Merge tag 'vfs-6.17-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 ext4 IOCB_DONTCACHE support

     This refactors the address_space_operations write_begin() and
     write_end() callbacks to take const struct kiocb * as their first
     argument, allowing IOCB flags such as IOCB_DONTCACHE to propagate
     to the filesystem's buffered I/O path.

     Ext4 is updated to implement handling of the IOCB_DONTCACHE flag
     and advertises support via the FOP_DONTCACHE file operation flag.

     Additionally, the i915 driver's shmem write paths are updated to
     bypass the legacy write_begin/write_end interface in favor of
     directly calling write_iter() with a constructed synchronous kiocb.
     Another i915 change replaces a manual write loop with
     kernel_write() during GEM shmem object creation.

  Cleanups:

   - don't duplicate vfs_open() in kernel_file_open()

   - proc_fd_getattr(): don't bother with S_ISDIR() check

   - fs/ecryptfs: replace snprintf with sysfs_emit in show function

   - vfs: Remove unnecessary list_for_each_entry_safe() from
     evict_inodes()

   - filelock: add new locks_wake_up_waiter() helper

   - fs: Remove three arguments from block_write_end()

   - VFS: change old_dir and new_dir in struct renamedata to dentrys

   - netfs: Remove unused declaration netfs_queue_write_request()

  Fixes:

   - eventpoll: Fix semi-unbounded recursion

   - eventpoll: fix sphinx documentation build warning

   - fs/read_write: Fix spelling typo

   - fs: annotate data race between poll_schedule_timeout() and
     pollwake()

   - fs/pipe: set FMODE_NOWAIT in create_pipe_files()

   - docs/vfs: update references to i_mutex to i_rwsem

   - fs/buffer: remove comment about hard sectorsize

   - fs/buffer: remove the min and max limit checks in __getblk_slow()

   - fs/libfs: don't assume blocksize <= PAGE_SIZE in
     generic_check_addressable

   - fs_context: fix parameter name in infofc() macro

   - fs: Prevent file descriptor table allocations exceeding INT_MAX"

* tag 'vfs-6.17-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (24 commits)
  netfs: Remove unused declaration netfs_queue_write_request()
  eventpoll: fix sphinx documentation build warning
  ext4: support uncached buffered I/O
  mm/pagemap: add write_begin_get_folio() helper function
  fs: change write_begin/write_end interface to take struct kiocb *
  drm/i915: Refactor shmem_pwrite() to use kiocb and write_iter
  drm/i915: Use kernel_write() in shmem object create
  eventpoll: Fix semi-unbounded recursion
  vfs: Remove unnecessary list_for_each_entry_safe() from evict_inodes()
  fs/libfs: don't assume blocksize <= PAGE_SIZE in generic_check_addressable
  fs/buffer: remove the min and max limit checks in __getblk_slow()
  fs: Prevent file descriptor table allocations exceeding INT_MAX
  fs: Remove three arguments from block_write_end()
  fs/ecryptfs: replace snprintf with sysfs_emit in show function
  fs: annotate suspected data race between poll_schedule_timeout() and pollwake()
  docs/vfs: update references to i_mutex to i_rwsem
  fs/buffer: remove comment about hard sectorsize
  fs_context: fix parameter name in infofc() macro
  VFS: change old_dir and new_dir in struct renamedata to dentrys
  proc_fd_getattr(): don't bother with S_ISDIR() check
  ...

88 files changed, 520 insertions, 457 deletions

diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index 2e567e341c3bd..580581281ed7a 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -253,10 +253,10 @@ prototypes::
 	int (*writepages)(struct address_space *, struct writeback_control *);
 	bool (*dirty_folio)(struct address_space *, struct folio *folio);
 	void (*readahead)(struct readahead_control *);
-	int (*write_begin)(struct file *, struct address_space *mapping,
+	int (*write_begin)(const struct kiocb *, struct address_space *mapping,
 				loff_t pos, unsigned len,
 				struct folio **foliop, void **fsdata);
-	int (*write_end)(struct file *, struct address_space *mapping,
+	int (*write_end)(const struct kiocb *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned copied,
 				struct folio *folio, void *fsdata);
 	sector_t (*bmap)(struct address_space *, sector_t);
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index fd32a9a17bfb3..57604b07bdc99 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -758,8 +758,9 @@ process is more complicated and uses write_begin/write_end or
 dirty_folio to write data into the address_space, and
 writepages to writeback data to storage.
 
-Adding and removing pages to/from an address_space is protected by the
-inode's i_mutex.
+Removing pages from an address_space requires holding the inode's i_rwsem
+exclusively, while adding pages to the address_space requires holding the
+inode's i_mapping->invalidate_lock exclusively.
 
 When data is written to a page, the PG_Dirty flag should be set.  It
 typically remains set until writepages asks for it to be written.  This
@@ -822,10 +823,10 @@ cache in your filesystem.  The following members are defined:
 		int (*writepages)(struct address_space *, struct writeback_control *);
 		bool (*dirty_folio)(struct address_space *, struct folio *);
 		void (*readahead)(struct readahead_control *);
-		int (*write_begin)(struct file *, struct address_space *mapping,
+		int (*write_begin)(const struct kiocb *, struct address_space *mapping,
 				   loff_t pos, unsigned len,
-				struct page **pagep, void **fsdata);
-		int (*write_end)(struct file *, struct address_space *mapping,
+				   struct page **pagep, void **fsdata);
+		int (*write_end)(const struct kiocb *, struct address_space *mapping,
 				 loff_t pos, unsigned len, unsigned copied,
 				 struct folio *folio, void *fsdata);
 		sector_t (*bmap)(struct address_space *, sector_t);
diff --git a/block/fops.c b/block/fops.c
index 1309861d4c2c4..f34e7315c83cd 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -496,18 +496,21 @@ static void blkdev_readahead(struct readahead_control *rac)
 	mpage_readahead(rac, blkdev_get_block);
 }
 
-static int blkdev_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
+static int blkdev_write_begin(const struct kiocb *iocb,
+			      struct address_space *mapping, loff_t pos,
+			      unsigned len, struct folio **foliop,
+			      void **fsdata)
 {
 	return block_write_begin(mapping, pos, len, foliop, blkdev_get_block);
 }
 
-static int blkdev_write_end(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned copied, struct folio *folio,
-		void *fsdata)
+static int blkdev_write_end(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len, unsigned copied,
+			    struct folio *folio, void *fsdata)
 {
 	int ret;
-	ret = block_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	ret = block_write_end(pos, len, copied, folio);
 
 	folio_unlock(folio);
 	folio_put(folio);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index 19a3eb82dc6a6..9cbb0f68a5bb9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -6,6 +6,7 @@
 #include <linux/pagevec.h>
 #include <linux/shmem_fs.h>
 #include <linux/swap.h>
+#include <linux/uio.h>
 
 #include <drm/drm_cache.h>
 
@@ -400,12 +401,12 @@ static int
 shmem_pwrite(struct drm_i915_gem_object *obj,
 	     const struct drm_i915_gem_pwrite *arg)
 {
-	struct address_space *mapping = obj->base.filp->f_mapping;
-	const struct address_space_operations *aops = mapping->a_ops;
 	char __user *user_data = u64_to_user_ptr(arg->data_ptr);
-	u64 remain;
-	loff_t pos;
-	unsigned int pg;
+	struct file *file = obj->base.filp;
+	struct kiocb kiocb;
+	struct iov_iter iter;
+	ssize_t written;
+	u64 size = arg->size;
 
 	/* Caller already validated user args */
 	GEM_BUG_ON(!access_ok(user_data, arg->size));
@@ -428,63 +429,24 @@ shmem_pwrite(struct drm_i915_gem_object *obj,
 	if (obj->mm.madv != I915_MADV_WILLNEED)
 		return -EFAULT;
 
-	/*
-	 * Before the pages are instantiated the object is treated as being
-	 * in the CPU domain. The pages will be clflushed as required before
-	 * use, and we can freely write into the pages directly. If userspace
-	 * races pwrite with any other operation; corruption will ensue -
-	 * that is userspace's prerogative!
-	 */
+	if (size > MAX_RW_COUNT)
+		return -EFBIG;
 
-	remain = arg->size;
-	pos = arg->offset;
-	pg = offset_in_page(pos);
+	if (!file->f_op->write_iter)
+		return -EINVAL;
 
-	do {
-		unsigned int len, unwritten;
-		struct folio *folio;
-		void *data, *vaddr;
-		int err;
-		char __maybe_unused c;
-
-		len = PAGE_SIZE - pg;
-		if (len > remain)
-			len = remain;
-
-		/* Prefault the user page to reduce potential recursion */
-		err = __get_user(c, user_data);
-		if (err)
-			return err;
-
-		err = __get_user(c, user_data + len - 1);
-		if (err)
-			return err;
-
-		err = aops->write_begin(obj->base.filp, mapping, pos, len,
-					&folio, &data);
-		if (err < 0)
-			return err;
-
-		vaddr = kmap_local_folio(folio, offset_in_folio(folio, pos));
-		pagefault_disable();
-		unwritten = __copy_from_user_inatomic(vaddr, user_data, len);
-		pagefault_enable();
-		kunmap_local(vaddr);
-
-		err = aops->write_end(obj->base.filp, mapping, pos, len,
-				      len - unwritten, folio, data);
-		if (err < 0)
-			return err;
-
-		/* We don't handle -EFAULT, leave it to the caller to check */
-		if (unwritten)
-			return -ENODEV;
-
-		remain -= len;
-		user_data += len;
-		pos += len;
-		pg = 0;
-	} while (remain);
+	init_sync_kiocb(&kiocb, file);
+	kiocb.ki_pos = arg->offset;
+	iov_iter_ubuf(&iter, ITER_SOURCE, (void __user *)user_data, size);
+
+	written = file->f_op->write_iter(&kiocb, &iter);
+	BUG_ON(written == -EIOCBQUEUED);
+
+	if (written != size)
+		return -EIO;
+
+	if (written < 0)
+		return written;
 
 	return 0;
 }
@@ -637,9 +599,8 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915,
 {
 	struct drm_i915_gem_object *obj;
 	struct file *file;
-	const struct address_space_operations *aops;
-	loff_t pos;
-	int err;
+	loff_t pos = 0;
+	ssize_t err;
 
 	GEM_WARN_ON(IS_DGFX(i915));
 	obj = i915_gem_object_create_shmem(i915, round_up(size, PAGE_SIZE));
@@ -649,29 +610,15 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915,
 	GEM_BUG_ON(obj->write_domain != I915_GEM_DOMAIN_CPU);
 
 	file = obj->base.filp;
-	aops = file->f_mapping->a_ops;
-	pos = 0;
-	do {
-		unsigned int len = min_t(typeof(size), size, PAGE_SIZE);
-		struct folio *folio;
-		void *fsdata;
-
-		err = aops->write_begin(file, file->f_mapping, pos, len,
-					&folio, &fsdata);
-		if (err < 0)
-			goto fail;
+	err = kernel_write(file, data, size, &pos);
 
-		memcpy_to_folio(folio, offset_in_folio(folio, pos), data, len);
+	if (err < 0)
+		goto fail;
 
-		err = aops->write_end(file, file->f_mapping, pos, len, len,
-				      folio, fsdata);
-		if (err < 0)
-			goto fail;
-
-		size -= len;
-		data += len;
-		pos += len;
-	} while (size);
+	if (err != size) {
+		err = -EIO;
+		goto fail;
+	}
 
 	return obj;
 
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index 21527189e4307..6830f8bc8d4eb 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -53,13 +53,14 @@ static void adfs_write_failed(struct address_space *mapping, loff_t to)
 		truncate_pagecache(inode, inode->i_size);
 }
 
-static int adfs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int adfs_write_begin(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len,
+			    struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,
+	ret = cont_write_begin(iocb, mapping, pos, len, foliop, fsdata,
 				adfs_get_block,
 				&ADFS_I(mapping->host)->mmu_private);
 	if (unlikely(ret))
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 7a71018e3f675..219ea03539060 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -415,13 +415,14 @@ affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	return ret;
 }
 
-static int affs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int affs_write_begin(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len,
+			    struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,
+	ret = cont_write_begin(iocb, mapping, pos, len, foliop, fsdata,
 				affs_get_block,
 				&AFFS_I(mapping->host)->mmu_private);
 	if (unlikely(ret))
@@ -430,14 +431,15 @@ static int affs_write_begin(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
-static int affs_write_end(struct file *file, struct address_space *mapping,
-			  loff_t pos, unsigned int len, unsigned int copied,
+static int affs_write_end(const struct kiocb *iocb,
+			  struct address_space *mapping, loff_t pos,
+			  unsigned int len, unsigned int copied,
 			  struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	int ret;
 
-	ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	ret = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata);
 
 	/* Clear Archived bit on file writes, as AmigaOS would do */
 	if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) {
@@ -645,7 +647,8 @@ static int affs_read_folio_ofs(struct file *file, struct folio *folio)
 	return err;
 }
 
-static int affs_write_begin_ofs(struct file *file, struct address_space *mapping,
+static int affs_write_begin_ofs(const struct kiocb *iocb,
+				struct address_space *mapping,
 				loff_t pos, unsigned len,
 				struct folio **foliop, void **fsdata)
 {
@@ -684,9 +687,10 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping
 	return err;
 }
 
