs/xattr.c b/fs/xattr.c
index 95bb6b30ab13..fcf67d80d7f9 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -458,6 +458,28 @@ nolsm:
 }
 EXPORT_SYMBOL_GPL(vfs_getxattr);
 
+/**
+ * vfs_listxattr - retrieve \0 separated list of xattr names
+ * @dentry: the dentry from whose inode the xattr names are retrieved
+ * @list: buffer to store xattr names into
+ * @size: size of the buffer
+ *
+ * This function returns the names of all xattrs associated with the
+ * inode of @dentry.
+ *
+ * Note, for legacy reasons the vfs_listxattr() function lists POSIX
+ * ACLs as well. Since POSIX ACLs are decoupled from IOP_XATTR the
+ * vfs_listxattr() function doesn't check for this flag since a
+ * filesystem could implement POSIX ACLs without implementing any other
+ * xattrs.
+ *
+ * However, since all codepaths that remove IOP_XATTR also assign of
+ * inode operations that either don't implement or implement a stub
+ * ->listxattr() operation.
+ *
+ * Return: On success, the size of the buffer that was used. On error a
+ *         negative error code.
+ */
 ssize_t
 vfs_listxattr(struct dentry *dentry, char *list, size_t size)
 {
@@ -467,7 +489,8 @@ vfs_listxattr(struct dentry *dentry, char *list, size_t size)
 	error = security_inode_listxattr(dentry);
 	if (error)
 		return error;
-	if (inode->i_op->listxattr && (inode->i_opflags & IOP_XATTR)) {
+
+	if (inode->i_op->listxattr) {
 		error = inode->i_op->listxattr(dentry, list, size);
 	} else {
 		error = security_inode_listsecurity(inode, list, size);

From 9e22031a5a6c038089dfd4220012c7fb7f1631af Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 7 Mar 2023 15:31:23 +0100
Subject: [PATCH 13/67] ufs: don't flush page immediately for DIRSYNC
 directories

We do not need to writeout modified directory blocks immediately when
modifying them while the page is locked. It is enough to do the flush
somewhat later which has the added benefit that inode times can be
flushed as well. It also allows us to stop depending on
write_one_page() function.

Ported from an ext2 patch by Jan Kara.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/ufs/dir.c | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c
index 391efaf1d528..379d75796a5c 100644
--- a/fs/ufs/dir.c
+++ b/fs/ufs/dir.c
@@ -42,11 +42,10 @@ static inline int ufs_match(struct super_block *sb, int len,
 	return !memcmp(name, de->d_name, len);
 }
 
-static int ufs_commit_chunk(struct page *page, loff_t pos, unsigned len)
+static void ufs_commit_chunk(struct page *page, loff_t pos, unsigned len)
 {
 	struct address_space *mapping = page->mapping;
 	struct inode *dir = mapping->host;
-	int err = 0;
 
 	inode_inc_iversion(dir);
 	block_write_end(NULL, mapping, pos, len, len, page, NULL);
@@ -54,10 +53,16 @@ static int ufs_commit_chunk(struct page *page, loff_t pos, unsigned len)
 		i_size_write(dir, pos+len);
 		mark_inode_dirty(dir);
 	}
-	if (IS_DIRSYNC(dir))
-		err = write_one_page(page);
-	else
-		unlock_page(page);
+	unlock_page(page);
+}
+
+static int ufs_handle_dirsync(struct inode *dir)
+{
+	int err;
+
+	err = filemap_write_and_wait(dir->i_mapping);
+	if (!err)
+		err = sync_inode_metadata(dir, 1);
 	return err;
 }
 
@@ -99,11 +104,12 @@ void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de,
 	de->d_ino = cpu_to_fs32(dir->i_sb, inode->i_ino);
 	ufs_set_de_type(dir->i_sb, de, inode->i_mode);
 
-	err = ufs_commit_chunk(page, pos, len);
+	ufs_commit_chunk(page, pos, len);
 	ufs_put_page(page);
 	if (update_times)
 		dir->i_mtime = dir->i_ctime = current_time(dir);
 	mark_inode_dirty(dir);
+	ufs_handle_dirsync(dir);
 }
 
 
@@ -390,10 +396,11 @@ got_it:
 	de->d_ino = cpu_to_fs32(sb, inode->i_ino);
 	ufs_set_de_type(sb, de, inode->i_mode);
 
-	err = ufs_commit_chunk(page, pos, rec_len);
+	ufs_commit_chunk(page, pos, rec_len);
 	dir->i_mtime = dir->i_ctime = current_time(dir);
 
 	mark_inode_dirty(dir);
+	err = ufs_handle_dirsync(dir);
 	/* OFFSET_CACHE */
 out_put:
 	ufs_put_page(page);
@@ -531,9 +538,10 @@ int ufs_delete_entry(struct inode *inode, struct ufs_dir_entry *dir,
 	if (pde)
 		pde->d_reclen = cpu_to_fs16(sb, to - from);
 	dir->d_ino = 0;
-	err = ufs_commit_chunk(page, pos, to - from);
+	ufs_commit_chunk(page, pos, to - from);
 	inode->i_ctime = inode->i_mtime = current_time(inode);
 	mark_inode_dirty(inode);
+	err = ufs_handle_dirsync(inode);
 out:
 	ufs_put_page(page);
 	UFSD("EXIT\n");
@@ -579,7 +587,8 @@ int ufs_make_empty(struct inode * inode, struct inode *dir)
 	strcpy (de->d_name, "..");
 	kunmap(page);
 
-	err = ufs_commit_chunk(page, 0, chunk_size);
+	ufs_commit_chunk(page, 0, chunk_size);
+	err = ufs_handle_dirsync(inode);
 fail:
 	put_page(page);
 	return err;

From 8e4bfd136410df75c915fb462914b36e6e5fdfc0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 18 Jan 2023 18:30:27 +0100
Subject: [PATCH 14/67] ocfs2: don't use write_one_page in
 ocfs2_duplicate_clusters_by_page

Use filemap_write_and_wait_range to write back the range of the dirty
page instead of write_one_page in preparation of removing write_one_page
and eventually ->writepage.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/ocfs2/refcounttree.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 5a656dc683f1..564ab48d03ef 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -2952,10 +2952,11 @@ retry:
 		 */
 		if (PAGE_SIZE <= OCFS2_SB(sb)->s_clustersize) {
 			if (PageDirty(page)) {
-				/*
-				 * write_on_page will unlock the page on return
-				 */
-				ret = write_one_page(page);
+				unlock_page(page);
+				put_page(page);
+
+				ret = filemap_write_and_wait_range(mapping,
+						offset, map_end - 1);
 				goto retry;
 			}
 		}

From 2d683175827171c982f91996fdbef4f3fd8b1b01 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 7 Mar 2023 15:31:25 +0100
Subject: [PATCH 15/67] mm,jfs: move write_one_page/folio_write_one to jfs

The last remaining user of folio_write_one through the write_one_page
wrapper is jfs, so move the functionality there and hard code the
call to metapage_writepage.

Note that the use of the pagecache by the JFS 'metapage' buffer cache
is a bit odd, and we could probably do without VM-level dirty tracking
at all, but that's a change for another time.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/jfs/jfs_metapage.c   | 39 ++++++++++++++++++++++++++++++++++-----
 include/linux/pagemap.h |  6 ------
 mm/page-writeback.c     | 40 ----------------------------------------
 3 files changed, 34 insertions(+), 51 deletions(-)

diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index 2e8461ce74de..961569c11159 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -691,6 +691,35 @@ void grab_metapage(struct metapage * mp)
 	unlock_page(mp->page);
 }
 
+static int metapage_write_one(struct page *page)
+{
+	struct folio *folio = page_folio(page);
+	struct address_space *mapping = folio->mapping;
+	struct writeback_control wbc = {
+		.sync_mode = WB_SYNC_ALL,
+		.nr_to_write = folio_nr_pages(folio),
+	};
+	int ret = 0;
+
+	BUG_ON(!folio_test_locked(folio));
+
+	folio_wait_writeback(folio);
+
+	if (folio_clear_dirty_for_io(folio)) {
+		folio_get(folio);
+		ret = metapage_writepage(page, &wbc);
+		if (ret == 0)
+			folio_wait_writeback(folio);
+		folio_put(folio);
+	} else {
+		folio_unlock(folio);
+	}
+
+	if (!ret)
+		ret = filemap_check_errors(mapping);
+	return ret;
+}
+
 void force_metapage(struct metapage *mp)
 {
 	struct page *page = mp->page;
@@ -700,8 +729,8 @@ void force_metapage(struct metapage *mp)
 	get_page(page);
 	lock_page(page);
 	set_page_dirty(page);
-	if (write_one_page(page))
-		jfs_error(mp->sb, "write_one_page() failed\n");
+	if (metapage_write_one(page))
+		jfs_error(mp->sb, "metapage_write_one() failed\n");
 	clear_bit(META_forcewrite, &mp->flag);
 	put_page(page);
 }
@@ -746,9 +775,9 @@ void release_metapage(struct metapage * mp)
 		set_page_dirty(page);
 		if (test_bit(META_sync, &mp->flag)) {
 			clear_bit(META_sync, &mp->flag);
-			if (write_one_page(page))
-				jfs_error(mp->sb, "write_one_page() failed\n");
-			lock_page(page); /* write_one_page unlocks the page */
+			if (metapage_write_one(page))
+				jfs_error(mp->sb, "metapage_write_one() failed\n");
+			lock_page(page);
 		}
 	} else if (mp->lsn)	/* discard_metapage doesn't remove it */
 		remove_from_logsync(mp);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 0acb8e1fb7af..853184a46411 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -1066,12 +1066,6 @@ static inline void folio_cancel_dirty(struct folio *folio)
 bool folio_clear_dirty_for_io(struct folio *folio);
 bool clear_page_dirty_for_io(struct page *page);
 void folio_invalidate(struct folio *folio, size_t offset, size_t length);
-int __must_check folio_write_one(struct folio *folio);
-static inline int __must_check write_one_page(struct page *page)
-{
-	return folio_write_one(page_folio(page));
-}
-
 int __set_page_dirty_nobuffers(struct page *page);
 bool noop_dirty_folio(struct address_space *mapping, struct folio *folio);
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 516b1aa247e8..db7943999007 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2583,46 +2583,6 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
 	return ret;
 }
 
-/**
- * folio_write_one - write out a single folio and wait on I/O.
- * @folio: The folio to write.
- *
- * The folio must be locked by the caller and will be unlocked upon return.
- *
- * Note that the mapping's AS_EIO/AS_ENOSPC flags will be cleared when this
- * function returns.
- *
- * Return: %0 on success, negative error code otherwise
- */
-int folio_write_one(struct folio *folio)
-{
-	struct address_space *mapping = folio->mapping;
-	int ret = 0;
-	struct writeback_control wbc = {
-		.sync_mode = WB_SYNC_ALL,
-		.nr_to_write = folio_nr_pages(folio),
-	};
-
-	BUG_ON(!folio_test_locked(folio));
-
-	folio_wait_writeback(folio);
-
-	if (folio_clear_dirty_for_io(folio)) {
-		folio_get(folio);
-		ret = mapping->a_ops->writepage(&folio->page, &wbc);
-		if (ret == 0)
-			folio_wait_writeback(folio);
-		folio_put(folio);
-	} else {
-		folio_unlock(folio);
-	}
-
-	if (!ret)
-		ret = filemap_check_errors(mapping);
-	return ret;
-}
-EXPORT_SYMBOL(folio_write_one);
-
 /*
  * For address_spaces which do not use buffers nor write back.
  */

From 8ad77c576721bd7f7b24bfd7fcb0a61bcfa1a1a2 Mon Sep 17 00:00:00 2001
From: "Fabio M. De Francesco" <fmdefrancesco@gmail.com>
Date: Mon, 6 Mar 2023 13:51:50 +0100
Subject: [PATCH 16/67] fs/sysv: Don't round down address for
 kunmap_flush_on_unmap()

The kernel virtual address passed to kunmap_flush_on_unmap() has no more
any need to be rounded down.

Therefore, delete the rounding down of "page_addr" when passed to
kunmap_local() in dir_put_page().

Don't backport without commit 88d7b12068b9 ("highmem: round down the
address passed to kunmap_flush_on_unmap()").

Cc: Ira Weiny <ira.weiny@intel.com>
Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Fabio M. De Francesco <fmdefrancesco@gmail.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/sysv/dir.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c
index 999bceb99974..e2d26eb78af7 100644
--- a/fs/sysv/dir.c
+++ b/fs/sysv/dir.c
@@ -30,7 +30,7 @@ const struct file_operations sysv_dir_operations = {
 
 inline void dir_put_page(struct page *page, void *page_addr)
 {
-	kunmap_local((void *)((unsigned long)page_addr & PAGE_MASK));
+	kunmap_local(page_addr);
 	put_page(page);
 }
 

From ede3ef5c1e0766b309a1bf087e4c50ea02d3f26f Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 7 Mar 2023 01:53:52 -0500
Subject: [PATCH 17/67] sysv: switch to put_and_unmap_page()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/sysv/dir.c   | 28 +++++++++++-----------------
 fs/sysv/namei.c |  8 ++++----
 fs/sysv/sysv.h  |  1 -
 3 files changed, 15 insertions(+), 22 deletions(-)

diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c
index e2d26eb78af7..cdb3d632c63d 100644
--- a/fs/sysv/dir.c
+++ b/fs/sysv/dir.c
@@ -28,12 +28,6 @@ const struct file_operations sysv_dir_operations = {
 	.fsync		= generic_file_fsync,
 };
 
-inline void dir_put_page(struct page *page, void *page_addr)
-{
-	kunmap_local(page_addr);
-	put_page(page);
-}
-
 static void dir_commit_chunk(struct page *page, loff_t pos, unsigned len)
 {
 	struct address_space *mapping = page->mapping;
@@ -58,7 +52,7 @@ static int sysv_handle_dirsync(struct inode *dir)
 }
 
 /*
- * Calls to dir_get_page()/dir_put_page() must be nested according to the
+ * Calls to dir_get_page()/put_and_unmap_page() must be nested according to the
  * rules documented in mm/highmem.rst.
  *
  * NOTE: sysv_find_entry() and sysv_dotdot() act as calls to dir_get_page()
@@ -109,11 +103,11 @@ static int sysv_readdir(struct file *file, struct dir_context *ctx)
 			if (!dir_emit(ctx, name, strnlen(name,SYSV_NAMELEN),
 					fs16_to_cpu(SYSV_SB(sb), de->inode),
 					DT_UNKNOWN)) {
-				dir_put_page(page, kaddr);
+				put_and_unmap_page(page, kaddr);
 				return 0;
 			}
 		}
-		dir_put_page(page, kaddr);
+		put_and_unmap_page(page, kaddr);
 	}
 	return 0;
 }
@@ -137,7 +131,7 @@ static inline int namecompare(int len, int maxlen,
  * itself (as a parameter - res_dir). It does NOT read the inode of the
  * entry - you'll have to do that yourself if you want to.
  *
- * On Success dir_put_page() should be called on *res_page.
+ * On Success put_and_unmap_page() should be called on *res_page.
  *
  * sysv_find_entry() acts as a call to dir_get_page() and must be treated
  * accordingly for nesting purposes.
@@ -172,7 +166,7 @@ struct sysv_dir_entry *sysv_find_entry(struct dentry *dentry, struct page **res_
 							name, de->name))
 					goto found;
 			}
-			dir_put_page(page, kaddr);
+			put_and_unmap_page(page, kaddr);
 		}
 
 		if (++n >= npages)
@@ -215,7 +209,7 @@ int sysv_add_link(struct dentry *dentry, struct inode *inode)
 				goto out_page;
 			de++;
 		}
-		dir_put_page(page, kaddr);
+		put_and_unmap_page(page, kaddr);
 	}
 	BUG();
 	return -EINVAL;
@@ -234,7 +228,7 @@ got_it:
 	mark_inode_dirty(dir);
 	err = sysv_handle_dirsync(dir);
 out_page:
-	dir_put_page(page, kaddr);
+	put_and_unmap_page(page, kaddr);
 	return err;
 out_unlock:
 	unlock_page(page);
@@ -327,12 +321,12 @@ int sysv_empty_dir(struct inode * inode)
 			if (de->name[1] != '.' || de->name[2])
 				goto not_empty;
 		}
-		dir_put_page(page, kaddr);
+		put_and_unmap_page(page, kaddr);
 	}
 	return 1;
 
 not_empty:
-	dir_put_page(page, kaddr);
+	put_and_unmap_page(page, kaddr);
 	return 0;
 }
 
@@ -358,7 +352,7 @@ int sysv_set_link(struct sysv_dir_entry *de, struct page *page,
 }
 
 /*
- * Calls to dir_get_page()/dir_put_page() must be nested according to the
+ * Calls to dir_get_page()/put_and_unmap_page() must be nested according to the
  * rules documented in mm/highmem.rst.
  *
  * sysv_dotdot() acts as a call to dir_get_page() and must be treated
@@ -382,7 +376,7 @@ ino_t sysv_inode_by_name(struct dentry *dentry)
 	
 	if (de) {
 		res = fs16_to_cpu(SYSV_SB(dentry->d_sb), de->inode);
-		dir_put_page(page, de);
+		put_and_unmap_page(page, de);
 	}
 	return res;
 }
diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c
index a25862773d82..2b2dba4c4f56 100644
--- a/fs/sysv/namei.c
+++ b/fs/sysv/namei.c
@@ -164,7 +164,7 @@ static int sysv_unlink(struct inode * dir, struct dentry * dentry)
 		inode->i_ctime = dir->i_ctime;
 		inode_dec_link_count(inode);
 	}
-	dir_put_page(page, de);
+	put_and_unmap_page(page, de);
 	return err;
 }
 
@@ -227,7 +227,7 @@ static int sysv_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 		if (!new_de)
 			goto out_dir;
 		err = sysv_set_link(new_de, new_page, old_inode);
-		dir_put_page(new_page, new_de);
+		put_and_unmap_page(new_page, new_de);
 		if (err)
 			goto out_dir;
 		new_inode->i_ctime = current_time(new_inode);
@@ -256,9 +256,9 @@ static int sysv_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 
 out_dir:
 	if (dir_de)
-		dir_put_page(dir_page, dir_de);
+		put_and_unmap_page(dir_page, dir_de);
 out_old:
-	dir_put_page(old_page, old_de);
+	put_and_unmap_page(old_page, old_de);
 out:
 	return err;
 }
diff --git a/fs/sysv/sysv.h b/fs/sysv/sysv.h
index f2c36ea42df6..e3f988b469ee 100644
--- a/fs/sysv/sysv.h
+++ b/fs/sysv/sysv.h
@@ -148,7 +148,6 @@ extern void sysv_destroy_icache(void);
 
 
 /* dir.c */
-extern void dir_put_page(struct page *page, void *vaddr);
 extern struct sysv_dir_entry *sysv_find_entry(struct dentry *, struct page **);
 extern int sysv_add_link(struct dentry *, struct inode *);
 extern int sysv_delete_entry(struct sysv_dir_entry *, struct page *);

From 73bb5a9017b93093854c18eb7ca99c7061b16367 Mon Sep 17 00:00:00 2001
From: Roberto Sassu <roberto.sassu@huawei.com>
Date: Mon, 6 Mar 2023 11:35:31 +0100
Subject: [PATCH 18/67] fs: Fix description of vfs_tmpfile()

Update the description of vfs_tmpfile() to match the current parameters of
that function.

Fixes: 9751b338656f ("vfs: move open right after ->tmpfile()")
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Acked-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index edfedfbccaef..f04f7be58933 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3574,9 +3574,9 @@ static int do_open(struct nameidata *nd,
 /**
  * vfs_tmpfile - create tmpfile
  * @idmap:	idmap of the mount the inode was found from
- * @dentry:	pointer to dentry of the base directory
+ * @parentpath:	pointer to the path of the base directory
+ * @file:	file descriptor of the new tmpfile
  * @mode:	mode of the new tmpfile
- * @open_flag:	flags
  *
  * Create a temporary file.
  *

From 7059a9aa4b6b8c6daf257a3978a4d8c476c29a96 Mon Sep 17 00:00:00 2001
From: Changcheng Liu <changchengx.liu@outlook.com>
Date: Sun, 12 Mar 2023 17:25:22 +0800
Subject: [PATCH 19/67] eventpoll: align comment with nested epoll limitation

fix comment in commit 02edc6fc4d5f ("epoll: comment the funky #ifdef")

Signed-off-by: Liu, Changcheng <changchengx.liu@outlook.com>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
---
 fs/eventpoll.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 64659b110973..f6d25050dd7a 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -483,8 +483,8 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
  * (efd1) notices that it may have some event ready, so it needs to wake up
  * the waiters on its poll wait list (efd2). So it calls ep_poll_safewake()
  * that ends up in another wake_up(), after having checked about the
- * recursion constraints. That are, no more than EP_MAX_POLLWAKE_NESTS, to
- * avoid stack blasting.
+ * recursion constraints. That are, no more than EP_MAX_NESTS, to avoid
+ * stack blasting.
  *
  * When CONFIG_DEBUG_LOCK_ALLOC is enabled, make sure lockdep can handle
  * this special case of epoll.

From 3e27877ac565807135209933e0894d8c522cc520 Mon Sep 17 00:00:00 2001
From: Luis Chamberlain <mcgrof@kernel.org>
Date: Fri, 10 Mar 2023 15:12:03 -0800
Subject: [PATCH 20/67] devpts: simplify two-level sysctl registration for
 pty_kern_table

There is no need to declare two tables to just create directories,
this can be easily be done with a prefix path with register_sysctl().

Simplify this registration.

Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
---
 fs/devpts/inode.c | 20 +-------------------
 1 file changed, 1 insertion(+), 19 deletions(-)

diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 4f25015aa534..fe3db0eda8e4 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -72,24 +72,6 @@ static struct ctl_table pty_table[] = {
 	{}
 };
 
-static struct ctl_table pty_kern_table[] = {
-	{
-		.procname	= "pty",
-		.mode		= 0555,
-		.child		= pty_table,
-	},
-	{}
-};
-
-static struct ctl_table pty_root_table[] = {
-	{
-		.procname	= "kernel",
-		.mode		= 0555,
-		.child		= pty_kern_table,
-	},
-	{}
-};
-
 struct pts_mount_opts {
 	int setuid;
 	int setgid;
@@ -630,7 +612,7 @@ static int __init init_devpts_fs(void)
 {
 	int err = register_filesystem(&devpts_fs_type);
 	if (!err) {
-		register_sysctl_table(pty_root_table);
+		register_sysctl("kernel/pty", pty_table);
 	}
 	return err;
 }

From 5d3ca5968480758a29a0b2777da9049a7c5134e3 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Mon, 6 Mar 2023 15:11:42 +0100
Subject: [PATCH 21/67] Documentation: update idmappings.rst

Quite a lot has changed over the last few kernel releases with the
introduction of vfs{g,u}id_t and struct mnt_idmap. Update the
documentation accordingly.

Cc: Seth Forshee <sforshee@kernel.org>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
---
 Documentation/filesystems/idmappings.rst | 178 ++++++++++++++++-------
 1 file changed, 125 insertions(+), 53 deletions(-)

diff --git a/Documentation/filesystems/idmappings.rst b/Documentation/filesystems/idmappings.rst
index b9b31066aef2..ad6d21640576 100644
--- a/Documentation/filesystems/idmappings.rst
+++ b/Documentation/filesystems/idmappings.rst
@@ -241,7 +241,7 @@ according to the filesystem's idmapping as this would give the wrong owner if
 the caller is using an idmapping.
 
 So the kernel will map the id back up in the idmapping of the caller. Let's
-assume the caller has the slighly unconventional idmapping
+assume the caller has the somewhat unconventional idmapping
 ``u3000:k20000:r10000`` then ``k21000`` would map back up to ``u4000``.
 Consequently the user would see that this file is owned by ``u4000``.
 
@@ -320,6 +320,10 @@ and equally wrong::
  from_kuid(u20000:k0:r10000, u1000) = k21000
                              ~~~~~
 
+Since userspace ids have type ``uid_t`` and ``gid_t`` and kernel ids have type
+``kuid_t`` and ``kgid_t`` the compiler will throw an error when they are
+conflated. So the two examples above would cause a compilation failure.
+
 Idmappings when creating filesystem objects
 -------------------------------------------
 
@@ -623,42 +627,105 @@ privileged users in the initial user namespace.
 However, it is perfectly possible to combine idmapped mounts with filesystems
 mountable inside user namespaces. We will touch on this further below.
 
