Merge tag 'v6.6-vfs.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull misc vfs updates from Christian Brauner:
 "This contains the usual miscellaneous features, cleanups, and fixes
  for vfs and individual filesystems.

  Features:

   - Block mode changes on symlinks and rectify our broken semantics

   - Report file modifications via fsnotify() for splice

   - Allow specifying an explicit timeout for the "rootwait" kernel
     command line option. This allows to timeout and reboot instead of
     always waiting indefinitely for the root device to show up

   - Use synchronous fput for the close system call

  Cleanups:

   - Get rid of open-coded lockdep workarounds for async io submitters
     and replace it all with a single consolidated helper

   - Simplify epoll allocation helper

   - Convert simple_write_begin and simple_write_end to use a folio

   - Convert page_cache_pipe_buf_confirm() to use a folio

   - Simplify __range_close to avoid pointless locking

   - Disable per-cpu buffer head cache for isolated cpus

   - Port ecryptfs to kmap_local_page() api

   - Remove redundant initialization of pointer buf in pipe code

   - Unexport the d_genocide() function which is only used within core
     vfs

   - Replace printk(KERN_ERR) and WARN_ON() with WARN()

  Fixes:

   - Fix various kernel-doc issues

   - Fix refcount underflow for eventfds when used as EFD_SEMAPHORE

   - Fix a mainly theoretical issue in devpts

   - Check the return value of __getblk() in reiserfs

   - Fix a racy assert in i_readcount_dec

   - Fix integer conversion issues in various functions

   - Fix LSM security context handling during automounts that prevented
     NFS superblock sharing"

* tag 'v6.6-vfs.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (39 commits)
  cachefiles: use kiocb_{start,end}_write() helpers
  ovl: use kiocb_{start,end}_write() helpers
  aio: use kiocb_{start,end}_write() helpers
  io_uring: use kiocb_{start,end}_write() helpers
  fs: create kiocb_{start,end}_write() helpers
  fs: add kerneldoc to file_{start,end}_write() helpers
  io_uring: rename kiocb_end_write() local helper
  splice: Convert page_cache_pipe_buf_confirm() to use a folio
  libfs: Convert simple_write_begin and simple_write_end to use a folio
  fs/dcache: Replace printk and WARN_ON by WARN
  fs/pipe: remove redundant initialization of pointer buf
  fs: Fix kernel-doc warnings
  devpts: Fix kernel-doc warnings
  doc: idmappings: fix an error and rephrase a paragraph
  init: Add support for rootwait timeout parameter
  vfs: fix up the assert in i_readcount_dec
  fs: Fix one kernel-doc comment
  docs: filesystems: idmappings: clarify from where idmappings are taken
  fs/buffer.c: disable per-CPU buffer_head cache for isolated CPUs
  vfs, security: Fix automount superblock LSM init problem, preventing NFS sb sharing
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -5522,6 +5522,10 @@
 			Useful for devices that are detected asynchronously
 			(e.g. USB and MMC devices).
 
+	rootwait=	[KNL] Maximum time (in seconds) to wait for root device
+			to show up before attempting to mount the root
+			filesystem.
+
 	rproc_mem=nn[KMG][@address]
 			[KNL,ARM,CMA] Remoteproc physical memory block.
 			Memory area to be used by remote processor image,

Documentation/filesystems/idmappings.rst

@@ -146,9 +146,10 @@ For the rest of this document we will prefix all userspace ids with ``u`` and
 all kernel ids with ``k``. Ranges of idmappings will be prefixed with ``r``. So
 an idmapping will be written as ``u0:k10000:r10000``.
 
-For example, the id ``u1000`` is an id in the upper idmapset or "userspace
-idmapset" starting with ``u1000``. And it is mapped to ``k11000`` which is a
-kernel id in the lower idmapset or "kernel idmapset" starting with ``k10000``.
+For example, within this idmapping, the id ``u1000`` is an id in the upper
+idmapset or "userspace idmapset" starting with ``u0``. And it is mapped to
+``k11000`` which is a kernel id in the lower idmapset or "kernel idmapset"
+starting with ``k10000``.
 
