1 files changed, 372 insertions, 194 deletions

diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index f4718098ac31..8cb1a94339b8 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -1,10 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * binfmt_misc.c
  *
  * Copyright (C) 1997 Richard Günther
  *
  * binfmt_misc detects binaries via a magic or filename extension and invokes
- * a specified wrapper. See Documentation/binfmt_misc.txt for more details.
+ * a specified wrapper. See Documentation/admin-guide/binfmt-misc.rst for more details.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -22,6 +23,7 @@
 #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/uaccess.h>
@@ -38,14 +40,11 @@ enum {
 	VERBOSE_STATUS = 1 /* make it zero to save 400 bytes kernel memory */
 };
 
-static LIST_HEAD(entries);
-static int enabled = 1;
-
 enum {Enabled, Magic};
-#define MISC_FMT_PRESERVE_ARGV0 (1 << 31)
-#define MISC_FMT_OPEN_BINARY (1 << 30)
-#define MISC_FMT_CREDENTIALS (1 << 29)
-#define MISC_FMT_OPEN_FILE (1 << 28)
+#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)
 
 typedef struct {
 	struct list_head list;
@@ -54,16 +53,14 @@ typedef struct {
 	int size;			/* size of magic/mask */
 	char *magic;			/* magic or filename extension */
 	char *mask;			/* mask, NULL for exact match */
-	char *interpreter;		/* filename of interpreter */
+	const char *interpreter;	/* filename of interpreter */
 	char *name;
 	struct dentry *dentry;
 	struct file *interp_file;
+	refcount_t users;		/* sync removal with load_misc_binary() */
 } Node;
 
-static DEFINE_RWLOCK(entries_lock);
 static struct file_system_type bm_fs_type;
-static struct vfsmount *bm_mnt;
-static int entry_count;
 
 /*
  * Max length of the register string.  Determined by:
@@ -80,19 +77,24 @@ static int entry_count;
  */
 #define MAX_REGISTER_LENGTH 1920
 
-/*
- * Check if we support the binfmt
- * if we do, return the node, else NULL
- * locking is done in load_misc_binary
+/**
+ * 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.
+ *
+ * Return: binary type list entry on success, NULL on failure
  */
-static Node *check_file(struct linux_binprm *bprm)
+static Node *search_binfmt_handler(struct binfmt_misc *misc,
+				   struct linux_binprm *bprm)
 {
 	char *p = strrchr(bprm->interp, '.');
-	struct list_head *l;
+	Node *e;
 
 	/* Walk all the registered handlers. */
-	list_for_each(l, &entries) {
-		Node *e = list_entry(l, Node, list);
+	list_for_each_entry(e, &misc->entries, list) {
 		char *s;
 		int j;
 
@@ -121,9 +123,79 @@ static Node *check_file(struct linux_binprm *bprm)
 		if (j == e->size)
 			return e;
 	}
+
 	return NULL;
 }
 
+/**
+ * get_binfmt_handler - try to find a binary type handler
+ * @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().
+ *
+ * Return: binary type list entry on success, NULL on failure
+ */
+static Node *get_binfmt_handler(struct binfmt_misc *misc,
+				struct linux_binprm *bprm)
+{
+	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;
+}
+
+/**
+ * put_binfmt_handler - put binary handler node
+ * @e: node to put
+ *
+ * Free node 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)
+{
+	if (refcount_dec_and_test(&e->users)) {
+		if (e->flags & MISC_FMT_OPEN_FILE)
+			filp_close(e->interp_file, NULL);
+		kfree(e);
+	}
+}
+
+/**
+ * load_binfmt_misc - load the binfmt_misc 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.
+ *
+ * Return: the binfmt_misc instance of the caller's user namespace
+ */
+static struct binfmt_misc *load_binfmt_misc(void)
+{
+	const struct user_namespace *user_ns;
+	struct binfmt_misc *misc;
+
+	user_ns = current_user_ns();
+	while (user_ns) {
+		/* 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;
+}
+
 /*
  * the loader itself
  */
@@ -131,117 +203,78 @@ static int load_misc_binary(struct linux_binprm *bprm)
 {
 	Node *fmt;
 	struct file *interp_file = NULL;
-	char iname[BINPRM_BUF_SIZE];
-	const char *iname_addr = iname;
-	int retval;
-	int fd_binary = -1;
+	int retval = -ENOEXEC;
+	struct binfmt_misc *misc;
 
