next-20260723/vfs-brauner

107 files changed, 2345 insertions, 2075 deletions

diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 5783d0336f96..3829554ca369 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -645,7 +645,6 @@ error:
  * @dir: The parent directory
  * @dentry: The name of file to be created
  * @mode: The UNIX file mode to set
- * @excl: True if the file must not yet exist
  *
  * open(.., O_CREAT) is handled in v9fs_vfs_atomic_open().  This is only called
  * for mknod(2).
@@ -654,7 +653,7 @@ error:
 
 static int
 v9fs_vfs_create(struct mnt_idmap *idmap, struct inode *dir,
-		struct dentry *dentry, umode_t mode, bool excl)
+		struct dentry *dentry, umode_t mode)
 {
 	struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir);
 	u32 perm = unixmode2p9mode(v9ses, mode);
@@ -689,7 +688,7 @@ static struct dentry *v9fs_vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 
 	p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry);
 	v9ses = v9fs_inode2v9ses(dir);
-	perm = unixmode2p9mode(v9ses, mode | S_IFDIR);
+	perm = unixmode2p9mode(v9ses, mode);
 	fid = v9fs_create(v9ses, dir, dentry, NULL, perm, P9_OREAD);
 	if (IS_ERR(fid))
 		return ERR_CAST(fid);
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index f7396d20cb6c..116b29e95f21 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -213,12 +213,11 @@ int v9fs_open_to_dotl_flags(int flags)
  * @dir: directory inode that is being created
  * @dentry:  dentry that is being deleted
  * @omode: create permissions
- * @excl: True if the file must not yet exist
  *
  */
 static int
 v9fs_vfs_create_dotl(struct mnt_idmap *idmap, struct inode *dir,
-		     struct dentry *dentry, umode_t omode, bool excl)
+		     struct dentry *dentry, umode_t omode)
 {
 	return v9fs_vfs_mknod_dotl(idmap, dir, dentry, omode, 0);
 }
@@ -362,7 +361,6 @@ static struct dentry *v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap,
 	p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry);
 	v9ses = v9fs_inode2v9ses(dir);
 
-	omode |= S_IFDIR;
 	if (dir->i_mode & S_ISGID)
 		omode |= S_ISGID;
 
diff --git a/fs/Kconfig b/fs/Kconfig
index cf6ae64776e6..64ff193fb42c 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -315,7 +315,6 @@ source "fs/hfs/Kconfig"
 source "fs/hfsplus/Kconfig"
 source "fs/befs/Kconfig"
 source "fs/bfs/Kconfig"
-source "fs/efs/Kconfig"
 source "fs/jffs2/Kconfig"
 # UBIFS File system configuration
 source "fs/ubifs/Kconfig"
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index 1949e25c7741..daeac4889d03 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -168,6 +168,20 @@ config BINFMT_MISC
 	  you have use for it; the module is called binfmt_misc. If you
 	  don't know what to answer at this point, say Y.
 
+config BINFMT_MISC_BPF
+	bool "BPF-selected interpreters for misc binaries"
+	depends on BINFMT_MISC=y
+	depends on BPF_SYSCALL && BPF_JIT && DEBUG_INFO_BTF
+	help
+	  Allow binfmt_misc binary type handlers to be implemented as bpf
+	  struct_ops programs. Instead of matching a fixed magic and
+	  redirecting to a fixed interpreter recorded at registration time
+	  such handlers match binaries programmatically and compute the
+	  interpreter to use per binary, e.g. relative to the location of
+	  the binary itself.
+
+	  If you don't know what to answer at this point, say N.
+
 config COREDUMP
 	bool "Enable core dump support" if EXPERT
 	default y
diff --git a/fs/Makefile b/fs/Makefile
index 89a8a9d207d1..447a1f7c5732 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -33,6 +33,7 @@ obj-$(CONFIG_FS_ENCRYPTION)	+= crypto/
 obj-$(CONFIG_FS_VERITY)		+= verity/
 obj-$(CONFIG_FILE_LOCKING)      += locks.o
 obj-$(CONFIG_BINFMT_MISC)	+= binfmt_misc.o
+obj-$(CONFIG_BINFMT_MISC_BPF)	+= binfmt_misc_bpf.o
 obj-$(CONFIG_BINFMT_SCRIPT)	+= binfmt_script.o
 obj-$(CONFIG_BINFMT_ELF)	+= binfmt_elf.o
 obj-$(CONFIG_COMPAT_BINFMT_ELF)	+= compat_binfmt_elf.o
@@ -92,7 +93,6 @@ obj-$(CONFIG_HPFS_FS)		+= hpfs/
 obj-$(CONFIG_NTFS_FS)		+= ntfs/
 obj-$(CONFIG_NTFS3_FS)		+= ntfs3/
 obj-$(CONFIG_UFS_FS)		+= ufs/
-obj-$(CONFIG_EFS_FS)		+= efs/
 obj-$(CONFIG_JFFS2_FS)		+= jffs2/
 obj-$(CONFIG_UBIFS_FS)		+= ubifs/
 obj-$(CONFIG_AFFS_FS)		+= affs/
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index 44a3f69d275f..d6b3393633f2 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -169,7 +169,7 @@ extern int	affs_hash_name(struct super_block *sb, const u8 *name, unsigned int l
 extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int);
 extern int	affs_unlink(struct inode *dir, struct dentry *dentry);
 extern int	affs_create(struct mnt_idmap *idmap, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool);
+			struct dentry *dentry, umode_t mode);
 extern struct dentry *affs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 			struct dentry *dentry, umode_t mode);
 extern int	affs_rmdir(struct inode *dir, struct dentry *dentry);
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index c3c6532da4b0..5311828b19e8 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -243,7 +243,7 @@ affs_unlink(struct inode *dir, struct dentry *dentry)
 
 int
 affs_create(struct mnt_idmap *idmap, struct inode *dir,
-	    struct dentry *dentry, umode_t mode, bool excl)
+	    struct dentry *dentry, umode_t mode)
 {
 	struct super_block *sb = dir->i_sb;
 	struct inode	*inode;
@@ -287,7 +287,7 @@ affs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	if (!inode)
 		return ERR_PTR(-ENOSPC);
 
-	inode->i_mode = S_IFDIR | mode;
+	inode->i_mode = mode;
 	affs_mode_to_prot(inode);
 
 	inode->i_op = &affs_dir_inode_operations;
diff --git a/fs/affs/super.c b/fs/affs/super.c
index b232251aa7bb..4f331f784db2 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -88,7 +88,7 @@ void affs_mark_sb_dirty(struct super_block *sb)
 	spin_lock(&sbi->work_lock);
 	if (!sbi->work_queued) {
 	       delay = msecs_to_jiffies(dirty_writeback_interval * 10);
-	       queue_delayed_work(system_long_wq, &sbi->sb_work, delay);
+	       queue_delayed_work(system_dfl_long_wq, &sbi->sb_work, delay);
 	       sbi->work_queued = 1;
 	}
 	spin_unlock(&sbi->work_lock);
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 6df56fe9163f..81565366d937 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -34,7 +34,7 @@ static bool afs_lookup_filldir(struct dir_context *ctx, const char *name, int nl
 			       u64 ino, u32 uniquifier);
 #define AFS_LOOKUP ((filldir_t)0x137UL)
 static int afs_create(struct mnt_idmap *idmap, struct inode *dir,
-		      struct dentry *dentry, umode_t mode, bool excl);
+		      struct dentry *dentry, umode_t mode);
 static struct dentry *afs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 				struct dentry *dentry, umode_t mode);
 static int afs_rmdir(struct inode *dir, struct dentry *dentry);
@@ -1333,7 +1333,7 @@ static struct dentry *afs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	op->file[0].modification = true;
 	op->file[0].update_ctime = true;
 	op->dentry	= dentry;
-	op->create.mode	= S_IFDIR | mode;
+	op->create.mode	= mode;
 	op->create.reason = afs_edit_dir_for_mkdir;
 	op->mtime	= current_time(dir);
 	op->ops		= &afs_mkdir_operation;
@@ -1633,7 +1633,7 @@ static const struct afs_operation_ops afs_create_operation = {
  * create a regular file on an AFS filesystem
  */
 static int afs_create(struct mnt_idmap *idmap, struct inode *dir,
-		      struct dentry *dentry, umode_t mode, bool excl)
+		      struct dentry *dentry, umode_t mode)
 {
 	struct afs_operation *op;
 	struct afs_vnode *dvnode = AFS_FS_I(dir);
diff --git a/fs/autofs/root.c b/fs/autofs/root.c
index 186e960f1e23..b36439f4521e 100644
--- a/fs/autofs/root.c
+++ b/fs/autofs/root.c
@@ -741,7 +741,7 @@ static struct dentry *autofs_dir_mkdir(struct mnt_idmap *idmap,
 
 	autofs_del_active(dentry);
 
-	inode = autofs_get_inode(dir->i_sb, S_IFDIR | mode);
+	inode = autofs_get_inode(dir->i_sb, mode);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index acf8613f5e36..486c40f73e51 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -29,7 +29,7 @@ static const struct file_operations bad_file_ops =
 
 static int bad_inode_create(struct mnt_idmap *idmap,
 			    struct inode *dir, struct dentry *dentry,
-			    umode_t mode, bool excl)
+			    umode_t mode)
 {
 	return -EIO;
 }
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index 5b40ab09a796..4c3b4db08cde 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -83,7 +83,7 @@ const struct file_operations bfs_dir_operations = {
 };
 
 static int bfs_create(struct mnt_idmap *idmap, struct inode *dir,
-		      struct dentry *dentry, umode_t mode, bool excl)
+		      struct dentry *dentry, umode_t mode)
 {
 	int err;
 	struct inode *inode;
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 5de615ca7a75..c06cea00a6d6 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -10,45 +10,49 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/hex.h>
-#include <linux/init.h>
-#include <linux/sched/mm.h>
-#include <linux/magic.h>
+#include <linux/binfmt_misc.h>
 #include <linux/binfmts.h>
-#include <linux/slab.h>
+#include <linux/bitops.h>
+#include <linux/bits.h>
+#include <linux/bug.h>
+#include <linux/cleanup.h>
+#include <linux/cred.h>
 #include <linux/ctype.h>
-#include <linux/string_helpers.h>
 #include <linux/file.h>
-#include <linux/pagemap.h>
-#include <linux/namei.h>
-#include <linux/mount.h>
-#include <linux/fs_context.h>
-#include <linux/syscalls.h>
 #include <linux/fs.h>
+#include <linux/fs_context.h>
+#include <linux/init.h>
+#include <linux/kstrtox.h>
+#include <linux/magic.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/rculist.h>
+#include <linux/refcount.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/srcu.h>
+#include <linux/string.h>
+#include <linux/string_helpers.h>
 #include <linux/uaccess.h>
+#include <linux/user_namespace.h>
 
-#include "internal.h"
-
-#ifdef DEBUG
-# define USE_DEBUG 1
-#else
-# define USE_DEBUG 0
-#endif
-
-enum {
-	VERBOSE_STATUS = 1 /* make it zero to save 400 bytes kernel memory */
+/* Entry status and match type bit numbers. */
+enum binfmt_misc_entry_bits {
+	MISC_FMT_ENABLED_BIT	= 0,
+	MISC_FMT_MAGIC_BIT	= 1,
+	MISC_FMT_BPF_BIT	= 2,
 };
 
-enum {Enabled, Magic};
-#define MISC_FMT_PRESERVE_ARGV0 (1UL << 31)
-#define MISC_FMT_OPEN_BINARY (1UL << 30)
-#define MISC_FMT_CREDENTIALS (1UL << 29)
-#define MISC_FMT_OPEN_FILE (1UL << 28)
+/* Entry behavior flags, fixed at registration time. */
+enum binfmt_misc_entry_flags {
+	MISC_FMT_PRESERVE_ARGV0	= (1U << 31),
+	MISC_FMT_OPEN_BINARY	= (1U << 30),
+	MISC_FMT_CREDENTIALS	= (1U << 29),
+	MISC_FMT_OPEN_FILE	= (1U << 28),
+};
 
-typedef struct {
-	struct list_head list;
+struct binfmt_misc_entry {
+	struct hlist_node node;
 	unsigned long flags;		/* type, status, etc. */
 	int offset;			/* offset of magic */
 	int size;			/* size of magic/mask */
@@ -58,10 +62,12 @@ typedef struct {
 	char *name;
 	struct dentry *dentry;
 	struct file *interp_file;
+	const struct binfmt_misc_ops *bpf_ops;	/* bpf-backed handler ('B') */
+	const char *bpf_ops_name;
 	refcount_t users;		/* sync removal with load_misc_binary() */
-} Node;
-
-static struct file_system_type bm_fs_type;
+	struct rcu_head rcu;
+	char buf[];			/* register string, fields point in here */
+};
 
 /*
  * Max length of the register string.  Determined by:
@@ -74,54 +80,83 @@ static struct file_system_type bm_fs_type;
  *  - interp: ~50 bytes
  *  - flags:  5 bytes
  * Round that up a bit, and then back off to hold the internal data
- * (like struct Node).
+ * (like struct binfmt_misc_entry).
  */
 #define MAX_REGISTER_LENGTH 1920
 
+/* Trailing delimiter pad so field parsing always terminates at a delimiter. */
+#define MISC_DELIM_PAD 8
+
+/* Protects the entry walk in load_misc_binary(), which may sleep in it. */
+DEFINE_STATIC_SRCU_FAST(bm_entries_srcu);
+
+/* Check if @e's magic matches @bprm's buffer, applying the mask if set. */
+static bool entry_matches_magic(const struct binfmt_misc_entry *e,
+				const struct linux_binprm *bprm)
+{
+	const char *s = bprm->buf + e->offset;
+	int i;
+
+	if (!e->mask)
+		return !memcmp(s, e->magic, e->size);
+
+	for (i = 0; i < e->size; i++)
+		if ((s[i] ^ e->magic[i]) & e->mask[i])
+			return false;
+	return true;
+}
+
+/* Check if @e's registered extension matches @ext, NULL if there is none. */
+static bool entry_matches_extension(const struct binfmt_misc_entry *e,
+				    const char *ext)
+{
+	return ext && !strcmp(e->magic, ext);
+}
+
 /**
  * search_binfmt_handler - search for a binary handler for @bprm
  * @misc: handle to binfmt_misc instance
  * @bprm: binary for which we are looking for a handler
  *
  * Search for a binary type handler for @bprm in the list of registered binary
- * type handlers.
+ * type handlers. A 'B' entry's match program decides whether the handler
+ * applies; it may sleep to read the binary. The matched entry is returned
+ * with a reference taken while the walk still held it; a dying entry -
+ * unlinked with its last reference gone - cannot be matched and the walk
+ * moves on.
  *
- * Return: binary type list entry on success, NULL on failure
+ * The caller must hold the bm_entries_srcu read lock, which allows an
+ * entry's evaluation to sleep.
+ *
+ * Return: referenced binary type list entry on success, NULL on failure
  */
-static Node *search_binfmt_handler(struct binfmt_misc *misc,
-				   struct linux_binprm *bprm)
+static struct binfmt_misc_entry *
+search_binfmt_handler(struct binfmt_misc *misc, struct linux_binprm *bprm)
 {
-	char *p = strrchr(bprm->interp, '.');
-	Node *e;
+	char *dot = strrchr(bprm->interp, '.');
+	const char *ext = dot ? dot + 1 : NULL;
+	struct binfmt_misc_entry *e;
 
 	/* Walk all the registered handlers. */
-	list_for_each_entry(e, &misc->entries, list) {
-		char *s;
-		int j;
-
+	hlist_for_each_entry_rcu(e, &misc->entries, node,
+				 srcu_read_lock_held(&bm_entries_srcu)) {
 		/* Make sure this one is currently enabled. */
-		if (!test_bit(Enabled, &e->flags))
-			continue;
-
-		/* Do matching based on extension if applicable. */
-		if (!test_bit(Magic, &e->flags)) {
-			if (p && !strcmp(e->magic, p + 1))
-				return e;
+		if (!test_bit(MISC_FMT_ENABLED_BIT, &e->flags))
 			continue;
-		}
 
-		/* Do matching based on magic & mask. */
-		s = bprm->buf + e->offset;
-		if (e->mask) {
-			for (j = 0; j < e->size; j++)
-				if ((*s++ ^ e->magic[j]) & e->mask[j])
-					break;
+		if (test_bit(MISC_FMT_BPF_BIT, &e->flags)) {
+			if (!e->bpf_ops->match(bprm))
+				continue;
+		} else if (test_bit(MISC_FMT_MAGIC_BIT, &e->flags)) {
+			if (!entry_matches_magic(e, bprm))
+				continue;
 		} else {
-			for (j = 0; j < e->size; j++)
-				if ((*s++ ^ e->magic[j]))
-					break;
+			if (!entry_matches_extension(e, ext))
+				continue;
 		}
-		if (j == e->size)
+
+		/* A dying entry cannot be matched, walk on. */
+		if (refcount_inc_not_zero(&e->users))
 			return e;
 	}
 
@@ -133,157 +168,244 @@ static Node *search_binfmt_handler(struct binfmt_misc *misc,
  * @misc: handle to binfmt_misc instance
  * @bprm: binary for which we are looking for a handler
  *
- * Try to find a binfmt handler for the binary type. If one is found take a
- * reference to protect against removal via bm_{entry,status}_write().
+ * Try to find a binfmt handler for the binary type. If one is found it is
+ * returned with a reference protecting it against removal via
+ * bm_{entry,status}_write().
  *
  * Return: binary type list entry on success, NULL on failure
  */
-static Node *get_binfmt_handler(struct binfmt_misc *misc,
-				struct linux_binprm *bprm)
+static struct binfmt_misc_entry *get_binfmt_handler(struct binfmt_misc *misc,
+						    struct linux_binprm *bprm)
+{
+	guard(srcu_fast)(&bm_entries_srcu);
+	return search_binfmt_handler(misc, bprm);
+}
+
+static void bm_entry_free_rcu(struct rcu_head *rcu)
 {
-	Node *e;
-
-	read_lock(&misc->entries_lock);
-	e = search_binfmt_handler(misc, bprm);
-	if (e)
-		refcount_inc(&e->users);
-	read_unlock(&misc->entries_lock);
-	return e;
+	struct binfmt_misc_entry *e = container_of(rcu, struct binfmt_misc_entry, rcu);
+
+	/* No walker that could sleep in the handler's programs is left. */
+	if (e->bpf_ops)
+		binfmt_misc_put_ops(e->bpf_ops);
+	kfree(e);
 }
 
 /**
- * put_binfmt_handler - put binary handler node
- * @e: node to put
+ * put_binfmt_handler - put binary handler entry
+ * @e: entry to put
  *
- * Free node syncing with load_misc_binary() and defer final free to
+ * Free entry syncing with load_misc_binary() and defer final free to
  * load_misc_binary() in case it is using the binary type handler we were
  * requested to remove.
  */
-static void put_binfmt_handler(Node *e)
+static void put_binfmt_handler(struct binfmt_misc_entry *e)
 {
 	if (refcount_dec_and_test(&e->users)) {
-		if (e->flags & MISC_FMT_OPEN_FILE)
+		if (e->flags & MISC_FMT_OPEN_FILE) {
+			exe_file_allow_write_access(e->interp_file);
 			filp_close(e->interp_file, NULL);
-		kfree(e);
+		}
+		/* Walkers may still dereference this entry, even sleeping. */
+		call_srcu(&bm_entries_srcu, &e->rcu, bm_entry_free_rcu);
 	}
 }
 
+DEFINE_FREE(put_binfmt_handler, struct binfmt_misc_entry *, if (_T) put_binfmt_handler(_T))
+
 /**
- * load_binfmt_misc - load the binfmt_misc of the caller's user namespace
+ * current_binfmt_misc - get the binfmt_misc instance of the caller's user namespace
  *
- * To be called in load_misc_binary() to load the relevant struct binfmt_misc.
- * If a user namespace doesn't have its own binfmt_misc mount it can make use
- * of its ancestor's binfmt_misc handlers. This mimicks the behavior of
- * pre-namespaced binfmt_misc where all registered binfmt_misc handlers where
- * available to all user and user namespaces on the system.
+ * If a user namespace doesn't have its own binfmt_misc mount it uses the
+ * handlers of its closest ancestor with one. This mimics the behavior of
+ * pre-namespaced binfmt_misc where all registered handlers were available
+ * to all users and user namespaces on the system. The init user namespace
+ * instance is statically set up so the fallback is never reached in
+ * practice.
  *
  * Return: the binfmt_misc instance of the caller's user namespace
  */
-static struct binfmt_misc *load_binfmt_misc(void)
+static struct binfmt_misc *current_binfmt_misc(void)
 {
 	const struct user_namespace *user_ns;
 	struct binfmt_misc *misc;
 
-	user_ns = current_user_ns();
-	while (user_ns) {
+	for (user_ns = current_user_ns(); user_ns; user_ns = user_ns->parent) {
 		/* Pairs with smp_store_release() in bm_fill_super(). */
 		misc = smp_load_acquire(&user_ns->binfmt_misc);
 		if (misc)
 			return misc;
-
-		user_ns = user_ns->parent;
 	}
 
 	return &init_binfmt_misc;
 }
 
+/**
+ * entry_select_interpreter - get the interpreter for the matched @e
+ * @e: matched binary type handler
+ * @bprm: binary that is being executed
+ *
+ * A static entry carries its interpreter path, for a 'B' entry the
+ * handler's load program selects it. The match is committed, so a failing
+ * program fails the exec.
+ *
+ * Return: the interpreter on success, an ERR_PTR on failure
+ */
+static const char *entry_select_interpreter(const struct binfmt_misc_entry *e,
+					    struct linux_binprm *bprm)
+{
+	int retval;
+
+	if (!test_bit(MISC_FMT_BPF_BIT, &e->flags))
+		return e->interpreter;
+
+	/* Drop any interpreter or flags a previous chain level staged. */
+	kfree(bprm->bpf_interp);
+	bprm->bpf_interp = NULL;
+	bprm->bpf_flags = 0;
+
+	retval = e->bpf_ops->load(bprm);
+	if (retval) {
+		/* Keep a program-supplied error within errno range. */
+		if (retval > 0 || retval < -MAX_ERRNO)
+			retval = -ENOEXEC;
+		goto drop_staged;
+	}
+
+	/* Selecting an interpreter is part of the contract. */
+	if (!bprm->bpf_interp) {
+		retval = -ENOEXEC;
+		goto drop_staged;
+	}
+
+	return bprm->bpf_interp;
+
+drop_staged:
+	/* A failing load leaves nothing behind for later entries. */
+	kfree(bprm->bpf_interp_arg);
+	bprm->bpf_interp_arg = NULL;
+	bprm->bpf_flags = 0;
+	return ERR_PTR(retval);
+}
+
 /*
  * the loader itself
  */
 static int load_misc_binary(struct linux_binprm *bprm)
 {
-	Node *fmt;
-	struct file *interp_file = NULL;
-	int retval = -ENOEXEC;
+	struct binfmt_misc_entry *fmt __free(put_binfmt_handler) = NULL;
+	const char *interpreter;
+	struct file *interp_file;
 	struct binfmt_misc *misc;
+	bool preserve_argv0, want_execfd, want_creds;
+	int retval;
 
-	misc = load_binfmt_misc();
-	if (!misc->enabled)
-		return retval;
+	misc = current_binfmt_misc();
+	if (!READ_ONCE(misc->enabled))
+		return -ENOEXEC;
 
 	fmt = get_binfmt_handler(misc, bprm);
 	if (!fmt)
-		return retval;
+		return -ENOEXEC;
 
 	/* Need to be able to load the file after exec */
-	retval = -ENOENT;
 	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
-		goto ret;
+		return -ENOENT;
+
+	interpreter = entry_select_interpreter(fmt, bprm);
+	if (IS_ERR(interpreter))
+		return PTR_ERR(interpreter);
+
+	/*
+	 * The invocation flags are fixed at registration for a static handler
+	 * and chosen per exec by the load program, via bpf_binprm_set_flags(),
+	 * for a bpf one.
+	 */
+	if (test_bit(MISC_FMT_BPF_BIT, &fmt->flags)) {
+		u64 f = bprm->bpf_flags;
 
-	if (fmt->flags & MISC_FMT_PRESERVE_ARGV0) {
+		/* Clear so it can't accumulate into a nested interpreter level. */
+		bprm->bpf_flags = 0;
+
+		preserve_argv0 = f & BPF_BINPRM_PRESERVE_ARGV0;
+		want_creds = f & BPF_BINPRM_CREDENTIALS;
+		want_execfd = f & (BPF_BINPRM_CREDENTIALS | BPF_BINPRM_EXECFD);
+	} else {
+		preserve_argv0 = fmt->flags & MISC_FMT_PRESERVE_ARGV0;
+		want_creds = fmt->flags & MISC_FMT_CREDENTIALS;
+		want_execfd = fmt->flags & MISC_FMT_OPEN_BINARY;
+	}
+
+	/* The entry's own choice - not one accumulated from an earlier level. */
+	if (preserve_argv0) {
 		bprm->interp_flags |= BINPRM_FLAGS_PRESERVE_ARGV0;
 	} else {
 		retval = remove_arg_zero(bprm);
 		if (retval)
-			goto ret;
+			return retval;
 	}
 
-	/* make argv[1] be the path to the binary */
+	/* make the binary the last argument to the interpreter */
 	retval = copy_string_kernel(bprm->interp, bprm);
 	if (retval < 0)
-		goto ret;
+		return retval;
 	bprm->argc++;
 
+	/*
+	 * A single optional argument to the interpreter, inserted between it
+	 * and the binary just like the argument of a #! interpreter line.
+	 */
+	if (bprm->bpf_interp_arg) {
+		retval = copy_string_kernel(bprm->bpf_interp_arg, bprm);
+		if (retval < 0)
+			return retval;
+		bprm->argc++;
+		/* Consumed - don't let it leak into a nested interpreter's argv. */
+		kfree(bprm->bpf_interp_arg);
+		bprm->bpf_interp_arg = NULL;
+	}
+
 	/* add the interp as argv[0] */
-	retval = copy_string_kernel(fmt->interpreter, bprm);
+	retval = copy_string_kernel(interpreter, bprm);
 	if (retval < 0)
-		goto ret;
+		return retval;
 	bprm->argc++;
 
 	/* Update interp in case binfmt_script needs it. */
-	retval = bprm_change_interp(fmt->interpreter, bprm);
+	retval = bprm_change_interp(interpreter, bprm);
 	if (retval < 0)
-		goto ret;
+		return retval;
 
 	if (fmt->flags & MISC_FMT_OPEN_FILE) {
 		interp_file = file_clone_open(fmt->interp_file);
-		if (!IS_ERR(interp_file))
-			deny_write_access(interp_file);
+		if (!IS_ERR(interp_file)) {
+			int err = exe_file_deny_write_access(interp_file);
+
+			if (err) {
+				fput(interp_file);
+				interp_file = ERR_PTR(err);
+			}
+		}
 	} else {
-		interp_file = open_exec(fmt->interpreter);
+		interp_file = open_exec(interpreter);
 	}
-	retval = PTR_ERR(interp_file);
 	if (IS_ERR(interp_file))
-		goto ret;
+		return PTR_ERR(interp_file);
 
 	bprm->interpreter = interp_file;
-	if (fmt->flags & MISC_FMT_OPEN_BINARY)
+	if (want_execfd)
 		bprm->have_execfd = 1;
-	if (fmt->flags & MISC_FMT_CREDENTIALS)
+	if (want_creds)
 		bprm->execfd_creds = 1;
-
-	retval = 0;
-ret:
-
-	/*
-	 * If we actually put the node here all concurrent calls to
-	 * load_misc_binary() will have finished. We also know
-	 * that for the refcount to be zero someone must have concurently
-	 * removed the binary type handler from the list and it's our job to
-	 * free it.
-	 */
-	put_binfmt_handler(fmt);
-
-	return retval;
+	return 0;
 }
 
 /* Command parsers */
 
 /*
- * parses and copies one argument enclosed in del from *sp to *dp,
- * recognising the \x special.
- * returns pointer to the copied argument or NULL in case of an
- * error (and sets err) or null argument length.
+ * Scan the argument starting at @s up to the delimiter @del, recognising
+ * the \x escape. Terminates the argument with a NUL and returns a pointer
+ * past it or NULL on a malformed escape.
  */
 static char *scanarg(char *s, char del)
 {
@@ -298,45 +420,143 @@ static char *scanarg(char *s, char del)
 				return NULL;
 		}
 	}
-	s[-1] ='\0';
+	s[-1] = '\0';
 	return s;
 }
 
-static char *check_special_flags(char *sfs, Node *e)
+static char *check_special_flags(char *p, struct binfmt_misc_entry *e)
 {
-	char *p = sfs;
-	int cont = 1;
-
-	/* special flags */
-	while (cont) {
+	for (;; p++) {
 		switch (*p) {
 		case 'P':
 			pr_debug("register: flag: P (preserve argv0)\n");
-			p++;
 			e->flags |= MISC_FMT_PRESERVE_ARGV0;
 			break;
 		case 'O':
 			pr_debug("register: flag: O (open binary)\n");
-			p++;
 			e->flags |= MISC_FMT_OPEN_BINARY;
 			break;
 		case 'C':
 			pr_debug("register: flag: C (preserve creds)\n");
-			p++;
-			/* this flags also implies the
-			   open-binary flag */
-			e->flags |= (MISC_FMT_CREDENTIALS |
-					MISC_FMT_OPEN_BINARY);
+			/* C implies O */
+			e->flags |= MISC_FMT_CREDENTIALS | MISC_FMT_OPEN_BINARY;
 			break;
 		case 'F':
 			pr_debug("register: flag: F: open interpreter file now\n");
-			p++;
 			e->flags |= MISC_FMT_OPEN_FILE;
 			break;
 		default:
-			cont = 0;
+			return p;
 		}
 	}
+}
+
+/* Parse the 'offset', 'magic' and 'mask' fields of an 'M' entry. */
+static char *parse_magic_fields(struct binfmt_misc_entry *e, char *p, char del)
+{
+	char *s;
+
+	/* Parse the 'offset' field. */
+	s = strchr(p, del);
+	if (!s)
+		return NULL;
+	*s = '\0';
+	if (p != s) {
+		if (kstrtoint(p, 10, &e->offset) || e->offset < 0)
+			return NULL;
+	}
+	p = s + 1;
+	pr_debug("register: offset: %#x\n", e->offset);
+
+	/* Parse the 'magic' field. */
+	e->magic = p;
+	p = scanarg(p, del);
+	if (!p || !e->magic[0])
+		return NULL;
+	print_hex_dump_debug(
+		KBUILD_MODNAME ": register: magic[raw]: ",
+		DUMP_PREFIX_NONE, 16, 1, e->magic, p - e->magic, true);
+
+	/* Parse the 'mask' field. */
+	e->mask = p;
+	p = scanarg(p, del);
+	if (!p)
+		return NULL;
+	if (!e->mask[0]) {
+		e->mask = NULL;
+		pr_debug("register:  mask[raw]: none\n");
+	} else {
+		print_hex_dump_debug(
+			KBUILD_MODNAME ": register:  mask[raw]: ",
+			DUMP_PREFIX_NONE, 16, 1, e->mask, p - e->mask, true);
+	}
+
+	/*
+	 * Decode the magic & mask fields. Note: while we might have accepted
+	 * embedded NUL bytes from above, the unescape helpers will stop at
+	 * the first one they encounter.
+	 */
+	e->size = string_unescape_inplace(e->magic, UNESCAPE_HEX);
+	if (e->mask && string_unescape_inplace(e->mask, UNESCAPE_HEX) != e->size)
+		return NULL;
+	if (e->size > BINPRM_BUF_SIZE || BINPRM_BUF_SIZE - e->size < e->offset)
+		return NULL;
+	pr_debug("register: magic/mask length: %i\n", e->size);
+	print_hex_dump_debug(
+		KBUILD_MODNAME ": register: magic[decoded]: ",
+		DUMP_PREFIX_NONE, 16, 1, e->magic, e->size, true);
+	if (e->mask)
+		print_hex_dump_debug(
+			KBUILD_MODNAME ": register:  mask[decoded]: ",
+			DUMP_PREFIX_NONE, 16, 1, e->mask, e->size, true);
+	return p;
+}
+
+/* Parse the 'magic' field of an 'E' entry: the filename extension. */
+static char *parse_extension_fields(struct binfmt_misc_entry *e, char *p,
+				    char del)
+{
+	/* Skip the 'offset' field. */
+	p = strchr(p, del);
+	if (!p)
+		return NULL;
+	*p++ = '\0';
+
+	/* Parse the 'magic' field. */
+	e->magic = p;
+	p = strchr(p, del);
+	if (!p)
+		return NULL;
+	*p++ = '\0';
+	if (!e->magic[0] || strchr(e->magic, '/'))
+		return NULL;
+	pr_debug("register: extension: {%s}\n", e->magic);
+
+	/* Skip the 'mask' field. */
+	p = strchr(p, del);
+	if (!p)
+		return NULL;
+	*p++ = '\0';
+	return p;
+}
+
+/*
+ * Parse the fields of a 'B' entry: the 'offset', 'magic' and 'mask' fields
+ * must be empty. The handler name is carried in the 'interpreter' field.
+ */
+static char *parse_bpf_fields(struct binfmt_misc_entry *e, char *p, char del)
+{
+	/* The 'offset' field must be empty. */
+	if (*p++ != del)
+		return NULL;
+
+	/* The 'magic' field must be empty. */
+	if (*p++ != del)
+		return NULL;
+
+	/* The 'mask' field must be empty. */
+	if (*p++ != del)
+		return NULL;
 
 	return p;
 }
@@ -346,50 +566,52 @@ static char *check_special_flags(char *sfs, Node *e)
  * ':name:type:offset:magic:mask:interpreter:flags'
  * where the ':' is the IFS, that can be chosen with the first char
  */
-static Node *create_entry(const char __user *buffer, size_t count)
+static struct binfmt_misc_entry *create_entry(const char __user *buffer,
+					      size_t count)
 {
-	Node *e;
-	int memsize, err;
+	struct binfmt_misc_entry *e __free(kfree) = NULL;
 	char *buf, *p;
 	char del;
 
 	pr_debug("register: received %zu bytes\n", count);
 