 A kernel id is always created by an idmapping. Such idmappings are associated
 with user namespaces. Since we mainly care about how idmappings work we're not
@@ -373,6 +374,13 @@ kernel maps the caller's userspace id down into a kernel id according to the
 caller's idmapping and then maps that kernel id up according to the
 filesystem's idmapping.
 
+From the implementation point it's worth mentioning how idmappings are represented.
+All idmappings are taken from the corresponding user namespace.
+
+    - caller's idmapping (usually taken from ``current_user_ns()``)
+    - filesystem's idmapping (``sb->s_user_ns``)
+    - mount's idmapping (``mnt_idmap(vfsmnt)``)
+
 Let's see some examples with caller/filesystem idmapping but without mount
 idmappings. This will exhibit some problems we can hit. After that we will
 revisit/reconsider these examples, this time using mount idmappings, to see how

fs/aio.c

@@ -1447,13 +1447,8 @@ static void aio_complete_rw(struct kiocb *kiocb, long res)
 	if (kiocb->ki_flags & IOCB_WRITE) {
 		struct inode *inode = file_inode(kiocb->ki_filp);
 
-		/*
-		 * Tell lockdep we inherited freeze protection from submission
-		 * thread.
-		 */
 		if (S_ISREG(inode->i_mode))
-			__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
-		file_end_write(kiocb->ki_filp);
+			kiocb_end_write(kiocb);
 	}
 
 	iocb->ki_res.res = res;
@@ -1581,17 +1576,8 @@ static int aio_write(struct kiocb *req, const struct iocb *iocb,
 		return ret;
 	ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter));
 	if (!ret) {
-		/*
-		 * Open-code file_start_write here to grab freeze protection,
-		 * which will be released by another thread in
-		 * aio_complete_rw().  Fool lockdep by telling it the lock got
-		 * released so that it doesn't complain about the held lock when
-		 * we return to userspace.
-		 */
-		if (S_ISREG(file_inode(file)->i_mode)) {
-			sb_start_write(file_inode(file)->i_sb);
-			__sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
-		}
+		if (S_ISREG(file_inode(file)->i_mode))
+			kiocb_start_write(req);
 		req->ki_flags |= IOCB_WRITE;
 		aio_rw_done(req, call_write_iter(file, req, &iter));
 	}

fs/attr.c

@@ -394,9 +394,25 @@ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry,
 		return error;
 
 	if ((ia_valid & ATTR_MODE)) {
-		umode_t amode = attr->ia_mode;
+		/*
+		 * Don't allow changing the mode of symlinks:
+		 *
+		 * (1) The vfs doesn't take the mode of symlinks into account
+		 *     during permission checking.
+		 * (2) This has never worked correctly. Most major filesystems
+		 *     did return EOPNOTSUPP due to interactions with POSIX ACLs
+		 *     but did still updated the mode of the symlink.
+		 *     This inconsistency led system call wrapper providers such
+		 *     as libc to block changing the mode of symlinks with
+		 *     EOPNOTSUPP already.
+		 * (3) To even do this in the first place one would have to use
+		 *     specific file descriptors and quite some effort.
+		 */
+		if (S_ISLNK(inode->i_mode))
+			return -EOPNOTSUPP;
+
 		/* Flag setting protected by i_mutex */
-		if (is_sxid(amode))
+		if (is_sxid(attr->ia_mode))
 			inode->i_flags &= ~S_NOSEC;
 	}
 

fs/buffer.c

@@ -49,6 +49,7 @@
 #include <trace/events/block.h>
 #include <linux/fscrypt.h>
 #include <linux/fsverity.h>
+#include <linux/sched/isolation.h>
 
 #include "internal.h"
 
@@ -1352,7 +1353,7 @@ static void bh_lru_install(struct buffer_head *bh)
 	 * failing page migration.
 	 * Skip putting upcoming bh into bh_lru until migration is done.
 	 */
-	if (lru_cache_disabled()) {
+	if (lru_cache_disabled() || cpu_is_isolated(smp_processor_id())) {
 		bh_lru_unlock();
 		return;
 	}
@@ -1382,6 +1383,10 @@ lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size)
 
 	check_irqs_on();
 	bh_lru_lock();
+	if (cpu_is_isolated(smp_processor_id())) {
+		bh_lru_unlock();
+		return NULL;
+	}
 	for (i = 0; i < BH_LRU_SIZE; i++) {
 		struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]);
 

fs/cachefiles/io.c

@@ -259,9 +259,7 @@ static void cachefiles_write_complete(struct kiocb *iocb, long ret)
 