-static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned copied,
-				struct folio *folio, void *fsdata)
+static int affs_write_end_ofs(const struct kiocb *iocb,
+			      struct address_space *mapping,
+			      loff_t pos, unsigned len, unsigned copied,
+			      struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	struct super_block *sb = inode->i_sb;
diff --git a/fs/attr.c b/fs/attr.c
index 9caf63d20d03e..5425c1dbbff92 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -230,7 +230,7 @@ EXPORT_SYMBOL(setattr_prepare);
  * @inode:	the inode to be truncated
  * @offset:	the new size to assign to the inode
  *
- * inode_newsize_ok must be called with i_mutex held.
+ * inode_newsize_ok must be called with i_rwsem held exclusively.
  *
  * inode_newsize_ok will check filesystem limits and ulimits to check that the
  * new inode size is within limits. inode_newsize_ok will also send SIGXFSZ
@@ -318,7 +318,7 @@ static void setattr_copy_mgtime(struct inode *inode, const struct iattr *attr)
  * @inode:	the inode to be updated
  * @attr:	the new attributes
  *
- * setattr_copy must be called with i_mutex held.
+ * setattr_copy must be called with i_rwsem held exclusively.
  *
  * setattr_copy updates the inode's metadata with that specified
  * in attr on idmapped mounts. Necessary permission checks to determine
@@ -403,13 +403,13 @@ EXPORT_SYMBOL(may_setattr);
  * @attr:	new attributes
  * @delegated_inode: returns inode, if the inode is delegated
  *
- * The caller must hold the i_mutex on the affected object.
+ * The caller must hold the i_rwsem exclusively on the affected object.
  *
  * If notify_change discovers a delegation in need of breaking,
  * it will return -EWOULDBLOCK and return a reference to the inode in
  * delegated_inode.  The caller should then break the delegation and
  * retry.  Because breaking a delegation may take a long time, the
- * caller should drop the i_mutex before doing so.
+ * caller should drop the i_rwsem before doing so.
  *
  * Alternatively, a caller may pass NULL for delegated_inode.  This may
  * be appropriate for callers that expect the underlying filesystem not
@@ -456,7 +456,7 @@ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry,
 		if (S_ISLNK(inode->i_mode))
 			return -EOPNOTSUPP;
 
-		/* Flag setting protected by i_mutex */
+		/* Flag setting protected by i_rwsem */
 		if (is_sxid(attr->ia_mode))
 			inode->i_flags &= ~S_NOSEC;
 	}
diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c
index 66bacdd49f789..1c54b9b5bd695 100644
--- a/fs/bcachefs/fs-io-buffered.c
+++ b/fs/bcachefs/fs-io-buffered.c
@@ -674,7 +674,7 @@ int bch2_writepages(struct address_space *mapping, struct writeback_control *wbc
 
 /* buffered writes: */
 
-int bch2_write_begin(struct file *file, struct address_space *mapping,
+int bch2_write_begin(const struct kiocb *iocb, struct address_space *mapping,
 		     loff_t pos, unsigned len,
 		     struct folio **foliop, void **fsdata)
 {
@@ -757,7 +757,7 @@ err_unlock:
 	return bch2_err_class(ret);
 }
 
-int bch2_write_end(struct file *file, struct address_space *mapping,
+int bch2_write_end(const struct kiocb *iocb, struct address_space *mapping,
 		   loff_t pos, unsigned len, unsigned copied,
 		   struct folio *folio, void *fsdata)
 {
diff --git a/fs/bcachefs/fs-io-buffered.h b/fs/bcachefs/fs-io-buffered.h
index 3207ebbb4ab43..14de91c276560 100644
--- a/fs/bcachefs/fs-io-buffered.h
+++ b/fs/bcachefs/fs-io-buffered.h
@@ -10,9 +10,9 @@ int bch2_read_folio(struct file *, struct folio *);
 int bch2_writepages(struct address_space *, struct writeback_control *);
 void bch2_readahead(struct readahead_control *);
 
-int bch2_write_begin(struct file *, struct address_space *, loff_t pos,
+int bch2_write_begin(const struct kiocb *, struct address_space *, loff_t pos,
 		     unsigned len, struct folio **, void **);
-int bch2_write_end(struct file *, struct address_space *, loff_t,
+int bch2_write_end(const struct kiocb *, struct address_space *, loff_t,
 		   unsigned len, unsigned copied, struct folio *, void *);
 
 ssize_t bch2_write_iter(struct kiocb *, struct iov_iter *);
diff --git a/fs/bfs/file.c b/fs/bfs/file.c
index fa66a09e496a8..10dc0151ea550 100644
--- a/fs/bfs/file.c
+++ b/fs/bfs/file.c
@@ -170,9 +170,10 @@ static void bfs_write_failed(struct address_space *mapping, loff_t to)
 		truncate_pagecache(inode, inode->i_size);
 }
 
-static int bfs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int bfs_write_begin(const struct kiocb *iocb,
+			   struct address_space *mapping,
+			   loff_t pos, unsigned len,
+			   struct folio **foliop, void **fsdata)
 {
 	int ret;
 
diff --git a/fs/buffer.c b/fs/buffer.c
index 8cf4a1dc481eb..ead4dc85debdd 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1122,15 +1122,9 @@ __getblk_slow(struct block_device *bdev, sector_t block,
 {
 	bool blocking = gfpflags_allow_blocking(gfp);
 
-	/* Size must be multiple of hard sectorsize */
-	if (unlikely(size & (bdev_logical_block_size(bdev)-1) ||
-			(size < 512 || size > PAGE_SIZE))) {
-		printk(KERN_ERR "getblk(): invalid block size %d requested\n",
-					size);
-		printk(KERN_ERR "logical block size: %d\n",
-					bdev_logical_block_size(bdev));
-
-		dump_stack();
+	if (WARN_ON_ONCE(!IS_ALIGNED(size, bdev_logical_block_size(bdev)))) {
+		printk(KERN_ERR "getblk(): block size %d not aligned to logical block size %d\n",
+		       size, bdev_logical_block_size(bdev));
 		return NULL;
 	}
 
@@ -2271,9 +2265,8 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 }
 EXPORT_SYMBOL(block_write_begin);
 
-int block_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+int block_write_end(loff_t pos, unsigned len, unsigned copied,
+		struct folio *folio)
 {
 	size_t start = pos - folio_pos(folio);
 
@@ -2304,15 +2297,15 @@ int block_write_end(struct file *file, struct address_space *mapping,
 }
 EXPORT_SYMBOL(block_write_end);
 
-int generic_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+int generic_write_end(const struct kiocb *iocb, struct address_space *mapping,
+		      loff_t pos, unsigned len, unsigned copied,
+		      struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	loff_t old_size = inode->i_size;
 	bool i_size_changed = false;
 
-	copied = block_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	copied = block_write_end(pos, len, copied, folio);
 
 	/*
 	 * No need to use i_size_read() here, the i_size cannot change under us
@@ -2501,7 +2494,8 @@ out:
 }
 EXPORT_SYMBOL(generic_cont_expand_simple);
 
-static int cont_expand_zero(struct file *file, struct address_space *mapping,
+static int cont_expand_zero(const struct kiocb *iocb,
+			    struct address_space *mapping,
 			    loff_t pos, loff_t *bytes)
 {
 	struct inode *inode = mapping->host;
@@ -2525,12 +2519,12 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 		}
 		len = PAGE_SIZE - zerofrom;
 
-		err = aops->write_begin(file, mapping, curpos, len,
+		err = aops->write_begin(iocb, mapping, curpos, len,
 					    &folio, &fsdata);
 		if (err)
 			goto out;
 		folio_zero_range(folio, offset_in_folio(folio, curpos), len);
-		err = aops->write_end(file, mapping, curpos, len, len,
+		err = aops->write_end(iocb, mapping, curpos, len, len,
 						folio, fsdata);
 		if (err < 0)
 			goto out;
@@ -2558,12 +2552,12 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 		}
 		len = offset - zerofrom;
 
-		err = aops->write_begin(file, mapping, curpos, len,
+		err = aops->write_begin(iocb, mapping, curpos, len,
 					    &folio, &fsdata);
 		if (err)
 			goto out;
 		folio_zero_range(folio, offset_in_folio(folio, curpos), len);
-		err = aops->write_end(file, mapping, curpos, len, len,
+		err = aops->write_end(iocb, mapping, curpos, len, len,
 						folio, fsdata);
 		if (err < 0)
 			goto out;
@@ -2578,17 +2572,16 @@ out:
  * For moronic filesystems that do not allow holes in file.
  * We may have to extend the file.
  */
-int cont_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata,
-			get_block_t *get_block, loff_t *bytes)
+int cont_write_begin(const struct kiocb *iocb, struct address_space *mapping,
+		     loff_t pos, unsigned len, struct folio **foliop,
+		     void **fsdata, get_block_t *get_block, loff_t *bytes)
 {
 	struct inode *inode = mapping->host;
 	unsigned int blocksize = i_blocksize(inode);
 	unsigned int zerofrom;
 	int err;
 
-	err = cont_expand_zero(file, mapping, pos, bytes);
+	err = cont_expand_zero(iocb, mapping, pos, bytes);
 	if (err)
 		return err;
 
@@ -2610,7 +2603,7 @@ EXPORT_SYMBOL(cont_write_begin);
  * holes and correct delalloc and unwritten extent mapping on filesystems that
  * support these features.
  *
- * We are not allowed to take the i_mutex here so we have to play games to
+ * We are not allowed to take the i_rwsem here so we have to play games to
  * protect against truncate races as the page could now be beyond EOF.  Because
  * truncate writes the inode size before removing pages, once we have the
  * page lock we can determine safely if the page is beyond EOF. If it is not
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index aecfc5c37b49a..91dfd02318772 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -388,10 +388,10 @@ try_again:
 	} else {
 		struct renamedata rd = {
 			.old_mnt_idmap	= &nop_mnt_idmap,
-			.old_dir	= d_inode(dir),
+			.old_parent	= dir,
 			.old_dentry	= rep,
 			.new_mnt_idmap	= &nop_mnt_idmap,
-			.new_dir	= d_inode(cache->graveyard),
+			.new_parent	= cache->graveyard,
 			.new_dentry	= grave,
 		};
 		trace_cachefiles_rename(object, d_inode(rep)->i_ino, why);
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 60a621b00c656..02468c848cce2 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1864,10 +1864,12 @@ static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned
  * We are only allowed to write into/dirty the page if the page is
  * clean, or already dirty within the same snap context.
  */
-static int ceph_write_begin(struct file *file, struct address_space *mapping,
+static int ceph_write_begin(const struct kiocb *iocb,
+			    struct address_space *mapping,
 			    loff_t pos, unsigned len,
 			    struct folio **foliop, void **fsdata)
 {
+	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int r;
@@ -1885,10 +1887,12 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
  * we don't do anything in here that simple_write_end doesn't do
  * except adjust dirty page accounting
  */
-static int ceph_write_end(struct file *file, struct address_space *mapping,
-			  loff_t pos, unsigned len, unsigned copied,
+static int ceph_write_end(const struct kiocb *iocb,
+			  struct address_space *mapping, loff_t pos,
+			  unsigned len, unsigned copied,
 			  struct folio *folio, void *fsdata)
 {
+	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct ceph_client *cl = ceph_inode_to_client(inode);
 	bool check_cap = false;
diff --git a/fs/dcache.c b/fs/dcache.c
index 2adac023ba23f..60046ae23d514 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2797,10 +2797,10 @@ static void copy_name(struct dentry *dentry, struct dentry *target)
  * @target: new dentry
  * @exchange: exchange the two dentries
  *
- * Update the dcache to reflect the move of a file name. Negative
- * dcache entries should not be moved in this way. Caller must hold
- * rename_lock, the i_mutex of the source and target directories,
- * and the sb->s_vfs_rename_mutex if they differ. See lock_rename().
+ * Update the dcache to reflect the move of a file name. Negative dcache
+ * entries should not be moved in this way. Caller must hold rename_lock, the
+ * i_rwsem of the source and target directories (exclusively), and the sb->
+ * s_vfs_rename_mutex if they differ. See lock_rename().
  */
 static void __d_move(struct dentry *dentry, struct dentry *target,
 		     bool exchange)
@@ -2946,7 +2946,7 @@ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2)
  * This helper attempts to cope with remotely renamed directories
  *
  * It assumes that the caller is already holding
- * dentry->d_parent->d_inode->i_mutex, and rename_lock
+ * dentry->d_parent->d_inode->i_rwsem, and rename_lock
  *
  * Note: If ever the locking in lock_rename() changes, then please
  * remember to update this too...
diff --git a/fs/direct-io.c b/fs/direct-io.c
index bbd05f1a21453..1694ee9a93820 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1083,8 +1083,8 @@ static inline int drop_refcount(struct dio *dio)
  * The locking rules are governed by the flags parameter:
  *  - if the flags value contains DIO_LOCKING we use a fancy locking
  *    scheme for dumb filesystems.
- *    For writes this function is called under i_mutex and returns with
- *    i_mutex held, for reads, i_mutex is not held on entry, but it is
+ *    For writes this function is called under i_rwsem and returns with
+ *    i_rwsem held, for reads, i_rwsem is not held on entry, but it is
  *    taken and dropped again before returning.
  *  - if the flags value does NOT contain DIO_LOCKING we don't use any
  *    internal locking but rather rely on the filesystem to synchronize
@@ -1094,7 +1094,7 @@ static inline int drop_refcount(struct dio *dio)
  * counter before starting direct I/O, and decrement it once we are done.
  * Truncate can wait for it to reach zero to provide exclusion.  It is
  * expected that filesystem provide exclusion between new direct I/O
- * and truncates.  For DIO_LOCKING filesystems this is done by i_mutex,
+ * and truncates.  For DIO_LOCKING filesystems this is done by i_rwsem,
  * but other filesystems need to take care of this on their own.
  *
  * NOTE: if you pass "sdio" to anything by pointer make sure that function
@@ -1279,7 +1279,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 
 	/*
 	 * All block lookups have been performed. For READ requests
-	 * we can let i_mutex go now that its achieved its purpose
+	 * we can let i_rwsem go now that its achieved its purpose
 	 * of protecting us from looking up uninitialized blocks.
 	 */
 	if (iov_iter_rw(iter) == READ && (dio->flags & DIO_LOCKING))
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 493d7f1949561..bd317d943d62e 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -635,10 +635,10 @@ ecryptfs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 	}
 
 	rd.old_mnt_idmap	= &nop_mnt_idmap;
-	rd.old_dir		= d_inode(lower_old_dir_dentry);
+	rd.old_parent		= lower_old_dir_dentry;
 	rd.old_dentry		= lower_old_dentry;
 	rd.new_mnt_idmap	= &nop_mnt_idmap;
-	rd.new_dir		= d_inode(lower_new_dir_dentry);
+	rd.new_parent		= lower_new_dir_dentry;
 	rd.new_dentry		= lower_new_dentry;
 	rc = vfs_rename(&rd);
 	if (rc)
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 45f9ca4465da8..eab1beb846d38 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -20,6 +20,7 @@
 #include <linux/fs_context.h>
 #include <linux/fs_parser.h>
 #include <linux/fs_stack.h>
+#include <linux/sysfs.h>
 #include <linux/slab.h>
 #include <linux/magic.h>
 #include "ecryptfs_kernel.h"
@@ -764,7 +765,7 @@ static struct kobject *ecryptfs_kobj;
 static ssize_t version_show(struct kobject *kobj,
 			    struct kobj_attribute *attr, char *buff)
 {
-	return snprintf(buff, PAGE_SIZE, "%d\n", ECRYPTFS_VERSIONING_MASK);
+	return sysfs_emit(buff, "%d\n", ECRYPTFS_VERSIONING_MASK);
 }
 
 static struct kobj_attribute version_attr = __ATTR_RO(version);
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 60f0ac8744b50..2c2b12fedeaec 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -228,7 +228,7 @@ out:
 