 	/* some sanity checks */
-	err = -EINVAL;
 	if ((count < 11) || (count > MAX_REGISTER_LENGTH))
-		goto out;
+		return ERR_PTR(-EINVAL);
 
-	err = -ENOMEM;
-	memsize = sizeof(Node) + count + 8;
-	e = kmalloc(memsize, GFP_KERNEL_ACCOUNT);
+	e = kmalloc(struct_size(e, buf, count + MISC_DELIM_PAD),
+		    GFP_KERNEL_ACCOUNT);
 	if (!e)
-		goto out;
+		return ERR_PTR(-ENOMEM);
 
-	p = buf = (char *)e + sizeof(Node);
+	p = buf = e->buf;
 
-	memset(e, 0, sizeof(Node));
+	memset(e, 0, sizeof(*e));
 	if (copy_from_user(buf, buffer, count))
-		goto efault;
+		return ERR_PTR(-EFAULT);
 
-	del = *p++;	/* delimeter */
+	del = *p++;	/* delimiter */
 
 	pr_debug("register: delim: %#x {%c}\n", del, del);
 
+	/* A flag-char delimiter runs the flag scan off the buffer. */
+	if (del == 'P' || del == 'O' || del == 'C' || del == 'F')
+		return ERR_PTR(-EINVAL);
+
 	/* Pad the buffer with the delim to simplify parsing below. */
-	memset(buf + count, del, 8);
+	memset(buf + count, del, MISC_DELIM_PAD);
 
 	/* Parse the 'name' field. */
 	e->name = p;
 	p = strchr(p, del);
 	if (!p)
-		goto einval;
+		return ERR_PTR(-EINVAL);
 	*p++ = '\0';
 	if (!e->name[0] ||
 	    !strcmp(e->name, ".") ||
 	    !strcmp(e->name, "..") ||
 	    strchr(e->name, '/'))
-		goto einval;
+		return ERR_PTR(-EINVAL);
 
 	pr_debug("register: name: {%s}\n", e->name);
 
@@ -397,159 +619,84 @@ static Node *create_entry(const char __user *buffer, size_t count)
 	switch (*p++) {
 	case 'E':
 		pr_debug("register: type: E (extension)\n");
-		e->flags = 1 << Enabled;
+		e->flags = BIT(MISC_FMT_ENABLED_BIT);
 		break;
 	case 'M':
 		pr_debug("register: type: M (magic)\n");
-		e->flags = (1 << Enabled) | (1 << Magic);
+		e->flags = BIT(MISC_FMT_ENABLED_BIT) | BIT(MISC_FMT_MAGIC_BIT);
+		break;
+	case 'B':
+		pr_debug("register: type: B (bpf)\n");
+		if (!IS_ENABLED(CONFIG_BINFMT_MISC_BPF))
+			return ERR_PTR(-EINVAL);
+		e->flags = BIT(MISC_FMT_ENABLED_BIT) | BIT(MISC_FMT_BPF_BIT);
 		break;
 	default:
-		goto einval;
+		return ERR_PTR(-EINVAL);
 	}
 	if (*p++ != del)
-		goto einval;
-
-	if (test_bit(Magic, &e->flags)) {
-		/* Handle the 'M' (magic) format. */
-		char *s;
-
-		/* Parse the 'offset' field. */
-		s = strchr(p, del);
-		if (!s)
-			goto einval;
-		*s = '\0';
-		if (p != s) {
-			int r = kstrtoint(p, 10, &e->offset);
-			if (r != 0 || e->offset < 0)
-				goto einval;
-		}
-		p = s;
-		if (*p++)
-			goto einval;
-		pr_debug("register: offset: %#x\n", e->offset);
-
-		/* Parse the 'magic' field. */
-		e->magic = p;
-		p = scanarg(p, del);
-		if (!p)
-			goto einval;
-		if (!e->magic[0])
-			goto einval;
-		if (USE_DEBUG)
-			print_hex_dump_bytes(
-				KBUILD_MODNAME ": register: magic[raw]: ",
-				DUMP_PREFIX_NONE, e->magic, p - e->magic);
-
-		/* Parse the 'mask' field. */
-		e->mask = p;
-		p = scanarg(p, del);
-		if (!p)
-			goto einval;
-		if (!e->mask[0]) {
-			e->mask = NULL;
-			pr_debug("register:  mask[raw]: none\n");
-		} else if (USE_DEBUG)
-			print_hex_dump_bytes(
-				KBUILD_MODNAME ": register:  mask[raw]: ",
-				DUMP_PREFIX_NONE, e->mask, p - e->mask);
-
-		/*
-		 * Decode the magic & mask fields.
-		 * Note: while we might have accepted embedded NUL bytes from
-		 * above, the unescape helpers here will stop at the first one
-		 * it encounters.
-		 */
-		e->size = string_unescape_inplace(e->magic, UNESCAPE_HEX);
-		if (e->mask &&
-		    string_unescape_inplace(e->mask, UNESCAPE_HEX) != e->size)
-			goto einval;
-		if (e->size > BINPRM_BUF_SIZE ||
-		    BINPRM_BUF_SIZE - e->size < e->offset)
-			goto einval;
-		pr_debug("register: magic/mask length: %i\n", e->size);
-		if (USE_DEBUG) {
-			print_hex_dump_bytes(
-				KBUILD_MODNAME ": register: magic[decoded]: ",
-				DUMP_PREFIX_NONE, e->magic, e->size);
-
-			if (e->mask) {
-				int i;
-				char *masked = kmalloc(e->size, GFP_KERNEL_ACCOUNT);
-
-				print_hex_dump_bytes(
-					KBUILD_MODNAME ": register:  mask[decoded]: ",
-					DUMP_PREFIX_NONE, e->mask, e->size);
-
-				if (masked) {
-					for (i = 0; i < e->size; ++i)
-						masked[i] = e->magic[i] & e->mask[i];
-					print_hex_dump_bytes(
-						KBUILD_MODNAME ": register:  magic[masked]: ",
-						DUMP_PREFIX_NONE, masked, e->size);
-
-					kfree(masked);
-				}
-			}
-		}
-	} else {
-		/* Handle the 'E' (extension) format. */
-
-		/* Skip the 'offset' field. */
-		p = strchr(p, del);
-		if (!p)
-			goto einval;
-		*p++ = '\0';
-
-		/* Parse the 'magic' field. */
-		e->magic = p;
-		p = strchr(p, del);
-		if (!p)
-			goto einval;
-		*p++ = '\0';
-		if (!e->magic[0] || strchr(e->magic, '/'))
-			goto einval;
-		pr_debug("register: extension: {%s}\n", e->magic);
-
-		/* Skip the 'mask' field. */
-		p = strchr(p, del);
-		if (!p)
-			goto einval;
-		*p++ = '\0';
-	}
+		return ERR_PTR(-EINVAL);
+
+	if (test_bit(MISC_FMT_BPF_BIT, &e->flags))
+		p = parse_bpf_fields(e, p, del);
+	else if (test_bit(MISC_FMT_MAGIC_BIT, &e->flags))
+		p = parse_magic_fields(e, p, del);
+	else
+		p = parse_extension_fields(e, p, del);
+	if (!p)
+		return ERR_PTR(-EINVAL);
 
 	/* Parse the 'interpreter' field. */
 	e->interpreter = p;
 	p = strchr(p, del);
 	if (!p)
-		goto einval;
+		return ERR_PTR(-EINVAL);
 	*p++ = '\0';
-	if (!e->interpreter[0])
-		goto einval;
-	pr_debug("register: interpreter: {%s}\n", e->interpreter);
+	if (test_bit(MISC_FMT_BPF_BIT, &e->flags)) {
+		/* The 'interpreter' field carries the handler name. */
+		e->bpf_ops_name = e->interpreter;
+		e->interpreter = NULL;
+		if (!e->bpf_ops_name[0])
+			return ERR_PTR(-EINVAL);
+		pr_debug("register: bpf handler: {%s}\n", e->bpf_ops_name);
+	} else if (!e->interpreter[0]) {
+		return ERR_PTR(-EINVAL);
+	} else {
+		pr_debug("register: interpreter: {%s}\n", e->interpreter);
+	}
 
 	/* Parse the 'flags' field. */
 	p = check_special_flags(p, e);
 	if (*p == '\n')
 		p++;
 	if (p != buf + count)
-		goto einval;
-
-	return e;
+		return ERR_PTR(-EINVAL);
 
-out:
-	return ERR_PTR(err);
+	/*
+	 * A bpf handler decides the invocation flags per exec with
+	 * bpf_binprm_set_flags() rather than fixing them at registration, so a
+	 * 'B' entry carries no flags: 'P', 'C' and 'O' become per-exec choices
+	 * and 'F' (pre-open a fixed interpreter) is meaningless for it.
+	 */
+	if (test_bit(MISC_FMT_BPF_BIT, &e->flags) &&
+	    (e->flags & (MISC_FMT_PRESERVE_ARGV0 | MISC_FMT_OPEN_BINARY |
+			 MISC_FMT_CREDENTIALS | MISC_FMT_OPEN_FILE)))
+		return ERR_PTR(-EINVAL);
 
-efault:
-	kfree(e);
-	return ERR_PTR(-EFAULT);
-einval:
-	kfree(e);
-	return ERR_PTR(-EINVAL);
+	return no_free_ptr(e);
 }
 
+/* Commands accepted by the /status and /<entry> files. */
+enum bm_command {
+	BM_CMD_IGNORE,	/* empty write */
+	BM_CMD_DISABLE,	/* "0" */
+	BM_CMD_ENABLE,	/* "1" */
+	BM_CMD_REMOVE,	/* "-1" */
+};
+
 /*
- * Set status of entry/binfmt_misc:
- * '1' enables, '0' disables and '-1' clears entry/binfmt_misc
+ * Parse what userspace wrote to /status or an entry file: '1' enables,
+ * '0' disables and '-1' removes the entry or all entries.
  */
 static int parse_command(const char __user *buffer, size_t count)
 {
@@ -560,62 +707,69 @@ static int parse_command(const char __user *buffer, size_t count)
 	if (copy_from_user(s, buffer, count))
 		return -EFAULT;
 	if (!count)
-		return 0;
+		return BM_CMD_IGNORE;
 	if (s[count - 1] == '\n')
 		count--;
 	if (count == 1 && s[0] == '0')
-		return 1;
+		return BM_CMD_DISABLE;
 	if (count == 1 && s[0] == '1')
-		return 2;
+		return BM_CMD_ENABLE;
 	if (count == 2 && s[0] == '-' && s[1] == '1')
-		return 3;
+		return BM_CMD_REMOVE;
 	return -EINVAL;
 }
 
 /* generic stuff */
 
-static void entry_status(Node *e, char *page)
+static void bm_seq_hex(struct seq_file *m, const u8 *data, int size)
 {
-	char *dp = page;
-	const char *status = "disabled";
+	for (int i = 0; i < size; i++)
+		seq_printf(m, "%02x", data[i]);
+}
 
-	if (test_bit(Enabled, &e->flags))
-		status = "enabled";
+static int bm_entry_show(struct seq_file *m, void *unused)
+{
+	struct binfmt_misc_entry *e = m->private;
 
-	if (!VERBOSE_STATUS) {
-		sprintf(page, "%s\n", status);
-		return;
-	}
+	if (test_bit(MISC_FMT_ENABLED_BIT, &e->flags))
+		seq_puts(m, "enabled\n");
+	else
+		seq_puts(m, "disabled\n");
 
-	dp += sprintf(dp, "%s\ninterpreter %s\n", status, e->interpreter);
+	if (test_bit(MISC_FMT_BPF_BIT, &e->flags))
+		seq_printf(m, "bpf %s\n", e->bpf_ops->name);
+	else
+		seq_printf(m, "interpreter %s\n", e->interpreter);
 
 	/* print the special flags */
-	dp += sprintf(dp, "flags: ");
+	seq_puts(m, "flags: ");
 	if (e->flags & MISC_FMT_PRESERVE_ARGV0)
-		*dp++ = 'P';
+		seq_putc(m, 'P');
 	if (e->flags & MISC_FMT_OPEN_BINARY)
-		*dp++ = 'O';
+		seq_putc(m, 'O');
 	if (e->flags & MISC_FMT_CREDENTIALS)
-		*dp++ = 'C';
+		seq_putc(m, 'C');
 	if (e->flags & MISC_FMT_OPEN_FILE)
-		*dp++ = 'F';
-	*dp++ = '\n';
+		seq_putc(m, 'F');
+	seq_putc(m, '\n');
 
-	if (!test_bit(Magic, &e->flags)) {
-		sprintf(dp, "extension .%s\n", e->magic);
+	if (test_bit(MISC_FMT_BPF_BIT, &e->flags)) {
+		/* The program does the matching. */
+	} else if (!test_bit(MISC_FMT_MAGIC_BIT, &e->flags)) {
+		seq_printf(m, "extension .%s\n", e->magic);
 	} else {
-		dp += sprintf(dp, "offset %i\nmagic ", e->offset);
-		dp = bin2hex(dp, e->magic, e->size);
+		seq_printf(m, "offset %i\nmagic ", e->offset);
+		bm_seq_hex(m, e->magic, e->size);
 		if (e->mask) {
-			dp += sprintf(dp, "\nmask ");
-			dp = bin2hex(dp, e->mask, e->size);
+			seq_puts(m, "\nmask ");
+			bm_seq_hex(m, e->mask, e->size);
 		}
-		*dp++ = '\n';
-		*dp = '\0';
+		seq_putc(m, '\n');
 	}
+	return 0;
 }
 
-static struct inode *bm_get_inode(struct super_block *sb, int mode)
+static struct inode *bm_get_inode(struct super_block *sb, umode_t mode)
 {
 	struct inode *inode = new_inode(sb);
 
@@ -651,14 +805,14 @@ static struct binfmt_misc *i_binfmt_misc(struct inode *inode)
  * entry is removed or the filesystem is unmounted and the super block is
  * shutdown.
  *
- * If the ->evict call was not caused by a super block shutdown but by a write
- * to remove the entry or all entries via bm_{entry,status}_write() the entry
- * will have already been removed from the list. We keep the list_empty() check
- * to make that explicit.
+ * If the ->evict call was not caused by a super block shutdown but by
+ * removing the entry via bm_{entry,status}_write() or unlink(2) the entry
+ * will have already been removed from the list. We keep the hlist_unhashed()
+ * check to make that explicit.
 */
 static void bm_evict_inode(struct inode *inode)
 {
-	Node *e = inode->i_private;
+	struct binfmt_misc_entry *e = inode->i_private;
 
 	clear_inode(inode);
 
@@ -666,89 +820,132 @@ static void bm_evict_inode(struct inode *inode)
 		struct binfmt_misc *misc;
 
 		misc = i_binfmt_misc(inode);
-		write_lock(&misc->entries_lock);
-		if (!list_empty(&e->list))
-			list_del_init(&e->list);
-		write_unlock(&misc->entries_lock);
+		spin_lock(&misc->entries_lock);
+		if (!hlist_unhashed(&e->node))
+			hlist_del_init_rcu(&e->node);
+		spin_unlock(&misc->entries_lock);
 		put_binfmt_handler(e);
 	}
 }
 
 /**
+ * unlink_binfmt_handler - unhash a binary type handler
+ * @misc: handle to binfmt_misc instance
+ * @e: binary type handler to unhash
+ *
+ * Adding and removing entries via bm_{entry,register,status}_write() and
+ * unlink(2) happens under the exclusively held inode lock of the root
+ * dentry keeping the list stable for writers. load_misc_binary() walks it
+ * concurrently under SRCU. The entries_lock is only held around the actual
+ * unlink to serialize against bm_evict_inode() which unlinks entries
+ * during umount without holding the root inode lock.
+ */
+static void unlink_binfmt_handler(struct binfmt_misc *misc,
+				  struct binfmt_misc_entry *e)
+{
+	spin_lock(&misc->entries_lock);
+	hlist_del_init_rcu(&e->node);
+	spin_unlock(&misc->entries_lock);
+}
+
+/**
  * remove_binfmt_handler - remove a binary type handler
  * @misc: handle to binfmt_misc instance
  * @e: binary type handler to remove
  *
  * Remove a binary type handler from the list of binary type handlers and
- * remove its associated dentry. This is called from
- * binfmt_{entry,status}_write(). In the future, we might want to think about
- * adding a proper ->unlink() method to binfmt_misc instead of forcing caller's
- * to use writes to files in order to delete binary type handlers. But it has
- * worked for so long that it's not a pressing issue.
+ * remove its associated dentry.
  */
-static void remove_binfmt_handler(struct binfmt_misc *misc, Node *e)
+static void remove_binfmt_handler(struct binfmt_misc *misc,
+				  struct binfmt_misc_entry *e)
 {
-	write_lock(&misc->entries_lock);
-	list_del_init(&e->list);
-	write_unlock(&misc->entries_lock);
+	unlink_binfmt_handler(misc, e);
 	locked_recursive_removal(e->dentry, NULL);
 }
 
-/* /<entry> */
+/* Remove @e unless it was already removed. */
+static void bm_remove_entry(struct binfmt_misc_entry *e, struct super_block *sb)
+{
+	struct inode *root = d_inode(sb->s_root);
 
-static ssize_t
-bm_entry_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
+	inode_lock_nested(root, I_MUTEX_PARENT);
+	if (!hlist_unhashed(&e->node))
+		remove_binfmt_handler(i_binfmt_misc(root), e);
+	inode_unlock(root);
+}
+
+/* Remove all entries of the binfmt_misc instance @misc belonging to @sb. */
+static void bm_remove_all_entries(struct binfmt_misc *misc,
+				  struct super_block *sb)
 {
-	Node *e = file_inode(file)->i_private;
-	ssize_t res;
-	char *page;
+	struct inode *root = d_inode(sb->s_root);
+	struct binfmt_misc_entry *e;
+	struct hlist_node *next;
+
+	inode_lock_nested(root, I_MUTEX_PARENT);
+	hlist_for_each_entry_safe(e, next, &misc->entries, node)
+		remove_binfmt_handler(misc, e);
+	inode_unlock(root);
+}
 
-	page = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!page)
-		return -ENOMEM;
+/**
+ * bm_unlink - remove a binary type handler via unlink(2)
+ * @dir: inode of the root directory
+ * @dentry: entry file to remove
+ *
+ * Removing the entry file removes its binary type handler, exactly like
+ * writing -1 to it does. The status and register control files can't be
+ * removed. The VFS calls this with the root inode lock held which
+ * serializes against the write based add and remove paths.
+ */
+static int bm_unlink(struct inode *dir, struct dentry *dentry)
+{
+	struct binfmt_misc_entry *e = d_inode(dentry)->i_private;
+
+	if (!e)
+		return -EPERM;
+
+	unlink_binfmt_handler(i_binfmt_misc(dir), e);
+	return simple_unlink(dir, dentry);
+}
+
+static const struct inode_operations bm_dir_inode_operations = {
+	.lookup		= simple_lookup,
+	.unlink		= bm_unlink,
+};
+
+/* /<entry> */
 
-	entry_status(e, page);
+static int bm_entry_open(struct inode *inode, struct file *file)
+{
+	int ret;
 
-	res = simple_read_from_buffer(buf, nbytes, ppos, page, strlen(page));
+	ret = single_open(file, bm_entry_show, inode->i_private);
+	if (ret)
+		return ret;
 
-	kfree(page);
-	return res;
+	/* seq_open() clears FMODE_PWRITE, bm_entry_write() takes any offset */
+	if (file->f_mode & FMODE_WRITE)
+		file->f_mode |= FMODE_PWRITE;
+	return 0;
 }
 
 static ssize_t bm_entry_write(struct file *file, const char __user *buffer,
 				size_t count, loff_t *ppos)
 {
 	struct inode *inode = file_inode(file);
-	Node *e = inode->i_private;
+	struct binfmt_misc_entry *e = inode->i_private;
 	int res = parse_command(buffer, count);
 
 	switch (res) {
-	case 1:
-		/* Disable this handler. */
-		clear_bit(Enabled, &e->flags);
+	case BM_CMD_DISABLE:
+		clear_bit(MISC_FMT_ENABLED_BIT, &e->flags);
 		break;
-	case 2:
-		/* Enable this handler. */
-		set_bit(Enabled, &e->flags);
+	case BM_CMD_ENABLE:
+		set_bit(MISC_FMT_ENABLED_BIT, &e->flags);
 		break;
-	case 3:
-		/* Delete this handler. */
-		inode = d_inode(inode->i_sb->s_root);
-		inode_lock_nested(inode, I_MUTEX_PARENT);
-
-		/*
-		 * In order to add new element or remove elements from the list
-		 * via bm_{entry,register,status}_write() inode_lock() on the
-		 * root inode must be held.
-		 * The lock is exclusive ensuring that the list can't be
-		 * modified. Only load_misc_binary() can access but does so
-		 * read-only. So we only need to take the write lock when we
-		 * actually remove the entry from the list.
-		 */
-		if (!list_empty(&e->list))
-			remove_binfmt_handler(i_binfmt_misc(inode), e);
-
-		inode_unlock(inode);
+	case BM_CMD_REMOVE:
+		bm_remove_entry(e, inode->i_sb);
 		break;
 	default:
 		return res;
@@ -758,15 +955,17 @@ static ssize_t bm_entry_write(struct file *file, const char __user *buffer,
 }
 
 static const struct file_operations bm_entry_operations = {
-	.read		= bm_entry_read,
+	.open		= bm_entry_open,
+	.read		= seq_read,
 	.write		= bm_entry_write,
-	.llseek		= default_llseek,
+	.llseek		= seq_lseek,
+	.release	= single_release,
 };
 
 /* /register */
 
 /* add to filesystem */
-static int add_entry(Node *e, struct super_block *sb)
+static int add_entry(struct binfmt_misc_entry *e, struct super_block *sb)
 {
 	struct dentry *dentry = simple_start_creating(sb->s_root, e->name);
 	struct inode *inode;
@@ -788,9 +987,9 @@ static int add_entry(Node *e, struct super_block *sb)
 
 	d_make_persistent(dentry, inode);
 	misc = i_binfmt_misc(inode);
-	write_lock(&misc->entries_lock);
-	list_add(&e->list, &misc->entries);
-	write_unlock(&misc->entries_lock);
+	spin_lock(&misc->entries_lock);
+	hlist_add_head_rcu(&e->node, &misc->entries);
+	spin_unlock(&misc->entries_lock);
 	simple_done_creating(dentry);
 	return 0;
 }
@@ -798,16 +997,24 @@ static int add_entry(Node *e, struct super_block *sb)
 static ssize_t bm_register_write(struct file *file, const char __user *buffer,
 			       size_t count, loff_t *ppos)
 {
-	Node *e;
+	struct binfmt_misc_entry *e __free(kfree) = NULL;
 	struct super_block *sb = file_inode(file)->i_sb;
-	int err = 0;
 	struct file *f = NULL;
+	int err;
 
 	e = create_entry(buffer, count);
-
 	if (IS_ERR(e))
 		return PTR_ERR(e);
 
+	if (test_bit(MISC_FMT_BPF_BIT, &e->flags)) {
+		e->bpf_ops = binfmt_misc_get_ops(sb->s_user_ns, e->bpf_ops_name);
+		if (!e->bpf_ops) {
+			pr_notice("register: no bpf handler named %s\n",
+				  e->bpf_ops_name);
+			return -ENOENT;
+		}
+	}
+
 	if (e->flags & MISC_FMT_OPEN_FILE) {
 		/*
 		 * Now that we support unprivileged binfmt_misc mounts make
@@ -821,7 +1028,6 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer,
 		if (IS_ERR(f)) {
 			pr_notice("register: failed to install interpreter file %s\n",
 				 e->interpreter);
-			kfree(e);
 			return PTR_ERR(f);
 		}
 		e->interp_file = f;
@@ -833,9 +1039,13 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer,
 			exe_file_allow_write_access(f);
 			filp_close(f, NULL);
 		}
-		kfree(e);
+		if (e->bpf_ops)
+			binfmt_misc_put_ops(e->bpf_ops);
 		return err;
 	}
+
+	/* The entry is owned by its inode now. */
+	retain_and_null_ptr(e);
 	return count;
 }
 
@@ -850,10 +1060,10 @@ static ssize_t
 bm_status_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 {
 	struct binfmt_misc *misc;
-	char *s;
+	const char *s;
 
 	misc = i_binfmt_misc(file_inode(file));
-	s = misc->enabled ? "enabled\n" : "disabled\n";
+	s = READ_ONCE(misc->enabled) ? "enabled\n" : "disabled\n";
 	return simple_read_from_buffer(buf, nbytes, ppos, s, strlen(s));
 }
 
@@ -862,37 +1072,17 @@ static ssize_t bm_status_write(struct file *file, const char __user *buffer,
 {
 	struct binfmt_misc *misc;
 	int res = parse_command(buffer, count);
-	Node *e, *next;
-	struct inode *inode;
 
 	misc = i_binfmt_misc(file_inode(file));
 	switch (res) {
-	case 1:
-		/* Disable all handlers. */
-		misc->enabled = false;
+	case BM_CMD_DISABLE:
+		WRITE_ONCE(misc->enabled, false);
 		break;
-	case 2:
-		/* Enable all handlers. */
-		misc->enabled = true;
+	case BM_CMD_ENABLE:
+		WRITE_ONCE(misc->enabled, true);
 		break;
-	case 3:
-		/* Delete all handlers. */
-		inode = d_inode(file_inode(file)->i_sb->s_root);
-		inode_lock_nested(inode, I_MUTEX_PARENT);
-
-		/*
-		 * In order to add new element or remove elements from the list
-		 * via bm_{entry,register,status}_write() inode_lock() on the
-		 * root inode must be held.
-		 * The lock is exclusive ensuring that the list can't be
-		 * modified. Only load_misc_binary() can access but does so
-		 * read-only. So we only need to take the write lock when we
-		 * actually remove the entry from the list.
-		 */
-		list_for_each_entry_safe(e, next, &misc->entries, list)
-			remove_binfmt_handler(misc, e);
-
-		inode_unlock(inode);
+	case BM_CMD_REMOVE:
+		bm_remove_all_entries(misc, file_inode(file)->i_sb);
 		break;
 	default:
 		return res;
@@ -917,7 +1107,7 @@ static void bm_put_super(struct super_block *sb)
 	put_user_ns(user_ns);
 }
 
-static const struct super_operations s_ops = {
+static const struct super_operations bm_super_ops = {
 	.statfs		= simple_statfs,
 	.evict_inode	= bm_evict_inode,
 	.put_super	= bm_put_super,
@@ -964,10 +1154,10 @@ static int bm_fill_super(struct super_block *sb, struct fs_context *fc)
 		if (!misc)
 			return -ENOMEM;
 
-		INIT_LIST_HEAD(&misc->entries);
-		rwlock_init(&misc->entries_lock);
+		INIT_HLIST_HEAD(&misc->entries);
+		spin_lock_init(&misc->entries_lock);
 
-		/* Pairs with smp_load_acquire() in load_binfmt_misc(). */
+		/* Pairs with smp_load_acquire() in current_binfmt_misc(). */
 		smp_store_release(&user_ns->binfmt_misc, misc);
 	}
 