 	_enter("%ld", ret);
 
-	/* Tell lockdep we inherited freeze protection from submission thread */
-	__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
-	__sb_end_write(inode->i_sb, SB_FREEZE_WRITE);
+	kiocb_end_write(iocb);
 
 	if (ret < 0)
 		trace_cachefiles_io_error(object, inode, ret,
@@ -286,7 +284,6 @@ int __cachefiles_write(struct cachefiles_object *object,
 {
 	struct cachefiles_cache *cache;
 	struct cachefiles_kiocb *ki;
-	struct inode *inode;
 	unsigned int old_nofs;
 	ssize_t ret;
 	size_t len = iov_iter_count(iter);
@@ -322,19 +319,12 @@ int __cachefiles_write(struct cachefiles_object *object,
 		ki->iocb.ki_complete = cachefiles_write_complete;
 	atomic_long_add(ki->b_writing, &cache->b_writing);
 
-	/* Open-code file_start_write here to grab freeze protection, which
-	 * will be released by another thread in aio_complete_rw().  Fool
-	 * lockdep by telling it the lock got released so that it doesn't
-	 * complain about the held lock when we return to userspace.
-	 */
-	inode = file_inode(file);
-	__sb_start_write(inode->i_sb, SB_FREEZE_WRITE);
-	__sb_writers_release(inode->i_sb, SB_FREEZE_WRITE);
+	kiocb_start_write(&ki->iocb);
 
 	get_file(ki->iocb.ki_filp);
 	cachefiles_grab_object(object, cachefiles_obj_get_ioreq);
 
-	trace_cachefiles_write(object, inode, ki->iocb.ki_pos, len);
+	trace_cachefiles_write(object, file_inode(file), ki->iocb.ki_pos, len);
 	old_nofs = memalloc_nofs_save();
 	ret = cachefiles_inject_write_error();
 	if (ret == 0)

fs/dcache.c

@@ -1664,7 +1664,7 @@ static enum d_walk_ret umount_check(void *_data, struct dentry *dentry)
 	if (dentry == _data && dentry->d_lockref.count == 1)
 		return D_WALK_CONTINUE;
 
-	printk(KERN_ERR "BUG: Dentry %p{i=%lx,n=%pd} "
+	WARN(1, "BUG: Dentry %p{i=%lx,n=%pd} "
 			" still in use (%d) [unmount of %s %s]\n",
 		       dentry,
 		       dentry->d_inode ?
@@ -1673,7 +1673,6 @@ static enum d_walk_ret umount_check(void *_data, struct dentry *dentry)
 		       dentry->d_lockref.count,
 		       dentry->d_sb->s_type->name,
 		       dentry->d_sb->s_id);
-	WARN_ON(1);
 	return D_WALK_CONTINUE;
 }
 
@@ -3247,8 +3246,6 @@ void d_genocide(struct dentry *parent)
 	d_walk(parent, parent, d_genocide_kill);
 }
 
-EXPORT_SYMBOL(d_genocide);
-
 void d_tmpfile(struct file *file, struct inode *inode)
 {
 	struct dentry *dentry = file->f_path.dentry;

fs/devpts/inode.c

@@ -534,12 +534,12 @@ void devpts_kill_index(struct pts_fs_info *fsi, int idx)
 
 /**
  * devpts_pty_new -- create a new inode in /dev/pts/
- * @ptmx_inode: inode of the master
- * @device: major+minor of the node to be created
+ * @fsi: Filesystem info for this instance.
  * @index: used as a name of the node
  * @priv: what's given back by devpts_get_priv
  *
- * The created inode is returned. Remove it from /dev/pts/ by devpts_pty_kill.
+ * The dentry for the created inode is returned.
+ * Remove it from /dev/pts/ with devpts_pty_kill().
  */
 struct dentry *devpts_pty_new(struct pts_fs_info *fsi, int index, void *priv)
 {
@@ -580,7 +580,7 @@ struct dentry *devpts_pty_new(struct pts_fs_info *fsi, int index, void *priv)
 