 /**
  * ecryptfs_write_begin
- * @file: The eCryptfs file
+ * @iocb: I/O control block for the eCryptfs file
  * @mapping: The eCryptfs object
  * @pos: The file offset at which to start writing
  * @len: Length of the write
@@ -239,7 +239,7 @@ out:
  *
  * Returns zero on success; non-zero otherwise
  */
-static int ecryptfs_write_begin(struct file *file,
+static int ecryptfs_write_begin(const struct kiocb *iocb,
 			struct address_space *mapping,
 			loff_t pos, unsigned len,
 			struct folio **foliop, void **fsdata)
@@ -322,7 +322,7 @@ static int ecryptfs_write_begin(struct file *file,
 	 * Note, this will increase i_size. */
 	if (index != 0) {
 		if (prev_page_end_size > i_size_read(mapping->host)) {
-			rc = ecryptfs_truncate(file->f_path.dentry,
+			rc = ecryptfs_truncate(iocb->ki_filp->f_path.dentry,
 					       prev_page_end_size);
 			if (rc) {
 				printk(KERN_ERR "%s: Error on attempt to "
@@ -429,7 +429,7 @@ int ecryptfs_write_inode_size_to_metadata(struct inode *ecryptfs_inode)
 
 /**
  * ecryptfs_write_end
- * @file: The eCryptfs file object
+ * @iocb: I/O control block for the eCryptfs file
  * @mapping: The eCryptfs object
  * @pos: The file position
  * @len: The length of the data (unused)
@@ -437,7 +437,7 @@ int ecryptfs_write_inode_size_to_metadata(struct inode *ecryptfs_inode)
  * @folio: The eCryptfs folio
  * @fsdata: The fsdata (unused)
  */
-static int ecryptfs_write_end(struct file *file,
+static int ecryptfs_write_end(const struct kiocb *iocb,
 			struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct folio *folio, void *fsdata)
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 0fbf5dfedb24e..b22d6f819f782 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -218,6 +218,7 @@ struct eventpoll {
 	/* used to optimize loop detection check */
 	u64 gen;
 	struct hlist_head refs;
+	u8 loop_check_depth;
 
 	/*
 	 * usage count, used together with epitem->dying to
@@ -2140,23 +2141,24 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 }
 
 /**
- * ep_loop_check_proc - verify that adding an epoll file inside another
- *                      epoll structure does not violate the constraints, in
- *                      terms of closed loops, or too deep chains (which can
- *                      result in excessive stack usage).
+ * ep_loop_check_proc - verify that adding an epoll file @ep inside another
+ *                      epoll file does not create closed loops, and
+ *                      determine the depth of the subtree starting at @ep
  *
  * @ep: the &struct eventpoll to be currently checked.
  * @depth: Current depth of the path being checked.
  *
- * Return: %zero if adding the epoll @file inside current epoll
- *          structure @ep does not violate the constraints, or %-1 otherwise.
+ * Return: depth of the subtree, or INT_MAX if we found a loop or went too deep.
  */
 static int ep_loop_check_proc(struct eventpoll *ep, int depth)
 {
-	int error = 0;
+	int result = 0;
 	struct rb_node *rbp;
 	struct epitem *epi;
 
+	if (ep->gen == loop_check_gen)
+		return ep->loop_check_depth;
+
 	mutex_lock_nested(&ep->mtx, depth + 1);
 	ep->gen = loop_check_gen;
 	for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
@@ -2164,13 +2166,11 @@ static int ep_loop_check_proc(struct eventpoll *ep, int depth)
 		if (unlikely(is_file_epoll(epi->ffd.file))) {
 			struct eventpoll *ep_tovisit;
 			ep_tovisit = epi->ffd.file->private_data;
-			if (ep_tovisit->gen == loop_check_gen)
-				continue;
 			if (ep_tovisit == inserting_into || depth > EP_MAX_NESTS)
-				error = -1;
+				result = INT_MAX;
 			else
-				error = ep_loop_check_proc(ep_tovisit, depth + 1);
-			if (error != 0)
+				result = max(result, ep_loop_check_proc(ep_tovisit, depth + 1) + 1);
+			if (result > EP_MAX_NESTS)
 				break;
 		} else {
 			/*
@@ -2184,9 +2184,25 @@ static int ep_loop_check_proc(struct eventpoll *ep, int depth)
 			list_file(epi->ffd.file);
 		}
 	}
+	ep->loop_check_depth = result;
 	mutex_unlock(&ep->mtx);
 
-	return error;
+	return result;
+}
+
+/* ep_get_upwards_depth_proc - determine depth of @ep when traversed upwards */
+static int ep_get_upwards_depth_proc(struct eventpoll *ep, int depth)
+{
+	int result = 0;
+	struct epitem *epi;
+
+	if (ep->gen == loop_check_gen)
+		return ep->loop_check_depth;
+	hlist_for_each_entry_rcu(epi, &ep->refs, fllink)
+		result = max(result, ep_get_upwards_depth_proc(epi->ep, depth + 1) + 1);
+	ep->gen = loop_check_gen;
+	ep->loop_check_depth = result;
+	return result;
 }
 
 /**
@@ -2202,8 +2218,22 @@ static int ep_loop_check_proc(struct eventpoll *ep, int depth)
  */
 static int ep_loop_check(struct eventpoll *ep, struct eventpoll *to)
 {
+	int depth, upwards_depth;
+
 	inserting_into = ep;
-	return ep_loop_check_proc(to, 0);
+	/*
+	 * Check how deep down we can get from @to, and whether it is possible
+	 * to loop up to @ep.
+	 */
+	depth = ep_loop_check_proc(to, 0);
+	if (depth > EP_MAX_NESTS)
+		return -1;
+	/* Check how far up we can go from @ep. */
+	rcu_read_lock();
+	upwards_depth = ep_get_upwards_depth_proc(ep, 0);
+	rcu_read_unlock();
+
+	return (depth+1+upwards_depth > EP_MAX_NESTS) ? -1 : 0;
 }
 
 static void clear_tfile_check_list(void)
diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index 841a5b18e3dfd..70f53edd0a104 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -532,11 +532,10 @@ int exfat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 	return blkdev_issue_flush(inode->i_sb->s_bdev);
 }
 
-static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size)
+static int exfat_extend_valid_size(struct inode *inode, loff_t new_valid_size)
 {
 	int err;
 	loff_t pos;
-	struct inode *inode = file_inode(file);
 	struct exfat_inode_info *ei = EXFAT_I(inode);
 	struct address_space *mapping = inode->i_mapping;
 	const struct address_space_operations *ops = mapping->a_ops;
@@ -551,14 +550,14 @@ static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size)
 		if (pos + len > new_valid_size)
 			len = new_valid_size - pos;
 
-		err = ops->write_begin(file, mapping, pos, len, &folio, NULL);
+		err = ops->write_begin(NULL, mapping, pos, len, &folio, NULL);
 		if (err)
 			goto out;
 
 		off = offset_in_folio(folio, pos);
 		folio_zero_new_buffers(folio, off, off + len);
 
-		err = ops->write_end(file, mapping, pos, len, len, folio, NULL);
+		err = ops->write_end(NULL, mapping, pos, len, len, folio, NULL);
 		if (err < 0)
 			goto out;
 		pos += len;
@@ -604,7 +603,7 @@ static ssize_t exfat_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	}
 
 	if (pos > valid_size) {
-		ret = exfat_extend_valid_size(file, pos);
+		ret = exfat_extend_valid_size(inode, pos);
 		if (ret < 0 && ret != -ENOSPC) {
 			exfat_err(inode->i_sb,
 				"write: fail to zero from %llu to %llu(%zd)",
@@ -665,7 +664,7 @@ static vm_fault_t exfat_page_mkwrite(struct vm_fault *vmf)
 			start + vma->vm_end - vma->vm_start);
 
 	if (ei->valid_size < end) {
-		err = exfat_extend_valid_size(file, end);
+		err = exfat_extend_valid_size(inode, end);
 		if (err < 0) {
 			inode_unlock(inode);
 			return vmf_fs_error(err);
diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c
index b22c02d6000f7..c10844e1e16c3 100644
--- a/fs/exfat/inode.c
+++ b/fs/exfat/inode.c
@@ -446,9 +446,10 @@ static void exfat_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-static int exfat_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned int len,
-		struct folio **foliop, void **fsdata)
+static int exfat_write_begin(const struct kiocb *iocb,
+			     struct address_space *mapping,
+			     loff_t pos, unsigned int len,
+			     struct folio **foliop, void **fsdata)
 {
 	int ret;
 
@@ -463,15 +464,16 @@ static int exfat_write_begin(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
-static int exfat_write_end(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned int len, unsigned int copied,
-		struct folio *folio, void *fsdata)
+static int exfat_write_end(const struct kiocb *iocb,
+			   struct address_space *mapping,
+			   loff_t pos, unsigned int len, unsigned int copied,
+			   struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	struct exfat_inode_info *ei = EXFAT_I(inode);
 	int err;
 
-	err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	err = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata);
 	if (err < len)
 		exfat_write_failed(mapping, pos+len);
 
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index 402fecf90a44b..b07b3b369710c 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -87,7 +87,7 @@ static void ext2_commit_chunk(struct folio *folio, loff_t pos, unsigned len)
 	struct inode *dir = mapping->host;
 
 	inode_inc_iversion(dir);
-	block_write_end(NULL, mapping, pos, len, len, folio, NULL);
+	block_write_end(pos, len, len, folio);
 
 	if (pos+len > dir->i_size) {
 		i_size_write(dir, pos+len);
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 30f8201c155f4..d35ca26eee3ce 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -915,7 +915,7 @@ static void ext2_readahead(struct readahead_control *rac)
 }
 
 static int
-ext2_write_begin(struct file *file, struct address_space *mapping,
+ext2_write_begin(const struct kiocb *iocb, struct address_space *mapping,
 		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
 {
 	int ret;
@@ -926,13 +926,14 @@ ext2_write_begin(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
-static int ext2_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+static int ext2_write_end(const struct kiocb *iocb,
+			  struct address_space *mapping,
+			  loff_t pos, unsigned len, unsigned copied,
+			  struct folio *folio, void *fsdata)
 {
 	int ret;
 
-	ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	ret = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata);
 	if (ret < len)
 		ext2_write_failed(mapping, pos + len);
 	return ret;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 21df81347147c..274b41a476c8f 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -977,7 +977,8 @@ const struct file_operations ext4_file_operations = {
 	.splice_write	= iter_file_splice_write,
 	.fallocate	= ext4_fallocate,
 	.fop_flags	= FOP_MMAP_SYNC | FOP_BUFFER_RASYNC |
-			  FOP_DIO_PARALLEL_WRITE,
+			  FOP_DIO_PARALLEL_WRITE |
+			  FOP_DONTCACHE,
 };
 
 const struct inode_operations ext4_file_inode_operations = {
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index be9a4cba35fd5..5c7024051f1ed 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1252,7 +1252,8 @@ int ext4_block_write_begin(handle_t *handle, struct folio *folio,
  * and the ext4_write_end().  So doing the jbd2_journal_start at the start of
  * ext4_write_begin() is the right place.
  */
-static int ext4_write_begin(struct file *file, struct address_space *mapping,
+static int ext4_write_begin(const struct kiocb *iocb,
+			    struct address_space *mapping,
 			    loff_t pos, unsigned len,
 			    struct folio **foliop, void **fsdata)
 {
@@ -1263,7 +1264,6 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 	struct folio *folio;
 	pgoff_t index;
 	unsigned from, to;
-	fgf_t fgp = FGP_WRITEBEGIN;
 
 	ret = ext4_emergency_state(inode->i_sb);
 	if (unlikely(ret))
@@ -1287,16 +1287,14 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 	}
 
 	/*
-	 * __filemap_get_folio() can take a long time if the
+	 * write_begin_get_folio() can take a long time if the
 	 * system is thrashing due to memory pressure, or if the folio
 	 * is being written back.  So grab it first before we start
 	 * the transaction handle.  This also allows us to allocate
 	 * the folio (if needed) without using GFP_NOFS.
 	 */
 retry_grab:
-	fgp |= fgf_set_order(len);
-	folio = __filemap_get_folio(mapping, index, fgp,
-				    mapping_gfp_mask(mapping));
+	folio = write_begin_get_folio(iocb, mapping, index, len);
 	if (IS_ERR(folio))
 		return PTR_ERR(folio);
 