+Filesystem types vs idmapped mount types
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+With the introduction of idmapped mounts we need to distinguish between
+filesystem ownership and mount ownership of a VFS object such as an inode. The
+owner of a inode might be different when looked at from a filesystem
+perspective than when looked at from an idmapped mount. Such fundamental
+conceptual distinctions should almost always be clearly expressed in the code.
+So, to distinguish idmapped mount ownership from filesystem ownership separate
+types have been introduced.
+
+If a uid or gid has been generated using the filesystem or caller's idmapping
+then we will use the ``kuid_t`` and ``kgid_t`` types. However, if a uid or gid
+has been generated using a mount idmapping then we will be using the dedicated
+``vfsuid_t`` and ``vfsgid_t`` types.
+
+All VFS helpers that generate or take uids and gids as arguments use the
+``vfsuid_t`` and ``vfsgid_t`` types and we will be able to rely on the compiler
+to catch errors that originate from conflating filesystem and VFS uids and gids.
+
+The ``vfsuid_t`` and ``vfsgid_t`` types are often mapped from and to ``kuid_t``
+and ``kgid_t`` types similar how ``kuid_t`` and ``kgid_t`` types are mapped
+from and to ``uid_t`` and ``gid_t`` types::
+
+ uid_t <--> kuid_t <--> vfsuid_t
+ gid_t <--> kgid_t <--> vfsgid_t
+
+Whenever we report ownership based on a ``vfsuid_t`` or ``vfsgid_t`` type,
+e.g., during ``stat()``, or store ownership information in a shared VFS object
+based on a ``vfsuid_t`` or ``vfsgid_t`` type, e.g., during ``chown()`` we can
+use the ``vfsuid_into_kuid()`` and ``vfsgid_into_kgid()`` helpers.
+
+To illustrate why this helper currently exists, consider what happens when we
+change ownership of an inode from an idmapped mount. After we generated
+a ``vfsuid_t`` or ``vfsgid_t`` based on the mount idmapping we later commit to
+this ``vfsuid_t`` or ``vfsgid_t`` to become the new filesytem wide ownership.
+Thus, we are turning the ``vfsuid_t`` or ``vfsgid_t`` into a global ``kuid_t``
+or ``kgid_t``. And this can be done by using ``vfsuid_into_kuid()`` and
+``vfsgid_into_kgid()``.
+
+Note, whenever a shared VFS object, e.g., a cached ``struct inode`` or a cached
+``struct posix_acl``, stores ownership information a filesystem or "global"
+``kuid_t`` and ``kgid_t`` must be used. Ownership expressed via ``vfsuid_t``
+and ``vfsgid_t`` is specific to an idmapped mount.
+
+We already noted that ``vfsuid_t`` and ``vfsgid_t`` types are generated based
+on mount idmappings whereas ``kuid_t`` and ``kgid_t`` types are generated based
+on filesystem idmappings. To prevent abusing filesystem idmappings to generate
+``vfsuid_t`` or ``vfsgid_t`` types or mount idmappings to generate ``kuid_t``
+or ``kgid_t`` types filesystem idmappings and mount idmappings are different
+types as well.
+
+All helpers that map to or from ``vfsuid_t`` and ``vfsgid_t`` types require
+a mount idmapping to be passed which is of type ``struct mnt_idmap``. Passing
+a filesystem or caller idmapping will cause a compilation error.
+
+Similar to how we prefix all userspace ids in this document with ``u`` and all
+kernel ids with ``k`` we will prefix all VFS ids with ``v``. So a mount
+idmapping will be written as: ``u0:v10000:r10000``.
+
 Remapping helpers
 ~~~~~~~~~~~~~~~~~
 
 Idmapping functions were added that translate between idmappings. They make use
-of the remapping algorithm we've introduced earlier. We're going to look at
-two:
+of the remapping algorithm we've introduced earlier. We're going to look at:
 
-- ``i_uid_into_mnt()`` and ``i_gid_into_mnt()``
+- ``i_uid_into_vfsuid()`` and ``i_gid_into_vfsgid()``
 
-  The ``i_*id_into_mnt()`` functions translate filesystem's kernel ids into
-  kernel ids in the mount's idmapping::
+  The ``i_*id_into_vfs*id()`` functions translate filesystem's kernel ids into
+  VFS ids in the mount's idmapping::
 
    /* Map the filesystem's kernel id up into a userspace id in the filesystem's idmapping. */
    from_kuid(filesystem, kid) = uid
 
-   /* Map the filesystem's userspace id down ito a kernel id in the mount's idmapping. */
+   /* Map the filesystem's userspace id down ito a VFS id in the mount's idmapping. */
    make_kuid(mount, uid) = kuid
 
 - ``mapped_fsuid()`` and ``mapped_fsgid()``
 
   The ``mapped_fs*id()`` functions translate the caller's kernel ids into
   kernel ids in the filesystem's idmapping. This translation is achieved by
-  remapping the caller's kernel ids using the mount's idmapping::
+  remapping the caller's VFS ids using the mount's idmapping::
 
-   /* Map the caller's kernel id up into a userspace id in the mount's idmapping. */
+   /* Map the caller's VFS id up into a userspace id in the mount's idmapping. */
    from_kuid(mount, kid) = uid
 
    /* Map the mount's userspace id down into a kernel id in the filesystem's idmapping. */
    make_kuid(filesystem, uid) = kuid
 
+- ``vfsuid_into_kuid()`` and ``vfsgid_into_kgid()``
+
+   Whenever
+
 Note that these two functions invert each other. Consider the following
 idmappings::
 
  caller idmapping:     u0:k10000:r10000
  filesystem idmapping: u0:k20000:r10000
- mount idmapping:      u0:k10000:r10000
+ mount idmapping:      u0:v10000:r10000
 
 Assume a file owned by ``u1000`` is read from disk. The filesystem maps this id
 to ``k21000`` according to its idmapping. This is what is stored in the
@@ -669,20 +736,21 @@ would usually simply use the crossmapping algorithm and map the filesystem's
 kernel id up to a userspace id in the caller's idmapping.
 
 But when the caller is accessing the file on an idmapped mount the kernel will
-first call ``i_uid_into_mnt()`` thereby translating the filesystem's kernel id
-into a kernel id in the mount's idmapping::
+first call ``i_uid_into_vfsuid()`` thereby translating the filesystem's kernel
+id into a VFS id in the mount's idmapping::
 
- i_uid_into_mnt(k21000):
+ i_uid_into_vfsuid(k21000):
    /* Map the filesystem's kernel id up into a userspace id. */
    from_kuid(u0:k20000:r10000, k21000) = u1000
 
-   /* Map the filesystem's userspace id down ito a kernel id in the mount's idmapping. */
-   make_kuid(u0:k10000:r10000, u1000) = k11000
+   /* Map the filesystem's userspace id down into a VFS id in the mount's idmapping. */
+   make_kuid(u0:v10000:r10000, u1000) = v11000
 
 Finally, when the kernel reports the owner to the caller it will turn the
-kernel id in the mount's idmapping into a userspace id in the caller's
+VFS id in the mount's idmapping into a userspace id in the caller's
 idmapping::
 
+  k11000 = vfsuid_into_kuid(v11000)
   from_kuid(u0:k10000:r10000, k11000) = u1000
 
 We can test whether this algorithm really works by verifying what happens when
@@ -696,18 +764,19 @@ fails.
 
 But when the caller is accessing the file on an idmapped mount the kernel will
 first call ``mapped_fs*id()`` thereby translating the caller's kernel id into
-a kernel id according to the mount's idmapping::
+a VFS id according to the mount's idmapping::
 
  mapped_fsuid(k11000):
     /* Map the caller's kernel id up into a userspace id in the mount's idmapping. */
     from_kuid(u0:k10000:r10000, k11000) = u1000
 
     /* Map the mount's userspace id down into a kernel id in the filesystem's idmapping. */
-    make_kuid(u0:k20000:r10000, u1000) = k21000
+    make_kuid(u0:v20000:r10000, u1000) = v21000
 
-When finally writing to disk the kernel will then map ``k21000`` up into a
+When finally writing to disk the kernel will then map ``v21000`` up into a
 userspace id in the filesystem's idmapping::
 
+   k21000 = vfsuid_into_kuid(v21000)
    from_kuid(u0:k20000:r10000, k21000) = u1000
 
 As we can see, we end up with an invertible and therefore information
@@ -725,7 +794,7 @@ Example 2 reconsidered
  caller id:            u1000
  caller idmapping:     u0:k10000:r10000
  filesystem idmapping: u0:k20000:r10000
- mount idmapping:      u0:k10000:r10000
+ mount idmapping:      u0:v10000:r10000
 
 When the caller is using a non-initial idmapping the common case is to attach
 the same idmapping to the mount. We now perform three steps:
@@ -734,12 +803,12 @@ the same idmapping to the mount. We now perform three steps:
 
     make_kuid(u0:k10000:r10000, u1000) = k11000
 
-2. Translate the caller's kernel id into a kernel id in the filesystem's
+2. Translate the caller's VFS id into a kernel id in the filesystem's
    idmapping::
 
-    mapped_fsuid(k11000):
-      /* Map the kernel id up into a userspace id in the mount's idmapping. */
-      from_kuid(u0:k10000:r10000, k11000) = u1000
+    mapped_fsuid(v11000):
+      /* Map the VFS id up into a userspace id in the mount's idmapping. */
+      from_kuid(u0:v10000:r10000, v11000) = u1000
 
       /* Map the userspace id down into a kernel id in the filesystem's idmapping. */
       make_kuid(u0:k20000:r10000, u1000) = k21000
@@ -759,7 +828,7 @@ Example 3 reconsidered
  caller id:            u1000
  caller idmapping:     u0:k10000:r10000
  filesystem idmapping: u0:k0:r4294967295
- mount idmapping:      u0:k10000:r10000
+ mount idmapping:      u0:v10000:r10000
 
 The same translation algorithm works with the third example.
 
@@ -767,12 +836,12 @@ The same translation algorithm works with the third example.
 
     make_kuid(u0:k10000:r10000, u1000) = k11000
 
-2. Translate the caller's kernel id into a kernel id in the filesystem's
+2. Translate the caller's VFS id into a kernel id in the filesystem's
    idmapping::
 
-    mapped_fsuid(k11000):
-       /* Map the kernel id up into a userspace id in the mount's idmapping. */
-       from_kuid(u0:k10000:r10000, k11000) = u1000
+    mapped_fsuid(v11000):
+       /* Map the VFS id up into a userspace id in the mount's idmapping. */
+       from_kuid(u0:v10000:r10000, v11000) = u1000
 
        /* Map the userspace id down into a kernel id in the filesystem's idmapping. */
        make_kuid(u0:k0:r4294967295, u1000) = k1000
@@ -792,7 +861,7 @@ Example 4 reconsidered
  file id:              u1000
  caller idmapping:     u0:k10000:r10000
  filesystem idmapping: u0:k0:r4294967295
- mount idmapping:      u0:k10000:r10000
+ mount idmapping:      u0:v10000:r10000
 
 In order to report ownership to userspace the kernel now does three steps using
 the translation algorithm we introduced earlier:
@@ -802,17 +871,18 @@ the translation algorithm we introduced earlier:
 
     make_kuid(u0:k0:r4294967295, u1000) = k1000
 
-2. Translate the kernel id into a kernel id in the mount's idmapping::
+2. Translate the kernel id into a VFS id in the mount's idmapping::
 
-    i_uid_into_mnt(k1000):
+    i_uid_into_vfsuid(k1000):
       /* Map the kernel id up into a userspace id in the filesystem's idmapping. */
       from_kuid(u0:k0:r4294967295, k1000) = u1000
 
-      /* Map the userspace id down into a kernel id in the mounts's idmapping. */
-      make_kuid(u0:k10000:r10000, u1000) = k11000
+      /* Map the userspace id down into a VFS id in the mounts's idmapping. */
+      make_kuid(u0:v10000:r10000, u1000) = v11000
 
-3. Map the kernel id up into a userspace id in the caller's idmapping::
+3. Map the VFS id up into a userspace id in the caller's idmapping::
 
+    k11000 = vfsuid_into_kuid(v11000)
     from_kuid(u0:k10000:r10000, k11000) = u1000
 
 Earlier, the caller's kernel id couldn't be crossmapped in the filesystems's
@@ -828,7 +898,7 @@ Example 5 reconsidered
  file id:              u1000
  caller idmapping:     u0:k10000:r10000
  filesystem idmapping: u0:k20000:r10000
- mount idmapping:      u0:k10000:r10000
+ mount idmapping:      u0:v10000:r10000
 
 Again, in order to report ownership to userspace the kernel now does three
 steps using the translation algorithm we introduced earlier:
@@ -838,17 +908,18 @@ steps using the translation algorithm we introduced earlier:
 
     make_kuid(u0:k20000:r10000, u1000) = k21000
 
-2. Translate the kernel id into a kernel id in the mount's idmapping::
+2. Translate the kernel id into a VFS id in the mount's idmapping::
 
-    i_uid_into_mnt(k21000):
+    i_uid_into_vfsuid(k21000):
       /* Map the kernel id up into a userspace id in the filesystem's idmapping. */
       from_kuid(u0:k20000:r10000, k21000) = u1000
 
-      /* Map the userspace id down into a kernel id in the mounts's idmapping. */
-      make_kuid(u0:k10000:r10000, u1000) = k11000
+      /* Map the userspace id down into a VFS id in the mounts's idmapping. */
+      make_kuid(u0:v10000:r10000, u1000) = v11000
 
-3. Map the kernel id up into a userspace id in the caller's idmapping::
+3. Map the VFS id up into a userspace id in the caller's idmapping::
 
+    k11000 = vfsuid_into_kuid(v11000)
     from_kuid(u0:k10000:r10000, k11000) = u1000
 
 Earlier, the file's kernel id couldn't be crossmapped in the filesystems's
@@ -899,23 +970,23 @@ from above:::
  caller id:            u1125
  caller idmapping:     u0:k0:r4294967295
  filesystem idmapping: u0:k0:r4294967295
- mount idmapping:      u1000:k1125:r1
+ mount idmapping:      u1000:v1125:r1
 
 1. Map the caller's userspace ids into kernel ids in the caller's idmapping::
 
     make_kuid(u0:k0:r4294967295, u1125) = k1125
 
-2. Translate the caller's kernel id into a kernel id in the filesystem's
+2. Translate the caller's VFS id into a kernel id in the filesystem's
    idmapping::
 
-    mapped_fsuid(k1125):
-      /* Map the kernel id up into a userspace id in the mount's idmapping. */
-      from_kuid(u1000:k1125:r1, k1125) = u1000
+    mapped_fsuid(v1125):
+      /* Map the VFS id up into a userspace id in the mount's idmapping. */
+      from_kuid(u1000:v1125:r1, v1125) = u1000
 
       /* Map the userspace id down into a kernel id in the filesystem's idmapping. */
       make_kuid(u0:k0:r4294967295, u1000) = k1000
 
-2. Verify that the caller's kernel ids can be mapped to userspace ids in the
+2. Verify that the caller's filesystem ids can be mapped to userspace ids in the
    filesystem's idmapping::
 
     from_kuid(u0:k0:r4294967295, k1000) = u1000
@@ -930,24 +1001,25 @@ on their work computer:
  file id:              u1000
  caller idmapping:     u0:k0:r4294967295
  filesystem idmapping: u0:k0:r4294967295
- mount idmapping:      u1000:k1125:r1
+ mount idmapping:      u1000:v1125:r1
 
 1. Map the userspace id on disk down into a kernel id in the filesystem's
    idmapping::
 
     make_kuid(u0:k0:r4294967295, u1000) = k1000
 
-2. Translate the kernel id into a kernel id in the mount's idmapping::
+2. Translate the kernel id into a VFS id in the mount's idmapping::
 
-    i_uid_into_mnt(k1000):
+    i_uid_into_vfsuid(k1000):
       /* Map the kernel id up into a userspace id in the filesystem's idmapping. */
       from_kuid(u0:k0:r4294967295, k1000) = u1000
 
-      /* Map the userspace id down into a kernel id in the mounts's idmapping. */
-      make_kuid(u1000:k1125:r1, u1000) = k1125
+      /* Map the userspace id down into a VFS id in the mounts's idmapping. */
+      make_kuid(u1000:v1125:r1, u1000) = v1125
 
-3. Map the kernel id up into a userspace id in the caller's idmapping::
+3. Map the VFS id up into a userspace id in the caller's idmapping::
 
+    k1125 = vfsuid_into_kuid(v1125)
     from_kuid(u0:k0:r4294967295, k1125) = u1125
 
 So ultimately the caller will be reported that the file belongs to ``u1125``

From 74e60b8b2f0fe3702710e648a31725ee8224dbdf Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 14 Mar 2023 17:09:06 +0200
Subject: [PATCH 22/67] fs/namespace: fnic: Switch to use %ptTd

Use %ptTd instead of open-coded variant to print contents
of time64_t type in human readable form.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
---
 fs/namespace.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index bc0f15257b49..a6e4c3a3179f 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2617,15 +2617,12 @@ static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *
 	   (ktime_get_real_seconds() + TIME_UPTIME_SEC_MAX > sb->s_time_max)) {
 		char *buf = (char *)__get_free_page(GFP_KERNEL);
 		char *mntpath = buf ? d_path(mountpoint, buf, PAGE_SIZE) : ERR_PTR(-ENOMEM);
-		struct tm tm;
 
-		time64_to_tm(sb->s_time_max, 0, &tm);
-
-		pr_warn("%s filesystem being %s at %s supports timestamps until %04ld (0x%llx)\n",
+		pr_warn("%s filesystem being %s at %s supports timestamps until %ptTd (0x%llx)\n",
 			sb->s_type->name,
 			is_mounted(mnt) ? "remounted" : "mounted",
-			mntpath,
-			tm.tm_year+1900, (unsigned long long)sb->s_time_max);
+			mntpath, &sb->s_time_max,
+			(unsigned long long)sb->s_time_max);
 
 		free_page((unsigned long)buf);
 		sb->s_iflags |= SB_I_TS_EXPIRY_WARNED;

From 4e04143c869c5b6d499fbd5083caa860d5c942c3 Mon Sep 17 00:00:00 2001
From: Ondrej Mosnacek <omosnace@redhat.com>
Date: Thu, 16 Mar 2023 14:07:51 +0100
Subject: [PATCH 23/67] fs_context: drop the unused lsm_flags member

This isn't ever used by VFS now, and it couldn't even work. Any FS that
uses the SECURITY_LSM_NATIVE_LABELS flag needs to also process the
value returned back from the LSM, so it needs to do its
security_sb_set_mnt_opts() call on its own anyway.

Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
---
 Documentation/filesystems/mount_api.rst | 1 -
 fs/nfs/super.c                          | 3 ---
 include/linux/fs_context.h              | 1 -
 include/linux/security.h                | 2 +-
 4 files changed, 1 insertion(+), 6 deletions(-)

diff --git a/Documentation/filesystems/mount_api.rst b/Documentation/filesystems/mount_api.rst
index 63204d2094fd..9aaf6ef75eb5 100644
--- a/Documentation/filesystems/mount_api.rst
+++ b/Documentation/filesystems/mount_api.rst
@@ -79,7 +79,6 @@ context.  This is represented by the fs_context structure::
 		unsigned int		sb_flags;
 		unsigned int		sb_flags_mask;
 		unsigned int		s_iflags;
-		unsigned int		lsm_flags;
 		enum fs_context_purpose	purpose:8;
 		...
 	};
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 05ae23657527..397c096d874e 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1274,9 +1274,6 @@ int nfs_get_tree_common(struct fs_context *fc)
 		if (ctx->clone_data.sb->s_flags & SB_SYNCHRONOUS)
 			fc->sb_flags |= SB_SYNCHRONOUS;
 
-	if (server->caps & NFS_CAP_SECURITY_LABEL)
-		fc->lsm_flags |= SECURITY_LSM_NATIVE_LABELS;
-
 	/* Get a superblock - note that we may end up sharing one that already exists */
 	fc->s_fs_info = server;
 	s = sget_fc(fc, compare_super, nfs_set_super);
diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
index 5469ffee21c7..ff6341e09925 100644
--- a/include/linux/fs_context.h
+++ b/include/linux/fs_context.h
@@ -104,7 +104,6 @@ struct fs_context {
 	unsigned int		sb_flags;	/* Proposed superblock flags (SB_*) */
 	unsigned int		sb_flags_mask;	/* Superblock flags that were changed */
 	unsigned int		s_iflags;	/* OR'd with sb->s_iflags */
-	unsigned int		lsm_flags;	/* Information flags from the fs to the LSM */
 	enum fs_context_purpose	purpose:8;
 	enum fs_context_phase	phase:8;	/* The phase the context is in */
 	bool			need_free:1;	/* Need to call ops->free() */
diff --git a/include/linux/security.h b/include/linux/security.h
index 5984d0d550b4..db9b659b02b9 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -68,7 +68,7 @@ struct watch_notification;
 /* If capable is being called by a setid function */
 #define CAP_OPT_INSETID BIT(2)
 
-/* LSM Agnostic defines for fs_context::lsm_flags */
+/* LSM Agnostic defines for security_sb_set_mnt_opts() flags */
 #define SECURITY_LSM_NATIVE_LABELS	1
 
 struct ctl_table;

From 7f400a1dc29f3ed6cb0fe0e58f706b6933f72625 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 13 Mar 2023 19:08:48 +0100
Subject: [PATCH 24/67] nubus: Drop noop match function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

nubus_bus_match() returned 1 unconditionally. This is equivalent to
no match function at all. (See driver_match_device() which does:

	return drv->bus->match ? drv->bus->match(dev, drv) : 1;

.)

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Finn Thain <fthain@linux-m68k.org>
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Link: https://lore.kernel.org/r/20230313180848.2770504-1-u.kleine-koenig@pengutronix.de
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
---
 drivers/nubus/bus.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/nubus/bus.c b/drivers/nubus/bus.c
index 17fad660032c..72921e4f35f6 100644
--- a/drivers/nubus/bus.c
+++ b/drivers/nubus/bus.c
@@ -14,11 +14,6 @@
 #define to_nubus_board(d)       container_of(d, struct nubus_board, dev)
 #define to_nubus_driver(d)      container_of(d, struct nubus_driver, driver)
 
-static int nubus_bus_match(struct device *dev, struct device_driver *driver)
-{
-	return 1;
-}
-
 static int nubus_device_probe(struct device *dev)
 {
 	struct nubus_driver *ndrv = to_nubus_driver(dev->driver);
@@ -39,7 +34,6 @@ static void nubus_device_remove(struct device *dev)
 
 struct bus_type nubus_bus_type = {
 	.name		= "nubus",
-	.match		= nubus_bus_match,
 	.probe		= nubus_device_probe,
 	.remove		= nubus_device_remove,
 };

From fda1941b8eab786112afe91088fa0a1ed4880360 Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Date: Mon, 20 Mar 2023 13:32:02 +0100
Subject: [PATCH 25/67] m68k: Remove obsolete config NO_KERNEL_MSG

The use of the config NO_KERNEL_MSG is long gone. Remove this config from
m68k's debug kernel configuration setup.

Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Link: https://lore.kernel.org/r/20230320123202.14474-1-lukas.bulwahn@gmail.com
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
---
 arch/m68k/Kconfig.debug | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/arch/m68k/Kconfig.debug b/arch/m68k/Kconfig.debug
index 465e28be0ce4..30638a6e8edc 100644
--- a/arch/m68k/Kconfig.debug
+++ b/arch/m68k/Kconfig.debug
@@ -36,11 +36,6 @@ config HIGHPROFILE
 	help
 	  Use a fast secondary clock to produce profiling information.
 
-config NO_KERNEL_MSG
-	bool "Suppress Kernel BUG Messages"
-	help
-	  Do not output any debug BUG messages within the kernel.
-
 config BDM_DISABLE
 	bool "Disable BDM signals"
 	depends on COLDFIRE

From 43b450632676fb60e9faeddff285d9fac94a4f58 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Tue, 21 Mar 2023 09:18:07 +0100
Subject: [PATCH 26/67] open: return EINVAL for O_DIRECTORY | O_CREAT

After a couple of years and multiple LTS releases we received a report
that the behavior of O_DIRECTORY | O_CREAT changed starting with v5.7.

On kernels prior to v5.7 combinations of O_DIRECTORY, O_CREAT, O_EXCL
had the following semantics:

(1) open("/tmp/d", O_DIRECTORY | O_CREAT)
    * d doesn't exist:                create regular file
    * d exists and is a regular file: ENOTDIR
    * d exists and is a directory:    EISDIR

(2) open("/tmp/d", O_DIRECTORY | O_CREAT | O_EXCL)
    * d doesn't exist:                create regular file
    * d exists and is a regular file: EEXIST
    * d exists and is a directory:    EEXIST

(3) open("/tmp/d", O_DIRECTORY | O_EXCL)
    * d doesn't exist:                ENOENT
    * d exists and is a regular file: ENOTDIR
    * d exists and is a directory:    open directory

On kernels since to v5.7 combinations of O_DIRECTORY, O_CREAT, O_EXCL
have the following semantics:

(1) open("/tmp/d", O_DIRECTORY | O_CREAT)
    * d doesn't exist:                ENOTDIR (create regular file)
    * d exists and is a regular file: ENOTDIR
    * d exists and is a directory:    EISDIR

(2) open("/tmp/d", O_DIRECTORY | O_CREAT | O_EXCL)
    * d doesn't exist:                ENOTDIR (create regular file)
    * d exists and is a regular file: EEXIST
    * d exists and is a directory:    EEXIST

(3) open("/tmp/d", O_DIRECTORY | O_EXCL)
    * d doesn't exist:                ENOENT
    * d exists and is a regular file: ENOTDIR
    * d exists and is a directory:    open directory

This is a fairly substantial semantic change that userspace didn't
notice until Pedro took the time to deliberately figure out corner
cases. Since no one noticed this breakage we can somewhat safely assume
that O_DIRECTORY | O_CREAT combinations are likely unused.

The v5.7 breakage is especially weird because while ENOTDIR is returned
indicating failure a regular file is actually created. This doesn't make
a lot of sense.

Time was spent finding potential users of this combination. Searching on
codesearch.debian.net showed that codebases often express semantical
expectations about O_DIRECTORY | O_CREAT which are completely contrary
to what our code has done and currently does.

The expectation often is that this particular combination would create
and open a directory. This suggests users who tried to use that
combination would stumble upon the counterintuitive behavior no matter
if pre-v5.7 or post v5.7 and quickly realize neither semantics give them
what they want. For some examples see the code examples in [1] to [3]
and the discussion in [4].

There are various ways to address this issue. The lazy/simple option
would be to restore the pre-v5.7 behavior and to just live with that bug
forever. But since there's a real chance that the O_DIRECTORY | O_CREAT
quirk isn't relied upon we should try to get away with murder(ing bad
semantics) first. If we need to Frankenstein pre-v5.7 behavior later so
be it.

So let's simply return EINVAL categorically for O_DIRECTORY | O_CREAT
combinations. In addition to cleaning up the old bug this also opens up
the possiblity to make that flag combination do something more intuitive
in the future.

Starting with this commit the following semantics apply:

(1) open("/tmp/d", O_DIRECTORY | O_CREAT)
    * d doesn't exist:                EINVAL
    * d exists and is a regular file: EINVAL
    * d exists and is a directory:    EINVAL

(2) open("/tmp/d", O_DIRECTORY | O_CREAT | O_EXCL)
    * d doesn't exist:                EINVAL
    * d exists and is a regular file: EINVAL
    * d exists and is a directory:    EINVAL

(3) open("/tmp/d", O_DIRECTORY | O_EXCL)
    * d doesn't exist:                ENOENT
    * d exists and is a regular file: ENOTDIR
    * d exists and is a directory:    open directory

One additional note, O_TMPFILE is implemented as:

    #define __O_TMPFILE    020000000
    #define O_TMPFILE      (__O_TMPFILE | O_DIRECTORY)
    #define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT)

For older kernels it was important to return an explicit error when
O_TMPFILE wasn't supported. So O_TMPFILE requires that O_DIRECTORY is
raised alongside __O_TMPFILE. It also enforced that O_CREAT wasn't
specified. Since O_DIRECTORY | O_CREAT could be used to create a regular
allowing that combination together with __O_TMPFILE would've meant that
false positives were possible, i.e., that a regular file was created
instead of a O_TMPFILE. This could've been used to trick userspace into
thinking it operated on a O_TMPFILE when it wasn't.

Now that we block O_DIRECTORY | O_CREAT completely the check for O_CREAT
in the __O_TMPFILE branch via if ((flags & O_TMPFILE_MASK) != O_TMPFILE)
can be dropped. Instead we can simply check verify that O_DIRECTORY is
raised via if (!(flags & O_DIRECTORY)) and explain this in two comments.

As Aleksa pointed out O_PATH is unaffected by this change since it
always returned EINVAL if O_CREAT was specified - with or without
O_DIRECTORY.

Link: https://lore.kernel.org/lkml/20230320071442.172228-1-pedro.falcato@gmail.com
Link: https://sources.debian.org/src/flatpak/1.14.4-1/subprojects/libglnx/glnx-dirfd.c/?hl=324#L324 [1]
Link: https://sources.debian.org/src/flatpak-builder/1.2.3-1/subprojects/libglnx/glnx-shutil.c/?hl=251#L251 [2]
Link: https://sources.debian.org/src/ostree/2022.7-2/libglnx/glnx-dirfd.c/?hl=324#L324 [3]
Link: https://www.openwall.com/lists/oss-security/2014/11/26/14 [4]
Reported-by: Pedro Falcato <pedro.falcato@gmail.com>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/open.c                              | 18 +++++++++++++-----
 include/uapi/asm-generic/fcntl.h       |  1 -
 tools/include/uapi/asm-generic/fcntl.h |  1 -
 3 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/fs/open.c b/fs/open.c
index 4401a73d4032..4478adcc4f3a 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1196,13 +1196,21 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op)
 	}
 
 	/*
-	 * In order to ensure programs get explicit errors when trying to use
-	 * O_TMPFILE on old kernels, O_TMPFILE is implemented such that it
-	 * looks like (O_DIRECTORY|O_RDWR & ~O_CREAT) to old kernels. But we
-	 * have to require userspace to explicitly set it.
+	 * Block bugs where O_DIRECTORY | O_CREAT created regular files.
+	 * Note, that blocking O_DIRECTORY | O_CREAT here also protects
+	 * O_TMPFILE below which requires O_DIRECTORY being raised.
 	 */
+	if ((flags & (O_DIRECTORY | O_CREAT)) == (O_DIRECTORY | O_CREAT))
+		return -EINVAL;
+
+	/* Now handle the creative implementation of O_TMPFILE. */
 	if (flags & __O_TMPFILE) {
-		if ((flags & O_TMPFILE_MASK) != O_TMPFILE)
+		/*
+		 * In order to ensure programs get explicit errors when trying
+		 * to use O_TMPFILE on old kernels we enforce that O_DIRECTORY
+		 * is raised alongside __O_TMPFILE.
+		 */
+		if (!(flags & O_DIRECTORY))
 			return -EINVAL;
 		if (!(acc_mode & MAY_WRITE))
 			return -EINVAL;
diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h
index 1ecdb911add8..80f37a0d40d7 100644