 /**
  * devpts_get_priv -- get private data for a slave
- * @pts_inode: inode of the slave
+ * @dentry: dentry of the slave
  *
  * Returns whatever was passed as priv in devpts_pty_new for a given inode.
  */
@@ -593,7 +593,7 @@ void *devpts_get_priv(struct dentry *dentry)
 
 /**
  * devpts_pty_kill -- remove inode form /dev/pts/
- * @inode: inode of the slave to be removed
+ * @dentry: dentry of the slave to be removed
  *
  * This is an inverse operation of devpts_pty_new.
  */

fs/ecryptfs/crypto.c

@@ -441,10 +441,10 @@ int ecryptfs_encrypt_page(struct page *page)
 	}
 
 	lower_offset = lower_offset_for_page(crypt_stat, page);
-	enc_extent_virt = kmap(enc_extent_page);
+	enc_extent_virt = kmap_local_page(enc_extent_page);
 	rc = ecryptfs_write_lower(ecryptfs_inode, enc_extent_virt, lower_offset,
 				  PAGE_SIZE);
-	kunmap(enc_extent_page);
+	kunmap_local(enc_extent_virt);
 	if (rc < 0) {
 		ecryptfs_printk(KERN_ERR,
 			"Error attempting to write lower page; rc = [%d]\n",
@@ -490,10 +490,10 @@ int ecryptfs_decrypt_page(struct page *page)
 	BUG_ON(!(crypt_stat->flags & ECRYPTFS_ENCRYPTED));
 
 	lower_offset = lower_offset_for_page(crypt_stat, page);
-	page_virt = kmap(page);
+	page_virt = kmap_local_page(page);
 	rc = ecryptfs_read_lower(page_virt, lower_offset, PAGE_SIZE,
 				 ecryptfs_inode);
-	kunmap(page);
+	kunmap_local(page_virt);
 	if (rc < 0) {
 		ecryptfs_printk(KERN_ERR,
 			"Error attempting to read lower page; rc = [%d]\n",

fs/ecryptfs/mmap.c

@@ -125,7 +125,7 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
 			/* This is a header extent */
 			char *page_virt;
 
-			page_virt = kmap_atomic(page);
+			page_virt = kmap_local_page(page);
 			memset(page_virt, 0, PAGE_SIZE);
 			/* TODO: Support more than one header extent */
 			if (view_extent_num == 0) {
@@ -138,7 +138,7 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
 							       crypt_stat,
 							       &written);
 			}
-			kunmap_atomic(page_virt);
+			kunmap_local(page_virt);
 			flush_dcache_page(page);
 			if (rc) {
 				printk(KERN_ERR "%s: Error reading xattr "
@@ -255,7 +255,6 @@ out:
  * @mapping: The eCryptfs object
  * @pos: The file offset at which to start writing
  * @len: Length of the write
- * @flags: Various flags
  * @pagep: Pointer to return the page
  * @fsdata: Pointer to return fs data (unused)
  *

fs/ecryptfs/read_write.c

@@ -64,11 +64,11 @@ int ecryptfs_write_lower_page_segment(struct inode *ecryptfs_inode,
 
 	offset = ((((loff_t)page_for_lower->index) << PAGE_SHIFT)
 		  + offset_in_page);
-	virt = kmap(page_for_lower);
+	virt = kmap_local_page(page_for_lower);
 	rc = ecryptfs_write_lower(ecryptfs_inode, virt, offset, size);
 	if (rc > 0)
 		rc = 0;
-	kunmap(page_for_lower);
+	kunmap_local(virt);
 	return rc;
 }
 
@@ -140,7 +140,7 @@ int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset,
 			       ecryptfs_page_idx, rc);
 			goto out;
 		}
-		ecryptfs_page_virt = kmap_atomic(ecryptfs_page);
+		ecryptfs_page_virt = kmap_local_page(ecryptfs_page);
 