-	retval = -ENOEXEC;
-	if (!enabled)
-		goto ret;
+	misc = load_binfmt_misc();
+	if (!misc->enabled)
+		return retval;
 
-	/* to keep locking time low, we copy the interpreter string */
-	read_lock(&entries_lock);
-	fmt = check_file(bprm);
-	if (fmt)
-		strlcpy(iname, fmt->interpreter, BINPRM_BUF_SIZE);
-	read_unlock(&entries_lock);
+	fmt = get_binfmt_handler(misc, bprm);
 	if (!fmt)
-		goto ret;
+		return retval;
 
 	/* Need to be able to load the file after exec */
+	retval = -ENOENT;
 	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
-		return -ENOENT;
+		goto ret;
 
-	if (!(fmt->flags & MISC_FMT_PRESERVE_ARGV0)) {
+	if (fmt->flags & MISC_FMT_PRESERVE_ARGV0) {
+		bprm->interp_flags |= BINPRM_FLAGS_PRESERVE_ARGV0;
+	} else {
 		retval = remove_arg_zero(bprm);
 		if (retval)
 			goto ret;
 	}
 
-	if (fmt->flags & MISC_FMT_OPEN_BINARY) {
-
-		/* if the binary should be opened on behalf of the
-		 * interpreter than keep it open and assign descriptor
-		 * to it
-		 */
-		fd_binary = get_unused_fd_flags(0);
-		if (fd_binary < 0) {
-			retval = fd_binary;
-			goto ret;
-		}
-		fd_install(fd_binary, bprm->file);
-
-		/* if the binary is not readable than enforce mm->dumpable=0
-		   regardless of the interpreter's permissions */
-		would_dump(bprm, bprm->file);
-
-		allow_write_access(bprm->file);
-		bprm->file = NULL;
-
-		/* mark the bprm that fd should be passed to interp */
-		bprm->interp_flags |= BINPRM_FLAGS_EXECFD;
-		bprm->interp_data = fd_binary;
+	if (fmt->flags & MISC_FMT_OPEN_BINARY)
+		bprm->have_execfd = 1;
 
-	} else {
-		allow_write_access(bprm->file);
-		fput(bprm->file);
-		bprm->file = NULL;
-	}
 	/* make argv[1] be the path to the binary */
-	retval = copy_strings_kernel(1, &bprm->interp, bprm);
+	retval = copy_string_kernel(bprm->interp, bprm);
 	if (retval < 0)
-		goto error;
+		goto ret;
 	bprm->argc++;
 
 	/* add the interp as argv[0] */
-	retval = copy_strings_kernel(1, &iname_addr, bprm);
+	retval = copy_string_kernel(fmt->interpreter, bprm);
 	if (retval < 0)
-		goto error;
+		goto ret;
 	bprm->argc++;
 
 	/* Update interp in case binfmt_script needs it. */
-	retval = bprm_change_interp(iname, bprm);
+	retval = bprm_change_interp(fmt->interpreter, bprm);
 	if (retval < 0)
-		goto error;
+		goto ret;
 
-	if (fmt->flags & MISC_FMT_OPEN_FILE && fmt->interp_file) {
-		interp_file = filp_clone_open(fmt->interp_file);
+	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);
 	} else {
-		interp_file = open_exec(iname);
+		interp_file = open_exec(fmt->interpreter);
 	}
 	retval = PTR_ERR(interp_file);
 	if (IS_ERR(interp_file))
-		goto error;
+		goto ret;
 