--- a/include/uapi/asm-generic/fcntl.h
+++ b/include/uapi/asm-generic/fcntl.h
@@ -91,7 +91,6 @@
 
 /* a horrid kludge trying to make sure that this will fail on old kernels */
 #define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
-#define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT)      
 
 #ifndef O_NDELAY
 #define O_NDELAY	O_NONBLOCK
diff --git a/tools/include/uapi/asm-generic/fcntl.h b/tools/include/uapi/asm-generic/fcntl.h
index b02c8e0f4057..1c7a0f6632c0 100644
--- a/tools/include/uapi/asm-generic/fcntl.h
+++ b/tools/include/uapi/asm-generic/fcntl.h
@@ -91,7 +91,6 @@
 
 /* a horrid kludge trying to make sure that this will fail on old kernels */
 #define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
-#define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT)      
 
 #ifndef O_NDELAY
 #define O_NDELAY	O_NONBLOCK

From dc7cb2d29805fe4fa4000fc0b09740fc24c93408 Mon Sep 17 00:00:00 2001
From: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Date: Thu, 23 Mar 2023 10:32:59 +0800
Subject: [PATCH 27/67] fs/buffer: Remove redundant assignment to err

Variable 'err' set but not used.

fs/buffer.c:2613:2: warning: Value stored to 'err' is never read.

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=4589
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/buffer.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index 9e1e2add541e..10390f53f3f5 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2581,7 +2581,7 @@ int block_truncate_page(struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	struct page *page;
 	struct buffer_head *bh;
-	int err;
+	int err = 0;
 
 	blocksize = i_blocksize(inode);
 	length = offset & (blocksize - 1);
@@ -2594,9 +2594,8 @@ int block_truncate_page(struct address_space *mapping,
 	iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits);
 	
 	page = grab_cache_page(mapping, index);
-	err = -ENOMEM;
 	if (!page)
-		goto out;
+		return -ENOMEM;
 
 	if (!page_has_buffers(page))
 		create_empty_buffers(page, blocksize, 0);
@@ -2610,7 +2609,6 @@ int block_truncate_page(struct address_space *mapping,
 		pos += blocksize;
 	}
 
-	err = 0;
 	if (!buffer_mapped(bh)) {
 		WARN_ON(bh->b_size != blocksize);
 		err = get_block(inode, iblock, bh, 0);
@@ -2634,12 +2632,11 @@ int block_truncate_page(struct address_space *mapping,
 
 	zero_user(page, offset, length);
 	mark_buffer_dirty(bh);
-	err = 0;
 
 unlock:
 	unlock_page(page);
 	put_page(page);
-out:
+
 	return err;
 }
 EXPORT_SYMBOL(block_truncate_page);

From d98ffa1aca264ce547b9135135f83d81cfe4345f Mon Sep 17 00:00:00 2001
From: Stephen Kitt <steve@sk2.org>
Date: Sat, 25 Mar 2023 09:22:32 +0100
Subject: [PATCH 28/67] Update relatime comments to include equality

relatime also updates atime if the previous atime is equal to one or
both of the ctime and mtime; a non-strict interpretation of "earlier
than" and "younger than" in the comments allows this, but for clarity,
this makes it explicit.

Pointed out by "epiii2" and "ctrl-alt-delor" in
https://unix.stackexchange.com/q/740862/86440.

Signed-off-by: Stephen Kitt <steve@sk2.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/inode.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/inode.c b/fs/inode.c
index 4558dc2f1355..3ec5a8f7b644 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1804,8 +1804,8 @@ EXPORT_SYMBOL(bmap);
 
 /*
  * With relative atime, only update atime if the previous atime is
- * earlier than either the ctime or mtime or if at least a day has
- * passed since the last atime update.
+ * earlier than or equal to either the ctime or mtime,
+ * or if at least a day has passed since the last atime update.
  */
 static int relatime_need_update(struct vfsmount *mnt, struct inode *inode,
 			     struct timespec64 now)
@@ -1814,12 +1814,12 @@ static int relatime_need_update(struct vfsmount *mnt, struct inode *inode,
 	if (!(mnt->mnt_flags & MNT_RELATIME))
 		return 1;
 	/*
-	 * Is mtime younger than atime? If yes, update atime:
+	 * Is mtime younger than or equal to atime? If yes, update atime:
 	 */
 	if (timespec64_compare(&inode->i_mtime, &inode->i_atime) >= 0)
 		return 1;
 	/*
-	 * Is ctime younger than atime? If yes, update atime:
+	 * Is ctime younger than or equal to atime? If yes, update atime:
 	 */
 	if (timespec64_compare(&inode->i_ctime, &inode->i_atime) >= 0)
 		return 1;

From 4f704d9a8352f5c0a8fcdb6213b934630342bd44 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Tue, 14 Mar 2023 12:51:10 +0100
Subject: [PATCH 29/67] nfs: use vfs setgid helper

We've aligned setgid behavior over multiple kernel releases. The details
can be found in the following two merge messages:
cf619f891971 ("Merge tag 'fs.ovl.setgid.v6.2')
426b4ca2d6a5 ("Merge tag 'fs.setgid.v6.0')
Consistent setgid stripping behavior is now encapsulated in the
setattr_should_drop_sgid() helper which is used by all filesystems that
strip setgid bits outside of vfs proper. Switch nfs to rely on this
helper as well. Without this patch the setgid stripping tests in
xfstests will fail.

Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Message-Id: <20230313-fs-nfs-setgid-v2-1-9a59f436cfc0@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/attr.c          | 1 +
 fs/internal.h      | 2 --
 fs/nfs/inode.c     | 4 +---
 include/linux/fs.h | 2 ++
 4 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/fs/attr.c b/fs/attr.c
index aca9ff7aed33..d60dc1edb526 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -47,6 +47,7 @@ int setattr_should_drop_sgid(struct mnt_idmap *idmap,
 		return ATTR_KILL_SGID;
 	return 0;
 }
+EXPORT_SYMBOL(setattr_should_drop_sgid);
 
 /**
  * setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to
diff --git a/fs/internal.h b/fs/internal.h
index dc4eb91a577a..ab36ed8fa41c 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -259,8 +259,6 @@ ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *po
 /*
  * fs/attr.c
  */
-int setattr_should_drop_sgid(struct mnt_idmap *idmap,
-			     const struct inode *inode);
 struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns);
 struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap);
 void mnt_idmap_put(struct mnt_idmap *idmap);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 222a28320e1c..97a76706fd54 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -717,9 +717,7 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
 		if ((attr->ia_valid & ATTR_KILL_SUID) != 0 &&
 		    inode->i_mode & S_ISUID)
 			inode->i_mode &= ~S_ISUID;
-		if ((attr->ia_valid & ATTR_KILL_SGID) != 0 &&
-		    (inode->i_mode & (S_ISGID | S_IXGRP)) ==
-		     (S_ISGID | S_IXGRP))
+		if (setattr_should_drop_sgid(&nop_mnt_idmap, inode))
 			inode->i_mode &= ~S_ISGID;
 		if ((attr->ia_valid & ATTR_MODE) != 0) {
 			int mode = attr->ia_mode & S_IALLUGO;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c85916e9f7db..af95b64fc810 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2675,6 +2675,8 @@ extern struct inode *new_inode(struct super_block *sb);
 extern void free_inode_nonrcu(struct inode *inode);
 extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *);
 extern int file_remove_privs(struct file *);
+int setattr_should_drop_sgid(struct mnt_idmap *idmap,
+			     const struct inode *inode);
 
 /*
  * This must be used for allocating filesystems specific inodes to set

From 364595a6851bf64e1c38224ae68f5dd6651906d1 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 30 Mar 2023 06:41:43 -0400
Subject: [PATCH 30/67] fs: consolidate duplicate dt_type helpers

There are three copies of the same dt_type helper sprinkled around the
tree. Convert them to use the common fs_umode_to_dtype function instead,
which has the added advantage of properly returning DT_UNKNOWN when
given a mode that contains an unrecognized type.

Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: Phillip Potter <phil@philpotter.co.uk>
Suggested-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Message-Id: <20230330104144.75547-1-jlayton@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/configfs/dir.c | 9 ++-------
 fs/kernfs/dir.c   | 8 +-------
 fs/libfs.c        | 9 ++-------
 3 files changed, 5 insertions(+), 21 deletions(-)

diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 4afcbbe63e68..18677cd4e62f 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1599,12 +1599,6 @@ static int configfs_dir_close(struct inode *inode, struct file *file)
 	return 0;
 }
 
-/* Relationship between s_mode and the DT_xxx types */
-static inline unsigned char dt_type(struct configfs_dirent *sd)
-{
-	return (sd->s_mode >> 12) & 15;
-}
-
 static int configfs_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct dentry *dentry = file->f_path.dentry;
@@ -1654,7 +1648,8 @@ static int configfs_readdir(struct file *file, struct dir_context *ctx)
 		name = configfs_get_name(next);
 		len = strlen(name);
 
-		if (!dir_emit(ctx, name, len, ino, dt_type(next)))
+		if (!dir_emit(ctx, name, len, ino,
+			      fs_umode_to_dtype(next->s_mode)))
 			return 0;
 
 		spin_lock(&configfs_dirent_lock);
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index ef00b5fe8cee..90de0e498371 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -1748,12 +1748,6 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 	return error;
 }
 
-/* Relationship between mode and the DT_xxx types */
-static inline unsigned char dt_type(struct kernfs_node *kn)
-{
-	return (kn->mode >> 12) & 15;
-}
-
 static int kernfs_dir_fop_release(struct inode *inode, struct file *filp)
 {
 	kernfs_put(filp->private_data);
@@ -1831,7 +1825,7 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx)
 	     pos;
 	     pos = kernfs_dir_next_pos(ns, parent, ctx->pos, pos)) {
 		const char *name = pos->name;
-		unsigned int type = dt_type(pos);
+		unsigned int type = fs_umode_to_dtype(pos->mode);
 		int len = strlen(name);
 		ino_t ino = kernfs_ino(pos);
 
diff --git a/fs/libfs.c b/fs/libfs.c
index 4eda519c3002..89cf614a3271 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -174,12 +174,6 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 }
 EXPORT_SYMBOL(dcache_dir_lseek);
 
-/* Relationship between i_mode and the DT_xxx types */
-static inline unsigned char dt_type(struct inode *inode)
-{
-	return (inode->i_mode >> 12) & 15;
-}
-
 /*
  * Directory is locked and all positive dentries in it are safe, since
  * for ramfs-type trees they can't go away without unlink() or rmdir(),
@@ -206,7 +200,8 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
 
 	while ((next = scan_positives(cursor, p, 1, next)) != NULL) {
 		if (!dir_emit(ctx, next->d_name.name, next->d_name.len,
-			      d_inode(next)->i_ino, dt_type(d_inode(next))))
+			      d_inode(next)->i_ino,
+			      fs_umode_to_dtype(d_inode(next)->i_mode)))
 			break;
 		ctx->pos++;
 		p = &next->d_child;

From 1ea3bb3e4b767d074c8215c515e959c6420908bf Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Mon, 6 Mar 2023 13:48:37 +0100
Subject: [PATCH 31/67] m68k: defconfig: Update defconfigs for v6.3-rc1

  - Drop CONFIG_IP_NF_TARGET_CLUSTERIP=m (removed in commit
    9db5d918e2c07fa0 ("netfilter: ip_tables: remove clusterip target")),
  - Enable modular build of the Kerberos V mechanism for Secure RPC
    (auto-builtin since commit dfe9a123451a6e73 ("SUNRPC: Enable
    rpcsec_gss_krb5.ko to be built without CRYPTO_DES")),
  - Enable modular build of the new Dhrystone benchmark test,
  - Drop accidental enablement of CONFIG_PCCARD=y in multi_defconfig.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Link: https://lore.kernel.org/r/2b6d1357f4cb7e23bb2c7a7d39c4486e77e138ad.1678106848.git.geert@linux-m68k.org
---
 arch/m68k/configs/amiga_defconfig    | 3 ++-
 arch/m68k/configs/apollo_defconfig   | 3 ++-
 arch/m68k/configs/atari_defconfig    | 3 ++-
 arch/m68k/configs/bvme6000_defconfig | 3 ++-
 arch/m68k/configs/hp300_defconfig    | 3 ++-
 arch/m68k/configs/mac_defconfig      | 3 ++-
 arch/m68k/configs/multi_defconfig    | 4 ++--
 arch/m68k/configs/mvme147_defconfig  | 3 ++-
 arch/m68k/configs/mvme16x_defconfig  | 3 ++-
 arch/m68k/configs/q40_defconfig      | 3 ++-
 arch/m68k/configs/sun3_defconfig     | 3 ++-
 arch/m68k/configs/sun3x_defconfig    | 3 ++-
 12 files changed, 24 insertions(+), 13 deletions(-)

diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index ec2d792015a4..b26469a65bc1 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -214,7 +214,6 @@ CONFIG_IP_NF_TARGET_MASQUERADE=m
 CONFIG_IP_NF_TARGET_NETMAP=m
 CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
@@ -495,6 +494,7 @@ CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
+CONFIG_RPCSEC_GSS_KRB5=m
 CONFIG_CIFS=m
 # CONFIG_CIFS_STATS2 is not set
 # CONFIG_CIFS_DEBUG is not set
@@ -621,6 +621,7 @@ CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_KUNIT=m
 CONFIG_KUNIT_ALL_TESTS=m
+CONFIG_TEST_DHRY=m
 CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_DIV64=m
 CONFIG_REED_SOLOMON_TEST=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 061a07824dc2..944a49a129be 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -210,7 +210,6 @@ CONFIG_IP_NF_TARGET_MASQUERADE=m
 CONFIG_IP_NF_TARGET_NETMAP=m
 CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
@@ -452,6 +451,7 @@ CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
+CONFIG_RPCSEC_GSS_KRB5=m
 CONFIG_CIFS=m
 # CONFIG_CIFS_STATS2 is not set
 # CONFIG_CIFS_DEBUG is not set
@@ -577,6 +577,7 @@ CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_KUNIT=m
 CONFIG_KUNIT_ALL_TESTS=m
+CONFIG_TEST_DHRY=m
 CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_DIV64=m
 CONFIG_REED_SOLOMON_TEST=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 02af5f501dae..a32dd884fcce 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -217,7 +217,6 @@ CONFIG_IP_NF_TARGET_MASQUERADE=m
 CONFIG_IP_NF_TARGET_NETMAP=m
 CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
@@ -472,6 +471,7 @@ CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
+CONFIG_RPCSEC_GSS_KRB5=m
 CONFIG_CIFS=m
 # CONFIG_CIFS_STATS2 is not set
 # CONFIG_CIFS_DEBUG is not set
@@ -598,6 +598,7 @@ CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_KUNIT=m
 CONFIG_KUNIT_ALL_TESTS=m
+CONFIG_TEST_DHRY=m
 CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_DIV64=m
 CONFIG_REED_SOLOMON_TEST=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 0d5832cb3e10..23b7805309bd 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -207,7 +207,6 @@ CONFIG_IP_NF_TARGET_MASQUERADE=m
 CONFIG_IP_NF_TARGET_NETMAP=m
 CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
@@ -444,6 +443,7 @@ CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
+CONFIG_RPCSEC_GSS_KRB5=m
 CONFIG_CIFS=m
 # CONFIG_CIFS_STATS2 is not set
 # CONFIG_CIFS_DEBUG is not set
@@ -569,6 +569,7 @@ CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_KUNIT=m
 CONFIG_KUNIT_ALL_TESTS=m
+CONFIG_TEST_DHRY=m
 CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_DIV64=m
 CONFIG_REED_SOLOMON_TEST=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index c246c3538839..5605ab5c3dcf 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -209,7 +209,6 @@ CONFIG_IP_NF_TARGET_MASQUERADE=m
 CONFIG_IP_NF_TARGET_NETMAP=m
 CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
@@ -454,6 +453,7 @@ CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
+CONFIG_RPCSEC_GSS_KRB5=m
 CONFIG_CIFS=m
 # CONFIG_CIFS_STATS2 is not set
 # CONFIG_CIFS_DEBUG is not set
@@ -579,6 +579,7 @@ CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_KUNIT=m
 CONFIG_KUNIT_ALL_TESTS=m
+CONFIG_TEST_DHRY=m
 CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_DIV64=m
 CONFIG_REED_SOLOMON_TEST=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 98d2d0599e5a..d0d1f9c33756 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -208,7 +208,6 @@ CONFIG_IP_NF_TARGET_MASQUERADE=m
 CONFIG_IP_NF_TARGET_NETMAP=m
 CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
@@ -474,6 +473,7 @@ CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
+CONFIG_RPCSEC_GSS_KRB5=m
 CONFIG_CIFS=m
 # CONFIG_CIFS_STATS2 is not set
 # CONFIG_CIFS_DEBUG is not set
@@ -600,6 +600,7 @@ CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_KUNIT=m
 CONFIG_KUNIT_ALL_TESTS=m
+CONFIG_TEST_DHRY=m
 CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_DIV64=m
 CONFIG_REED_SOLOMON_TEST=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index b2d5ec6ba625..6d04314ce7ea 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -228,7 +228,6 @@ CONFIG_IP_NF_TARGET_MASQUERADE=m
 CONFIG_IP_NF_TARGET_NETMAP=m
 CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
@@ -314,7 +313,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_PCCARD=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
@@ -561,6 +559,7 @@ CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
+CONFIG_RPCSEC_GSS_KRB5=m
 CONFIG_CIFS=m
 # CONFIG_CIFS_STATS2 is not set
 # CONFIG_CIFS_DEBUG is not set
@@ -687,6 +686,7 @@ CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_KUNIT=m
 CONFIG_KUNIT_ALL_TESTS=m
+CONFIG_TEST_DHRY=m
 CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_DIV64=m
 CONFIG_REED_SOLOMON_TEST=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index d3420c642992..e6f5ae526d08 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -206,7 +206,6 @@ CONFIG_IP_NF_TARGET_MASQUERADE=m
 CONFIG_IP_NF_TARGET_NETMAP=m
 CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
@@ -443,6 +442,7 @@ CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
+CONFIG_RPCSEC_GSS_KRB5=m
 CONFIG_CIFS=m
 # CONFIG_CIFS_STATS2 is not set
 # CONFIG_CIFS_DEBUG is not set
@@ -568,6 +568,7 @@ CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_KUNIT=m
 CONFIG_KUNIT_ALL_TESTS=m
+CONFIG_TEST_DHRY=m
 CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_DIV64=m
 CONFIG_REED_SOLOMON_TEST=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index e294b0b67695..f2d4dff4787a 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -207,7 +207,6 @@ CONFIG_IP_NF_TARGET_MASQUERADE=m
 CONFIG_IP_NF_TARGET_NETMAP=m
 CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
@@ -444,6 +443,7 @@ CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
+CONFIG_RPCSEC_GSS_KRB5=m
 CONFIG_CIFS=m
 # CONFIG_CIFS_STATS2 is not set
 # CONFIG_CIFS_DEBUG is not set
@@ -569,6 +569,7 @@ CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_KUNIT=m
 CONFIG_KUNIT_ALL_TESTS=m
+CONFIG_TEST_DHRY=m
 CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_DIV64=m
 CONFIG_REED_SOLOMON_TEST=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 764a94b08936..907eedecd040 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -208,7 +208,6 @@ CONFIG_IP_NF_TARGET_MASQUERADE=m
 CONFIG_IP_NF_TARGET_NETMAP=m
 CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
@@ -461,6 +460,7 @@ CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
+CONFIG_RPCSEC_GSS_KRB5=m
 CONFIG_CIFS=m
 # CONFIG_CIFS_STATS2 is not set
 # CONFIG_CIFS_DEBUG is not set
@@ -587,6 +587,7 @@ CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_KUNIT=m
 CONFIG_KUNIT_ALL_TESTS=m
+CONFIG_TEST_DHRY=m
 CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_DIV64=m
 CONFIG_REED_SOLOMON_TEST=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index d4eeddac6bb8..9e3d47008f21 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -204,7 +204,6 @@ CONFIG_IP_NF_TARGET_MASQUERADE=m
 CONFIG_IP_NF_TARGET_NETMAP=m
 CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
@@ -443,6 +442,7 @@ CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
+CONFIG_RPCSEC_GSS_KRB5=m
 CONFIG_CIFS=m
 # CONFIG_CIFS_STATS2 is not set
 # CONFIG_CIFS_DEBUG is not set
@@ -567,6 +567,7 @@ CONFIG_TEST_LOCKUP=m
 CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_KUNIT=m
 CONFIG_KUNIT_ALL_TESTS=m
+CONFIG_TEST_DHRY=m
 CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_DIV64=m
 CONFIG_REED_SOLOMON_TEST=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index ca359b880683..f6540078cb4b 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -204,7 +204,6 @@ CONFIG_IP_NF_TARGET_MASQUERADE=m
 CONFIG_IP_NF_TARGET_NETMAP=m
 CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
@@ -442,6 +441,7 @@ CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
+CONFIG_RPCSEC_GSS_KRB5=m
 CONFIG_CIFS=m
 # CONFIG_CIFS_STATS2 is not set
 # CONFIG_CIFS_DEBUG is not set
@@ -567,6 +567,7 @@ CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_KUNIT=m
 CONFIG_KUNIT_ALL_TESTS=m
+CONFIG_TEST_DHRY=m
 CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_DIV64=m
 CONFIG_REED_SOLOMON_TEST=m

From 6ae930d9dbf2d093157be33428538c91966d8a9f Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Mon, 27 Mar 2023 20:22:51 +0200
Subject: [PATCH 32/67] pid: add pidfd_prepare()

Add a new helper that allows to reserve a pidfd and allocates a new
pidfd file that stashes the provided struct pid. This will allow us to
remove places that either open code this function or that call
pidfd_create() but then have to call close_fd() because there are still
failure points after pidfd_create() has been called.

Reviewed-by: Jan Kara <jack@suse.cz>
Message-Id: <20230327-pidfd-file-api-v1-1-5c0e9a3158e4@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/pid.h |  1 +
 kernel/fork.c       | 85 +++++++++++++++++++++++++++++++++++++++++++++
 kernel/pid.c        | 19 ++++------
 3 files changed, 93 insertions(+), 12 deletions(-)

diff --git a/include/linux/pid.h b/include/linux/pid.h
index 343abf22092e..b75de288a8c2 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -80,6 +80,7 @@ extern struct pid *pidfd_pid(const struct file *file);
 struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags);
 struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags);
 int pidfd_create(struct pid *pid, unsigned int flags);
+int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret);
 
 static inline struct pid *get_pid(struct pid *pid)
 {
diff --git a/kernel/fork.c b/kernel/fork.c
index c0257cbee093..a34395bd708a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1951,6 +1951,91 @@ const struct file_operations pidfd_fops = {
 #endif
 };
 
+/**
+ * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd
+ * @pid:   the struct pid for which to create a pidfd
+ * @flags: flags of the new @pidfd
+ * @pidfd: the pidfd to return
+ *
+ * Allocate a new file that stashes @pid and reserve a new pidfd number in the
+ * caller's file descriptor table. The pidfd is reserved but not installed yet.
+
+ * The helper doesn't perform checks on @pid which makes it useful for pidfds
+ * created via CLONE_PIDFD where @pid has no task attached when the pidfd and
+ * pidfd file are prepared.
+ *
+ * If this function returns successfully the caller is responsible to either
+ * call fd_install() passing the returned pidfd and pidfd file as arguments in
+ * order to install the pidfd into its file descriptor table or they must use
+ * put_unused_fd() and fput() on the returned pidfd and pidfd file
+ * respectively.
+ *
+ * This function is useful when a pidfd must already be reserved but there
+ * might still be points of failure afterwards and the caller wants to ensure
+ * that no pidfd is leaked into its file descriptor table.
+ *
+ * Return: On success, a reserved pidfd is returned from the function and a new
+ *         pidfd file is returned in the last argument to the function. On
+ *         error, a negative error code is returned from the function and the
+ *         last argument remains unchanged.
+ */
+static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret)
+{
+	int pidfd;
+	struct file *pidfd_file;
+
+	if (flags & ~(O_NONBLOCK | O_RDWR | O_CLOEXEC))
+		return -EINVAL;
+
+	pidfd = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
+	if (pidfd < 0)
+		return pidfd;
+
+	pidfd_file = anon_inode_getfile("[pidfd]", &pidfd_fops, pid,
+					flags | O_RDWR | O_CLOEXEC);
+	if (IS_ERR(pidfd_file)) {
+		put_unused_fd(pidfd);
+		return PTR_ERR(pidfd_file);
+	}
+	get_pid(pid); /* held by pidfd_file now */
+	*ret = pidfd_file;
+	return pidfd;
+}
+
+/**
+ * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd
+ * @pid:   the struct pid for which to create a pidfd
+ * @flags: flags of the new @pidfd
+ * @pidfd: the pidfd to return
+ *
+ * Allocate a new file that stashes @pid and reserve a new pidfd number in the
+ * caller's file descriptor table. The pidfd is reserved but not installed yet.
+ *
+ * The helper verifies that @pid is used as a thread group leader.
+ *
+ * If this function returns successfully the caller is responsible to either
+ * call fd_install() passing the returned pidfd and pidfd file as arguments in
+ * order to install the pidfd into its file descriptor table or they must use
+ * put_unused_fd() and fput() on the returned pidfd and pidfd file
+ * respectively.
+ *
+ * This function is useful when a pidfd must already be reserved but there
+ * might still be points of failure afterwards and the caller wants to ensure
+ * that no pidfd is leaked into its file descriptor table.
+ *
+ * Return: On success, a reserved pidfd is returned from the function and a new
+ *         pidfd file is returned in the last argument to the function. On
+ *         error, a negative error code is returned from the function and the
+ *         last argument remains unchanged.
+ */
+int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret)
+{
+	if (!pid || !pid_has_task(pid, PIDTYPE_TGID))
+		return -EINVAL;
+
+	return __pidfd_prepare(pid, flags, ret);
+}
+
 static void __delayed_free_task(struct rcu_head *rhp)
 {
 	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
diff --git a/kernel/pid.c b/kernel/pid.c
index 3fbc5e46b721..f93954a0384d 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -594,20 +594,15 @@ struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags)
  */
 int pidfd_create(struct pid *pid, unsigned int flags)
 {
-	int fd;
+	int pidfd;
+	struct file *pidfd_file;
 
-	if (!pid || !pid_has_task(pid, PIDTYPE_TGID))
-		return -EINVAL;
+	pidfd = pidfd_prepare(pid, flags, &pidfd_file);
+	if (pidfd < 0)
+		return pidfd;
 
-	if (flags & ~(O_NONBLOCK | O_RDWR | O_CLOEXEC))
-		return -EINVAL;
-
-	fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid),
-			      flags | O_RDWR | O_CLOEXEC);
-	if (fd < 0)
-		put_pid(pid);
-
-	return fd;
+	fd_install(pidfd, pidfd_file);
+	return pidfd;
 }
 
 /**

From ca7707f5430ad6b1c9cb7cee0a7f67d69328bb2d Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Mon, 27 Mar 2023 20:22:52 +0200
Subject: [PATCH 33/67] fork: use pidfd_prepare()

Stop open-coding get_unused_fd_flags() and anon_inode_getfile(). That's
brittle just for keeping the flags between both calls in sync. Use the
dedicated helper.

Message-Id: <20230327-pidfd-file-api-v1-2-5c0e9a3158e4@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 kernel/fork.c | 13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index a34395bd708a..67bec6f1cb7a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2376,21 +2376,12 @@ static __latent_entropy struct task_struct *copy_process(
 	 * if the fd table isn't shared).
 	 */
 	if (clone_flags & CLONE_PIDFD) {
-		retval = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
+		/* Note that no task has been attached to @pid yet. */
+		retval = __pidfd_prepare(pid, O_RDWR | O_CLOEXEC, &pidfile);
 		if (retval < 0)
 			goto bad_fork_free_pid;
-
 		pidfd = retval;
 
-		pidfile = anon_inode_getfile("[pidfd]", &pidfd_fops, pid,
-					      O_RDWR | O_CLOEXEC);
-		if (IS_ERR(pidfile)) {
-			put_unused_fd(pidfd);
-			retval = PTR_ERR(pidfile);
-			goto bad_fork_free_pid;
-		}
-		get_pid(pid);	/* held by pidfile now */
-
 		retval = put_user(pidfd, args->pidfd);
 		if (retval)
 			goto bad_fork_put_pidfd;

From eee3a0e93924f2aab8ebaa7f2e26fd0f3b33f9e7 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Mon, 27 Mar 2023 20:22:53 +0200
Subject: [PATCH 34/67] fanotify: use pidfd_prepare()

We generally try to avoid installing a file descriptor into the caller's
file descriptor table just to close it again via close_fd() in case an
error occurs. Instead we reserve a file descriptor but don't install it
into the caller's file descriptor table yet. If we fail for other,
unrelated reasons we can just close the reserved file descriptor and if
we make it past all meaningful error paths we just install it. Fanotify
gets this right already for one fd type but not for pidfds.

Use the new pidfd_prepare() helper to reserve a pidfd and a pidfd file
and switch to the more common fd allocation and installation pattern.

Acked-by: Jan Kara <jack@suse.cz>
Message-Id: <20230327-pidfd-file-api-v1-3-5c0e9a3158e4@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/notify/fanotify/fanotify_user.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 8f430bfad487..22fb1cf7e1fc 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -663,7 +663,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 	struct fanotify_info *info = fanotify_event_info(event);
 	unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES);
 	unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD;
-	struct file *f = NULL;
+	struct file *f = NULL, *pidfd_file = NULL;
 	int ret, pidfd = FAN_NOPIDFD, fd = FAN_NOFD;
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
@@ -718,7 +718,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 		    !pid_has_task(event->pid, PIDTYPE_TGID)) {
 			pidfd = FAN_NOPIDFD;
 		} else {
-			pidfd = pidfd_create(event->pid, 0);