@@ -982,12 +1172,15 @@ static int bm_fill_super(struct super_block *sb, struct fs_context *fc)
 	 * someone mounts binfmt_misc for the first time or again we simply
 	 * reset ->enabled to true.
 	 */
-	misc->enabled = true;
+	WRITE_ONCE(misc->enabled, true);
 
 	err = simple_fill_super(sb, BINFMTFS_MAGIC, bm_files);
-	if (!err)
-		sb->s_op = &s_ops;
-	return err;
+	if (err)
+		return err;
+
+	sb->s_op = &bm_super_ops;
+	d_inode(sb->s_root)->i_op = &bm_dir_inode_operations;
+	return 0;
 }
 
 static void bm_free(struct fs_context *fc)
@@ -1038,6 +1231,8 @@ static void __exit exit_misc_binfmt(void)
 {
 	unregister_binfmt(&misc_format);
 	unregister_filesystem(&bm_fs_type);
+	/* Flush pending bm_entry_free_rcu() callbacks before the text goes. */
+	srcu_barrier(&bm_entries_srcu);
 }
 
 core_initcall(init_misc_binfmt);
diff --git a/fs/binfmt_misc_bpf.c b/fs/binfmt_misc_bpf.c
new file mode 100644
index 000000000000..65a3b8313fbe
--- /dev/null
+++ b/fs/binfmt_misc_bpf.c
@@ -0,0 +1,354 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * BPF-backed binary type handlers for binfmt_misc.
+ *
+ * A handler is a struct binfmt_misc_ops struct_ops map. Loading and
+ * registering it makes the handler available under its name in the user
+ * namespace it was registered in. A binfmt_misc 'B' entry activates it:
+ *
+ *   echo ':entry:B::::<handler-name>:' > <binfmt_misc>/register
+ */
+
+#include <linux/binfmt_misc.h>
+#include <linux/binfmts.h>
+#include <linux/bpf.h>
+#include <linux/bpf_verifier.h>
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
+#include <linux/cred.h>
+#include <linux/init.h>
+#include <linux/limits.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/user_namespace.h>
+
+struct bm_bpf_ops_reg {
+	struct list_head list;
+	const struct binfmt_misc_ops *ops;
+	struct bpf_link *link;
+	struct user_namespace *user_ns;
+};
+
+static DEFINE_SPINLOCK(bm_bpf_ops_lock);
+static LIST_HEAD(bm_bpf_ops_list);
+
+static struct bpf_struct_ops bpf_binfmt_misc_ops;
+
+static struct bm_bpf_ops_reg *bm_bpf_ops_find(const struct user_namespace *user_ns,
+					      const char *name)
+{
+	struct bm_bpf_ops_reg *reg;
+
+	lockdep_assert_held(&bm_bpf_ops_lock);
+
+	list_for_each_entry(reg, &bm_bpf_ops_list, list) {
+		if (reg->user_ns == user_ns && !strcmp(reg->ops->name, name))
+			return reg;
+	}
+	return NULL;
+}
+
+/**
+ * binfmt_misc_get_ops - look up a bpf binary type handler by name
+ * @user_ns: user namespace of the binfmt_misc instance
+ * @name: name the handler was registered under
+ *
+ * Search @user_ns and its ancestors for a handler named @name, mirroring
+ * the instance lookup in current_binfmt_misc(). The returned handler stays
+ * callable until binfmt_misc_put_ops() even if the backing struct_ops map
+ * is detached or deleted in the meantime.
+ *
+ * Return: the handler on success, NULL on failure
+ */
+const struct binfmt_misc_ops *binfmt_misc_get_ops(struct user_namespace *user_ns,
+						  const char *name)
+{
+	const struct user_namespace *ns;
+	struct bm_bpf_ops_reg *reg;
+
+	guard(spinlock)(&bm_bpf_ops_lock);
+
+	for (ns = user_ns; ns; ns = ns->parent) {
+		reg = bm_bpf_ops_find(ns, name);
+		if (!reg)
+			continue;
+		if (!bpf_struct_ops_get(reg->ops))
+			return NULL;
+		return reg->ops;
+	}
+	return NULL;
+}
+
+void binfmt_misc_put_ops(const struct binfmt_misc_ops *ops)
+{
+	bpf_struct_ops_put(ops);
+}
+
+bool bpf_prog_is_binfmt_misc_ops(const struct bpf_prog *prog)
+{
+	return prog->type == BPF_PROG_TYPE_STRUCT_OPS &&
+	       prog->aux->st_ops == &bpf_binfmt_misc_ops;
+}
+
+__bpf_kfunc_start_defs();
+
+/**
+ * bpf_binprm_set_interp - select the interpreter for the current exec
+ * @bprm: binary that is being executed
+ * @path: absolute path to the interpreter
+ * @path__sz: size of the @path buffer, including the terminating NUL
+ *
+ * To be called from the load program of a struct binfmt_misc_ops handler
+ * before returning zero; the verifier rejects the call from any other
+ * program, including the handler's own match program. The path is opened
+ * with the credentials of the task doing the exec after the program
+ * returns.
+ *
+ * Return: 0 on success, a negative errno on failure
+ */
+__bpf_kfunc int bpf_binprm_set_interp(struct linux_binprm *bprm,
+				      const char *path, size_t path__sz)
+{
+	size_t len;
+	char *interp;
+
+	if (!path__sz)
+		return -EINVAL;
+	len = strnlen(path, path__sz);
+	if (len == path__sz)
+		return -EINVAL;
+	if (path[0] != '/')
+		return -EINVAL;
+	if (len >= PATH_MAX)
+		return -ENAMETOOLONG;
+
+	interp = kmemdup_nul(path, len, GFP_KERNEL);
+	if (!interp)
+		return -ENOMEM;
+
+	kfree(bprm->bpf_interp);
+	bprm->bpf_interp = interp;
+	return 0;
+}
+
+/**
+ * bpf_binprm_set_interp_arg - set a single argument for the interpreter
+ * @bprm: binary that is being executed
+ * @arg: argument to pass to the interpreter
+ * @arg__sz: size of the @arg buffer, including the terminating NUL
+ *
+ * To be called from the load program of a struct binfmt_misc_ops handler. The
+ * argument is passed to the interpreter ahead of the binary, mirroring the
+ * single optional argument of a #! interpreter line. Calling it again
+ * replaces the argument.
+ *
+ * Return: 0 on success, a negative errno on failure
+ */
+__bpf_kfunc int bpf_binprm_set_interp_arg(struct linux_binprm *bprm,
+					  const char *arg, size_t arg__sz)
+{
+	size_t len;
+	char *val;
+
+	if (!arg__sz)
+		return -EINVAL;
+	len = strnlen(arg, arg__sz);
+	if (len == arg__sz)
+		return -EINVAL;
+	if (!len)
+		return -EINVAL;
+
+	val = kmemdup_nul(arg, len, GFP_KERNEL);
+	if (!val)
+		return -ENOMEM;
+
+	kfree(bprm->bpf_interp_arg);
+	bprm->bpf_interp_arg = val;
+	return 0;
+}
+
+/**
+ * bpf_binprm_set_flags - choose the interpreter invocation flags for this exec
+ * @bprm: binary that is being executed
+ * @flags: an OR of enum bpf_binprm_flags values
+ *
+ * To be called from the load program of a struct binfmt_misc_ops handler. It
+ * decides per exec what a static entry fixes at registration with the P, C and
+ * O flags: BPF_BINPRM_PRESERVE_ARGV0 keeps the caller's argv[0],
+ * BPF_BINPRM_CREDENTIALS computes credentials from the binary, and
+ * BPF_BINPRM_EXECFD hands the binary to the interpreter through AT_EXECFD.
+ * Calling it again replaces the flags, passing zero clears them again.
+ *
+ * Return: 0 on success, -EINVAL if @flags contains an unknown bit
+ */
+__bpf_kfunc int bpf_binprm_set_flags(struct linux_binprm *bprm,
+				     enum bpf_binprm_flags flags)
+{
+	if (flags & ~(BPF_BINPRM_PRESERVE_ARGV0 | BPF_BINPRM_CREDENTIALS |
+		      BPF_BINPRM_EXECFD))
+		return -EINVAL;
+
+	bprm->bpf_flags = flags;
+	return 0;
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(bm_bpf_kfunc_ids)
+BTF_ID_FLAGS(func, bpf_binprm_set_interp, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_binprm_set_interp_arg, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_binprm_set_flags, KF_SLEEPABLE)
+BTF_KFUNCS_END(bm_bpf_kfunc_ids)
+
+static int bm_bpf_kfunc_filter(const struct bpf_prog *prog, u32 kfunc_id)
+{
+	if (!btf_id_set8_contains(&bm_bpf_kfunc_ids, kfunc_id))
+		return 0;
+	if (prog->type != BPF_PROG_TYPE_STRUCT_OPS)
+		return -EACCES;
+	/* ->st_ops is unset during the cfg pass; enforced once it is set. */
+	if (!prog->aux->st_ops)
+		return 0;
+	/* Only the load program decides how a binary is run. */
+	if (bpf_prog_is_binfmt_misc_ops(prog) &&
+	    prog->aux->attach_st_ops_member_off == offsetof(struct binfmt_misc_ops, load))
+		return 0;
+	return -EACCES;
+}
+
+static const struct btf_kfunc_id_set bm_bpf_kfunc_set = {
+	.owner	= THIS_MODULE,
+	.set	= &bm_bpf_kfunc_ids,
+	.filter	= bm_bpf_kfunc_filter,
+};
+
+static bool bm_bpf_ops__match(struct linux_binprm *bprm)
+{
+	return false;
+}
+
+static int bm_bpf_ops__load(struct linux_binprm *bprm)
+{
+	return 0;
+}
+
+static struct binfmt_misc_ops bm_bpf_ops_stubs = {
+	.match = bm_bpf_ops__match,
+	.load = bm_bpf_ops__load,
+};
+
+static int bm_bpf_init(struct btf *btf)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
+					 &bm_bpf_kfunc_set);
+}
+
+static int bm_bpf_check_member(const struct btf_type *t,
+			       const struct btf_member *member,
+			       const struct bpf_prog *prog)
+{
+	u32 moff = __btf_member_bit_offset(t, member) / 8;
+
+	switch (moff) {
+	case offsetof(struct binfmt_misc_ops, match):
+	case offsetof(struct binfmt_misc_ops, load):
+		/* Reliable file reads at exec time require sleeping. */
+		if (!prog->sleepable)
+			return -EINVAL;
+		break;
+	}
+	return 0;
+}
+
+static int bm_bpf_init_member(const struct btf_type *t,
+			      const struct btf_member *member,
+			      void *kdata, const void *udata)
+{
+	const struct binfmt_misc_ops *uops = udata;
+	struct binfmt_misc_ops *ops = kdata;
+	u32 moff = __btf_member_bit_offset(t, member) / 8;
+
+	switch (moff) {
+	case offsetof(struct binfmt_misc_ops, name):
+		if (bpf_obj_name_cpy(ops->name, uops->name,
+				     sizeof(ops->name)) <= 0)
+			return -EINVAL;
+		return 1;
+	}
+	return 0;
+}
+
+static int bm_bpf_validate(void *kdata)
+{
+	struct binfmt_misc_ops *ops = kdata;
+
+	if (!ops->match || !ops->load)
+		return -EINVAL;
+	return 0;
+}
+
+static int bm_bpf_reg(void *kdata, struct bpf_link *link)
+{
+	struct binfmt_misc_ops *ops = kdata;
+	struct bm_bpf_ops_reg *reg;
+
+	reg = kzalloc_obj(*reg, GFP_KERNEL_ACCOUNT);
+	if (!reg)
+		return -ENOMEM;
+
+	reg->ops = ops;
+	reg->link = link;
+	reg->user_ns = get_user_ns(current_user_ns());
+
+	guard(spinlock)(&bm_bpf_ops_lock);
+
+	if (bm_bpf_ops_find(reg->user_ns, ops->name)) {
+		put_user_ns(reg->user_ns);
+		kfree(reg);
+		return -EEXIST;
+	}
+
+	list_add(&reg->list, &bm_bpf_ops_list);
+	return 0;
+}
+
+static void bm_bpf_unreg(void *kdata, struct bpf_link *link)
+{
+	struct bm_bpf_ops_reg *reg;
+
+	guard(spinlock)(&bm_bpf_ops_lock);
+
+	list_for_each_entry(reg, &bm_bpf_ops_list, list) {
+		if (reg->ops == kdata && reg->link == link) {
+			list_del(&reg->list);
+			put_user_ns(reg->user_ns);
+			kfree(reg);
+			return;
+		}
+	}
+}
+
+static const struct bpf_verifier_ops bm_bpf_verifier_ops = {
+	.get_func_proto		= bpf_base_func_proto,
+	.is_valid_access	= bpf_tracing_btf_ctx_access,
+};
+
+static struct bpf_struct_ops bpf_binfmt_misc_ops = {
+	.verifier_ops	= &bm_bpf_verifier_ops,
+	.init		= bm_bpf_init,
+	.check_member	= bm_bpf_check_member,
+	.init_member	= bm_bpf_init_member,
+	.validate	= bm_bpf_validate,
+	.reg		= bm_bpf_reg,
+	.unreg		= bm_bpf_unreg,
+	.cfi_stubs	= &bm_bpf_ops_stubs,
+	.name		= "binfmt_misc_ops",
+	.owner		= THIS_MODULE,
+};
+
+static int __init bm_bpf_struct_ops_init(void)
+{
+	return register_bpf_struct_ops(&bpf_binfmt_misc_ops, binfmt_misc_ops);
+}
+late_initcall(bm_bpf_struct_ops_init);
diff --git a/fs/bpf_fs_kfuncs.c b/fs/bpf_fs_kfuncs.c
index f1863a891db6..6cb877267978 100644
--- a/fs/bpf_fs_kfuncs.c
+++ b/fs/bpf_fs_kfuncs.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2024 Google LLC. */
 
+#include <linux/binfmt_misc.h>
 #include <linux/bpf.h>
 #include <linux/bpf_lsm.h>
 #include <linux/btf.h>
@@ -11,6 +12,7 @@
 #include <linux/file.h>
 #include <linux/kernfs.h>
 #include <linux/mm.h>
+#include <linux/net.h>
 #include <linux/xattr.h>
 
 __bpf_kfunc_start_defs();
@@ -359,6 +361,39 @@ __bpf_kfunc int bpf_cgroup_read_xattr(struct cgroup *cgroup, const char *name__s
 }
 #endif /* CONFIG_CGROUPS */
 
+#ifdef CONFIG_NET
+/**
+ * bpf_sock_read_xattr - read xattr of a socket's inode in sockfs
+ * @sock: socket to get xattr from
+ * @name__str: name of the xattr
+ * @value_p: output buffer of the xattr value
+ *
+ * Get xattr *name__str* of *sock* and store the output in *value_p*.
+ *
+ * For security reasons, only *name__str* with prefix "user." is allowed.
+ *
+ * Return: length of the xattr value on success, a negative value on error.
+ */
+__bpf_kfunc int bpf_sock_read_xattr(struct socket *sock, const char *name__str,
+				    struct bpf_dynptr *value_p)
+{
+	struct bpf_dynptr_kern *value_ptr = (struct bpf_dynptr_kern *)value_p;
+	u32 value_len;
+	void *value;
+
+	/* Only allow reading "user.*" xattrs */
+	if (strncmp(name__str, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN))
+		return -EPERM;
+
+	value_len = __bpf_dynptr_size(value_ptr);
+	value = __bpf_dynptr_data_rw(value_ptr, value_len);
+	if (!value)
+		return -EINVAL;
+
+	return sock_read_xattr(sock, name__str, value, value_len);
+}
+#endif /* CONFIG_NET */
+
 /**
  * bpf_real_data_inode - get the real inode hosting a file's data
  * @file: file to resolve
@@ -390,12 +425,30 @@ BTF_ID_FLAGS(func, bpf_get_file_xattr, KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_set_dentry_xattr, KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_remove_dentry_xattr, KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_real_data_inode, KF_SLEEPABLE | KF_RET_NULL)
+#ifdef CONFIG_NET
+BTF_ID_FLAGS(func, bpf_sock_read_xattr, KF_RCU)
+#endif
 BTF_KFUNCS_END(bpf_fs_kfunc_set_ids)
 
+/* Side-effecting kfuncs that stay exclusive to LSM programs. */
+BTF_SET_START(bpf_fs_kfunc_lsm_only_ids)
+BTF_ID(func, bpf_set_dentry_xattr)
+BTF_ID(func, bpf_remove_dentry_xattr)
+BTF_SET_END(bpf_fs_kfunc_lsm_only_ids)
+
 static int bpf_fs_kfuncs_filter(const struct bpf_prog *prog, u32 kfunc_id)
 {
-	if (!btf_id_set8_contains(&bpf_fs_kfunc_set_ids, kfunc_id) ||
-	    prog->type == BPF_PROG_TYPE_LSM)
+	if (!btf_id_set8_contains(&bpf_fs_kfunc_set_ids, kfunc_id))
+		return 0;
+	if (prog->type == BPF_PROG_TYPE_LSM)
+		return 0;
+	if (prog->type != BPF_PROG_TYPE_STRUCT_OPS)
+		return -EACCES;
+	/* ->st_ops is unset during the cfg pass; enforced once it is set. */
+	if (!prog->aux->st_ops)
+		return 0;
+	if (bpf_prog_is_binfmt_misc_ops(prog) &&
+	    !btf_id_set_contains(&bpf_fs_kfunc_lsm_only_ids, kfunc_id))
 		return 0;
 	return -EACCES;
 }
@@ -438,7 +491,13 @@ static const struct btf_kfunc_id_set bpf_fs_kfunc_set = {
 
 static int __init bpf_fs_kfuncs_init(void)
 {
-	return register_btf_kfunc_id_set(BPF_PROG_TYPE_LSM, &bpf_fs_kfunc_set);
+	int ret;
+
+	ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_LSM, &bpf_fs_kfunc_set);
+	if (ret || !IS_ENABLED(CONFIG_BINFMT_MISC_BPF))
+		return ret;
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
+					 &bpf_fs_kfunc_set);
 }
 
 late_initcall(bpf_fs_kfuncs_init);
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 318ddb790429..dc0834f920c3 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -247,8 +247,8 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 		return -EINVAL;
 	}
 
-	bdev_file = bdev_file_open_by_path(device_path, BLK_OPEN_WRITE,
-					   fs_info->sb, &fs_holder_ops);
+	/* Unfreezable for the whole replace; see btrfs_dev_replace_start(). */
+	bdev_file = btrfs_open_device_deny_freeze(device_path, fs_info->sb);
 	if (IS_ERR(bdev_file)) {
 		btrfs_err(fs_info, "target device %s is invalid!", device_path);
 		return PTR_ERR(bdev_file);
@@ -327,7 +327,8 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	return 0;
 
 error:
-	bdev_fput(bdev_file);
+	/* Undo the open-time freeze deny. */
+	btrfs_release_device_allow_freeze(bdev_file);
 	return ret;
 }
 
@@ -624,6 +625,15 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 	if (ret)
 		return ret;
 
+	/* Deny the source before mark, so every 'leave' unwinds both denied. */
+	if (src_device->bdev) {
+		ret = bdev_deny_freeze(src_device->bdev);
+		if (ret) {
+			btrfs_destroy_dev_replace_tgtdev(tgt_device, true);
+			return ret;
+		}
+	}
+
 	ret = mark_block_group_to_copy(fs_info, src_device);
 	if (ret)
 		return ret;
@@ -708,7 +718,9 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 	return ret;
 
 leave:
-	btrfs_destroy_dev_replace_tgtdev(tgt_device);
+	if (src_device->bdev)
+		bdev_allow_freeze(src_device->bdev);
+	btrfs_destroy_dev_replace_tgtdev(tgt_device, true);
 	return ret;
 }
 
@@ -889,6 +901,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	 */
 	ret = btrfs_start_delalloc_roots(fs_info, LONG_MAX, false);
 	if (ret) {
+		/* Stays started/resumable; keep both denied. */
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 		return ret;
 	}
@@ -902,6 +915,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	while (1) {
 		trans = btrfs_start_transaction(root, 0);
 		if (IS_ERR(trans)) {
+			/* Stays started/resumable; keep both denied. */
 			mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 			return PTR_ERR(trans);
 		}
@@ -954,7 +968,10 @@ error:
 		mutex_unlock(&fs_devices->device_list_mutex);
 		btrfs_rm_dev_replace_blocked(fs_info);
 		if (tgt_device)
-			btrfs_destroy_dev_replace_tgtdev(tgt_device);
+			btrfs_destroy_dev_replace_tgtdev(tgt_device, true);
+		/* The source stays a member; re-allow freezing it. */
+		if (src_device->bdev)
+			bdev_allow_freeze(src_device->bdev);
 		btrfs_rm_dev_replace_unblocked(fs_info);
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 
@@ -1027,6 +1044,8 @@ error:
 
 	mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 
+	/* The target is now a member; the source is freed (allow + release). */
+	bdev_allow_freeze(tgt_device->bdev);
 	btrfs_rm_dev_replace_free_srcdev(src_device);
 
 	return 0;
@@ -1155,8 +1174,9 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info)
 			btrfs_dev_name(src_device), src_device->devid,
 			btrfs_dev_name(tgt_device));
 
+		/* A suspended replace never re-denied freezing; do not allow. */
 		if (tgt_device)
-			btrfs_destroy_dev_replace_tgtdev(tgt_device);
+			btrfs_destroy_dev_replace_tgtdev(tgt_device, false);
 		break;
 	default:
 		up_write(&dev_replace->rwsem);
@@ -1186,6 +1206,11 @@ void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info)
 		dev_replace->time_stopped = ktime_get_real_seconds();
 		dev_replace->item_needs_writeback = 1;
 		btrfs_info(fs_info, "suspending dev_replace for unmount");
+		/* Reopened freezable next mount; resume re-denies. */
+		if (dev_replace->srcdev && dev_replace->srcdev->bdev)
+			bdev_allow_freeze(dev_replace->srcdev->bdev);
+		if (dev_replace->tgtdev && dev_replace->tgtdev->bdev)
+			bdev_allow_freeze(dev_replace->tgtdev->bdev);
 		break;
 	}
 
@@ -1198,6 +1223,7 @@ int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info)
 {
 	struct task_struct *task;
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
+	int ret = 0;
 
 	down_write(&dev_replace->rwsem);
 
@@ -1241,8 +1267,33 @@ int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info)
 		return 0;
 	}
 
+	/* Re-deny for the resumed replace; stay suspended if frozen now. */
+	if (dev_replace->srcdev->bdev &&
+	    bdev_deny_freeze(dev_replace->srcdev->bdev))
+		goto suspend;
+	if (bdev_deny_freeze(dev_replace->tgtdev->bdev)) {
+		if (dev_replace->srcdev->bdev)
+			bdev_allow_freeze(dev_replace->srcdev->bdev);
+		goto suspend;
+	}
+
 	task = kthread_run(btrfs_dev_replace_kthread, fs_info, "btrfs-devrepl");
-	return PTR_ERR_OR_ZERO(task);
+	if (IS_ERR(task)) {
+		bdev_allow_freeze(dev_replace->tgtdev->bdev);
+		if (dev_replace->srcdev->bdev)
+			bdev_allow_freeze(dev_replace->srcdev->bdev);
+		/* Undo the deny and suspend, but still fail the mount. */
+		ret = PTR_ERR(task);
+		goto suspend;
+	}
+	return 0;
+
+suspend:
+	btrfs_exclop_finish(fs_info);
+	down_write(&dev_replace->rwsem);
+	dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED;
+	up_write(&dev_replace->rwsem);
+	return ret;
 }
 
 static int btrfs_dev_replace_kthread(void *data)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 636196705fa3..0fcbfc393946 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6843,7 +6843,7 @@ static int btrfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 }
 
 static int btrfs_create(struct mnt_idmap *idmap, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool excl)
+			struct dentry *dentry, umode_t mode)
 {
 	struct inode *inode;
 
@@ -6947,7 +6947,7 @@ static struct dentry *btrfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	inode = new_inode(dir->i_sb);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
-	inode_init_owner(idmap, inode, dir, S_IFDIR | mode);
+	inode_init_owner(idmap, inode, dir, mode);
 	inode->i_op = &btrfs_dir_inode_operations;
 	inode->i_fop = &btrfs_dir_file_operations;
 	return ERR_PTR(btrfs_create_common(dir, dentry, inode));
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 5cb927c6e53d..07ce84070efd 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2627,7 +2627,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 err_drop:
 	mnt_drop_write_file(file);
 	if (bdev_file)
-		bdev_fput(bdev_file);
+		btrfs_release_device_allow_freeze(bdev_file);
 out:
 	btrfs_put_dev_args_from_path(&args);
 	return ret;
@@ -2677,7 +2677,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 
 	mnt_drop_write_file(file);
 	if (bdev_file)
-		bdev_fput(bdev_file);
+		btrfs_release_device_allow_freeze(bdev_file);
 out:
 	btrfs_put_dev_args_from_path(&args);
 	return ret;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index a8e27db8e4bc..9b66eb584ece 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -12,6 +12,7 @@
 #include <linux/uuid.h>
 #include <linux/list_sort.h>
 #include <linux/namei.h>
+#include <linux/fs_struct.h>
 #include "misc.h"
 #include "disk-io.h"
 #include "extent-tree.h"
@@ -480,7 +481,12 @@ btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder,
 	struct block_device *bdev;
 	int ret;
 
-	*bdev_file = bdev_file_open_by_path(device_path, flags, holder, &fs_holder_ops);
+	if (holder)
+		*bdev_file = fs_bdev_file_open_by_path(device_path, flags,
+						       holder, holder);
+	else
+		*bdev_file = bdev_file_open_by_path(device_path, flags, NULL,
+						    NULL);
 
 	if (IS_ERR(*bdev_file)) {
 		ret = PTR_ERR(*bdev_file);
@@ -495,7 +501,7 @@ btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder,
 	if (holder) {
 		ret = set_blocksize(*bdev_file, BTRFS_BDEV_BLOCKSIZE);
 		if (ret) {
-			bdev_fput(*bdev_file);
+			fs_bdev_file_release(*bdev_file, holder);
 			goto error;
 		}
 	}
@@ -503,7 +509,10 @@ btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder,
 	*disk_super = btrfs_read_disk_super(bdev, 0, false);
 	if (IS_ERR(*disk_super)) {
 		ret = PTR_ERR(*disk_super);
-		bdev_fput(*bdev_file);
+		if (holder)
+			fs_bdev_file_release(*bdev_file, holder);
+		else
+			bdev_fput(*bdev_file);
 		goto error;
 	}
 
@@ -727,7 +736,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 
 error_free_page:
 	btrfs_release_disk_super(disk_super);
-	bdev_fput(bdev_file);
+	fs_bdev_file_release(bdev_file, holder);
 
 	return -EINVAL;
 }
@@ -1052,7 +1061,7 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices,
 			continue;
 
 		if (device->bdev_file) {
-			bdev_fput(device->bdev_file);
+			fs_bdev_file_release(device->bdev_file, device->bdev_file->private_data);
 			device->bdev = NULL;
 			device->bdev_file = NULL;
 			fs_devices->open_devices--;
@@ -1089,7 +1098,18 @@ void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices)
 	mutex_unlock(&uuid_mutex);
 }
 
-static void btrfs_close_bdev(struct btrfs_device *device)
+/* Release a device that was made unfreezable for a membership change. */
+void btrfs_release_device_allow_freeze(struct file *bdev_file)
+{
+	struct super_block *sb = bdev_file->private_data;
+
+	/* Unregister before re-allowing (strand-safe); file still open (UAF-safe). */
+	fs_bdev_unregister(bdev_file, sb);
+	bdev_allow_freeze(file_bdev(bdev_file));
+	bdev_fput(bdev_file);
+}
+
+static void btrfs_close_bdev(struct btrfs_device *device, bool allow_freeze)
 {
 	if (!device->bdev)
 		return;
@@ -1099,7 +1119,12 @@ static void btrfs_close_bdev(struct btrfs_device *device)
 		invalidate_bdev(device->bdev);
 	}
 
-	bdev_fput(device->bdev_file);
+	/* @allow_freeze undoes a replace-time deny; unmount-close was never denied. */
+	if (allow_freeze)
+		btrfs_release_device_allow_freeze(device->bdev_file);
+	else
+		fs_bdev_file_release(device->bdev_file,
+				     device->bdev_file->private_data);
 }
 
 static void btrfs_close_one_device(struct btrfs_device *device)
@@ -1120,7 +1145,7 @@ static void btrfs_close_one_device(struct btrfs_device *device)
 		fs_devices->missing_devices--;
 	}
 
-	btrfs_close_bdev(device);
+	btrfs_close_bdev(device, false);
 	if (device->bdev) {
 		fs_devices->open_devices--;
 		device->bdev = NULL;
@@ -2090,8 +2115,16 @@ static int btrfs_add_dev_item(struct btrfs_trans_handle *trans,
 static void update_dev_time(const char *device_path)
 {
 	struct path path;
+	int err;
+
+	if (tsk_is_kthread(current)) {
+		scoped_with_init_fs()
+			err = kern_path(device_path, LOOKUP_FOLLOW, &path);
+	} else {
+		err = kern_path(device_path, LOOKUP_FOLLOW, &path);
+	}
 
-	if (!kern_path(device_path, LOOKUP_FOLLOW, &path)) {
+	if (!err) {
 		vfs_utimes(&path, NULL);
 		path_put(&path);
 	}
@@ -2338,6 +2371,13 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 	    fs_info->fs_devices->rw_devices == 1)
 		return BTRFS_ERROR_DEV_ONLY_WRITABLE;
 
+	/* Removal and freezing are mutually exclusive; refuse if frozen now. */
+	if (device->bdev) {
+		ret = bdev_deny_freeze(device->bdev);
+		if (ret)
+			return ret;
+	}
+
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
 		mutex_lock(&fs_info->chunk_mutex);
 		list_del_init(&device->dev_alloc_list);
@@ -2364,6 +2404,8 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 			   device->devid, ret);
 		btrfs_abort_transaction(trans, ret);
 		btrfs_end_transaction(trans);
+		if (device->bdev)
+			bdev_allow_freeze(device->bdev);
 		return ret;
 	}
 
@@ -2455,6 +2497,8 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 	return btrfs_commit_transaction(trans);
 
 error_undo:
+	if (device->bdev)
+		bdev_allow_freeze(device->bdev);
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
 		mutex_lock(&fs_info->chunk_mutex);
 		list_add(&device->dev_alloc_list,
@@ -2499,7 +2543,8 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_device *srcdev)
 
 	mutex_lock(&uuid_mutex);
 
-	btrfs_close_bdev(srcdev);
+	/* The source was made unfreezable for the replace; undo it. */
+	btrfs_close_bdev(srcdev, true);
 	synchronize_rcu();
 	btrfs_free_device(srcdev);
 
@@ -2520,7 +2565,8 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_device *srcdev)
 	mutex_unlock(&uuid_mutex);
 }
 
-void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev)
+void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev,
+				      bool allow_freeze)
 {
 	struct btrfs_fs_devices *fs_devices = tgtdev->fs_info->fs_devices;
 
@@ -2541,7 +2587,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev)
 
 	btrfs_scratch_superblocks(tgtdev->fs_info, tgtdev);
 
-	btrfs_close_bdev(tgtdev);
+	btrfs_close_bdev(tgtdev, allow_freeze);
 	synchronize_rcu();
 	btrfs_free_device(tgtdev);
 }
@@ -2810,6 +2856,37 @@ next_slot:
 	return 0;
 }
 
+/*
+ * Open @path for @sb with freezing denied before the holder claim is published,
+ * so a racing bdev_freeze() can never reach a claim a device add or replace may
+ * still abort.  The deny is taken on a throwaway non-holder probe open, then the
+ * holder is opened by the probe's dev_t.  Balanced by the caller.
+ */
+struct file *btrfs_open_device_deny_freeze(const char *path,
+					   struct super_block *sb)
+{
+	struct file *probe_file, *bdev_file;
+	int ret;
+
+	/* WRITE so bdev_file_open_by_path() rejects a read-only device. */
+	probe_file = bdev_file_open_by_path(path, BLK_OPEN_WRITE, NULL, NULL);
+	if (IS_ERR(probe_file))
+		return probe_file;
+
+	ret = bdev_deny_freeze(file_bdev(probe_file));
+	if (ret) {
+		bdev_fput(probe_file);
+		return ERR_PTR(ret);
+	}
+
+	bdev_file = fs_bdev_file_open_by_dev(file_bdev(probe_file)->bd_dev,
+					     BLK_OPEN_WRITE, sb, sb);
+	if (IS_ERR(bdev_file))
+		bdev_allow_freeze(file_bdev(probe_file));
+	bdev_fput(probe_file);
+	return bdev_file;
+}
+
 int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path)
 {
 	struct btrfs_root *root = fs_info->dev_root;
@@ -2828,8 +2905,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	if (sb_rdonly(sb) && !fs_devices->seeding)
 		return -EROFS;
 
-	bdev_file = bdev_file_open_by_path(device_path, BLK_OPEN_WRITE,
-					   fs_info->sb, &fs_holder_ops);
+	/* Forbid freezing until the device is a committed member (or unwound). */
+	bdev_file = btrfs_open_device_deny_freeze(device_path, fs_info->sb);
 	if (IS_ERR(bdev_file))
 		return PTR_ERR(bdev_file);
 
@@ -3000,8 +3077,10 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		up_write(&sb->s_umount);
 		locked = false;
 
-		if (ret) /* transaction commit */
+		if (ret) { /* transaction commit */
+			bdev_allow_freeze(file_bdev(bdev_file));
 			return ret;
+		}
 
 		ret = btrfs_relocate_sys_chunks(fs_info);
 		if (ret < 0)
@@ -3009,8 +3088,10 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 				    "Failed to relocate sys chunks after device initialization. This can be fixed using the \"btrfs balance\" command.");
 		trans = btrfs_attach_transaction(root);
 		if (IS_ERR(trans)) {
-			if (PTR_ERR(trans) == -ENOENT)
+			if (PTR_ERR(trans) == -ENOENT) {
+				bdev_allow_freeze(file_bdev(bdev_file));
 				return 0;
+			}
 			ret = PTR_ERR(trans);
 			trans = NULL;
 			goto error_sysfs;
@@ -3030,6 +3111,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	/* Update ctime/mtime for blkid or udev */
 	update_dev_time(device_path);
 
+	bdev_allow_freeze(file_bdev(bdev_file));
 	return ret;
 
 error_sysfs:
@@ -3059,7 +3141,7 @@ error_free_zone:
 error_free_device:
 	btrfs_free_device(device);
 error:
-	bdev_fput(bdev_file);
+	btrfs_release_device_allow_freeze(bdev_file);
 	if (locked) {
 		mutex_unlock(&uuid_mutex);
 		up_write(&sb->s_umount);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index eaf23c0dcbf6..0415d74cad9b 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -750,6 +750,7 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 struct btrfs_device *btrfs_scan_one_device(const char *path, bool mount_arg_dev);
 int btrfs_forget_devices(dev_t devt);
 void btrfs_close_devices(struct btrfs_fs_devices *fs_devices);
+void btrfs_release_device_allow_freeze(struct file *bdev_file);
 void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices);
 void btrfs_assign_next_active_device(struct btrfs_device *device,
 				     struct btrfs_device *this_dev);
@@ -774,6 +775,8 @@ struct btrfs_device *btrfs_find_device(const struct btrfs_fs_devices *fs_devices
 				       const struct btrfs_dev_lookup_args *args);
 int btrfs_shrink_device(struct btrfs_device *device, u64 new_size);
 int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *path);
+struct file *btrfs_open_device_deny_freeze(const char *path,
+					   struct super_block *sb);
 int btrfs_balance(struct btrfs_fs_info *fs_info,
 		  struct btrfs_balance_control *bctl,
 		  struct btrfs_ioctl_balance_args *bargs);
@@ -794,7 +797,8 @@ int btrfs_init_writeback_bio_size(struct btrfs_fs_info *fs_info);
 int btrfs_run_dev_stats(struct btrfs_trans_handle *trans);
 void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev);
 void btrfs_rm_dev_replace_free_srcdev(struct btrfs_device *srcdev);
-void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev);
+void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev,
+				      bool allow_freeze);
 unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
 				    u64 logical);
 u64 btrfs_calc_stripe_length(const struct btrfs_chunk_map *map);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index ef9e92e362d3..dfa590a220ea 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -983,7 +983,7 @@ out:
 }
 
 static int ceph_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *dentry, umode_t mode, bool excl)
+		       struct dentry *dentry, umode_t mode)
 {
 	return ceph_mknod(idmap, dir, dentry, mode, 0);
 }
@@ -1147,7 +1147,6 @@ static struct dentry *ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 		goto out;
 	}
 
-	mode |= S_IFDIR;
 	req->r_new_inode = ceph_new_inode(dir, dentry, &mode, &as_ctx);
 	if (IS_ERR(req->r_new_inode)) {
 		ret = ERR_CAST(req->r_new_inode);
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 835eb7fdfdad..67148edfadee 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -134,7 +134,7 @@ static inline void coda_dir_drop_nlink(struct inode *dir)
 
 /* creation routines: create, mknod, mkdir, link, symlink */
 static int coda_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *de, umode_t mode, bool excl)
+		       struct dentry *de, umode_t mode)
 {
 	int error;
 	const char *name=de->d_name.name;
@@ -179,7 +179,12 @@ static struct dentry *coda_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	if (is_root_inode(dir) && coda_iscontrol(name, len))
 		return ERR_PTR(-EPERM);
 
