diff --git a/Documentation/filesystems/nfs/exporting.rst b/Documentation/filesystems/nfs/exporting.rst
index de64d2d002a2..a01d9b9b5bc3 100644
--- a/Documentation/filesystems/nfs/exporting.rst
+++ b/Documentation/filesystems/nfs/exporting.rst
@@ -119,43 +119,11 @@ For a filesystem to be exportable it must:
 
 A file system implementation declares that instances of the filesystem
 are exportable by setting the s_export_op field in the struct
-super_block.  This field must point to a "struct export_operations"
-struct which has the following members:
+super_block.  This field must point to a struct export_operations
+which has the following members:
 
-  encode_fh (mandatory)
-    Takes a dentry and creates a filehandle fragment which may later be used
-    to find or create a dentry for the same object.
-
-  fh_to_dentry (mandatory)
-    Given a filehandle fragment, this should find the implied object and
-    create a dentry for it (possibly with d_obtain_alias).
-
-  fh_to_parent (optional but strongly recommended)
-    Given a filehandle fragment, this should find the parent of the
-    implied object and create a dentry for it (possibly with
-    d_obtain_alias).  May fail if the filehandle fragment is too small.
-
-  get_parent (optional but strongly recommended)
-    When given a dentry for a directory, this should return  a dentry for
-    the parent.  Quite possibly the parent dentry will have been allocated
-    by d_alloc_anon.  The default get_parent function just returns an error
-    so any filehandle lookup that requires finding a parent will fail.
-    ->lookup("..") is *not* used as a default as it can leave ".." entries
-    in the dcache which are too messy to work with.
-
-  get_name (optional)
-    When given a parent dentry and a child dentry, this should find a name
-    in the directory identified by the parent dentry, which leads to the
-    object identified by the child dentry.  If no get_name function is
-    supplied, a default implementation is provided which uses vfs_readdir
-    to find potential names, and matches inode numbers to find the correct
-    match.
-
-  flags
-    Some filesystems may need to be handled differently than others. The
-    export_operations struct also includes a flags field that allows the
-    filesystem to communicate such information to nfsd. See the Export
-    Operations Flags section below for more explanation.
+.. kernel-doc:: include/linux/exportfs.h
+   :identifiers: struct export_operations
 
 A filehandle fragment consists of an array of 1 or more 4byte words,
 together with a one byte "type".
diff --git a/fs/9p/acl.c b/fs/9p/acl.c
index 633da5e37299..ae7e7cf7523a 100644
--- a/fs/9p/acl.c
+++ b/fs/9p/acl.c
@@ -167,17 +167,11 @@ int v9fs_iop_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 		if (retval)
 			goto err_out;
 
-		size = posix_acl_xattr_size(acl->a_count);
-
-		value = kzalloc(size, GFP_NOFS);
+		value = posix_acl_to_xattr(&init_user_ns, acl, &size, GFP_NOFS);
 		if (!value) {
 			retval = -ENOMEM;
 			goto err_out;
 		}
-
-		retval = posix_acl_to_xattr(&init_user_ns, acl, value, size);
-		if (retval < 0)
-			goto err_out;
 	}
 
 	/*
@@ -257,13 +251,10 @@ static int v9fs_set_acl(struct p9_fid *fid, int type, struct posix_acl *acl)
 		return 0;
 
 	/* Set a setxattr request to server */
-	size = posix_acl_xattr_size(acl->a_count);
-	buffer = kmalloc(size, GFP_KERNEL);
+	buffer = posix_acl_to_xattr(&init_user_ns, acl, &size, GFP_KERNEL);
 	if (!buffer)
 		return -ENOMEM;
-	retval = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
-	if (retval < 0)
-		goto err_free_out;
+
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name = XATTR_NAME_POSIX_ACL_ACCESS;
@@ -275,7 +266,6 @@ static int v9fs_set_acl(struct p9_fid *fid, int type, struct posix_acl *acl)
 		BUG();
 	}
 	retval = v9fs_fid_xattr_set(fid, name, buffer, size, 0);
-err_free_out:
 	kfree(buffer);
 	return retval;
 }
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index c336e2ab7f8a..e55b686fe1ab 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -57,7 +57,8 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type, bool rcu)
 int __btrfs_set_acl(struct btrfs_trans_handle *trans, struct inode *inode,
 		    struct posix_acl *acl, int type)
 {
-	int ret, size = 0;
+	int ret;
+	size_t size = 0;
 	const char *name;
 	char AUTO_KFREE(value);
 
@@ -77,20 +78,15 @@ int __btrfs_set_acl(struct btrfs_trans_handle *trans, struct inode *inode,
 	if (acl) {
 		unsigned int nofs_flag;
 
-		size = posix_acl_xattr_size(acl->a_count);
 		/*
 		 * We're holding a transaction handle, so use a NOFS memory
 		 * allocation context to avoid deadlock if reclaim happens.
 		 */
 		nofs_flag = memalloc_nofs_save();
-		value = kmalloc(size, GFP_KERNEL);
+		value = posix_acl_to_xattr(&init_user_ns, acl, &size, GFP_KERNEL);
 		memalloc_nofs_restore(nofs_flag);
 		if (!value)
 			return -ENOMEM;
-
-		ret = posix_acl_to_xattr(&init_user_ns, acl, value, size);
-		if (ret < 0)
-			return ret;
 	}
 
 	if (trans)
diff --git a/fs/buffer.c b/fs/buffer.c
index 838c0c571022..fd53b806ab7e 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2354,7 +2354,7 @@ bool block_is_partially_uptodate(struct folio *folio, size_t from, size_t count)
 	if (!head)
 		return false;
 	blocksize = head->b_size;
-	to = min_t(unsigned, folio_size(folio) - from, count);
+	to = min(folio_size(folio) - from, count);
 	to = from + to;
 	if (from < blocksize && to > folio_size(folio) - blocksize)
 		return false;
@@ -2948,6 +2948,10 @@ bool try_to_free_buffers(struct folio *folio)
 	if (folio_test_writeback(folio))
 		return false;
 
+	/* Misconfigured folio check */
+	if (WARN_ON_ONCE(!folio_buffers(folio)))
+		return true;
+
 	if (mapping == NULL) {		/* can this still happen? */
 		ret = drop_buffers(folio, &buffers_to_free);
 		goto out;
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index 1564eacc253d..85d3dd48b167 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -90,7 +90,8 @@ retry:
 int ceph_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 		 struct posix_acl *acl, int type)
 {
-	int ret = 0, size = 0;
+	int ret = 0;
+	size_t size = 0;
 	const char *name = NULL;
 	char *value = NULL;
 	struct iattr newattrs;
@@ -126,16 +127,11 @@ int ceph_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 	}
 
 	if (acl) {
-		size = posix_acl_xattr_size(acl->a_count);
-		value = kmalloc(size, GFP_NOFS);
+		value = posix_acl_to_xattr(&init_user_ns, acl, &size, GFP_NOFS);
 		if (!value) {
 			ret = -ENOMEM;
 			goto out;
 		}
-
-		ret = posix_acl_to_xattr(&init_user_ns, acl, value, size);
-		if (ret < 0)
-			goto out_free;
 	}
 
 	if (new_mode != old_mode) {
@@ -172,7 +168,7 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
 	struct posix_acl *acl, *default_acl;
 	size_t val_size1 = 0, val_size2 = 0;
 	struct ceph_pagelist *pagelist = NULL;
-	void *tmp_buf = NULL;
+	void *tmp_buf1 = NULL, *tmp_buf2 = NULL;
 	int err;
 
 	err = posix_acl_create(dir, mode, &default_acl, &acl);
@@ -192,15 +188,7 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
 	if (!default_acl && !acl)
 		return 0;
 