+			pidfd = pidfd_prepare(event->pid, 0, &pidfd_file);
 			if (pidfd < 0)
 				pidfd = FAN_EPIDFD;
 		}
@@ -751,6 +751,9 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 	if (f)
 		fd_install(fd, f);
 
+	if (pidfd_file)
+		fd_install(pidfd, pidfd_file);
+
 	return metadata.event_len;
 
 out_close_fd:
@@ -759,8 +762,10 @@ out_close_fd:
 		fput(f);
 	}
 
-	if (pidfd >= 0)
-		close_fd(pidfd);
+	if (pidfd >= 0) {
+		put_unused_fd(pidfd);
+		fput(pidfd_file);
+	}
 
 	return ret;
 }

From 983652c691990b3257a07f67f4263eb847baa82d Mon Sep 17 00:00:00 2001
From: Chung-Chiang Cheng <cccheng@synology.com>
Date: Wed, 22 Mar 2023 14:25:19 +0800
Subject: [PATCH 35/67] splice: report related fsnotify events

The fsnotify ACCESS and MODIFY event are missing when manipulating a file
with splice(2).

Signed-off-by: Chung-Chiang Cheng <cccheng@synology.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Acked-by: Jan Kara <jack@suse.cz>
Message-Id: <20230322062519.409752-1-cccheng@synology.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/splice.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/fs/splice.c b/fs/splice.c
index 2c3dec2b6dfa..0af8d150394f 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -30,6 +30,7 @@
 #include <linux/export.h>
 #include <linux/syscalls.h>
 #include <linux/uio.h>
+#include <linux/fsnotify.h>
 #include <linux/security.h>
 #include <linux/gfp.h>
 #include <linux/socket.h>
@@ -1165,6 +1166,9 @@ long do_splice(struct file *in, loff_t *off_in, struct file *out,
 		ret = do_splice_from(ipipe, out, &offset, len, flags);
 		file_end_write(out);
 
+		if (ret > 0)
+			fsnotify_modify(out);
+
 		if (!off_out)
 			out->f_pos = offset;
 		else
@@ -1188,6 +1192,10 @@ long do_splice(struct file *in, loff_t *off_in, struct file *out,
 			flags |= SPLICE_F_NONBLOCK;
 
 		ret = splice_file_to_pipe(in, opipe, &offset, len, flags);
+
+		if (ret > 0)
+			fsnotify_access(in);
+
 		if (!off_in)
 			in->f_pos = offset;
 		else

From 113348a44b8622b497fb884f41c8659481ad0b04 Mon Sep 17 00:00:00 2001
From: Wen Yang <wenyang.linux@foxmail.com>
Date: Thu, 6 Apr 2023 03:20:02 +0800
Subject: [PATCH 36/67] eventfd: use wait_event_interruptible_locked_irq()
 helper

wait_event_interruptible_locked_irq was introduced by commit 22c43c81a51e
("wait_event_interruptible_locked() interface"), but older code such as
eventfd_{write,read} still uses the open code implementation.
Inspired by commit 8120a8aadb20
("fs/timerfd.c: make use of wait_event_interruptible_locked_irq()"), this
patch replaces the open code implementation with a single macro call.

No functional change intended.

Signed-off-by: Wen Yang <wenyang.linux@foxmail.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dylan Yudaken <dylany@fb.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: David Woodhouse <dwmw@amazon.co.uk>
Cc: Fu Wei <wefu@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Michal Nazarewicz <m.nazarewicz@samsung.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Message-Id: <tencent_16F9553E8354D950D704214D6EA407315F0A@qq.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/eventfd.c | 41 +++++++----------------------------------
 1 file changed, 7 insertions(+), 34 deletions(-)

diff --git a/fs/eventfd.c b/fs/eventfd.c
index 249ca6c0b784..95850a13ce8d 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -228,7 +228,6 @@ static ssize_t eventfd_read(struct kiocb *iocb, struct iov_iter *to)
 	struct file *file = iocb->ki_filp;
 	struct eventfd_ctx *ctx = file->private_data;
 	__u64 ucnt = 0;
-	DECLARE_WAITQUEUE(wait, current);
 
 	if (iov_iter_count(to) < sizeof(ucnt))
 		return -EINVAL;
@@ -239,23 +238,11 @@ static ssize_t eventfd_read(struct kiocb *iocb, struct iov_iter *to)
 			spin_unlock_irq(&ctx->wqh.lock);
 			return -EAGAIN;
 		}
-		__add_wait_queue(&ctx->wqh, &wait);
-		for (;;) {
-			set_current_state(TASK_INTERRUPTIBLE);
-			if (ctx->count)
-				break;
-			if (signal_pending(current)) {
-				__remove_wait_queue(&ctx->wqh, &wait);
-				__set_current_state(TASK_RUNNING);
-				spin_unlock_irq(&ctx->wqh.lock);
-				return -ERESTARTSYS;
-			}
+
+		if (wait_event_interruptible_locked_irq(ctx->wqh, ctx->count)) {
 			spin_unlock_irq(&ctx->wqh.lock);
-			schedule();
-			spin_lock_irq(&ctx->wqh.lock);
+			return -ERESTARTSYS;
 		}
-		__remove_wait_queue(&ctx->wqh, &wait);
-		__set_current_state(TASK_RUNNING);
 	}
 	eventfd_ctx_do_read(ctx, &ucnt);
 	current->in_eventfd = 1;
@@ -275,7 +262,6 @@ static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t c
 	struct eventfd_ctx *ctx = file->private_data;
 	ssize_t res;
 	__u64 ucnt;
-	DECLARE_WAITQUEUE(wait, current);
 
 	if (count < sizeof(ucnt))
 		return -EINVAL;
@@ -288,23 +274,10 @@ static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t c
 	if (ULLONG_MAX - ctx->count > ucnt)
 		res = sizeof(ucnt);
 	else if (!(file->f_flags & O_NONBLOCK)) {
-		__add_wait_queue(&ctx->wqh, &wait);
-		for (res = 0;;) {
-			set_current_state(TASK_INTERRUPTIBLE);
-			if (ULLONG_MAX - ctx->count > ucnt) {
-				res = sizeof(ucnt);
-				break;
-			}
-			if (signal_pending(current)) {
-				res = -ERESTARTSYS;
-				break;
-			}
-			spin_unlock_irq(&ctx->wqh.lock);
-			schedule();
-			spin_lock_irq(&ctx->wqh.lock);
-		}
-		__remove_wait_queue(&ctx->wqh, &wait);
-		__set_current_state(TASK_RUNNING);
+		res = wait_event_interruptible_locked_irq(ctx->wqh,
+				ULLONG_MAX - ctx->count > ucnt);
+		if (!res)
+			res = sizeof(ucnt);
 	}
 	if (likely(res > 0)) {
 		ctx->count += ucnt;

From 4ea2a8d84c75e20b4d9b5d9010879cdb89f2e384 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Tue, 28 Mar 2023 18:13:07 +0200
Subject: [PATCH 37/67] pnode: pass mountpoint directly

Currently, we use a global variable to stash the destination
mountpoint. All global variables are changed in propagate_one(). The
mountpoint variable is one of the few which doesn't change after
initialization. Instead, just pass the destination mountpoint directly
making it easy to verify directly in propagate_mnt() that the
destination mountpoint never changes.

Reviewed-by: Seth Forshee (DigitalOcean) <sforshee@kernel.org>
Message-Id: <20230202-fs-move-mount-replace-v2-2-f53cd31d6392@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/pnode.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/fs/pnode.c b/fs/pnode.c
index 468e4e65a615..3cede8b18c8b 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -214,7 +214,6 @@ static struct mount *next_group(struct mount *m, struct mount *origin)
 
 /* all accesses are serialized by namespace_sem */
 static struct mount *last_dest, *first_source, *last_source, *dest_master;
-static struct mountpoint *mp;
 static struct hlist_head *list;
 
 static inline bool peers(struct mount *m1, struct mount *m2)
@@ -222,7 +221,7 @@ static inline bool peers(struct mount *m1, struct mount *m2)
 	return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id;
 }
 
-static int propagate_one(struct mount *m)
+static int propagate_one(struct mount *m, struct mountpoint *dest_mp)
 {
 	struct mount *child;
 	int type;
@@ -230,7 +229,7 @@ static int propagate_one(struct mount *m)
 	if (IS_MNT_NEW(m))
 		return 0;
 	/* skip if mountpoint isn't covered by it */
-	if (!is_subdir(mp->m_dentry, m->mnt.mnt_root))
+	if (!is_subdir(dest_mp->m_dentry, m->mnt.mnt_root))
 		return 0;
 	if (peers(m, last_dest)) {
 		type = CL_MAKE_SHARED;
@@ -262,7 +261,7 @@ static int propagate_one(struct mount *m)
 	if (IS_ERR(child))
 		return PTR_ERR(child);
 	read_seqlock_excl(&mount_lock);
-	mnt_set_mountpoint(m, mp, child);
+	mnt_set_mountpoint(m, dest_mp, child);
 	if (m->mnt_master != dest_master)
 		SET_MNT_MARK(m->mnt_master);
 	read_sequnlock_excl(&mount_lock);
@@ -299,13 +298,12 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
 	last_dest = dest_mnt;
 	first_source = source_mnt;
 	last_source = source_mnt;
-	mp = dest_mp;
 	list = tree_list;
 	dest_master = dest_mnt->mnt_master;
 
 	/* all peers of dest_mnt, except dest_mnt itself */
 	for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) {
-		ret = propagate_one(n);
+		ret = propagate_one(n, dest_mp);
 		if (ret)
 			goto out;
 	}
@@ -316,7 +314,7 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
 		/* everything in that slave group */
 		n = m;
 		do {
-			ret = propagate_one(n);
+			ret = propagate_one(n, dest_mp);
 			if (ret)
 				goto out;
 			n = next_peer(n);

From 81b21c0f0138ff5a499eafc3eb0578ad2a99622c Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Tue, 11 Apr 2023 19:57:33 +0900
Subject: [PATCH 38/67] fs: hfsplus: remove WARN_ON() from
 hfsplus_cat_{read,write}_inode()

syzbot is hitting WARN_ON() in hfsplus_cat_{read,write}_inode(), for
crafted filesystem image can contain bogus length. There conditions are
not kernel bugs that can justify kernel to panic.

Reported-by: syzbot <syzbot+e2787430e752a92b8750@syzkaller.appspotmail.com>
Link: https://syzkaller.appspot.com/bug?extid=e2787430e752a92b8750
Reported-by: syzbot <syzbot+4913dca2ea6e4d43f3f1@syzkaller.appspotmail.com>
Link: https://syzkaller.appspot.com/bug?extid=4913dca2ea6e4d43f3f1
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Reviewed-by: Viacheslav Dubeyko <slava@dubeyko.com>
Message-Id: <15308173-5252-d6a3-ae3b-e96d46cb6f41@I-love.SAKURA.ne.jp>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/hfsplus/inode.c | 28 +++++++++++++++++++++++-----
 1 file changed, 23 insertions(+), 5 deletions(-)

diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index abb91f5fae92..b21660475ac1 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -511,7 +511,11 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
 	if (type == HFSPLUS_FOLDER) {
 		struct hfsplus_cat_folder *folder = &entry.folder;
 
-		WARN_ON(fd->entrylength < sizeof(struct hfsplus_cat_folder));
+		if (fd->entrylength < sizeof(struct hfsplus_cat_folder)) {
+			pr_err("bad catalog folder entry\n");
+			res = -EIO;
+			goto out;
+		}
 		hfs_bnode_read(fd->bnode, &entry, fd->entryoffset,
 					sizeof(struct hfsplus_cat_folder));
 		hfsplus_get_perms(inode, &folder->permissions, 1);
@@ -531,7 +535,11 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
 	} else if (type == HFSPLUS_FILE) {
 		struct hfsplus_cat_file *file = &entry.file;
 
-		WARN_ON(fd->entrylength < sizeof(struct hfsplus_cat_file));
+		if (fd->entrylength < sizeof(struct hfsplus_cat_file)) {
+			pr_err("bad catalog file entry\n");
+			res = -EIO;
+			goto out;
+		}
 		hfs_bnode_read(fd->bnode, &entry, fd->entryoffset,
 					sizeof(struct hfsplus_cat_file));
 
@@ -562,6 +570,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
 		pr_err("bad catalog entry used to create inode\n");
 		res = -EIO;
 	}
+out:
 	return res;
 }
 
@@ -570,6 +579,7 @@ int hfsplus_cat_write_inode(struct inode *inode)
 	struct inode *main_inode = inode;
 	struct hfs_find_data fd;
 	hfsplus_cat_entry entry;
+	int res = 0;
 
 	if (HFSPLUS_IS_RSRC(inode))
 		main_inode = HFSPLUS_I(inode)->rsrc_inode;
@@ -588,7 +598,11 @@ int hfsplus_cat_write_inode(struct inode *inode)
 	if (S_ISDIR(main_inode->i_mode)) {
 		struct hfsplus_cat_folder *folder = &entry.folder;
 
-		WARN_ON(fd.entrylength < sizeof(struct hfsplus_cat_folder));
+		if (fd.entrylength < sizeof(struct hfsplus_cat_folder)) {
+			pr_err("bad catalog folder entry\n");
+			res = -EIO;
+			goto out;
+		}
 		hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
 					sizeof(struct hfsplus_cat_folder));
 		/* simple node checks? */
@@ -613,7 +627,11 @@ int hfsplus_cat_write_inode(struct inode *inode)
 	} else {
 		struct hfsplus_cat_file *file = &entry.file;
 
-		WARN_ON(fd.entrylength < sizeof(struct hfsplus_cat_file));
+		if (fd.entrylength < sizeof(struct hfsplus_cat_file)) {
+			pr_err("bad catalog file entry\n");
+			res = -EIO;
+			goto out;
+		}
 		hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
 					sizeof(struct hfsplus_cat_file));
 		hfsplus_inode_write_fork(inode, &file->data_fork);
@@ -634,7 +652,7 @@ int hfsplus_cat_write_inode(struct inode *inode)
 	set_bit(HFSPLUS_I_CAT_DIRTY, &HFSPLUS_I(inode)->flags);
 out:
 	hfs_find_exit(&fd);
-	return 0;
+	return res;
 }
 
 int hfsplus_fileattr_get(struct dentry *dentry, struct fileattr *fa)

From 3acea5fc335420ba7ef53947cf2d98d07fac39f7 Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Mon, 13 Mar 2023 21:53:08 +0800
Subject: [PATCH 39/67] erofs: avoid hardcoded blocksize for subpage block
 support

As the first step of converting hardcoded blocksize to that specified in
on-disk superblock, convert all call sites of hardcoded blocksize to
sb->s_blocksize except for:

1) use sbi->blkszbits instead of sb->s_blocksize in
erofs_superblock_csum_verify() since sb->s_blocksize has not been
updated with the on-disk blocksize yet when the function is called.

2) use inode->i_blkbits instead of sb->s_blocksize in erofs_bread(),
since the inode operated on may be an anonymous inode in fscache mode.
Currently the anonymous inode is allocated from an anonymous mount
maintained in erofs, while in the near future we may allocate anonymous
inodes from a generic API directly and thus have no access to the
anonymous inode's i_sb.  Thus we keep the block size in i_blkbits for
anonymous inodes in fscache mode.

Be noted that this patch only gets rid of the hardcoded blocksize, in
preparation for actually setting the on-disk block size in the following
patch.  The hard limit of constraining the block size to PAGE_SIZE still
exists until the next patch.

Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Yue Hu <huyue2@coolpad.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20230313135309.75269-2-jefflexu@linux.alibaba.com
[ Gao Xiang: fold a patch to fix incorrect truncated offsets. ]
Link: https://lore.kernel.org/r/20230413035734.15457-1-zhujia.zj@bytedance.com
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/data.c              | 50 +++++++++++++++++++-----------------
 fs/erofs/decompressor.c      |  6 ++---
 fs/erofs/decompressor_lzma.c |  4 +--
 fs/erofs/dir.c               | 22 ++++++++--------
 fs/erofs/fscache.c           |  5 ++--
 fs/erofs/inode.c             | 20 ++++++++-------
 fs/erofs/internal.h          | 20 +++++----------
 fs/erofs/namei.c             | 14 +++++-----
 fs/erofs/super.c             | 27 +++++++++++--------
 fs/erofs/xattr.c             | 40 ++++++++++++++---------------
 fs/erofs/xattr.h             | 10 ++++----
 fs/erofs/zdata.c             | 18 +++++++------
 fs/erofs/zmap.c              | 29 +++++++++++----------
 include/trace/events/erofs.h |  4 +--
 14 files changed, 137 insertions(+), 132 deletions(-)

diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index c08c0f578bc6..1c931e32d28e 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -27,11 +27,15 @@ void erofs_put_metabuf(struct erofs_buf *buf)
 	buf->page = NULL;
 }
 
+/*
+ * Derive the block size from inode->i_blkbits to make compatible with
+ * anonymous inode in fscache mode.
+ */
 void *erofs_bread(struct erofs_buf *buf, struct inode *inode,
 		  erofs_blk_t blkaddr, enum erofs_kmap_type type)
 {
+	erofs_off_t offset = (erofs_off_t)blkaddr << inode->i_blkbits;
 	struct address_space *const mapping = inode->i_mapping;
-	erofs_off_t offset = blknr_to_addr(blkaddr);
 	pgoff_t index = offset >> PAGE_SHIFT;
 	struct page *page = buf->page;
 	struct folio *folio;
@@ -79,33 +83,32 @@ static int erofs_map_blocks_flatmode(struct inode *inode,
 	erofs_blk_t nblocks, lastblk;
 	u64 offset = map->m_la;
 	struct erofs_inode *vi = EROFS_I(inode);
+	struct super_block *sb = inode->i_sb;
 	bool tailendpacking = (vi->datalayout == EROFS_INODE_FLAT_INLINE);
 
-	nblocks = DIV_ROUND_UP(inode->i_size, EROFS_BLKSIZ);
+	nblocks = erofs_iblks(inode);
 	lastblk = nblocks - tailendpacking;
 
 	/* there is no hole in flatmode */
 	map->m_flags = EROFS_MAP_MAPPED;
-	if (offset < blknr_to_addr(lastblk)) {
-		map->m_pa = blknr_to_addr(vi->raw_blkaddr) + map->m_la;
-		map->m_plen = blknr_to_addr(lastblk) - offset;
+	if (offset < erofs_pos(sb, lastblk)) {
+		map->m_pa = erofs_pos(sb, vi->raw_blkaddr) + map->m_la;
+		map->m_plen = erofs_pos(sb, lastblk) - offset;
 	} else if (tailendpacking) {
 		map->m_pa = erofs_iloc(inode) + vi->inode_isize +
-			vi->xattr_isize + erofs_blkoff(offset);
+			vi->xattr_isize + erofs_blkoff(sb, offset);
 		map->m_plen = inode->i_size - offset;
 
 		/* inline data should be located in the same meta block */
-		if (erofs_blkoff(map->m_pa) + map->m_plen > EROFS_BLKSIZ) {
-			erofs_err(inode->i_sb,
-				  "inline data cross block boundary @ nid %llu",
+		if (erofs_blkoff(sb, map->m_pa) + map->m_plen > sb->s_blocksize) {
+			erofs_err(sb, "inline data cross block boundary @ nid %llu",
 				  vi->nid);
 			DBG_BUGON(1);
 			return -EFSCORRUPTED;
 		}
 		map->m_flags |= EROFS_MAP_META;
 	} else {
-		erofs_err(inode->i_sb,
-			  "internal error @ nid: %llu (size %llu), m_la 0x%llx",
+		erofs_err(sb, "internal error @ nid: %llu (size %llu), m_la 0x%llx",
 			  vi->nid, inode->i_size, map->m_la);
 		DBG_BUGON(1);
 		return -EIO;
@@ -148,29 +151,29 @@ int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map)
 	pos = ALIGN(erofs_iloc(inode) + vi->inode_isize +
 		    vi->xattr_isize, unit) + unit * chunknr;
 
-	kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos), EROFS_KMAP);
+	kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(sb, pos), EROFS_KMAP);
 	if (IS_ERR(kaddr)) {
 		err = PTR_ERR(kaddr);
 		goto out;
 	}
 	map->m_la = chunknr << vi->chunkbits;
 	map->m_plen = min_t(erofs_off_t, 1UL << vi->chunkbits,
-			    roundup(inode->i_size - map->m_la, EROFS_BLKSIZ));
+			round_up(inode->i_size - map->m_la, sb->s_blocksize));
 
 	/* handle block map */
 	if (!(vi->chunkformat & EROFS_CHUNK_FORMAT_INDEXES)) {
-		__le32 *blkaddr = kaddr + erofs_blkoff(pos);
+		__le32 *blkaddr = kaddr + erofs_blkoff(sb, pos);
 
 		if (le32_to_cpu(*blkaddr) == EROFS_NULL_ADDR) {
 			map->m_flags = 0;
 		} else {
-			map->m_pa = blknr_to_addr(le32_to_cpu(*blkaddr));
+			map->m_pa = erofs_pos(sb, le32_to_cpu(*blkaddr));
 			map->m_flags = EROFS_MAP_MAPPED;
 		}
 		goto out_unlock;
 	}
 	/* parse chunk indexes */
-	idx = kaddr + erofs_blkoff(pos);
+	idx = kaddr + erofs_blkoff(sb, pos);
 	switch (le32_to_cpu(idx->blkaddr)) {
 	case EROFS_NULL_ADDR:
 		map->m_flags = 0;
@@ -178,7 +181,7 @@ int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map)
 	default:
 		map->m_deviceid = le16_to_cpu(idx->device_id) &
 			EROFS_SB(sb)->device_id_mask;
-		map->m_pa = blknr_to_addr(le32_to_cpu(idx->blkaddr));
+		map->m_pa = erofs_pos(sb, le32_to_cpu(idx->blkaddr));
 		map->m_flags = EROFS_MAP_MAPPED;
 		break;
 	}
@@ -222,8 +225,8 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 
 			if (!dif->mapped_blkaddr)
 				continue;
-			startoff = blknr_to_addr(dif->mapped_blkaddr);
-			length = blknr_to_addr(dif->blocks);
+			startoff = erofs_pos(sb, dif->mapped_blkaddr);
+			length = erofs_pos(sb, dif->blocks);
 
 			if (map->m_pa >= startoff &&
 			    map->m_pa < startoff + length) {
@@ -244,6 +247,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 		unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
 {
 	int ret;
+	struct super_block *sb = inode->i_sb;
 	struct erofs_map_blocks map;
 	struct erofs_map_dev mdev;
 
@@ -258,7 +262,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 		.m_deviceid = map.m_deviceid,
 		.m_pa = map.m_pa,
 	};
-	ret = erofs_map_dev(inode->i_sb, &mdev);
+	ret = erofs_map_dev(sb, &mdev);
 	if (ret)
 		return ret;
 
@@ -284,11 +288,11 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 		struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
 
 		iomap->type = IOMAP_INLINE;
-		ptr = erofs_read_metabuf(&buf, inode->i_sb,
-					 erofs_blknr(mdev.m_pa), EROFS_KMAP);
+		ptr = erofs_read_metabuf(&buf, sb,
+				erofs_blknr(sb, mdev.m_pa), EROFS_KMAP);
 		if (IS_ERR(ptr))
 			return PTR_ERR(ptr);
-		iomap->inline_data = ptr + erofs_blkoff(mdev.m_pa);
+		iomap->inline_data = ptr + erofs_blkoff(sb, mdev.m_pa);
 		iomap->private = buf.base;
 	} else {
 		iomap->type = IOMAP_MAPPED;
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index 51b7ac7166d9..7021e2cf6146 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -42,7 +42,7 @@ int z_erofs_load_lz4_config(struct super_block *sb,
 		if (!sbi->lz4.max_pclusterblks) {
 			sbi->lz4.max_pclusterblks = 1;	/* reserved case */
 		} else if (sbi->lz4.max_pclusterblks >
-			   Z_EROFS_PCLUSTER_MAX_SIZE / EROFS_BLKSIZ) {
+			   erofs_blknr(sb, Z_EROFS_PCLUSTER_MAX_SIZE)) {
 			erofs_err(sb, "too large lz4 pclusterblks %u",
 				  sbi->lz4.max_pclusterblks);
 			return -EINVAL;
@@ -221,13 +221,13 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx,
 		support_0padding = true;
 		ret = z_erofs_fixup_insize(rq, headpage + rq->pageofs_in,
 				min_t(unsigned int, rq->inputsize,
-				      EROFS_BLKSIZ - rq->pageofs_in));
+				      rq->sb->s_blocksize - rq->pageofs_in));
 		if (ret) {
 			kunmap_atomic(headpage);
 			return ret;
 		}
 		may_inplace = !((rq->pageofs_in + rq->inputsize) &
-				(EROFS_BLKSIZ - 1));
+				(rq->sb->s_blocksize - 1));
 	}
 
 	inputmargin = rq->pageofs_in;
diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c
index d38e19c11270..73091fbe3ea4 100644
--- a/fs/erofs/decompressor_lzma.c
+++ b/fs/erofs/decompressor_lzma.c
@@ -166,8 +166,8 @@ int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq,
 	/* 1. get the exact LZMA compressed size */
 	kin = kmap(*rq->in);
 	err = z_erofs_fixup_insize(rq, kin + rq->pageofs_in,
-				   min_t(unsigned int, rq->inputsize,
-					 EROFS_BLKSIZ - rq->pageofs_in));
+			min_t(unsigned int, rq->inputsize,
+			      rq->sb->s_blocksize - rq->pageofs_in));
 	if (err) {
 		kunmap(*rq->in);
 		return err;
diff --git a/fs/erofs/dir.c b/fs/erofs/dir.c
index 6970b09b8307..963bbed0b699 100644
--- a/fs/erofs/dir.c
+++ b/fs/erofs/dir.c
@@ -50,9 +50,11 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx)
 {
 	struct inode *dir = file_inode(f);
 	struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
+	struct super_block *sb = dir->i_sb;
+	unsigned long bsz = sb->s_blocksize;
 	const size_t dirsize = i_size_read(dir);
-	unsigned int i = ctx->pos / EROFS_BLKSIZ;
-	unsigned int ofs = ctx->pos % EROFS_BLKSIZ;
+	unsigned int i = erofs_blknr(sb, ctx->pos);
+	unsigned int ofs = erofs_blkoff(sb, ctx->pos);
 	int err = 0;
 	bool initial = true;
 
@@ -62,32 +64,28 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx)
 
 		de = erofs_bread(&buf, dir, i, EROFS_KMAP);
 		if (IS_ERR(de)) {
-			erofs_err(dir->i_sb,
-				  "fail to readdir of logical block %u of nid %llu",
+			erofs_err(sb, "fail to readdir of logical block %u of nid %llu",
 				  i, EROFS_I(dir)->nid);
 			err = PTR_ERR(de);
 			break;
 		}
 
 		nameoff = le16_to_cpu(de->nameoff);
-		if (nameoff < sizeof(struct erofs_dirent) ||
-		    nameoff >= EROFS_BLKSIZ) {
-			erofs_err(dir->i_sb,
-				  "invalid de[0].nameoff %u @ nid %llu",
+		if (nameoff < sizeof(struct erofs_dirent) || nameoff >= bsz) {
+			erofs_err(sb, "invalid de[0].nameoff %u @ nid %llu",
 				  nameoff, EROFS_I(dir)->nid);
 			err = -EFSCORRUPTED;
 			break;
 		}
 
-		maxsize = min_t(unsigned int,
-				dirsize - ctx->pos + ofs, EROFS_BLKSIZ);
+		maxsize = min_t(unsigned int, dirsize - ctx->pos + ofs, bsz);
 
 		/* search dirents at the arbitrary position */
 		if (initial) {
 			initial = false;
 
 			ofs = roundup(ofs, sizeof(struct erofs_dirent));
-			ctx->pos = blknr_to_addr(i) + ofs;
+			ctx->pos = erofs_pos(sb, i) + ofs;
 			if (ofs >= nameoff)
 				goto skip_this;
 		}
@@ -97,7 +95,7 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx)
 		if (err)
 			break;
 skip_this:
-		ctx->pos = blknr_to_addr(i) + maxsize;
+		ctx->pos = erofs_pos(sb, i) + maxsize;
 		++i;
 		ofs = 0;
 	}
diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c
index 96a87c023128..87ff35bff8d5 100644
--- a/fs/erofs/fscache.c
+++ b/fs/erofs/fscache.c
@@ -209,8 +209,8 @@ static int erofs_fscache_data_read_slice(struct erofs_fscache_request *primary)
 		void *src;
 
 		/* For tail packing layout, the offset may be non-zero. */
-		offset = erofs_blkoff(map.m_pa);
-		blknr = erofs_blknr(map.m_pa);
+		offset = erofs_blkoff(sb, map.m_pa);
+		blknr = erofs_blknr(sb, map.m_pa);
 		size = map.m_llen;
 
 		src = erofs_read_metabuf(&buf, sb, blknr, EROFS_KMAP);
@@ -460,6 +460,7 @@ static struct erofs_fscache *erofs_fscache_acquire_cookie(struct super_block *sb
 	inode->i_size = OFFSET_MAX;
 	inode->i_mapping->a_ops = &erofs_fscache_meta_aops;
 	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
+	inode->i_blkbits = EROFS_SB(sb)->blkszbits;
 	inode->i_private = ctx;
 
 	ctx->cookie = cookie;
diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index 4be7dda3cd24..3502daee8d3b 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -23,8 +23,8 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 	unsigned int ifmt;
 	int err;
 
-	blkaddr = erofs_blknr(inode_loc);
-	*ofs = erofs_blkoff(inode_loc);
+	blkaddr = erofs_blknr(sb, inode_loc);
+	*ofs = erofs_blkoff(sb, inode_loc);
 
 	erofs_dbg("%s, reading inode nid %llu at %u of blkaddr %u",
 		  __func__, vi->nid, *ofs, blkaddr);
@@ -58,11 +58,11 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 	case EROFS_INODE_LAYOUT_EXTENDED:
 		vi->inode_isize = sizeof(struct erofs_inode_extended);
 		/* check if the extended inode acrosses block boundary */
-		if (*ofs + vi->inode_isize <= EROFS_BLKSIZ) {
+		if (*ofs + vi->inode_isize <= sb->s_blocksize) {
 			*ofs += vi->inode_isize;
 			die = (struct erofs_inode_extended *)dic;
 		} else {
-			const unsigned int gotten = EROFS_BLKSIZ - *ofs;
+			const unsigned int gotten = sb->s_blocksize - *ofs;
 
 			copied = kmalloc(vi->inode_isize, GFP_NOFS);
 			if (!copied) {
@@ -176,7 +176,7 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 			err = -EOPNOTSUPP;
 			goto err_out;
 		}
-		vi->chunkbits = LOG_BLOCK_SIZE +
+		vi->chunkbits = sb->s_blocksize_bits +
 			(vi->chunkformat & EROFS_CHUNK_FORMAT_BLKBITS_MASK);
 	}
 	inode->i_mtime.tv_sec = inode->i_ctime.tv_sec;
@@ -188,11 +188,12 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 	if (test_opt(&sbi->opt, DAX_ALWAYS) && S_ISREG(inode->i_mode) &&
 	    vi->datalayout == EROFS_INODE_FLAT_PLAIN)
 		inode->i_flags |= S_DAX;
+
 	if (!nblks)
 		/* measure inode.i_blocks as generic filesystems */
-		inode->i_blocks = roundup(inode->i_size, EROFS_BLKSIZ) >> 9;
+		inode->i_blocks = round_up(inode->i_size, sb->s_blocksize) >> 9;
 	else
-		inode->i_blocks = nblks << LOG_SECTORS_PER_BLOCK;
+		inode->i_blocks = nblks << (sb->s_blocksize_bits - 9);
 	return kaddr;
 
 bogusimode:
@@ -210,11 +211,12 @@ static int erofs_fill_symlink(struct inode *inode, void *kaddr,
 			      unsigned int m_pofs)
 {
 	struct erofs_inode *vi = EROFS_I(inode);
+	unsigned int bsz = i_blocksize(inode);
 	char *lnk;
 
 	/* if it cannot be handled with fast symlink scheme */
 	if (vi->datalayout != EROFS_INODE_FLAT_INLINE ||
-	    inode->i_size >= EROFS_BLKSIZ || inode->i_size < 0) {
+	    inode->i_size >= bsz || inode->i_size < 0) {
 		inode->i_op = &erofs_symlink_iops;
 		return 0;
 	}
@@ -225,7 +227,7 @@ static int erofs_fill_symlink(struct inode *inode, void *kaddr,
 
 	m_pofs += vi->xattr_isize;
 	/* inline symlink data shouldn't cross block boundary */
-	if (m_pofs + inode->i_size > EROFS_BLKSIZ) {
+	if (m_pofs + inode->i_size > bsz) {
 		kfree(lnk);
 		erofs_err(inode->i_sb,
 			  "inline data cross block boundary @ nid %llu",
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 1db018f8c2e8..66ff0513866f 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -147,8 +147,8 @@ struct erofs_sb_info {
 #endif
 	u16 device_id_mask;	/* valid bits of device id to be used */
 
-	/* inode slot unit size in bit shift */
-	unsigned char islotbits;
+	unsigned char islotbits;	/* inode slot unit size in bit shift */
+	unsigned char blkszbits;
 
 	u32 sb_size;			/* total superblock size */
 	u32 build_time_nsec;
@@ -242,13 +242,6 @@ static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
 
 /* we strictly follow PAGE_SIZE and no buffer head yet */
 #define LOG_BLOCK_SIZE		PAGE_SHIFT
-
-#undef LOG_SECTORS_PER_BLOCK
-#define LOG_SECTORS_PER_BLOCK	(PAGE_SHIFT - 9)
-
-#undef SECTORS_PER_BLOCK
-#define SECTORS_PER_BLOCK	(1 << SECTORS_PER_BLOCK)
-
 #define EROFS_BLKSIZ		(1 << LOG_BLOCK_SIZE)
 
 #if (EROFS_BLKSIZ % 4096 || !EROFS_BLKSIZ)
@@ -269,9 +262,10 @@ struct erofs_buf {
 
 #define ROOT_NID(sb)		((sb)->root_nid)
 
-#define erofs_blknr(addr)       ((addr) / EROFS_BLKSIZ)
-#define erofs_blkoff(addr)      ((addr) % EROFS_BLKSIZ)
-#define blknr_to_addr(nr)       ((erofs_off_t)(nr) * EROFS_BLKSIZ)
+#define erofs_blknr(sb, addr)	((addr) >> (sb)->s_blocksize_bits)
+#define erofs_blkoff(sb, addr)	((addr) & ((sb)->s_blocksize - 1))
+#define erofs_pos(sb, blk)	((erofs_off_t)(blk) << (sb)->s_blocksize_bits)
+#define erofs_iblks(i)	(round_up((i)->i_size, i_blocksize(i)) >> (i)->i_blkbits)
 
 #define EROFS_FEATURE_FUNCS(name, compat, feature) \
 static inline bool erofs_sb_has_##name(struct erofs_sb_info *sbi) \
@@ -343,7 +337,7 @@ static inline erofs_off_t erofs_iloc(struct inode *inode)
 {
 	struct erofs_sb_info *sbi = EROFS_I_SB(inode);
 
-	return blknr_to_addr(sbi->meta_blkaddr) +
+	return erofs_pos(inode->i_sb, sbi->meta_blkaddr) +
 		(EROFS_I(inode)->nid << sbi->islotbits);
 }
 
diff --git a/fs/erofs/namei.c b/fs/erofs/namei.c
index 966eabc61c13..f091e9a0f0a1 100644
