Merge tag 'vfs-6.18-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull misc vfs updates from Christian Brauner:
 "This contains the usual selections of misc updates for this cycle.

  Features:

   - Add "initramfs_options" parameter to set initramfs mount options.
     This allows to add specific mount options to the rootfs to e.g.,
     limit the memory size

   - Add RWF_NOSIGNAL flag for pwritev2()

     Add RWF_NOSIGNAL flag for pwritev2. This flag prevents the SIGPIPE
     signal from being raised when writing on disconnected pipes or
     sockets. The flag is handled directly by the pipe filesystem and
     converted to the existing MSG_NOSIGNAL flag for sockets

   - Allow to pass pid namespace as procfs mount option

     Ever since the introduction of pid namespaces, procfs has had very
     implicit behaviour surrounding them (the pidns used by a procfs
     mount is auto-selected based on the mounting process's active
     pidns, and the pidns itself is basically hidden once the mount has
     been constructed)

     This implicit behaviour has historically meant that userspace was
     required to do some special dances in order to configure the pidns
     of a procfs mount as desired. Examples include:

     * In order to bypass the mnt_too_revealing() check, Kubernetes
       creates a procfs mount from an empty pidns so that user
       namespaced containers can be nested (without this, the nested
       containers would fail to mount procfs)

       But this requires forking off a helper process because you cannot
       just one-shot this using mount(2)

     * Container runtimes in general need to fork into a container
       before configuring its mounts, which can lead to security issues
       in the case of shared-pidns containers (a privileged process in
       the pidns can interact with your container runtime process)

       While SUID_DUMP_DISABLE and user namespaces make this less of an
       issue, the strict need for this due to a minor uAPI wart is kind
       of unfortunate

       Things would be much easier if there was a way for userspace to
       just specify the pidns they want. So this pull request contains
       changes to implement a new "pidns" argument which can be set
       using fsconfig(2):

           fsconfig(procfd, FSCONFIG_SET_FD, "pidns", NULL, nsfd);
           fsconfig(procfd, FSCONFIG_SET_STRING, "pidns", "/proc/self/ns/pid", 0);

       or classic mount(2) / mount(8):

           // mount -t proc -o pidns=/proc/self/ns/pid proc /tmp/proc
           mount("proc", "/tmp/proc", "proc", MS_..., "pidns=/proc/self/ns/pid");

  Cleanups:

   - Remove the last references to EXPORT_OP_ASYNC_LOCK

   - Make file_remove_privs_flags() static

   - Remove redundant __GFP_NOWARN when GFP_NOWAIT is used

   - Use try_cmpxchg() in start_dir_add()

   - Use try_cmpxchg() in sb_init_done_wq()

   - Replace offsetof() with struct_size() in ioctl_file_dedupe_range()

   - Remove vfs_ioctl() export

   - Replace rwlock() with spinlock in epoll code as rwlock causes
     priority inversion on preempt rt kernels

   - Make ns_entries in fs/proc/namespaces const

   - Use a switch() statement() in init_special_inode() just like we do
     in may_open()

   - Use struct_size() in dir_add() in the initramfs code

   - Use str_plural() in rd_load_image()

   - Replace strcpy() with strscpy() in find_link()

   - Rename generic_delete_inode() to inode_just_drop() and
     generic_drop_inode() to inode_generic_drop()

   - Remove unused arguments from fcntl_{g,s}et_rw_hint()

  Fixes:

   - Document @name parameter for name_contains_dotdot() helper

   - Fix spelling mistake

   - Always return zero from replace_fd() instead of the file descriptor
     number

   - Limit the size for copy_file_range() in compat mode to prevent a
     signed overflow

   - Fix debugfs mount options not being applied

   - Verify the inode mode when loading it from disk in minixfs

   - Verify the inode mode when loading it from disk in cramfs

   - Don't trigger automounts with RESOLVE_NO_XDEV

     If openat2() was called with RESOLVE_NO_XDEV it didn't traverse
     through automounts, but could still trigger them