 		/*
 		 * pos: where we're now writing, offset: where the request was
@@ -163,7 +163,7 @@ int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset,
 			       (data + data_offset), num_bytes);
 			data_offset += num_bytes;
 		}
-		kunmap_atomic(ecryptfs_page_virt);
+		kunmap_local(ecryptfs_page_virt);
 		flush_dcache_page(ecryptfs_page);
 		SetPageUptodate(ecryptfs_page);
 		unlock_page(ecryptfs_page);
@@ -253,11 +253,11 @@ int ecryptfs_read_lower_page_segment(struct page *page_for_ecryptfs,
 	int rc;
 
 	offset = ((((loff_t)page_index) << PAGE_SHIFT) + offset_in_page);
-	virt = kmap(page_for_ecryptfs);
+	virt = kmap_local_page(page_for_ecryptfs);
 	rc = ecryptfs_read_lower(virt, offset, size, ecryptfs_inode);
 	if (rc > 0)
 		rc = 0;
-	kunmap(page_for_ecryptfs);
+	kunmap_local(virt);
 	flush_dcache_page(page_for_ecryptfs);
 	return rc;
 }

fs/eventfd.c

@@ -189,7 +189,7 @@ void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
 {
 	lockdep_assert_held(&ctx->wqh.lock);
 
-	*cnt = (ctx->flags & EFD_SEMAPHORE) ? 1 : ctx->count;
+	*cnt = ((ctx->flags & EFD_SEMAPHORE) && ctx->count) ? 1 : ctx->count;
 	ctx->count -= *cnt;
 }
 EXPORT_SYMBOL_GPL(eventfd_ctx_do_read);

fs/eventpoll.c

@@ -975,15 +975,11 @@ again:
 
 static int ep_alloc(struct eventpoll **pep)
 {
-	int error;
-	struct user_struct *user;
 	struct eventpoll *ep;
 
-	user = get_current_user();
-	error = -ENOMEM;
 	ep = kzalloc(sizeof(*ep), GFP_KERNEL);
 	if (unlikely(!ep))
-		goto free_uid;
+		return -ENOMEM;
 
 	mutex_init(&ep->mtx);
 	rwlock_init(&ep->lock);
@@ -992,16 +988,12 @@ static int ep_alloc(struct eventpoll **pep)
 	INIT_LIST_HEAD(&ep->rdllist);
 	ep->rbr = RB_ROOT_CACHED;
 	ep->ovflist = EP_UNACTIVE_PTR;
-	ep->user = user;
+	ep->user = get_current_user();
 	refcount_set(&ep->refcount, 1);
 
 	*pep = ep;
 
 	return 0;
-
-free_uid:
-	free_uid(user);
-	return error;
 }
 
 /*

fs/fcntl.c

@@ -34,7 +34,7 @@
 
 #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)
 
-static int setfl(int fd, struct file * filp, unsigned long arg)
+static int setfl(int fd, struct file * filp, unsigned int arg)
 {
 	struct inode * inode = file_inode(filp);
 	int error = 0;
@@ -112,11 +112,11 @@ void __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
 }
 EXPORT_SYMBOL(__f_setown);
 
-int f_setown(struct file *filp, unsigned long arg, int force)
+int f_setown(struct file *filp, int who, int force)
 {
 	enum pid_type type;
 	struct pid *pid = NULL;
-	int who = arg, ret = 0;
+	int ret = 0;
 
 	type = PIDTYPE_TGID;
 	if (who < 0) {
@@ -317,28 +317,29 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		struct file *filp)
 {
 	void __user *argp = (void __user *)arg;
+	int argi = (int)arg;
 	struct flock flock;
 	long err = -EINVAL;
 