--- a/fs/erofs/namei.c
+++ b/fs/erofs/namei.c
@@ -89,7 +89,8 @@ static struct erofs_dirent *find_target_dirent(struct erofs_qstr *name,
 static void *erofs_find_target_block(struct erofs_buf *target,
 		struct inode *dir, struct erofs_qstr *name, int *_ndirents)
 {
-	int head = 0, back = DIV_ROUND_UP(dir->i_size, EROFS_BLKSIZ) - 1;
+	unsigned int bsz = i_blocksize(dir);
+	int head = 0, back = erofs_iblks(dir) - 1;
 	unsigned int startprfx = 0, endprfx = 0;
 	void *candidate = ERR_PTR(-ENOENT);
 
@@ -100,8 +101,7 @@ static void *erofs_find_target_block(struct erofs_buf *target,
 
 		de = erofs_bread(&buf, dir, mid, EROFS_KMAP);
 		if (!IS_ERR(de)) {
-			const int nameoff = nameoff_from_disk(de->nameoff,
-							      EROFS_BLKSIZ);
+			const int nameoff = nameoff_from_disk(de->nameoff, bsz);
 			const int ndirents = nameoff / sizeof(*de);
 			int diff;
 			unsigned int matched;
@@ -121,11 +121,10 @@ static void *erofs_find_target_block(struct erofs_buf *target,
 
 			dname.name = (u8 *)de + nameoff;
 			if (ndirents == 1)
-				dname.end = (u8 *)de + EROFS_BLKSIZ;
+				dname.end = (u8 *)de + bsz;
 			else
 				dname.end = (u8 *)de +
-					nameoff_from_disk(de[1].nameoff,
-							  EROFS_BLKSIZ);
+					nameoff_from_disk(de[1].nameoff, bsz);
 
 			/* string comparison without already matched prefix */
 			diff = erofs_dirnamecmp(name, &dname, &matched);
@@ -178,7 +177,8 @@ int erofs_namei(struct inode *dir, const struct qstr *name, erofs_nid_t *nid,
 		return PTR_ERR(de);
 
 	if (ndirents)
-		de = find_target_dirent(&qn, (u8 *)de, EROFS_BLKSIZ, ndirents);
+		de = find_target_dirent(&qn, (u8 *)de, i_blocksize(dir),
+					ndirents);
 
 	if (!IS_ERR(de)) {
 		*nid = le64_to_cpu(de->nid);
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 19b1ae79cec4..4303b4e69e55 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -52,18 +52,21 @@ void _erofs_info(struct super_block *sb, const char *function,
 
 static int erofs_superblock_csum_verify(struct super_block *sb, void *sbdata)
 {
+	size_t len = 1 << EROFS_SB(sb)->blkszbits;
 	struct erofs_super_block *dsb;
 	u32 expected_crc, crc;
 
-	dsb = kmemdup(sbdata + EROFS_SUPER_OFFSET,
-		      EROFS_BLKSIZ - EROFS_SUPER_OFFSET, GFP_KERNEL);
+	if (len > EROFS_SUPER_OFFSET)
+		len -= EROFS_SUPER_OFFSET;
+
+	dsb = kmemdup(sbdata + EROFS_SUPER_OFFSET, len, GFP_KERNEL);
 	if (!dsb)
 		return -ENOMEM;
 
 	expected_crc = le32_to_cpu(dsb->checksum);
 	dsb->checksum = 0;
 	/* to allow for x86 boot sectors and other oddities. */
-	crc = crc32c(~0, dsb, EROFS_BLKSIZ - EROFS_SUPER_OFFSET);
+	crc = crc32c(~0, dsb, len);
 	kfree(dsb);
 
 	if (crc != expected_crc) {
@@ -132,11 +135,11 @@ static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf,
 	int len, i, cnt;
 
 	*offset = round_up(*offset, 4);
-	ptr = erofs_read_metabuf(buf, sb, erofs_blknr(*offset), EROFS_KMAP);
+	ptr = erofs_read_metabuf(buf, sb, erofs_blknr(sb, *offset), EROFS_KMAP);
 	if (IS_ERR(ptr))
 		return ptr;
 
-	len = le16_to_cpu(*(__le16 *)&ptr[erofs_blkoff(*offset)]);
+	len = le16_to_cpu(*(__le16 *)&ptr[erofs_blkoff(sb, *offset)]);
 	if (!len)
 		len = U16_MAX + 1;
 	buffer = kmalloc(len, GFP_KERNEL);
@@ -146,14 +149,15 @@ static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf,
 	*lengthp = len;
 
 	for (i = 0; i < len; i += cnt) {
-		cnt = min(EROFS_BLKSIZ - (int)erofs_blkoff(*offset), len - i);
-		ptr = erofs_read_metabuf(buf, sb, erofs_blknr(*offset),
+		cnt = min_t(int, sb->s_blocksize - erofs_blkoff(sb, *offset),
+			    len - i);
+		ptr = erofs_read_metabuf(buf, sb, erofs_blknr(sb, *offset),
 					 EROFS_KMAP);
 		if (IS_ERR(ptr)) {
 			kfree(buffer);
 			return ptr;
 		}
-		memcpy(buffer + i, ptr + erofs_blkoff(*offset), cnt);
+		memcpy(buffer + i, ptr + erofs_blkoff(sb, *offset), cnt);
 		*offset += cnt;
 	}
 	return buffer;
@@ -228,10 +232,10 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 	struct block_device *bdev;
 	void *ptr;
 
-	ptr = erofs_read_metabuf(buf, sb, erofs_blknr(*pos), EROFS_KMAP);
+	ptr = erofs_read_metabuf(buf, sb, erofs_blknr(sb, *pos), EROFS_KMAP);
 	if (IS_ERR(ptr))
 		return PTR_ERR(ptr);
-	dis = ptr + erofs_blkoff(*pos);
+	dis = ptr + erofs_blkoff(sb, *pos);
 
 	if (!dif->path) {
 		if (!dis->tag[0]) {
@@ -733,6 +737,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 	sbi->domain_id = ctx->domain_id;
 	ctx->domain_id = NULL;
 
+	sbi->blkszbits = PAGE_SHIFT;
 	if (erofs_is_fscache_mode(sb)) {
 		sb->s_blocksize = EROFS_BLKSIZ;
 		sb->s_blocksize_bits = LOG_BLOCK_SIZE;
@@ -1060,7 +1065,7 @@ static int erofs_statfs(struct dentry *dentry, struct kstatfs *buf)
 		id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	buf->f_type = sb->s_magic;
-	buf->f_bsize = EROFS_BLKSIZ;
+	buf->f_bsize = sb->s_blocksize;
 	buf->f_blocks = sbi->total_blocks;
 	buf->f_bfree = buf->f_bavail = 0;
 
diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c
index 60729b1220b6..459caa3cd65d 100644
--- a/fs/erofs/xattr.c
+++ b/fs/erofs/xattr.c
@@ -68,8 +68,8 @@ static int init_inode_xattrs(struct inode *inode)
 	}
 
 	it.buf = __EROFS_BUF_INITIALIZER;
-	it.blkaddr = erofs_blknr(erofs_iloc(inode) + vi->inode_isize);
-	it.ofs = erofs_blkoff(erofs_iloc(inode) + vi->inode_isize);
+	it.blkaddr = erofs_blknr(sb, erofs_iloc(inode) + vi->inode_isize);
+	it.ofs = erofs_blkoff(sb, erofs_iloc(inode) + vi->inode_isize);
 
 	/* read in shared xattr array (non-atomic, see kmalloc below) */
 	it.kaddr = erofs_read_metabuf(&it.buf, sb, it.blkaddr, EROFS_KMAP);
@@ -92,9 +92,9 @@ static int init_inode_xattrs(struct inode *inode)
 	it.ofs += sizeof(struct erofs_xattr_ibody_header);
 
 	for (i = 0; i < vi->xattr_shared_count; ++i) {
-		if (it.ofs >= EROFS_BLKSIZ) {
+		if (it.ofs >= sb->s_blocksize) {
 			/* cannot be unaligned */
-			DBG_BUGON(it.ofs != EROFS_BLKSIZ);
+			DBG_BUGON(it.ofs != sb->s_blocksize);
 
 			it.kaddr = erofs_read_metabuf(&it.buf, sb, ++it.blkaddr,
 						      EROFS_KMAP);
@@ -139,15 +139,15 @@ struct xattr_iter_handlers {
 
 static inline int xattr_iter_fixup(struct xattr_iter *it)
 {
-	if (it->ofs < EROFS_BLKSIZ)
+	if (it->ofs < it->sb->s_blocksize)
 		return 0;
 
-	it->blkaddr += erofs_blknr(it->ofs);
+	it->blkaddr += erofs_blknr(it->sb, it->ofs);
 	it->kaddr = erofs_read_metabuf(&it->buf, it->sb, it->blkaddr,
 				       EROFS_KMAP);
 	if (IS_ERR(it->kaddr))
 		return PTR_ERR(it->kaddr);
-	it->ofs = erofs_blkoff(it->ofs);
+	it->ofs = erofs_blkoff(it->sb, it->ofs);
 	return 0;
 }
 
@@ -165,8 +165,8 @@ static int inline_xattr_iter_begin(struct xattr_iter *it,
 
 	inline_xattr_ofs = vi->inode_isize + xattr_header_sz;
 
-	it->blkaddr = erofs_blknr(erofs_iloc(inode) + inline_xattr_ofs);
-	it->ofs = erofs_blkoff(erofs_iloc(inode) + inline_xattr_ofs);
+	it->blkaddr = erofs_blknr(it->sb, erofs_iloc(inode) + inline_xattr_ofs);
+	it->ofs = erofs_blkoff(it->sb, erofs_iloc(inode) + inline_xattr_ofs);
 	it->kaddr = erofs_read_metabuf(&it->buf, inode->i_sb, it->blkaddr,
 				       EROFS_KMAP);
 	if (IS_ERR(it->kaddr))
@@ -222,8 +222,8 @@ static int xattr_foreach(struct xattr_iter *it,
 	processed = 0;
 
 	while (processed < entry.e_name_len) {
-		if (it->ofs >= EROFS_BLKSIZ) {
-			DBG_BUGON(it->ofs > EROFS_BLKSIZ);
+		if (it->ofs >= it->sb->s_blocksize) {
+			DBG_BUGON(it->ofs > it->sb->s_blocksize);
 
 			err = xattr_iter_fixup(it);
 			if (err)
@@ -231,7 +231,7 @@ static int xattr_foreach(struct xattr_iter *it,
 			it->ofs = 0;
 		}
 
-		slice = min_t(unsigned int, EROFS_BLKSIZ - it->ofs,
+		slice = min_t(unsigned int, it->sb->s_blocksize - it->ofs,
 			      entry.e_name_len - processed);
 
 		/* handle name */
@@ -257,8 +257,8 @@ static int xattr_foreach(struct xattr_iter *it,
 	}
 
 	while (processed < value_sz) {
-		if (it->ofs >= EROFS_BLKSIZ) {
-			DBG_BUGON(it->ofs > EROFS_BLKSIZ);
+		if (it->ofs >= it->sb->s_blocksize) {
+			DBG_BUGON(it->ofs > it->sb->s_blocksize);
 
 			err = xattr_iter_fixup(it);
 			if (err)
@@ -266,7 +266,7 @@ static int xattr_foreach(struct xattr_iter *it,
 			it->ofs = 0;
 		}
 
-		slice = min_t(unsigned int, EROFS_BLKSIZ - it->ofs,
+		slice = min_t(unsigned int, it->sb->s_blocksize - it->ofs,
 			      value_sz - processed);
 		op->value(it, processed, it->kaddr + it->ofs, slice);
 		it->ofs += slice;
@@ -352,15 +352,14 @@ static int shared_getxattr(struct inode *inode, struct getxattr_iter *it)
 {
 	struct erofs_inode *const vi = EROFS_I(inode);
 	struct super_block *const sb = inode->i_sb;
-	struct erofs_sb_info *const sbi = EROFS_SB(sb);
 	unsigned int i;
 	int ret = -ENOATTR;
 
 	for (i = 0; i < vi->xattr_shared_count; ++i) {
 		erofs_blk_t blkaddr =
-			xattrblock_addr(sbi, vi->xattr_shared_xattrs[i]);
+			xattrblock_addr(sb, vi->xattr_shared_xattrs[i]);
 
-		it->it.ofs = xattrblock_offset(sbi, vi->xattr_shared_xattrs[i]);
+		it->it.ofs = xattrblock_offset(sb, vi->xattr_shared_xattrs[i]);
 		it->it.kaddr = erofs_read_metabuf(&it->it.buf, sb, blkaddr,
 						  EROFS_KMAP);
 		if (IS_ERR(it->it.kaddr))
@@ -564,15 +563,14 @@ static int shared_listxattr(struct listxattr_iter *it)
 	struct inode *const inode = d_inode(it->dentry);
 	struct erofs_inode *const vi = EROFS_I(inode);
 	struct super_block *const sb = inode->i_sb;
-	struct erofs_sb_info *const sbi = EROFS_SB(sb);
 	unsigned int i;
 	int ret = 0;
 
 	for (i = 0; i < vi->xattr_shared_count; ++i) {
 		erofs_blk_t blkaddr =
-			xattrblock_addr(sbi, vi->xattr_shared_xattrs[i]);
+			xattrblock_addr(sb, vi->xattr_shared_xattrs[i]);
 
-		it->it.ofs = xattrblock_offset(sbi, vi->xattr_shared_xattrs[i]);
+		it->it.ofs = xattrblock_offset(sb, vi->xattr_shared_xattrs[i]);
 		it->it.kaddr = erofs_read_metabuf(&it->it.buf, sb, blkaddr,
 						  EROFS_KMAP);
 		if (IS_ERR(it->it.kaddr))
diff --git a/fs/erofs/xattr.h b/fs/erofs/xattr.h
index 0a43c9ee9f8f..f7a21aaa9755 100644
--- a/fs/erofs/xattr.h
+++ b/fs/erofs/xattr.h
@@ -19,21 +19,21 @@ static inline unsigned int inlinexattr_header_size(struct inode *inode)
 		sizeof(u32) * EROFS_I(inode)->xattr_shared_count;
 }
 
-static inline erofs_blk_t xattrblock_addr(struct erofs_sb_info *sbi,
+static inline erofs_blk_t xattrblock_addr(struct super_block *sb,
 					  unsigned int xattr_id)
 {
 #ifdef CONFIG_EROFS_FS_XATTR
-	return sbi->xattr_blkaddr +
-		xattr_id * sizeof(__u32) / EROFS_BLKSIZ;
+	return EROFS_SB(sb)->xattr_blkaddr +
+		xattr_id * sizeof(__u32) / sb->s_blocksize;
 #else
 	return 0;
 #endif
 }
 
-static inline unsigned int xattrblock_offset(struct erofs_sb_info *sbi,
+static inline unsigned int xattrblock_offset(struct super_block *sb,
 					     unsigned int xattr_id)
 {
-	return (xattr_id * sizeof(__u32)) % EROFS_BLKSIZ;
+	return (xattr_id * sizeof(__u32)) % sb->s_blocksize;
 }
 
 #ifdef CONFIG_EROFS_FS_XATTR
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index f1708c77a991..a90d37c7bdd7 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -807,7 +807,7 @@ static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe)
 
 	if (ztailpacking) {
 		pcl->obj.index = 0;	/* which indicates ztailpacking */
-		pcl->pageofs_in = erofs_blkoff(map->m_pa);
+		pcl->pageofs_in = erofs_blkoff(fe->inode->i_sb, map->m_pa);
 		pcl->tailpacking_size = map->m_plen;
 	} else {
 		pcl->obj.index = map->m_pa >> PAGE_SHIFT;
@@ -930,6 +930,7 @@ static int z_erofs_read_fragment(struct inode *inode, erofs_off_t pos,
 				 struct page *page, unsigned int pageofs,
 				 unsigned int len)
 {
+	struct super_block *sb = inode->i_sb;
 	struct inode *packed_inode = EROFS_I_SB(inode)->packed_inode;
 	struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
 	u8 *src, *dst;
@@ -941,16 +942,16 @@ static int z_erofs_read_fragment(struct inode *inode, erofs_off_t pos,
 	pos += EROFS_I(inode)->z_fragmentoff;
 	for (i = 0; i < len; i += cnt) {
 		cnt = min_t(unsigned int, len - i,
-			    EROFS_BLKSIZ - erofs_blkoff(pos));
+			    sb->s_blocksize - erofs_blkoff(sb, pos));
 		src = erofs_bread(&buf, packed_inode,
-				  erofs_blknr(pos), EROFS_KMAP);
+				  erofs_blknr(sb, pos), EROFS_KMAP);
 		if (IS_ERR(src)) {
 			erofs_put_metabuf(&buf);
 			return PTR_ERR(src);
 		}
 
 		dst = kmap_local_page(page);
-		memcpy(dst + pageofs + i, src + erofs_blkoff(pos), cnt);
+		memcpy(dst + pageofs + i, src + erofs_blkoff(sb, pos), cnt);
 		kunmap_local(dst);
 		pos += cnt;
 	}
@@ -1005,7 +1006,8 @@ repeat:
 		void *mp;
 
 		mp = erofs_read_metabuf(&fe->map.buf, inode->i_sb,
-					erofs_blknr(map->m_pa), EROFS_NO_KMAP);
+					erofs_blknr(inode->i_sb, map->m_pa),
+					EROFS_NO_KMAP);
 		if (IS_ERR(mp)) {
 			err = PTR_ERR(mp);
 			erofs_err(inode->i_sb,
@@ -1726,11 +1728,11 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 
 		/* no device id here, thus it will always succeed */
 		mdev = (struct erofs_map_dev) {
-			.m_pa = blknr_to_addr(pcl->obj.index),
+			.m_pa = erofs_pos(sb, pcl->obj.index),
 		};
 		(void)erofs_map_dev(sb, &mdev);
 
-		cur = erofs_blknr(mdev.m_pa);
+		cur = erofs_blknr(sb, mdev.m_pa);
 		end = cur + pcl->pclusterpages;
 
 		do {
@@ -1764,7 +1766,7 @@ submit_bio_retry:
 
 				last_bdev = mdev.m_bdev;
 				bio->bi_iter.bi_sector = (sector_t)cur <<
-					LOG_SECTORS_PER_BLOCK;
+					(sb->s_blocksize_bits - 9);
 				bio->bi_private = q[JQ_SUBMIT];
 				if (f->readahead)
 					bio->bi_opf |= REQ_RAHEAD;
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 655da4d739cb..ecbcae9b5494 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -18,7 +18,7 @@ int z_erofs_fill_inode(struct inode *inode)
 		vi->z_advise = 0;
 		vi->z_algorithmtype[0] = 0;
 		vi->z_algorithmtype[1] = 0;
-		vi->z_logical_clusterbits = LOG_BLOCK_SIZE;
+		vi->z_logical_clusterbits = inode->i_sb->s_blocksize_bits;
 		set_bit(EROFS_I_Z_INITED_BIT, &vi->flags);
 	}
 	inode->i_mapping->a_ops = &z_erofs_aops;
@@ -53,13 +53,13 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m,
 	unsigned int advise, type;
 
 	m->kaddr = erofs_read_metabuf(&m->map->buf, inode->i_sb,
-				      erofs_blknr(pos), EROFS_KMAP);
+				      erofs_blknr(inode->i_sb, pos), EROFS_KMAP);
 	if (IS_ERR(m->kaddr))
 		return PTR_ERR(m->kaddr);
 
 	m->nextpackoff = pos + sizeof(struct z_erofs_vle_decompressed_index);
 	m->lcn = lcn;
-	di = m->kaddr + erofs_blkoff(pos);
+	di = m->kaddr + erofs_blkoff(inode->i_sb, pos);
 
 	advise = le16_to_cpu(di->di_advise);
 	type = (advise >> Z_EROFS_VLE_DI_CLUSTER_TYPE_BIT) &
@@ -156,7 +156,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 			 (vcnt << amortizedshift);
 	big_pcluster = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1;
 	encodebits = ((vcnt << amortizedshift) - sizeof(__le32)) * 8 / vcnt;
-	eofs = erofs_blkoff(pos);
+	eofs = erofs_blkoff(m->inode->i_sb, pos);
 	base = round_down(eofs, vcnt << amortizedshift);
 	in = m->kaddr + base;
 
@@ -249,7 +249,7 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m,
 	const unsigned int lclusterbits = vi->z_logical_clusterbits;
 	const erofs_off_t ebase = sizeof(struct z_erofs_map_header) +
 		ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, 8);
-	const unsigned int totalidx = DIV_ROUND_UP(inode->i_size, EROFS_BLKSIZ);
+	unsigned int totalidx = erofs_iblks(inode);
 	unsigned int compacted_4b_initial, compacted_2b;
 	unsigned int amortizedshift;
 	erofs_off_t pos;
@@ -290,7 +290,7 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m,
 out:
 	pos += lcn * (1 << amortizedshift);
 	m->kaddr = erofs_read_metabuf(&m->map->buf, inode->i_sb,
-				      erofs_blknr(pos), EROFS_KMAP);
+				      erofs_blknr(inode->i_sb, pos), EROFS_KMAP);
 	if (IS_ERR(m->kaddr))
 		return PTR_ERR(m->kaddr);
 	return unpack_compacted_index(m, amortizedshift, pos, lookahead);
@@ -360,6 +360,7 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m,
 static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
 					    unsigned int initial_lcn)
 {
+	struct super_block *sb = m->inode->i_sb;
 	struct erofs_inode *const vi = EROFS_I(m->inode);
 	struct erofs_map_blocks *const map = m->map;
 	const unsigned int lclusterbits = vi->z_logical_clusterbits;
@@ -406,7 +407,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
 		 * if the 1st NONHEAD lcluster is actually PLAIN or HEAD type
 		 * rather than CBLKCNT, it's a 1 lcluster-sized pcluster.
 		 */
-		m->compressedblks = 1 << (lclusterbits - LOG_BLOCK_SIZE);
+		m->compressedblks = 1 << (lclusterbits - sb->s_blocksize_bits);
 		break;
 	case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
 		if (m->delta[0] != 1)
@@ -422,7 +423,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
 		return -EFSCORRUPTED;
 	}
 out:
-	map->m_plen = (u64)m->compressedblks << LOG_BLOCK_SIZE;
+	map->m_plen = erofs_pos(sb, m->compressedblks);
 	return 0;
 err_bonus_cblkcnt:
 	erofs_err(m->inode->i_sb,
@@ -565,7 +566,7 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 	} else if (fragment && m.lcn == vi->z_tailextent_headlcn) {
 		map->m_flags |= EROFS_MAP_FRAGMENT;
 	} else {
-		map->m_pa = blknr_to_addr(m.pblk);
+		map->m_pa = erofs_pos(inode->i_sb, m.pblk);
 		err = z_erofs_get_extent_compressedlen(&m, initial_lcn);
 		if (err)
 			goto unmap_out;
@@ -592,7 +593,7 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 	if ((flags & EROFS_GET_BLOCKS_FIEMAP) ||
 	    ((flags & EROFS_GET_BLOCKS_READMORE) &&
 	     map->m_algorithmformat == Z_EROFS_COMPRESSION_LZMA &&
-	     map->m_llen >= EROFS_BLKSIZ)) {
+	     map->m_llen >= i_blocksize(inode))) {
 		err = z_erofs_get_extent_decompressedlen(&m);
 		if (!err)
 			map->m_flags |= EROFS_MAP_FULL_MAPPED;
@@ -633,13 +634,13 @@ static int z_erofs_fill_inode_lazy(struct inode *inode)
 		goto out_unlock;
 
 	pos = ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, 8);
-	kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos), EROFS_KMAP);
+	kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(sb, pos), EROFS_KMAP);
 	if (IS_ERR(kaddr)) {
 		err = PTR_ERR(kaddr);
 		goto out_unlock;
 	}
 
-	h = kaddr + erofs_blkoff(pos);
+	h = kaddr + erofs_blkoff(sb, pos);
 	/*
 	 * if the highest bit of the 8-byte map header is set, the whole file
 	 * is stored in the packed inode. The rest bits keeps z_fragmentoff.
@@ -663,7 +664,7 @@ static int z_erofs_fill_inode_lazy(struct inode *inode)
 		goto out_put_metabuf;
 	}
 
-	vi->z_logical_clusterbits = LOG_BLOCK_SIZE + (h->h_clusterbits & 7);
+	vi->z_logical_clusterbits = sb->s_blocksize_bits + (h->h_clusterbits & 7);
 	if (!erofs_sb_has_big_pcluster(EROFS_SB(sb)) &&
 	    vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 |
 			    Z_EROFS_ADVISE_BIG_PCLUSTER_2)) {
@@ -692,7 +693,7 @@ static int z_erofs_fill_inode_lazy(struct inode *inode)
 		erofs_put_metabuf(&map.buf);
 
 		if (!map.m_plen ||
-		    erofs_blkoff(map.m_pa) + map.m_plen > EROFS_BLKSIZ) {
+		    erofs_blkoff(sb, map.m_pa) + map.m_plen > sb->s_blocksize) {
 			erofs_err(sb, "invalid tail-packing pclustersize %llu",
 				  map.m_plen);
 			err = -EFSCORRUPTED;
diff --git a/include/trace/events/erofs.h b/include/trace/events/erofs.h
index cf4a0d28b178..71dbe8bfa7db 100644
--- a/include/trace/events/erofs.h
+++ b/include/trace/events/erofs.h
@@ -71,8 +71,8 @@ TRACE_EVENT(erofs_fill_inode,
 	TP_fast_assign(
 		__entry->dev		= inode->i_sb->s_dev;
 		__entry->nid		= EROFS_I(inode)->nid;
-		__entry->blkaddr	= erofs_blknr(erofs_iloc(inode));
-		__entry->ofs		= erofs_blkoff(erofs_iloc(inode));
+		__entry->blkaddr	= erofs_blknr(inode->i_sb, erofs_iloc(inode));
+		__entry->ofs		= erofs_blkoff(inode->i_sb, erofs_iloc(inode));
 	),
 
 	TP_printk("dev = (%d,%d), nid = %llu, blkaddr %u ofs %u",

From d3c4bdcc756e60b95365c66ff58844ce75d1c8f8 Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Mon, 13 Mar 2023 21:53:09 +0800
Subject: [PATCH 40/67] erofs: set block size to the on-disk block size

Set the block size to that specified in on-disk superblock.

Also remove the hard constraint of PAGE_SIZE block size for the
uncompressed device backend.  This constraint is temporarily remained
for compressed device and fscache backend, as there is more work needed
to handle the condition where the block size is not equal to PAGE_SIZE.

It is worth noting that the on-disk block size is read prior to
erofs_superblock_csum_verify(), as the read block size is needed in the
latter.

Besides, later we are going to make erofs refer to tar data blobs (which
is 512-byte aligned) for OCI containers, where the block size is 512
bytes.  In this case, the 512-byte block size may not be adequate for a
directory to contain enough dirents.  To fix this, we are also going to
introduce directory block size independent on the block size.

Due to we have already supported block size smaller than PAGE_SIZE now,
disable all these images with such separated directory block size until
we supported this feature later.

Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Yue Hu <huyue2@coolpad.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20230313135309.75269-3-jefflexu@linux.alibaba.com
[ Gao Xiang: update documentation. ]
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 Documentation/filesystems/erofs.rst |  4 +--
 fs/erofs/erofs_fs.h                 |  5 ++--
 fs/erofs/inode.c                    |  3 +-
 fs/erofs/internal.h                 | 10 +------
 fs/erofs/super.c                    | 45 +++++++++++++++++++----------
 5 files changed, 37 insertions(+), 30 deletions(-)

diff --git a/Documentation/filesystems/erofs.rst b/Documentation/filesystems/erofs.rst
index a43aacf1494e..4654ee57c1d5 100644
--- a/Documentation/filesystems/erofs.rst
+++ b/Documentation/filesystems/erofs.rst
@@ -40,8 +40,8 @@ Here are the main features of EROFS:
  - Support multiple devices to refer to external blobs, which can be used
    for container images;
 
- - 4KiB block size and 32-bit block addresses for each device, therefore
-   16TiB address space at most for now;
+ - 32-bit block addresses for each device, therefore 16TiB address space at
+   most with 4KiB block size for now;
 
  - Two inode layouts for different requirements:
 
diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index dbcd24371002..44876a97cabd 100644
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -53,7 +53,7 @@ struct erofs_super_block {
 	__le32 magic;           /* file system magic number */
 	__le32 checksum;        /* crc32c(super_block) */
 	__le32 feature_compat;
-	__u8 blkszbits;         /* support block_size == PAGE_SIZE only */
+	__u8 blkszbits;         /* filesystem block size in bit shift */
 	__u8 sb_extslots;	/* superblock size = 128 + sb_extslots * 16 */
 
 	__le16 root_nid;	/* nid of root directory */
@@ -75,7 +75,8 @@ struct erofs_super_block {
 	} __packed u1;
 	__le16 extra_devices;	/* # of devices besides the primary device */
 	__le16 devt_slotoff;	/* startoff = devt_slotoff * devt_slotsize */
-	__u8 reserved[6];
+	__u8 dirblkbits;	/* directory block size in bit shift */
+	__u8 reserved[5];
 	__le64 packed_nid;	/* nid of the special packed inode */
 	__u8 reserved2[24];
 };
diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index 3502daee8d3b..7ca9aafb7471 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -291,7 +291,8 @@ static int erofs_fill_inode(struct inode *inode)
 	}
 
 	if (erofs_inode_is_data_compressed(vi->datalayout)) {
-		if (!erofs_is_fscache_mode(inode->i_sb))
+		if (!erofs_is_fscache_mode(inode->i_sb) &&
+		    inode->i_sb->s_blocksize_bits == PAGE_SHIFT)
 			err = z_erofs_fill_inode(inode);
 		else
 			err = -EOPNOTSUPP;
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 66ff0513866f..9eff0c0ad2d7 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -148,7 +148,7 @@ struct erofs_sb_info {
 	u16 device_id_mask;	/* valid bits of device id to be used */
 
 	unsigned char islotbits;	/* inode slot unit size in bit shift */
-	unsigned char blkszbits;
+	unsigned char blkszbits;	/* filesystem block size in bit shift */
 
 	u32 sb_size;			/* total superblock size */
 	u32 build_time_nsec;
@@ -240,14 +240,6 @@ static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
 					VAL != EROFS_LOCKED_MAGIC);
 }
 
-/* we strictly follow PAGE_SIZE and no buffer head yet */
-#define LOG_BLOCK_SIZE		PAGE_SHIFT
-#define EROFS_BLKSIZ		(1 << LOG_BLOCK_SIZE)
-
-#if (EROFS_BLKSIZ % 4096 || !EROFS_BLKSIZ)
-#error erofs cannot be used in this platform
-#endif
-
 enum erofs_kmap_type {
 	EROFS_NO_KMAP,		/* don't map the buffer */
 	EROFS_KMAP,		/* use kmap_local_page() to map the buffer */
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 4303b4e69e55..dbffcdd696df 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -333,7 +333,6 @@ static int erofs_read_superblock(struct super_block *sb)
 	struct erofs_sb_info *sbi;
 	struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
 	struct erofs_super_block *dsb;
-	unsigned int blkszbits;
 	void *data;
 	int ret;
 
@@ -352,6 +351,16 @@ static int erofs_read_superblock(struct super_block *sb)
 		goto out;
 	}
 
+	sbi->blkszbits  = dsb->blkszbits;
+	if (sbi->blkszbits < 9 || sbi->blkszbits > PAGE_SHIFT) {
+		erofs_err(sb, "blkszbits %u isn't supported", sbi->blkszbits);
+		goto out;
+	}
+	if (dsb->dirblkbits) {
+		erofs_err(sb, "dirblkbits %u isn't supported", dsb->dirblkbits);
+		goto out;
+	}
+
 	sbi->feature_compat = le32_to_cpu(dsb->feature_compat);
 	if (erofs_sb_has_sb_chksum(sbi)) {
 		ret = erofs_superblock_csum_verify(sb, data);
@@ -360,19 +369,11 @@ static int erofs_read_superblock(struct super_block *sb)
 	}
 
 	ret = -EINVAL;
-	blkszbits = dsb->blkszbits;
-	/* 9(512 bytes) + LOG_SECTORS_PER_BLOCK == LOG_BLOCK_SIZE */
-	if (blkszbits != LOG_BLOCK_SIZE) {
-		erofs_err(sb, "blkszbits %u isn't supported on this platform",
-			  blkszbits);
-		goto out;
-	}
-
 	if (!check_layout_compatibility(sb, dsb))
 		goto out;
 
 	sbi->sb_size = 128 + dsb->sb_extslots * EROFS_SB_EXTSLOT_SIZE;
-	if (sbi->sb_size > EROFS_BLKSIZ) {
+	if (sbi->sb_size > PAGE_SIZE - EROFS_SUPER_OFFSET) {
 		erofs_err(sb, "invalid sb_extslots %u (more than a fs block)",
 			  sbi->sb_size);
 		goto out;
@@ -739,8 +740,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 
 	sbi->blkszbits = PAGE_SHIFT;
 	if (erofs_is_fscache_mode(sb)) {
-		sb->s_blocksize = EROFS_BLKSIZ;
-		sb->s_blocksize_bits = LOG_BLOCK_SIZE;
+		sb->s_blocksize = PAGE_SIZE;
+		sb->s_blocksize_bits = PAGE_SHIFT;
 
 		err = erofs_fscache_register_fs(sb);
 		if (err)
@@ -750,8 +751,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 		if (err)
 			return err;
 	} else {
-		if (!sb_set_blocksize(sb, EROFS_BLKSIZ)) {
-			erofs_err(sb, "failed to set erofs blksize");
+		if (!sb_set_blocksize(sb, PAGE_SIZE)) {
+			errorfc(fc, "failed to set initial blksize");
 			return -EINVAL;
 		}
 
@@ -764,12 +765,24 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (err)
 		return err;
 
-	if (test_opt(&sbi->opt, DAX_ALWAYS)) {
-		BUILD_BUG_ON(EROFS_BLKSIZ != PAGE_SIZE);
+	if (sb->s_blocksize_bits != sbi->blkszbits) {
+		if (erofs_is_fscache_mode(sb)) {
+			errorfc(fc, "unsupported blksize for fscache mode");
+			return -EINVAL;
+		}
+		if (!sb_set_blocksize(sb, 1 << sbi->blkszbits)) {
+			errorfc(fc, "failed to set erofs blksize");
+			return -EINVAL;
+		}
+	}
 
+	if (test_opt(&sbi->opt, DAX_ALWAYS)) {
 		if (!sbi->dax_dev) {
 			errorfc(fc, "DAX unsupported by block device. Turning off DAX.");
 			clear_opt(&sbi->opt, DAX_ALWAYS);
+		} else if (sbi->blkszbits != PAGE_SHIFT) {
+			errorfc(fc, "unsupported blocksize for DAX");
+			clear_opt(&sbi->opt, DAX_ALWAYS);
 		}
 	}
 

From 8b465fecc35a434e61728a6184d188c6daa37a5d Mon Sep 17 00:00:00 2001
From: Jia Zhu <zhujia.zj@bytedance.com>
Date: Thu, 2 Mar 2023 15:17:51 +0800
Subject: [PATCH 41/67] erofs: support flattened block device for multi-blob
 images

In order to support mounting multi-blobs container image as a single
block device, add flattened block device feature for EROFS.

In this mode, all meta/data contents will be mapped into one block
space. User could compose a block device(by nbd/ublk/virtio-blk/
vhost-user-blk) from multiple sources and mount the block device by
EROFS directly. It can reduce the number of block devices used, and
it's also benefits in both VM file passthrough and distributed storage
scenarios.

You can test this using the method mentioned by:
https://github.com/dragonflyoss/image-service/pull/1139
1. Compose a (nbd)block device from multi-blobs.
2. Mount EROFS on mntdir/.
3. Compare the md5sum between source dir and mntdir/.

Later, we could also use it to refer original tar blobs.

Signed-off-by: Jia Zhu <zhujia.zj@bytedance.com>
Signed-off-by: Xin Yin <yinxin.x@bytedance.com>
Reviewed-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Acked-by: Chao Yu <chao@kernel.org>
Tested-by: Jiang Liu <gerry@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230302071751.48425-1-zhujia.zj@bytedance.com
[ Gao Xiang: refine commit message and use erofs_pos(). ]
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/data.c     | 8 ++++++--
 fs/erofs/internal.h | 1 +
 fs/erofs/super.c    | 5 ++++-
 3 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 1c931e32d28e..03c6ffdfcbfb 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -200,7 +200,6 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 	struct erofs_device_info *dif;
 	int id;
 
-	/* primary device by default */
 	map->m_bdev = sb->s_bdev;
 	map->m_daxdev = EROFS_SB(sb)->dax_dev;
 	map->m_dax_part_off = EROFS_SB(sb)->dax_part_off;
@@ -213,12 +212,17 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 			up_read(&devs->rwsem);
 			return -ENODEV;
 		}