   - Add FL_RECLAIM flag to show_fl_flags() macro so it appears in
     tracepoints

   - Fix unused variable warning in rd_load_image() on s390

   - Make INITRAMFS_PRESERVE_MTIME depend on BLK_DEV_INITRD

   - Use ns_capable_noaudit() when determining net sysctl permissions

   - Don't call path_put() under namespace semaphore in listmount() and
     statmount()"

* tag 'vfs-6.18-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (38 commits)
  fcntl: trim arguments
  listmount: don't call path_put() under namespace semaphore
  statmount: don't call path_put() under namespace semaphore
  pid: use ns_capable_noaudit() when determining net sysctl permissions
  fs: rename generic_delete_inode() and generic_drop_inode()
  init: INITRAMFS_PRESERVE_MTIME should depend on BLK_DEV_INITRD
  initramfs: Replace strcpy() with strscpy() in find_link()
  initrd: Use str_plural() in rd_load_image()
  initramfs: Use struct_size() helper to improve dir_add()
  initrd: Fix unused variable warning in rd_load_image() on s390
  fs: use the switch statement in init_special_inode()
  fs/proc/namespaces: make ns_entries const
  filelock: add FL_RECLAIM to show_fl_flags() macro
  eventpoll: Replace rwlock with spinlock
  selftests/proc: add tests for new pidns APIs
  procfs: add "pidns" mount option
  pidns: move is-ancestor logic to helper
  openat2: don't trigger automounts with RESOLVE_NO_XDEV
  namei: move cross-device check to __traverse_mounts
  namei: remove LOOKUP_NO_XDEV check from handle_mounts
  ...

40 files changed, 300 insertions, 226 deletions

diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 795c6388744c..1581ebac5bb4 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -252,7 +252,7 @@ static int v9fs_drop_inode(struct inode *inode)
 
 	v9ses = v9fs_inode2v9ses(inode);
 	if (v9ses->cache & (CACHE_META|CACHE_LOOSE))
-		return generic_drop_inode(inode);
+		return inode_generic_drop(inode);
 	/*
 	 * in case of non cached mode always drop the
 	 * inode because we want the inode attribute
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index e9538e91f848..e1cb17b85791 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -723,9 +723,9 @@ int afs_drop_inode(struct inode *inode)
 	_enter("");
 
 	if (test_bit(AFS_VNODE_PSEUDODIR, &AFS_FS_I(inode)->flags))
-		return generic_delete_inode(inode);
+		return inode_just_drop(inode);
 	else
-		return generic_drop_inode(inode);
+		return inode_generic_drop(inode);
 }
 
 /*
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 18db1053cdf0..3923be975e47 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7973,7 +7973,7 @@ int btrfs_drop_inode(struct inode *inode)
 	if (btrfs_root_refs(&root->root_item) == 0)
 		return 1;
 	else
-		return generic_drop_inode(inode);
+		return inode_generic_drop(inode);
 }
 
 static void init_once(void *foo)
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index c3eb651862c5..70dc9467f6a0 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -1042,7 +1042,7 @@ static const struct super_operations ceph_super_ops = {
 	.alloc_inode	= ceph_alloc_inode,
 	.free_inode	= ceph_free_inode,
 	.write_inode    = ceph_write_inode,
-	.drop_inode	= generic_delete_inode,
+	.drop_inode	= inode_just_drop,
 	.evict_inode	= ceph_evict_inode,
 	.sync_fs        = ceph_sync_fs,
 	.put_super	= ceph_put_super,
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index 740f18b60c9d..456c4a2efb53 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -36,7 +36,7 @@ static void configfs_free_inode(struct inode *inode)
 
 static const struct super_operations configfs_ops = {
 	.statfs		= simple_statfs,
-	.drop_inode	= generic_delete_inode,
+	.drop_inode	= inode_just_drop,
 	.free_inode	= configfs_free_inode,
 };
 