 	switch (cmd) {
 	case F_DUPFD:
-		err = f_dupfd(arg, filp, 0);
+		err = f_dupfd(argi, filp, 0);
 		break;
 	case F_DUPFD_CLOEXEC:
-		err = f_dupfd(arg, filp, O_CLOEXEC);
+		err = f_dupfd(argi, filp, O_CLOEXEC);
 		break;
 	case F_GETFD:
 		err = get_close_on_exec(fd) ? FD_CLOEXEC : 0;
 		break;
 	case F_SETFD:
 		err = 0;
-		set_close_on_exec(fd, arg & FD_CLOEXEC);
+		set_close_on_exec(fd, argi & FD_CLOEXEC);
 		break;
 	case F_GETFL:
 		err = filp->f_flags;
 		break;
 	case F_SETFL:
-		err = setfl(fd, filp, arg);
+		err = setfl(fd, filp, argi);
 		break;
 #if BITS_PER_LONG != 32
 	/* 32-bit arches must use fcntl64() */
@@ -375,7 +376,7 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		force_successful_syscall_return();
 		break;
 	case F_SETOWN:
-		err = f_setown(filp, arg, 1);
+		err = f_setown(filp, argi, 1);
 		break;
 	case F_GETOWN_EX:
 		err = f_getown_ex(filp, arg);
@@ -391,28 +392,28 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		break;
 	case F_SETSIG:
 		/* arg == 0 restores default behaviour. */
-		if (!valid_signal(arg)) {
+		if (!valid_signal(argi)) {
 			break;
 		}
 		err = 0;
-		filp->f_owner.signum = arg;
+		filp->f_owner.signum = argi;
 		break;
 	case F_GETLEASE:
 		err = fcntl_getlease(filp);
 		break;
 	case F_SETLEASE:
-		err = fcntl_setlease(fd, filp, arg);
+		err = fcntl_setlease(fd, filp, argi);
 		break;
 	case F_NOTIFY:
-		err = fcntl_dirnotify(fd, filp, arg);
+		err = fcntl_dirnotify(fd, filp, argi);
 		break;
 	case F_SETPIPE_SZ:
 	case F_GETPIPE_SZ:
-		err = pipe_fcntl(filp, cmd, arg);
+		err = pipe_fcntl(filp, cmd, argi);
 		break;
 	case F_ADD_SEALS:
 	case F_GET_SEALS:
-		err = memfd_fcntl(filp, cmd, arg);
+		err = memfd_fcntl(filp, cmd, argi);
 		break;
 	case F_GET_RW_HINT:
 	case F_SET_RW_HINT:

fs/file.c

@@ -668,7 +668,7 @@ EXPORT_SYMBOL(close_fd); /* for ksys_close() */
 
 /**
  * last_fd - return last valid index into fd table
- * @cur_fds: files struct
+ * @fdt: File descriptor table.
  *
  * Context: Either rcu read lock or files_lock must be held.
  *
@@ -693,29 +693,30 @@ static inline void __range_cloexec(struct files_struct *cur_fds,
 	spin_unlock(&cur_fds->file_lock);
 }
 
-static inline void __range_close(struct files_struct *cur_fds, unsigned int fd,
+static inline void __range_close(struct files_struct *files, unsigned int fd,
 				 unsigned int max_fd)
 {
+	struct file *file;
 	unsigned n;
 
-	rcu_read_lock();
-	n = last_fd(files_fdtable(cur_fds));
-	rcu_read_unlock();
+	spin_lock(&files->file_lock);
+	n = last_fd(files_fdtable(files));
 	max_fd = min(max_fd, n);
 
-	while (fd <= max_fd) {
-		struct file *file;
-
-		spin_lock(&cur_fds->file_lock);
-		file = pick_file(cur_fds, fd++);
-		spin_unlock(&cur_fds->file_lock);
-
+	for (; fd <= max_fd; fd++) {
+		file = pick_file(files, fd);
 		if (file) {
-			/* found a valid file to close */
-			filp_close(file, cur_fds);
+			spin_unlock(&files->file_lock);
+			filp_close(file, files);
 			cond_resched();
+			spin_lock(&files->file_lock);
+		} else if (need_resched()) {
+			spin_unlock(&files->file_lock);
+			cond_resched();
+			spin_lock(&files->file_lock);
 		}
 	}
+	spin_unlock(&files->file_lock);
 }
 
 /**
@@ -723,6 +724,7 @@ static inline void __range_close(struct files_struct *cur_fds, unsigned int fd,
  *
  * @fd:     starting file descriptor to close
  * @max_fd: last file descriptor to close
+ * @flags:  CLOSE_RANGE flags.
  *
  * This closes a range of file descriptors. All file descriptors
  * from @fd up to and including @max_fd are closed.

fs/file_table.c

@@ -461,11 +461,8 @@ void fput(struct file *file)
  */
 void __fput_sync(struct file *file)
 {
-	if (atomic_long_dec_and_test(&file->f_count)) {
-		struct task_struct *task = current;
-		BUG_ON(!(task->flags & PF_KTHREAD));
+	if (atomic_long_dec_and_test(&file->f_count))
 		__fput(file);
-	}
 }
 
 EXPORT_SYMBOL(fput);

fs/fs_context.c

@@ -162,6 +162,10 @@ EXPORT_SYMBOL(vfs_parse_fs_param);
 