+		if (devs->flatdev) {
+			map->m_pa += erofs_pos(sb, dif->mapped_blkaddr);
+			up_read(&devs->rwsem);
+			return 0;
+		}
 		map->m_bdev = dif->bdev;
 		map->m_daxdev = dif->dax_dev;
 		map->m_dax_part_off = dif->dax_part_off;
 		map->m_fscache = dif->fscache;
 		up_read(&devs->rwsem);
-	} else if (devs->extra_devices) {
+	} else if (devs->extra_devices && !devs->flatdev) {
 		down_read(&devs->rwsem);
 		idr_for_each_entry(&devs->tree, dif, id) {
 			erofs_off_t startoff, length;
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 9eff0c0ad2d7..e30a4fd43ccb 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -81,6 +81,7 @@ struct erofs_dev_context {
 	struct rw_semaphore rwsem;
 
 	unsigned int extra_devices;
+	bool flatdev;
 };
 
 struct erofs_fs_context {
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index dbffcdd696df..9e56a6fb2267 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -252,7 +252,7 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 		if (IS_ERR(fscache))
 			return PTR_ERR(fscache);
 		dif->fscache = fscache;
-	} else {
+	} else if (!sbi->devs->flatdev) {
 		bdev = blkdev_get_by_path(dif->path, FMODE_READ | FMODE_EXCL,
 					  sb->s_type);
 		if (IS_ERR(bdev))
@@ -294,6 +294,9 @@ static int erofs_scan_devices(struct super_block *sb,
 	if (!ondisk_extradevs)
 		return 0;
 
+	if (!sbi->devs->extra_devices && !erofs_is_fscache_mode(sb))
+		sbi->devs->flatdev = true;
+
 	sbi->device_id_mask = roundup_pow_of_two(ondisk_extradevs + 1) - 1;
 	pos = le16_to_cpu(dsb->devt_slotoff) * EROFS_DEVT_SLOT_SIZE;
 	down_read(&sbi->devs->rwsem);

From 1c7f49a76773bcf95d3c840cff6cd449114ddf56 Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Fri, 31 Mar 2023 14:31:49 +0800
Subject: [PATCH 42/67] erofs: tidy up EROFS on-disk naming

 - Get rid of all "vle" (variable-length extents) expressions
   since they only expand overall name lengths unnecessarily;
 - Rename COMPRESSION_LEGACY to COMPRESSED_FULL;
 - Move on-disk directory definitions ahead of compression;
 - Drop unused extended attribute definitions;
 - Move inode ondisk union `i_u` out as `union erofs_inode_i_u`.

No actual logical change.

Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Yue Hu <huyue2@coolpad.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20230331063149.25611-1-hsiangkao@linux.alibaba.com
---
 fs/erofs/erofs_fs.h | 143 +++++++++++++++++++-------------------------
 fs/erofs/zmap.c     | 116 ++++++++++++++++++-----------------
 2 files changed, 118 insertions(+), 141 deletions(-)

diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index 44876a97cabd..1a4a614895c6 100644
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -82,32 +82,27 @@ struct erofs_super_block {
 };
 
 /*
- * erofs inode datalayout (i_format in on-disk inode):
+ * EROFS inode datalayout (i_format in on-disk inode):
  * 0 - uncompressed flat inode without tail-packing inline data:
- * inode, [xattrs], ... | ... | no-holed data
  * 1 - compressed inode with non-compact indexes:
- * inode, [xattrs], [map_header], extents ... | ...
  * 2 - uncompressed flat inode with tail-packing inline data:
- * inode, [xattrs], tailpacking data, ... | ... | no-holed data
  * 3 - compressed inode with compact indexes:
- * inode, [xattrs], map_header, extents ... | ...
  * 4 - chunk-based inode with (optional) multi-device support:
- * inode, [xattrs], chunk indexes ... | ...
  * 5~7 - reserved
  */
 enum {
 	EROFS_INODE_FLAT_PLAIN			= 0,
-	EROFS_INODE_FLAT_COMPRESSION_LEGACY	= 1,
+	EROFS_INODE_COMPRESSED_FULL		= 1,
 	EROFS_INODE_FLAT_INLINE			= 2,
-	EROFS_INODE_FLAT_COMPRESSION		= 3,
+	EROFS_INODE_COMPRESSED_COMPACT		= 3,
 	EROFS_INODE_CHUNK_BASED			= 4,
 	EROFS_INODE_DATALAYOUT_MAX
 };
 
 static inline bool erofs_inode_is_data_compressed(unsigned int datamode)
 {
-	return datamode == EROFS_INODE_FLAT_COMPRESSION ||
-		datamode == EROFS_INODE_FLAT_COMPRESSION_LEGACY;
+	return datamode == EROFS_INODE_COMPRESSED_COMPACT ||
+		datamode == EROFS_INODE_COMPRESSED_FULL;
 }
 
 /* bit definitions of inode i_format */
@@ -128,11 +123,30 @@ static inline bool erofs_inode_is_data_compressed(unsigned int datamode)
 #define EROFS_CHUNK_FORMAT_ALL	\
 	(EROFS_CHUNK_FORMAT_BLKBITS_MASK | EROFS_CHUNK_FORMAT_INDEXES)
 
+/* 32-byte on-disk inode */
+#define EROFS_INODE_LAYOUT_COMPACT	0
+/* 64-byte on-disk inode */
+#define EROFS_INODE_LAYOUT_EXTENDED	1
+
 struct erofs_inode_chunk_info {
 	__le16 format;		/* chunk blkbits, etc. */
 	__le16 reserved;
 };
 
+union erofs_inode_i_u {
+	/* total compressed blocks for compressed inodes */
+	__le32 compressed_blocks;
+
+	/* block address for uncompressed flat inodes */
+	__le32 raw_blkaddr;
+
+	/* for device files, used to indicate old/new device # */
+	__le32 rdev;
+
+	/* for chunk-based files, it contains the summary info */
+	struct erofs_inode_chunk_info c;
+};
+
 /* 32-byte reduced form of an ondisk inode */
 struct erofs_inode_compact {
 	__le16 i_format;	/* inode format hints */
@@ -143,29 +157,14 @@ struct erofs_inode_compact {
 	__le16 i_nlink;
 	__le32 i_size;
 	__le32 i_reserved;
-	union {
-		/* total compressed blocks for compressed inodes */
-		__le32 compressed_blocks;
-		/* block address for uncompressed flat inodes */
-		__le32 raw_blkaddr;
+	union erofs_inode_i_u i_u;
 
-		/* for device files, used to indicate old/new device # */
-		__le32 rdev;
-
-		/* for chunk-based files, it contains the summary info */
-		struct erofs_inode_chunk_info c;
-	} i_u;
-	__le32 i_ino;           /* only used for 32-bit stat compatibility */
+	__le32 i_ino;		/* only used for 32-bit stat compatibility */
 	__le16 i_uid;
 	__le16 i_gid;
 	__le32 i_reserved2;
 };
 
-/* 32-byte on-disk inode */
-#define EROFS_INODE_LAYOUT_COMPACT	0
-/* 64-byte on-disk inode */
-#define EROFS_INODE_LAYOUT_EXTENDED	1
-
 /* 64-byte complete form of an ondisk inode */
 struct erofs_inode_extended {
 	__le16 i_format;	/* inode format hints */
@@ -175,22 +174,9 @@ struct erofs_inode_extended {
 	__le16 i_mode;
 	__le16 i_reserved;
 	__le64 i_size;
-	union {
-		/* total compressed blocks for compressed inodes */
-		__le32 compressed_blocks;
-		/* block address for uncompressed flat inodes */
-		__le32 raw_blkaddr;
-
-		/* for device files, used to indicate old/new device # */
-		__le32 rdev;
-
-		/* for chunk-based files, it contains the summary info */
-		struct erofs_inode_chunk_info c;
-	} i_u;
-
-	/* only used for 32-bit stat compatibility */
-	__le32 i_ino;
+	union erofs_inode_i_u i_u;
 
+	__le32 i_ino;		/* only used for 32-bit stat compatibility */
 	__le32 i_uid;
 	__le32 i_gid;
 	__le64 i_mtime;
@@ -199,10 +185,6 @@ struct erofs_inode_extended {
 	__u8   i_reserved2[16];
 };
 
-#define EROFS_MAX_SHARED_XATTRS         (128)
-/* h_shared_count between 129 ... 255 are special # */
-#define EROFS_SHARED_XATTR_EXTENT       (255)
-
 /*
  * inline xattrs (n == i_xattr_icount):
  * erofs_xattr_ibody_header(1) + (n - 1) * 4 bytes
@@ -268,6 +250,22 @@ struct erofs_inode_chunk_index {
 	__le32 blkaddr;		/* start block address of this inode chunk */
 };
 
+/* dirent sorts in alphabet order, thus we can do binary search */
+struct erofs_dirent {
+	__le64 nid;     /* node number */
+	__le16 nameoff; /* start offset of file name */
+	__u8 file_type; /* file type */
+	__u8 reserved;  /* reserved */
+} __packed;
+
+/*
+ * EROFS file types should match generic FT_* types and
+ * it seems no need to add BUILD_BUG_ONs since potential
+ * unmatchness will break other fses as well...
+ */
+
+#define EROFS_NAME_LEN      255
+
 /* maximum supported size of a physical compression cluster */
 #define Z_EROFS_PCLUSTER_MAX_SIZE	(1024 * 1024)
 
@@ -337,10 +335,8 @@ struct z_erofs_map_header {
 	__u8	h_clusterbits;
 };
 
-#define Z_EROFS_VLE_LEGACY_HEADER_PADDING       8
-
 /*
- * Fixed-sized output compression on-disk logical cluster type:
+ * On-disk logical cluster type:
  *    0   - literal (uncompressed) lcluster
  *    1,3 - compressed lcluster (for HEAD lclusters)
  *    2   - compressed lcluster (for NONHEAD lclusters)
@@ -364,27 +360,27 @@ struct z_erofs_map_header {
  *        di_u.delta[1] = distance to the next HEAD lcluster
  */
 enum {
-	Z_EROFS_VLE_CLUSTER_TYPE_PLAIN		= 0,
-	Z_EROFS_VLE_CLUSTER_TYPE_HEAD1		= 1,
-	Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD	= 2,
-	Z_EROFS_VLE_CLUSTER_TYPE_HEAD2		= 3,
-	Z_EROFS_VLE_CLUSTER_TYPE_MAX
+	Z_EROFS_LCLUSTER_TYPE_PLAIN	= 0,
+	Z_EROFS_LCLUSTER_TYPE_HEAD1	= 1,
+	Z_EROFS_LCLUSTER_TYPE_NONHEAD	= 2,
+	Z_EROFS_LCLUSTER_TYPE_HEAD2	= 3,
+	Z_EROFS_LCLUSTER_TYPE_MAX
 };
 
-#define Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS        2
-#define Z_EROFS_VLE_DI_CLUSTER_TYPE_BIT         0
+#define Z_EROFS_LI_LCLUSTER_TYPE_BITS        2
+#define Z_EROFS_LI_LCLUSTER_TYPE_BIT         0
 
 /* (noncompact only, HEAD) This pcluster refers to partial decompressed data */
-#define Z_EROFS_VLE_DI_PARTIAL_REF		(1 << 15)
+#define Z_EROFS_LI_PARTIAL_REF		(1 << 15)
 
 /*
  * D0_CBLKCNT will be marked _only_ at the 1st non-head lcluster to store the
  * compressed block count of a compressed extent (in logical clusters, aka.
  * block count of a pcluster).
  */
-#define Z_EROFS_VLE_DI_D0_CBLKCNT		(1 << 11)
+#define Z_EROFS_LI_D0_CBLKCNT		(1 << 11)
 
-struct z_erofs_vle_decompressed_index {
+struct z_erofs_lcluster_index {
 	__le16 di_advise;
 	/* where to decompress in the head lcluster */
 	__le16 di_clusterofs;
@@ -401,25 +397,8 @@ struct z_erofs_vle_decompressed_index {
 	} di_u;
 };
 
-#define Z_EROFS_VLE_LEGACY_INDEX_ALIGN(size) \
-	(round_up(size, sizeof(struct z_erofs_vle_decompressed_index)) + \
-	 sizeof(struct z_erofs_map_header) + Z_EROFS_VLE_LEGACY_HEADER_PADDING)
-
-/* dirent sorts in alphabet order, thus we can do binary search */
-struct erofs_dirent {
-	__le64 nid;     /* node number */
-	__le16 nameoff; /* start offset of file name */
-	__u8 file_type; /* file type */
-	__u8 reserved;  /* reserved */
-} __packed;
-
-/*
- * EROFS file types should match generic FT_* types and
- * it seems no need to add BUILD_BUG_ONs since potential
- * unmatchness will break other fses as well...
- */
-
-#define EROFS_NAME_LEN      255
+#define Z_EROFS_FULL_INDEX_ALIGN(end)	\
+	(ALIGN(end, 8) + sizeof(struct z_erofs_map_header) + 8)
 
 /* check the EROFS on-disk layout strictly at compile time */
 static inline void erofs_check_ondisk_layout_definitions(void)
@@ -436,15 +415,15 @@ static inline void erofs_check_ondisk_layout_definitions(void)
 	BUILD_BUG_ON(sizeof(struct erofs_inode_chunk_info) != 4);
 	BUILD_BUG_ON(sizeof(struct erofs_inode_chunk_index) != 8);
 	BUILD_BUG_ON(sizeof(struct z_erofs_map_header) != 8);
-	BUILD_BUG_ON(sizeof(struct z_erofs_vle_decompressed_index) != 8);
+	BUILD_BUG_ON(sizeof(struct z_erofs_lcluster_index) != 8);
 	BUILD_BUG_ON(sizeof(struct erofs_dirent) != 12);
 	/* keep in sync between 2 index structures for better extendibility */
 	BUILD_BUG_ON(sizeof(struct erofs_inode_chunk_index) !=
-		     sizeof(struct z_erofs_vle_decompressed_index));
+		     sizeof(struct z_erofs_lcluster_index));
 	BUILD_BUG_ON(sizeof(struct erofs_deviceslot) != 128);
 
-	BUILD_BUG_ON(BIT(Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS) <
-		     Z_EROFS_VLE_CLUSTER_TYPE_MAX - 1);
+	BUILD_BUG_ON(BIT(Z_EROFS_LI_LCLUSTER_TYPE_BITS) <
+		     Z_EROFS_LCLUSTER_TYPE_MAX - 1);
 	/* exclude old compiler versions like gcc 7.5.0 */
 	BUILD_BUG_ON(__builtin_constant_p(fmh) ?
 		     fmh != cpu_to_le64(1ULL << 63) : 0);
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index ecbcae9b5494..cbd3f72c83e9 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -14,7 +14,7 @@ int z_erofs_fill_inode(struct inode *inode)
 
 	if (!erofs_sb_has_big_pcluster(sbi) &&
 	    !erofs_sb_has_ztailpacking(sbi) && !erofs_sb_has_fragments(sbi) &&
-	    vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY) {
+	    vi->datalayout == EROFS_INODE_COMPRESSED_FULL) {
 		vi->z_advise = 0;
 		vi->z_algorithmtype[0] = 0;
 		vi->z_algorithmtype[1] = 0;
@@ -45,11 +45,10 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m,
 {
 	struct inode *const inode = m->inode;
 	struct erofs_inode *const vi = EROFS_I(inode);
-	const erofs_off_t pos =
-		Z_EROFS_VLE_LEGACY_INDEX_ALIGN(erofs_iloc(inode) +
-				vi->inode_isize + vi->xattr_isize) +
-		lcn * sizeof(struct z_erofs_vle_decompressed_index);
-	struct z_erofs_vle_decompressed_index *di;
+	const erofs_off_t pos = Z_EROFS_FULL_INDEX_ALIGN(erofs_iloc(inode) +
+			vi->inode_isize + vi->xattr_isize) +
+			lcn * sizeof(struct z_erofs_lcluster_index);
+	struct z_erofs_lcluster_index *di;
 	unsigned int advise, type;
 
 	m->kaddr = erofs_read_metabuf(&m->map->buf, inode->i_sb,
@@ -57,33 +56,33 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m,
 	if (IS_ERR(m->kaddr))
 		return PTR_ERR(m->kaddr);
 
-	m->nextpackoff = pos + sizeof(struct z_erofs_vle_decompressed_index);
+	m->nextpackoff = pos + sizeof(struct z_erofs_lcluster_index);
 	m->lcn = lcn;
 	di = m->kaddr + erofs_blkoff(inode->i_sb, pos);
 
 	advise = le16_to_cpu(di->di_advise);
-	type = (advise >> Z_EROFS_VLE_DI_CLUSTER_TYPE_BIT) &
-		((1 << Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS) - 1);
+	type = (advise >> Z_EROFS_LI_LCLUSTER_TYPE_BIT) &
+		((1 << Z_EROFS_LI_LCLUSTER_TYPE_BITS) - 1);
 	switch (type) {
-	case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
+	case Z_EROFS_LCLUSTER_TYPE_NONHEAD:
 		m->clusterofs = 1 << vi->z_logical_clusterbits;
 		m->delta[0] = le16_to_cpu(di->di_u.delta[0]);
-		if (m->delta[0] & Z_EROFS_VLE_DI_D0_CBLKCNT) {
+		if (m->delta[0] & Z_EROFS_LI_D0_CBLKCNT) {
 			if (!(vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 |
 					Z_EROFS_ADVISE_BIG_PCLUSTER_2))) {
 				DBG_BUGON(1);
 				return -EFSCORRUPTED;
 			}
 			m->compressedblks = m->delta[0] &
-				~Z_EROFS_VLE_DI_D0_CBLKCNT;
+				~Z_EROFS_LI_D0_CBLKCNT;
 			m->delta[0] = 1;
 		}
 		m->delta[1] = le16_to_cpu(di->di_u.delta[1]);
 		break;
-	case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
-	case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1:
-	case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2:
-		if (advise & Z_EROFS_VLE_DI_PARTIAL_REF)
+	case Z_EROFS_LCLUSTER_TYPE_PLAIN:
+	case Z_EROFS_LCLUSTER_TYPE_HEAD1:
+	case Z_EROFS_LCLUSTER_TYPE_HEAD2:
+		if (advise & Z_EROFS_LI_PARTIAL_REF)
 			m->partialref = true;
 		m->clusterofs = le16_to_cpu(di->di_clusterofs);
 		m->pblk = le32_to_cpu(di->di_u.blkaddr);
@@ -121,13 +120,13 @@ static int get_compacted_la_distance(unsigned int lclusterbits,
 		lo = decode_compactedbits(lclusterbits, lomask,
 					  in, encodebits * i, &type);
 
-		if (type != Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
+		if (type != Z_EROFS_LCLUSTER_TYPE_NONHEAD)
 			return d1;
 		++d1;
 	} while (++i < vcnt);
 
-	/* vcnt - 1 (Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) item */
-	if (!(lo & Z_EROFS_VLE_DI_D0_CBLKCNT))
+	/* vcnt - 1 (Z_EROFS_LCLUSTER_TYPE_NONHEAD) item */
+	if (!(lo & Z_EROFS_LI_D0_CBLKCNT))
 		d1 += lo - 1;
 	return d1;
 }
@@ -165,19 +164,19 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 	lo = decode_compactedbits(lclusterbits, lomask,
 				  in, encodebits * i, &type);
 	m->type = type;
-	if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) {
+	if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) {
 		m->clusterofs = 1 << lclusterbits;
 
 		/* figure out lookahead_distance: delta[1] if needed */
 		if (lookahead)
 			m->delta[1] = get_compacted_la_distance(lclusterbits,
 						encodebits, vcnt, in, i);
-		if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) {
+		if (lo & Z_EROFS_LI_D0_CBLKCNT) {
 			if (!big_pcluster) {
 				DBG_BUGON(1);
 				return -EFSCORRUPTED;
 			}
-			m->compressedblks = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT;
+			m->compressedblks = lo & ~Z_EROFS_LI_D0_CBLKCNT;
 			m->delta[0] = 1;
 			return 0;
 		} else if (i + 1 != (int)vcnt) {
@@ -191,9 +190,9 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 		 */
 		lo = decode_compactedbits(lclusterbits, lomask,
 					  in, encodebits * (i - 1), &type);
-		if (type != Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
+		if (type != Z_EROFS_LCLUSTER_TYPE_NONHEAD)
 			lo = 0;
-		else if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT)
+		else if (lo & Z_EROFS_LI_D0_CBLKCNT)
 			lo = 1;
 		m->delta[0] = lo + 1;
 		return 0;
@@ -207,7 +206,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 			--i;
 			lo = decode_compactedbits(lclusterbits, lomask,
 						  in, encodebits * i, &type);
-			if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
+			if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD)
 				i -= lo;
 
 			if (i >= 0)
@@ -219,10 +218,10 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 			--i;
 			lo = decode_compactedbits(lclusterbits, lomask,
 						  in, encodebits * i, &type);
-			if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) {
-				if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) {
+			if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) {
+				if (lo & Z_EROFS_LI_D0_CBLKCNT) {
 					--i;
-					nblk += lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT;
+					nblk += lo & ~Z_EROFS_LI_D0_CBLKCNT;
 					continue;
 				}
 				/* bigpcluster shouldn't have plain d0 == 1 */
@@ -301,10 +300,10 @@ static int z_erofs_load_cluster_from_disk(struct z_erofs_maprecorder *m,
 {
 	const unsigned int datamode = EROFS_I(m->inode)->datalayout;
 
-	if (datamode == EROFS_INODE_FLAT_COMPRESSION_LEGACY)
+	if (datamode == EROFS_INODE_COMPRESSED_FULL)
 		return legacy_load_cluster_from_disk(m, lcn);
 
-	if (datamode == EROFS_INODE_FLAT_COMPRESSION)
+	if (datamode == EROFS_INODE_COMPRESSED_COMPACT)
 		return compacted_load_cluster_from_disk(m, lcn, lookahead);
 
 	return -EINVAL;
@@ -326,7 +325,7 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m,
 			return err;
 
 		switch (m->type) {
-		case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
+		case Z_EROFS_LCLUSTER_TYPE_NONHEAD:
 			if (!m->delta[0]) {
 				erofs_err(m->inode->i_sb,
 					  "invalid lookback distance 0 @ nid %llu",
@@ -336,9 +335,9 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m,
 			}
 			lookback_distance = m->delta[0];
 			continue;
-		case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
-		case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1:
-		case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2:
+		case Z_EROFS_LCLUSTER_TYPE_PLAIN:
+		case Z_EROFS_LCLUSTER_TYPE_HEAD1:
+		case Z_EROFS_LCLUSTER_TYPE_HEAD2:
 			m->headtype = m->type;
 			m->map->m_la = (lcn << lclusterbits) | m->clusterofs;
 			return 0;
@@ -367,15 +366,15 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
 	unsigned long lcn;
 	int err;
 
-	DBG_BUGON(m->type != Z_EROFS_VLE_CLUSTER_TYPE_PLAIN &&
-		  m->type != Z_EROFS_VLE_CLUSTER_TYPE_HEAD1 &&
-		  m->type != Z_EROFS_VLE_CLUSTER_TYPE_HEAD2);
+	DBG_BUGON(m->type != Z_EROFS_LCLUSTER_TYPE_PLAIN &&
+		  m->type != Z_EROFS_LCLUSTER_TYPE_HEAD1 &&
+		  m->type != Z_EROFS_LCLUSTER_TYPE_HEAD2);
 	DBG_BUGON(m->type != m->headtype);
 
-	if (m->headtype == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN ||
-	    ((m->headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD1) &&
+	if (m->headtype == Z_EROFS_LCLUSTER_TYPE_PLAIN ||
+	    ((m->headtype == Z_EROFS_LCLUSTER_TYPE_HEAD1) &&
 	     !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1)) ||
-	    ((m->headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) &&
+	    ((m->headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) &&
 	     !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2))) {
 		map->m_plen = 1ULL << lclusterbits;
 		return 0;
@@ -397,19 +396,19 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
 	 * BUG_ON in the debugging mode only for developers to notice that.
 	 */
 	DBG_BUGON(lcn == initial_lcn &&
-		  m->type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD);
+		  m->type == Z_EROFS_LCLUSTER_TYPE_NONHEAD);
 
 	switch (m->type) {
-	case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
-	case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1:
-	case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2:
+	case Z_EROFS_LCLUSTER_TYPE_PLAIN:
+	case Z_EROFS_LCLUSTER_TYPE_HEAD1:
+	case Z_EROFS_LCLUSTER_TYPE_HEAD2:
 		/*
 		 * if the 1st NONHEAD lcluster is actually PLAIN or HEAD type
 		 * rather than CBLKCNT, it's a 1 lcluster-sized pcluster.
 		 */
 		m->compressedblks = 1 << (lclusterbits - sb->s_blocksize_bits);
 		break;
-	case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
+	case Z_EROFS_LCLUSTER_TYPE_NONHEAD:
 		if (m->delta[0] != 1)
 			goto err_bonus_cblkcnt;
 		if (m->compressedblks)
@@ -453,12 +452,12 @@ static int z_erofs_get_extent_decompressedlen(struct z_erofs_maprecorder *m)
 		if (err)
 			return err;
 
-		if (m->type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) {
+		if (m->type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) {
 			DBG_BUGON(!m->delta[1] &&
 				  m->clusterofs != 1 << lclusterbits);
-		} else if (m->type == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN ||
-			   m->type == Z_EROFS_VLE_CLUSTER_TYPE_HEAD1 ||
-			   m->type == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) {
+		} else if (m->type == Z_EROFS_LCLUSTER_TYPE_PLAIN ||
+			   m->type == Z_EROFS_LCLUSTER_TYPE_HEAD1 ||
+			   m->type == Z_EROFS_LCLUSTER_TYPE_HEAD2) {
 			/* go on until the next HEAD lcluster */
 			if (lcn != headlcn)
 				break;
@@ -477,8 +476,7 @@ static int z_erofs_get_extent_decompressedlen(struct z_erofs_maprecorder *m)
 }
 
 static int z_erofs_do_map_blocks(struct inode *inode,
-				 struct erofs_map_blocks *map,
-				 int flags)
+				 struct erofs_map_blocks *map, int flags)
 {
 	struct erofs_inode *const vi = EROFS_I(inode);
 	bool ztailpacking = vi->z_advise & Z_EROFS_ADVISE_INLINE_PCLUSTER;
@@ -508,9 +506,9 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 	end = (m.lcn + 1ULL) << lclusterbits;
 
 	switch (m.type) {
-	case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
-	case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1:
-	case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2:
+	case Z_EROFS_LCLUSTER_TYPE_PLAIN:
+	case Z_EROFS_LCLUSTER_TYPE_HEAD1:
+	case Z_EROFS_LCLUSTER_TYPE_HEAD2:
 		if (endoff >= m.clusterofs) {
 			m.headtype = m.type;
 			map->m_la = (m.lcn << lclusterbits) | m.clusterofs;
@@ -535,7 +533,7 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 		map->m_flags |= EROFS_MAP_FULL_MAPPED;
 		m.delta[0] = 1;
 		fallthrough;
-	case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
+	case Z_EROFS_LCLUSTER_TYPE_NONHEAD:
 		/* get the corresponding first chunk */
 		err = z_erofs_extent_lookback(&m, m.delta[0]);
 		if (err)
@@ -556,7 +554,7 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 		vi->z_tailextent_headlcn = m.lcn;
 		/* for non-compact indexes, fragmentoff is 64 bits */
 		if (fragment &&
-		    vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY)
+		    vi->datalayout == EROFS_INODE_COMPRESSED_FULL)
 			vi->z_fragmentoff |= (u64)m.pblk << 32;
 	}
 	if (ztailpacking && m.lcn == vi->z_tailextent_headlcn) {
@@ -572,7 +570,7 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 			goto unmap_out;
 	}
 
-	if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN) {
+	if (m.headtype == Z_EROFS_LCLUSTER_TYPE_PLAIN) {
 		if (map->m_llen > map->m_plen) {
 			DBG_BUGON(1);
 			err = -EFSCORRUPTED;
@@ -584,7 +582,7 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 		else
 			map->m_algorithmformat =
 				Z_EROFS_COMPRESSION_SHIFTED;
-	} else if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) {
+	} else if (m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) {
 		map->m_algorithmformat = vi->z_algorithmtype[1];
 	} else {
 		map->m_algorithmformat = vi->z_algorithmtype[0];
@@ -673,7 +671,7 @@ static int z_erofs_fill_inode_lazy(struct inode *inode)
 		err = -EFSCORRUPTED;
 		goto out_put_metabuf;
 	}
-	if (vi->datalayout == EROFS_INODE_FLAT_COMPRESSION &&
+	if (vi->datalayout == EROFS_INODE_COMPRESSED_COMPACT &&
 	    !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1) ^
 	    !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2)) {
 		erofs_err(sb, "big pcluster head1/2 of compact indexes should be consistent for nid %llu",

From 399f36d8c6e0c8292d2ff3db4fdcd33263b415ec Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Thu, 30 Mar 2023 16:29:03 +0800
Subject: [PATCH 43/67] erofs: move several xattr helpers into xattr.c

Move xattrblock_addr() and xattrblock_offset() helpers into xattr.c,
as they are not used outside of xattr.c.

inlinexattr_header_size() has only one caller, and thus make it inlined
into the caller directly.

Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230330082910.125374-2-jefflexu@linux.alibaba.com
Reviewed-by: Yue Hu <huyue2@coolpad.com>
Acked-by: Chao Yu <chao@kernel.org>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/xattr.c | 48 +++++++++++++++++++++++++++++-------------------
 fs/erofs/xattr.h | 23 -----------------------
 2 files changed, 29 insertions(+), 42 deletions(-)

diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c
index 459caa3cd65d..9ccd57581bc7 100644
--- a/fs/erofs/xattr.c
+++ b/fs/erofs/xattr.c
@@ -7,6 +7,19 @@
 #include <linux/security.h>
 #include "xattr.h"
 
+static inline erofs_blk_t erofs_xattr_blkaddr(struct super_block *sb,
+					      unsigned int xattr_id)
+{
+	return EROFS_SB(sb)->xattr_blkaddr +
+	       erofs_blknr(sb, xattr_id * sizeof(__u32));
+}
+
+static inline unsigned int erofs_xattr_blkoff(struct super_block *sb,
+					      unsigned int xattr_id)
+{
+	return erofs_blkoff(sb, xattr_id * sizeof(__u32));
+}
+
 struct xattr_iter {
 	struct super_block *sb;
 	struct erofs_buf buf;
@@ -157,7 +170,8 @@ static int inline_xattr_iter_begin(struct xattr_iter *it,
 	struct erofs_inode *const vi = EROFS_I(inode);
 	unsigned int xattr_header_sz, inline_xattr_ofs;
 
-	xattr_header_sz = inlinexattr_header_size(inode);
+	xattr_header_sz = sizeof(struct erofs_xattr_ibody_header) +
+			  sizeof(u32) * vi->xattr_shared_count;
 	if (xattr_header_sz >= vi->xattr_isize) {
 		DBG_BUGON(xattr_header_sz > vi->xattr_isize);
 		return -ENOATTR;
@@ -351,20 +365,18 @@ static int inline_getxattr(struct inode *inode, struct getxattr_iter *it)
 static int shared_getxattr(struct inode *inode, struct getxattr_iter *it)
 {
 	struct erofs_inode *const vi = EROFS_I(inode);
-	struct super_block *const sb = inode->i_sb;
-	unsigned int i;
+	struct super_block *const sb = it->it.sb;
+	unsigned int i, xsid;
 	int ret = -ENOATTR;
 
 	for (i = 0; i < vi->xattr_shared_count; ++i) {
-		erofs_blk_t blkaddr =
-			xattrblock_addr(sb, vi->xattr_shared_xattrs[i]);
-
-		it->it.ofs = xattrblock_offset(sb, vi->xattr_shared_xattrs[i]);
-		it->it.kaddr = erofs_read_metabuf(&it->it.buf, sb, blkaddr,
-						  EROFS_KMAP);
+		xsid = vi->xattr_shared_xattrs[i];
+		it->it.blkaddr = erofs_xattr_blkaddr(sb, xsid);
+		it->it.ofs = erofs_xattr_blkoff(sb, xsid);
+		it->it.kaddr = erofs_read_metabuf(&it->it.buf, sb,
+						  it->it.blkaddr, EROFS_KMAP);
 		if (IS_ERR(it->it.kaddr))
 			return PTR_ERR(it->it.kaddr);
-		it->it.blkaddr = blkaddr;
 
 		ret = xattr_foreach(&it->it, &find_xattr_handlers, NULL);
 		if (ret != -ENOATTR)
@@ -562,20 +574,18 @@ static int shared_listxattr(struct listxattr_iter *it)
 {
 	struct inode *const inode = d_inode(it->dentry);
 	struct erofs_inode *const vi = EROFS_I(inode);
-	struct super_block *const sb = inode->i_sb;
-	unsigned int i;
+	struct super_block *const sb = it->it.sb;
+	unsigned int i, xsid;
 	int ret = 0;
 
 	for (i = 0; i < vi->xattr_shared_count; ++i) {
-		erofs_blk_t blkaddr =
-			xattrblock_addr(sb, vi->xattr_shared_xattrs[i]);
-
-		it->it.ofs = xattrblock_offset(sb, vi->xattr_shared_xattrs[i]);
-		it->it.kaddr = erofs_read_metabuf(&it->it.buf, sb, blkaddr,
-						  EROFS_KMAP);
+		xsid = vi->xattr_shared_xattrs[i];
+		it->it.blkaddr = erofs_xattr_blkaddr(sb, xsid);
+		it->it.ofs = erofs_xattr_blkoff(sb, xsid);
+		it->it.kaddr = erofs_read_metabuf(&it->it.buf, sb,
+						  it->it.blkaddr, EROFS_KMAP);
 		if (IS_ERR(it->it.kaddr))
 			return PTR_ERR(it->it.kaddr);
-		it->it.blkaddr = blkaddr;
 
 		ret = xattr_foreach(&it->it, &list_xattr_handlers, NULL);
 		if (ret)
diff --git a/fs/erofs/xattr.h b/fs/erofs/xattr.h
index f7a21aaa9755..a65158cba14f 100644
--- a/fs/erofs/xattr.h
+++ b/fs/erofs/xattr.h
@@ -13,29 +13,6 @@
 /* Attribute not found */
 #define ENOATTR         ENODATA
 
-static inline unsigned int inlinexattr_header_size(struct inode *inode)
-{
-	return sizeof(struct erofs_xattr_ibody_header) +
-		sizeof(u32) * EROFS_I(inode)->xattr_shared_count;
-}
-
-static inline erofs_blk_t xattrblock_addr(struct super_block *sb,
-					  unsigned int xattr_id)
-{
-#ifdef CONFIG_EROFS_FS_XATTR
-	return EROFS_SB(sb)->xattr_blkaddr +
-		xattr_id * sizeof(__u32) / sb->s_blocksize;
-#else
-	return 0;
-#endif
-}
-
-static inline unsigned int xattrblock_offset(struct super_block *sb,
-					     unsigned int xattr_id)
-{
-	return (xattr_id * sizeof(__u32)) % sb->s_blocksize;
-}
-
 #ifdef CONFIG_EROFS_FS_XATTR
 extern const struct xattr_handler erofs_xattr_user_handler;
 extern const struct xattr_handler erofs_xattr_trusted_handler;

From 6020ffe76d1119241871300aad2ec7ef2cdc5e6c Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Thu, 30 Mar 2023 16:29:04 +0800
Subject: [PATCH 44/67] erofs: rename init_inode_xattrs with erofs_ prefix