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index b002e9b734f9..12daa85ed941 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -116,9 +116,18 @@ static struct inode *get_cramfs_inode(struct super_block *sb,
 		inode_nohighmem(inode);
 		inode->i_data.a_ops = &cramfs_aops;
 		break;
-	default:
+	case S_IFCHR:
+	case S_IFBLK:
+	case S_IFIFO:
+	case S_IFSOCK:
 		init_special_inode(inode, cramfs_inode->mode,
 				old_decode_dev(cramfs_inode->size));
+		break;
+	default:
+		printk(KERN_DEBUG "CRAMFS: Invalid file type 0%04o for inode %lu.\n",
+		       inode->i_mode, inode->i_ino);
+		iget_failed(inode);
+		return ERR_PTR(-EIO);
 	}
 
 	inode->i_mode = cramfs_inode->mode;
diff --git a/fs/dcache.c b/fs/dcache.c
index 60046ae23d51..336bdb4c4b1f 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2509,8 +2509,8 @@ static inline unsigned start_dir_add(struct inode *dir)
 {
 	preempt_disable_nested();
 	for (;;) {
-		unsigned n = dir->i_dir_seq;
-		if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n)
+		unsigned n = READ_ONCE(dir->i_dir_seq);
+		if (!(n & 1) && try_cmpxchg(&dir->i_dir_seq, &n, n + 1))
 			return n;
 		cpu_relax();
 	}
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 4bb4002e3cdf..1f4d8ce56667 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -127,7 +127,7 @@ static int efivarfs_unfreeze_fs(struct super_block *sb);
 
 static const struct super_operations efivarfs_ops = {
 	.statfs = efivarfs_statfs,
-	.drop_inode = generic_delete_inode,
+	.drop_inode = inode_just_drop,
 	.alloc_inode = efivarfs_alloc_inode,
 	.free_inode = efivarfs_free_inode,
 	.show_options = efivarfs_show_options,
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index b22d6f819f78..ee7c4b683ec3 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -46,10 +46,10 @@
  *
  * 1) epnested_mutex (mutex)
  * 2) ep->mtx (mutex)
- * 3) ep->lock (rwlock)
+ * 3) ep->lock (spinlock)
  *
  * The acquire order is the one listed above, from 1 to 3.
- * We need a rwlock (ep->lock) because we manipulate objects
+ * We need a spinlock (ep->lock) because we manipulate objects
  * from inside the poll callback, that might be triggered from
  * a wake_up() that in turn might be called from IRQ context.
  * So we can't sleep inside the poll callback and hence we need
@@ -195,7 +195,7 @@ struct eventpoll {
 	struct list_head rdllist;
 
 	/* Lock which protects rdllist and ovflist */
-	rwlock_t lock;
+	spinlock_t lock;
 
 	/* RB tree root used to store monitored fd structs */
 	struct rb_root_cached rbr;
@@ -741,10 +741,10 @@ static void ep_start_scan(struct eventpoll *ep, struct list_head *txlist)
 	 * in a lockless way.
 	 */
 	lockdep_assert_irqs_enabled();
-	write_lock_irq(&ep->lock);
+	spin_lock_irq(&ep->lock);
 	list_splice_init(&ep->rdllist, txlist);
 	WRITE_ONCE(ep->ovflist, NULL);
-	write_unlock_irq(&ep->lock);
+	spin_unlock_irq(&ep->lock);
 }
 
 static void ep_done_scan(struct eventpoll *ep,
@@ -752,7 +752,7 @@ static void ep_done_scan(struct eventpoll *ep,
 {
 	struct epitem *epi, *nepi;
 
-	write_lock_irq(&ep->lock);
+	spin_lock_irq(&ep->lock);
 	/*
 	 * During the time we spent inside the "sproc" callback, some
 	 * other events might have been queued by the poll callback.
@@ -793,7 +793,7 @@ static void ep_done_scan(struct eventpoll *ep,
 			wake_up(&ep->wq);
 	}
 