@@ -1400,12 +1398,12 @@ static int write_end_fn(handle_t *handle, struct inode *inode,
 
 /*
  * We need to pick up the new inode size which generic_commit_write gave us
- * `file' can be NULL - eg, when called from page_symlink().
+ * `iocb` can be NULL - eg, when called from page_symlink().
  *
  * ext4 never places buffers on inode->i_mapping->i_private_list.  metadata
  * buffers are managed internally.
  */
-static int ext4_write_end(struct file *file,
+static int ext4_write_end(const struct kiocb *iocb,
 			  struct address_space *mapping,
 			  loff_t pos, unsigned len, unsigned copied,
 			  struct folio *folio, void *fsdata)
@@ -1424,7 +1422,7 @@ static int ext4_write_end(struct file *file,
 		return ext4_write_inline_data_end(inode, pos, len, copied,
 						  folio);
 
-	copied = block_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	copied = block_write_end(pos, len, copied, folio);
 	/*
 	 * it's important to update i_size while still holding folio lock:
 	 * page writeout could otherwise come in and zero beyond i_size.
@@ -1510,7 +1508,7 @@ static void ext4_journalled_zero_new_buffers(handle_t *handle,
 	} while (bh != head);
 }
 
-static int ext4_journalled_write_end(struct file *file,
+static int ext4_journalled_write_end(const struct kiocb *iocb,
 				     struct address_space *mapping,
 				     loff_t pos, unsigned len, unsigned copied,
 				     struct folio *folio, void *fsdata)
@@ -3036,7 +3034,8 @@ static int ext4_nonda_switch(struct super_block *sb)
 	return 0;
 }
 
-static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
+static int ext4_da_write_begin(const struct kiocb *iocb,
+			       struct address_space *mapping,
 			       loff_t pos, unsigned len,
 			       struct folio **foliop, void **fsdata)
 {
@@ -3044,7 +3043,6 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 	struct folio *folio;
 	pgoff_t index;
 	struct inode *inode = mapping->host;
-	fgf_t fgp = FGP_WRITEBEGIN;
 
 	ret = ext4_emergency_state(inode->i_sb);
 	if (unlikely(ret))
@@ -3054,7 +3052,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 
 	if (ext4_nonda_switch(inode->i_sb) || ext4_verity_in_progress(inode)) {
 		*fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
-		return ext4_write_begin(file, mapping, pos,
+		return ext4_write_begin(iocb, mapping, pos,
 					len, foliop, fsdata);
 	}
 	*fsdata = (void *)0;
@@ -3070,9 +3068,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 	}
 
 retry:
-	fgp |= fgf_set_order(len);
-	folio = __filemap_get_folio(mapping, index, fgp,
-				    mapping_gfp_mask(mapping));
+	folio = write_begin_get_folio(iocb, mapping, index, len);
 	if (IS_ERR(folio))
 		return PTR_ERR(folio);
 
@@ -3144,8 +3140,7 @@ static int ext4_da_do_write_end(struct address_space *mapping,
 	 * block_write_end() will mark the inode as dirty with I_DIRTY_PAGES
 	 * flag, which all that's needed to trigger page writeback.
 	 */
-	copied = block_write_end(NULL, mapping, pos, len, copied,
-			folio, NULL);
+	copied = block_write_end(pos, len, copied, folio);
 	new_i_size = pos + copied;
 
 	/*
@@ -3196,7 +3191,7 @@ static int ext4_da_do_write_end(struct address_space *mapping,
 	return copied;
 }
 
-static int ext4_da_write_end(struct file *file,
+static int ext4_da_write_end(const struct kiocb *iocb,
 			     struct address_space *mapping,
 			     loff_t pos, unsigned len, unsigned copied,
 			     struct folio *folio, void *fsdata)
@@ -3205,7 +3200,7 @@ static int ext4_da_write_end(struct file *file,
 	int write_mode = (int)(unsigned long)fsdata;
 
 	if (write_mode == FALL_BACK_TO_NONDELALLOC)
-		return ext4_write_end(file, mapping, pos,
+		return ext4_write_end(iocb, mapping, pos,
 				      len, copied, folio, fsdata);
 
 	trace_ext4_da_write_end(inode, pos, len, copied);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 31e8928426259..711ad80b38d05 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -3519,8 +3519,10 @@ reserve_block:
 	return 0;
 }
 
-static int f2fs_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
+static int f2fs_write_begin(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len, struct folio **foliop,
+			    void **fsdata)
 {
 	struct inode *inode = mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -3656,7 +3658,7 @@ fail:
 	return err;
 }
 
-static int f2fs_write_end(struct file *file,
+static int f2fs_write_end(const struct kiocb *iocb,
 			struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct folio *folio, void *fsdata)
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 3852bb66358cc..9648ed0978168 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -219,13 +219,14 @@ static void fat_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-static int fat_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int fat_write_begin(const struct kiocb *iocb,
+			   struct address_space *mapping,
+			   loff_t pos, unsigned len,
+			   struct folio **foliop, void **fsdata)
 {
 	int err;
 
-	err = cont_write_begin(file, mapping, pos, len,
+	err = cont_write_begin(iocb, mapping, pos, len,
 				foliop, fsdata, fat_get_block,
 				&MSDOS_I(mapping->host)->mmu_private);
 	if (err < 0)
@@ -233,13 +234,14 @@ static int fat_write_begin(struct file *file, struct address_space *mapping,
 	return err;
 }
 
-static int fat_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+static int fat_write_end(const struct kiocb *iocb,
+			 struct address_space *mapping,
+			 loff_t pos, unsigned len, unsigned copied,
+			 struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	int err;
-	err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	err = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata);
 	if (err < len)
 		fat_write_failed(mapping, pos + len);
 	if (!(err < 0) && !(MSDOS_I(inode)->i_attrs & ATTR_ARCH)) {
diff --git a/fs/file.c b/fs/file.c
index b6db031545e65..6d2275c3be9c6 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -197,6 +197,21 @@ static struct fdtable *alloc_fdtable(unsigned int slots_wanted)
 			return ERR_PTR(-EMFILE);
 	}
 
+	/*
+	 * Check if the allocation size would exceed INT_MAX. kvmalloc_array()
+	 * and kvmalloc() will warn if the allocation size is greater than
+	 * INT_MAX, as filp_cachep objects are not __GFP_NOWARN.
+	 *
+	 * This can happen when sysctl_nr_open is set to a very high value and
+	 * a process tries to use a file descriptor near that limit. For example,
+	 * if sysctl_nr_open is set to 1073741816 (0x3ffffff8) - which is what
+	 * systemd typically sets it to - then trying to use a file descriptor
+	 * close to that value will require allocating a file descriptor table
+	 * that exceeds 8GB in size.
+	 */
+	if (unlikely(nr > INT_MAX / sizeof(struct file *)))
+		return ERR_PTR(-EMFILE);
+
 	fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT);
 	if (!fdt)
 		goto out;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 47006d0753f1c..2ddfb3bb64836 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2212,10 +2212,13 @@ out:
  * It's worthy to make sure that space is reserved on disk for the write,
  * but how to implement it without killing performance need more thinking.
  */
-static int fuse_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
+static int fuse_write_begin(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len, struct folio **foliop,
+			    void **fsdata)
 {
 	pgoff_t index = pos >> PAGE_SHIFT;
+	struct file *file = iocb->ki_filp;
 	struct fuse_conn *fc = get_fuse_conn(file_inode(file));
 	struct folio *folio;
 	loff_t fsize;
@@ -2255,9 +2258,10 @@ error:
 	return err;
 }
 
-static int fuse_write_end(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned copied,
-		struct folio *folio, void *fsdata)
+static int fuse_write_end(const struct kiocb *iocb,
+			  struct address_space *mapping,
+			  loff_t pos, unsigned len, unsigned copied,
+			  struct folio *folio, void *fsdata)
 {
 	struct inode *inode = folio->mapping->host;
 
diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h
index a0c7cb0f79fcc..c3fd3172fdd60 100644
--- a/fs/hfs/hfs_fs.h
+++ b/fs/hfs/hfs_fs.h
@@ -201,7 +201,7 @@ extern int hfs_get_block(struct inode *, sector_t, struct buffer_head *, int);
 extern const struct address_space_operations hfs_aops;
 extern const struct address_space_operations hfs_btree_aops;
 
-int hfs_write_begin(struct file *file, struct address_space *mapping,
+int hfs_write_begin(const struct kiocb *iocb, struct address_space *mapping,
 		loff_t pos, unsigned len, struct folio **foliop, void **fsdata);
 extern struct inode *hfs_new_inode(struct inode *, const struct qstr *, umode_t);
 extern void hfs_inode_write_fork(struct inode *, struct hfs_extent *, __be32 *, __be32 *);
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index a81ce7a740b91..096f338134f93 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -44,12 +44,12 @@ static void hfs_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-int hfs_write_begin(struct file *file, struct address_space *mapping,
+int hfs_write_begin(const struct kiocb *iocb, struct address_space *mapping,
 		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,
+	ret = cont_write_begin(iocb, mapping, pos, len, foliop, fsdata,
 				hfs_get_block,
 				&HFS_I(mapping->host)->phys_size);
 	if (unlikely(ret))
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 2f089bff0095c..3d5c65aef3b23 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -473,8 +473,10 @@ extern const struct address_space_operations hfsplus_aops;
 extern const struct address_space_operations hfsplus_btree_aops;
 extern const struct dentry_operations hfsplus_dentry_operations;
 
-int hfsplus_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct folio **foliop, void **fsdata);
+int hfsplus_write_begin(const struct kiocb *iocb,
+			struct address_space *mapping,
+			loff_t pos, unsigned len, struct folio **foliop,
+			void **fsdata);
 struct inode *hfsplus_new_inode(struct super_block *sb, struct inode *dir,
 				umode_t mode);
 void hfsplus_delete_inode(struct inode *inode);
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index f331e95742178..97d75bb2c388e 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -38,12 +38,14 @@ static void hfsplus_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-int hfsplus_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
+int hfsplus_write_begin(const struct kiocb *iocb,
+			struct address_space *mapping, loff_t pos,
+			unsigned len, struct folio **foliop,
+			void **fsdata)
 {
 	int ret;
 
-	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,
+	ret = cont_write_begin(iocb, mapping, pos, len, foliop, fsdata,
 				hfsplus_get_block,
 				&HFSPLUS_I(mapping->host)->phys_size);
 	if (unlikely(ret))
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 1f512f8ea757d..2ac60d5d7314a 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -445,7 +445,8 @@ static int hostfs_read_folio(struct file *file, struct folio *folio)
 	return ret;
 }
 
-static int hostfs_write_begin(struct file *file, struct address_space *mapping,
+static int hostfs_write_begin(const struct kiocb *iocb,
+			      struct address_space *mapping,
 			      loff_t pos, unsigned len,
 			      struct folio **foliop, void **fsdata)
 {
@@ -458,7 +459,8 @@ static int hostfs_write_begin(struct file *file, struct address_space *mapping,
 	return 0;
 }
 
-static int hostfs_write_end(struct file *file, struct address_space *mapping,
+static int hostfs_write_end(const struct kiocb *iocb,
+			    struct address_space *mapping,
 			    loff_t pos, unsigned len, unsigned copied,
 			    struct folio *folio, void *fsdata)
 {
@@ -468,7 +470,7 @@ static int hostfs_write_end(struct file *file, struct address_space *mapping,
 	int err;
 
 	buffer = kmap_local_folio(folio, from);
-	err = write_file(FILE_HOSTFS_I(file)->fd, &pos, buffer, copied);
+	err = write_file(FILE_HOSTFS_I(iocb->ki_filp)->fd, &pos, buffer, copied);
 	kunmap_local(buffer);
 
 	if (!folio_test_uptodate(folio) && err == folio_size(folio))
diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c
index 449a3fc1b8d90..7b95a3d2e2a6d 100644
--- a/fs/hpfs/file.c
+++ b/fs/hpfs/file.c
@@ -188,13 +188,14 @@ static void hpfs_write_failed(struct address_space *mapping, loff_t to)
 	hpfs_unlock(inode->i_sb);
 }
 
-static int hpfs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int hpfs_write_begin(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len,
+			    struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,
+	ret = cont_write_begin(iocb, mapping, pos, len, foliop, fsdata,
 				hpfs_get_block,
 				&hpfs_i(mapping->host)->mmu_private);
 	if (unlikely(ret))
@@ -203,13 +204,14 @@ static int hpfs_write_begin(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
-static int hpfs_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+static int hpfs_write_end(const struct kiocb *iocb,
+			  struct address_space *mapping,
+			  loff_t pos, unsigned len, unsigned copied,
+			  struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	int err;
-	err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	err = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata);
 	if (err < len)
 		hpfs_write_failed(mapping, pos + len);
 	if (!(err < 0)) {
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index b7994186fc665..9ddd67da0eeb5 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -311,7 +311,7 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	return retval;
 }
 
-static int hugetlbfs_write_begin(struct file *file,
+static int hugetlbfs_write_begin(const struct kiocb *iocb,
 			struct address_space *mapping,
 			loff_t pos, unsigned len,
 			struct folio **foliop, void **fsdata)
@@ -319,9 +319,10 @@ static int hugetlbfs_write_begin(struct file *file,
 	return -EINVAL;
 }
 
-static int hugetlbfs_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+static int hugetlbfs_write_end(const struct kiocb *iocb,
+			       struct address_space *mapping,
+			       loff_t pos, unsigned len, unsigned copied,
+			       struct folio *folio, void *fsdata)
 {
 	BUG();
 	return -EINVAL;
diff --git a/fs/inode.c b/fs/inode.c
index 99318b157a9a1..01ebdc40021e2 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -865,12 +865,12 @@ static void dispose_list(struct list_head *head)
  */
 void evict_inodes(struct super_block *sb)
 {
-	struct inode *inode, *next;
+	struct inode *inode;
 	LIST_HEAD(dispose);
 
 again:
 	spin_lock(&sb->s_inode_list_lock);
-	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
+	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
 		if (atomic_read(&inode->i_count))
 			continue;
 