-	bprm->file = interp_file;
-	if (fmt->flags & MISC_FMT_CREDENTIALS) {
-		/*
-		 * No need to call prepare_binprm(), it's already been
-		 * done.  bprm->buf is stale, update from interp_file.
-		 */
-		memset(bprm->buf, 0, BINPRM_BUF_SIZE);
-		retval = kernel_read(bprm->file, 0, bprm->buf, BINPRM_BUF_SIZE);
-	} else
-		retval = prepare_binprm(bprm);
+	bprm->interpreter = interp_file;
+	if (fmt->flags & MISC_FMT_CREDENTIALS)
+		bprm->execfd_creds = 1;
 
-	if (retval < 0)
-		goto error;
+	retval = 0;
+ret:
 
-	retval = search_binary_handler(bprm);
-	if (retval < 0)
-		goto error;
+	/*
+	 * 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);
 
-ret:
 	return retval;
-error:
-	if (fd_binary > 0)
-		sys_close(fd_binary);
-	bprm->interp_flags = 0;
-	bprm->interp_data = 0;
-	goto ret;
 }
 
 /* Command parsers */
@@ -329,7 +362,7 @@ static Node *create_entry(const char __user *buffer, size_t count)
 
 	err = -ENOMEM;
 	memsize = sizeof(Node) + count + 8;
-	e = kmalloc(memsize, GFP_KERNEL);
+	e = kmalloc(memsize, GFP_KERNEL_ACCOUNT);
 	if (!e)
 		goto out;
 
@@ -384,8 +417,13 @@ static Node *create_entry(const char __user *buffer, size_t count)
 		s = strchr(p, del);
 		if (!s)
 			goto einval;
-		*s++ = '\0';
-		e->offset = simple_strtoul(p, &p, 10);
+		*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);
@@ -425,7 +463,8 @@ static Node *create_entry(const char __user *buffer, size_t count)
 		if (e->mask &&
 		    string_unescape_inplace(e->mask, UNESCAPE_HEX) != e->size)
 			goto einval;
-		if (e->size + e->offset > BINPRM_BUF_SIZE)
+		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) {
@@ -435,7 +474,7 @@ static Node *create_entry(const char __user *buffer, size_t count)
 
 			if (e->mask) {
 				int i;
-				char *masked = kmalloc(e->size, GFP_KERNEL);
+				char *masked = kmalloc(e->size, GFP_KERNEL_ACCOUNT);
 
 				print_hex_dump_bytes(
 					KBUILD_MODNAME ": register:  mask[decoded]: ",
@@ -583,43 +622,78 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode)
 	if (inode) {
 		inode->i_ino = get_next_ino();
 		inode->i_mode = mode;
-		inode->i_atime = inode->i_mtime = inode->i_ctime =
-			current_time(inode);
+		simple_inode_init_ts(inode);
 	}
 	return inode;
 }
 
-static void bm_evict_inode(struct inode *inode)
+/**
+ * i_binfmt_misc - retrieve struct binfmt_misc from a binfmt_misc inode
+ * @inode: inode of the relevant binfmt_misc instance
+ *
+ * This helper retrieves struct binfmt_misc from a binfmt_misc inode. This can
+ * be done without any memory barriers because we are guaranteed that
+ * user_ns->binfmt_misc is fully initialized. It was fully initialized when the
+ * binfmt_misc mount was first created.
+ *
+ * Return: struct binfmt_misc of the relevant binfmt_misc instance
+ */
+static struct binfmt_misc *i_binfmt_misc(struct inode *inode)
 {
-	clear_inode(inode);
-	kfree(inode->i_private);
+	return inode->i_sb->s_user_ns->binfmt_misc;
 }
 
-static void kill_node(Node *e)
+/**
+ * bm_evict_inode - cleanup data associated with @inode
+ * @inode: inode to which the data is attached
+ *
+ * Cleanup the binary type handler data associated with @inode if a binary type
+ * 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.
+*/
+static void bm_evict_inode(struct inode *inode)
 {
-	struct dentry *dentry;
+	Node *e = inode->i_private;
 
-	write_lock(&entries_lock);
-	dentry = e->dentry;
-	if (dentry) {
-		list_del_init(&e->list);
-		e->dentry = NULL;
-	}
-	write_unlock(&entries_lock);
+	clear_inode(inode);
 