-	if (acl)
-		val_size1 = posix_acl_xattr_size(acl->a_count);
-	if (default_acl)
-		val_size2 = posix_acl_xattr_size(default_acl->a_count);
-
 	err = -ENOMEM;
-	tmp_buf = kmalloc(max(val_size1, val_size2), GFP_KERNEL);
-	if (!tmp_buf)
-		goto out_err;
 	pagelist = ceph_pagelist_alloc(GFP_KERNEL);
 	if (!pagelist)
 		goto out_err;
@@ -213,34 +201,39 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
 
 	if (acl) {
 		size_t len = strlen(XATTR_NAME_POSIX_ACL_ACCESS);
+
+		err = -ENOMEM;
+		tmp_buf1 = posix_acl_to_xattr(&init_user_ns, acl,
+					      &val_size1, GFP_KERNEL);
+		if (!tmp_buf1)
+			goto out_err;
 		err = ceph_pagelist_reserve(pagelist, len + val_size1 + 8);
 		if (err)
 			goto out_err;
 		ceph_pagelist_encode_string(pagelist, XATTR_NAME_POSIX_ACL_ACCESS,
 					    len);
-		err = posix_acl_to_xattr(&init_user_ns, acl,
-					 tmp_buf, val_size1);
-		if (err < 0)
-			goto out_err;
 		ceph_pagelist_encode_32(pagelist, val_size1);
-		ceph_pagelist_append(pagelist, tmp_buf, val_size1);
+		ceph_pagelist_append(pagelist, tmp_buf1, val_size1);
 	}
 	if (default_acl) {
 		size_t len = strlen(XATTR_NAME_POSIX_ACL_DEFAULT);
+
+		err = -ENOMEM;
+		tmp_buf2 = posix_acl_to_xattr(&init_user_ns, default_acl,
+					      &val_size2, GFP_KERNEL);
+		if (!tmp_buf2)
+			goto out_err;
 		err = ceph_pagelist_reserve(pagelist, len + val_size2 + 8);
 		if (err)
 			goto out_err;
 		ceph_pagelist_encode_string(pagelist,
 					  XATTR_NAME_POSIX_ACL_DEFAULT, len);
-		err = posix_acl_to_xattr(&init_user_ns, default_acl,
-					 tmp_buf, val_size2);
-		if (err < 0)
-			goto out_err;
 		ceph_pagelist_encode_32(pagelist, val_size2);
-		ceph_pagelist_append(pagelist, tmp_buf, val_size2);
+		ceph_pagelist_append(pagelist, tmp_buf2, val_size2);
 	}
 
-	kfree(tmp_buf);
+	kfree(tmp_buf1);
+	kfree(tmp_buf2);
 
 	as_ctx->acl = acl;
 	as_ctx->default_acl = default_acl;
@@ -250,7 +243,8 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
 out_err:
 	posix_acl_release(acl);
 	posix_acl_release(default_acl);
-	kfree(tmp_buf);
+	kfree(tmp_buf1);
+	kfree(tmp_buf2);
 	if (pagelist)
 		ceph_pagelist_release(pagelist);
 	return err;
diff --git a/fs/char_dev.c b/fs/char_dev.c
index c2ddb998f3c9..bf7b32650e54 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -10,6 +10,7 @@
 #include <linux/kdev_t.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/cleanup.h>
 
 #include <linux/major.h>
 #include <linux/errno.h>
@@ -97,7 +98,8 @@ static struct char_device_struct *
 __register_chrdev_region(unsigned int major, unsigned int baseminor,
 			   int minorct, const char *name)
 {
-	struct char_device_struct *cd, *curr, *prev = NULL;
+	struct char_device_struct *cd __free(kfree) = NULL;
+	struct char_device_struct *curr, *prev = NULL;
 	int ret;
 	int i;
 
@@ -117,14 +119,14 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor,
 	if (cd == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	mutex_lock(&chrdevs_lock);
+	guard(mutex)(&chrdevs_lock);
 
 	if (major == 0) {
 		ret = find_dynamic_major();
 		if (ret < 0) {
 			pr_err("CHRDEV \"%s\" dynamic allocation region is full\n",
 			       name);
-			goto out;
+			return ERR_PTR(ret);
 		}
 		major = ret;
 	}
@@ -144,7 +146,7 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor,
 		if (curr->baseminor >= baseminor + minorct)
 			break;
 
-		goto out;
+		return ERR_PTR(ret);
 	}
 
 	cd->major = major;
@@ -160,12 +162,7 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor,
 		prev->next = cd;
 	}
 
-	mutex_unlock(&chrdevs_lock);
-	return cd;
-out:
-	mutex_unlock(&chrdevs_lock);
-	kfree(cd);
-	return ERR_PTR(ret);
+	return_ptr(cd);
 }
 
 static struct char_device_struct *
@@ -343,7 +340,7 @@ void __unregister_chrdev(unsigned int major, unsigned int baseminor,
 	kfree(cd);
 }
 
-static DEFINE_SPINLOCK(cdev_lock);
+static __cacheline_aligned_in_smp DEFINE_SPINLOCK(cdev_lock);
 
 static struct kobject *cdev_get(struct cdev *p)
 {
diff --git a/fs/dcache.c b/fs/dcache.c
index 66dd1bb830d1..7088df2d042c 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -3237,10 +3237,7 @@ EXPORT_SYMBOL(d_parent_ino);
 static __initdata unsigned long dhash_entries;
 static int __init set_dhash_entries(char *str)
 {
-	if (!str)
-		return 0;
-	dhash_entries = simple_strtoul(str, &str, 0);
-	return 1;
+	return kstrtoul(str, 0, &dhash_entries) == 0;
 }
 __setup("dhash_entries=", set_dhash_entries);
 
diff --git a/fs/exec.c b/fs/exec.c
index 9d5ebc9d15b0..d0606e53376f 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -555,7 +555,7 @@ int copy_string_kernel(const char *arg, struct linux_binprm *bprm)
 		return -E2BIG;
 
 	while (len > 0) {
-		unsigned int bytes_to_copy = min_t(unsigned int, len,
+		unsigned int bytes_to_copy = min(len,
 				min_not_zero(offset_in_page(pos), PAGE_SIZE));
 		struct page *page;
 
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 56d50fd3310b..e817a758801d 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4276,8 +4276,7 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 		 * get the corresponding group metadata to work with.
 		 * For this we have goto again loop.
 		 */
-		thisgrp_len = min_t(unsigned int, (unsigned int)len,
-			EXT4_BLOCKS_PER_GROUP(sb) - EXT4_C2B(sbi, blkoff));
+		thisgrp_len = min(len, EXT4_BLOCKS_PER_GROUP(sb) - EXT4_C2B(sbi, blkoff));
 		clen = EXT4_NUM_B2C(sbi, thisgrp_len);
 
 		if (!ext4_sb_block_valid(sb, NULL, block, thisgrp_len)) {
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 050f26168d97..76842f0957b5 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1479,7 +1479,7 @@ static void ext4_update_super(struct super_block *sb,
 
 	/* Update the global fs size fields */
 	sbi->s_groups_count += flex_gd->count;
-	sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count,
+	sbi->s_blockfile_groups = min(sbi->s_groups_count,
 			(EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
 