-	write_unlock_irq(&ep->lock);
+	spin_unlock_irq(&ep->lock);
 }
 
 static void ep_get(struct eventpoll *ep)
@@ -868,10 +868,10 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
 
 	rb_erase_cached(&epi->rbn, &ep->rbr);
 
-	write_lock_irq(&ep->lock);
+	spin_lock_irq(&ep->lock);
 	if (ep_is_linked(epi))
 		list_del_init(&epi->rdllink);
-	write_unlock_irq(&ep->lock);
+	spin_unlock_irq(&ep->lock);
 
 	wakeup_source_unregister(ep_wakeup_source(epi));
 	/*
@@ -1152,7 +1152,7 @@ static int ep_alloc(struct eventpoll **pep)
 		return -ENOMEM;
 
 	mutex_init(&ep->mtx);
-	rwlock_init(&ep->lock);
+	spin_lock_init(&ep->lock);
 	init_waitqueue_head(&ep->wq);
 	init_waitqueue_head(&ep->poll_wait);
 	INIT_LIST_HEAD(&ep->rdllist);
@@ -1240,99 +1240,9 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd,
 #endif /* CONFIG_KCMP */
 
 /*
- * Adds a new entry to the tail of the list in a lockless way, i.e.
- * multiple CPUs are allowed to call this function concurrently.
- *
- * Beware: it is necessary to prevent any other modifications of the
- *         existing list until all changes are completed, in other words
- *         concurrent list_add_tail_lockless() calls should be protected
- *         with a read lock, where write lock acts as a barrier which
- *         makes sure all list_add_tail_lockless() calls are fully
- *         completed.
- *
- *        Also an element can be locklessly added to the list only in one
- *        direction i.e. either to the tail or to the head, otherwise
- *        concurrent access will corrupt the list.
- *
- * Return: %false if element has been already added to the list, %true
- * otherwise.
- */
-static inline bool list_add_tail_lockless(struct list_head *new,
-					  struct list_head *head)
-{
-	struct list_head *prev;
-
-	/*
-	 * This is simple 'new->next = head' operation, but cmpxchg()
-	 * is used in order to detect that same element has been just
-	 * added to the list from another CPU: the winner observes
-	 * new->next == new.
-	 */
-	if (!try_cmpxchg(&new->next, &new, head))
-		return false;
-
-	/*
-	 * Initially ->next of a new element must be updated with the head
-	 * (we are inserting to the tail) and only then pointers are atomically
-	 * exchanged.  XCHG guarantees memory ordering, thus ->next should be
-	 * updated before pointers are actually swapped and pointers are
-	 * swapped before prev->next is updated.
-	 */
-
-	prev = xchg(&head->prev, new);
-
-	/*
-	 * It is safe to modify prev->next and new->prev, because a new element
-	 * is added only to the tail and new->next is updated before XCHG.
-	 */
-
-	prev->next = new;
-	new->prev = prev;
-
-	return true;
-}
-
-/*
- * Chains a new epi entry to the tail of the ep->ovflist in a lockless way,
- * i.e. multiple CPUs are allowed to call this function concurrently.
- *
- * Return: %false if epi element has been already chained, %true otherwise.
- */
-static inline bool chain_epi_lockless(struct epitem *epi)
-{
-	struct eventpoll *ep = epi->ep;
-
-	/* Fast preliminary check */
-	if (epi->next != EP_UNACTIVE_PTR)
-		return false;
-
-	/* Check that the same epi has not been just chained from another CPU */
-	if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR)
-		return false;
-
-	/* Atomically exchange tail */
-	epi->next = xchg(&ep->ovflist, epi);
-
-	return true;
-}
-
-/*
  * This is the callback that is passed to the wait queue wakeup
  * mechanism. It is called by the stored file descriptors when they
  * have events to report.
- *
- * This callback takes a read lock in order not to contend with concurrent
- * events from another file descriptor, thus all modifications to ->rdllist
- * or ->ovflist are lockless.  Read lock is paired with the write lock from
- * ep_start/done_scan(), which stops all list modifications and guarantees
- * that lists state is seen correctly.
- *
- * Another thing worth to mention is that ep_poll_callback() can be called
- * concurrently for the same @epi from different CPUs if poll table was inited
- * with several wait queues entries.  Plural wakeup from different CPUs of a
- * single wait queue is serialized by wq.lock, but the case when multiple wait
- * queues are used should be detected accordingly.  This is detected using
- * cmpxchg() operation.
  */
 static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 {
@@ -1343,7 +1253,7 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
 	unsigned long flags;
 	int ewake = 0;
 