-	attrs.va_mode = mode;
+	/*
+	 * vfs_mkdir() now passes S_IFDIR in @mode, but @mode is forwarded
+	 * verbatim to userspace, which has only ever been given the permission
+	 * bits. Strip the type bit until venus is known to cope with it.
+	 */
+	attrs.va_mode = mode & ~S_IFDIR;
 	error = venus_mkdir(dir->i_sb, coda_i2f(dir),
 			       name, len, &newfid, &attrs);
 	if (error)
diff --git a/fs/coredump.c b/fs/coredump.c
index e68a76ff92a3..ac3cd74808c6 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -921,15 +921,10 @@ static bool coredump_file(struct core_name *cn, struct coredump_params *cprm,
 		 * with a fully qualified path" rule is to control where
 		 * coredumps may be placed using root privileges,
 		 * current->fs->root must not be used. Instead, use the
-		 * root directory of init_task.
+		 * root directory of PID 1.
 		 */
-		struct path root;
-
-		task_lock(&init_task);
-		get_fs_root(init_task.fs, &root);
-		task_unlock(&init_task);
-		file = file_open_root(&root, cn->corename, open_flags, 0600);
-		path_put(&root);
+		scoped_with_init_fs()
+			file = filp_open(cn->corename, open_flags, 0600);
 	} else {
 		file = filp_open(cn->corename, open_flags, 0600);
 	}
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 4edbfccd0bbe..d4cd03f4f60d 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -504,7 +504,7 @@ static void cramfs_kill_sb(struct super_block *sb)
 		sb->s_mtd = NULL;
 	} else if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV) && sb->s_bdev) {
 		sync_blockdev(sb->s_bdev);
-		bdev_fput(sb->s_bdev_file);
+		fs_bdev_file_release(sb->s_bdev_file, sb);
 	}
 	kfree(sbi);
 }
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 7aaf1913f9c6..525297c7ebd8 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -268,7 +268,7 @@ out:
 static int
 ecryptfs_create(struct mnt_idmap *idmap,
 		struct inode *directory_inode, struct dentry *ecryptfs_dentry,
-		umode_t mode, bool excl)
+		umode_t mode)
 {
 	struct inode *ecryptfs_inode;
 	int rc;
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index 95dcad83da11..f0d009555fc6 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -75,7 +75,7 @@ static bool efivarfs_valid_name(const char *str, int len)
 }
 
 static int efivarfs_create(struct mnt_idmap *idmap, struct inode *dir,
-			   struct dentry *dentry, umode_t mode, bool excl)
+			   struct dentry *dentry, umode_t mode)
 {
 	struct inode *inode = NULL;
 	struct efivar_entry *var;
diff --git a/fs/efs/Kconfig b/fs/efs/Kconfig
deleted file mode 100644
index 0833e533df9d..000000000000
--- a/fs/efs/Kconfig
+++ /dev/null
@@ -1,16 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-config EFS_FS
-	tristate "EFS file system support (read only)"
-	depends on BLOCK
-	select BUFFER_HEAD
-	help
-	  EFS is an older file system used for non-ISO9660 CD-ROMs and hard
-	  disk partitions by SGI's IRIX operating system (IRIX 6.0 and newer
-	  uses the XFS file system for hard disk partitions however).
-
-	  This implementation only offers read-only access. If you don't know
-	  what all this is about, it's safe to say N. For more information
-	  about EFS see its home page at <http://aeschi.ch.eu.org/efs/>.
-
-	  To compile the EFS file system support as a module, choose M here: the
-	  module will be called efs.
diff --git a/fs/efs/Makefile b/fs/efs/Makefile
deleted file mode 100644
index 85e5b88f9471..000000000000
--- a/fs/efs/Makefile
+++ /dev/null
@@ -1,8 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Makefile for the linux efs-filesystem routines.
-#
-
-obj-$(CONFIG_EFS_FS) += efs.o
-
-efs-objs := super.o inode.o namei.o dir.o file.o symlink.o
diff --git a/fs/efs/dir.c b/fs/efs/dir.c
deleted file mode 100644
index 35ad0092c115..000000000000
--- a/fs/efs/dir.c
+++ /dev/null
@@ -1,105 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * dir.c
- *
- * Copyright (c) 1999 Al Smith
- */
-
-#include <linux/buffer_head.h>
-#include <linux/filelock.h>
-#include "efs.h"
-
-static int efs_readdir(struct file *, struct dir_context *);
-
-const struct file_operations efs_dir_operations = {
-	.llseek		= generic_file_llseek,
-	.read		= generic_read_dir,
-	.iterate_shared	= efs_readdir,
-	.setlease	= generic_setlease,
-};
-
-const struct inode_operations efs_dir_inode_operations = {
-	.lookup		= efs_lookup,
-};
-
-static int efs_readdir(struct file *file, struct dir_context *ctx)
-{
-	struct inode *inode = file_inode(file);
-	efs_block_t		block;
-	int			slot;
-
-	if (inode->i_size & (EFS_DIRBSIZE-1))
-		pr_warn("%s(): directory size not a multiple of EFS_DIRBSIZE\n",
-			__func__);
-
-	/* work out where this entry can be found */
-	block = ctx->pos >> EFS_DIRBSIZE_BITS;
-
-	/* each block contains at most 256 slots */
-	slot  = ctx->pos & 0xff;
-
-	/* look at all blocks */
-	while (block < inode->i_blocks) {
-		struct efs_dir		*dirblock;
-		struct buffer_head *bh;
-
-		/* read the dir block */
-		bh = sb_bread(inode->i_sb, efs_bmap(inode, block));
-
-		if (!bh) {
-			pr_err("%s(): failed to read dir block %d\n",
-			       __func__, block);
-			break;
-		}
-
-		dirblock = (struct efs_dir *) bh->b_data; 
-
-		if (be16_to_cpu(dirblock->magic) != EFS_DIRBLK_MAGIC) {
-			pr_err("%s(): invalid directory block\n", __func__);
-			brelse(bh);
-			break;
-		}
-
-		for (; slot < dirblock->slots; slot++) {
-			struct efs_dentry *dirslot;
-			efs_ino_t inodenum;
-			const char *nameptr;
-			int namelen;
-
-			if (dirblock->space[slot] == 0)
-				continue;
-
-			dirslot  = (struct efs_dentry *) (((char *) bh->b_data) + EFS_SLOTAT(dirblock, slot));
-
-			inodenum = be32_to_cpu(dirslot->inode);
-			namelen  = dirslot->namelen;
-			nameptr  = dirslot->name;
-			pr_debug("%s(): block %d slot %d/%d: inode %u, name \"%s\", namelen %u\n",
-				 __func__, block, slot, dirblock->slots-1,
-				 inodenum, nameptr, namelen);
-			if (!namelen)
-				continue;
-			/* found the next entry */
-			ctx->pos = (block << EFS_DIRBSIZE_BITS) | slot;
-
-			/* sanity check */
-			if (nameptr - (char *) dirblock + namelen > EFS_DIRBSIZE) {
-				pr_warn("directory entry %d exceeds directory block\n",
-					slot);
-				continue;
-			}
-
-			/* copy filename and data in dirslot */
-			if (!dir_emit(ctx, nameptr, namelen, inodenum, DT_UNKNOWN)) {
-				brelse(bh);
-				return 0;
-			}
-		}
-		brelse(bh);
-
-		slot = 0;
-		block++;
-	}
-	ctx->pos = (block << EFS_DIRBSIZE_BITS) | slot;
-	return 0;
-}
diff --git a/fs/efs/efs.h b/fs/efs/efs.h
deleted file mode 100644
index 918d2b9abb76..000000000000
--- a/fs/efs/efs.h
+++ /dev/null
@@ -1,144 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (c) 1999 Al Smith, <Al.Smith@aeschi.ch.eu.org>
- *
- * Portions derived from work (c) 1995,1996 Christian Vogelgsang.
- * Portions derived from IRIX header files (c) 1988 Silicon Graphics
- */
-#ifndef _EFS_EFS_H_
-#define _EFS_EFS_H_
-
-#ifdef pr_fmt
-#undef pr_fmt
-#endif
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/fs.h>
-#include <linux/uaccess.h>
-
-#define EFS_VERSION "1.0a"
-
-/* 1 block is 512 bytes */
-#define	EFS_BLOCKSIZE_BITS	9
-#define	EFS_BLOCKSIZE		(1 << EFS_BLOCKSIZE_BITS)
-
-typedef	int32_t		efs_block_t;
-typedef uint32_t	efs_ino_t;
-
-#define	EFS_DIRECTEXTENTS	12
-
-/*
- * layout of an extent, in memory and on disk. 8 bytes exactly.
- */
-typedef union extent_u {
-	unsigned char raw[8];
-	struct extent_s {
-		unsigned int	ex_magic:8;	/* magic # (zero) */
-		unsigned int	ex_bn:24;	/* basic block */
-		unsigned int	ex_length:8;	/* numblocks in this extent */
-		unsigned int	ex_offset:24;	/* logical offset into file */
-	} cooked;
-} efs_extent;
-
-typedef struct edevs {
-	__be16		odev;
-	__be32		ndev;
-} efs_devs;
-
-/*
- * extent based filesystem inode as it appears on disk.  The efs inode
- * is exactly 128 bytes long.
- */
-struct	efs_dinode {
-	__be16		di_mode;	/* mode and type of file */
-	__be16		di_nlink;	/* number of links to file */
-	__be16		di_uid;		/* owner's user id */
-	__be16		di_gid;		/* owner's group id */
-	__be32		di_size;	/* number of bytes in file */
-	__be32		di_atime;	/* time last accessed */
-	__be32		di_mtime;	/* time last modified */
-	__be32		di_ctime;	/* time created */
-	__be32		di_gen;		/* generation number */
-	__be16		di_numextents;	/* # of extents */
-	u_char		di_version;	/* version of inode */
-	u_char		di_spare;	/* spare - used by AFS */
-	union di_addr {
-		efs_extent	di_extents[EFS_DIRECTEXTENTS];
-		efs_devs	di_dev;	/* device for IFCHR/IFBLK */
-	} di_u;
-};
-
-/* efs inode storage in memory */
-struct efs_inode_info {
-	int		numextents;
-	int		lastextent;
-
-	efs_extent	extents[EFS_DIRECTEXTENTS];
-	struct inode	vfs_inode;
-};
-
-#include <linux/efs_fs_sb.h>
-
-#define EFS_DIRBSIZE_BITS	EFS_BLOCKSIZE_BITS
-#define EFS_DIRBSIZE		(1 << EFS_DIRBSIZE_BITS)
-
-struct efs_dentry {
-	__be32		inode;
-	unsigned char	namelen;
-	char		name[3];
-};
-
-#define EFS_DENTSIZE	(sizeof(struct efs_dentry) - 3 + 1)
-#define EFS_MAXNAMELEN  ((1 << (sizeof(char) * 8)) - 1)
-
-#define EFS_DIRBLK_HEADERSIZE	4
-#define EFS_DIRBLK_MAGIC	0xbeef	/* moo */
-
-struct efs_dir {
-	__be16	magic;
-	unsigned char	firstused;
-	unsigned char	slots;
-
-	unsigned char	space[EFS_DIRBSIZE - EFS_DIRBLK_HEADERSIZE];
-};
-
-#define EFS_MAXENTS \
-	((EFS_DIRBSIZE - EFS_DIRBLK_HEADERSIZE) / \
-	 (EFS_DENTSIZE + sizeof(char)))
-
-#define EFS_SLOTAT(dir, slot) EFS_REALOFF((dir)->space[slot])
-
-#define EFS_REALOFF(offset) ((offset << 1))
-
-
-static inline struct efs_inode_info *INODE_INFO(struct inode *inode)
-{
-	return container_of(inode, struct efs_inode_info, vfs_inode);
-}
-
-static inline struct efs_sb_info *SUPER_INFO(struct super_block *sb)
-{
-	return sb->s_fs_info;
-}
-
-struct statfs;
-struct fid;
-
-extern const struct inode_operations efs_dir_inode_operations;
-extern const struct file_operations efs_dir_operations;
-extern const struct address_space_operations efs_symlink_aops;
-
-extern struct inode *efs_iget(struct super_block *, unsigned long);
-extern efs_block_t efs_map_block(struct inode *, efs_block_t);
-extern int efs_get_block(struct inode *, sector_t, struct buffer_head *, int);
-
-extern struct dentry *efs_lookup(struct inode *, struct dentry *, unsigned int);
-extern struct dentry *efs_fh_to_dentry(struct super_block *sb, struct fid *fid,
-		int fh_len, int fh_type);
-extern struct dentry *efs_fh_to_parent(struct super_block *sb, struct fid *fid,
-		int fh_len, int fh_type);
-extern struct dentry *efs_get_parent(struct dentry *);
-extern int efs_bmap(struct inode *, int);
-
-#endif /* _EFS_EFS_H_ */
diff --git a/fs/efs/file.c b/fs/efs/file.c
deleted file mode 100644
index 9153dfe79bbc..000000000000
--- a/fs/efs/file.c
+++ /dev/null
@@ -1,42 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * file.c
- *
- * Copyright (c) 1999 Al Smith
- *
- * Portions derived from work (c) 1995,1996 Christian Vogelgsang.
- */
-
-#include <linux/buffer_head.h>
-#include "efs.h"
-
-int efs_get_block(struct inode *inode, sector_t iblock,
-		  struct buffer_head *bh_result, int create)
-{
-	int error = -EROFS;
-	long phys;
-
-	if (create)
-		return error;
-	if (iblock >= inode->i_blocks)
-		return 0;
-
-	phys = efs_map_block(inode, iblock);
-	if (phys)
-		map_bh(bh_result, inode->i_sb, phys);
-	return 0;
-}
-
-int efs_bmap(struct inode *inode, efs_block_t block) {
-
-	if (block < 0) {
-		pr_warn("%s(): block < 0\n", __func__);
-		return 0;
-	}
-
-	/* are we about to read past the end of a file ? */
-	if (!(block < inode->i_blocks))
-		return 0;
-
-	return efs_map_block(inode, block);
-}
diff --git a/fs/efs/inode.c b/fs/efs/inode.c
deleted file mode 100644
index 4b132729e638..000000000000
--- a/fs/efs/inode.c
+++ /dev/null
@@ -1,315 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * inode.c
- *
- * Copyright (c) 1999 Al Smith
- *
- * Portions derived from work (c) 1995,1996 Christian Vogelgsang,
- *              and from work (c) 1998 Mike Shaver.
- */
-
-#include <linux/buffer_head.h>
-#include <linux/module.h>
-#include <linux/fs.h>
-#include "efs.h"
-#include <linux/efs_fs_sb.h>
-
-static int efs_read_folio(struct file *file, struct folio *folio)
-{
-	return block_read_full_folio(folio, efs_get_block);
-}
-
-static sector_t _efs_bmap(struct address_space *mapping, sector_t block)
-{
-	return generic_block_bmap(mapping,block,efs_get_block);
-}
-
-static const struct address_space_operations efs_aops = {
-	.read_folio = efs_read_folio,
-	.bmap = _efs_bmap
-};
-
-static inline void extent_copy(efs_extent *src, efs_extent *dst) {
-	/*
-	 * this is slightly evil. it doesn't just copy
-	 * efs_extent from src to dst, it also mangles
-	 * the bits so that dst ends up in cpu byte-order.
-	 */
-
-	dst->cooked.ex_magic  =  (unsigned int) src->raw[0];
-	dst->cooked.ex_bn     = ((unsigned int) src->raw[1] << 16) |
-				((unsigned int) src->raw[2] <<  8) |
-				((unsigned int) src->raw[3] <<  0);
-	dst->cooked.ex_length =  (unsigned int) src->raw[4];
-	dst->cooked.ex_offset = ((unsigned int) src->raw[5] << 16) |
-				((unsigned int) src->raw[6] <<  8) |
-				((unsigned int) src->raw[7] <<  0);
-	return;
-}
-
-struct inode *efs_iget(struct super_block *super, unsigned long ino)
-{
-	int i, inode_index;
-	dev_t device;
-	u32 rdev;
-	struct buffer_head *bh;
-	struct efs_sb_info    *sb = SUPER_INFO(super);
-	struct efs_inode_info *in;
-	efs_block_t block, offset;
-	struct efs_dinode *efs_inode;
-	struct inode *inode;
-
-	inode = iget_locked(super, ino);
-	if (!inode)
-		return ERR_PTR(-ENOMEM);
-	if (!(inode_state_read_once(inode) & I_NEW))
-		return inode;
-
-	in = INODE_INFO(inode);
-
-	/*
-	** EFS layout:
-	**
-	** |   cylinder group    |   cylinder group    |   cylinder group ..etc
-	** |inodes|data          |inodes|data          |inodes|data       ..etc
-	**
-	** work out the inode block index, (considering initially that the
-	** inodes are stored as consecutive blocks). then work out the block
-	** number of that inode given the above layout, and finally the
-	** offset of the inode within that block.
-	*/
-
-	inode_index = inode->i_ino /
-		(EFS_BLOCKSIZE / sizeof(struct efs_dinode));
-
-	block = sb->fs_start + sb->first_block + 
-		(sb->group_size * (inode_index / sb->inode_blocks)) +
-		(inode_index % sb->inode_blocks);
-
-	offset = (inode->i_ino %
-			(EFS_BLOCKSIZE / sizeof(struct efs_dinode))) *
-		sizeof(struct efs_dinode);
-
-	bh = sb_bread(inode->i_sb, block);
-	if (!bh) {
-		pr_warn("%s() failed at block %d\n", __func__, block);
-		goto read_inode_error;
-	}
-
-	efs_inode = (struct efs_dinode *) (bh->b_data + offset);
-    
-	inode->i_mode  = be16_to_cpu(efs_inode->di_mode);
-	set_nlink(inode, be16_to_cpu(efs_inode->di_nlink));
-	i_uid_write(inode, (uid_t)be16_to_cpu(efs_inode->di_uid));
-	i_gid_write(inode, (gid_t)be16_to_cpu(efs_inode->di_gid));
-	inode->i_size  = be32_to_cpu(efs_inode->di_size);
-	inode_set_atime(inode, be32_to_cpu(efs_inode->di_atime), 0);
-	inode_set_mtime(inode, be32_to_cpu(efs_inode->di_mtime), 0);
-	inode_set_ctime(inode, be32_to_cpu(efs_inode->di_ctime), 0);
-
-	/* this is the number of blocks in the file */
-	if (inode->i_size == 0) {
-		inode->i_blocks = 0;
-	} else {
-		inode->i_blocks = ((inode->i_size - 1) >> EFS_BLOCKSIZE_BITS) + 1;
-	}
-
-	rdev = be16_to_cpu(efs_inode->di_u.di_dev.odev);
-	if (rdev == 0xffff) {
-		rdev = be32_to_cpu(efs_inode->di_u.di_dev.ndev);
-		if (sysv_major(rdev) > 0xfff)
-			device = 0;
-		else
-			device = MKDEV(sysv_major(rdev), sysv_minor(rdev));
-	} else
-		device = old_decode_dev(rdev);
-
-	/* get the number of extents for this object */
-	in->numextents = be16_to_cpu(efs_inode->di_numextents);
-	in->lastextent = 0;
-
-	/* copy the extents contained within the inode to memory */
-	for(i = 0; i < EFS_DIRECTEXTENTS; i++) {
-		extent_copy(&(efs_inode->di_u.di_extents[i]), &(in->extents[i]));
-		if (i < in->numextents && in->extents[i].cooked.ex_magic != 0) {
-			pr_warn("extent %d has bad magic number in inode %llu\n",
-				i, inode->i_ino);
-			brelse(bh);
-			goto read_inode_error;
-		}
-	}
-
-	brelse(bh);
-	pr_debug("efs_iget(): inode %llu, extents %d, mode %o\n",
-		 inode->i_ino, in->numextents, inode->i_mode);
-	switch (inode->i_mode & S_IFMT) {
-		case S_IFDIR: 
-			inode->i_op = &efs_dir_inode_operations; 
-			inode->i_fop = &efs_dir_operations; 
-			break;
-		case S_IFREG:
-			inode->i_fop = &generic_ro_fops;
-			inode->i_data.a_ops = &efs_aops;
-			break;
-		case S_IFLNK:
-			inode->i_op = &page_symlink_inode_operations;
-			inode_nohighmem(inode);
-			inode->i_data.a_ops = &efs_symlink_aops;
-			break;
-		case S_IFCHR:
-		case S_IFBLK:
-		case S_IFIFO:
-			init_special_inode(inode, inode->i_mode, device);
-			break;
-		default:
-			pr_warn("unsupported inode mode %o\n", inode->i_mode);
-			goto read_inode_error;
-			break;
-	}
-
-	unlock_new_inode(inode);
-	return inode;
-        
-read_inode_error:
-	pr_warn("failed to read inode %llu\n", inode->i_ino);
-	iget_failed(inode);
-	return ERR_PTR(-EIO);
-}
-
-static inline efs_block_t
-efs_extent_check(efs_extent *ptr, efs_block_t block, struct efs_sb_info *sb) {
-	efs_block_t start;
-	efs_block_t length;
-	efs_block_t offset;
-
-	/*
-	 * given an extent and a logical block within a file,
-	 * can this block be found within this extent ?
-	 */
-	start  = ptr->cooked.ex_bn;
-	length = ptr->cooked.ex_length;
-	offset = ptr->cooked.ex_offset;
-
-	if ((block >= offset) && (block < offset+length)) {
-		return(sb->fs_start + start + block - offset);
-	} else {
-		return 0;
-	}
-}
-
-efs_block_t efs_map_block(struct inode *inode, efs_block_t block) {
-	struct efs_sb_info    *sb = SUPER_INFO(inode->i_sb);
-	struct efs_inode_info *in = INODE_INFO(inode);
-	struct buffer_head    *bh = NULL;
-
-	int cur, last, first = 1;
-	int ibase, ioffset, dirext, direxts, indext, indexts;
-	efs_block_t iblock, result = 0, lastblock = 0;
-	efs_extent ext, *exts;
-
-	last = in->lastextent;
-
-	if (in->numextents <= EFS_DIRECTEXTENTS) {
-		/* first check the last extent we returned */
-		if ((result = efs_extent_check(&in->extents[last], block, sb)))
-			return result;
-    
-		/* if we only have one extent then nothing can be found */
-		if (in->numextents == 1) {
-			pr_err("%s() failed to map (1 extent)\n", __func__);
-			return 0;
-		}
-
-		direxts = in->numextents;
-
-		/*
-		 * check the stored extents in the inode
-		 * start with next extent and check forwards
-		 */
-		for(dirext = 1; dirext < direxts; dirext++) {
-			cur = (last + dirext) % in->numextents;
-			if ((result = efs_extent_check(&in->extents[cur], block, sb))) {
-				in->lastextent = cur;
-				return result;
-			}
-		}
-
-		pr_err("%s() failed to map block %u (dir)\n", __func__, block);
-		return 0;
-	}
-
-	pr_debug("%s(): indirect search for logical block %u\n",
-		 __func__, block);
-	direxts = in->extents[0].cooked.ex_offset;
-	indexts = in->numextents;
-
-	for(indext = 0; indext < indexts; indext++) {
-		cur = (last + indext) % indexts;
-
-		/*
-		 * work out which direct extent contains `cur'.
-		 *
-		 * also compute ibase: i.e. the number of the first
-		 * indirect extent contained within direct extent `cur'.
-		 *
-		 */
-		ibase = 0;
-		for(dirext = 0; cur < ibase && dirext < direxts; dirext++) {
-			ibase += in->extents[dirext].cooked.ex_length *
-				(EFS_BLOCKSIZE / sizeof(efs_extent));
-		}
-
-		if (dirext == direxts) {
-			/* should never happen */
-			pr_err("couldn't find direct extent for indirect extent %d (block %u)\n",
-			       cur, block);
-			if (bh) brelse(bh);
-			return 0;
-		}
-		
-		/* work out block number and offset of this indirect extent */
-		iblock = sb->fs_start + in->extents[dirext].cooked.ex_bn +
-			(cur - ibase) /
-			(EFS_BLOCKSIZE / sizeof(efs_extent));
-		ioffset = (cur - ibase) %
-			(EFS_BLOCKSIZE / sizeof(efs_extent));
-
-		if (first || lastblock != iblock) {
-			if (bh) brelse(bh);
-
-			bh = sb_bread(inode->i_sb, iblock);
-			if (!bh) {
-				pr_err("%s() failed at block %d\n",
-				       __func__, iblock);
-				return 0;
-			}
-			pr_debug("%s(): read indirect extent block %d\n",
-				 __func__, iblock);
-			first = 0;
-			lastblock = iblock;
-		}
-
-		exts = (efs_extent *) bh->b_data;
-
-		extent_copy(&(exts[ioffset]), &ext);
-
-		if (ext.cooked.ex_magic != 0) {
-			pr_err("extent %d has bad magic number in block %d\n",
-			       cur, iblock);
-			if (bh) brelse(bh);
-			return 0;
-		}
-
-		if ((result = efs_extent_check(&ext, block, sb))) {
-			if (bh) brelse(bh);
-			in->lastextent = cur;
-			return result;
-		}
-	}
-	if (bh) brelse(bh);
-	pr_err("%s() failed to map block %u (indir)\n", __func__, block);
-	return 0;
-}  
-
-MODULE_DESCRIPTION("Extent File System (efs)");
-MODULE_LICENSE("GPL");
diff --git a/fs/efs/namei.c b/fs/efs/namei.c
deleted file mode 100644
index 38961ee1d1af..000000000000
--- a/fs/efs/namei.c
+++ /dev/null
@@ -1,120 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * namei.c
- *
- * Copyright (c) 1999 Al Smith
- *
- * Portions derived from work (c) 1995,1996 Christian Vogelgsang.
- */
-
-#include <linux/buffer_head.h>
-#include <linux/string.h>
-#include <linux/exportfs.h>
-#include "efs.h"
-
-
-static efs_ino_t efs_find_entry(struct inode *inode, const char *name, int len)
-{
-	struct buffer_head *bh;
-
-	int			slot, namelen;
-	char			*nameptr;
-	struct efs_dir		*dirblock;
-	struct efs_dentry	*dirslot;
-	efs_ino_t		inodenum;
-	efs_block_t		block;
- 
-	if (inode->i_size & (EFS_DIRBSIZE-1))
-		pr_warn("%s(): directory size not a multiple of EFS_DIRBSIZE\n",
-			__func__);
-
-	for(block = 0; block < inode->i_blocks; block++) {
-
-		bh = sb_bread(inode->i_sb, efs_bmap(inode, block));
-		if (!bh) {
-			pr_err("%s(): failed to read dir block %d\n",
-			       __func__, block);
-			return 0;
-		}
-    
-		dirblock = (struct efs_dir *) bh->b_data;
-
-		if (be16_to_cpu(dirblock->magic) != EFS_DIRBLK_MAGIC) {
-			pr_err("%s(): invalid directory block\n", __func__);
-			brelse(bh);
-			return 0;
-		}
-
-		for (slot = 0; slot < dirblock->slots; slot++) {
-			dirslot  = (struct efs_dentry *) (((char *) bh->b_data) + EFS_SLOTAT(dirblock, slot));
-
-			namelen  = dirslot->namelen;
-			nameptr  = dirslot->name;
-
-			if ((namelen == len) && (!memcmp(name, nameptr, len))) {
-				inodenum = be32_to_cpu(dirslot->inode);
-				brelse(bh);
-				return inodenum;
-			}
-		}
-		brelse(bh);
-	}
-	return 0;
-}
-
-struct dentry *efs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
-{
-	efs_ino_t inodenum;
-	struct inode *inode = NULL;
-
-	inodenum = efs_find_entry(dir, dentry->d_name.name, dentry->d_name.len);
-	if (inodenum)
-		inode = efs_iget(dir->i_sb, inodenum);
-
-	return d_splice_alias(inode, dentry);
-}
-
-static struct inode *efs_nfs_get_inode(struct super_block *sb, u64 ino,
-		u32 generation)
-{
-	struct inode *inode;
-
-	if (ino == 0)
-		return ERR_PTR(-ESTALE);
-	inode = efs_iget(sb, ino);
-	if (IS_ERR(inode))
-		return ERR_CAST(inode);
-
-	if (generation && inode->i_generation != generation) {
-		iput(inode);
-		return ERR_PTR(-ESTALE);
-	}
-
-	return inode;
-}
-
-struct dentry *efs_fh_to_dentry(struct super_block *sb, struct fid *fid,
-		int fh_len, int fh_type)
-{
-	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
-				    efs_nfs_get_inode);
-}
-
-struct dentry *efs_fh_to_parent(struct super_block *sb, struct fid *fid,
-		int fh_len, int fh_type)
-{
-	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
-				    efs_nfs_get_inode);
-}
-
-struct dentry *efs_get_parent(struct dentry *child)
-{
-	struct dentry *parent = ERR_PTR(-ENOENT);
-	efs_ino_t ino;
-
-	ino = efs_find_entry(d_inode(child), "..", 2);
-	if (ino)
-		parent = d_obtain_alias(efs_iget(child->d_sb, ino));
-
-	return parent;
-}
diff --git a/fs/efs/super.c b/fs/efs/super.c
deleted file mode 100644
index 11fea3bbce7c..000000000000
--- a/fs/efs/super.c
+++ /dev/null
@@ -1,368 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * super.c
- *
- * Copyright (c) 1999 Al Smith
- *
- * Portions derived from work (c) 1995,1996 Christian Vogelgsang.
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/exportfs.h>
-#include <linux/slab.h>
-#include <linux/buffer_head.h>
-#include <linux/vfs.h>
-#include <linux/blkdev.h>
-#include <linux/fs_context.h>
-#include "efs.h"
-#include <linux/efs_vh.h>
-#include <linux/efs_fs_sb.h>
-
-static int efs_statfs(struct dentry *dentry, struct kstatfs *buf);
-static int efs_init_fs_context(struct fs_context *fc);
-
-static void efs_kill_sb(struct super_block *s)
-{
-	struct efs_sb_info *sbi = SUPER_INFO(s);
-	kill_block_super(s);
-	kfree(sbi);
-}
-
-static struct pt_types sgi_pt_types[] = {
-	{0x00,		"SGI vh"},
-	{0x01,		"SGI trkrepl"},
-	{0x02,		"SGI secrepl"},
-	{0x03,		"SGI raw"},
-	{0x04,		"SGI bsd"},
-	{SGI_SYSV,	"SGI sysv"},
-	{0x06,		"SGI vol"},
-	{SGI_EFS,	"SGI efs"},
-	{0x08,		"SGI lv"},
-	{0x09,		"SGI rlv"},
-	{0x0A,		"SGI xfs"},
-	{0x0B,		"SGI xfslog"},
-	{0x0C,		"SGI xlv"},
-	{0x82,		"Linux swap"},
-	{0x83,		"Linux native"},
-	{0,		NULL}
-};
-
-/*
- * File system definition and registration.
- */
-static struct file_system_type efs_fs_type = {
-	.owner			= THIS_MODULE,
-	.name			= "efs",
-	.kill_sb		= efs_kill_sb,
-	.fs_flags		= FS_REQUIRES_DEV,
-	.init_fs_context	= efs_init_fs_context,
-};
-MODULE_ALIAS_FS("efs");
-
-static struct kmem_cache * efs_inode_cachep;
-
-static struct inode *efs_alloc_inode(struct super_block *sb)
-{
-	struct efs_inode_info *ei;
-	ei = alloc_inode_sb(sb, efs_inode_cachep, GFP_KERNEL);
-	if (!ei)
-		return NULL;
-	return &ei->vfs_inode;
-}
-
-static void efs_free_inode(struct inode *inode)
-{
-	kmem_cache_free(efs_inode_cachep, INODE_INFO(inode));
-}
-
-static void init_once(void *foo)
-{
-	struct efs_inode_info *ei = (struct efs_inode_info *) foo;
-
-	inode_init_once(&ei->vfs_inode);
-}
-
-static int __init init_inodecache(void)
-{
-	efs_inode_cachep = kmem_cache_create("efs_inode_cache",
-				sizeof(struct efs_inode_info), 0,
-				SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT,
-				init_once);
-	if (efs_inode_cachep == NULL)
-		return -ENOMEM;
-	return 0;
-}
-
-static void destroy_inodecache(void)
-{
-	/*
-	 * Make sure all delayed rcu free inodes are flushed before we
-	 * destroy cache.
-	 */
-	rcu_barrier();
-	kmem_cache_destroy(efs_inode_cachep);
-}
-
-static const struct super_operations efs_superblock_operations = {
-	.alloc_inode	= efs_alloc_inode,
-	.free_inode	= efs_free_inode,
-	.statfs		= efs_statfs,
-};
-
-static const struct export_operations efs_export_ops = {
-	.encode_fh	= generic_encode_ino32_fh,
-	.fh_to_dentry	= efs_fh_to_dentry,
-	.fh_to_parent	= efs_fh_to_parent,
-	.get_parent	= efs_get_parent,
-};
-
-static int __init init_efs_fs(void) {
-	int err;
-	pr_info(EFS_VERSION" - http://aeschi.ch.eu.org/efs/\n");
-	err = init_inodecache();
-	if (err)
-		goto out1;
-	err = register_filesystem(&efs_fs_type);
-	if (err)
-		goto out;
-	return 0;
-out:
-	destroy_inodecache();
-out1:
-	return err;
-}
-
-static void __exit exit_efs_fs(void) {
-	unregister_filesystem(&efs_fs_type);
-	destroy_inodecache();
-}
-
-module_init(init_efs_fs)
-module_exit(exit_efs_fs)
-
-static efs_block_t efs_validate_vh(struct volume_header *vh) {
-	int		i;
-	__be32		cs, *ui;
-	int		csum;
-	efs_block_t	sblock = 0; /* shuts up gcc */
-	struct pt_types	*pt_entry;
-	int		pt_type, slice = -1;
-
-	if (be32_to_cpu(vh->vh_magic) != VHMAGIC) {
-		/*
-		 * assume that we're dealing with a partition and allow
-		 * read_super() to try and detect a valid superblock
-		 * on the next block.
-		 */
-		return 0;
-	}
-
-	ui = ((__be32 *) (vh + 1)) - 1;
-	for(csum = 0; ui >= ((__be32 *) vh);) {
-		cs = *ui--;
-		csum += be32_to_cpu(cs);
-	}
-	if (csum) {
-		pr_warn("SGI disklabel: checksum bad, label corrupted\n");
-		return 0;
-	}
-
-#ifdef DEBUG
-	pr_debug("bf: \"%16s\"\n", vh->vh_bootfile);
-
-	for(i = 0; i < NVDIR; i++) {
-		int	j;
-		char	name[VDNAMESIZE+1];
-
-		for(j = 0; j < VDNAMESIZE; j++) {
-			name[j] = vh->vh_vd[i].vd_name[j];
-		}
-		name[j] = (char) 0;
-
-		if (name[0]) {
-			pr_debug("vh: %8s block: 0x%08x size: 0x%08x\n",
-				name, (int) be32_to_cpu(vh->vh_vd[i].vd_lbn),
-				(int) be32_to_cpu(vh->vh_vd[i].vd_nbytes));
-		}
-	}
-#endif
-
-	for(i = 0; i < NPARTAB; i++) {
-		pt_type = (int) be32_to_cpu(vh->vh_pt[i].pt_type);
-		for(pt_entry = sgi_pt_types; pt_entry->pt_name; pt_entry++) {
-			if (pt_type == pt_entry->pt_type) break;
-		}
-#ifdef DEBUG
-		if (be32_to_cpu(vh->vh_pt[i].pt_nblks)) {
-			pr_debug("pt %2d: start: %08d size: %08d type: 0x%02x (%s)\n",
-				 i, (int)be32_to_cpu(vh->vh_pt[i].pt_firstlbn),
-				 (int)be32_to_cpu(vh->vh_pt[i].pt_nblks),
-				 pt_type, (pt_entry->pt_name) ?
-				 pt_entry->pt_name : "unknown");
-		}
-#endif
-		if (IS_EFS(pt_type)) {
-			sblock = be32_to_cpu(vh->vh_pt[i].pt_firstlbn);
-			slice = i;
-		}
-	}
-
-	if (slice == -1) {
-		pr_notice("partition table contained no EFS partitions\n");
-#ifdef DEBUG
-	} else {
-		pr_info("using slice %d (type %s, offset 0x%x)\n", slice,
-			(pt_entry->pt_name) ? pt_entry->pt_name : "unknown",
-			sblock);
-#endif
-	}
-	return sblock;
-}
-
-static int efs_validate_super(struct efs_sb_info *sb, struct efs_super *super) {
-
-	if (!IS_EFS_MAGIC(be32_to_cpu(super->fs_magic)))
-		return -1;
-
-	sb->fs_magic     = be32_to_cpu(super->fs_magic);
-	sb->total_blocks = be32_to_cpu(super->fs_size);
-	sb->first_block  = be32_to_cpu(super->fs_firstcg);
-	sb->group_size   = be32_to_cpu(super->fs_cgfsize);
-	sb->data_free    = be32_to_cpu(super->fs_tfree);
-	sb->inode_free   = be32_to_cpu(super->fs_tinode);
-	sb->inode_blocks = be16_to_cpu(super->fs_cgisize);
-	sb->total_groups = be16_to_cpu(super->fs_ncg);
-    
-	return 0;    
-}
-
-static int efs_fill_super(struct super_block *s, struct fs_context *fc)
-{
-	struct efs_sb_info *sb;
-	struct buffer_head *bh;
-	struct inode *root;
-
-	sb = kzalloc_obj(struct efs_sb_info);
-	if (!sb)
-		return -ENOMEM;
-	s->s_fs_info = sb;
-	s->s_time_min = 0;
-	s->s_time_max = U32_MAX;
-
-	s->s_magic		= EFS_SUPER_MAGIC;
-	if (!sb_set_blocksize(s, EFS_BLOCKSIZE)) {
-		pr_err("device does not support %d byte blocks\n",
-			EFS_BLOCKSIZE);
-		return invalf(fc, "device does not support %d byte blocks\n",
-			      EFS_BLOCKSIZE);
-	}
-
-	/* read the vh (volume header) block */
-	bh = sb_bread(s, 0);
-
-	if (!bh) {
-		pr_err("cannot read volume header\n");
-		return -EIO;
-	}
-
-	/*
-	 * if this returns zero then we didn't find any partition table.
-	 * this isn't (yet) an error - just assume for the moment that
-	 * the device is valid and go on to search for a superblock.
-	 */
-	sb->fs_start = efs_validate_vh((struct volume_header *) bh->b_data);
-	brelse(bh);
-
-	if (sb->fs_start == -1) {
-		return -EINVAL;
-	}
-
-	bh = sb_bread(s, sb->fs_start + EFS_SUPER);
-	if (!bh) {
-		pr_err("cannot read superblock\n");
-		return -EIO;
-	}
-
-	if (efs_validate_super(sb, (struct efs_super *) bh->b_data)) {
-#ifdef DEBUG
-		pr_warn("invalid superblock at block %u\n",
-			sb->fs_start + EFS_SUPER);
-#endif
-		brelse(bh);
-		return -EINVAL;
-	}
-	brelse(bh);
-
-	if (!sb_rdonly(s)) {
-#ifdef DEBUG
-		pr_info("forcing read-only mode\n");
-#endif
-		s->s_flags |= SB_RDONLY;
-	}
-	s->s_op   = &efs_superblock_operations;
-	s->s_export_op = &efs_export_ops;
-	root = efs_iget(s, EFS_ROOTINODE);
-	if (IS_ERR(root)) {
-		pr_err("get root inode failed\n");
-		return PTR_ERR(root);
-	}
-
-	s->s_root = d_make_root(root);
-	if (!(s->s_root)) {
-		pr_err("get root dentry failed\n");
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-static int efs_get_tree(struct fs_context *fc)
-{
-	return get_tree_bdev(fc, efs_fill_super);
-}
-
-static int efs_reconfigure(struct fs_context *fc)
-{
-	sync_filesystem(fc->root->d_sb);
-	fc->sb_flags |= SB_RDONLY;
-
-	return 0;
-}
-
-static const struct fs_context_operations efs_context_opts = {
-	.get_tree	= efs_get_tree,
-	.reconfigure	= efs_reconfigure,
-};
-
-/*
- * Set up the filesystem mount context.
- */
-static int efs_init_fs_context(struct fs_context *fc)
-{
-	fc->ops = &efs_context_opts;
-
-	return 0;
-}
-
-static int efs_statfs(struct dentry *dentry, struct kstatfs *buf) {
-	struct super_block *sb = dentry->d_sb;
-	struct efs_sb_info *sbi = SUPER_INFO(sb);
-	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
-
-	buf->f_type    = EFS_SUPER_MAGIC;	/* efs magic number */
-	buf->f_bsize   = EFS_BLOCKSIZE;		/* blocksize */
-	buf->f_blocks  = sbi->total_groups *	/* total data blocks */
-			(sbi->group_size - sbi->inode_blocks);
-	buf->f_bfree   = sbi->data_free;	/* free data blocks */
-	buf->f_bavail  = sbi->data_free;	/* free blocks for non-root */
-	buf->f_files   = sbi->total_groups *	/* total inodes */
-			sbi->inode_blocks *
-			(EFS_BLOCKSIZE / sizeof(struct efs_dinode));
-	buf->f_ffree   = sbi->inode_free;	/* free inodes */
-	buf->f_fsid    = u64_to_fsid(id);
-	buf->f_namelen = EFS_MAXNAMELEN;	/* max filename length */
-
-	return 0;
-}
-
diff --git a/fs/efs/symlink.c b/fs/efs/symlink.c
deleted file mode 100644
index 7749feded722..000000000000
--- a/fs/efs/symlink.c
+++ /dev/null
@@ -1,50 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * symlink.c
- *
- * Copyright (c) 1999 Al Smith
- *
- * Portions derived from work (c) 1995,1996 Christian Vogelgsang.
- */
-
-#include <linux/string.h>
-#include <linux/pagemap.h>
-#include <linux/buffer_head.h>
-#include "efs.h"
-
-static int efs_symlink_read_folio(struct file *file, struct folio *folio)
-{
-	char *link = folio_address(folio);
-	struct buffer_head *bh;
-	struct inode *inode = folio->mapping->host;
-	efs_block_t size = inode->i_size;
-	int err;
-  
-	err = -ENAMETOOLONG;
-	if (size > 2 * EFS_BLOCKSIZE)
-		goto fail;
-  
-	/* read first 512 bytes of link target */
-	err = -EIO;
-	bh = sb_bread(inode->i_sb, efs_bmap(inode, 0));
-	if (!bh)
-		goto fail;
-	memcpy(link, bh->b_data, (size > EFS_BLOCKSIZE) ? EFS_BLOCKSIZE : size);
-	brelse(bh);
-	if (size > EFS_BLOCKSIZE) {
-		bh = sb_bread(inode->i_sb, efs_bmap(inode, 1));
-		if (!bh)
-			goto fail;
-		memcpy(link + EFS_BLOCKSIZE, bh->b_data, size - EFS_BLOCKSIZE);
-		brelse(bh);
-	}
-	link[size] = '\0';
-	err = 0;
-fail:
-	folio_end_read(folio, err == 0);
-	return err;
-}
-
-const struct address_space_operations efs_symlink_aops = {
-	.read_folio	= efs_symlink_read_folio
-};
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index bc55be84d945..8ead1646f329 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -147,8 +147,8 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 	if (!sbi->devs->flatdev) {
 		file = erofs_is_fileio_mode(sbi) ?
 				filp_open(dif->path, O_RDONLY | O_LARGEFILE, 0) :
-				bdev_file_open_by_path(dif->path,
-						BLK_OPEN_READ, sb->s_type, NULL);
+				fs_bdev_file_open_by_path(dif->path,
+						BLK_OPEN_READ, sb->s_type, sb);
 		if (IS_ERR(file)) {
 			if (file == ERR_PTR(-ENOTBLK))
 				return -EINVAL;
@@ -841,28 +841,34 @@ static int erofs_fc_reconfigure(struct fs_context *fc)
 