@@ -1158,9 +1158,8 @@ void lockdep_annotate_inode_mutex_key(struct inode *inode)
 		/* Set new key only if filesystem hasn't already changed it */
 		if (lockdep_match_class(&inode->i_rwsem, &type->i_mutex_key)) {
 			/*
-			 * ensure nobody is actually holding i_mutex
+			 * ensure nobody is actually holding i_rwsem
 			 */
-			// mutex_destroy(&inode->i_mutex);
 			init_rwsem(&inode->i_rwsem);
 			lockdep_set_class(&inode->i_rwsem,
 					  &type->i_mutex_dir_key);
@@ -2615,7 +2614,7 @@ EXPORT_SYMBOL(inode_dio_finished);
  * proceed with a truncate or equivalent operation.
  *
  * Must be called under a lock that serializes taking new references
- * to i_dio_count, usually by inode->i_mutex.
+ * to i_dio_count, usually by inode->i_rwsem.
  */
 void inode_dio_wait(struct inode *inode)
 {
@@ -2633,7 +2632,7 @@ EXPORT_SYMBOL(inode_dio_wait_interruptible);
 /*
  * inode_set_flags - atomically set some inode flags
  *
- * Note: the caller should be holding i_mutex, or else be sure that
+ * Note: the caller should be holding i_rwsem exclusively, or else be sure that
  * they have exclusive access to the inode structure (i.e., while the
  * inode is being instantiated).  The reason for the cmpxchg() loop
  * --- which wouldn't be necessary if all code paths which modify
@@ -2641,7 +2640,7 @@ EXPORT_SYMBOL(inode_dio_wait_interruptible);
  * code path which doesn't today so we use cmpxchg() out of an abundance
  * of caution.
  *
- * In the long run, i_mutex is overkill, and we should probably look
+ * In the long run, i_rwsem is overkill, and we should probably look
  * at using the i_lock spinlock to protect i_flags, and then make sure
  * it is so documented in include/linux/fs.h and that all code follows
  * the locking convention!!
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index fb4519158f3a7..8f29be98a46ee 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -926,8 +926,7 @@ static bool iomap_write_end(struct iomap_iter *iter, size_t len, size_t copied,
 	if (srcmap->flags & IOMAP_F_BUFFER_HEAD) {
 		size_t bh_written;
 
-		bh_written = block_write_end(NULL, iter->inode->i_mapping, pos,
-					len, copied, folio, NULL);
+		bh_written = block_write_end(pos, len, copied, folio);
 		WARN_ON_ONCE(bh_written != copied && bh_written != 0);
 		return bh_written == copied;
 	}
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 13c18ccc13b0a..adec3af9bf8d1 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -21,12 +21,14 @@
 #include <linux/jffs2.h>
 #include "nodelist.h"
 
-static int jffs2_write_end(struct file *filp, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata);
-static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata);
+static int jffs2_write_end(const struct kiocb *iocb,
+			   struct address_space *mapping,
+			   loff_t pos, unsigned len, unsigned copied,
+			   struct folio *folio, void *fsdata);
+static int jffs2_write_begin(const struct kiocb *iocb,
+			     struct address_space *mapping,
+			     loff_t pos, unsigned len,
+			     struct folio **foliop, void **fsdata);
 static int jffs2_read_folio(struct file *filp, struct folio *folio);
 
 int jffs2_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
@@ -121,9 +123,10 @@ static int jffs2_read_folio(struct file *file, struct folio *folio)
 	return ret;
 }
 
-static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int jffs2_write_begin(const struct kiocb *iocb,
+			     struct address_space *mapping,
+			     loff_t pos, unsigned len,
+			     struct folio **foliop, void **fsdata)
 {
 	struct folio *folio;
 	struct inode *inode = mapping->host;
@@ -235,9 +238,10 @@ out_err:
 	return ret;
 }
 
-static int jffs2_write_end(struct file *filp, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+static int jffs2_write_end(const struct kiocb *iocb,
+			   struct address_space *mapping,
+			   loff_t pos, unsigned len, unsigned copied,
+			   struct folio *folio, void *fsdata)
 {
 	/* Actually commit the write from the page cache page we're looking at.
 	 * For now, we write the full page out each time. It sucks, but it's simple
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 60fc92dee24d2..083e7fa54709d 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -290,9 +290,10 @@ static void jfs_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-static int jfs_write_begin(struct file *file, struct address_space *mapping,
-				loff_t pos, unsigned len,
-				struct folio **foliop, void **fsdata)
+static int jfs_write_begin(const struct kiocb *iocb,
+			   struct address_space *mapping,
+			   loff_t pos, unsigned len,
+			   struct folio **foliop, void **fsdata)
 {
 	int ret;
 
@@ -303,13 +304,14 @@ static int jfs_write_begin(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
-static int jfs_write_end(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned copied, struct folio *folio,
-		void *fsdata)
+static int jfs_write_end(const struct kiocb *iocb,
+			 struct address_space *mapping,
+			 loff_t pos, unsigned len, unsigned copied,
+			 struct folio *folio, void *fsdata)
 {
 	int ret;
 
-	ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	ret = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata);
 	if (ret < len)
 		jfs_write_failed(mapping, pos + len);
 	return ret;
diff --git a/fs/libfs.c b/fs/libfs.c
index 89e47af931f1b..67bd8eea4af14 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -921,7 +921,7 @@ static int simple_read_folio(struct file *file, struct folio *folio)
 	return 0;
 }
 
-int simple_write_begin(struct file *file, struct address_space *mapping,
+int simple_write_begin(const struct kiocb *iocb, struct address_space *mapping,
 			loff_t pos, unsigned len,
 			struct folio **foliop, void **fsdata)
 {
@@ -946,7 +946,7 @@ EXPORT_SYMBOL(simple_write_begin);
 
 /**
  * simple_write_end - .write_end helper for non-block-device FSes
- * @file: See .write_end of address_space_operations
+ * @iocb: kernel I/O control block
  * @mapping: 		"
  * @pos: 		"
  * @len: 		"
@@ -957,7 +957,8 @@ EXPORT_SYMBOL(simple_write_begin);
  * simple_write_end does the minimum needed for updating a folio after
  * writing is done. It has the same API signature as the .write_end of
  * address_space_operations vector. So it can just be set onto .write_end for
- * FSes that don't need any other processing. i_mutex is assumed to be held.
+ * FSes that don't need any other processing. i_rwsem is assumed to be held
+ * exclusively.
  * Block based filesystems should use generic_write_end().
  * NOTE: Even though i_size might get updated by this function, mark_inode_dirty
  * is not called, so a filesystem that actually does store data in .write_inode
@@ -966,9 +967,10 @@ EXPORT_SYMBOL(simple_write_begin);
  *
  * Use *ONLY* with simple_read_folio()
  */
-static int simple_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+static int simple_write_end(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len, unsigned copied,
+			    struct folio *folio, void *fsdata)
 {
 	struct inode *inode = folio->mapping->host;
 	loff_t last_pos = pos + copied;
@@ -984,7 +986,7 @@ static int simple_write_end(struct file *file, struct address_space *mapping,
 	}
 	/*
 	 * No need to use i_size_read() here, the i_size
-	 * cannot change under us because we hold the i_mutex.
+	 * cannot change under us because we hold the i_rwsem.
 	 */
 	if (last_pos > inode->i_size)
 		i_size_write(inode, last_pos);
@@ -1594,13 +1596,17 @@ EXPORT_SYMBOL(generic_file_fsync);
 int generic_check_addressable(unsigned blocksize_bits, u64 num_blocks)
 {
 	u64 last_fs_block = num_blocks - 1;
-	u64 last_fs_page =
-		last_fs_block >> (PAGE_SHIFT - blocksize_bits);
+	u64 last_fs_page, max_bytes;
+
+	if (check_shl_overflow(num_blocks, blocksize_bits, &max_bytes))
+		return -EFBIG;
+
+	last_fs_page = (max_bytes >> PAGE_SHIFT) - 1;
 
 	if (unlikely(num_blocks == 0))
 		return 0;
 
-	if ((blocksize_bits < 9) || (blocksize_bits > PAGE_SHIFT))
+	if (blocksize_bits < 9)
 		return -EINVAL;
 
 	if ((last_fs_block > (sector_t)(~0ULL) >> (blocksize_bits - 9)) ||
diff --git a/fs/locks.c b/fs/locks.c
index 1619cddfa7a4d..559f02aa41722 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -712,7 +712,7 @@ static void __locks_wake_up_blocks(struct file_lock_core *blocker)
 		    fl->fl_lmops && fl->fl_lmops->lm_notify)
 			fl->fl_lmops->lm_notify(fl);
 		else
-			locks_wake_up(fl);
+			locks_wake_up_waiter(waiter);
 
 		/*
 		 * The setting of flc_blocker to NULL marks the "done"
@@ -1794,7 +1794,7 @@ generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **pr
 
 	/*
 	 * In the delegation case we need mutual exclusion with
-	 * a number of operations that take the i_mutex.  We trylock
+	 * a number of operations that take the i_rwsem.  We trylock
 	 * because delegations are an optional optimization, and if
 	 * there's some chance of a conflict--we'd rather not
 	 * bother, maybe that's a sign this just isn't a good file to
diff --git a/fs/minix/dir.c b/fs/minix/dir.c
index dd2a425b41f04..19052fc47e9ea 100644
--- a/fs/minix/dir.c
+++ b/fs/minix/dir.c
@@ -45,7 +45,7 @@ static void dir_commit_chunk(struct folio *folio, loff_t pos, unsigned len)
 	struct address_space *mapping = folio->mapping;
 	struct inode *dir = mapping->host;
 
-	block_write_end(NULL, mapping, pos, len, len, folio, NULL);
+	block_write_end(pos, len, len, folio);
 
 	if (pos+len > dir->i_size) {
 		i_size_write(dir, pos+len);
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index f007e389d5d29..df9d11479caf1 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -442,9 +442,10 @@ static void minix_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-static int minix_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int minix_write_begin(const struct kiocb *iocb,
+			     struct address_space *mapping,
+			     loff_t pos, unsigned len,
+			     struct folio **foliop, void **fsdata)
 {
 	int ret;
 
diff --git a/fs/namei.c b/fs/namei.c
index c26a7ee421849..ae95bea02bbc0 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1469,7 +1469,7 @@ static int __traverse_mounts(struct path *path, unsigned flags, bool *jumped,
 	int ret = 0;
 
 	while (flags & DCACHE_MANAGED_DENTRY) {
-		/* Allow the filesystem to manage the transit without i_mutex
+		/* Allow the filesystem to manage the transit without i_rwsem
 		 * being held. */
 		if (flags & DCACHE_MANAGE_TRANSIT) {
 			ret = path->dentry->d_op->d_manage(path, false);
@@ -2946,7 +2946,7 @@ EXPORT_SYMBOL(try_lookup_noperm);
  * Note that this routine is purely a helper for filesystem usage and should
  * not be called by generic code.  It does no permission checking.
  *
- * The caller must hold base->i_mutex.
+ * The caller must hold base->i_rwsem.
  */
 struct dentry *lookup_noperm(struct qstr *name, struct dentry *base)
 {
@@ -2972,7 +2972,7 @@ EXPORT_SYMBOL(lookup_noperm);
  *
  * This can be used for in-kernel filesystem clients such as file servers.
  *
- * The caller must hold base->i_mutex.
+ * The caller must hold base->i_rwsem.
  */
 struct dentry *lookup_one(struct mnt_idmap *idmap, struct qstr *name,
 			  struct dentry *base)
@@ -4551,13 +4551,13 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname)
  * @dentry:	victim
  * @delegated_inode: returns victim inode, if the inode is delegated.
  *
- * The caller must hold dir->i_mutex.
+ * The caller must hold dir->i_rwsem exclusively.
  *
  * If vfs_unlink discovers a delegation, it will return -EWOULDBLOCK and
  * return a reference to the inode in delegated_inode.  The caller
  * should then break the delegation on that inode and retry.  Because
  * breaking a delegation may take a long time, the caller should drop
- * dir->i_mutex before doing so.
+ * dir->i_rwsem before doing so.
  *
  * Alternatively, a caller may pass NULL for delegated_inode.  This may
  * be appropriate for callers that expect the underlying filesystem not
@@ -4616,7 +4616,7 @@ EXPORT_SYMBOL(vfs_unlink);
 
 /*
  * Make sure that the actual truncation of the file will occur outside its
- * directory's i_mutex.  Truncate can take a long time if there is a lot of
+ * directory's i_rwsem.  Truncate can take a long time if there is a lot of
  * writeout happening, and we don't want to prevent access to the directory
  * while waiting on the I/O.
  */
@@ -4794,13 +4794,13 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn
  * @new_dentry:	where to create the new link
  * @delegated_inode: returns inode needing a delegation break
  *
- * The caller must hold dir->i_mutex
+ * The caller must hold dir->i_rwsem exclusively.
  *
  * If vfs_link discovers a delegation on the to-be-linked file in need
  * of breaking, it will return -EWOULDBLOCK and return a reference to the
  * inode in delegated_inode.  The caller should then break the delegation
  * and retry.  Because breaking a delegation may take a long time, the
- * caller should drop the i_mutex before doing so.
+ * caller should drop the i_rwsem before doing so.
  *
  * Alternatively, a caller may pass NULL for delegated_inode.  This may
  * be appropriate for callers that expect the underlying filesystem not
@@ -4996,7 +4996,7 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
  *	c) we may have to lock up to _four_ objects - parents and victim (if it exists),
  *	   and source (if it's a non-directory or a subdirectory that moves to
  *	   different parent).
- *	   And that - after we got ->i_mutex on parents (until then we don't know
+ *	   And that - after we got ->i_rwsem on parents (until then we don't know
  *	   whether the target exists).  Solution: try to be smart with locking
  *	   order for inodes.  We rely on the fact that tree topology may change
  *	   only under ->s_vfs_rename_mutex _and_ that parent of the object we
@@ -5008,15 +5008,16 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
  *	   has no more than 1 dentry.  If "hybrid" objects will ever appear,
  *	   we'd better make sure that there's no link(2) for them.
  *	d) conversion from fhandle to dentry may come in the wrong moment - when
- *	   we are removing the target. Solution: we will have to grab ->i_mutex
+ *	   we are removing the target. Solution: we will have to grab ->i_rwsem
  *	   in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on
- *	   ->i_mutex on parents, which works but leads to some truly excessive
+ *	   ->i_rwsem on parents, which works but leads to some truly excessive
  *	   locking].
  */
 int vfs_rename(struct renamedata *rd)
 {
 	int error;
-	struct inode *old_dir = rd->old_dir, *new_dir = rd->new_dir;
+	struct inode *old_dir = d_inode(rd->old_parent);
+	struct inode *new_dir = d_inode(rd->new_parent);
 	struct dentry *old_dentry = rd->old_dentry;
 	struct dentry *new_dentry = rd->new_dentry;
 	struct inode **delegated_inode = rd->delegated_inode;
@@ -5275,10 +5276,10 @@ retry_deleg:
 	if (error)
 		goto exit5;
 