 /**
  * vfs_parse_fs_string - Convenience function to just parse a string.
+ * @fc: Filesystem context.
+ * @key: Parameter name.
+ * @value: Default value.
+ * @v_size: Maximum number of bytes in the value.
  */
 int vfs_parse_fs_string(struct fs_context *fc, const char *key,
 			const char *value, size_t v_size)
@@ -189,7 +193,7 @@ EXPORT_SYMBOL(vfs_parse_fs_string);
 
 /**
  * generic_parse_monolithic - Parse key[=val][,key[=val]]* mount data
- * @ctx: The superblock configuration to fill in.
+ * @fc: The superblock configuration to fill in.
  * @data: The data to parse
  *
  * Parse a blob of data that's in key[=val][,key[=val]]* form.  This can be
@@ -315,10 +319,31 @@ struct fs_context *fs_context_for_reconfigure(struct dentry *dentry,
 }
 EXPORT_SYMBOL(fs_context_for_reconfigure);
 
+/**
+ * fs_context_for_submount: allocate a new fs_context for a submount
+ * @type: file_system_type of the new context
+ * @reference: reference dentry from which to copy relevant info
+ *
+ * Allocate a new fs_context suitable for a submount. This also ensures that
+ * the fc->security object is inherited from @reference (if needed).
+ */
 struct fs_context *fs_context_for_submount(struct file_system_type *type,
 					   struct dentry *reference)
 {
-	return alloc_fs_context(type, reference, 0, 0, FS_CONTEXT_FOR_SUBMOUNT);
+	struct fs_context *fc;
+	int ret;
+
+	fc = alloc_fs_context(type, reference, 0, 0, FS_CONTEXT_FOR_SUBMOUNT);
+	if (IS_ERR(fc))
+		return fc;
+
+	ret = security_fs_context_submount(fc, reference->d_sb);
+	if (ret) {
+		put_fs_context(fc);
+		return ERR_PTR(ret);
+	}
+
+	return fc;
 }
 EXPORT_SYMBOL(fs_context_for_submount);
 
@@ -333,7 +358,7 @@ void fc_drop_locked(struct fs_context *fc)
 static void legacy_fs_context_free(struct fs_context *fc);
 
 /**
- * vfs_dup_fc_config: Duplicate a filesystem context.
+ * vfs_dup_fs_context - Duplicate a filesystem context.
  * @src_fc: The context to copy.
  */
 struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc)
@@ -379,7 +404,9 @@ EXPORT_SYMBOL(vfs_dup_fs_context);
 
 /**
  * logfc - Log a message to a filesystem context
- * @fc: The filesystem context to log to.
+ * @log: The filesystem context to log to, or NULL to use printk.
+ * @prefix: A string to prefix the output with, or NULL.
+ * @level: 'w' for a warning, 'e' for an error.  Anything else is a notice.
  * @fmt: The format of the buffer.
  */
 void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, ...)

fs/ioctl.c

@@ -109,9 +109,6 @@ static int ioctl_fibmap(struct file *filp, int __user *p)
  * Returns 0 on success, -errno on error, 1 if this was the last
  * extent that will fit in user array.
  */
-#define SET_UNKNOWN_FLAGS	(FIEMAP_EXTENT_DELALLOC)
-#define SET_NO_UNMOUNTED_IO_FLAGS	(FIEMAP_EXTENT_DATA_ENCRYPTED)
-#define SET_NOT_ALIGNED_FLAGS	(FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE)
 int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical,
 			    u64 phys, u64 len, u32 flags)
 {
@@ -127,6 +124,10 @@ int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical,
 	if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max)
 		return 1;
 