 	/* Update the reserved block counts only once the new group is
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index a6241ffb8639..a8d2460b527a 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4837,7 +4837,7 @@ static int ext4_check_geometry(struct super_block *sb,
 		return -EINVAL;
 	}
 	sbi->s_groups_count = blocks_count;
-	sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count,
+	sbi->s_blockfile_groups = min(sbi->s_groups_count,
 			(EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
 	if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) !=
 	    le32_to_cpu(es->s_inodes_count)) {
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 0e97ef6c2327..07d95f1442c8 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -1355,7 +1355,7 @@ found:
 
 		/* Fill the long name slots. */
 		for (i = 0; i < long_bhs; i++) {
-			int copy = min_t(int, sb->s_blocksize - offset, size);
+			int copy = umin(sb->s_blocksize - offset, size);
 			memcpy(bhs[i]->b_data + offset, slots, copy);
 			mark_buffer_dirty_inode(bhs[i], dir);
 			offset = 0;
@@ -1366,7 +1366,7 @@ found:
 			err = fat_sync_bhs(bhs, long_bhs);
 		if (!err && i < nr_bhs) {
 			/* Fill the short name slot. */
-			int copy = min_t(int, sb->s_blocksize - offset, size);
+			int copy = umin(sb->s_blocksize - offset, size);
 			memcpy(bhs[i]->b_data + offset, slots, copy);
 			mark_buffer_dirty_inode(bhs[i], dir);
 			if (IS_DIRSYNC(dir))
diff --git a/fs/fat/file.c b/fs/fat/file.c
index afc0e3ad6536..124d9c5431c8 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -141,8 +141,7 @@ static int fat_ioctl_fitrim(struct inode *inode, unsigned long arg)
 	if (copy_from_user(&range, user_range, sizeof(range)))
 		return -EFAULT;
 
-	range.minlen = max_t(unsigned int, range.minlen,
-			     bdev_discard_granularity(sb->s_bdev));
+	range.minlen = max(range.minlen, bdev_discard_granularity(sb->s_bdev));
 
 	err = fat_trim_fs(inode, &range);
 	if (err < 0)
diff --git a/fs/file_table.c b/fs/file_table.c
index cd4a3db4659a..34244fccf2ed 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -176,6 +176,11 @@ static int init_file(struct file *f, int flags, const struct cred *cred)
 
 	f->f_flags	= flags;
 	f->f_mode	= OPEN_FMODE(flags);
+	/*
+	 * Disable permission and pre-content events for all files by default.
+	 * They may be enabled later by fsnotify_open_perm_and_set_mode().
+	 */
+	file_set_fsnotify_mode(f, FMODE_NONOTIFY_PERM);
 
 	f->f_op		= NULL;
 	f->f_mapping	= NULL;
@@ -197,11 +202,6 @@ static int init_file(struct file *f, int flags, const struct cred *cred)
 	 * refcount bumps we should reinitialize the reused file first.
 	 */
 	file_ref_init(&f->f_ref, 1);
-	/*
-	 * Disable permission and pre-content events for all files by default.
-	 * They may be enabled later by fsnotify_open_perm_and_set_mode().
-	 */
-	file_set_fsnotify_mode(f, FMODE_NONOTIFY_PERM);
 	return 0;
 }
 
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index b8c46c5a38a0..394875d06fd6 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -6,6 +6,7 @@
 #include <linux/path.h>
 #include <linux/slab.h>
 #include <linux/fs_struct.h>
+#include <linux/init_task.h>
 #include "internal.h"
 
 /*
diff --git a/fs/fuse/acl.c b/fs/fuse/acl.c
index 8f484b105f13..cbde6ac1add3 100644
--- a/fs/fuse/acl.c
+++ b/fs/fuse/acl.c
@@ -122,20 +122,16 @@ int fuse_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 		 * them to be refreshed the next time they are used,
 		 * and it also updates i_ctime.
 		 */
-		size_t size = posix_acl_xattr_size(acl->a_count);
+		size_t size;
 		void *value;
 
-		if (size > PAGE_SIZE)
-			return -E2BIG;
-
-		value = kmalloc(size, GFP_KERNEL);
+		value = posix_acl_to_xattr(fc->user_ns, acl, &size, GFP_KERNEL);
 		if (!value)
 			return -ENOMEM;
 
-		ret = posix_acl_to_xattr(fc->user_ns, acl, value, size);
-		if (ret < 0) {
+		if (size > PAGE_SIZE) {
 			kfree(value);
-			return ret;
+			return -E2BIG;
 		}
 
 		/*
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 6d59cbc877c6..a30c8b57d478 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1813,7 +1813,7 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
 			goto out_iput;
 
 		folio_offset = ((index - folio->index) << PAGE_SHIFT) + offset;
-		nr_bytes = min_t(unsigned, num, folio_size(folio) - folio_offset);
+		nr_bytes = min(num, folio_size(folio) - folio_offset);
 		nr_pages = (offset + nr_bytes + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 		err = fuse_copy_folio(cs, &folio, folio_offset, nr_bytes, 0);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 78fa46cfc636..dffd454e30e2 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1323,10 +1323,8 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 static inline unsigned int fuse_wr_pages(loff_t pos, size_t len,
 				     unsigned int max_pages)
 {
-	return min_t(unsigned int,
-		     ((pos + len - 1) >> PAGE_SHIFT) -
-		     (pos >> PAGE_SHIFT) + 1,
-		     max_pages);
+	return min(((pos + len - 1) >> PAGE_SHIFT) - (pos >> PAGE_SHIFT) + 1,
+		   max_pages);
 }
 
 static ssize_t fuse_perform_write(struct kiocb *iocb, struct iov_iter *ii)
@@ -1607,7 +1605,7 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
 			struct folio *folio = page_folio(pages[i]);
 			unsigned int offset = start +
 				(folio_page_idx(folio, pages[i]) << PAGE_SHIFT);
-			unsigned int len = min_t(unsigned int, ret, PAGE_SIZE - start);
+			unsigned int len = umin(ret, PAGE_SIZE - start);
 
 			ap->descs[ap->num_folios].offset = offset;
 			ap->descs[ap->num_folios].length = len;
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index 443640e6fb9c..a5b60778b91c 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -83,21 +83,14 @@ struct posix_acl *gfs2_get_acl(struct inode *inode, int type, bool rcu)
 int __gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
 	int error;
-	size_t len;
-	char *data;
+	size_t len = 0;
+	char *data = NULL;
 	const char *name = gfs2_acl_name(type);
 
 	if (acl) {
-		len = posix_acl_xattr_size(acl->a_count);
-		data = kmalloc(len, GFP_NOFS);
+		data = posix_acl_to_xattr(&init_user_ns, acl, &len, GFP_NOFS);
 		if (data == NULL)
 			return -ENOMEM;
-		error = posix_acl_to_xattr(&init_user_ns, acl, data, len);
-		if (error < 0)
-			goto out;
-	} else {
-		data = NULL;
-		len = 0;
 	}
 
 	error = __gfs2_xattr_set(inode, name, data, len, 0, GFS2_EATYPE_SYS);
diff --git a/fs/inode.c b/fs/inode.c
index 1d0474745e77..dae43a8de7e0 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1028,19 +1028,20 @@ long prune_icache_sb(struct super_block *sb, struct shrink_control *sc)
 	return freed;
 }
 