Rename init_inode_xattrs() to erofs_init_inode_xattrs() without logic
change.

Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230330082910.125374-3-jefflexu@linux.alibaba.com
Reviewed-by: Yue Hu <huyue2@coolpad.com>
Acked-by: Chao Yu <chao@kernel.org>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/xattr.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c
index 9ccd57581bc7..dc36a0c0919c 100644
--- a/fs/erofs/xattr.c
+++ b/fs/erofs/xattr.c
@@ -29,7 +29,7 @@ struct xattr_iter {
 	unsigned int ofs;
 };
 
-static int init_inode_xattrs(struct inode *inode)
+static int erofs_init_inode_xattrs(struct inode *inode)
 {
 	struct erofs_inode *const vi = EROFS_I(inode);
 	struct xattr_iter it;
@@ -405,7 +405,7 @@ int erofs_getxattr(struct inode *inode, int index,
 	if (!name)
 		return -EINVAL;
 
-	ret = init_inode_xattrs(inode);
+	ret = erofs_init_inode_xattrs(inode);
 	if (ret)
 		return ret;
 
@@ -600,7 +600,7 @@ ssize_t erofs_listxattr(struct dentry *dentry,
 	int ret;
 	struct listxattr_iter it;
 
-	ret = init_inode_xattrs(d_inode(dentry));
+	ret = erofs_init_inode_xattrs(d_inode(dentry));
 	if (ret == -ENOATTR)
 		return 0;
 	if (ret)

From b05f30bcf71b8060d4a32b11353aaa2c5b0a8e3d Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Thu, 30 Mar 2023 16:29:05 +0800
Subject: [PATCH 45/67] erofs: simplify erofs_xattr_generic_get()

erofs_xattr_generic_get() won't be called from xattr handlers other than
user/trusted/security xattr handler, and thus there's no need of extra
checking.

Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230330082910.125374-4-jefflexu@linux.alibaba.com
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Yue Hu <huyue2@coolpad.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/xattr.c | 17 +++--------------
 1 file changed, 3 insertions(+), 14 deletions(-)

diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c
index dc36a0c0919c..d76b74ece2e5 100644
--- a/fs/erofs/xattr.c
+++ b/fs/erofs/xattr.c
@@ -432,20 +432,9 @@ static int erofs_xattr_generic_get(const struct xattr_handler *handler,
 				   struct dentry *unused, struct inode *inode,
 				   const char *name, void *buffer, size_t size)
 {
-	struct erofs_sb_info *const sbi = EROFS_I_SB(inode);
-
-	switch (handler->flags) {
-	case EROFS_XATTR_INDEX_USER:
-		if (!test_opt(&sbi->opt, XATTR_USER))
-			return -EOPNOTSUPP;
-		break;
-	case EROFS_XATTR_INDEX_TRUSTED:
-		break;
-	case EROFS_XATTR_INDEX_SECURITY:
-		break;
-	default:
-		return -EINVAL;
-	}
+	if (handler->flags == EROFS_XATTR_INDEX_USER &&
+	    !test_opt(&EROFS_I_SB(inode)->opt, XATTR_USER))
+		return -EOPNOTSUPP;
 
 	return erofs_getxattr(inode, handler->flags, name, buffer, size);
 }

From 12c2987e896bd1c433150a64f5bae9993c29d551 Mon Sep 17 00:00:00 2001
From: Yue Hu <huyue2@coolpad.com>
Date: Mon, 27 Feb 2023 16:44:57 +0800
Subject: [PATCH 46/67] erofs: don't warn ztailpacking feature anymore

The ztailpacking feature has been merged for a year, it has been mostly
stable now.

Signed-off-by: Yue Hu <huyue2@coolpad.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20230227084457.3510-1-zbestahu@gmail.com
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/super.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 9e56a6fb2267..6be232a97ec6 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -425,8 +425,6 @@ static int erofs_read_superblock(struct super_block *sb)
 	/* handle multiple devices */
 	ret = erofs_scan_devices(sb, dsb);
 
-	if (erofs_sb_has_ztailpacking(sbi))
-		erofs_info(sb, "EXPERIMENTAL compressed inline data feature in use. Use at your own risk!");
 	if (erofs_is_fscache_mode(sb))
 		erofs_info(sb, "EXPERIMENTAL fscache-based on-demand read feature in use. Use at your own risk!");
 	if (erofs_sb_has_fragments(sbi))

From cc4efd3dd2ac9f89143e5d881609747ecff04164 Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Tue, 11 Apr 2023 01:37:14 +0800
Subject: [PATCH 47/67] erofs: stop parsing non-compact HEAD index if
 clusterofs is invalid

Syzbot generated a crafted image [1] with a non-compact HEAD index of
clusterofs 33024 while valid numbers should be 0 ~ lclustersize-1,
which causes the following unexpected behavior as below:

 BUG: unable to handle page fault for address: fffff52101a3fff9
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 23ffed067 P4D 23ffed067 PUD 0
 Oops: 0000 [#1] PREEMPT SMP KASAN
 CPU: 1 PID: 4398 Comm: kworker/u5:1 Not tainted 6.3.0-rc6-syzkaller-g09a9639e56c0 #0
 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/30/2023
 Workqueue: erofs_worker z_erofs_decompressqueue_work
 RIP: 0010:z_erofs_decompress_queue+0xb7e/0x2b40
 ...
 Call Trace:
  <TASK>
  z_erofs_decompressqueue_work+0x99/0xe0
  process_one_work+0x8f6/0x1170
  worker_thread+0xa63/0x1210
  kthread+0x270/0x300
  ret_from_fork+0x1f/0x30

Note that normal images or images using compact indexes are not
impacted.  Let's fix this now.

[1] https://lore.kernel.org/r/000000000000ec75b005ee97fbaa@google.com

Reported-and-tested-by: syzbot+aafb3f37cfeb6534c4ac@syzkaller.appspotmail.com
Fixes: 02827e1796b3 ("staging: erofs: add erofs_map_blocks_iter")
Fixes: 152a333a5895 ("staging: erofs: add compacted compression indexes support")
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20230410173714.104604-1-hsiangkao@linux.alibaba.com
---
 fs/erofs/zmap.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index cbd3f72c83e9..7ca108c3834c 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -85,6 +85,10 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m,
 		if (advise & Z_EROFS_LI_PARTIAL_REF)
 			m->partialref = true;
 		m->clusterofs = le16_to_cpu(di->di_clusterofs);
+		if (m->clusterofs >= 1 << vi->z_logical_clusterbits) {
+			DBG_BUGON(1);
+			return -EFSCORRUPTED;
+		}
 		m->pblk = le32_to_cpu(di->di_u.blkaddr);
 		break;
 	default:

From cb9bce79514392a9a216ff67148e05e2d72c28bd Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Fri, 7 Apr 2023 22:17:05 +0800
Subject: [PATCH 48/67] erofs: initialize packed inode after root inode is
 assigned

As commit 8f7acdae2cd4 ("staging: erofs: kill all failure handling in
fill_super()"), move the initialization of packed inode after root
inode is assigned, so that the iput() in .put_super() is adequate as
the failure handling.

Otherwise, iput() is also needed in .kill_sb(), in case of the mounting
fails halfway.

Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Reviewed-by: Yue Hu <huyue2@coolpad.com>
Fixes: b15b2e307c3a ("erofs: support on-disk compressed fragments data")
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Acked-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20230407141710.113882-3-jefflexu@linux.alibaba.com
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/internal.h |  1 +
 fs/erofs/super.c    | 22 +++++++++++-----------
 2 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index e30a4fd43ccb..1581ad78ee65 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -157,6 +157,7 @@ struct erofs_sb_info {
 
 	/* what we really care is nid, rather than ino.. */
 	erofs_nid_t root_nid;
+	erofs_nid_t packed_nid;
 	/* used for statfs, f_files - f_favail */
 	u64 inos;
 
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 6be232a97ec6..5475ff2f7327 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -388,17 +388,7 @@ static int erofs_read_superblock(struct super_block *sb)
 #endif
 	sbi->islotbits = ilog2(sizeof(struct erofs_inode_compact));
 	sbi->root_nid = le16_to_cpu(dsb->root_nid);
-#ifdef CONFIG_EROFS_FS_ZIP
-	sbi->packed_inode = NULL;
-	if (erofs_sb_has_fragments(sbi) && dsb->packed_nid) {
-		sbi->packed_inode =
-			erofs_iget(sb, le64_to_cpu(dsb->packed_nid));
-		if (IS_ERR(sbi->packed_inode)) {
-			ret = PTR_ERR(sbi->packed_inode);
-			goto out;
-		}
-	}
-#endif
+	sbi->packed_nid = le64_to_cpu(dsb->packed_nid);
 	sbi->inos = le64_to_cpu(dsb->inos);
 
 	sbi->build_time = le64_to_cpu(dsb->build_time);
@@ -818,6 +808,16 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 
 	erofs_shrinker_register(sb);
 	/* sb->s_umount is already locked, SB_ACTIVE and SB_BORN are not set */
+#ifdef CONFIG_EROFS_FS_ZIP
+	if (erofs_sb_has_fragments(sbi) && sbi->packed_nid) {
+		sbi->packed_inode = erofs_iget(sb, sbi->packed_nid);
+		if (IS_ERR(sbi->packed_inode)) {
+			err = PTR_ERR(sbi->packed_inode);
+			sbi->packed_inode = NULL;
+			return err;
+		}
+	}
+#endif
 	err = erofs_init_managed_cache(sb);
 	if (err)
 		return err;

From eb2c5e41be1495cf7a20ff49df473b1c45b82e77 Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Fri, 7 Apr 2023 22:17:04 +0800
Subject: [PATCH 49/67] erofs: keep meta inode into erofs_buf

So that erofs_read_metadata() can read metadata from other inodes
(e.g. packed inode) as well.

Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Acked-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20230407141710.113882-2-jefflexu@linux.alibaba.com
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/data.c     | 23 ++++++++++++++---------
 fs/erofs/dir.c      |  3 ++-
 fs/erofs/internal.h |  6 ++++--
 fs/erofs/namei.c    |  4 +++-
 fs/erofs/super.c    |  6 +++---
 fs/erofs/zdata.c    |  4 ++--
 6 files changed, 28 insertions(+), 18 deletions(-)

diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 03c6ffdfcbfb..6fe9a779fa91 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -31,11 +31,11 @@ void erofs_put_metabuf(struct erofs_buf *buf)
  * Derive the block size from inode->i_blkbits to make compatible with
  * anonymous inode in fscache mode.
  */
-void *erofs_bread(struct erofs_buf *buf, struct inode *inode,
-		  erofs_blk_t blkaddr, enum erofs_kmap_type type)
+void *erofs_bread(struct erofs_buf *buf, erofs_blk_t blkaddr,
+		  enum erofs_kmap_type type)
 {
+	struct inode *inode = buf->inode;
 	erofs_off_t offset = (erofs_off_t)blkaddr << inode->i_blkbits;
-	struct address_space *const mapping = inode->i_mapping;
 	pgoff_t index = offset >> PAGE_SHIFT;
 	struct page *page = buf->page;
 	struct folio *folio;
@@ -45,7 +45,7 @@ void *erofs_bread(struct erofs_buf *buf, struct inode *inode,
 		erofs_put_metabuf(buf);
 
 		nofs_flag = memalloc_nofs_save();
-		folio = read_cache_folio(mapping, index, NULL, NULL);
+		folio = read_cache_folio(inode->i_mapping, index, NULL, NULL);
 		memalloc_nofs_restore(nofs_flag);
 		if (IS_ERR(folio))
 			return folio;
@@ -67,14 +67,19 @@ void *erofs_bread(struct erofs_buf *buf, struct inode *inode,
 	return buf->base + (offset & ~PAGE_MASK);
 }
 
+void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb)
+{
+	if (erofs_is_fscache_mode(sb))
+		buf->inode = EROFS_SB(sb)->s_fscache->inode;
+	else
+		buf->inode = sb->s_bdev->bd_inode;
+}
+
 void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb,
 			 erofs_blk_t blkaddr, enum erofs_kmap_type type)
 {
-	if (erofs_is_fscache_mode(sb))
-		return erofs_bread(buf, EROFS_SB(sb)->s_fscache->inode,
-				   blkaddr, type);
-
-	return erofs_bread(buf, sb->s_bdev->bd_inode, blkaddr, type);
+	erofs_init_metabuf(buf, sb);
+	return erofs_bread(buf, blkaddr, type);
 }
 
 static int erofs_map_blocks_flatmode(struct inode *inode,
diff --git a/fs/erofs/dir.c b/fs/erofs/dir.c
index 963bbed0b699..b80abec0531a 100644
--- a/fs/erofs/dir.c
+++ b/fs/erofs/dir.c
@@ -58,11 +58,12 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx)
 	int err = 0;
 	bool initial = true;
 
+	buf.inode = dir;
 	while (ctx->pos < dirsize) {
 		struct erofs_dirent *de;
 		unsigned int nameoff, maxsize;
 
-		de = erofs_bread(&buf, dir, i, EROFS_KMAP);
+		de = erofs_bread(&buf, i, EROFS_KMAP);
 		if (IS_ERR(de)) {
 			erofs_err(sb, "fail to readdir of logical block %u of nid %llu",
 				  i, EROFS_I(dir)->nid);
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 1581ad78ee65..caea9dc1cd82 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -248,6 +248,7 @@ enum erofs_kmap_type {
 };
 
 struct erofs_buf {
+	struct inode *inode;
 	struct page *page;
 	void *base;
 	enum erofs_kmap_type kmap_type;
@@ -441,8 +442,9 @@ extern const struct iomap_ops z_erofs_iomap_report_ops;
 
 void erofs_unmap_metabuf(struct erofs_buf *buf);
 void erofs_put_metabuf(struct erofs_buf *buf);
-void *erofs_bread(struct erofs_buf *buf, struct inode *inode,
-		  erofs_blk_t blkaddr, enum erofs_kmap_type type);
+void *erofs_bread(struct erofs_buf *buf, erofs_blk_t blkaddr,
+		  enum erofs_kmap_type type);
+void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb);
 void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb,
 			 erofs_blk_t blkaddr, enum erofs_kmap_type type);
 int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *dev);
diff --git a/fs/erofs/namei.c b/fs/erofs/namei.c
index f091e9a0f0a1..43096bac4c99 100644
--- a/fs/erofs/namei.c
+++ b/fs/erofs/namei.c
@@ -99,7 +99,8 @@ static void *erofs_find_target_block(struct erofs_buf *target,
 		struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
 		struct erofs_dirent *de;
 
-		de = erofs_bread(&buf, dir, mid, EROFS_KMAP);
+		buf.inode = dir;
+		de = erofs_bread(&buf, mid, EROFS_KMAP);
 		if (!IS_ERR(de)) {
 			const int nameoff = nameoff_from_disk(de->nameoff, bsz);
 			const int ndirents = nameoff / sizeof(*de);
@@ -170,6 +171,7 @@ int erofs_namei(struct inode *dir, const struct qstr *name, erofs_nid_t *nid,
 
 	qn.name = name->name;
 	qn.end = name->name + name->len;
+	buf.inode = dir;
 
 	ndirents = 0;
 	de = erofs_find_target_block(&buf, dir, &qn, &ndirents);
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 5475ff2f7327..f45a15ee2311 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -135,7 +135,7 @@ static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf,
 	int len, i, cnt;
 
 	*offset = round_up(*offset, 4);
-	ptr = erofs_read_metabuf(buf, sb, erofs_blknr(sb, *offset), EROFS_KMAP);
+	ptr = erofs_bread(buf, erofs_blknr(sb, *offset), EROFS_KMAP);
 	if (IS_ERR(ptr))
 		return ptr;
 
@@ -151,8 +151,7 @@ static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf,
 	for (i = 0; i < len; i += cnt) {
 		cnt = min_t(int, sb->s_blocksize - erofs_blkoff(sb, *offset),
 			    len - i);
-		ptr = erofs_read_metabuf(buf, sb, erofs_blknr(sb, *offset),
-					 EROFS_KMAP);
+		ptr = erofs_bread(buf, erofs_blknr(sb, *offset), EROFS_KMAP);
 		if (IS_ERR(ptr)) {
 			kfree(buffer);
 			return ptr;
@@ -179,6 +178,7 @@ static int erofs_load_compr_cfgs(struct super_block *sb,
 		return -EINVAL;
 	}
 
+	erofs_init_metabuf(&buf, sb);
 	offset = EROFS_SUPER_OFFSET + sbi->sb_size;
 	alg = 0;
 	for (algs = sbi->available_compr_algs; algs; algs >>= 1, ++alg) {
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index a90d37c7bdd7..34944e400037 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -939,12 +939,12 @@ static int z_erofs_read_fragment(struct inode *inode, erofs_off_t pos,
 	if (!packed_inode)
 		return -EFSCORRUPTED;
 
+	buf.inode = packed_inode;
 	pos += EROFS_I(inode)->z_fragmentoff;
 	for (i = 0; i < len; i += cnt) {
 		cnt = min_t(unsigned int, len - i,
 			    sb->s_blocksize - erofs_blkoff(sb, pos));
-		src = erofs_bread(&buf, packed_inode,
-				  erofs_blknr(sb, pos), EROFS_KMAP);
+		src = erofs_bread(&buf, erofs_blknr(sb, pos), EROFS_KMAP);
 		if (IS_ERR(src)) {
 			erofs_put_metabuf(&buf);
 			return PTR_ERR(src);

From a97a218b08868029507272a8fc6b52491a157ec5 Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Fri, 7 Apr 2023 22:17:06 +0800
Subject: [PATCH 50/67] erofs: move packed inode out of the compression part

packed inode could be used in more scenarios which are independent of
compression in the future.

For example, packed inode could be used to keep extra long xattr
prefixes with the help of following patches.

Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Reviewed-by: Yue Hu <huyue2@coolpad.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Acked-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20230407141710.113882-4-jefflexu@linux.alibaba.com
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/internal.h | 2 +-
 fs/erofs/super.c    | 4 +---
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index caea9dc1cd82..8b5168f94dd2 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -134,8 +134,8 @@ struct erofs_sb_info {
 	struct inode *managed_cache;
 
 	struct erofs_sb_lz4_info lz4;
-	struct inode *packed_inode;
 #endif	/* CONFIG_EROFS_FS_ZIP */
+	struct inode *packed_inode;
 	struct erofs_dev_context *devs;
 	struct dax_device *dax_dev;
 	u64 dax_part_off;
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index f45a15ee2311..2ab70e960e47 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -808,7 +808,6 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 
 	erofs_shrinker_register(sb);
 	/* sb->s_umount is already locked, SB_ACTIVE and SB_BORN are not set */
-#ifdef CONFIG_EROFS_FS_ZIP
 	if (erofs_sb_has_fragments(sbi) && sbi->packed_nid) {
 		sbi->packed_inode = erofs_iget(sb, sbi->packed_nid);
 		if (IS_ERR(sbi->packed_inode)) {
@@ -817,7 +816,6 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 			return err;
 		}
 	}
-#endif
 	err = erofs_init_managed_cache(sb);
 	if (err)
 		return err;
@@ -984,9 +982,9 @@ static void erofs_put_super(struct super_block *sb)
 #ifdef CONFIG_EROFS_FS_ZIP
 	iput(sbi->managed_cache);
 	sbi->managed_cache = NULL;
+#endif
 	iput(sbi->packed_inode);
 	sbi->packed_inode = NULL;
-#endif
 	erofs_free_dev_context(sbi->devs);
 	sbi->devs = NULL;
 	erofs_fscache_unregister_fs(sb);

From b3bfcb9dbfff3da26a63efc60558acd60b96392a Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Fri, 7 Apr 2023 22:17:07 +0800
Subject: [PATCH 51/67] erofs: introduce on-disk format for long xattr name
 prefixes

Besides the predefined xattr name prefixes, introduces long xattr name
prefixes, which work similarly as the predefined name prefixes, except
that they are user specified.

It is especially useful for use cases together with overlayfs like
Composefs model, which introduces diverse xattr values with only a few
common xattr names (trusted.overlay.redirect, trusted.overlay.digest,
and maybe more in the future).  That makes the existing predefined
prefixes ineffective in both image size and runtime performance.

When a user specified long xattr name prefix is used, only the trailing
part of the xattr name apart from the long xattr name prefix will be
stored in erofs_xattr_entry.e_name.  e_name is empty if the xattr name
matches exactly as the long xattr name prefix.  All long xattr prefixes
are stored in the packed or meta inode, which depends if fragments
feature is enabled or not.

For each long xattr name prefix, the on-disk format is kept as the same
as the unique metadata format: ALIGN({__le16 len, data}, 4), where len
represents the total size of struct erofs_xattr_long_prefix, followed
by data of struct erofs_xattr_long_prefix itself.

Each erofs_xattr_long_prefix keeps predefined prefixes (base_index)
and the remaining prefix string without the trailing '\0'.

Two fields are introduced to the on-disk superblock, where
xattr_prefix_count represents the total number of the long xattr name
prefixes recorded, and xattr_prefix_start represents the start offset of
recorded name prefixes in the packed/meta inode divided by 4.

When referring to a long xattr name prefix, the highest bit (bit 7) of
erofs_xattr_entry.e_name_index is set, while the lower bits (bit 0-6)
as a whole represents the index of the referred long name prefix among
all long xattr name prefixes.

Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Acked-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20230407141710.113882-5-jefflexu@linux.alibaba.com
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/erofs_fs.h | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index 1a4a614895c6..71a4b3c83132 100644
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -76,7 +76,8 @@ struct erofs_super_block {
 	__le16 extra_devices;	/* # of devices besides the primary device */
 	__le16 devt_slotoff;	/* startoff = devt_slotoff * devt_slotsize */
 	__u8 dirblkbits;	/* directory block size in bit shift */
-	__u8 reserved[5];
+	__u8 xattr_prefix_count;	/* # of long xattr name prefixes */
+	__le32 xattr_prefix_start;	/* start of long xattr prefixes */
 	__le64 packed_nid;	/* nid of the special packed inode */
 	__u8 reserved2[24];
 };
@@ -211,6 +212,13 @@ struct erofs_xattr_ibody_header {
 #define EROFS_XATTR_INDEX_LUSTRE            5
 #define EROFS_XATTR_INDEX_SECURITY          6
 
+/*
+ * bit 7 of e_name_index is set when it refers to a long xattr name prefix,
+ * while the remained lower bits represent the index of the prefix.
+ */
+#define EROFS_XATTR_LONG_PREFIX		0x80
+#define EROFS_XATTR_LONG_PREFIX_MASK	0x7f
+
 /* xattr entry (for both inline & shared xattrs) */
 struct erofs_xattr_entry {
 	__u8   e_name_len;      /* length of name */
@@ -220,6 +228,12 @@ struct erofs_xattr_entry {
 	char   e_name[];        /* attribute name */
 };
 
+/* long xattr name prefix */
+struct erofs_xattr_long_prefix {
+	__u8   base_index;	/* short xattr name prefix index */
+	char   infix[];		/* infix apart from short prefix */
+};
+
 static inline unsigned int erofs_xattr_ibody_size(__le16 i_xattr_icount)
 {
 	if (!i_xattr_icount)

From 9e382914617c5cab89a01a223b8d00bbd43ad3b3 Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Fri, 7 Apr 2023 22:17:08 +0800
Subject: [PATCH 52/67] erofs: add helpers to load long xattr name prefixes

Long xattr name prefixes will be scanned upon mounting and the in-memory
long xattr name prefix array will be initialized accordingly.

Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Acked-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20230407141710.113882-6-jefflexu@linux.alibaba.com
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/internal.h | 10 ++++++++
 fs/erofs/super.c    |  6 ++---
 fs/erofs/xattr.c    | 56 +++++++++++++++++++++++++++++++++++++++++++++
 fs/erofs/xattr.h    |  4 ++++
 4 files changed, 73 insertions(+), 3 deletions(-)

diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 8b5168f94dd2..5a9c19654b19 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -117,6 +117,11 @@ struct erofs_fscache {
 	char *name;
 };
 
+struct erofs_xattr_prefix_item {
+	struct erofs_xattr_long_prefix *prefix;
+	u8 infix_len;
+};
+
 struct erofs_sb_info {
 	struct erofs_mount_opts opt;	/* options */
 #ifdef CONFIG_EROFS_FS_ZIP
@@ -145,6 +150,9 @@ struct erofs_sb_info {
 	u32 meta_blkaddr;
 #ifdef CONFIG_EROFS_FS_XATTR
 	u32 xattr_blkaddr;
+	u32 xattr_prefix_start;
+	u8 xattr_prefix_count;
+	struct erofs_xattr_prefix_item *xattr_prefixes;
 #endif
 	u16 device_id_mask;	/* valid bits of device id to be used */
 
@@ -440,6 +448,8 @@ extern const struct iomap_ops z_erofs_iomap_report_ops;
 #define EROFS_REG_COOKIE_SHARE		0x0001
 #define EROFS_REG_COOKIE_NEED_NOEXIST	0x0002
 
+void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf,
+			  erofs_off_t *offset, int *lengthp);
 void erofs_unmap_metabuf(struct erofs_buf *buf);
 void erofs_put_metabuf(struct erofs_buf *buf);
 void *erofs_bread(struct erofs_buf *buf, erofs_blk_t blkaddr,
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 2ab70e960e47..ddfb73b5a48e 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -126,10 +126,9 @@ static bool check_layout_compatibility(struct super_block *sb,
 	return true;
 }
 
-#ifdef CONFIG_EROFS_FS_ZIP
 /* read variable-sized metadata, offset will be aligned by 4-byte */
-static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf,
-				 erofs_off_t *offset, int *lengthp)
+void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf,
+			  erofs_off_t *offset, int *lengthp)
 {
 	u8 *buffer, *ptr;
 	int len, i, cnt;
@@ -162,6 +161,7 @@ static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf,
 	return buffer;
 }
 
+#ifdef CONFIG_EROFS_FS_ZIP
 static int erofs_load_compr_cfgs(struct super_block *sb,
 				 struct erofs_super_block *dsb)
 {
diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c
index d76b74ece2e5..684571e83a2c 100644
--- a/fs/erofs/xattr.c
+++ b/fs/erofs/xattr.c
@@ -610,6 +610,62 @@ ssize_t erofs_listxattr(struct dentry *dentry,
 	return ret;
 }
 
+void erofs_xattr_prefixes_cleanup(struct super_block *sb)
+{
+	struct erofs_sb_info *sbi = EROFS_SB(sb);
+	int i;
+
+	if (sbi->xattr_prefixes) {
+		for (i = 0; i < sbi->xattr_prefix_count; i++)
+			kfree(sbi->xattr_prefixes[i].prefix);
+		kfree(sbi->xattr_prefixes);
+		sbi->xattr_prefixes = NULL;
+	}
+}
+
+int erofs_xattr_prefixes_init(struct super_block *sb)
+{
+	struct erofs_sb_info *sbi = EROFS_SB(sb);
+	struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
+	erofs_off_t pos = (erofs_off_t)sbi->xattr_prefix_start << 2;
+	struct erofs_xattr_prefix_item *pfs;
+	int ret = 0, i, len;
+
+	if (!sbi->xattr_prefix_count)
+		return 0;
+
+	pfs = kzalloc(sbi->xattr_prefix_count * sizeof(*pfs), GFP_KERNEL);
+	if (!pfs)
+		return -ENOMEM;
+
+	if (erofs_sb_has_fragments(sbi))
+		buf.inode = sbi->packed_inode;
+	else
+		erofs_init_metabuf(&buf, sb);
+
+	for (i = 0; i < sbi->xattr_prefix_count; i++) {
+		void *ptr = erofs_read_metadata(sb, &buf, &pos, &len);
+
+		if (IS_ERR(ptr)) {
+			ret = PTR_ERR(ptr);
+			break;
+		} else if (len < sizeof(*pfs->prefix) ||
+			   len > EROFS_NAME_LEN + sizeof(*pfs->prefix)) {
+			kfree(ptr);
+			ret = -EFSCORRUPTED;
+			break;
+		}
+		pfs[i].prefix = ptr;
+		pfs[i].infix_len = len - sizeof(struct erofs_xattr_long_prefix);
+	}
+
+	erofs_put_metabuf(&buf);
+	sbi->xattr_prefixes = pfs;
+	if (ret)
+		erofs_xattr_prefixes_cleanup(sb);
+	return ret;
+}
+
 #ifdef CONFIG_EROFS_FS_POSIX_ACL
 struct posix_acl *erofs_get_acl(struct inode *inode, int type, bool rcu)
 {
diff --git a/fs/erofs/xattr.h b/fs/erofs/xattr.h
index a65158cba14f..e1265351aedd 100644
--- a/fs/erofs/xattr.h
+++ b/fs/erofs/xattr.h
@@ -40,9 +40,13 @@ static inline const struct xattr_handler *erofs_xattr_handler(unsigned int idx)
 
 extern const struct xattr_handler *erofs_xattr_handlers[];
 
+int erofs_xattr_prefixes_init(struct super_block *sb);
+void erofs_xattr_prefixes_cleanup(struct super_block *sb);
 int erofs_getxattr(struct inode *, int, const char *, void *, size_t);
 ssize_t erofs_listxattr(struct dentry *, char *, size_t);
 #else
+static inline int erofs_xattr_prefixes_init(struct super_block *sb) { return 0; }
+static inline void erofs_xattr_prefixes_cleanup(struct super_block *sb) {}
 static inline int erofs_getxattr(struct inode *inode, int index,
 				 const char *name, void *buffer,
 				 size_t buffer_size)

From 82bc1ef41d275106a2b5288e4f5b0df19223066a Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Tue, 11 Apr 2023 17:35:37 +0800
Subject: [PATCH 53/67] erofs: handle long xattr name prefixes properly

Make .{list,get}xattr routines adapted to long xattr name prefixes.
When the bit 7 of erofs_xattr_entry.e_name_index is set, it indicates
that it refers to a long xattr name prefix.

Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Acked-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20230411093537.127286-1-jefflexu@linux.alibaba.com
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/xattr.c | 66 ++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 55 insertions(+), 11 deletions(-)

diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c
index 684571e83a2c..a04724c816e5 100644
--- a/fs/erofs/xattr.c
+++ b/fs/erofs/xattr.c
@@ -297,17 +297,45 @@ struct getxattr_iter {
 	struct xattr_iter it;
 
 	char *buffer;
-	int buffer_size, index;
+	int buffer_size, index, infix_len;
 	struct qstr name;
 };
 
+static int erofs_xattr_long_entrymatch(struct getxattr_iter *it,
+				       struct erofs_xattr_entry *entry)
+{
+	struct erofs_sb_info *sbi = EROFS_SB(it->it.sb);
+	struct erofs_xattr_prefix_item *pf = sbi->xattr_prefixes +
+		(entry->e_name_index & EROFS_XATTR_LONG_PREFIX_MASK);
+
+	if (pf >= sbi->xattr_prefixes + sbi->xattr_prefix_count)
+		return -ENOATTR;
+
+	if (it->index != pf->prefix->base_index ||
+	    it->name.len != entry->e_name_len + pf->infix_len)
+		return -ENOATTR;
+
+	if (memcmp(it->name.name, pf->prefix->infix, pf->infix_len))
+		return -ENOATTR;
+
+	it->infix_len = pf->infix_len;
+	return 0;
+}
+
 static int xattr_entrymatch(struct xattr_iter *_it,
 			    struct erofs_xattr_entry *entry)
 {
 	struct getxattr_iter *it = container_of(_it, struct getxattr_iter, it);
 
-	return (it->index != entry->e_name_index ||
-		it->name.len != entry->e_name_len) ? -ENOATTR : 0;
+	/* should also match the infix for long name prefixes */
+	if (entry->e_name_index & EROFS_XATTR_LONG_PREFIX)
+		return erofs_xattr_long_entrymatch(it, entry);
+
+	if (it->index != entry->e_name_index ||
+	    it->name.len != entry->e_name_len)
+		return -ENOATTR;
+	it->infix_len = 0;
+	return 0;
 }
 
 static int xattr_namematch(struct xattr_iter *_it,
@@ -315,7 +343,9 @@ static int xattr_namematch(struct xattr_iter *_it,
 {
 	struct getxattr_iter *it = container_of(_it, struct getxattr_iter, it);
 
-	return memcmp(buf, it->name.name + processed, len) ? -ENOATTR : 0;
+	if (memcmp(buf, it->name.name + it->infix_len + processed, len))
+		return -ENOATTR;
+	return 0;
 }
 
 static int xattr_checkbuffer(struct xattr_iter *_it,
@@ -487,12 +517,24 @@ static int xattr_entrylist(struct xattr_iter *_it,
 {
 	struct listxattr_iter *it =
 		container_of(_it, struct listxattr_iter, it);
-	unsigned int prefix_len;
-	const char *prefix;
+	unsigned int base_index = entry->e_name_index;
+	unsigned int prefix_len, infix_len = 0;