 static int erofs_release_device_info(int id, void *ptr, void *data)
 {
+	struct super_block *sb = data;
 	struct erofs_device_info *dif = ptr;
 
 	fs_put_dax(dif->dax_dev, NULL);
-	if (dif->file)
-		fput(dif->file);
+	if (dif->file) {
+		if (S_ISBLK(file_inode(dif->file)->i_mode))
+			fs_bdev_file_release(dif->file, sb);
+		else
+			fput(dif->file);
+	}
 	kfree(dif->path);
 	kfree(dif);
 	return 0;
 }
 
-static void erofs_free_dev_context(struct erofs_dev_context *devs)
+static void erofs_free_dev_context(struct erofs_dev_context *devs,
+				   struct super_block *sb)
 {
 	if (!devs)
 		return;
-	idr_for_each(&devs->tree, &erofs_release_device_info, NULL);
+	idr_for_each(&devs->tree, &erofs_release_device_info, sb);
 	idr_destroy(&devs->tree);
 	kfree(devs);
 }
 
-static void erofs_sb_free(struct erofs_sb_info *sbi)
+static void erofs_sb_free(struct erofs_sb_info *sbi, struct super_block *sb)
 {
-	erofs_free_dev_context(sbi->devs);
+	erofs_free_dev_context(sbi->devs, sb);
 	kfree_sensitive(sbi->domain_id);
 	if (sbi->dif0.file)
 		fput(sbi->dif0.file);
@@ -874,8 +880,13 @@ static void erofs_fc_free(struct fs_context *fc)
 {
 	struct erofs_sb_info *sbi = fc->s_fs_info;
 
-	if (sbi) /* free here if an error occurs before transferring to sb */
-		erofs_sb_free(sbi);
+	/*
+	 * Freed here only if an error occurs before the sb is set up; at that
+	 * point no block-backed device has been claimed (that happens in
+	 * fill_super), so the NULL sb never reaches fs_bdev_file_release().
+	 */
+	if (sbi)
+		erofs_sb_free(sbi, NULL);
 }
 
 static const struct fs_context_operations erofs_context_ops = {
@@ -929,7 +940,7 @@ static void erofs_kill_sb(struct super_block *sb)
 		kill_block_super(sb);
 	erofs_drop_internal_inodes(sbi);
 	fs_put_dax(sbi->dif0.dax_dev, NULL);
-	erofs_sb_free(sbi);
+	erofs_sb_free(sbi, sb);
 	sb->s_fs_info = NULL;
 }
 
@@ -941,7 +952,7 @@ static void erofs_put_super(struct super_block *sb)
 	erofs_shrinker_unregister(sb);
 	erofs_xattr_prefixes_cleanup(sb);
 	erofs_drop_internal_inodes(sbi);
-	erofs_free_dev_context(sbi->devs);
+	erofs_free_dev_context(sbi->devs, sb);
 	sbi->devs = NULL;
 }
 
diff --git a/fs/exec.c b/fs/exec.c
index c7b8f2d6366c..41e1684d999c 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1418,6 +1418,8 @@ static void free_bprm(struct linux_binprm *bprm)
 	/* If a binfmt changed the interp, free it. */
 	if (bprm->interp != bprm->filename)
 		kfree(bprm->interp);
+	kfree(bprm->bpf_interp);
+	kfree(bprm->bpf_interp_arg);
 	kfree(bprm->fdpath);
 	kfree(bprm);
 }
diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index b7d5e44ad38e..cd9c9eca58f8 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -538,7 +538,7 @@ out:
 }
 
 static int exfat_create(struct mnt_idmap *idmap, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool excl)
+			struct dentry *dentry, umode_t mode)
 {
 	struct super_block *sb = dir->i_sb;
 	struct inode *inode;
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 0d09d22fe708..8666233ec63b 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -99,7 +99,7 @@ struct dentry *ext2_get_parent(struct dentry *child)
  */
 static int ext2_create (struct mnt_idmap * idmap,
 			struct inode * dir, struct dentry * dentry,
-			umode_t mode, bool excl)
+			umode_t mode)
 {
 	struct inode *inode;
 	int err;
@@ -236,7 +236,7 @@ static struct dentry *ext2_mkdir(struct mnt_idmap * idmap,
 
 	inode_inc_link_count(dir);
 
-	inode = ext2_new_inode(dir, S_IFDIR | mode, &dentry->d_name);
+	inode = ext2_new_inode(dir, mode, &dentry->d_name);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
 		goto out_dir;
diff --git a/fs/ext4/extents-test.c b/fs/ext4/extents-test.c
index bd7795a82607..c3836ecb89f9 100644
--- a/fs/ext4/extents-test.c
+++ b/fs/ext4/extents-test.c
@@ -126,11 +126,6 @@ struct kunit_ext_test_param {
 	struct kunit_ext_data_state exp_data_state[3];
 };
 
-static void ext_kill_sb(struct super_block *sb)
-{
-	generic_shutdown_super(sb);
-}
-
 static int ext_init_fs_context(struct fs_context *fc)
 {
 	return 0;
@@ -138,13 +133,13 @@ static int ext_init_fs_context(struct fs_context *fc)
 
 static int ext_set(struct super_block *sb, struct fs_context *fc)
 {
-	return 0;
+	return set_anon_super_fc(sb, fc);
 }
 
 static struct file_system_type ext_fs_type = {
 	.name		 = "extents test",
 	.init_fs_context = ext_init_fs_context,
-	.kill_sb	 = ext_kill_sb,
+	.kill_sb	 = kill_anon_super,
 };
 
 static void extents_kunit_exit(struct kunit *test)
diff --git a/fs/ext4/mballoc-test.c b/fs/ext4/mballoc-test.c
index 0424b8b0b4c3..d31780075c21 100644
--- a/fs/ext4/mballoc-test.c
+++ b/fs/ext4/mballoc-test.c
@@ -59,11 +59,6 @@ static const struct super_operations mbt_sops = {
 	.free_inode	= mbt_free_inode,
 };
 
-static void mbt_kill_sb(struct super_block *sb)
-{
-	generic_shutdown_super(sb);
-}
-
 static int mbt_init_fs_context(struct fs_context *fc)
 {
 	return 0;
@@ -72,7 +67,7 @@ static int mbt_init_fs_context(struct fs_context *fc)
 static struct file_system_type mbt_fs_type = {
 	.name			= "mballoc test",
 	.init_fs_context	= mbt_init_fs_context,
-	.kill_sb		= mbt_kill_sb,
+	.kill_sb		= kill_anon_super,
 };
 
 static int mbt_mb_init(struct super_block *sb)
@@ -136,7 +131,7 @@ static void mbt_mb_release(struct super_block *sb)
 
 static int mbt_set(struct super_block *sb, struct fs_context *fc)
 {
-	return 0;
+	return set_anon_super_fc(sb, fc);
 }
 
 static struct super_block *mbt_ext4_alloc_super_block(void)
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 3b9740c1c16d..a6386c1d237f 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2813,7 +2813,7 @@ static int ext4_add_nondir(handle_t *handle,
  * with d_instantiate().
  */
 static int ext4_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *dentry, umode_t mode, bool excl)
+		       struct dentry *dentry, umode_t mode)
 {
 	handle_t *handle;
 	struct inode *inode;
@@ -3011,7 +3011,7 @@ static struct dentry *ext4_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
 		   EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3);
 retry:
-	inode = ext4_new_inode_start_handle(idmap, dir, S_IFDIR | mode,
+	inode = ext4_new_inode_start_handle(idmap, dir, mode,
 					    &dentry->d_name,
 					    0, NULL, EXT4_HT_DIR, credits);
 	handle = ext4_journal_current_handle();
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 32c8e33b5036..8e7c93a5e458 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5816,7 +5816,7 @@ failed_mount:
 	brelse(sbi->s_sbh);
 	if (sbi->s_journal_bdev_file) {
 		invalidate_bdev(file_bdev(sbi->s_journal_bdev_file));
-		bdev_fput(sbi->s_journal_bdev_file);
+		fs_bdev_file_release(sbi->s_journal_bdev_file, sb);
 	}
 out_fail:
 	invalidate_bdev(sb->s_bdev);
@@ -6000,9 +6000,9 @@ static struct file *ext4_get_journal_blkdev(struct super_block *sb,
 	struct ext4_super_block *es;
 	int errno;
 
-	bdev_file = bdev_file_open_by_dev(j_dev,
+	bdev_file = fs_bdev_file_open_by_dev(j_dev,
 		BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES,
-		sb, &fs_holder_ops);
+		sb, sb);
 	if (IS_ERR(bdev_file)) {
 		ext4_msg(sb, KERN_ERR,
 			 "failed to open journal device unknown-block(%u,%u) %pe",
@@ -6062,7 +6062,7 @@ static struct file *ext4_get_journal_blkdev(struct super_block *sb,
 out_bh:
 	brelse(bh);
 out_bdev:
-	bdev_fput(bdev_file);
+	fs_bdev_file_release(bdev_file, sb);
 	return ERR_PTR(errno);
 }
 
@@ -6101,7 +6101,7 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb,
 out_journal:
 	ext4_journal_destroy(EXT4_SB(sb), journal);
 out_bdev:
-	bdev_fput(bdev_file);
+	fs_bdev_file_release(bdev_file, sb);
 	return ERR_PTR(errno);
 }
 
@@ -7519,7 +7519,7 @@ static void ext4_kill_sb(struct super_block *sb)
 	kill_block_super(sb);
 
 	if (bdev_file)
-		bdev_fput(bdev_file);
+		fs_bdev_file_release(bdev_file, sb);
 }
 
 static struct file_system_type ext4_fs_type = {
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index cac03b8e91a1..5ae647a352aa 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -366,7 +366,7 @@ fail_drop:
 }
 
 static int f2fs_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *dentry, umode_t mode, bool excl)
+		       struct dentry *dentry, umode_t mode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
 	struct f2fs_lock_context lc;
@@ -742,7 +742,7 @@ static struct dentry *f2fs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	if (err)
 		return ERR_PTR(err);
 
-	inode = f2fs_new_inode(idmap, dir, S_IFDIR | mode, NULL);
+	inode = f2fs_new_inode(idmap, dir, mode, NULL);
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 769d16d54997..de99eead6f8d 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1971,7 +1971,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi)
 
 	for (i = 0; i < sbi->s_ndevs; i++) {
 		if (i > 0)
-			bdev_fput(FDEV(i).bdev_file);
+			fs_bdev_file_release(FDEV(i).bdev_file, sbi->sb);
 #ifdef CONFIG_BLK_DEV_ZONED
 		kvfree(FDEV(i).blkz_seq);
 #endif
@@ -4901,8 +4901,8 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 				FDEV(i).end_blk = FDEV(i).start_blk +
 						SEGS_TO_BLKS(sbi,
 						FDEV(i).total_segments) - 1;
-				FDEV(i).bdev_file = bdev_file_open_by_path(
-					FDEV(i).path, mode, sbi->sb, NULL);
+				FDEV(i).bdev_file = fs_bdev_file_open_by_path(
+					FDEV(i).path, mode, sbi->sb, sbi->sb);
 			}
 		}
 		if (IS_ERR(FDEV(i).bdev_file))
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index 0fd2971ad4b1..ee6824c5d136 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -29,6 +29,9 @@ static int msdos_format_name(const unsigned char *name, int len,
 	unsigned char c;
 	int space;
 
+	if (len > NAME_MAX)
+		return -ENAMETOOLONG;
+
 	if (name[0] == '.') {	/* dotfile because . and .. already done */
 		if (opts->dotsOK) {
 			/* Get rid of dot - test for it elsewhere */
@@ -262,7 +265,7 @@ static int msdos_add_entry(struct inode *dir, const unsigned char *name,
 
 /***** Create a file */
 static int msdos_create(struct mnt_idmap *idmap, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool excl)
+			struct dentry *dentry, umode_t mode)
 {
 	struct super_block *sb = dir->i_sb;
 	struct inode *inode = NULL;
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index e909447873e3..139d3ef4bfae 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -755,7 +755,7 @@ error:
 }
 
 static int vfat_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *dentry, umode_t mode, bool excl)
+		       struct dentry *dentry, umode_t mode)
 {
 	struct super_block *sb = dir->i_sb;
 	struct inode *inode;
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index 394875d06fd6..34699f3b6f88 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -8,6 +8,7 @@
 #include <linux/fs_struct.h>
 #include <linux/init_task.h>
 #include "internal.h"
+#include "mount.h"
 
 /*
  * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values.
@@ -60,8 +61,11 @@ void chroot_fs_refs(const struct path *old_root, const struct path *new_root)
 
 	read_lock(&tasklist_lock);
 	for_each_process_thread(g, p) {
+		if (p->flags & (PF_KTHREAD | PF_EXITING | PF_DUMPCORE))
+			continue;
+
 		task_lock(p);
-		fs = p->fs;
+		fs = p->real_fs;
 		if (fs) {
 			int hits = 0;
 			write_seqlock(&fs->seq);
@@ -89,12 +93,13 @@ void free_fs_struct(struct fs_struct *fs)
 
 void exit_fs(struct task_struct *tsk)
 {
-	struct fs_struct *fs = tsk->fs;
+	struct fs_struct *fs = tsk->real_fs;
 
 	if (fs) {
 		int kill;
 		task_lock(tsk);
 		read_seqlock_excl(&fs->seq);
+		tsk->real_fs = NULL;
 		tsk->fs = NULL;
 		kill = !--fs->users;
 		read_sequnlock_excl(&fs->seq);
@@ -126,7 +131,7 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old)
 
 int unshare_fs_struct(void)
 {
-	struct fs_struct *fs = current->fs;
+	struct fs_struct *fs = current->real_fs;
 	struct fs_struct *new_fs = copy_fs_struct(fs);
 	int kill;
 
@@ -135,8 +140,10 @@ int unshare_fs_struct(void)
 
 	task_lock(current);
 	read_seqlock_excl(&fs->seq);
+	VFS_WARN_ON_ONCE(fs != current->fs);
 	kill = !--fs->users;
 	current->fs = new_fs;
+	current->real_fs = new_fs;
 	read_sequnlock_excl(&fs->seq);
 	task_unlock(current);
 
@@ -147,9 +154,99 @@ int unshare_fs_struct(void)
 }
 EXPORT_SYMBOL_GPL(unshare_fs_struct);
 
+/*
+ * PID 1 may choose to stop sharing fs_struct state with us.
+ * Either via unshare(CLONE_FS) or unshare(CLONE_NEWNS). Of
+ * course, PID 1 could have chosen to create arbitrary process
+ * trees that all share fs_struct state via CLONE_FS. This is a
+ * strong statement: We only care about PID 1 aka the thread-group
+ * leader so subthread's fs_struct state doesn't matter.
+ *
+ * PID 1 unsharing fs_struct state is a bug. PID 1 relies on
+ * various kthreads to be able to perform work based on its
+ * fs_struct state. Breaking that contract sucks for both sides.
+ * So just don't bother with extra work for this. No sane init
+ * system should ever do this.
+ *
+ * On older kernels if PID 1 unshared its filesystem state with us the
+ * kernel simply used the stale fs_struct state implicitly pinning
+ * anything that PID 1 had last used. Even if PID 1 might've moved on to
+ * some completely different fs_struct state and might've even unmounted
+ * the old root.
+ *
+ * This has hilarious consequences: Think continuing to dump coredump
+ * state into an implicitly pinned directory somewhere. Calling random
+ * binaries in the old rootfs via usermodehelpers.
+ *
+ * Be aggressive about this: We simply reject operating on stale
+ * fs_struct state by reverting to nullfs. Every kworker that does
+ * lookups after this point will fail. Every usermodehelper call will
+ * fail. Tough luck but let's be kind and emit a warning to userspace.
+ */
+static inline void validate_fs_switch(struct fs_struct *old_fs)
+{
+	might_sleep();
+
+	if (likely(current->pid != 1))
+		return;
+	/* @old_fs may be dangling but for comparison it's fine */
+	if (old_fs != userspace_init_fs)
+		return;
+	pr_warn("VFS: Pid 1 stopped sharing filesystem state\n");
+	set_fs_root(userspace_init_fs, &init_fs.root);
+	set_fs_pwd(userspace_init_fs, &init_fs.root);
+}
+
+struct fs_struct *switch_fs_struct(struct fs_struct *new_fs)
+{
+	struct fs_struct *fs;
+
+	scoped_guard(task_lock, current) {
+		fs = current->fs;
+		VFS_WARN_ON_ONCE(fs != current->real_fs);
+		read_seqlock_excl(&fs->seq);
+		current->fs = new_fs;
+		current->real_fs = new_fs;
+		if (--fs->users)
+			new_fs = NULL;
+		else
+			new_fs = fs;
+		read_sequnlock_excl(&fs->seq);
+	}
+
+	validate_fs_switch(fs);
+	return new_fs;
+}
+
 /* to be mentioned only in INIT_TASK */
 struct fs_struct init_fs = {
 	.users		= 1,
 	.seq		= __SEQLOCK_UNLOCKED(init_fs.seq),
 	.umask		= 0022,
 };
+
+struct fs_struct *userspace_init_fs __ro_after_init;
+EXPORT_SYMBOL_GPL(userspace_init_fs);
+
+void __init init_userspace_fs(void)
+{
+	struct mount *m;
+	struct path root;
+
+	/* Move PID 1 from nullfs into the initramfs. */
+	m = topmost_overmount(current->nsproxy->mnt_ns->root);
+	root.mnt = &m->mnt;
+	root.dentry = root.mnt->mnt_root;
+
+	VFS_WARN_ON_ONCE(current->pid != 1);
+
+	set_fs_root(current->fs, &root);
+	set_fs_pwd(current->fs, &root);
+
+	/* Hold a reference for the global pointer. */
+	read_seqlock_excl(&current->fs->seq);
+	current->fs->users++;
+	read_sequnlock_excl(&current->fs->seq);
+
+	userspace_init_fs = current->fs;
+}
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 0e2a1039fa43..d4e0029810c0 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1084,7 +1084,7 @@ static int fuse_mknod(struct mnt_idmap *idmap, struct inode *dir,
 }
 
 static int fuse_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *entry, umode_t mode, bool excl)
+		       struct dentry *entry, umode_t mode)
 {
 	return fuse_mknod(idmap, dir, entry, mode, 0);
 }
@@ -1117,6 +1117,14 @@ static struct dentry *fuse_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	if (!fm->fc->dont_mask)
 		mode &= ~current_umask();
 
+	/*
+	 * vfs_mkdir() now passes S_IFDIR in @mode, but @mode is forwarded
+	 * verbatim to the userspace server which has only ever been given the
+	 * permission bits. Strip the type bit until the protocol is known to
+	 * cope with it.
+	 */
+	mode &= ~S_IFDIR;
+
 	memset(&inarg, 0, sizeof(inarg));
 	inarg.mode = mode;
 	inarg.umask = current_umask();
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 8a77794bbd4a..f361876c5583 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -963,15 +963,14 @@ fail:
  * @dir: The directory in which to create the file
  * @dentry: The dentry of the new file
  * @mode: The mode of the new file
- * @excl: Force fail if inode exists
  *
  * Returns: errno
  */
 
 static int gfs2_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *dentry, umode_t mode, bool excl)
+		       struct dentry *dentry, umode_t mode)
 {
-	return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl);
+	return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, 1);
 }
 
 /**
@@ -1351,7 +1350,7 @@ static struct dentry *gfs2_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 {
 	unsigned dsize = gfs2_max_stuffed_size(GFS2_I(dir));
 
-	return ERR_PTR(gfs2_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, dsize, 0));
+	return ERR_PTR(gfs2_create_inode(dir, dentry, NULL, mode, 0, NULL, dsize, 0));
 }
 
 /**
diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index e13450bb933e..e1f1fb351464 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -184,7 +184,7 @@ static int hfs_dir_release(struct inode *inode, struct file *file)
  * the directory and the name (and its length) of the new file.
  */
 static int hfs_create(struct mnt_idmap *idmap, struct inode *dir,
-		      struct dentry *dentry, umode_t mode, bool excl)
+		      struct dentry *dentry, umode_t mode)
 {
 	struct inode *inode;
 	int res;
@@ -219,7 +219,7 @@ static struct dentry *hfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	struct inode *inode;
 	int res;
 