-static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_locked);
+static void __wait_on_freeing_inode(struct inode *inode, bool hash_locked, bool rcu_locked);
+
 /*
  * Called with the inode lock held.
  */
 static struct inode *find_inode(struct super_block *sb,
 				struct hlist_head *head,
 				int (*test)(struct inode *, void *),
-				void *data, bool is_inode_hash_locked,
+				void *data, bool hash_locked,
 				bool *isnew)
 {
 	struct inode *inode = NULL;
 
-	if (is_inode_hash_locked)
+	if (hash_locked)
 		lockdep_assert_held(&inode_hash_lock);
 	else
 		lockdep_assert_not_held(&inode_hash_lock);
@@ -1054,7 +1055,7 @@ repeat:
 			continue;
 		spin_lock(&inode->i_lock);
 		if (inode_state_read(inode) & (I_FREEING | I_WILL_FREE)) {
-			__wait_on_freeing_inode(inode, is_inode_hash_locked);
+			__wait_on_freeing_inode(inode, hash_locked, true);
 			goto repeat;
 		}
 		if (unlikely(inode_state_read(inode) & I_CREATING)) {
@@ -1078,11 +1079,11 @@ repeat:
  */
 static struct inode *find_inode_fast(struct super_block *sb,
 				struct hlist_head *head, unsigned long ino,
-				bool is_inode_hash_locked, bool *isnew)
+				bool hash_locked, bool *isnew)
 {
 	struct inode *inode = NULL;
 
-	if (is_inode_hash_locked)
+	if (hash_locked)
 		lockdep_assert_held(&inode_hash_lock);
 	else
 		lockdep_assert_not_held(&inode_hash_lock);
@@ -1096,7 +1097,7 @@ repeat:
 			continue;
 		spin_lock(&inode->i_lock);
 		if (inode_state_read(inode) & (I_FREEING | I_WILL_FREE)) {
-			__wait_on_freeing_inode(inode, is_inode_hash_locked);
+			__wait_on_freeing_inode(inode, hash_locked, true);
 			goto repeat;
 		}
 		if (unlikely(inode_state_read(inode) & I_CREATING)) {
@@ -1832,16 +1833,13 @@ int insert_inode_locked(struct inode *inode)
 	while (1) {
 		struct inode *old = NULL;
 		spin_lock(&inode_hash_lock);
+repeat:
 		hlist_for_each_entry(old, head, i_hash) {
 			if (old->i_ino != ino)
 				continue;
 			if (old->i_sb != sb)
 				continue;
 			spin_lock(&old->i_lock);
-			if (inode_state_read(old) & (I_FREEING | I_WILL_FREE)) {
-				spin_unlock(&old->i_lock);
-				continue;
-			}
 			break;
 		}
 		if (likely(!old)) {
@@ -1852,6 +1850,11 @@ int insert_inode_locked(struct inode *inode)
 			spin_unlock(&inode_hash_lock);
 			return 0;
 		}
+		if (inode_state_read(old) & (I_FREEING | I_WILL_FREE)) {
+			__wait_on_freeing_inode(old, true, false);
+			old = NULL;
+			goto repeat;
+		}
 		if (unlikely(inode_state_read(old) & I_CREATING)) {
 			spin_unlock(&old->i_lock);
 			spin_unlock(&inode_hash_lock);
@@ -2522,16 +2525,18 @@ EXPORT_SYMBOL(inode_needs_sync);
  * wake_up_bit(&inode->i_state, __I_NEW) after removing from the hash list
  * will DTRT.
  */
-static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_locked)
+static void __wait_on_freeing_inode(struct inode *inode, bool hash_locked, bool rcu_locked)
 {
 	struct wait_bit_queue_entry wqe;
 	struct wait_queue_head *wq_head;
 
+	VFS_BUG_ON(!hash_locked && !rcu_locked);
+
 	/*
 	 * Handle racing against evict(), see that routine for more details.
 	 */
 	if (unlikely(inode_unhashed(inode))) {
-		WARN_ON(is_inode_hash_locked);
+		WARN_ON(hash_locked);
 		spin_unlock(&inode->i_lock);
 		return;
 	}
@@ -2539,23 +2544,22 @@ static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_lock
 	wq_head = inode_bit_waitqueue(&wqe, inode, __I_NEW);
 	prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE);
 	spin_unlock(&inode->i_lock);
-	rcu_read_unlock();
-	if (is_inode_hash_locked)
+	if (rcu_locked)
+		rcu_read_unlock();
+	if (hash_locked)
 		spin_unlock(&inode_hash_lock);
 	schedule();
 	finish_wait(wq_head, &wqe.wq_entry);
-	if (is_inode_hash_locked)
+	if (hash_locked)
 		spin_lock(&inode_hash_lock);
-	rcu_read_lock();
+	if (rcu_locked)
+		rcu_read_lock();
 }
 
 static __initdata unsigned long ihash_entries;
 static int __init set_ihash_entries(char *str)
 {
-	if (!str)
-		return 0;
-	ihash_entries = simple_strtoul(str, &str, 0);
-	return 1;
+	return kstrtoul(str, 0, &ihash_entries) == 0;
 }
 __setup("ihash_entries=", set_ihash_entries);
 
@@ -3005,24 +3009,45 @@ umode_t mode_strip_sgid(struct mnt_idmap *idmap,
 EXPORT_SYMBOL(mode_strip_sgid);
 
 #ifdef CONFIG_DEBUG_VFS
-/*
- * Dump an inode.
+/**
+ * dump_inode - dump an inode.
+ * @inode: inode to dump
+ * @reason: reason for dumping
  *
- * TODO: add a proper inode dumping routine, this is a stub to get debug off the
- * ground.
- *
- * TODO: handle getting to fs type with get_kernel_nofault()?
- * See dump_mapping() above.
+ * If inode is an invalid pointer, we don't want to crash accessing it,
+ * so probe everything depending on it carefully with get_kernel_nofault().
  */
 void dump_inode(struct inode *inode, const char *reason)
 {
-	struct super_block *sb = inode->i_sb;
+	struct super_block *sb;
+	struct file_system_type *s_type;
+	const char *fs_name_ptr;
+	char fs_name[32] = {};
+	umode_t mode;
+	unsigned short opflags;
+	unsigned int flags;
+	unsigned int state;
+	int count;
 
-	pr_warn("%s encountered for inode %px\n"
-		"fs %s mode %ho opflags 0x%hx flags 0x%x state 0x%x count %d\n",
-		reason, inode, sb->s_type->name, inode->i_mode, inode->i_opflags,
-		inode->i_flags, inode_state_read_once(inode), atomic_read(&inode->i_count));
+	if (get_kernel_nofault(sb, &inode->i_sb) ||
+	    get_kernel_nofault(mode, &inode->i_mode) ||
+	    get_kernel_nofault(opflags, &inode->i_opflags) ||
+	    get_kernel_nofault(flags, &inode->i_flags)) {
+		pr_warn("%s: unreadable inode:%px\n", reason, inode);
+		return;
+	}
+
+	state = inode_state_read_once(inode);
+	count = atomic_read(&inode->i_count);
+
+	if (!sb ||
+	    get_kernel_nofault(s_type, &sb->s_type) || !s_type ||
+	    get_kernel_nofault(fs_name_ptr, &s_type->name) || !fs_name_ptr ||
+	    strncpy_from_kernel_nofault(fs_name, fs_name_ptr, sizeof(fs_name) - 1) < 0)
+		strscpy(fs_name, "<unknown, sb unreadable>");
+
+	pr_warn("%s: inode:%px fs:%s mode:%ho opflags:%#x flags:%#x state:%#x count:%d\n",
+		reason, inode, fs_name, mode, opflags, flags, state, count);
 }
-
 EXPORT_SYMBOL(dump_inode);
 #endif
diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c
index 1de3602c98de..16b71a23ff1e 100644
--- a/fs/jfs/acl.c
+++ b/fs/jfs/acl.c
@@ -61,7 +61,7 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type,
 {
 	char *ea_name;
 	int rc;
-	int size = 0;
+	size_t size = 0;
 	char *value = NULL;
 