-	read_lock_irqsave(&ep->lock, flags);
+	spin_lock_irqsave(&ep->lock, flags);
 
 	ep_set_busy_poll_napi_id(epi);
 
@@ -1372,12 +1282,15 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
 	 * chained in ep->ovflist and requeued later on.
 	 */
 	if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) {
-		if (chain_epi_lockless(epi))
+		if (epi->next == EP_UNACTIVE_PTR) {
+			epi->next = READ_ONCE(ep->ovflist);
+			WRITE_ONCE(ep->ovflist, epi);
 			ep_pm_stay_awake_rcu(epi);
+		}
 	} else if (!ep_is_linked(epi)) {
 		/* In the usual case, add event to ready list. */
-		if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist))
-			ep_pm_stay_awake_rcu(epi);
+		list_add_tail(&epi->rdllink, &ep->rdllist);
+		ep_pm_stay_awake_rcu(epi);
 	}
 
 	/*
@@ -1410,7 +1323,7 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
 		pwake++;
 
 out_unlock:
-	read_unlock_irqrestore(&ep->lock, flags);
+	spin_unlock_irqrestore(&ep->lock, flags);
 
 	/* We have to call this outside the lock */
 	if (pwake)
@@ -1745,7 +1658,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 	}
 
 	/* We have to drop the new item inside our item list to keep track of it */
-	write_lock_irq(&ep->lock);
+	spin_lock_irq(&ep->lock);
 
 	/* record NAPI ID of new item if present */
 	ep_set_busy_poll_napi_id(epi);
@@ -1762,7 +1675,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 			pwake++;
 	}
 
-	write_unlock_irq(&ep->lock);
+	spin_unlock_irq(&ep->lock);
 
 	/* We have to call this outside the lock */
 	if (pwake)
@@ -1826,7 +1739,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi,
 	 * list, push it inside.
 	 */
 	if (ep_item_poll(epi, &pt, 1)) {
-		write_lock_irq(&ep->lock);
+		spin_lock_irq(&ep->lock);
 		if (!ep_is_linked(epi)) {
 			list_add_tail(&epi->rdllink, &ep->rdllist);
 			ep_pm_stay_awake(epi);
@@ -1837,7 +1750,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi,
 			if (waitqueue_active(&ep->poll_wait))
 				pwake++;
 		}
-		write_unlock_irq(&ep->lock);
+		spin_unlock_irq(&ep->lock);
 	}
 
 	/* We have to call this outside the lock */
@@ -2089,7 +2002,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		init_wait(&wait);
 		wait.func = ep_autoremove_wake_function;
 
-		write_lock_irq(&ep->lock);
+		spin_lock_irq(&ep->lock);
 		/*
 		 * Barrierless variant, waitqueue_active() is called under
 		 * the same lock on wakeup ep_poll_callback() side, so it
@@ -2108,7 +2021,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		if (!eavail)
 			__add_wait_queue_exclusive(&ep->wq, &wait);
 