+#define SET_UNKNOWN_FLAGS	(FIEMAP_EXTENT_DELALLOC)
+#define SET_NO_UNMOUNTED_IO_FLAGS	(FIEMAP_EXTENT_DATA_ENCRYPTED)
+#define SET_NOT_ALIGNED_FLAGS	(FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE)
+
 	if (flags & SET_UNKNOWN_FLAGS)
 		flags |= FIEMAP_EXTENT_UNKNOWN;
 	if (flags & SET_NO_UNMOUNTED_IO_FLAGS)
@@ -877,6 +878,9 @@ out:
 #ifdef CONFIG_COMPAT
 /**
  * compat_ptr_ioctl - generic implementation of .compat_ioctl file operation
+ * @file: The file to operate on.
+ * @cmd: The ioctl command number.
+ * @arg: The argument to the ioctl.
  *
  * This is not normally called as a function, but instead set in struct
  * file_operations as

fs/kernel_read_file.c

@@ -8,16 +8,16 @@
 /**
  * kernel_read_file() - read file contents into a kernel buffer
  *
- * @file	file to read from
- * @offset	where to start reading from (see below).
- * @buf		pointer to a "void *" buffer for reading into (if
+ * @file:	file to read from
+ * @offset:	where to start reading from (see below).
+ * @buf:	pointer to a "void *" buffer for reading into (if
  *		*@buf is NULL, a buffer will be allocated, and
  *		@buf_size will be ignored)
- * @buf_size	size of buf, if already allocated. If @buf not
+ * @buf_size:	size of buf, if already allocated. If @buf not
  *		allocated, this is the largest size to allocate.
- * @file_size	if non-NULL, the full size of @file will be
+ * @file_size:	if non-NULL, the full size of @file will be
  *		written here.
- * @id		the kernel_read_file_id identifying the type of
+ * @id:		the kernel_read_file_id identifying the type of
  *		file contents being read (for LSMs to examine)
  *
  * @offset must be 0 unless both @buf and @file_size are non-NULL

fs/libfs.c

@@ -815,21 +815,20 @@ int simple_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
-	struct page *page;
-	pgoff_t index;
+	struct folio *folio;
 
-	index = pos >> PAGE_SHIFT;
+	folio = __filemap_get_folio(mapping, pos / PAGE_SIZE, FGP_WRITEBEGIN,
+			mapping_gfp_mask(mapping));
+	if (IS_ERR(folio))
+		return PTR_ERR(folio);
 
-	page = grab_cache_page_write_begin(mapping, index);
-	if (!page)
-		return -ENOMEM;
+	*pagep = &folio->page;
 
-	*pagep = page;
+	if (!folio_test_uptodate(folio) && (len != folio_size(folio))) {
+		size_t from = offset_in_folio(folio, pos);
 
-	if (!PageUptodate(page) && (len != PAGE_SIZE)) {
-		unsigned from = pos & (PAGE_SIZE - 1);
-
-		zero_user_segments(page, 0, from, from + len, PAGE_SIZE);
+		folio_zero_segments(folio, 0, from,
+				from + len, folio_size(folio));
 	}
 	return 0;
 }
@@ -861,17 +860,18 @@ static int simple_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct page *page, void *fsdata)
 {
-	struct inode *inode = page->mapping->host;
+	struct folio *folio = page_folio(page);
+	struct inode *inode = folio->mapping->host;
 	loff_t last_pos = pos + copied;
 
-	/* zero the stale part of the page if we did a short copy */
-	if (!PageUptodate(page)) {
+	/* zero the stale part of the folio if we did a short copy */
+	if (!folio_test_uptodate(folio)) {
 		if (copied < len) {
-			unsigned from = pos & (PAGE_SIZE - 1);
+			size_t from = offset_in_folio(folio, pos);
 
-			zero_user(page, from + copied, len - copied);
+			folio_zero_range(folio, from + copied, len - copied);
 		}
-		SetPageUptodate(page);
+		folio_mark_uptodate(folio);
 	}
 	/*
 	 * No need to use i_size_read() here, the i_size
@@ -880,9 +880,9 @@ static int simple_write_end(struct file *file, struct address_space *mapping,
 	if (last_pos > inode->i_size)
 		i_size_write(inode, last_pos);
 
-	set_page_dirty(page);
-	unlock_page(page);
-	put_page(page);
+	folio_mark_dirty(folio);
+	folio_unlock(folio);
+	folio_put(folio);
 
 	return copied;
 }
@@ -1536,7 +1536,7 @@ EXPORT_SYMBOL(alloc_anon_inode);
  * All arguments are ignored and it just returns -EINVAL.
  */
 int
-simple_nosetlease(struct file *filp, long arg, struct file_lock **flp,
+simple_nosetlease(struct file *filp, int arg, struct file_lock **flp,
 		  void **priv)
 {
 	return -EINVAL;