 	switch (type) {
@@ -76,16 +76,11 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type,
 	}
 
 	if (acl) {
-		size = posix_acl_xattr_size(acl->a_count);
-		value = kmalloc(size, GFP_KERNEL);
+		value = posix_acl_to_xattr(&init_user_ns, acl, &size, GFP_KERNEL);
 		if (!value)
 			return -ENOMEM;
-		rc = posix_acl_to_xattr(&init_user_ns, acl, value, size);
-		if (rc < 0)
-			goto out;
 	}
 	rc = __jfs_setxattr(tid, inode, ea_name, value, size, 0);
-out:
 	kfree(value);
 
 	if (!rc)
diff --git a/fs/locks.c b/fs/locks.c
index cf1968b01bcb..3ea25d3a780f 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -178,7 +178,6 @@ locks_get_lock_context(struct inode *inode, int type)
 {
 	struct file_lock_context *ctx;
 
-	/* paired with cmpxchg() below */
 	ctx = locks_inode_context(inode);
 	if (likely(ctx) || type == F_UNLCK)
 		goto out;
@@ -196,7 +195,18 @@ locks_get_lock_context(struct inode *inode, int type)
 	 * Assign the pointer if it's not already assigned. If it is, then
 	 * free the context we just allocated.
 	 */
-	if (cmpxchg(&inode->i_flctx, NULL, ctx)) {
+	spin_lock(&inode->i_lock);
+	if (!(inode->i_opflags & IOP_FLCTX)) {
+		VFS_BUG_ON_INODE(inode->i_flctx, inode);
+		WRITE_ONCE(inode->i_flctx, ctx);
+		/*
+		 * Paired with locks_inode_context().
+		 */
+		smp_store_release(&inode->i_opflags, inode->i_opflags | IOP_FLCTX);
+		spin_unlock(&inode->i_lock);
+	} else {
+		VFS_BUG_ON_INODE(!inode->i_flctx, inode);
+		spin_unlock(&inode->i_lock);
 		kmem_cache_free(flctx_cache, ctx);
 		ctx = locks_inode_context(inode);
 	}
diff --git a/fs/namei.c b/fs/namei.c
index 76bc569ace8e..b28ecb699f32 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -879,7 +879,7 @@ static bool try_to_unlazy(struct nameidata *nd)
 {
 	struct dentry *parent = nd->path.dentry;
 
-	BUG_ON(!(nd->flags & LOOKUP_RCU));
+	VFS_BUG_ON(!(nd->flags & LOOKUP_RCU));
 
 	if (unlikely(nd->flags & LOOKUP_CACHED)) {
 		drop_links(nd);
@@ -919,7 +919,8 @@ out:
 static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry)
 {
 	int res;
-	BUG_ON(!(nd->flags & LOOKUP_RCU));
+
+	VFS_BUG_ON(!(nd->flags & LOOKUP_RCU));
 
 	if (unlikely(nd->flags & LOOKUP_CACHED)) {
 		drop_links(nd);
@@ -1631,9 +1632,6 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path)
 	struct dentry *dentry = path->dentry;
 	unsigned int flags = dentry->d_flags;
 
-	if (likely(!(flags & DCACHE_MANAGED_DENTRY)))
-		return true;
-
 	if (unlikely(nd->flags & LOOKUP_NO_XDEV))
 		return false;
 
diff --git a/fs/namespace.c b/fs/namespace.c
index 1d2089ffb6ab..0cc8c2757500 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -49,20 +49,14 @@ static unsigned int mp_hash_shift __ro_after_init;
 static __initdata unsigned long mhash_entries;
 static int __init set_mhash_entries(char *str)
 {
-	if (!str)
-		return 0;
-	mhash_entries = simple_strtoul(str, &str, 0);
-	return 1;
+	return kstrtoul(str, 0, &mhash_entries) == 0;
 }
 __setup("mhash_entries=", set_mhash_entries);
 
 static __initdata unsigned long mphash_entries;
 static int __init set_mphash_entries(char *str)
 {
-	if (!str)
-		return 0;
-	mphash_entries = simple_strtoul(str, &str, 0);
-	return 1;
+	return kstrtoul(str, 0, &mphash_entries) == 0;
 }
 __setup("mphash_entries=", set_mphash_entries);
 
diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c
index c93df55e98d0..37a69a75ce68 100644
--- a/fs/ntfs3/xattr.c
+++ b/fs/ntfs3/xattr.c
@@ -641,13 +641,9 @@ static noinline int ntfs_set_acl_ex(struct mnt_idmap *idmap,
 		value = NULL;
 		flags = XATTR_REPLACE;
 	} else {
-		size = posix_acl_xattr_size(acl->a_count);
-		value = kmalloc(size, GFP_NOFS);
+		value = posix_acl_to_xattr(&init_user_ns, acl, &size, GFP_NOFS);
 		if (!value)
 			return -ENOMEM;
-		err = posix_acl_to_xattr(&init_user_ns, acl, value, size);
-		if (err < 0)
-			goto out;
 		flags = 0;
 	}
 
diff --git a/fs/orangefs/acl.c b/fs/orangefs/acl.c
index 5aefb705bcc8..a01ef0c1b1bf 100644
--- a/fs/orangefs/acl.c
+++ b/fs/orangefs/acl.c
@@ -90,14 +90,9 @@ int __orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 		     type);
 
 	if (acl) {
-		size = posix_acl_xattr_size(acl->a_count);
-		value = kmalloc(size, GFP_KERNEL);
+		value = posix_acl_to_xattr(&init_user_ns, acl, &size, GFP_KERNEL);
 		if (!value)
 			return -ENOMEM;
-
-		error = posix_acl_to_xattr(&init_user_ns, acl, value, size);
-		if (error < 0)
-			goto out;
 	}
 
 	gossip_debug(GOSSIP_ACL_DEBUG,
@@ -111,7 +106,6 @@ int __orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	 */
 	error = orangefs_inode_setxattr(inode, name, value, size, 0);
 
-out:
 	kfree(value);
 	if (!error)
 		set_cached_acl(inode, type, acl);
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 768f027c1428..4ef6f9d2b8d6 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -829,19 +829,19 @@ EXPORT_SYMBOL (posix_acl_from_xattr);
 /*
  * Convert from in-memory to extended attribute representation.
  */
-int
+void *
 posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl,
-		   void *buffer, size_t size)
+		   size_t *sizep, gfp_t gfp)
 {
-	struct posix_acl_xattr_header *ext_acl = buffer;
+	struct posix_acl_xattr_header *ext_acl;
 	struct posix_acl_xattr_entry *ext_entry;
-	int real_size, n;
+	size_t size;
+	int n;
 