-	if ((e->flags & MISC_FMT_OPEN_FILE) && e->interp_file) {
-		filp_close(e->interp_file, NULL);
-		e->interp_file = NULL;
-	}
+	if (e) {
+		struct binfmt_misc *misc;
 
-	if (dentry) {
-		drop_nlink(d_inode(dentry));
-		d_drop(dentry);
-		dput(dentry);
-		simple_release_fs(&bm_mnt, &entry_count);
+		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);
+		put_binfmt_handler(e);
 	}
 }
 
+/**
+ * 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.
+ */
+static void remove_binfmt_handler(struct binfmt_misc *misc, Node *e)
+{
+	write_lock(&misc->entries_lock);
+	list_del_init(&e->list);
+	write_unlock(&misc->entries_lock);
+	locked_recursive_removal(e->dentry, NULL);
+}
+
 /* /<entry> */
 
 static ssize_t
@@ -644,8 +718,8 @@ bm_entry_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 static ssize_t bm_entry_write(struct file *file, const char __user *buffer,
 				size_t count, loff_t *ppos)
 {
-	struct dentry *root;
-	Node *e = file_inode(file)->i_private;
+	struct inode *inode = file_inode(file);
+	Node *e = inode->i_private;
 	int res = parse_command(buffer, count);
 
 	switch (res) {
@@ -659,12 +733,22 @@ static ssize_t bm_entry_write(struct file *file, const char __user *buffer,
 		break;
 	case 3:
 		/* Delete this handler. */
-		root = file_inode(file)->i_sb->s_root;
-		inode_lock(d_inode(root));
+		inode = d_inode(inode->i_sb->s_root);
+		inode_lock_nested(inode, I_MUTEX_PARENT);
 
-		kill_node(e);
+		/*
+		 * 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(d_inode(root));
+		inode_unlock(inode);
 		break;
 	default:
 		return res;
@@ -681,74 +765,74 @@ static const struct file_operations bm_entry_operations = {
 
 /* /register */
 
+/* add to filesystem */
+static int add_entry(Node *e, struct super_block *sb)
+{
+	struct dentry *dentry = simple_start_creating(sb->s_root, e->name);
+	struct inode *inode;
+	struct binfmt_misc *misc;
+
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	inode = bm_get_inode(sb, S_IFREG | 0644);
+	if (unlikely(!inode)) {
+		simple_done_creating(dentry);
+		return -ENOMEM;
+	}
+
+	refcount_set(&e->users, 1);
+	e->dentry = dentry;
+	inode->i_private = e;
+	inode->i_fop = &bm_entry_operations;
+
+	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);
+	simple_done_creating(dentry);
+	return 0;
+}
+
 static ssize_t bm_register_write(struct file *file, const char __user *buffer,
 			       size_t count, loff_t *ppos)
 {
 	Node *e;
-	struct inode *inode;
 	struct super_block *sb = file_inode(file)->i_sb;
-	struct dentry *root = sb->s_root, *dentry;
 	int err = 0;
+	struct file *f = NULL;
 
 	e = create_entry(buffer, count);
 
 	if (IS_ERR(e))
 		return PTR_ERR(e);
 
-	inode_lock(d_inode(root));
-	dentry = lookup_one_len(e->name, root, strlen(e->name));
-	err = PTR_ERR(dentry);
-	if (IS_ERR(dentry))
-		goto out;
-
-	err = -EEXIST;
-	if (d_really_is_positive(dentry))
-		goto out2;
-
-	inode = bm_get_inode(sb, S_IFREG | 0644);
-
-	err = -ENOMEM;
-	if (!inode)
-		goto out2;
-
-	err = simple_pin_fs(&bm_fs_type, &bm_mnt, &entry_count);
-	if (err) {
-		iput(inode);
-		inode = NULL;
-		goto out2;
-	}
-
 	if (e->flags & MISC_FMT_OPEN_FILE) {
-		struct file *f;
-
-		f = open_exec(e->interpreter);
+		/*
+		 * Now that we support unprivileged binfmt_misc mounts make
+		 * sure we use the credentials that the register @file was
+		 * opened with to also open the interpreter. Before that this
+		 * didn't matter much as only a privileged process could open
+		 * the register file.
+		 */
+		scoped_with_creds(file->f_cred)
+			f = open_exec(e->interpreter);
 		if (IS_ERR(f)) {
-			err = PTR_ERR(f);
-			pr_notice("register: failed to install interpreter file %s\n", e->interpreter);
-			simple_release_fs(&bm_mnt, &entry_count);
-			iput(inode);
-			inode = NULL;
-			goto out2;
+			pr_notice("register: failed to install interpreter file %s\n",
+				 e->interpreter);
+			kfree(e);
+			return PTR_ERR(f);
 		}
 		e->interp_file = f;
 	}
 