-	inode = hfs_new_inode(dir, &dentry->d_name, S_IFDIR | mode);
+	inode = hfs_new_inode(dir, &dentry->d_name, mode);
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index a466c401f6bb..ecdafc658928 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -82,7 +82,7 @@ void hfs_mark_mdb_dirty(struct super_block *sb)
 	spin_lock(&sbi->work_lock);
 	if (!sbi->work_queued) {
 		delay = msecs_to_jiffies(dirty_writeback_interval * 10);
-		queue_delayed_work(system_long_wq, &sbi->mdb_work, delay);
+		queue_delayed_work(system_dfl_long_wq, &sbi->mdb_work, delay);
 		sbi->work_queued = 1;
 	}
 	spin_unlock(&sbi->work_lock);
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 8bf6c7cdd9a8..51fcba2e6d40 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -562,7 +562,7 @@ out:
 }
 
 static int hfsplus_create(struct mnt_idmap *idmap, struct inode *dir,
-			  struct dentry *dentry, umode_t mode, bool excl)
+			  struct dentry *dentry, umode_t mode)
 {
 	return hfsplus_mknod(&nop_mnt_idmap, dir, dentry, mode, 0);
 }
@@ -570,7 +570,7 @@ static int hfsplus_create(struct mnt_idmap *idmap, struct inode *dir,
 static struct dentry *hfsplus_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 				    struct dentry *dentry, umode_t mode)
 {
-	return ERR_PTR(hfsplus_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFDIR, 0));
+	return ERR_PTR(hfsplus_mknod(&nop_mnt_idmap, dir, dentry, mode, 0));
 }
 
 static int hfsplus_rename(struct mnt_idmap *idmap,
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 5777e31de45a..ff7d6b3336a6 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -312,7 +312,7 @@ void hfsplus_mark_mdb_dirty(struct super_block *sb)
 	spin_lock(&sbi->work_lock);
 	if (!sbi->work_queued) {
 		delay = msecs_to_jiffies(dirty_writeback_interval * 10);
-		queue_delayed_work(system_long_wq, &sbi->sync_work, delay);
+		queue_delayed_work(system_dfl_long_wq, &sbi->sync_work, delay);
 		sbi->work_queued = 1;
 	}
 	spin_unlock(&sbi->work_lock);
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index abe86d72d9ef..7add056d47d8 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -593,7 +593,7 @@ static struct inode *hostfs_iget(struct super_block *sb, char *name)
 }
 
 static int hostfs_create(struct mnt_idmap *idmap, struct inode *dir,
-			 struct dentry *dentry, umode_t mode, bool excl)
+			 struct dentry *dentry, umode_t mode)
 {
 	struct inode *inode;
 	char *name;
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index 353e13a615f5..9446f4038874 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -105,10 +105,10 @@ static struct dentry *hpfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 
 	if (!uid_eq(result->i_uid, current_fsuid()) ||
 	    !gid_eq(result->i_gid, current_fsgid()) ||
-	    result->i_mode != (mode | S_IFDIR)) {
+	    result->i_mode != mode) {
 		result->i_uid = current_fsuid();
 		result->i_gid = current_fsgid();
-		result->i_mode = mode | S_IFDIR;
+		result->i_mode = mode;
 		hpfs_write_inode_nolock(result);
 	}
 	hpfs_update_directory_times(dir);
@@ -129,7 +129,7 @@ bail:
 }
 
 static int hpfs_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *dentry, umode_t mode, bool excl)
+		       struct dentry *dentry, umode_t mode)
 {
 	const unsigned char *name = dentry->d_name.name;
 	unsigned len = dentry->d_name.len;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 216e1a0dd0b2..38e9e59f64d8 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -971,7 +971,7 @@ static struct dentry *hugetlbfs_mkdir(struct mnt_idmap *idmap, struct inode *dir
 				      struct dentry *dentry, umode_t mode)
 {
 	int retval = hugetlbfs_mknod(idmap, dir, dentry,
-				     mode | S_IFDIR, 0);
+				     mode, 0);
 	if (!retval)
 		inc_nlink(dir);
 	return ERR_PTR(retval);
@@ -979,7 +979,7 @@ static struct dentry *hugetlbfs_mkdir(struct mnt_idmap *idmap, struct inode *dir
 
 static int hugetlbfs_create(struct mnt_idmap *idmap,
 			    struct inode *dir, struct dentry *dentry,
-			    umode_t mode, bool excl)
+			    umode_t mode)
 {
 	return hugetlbfs_mknod(idmap, dir, dentry, mode | S_IFREG, 0);
 }
diff --git a/fs/inode.c b/fs/inode.c
index 31c5b9ee3a81..a31aa7cb47f6 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -763,21 +763,18 @@ void clear_inode(struct inode *inode)
 		fsverity_cleanup_inode(inode);
 
 	/*
-	 * We have to cycle the i_pages lock here because reclaim can be in the
-	 * process of removing the last page (in __filemap_remove_folio())
-	 * and we must not free the mapping under it.
+	 * We have to cycle the i_pages lock here because reclaim
+	 * can be in the process of removing the last page (in
+	 * __filemap_remove_folio()) and we must not free the mapping
+	 * under it.  We also remove nodes which are empty; these
+	 * can occur in two different ways.  The first is that radix
+	 * tree expansion can fail partway and the second is that THP
+	 * collapse_file() can allocate some temporary nodes and not
+	 * clean them up.
 	 */
-	xa_lock_irq(&inode->i_data.i_pages);
+	xa_destroy(&inode->i_data.i_pages);
+
 	BUG_ON(inode->i_data.nrpages);
-	/*
-	 * Almost always, mapping_empty(&inode->i_data) here; but there are
-	 * two known and long-standing ways in which nodes may get left behind
-	 * (when deep radix-tree node allocation failed partway; or when THP
-	 * collapse_file() failed). Until those two known cases are cleaned up,
-	 * or a cleanup function is called here, do not BUG_ON(!mapping_empty),
-	 * nor even WARN_ON(!mapping_empty).
-	 */
-	xa_unlock_irq(&inode->i_data.i_pages);
 	BUG_ON(!(inode_state_read_once(inode) & I_FREEING));
 	BUG_ON(inode_state_read_once(inode) & I_CLEAR);
 	BUG_ON(!list_empty(&inode->i_wb_list));
diff --git a/fs/internal.h b/fs/internal.h
index 355d93f92208..174f06357555 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -137,6 +137,7 @@ extern int reconfigure_super(struct fs_context *);
 extern bool super_trylock_shared(struct super_block *sb);
 struct super_block *user_get_super(dev_t, bool excl);
 void put_super(struct super_block *sb);
+void __init super_dev_init(void);
 extern bool mount_capable(struct fs_context *);
 
 /*
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 6d9a2efd4bee..f669fcdca2f0 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -792,7 +792,7 @@ EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate);
  */
 struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len)
 {
-	fgf_t fgp = FGP_WRITEBEGIN | FGP_NOFS;
+	fgf_t fgp = FGP_WRITEBEGIN;
 
 	if (iter->flags & IOMAP_NOWAIT)
 		fgp |= FGP_NOWAIT;
@@ -1182,7 +1182,6 @@ static bool iomap_write_end(struct iomap_iter *iter, size_t len, size_t copied,
 static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i,
 		const struct iomap_write_ops *write_ops)
 {
-	ssize_t total_written = 0;
 	int status = 0;
 	struct address_space *mapping = iter->inode->i_mapping;
 	size_t chunk = mapping_max_folio_size(mapping);
@@ -1278,12 +1277,11 @@ retry:
 				goto retry;
 			}
 		} else {
-			total_written += written;
 			iomap_iter_advance(iter, written);
 		}
 	} while (iov_iter_count(i) && iomap_length(iter));
 
-	return total_written ? 0 : status;
+	return status;
 }
 
 ssize_t
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index e2cd5f92babe..64c6b7286c20 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -10,6 +10,7 @@
 #include <linux/iomap.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/fserror.h>
+#include <linux/init.h>
 #include "internal.h"
 #include "trace.h"
 
@@ -88,9 +89,9 @@ static inline enum fserror_type iomap_dio_err_type(const struct iomap_dio *dio)
 	return FSERR_DIRECTIO_READ;
 }
 
-static inline bool should_report_dio_fserror(const struct iomap_dio *dio)
+static inline bool should_report_dio_fserror(int error)
 {
-	switch (dio->error) {
+	switch (error) {
 	case 0:
 	case -EAGAIN:
 	case -ENOTBLK:
@@ -110,7 +111,7 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 
 	if (dops && dops->end_io)
 		ret = dops->end_io(iocb, dio->size, ret, dio->flags);
-	if (should_report_dio_fserror(dio))
+	if (should_report_dio_fserror(dio->error))
 		fserror_report_io(file_inode(iocb->ki_filp),
 				  iomap_dio_err_type(dio), offset, dio->size,
 				  dio->error, GFP_NOFS);
@@ -403,6 +404,14 @@ out_put_bio:
 	return ret;
 }
 
+static inline unsigned int iomap_dio_alignment(struct inode *inode,
+		struct block_device *bdev, unsigned int dio_flags)
+{
+	if (dio_flags & IOMAP_DIO_FSBLOCK_ALIGNED)
+		return i_blocksize(inode);
+	return bdev_logical_block_size(bdev);
+}
+
 static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 {
 	const struct iomap *iomap = &iter->iomap;
@@ -421,10 +430,7 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 	 * File systems that write out of place and always allocate new blocks
 	 * need each bio to be block aligned as that's the unit of allocation.
 	 */
-	if (dio->flags & IOMAP_DIO_FSBLOCK_ALIGNED)
-		alignment = fs_block_size;
-	else
-		alignment = bdev_logical_block_size(iomap->bdev);
+	alignment = iomap_dio_alignment(inode, iomap->bdev, dio->flags);
 
 	if ((pos | length) & (alignment - 1))
 		return -EINVAL;
@@ -893,12 +899,277 @@ out_free_dio:
 }
 EXPORT_SYMBOL_GPL(__iomap_dio_rw);
 
+struct iomap_dio_simple {
+	struct kiocb		*iocb;
+	size_t			size;
+	unsigned int		dio_flags;
+	struct work_struct	work;
+	/*
+	 * Align @bio to a cacheline boundary so that, combined with the
+	 * front_pad passed to bioset_init(), the bio sits at the start of
+	 * a cacheline in memory returned by the (HWCACHE-aligned) bio
+	 * slab.  This keeps the hot fields block layer touches on submit
+	 * and completion (bi_iter, bi_status, ...) within a single line.
+	 */
+	struct bio		bio ____cacheline_aligned_in_smp;
+};
+
+static struct bio_set iomap_dio_simple_pool;
+
+static ssize_t iomap_dio_simple_complete(struct iomap_dio_simple *sr)
+{
+	struct bio *bio = &sr->bio;
+	struct kiocb *iocb = sr->iocb;
+	struct inode *inode = file_inode(iocb->ki_filp);
+	ssize_t ret;
+
+	if (unlikely(bio->bi_status)) {
+		ret = blk_status_to_errno(bio->bi_status);
+		if (should_report_dio_fserror(ret))
+			fserror_report_io(inode, FSERR_DIRECTIO_READ,
+					  iocb->ki_pos, sr->size, ret,
+					  GFP_NOFS);
+	} else {
+		ret = sr->size;
+		iocb->ki_pos += ret;
+	}
+
+	if (sr->dio_flags & IOMAP_DIO_USER_BACKED) {
+		bio_check_pages_dirty(bio);
+	} else {
+		bio_release_pages(bio, false);
+		bio_put(bio);
+	}
+	inode_dio_end(inode);
+	trace_iomap_dio_complete(iocb, ret < 0 ? ret : 0, ret);
+	return ret;
+}
+
+static void iomap_dio_simple_complete_work(struct work_struct *work)
+{
+	struct iomap_dio_simple *sr =
+		container_of(work, struct iomap_dio_simple, work);
+	struct kiocb *iocb = sr->iocb;
+
+	WRITE_ONCE(iocb->private, NULL);
+	iocb->ki_complete(iocb, iomap_dio_simple_complete(sr));
+}
+
+static void iomap_dio_simple_end_io(struct bio *bio)
+{
+	struct iomap_dio_simple *sr =
+		container_of(bio, struct iomap_dio_simple, bio);
+	struct kiocb *iocb = sr->iocb;
+
+	if (unlikely(sr->bio.bi_status)) {
+		struct inode *inode = file_inode(iocb->ki_filp);
+
+		INIT_WORK(&sr->work, iomap_dio_simple_complete_work);
+		queue_work(inode->i_sb->s_dio_done_wq, &sr->work);
+		return;
+	}
+
+	WRITE_ONCE(iocb->private, NULL);
+	iocb->ki_complete(iocb, iomap_dio_simple_complete(sr));
+}
+
+static inline bool
+iomap_dio_simple_supported(struct kiocb *iocb, struct iov_iter *iter,
+			   const struct iomap_dio_ops *dops,
+			   unsigned int dio_flags, size_t done_before)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	size_t count = iov_iter_count(iter);
+
+	if (dops || done_before)
+		return false;
+	if (iov_iter_rw(iter) != READ)
+		return false;
+	if (!count)
+		return false;
+	/*
+	 * Simple dio is an optimization for small IO. Filter out large IO
+	 * early as it's the most common case to fail for typical direct IO
+	 * workloads.
+	 */
+	if (count > inode->i_sb->s_blocksize)
+		return false;
+	if (dio_flags & (IOMAP_DIO_FORCE_WAIT | IOMAP_DIO_PARTIAL |
+			 IOMAP_DIO_BOUNCE))
+		return false;
+	if (iocb->ki_pos + count > i_size_read(inode))
+		return false;
+	if (IS_ENCRYPTED(inode))
+		return false;
+
+	return true;
+}
+
+/*
+ * Fast path for small, block-aligned direct I/Os that map to a single
+ * contiguous on-disk extent.
+ *
+ * iomap_dio_simple_supported() enforces the cheap up-front constraints before
+ * entering this path.
+ *
+ * @dops must be NULL: a non-NULL @dops means the caller wants its
+ * ->end_io / ->submit_io hooks invoked, and in particular wants its bios to be
+ * allocated from the filesystem-private @dops->bio_set (whose front_pad sizes a
+ * filesystem-private wrapper around the bio).  The fast path instead allocates
+ * from the shared iomap_dio_simple_pool, whose front_pad matches struct
+ * iomap_dio_simple; the two wrappers are not interchangeable, so we must fall
+ * back to __iomap_dio_rw() in that case.
+ *
+ * @done_before must be zero: a non-zero caller-accumulated residual cannot be
+ * carried through a single-bio inline completion.
+ *
+ * @iter must describe a non-empty READ no larger than the inode block size:
+ * writes, zero-length I/O, and larger requests need the generic iomap direct
+ * I/O path.
+ *
+ * @dio_flags must not request IOMAP_DIO_FORCE_WAIT, IOMAP_DIO_PARTIAL, or
+ * IOMAP_DIO_BOUNCE: this path does not support forced waiting, partial direct
+ * I/O, or bouncing.  The range must also stay within i_size and encrypted
+ * inodes must use the generic iomap direct I/O path.
+ *
+ * -ENOTBLK is the private sentinel returned by iomap_dio_simple() when it
+ * decides the request does not fit the fast path.  In that case we proceed to
+ * the generic __iomap_dio_rw() slow path.  Any other errno is a real result and
+ * is propagated as-is, in particular -EAGAIN for IOCB_NOWAIT must reach the
+ * caller.
+ */
+static ssize_t
+iomap_dio_simple(struct kiocb *iocb, struct iov_iter *iter,
+		 const struct iomap_ops *ops, void *private,
+		 unsigned int dio_flags)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	size_t count = iov_iter_count(iter);
+	bool wait_for_completion = is_sync_kiocb(iocb);
+	struct iomap_iter iomi = {
+		.inode		= inode,
+		.pos		= iocb->ki_pos,
+		.len		= count,
+		.flags		= IOMAP_DIRECT,
+		.private	= private,
+	};
+	struct iomap_dio_simple *sr;
+	unsigned int alignment;
+	struct bio *bio;
+	ssize_t ret;
+
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		iomi.flags |= IOMAP_NOWAIT;
+
+	ret = kiocb_write_and_wait(iocb, count);
+	if (ret)
+		return ret;
+
+	inode_dio_begin(inode);
+
+	ret = ops->iomap_begin(inode, iomi.pos, count, iomi.flags,
+			       &iomi.iomap, &iomi.srcmap);
+	if (ret) {
+		inode_dio_end(inode);
+		return ret;
+	}
+
+	if (iomi.iomap.type != IOMAP_MAPPED ||
+	    iomi.iomap.offset + iomi.iomap.length < iomi.pos + count ||
+	    (iomi.iomap.flags & IOMAP_F_INTEGRITY)) {
+		ret = -ENOTBLK;
+		goto out_iomap_end;
+	}
+
+	alignment = iomap_dio_alignment(inode, iomi.iomap.bdev, dio_flags);
+	if ((iomi.pos | count) & (alignment - 1)) {
+		ret = -EINVAL;
+		goto out_iomap_end;
+	}
+
+	if (!wait_for_completion && unlikely(!inode->i_sb->s_dio_done_wq)) {
+		ret = sb_init_dio_done_wq(inode->i_sb);
+		if (ret < 0)
+			goto out_iomap_end;
+	}
+
+	trace_iomap_dio_rw_begin(iocb, iter, dio_flags, 0);
+
+	if (user_backed_iter(iter))
+		dio_flags |= IOMAP_DIO_USER_BACKED;
+
+	bio = bio_alloc_bioset(iomi.iomap.bdev,
+			       bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS),
+			       REQ_OP_READ, GFP_KERNEL, &iomap_dio_simple_pool);
+	sr = container_of(bio, struct iomap_dio_simple, bio);
+	sr->iocb = iocb;
+	sr->dio_flags = dio_flags;
+
+	bio->bi_iter.bi_sector = iomap_sector(&iomi.iomap, iomi.pos);
+	bio->bi_ioprio = iocb->ki_ioprio;
+
+	ret = bio_iov_iter_get_pages(bio, iter, alignment - 1);
+	if (unlikely(ret))
+		goto out_bio_put;
+
+	if (bio->bi_iter.bi_size != count) {
+		iov_iter_revert(iter, bio->bi_iter.bi_size);
+		ret = -ENOTBLK;
+		goto out_bio_release_pages;
+	}
+
+	sr->size = bio->bi_iter.bi_size;
+
+	if (dio_flags & IOMAP_DIO_USER_BACKED)
+		bio_set_pages_dirty(bio);
+
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		bio->bi_opf |= REQ_NOWAIT;
+	if ((iocb->ki_flags & IOCB_HIPRI) && !wait_for_completion) {
+		bio->bi_opf |= REQ_POLLED;
+		WRITE_ONCE(iocb->private, bio);
+	}
+
+	if (ops->iomap_end)
+		ops->iomap_end(inode, iomi.pos, count, count, iomi.flags,
+			       &iomi.iomap);
+
+	if (!wait_for_completion) {
+		bio->bi_end_io = iomap_dio_simple_end_io;
+		submit_bio(bio);
+		trace_iomap_dio_rw_queued(inode, iomi.pos, count);
+		return -EIOCBQUEUED;
+	}
+
+	submit_bio_wait(bio);
+	return iomap_dio_simple_complete(sr);
+
+out_bio_release_pages:
+	bio_release_pages(bio, false);
+out_bio_put:
+	bio_put(bio);
+out_iomap_end:
+	if (ops->iomap_end)
+		ops->iomap_end(inode, iomi.pos, count, 0, iomi.flags,
+			       &iomi.iomap);
+	inode_dio_end(inode);
+	return ret;
+}
+
 ssize_t
 iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		unsigned int dio_flags, void *private, size_t done_before)
 {
 	struct iomap_dio *dio;
+	ssize_t ret;
+
+	if (iomap_dio_simple_supported(iocb, iter, dops, dio_flags,
+				       done_before)) {
+		ret = iomap_dio_simple(iocb, iter, ops, private, dio_flags);
+		if (ret != -ENOTBLK)
+			return ret;
+	}
 
 	dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags, private,
 			     done_before);
@@ -907,3 +1178,11 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	return iomap_dio_complete(dio);
 }
 EXPORT_SYMBOL_GPL(iomap_dio_rw);
+
+static int __init iomap_dio_init(void)
+{
+	return bioset_init(&iomap_dio_simple_pool, 4,
+			   offsetof(struct iomap_dio_simple, bio),
+			   BIOSET_NEED_BVECS | BIOSET_PERCPU_CACHE);
+}
+fs_initcall(iomap_dio_init);
diff --git a/fs/iomap/ioend.c b/fs/iomap/ioend.c
index 30468d51b5ad..fb636dce43af 100644
--- a/fs/iomap/ioend.c
+++ b/fs/iomap/ioend.c
@@ -13,6 +13,7 @@
 
 struct bio_set iomap_ioend_bioset;
 EXPORT_SYMBOL_GPL(iomap_ioend_bioset);
+static struct bio_set iomap_ioend_split_bioset;
 
 struct iomap_ioend *iomap_init_ioend(struct inode *inode,
 		struct bio *bio, loff_t file_offset, u16 ioend_flags)
@@ -488,7 +489,8 @@ struct iomap_ioend *iomap_split_ioend(struct iomap_ioend *ioend,
 	sector_offset = ALIGN_DOWN(sector_offset << SECTOR_SHIFT,
 			i_blocksize(ioend->io_inode)) >> SECTOR_SHIFT;
 
-	split = bio_split(bio, sector_offset, GFP_NOFS, &iomap_ioend_bioset);
+	split = bio_split(bio, sector_offset, GFP_NOFS,
+			&iomap_ioend_split_bioset);
 	if (IS_ERR(split))
 		return ERR_CAST(split);
 	split->bi_private = bio->bi_private;
@@ -511,8 +513,23 @@ EXPORT_SYMBOL_GPL(iomap_split_ioend);
 
 static int __init iomap_ioend_init(void)
 {
-	return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
+	const unsigned int nr_mempool_entries = 4 * (PAGE_SIZE / SECTOR_SIZE);
+	int error;
+
+	error = bioset_init(&iomap_ioend_bioset, nr_mempool_entries,
 			   offsetof(struct iomap_ioend, io_bio),
 			   BIOSET_NEED_BVECS);
+	if (error)
+		return error;
+	error = bioset_init(&iomap_ioend_split_bioset, nr_mempool_entries,
+			   offsetof(struct iomap_ioend, io_bio),
+			   BIOSET_NEED_BVECS);
+	if (error)
+		goto out_exit_ioend_bioset;
+	return 0;
+
+out_exit_ioend_bioset:
+	bioset_exit(&iomap_ioend_bioset);
+	return error;
 }
 fs_initcall(iomap_ioend_init);
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index c4088c3b4ac0..656c920864c5 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -26,7 +26,7 @@
 static int jffs2_readdir (struct file *, struct dir_context *);
 
 static int jffs2_create (struct mnt_idmap *, struct inode *,
-		         struct dentry *, umode_t, bool);
+		         struct dentry *, umode_t);
 static struct dentry *jffs2_lookup (struct inode *,struct dentry *,
 				    unsigned int);
 static int jffs2_link (struct dentry *,struct inode *,struct dentry *);
@@ -163,7 +163,7 @@ static int jffs2_readdir(struct file *file, struct dir_context *ctx)
 
 
 static int jffs2_create(struct mnt_idmap *idmap, struct inode *dir_i,
-			struct dentry *dentry, umode_t mode, bool excl)
+			struct dentry *dentry, umode_t mode)
 {
 	struct jffs2_raw_inode *ri;
 	struct jffs2_inode_info *f, *dir_f;
@@ -462,8 +462,6 @@ static struct dentry *jffs2_mkdir (struct mnt_idmap *idmap, struct inode *dir_i,
 	uint32_t alloclen;
 	int ret;
 
-	mode |= S_IFDIR;
-
 	ri = jffs2_alloc_raw_inode();
 	if (!ri)
 		return ERR_PTR(-ENOMEM);
diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c
index 8ff7a0b6add2..3b7803c75d58 100644
--- a/fs/jffs2/wbuf.c
+++ b/fs/jffs2/wbuf.c
@@ -1177,7 +1177,7 @@ void jffs2_dirty_trigger(struct jffs2_sb_info *c)
 		return;
 
 	delay = msecs_to_jiffies(dirty_writeback_interval * 10);
-	if (queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay))
+	if (queue_delayed_work(system_dfl_long_wq, &c->wbuf_dwork, delay))
 		jffs2_dbg(1, "%s()\n", __func__);
 }
 
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 442d62679262..8a36c218f0f7 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -61,7 +61,7 @@ static inline void free_ea_wmap(struct inode *inode)
  *
  */
 static int jfs_create(struct mnt_idmap *idmap, struct inode *dip,
-		      struct dentry *dentry, umode_t mode, bool excl)
+		      struct dentry *dentry, umode_t mode)
 {
 	int rc = 0;
 	tid_t tid;		/* transaction id */
@@ -223,7 +223,7 @@ static struct dentry *jfs_mkdir(struct mnt_idmap *idmap, struct inode *dip,
 	 * block there while holding dtree page, so we allocate the inode &
 	 * begin the transaction before we search the directory.
 	 */
-	ip = ialloc(dip, S_IFDIR | mode);
+	ip = ialloc(dip, mode);
 	if (IS_ERR(ip)) {
 		rc = PTR_ERR(ip);
 		goto out2;
diff --git a/fs/kernel_read_file.c b/fs/kernel_read_file.c
index de32c95d823d..9c2ba9240083 100644
--- a/fs/kernel_read_file.c
+++ b/fs/kernel_read_file.c
@@ -150,18 +150,13 @@ ssize_t kernel_read_file_from_path_initns(const char *path, loff_t offset,
 					  enum kernel_read_file_id id)
 {
 	struct file *file;
-	struct path root;
 	ssize_t ret;
 
 	if (!path || !*path)
 		return -EINVAL;
 
-	task_lock(&init_task);
-	get_fs_root(init_task.fs, &root);
-	task_unlock(&init_task);
-
-	file = file_open_root(&root, path, O_RDONLY, 0);
-	path_put(&root);
+	scoped_with_init_fs()
+		file = filp_open(path, O_RDONLY, 0);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
diff --git a/fs/minix/namei.c b/fs/minix/namei.c
index 263e4ba8b1c8..5525ba367ed7 100644
--- a/fs/minix/namei.c
+++ b/fs/minix/namei.c
@@ -64,7 +64,7 @@ static int minix_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
 }
 
 static int minix_create(struct mnt_idmap *idmap, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool excl)
+			struct dentry *dentry, umode_t mode)
 {
 	return minix_mknod(&nop_mnt_idmap, dir, dentry, mode, 0);
 }
@@ -110,7 +110,7 @@ static struct dentry *minix_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	struct inode * inode;
 	int err;
 
-	inode = minix_new_inode(dir, S_IFDIR | mode);
+	inode = minix_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
diff --git a/fs/namei.c b/fs/namei.c
index 19ce43c9a6e6..e4ef48583a3b 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4140,11 +4140,6 @@ EXPORT_SYMBOL(end_renaming);
  * after setgid stripping allows the same ordering for both non-POSIX ACL and
  * POSIX ACL supporting filesystems.
  *
- * Note that it's currently valid for @type to be 0 if a directory is created.
- * Filesystems raise that flag individually and we need to check whether each
- * filesystem can deal with receiving S_IFDIR from the vfs before we enforce a
- * non-zero type.
- *
  * Returns: mode to be passed to the filesystem
  */
 static inline umode_t vfs_prepare_mode(struct mnt_idmap *idmap,
@@ -4190,7 +4185,7 @@ int vfs_create(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode,
 		return error;
 
 	if (!dir->i_op->create)
-		return -EACCES;	/* shouldn't it be ENOSYS? */
+		return -EOPNOTSUPP;
 
 	mode = vfs_prepare_mode(idmap, dir, mode, S_IALLUGO, S_IFREG);
 	error = security_inode_create(dir, dentry, mode);
@@ -4199,7 +4194,7 @@ int vfs_create(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode,
 	error = try_break_deleg(dir, LEASE_BREAK_DIR_CREATE, di);
 	if (error)
 		return error;
-	error = dir->i_op->create(idmap, dir, dentry, mode, true);
+	error = dir->i_op->create(idmap, dir, dentry, mode);
 	if (!error)
 		fsnotify_create(dir, dentry);
 	return error;
@@ -4501,12 +4496,11 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file,
 		file->f_mode |= FMODE_CREATED;
 		audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE);
 		if (!dir_inode->i_op->create) {
-			error = -EACCES;
+			error = -EOPNOTSUPP;
 			goto out_dput;
 		}
 
-		error = dir_inode->i_op->create(idmap, dir_inode, dentry,
-						mode, open_flag & O_EXCL);
+		error = dir_inode->i_op->create(idmap, dir_inode, dentry, mode);
 		if (error)
 			goto out_dput;
 	}
@@ -5117,7 +5111,7 @@ int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 		return -EPERM;
 
 	if (!dir->i_op->mknod)
-		return -EPERM;
+		return -EOPNOTSUPP;
 
 	mode = vfs_prepare_mode(idmap, dir, mode, mode, mode);
 	error = devcgroup_inode_mknod(mode, dev);
@@ -5256,11 +5250,11 @@ struct dentry *vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	if (error)
 		goto err;
 
-	error = -EPERM;
+	error = -EOPNOTSUPP;
 	if (!dir->i_op->mkdir)
 		goto err;
 
-	mode = vfs_prepare_mode(idmap, dir, mode, S_IRWXUGO | S_ISVTX, 0);
+	mode = vfs_prepare_mode(idmap, dir, mode, S_IRWXUGO | S_ISVTX, S_IFDIR);
 	error = security_inode_mkdir(dir, dentry, mode);
 	if (error)
 		goto err;
@@ -5360,7 +5354,7 @@ int vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir,
 		return error;
 
 	if (!dir->i_op->rmdir)
-		return -EPERM;
+		return -EOPNOTSUPP;
 
 	dget(dentry);
 	inode_lock(dentry->d_inode);
@@ -5496,7 +5490,7 @@ int vfs_unlink(struct mnt_idmap *idmap, struct inode *dir,
 		return error;
 
 	if (!dir->i_op->unlink)
-		return -EPERM;
+		return -EOPNOTSUPP;
 
 	inode_lock(target);
 	if (IS_SWAPFILE(target))
@@ -5647,7 +5641,7 @@ int vfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 		return error;
 
 	if (!dir->i_op->symlink)
-		return -EPERM;
+		return -EOPNOTSUPP;
 
 	error = security_inode_symlink(dir, dentry, oldname);
 	if (error)
@@ -5769,7 +5763,7 @@ int vfs_link(struct dentry *old_dentry, struct mnt_idmap *idmap,
 	if (HAS_UNMAPPED_ID(idmap, inode))
 		return -EPERM;
 	if (!dir->i_op->link)
-		return -EPERM;
+		return -EOPNOTSUPP;
 	if (S_ISDIR(inode->i_mode))
 		return -EPERM;
 
@@ -5978,7 +5972,7 @@ int vfs_rename(struct renamedata *rd)
 		return error;
 
 	if (!old_dir->i_op->rename)
-		return -EPERM;
+		return -EOPNOTSUPP;
 
 	/*
 	 * If we are going to change the parent - check write permissions,
diff --git a/fs/namespace.c b/fs/namespace.c
index 3d5cd5bf3b05..6b81b77f9303 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2908,6 +2908,9 @@ static int do_change_type(const struct path *path, int ms_flags)
 	for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL))
 		change_mnt_propagation(m, type);
 
+	guard(mount_locked_reader)();
+	touch_mnt_namespace(mnt->mnt_ns);
+
 	return 0;
 }
 
@@ -3481,6 +3484,10 @@ static int do_set_group(const struct path *from_path, const struct path *to_path
 		list_add(&to->mnt_share, &from->mnt_share);
 		set_mnt_shared(to);
 	}
+
+	guard(mount_locked_reader)();
+	touch_mnt_namespace(to->mnt_ns);
+
 	return 0;
 }
 
@@ -6184,12 +6191,14 @@ static void __init init_mount_tree(void)
 	struct path root;
 
 	/*
-	 * We create two mounts:
+	 * We create three mounts:
 	 *
 	 * (1) nullfs with mount id 1
 	 * (2) mutable rootfs with mount id 2
+	 * (3) private nullfs for kthreads (SB_KERNMOUNT)
 	 *
-	 * with (2) mounted on top of (1).
+	 * with (2) mounted on top of (1). The init_task's root and pwd
+	 * are pointed at (3) so all kthreads start isolated in nullfs.
 	 */
 	nullfs_mnt = vfs_kern_mount(&nullfs_fs_type, 0, "nullfs", NULL);
 	if (IS_ERR(nullfs_mnt))
@@ -6229,12 +6238,14 @@ static void __init init_mount_tree(void)
 		init_mnt_ns.nr_mounts++;
 	}
 
+	nullfs_mnt = kern_mount(&nullfs_fs_type);
+	if (IS_ERR(nullfs_mnt))
+		panic("VFS: Failed to create private nullfs instance");
+	root.mnt	= nullfs_mnt;
+	root.dentry	= nullfs_mnt->mnt_root;
+
 	init_task.nsproxy->mnt_ns = &init_mnt_ns;
 	get_mnt_ns(&init_mnt_ns);
-
-	/* The root and pwd always point to the mutable rootfs. */
-	root.mnt	= mnt;
-	root.dentry	= mnt->mnt_root;
 	set_fs_pwd(current->fs, &root);
 	set_fs_root(current->fs, &root);
 
@@ -6262,6 +6273,8 @@ void __init mnt_init(void)
 	if (!mount_hashtable || !mountpoint_hashtable)
 		panic("Failed to allocate mount hash table\n");
 
+	super_dev_init();
+
 	kernfs_init();
 
 	err = sysfs_init();
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index bb35f88501ce..368d20daf67b 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -4,6 +4,7 @@
  */
 #include <linux/sunrpc/svc.h>
 #include <linux/blkdev.h>
+#include <linux/fs_struct.h>
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_xdr.h>
@@ -363,15 +364,22 @@ static struct file *
 bl_open_path(struct pnfs_block_volume *v, const char *prefix)
 {
 	struct file *bdev_file;
-	const char *devname;
+	const char *devname __free(kfree) = NULL;
 
 	devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/%s%*phN",
 			prefix, v->scsi.designator_len, v->scsi.designator);
 	if (!devname)
 		return ERR_PTR(-ENOMEM);
 
-	bdev_file = bdev_file_open_by_path(devname,
-			BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, NULL);
+	if (tsk_is_kthread(current)) {
+		scoped_with_init_fs()
+			bdev_file = bdev_file_open_by_path(devname,
+					BLK_OPEN_READ | BLK_OPEN_WRITE,
+					NULL, NULL);
+	} else {
+		bdev_file = bdev_file_open_by_path(devname,
+				BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, NULL);
+	}
 	if (IS_ERR(bdev_file)) {
 		dprintk("failed to open device %s (%ld)\n",
 			devname, PTR_ERR(bdev_file));
@@ -380,7 +388,6 @@ bl_open_path(struct pnfs_block_volume *v, const char *prefix)
 			file_bdev(bdev_file)->bd_disk->disk_name);
 	}
 