-	real_size = posix_acl_xattr_size(acl->a_count);
-	if (!buffer)
-		return real_size;
-	if (real_size > size)
-		return -ERANGE;
+	size = posix_acl_xattr_size(acl->a_count);
+	ext_acl = kmalloc(size, gfp);
+	if (!ext_acl)
+		return NULL;
 
 	ext_entry = (void *)(ext_acl + 1);
 	ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION);
@@ -864,7 +864,8 @@ posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl,
 			break;
 		}
 	}
-	return real_size;
+	*sizep = size;
+	return ext_acl;
 }
 EXPORT_SYMBOL (posix_acl_to_xattr);
 
diff --git a/fs/select.c b/fs/select.c
index 65019b8ba3f7..78a1508c84d3 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -1038,14 +1038,11 @@ static long do_restart_poll(struct restart_block *restart_block)
 {
 	struct pollfd __user *ufds = restart_block->poll.ufds;
 	int nfds = restart_block->poll.nfds;
-	struct timespec64 *to = NULL, end_time;
+	struct timespec64 *to = NULL;
 	int ret;
 
-	if (restart_block->poll.has_timeout) {
-		end_time.tv_sec = restart_block->poll.tv_sec;
-		end_time.tv_nsec = restart_block->poll.tv_nsec;
-		to = &end_time;
-	}
+	if (restart_block->poll.has_timeout)
+		to = &restart_block->poll.end_time;
 
 	ret = do_sys_poll(ufds, nfds, to);
 
@@ -1077,8 +1074,7 @@ SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
 		restart_block->poll.nfds = nfds;
 
 		if (timeout_msecs >= 0) {
-			restart_block->poll.tv_sec = end_time.tv_sec;
-			restart_block->poll.tv_nsec = end_time.tv_nsec;
+			restart_block->poll.end_time = end_time;
 			restart_block->poll.has_timeout = 1;
 		} else
 			restart_block->poll.has_timeout = 0;
diff --git a/fs/splice.c b/fs/splice.c
index d338fe56b50b..5fb07c01936f 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1467,7 +1467,7 @@ static ssize_t iter_to_pipe(struct iov_iter *from,
 
 		n = DIV_ROUND_UP(left + start, PAGE_SIZE);
 		for (i = 0; i < n; i++) {
-			int size = min_t(int, left, PAGE_SIZE - start);
+			int size = umin(left, PAGE_SIZE - start);
 
 			buf.page = pages[i];
 			buf.offset = start;
diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h
index 0864773a57e8..822085bc2d20 100644
--- a/include/linux/device_cgroup.h
+++ b/include/linux/device_cgroup.h
@@ -21,7 +21,7 @@ static inline int devcgroup_inode_permission(struct inode *inode, int mask)
 	if (likely(!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode)))
 		return 0;
 
-	if (likely(!inode->i_rdev))
+	if (!inode->i_rdev)
 		return 0;
 
 	if (S_ISBLK(inode->i_mode))
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index f0cf2714ec52..262e24d83313 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -201,9 +201,9 @@ struct handle_to_path_ctx {
  * @commit_metadata: commit metadata changes to stable storage
  *
  * See Documentation/filesystems/nfs/exporting.rst for details on how to use
- * this interface correctly.
+ * this interface correctly and the definition of the flags.
  *
- * encode_fh:
+ * @encode_fh:
  *    @encode_fh should store in the file handle fragment @fh (using at most
  *    @max_len bytes) information that can be used by @decode_fh to recover the
  *    file referred to by the &struct dentry @de.  If @flag has CONNECTABLE bit
@@ -215,7 +215,7 @@ struct handle_to_path_ctx {
  *    greater than @max_len*4 bytes). On error @max_len contains the minimum
  *    size(in 4 byte unit) needed to encode the file handle.
  *
- * fh_to_dentry:
+ * @fh_to_dentry:
  *    @fh_to_dentry is given a &struct super_block (@sb) and a file handle
  *    fragment (@fh, @fh_len). It should return a &struct dentry which refers
  *    to the same file that the file handle fragment refers to.  If it cannot,
@@ -227,31 +227,44 @@ struct handle_to_path_ctx {
  *    created with d_alloc_root.  The caller can then find any other extant
  *    dentries by following the d_alias links.
  *
- * fh_to_parent:
+ * @fh_to_parent:
  *    Same as @fh_to_dentry, except that it returns a pointer to the parent
  *    dentry if it was encoded into the filehandle fragment by @encode_fh.
  *
- * get_name:
+ * @get_name:
  *    @get_name should find a name for the given @child in the given @parent
  *    directory.  The name should be stored in the @name (with the
- *    understanding that it is already pointing to a %NAME_MAX+1 sized
+ *    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_rwsem held.
  *
- * get_parent:
+ * @get_parent:
  *    @get_parent should find the parent directory for the given @child which
  *    is also a directory.  In the event that it cannot be found, or storage
  *    space cannot be allocated, a %ERR_PTR should be returned.
  *
- * permission:
+ * @permission:
  *    Allow filesystems to specify a custom permission function.
  *
- * open:
+ * @open:
  *    Allow filesystems to specify a custom open function.
  *
- * commit_metadata:
+ * @commit_metadata:
  *    @commit_metadata should commit metadata changes to stable storage.
  *
+ * @get_uuid:
+ *    Get a filesystem unique signature exposed to clients.
+ *
+ * @map_blocks:
+ *    Map and, if necessary, allocate blocks for a layout.
+ *
+ * @commit_blocks:
+ *    Commit blocks in a layout once the client is done with them.
+ *
+ * @flags:
+ *    Allows the filesystem to communicate to nfsd that it may want to do things
+ *    differently when dealing with it.
+ *
  * Locking rules:
  *    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 2f5e5588ee07..d2c9740e26a8 100644
--- a/include/linux/filelock.h
+++ b/include/linux/filelock.h
@@ -242,7 +242,14 @@ bool locks_owner_has_blockers(struct file_lock_context *flctx,
 static inline struct file_lock_context *
 locks_inode_context(const struct inode *inode)
 {
-	return smp_load_acquire(&inode->i_flctx);
+	/*
+	 * Paired with smp_store_release in locks_get_lock_context().
+	 *
+	 * Ensures ->i_flctx will be visible if we spotted the flag.
+	 */
+	if (likely(!(smp_load_acquire(&inode->i_opflags) & IOP_FLCTX)))
+		return NULL;
+	return READ_ONCE(inode->i_flctx);
 }
 
 #else /* !CONFIG_FILE_LOCKING */
@@ -469,7 +476,7 @@ static inline int break_lease(struct inode *inode, unsigned int mode)
 	 * could end up racing with tasks trying to set a new lease on this
 	 * file.
 	 */
-	flctx = READ_ONCE(inode->i_flctx);
+	flctx = locks_inode_context(inode);
 	if (!flctx)
 		return 0;
 	smp_mb();
@@ -488,7 +495,7 @@ static inline int break_deleg(struct inode *inode, unsigned int flags)
 	 * could end up racing with tasks trying to set a new lease on this
 	 * file.
 	 */
-	flctx = READ_ONCE(inode->i_flctx);
+	flctx = locks_inode_context(inode);
 	if (!flctx)
 		return 0;
 	smp_mb();
@@ -533,8 +540,11 @@ static inline int break_deleg_wait(struct delegated_inode *di)
 
 static inline int break_layout(struct inode *inode, bool wait)
 {
+	struct file_lock_context *flctx;
+
 	smp_mb();
-	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) {
+	flctx = locks_inode_context(inode);
+	if (flctx && !list_empty_careful(&flctx->flc_lease)) {
 		unsigned int flags = LEASE_BREAK_LAYOUT;
 
 		if (!wait)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ca31bc9308a3..73911f961c7e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -631,6 +631,7 @@ is_uncached_acl(struct posix_acl *acl)
 #define IOP_MGTIME		0x0020
 #define IOP_CACHED_LINK		0x0040
 #define IOP_FASTPERM_MAY_EXEC	0x0080
+#define IOP_FLCTX		0x0100
 
