Revision bbcd53c960713507ae764bf81970651b5577b95a authored by David Hildenbrand on 07 May 2021, 01:05:55 UTC, committed by Linus Torvalds on 07 May 2021, 07:26:34 UTC
Patch series "drivers/char: remove /dev/kmem for good".

Exploring /dev/kmem and /dev/mem in the context of memory hot(un)plug and
memory ballooning, I started questioning the existence of /dev/kmem.

Comparing it with the /proc/kcore implementation, it does not seem to be
able to deal with things like

a) Pages unmapped from the direct mapping (e.g., to be used by secretmem)
  -> kern_addr_valid(). virt_addr_valid() is not sufficient.

b) Special cases like gart aperture memory that is not to be touched
  -> mem_pfn_is_ram()

Unless I am missing something, it's at least broken in some cases and might
fault/crash the machine.

Looks like its existence has been questioned before in 2005 and 2010 [1],
after ~11 additional years, it might make sense to revive the discussion.

CONFIG_DEVKMEM is only enabled in a single defconfig (on purpose or by
mistake?).  All distributions disable it: in Ubuntu it has been disabled
for more than 10 years, in Debian since 2.6.31, in Fedora at least
starting with FC3, in RHEL starting with RHEL4, in SUSE starting from
15sp2, and OpenSUSE has it disabled as well.

1) /dev/kmem was popular for rootkits [2] before it got disabled
   basically everywhere. Ubuntu documents [3] "There is no modern user of
   /dev/kmem any more beyond attackers using it to load kernel rootkits.".
   RHEL documents in a BZ [5] "it served no practical purpose other than to
   serve as a potential security problem or to enable binary module drivers
   to access structures/functions they shouldn't be touching"

2) /proc/kcore is a decent interface to have a controlled way to read
   kernel memory for debugging puposes. (will need some extensions to
   deal with memory offlining/unplug, memory ballooning, and poisoned
   pages, though)

3) It might be useful for corner case debugging [1]. KDB/KGDB might be a
   better fit, especially, to write random memory; harder to shoot
   yourself into the foot.

4) "Kernel Memory Editor" [4] hasn't seen any updates since 2000 and seems
   to be incompatible with 64bit [1]. For educational purposes,
   /proc/kcore might be used to monitor value updates -- or older
   kernels can be used.

5) It's broken on arm64, and therefore, completely disabled there.

Looks like it's essentially unused and has been replaced by better
suited interfaces for individual tasks (/proc/kcore, KDB/KGDB). Let's
just remove it.

[1] https://lwn.net/Articles/147901/
[2] https://www.linuxjournal.com/article/10505
[3] https://wiki.ubuntu.com/Security/Features#A.2Fdev.2Fkmem_disabled
[4] https://sourceforge.net/projects/kme/
[5] https://bugzilla.redhat.com/show_bug.cgi?id=154796

Link: https://lkml.kernel.org/r/20210324102351.6932-1-david@redhat.com
Link: https://lkml.kernel.org/r/20210324102351.6932-2-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Alexander A. Klimov" <grandmaster@al2klimov.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexandre Belloni <alexandre.belloni@bootlin.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Andrey Zhizhikin <andrey.zhizhikin@leica-geosystems.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Brian Cain <bcain@codeaurora.org>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Chris Zankel <chris@zankel.net>
Cc: Corentin Labbe <clabbe@baylibre.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Gregory Clement <gregory.clement@bootlin.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: Hillf Danton <hdanton@sina.com>
Cc: huang ying <huang.ying.caritas@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: James Troup <james.troup@canonical.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kairui Song <kasong@redhat.com>
Cc: Krzysztof Kozlowski <krzk@kernel.org>
Cc: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Cc: Liviu Dudau <liviu.dudau@arm.com>
Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Mikulas Patocka <mpatocka@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Niklas Schnelle <schnelle@linux.ibm.com>
Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com>
Cc: openrisc@lists.librecores.org
Cc: Palmer Dabbelt <palmerdabbelt@google.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "Pavel Machek (CIP)" <pavel@denx.de>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Cc: Pierre Morel <pmorel@linux.ibm.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Rich Felker <dalias@libc.org>
Cc: Robert Richter <rric@kernel.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Cc: sparclinux@vger.kernel.org
Cc: Stafford Horne <shorne@gmail.com>
Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Cc: Theodore Dubois <tblodt@icloud.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: William Cohen <wcohen@redhat.com>
Cc: Xiaoming Ni <nixiaoming@huawei.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent cb152a1
Raw File
binfmt_misc.c
// 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/admin-guide/binfmt-misc.rst for more details.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/sched/mm.h>
#include <linux/magic.h>
#include <linux/binfmts.h>
#include <linux/slab.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/uaccess.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 */
};