-	rd.old_dir	   = old_path.dentry->d_inode;
+	rd.old_parent	   = old_path.dentry;
 	rd.old_dentry	   = old_dentry;
 	rd.old_mnt_idmap   = mnt_idmap(old_path.mnt);
-	rd.new_dir	   = new_path.dentry->d_inode;
+	rd.new_parent	   = new_path.dentry;
 	rd.new_dentry	   = new_dentry;
 	rd.new_mnt_idmap   = mnt_idmap(new_path.mnt);
 	rd.delegated_inode = &delegated_inode;
diff --git a/fs/namespace.c b/fs/namespace.c
index c549bd39c210a..87c0061302051 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2022,7 +2022,7 @@ out:
  * detach_mounts allows lazily unmounting those mounts instead of
  * leaking them.
  *
- * The caller may hold dentry->d_inode->i_mutex.
+ * The caller may hold dentry->d_inode->i_rwsem.
  */
 void __detach_mounts(struct dentry *dentry)
 {
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 033feeab8c346..2bd557ca1af95 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -342,12 +342,14 @@ static bool nfs_want_read_modify_write(struct file *file, struct folio *folio,
  * If the writer ends up delaying the write, the writer needs to
  * increment the page use counts until he is done with the page.
  */
-static int nfs_write_begin(struct file *file, struct address_space *mapping,
+static int nfs_write_begin(const struct kiocb *iocb,
+			   struct address_space *mapping,
 			   loff_t pos, unsigned len, struct folio **foliop,
 			   void **fsdata)
 {
 	fgf_t fgp = FGP_WRITEBEGIN;
 	struct folio *folio;
+	struct file *file = iocb->ki_filp;
 	int once_thru = 0;
 	int ret;
 
@@ -377,10 +379,12 @@ start:
 	return ret;
 }
 
-static int nfs_write_end(struct file *file, struct address_space *mapping,
+static int nfs_write_end(const struct kiocb *iocb,
+			 struct address_space *mapping,
 			 loff_t pos, unsigned len, unsigned copied,
 			 struct folio *folio, void *fsdata)
 {
+	struct file *file = iocb->ki_filp;
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	unsigned offset = offset_in_folio(folio, pos);
 	int status;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index ee78b6fb17098..98ab55ba3ced7 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1867,7 +1867,6 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 			    struct svc_fh *tfhp, char *tname, int tlen)
 {
 	struct dentry	*fdentry, *tdentry, *odentry, *ndentry, *trap;
-	struct inode	*fdir, *tdir;
 	int		type = S_IFDIR;
 	__be32		err;
 	int		host_err;
@@ -1883,10 +1882,8 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 		goto out;
 
 	fdentry = ffhp->fh_dentry;
-	fdir = d_inode(fdentry);
 
 	tdentry = tfhp->fh_dentry;
-	tdir = d_inode(tdentry);
 
 	err = nfserr_perm;
 	if (!flen || isdotent(fname, flen) || !tlen || isdotent(tname, tlen))
@@ -1947,10 +1944,10 @@ retry:
 	} else {
 		struct renamedata rd = {
 			.old_mnt_idmap	= &nop_mnt_idmap,
-			.old_dir	= fdir,
+			.old_parent	= fdentry,
 			.old_dentry	= odentry,
 			.new_mnt_idmap	= &nop_mnt_idmap,
-			.new_dir	= tdir,
+			.new_parent	= tdentry,
 			.new_dentry	= ndentry,
 		};
 		int retries;
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index 9b7f8e9655a27..6ca3d74be1e16 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -96,7 +96,7 @@ static void nilfs_commit_chunk(struct folio *folio,
 	int err;
 
 	nr_dirty = nilfs_page_count_clean_buffers(folio, from, to);
-	copied = block_write_end(NULL, mapping, pos, len, len, folio, NULL);
+	copied = block_write_end(pos, len, len, folio);
 	if (pos + copied > dir->i_size)
 		i_size_write(dir, pos + copied);
 	if (IS_DIRSYNC(dir))
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 5cf7328d53605..87ddde159f0c9 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -218,7 +218,8 @@ void nilfs_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-static int nilfs_write_begin(struct file *file, struct address_space *mapping,
+static int nilfs_write_begin(const struct kiocb *iocb,
+			     struct address_space *mapping,
 			     loff_t pos, unsigned len,
 			     struct folio **foliop, void **fsdata)
 
@@ -237,7 +238,8 @@ static int nilfs_write_begin(struct file *file, struct address_space *mapping,
 	return err;
 }
 
-static int nilfs_write_end(struct file *file, struct address_space *mapping,
+static int nilfs_write_end(const struct kiocb *iocb,
+			   struct address_space *mapping,
 			   loff_t pos, unsigned len, unsigned copied,
 			   struct folio *folio, void *fsdata)
 {
@@ -248,7 +250,7 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping,
 
 	nr_dirty = nilfs_page_count_clean_buffers(folio, start,
 						  start + copied);
-	copied = generic_write_end(file, mapping, pos, len, copied, folio,
+	copied = generic_write_end(iocb, mapping, pos, len, copied, folio,
 				   fsdata);
 	nilfs_set_file_dirty(inode, nr_dirty);
 	err = nilfs_transaction_commit(inode->i_sb);
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index 22aecf6e23445..a9c61d0492cbd 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -560,8 +560,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
 		if (unlikely(err))
 			goto failed_folio;
 
-		block_write_end(NULL, inode->i_mapping, pos, blocksize,
-				blocksize, folio, NULL);
+		block_write_end(pos, blocksize, blocksize, folio);
 
 		folio_unlock(folio);
 		folio_put(folio);
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 2e321b84a1ed9..c12ae1fb8b370 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -162,13 +162,13 @@ static int ntfs_extend_initialized_size(struct file *file,
 		if (pos + len > new_valid)
 			len = new_valid - pos;
 
-		err = ntfs_write_begin(file, mapping, pos, len, &folio, NULL);
+		err = ntfs_write_begin(NULL, mapping, pos, len, &folio, NULL);
 		if (err)
 			goto out;
 
 		folio_zero_range(folio, zerofrom, folio_size(folio) - zerofrom);
 
-		err = ntfs_write_end(file, mapping, pos, len, len, folio, NULL);
+		err = ntfs_write_end(NULL, mapping, pos, len, len, folio, NULL);
 		if (err < 0)
 			goto out;
 		pos += len;
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index 4f9020df8912d..37cbbee7fa580 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -920,7 +920,7 @@ static int ntfs_get_block_write_begin(struct inode *inode, sector_t vbn,
 				  bh_result, create, GET_BLOCK_WRITE_BEGIN);
 }
 
-int ntfs_write_begin(struct file *file, struct address_space *mapping,
+int ntfs_write_begin(const struct kiocb *iocb, struct address_space *mapping,
 		     loff_t pos, u32 len, struct folio **foliop, void **fsdata)
 {
 	int err;
@@ -969,7 +969,8 @@ out:
 /*
  * ntfs_write_end - Address_space_operations::write_end.
  */
-int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos,
+int ntfs_write_end(const struct kiocb *iocb,
+		   struct address_space *mapping, loff_t pos,
 		   u32 len, u32 copied, struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
@@ -1001,7 +1002,7 @@ int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos,
 		folio_unlock(folio);
 		folio_put(folio);
 	} else {
-		err = generic_write_end(file, mapping, pos, len, copied, folio,
+		err = generic_write_end(iocb, mapping, pos, len, copied, folio,
 					fsdata);
 	}
 
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 9a25fec25f010..1296e6fcc779c 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -708,10 +708,12 @@ struct inode *ntfs_iget5(struct super_block *sb, const struct MFT_REF *ref,
 int ntfs_set_size(struct inode *inode, u64 new_size);
 int ntfs_get_block(struct inode *inode, sector_t vbn,
 		   struct buffer_head *bh_result, int create);
-int ntfs_write_begin(struct file *file, struct address_space *mapping,
-		     loff_t pos, u32 len, struct folio **foliop, void **fsdata);
-int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos,
-		   u32 len, u32 copied, struct folio *folio, void *fsdata);
+int ntfs_write_begin(const struct kiocb *iocb, struct address_space *mapping,
+		     loff_t pos, u32 len, struct folio **foliop,
+		     void **fsdata);
+int ntfs_write_end(const struct kiocb *iocb, struct address_space *mapping,
+		   loff_t pos, u32 len, u32 copied, struct folio *folio,
+		   void *fsdata);
 int ntfs3_write_inode(struct inode *inode, struct writeback_control *wbc);
 int ntfs_sync_inode(struct inode *inode);
 int inode_read_data(struct inode *inode, void *data, size_t bytes);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 40b6bce12951e..2203438738f68 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1856,7 +1856,8 @@ out:
 	return ret;
 }
 
-static int ocfs2_write_begin(struct file *file, struct address_space *mapping,
+static int ocfs2_write_begin(const struct kiocb *iocb,
+			     struct address_space *mapping,
 			     loff_t pos, unsigned len,
 			     struct folio **foliop, void **fsdata)
 {
@@ -2047,7 +2048,8 @@ out:
 	return copied;
 }
 
-static int ocfs2_write_end(struct file *file, struct address_space *mapping,
+static int ocfs2_write_end(const struct kiocb *iocb,
+			   struct address_space *mapping,
 			   loff_t pos, unsigned len, unsigned copied,
 			   struct folio *folio, void *fsdata)
 {
diff --git a/fs/omfs/file.c b/fs/omfs/file.c
index 98358d405b6ab..8d70f816b0c9d 100644
--- a/fs/omfs/file.c
+++ b/fs/omfs/file.c
@@ -310,9 +310,10 @@ static void omfs_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-static int omfs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int omfs_write_begin(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len,
+			    struct folio **foliop, void **fsdata)
 {
 	int ret;
 
diff --git a/fs/open.c b/fs/open.c
index 7828234a7caa4..b29d1e077164b 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1204,14 +1204,11 @@ struct file *kernel_file_open(const struct path *path, int flags,
 	if (IS_ERR(f))
 		return f;
 
-	f->f_path = *path;
-	error = do_dentry_open(f, NULL);
+	error = vfs_open(path, f);
 	if (error) {
 		fput(f);
 		return ERR_PTR(error);
 	}
-
-	fsnotify_open(f);
 	return f;
 }
 EXPORT_SYMBOL_GPL(kernel_file_open);
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index 08a6f372a352f..a7ab637767359 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -285,9 +285,10 @@ static int orangefs_read_folio(struct file *file, struct folio *folio)
 	return ret;
 }
 
-static int orangefs_write_begin(struct file *file,
-		struct address_space *mapping, loff_t pos, unsigned len,
-		struct folio **foliop, void **fsdata)
+static int orangefs_write_begin(const struct kiocb *iocb,
+				struct address_space *mapping, loff_t pos,
+				unsigned len, struct folio **foliop,
+				void **fsdata)
 {
 	struct orangefs_write_range *wr;
 	struct folio *folio;
@@ -340,9 +341,10 @@ okay:
 	return 0;
 }
 
-static int orangefs_write_end(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned copied, struct folio *folio,
-		void *fsdata)
+static int orangefs_write_end(const struct kiocb *iocb,
+			      struct address_space *mapping,
+			      loff_t pos, unsigned len, unsigned copied,
+			      struct folio *folio, void *fsdata)
 {
 	struct inode *inode = folio->mapping->host;
 	loff_t last_pos = pos + copied;
@@ -372,7 +374,7 @@ static int orangefs_write_end(struct file *file, struct address_space *mapping,
 	folio_unlock(folio);
 	folio_put(folio);
 
-	mark_inode_dirty_sync(file_inode(file));
+	mark_inode_dirty_sync(file_inode(iocb->ki_filp));
 	return copied;
 }
 
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index d7310fcf38881..8a3c0d18ec2ea 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -563,7 +563,7 @@ static int ovl_create_index(struct dentry *dentry, const struct ovl_fh *fh,
 	if (IS_ERR(index)) {
 		err = PTR_ERR(index);
 	} else {
-		err = ovl_do_rename(ofs, dir, temp, dir, index, 0);
+		err = ovl_do_rename(ofs, indexdir, temp, indexdir, index, 0);
 		dput(index);
 	}
 out:
@@ -762,7 +762,7 @@ static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c)
 {
 	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
 	struct inode *inode;
-	struct inode *udir = d_inode(c->destdir), *wdir = d_inode(c->workdir);
+	struct inode *wdir = d_inode(c->workdir);
 	struct path path = { .mnt = ovl_upper_mnt(ofs) };
 	struct dentry *temp, *upper, *trap;
 	struct ovl_cu_creds cc;
@@ -829,7 +829,7 @@ static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c)
 	if (IS_ERR(upper))
 		goto cleanup;
 