-	e->dentry = dget(dentry);
-	inode->i_private = e;
-	inode->i_fop = &bm_entry_operations;
-
-	d_instantiate(dentry, inode);
-	write_lock(&entries_lock);
-	list_add(&e->list, &entries);
-	write_unlock(&entries_lock);
-
-	err = 0;
-out2:
-	dput(dentry);
-out:
-	inode_unlock(d_inode(root));
-
+	err = add_entry(e, sb);
 	if (err) {
+		if (f) {
+			exe_file_allow_write_access(f);
+			filp_close(f, NULL);
+		}
 		kfree(e);
 		return err;
 	}
@@ -765,35 +849,50 @@ static const struct file_operations bm_register_operations = {
 static ssize_t
 bm_status_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 {
-	char *s = enabled ? "enabled\n" : "disabled\n";
+	struct binfmt_misc *misc;
+	char *s;
 
+	misc = i_binfmt_misc(file_inode(file));
+	s = misc->enabled ? "enabled\n" : "disabled\n";
 	return simple_read_from_buffer(buf, nbytes, ppos, s, strlen(s));
 }
 
 static ssize_t bm_status_write(struct file *file, const char __user *buffer,
 		size_t count, loff_t *ppos)
 {
+	struct binfmt_misc *misc;
 	int res = parse_command(buffer, count);
-	struct dentry *root;
+	Node *e, *next;
+	struct inode *inode;
 
+	misc = i_binfmt_misc(file_inode(file));
 	switch (res) {
 	case 1:
 		/* Disable all handlers. */
-		enabled = 0;
+		misc->enabled = false;
 		break;
 	case 2:
 		/* Enable all handlers. */
-		enabled = 1;
+		misc->enabled = true;
 		break;
 	case 3:
 		/* Delete all handlers. */
-		root = file_inode(file)->i_sb->s_root;
-		inode_lock(d_inode(root));
+		inode = d_inode(file_inode(file)->i_sb->s_root);
+		inode_lock_nested(inode, I_MUTEX_PARENT);
 
-		while (!list_empty(&entries))
-			kill_node(list_entry(entries.next, Node, list));
+		/*
+		 * 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(d_inode(root));
+		inode_unlock(inode);
 		break;
 	default:
 		return res;
@@ -810,30 +909,107 @@ static const struct file_operations bm_status_operations = {
 
 /* Superblock handling */
 
+static void bm_put_super(struct super_block *sb)
+{
+	struct user_namespace *user_ns = sb->s_fs_info;
+
+	sb->s_fs_info = NULL;
+	put_user_ns(user_ns);
+}
+
 static const struct super_operations s_ops = {
 	.statfs		= simple_statfs,
 	.evict_inode	= bm_evict_inode,
+	.put_super	= bm_put_super,
 };
 
-static int bm_fill_super(struct super_block *sb, void *data, int silent)
+static int bm_fill_super(struct super_block *sb, struct fs_context *fc)
 {
 	int err;
+	struct user_namespace *user_ns = sb->s_user_ns;
+	struct binfmt_misc *misc;
 	static const struct tree_descr bm_files[] = {
 		[2] = {"status", &bm_status_operations, S_IWUSR|S_IRUGO},
 		[3] = {"register", &bm_register_operations, S_IWUSR},
 		/* last one */ {""}
 	};
 