-	kfree(devname);
 	return bdev_file;
 }
 
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index c7caffb31935..36f2e8588922 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2427,9 +2427,9 @@ out_err:
 }
 
 int nfs_create(struct mnt_idmap *idmap, struct inode *dir,
-	       struct dentry *dentry, umode_t mode, bool excl)
+	       struct dentry *dentry, umode_t mode)
 {
-	return nfs_do_create(dir, dentry, mode, excl ? O_EXCL : 0);
+	return nfs_do_create(dir, dentry, mode, O_EXCL);
 }
 EXPORT_SYMBOL_GPL(nfs_create);
 
@@ -2474,7 +2474,7 @@ struct dentry *nfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 			dir->i_sb->s_id, dir->i_ino, dentry);
 
 	attr.ia_valid = ATTR_MODE;
-	attr.ia_mode = mode | S_IFDIR;
+	attr.ia_mode = mode;
 
 	trace_nfs_mkdir_enter(dir, dentry);
 	ret = NFS_PROTO(dir)->mkdir(dir, dentry, &attr);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index e4533f583632..7f96a258af76 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -395,7 +395,7 @@ extern unsigned long nfs_access_cache_scan(struct shrinker *shrink,
 struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int);
 void nfs_d_prune_case_insensitive_aliases(struct inode *inode);
 int nfs_create(struct mnt_idmap *, struct inode *, struct dentry *,
-	       umode_t, bool);
+	       umode_t);
 struct dentry *nfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *,
 			 umode_t);
 int nfs_rmdir(struct inode *, struct dentry *);
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index e2fe95de3d71..77c5f7f74fbf 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -86,7 +86,7 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
  * with d_instantiate().
  */
 static int nilfs_create(struct mnt_idmap *idmap, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool excl)
+			struct dentry *dentry, umode_t mode)
 {
 	struct inode *inode;
 	struct nilfs_transaction_info ti;
@@ -231,7 +231,7 @@ static struct dentry *nilfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 
 	inc_nlink(dir);
 
-	inode = nilfs_new_inode(dir, S_IFDIR | mode);
+	inode = nilfs_new_inode(dir, mode);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
 		goto out_dir;
diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c
index aee7aabaf059..0de5b63ef407 100644
--- a/fs/ntfs/namei.c
+++ b/fs/ntfs/namei.c
@@ -737,7 +737,7 @@ err_out:
 }
 
 static int ntfs_create(struct mnt_idmap *idmap, struct inode *dir,
-		struct dentry *dentry, umode_t mode, bool excl)
+		struct dentry *dentry, umode_t mode)
 {
 	struct ntfs_volume *vol = NTFS_SB(dir->i_sb);
 	struct ntfs_inode *ni;
@@ -1083,7 +1083,7 @@ static struct dentry *ntfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	if (!(vol->vol_flags & VOLUME_IS_DIRTY))
 		ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY);
 
-	ni = __ntfs_create(idmap, dir, uname, uname_len, S_IFDIR | mode, 0, NULL, 0);
+	ni = __ntfs_create(idmap, dir, uname, uname_len, mode, 0, NULL, 0);
 	kmem_cache_free(ntfs_name_cache, uname);
 	if (IS_ERR(ni)) {
 		err = PTR_ERR(ni);
diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c
index 937d349e841d..7bf889a4ca35 100644
--- a/fs/ntfs3/namei.c
+++ b/fs/ntfs3/namei.c
@@ -110,7 +110,7 @@ static struct dentry *ntfs_lookup(struct inode *dir, struct dentry *dentry,
  * ntfs_create - inode_operations::create
  */
 static int ntfs_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *dentry, umode_t mode, bool excl)
+		       struct dentry *dentry, umode_t mode)
 {
 	return ntfs_create_inode(idmap, dir, dentry, NULL, S_IFREG | mode, 0,
 				 NULL, 0, NULL);
@@ -218,7 +218,7 @@ static struct dentry *ntfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 				 struct dentry *dentry, umode_t mode)
 {
 	return ERR_PTR(ntfs_create_inode(idmap, dir, dentry, NULL,
-					 S_IFDIR | mode, 0, NULL, 0, NULL));
+					 mode, 0, NULL, 0, NULL));
 }
 
 /*
diff --git a/fs/nullfs.c b/fs/nullfs.c
index fdbd3e5d3d71..e06352c7b2cc 100644
--- a/fs/nullfs.c
+++ b/fs/nullfs.c
@@ -4,6 +4,8 @@
 #include <linux/fs_context.h>
 #include <linux/magic.h>
 
+#include "mount.h"
+
 static const struct super_operations nullfs_super_operations = {
 	.statfs	= simple_statfs,
 };
@@ -40,14 +42,9 @@ static int nullfs_fs_fill_super(struct super_block *s, struct fs_context *fc)
 	return 0;
 }
 
-/*
- * For now this is a single global instance. If needed we can make it
- * mountable by userspace at which point we will need to make it
- * multi-instance.
- */
 static int nullfs_fs_get_tree(struct fs_context *fc)
 {
-	return get_tree_single(fc, nullfs_fs_fill_super);
+	return get_tree_nodev(fc, nullfs_fs_fill_super);
 }
 
 static const struct fs_context_operations nullfs_fs_context_ops = {
@@ -57,9 +54,8 @@ static const struct fs_context_operations nullfs_fs_context_ops = {
 static int nullfs_init_fs_context(struct fs_context *fc)
 {
 	fc->ops		= &nullfs_fs_context_ops;
-	fc->global	= true;
-	fc->sb_flags	= SB_NOUSER;
-	fc->s_iflags	= SB_I_NOEXEC | SB_I_NODEV;
+	fc->sb_flags	|= SB_NOUSER;
+	fc->s_iflags	|= SB_I_NOEXEC | SB_I_NODEV;
 	return 0;
 }
 
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 5821e33df78f..53df5dd10ad0 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -422,7 +422,7 @@ static struct dentry *dlmfs_mkdir(struct mnt_idmap * idmap,
 		goto bail;
 	}
 
-	inode = dlmfs_get_inode(dir, dentry, mode | S_IFDIR);
+	inode = dlmfs_get_inode(dir, dentry, mode);
 	if (!inode) {
 		status = -ENOMEM;
 		mlog_errno(status);
@@ -453,8 +453,7 @@ bail:
 static int dlmfs_create(struct mnt_idmap *idmap,
 			struct inode *dir,
 			struct dentry *dentry,
-			umode_t mode,
-			bool excl)
+			umode_t mode)
 {
 	int status = 0;
 	struct inode *inode;
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 1277666c77cd..b23dd678a7e0 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -657,7 +657,7 @@ static struct dentry *ocfs2_mkdir(struct mnt_idmap *idmap,
 
 	trace_ocfs2_mkdir(dir, dentry, dentry->d_name.len, dentry->d_name.name,
 			  OCFS2_I(dir)->ip_blkno, mode);
-	ret = ocfs2_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFDIR, 0);
+	ret = ocfs2_mknod(&nop_mnt_idmap, dir, dentry, mode, 0);
 	if (ret)
 		mlog_errno(ret);
 
@@ -667,8 +667,7 @@ static struct dentry *ocfs2_mkdir(struct mnt_idmap *idmap,
 static int ocfs2_create(struct mnt_idmap *idmap,
 			struct inode *dir,
 			struct dentry *dentry,
-			umode_t mode,
-			bool excl)
+			umode_t mode)
 {
 	int ret;
 
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index bcac614ff02a..c62e389d4dd6 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1882,7 +1882,6 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 
 	ocfs2_delete_osb(osb);
 	kfree(osb);
-	sb->s_dev = 0;
 	sb->s_fs_info = NULL;
 }
 
diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c
index 2ed541fccf33..692297cf84e7 100644
--- a/fs/omfs/dir.c
+++ b/fs/omfs/dir.c
@@ -282,11 +282,11 @@ out_free_inode:
 static struct dentry *omfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 				 struct dentry *dentry, umode_t mode)
 {
-	return ERR_PTR(omfs_add_node(dir, dentry, mode | S_IFDIR));
+	return ERR_PTR(omfs_add_node(dir, dentry, mode));
 }
 
 static int omfs_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *dentry, umode_t mode, bool excl)
+		       struct dentry *dentry, umode_t mode)
 {
 	return omfs_add_node(dir, dentry, mode | S_IFREG);
 }
diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c
index 75e65e72c2d6..8ebc34e112d5 100644
--- a/fs/orangefs/namei.c
+++ b/fs/orangefs/namei.c
@@ -18,8 +18,7 @@
 static int orangefs_create(struct mnt_idmap *idmap,
 			struct inode *dir,
 			struct dentry *dentry,
-			umode_t mode,
-			bool exclusive)
+			umode_t mode)
 {
 	struct orangefs_inode_s *parent = ORANGEFS_I(dir);
 	struct orangefs_kernel_op_s *new_op;
@@ -333,7 +332,7 @@ static struct dentry *orangefs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 
 	ref = new_op->downcall.resp.mkdir.refn;
 
-	inode = orangefs_new_inode(dir->i_sb, dir, S_IFDIR | mode, 0, &ref);
+	inode = orangefs_new_inode(dir->i_sb, dir, mode, 0, &ref);
 	if (IS_ERR(inode)) {
 		gossip_err("*** Failed to allocate orangefs dir inode\n");
 		ret = PTR_ERR(inode);
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index a033743dbf51..610c0116252c 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -689,8 +689,8 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
 	return err;
 }
 
-static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev,
-			     const char *link)
+static int ovl_create_object(struct mnt_idmap *idmap, struct dentry *dentry,
+			     int mode, dev_t rdev, const char *link)
 {
 	int err;
 	struct inode *inode;
@@ -717,7 +717,7 @@ static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev,
 	inode_state_set(inode, I_CREATING);
 	spin_unlock(&inode->i_lock);
 
-	inode_init_owner(&nop_mnt_idmap, inode, dentry->d_parent->d_inode, mode);
+	inode_init_owner(idmap, inode, dentry->d_parent->d_inode, mode);
 	attr.mode = inode->i_mode;
 
 	err = ovl_create_or_link(dentry, inode, &attr, false);
@@ -732,15 +732,15 @@ out:
 }
 
 static int ovl_create(struct mnt_idmap *idmap, struct inode *dir,
-		      struct dentry *dentry, umode_t mode, bool excl)
+		      struct dentry *dentry, umode_t mode)
 {
-	return ovl_create_object(dentry, (mode & 07777) | S_IFREG, 0, NULL);
+	return ovl_create_object(idmap, dentry, (mode & 07777) | S_IFREG, 0, NULL);
 }
 
 static struct dentry *ovl_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 				struct dentry *dentry, umode_t mode)
 {
-	return ERR_PTR(ovl_create_object(dentry, (mode & 07777) | S_IFDIR, 0, NULL));
+	return ERR_PTR(ovl_create_object(idmap, dentry, (mode & 07777) | S_IFDIR, 0, NULL));
 }
 
 static int ovl_mknod(struct mnt_idmap *idmap, struct inode *dir,
@@ -750,13 +750,13 @@ static int ovl_mknod(struct mnt_idmap *idmap, struct inode *dir,
 	if (S_ISCHR(mode) && rdev == WHITEOUT_DEV)
 		return -EPERM;
 
-	return ovl_create_object(dentry, mode, rdev, NULL);
+	return ovl_create_object(idmap, dentry, mode, rdev, NULL);
 }
 
 static int ovl_symlink(struct mnt_idmap *idmap, struct inode *dir,
 		       struct dentry *dentry, const char *link)
 {
-	return ovl_create_object(dentry, S_IFLNK, 0, link);
+	return ovl_create_object(idmap, dentry, S_IFLNK, 0, link);
 }
 
 static int ovl_set_link_redirect(struct dentry *dentry)
@@ -1444,7 +1444,7 @@ static int ovl_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
 	if (!inode)
 		goto drop_write;
 
-	inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
+	inode_init_owner(idmap, inode, dir, mode);
 	err = ovl_create_tmpfile(file, dentry, inode, inode->i_mode);
 	if (err)
 		goto put_inode;
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index bc71231cad53..401cb8c75520 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -26,10 +26,18 @@ int ovl_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	bool full_copy_up = false;
 	struct dentry *upperdentry;
 
-	err = setattr_prepare(&nop_mnt_idmap, dentry, attr);
+	err = setattr_prepare(idmap, dentry, attr);
 	if (err)
 		return err;
 
+	/* Rebase ownership from the mount idmap into overlay id space. */
+	if (attr->ia_valid & ATTR_UID)
+		attr->ia_vfsuid = VFSUIDT_INIT(from_vfsuid(idmap,
+				i_user_ns(d_inode(dentry)), attr->ia_vfsuid));
+	if (attr->ia_valid & ATTR_GID)
+		attr->ia_vfsgid = VFSGIDT_INIT(from_vfsgid(idmap,
+				i_user_ns(d_inode(dentry)), attr->ia_vfsgid));
+
 	if (attr->ia_valid & ATTR_SIZE) {
 		/* Truncate should trigger data copy up as well */
 		full_copy_up = true;
@@ -172,6 +180,8 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path,
 	int fsid = 0;
 	int err;
 	bool metacopy_blocks = false;
+	vfsuid_t vfsuid;
+	vfsgid_t vfsgid;
 
 	metacopy_blocks = ovl_is_metacopy_dentry(dentry);
 
@@ -284,6 +294,12 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path,
 	if (!is_dir && ovl_test_flag(OVL_INDEX, d_inode(dentry)))
 		stat->nlink = dentry->d_inode->i_nlink;
 
+	/* Map ownership of the real inode through the overlay mount idmap. */
+	vfsuid = make_vfsuid(idmap, i_user_ns(inode), stat->uid);
+	vfsgid = make_vfsgid(idmap, i_user_ns(inode), stat->gid);
+	stat->uid = vfsuid_into_kuid(vfsuid);
+	stat->gid = vfsgid_into_kgid(vfsgid);
+
 	return err;
 }
 
@@ -306,7 +322,7 @@ int ovl_permission(struct mnt_idmap *idmap,
 	 * Check overlay inode with the creds of task and underlying inode
 	 * with creds of mounter
 	 */
-	err = generic_permission(&nop_mnt_idmap, inode, mask);
+	err = generic_permission(idmap, inode, mask);
 	if (err)
 		return err;
 
@@ -534,7 +550,7 @@ int ovl_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 		return -EOPNOTSUPP;
 	if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
 		return acl ? -EACCES : 0;
-	if (!inode_owner_or_capable(&nop_mnt_idmap, inode))
+	if (!inode_owner_or_capable(idmap, inode))
 		return -EPERM;
 
 	/*
@@ -542,8 +558,8 @@ int ovl_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 	 * be done with mounter's capabilities and so that won't do it for us).
 	 */
 	if (unlikely(inode->i_mode & S_ISGID) && type == ACL_TYPE_ACCESS &&
-	    !in_group_p(inode->i_gid) &&
-	    !capable_wrt_inode_uidgid(&nop_mnt_idmap, inode, CAP_FSETID)) {
+	    !in_group_or_capable(idmap, inode,
+				 i_gid_into_vfsgid(idmap, inode))) {
 		struct iattr iattr = { .ia_valid = ATTR_KILL_SGID };
 
 		err = ovl_setattr(&nop_mnt_idmap, dentry, &iattr);
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index b75df37f70ac..e0d8c6152e9f 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -320,6 +320,7 @@ static inline int ovl_do_setxattr(struct ovl_fs *ofs, struct dentry *dentry,
 				  const char *name, const void *value,
 				  size_t size, int flags)
 {
+	/* Use vfs_setxattr(), not __vfs_setxattr(): it idmaps the security.capability rootid. */
 	int err = vfs_setxattr(ovl_upper_mnt_idmap(ofs), dentry, name,
 			       value, size, flags);
 
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 60f0b7ceef0a..f2889cf9bc07 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1573,7 +1573,7 @@ struct file_system_type ovl_fs_type = {
 	.name			= "overlay",
 	.init_fs_context	= ovl_init_fs_context,
 	.parameters		= ovl_parameter_spec,
-	.fs_flags		= FS_USERNS_MOUNT,
+	.fs_flags		= FS_USERNS_MOUNT | FS_ALLOW_IDMAP,
 	.kill_sb		= kill_anon_super,
 };
 MODULE_ALIAS_FS("overlay");
diff --git a/fs/overlayfs/xattrs.c b/fs/overlayfs/xattrs.c
index 859e80ae6f40..5ae44b9c8790 100644
--- a/fs/overlayfs/xattrs.c
+++ b/fs/overlayfs/xattrs.c
@@ -84,6 +84,7 @@ static int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char
 	struct path realpath;
 
 	ovl_i_path_real(inode, &realpath);
+	/* Use vfs_getxattr(), not __vfs_getxattr(): it idmaps the security.capability rootid. */
 	with_ovl_creds(dentry->d_sb)
 		return vfs_getxattr(mnt_idmap(realpath.mnt), realpath.dentry, name, value, size);
 }
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 3dc62c1c2708..18b302f94174 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -747,8 +747,6 @@ static int posix_acl_fix_xattr_common(const void *value, size_t size)
 	count = posix_acl_xattr_count(size);
 	if (count < 0)
 		return -EINVAL;
-	if (count == 0)
-		return 0;
 
 	return count;
 }
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 479ea8cb4ef4..f6f75d206762 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -168,8 +168,8 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 	cred = get_task_cred(p);
 
 	task_lock(p);
-	if (p->fs)
-		umask = p->fs->umask;
+	if (p->real_fs)
+		umask = p->real_fs->umask;
 	if (p->files)
 		max_fds = files_fdtable(p->files)->max_fds;
 	task_unlock(p);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 780f81259052..6a39de424f62 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -211,8 +211,8 @@ static int get_task_root(struct task_struct *task, struct path *root)
 	int result = -ENOENT;
 
 	task_lock(task);
-	if (task->fs) {
-		get_fs_root(task->fs, root);
+	if (task->real_fs) {
+		get_fs_root(task->real_fs, root);
 		result = 0;
 	}
 	task_unlock(task);
@@ -225,8 +225,8 @@ static int proc_cwd_link(struct dentry *dentry, struct path *path,
 	int result = -ENOENT;
 
 	task_lock(task);
-	if (task->fs) {
-		get_fs_pwd(task->fs, path);
+	if (task->real_fs) {
+		get_fs_pwd(task->real_fs, path);
 		result = 0;
 	}
 	task_unlock(task);
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index 5c555db68aa2..036356c0a55b 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -254,13 +254,13 @@ static int mounts_open_common(struct inode *inode, struct file *file,
 	}
 	ns = nsp->mnt_ns;
 	get_mnt_ns(ns);
-	if (!task->fs) {
+	if (!task->real_fs) {
 		task_unlock(task);
 		put_task_struct(task);
 		ret = -ENOENT;
 		goto err_put_ns;
 	}
-	get_fs_root(task->fs, &root);
+	get_fs_root(task->real_fs, &root);
 	task_unlock(task);
 	put_task_struct(task);
 
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index 3987639ed132..0a88ede48e0a 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -121,14 +121,14 @@ out:
 static struct dentry *ramfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 				 struct dentry *dentry, umode_t mode)
 {
-	int retval = ramfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFDIR, 0);
+	int retval = ramfs_mknod(&nop_mnt_idmap, dir, dentry, mode, 0);
 	if (!retval)
 		inc_nlink(dir);
 	return ERR_PTR(retval);
 }
 
 static int ramfs_create(struct mnt_idmap *idmap, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool excl)
+			struct dentry *dentry, umode_t mode)
 {
 	return ramfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFREG, 0);
 }
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index ac55193bf398..7f783d6173e8 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -240,6 +240,8 @@ static struct dentry *romfs_lookup(struct inode *dir, struct dentry *dentry,
 			if ((be32_to_cpu(ri.next) & ROMFH_TYPE) == ROMFH_HRD)
 				offset = be32_to_cpu(ri.spec) & ROMFH_MASK;
 			inode = romfs_iget(dir->i_sb, offset);
+			if (IS_ERR(inode))
+				return ERR_CAST(inode);
 			break;
 		}
 
@@ -262,6 +264,8 @@ static const struct inode_operations romfs_dir_inode_operations = {
 	.lookup		= romfs_lookup,
 };
 
+#define ROMFS_MAX_HARDLINK_DEPTH 64
+
 /*
  * get a romfs inode based on its position in the image (which doubles as the
  * inode number)
@@ -273,6 +277,7 @@ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos)
 	struct inode *i;
 	unsigned long nlen;
 	unsigned nextfh;
+	unsigned int depth = 0;
 	int ret;
 	umode_t mode;
 
@@ -289,6 +294,9 @@ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos)
 		if ((nextfh & ROMFH_TYPE) != ROMFH_HRD)
 			break;
 
+		if (++depth > ROMFS_MAX_HARDLINK_DEPTH)
+			return ERR_PTR(-ELOOP);
+
 		pos = be32_to_cpu(ri.spec) & ROMFH_MASK;
 	}
 
@@ -587,7 +595,7 @@ static void romfs_kill_sb(struct super_block *sb)
 #ifdef CONFIG_ROMFS_ON_BLOCK
 	if (sb->s_bdev) {
 		sync_blockdev(sb->s_bdev);
-		bdev_fput(sb->s_bdev_file);
+		fs_bdev_file_release(sb->s_bdev_file, sb);
 	}
 #endif
 }
diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h
index 854e672a4e37..287c632392c4 100644
--- a/fs/smb/client/cifsfs.h
+++ b/fs/smb/client/cifsfs.h
@@ -54,7 +54,7 @@ void cifs_sb_deactive(struct super_block *sb);
 extern const struct inode_operations cifs_dir_inode_ops;
 struct inode *cifs_root_iget(struct super_block *sb);
 int cifs_create(struct mnt_idmap *idmap, struct inode *dir,
-		struct dentry *direntry, umode_t mode, bool excl);
+		struct dentry *direntry, umode_t mode);
 int cifs_atomic_open(struct inode *dir, struct dentry *direntry,
 		     struct file *file, unsigned int oflags, umode_t mode);
 int cifs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c
index 88a4a1787ff0..7803bd5bd01f 100644
--- a/fs/smb/client/dir.c
+++ b/fs/smb/client/dir.c
@@ -645,7 +645,7 @@ out_free_xid:
  * hashed-positive by calling d_instantiate().
  */
 int cifs_create(struct mnt_idmap *idmap, struct inode *dir,
-		struct dentry *direntry, umode_t mode, bool excl)
+		struct dentry *direntry, umode_t mode)
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(dir);
 	int rc;
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index b2806371bfde..dc64474d16f6 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -2287,6 +2287,13 @@ struct dentry *cifs_mkdir(struct mnt_idmap *idmap, struct inode *inode,
 	const char *full_path;
 	void *page;
 
+	/*
+	 * vfs_mkdir() now passes S_IFDIR in @mode, but @mode is forwarded
+	 * verbatim to the server and in the past only contained permission
+	 * bits. Strip the type bit until SMB is verified to deal with it.
+	 */
+	mode &= ~S_IFDIR;
+
 	cifs_dbg(FYI, "In cifs_mkdir, mode = %04ho inode = 0x%p\n",
 		 mode, inode);
 
diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c
index 6f97f8d39657..e00aee155935 100644
--- a/fs/smb/server/mgmt/share_config.c
+++ b/fs/smb/server/mgmt/share_config.c
@@ -9,6 +9,7 @@
 #include <linux/rwsem.h>
 #include <linux/parser.h>
 #include <linux/namei.h>
+#include <linux/fs_struct.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
 
@@ -193,7 +194,8 @@ static struct ksmbd_share_config *share_config_request(struct ksmbd_work *work,
 				goto out;
 			}
 
-			ret = kern_path(share->path, 0, &share->vfs_path);
+			scoped_with_init_fs()
+				ret = kern_path(share->path, 0, &share->vfs_path);
 			ksmbd_revert_fsids(work);
 			if (ret) {
 				ksmbd_debug(SMB, "failed to access '%s'\n",
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index add6194cd565..0caf1598aae7 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -9,6 +9,7 @@
 #include <net/addrconf.h>
 #include <linux/syscalls.h>
 #include <linux/namei.h>
+#include <linux/fs_struct.h>
 #include <linux/statfs.h>
 #include <linux/ethtool.h>
 #include <linux/falloc.h>
@@ -6057,7 +6058,8 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
 	if (!share->path)
 		return -EIO;
 
-	rc = kern_path(share->path, LOOKUP_NO_SYMLINKS, &path);
+	scoped_with_init_fs()
+		rc = kern_path(share->path, LOOKUP_NO_SYMLINKS, &path);
 	if (rc) {
 		pr_err("cannot create vfs path\n");
 		return -EIO;
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index 6600c2f5a404..2f111b1923d7 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -7,6 +7,7 @@
 #include <crypto/sha2.h>
 #include <linux/kernel.h>
 #include <linux/fs.h>
+#include <linux/fs_struct.h>
 #include <linux/filelock.h>
 #include <linux/uaccess.h>
 #include <linux/backing-dev.h>
@@ -67,8 +68,9 @@ static int ksmbd_vfs_path_lookup(struct ksmbd_share_config *share_conf,
 	}
 
 	CLASS(filename_kernel, filename)(pathname);
-	err = vfs_path_parent_lookup(filename, flags, path, &last,
-				     root_share_path);
+	scoped_with_init_fs()
+		err = vfs_path_parent_lookup(filename, flags, path, &last,
+					     root_share_path);
 	if (err)
 		return err;
 
@@ -621,7 +623,8 @@ int ksmbd_vfs_link(struct ksmbd_work *work, const char *oldname,
 	if (ksmbd_override_fsids(work))
 		return -ENOMEM;
 
-	err = kern_path(oldname, LOOKUP_NO_SYMLINKS, &oldpath);
+	scoped_with_init_fs()
+		err = kern_path(oldname, LOOKUP_NO_SYMLINKS, &oldpath);
 	if (err) {
 		pr_err("cannot get linux path for %s, err = %d\n",
 		       oldname, err);
diff --git a/fs/super.c b/fs/super.c
index ffdcc6a2e0de..5feecf5d9038 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -24,6 +24,8 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/blkdev.h>
+#include <linux/memcontrol.h>
+#include <linux/rhashtable.h>
 #include <linux/mount.h>
 #include <linux/security.h>
 #include <linux/writeback.h>		/* for the emergency remount stuff */
@@ -102,7 +104,7 @@ static bool super_flags(const struct super_block *sb, unsigned int flags)
  * creation will succeed and SB_BORN is set by vfs_get_tree() or we're
  * woken and we'll see SB_DYING.
  *
- * The caller must have acquired a temporary reference on @sb->s_count.
+ * The caller must have acquired a temporary reference on @sb->s_passive.
  *
  * Return: The function returns true if SB_BORN was set and with
  *         s_umount held. The function returns false if SB_DYING was
@@ -170,6 +172,19 @@ static void super_wake(struct super_block *sb, unsigned int flag)
 }
 
 /*
+ * The s_op->nr_cached_objects hooks (used for example by btrfs and xfs)
+ * operate on filesystem-global state and ignore sc->memcg. Driving them
+ * from per-memcg shrink_slab_memcg() invocations only burns CPU walking
+ * per-cpu counters and queueing duplicate work: the actual reclaim happens on
+ * the global path (kswapd or root direct reclaim) regardless. Restrict them
+ * to that path.
+ */
+static inline bool super_fs_objects_eligible(struct shrink_control *sc)
+{
+	return !sc->memcg || mem_cgroup_is_root(sc->memcg);
+}
+
+/*
  * One thing we have to be careful of with a per-sb shrinker is that we don't
  * drop the last active reference to the superblock from within the shrinker.
  * If that happens we could trigger unregistering the shrinker from within the
@@ -198,7 +213,7 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
 	if (!super_trylock_shared(sb))
 		return SHRINK_STOP;
 
-	if (sb->s_op->nr_cached_objects)
+	if (sb->s_op->nr_cached_objects && super_fs_objects_eligible(sc))
 		fs_objects = sb->s_op->nr_cached_objects(sb, sc);
 
 	inodes = list_lru_shrink_count(&sb->s_inode_lru, sc);
@@ -259,7 +274,8 @@ static unsigned long super_cache_count(struct shrinker *shrink,
 		return 0;
 	smp_rmb();
 
-	if (sb->s_op && sb->s_op->nr_cached_objects)
+	if (sb->s_op && sb->s_op->nr_cached_objects &&
+	    super_fs_objects_eligible(sc))
 		total_objects = sb->s_op->nr_cached_objects(sb, sc);
 
 	total_objects += list_lru_shrink_count(&sb->s_dentry_lru, sc);
@@ -272,6 +288,8 @@ static unsigned long super_cache_count(struct shrinker *shrink,
 	return total_objects;
 }
 
+static struct super_dev *super_dev_alloc(dev_t dev, struct super_block *sb);
+
 static void destroy_super_work(struct work_struct *work)
 {
 	struct super_block *s = container_of(work, struct super_block,
@@ -279,6 +297,8 @@ static void destroy_super_work(struct work_struct *work)
 	fsnotify_sb_free(s);
 	security_sb_free(s);
 	put_user_ns(s->s_user_ns);
+	/* Only an unregistered entry is still owned by the superblock. */
+	kfree(s->s_super_dev);
 	kfree(s->s_subtype);
 	for (int i = 0; i < SB_FREEZE_LEVELS; i++)
 		percpu_free_rwsem(&s->s_writers.rw_sem[i]);
@@ -367,7 +387,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags,
 	spin_lock_init(&s->s_inode_wblist_lock);
 	fserror_mount(s);
 
-	s->s_count = 1;
+	refcount_set(&s->s_passive, 1);
 	atomic_set(&s->s_active, 1);
 	mutex_init(&s->s_vfs_rename_mutex);
 	lockdep_set_class(&s->s_vfs_rename_mutex, &type->s_vfs_rename_key);
@@ -392,6 +412,10 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags,
 		goto fail;
 	if (list_lru_init_memcg(&s->s_inode_lru, s->s_shrink))
 		goto fail;
+	s->s_super_dev = super_dev_alloc(0, s);
+	if (!s->s_super_dev)
+		goto fail;
+
 	s->s_min_writeback_pages = MIN_WRITEBACK_PAGES;
 	return s;
 
@@ -403,12 +427,17 @@ fail:
 /* Superblock refcounting  */
 
 /*
- * Drop a superblock's refcount.  The caller must hold sb_lock.
+ * Drop a superblock's passive reference.  Must be called WITHOUT sb_lock held;
+ * put_super() acquires sb_lock itself when the final reference is dropped.
  */
-static void __put_super(struct super_block *s)
+void put_super(struct super_block *s)
 {
-	if (!--s->s_count) {
+	if (refcount_dec_and_test(&s->s_passive)) {
+
+		spin_lock(&sb_lock);
 		list_del_init(&s->s_list);
+		spin_unlock(&sb_lock);
+
 		WARN_ON(s->s_dentry_lru.node);
 		WARN_ON(s->s_inode_lru.node);
 		WARN_ON(s->s_mounts);
@@ -416,18 +445,109 @@ static void __put_super(struct super_block *s)
 	}
 }
 