-	err = ovl_do_rename(ofs, wdir, temp, udir, upper, 0);
+	err = ovl_do_rename(ofs, c->workdir, temp, c->destdir, upper, 0);
 	dput(upper);
 	if (err)
 		goto cleanup;
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index fe493f3ed6b6f..4fc221ea6480c 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -107,7 +107,7 @@ out:
 }
 
 /* Caller must hold i_mutex on both workdir and dir */
-int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct inode *dir,
+int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct dentry *dir,
 			     struct dentry *dentry)
 {
 	struct inode *wdir = ofs->workdir->d_inode;
@@ -123,7 +123,7 @@ int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct inode *dir,
 	if (d_is_dir(dentry))
 		flags = RENAME_EXCHANGE;
 
-	err = ovl_do_rename(ofs, wdir, whiteout, dir, dentry, flags);
+	err = ovl_do_rename(ofs, ofs->workdir, whiteout, dir, dentry, flags);
 	if (err)
 		goto kill_whiteout;
 	if (flags)
@@ -384,7 +384,7 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry,
 	if (err)
 		goto out_cleanup;
 
-	err = ovl_do_rename(ofs, wdir, opaquedir, udir, upper, RENAME_EXCHANGE);
+	err = ovl_do_rename(ofs, workdir, opaquedir, upperdir, upper, RENAME_EXCHANGE);
 	if (err)
 		goto out_cleanup;
 
@@ -491,14 +491,14 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
 		if (err)
 			goto out_cleanup;
 
-		err = ovl_do_rename(ofs, wdir, newdentry, udir, upper,
+		err = ovl_do_rename(ofs, workdir, newdentry, upperdir, upper,
 				    RENAME_EXCHANGE);
 		if (err)
 			goto out_cleanup;
 
 		ovl_cleanup(ofs, wdir, upper);
 	} else {
-		err = ovl_do_rename(ofs, wdir, newdentry, udir, upper, 0);
+		err = ovl_do_rename(ofs, workdir, newdentry, upperdir, upper, 0);
 		if (err)
 			goto out_cleanup;
 	}
@@ -774,7 +774,7 @@ static int ovl_remove_and_whiteout(struct dentry *dentry,
 		goto out_dput_upper;
 	}
 
-	err = ovl_cleanup_and_whiteout(ofs, d_inode(upperdir), upper);
+	err = ovl_cleanup_and_whiteout(ofs, upperdir, upper);
 	if (err)
 		goto out_d_drop;
 
@@ -1246,8 +1246,8 @@ static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir,
 	if (err)
 		goto out_dput;
 
-	err = ovl_do_rename(ofs, old_upperdir->d_inode, olddentry,
-			    new_upperdir->d_inode, newdentry, flags);
+	err = ovl_do_rename(ofs, old_upperdir, olddentry,
+			    new_upperdir, newdentry, flags);
 	if (err)
 		goto out_dput;
 
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 497323128e5fc..42228d10f6b9b 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -355,19 +355,19 @@ static inline int ovl_do_remove_acl(struct ovl_fs *ofs, struct dentry *dentry,
 	return vfs_remove_acl(ovl_upper_mnt_idmap(ofs), dentry, acl_name);
 }
 
-static inline int ovl_do_rename(struct ovl_fs *ofs, struct inode *olddir,
-				struct dentry *olddentry, struct inode *newdir,
+static inline int ovl_do_rename(struct ovl_fs *ofs, struct dentry *olddir,
+				struct dentry *olddentry, struct dentry *newdir,
 				struct dentry *newdentry, unsigned int flags)
 {
 	int err;
 	struct renamedata rd = {
 		.old_mnt_idmap	= ovl_upper_mnt_idmap(ofs),
-		.old_dir 	= olddir,
-		.old_dentry 	= olddentry,
+		.old_parent	= olddir,
+		.old_dentry	= olddentry,
 		.new_mnt_idmap	= ovl_upper_mnt_idmap(ofs),
-		.new_dir 	= newdir,
-		.new_dentry 	= newdentry,
-		.flags 		= flags,
+		.new_parent	= newdir,
+		.new_dentry	= newdentry,
+		.flags		= flags,
 	};
 
 	pr_debug("rename(%pd2, %pd2, 0x%x)\n", olddentry, newdentry, flags);
@@ -828,7 +828,7 @@ static inline void ovl_copyflags(struct inode *from, struct inode *to)
 
 /* dir.c */
 extern const struct inode_operations ovl_dir_inode_operations;
-int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct inode *dir,
+int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct dentry *dir,
 			     struct dentry *dentry);
 struct ovl_cattr {
 	dev_t rdev;
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 474c80d210d18..68cca52ae2acb 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -1235,7 +1235,7 @@ int ovl_indexdir_cleanup(struct ovl_fs *ofs)
 			 * Whiteout orphan index to block future open by
 			 * handle after overlay nlink dropped to zero.
 			 */
-			err = ovl_cleanup_and_whiteout(ofs, dir, index);
+			err = ovl_cleanup_and_whiteout(ofs, indexdir, index);
 		} else {
 			/* Cleanup orphan index entries */
 			err = ovl_cleanup(ofs, dir, index);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index efbf0b2915516..4e7e0711a1ff7 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -580,7 +580,7 @@ static int ovl_check_rename_whiteout(struct ovl_fs *ofs)
 
 	/* Name is inline and stable - using snapshot as a copy helper */
 	take_dentry_name_snapshot(&name, temp);
-	err = ovl_do_rename(ofs, dir, temp, dir, dest, RENAME_WHITEOUT);
+	err = ovl_do_rename(ofs, workdir, temp, workdir, dest, RENAME_WHITEOUT);
 	if (err) {
 		if (err == -EINVAL)
 			err = 0;
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index dcccb4b4a66c7..2b4754c645eea 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -1115,7 +1115,7 @@ static void ovl_cleanup_index(struct dentry *dentry)
 	} else if (ovl_index_all(dentry->d_sb)) {
 		/* Whiteout orphan index to block future open by handle */
 		err = ovl_cleanup_and_whiteout(OVL_FS(dentry->d_sb),
-					       dir, index);
+					       indexdir, index);
 	} else {
 		/* Cleanup orphan index entries */
 		err = ovl_cleanup(ofs, dir, index);
diff --git a/fs/pipe.c b/fs/pipe.c
index 45077c37bad15..731622d0738d4 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -963,6 +963,11 @@ int create_pipe_files(struct file **res, int flags)
 	res[1] = f;
 	stream_open(inode, res[0]);
 	stream_open(inode, res[1]);
+
+	/* pipe groks IOCB_NOWAIT */
+	res[0]->f_mode |= FMODE_NOWAIT;
+	res[1]->f_mode |= FMODE_NOWAIT;
+
 	/*
 	 * Disable permission and pre-content events, but enable legacy
 	 * inotify events for legacy users.
@@ -997,9 +1002,6 @@ static int __do_pipe_flags(int *fd, struct file **files, int flags)
 	audit_fd_pair(fdr, fdw);
 	fd[0] = fdr;
 	fd[1] = fdw;
-	/* pipe groks IOCB_NOWAIT */
-	files[0]->f_mode |= FMODE_NOWAIT;
-	files[1]->f_mode |= FMODE_NOWAIT;
 	return 0;
 
  err_fdr:
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 37aa778d1af7b..9eeccff49b2ab 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -352,18 +352,9 @@ static int proc_fd_getattr(struct mnt_idmap *idmap,
 			u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_inode(path->dentry);
-	int rv = 0;
 
 	generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
-
-	/* If it's a directory, put the number of open fds there */
-	if (S_ISDIR(inode->i_mode)) {
-		rv = proc_readfd_count(inode, &stat->size);
-		if (rv < 0)
-			return rv;
-	}
-
-	return rv;
+	return proc_readfd_count(inode, &stat->size);
 }
 
 const struct inode_operations proc_fd_inode_operations = {
diff --git a/fs/read_write.c b/fs/read_write.c
index 0ef70e128c4af..81a9474dc3963 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -237,7 +237,7 @@ EXPORT_SYMBOL(generic_llseek_cookie);
  * @offset:	file offset to seek to
  * @whence:	type of seek
  *
- * This is a generic implemenation of ->llseek useable for all normal local
+ * This is a generic implementation of ->llseek useable for all normal local
  * filesystems.  It just updates the file offset to the value specified by
  * @offset and @whence.
  */
diff --git a/fs/select.c b/fs/select.c
index 9fb650d03d52e..082cf60c7e235 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -192,7 +192,7 @@ static int __pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *k
 	 * and is paired with smp_store_mb() in poll_schedule_timeout.
 	 */
 	smp_wmb();
-	pwq->triggered = 1;
+	WRITE_ONCE(pwq->triggered, 1);
 
 	/*
 	 * Perform the default wake up operation using a dummy
@@ -237,7 +237,7 @@ static int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
 	int rc = -EINTR;
 
 	set_current_state(state);
-	if (!pwq->triggered)
+	if (!READ_ONCE(pwq->triggered))
 		rc = schedule_hrtimeout_range(expires, slack, HRTIMER_MODE_ABS);
 	__set_current_state(TASK_RUNNING);
 
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index d3437f6644e33..34871a7f3e4b8 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -765,10 +765,10 @@ retry:
 	}
 
 	rd.old_mnt_idmap	= mnt_idmap(old_path->mnt),
-	rd.old_dir		= d_inode(old_parent),
+	rd.old_parent		= old_parent,
 	rd.old_dentry		= old_child,
 	rd.new_mnt_idmap	= mnt_idmap(new_path.mnt),
-	rd.new_dir		= new_path.dentry->d_inode,
+	rd.new_parent		= new_path.dentry,
 	rd.new_dentry		= new_dentry,
 	rd.flags		= flags,
 	rd.delegated_inode	= NULL,
diff --git a/fs/stack.c b/fs/stack.c
index f189201199443..d8c782e064e3e 100644
--- a/fs/stack.c
+++ b/fs/stack.c
@@ -3,7 +3,7 @@
 #include <linux/fs.h>
 #include <linux/fs_stack.h>
 
-/* does _NOT_ require i_mutex to be held.
+/* does _NOT_ require i_rwsem to be held.
  *
  * This function cannot be inlined since i_size_{read,write} is rather
  * heavy-weight on 32-bit systems
@@ -41,7 +41,7 @@ void fsstack_copy_inode_size(struct inode *dst, struct inode *src)
 	 * If CONFIG_SMP or CONFIG_PREEMPTION on 32-bit, it's vital for
 	 * fsstack_copy_inode_size() to hold some lock around
 	 * i_size_write(), otherwise i_size_read() may spin forever (see
-	 * include/linux/fs.h).  We don't necessarily hold i_mutex when this
+	 * include/linux/fs.h).  We don't necessarily hold i_rwsem when this
 	 * is called, so take i_lock for that case.
 	 *
 	 * And if on 32-bit, continue our effort to keep the two halves of
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index bf311c38d9a89..cee8bec1ea26d 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -404,7 +404,8 @@ static int allocate_budget(struct ubifs_info *c, struct folio *folio,
  * there is a plenty of flash space and the budget will be acquired quickly,
  * without forcing write-back. The slow path does not make this assumption.
  */
-static int ubifs_write_begin(struct file *file, struct address_space *mapping,
+static int ubifs_write_begin(const struct kiocb *iocb,
+			     struct address_space *mapping,
 			     loff_t pos, unsigned len,
 			     struct folio **foliop, void **fsdata)
 {
@@ -514,8 +515,9 @@ static void cancel_budget(struct ubifs_info *c, struct folio *folio,
 	}
 }
 
-static int ubifs_write_end(struct file *file, struct address_space *mapping,
-			   loff_t pos, unsigned len, unsigned copied,
+static int ubifs_write_end(const struct kiocb *iocb,
+			   struct address_space *mapping, loff_t pos,
+			   unsigned len, unsigned copied,
 			   struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 4386dd845e400..356b75676fa93 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -244,10 +244,12 @@ static void udf_readahead(struct readahead_control *rac)
 	mpage_readahead(rac, udf_get_block);
 }
 
-static int udf_write_begin(struct file *file, struct address_space *mapping,
+static int udf_write_begin(const struct kiocb *iocb,
+			   struct address_space *mapping,
 			   loff_t pos, unsigned len,
 			   struct folio **foliop, void **fsdata)
 {
+	struct file *file = iocb->ki_filp;
 	struct udf_inode_info *iinfo = UDF_I(file_inode(file));
 	struct folio *folio;
 	int ret;
@@ -271,15 +273,16 @@ static int udf_write_begin(struct file *file, struct address_space *mapping,
 	return 0;
 }
 
-static int udf_write_end(struct file *file, struct address_space *mapping,
+static int udf_write_end(const struct kiocb *iocb,
+			 struct address_space *mapping,
 			 loff_t pos, unsigned len, unsigned copied,
 			 struct folio *folio, void *fsdata)
 {
-	struct inode *inode = file_inode(file);
+	struct inode *inode = file_inode(iocb->ki_filp);
 	loff_t last_pos;
 
 	if (UDF_I(inode)->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB)
-		return generic_write_end(file, mapping, pos, len, copied, folio,
+		return generic_write_end(iocb, mapping, pos, len, copied, folio,
 					 fsdata);
 	last_pos = pos + copied;
 	if (last_pos > inode->i_size)
diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c
index 88d0062cfdb9e..0388a1bae326b 100644
--- a/fs/ufs/dir.c
+++ b/fs/ufs/dir.c
@@ -48,7 +48,7 @@ static void ufs_commit_chunk(struct folio *folio, loff_t pos, unsigned len)
 	struct inode *dir = mapping->host;
 
 	inode_inc_iversion(dir);
-	block_write_end(NULL, mapping, pos, len, len, folio, NULL);
+	block_write_end(pos, len, len, folio);
 	if (pos+len > dir->i_size) {
 		i_size_write(dir, pos+len);
 		mark_inode_dirty(dir);
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index 7dc38fdef2eab..8361c00e8fa6f 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -474,9 +474,10 @@ static void ufs_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-static int ufs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int ufs_write_begin(const struct kiocb *iocb,
+			   struct address_space *mapping,
+			   loff_t pos, unsigned len,
+			   struct folio **foliop, void **fsdata)
 {
 	int ret;
 