-		write_unlock_irq(&ep->lock);
+		spin_unlock_irq(&ep->lock);
 
 		if (!eavail)
 			timed_out = !ep_schedule_timeout(to) ||
@@ -2124,7 +2037,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		eavail = 1;
 
 		if (!list_empty_careful(&wait.entry)) {
-			write_lock_irq(&ep->lock);
+			spin_lock_irq(&ep->lock);
 			/*
 			 * If the thread timed out and is not on the wait queue,
 			 * it means that the thread was woken up after its
@@ -2135,7 +2048,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 			if (timed_out)
 				eavail = list_empty(&wait.entry);
 			__remove_wait_queue(&ep->wq, &wait);
-			write_unlock_irq(&ep->lock);
+			spin_unlock_irq(&ep->lock);
 		}
 	}
 }
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 699c15db28a8..caac4067f777 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1417,7 +1417,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 
 static int ext4_drop_inode(struct inode *inode)
 {
-	int drop = generic_drop_inode(inode);
+	int drop = inode_generic_drop(inode);
 
 	if (!drop)
 		drop = fscrypt_drop_inode(inode);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index e16c4e2830c2..63cf73409da6 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1768,7 +1768,7 @@ static int f2fs_drop_inode(struct inode *inode)
 		trace_f2fs_drop_inode(inode, 0);
 		return 0;
 	}
-	ret = generic_drop_inode(inode);
+	ret = inode_generic_drop(inode);
 	if (!ret)
 		ret = fscrypt_drop_inode(inode);
 	trace_f2fs_drop_inode(inode, ret);
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 5598e4d57422..72f8433d9109 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -355,8 +355,7 @@ static bool rw_hint_valid(u64 hint)
 	}
 }
 
-static long fcntl_get_rw_hint(struct file *file, unsigned int cmd,
-			      unsigned long arg)
+static long fcntl_get_rw_hint(struct file *file, unsigned long arg)
 {
 	struct inode *inode = file_inode(file);
 	u64 __user *argp = (u64 __user *)arg;
@@ -367,8 +366,7 @@ static long fcntl_get_rw_hint(struct file *file, unsigned int cmd,
 	return 0;
 }
 
-static long fcntl_set_rw_hint(struct file *file, unsigned int cmd,
-			      unsigned long arg)
+static long fcntl_set_rw_hint(struct file *file, unsigned long arg)
 {
 	struct inode *inode = file_inode(file);
 	u64 __user *argp = (u64 __user *)arg;
@@ -547,10 +545,10 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		err = memfd_fcntl(filp, cmd, argi);
 		break;
 	case F_GET_RW_HINT:
-		err = fcntl_get_rw_hint(filp, cmd, arg);
+		err = fcntl_get_rw_hint(filp, arg);
 		break;
 	case F_SET_RW_HINT:
-		err = fcntl_set_rw_hint(filp, cmd, arg);
+		err = fcntl_set_rw_hint(filp, arg);
 		break;
 	default:
 		break;
diff --git a/fs/file.c b/fs/file.c
index 6d2275c3be9c..28743b742e3c 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -1330,7 +1330,10 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags)
 	err = expand_files(files, fd);
 	if (unlikely(err < 0))
 		goto out_unlock;
-	return do_dup2(files, file, fd, flags);
+	err = do_dup2(files, file, fd, flags);
+	if (err < 0)
+		return err;
+	return 0;
 
 out_unlock:
 	spin_unlock(&files->file_lock);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index a07b8cf73ae2..a6cc3d305b84 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1123,7 +1123,7 @@ int cgroup_writeback_by_id(u64 bdi_id, int memcg_id,
 	dirty = dirty * 10 / 8;
 
 	/* issue the writeback work */
-	work = kzalloc(sizeof(*work), GFP_NOWAIT | __GFP_NOWARN);
+	work = kzalloc(sizeof(*work), GFP_NOWAIT);
 	if (work) {
 		work->nr_pages = dirty;
 		work->sync_mode = WB_SYNC_NONE;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 7ddfd2b3cc9c..fdecd5a90dee 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1209,7 +1209,7 @@ static const struct super_operations fuse_super_operations = {
 	.free_inode     = fuse_free_inode,
 	.evict_inode	= fuse_evict_inode,
 	.write_inode	= fuse_write_inode,
-	.drop_inode	= generic_delete_inode,
+	.drop_inode	= inode_just_drop,
 	.umount_begin	= fuse_umount_begin,
 	.statfs		= fuse_statfs,
 	.sync_fs	= fuse_sync_fs,
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index b42e2110084b..644b2d1e7276 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1050,7 +1050,7 @@ static int gfs2_drop_inode(struct inode *inode)
 	if (test_bit(SDF_EVICTING, &sdp->sd_flags))
 		return 1;
 