+	const char *prefix, *infix = NULL;
+	const struct xattr_handler *h;
 
-	const struct xattr_handler *h =
-		erofs_xattr_handler(entry->e_name_index);
+	if (entry->e_name_index & EROFS_XATTR_LONG_PREFIX) {
+		struct erofs_sb_info *sbi = EROFS_SB(_it->sb);
+		struct erofs_xattr_prefix_item *pf = sbi->xattr_prefixes +
+			(entry->e_name_index & EROFS_XATTR_LONG_PREFIX_MASK);
 
+		if (pf >= sbi->xattr_prefixes + sbi->xattr_prefix_count)
+			return 1;
+		infix = pf->prefix->infix;
+		infix_len = pf->infix_len;
+		base_index = pf->prefix->base_index;
+	}
+
+	h = erofs_xattr_handler(base_index);
 	if (!h || (h->list && !h->list(it->dentry)))
 		return 1;
 
@@ -500,16 +542,18 @@ static int xattr_entrylist(struct xattr_iter *_it,
 	prefix_len = strlen(prefix);
 
 	if (!it->buffer) {
-		it->buffer_ofs += prefix_len + entry->e_name_len + 1;
+		it->buffer_ofs += prefix_len + infix_len +
+					entry->e_name_len + 1;
 		return 1;
 	}
 
-	if (it->buffer_ofs + prefix_len
+	if (it->buffer_ofs + prefix_len + infix_len +
 		+ entry->e_name_len + 1 > it->buffer_size)
 		return -ERANGE;
 
 	memcpy(it->buffer + it->buffer_ofs, prefix, prefix_len);
-	it->buffer_ofs += prefix_len;
+	memcpy(it->buffer + it->buffer_ofs + prefix_len, infix, infix_len);
+	it->buffer_ofs += prefix_len + infix_len;
 	return 0;
 }
 

From 6a318ccd7e083729cbcdbd174d7070f6b7d24130 Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Sat, 8 Apr 2023 06:28:08 +0800
Subject: [PATCH 54/67] erofs: enable long extended attribute name prefixes

Let's enable long xattr name prefix feature.  Old kernels will just
ignore / skip such extended attributes.  In addition, in case you
don't want to mount such images, add another incompatible feature as
an option for this.

Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Acked-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20230407222808.19670-1-jefflexu@linux.alibaba.com
[ Gao Xiang: minor commit message fix. ]
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/erofs_fs.h | 4 +++-
 fs/erofs/internal.h | 1 +
 fs/erofs/super.c    | 7 +++++++
 3 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index 71a4b3c83132..4ec422c2b74f 100644
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -27,6 +27,7 @@
 #define EROFS_FEATURE_INCOMPAT_ZTAILPACKING	0x00000010
 #define EROFS_FEATURE_INCOMPAT_FRAGMENTS	0x00000020
 #define EROFS_FEATURE_INCOMPAT_DEDUPE		0x00000020
+#define EROFS_FEATURE_INCOMPAT_XATTR_PREFIXES	0x00000040
 #define EROFS_ALL_FEATURE_INCOMPAT		\
 	(EROFS_FEATURE_INCOMPAT_ZERO_PADDING | \
 	 EROFS_FEATURE_INCOMPAT_COMPR_CFGS | \
@@ -36,7 +37,8 @@
 	 EROFS_FEATURE_INCOMPAT_COMPR_HEAD2 | \
 	 EROFS_FEATURE_INCOMPAT_ZTAILPACKING | \
 	 EROFS_FEATURE_INCOMPAT_FRAGMENTS | \
-	 EROFS_FEATURE_INCOMPAT_DEDUPE)
+	 EROFS_FEATURE_INCOMPAT_DEDUPE | \
+	 EROFS_FEATURE_INCOMPAT_XATTR_PREFIXES)
 
 #define EROFS_SB_EXTSLOT_SIZE	16
 
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 5a9c19654b19..f675050af2bb 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -285,6 +285,7 @@ EROFS_FEATURE_FUNCS(compr_head2, incompat, INCOMPAT_COMPR_HEAD2)
 EROFS_FEATURE_FUNCS(ztailpacking, incompat, INCOMPAT_ZTAILPACKING)
 EROFS_FEATURE_FUNCS(fragments, incompat, INCOMPAT_FRAGMENTS)
 EROFS_FEATURE_FUNCS(dedupe, incompat, INCOMPAT_DEDUPE)
+EROFS_FEATURE_FUNCS(xattr_prefixes, incompat, INCOMPAT_XATTR_PREFIXES)
 EROFS_FEATURE_FUNCS(sb_chksum, compat, COMPAT_SB_CHKSUM)
 
 /* atomic flag definitions */
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index ddfb73b5a48e..811ab66d805e 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -385,6 +385,8 @@ static int erofs_read_superblock(struct super_block *sb)
 	sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr);
 #ifdef CONFIG_EROFS_FS_XATTR
 	sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr);
+	sbi->xattr_prefix_start = le32_to_cpu(dsb->xattr_prefix_start);
+	sbi->xattr_prefix_count = dsb->xattr_prefix_count;
 #endif
 	sbi->islotbits = ilog2(sizeof(struct erofs_inode_compact));
 	sbi->root_nid = le16_to_cpu(dsb->root_nid);
@@ -820,6 +822,10 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (err)
 		return err;
 
+	err = erofs_xattr_prefixes_init(sb);
+	if (err)
+		return err;
+
 	err = erofs_register_sysfs(sb);
 	if (err)
 		return err;
@@ -979,6 +985,7 @@ static void erofs_put_super(struct super_block *sb)
 
 	erofs_unregister_sysfs(sb);
 	erofs_shrinker_unregister(sb);
+	erofs_xattr_prefixes_cleanup(sb);
 #ifdef CONFIG_EROFS_FS_ZIP
 	iput(sbi->managed_cache);
 	sbi->managed_cache = NULL;

From 4fdadd5b0f0c723c812842454f8cca1619f2e731 Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Thu, 13 Apr 2023 17:22:41 +0800
Subject: [PATCH 55/67] erofs: get rid of z_erofs_fill_inode()

Prior to big pclusters, non-compact compression indexes could have
empty headers.

Let's just avoid the legacy path since it can be handled properly
as a specific compression header with z_erofs_fill_inode_lazy() too.

Tested with erofs-utils exist versions.

Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Yue Hu <huyue2@coolpad.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20230413092241.73829-1-hsiangkao@linux.alibaba.com
---
 fs/erofs/inode.c    | 12 ++++++++----
 fs/erofs/internal.h |  2 --
 fs/erofs/zmap.c     | 18 ------------------
 3 files changed, 8 insertions(+), 24 deletions(-)

diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index 7ca9aafb7471..e196d453291b 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -291,11 +291,15 @@ static int erofs_fill_inode(struct inode *inode)
 	}
 
 	if (erofs_inode_is_data_compressed(vi->datalayout)) {
+#ifdef CONFIG_EROFS_FS_ZIP
 		if (!erofs_is_fscache_mode(inode->i_sb) &&
-		    inode->i_sb->s_blocksize_bits == PAGE_SHIFT)
-			err = z_erofs_fill_inode(inode);
-		else
-			err = -EOPNOTSUPP;
+		    inode->i_sb->s_blocksize_bits == PAGE_SHIFT) {
+			inode->i_mapping->a_ops = &z_erofs_aops;
+			err = 0;
+			goto out_unlock;
+		}
+#endif
+		err = -EOPNOTSUPP;
 		goto out_unlock;
 	}
 	inode->i_mapping->a_ops = &erofs_raw_access_aops;
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index f675050af2bb..f1268cb6a37c 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -522,7 +522,6 @@ int erofs_try_to_free_cached_page(struct page *page);
 int z_erofs_load_lz4_config(struct super_block *sb,
 			    struct erofs_super_block *dsb,
 			    struct z_erofs_lz4_cfgs *lz4, int len);
-int z_erofs_fill_inode(struct inode *inode);
 int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map,
 			    int flags);
 #else
@@ -542,7 +541,6 @@ static inline int z_erofs_load_lz4_config(struct super_block *sb,
 	}
 	return 0;
 }
-static inline int z_erofs_fill_inode(struct inode *inode) { return -EOPNOTSUPP; }
 #endif	/* !CONFIG_EROFS_FS_ZIP */
 
 #ifdef CONFIG_EROFS_FS_ZIP_LZMA
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 7ca108c3834c..14c21284d019 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -7,24 +7,6 @@
 #include <asm/unaligned.h>
 #include <trace/events/erofs.h>
 
-int z_erofs_fill_inode(struct inode *inode)
-{
-	struct erofs_inode *const vi = EROFS_I(inode);
-	struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb);
-
-	if (!erofs_sb_has_big_pcluster(sbi) &&
-	    !erofs_sb_has_ztailpacking(sbi) && !erofs_sb_has_fragments(sbi) &&
-	    vi->datalayout == EROFS_INODE_COMPRESSED_FULL) {
-		vi->z_advise = 0;
-		vi->z_algorithmtype[0] = 0;
-		vi->z_algorithmtype[1] = 0;
-		vi->z_logical_clusterbits = inode->i_sb->s_blocksize_bits;
-		set_bit(EROFS_I_Z_INITED_BIT, &vi->flags);
-	}
-	inode->i_mapping->a_ops = &z_erofs_aops;
-	return 0;
-}
-
 struct z_erofs_maprecorder {
 	struct inode *inode;
 	struct erofs_map_blocks *map;

From 1b3567a1969b26f709d82a874498c0754ea841c3 Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Fri, 14 Apr 2023 14:18:10 +0800
Subject: [PATCH 56/67] erofs: fix potential overflow calculating xattr_isize

Given on-disk i_xattr_icount is 16 bits and xattr_isize is calculated
from i_xattr_icount multiplying 4, xattr_isize has a theoretical maximum
of 256K (64K * 4).

Thus declare xattr_isize as unsigned int to avoid the potential overflow.

Fixes: bfb8674dc044 ("staging: erofs: add erofs in-memory stuffs")
Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20230414061810.6479-1-jefflexu@linux.alibaba.com
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/internal.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index f1268cb6a37c..b5e91d7cc3f3 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -304,7 +304,7 @@ struct erofs_inode {
 
 	unsigned char datalayout;
 	unsigned char inode_isize;
-	unsigned short xattr_isize;
+	unsigned int xattr_isize;
 
 	unsigned int xattr_shared_count;
 	unsigned int *xattr_shared_xattrs;

From 10656f9ca60ed85f4cfc06bcbe1f240ee310fa8c Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Fri, 14 Apr 2023 16:30:26 +0800
Subject: [PATCH 57/67] erofs: sunset erofs_dbg()

Such debug messages are rarely used now.  Let's get rid of these,
and revert locally if they are needed for debugging.

Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20230414083027.12307-1-hsiangkao@linux.alibaba.com
---
 fs/erofs/inode.c    | 3 ---
 fs/erofs/internal.h | 2 --
 fs/erofs/namei.c    | 9 +++------
 fs/erofs/zdata.c    | 5 -----
 fs/erofs/zmap.c     | 3 ---
 5 files changed, 3 insertions(+), 19 deletions(-)

diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index e196d453291b..d70b12b81507 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -26,9 +26,6 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 	blkaddr = erofs_blknr(sb, inode_loc);
 	*ofs = erofs_blkoff(sb, inode_loc);
 
-	erofs_dbg("%s, reading inode nid %llu at %u of blkaddr %u",
-		  __func__, vi->nid, *ofs, blkaddr);
-
 	kaddr = erofs_read_metabuf(buf, sb, blkaddr, EROFS_KMAP);
 	if (IS_ERR(kaddr)) {
 		erofs_err(sb, "failed to get inode (nid: %llu) page, err %ld",
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index b5e91d7cc3f3..34d5113e13eb 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -31,10 +31,8 @@ __printf(3, 4) void _erofs_info(struct super_block *sb,
 #define erofs_info(sb, fmt, ...) \
 	_erofs_info(sb, __func__, fmt "\n", ##__VA_ARGS__)
 #ifdef CONFIG_EROFS_FS_DEBUG
-#define erofs_dbg(x, ...)       pr_debug(x "\n", ##__VA_ARGS__)
 #define DBG_BUGON               BUG_ON
 #else
-#define erofs_dbg(x, ...)       ((void)0)
 #define DBG_BUGON(x)            ((void)(x))
 #endif	/* !CONFIG_EROFS_FS_DEBUG */
 
diff --git a/fs/erofs/namei.c b/fs/erofs/namei.c
index 43096bac4c99..d4f631d39f0f 100644
--- a/fs/erofs/namei.c
+++ b/fs/erofs/namei.c
@@ -205,16 +205,13 @@ static struct dentry *erofs_lookup(struct inode *dir, struct dentry *dentry,
 
 	err = erofs_namei(dir, &dentry->d_name, &nid, &d_type);
 
-	if (err == -ENOENT) {
+	if (err == -ENOENT)
 		/* negative dentry */
 		inode = NULL;
-	} else if (err) {
+	else if (err)
 		inode = ERR_PTR(err);
-	} else {
-		erofs_dbg("%s, %pd (nid %llu) found, d_type %u", __func__,
-			  dentry, nid, d_type);
+	else
 		inode = erofs_iget(dir->i_sb, nid);
-	}
 	return d_splice_alias(inode, dentry);
 }
 
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 34944e400037..45f21db2303a 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -979,8 +979,6 @@ repeat:
 
 	if (offset + cur < map->m_la ||
 	    offset + cur >= map->m_la + map->m_llen) {
-		erofs_dbg("out-of-range map @ pos %llu", offset + cur);
-
 		if (z_erofs_collector_end(fe))
 			fe->backmost = false;
 		map->m_la = offset + cur;
@@ -1105,9 +1103,6 @@ out:
 	if (err)
 		z_erofs_page_mark_eio(page);
 	z_erofs_onlinepage_endio(page);
-
-	erofs_dbg("%s, finish page: %pK spiltted: %u map->m_llen %llu",
-		  __func__, page, spiltted, map->m_llen);
 	return err;
 }
 
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 14c21284d019..d37c5c89c728 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -585,9 +585,6 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 
 unmap_out:
 	erofs_unmap_metabuf(&m.map->buf);
-	erofs_dbg("%s, m_la %llu m_pa %llu m_llen %llu m_plen %llu m_flags 0%o",
-		  __func__, map->m_la, map->m_pa,
-		  map->m_llen, map->m_plen, map->m_flags);
 	return err;
 }
 

From 745ed7d77834048879bf24088c94e5a6462b613f Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Fri, 14 Apr 2023 16:30:27 +0800
Subject: [PATCH 58/67] erofs: cleanup i_format-related stuffs

Switch EROFS_I_{VERSION,DATALAYOUT}_BITS into
EROFS_I_{VERSION,DATALAYOUT}_MASK.

Also avoid erofs_bitrange() since its functionality is simple enough.

Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20230414083027.12307-2-hsiangkao@linux.alibaba.com
---
 fs/erofs/erofs_fs.h |  8 ++++----
 fs/erofs/internal.h | 18 ++++--------------
 2 files changed, 8 insertions(+), 18 deletions(-)

diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index 4ec422c2b74f..2c7b16e340fe 100644
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -109,14 +109,14 @@ static inline bool erofs_inode_is_data_compressed(unsigned int datamode)
 }
 
 /* bit definitions of inode i_format */
-#define EROFS_I_VERSION_BITS            1
-#define EROFS_I_DATALAYOUT_BITS         3
+#define EROFS_I_VERSION_MASK            0x01
+#define EROFS_I_DATALAYOUT_MASK         0x07
 
 #define EROFS_I_VERSION_BIT             0
 #define EROFS_I_DATALAYOUT_BIT          1
+#define EROFS_I_ALL_BIT			4
 
-#define EROFS_I_ALL	\
-	((1 << (EROFS_I_DATALAYOUT_BIT + EROFS_I_DATALAYOUT_BITS)) - 1)
+#define EROFS_I_ALL	((1 << EROFS_I_ALL_BIT) - 1)
 
 /* indicate chunk blkbits, thus 'chunksize = blocksize << chunk blkbits' */
 #define EROFS_CHUNK_FORMAT_BLKBITS_MASK		0x001F
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 34d5113e13eb..af0431a40647 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -343,24 +343,14 @@ static inline erofs_off_t erofs_iloc(struct inode *inode)
 		(EROFS_I(inode)->nid << sbi->islotbits);
 }
 
-static inline unsigned int erofs_bitrange(unsigned int value, unsigned int bit,
-					  unsigned int bits)
+static inline unsigned int erofs_inode_version(unsigned int ifmt)
 {
-
-	return (value >> bit) & ((1 << bits) - 1);
+	return (ifmt >> EROFS_I_VERSION_BIT) & EROFS_I_VERSION_MASK;
 }
 
-
-static inline unsigned int erofs_inode_version(unsigned int value)
+static inline unsigned int erofs_inode_datalayout(unsigned int ifmt)
 {
-	return erofs_bitrange(value, EROFS_I_VERSION_BIT,
-			      EROFS_I_VERSION_BITS);
-}
-
-static inline unsigned int erofs_inode_datalayout(unsigned int value)
-{
-	return erofs_bitrange(value, EROFS_I_DATALAYOUT_BIT,
-			      EROFS_I_DATALAYOUT_BITS);
+	return (ifmt >> EROFS_I_DATALAYOUT_BIT) & EROFS_I_DATALAYOUT_MASK;
 }
 
 /*

From 281117ccb2d2511d03f592dfec7ffdc33651e9b3 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 14 May 2022 19:33:38 -0400
Subject: [PATCH 59/67] convert setns(2) to fdget()/fdput()

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 kernel/nsproxy.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index a487ff24129b..80d9c6d77a45 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -545,21 +545,20 @@ static void commit_nsset(struct nsset *nsset)
 
 SYSCALL_DEFINE2(setns, int, fd, int, flags)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
 	struct ns_common *ns = NULL;
 	struct nsset nsset = {};
 	int err = 0;
 
-	file = fget(fd);
-	if (!file)
+	if (!f.file)
 		return -EBADF;
 
-	if (proc_ns_file(file)) {
-		ns = get_proc_ns(file_inode(file));
+	if (proc_ns_file(f.file)) {
+		ns = get_proc_ns(file_inode(f.file));
 		if (flags && (ns->ops->type != flags))
 			err = -EINVAL;
 		flags = ns->ops->type;
-	} else if (!IS_ERR(pidfd_pid(file))) {
+	} else if (!IS_ERR(pidfd_pid(f.file))) {
 		err = check_setns_flags(flags);
 	} else {
 		err = -EINVAL;
@@ -571,17 +570,17 @@ SYSCALL_DEFINE2(setns, int, fd, int, flags)
 	if (err)
 		goto out;
 
-	if (proc_ns_file(file))
+	if (proc_ns_file(f.file))
 		err = validate_ns(&nsset, ns);
 	else
-		err = validate_nsset(&nsset, file->private_data);
+		err = validate_nsset(&nsset, f.file->private_data);
 	if (!err) {
 		commit_nsset(&nsset);
 		perf_event_namespaces(current);
 	}
 	put_nsset(&nsset);
 out:
-	fput(file);
+	fdput(f);
 	return err;
 }
 

From e73d43760ad938428537dd6ccbb3653297a1bd69 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 14 May 2022 19:40:47 -0400
Subject: [PATCH 60/67] convert sgx_set_attribute() to fdget()/fdput()

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/x86/kernel/cpu/sgx/main.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index e5a37b6e9aa5..166692f2d501 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -892,20 +892,19 @@ static struct miscdevice sgx_dev_provision = {
 int sgx_set_attribute(unsigned long *allowed_attributes,
 		      unsigned int attribute_fd)
 {
-	struct file *file;
+	struct fd f = fdget(attribute_fd);
 
-	file = fget(attribute_fd);
-	if (!file)
+	if (!f.file)
 		return -EINVAL;
 
-	if (file->f_op != &sgx_provision_fops) {
-		fput(file);
+	if (f.file->f_op != &sgx_provision_fops) {
+		fdput(f);
 		return -EINVAL;
 	}
 
 	*allowed_attributes |= SGX_ATTR_PROVISIONKEY;
 
-	fput(file);
+	fdput(f);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(sgx_set_attribute);

From d2084fd84569fb7054c97ae6ffaf2755086fd267 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 14 May 2022 19:45:22 -0400
Subject: [PATCH 61/67] SVM-SEV: convert the rest of fget() uses to fdget() in
 there

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/x86/kvm/svm/sev.c | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index c25aeb550cd9..52398d49bc2f 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1767,18 +1767,20 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 {
 	struct kvm_sev_info *dst_sev = &to_kvm_svm(kvm)->sev_info;
 	struct kvm_sev_info *src_sev, *cg_cleanup_sev;
-	struct file *source_kvm_file;
+	struct fd f = fdget(source_fd);
 	struct kvm *source_kvm;
 	bool charged = false;
 	int ret;
 
-	source_kvm_file = fget(source_fd);
-	if (!file_is_kvm(source_kvm_file)) {
+	if (!f.file)
+		return -EBADF;
+
+	if (!file_is_kvm(f.file)) {
 		ret = -EBADF;
 		goto out_fput;
 	}
 
-	source_kvm = source_kvm_file->private_data;
+	source_kvm = f.file->private_data;
 	ret = sev_lock_two_vms(kvm, source_kvm);
 	if (ret)
 		goto out_fput;
@@ -1828,8 +1830,7 @@ out_dst_cgroup:
 out_unlock:
 	sev_unlock_two_vms(kvm, source_kvm);
 out_fput:
-	if (source_kvm_file)
-		fput(source_kvm_file);
+	fdput(f);
 	return ret;
 }
 
@@ -2046,18 +2047,20 @@ failed:
 
 int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 {
-	struct file *source_kvm_file;
+	struct fd f = fdget(source_fd);
 	struct kvm *source_kvm;
 	struct kvm_sev_info *source_sev, *mirror_sev;
 	int ret;
 
-	source_kvm_file = fget(source_fd);
-	if (!file_is_kvm(source_kvm_file)) {
+	if (!f.file)
+		return -EBADF;
+
+	if (!file_is_kvm(f.file)) {
 		ret = -EBADF;
 		goto e_source_fput;
 	}
 
-	source_kvm = source_kvm_file->private_data;
+	source_kvm = f.file->private_data;
 	ret = sev_lock_two_vms(kvm, source_kvm);
 	if (ret)
 		goto e_source_fput;
@@ -2103,8 +2106,7 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 e_unlock:
 	sev_unlock_two_vms(kvm, source_kvm);
 e_source_fput:
-	if (source_kvm_file)
-		fput(source_kvm_file);
+	fdput(f);
 	return ret;
 }
 

From 38e124086282715e3b9b3d193d9308bb3499b46c Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 15 May 2022 18:16:54 -0400
Subject: [PATCH 62/67] kill the last remaining user of proc_ns_fget()

lookups by descriptor are better off closer to syscall surface...

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/nsfs.c                | 18 ------------------
 include/linux/proc_ns.h  |  1 -
 net/core/net_namespace.c | 23 +++++++++++------------
 3 files changed, 11 insertions(+), 31 deletions(-)

diff --git a/fs/nsfs.c b/fs/nsfs.c
index f8df60b3b901..f602a96a1afe 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -235,24 +235,6 @@ bool proc_ns_file(const struct file *file)
 	return file->f_op == &ns_file_operations;
 }
 
-struct file *proc_ns_fget(int fd)
-{
-	struct file *file;
-
-	file = fget(fd);
-	if (!file)
-		return ERR_PTR(-EBADF);
-
-	if (file->f_op != &ns_file_operations)
-		goto out_invalid;
-
-	return file;
-
-out_invalid:
-	fput(file);
-	return ERR_PTR(-EINVAL);
-}
-
 /**
  * ns_match() - Returns true if current namespace matches dev/ino provided.
  * @ns: current namespace
diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index 75807ecef880..49539bc416ce 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -72,7 +72,6 @@ static inline int ns_alloc_inum(struct ns_common *ns)
 
 #define ns_free_inum(ns) proc_free_inum((ns)->inum)
 
-extern struct file *proc_ns_fget(int fd);
 #define get_proc_ns(inode) ((struct ns_common *)(inode)->i_private)
 extern int ns_get_path(struct path *path, struct task_struct *task,
 			const struct proc_ns_operations *ns_ops);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 7b69cf882b8e..3e3598cd49f2 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -20,6 +20,7 @@
 #include <linux/sched/task.h>
 #include <linux/uidgid.h>
 #include <linux/cookie.h>
+#include <linux/proc_fs.h>
 
 #include <net/sock.h>
 #include <net/netlink.h>
@@ -676,21 +677,19 @@ EXPORT_SYMBOL_GPL(get_net_ns);
 
 struct net *get_net_ns_by_fd(int fd)
 {
-	struct file *file;
-	struct ns_common *ns;
-	struct net *net;
+	struct fd f = fdget(fd);
+	struct net *net = ERR_PTR(-EINVAL);
 
-	file = proc_ns_fget(fd);
-	if (IS_ERR(file))
-		return ERR_CAST(file);
+	if (!f.file)
+		return ERR_PTR(-EBADF);
 
-	ns = get_proc_ns(file_inode(file));
-	if (ns->ops == &netns_operations)
-		net = get_net(container_of(ns, struct net, ns));
-	else
-		net = ERR_PTR(-EINVAL);
+	if (proc_ns_file(f.file)) {
+		struct ns_common *ns = get_proc_ns(file_inode(f.file));
+		if (ns->ops == &netns_operations)
+			net = get_net(container_of(ns, struct net, ns));
+	}
+	fdput(f);
 
-	fput(file);
 	return net;
 }
 EXPORT_SYMBOL_GPL(get_net_ns_by_fd);

From 96e85e95dc22d53650cbd499e963c70103c06738 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 6 Jun 2022 00:30:50 -0400
Subject: [PATCH 63/67] build_mount_idmapped(): switch to fdget()

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namespace.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index bc0f15257b49..d26ea0d9041f 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -4197,7 +4197,7 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize,
 	int err = 0;
 	struct ns_common *ns;
 	struct user_namespace *mnt_userns;
-	struct file *file;
+	struct fd f;
 
 	if (!((attr->attr_set | attr->attr_clr) & MOUNT_ATTR_IDMAP))
 		return 0;
@@ -4213,16 +4213,16 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize,
 	if (attr->userns_fd > INT_MAX)
 		return -EINVAL;
 
-	file = fget(attr->userns_fd);
-	if (!file)
+	f = fdget(attr->userns_fd);
+	if (!f.file)
 		return -EBADF;
 
-	if (!proc_ns_file(file)) {
+	if (!proc_ns_file(f.file)) {
 		err = -EINVAL;
 		goto out_fput;
 	}
 
-	ns = get_proc_ns(file_inode(file));
+	ns = get_proc_ns(file_inode(f.file));
 	if (ns->ops->type != CLONE_NEWUSER) {
 		err = -EINVAL;
 		goto out_fput;
@@ -4251,7 +4251,7 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize,
 	kattr->mnt_userns = get_user_ns(mnt_userns);
 
 out_fput:
-	fput(file);
+	fdput(f);
 	return err;
 }
 

From 1d0027dc9a3c2be501de625feca2eaac7f67b509 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 3 Aug 2022 20:13:33 -0400
Subject: [PATCH 64/67] bpf: switch to fdget_raw()

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 kernel/bpf/bpf_inode_storage.c | 38 ++++++++++++++--------------------
 1 file changed, 15 insertions(+), 23 deletions(-)

diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
index 05f4c66c9089..85720311cc67 100644
--- a/kernel/bpf/bpf_inode_storage.c
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -84,16 +84,13 @@ void bpf_inode_storage_free(struct inode *inode)
 static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_local_storage_data *sdata;
-	struct file *f;
-	int fd;
+	struct fd f = fdget_raw(*(int *)key);
 
-	fd = *(int *)key;
-	f = fget_raw(fd);
-	if (!f)
+	if (!f.file)
 		return ERR_PTR(-EBADF);
 
-	sdata = inode_storage_lookup(f->f_inode, map, true);
-	fput(f);
+	sdata = inode_storage_lookup(file_inode(f.file), map, true);
+	fdput(f);
 	return sdata ? sdata->data : NULL;
 }
 
@@ -101,22 +98,19 @@ static int bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key,
 					 void *value, u64 map_flags)
 {
 	struct bpf_local_storage_data *sdata;
-	struct file *f;
-	int fd;
+	struct fd f = fdget_raw(*(int *)key);
 
-	fd = *(int *)key;
-	f = fget_raw(fd);
-	if (!f)
+	if (!f.file)
 		return -EBADF;
-	if (!inode_storage_ptr(f->f_inode)) {
-		fput(f);
+	if (!inode_storage_ptr(file_inode(f.file))) {
+		fdput(f);
 		return -EBADF;
 	}
 
-	sdata = bpf_local_storage_update(f->f_inode,
+	sdata = bpf_local_storage_update(file_inode(f.file),
 					 (struct bpf_local_storage_map *)map,
 					 value, map_flags, GFP_ATOMIC);
-	fput(f);
+	fdput(f);
 	return PTR_ERR_OR_ZERO(sdata);
 }
 
@@ -135,16 +129,14 @@ static int inode_storage_delete(struct inode *inode, struct bpf_map *map)
 
 static int bpf_fd_inode_storage_delete_elem(struct bpf_map *map, void *key)
 {
-	struct file *f;
-	int fd, err;
+	struct fd f = fdget_raw(*(int *)key);
+	int err;
 
-	fd = *(int *)key;
-	f = fget_raw(fd);
-	if (!f)
+	if (!f.file)
 		return -EBADF;
 
-	err = inode_storage_delete(f->f_inode, map);
-	fput(f);
+	err = inode_storage_delete(file_inode(f.file), map);
+	fdput(f);
 	return err;
 }
 

From 2f31fa029d99f3614e76e3ea4f2e9832c13ba429 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 21 Aug 2022 12:01:26 -0400
Subject: [PATCH 65/67] cgroup_get_from_fd(): switch to fdget_raw()

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 kernel/cgroup/cgroup.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 935e8121b21e..4b249f81c693 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6856,14 +6856,12 @@ EXPORT_SYMBOL_GPL(cgroup_get_from_path);
 struct cgroup *cgroup_v1v2_get_from_fd(int fd)
 {
 	struct cgroup *cgrp;
-	struct file *f;
-
-	f = fget_raw(fd);
-	if (!f)
+	struct fd f = fdget_raw(fd);
+	if (!f.file)
 		return ERR_PTR(-EBADF);
 
-	cgrp = cgroup_v1v2_get_from_file(f);
-	fput(f);
+	cgrp = cgroup_v1v2_get_from_file(f.file);
+	fdput(f);
 	return cgrp;
 }
 

From 4a892c0fe4bb0546d68a89fa595bd22cb4be2576 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 21 Aug 2022 14:02:15 -0400
Subject: [PATCH 66/67] fuse_dev_ioctl(): switch to fdget()

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/fuse/dev.c | 37 +++++++++++++++++++------------------
 1 file changed, 19 insertions(+), 18 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index eb4f88e3dc97..1a8f82f478cb 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -2257,30 +2257,31 @@ static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
 	int res;
 	int oldfd;
 	struct fuse_dev *fud = NULL;
+	struct fd f;
 
 	switch (cmd) {
 	case FUSE_DEV_IOC_CLONE:
-		res = -EFAULT;
-		if (!get_user(oldfd, (__u32 __user *)arg)) {
-			struct file *old = fget(oldfd);
+		if (get_user(oldfd, (__u32 __user *)arg))
+			return -EFAULT;
 
-			res = -EINVAL;
-			if (old) {
-				/*
-				 * Check against file->f_op because CUSE
-				 * uses the same ioctl handler.
-				 */
-				if (old->f_op == file->f_op)
-					fud = fuse_get_dev(old);
+		f = fdget(oldfd);
+		if (!f.file)
+			return -EINVAL;
 
-				if (fud) {
-					mutex_lock(&fuse_mutex);
-					res = fuse_device_clone(fud->fc, file);
-					mutex_unlock(&fuse_mutex);
-				}
-				fput(old);
-			}
+		/*
+		 * Check against file->f_op because CUSE
+		 * uses the same ioctl handler.
+		 */
+		if (f.file->f_op == file->f_op)
+			fud = fuse_get_dev(f.file);
+
+		res = -EINVAL;
+		if (fud) {
+			mutex_lock(&fuse_mutex);
+			res = fuse_device_clone(fud->fc, file);
+			mutex_unlock(&fuse_mutex);
 		}
+		fdput(f);
 		break;
 	default:
 		res = -ENOTTY;

From aaee8c7f2a17d2dd015dc97c113c9ea0cc97272a Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Fri, 21 Apr 2023 09:11:49 +0200
Subject: [PATCH 67/67] m68k: kexec: Include <linux/reboot.h>

Include reboot.h in machine_kexec.c for declaration of
machine_crash_shutdown and machine_shutdown.

gcc-12 with W=1 reports:

 arch/m68k/kernel/machine_kexec.c:26:6: warning: no previous prototype for 'machine_shutdown' [-Wmissing-prototypes]
    26 | void machine_shutdown(void)
       |      ^~~~~~~~~~~~~~~~
 arch/m68k/kernel/machine_kexec.c:30:6: warning: no previous prototype for 'machine_crash_shutdown' [-Wmissing-prototypes]
    30 | void machine_crash_shutdown(struct pt_regs *regs)
       |      ^~~~~~~~~~~~~~~~~~~~~~

No functional changes intended.
Compile tested only.

Signed-off-by: Simon Horman <horms@kernel.org>
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Link: https://lore.kernel.org/r/20230421-m68k-kexec-include-reboot-v1-1-7552963a0f25@kernel.org
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
---
 arch/m68k/kernel/machine_kexec.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/m68k/kernel/machine_kexec.c b/arch/m68k/kernel/machine_kexec.c
index 206f84983120..739875540e89 100644
--- a/arch/m68k/kernel/machine_kexec.c
+++ b/arch/m68k/kernel/machine_kexec.c
@@ -6,6 +6,7 @@
 #include <linux/kexec.h>
 #include <linux/mm.h>
 #include <linux/delay.h>
+#include <linux/reboot.h>
 
 #include <asm/cacheflush.h>
 #include <asm/page.h>