 /*
  * Inode state bits.  Protected by inode->i_lock
diff --git a/include/linux/ns/ns_common_types.h b/include/linux/ns/ns_common_types.h
index b332b019b29c..0014fbc1c626 100644
--- a/include/linux/ns/ns_common_types.h
+++ b/include/linux/ns/ns_common_types.h
@@ -108,11 +108,13 @@ extern const struct proc_ns_operations utsns_operations;
  * @ns_tree: namespace tree nodes and active reference count
  */
 struct ns_common {
+	struct {
+		refcount_t __ns_ref; /* do not use directly */
+	} ____cacheline_aligned_in_smp;
 	u32 ns_type;
 	struct dentry *stashed;
 	const struct proc_ns_operations *ops;
 	unsigned int inum;
-	refcount_t __ns_ref; /* do not use directly */
 	union {
 		struct ns_tree;
 		struct rcu_head ns_rcu;
diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h
index e86f3b731da2..9e1892525eac 100644
--- a/include/linux/posix_acl_xattr.h
+++ b/include/linux/posix_acl_xattr.h
@@ -44,8 +44,9 @@ posix_acl_from_xattr(struct user_namespace *user_ns, const void *value,
 }
 #endif
 
-int posix_acl_to_xattr(struct user_namespace *user_ns,
-		       const struct posix_acl *acl, void *buffer, size_t size);
+extern void *posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl,
+				size_t *sizep, gfp_t gfp);
+
 static inline const char *posix_acl_xattr_name(int type)
 {
 	switch (type) {
diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h
index 67d2bf579942..9b262109726d 100644
--- a/include/linux/restart_block.h
+++ b/include/linux/restart_block.h
@@ -6,6 +6,7 @@
 #define __LINUX_RESTART_BLOCK_H
 
 #include <linux/compiler.h>
+#include <linux/time64.h>
 #include <linux/types.h>
 
 struct __kernel_timespec;
@@ -50,8 +51,7 @@ struct restart_block {
 			struct pollfd __user *ufds;
 			int nfds;
 			int has_timeout;
-			unsigned long tv_sec;
-			unsigned long tv_nsec;
+			struct timespec64 end_time;
 		} poll;
 	};
 };
diff --git a/init/Kconfig b/init/Kconfig
index fa79feb8fe57..160c1c4ef253 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -624,8 +624,9 @@ config SCHED_HW_PRESSURE
 	  arch_update_hw_pressure() and arch_scale_thermal_pressure().
 
 config BSD_PROCESS_ACCT
-	bool "BSD Process Accounting"
+	bool "BSD Process Accounting (DEPRECATED)"
 	depends on MULTIUSER
+	default n
 	help
 	  If you say Y here, a user level program will be able to instruct the
 	  kernel (via a special system call) to write process accounting
@@ -635,7 +636,9 @@ config BSD_PROCESS_ACCT
 	  command name, memory usage, controlling terminal etc. (the complete
 	  list is in the struct acct in <file:include/linux/acct.h>).  It is
 	  up to the user level program to do useful things with this
-	  information.  This is generally a good idea, so say Y.
+	  information.  This mechanism is antiquated and has significant
+	  scalability issues.  You probably want to use eBPF instead.  Say
+	  N unless you really need this.
 
 config BSD_PROCESS_ACCT_V3
 	bool "BSD Process Accounting version 3 file format"
diff --git a/init/initramfs_test.c b/init/initramfs_test.c
index 5d2db455e60c..beb6e3cf7808 100644
--- a/init/initramfs_test.c
+++ b/init/initramfs_test.c
@@ -447,6 +447,53 @@ out:
 	kfree(tbufs);
 }
 
+static void __init initramfs_test_fname_path_max(struct kunit *test)
+{
+	char *err;
+	size_t len;
+	struct kstat st0, st1;
+	char fdata[] = "this file data will not be unpacked";
+	struct test_fname_path_max {
+		char fname_oversize[PATH_MAX + 1];
+		char fname_ok[PATH_MAX];
+		char cpio_src[(CPIO_HDRLEN + PATH_MAX + 3 + sizeof(fdata)) * 2];
+	} *tbufs = kzalloc(sizeof(struct test_fname_path_max), GFP_KERNEL);
+	struct initramfs_test_cpio c[] = { {
+		.magic = "070701",
+		.ino = 1,
+		.mode = S_IFDIR | 0777,
+		.nlink = 1,
+		.namesize = sizeof(tbufs->fname_oversize),
+		.fname = tbufs->fname_oversize,
+		.filesize = sizeof(fdata),
+		.data = fdata,
+	}, {
+		.magic = "070701",
+		.ino = 2,
+		.mode = S_IFDIR | 0777,
+		.nlink = 1,
+		.namesize = sizeof(tbufs->fname_ok),
+		.fname = tbufs->fname_ok,
+	} };
+
+	memset(tbufs->fname_oversize, '/', sizeof(tbufs->fname_oversize) - 1);
+	memset(tbufs->fname_ok, '/', sizeof(tbufs->fname_ok) - 1);
+	memcpy(tbufs->fname_oversize, "fname_oversize",
+	       sizeof("fname_oversize") - 1);
+	memcpy(tbufs->fname_ok, "fname_ok", sizeof("fname_ok") - 1);
+	len = fill_cpio(c, ARRAY_SIZE(c), tbufs->cpio_src);
+
+	/* unpack skips over fname_oversize instead of returning an error */
+	err = unpack_to_rootfs(tbufs->cpio_src, len);
+	KUNIT_EXPECT_NULL(test, err);
+
+	KUNIT_EXPECT_EQ(test, init_stat("fname_oversize", &st0, 0), -ENOENT);
+	KUNIT_EXPECT_EQ(test, init_stat("fname_ok", &st1, 0), 0);
+	KUNIT_EXPECT_EQ(test, init_rmdir("fname_ok"), 0);
+
+	kfree(tbufs);
+}
+
 /*
  * The kunit_case/_suite struct cannot be marked as __initdata as this will be
  * used in debugfs to retrieve results after test has run.
@@ -459,6 +506,7 @@ static struct kunit_case __refdata initramfs_test_cases[] = {
 	KUNIT_CASE(initramfs_test_hardlink),
 	KUNIT_CASE(initramfs_test_many),
 	KUNIT_CASE(initramfs_test_fname_pad),
+	KUNIT_CASE(initramfs_test_fname_path_max),
 	{},
 };
 
diff --git a/kernel/pid.c b/kernel/pid.c
index a31771bc89c1..f45ae56db7da 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -159,58 +159,86 @@ void free_pids(struct pid **pids)
 			free_pid(pids[tmp]);
 }
 
-struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
-		      size_t set_tid_size)
+struct pid *alloc_pid(struct pid_namespace *ns, pid_t *arg_set_tid,
+		      size_t arg_set_tid_size)
 {
+	int set_tid[MAX_PID_NS_LEVEL + 1] = {};
+	int pid_max[MAX_PID_NS_LEVEL + 1] = {};
 	struct pid *pid;
 	enum pid_type type;
 	int i, nr;
 	struct pid_namespace *tmp;
 	struct upid *upid;
 	int retval = -ENOMEM;
+	bool retried_preload;
 