+	if (WARN_ON(user_ns != current_user_ns()))
+		return -EINVAL;
+
+	/*
+	 * Lazily allocate a new binfmt_misc instance for this namespace, i.e.
+	 * do it here during the first mount of binfmt_misc. We don't need to
+	 * waste memory for every user namespace allocation. It's likely much
+	 * more common to not mount a separate binfmt_misc instance than it is
+	 * to mount one.
+	 *
+	 * While multiple superblocks can exist they are keyed by userns in
+	 * s_fs_info for binfmt_misc. Hence, the vfs guarantees that
+	 * bm_fill_super() is called exactly once whenever a binfmt_misc
+	 * superblock for a userns is created. This in turn lets us conclude
+	 * that when a binfmt_misc superblock is created for the first time for
+	 * a userns there's no one racing us. Therefore we don't need any
+	 * barriers when we dereference binfmt_misc.
+	 */
+	misc = user_ns->binfmt_misc;
+	if (!misc) {
+		/*
+		 * If it turns out that most user namespaces actually want to
+		 * register their own binary type handler and therefore all
+		 * create their own separate binfmt_misc mounts we should
+		 * consider turning this into a kmem cache.
+		 */
+		misc = kzalloc(sizeof(struct binfmt_misc), GFP_KERNEL);
+		if (!misc)
+			return -ENOMEM;
+
+		INIT_LIST_HEAD(&misc->entries);
+		rwlock_init(&misc->entries_lock);
+
+		/* Pairs with smp_load_acquire() in load_binfmt_misc(). */
+		smp_store_release(&user_ns->binfmt_misc, misc);
+	}
+
+	/*
+	 * When the binfmt_misc superblock for this userns is shutdown
+	 * ->enabled might have been set to false and we don't reinitialize
+	 * ->enabled again in put_super() as someone might already be mounting
+	 * binfmt_misc again. It also would be pointless since by the time
+	 * ->put_super() is called we know that the binary type list for this
+	 * bintfmt_misc mount is empty making load_misc_binary() return
+	 * -ENOEXEC independent of whether ->enabled is true. Instead, if
+	 * someone mounts binfmt_misc for the first time or again we simply
+	 * reset ->enabled to true.
+	 */
+	misc->enabled = true;
+
 	err = simple_fill_super(sb, BINFMTFS_MAGIC, bm_files);
 	if (!err)
 		sb->s_op = &s_ops;
 	return err;
 }
 
-static struct dentry *bm_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static void bm_free(struct fs_context *fc)
+{
+	if (fc->s_fs_info)
+		put_user_ns(fc->s_fs_info);
+}
+
+static int bm_get_tree(struct fs_context *fc)
+{
+	return get_tree_keyed(fc, bm_fill_super, get_user_ns(fc->user_ns));
+}
+
+static const struct fs_context_operations bm_context_ops = {
+	.free		= bm_free,
+	.get_tree	= bm_get_tree,
+};
+
+static int bm_init_fs_context(struct fs_context *fc)
 {
-	return mount_single(fs_type, flags, data, bm_fill_super);
+	fc->ops = &bm_context_ops;
+	return 0;
 }
 
 static struct linux_binfmt misc_format = {
@@ -844,8 +1020,9 @@ static struct linux_binfmt misc_format = {
 static struct file_system_type bm_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "binfmt_misc",
-	.mount		= bm_mount,
-	.kill_sb	= kill_litter_super,
+	.init_fs_context = bm_init_fs_context,
+	.fs_flags	= FS_USERNS_MOUNT,
+	.kill_sb	= kill_anon_super,
 };
 MODULE_ALIAS_FS("binfmt_misc");
 
@@ -865,4 +1042,5 @@ static void __exit exit_misc_binfmt(void)
 
 core_initcall(init_misc_binfmt);
 module_exit(exit_misc_binfmt);
+MODULE_DESCRIPTION("Kernel support for miscellaneous binaries");
 MODULE_LICENSE("GPL");