-	return generic_drop_inode(inode);
+	return inode_generic_drop(inode);
 }
 
 /**
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 01e516175bcd..1e1acf5775ab 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -261,7 +261,7 @@ static int hostfs_show_options(struct seq_file *seq, struct dentry *root)
 static const struct super_operations hostfs_sbops = {
 	.alloc_inode	= hostfs_alloc_inode,
 	.free_inode	= hostfs_free_inode,
-	.drop_inode	= generic_delete_inode,
+	.drop_inode	= inode_just_drop,
 	.evict_inode	= hostfs_evict_inode,
 	.statfs		= hostfs_statfs,
 	.show_options	= hostfs_show_options,
diff --git a/fs/inode.c b/fs/inode.c
index 01ebdc40021e..a66c02123bca 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1838,11 +1838,11 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval,
 EXPORT_SYMBOL(insert_inode_locked4);
 
 
-int generic_delete_inode(struct inode *inode)
+int inode_just_drop(struct inode *inode)
 {
 	return 1;
 }
-EXPORT_SYMBOL(generic_delete_inode);
+EXPORT_SYMBOL(inode_just_drop);
 
 /*
  * Called when we're dropping the last reference
@@ -1866,7 +1866,7 @@ static void iput_final(struct inode *inode)
 	if (op->drop_inode)
 		drop = op->drop_inode(inode);
 	else
-		drop = generic_drop_inode(inode);
+		drop = inode_generic_drop(inode);
 
 	if (!drop &&
 	    !(inode->i_state & I_DONTCACHE) &&
@@ -2189,7 +2189,7 @@ static int __remove_privs(struct mnt_idmap *idmap,
 	return notify_change(idmap, dentry, &newattrs, NULL);
 }
 
-int file_remove_privs_flags(struct file *file, unsigned int flags)
+static int file_remove_privs_flags(struct file *file, unsigned int flags)
 {
 	struct dentry *dentry = file_dentry(file);
 	struct inode *inode = file_inode(file);
@@ -2214,7 +2214,6 @@ int file_remove_privs_flags(struct file *file, unsigned int flags)
 		inode_has_no_xattr(inode);
 	return error;
 }
-EXPORT_SYMBOL_GPL(file_remove_privs_flags);
 
 /**
  * file_remove_privs - remove special file privileges (suid, capabilities)
@@ -2519,21 +2518,28 @@ void __init inode_init(void)
 void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev)
 {
 	inode->i_mode = mode;
-	if (S_ISCHR(mode)) {
+	switch (inode->i_mode & S_IFMT) {
+	case S_IFCHR:
 		inode->i_fop = &def_chr_fops;
 		inode->i_rdev = rdev;
-	} else if (S_ISBLK(mode)) {
+		break;
+	case S_IFBLK:
 		if (IS_ENABLED(CONFIG_BLOCK))
 			inode->i_fop = &def_blk_fops;
 		inode->i_rdev = rdev;
-	} else if (S_ISFIFO(mode))
+		break;
+	case S_IFIFO:
 		inode->i_fop = &pipefifo_fops;
-	else if (S_ISSOCK(mode))
-		;	/* leave it no_open_fops */
-	else
+		break;
+	case S_IFSOCK:
+		/* leave it no_open_fops */
+		break;
+	default:
 		printk(KERN_DEBUG "init_special_inode: bogus i_mode (%o) for"
 				  " inode %s:%lu\n", mode, inode->i_sb->s_id,
 				  inode->i_ino);
+		break;
+	}
 }
 EXPORT_SYMBOL(init_special_inode);
 
@@ -2914,7 +2920,7 @@ EXPORT_SYMBOL(mode_strip_sgid);
  */
 void dump_inode(struct inode *inode, const char *reason)
 {