 	/*
-	 * set_tid_size contains the size of the set_tid array. Starting at
+	 * arg_set_tid_size contains the size of the arg_set_tid array. Starting at
 	 * the most nested currently active PID namespace it tells alloc_pid()
 	 * which PID to set for a process in that most nested PID namespace
-	 * up to set_tid_size PID namespaces. It does not have to set the PID
-	 * for a process in all nested PID namespaces but set_tid_size must
+	 * up to arg_set_tid_size PID namespaces. It does not have to set the PID
+	 * for a process in all nested PID namespaces but arg_set_tid_size must
 	 * never be greater than the current ns->level + 1.
 	 */
-	if (set_tid_size > ns->level + 1)
+	if (arg_set_tid_size > ns->level + 1)
 		return ERR_PTR(-EINVAL);
 
+	/*
+	 * Prep before we take locks:
+	 *
+	 * 1. allocate and fill in pid struct
+	 */
 	pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
 	if (!pid)
 		return ERR_PTR(retval);
 
-	tmp = ns;
+	get_pid_ns(ns);
 	pid->level = ns->level;
+	refcount_set(&pid->count, 1);
+	spin_lock_init(&pid->lock);
+	for (type = 0; type < PIDTYPE_MAX; ++type)
+		INIT_HLIST_HEAD(&pid->tasks[type]);
+	init_waitqueue_head(&pid->wait_pidfd);
+	INIT_HLIST_HEAD(&pid->inodes);
 
-	for (i = ns->level; i >= 0; i--) {
-		int tid = 0;
-		int pid_max = READ_ONCE(tmp->pid_max);
+	/*
+	 * 2. perm check checkpoint_restore_ns_capable()
+	 *
+	 * This stores found pid_max to make sure the used value is the same should
+	 * later code need it.
+	 */
+	for (tmp = ns, i = ns->level; i >= 0; i--) {
+		pid_max[ns->level - i] = READ_ONCE(tmp->pid_max);
 
-		if (set_tid_size) {
-			tid = set_tid[ns->level - i];
+		if (arg_set_tid_size) {
+			int tid = set_tid[ns->level - i] = arg_set_tid[ns->level - i];
 
 			retval = -EINVAL;
-			if (tid < 1 || tid >= pid_max)
-				goto out_free;
+			if (tid < 1 || tid >= pid_max[ns->level - i])
+				goto out_abort;
 			/*
 			 * Also fail if a PID != 1 is requested and
 			 * no PID 1 exists.
 			 */
 			if (tid != 1 && !tmp->child_reaper)
-				goto out_free;
+				goto out_abort;
 			retval = -EPERM;
 			if (!checkpoint_restore_ns_capable(tmp->user_ns))
-				goto out_free;
-			set_tid_size--;
+				goto out_abort;
+			arg_set_tid_size--;
 		}
 
-		idr_preload(GFP_KERNEL);
-		spin_lock(&pidmap_lock);
+		tmp = tmp->parent;
+	}
+
+	/*
+	 * Prep is done, id allocation goes here:
+	 */
+	retried_preload = false;
+	idr_preload(GFP_KERNEL);
+	spin_lock(&pidmap_lock);
+	for (tmp = ns, i = ns->level; i >= 0;) {
+		int tid = set_tid[ns->level - i];
 
 		if (tid) {
 			nr = idr_alloc(&tmp->idr, NULL, tid,
@@ -220,6 +248,7 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 			 * alreay in use. Return EEXIST in that case.
 			 */
 			if (nr == -ENOSPC)
+
 				nr = -EEXIST;
 		} else {
 			int pid_min = 1;
@@ -235,19 +264,42 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 			 * a partially initialized PID (see below).
 			 */
 			nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min,
-					      pid_max, GFP_ATOMIC);
+					      pid_max[ns->level - i], GFP_ATOMIC);
+			if (nr == -ENOSPC)
+				nr = -EAGAIN;
 		}
-		spin_unlock(&pidmap_lock);
-		idr_preload_end();
 
-		if (nr < 0) {
-			retval = (nr == -ENOSPC) ? -EAGAIN : nr;
+		if (unlikely(nr < 0)) {
+			/*
+			 * Preload more memory if idr_alloc{,cyclic} failed with -ENOMEM.
+			 *
+			 * The IDR API only allows us to preload memory for one call, while we may end
+			 * up doing several under pidmap_lock with GFP_ATOMIC. The situation may be
+			 * salvageable with GFP_KERNEL. But make sure to not loop indefinitely if preload
+			 * did not help (the routine unfortunately returns void, so we have no idea
+			 * if it got anywhere).
+			 *
+			 * The lock can be safely dropped and picked up as historically pid allocation
+			 * for different namespaces was *not* atomic -- we try to hold on to it the
+			 * entire time only for performance reasons.
+			 */
+			if (nr == -ENOMEM && !retried_preload) {
+				spin_unlock(&pidmap_lock);
+				idr_preload_end();
+				retried_preload = true;
+				idr_preload(GFP_KERNEL);
+				spin_lock(&pidmap_lock);
+				continue;
+			}
+			retval = nr;
 			goto out_free;
 		}
 
 		pid->numbers[i].nr = nr;
 		pid->numbers[i].ns = tmp;
 		tmp = tmp->parent;
+		i--;
+		retried_preload = false;
 	}
 
 	/*
@@ -257,25 +309,15 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 	 * is what we have exposed to userspace for a long time and it is
 	 * documented behavior for pid namespaces. So we can't easily
 	 * change it even if there were an error code better suited.
+	 *
+	 * This can't be done earlier because we need to preserve other
+	 * error conditions.
 	 */
 	retval = -ENOMEM;
-
-	get_pid_ns(ns);
-	refcount_set(&pid->count, 1);
-	spin_lock_init(&pid->lock);
-	for (type = 0; type < PIDTYPE_MAX; ++type)
-		INIT_HLIST_HEAD(&pid->tasks[type]);
-
-	init_waitqueue_head(&pid->wait_pidfd);
-	INIT_HLIST_HEAD(&pid->inodes);
-
-	upid = pid->numbers + ns->level;
-	idr_preload(GFP_KERNEL);
-	spin_lock(&pidmap_lock);
-	if (!(ns->pid_allocated & PIDNS_ADDING))
-		goto out_unlock;
+	if (unlikely(!(ns->pid_allocated & PIDNS_ADDING)))
+		goto out_free;
 	pidfs_add_pid(pid);
-	for ( ; upid >= pid->numbers; --upid) {
+	for (upid = pid->numbers + ns->level; upid >= pid->numbers; --upid) {
 		/* Make the PID visible to find_pid_ns. */
 		idr_replace(&upid->ns->idr, pid, upid->nr);
 		upid->ns->pid_allocated++;
@@ -286,13 +328,7 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 
 	return pid;
 
-out_unlock:
-	spin_unlock(&pidmap_lock);
-	idr_preload_end();
-	put_pid_ns(ns);
-
 out_free:
-	spin_lock(&pidmap_lock);
 	while (++i <= ns->level) {
 		upid = pid->numbers + i;
 		idr_remove(&upid->ns->idr, upid->nr);
@@ -303,7 +339,10 @@ out_free:
 		idr_set_cursor(&ns->idr, 0);
 
 	spin_unlock(&pidmap_lock);
+	idr_preload_end();
 
+out_abort:
+	put_pid_ns(ns);
 	kmem_cache_free(ns->pid_cachep, pid);
 	return ERR_PTR(retval);
 }