@@ -487,13 +488,14 @@ static int ufs_write_begin(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
-static int ufs_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+static int ufs_write_end(const struct kiocb *iocb,
+			 struct address_space *mapping,
+			 loff_t pos, unsigned len, unsigned copied,
+			 struct folio *folio, void *fsdata)
 {
 	int ret;
 
-	ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	ret = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata);
 	if (ret < len)
 		ufs_write_failed(mapping, pos + len);
 	return ret;
diff --git a/fs/vboxsf/file.c b/fs/vboxsf/file.c
index b492794f8e9a7..af01e3beaa42b 100644
--- a/fs/vboxsf/file.c
+++ b/fs/vboxsf/file.c
@@ -300,12 +300,13 @@ static int vboxsf_writepages(struct address_space *mapping,
 	return error;
 }
 
-static int vboxsf_write_end(struct file *file, struct address_space *mapping,
+static int vboxsf_write_end(const struct kiocb *iocb,
+			    struct address_space *mapping,
 			    loff_t pos, unsigned int len, unsigned int copied,
 			    struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
-	struct vboxsf_handle *sf_handle = file->private_data;
+	struct vboxsf_handle *sf_handle = iocb->ki_filp->private_data;
 	size_t from = offset_in_folio(folio, pos);
 	u32 nwritten = len;
 	u8 *buf;
diff --git a/fs/xattr.c b/fs/xattr.c
index 600ae97969cf2..8851a5ef34f5a 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -215,7 +215,7 @@ EXPORT_SYMBOL(__vfs_setxattr);
  *
  *  returns the result of the internal setxattr or setsecurity operations.
  *
- *  This function requires the caller to lock the inode's i_mutex before it
+ *  This function requires the caller to lock the inode's i_rwsem before it
  *  is executed. It also assumes that the caller will make the appropriate
  *  permission checks.
  */
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 0029ff880e274..b16b88bfbc3e7 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -262,14 +262,12 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 		struct folio **foliop, get_block_t *get_block);
 int __block_write_begin(struct folio *folio, loff_t pos, unsigned len,
 		get_block_t *get_block);
-int block_write_end(struct file *, struct address_space *,
-				loff_t, unsigned len, unsigned copied,
-				struct folio *, void *);
-int generic_write_end(struct file *, struct address_space *,
+int block_write_end(loff_t pos, unsigned len, unsigned copied, struct folio *);
+int generic_write_end(const struct kiocb *, struct address_space *,
 				loff_t, unsigned len, unsigned copied,
 				struct folio *, void *);
 void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to);
-int cont_write_begin(struct file *, struct address_space *, loff_t,
+int cont_write_begin(const struct kiocb *, struct address_space *, loff_t,
 			unsigned, struct folio **, void **,
 			get_block_t *, loff_t *);
 int generic_cont_expand_simple(struct inode *inode, loff_t size);
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 25c4a5afbd443..cfb0dd1ea49c7 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -230,7 +230,7 @@ struct handle_to_path_ctx {
  *    directory.  The name should be stored in the @name (with the
  *    understanding that it is already pointing to a %NAME_MAX+1 sized
  *    buffer.   get_name() should return %0 on success, a negative error code
- *    or error.  @get_name will be called without @parent->i_mutex held.
+ *    or error.  @get_name will be called without @parent->i_rwsem held.
  *
  * get_parent:
  *    @get_parent should find the parent directory for the given @child which
@@ -247,7 +247,7 @@ struct handle_to_path_ctx {
  *    @commit_metadata should commit metadata changes to stable storage.
  *
  * Locking rules:
- *    get_parent is called with child->d_inode->i_mutex down
+ *    get_parent is called with child->d_inode->i_rwsem down
  *    get_name is not (which is possibly inconsistent)
  */
 
diff --git a/include/linux/filelock.h b/include/linux/filelock.h
index c412ded9171ed..c2ce8ba05d068 100644
--- a/include/linux/filelock.h
+++ b/include/linux/filelock.h
@@ -175,9 +175,14 @@ static inline bool lock_is_write(struct file_lock *fl)
 	return fl->c.flc_type == F_WRLCK;
 }
 
+static inline void locks_wake_up_waiter(struct file_lock_core *flc)
+{
+	wake_up(&flc->flc_wait);
+}
+
 static inline void locks_wake_up(struct file_lock *fl)
 {
-	wake_up(&fl->c.flc_wait);
+	locks_wake_up_waiter(&fl->c);
 }
 
 static inline bool locks_can_async_lock(const struct file_operations *fops)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ea5b14fe424d9..1b5212de57021 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -446,10 +446,10 @@ struct address_space_operations {
 
 	void (*readahead)(struct readahead_control *);
 
-	int (*write_begin)(struct file *, struct address_space *mapping,
+	int (*write_begin)(const struct kiocb *, struct address_space *mapping,
 				loff_t pos, unsigned len,
 				struct folio **foliop, void **fsdata);
-	int (*write_end)(struct file *, struct address_space *mapping,
+	int (*write_end)(const struct kiocb *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned copied,
 				struct folio *folio, void *fsdata);
 
@@ -839,7 +839,7 @@ static inline void inode_fake_hash(struct inode *inode)
 }
 
 /*
- * inode->i_mutex nesting subclasses for the lock validator:
+ * inode->i_rwsem nesting subclasses for the lock validator:
  *
  * 0: the object of the current VFS operation
  * 1: parent
@@ -991,7 +991,7 @@ static inline loff_t i_size_read(const struct inode *inode)
 
 /*
  * NOTE: unlike i_size_read(), i_size_write() does need locking around it
- * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount
+ * (normally i_rwsem), otherwise on 32bit/SMP an update of i_size_seqcount
  * can be lost, resulting in subsequent i_size_read() calls spinning forever.
  */
 static inline void i_size_write(struct inode *inode, loff_t i_size)
@@ -1924,7 +1924,7 @@ static inline void sb_end_intwrite(struct super_block *sb)
  * freeze protection should be the outermost lock. In particular, we have:
  *
  * sb_start_write
- *   -> i_mutex			(write path, truncate, directory ops, ...)
+ *   -> i_rwsem			(write path, truncate, directory ops, ...)
  *   -> s_umount		(freeze_super, thaw_super)
  */
 static inline void sb_start_write(struct super_block *sb)
@@ -2007,20 +2007,20 @@ int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *,
 /**
  * struct renamedata - contains all information required for renaming
  * @old_mnt_idmap:     idmap of the old mount the inode was found from
- * @old_dir:           parent of source
+ * @old_parent:        parent of source
  * @old_dentry:                source
  * @new_mnt_idmap:     idmap of the new mount the inode was found from
- * @new_dir:           parent of destination
+ * @new_parent:        parent of destination
  * @new_dentry:                destination
  * @delegated_inode:   returns an inode needing a delegation break
  * @flags:             rename flags
  */
 struct renamedata {
 	struct mnt_idmap *old_mnt_idmap;
-	struct inode *old_dir;
+	struct dentry *old_parent;
 	struct dentry *old_dentry;
 	struct mnt_idmap *new_mnt_idmap;
-	struct inode *new_dir;
+	struct dentry *new_parent;
 	struct dentry *new_dentry;
 	struct inode **delegated_inode;
 	unsigned int flags;
@@ -3605,9 +3605,10 @@ extern void locked_recursive_removal(struct dentry *,
 extern int noop_fsync(struct file *, loff_t, loff_t, int);
 extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter);
 extern int simple_empty(struct dentry *);
-extern int simple_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata);
+extern int simple_write_begin(const struct kiocb *iocb,
+			      struct address_space *mapping,
+			      loff_t pos, unsigned len,
+			      struct folio **foliop, void **fsdata);
 extern const struct address_space_operations ram_aops;
 extern int always_delete_dentry(const struct dentry *);
 extern struct inode *alloc_anon_inode(struct super_block *);
diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
index a19e4bd32e4d3..7773eb870039c 100644
--- a/include/linux/fs_context.h
+++ b/include/linux/fs_context.h
@@ -200,7 +200,7 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt,
  */
 #define infof(fc, fmt, ...) __logfc(fc, 'i', fmt, ## __VA_ARGS__)
 #define info_plog(p, fmt, ...) __plog(p, 'i', fmt, ## __VA_ARGS__)
-#define infofc(p, fmt, ...) __plog((&(fc)->log), 'i', fmt, ## __VA_ARGS__)
+#define infofc(fc, fmt, ...) __plog((&(fc)->log), 'i', fmt, ## __VA_ARGS__)
 
 /**
  * warnf - Store supplementary warning message
diff --git a/include/linux/fs_stack.h b/include/linux/fs_stack.h
index 2b1f74b240707..0cc2fa283305b 100644
--- a/include/linux/fs_stack.h
+++ b/include/linux/fs_stack.h
@@ -3,7 +3,7 @@
 #define _LINUX_FS_STACK_H
 
 /* This file defines generic functions used primarily by stackable
- * filesystems; none of these functions require i_mutex to be held.
+ * filesystems; none of these functions require i_rwsem to be held.
  */
 
 #include <linux/fs.h>
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index f43f075852c06..185bd8196503d 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -442,7 +442,6 @@ size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset,
 			size_t max_size, size_t max_segs);
 void netfs_prepare_write_failed(struct netfs_io_subrequest *subreq);
 void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error);
-void netfs_queue_write_request(struct netfs_io_subrequest *subreq);
 
 int netfs_start_io_read(struct inode *inode);
 void netfs_end_io_read(struct inode *inode);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e63fbfbd5b0f3..ce2bcdcadb733 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -751,6 +751,33 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
 		fgf_t fgp_flags, gfp_t gfp);
 
 /**
+ * write_begin_get_folio - Get folio for write_begin with flags.
+ * @iocb: The kiocb passed from write_begin (may be NULL).
+ * @mapping: The address space to search.
+ * @index: The page cache index.
+ * @len: Length of data being written.
+ *
+ * This is a helper for filesystem write_begin() implementations.
+ * It wraps __filemap_get_folio(), setting appropriate flags in
+ * the write begin context.
+ *
+ * Return: A folio or an ERR_PTR.
+ */
+static inline struct folio *write_begin_get_folio(const struct kiocb *iocb,
+		  struct address_space *mapping, pgoff_t index, size_t len)
+{
+        fgf_t fgp_flags = FGP_WRITEBEGIN;
+
+        fgp_flags |= fgf_set_order(len);
+
+        if (iocb && iocb->ki_flags & IOCB_DONTCACHE)
+                fgp_flags |= FGP_DONTCACHE;
+
+        return __filemap_get_folio(mapping, index, fgp_flags,
+                                   mapping_gfp_mask(mapping));
+}
+
+/**
  * filemap_get_folio - Find and get a folio.
  * @mapping: The address_space to search.
  * @index: The page index.
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 06cc8888199e8..c334f82ed385a 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -19,7 +19,7 @@ static inline struct quota_info *sb_dqopt(struct super_block *sb)
 	return &sb->s_dquot;
 }
 
-/* i_mutex must being held */
+/* i_rwsem must being held */
 static inline bool is_quota_modification(struct mnt_idmap *idmap,
 					 struct inode *inode, struct iattr *ia)
 {
diff --git a/io_uring/openclose.c b/io_uring/openclose.c
index 83e36ad4e31be..d70700e5cef88 100644
--- a/io_uring/openclose.c
+++ b/io_uring/openclose.c
@@ -416,8 +416,6 @@ int io_pipe(struct io_kiocb *req, unsigned int issue_flags)
 	ret = create_pipe_files(files, p->flags);
 	if (ret)
 		return ret;
-	files[0]->f_mode |= FMODE_NOWAIT;
-	files[1]->f_mode |= FMODE_NOWAIT;
 
 	if (!!p->file_slot)
 		ret = io_pipe_fixed(req, files, issue_flags);
diff --git a/mm/filemap.c b/mm/filemap.c
index bada249b9fb76..ba089d75fc868 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -4109,7 +4109,7 @@ retry:
 			break;
 		}
 
-		status = a_ops->write_begin(file, mapping, pos, bytes,
+		status = a_ops->write_begin(iocb, mapping, pos, bytes,
 						&folio, &fsdata);
 		if (unlikely(status < 0))
 			break;
@@ -4130,7 +4130,7 @@ retry:
 		copied = copy_folio_from_iter_atomic(folio, offset, bytes, i);
 		flush_dcache_folio(folio);
 
-		status = a_ops->write_end(file, mapping, pos, bytes, copied,
+		status = a_ops->write_end(iocb, mapping, pos, bytes, copied,
 						folio, fsdata);
 		if (unlikely(status != copied)) {
 			iov_iter_revert(i, copied - max(status, 0L));
diff --git a/mm/shmem.c b/mm/shmem.c
index cbcb573cde061..457355cda4a9d 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3270,9 +3270,9 @@ static const struct inode_operations shmem_symlink_inode_operations;
 static const struct inode_operations shmem_short_symlink_operations;
 
 static int
-shmem_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+shmem_write_begin(const struct kiocb *iocb, struct address_space *mapping,
+		  loff_t pos, unsigned len,
+		  struct folio **foliop, void **fsdata)
 {
 	struct inode *inode = mapping->host;
 	struct shmem_inode_info *info = SHMEM_I(inode);
@@ -3304,9 +3304,9 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
 }
 
 static int
-shmem_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+shmem_write_end(const struct kiocb *iocb, struct address_space *mapping,
+		loff_t pos, unsigned len, unsigned copied,
+		struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;