-/**
- *	put_super	-	drop a temporary reference to superblock
- *	@sb: superblock in question
- *
- *	Drops a temporary reference, frees superblock if there's no
- *	references left.
- */
-void put_super(struct super_block *sb)
+struct super_dev {
+	dev_t			sd_dev;
+	struct super_block	*sd_sb;
+	refcount_t		sd_ref;
+	struct rhlist_head	sd_node;
+	struct rcu_head		sd_rcu;
+};
+
+static struct rhltable super_dev_table;
+static const struct rhashtable_params super_dev_params = {
+	.key_len	= sizeof(dev_t),
+	.key_offset	= offsetof(struct super_dev, sd_dev),
+	.head_offset	= offsetof(struct super_dev, sd_node),
+};
+
+static struct super_dev *super_dev_alloc(dev_t dev, struct super_block *sb)
 {
-	spin_lock(&sb_lock);
-	__put_super(sb);
-	spin_unlock(&sb_lock);
+	struct super_dev *fsd;
+
+	fsd = kzalloc_obj(*fsd);
+	if (!fsd)
+		return NULL;
+	fsd->sd_dev = dev;
+	fsd->sd_sb = sb;
+	refcount_set(&fsd->sd_ref, 1);
+	return fsd;
+}
+
+static void super_dev_put(struct super_dev *fsd)
+{
+	/* Unlink only once unpinned, so a cursor never resumes from a removed node. */
+	if (fsd && refcount_dec_and_test(&fsd->sd_ref)) {
+		rhltable_remove(&super_dev_table, &fsd->sd_node, super_dev_params);
+		put_super(fsd->sd_sb);
+		kfree_rcu(fsd, sd_rcu);
+	}
+}
+
+void __init super_dev_init(void)
+{
+	if (rhltable_init(&super_dev_table, &super_dev_params))
+		panic("VFS: Cannot initialise super_dev_table\n");
+}
+
+static int super_dev_insert(struct super_dev *fsd)
+{
+	int err;
+
+	err = rhltable_insert(&super_dev_table, &fsd->sd_node, super_dev_params);
+	if (!err)
+		refcount_inc(&fsd->sd_sb->s_passive);
+	return err;
+}
+
+/* Register @sb under @sb->s_dev as the final fallible act of a set callback. */
+static int super_dev_register(struct super_block *sb)
+{
+	struct super_dev *fsd = sb->s_super_dev;
+	int err;
+
+	lockdep_assert_held(&sb_lock);
+	VFS_WARN_ON_ONCE(!sb->s_dev);
+	VFS_WARN_ON_ONCE(!fsd || fsd->sd_dev);
+
+	fsd->sd_dev = sb->s_dev;
+	err = super_dev_insert(fsd);
+	if (err)
+		fsd->sd_dev = 0;
+	return err;
+}
+
+static struct super_dev *super_dev_get(struct rhlist_head *pos)
+{
+	struct super_dev *sb_dev;
+
+	for (; pos; pos = rcu_dereference_all(pos->next)) {
+		sb_dev = container_of(pos, struct super_dev, sd_node);
+		if (refcount_inc_not_zero(&sb_dev->sd_ref))
+			return sb_dev;
+	}
+	return NULL;
+}
+
+static struct super_dev *super_dev_first(dev_t dev)
+{
+	struct super_dev *sb_dev;
+
+	rcu_read_lock();
+	sb_dev = super_dev_get(rhltable_lookup(&super_dev_table, &dev, super_dev_params));
+	rcu_read_unlock();
+	return sb_dev;
+}
+
+static struct super_dev *super_dev_next(struct super_dev *prev)
+{
+	struct super_dev *sb_dev;
+
+	rcu_read_lock();
+	sb_dev = super_dev_get(rcu_dereference_all(prev->sd_node.next));
+	rcu_read_unlock();
+
+	super_dev_put(prev);
+	return sb_dev;
 }
 
 static void kill_super_notify(struct super_block *sb)
@@ -449,6 +569,12 @@ static void kill_super_notify(struct super_block *sb)
 	hlist_del_init(&sb->s_instances);
 	spin_unlock(&sb_lock);
 
+	/* Drop sget_fc()'s claim; a never-registered entry stays with the sb. */
+	if (sb->s_super_dev->sd_dev) {
+		super_dev_put(sb->s_super_dev);
+		sb->s_super_dev = NULL;
+	}
+
 	/*
 	 * Let concurrent mounts know that this thing is really dead.
 	 * We don't need @sb->s_umount here as every concurrent caller
@@ -478,11 +604,7 @@ void deactivate_locked_super(struct super_block *s)
 
 		kill_super_notify(s);
 
-		/*
-		 * Since list_lru_destroy() may sleep, we cannot call it from
-		 * put_super(), where we hold the sb_lock. Therefore we destroy
-		 * the lru lists right now.
-		 */
+		/* list_lru_destroy() may sleep; put_super() callers may not. */
 		list_lru_destroy(&s->s_dentry_lru);
 		list_lru_destroy(&s->s_inode_lru);
 
@@ -529,7 +651,7 @@ static bool grab_super(struct super_block *sb)
 {
 	bool locked;
 
-	sb->s_count++;
+	refcount_inc(&sb->s_passive);
 	spin_unlock(&sb_lock);
 	locked = super_lock_excl(sb);
 	if (locked) {
@@ -556,7 +678,7 @@ static bool grab_super(struct super_block *sb)
  *	lock held in read mode in case of success. On successful return,
  *	the caller must drop the s_umount lock when done.
  *
- *	Note that unlike get_super() et.al. this one does *not* bump ->s_count.
+ *	Note that unlike get_super() et.al. this one does *not* bump ->s_passive.
  *	The reason why it's safe is that we are OK with doing trylock instead
  *	of down_read().  There's a couple of places that are OK with that, but
  *	it's very much not a general-purpose interface.
@@ -763,6 +885,7 @@ retry:
 	}
 	if (!s) {
 		spin_unlock(&sb_lock);
+
 		s = alloc_super(fc->fs_type, fc->sb_flags, user_ns);
 		if (!s)
 			return ERR_PTR(-ENOMEM);
@@ -772,11 +895,13 @@ retry:
 	s->s_fs_info = fc->s_fs_info;
 	err = set(s, fc);
 	if (err) {
+		VFS_WARN_ON_ONCE(s->s_super_dev->sd_dev);
 		s->s_fs_info = NULL;
 		spin_unlock(&sb_lock);
 		destroy_unused_super(s);
 		return ERR_PTR(err);
 	}
+	VFS_WARN_ON_ONCE(!s->s_super_dev->sd_dev);
 	fc->s_fs_info = NULL;
 	s->s_type = fc->fs_type;
 	s->s_iflags |= fc->s_iflags;
@@ -851,14 +976,17 @@ static void __iterate_supers(void (*f)(struct super_block *, void *), void *arg,
 	struct super_block *sb, *p = NULL;
 	bool excl = flags & SUPER_ITER_EXCL;
 
-	guard(spinlock)(&sb_lock);
+	spin_lock(&sb_lock);
 
 	for (sb = first_super(flags);
 	     !list_entry_is_head(sb, &super_blocks, s_list);
 	     sb = next_super(sb, flags)) {
 		if (super_flags(sb, SB_DYING))
 			continue;
-		sb->s_count++;
+
+		if (!refcount_inc_not_zero(&sb->s_passive))
+			continue;
+
 		spin_unlock(&sb_lock);
 
 		if (flags & SUPER_ITER_UNLOCKED) {
@@ -868,13 +996,14 @@ static void __iterate_supers(void (*f)(struct super_block *, void *), void *arg,
 			super_unlock(sb, excl);
 		}
 
-		spin_lock(&sb_lock);
 		if (p)
-			__put_super(p);
+			put_super(p);
 		p = sb;
+		spin_lock(&sb_lock);
 	}
+	spin_unlock(&sb_lock);
 	if (p)
-		__put_super(p);
+		put_super(p);
 }
 
 void iterate_supers(void (*f)(struct super_block *, void *), void *arg)
@@ -903,7 +1032,9 @@ void iterate_supers_type(struct file_system_type *type,
 		if (super_flags(sb, SB_DYING))
 			continue;
 
-		sb->s_count++;
+		if (!refcount_inc_not_zero(&sb->s_passive))
+			continue;
+
 		spin_unlock(&sb_lock);
 
 		locked = super_lock_shared(sb);
@@ -912,41 +1043,33 @@ void iterate_supers_type(struct file_system_type *type,
 			super_unlock_shared(sb);
 		}
 
-		spin_lock(&sb_lock);
 		if (p)
-			__put_super(p);
+			put_super(p);
 		p = sb;
+		spin_lock(&sb_lock);
 	}
-	if (p)
-		__put_super(p);
 	spin_unlock(&sb_lock);
+	if (p)
+		put_super(p);
 }
 
 EXPORT_SYMBOL(iterate_supers_type);
 
 struct super_block *user_get_super(dev_t dev, bool excl)
 {
-	struct super_block *sb;
+	struct super_dev *sb_dev;
 
-	spin_lock(&sb_lock);
-	list_for_each_entry(sb, &super_blocks, s_list) {
-		bool locked;
+	for (sb_dev = super_dev_first(dev); sb_dev; sb_dev = super_dev_next(sb_dev)) {
+		struct super_block *sb = sb_dev->sd_sb;
 
-		if (sb->s_dev != dev)
+		if (!super_lock(sb, excl))
 			continue;
 
-		sb->s_count++;
-		spin_unlock(&sb_lock);
-
-		locked = super_lock(sb, excl);
-		if (locked)
-			return sb;
-
-		spin_lock(&sb_lock);
-		__put_super(sb);
-		break;
+		/* The pinned entry holds a passive reference, take our own. */
+		refcount_inc(&sb->s_passive);
+		super_dev_put(sb_dev);
+		return sb;
 	}
-	spin_unlock(&sb_lock);
 	return NULL;
 }
 
@@ -1228,7 +1351,16 @@ EXPORT_SYMBOL(free_anon_bdev);
 
 int set_anon_super(struct super_block *s, void *data)
 {
-	return get_anon_bdev(&s->s_dev);
+	int error;
+
+	error = get_anon_bdev(&s->s_dev);
+	if (error)
+		return error;
+
+	error = super_dev_register(s);
+	if (error)
+		free_anon_bdev(s->s_dev);
+	return error;
 }
 EXPORT_SYMBOL(set_anon_super);
 
@@ -1314,7 +1446,7 @@ EXPORT_SYMBOL(get_tree_keyed);
 static int set_bdev_super(struct super_block *s, void *data)
 {
 	s->s_dev = *(dev_t *)data;
-	return 0;
+	return super_dev_register(s);
 }
 
 static int super_s_dev_set(struct super_block *s, struct fs_context *fc)
@@ -1356,197 +1488,313 @@ struct super_block *sget_dev(struct fs_context *fc, dev_t dev)
 EXPORT_SYMBOL(sget_dev);
 
 #ifdef CONFIG_BLOCK
-/*
- * Lock the superblock that is holder of the bdev. Returns the superblock
- * pointer if we successfully locked the superblock and it is alive. Otherwise
- * we return NULL and just unlock bdev->bd_holder_lock.
- *
- * The function must be called with bdev->bd_holder_lock and releases it.
- */
-static struct super_block *bdev_super_lock(struct block_device *bdev, bool excl)
-	__releases(&bdev->bd_holder_lock)
+static int fs_super_freeze(struct super_block *sb)
 {
-	struct super_block *sb = bdev->bd_holder;
-	bool locked;
-
-	lockdep_assert_held(&bdev->bd_holder_lock);
-	lockdep_assert_not_held(&sb->s_umount);
-	lockdep_assert_not_held(&bdev->bd_disk->open_mutex);
-
-	/* Make sure sb doesn't go away from under us */
-	spin_lock(&sb_lock);
-	sb->s_count++;
-	spin_unlock(&sb_lock);
-
-	mutex_unlock(&bdev->bd_holder_lock);
-
-	locked = super_lock(sb, excl);
-
-	/*
-	 * If the superblock wasn't already SB_DYING then we hold
-	 * s_umount and can safely drop our temporary reference.
-         */
-	put_super(sb);
-
-	if (!locked)
-		return NULL;
-
-	if (!sb->s_root || !(sb->s_flags & SB_ACTIVE)) {
-		super_unlock(sb, excl);
-		return NULL;
-	}
+	if (sb->s_op->freeze_super)
+		return sb->s_op->freeze_super(sb,
+				FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL);
+	return freeze_super(sb, FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL);
+}
 
-	return sb;
+static int fs_super_thaw(struct super_block *sb)
+{
+	if (sb->s_op->thaw_super)
+		return sb->s_op->thaw_super(sb,
+				FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL);
+	return thaw_super(sb, FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL);
 }
 
 static void fs_bdev_mark_dead(struct block_device *bdev, bool surprise)
 {
-	struct super_block *sb;
+	struct super_dev *sb_dev;
+	dev_t dev = bdev->bd_dev;
 
-	sb = bdev_super_lock(bdev, false);
-	if (!sb)
-		return;
+	mutex_unlock(&bdev->bd_holder_lock);
 
-	if (sb->s_op->remove_bdev) {
-		int ret;
+	for (sb_dev = super_dev_first(dev); sb_dev; sb_dev = super_dev_next(sb_dev)) {
+		struct super_block *sb = sb_dev->sd_sb;
 
-		ret = sb->s_op->remove_bdev(sb, bdev);
-		if (!ret) {
-			super_unlock_shared(sb);
-			return;
+		if (!super_lock_shared(sb))
+			continue;
+		if (sb->s_root && (sb->s_flags & SB_ACTIVE)) {
+			if (!sb->s_op->remove_bdev ||
+			    sb->s_op->remove_bdev(sb, bdev)) {
+				if (!surprise)
+					sync_filesystem(sb);
+				shrink_dcache_sb(sb);
+				evict_inodes(sb);
+				if (sb->s_op->shutdown)
+					sb->s_op->shutdown(sb);
+			}
 		}
-		/* Fallback to shutdown. */
+		super_unlock_shared(sb);
 	}
-
-	if (!surprise)
-		sync_filesystem(sb);
-	shrink_dcache_sb(sb);
-	evict_inodes(sb);
-	if (sb->s_op->shutdown)
-		sb->s_op->shutdown(sb);
-
-	super_unlock_shared(sb);
 }
 
 static void fs_bdev_sync(struct block_device *bdev)
 {
-	struct super_block *sb;
-
-	sb = bdev_super_lock(bdev, false);
-	if (!sb)
-		return;
+	struct super_dev *sb_dev;
+	dev_t dev = bdev->bd_dev;
 
-	sync_filesystem(sb);
-	super_unlock_shared(sb);
-}
+	mutex_unlock(&bdev->bd_holder_lock);
 
-static struct super_block *get_bdev_super(struct block_device *bdev)
-{
-	bool active = false;
-	struct super_block *sb;
+	for (sb_dev = super_dev_first(dev); sb_dev; sb_dev = super_dev_next(sb_dev)) {
+		struct super_block *sb = sb_dev->sd_sb;
 
-	sb = bdev_super_lock(bdev, true);
-	if (sb) {
-		active = atomic_inc_not_zero(&sb->s_active);
-		super_unlock_excl(sb);
+		if (!super_lock_shared(sb))
+			continue;
+		if (sb->s_root && (sb->s_flags & SB_ACTIVE))
+			sync_filesystem(sb);
+		super_unlock_shared(sb);
 	}
-	if (!active)
-		return NULL;
-	return sb;
 }
 
 /**
- * fs_bdev_freeze - freeze owning filesystem of block device
+ * fs_bdev_freeze - freeze every superblock using a block device
  * @bdev: block device
  *
- * Freeze the filesystem that owns this block device if it is still
- * active.
- *
- * A filesystem that owns multiple block devices may be frozen from each
- * block device and won't be unfrozen until all block devices are
- * unfrozen. Each block device can only freeze the filesystem once as we
- * nest freezes for block devices in the block layer.
+ * Freeze each live superblock using @bdev.  A superblock owning several block
+ * devices is frozen once per device and stays frozen until all are thawed; the
+ * block layer nests these freezes so the count stays balanced.
  *
- * Return: If the freeze was successful zero is returned. If the freeze
- *         failed a negative error code is returned.
+ * Return: 0, or the error from the one superblock on a single-fs device.  When
+ *         several superblocks share @bdev a per-superblock failure is swallowed
+ *         (see below), but a sync_blockdev() failure is always reported.
  */
 static int fs_bdev_freeze(struct block_device *bdev)
 {
-	struct super_block *sb;
-	int error = 0;
+	dev_t dev = bdev->bd_dev;
+	struct super_dev *sb_dev;
+	unsigned int count = 0;
+	int error = 0, err;
 
 	lockdep_assert_held(&bdev->bd_fsfreeze_mutex);
 
-	sb = get_bdev_super(bdev);
-	if (!sb)
-		return -EINVAL;
+	mutex_unlock(&bdev->bd_holder_lock);
 
-	if (sb->s_op->freeze_super)
-		error = sb->s_op->freeze_super(sb,
-				FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL);
-	else
-		error = freeze_super(sb,
-				FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL);
+	for (sb_dev = super_dev_first(dev); sb_dev; sb_dev = super_dev_next(sb_dev)) {
+		if (!get_active_super(sb_dev->sd_sb))
+			continue;
+		err = fs_super_freeze(sb_dev->sd_sb);
+		if (err && !error)
+			error = err;
+		deactivate_super(sb_dev->sd_sb);
+		count++;
+	}
+
+	/*
+	 * When several superblocks share the device, keep it frozen even if some
+	 * of them failed to freeze and swallow the error: rolling the rest back
+	 * via thaw_super() can fail too, so neither is a clear win. A single
+	 * filesystem (count == 1) still reports its error.
+	 */
+	if (error && count > 1)
+		error = 0;
 	if (!error)
 		error = sync_blockdev(bdev);
-	deactivate_super(sb);
 	return error;
 }
 
 /**
- * fs_bdev_thaw - thaw owning filesystem of block device
+ * fs_bdev_thaw - thaw every superblock using a block device
  * @bdev: block device
  *
- * Thaw the filesystem that owns this block device.
- *
- * A filesystem that owns multiple block devices may be frozen from each
- * block device and won't be unfrozen until all block devices are
- * unfrozen. Each block device can only freeze the filesystem once as we
- * nest freezes for block devices in the block layer.
+ * The counterpart to fs_bdev_freeze(): thaw each live superblock using @bdev.
+ * A zero return does not imply a superblock is fully unfrozen; it may have been
+ * frozen more than once (by the kernel or via another device).
  *
- * Return: If the thaw was successful zero is returned. If the thaw
- *         failed a negative error code is returned. If this function
- *         returns zero it doesn't mean that the filesystem is unfrozen
- *         as it may have been frozen multiple times (kernel may hold a
- *         freeze or might be frozen from other block devices).
+ * Return: 0, or the first error on a single-fs device; a shared device swallows
+ *         per-superblock errors, as fs_bdev_freeze() does.
  */
 static int fs_bdev_thaw(struct block_device *bdev)
 {
-	struct super_block *sb;
-	int error;
+	dev_t dev = bdev->bd_dev;
+	struct super_dev *sb_dev;
+	unsigned int count = 0;
+	int error = 0, err;
 
 	lockdep_assert_held(&bdev->bd_fsfreeze_mutex);
 
-	/*
-	 * The block device may have been frozen before it was claimed by a
-	 * filesystem. Concurrently another process might try to mount that
-	 * frozen block device and has temporarily claimed the block device for
-	 * that purpose causing a concurrent fs_bdev_thaw() to end up here. The
-	 * mounter is already about to abort mounting because they still saw an
-	 * elevanted bdev->bd_fsfreeze_count so get_bdev_super() will return
-	 * NULL in that case.
-	 */
-	sb = get_bdev_super(bdev);
-	if (!sb)
-		return -EINVAL;
+	mutex_unlock(&bdev->bd_holder_lock);
 
-	if (sb->s_op->thaw_super)
-		error = sb->s_op->thaw_super(sb,
-				FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL);
-	else
-		error = thaw_super(sb,
-				FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL);
-	deactivate_super(sb);
+	for (sb_dev = super_dev_first(dev); sb_dev; sb_dev = super_dev_next(sb_dev)) {
+		if (!get_active_super(sb_dev->sd_sb))
+			continue;
+		err = fs_super_thaw(sb_dev->sd_sb);
+		if (err && !error)
+			error = err;
+		deactivate_super(sb_dev->sd_sb);
+		count++;
+	}
+
+	/* Shared device: swallow per-superblock errors, like fs_bdev_freeze(). */
+	if (error && count > 1)
+		error = 0;
 	return error;
 }
 
-const struct blk_holder_ops fs_holder_ops = {
+static const struct blk_holder_ops fs_holder_ops = {
 	.mark_dead		= fs_bdev_mark_dead,
 	.sync			= fs_bdev_sync,
 	.freeze			= fs_bdev_freeze,
 	.thaw			= fs_bdev_thaw,
 };
-EXPORT_SYMBOL_GPL(fs_holder_ops);
+
+static struct super_dev *super_dev_lookup(dev_t dev, struct super_block *sb)
+{
+	struct super_dev *it;
+	struct rhlist_head *list, *pos;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious super_dev_lookup() usage");
+	VFS_WARN_ON_ONCE(!dev);
+	VFS_WARN_ON_ONCE(!sb);
+
+	list = rhltable_lookup(&super_dev_table, &dev, super_dev_params);
+	rhl_for_each_entry_rcu(it, pos, list, sd_node) {
+		if (it->sd_sb == sb)
+			return it;
+	}
+
+	return NULL;
+}
+
+static int fs_bdev_register(struct file *bdev_file, struct super_block *sb)
+{
+	struct super_dev *sb_dev __free(kfree) = NULL;
+	dev_t dev = file_bdev(bdev_file)->bd_dev;
+	int err;
+
+	scoped_guard(rcu) {
+		sb_dev = super_dev_lookup(dev, sb);
+		if (sb_dev && refcount_inc_not_zero(&sb_dev->sd_ref)) {
+			retain_and_null_ptr(sb_dev);
+			return 0;
+		}
+	}
+
+	sb_dev = super_dev_alloc(dev, sb);
+	if (!sb_dev)
+		return -ENOMEM;
+
+	err = super_dev_insert(sb_dev);
+	if (err)
+		return err;
+
+	/* Publish the entry before reading the count; pairs with bdev_freeze(). */
+	smp_mb();
+	if (atomic_read(&file_bdev(bdev_file)->bd_fsfreeze_count) > 0) {
+		err = -EBUSY;
+		super_dev_put(sb_dev);
+	}
+
+	retain_and_null_ptr(sb_dev);
+	return err;
+}
+
+/**
+ * fs_bdev_file_open_by_dev - claim a block device on behalf of a superblock
+ * @dev: block device number
+ * @mode: open mode
+ * @holder: block-layer exclusivity token (a superblock, or the file_system_type
+ *          when the device may be shared by several superblocks of that type)
+ * @sb: superblock to drive fs_holder_ops events for
+ *
+ * Open @dev with &fs_holder_ops and register that @sb uses it, so device
+ * removal/sync/freeze/thaw are propagated to @sb (and any other superblock
+ * sharing @dev).  Must be paired with fs_bdev_file_release().
+ *
+ * Return: an opened block-device file or an ERR_PTR().
+ */
+struct file *fs_bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
+				      struct super_block *sb)
+{
+	struct file *bdev_file;
+	int err;
+
+	bdev_file = bdev_file_open_by_dev(dev, mode, holder, &fs_holder_ops);
+	if (IS_ERR(bdev_file))
+		return bdev_file;
+
+	err = fs_bdev_register(bdev_file, sb);
+	if (err) {
+		bdev_fput(bdev_file);
+		return ERR_PTR(err);
+	}
+	return bdev_file;
+}
+EXPORT_SYMBOL_GPL(fs_bdev_file_open_by_dev);
+
+/**
+ * fs_bdev_file_open_by_path - claim a block device on behalf of a superblock
+ * @path: path to the block device
+ * @mode: open mode
+ * @holder: block-layer exclusivity token (a superblock, or the file_system_type
+ *          when the device may be shared by several superblocks of that type)
+ * @sb: superblock to drive fs_holder_ops events for
+ *
+ * Open the block device at @path with &fs_holder_ops and register that @sb
+ * uses it, so device removal/sync/freeze/thaw are propagated to @sb (and any
+ * other superblock sharing the device).  Must be paired with
+ * fs_bdev_file_release().
+ *
+ * Return: an opened block-device file or an ERR_PTR().
+ */
+struct file *fs_bdev_file_open_by_path(const char *path, blk_mode_t mode,
+				       void *holder, struct super_block *sb)
+{
+	struct file *bdev_file;
+	int err;
+
+	bdev_file = bdev_file_open_by_path(path, mode, holder, &fs_holder_ops);
+	if (IS_ERR(bdev_file))
+		return bdev_file;
+
+	err = fs_bdev_register(bdev_file, sb);
+	if (err) {
+		bdev_fput(bdev_file);
+		return ERR_PTR(err);
+	}
+	return bdev_file;
+}
+EXPORT_SYMBOL_GPL(fs_bdev_file_open_by_path);
+
+/**
+ * fs_bdev_unregister - drop a superblock's claim on a block device
+ * @bdev_file: file returned by fs_bdev_file_open_by_{dev,path}()
+ * @sb: superblock the device was claimed for
+ *
+ * The inverse of fs_bdev_register(): drop one claim on the {dev, @sb} entry
+ * (the last claim unregisters it; a pinning cursor defers the actual unlink)
+ * without closing the device.  A caller that must act on the still-open device
+ * between unregistering and closing - e.g. re-allow freezing one denied for a
+ * membership change - pairs this with bdev_fput().  fs_bdev_file_release() is
+ * the common unregister-and-close.
+ */
+void fs_bdev_unregister(struct file *bdev_file, struct super_block *sb)
+{
+	dev_t dev = file_bdev(bdev_file)->bd_dev;
+	struct super_dev *sb_dev;
+
+	rcu_read_lock();
+	sb_dev = super_dev_lookup(dev, sb);
+	rcu_read_unlock();
+	super_dev_put(sb_dev);
+}
+EXPORT_SYMBOL_GPL(fs_bdev_unregister);
+
+/**
+ * fs_bdev_file_release - release a block device claimed for a superblock
+ * @bdev_file: file returned by fs_bdev_file_open_by_{dev,path}()
+ * @sb: superblock the device was claimed for
+ *
+ * Unregister the {dev, @sb} entry, then close the block device.
+ */
+void fs_bdev_file_release(struct file *bdev_file, struct super_block *sb)
+{
+	fs_bdev_unregister(bdev_file, sb);
+	bdev_fput(bdev_file);
+}
+EXPORT_SYMBOL_GPL(fs_bdev_file_release);
 
 int setup_bdev_super(struct super_block *sb, int sb_flags,
 		struct fs_context *fc)
@@ -1555,7 +1803,7 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
 	struct file *bdev_file;
 	struct block_device *bdev;
 
-	bdev_file = bdev_file_open_by_dev(sb->s_dev, mode, sb, &fs_holder_ops);
+	bdev_file = fs_bdev_file_open_by_dev(sb->s_dev, mode, sb, sb);
 	if (IS_ERR(bdev_file)) {
 		if (fc)
 			errorf(fc, "%s: Can't open blockdev", fc->source);
@@ -1569,20 +1817,19 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
 	 * writable from userspace even for a read-only block device.
 	 */
 	if ((mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) {
-		bdev_fput(bdev_file);
+		fs_bdev_file_release(bdev_file, sb);
 		return -EACCES;
 	}
 
-	/*
-	 * It is enough to check bdev was not frozen before we set
-	 * s_bdev as freezing will wait until SB_BORN is set.
-	 */
+	/* The sget_fc() entry is already published; pairs with bdev_freeze(). */
+	smp_mb();
 	if (atomic_read(&bdev->bd_fsfreeze_count) > 0) {
 		if (fc)
 			warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev);
-		bdev_fput(bdev_file);
+		fs_bdev_file_release(bdev_file, sb);
 		return -EBUSY;
 	}
+
 	spin_lock(&sb_lock);
 	sb->s_bdev_file = bdev_file;
 	sb->s_bdev = bdev;
@@ -1671,7 +1918,7 @@ void kill_block_super(struct super_block *sb)
 	generic_shutdown_super(sb);
 	if (bdev) {
 		sync_blockdev(bdev);
-		bdev_fput(sb->s_bdev_file);
+		fs_bdev_file_release(sb->s_bdev_file, sb);
 	}
 }
 
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 86d41e077e4d..23ec924162d6 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -303,7 +303,7 @@ static int ubifs_prepare_create(struct inode *dir, struct dentry *dentry,
 }
 
 static int ubifs_create(struct mnt_idmap *idmap, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool excl)
+			struct dentry *dentry, umode_t mode)
 {
 	struct inode *inode;
 	struct ubifs_info *c = dir->i_sb->s_fs_info;
@@ -1031,7 +1031,7 @@ static struct dentry *ubifs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 
 	sz_change = CALC_DENT_SIZE(fname_len(&nm));
 
-	inode = ubifs_new_inode(c, dir, S_IFDIR | mode, false);
+	inode = ubifs_new_inode(c, dir, mode, false);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto out_fname;
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index 9a3b7cef3606..b90841ac0a40 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -371,7 +371,7 @@ static int udf_add_nondir(struct dentry *dentry, struct inode *inode)
 }
 
 static int udf_create(struct mnt_idmap *idmap, struct inode *dir,
-		      struct dentry *dentry, umode_t mode, bool excl)
+		      struct dentry *dentry, umode_t mode)
 {
 	struct inode *inode = udf_new_inode(dir, mode);
 
@@ -428,7 +428,7 @@ static struct dentry *udf_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	struct udf_inode_info *dinfo = UDF_I(dir);
 	struct udf_inode_info *iinfo;
 
-	inode = udf_new_inode(dir, S_IFDIR | mode);
+	inode = udf_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index 5b3c85c93242..6703f3bcf76f 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -70,8 +70,7 @@ static struct dentry *ufs_lookup(struct inode * dir, struct dentry *dentry, unsi
  * with d_instantiate(). 
  */
 static int ufs_create (struct mnt_idmap * idmap,
-		struct inode * dir, struct dentry * dentry, umode_t mode,
-		bool excl)
+		struct inode * dir, struct dentry * dentry, umode_t mode)
 {
 	struct inode *inode;
 
@@ -174,7 +173,7 @@ static struct dentry *ufs_mkdir(struct mnt_idmap * idmap, struct inode * dir,
 
 	inode_inc_link_count(dir);
 
-	inode = ufs_new_inode(dir, S_IFDIR|mode);
+	inode = ufs_new_inode(dir, mode);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
 		goto out_dir;
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index c4831a8b9b3f..6dcf6d048cce 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -672,7 +672,7 @@ void ufs_mark_sb_dirty(struct super_block *sb)
 	spin_lock(&sbi->work_lock);
 	if (!sbi->work_queued) {
 		delay = msecs_to_jiffies(dirty_writeback_interval * 10);
-		queue_delayed_work(system_long_wq, &sbi->sync_work, delay);
+		queue_delayed_work(system_dfl_long_wq, &sbi->sync_work, delay);
 		sbi->work_queued = 1;
 	}
 	spin_unlock(&sbi->work_lock);
diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c
index c5bd3271aa96..0b9eab157432 100644
--- a/fs/vboxsf/dir.c
+++ b/fs/vboxsf/dir.c
@@ -298,9 +298,9 @@ out:
 
 static int vboxsf_dir_mkfile(struct mnt_idmap *idmap,
 			     struct inode *parent, struct dentry *dentry,
-			     umode_t mode, bool excl)
+			     umode_t mode)
 {
-	return vboxsf_dir_create(parent, dentry, mode, false, excl, NULL);
+	return vboxsf_dir_create(parent, dentry, mode, false, true, NULL);
 }
 
 static struct dentry *vboxsf_dir_mkdir(struct mnt_idmap *idmap,
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 48d7dfd3e15f..21d67af781da 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1631,7 +1631,7 @@ xfs_free_buftarg(
 	fs_put_dax(btp->bt_daxdev, btp->bt_mount);
 	/* the main block device is closed by kill_block_super */
 	if (btp->bt_bdev != btp->bt_mount->m_super->s_bdev)
-		bdev_fput(btp->bt_file);
+		fs_bdev_file_release(btp->bt_file, btp->bt_mount->m_super);
 	kfree(btp);
 }
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 6339f4956ecb..4a3299abf774 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -293,8 +293,7 @@ xfs_vn_create(
 	struct mnt_idmap	*idmap,
 	struct inode		*dir,
 	struct dentry		*dentry,
-	umode_t			mode,
-	bool			flags)
+	umode_t			mode)
 {
 	return xfs_generic_create(idmap, dir, dentry, mode, 0, NULL);
 }
@@ -306,7 +305,7 @@ xfs_vn_mkdir(
 	struct dentry		*dentry,
 	umode_t			mode)
 {
-	return ERR_PTR(xfs_generic_create(idmap, dir, dentry, mode | S_IFDIR, 0, NULL));
+	return ERR_PTR(xfs_generic_create(idmap, dir, dentry, mode, 0, NULL));
 }
 
 STATIC struct dentry *
@@ -338,7 +337,7 @@ STATIC struct dentry *
 xfs_vn_ci_lookup(
 	struct inode	*dir,
 	struct dentry	*dentry,
-	unsigned int flags)
+	unsigned int	flags)
 {
 	struct xfs_inode *ip;
 	struct xfs_name	xname;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 63c4bcbe6c2b..4b2eeb7783f7 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -400,8 +400,8 @@ xfs_blkdev_get(
 	blk_mode_t		mode;
 
 	mode = sb_open_mode(mp->m_super->s_flags);
-	*bdev_filep = bdev_file_open_by_path(name, mode,
-			mp->m_super, &fs_holder_ops);
+	*bdev_filep = fs_bdev_file_open_by_path(name, mode,
+			mp->m_super, mp->m_super);
 	if (IS_ERR(*bdev_filep)) {
 		error = PTR_ERR(*bdev_filep);
 		*bdev_filep = NULL;
@@ -526,7 +526,7 @@ xfs_open_devices(
 		mp->m_logdev_targp = mp->m_ddev_targp;
 		/* Handle won't be used, drop it */
 		if (logdev_file)
-			bdev_fput(logdev_file);
+			fs_bdev_file_release(logdev_file, mp->m_super);
 	}
 
 	return 0;
@@ -541,10 +541,10 @@ xfs_open_devices(
 	mp->m_ddev_targp = NULL;
  out_close_rtdev:
 	 if (rtdev_file)
-		bdev_fput(rtdev_file);
+		fs_bdev_file_release(rtdev_file, mp->m_super);
  out_close_logdev:
 	if (logdev_file)
-		bdev_fput(logdev_file);
+		fs_bdev_file_release(logdev_file, mp->m_super);
 	return error;
 }