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)

typedef struct {
	struct list_head list;
	unsigned long flags;		/* type, status, etc. */
	int offset;			/* offset of magic */
	int size;			/* size of magic/mask */
	char *magic;			/* magic or filename extension */
	char *mask;			/* mask, NULL for exact match */
	const char *interpreter;	/* filename of interpreter */
	char *name;
	struct dentry *dentry;
	struct file *interp_file;
} 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:
 *  - 7 delimiters
 *  - name:   ~50 bytes
 *  - type:   1 byte
 *  - offset: 3 bytes (has to be smaller than BINPRM_BUF_SIZE)
 *  - magic:  128 bytes (512 in escaped form)
 *  - mask:   128 bytes (512 in escaped form)
 *  - interp: ~50 bytes
 *  - flags:  5 bytes
 * Round that up a bit, and then back off to hold the internal data
 * (like struct Node).
 */
#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
 */
static Node *check_file(struct linux_binprm *bprm)
{
	char *p = strrchr(bprm->interp, '.');
	struct list_head *l;

	/* Walk all the registered handlers. */
	list_for_each(l, &entries) {
		Node *e = list_entry(l, Node, list);
		char *s;
		int j;

		/* 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;
			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;
		} else {
			for (j = 0; j < e->size; j++)
				if ((*s++ ^ e->magic[j]))
					break;
		}
		if (j == e->size)
			return e;
	}
	return NULL;
}

/*
 * the loader itself
 */
static int load_misc_binary(struct linux_binprm *bprm)
{
	Node *fmt;
	struct file *interp_file = NULL;
	int retval;

	retval = -ENOEXEC;
	if (!enabled)
		return retval;

	/* to keep locking time low, we copy the interpreter string */
	read_lock(&entries_lock);
	fmt = check_file(bprm);
	if (fmt)
		dget(fmt->dentry);
	read_unlock(&entries_lock);
	if (!fmt)
		return retval;

	/* Need to be able to load the file after exec */
	retval = -ENOENT;
	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
		goto ret;

	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)
		bprm->have_execfd = 1;

	/* make argv[1] be the path to the binary */
	retval = copy_string_kernel(bprm->interp, bprm);
	if (retval < 0)
		goto ret;
	bprm->argc++;

	/* add the interp as argv[0] */
	retval = copy_string_kernel(fmt->interpreter, bprm);
	if (retval < 0)
		goto ret;
	bprm->argc++;

	/* Update interp in case binfmt_script needs it. */
	retval = bprm_change_interp(fmt->interpreter, bprm);
	if (retval < 0)
		goto ret;

	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(fmt->interpreter);
	}
	retval = PTR_ERR(interp_file);
	if (IS_ERR(interp_file))
		goto ret;

	bprm->interpreter = interp_file;
	if (fmt->flags & MISC_FMT_CREDENTIALS)
		bprm->execfd_creds = 1;

	retval = 0;
ret:
	dput(fmt->dentry);
	return retval;
}

/* 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.
 */
static char *scanarg(char *s, char del)
{
	char c;

	while ((c = *s++) != del) {
		if (c == '\\' && *s == 'x') {
			s++;
			if (!isxdigit(*s++))
				return NULL;
			if (!isxdigit(*s++))
				return NULL;
		}
	}
	s[-1] ='\0';
	return s;
}

static char *check_special_flags(char *sfs, Node *e)
{
	char *p = sfs;
	int cont = 1;

	/* special flags */
	while (cont) {
		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);
			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;
}

/*
 * This registers a new binary format, it recognises the syntax
 * ':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)
{
	Node *e;
	int memsize, err;
	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;

	err = -ENOMEM;
	memsize = sizeof(Node) + count + 8;
	e = kmalloc(memsize, GFP_KERNEL);
	if (!e)
		goto out;

	p = buf = (char *)e + sizeof(Node);

	memset(e, 0, sizeof(Node));
	if (copy_from_user(buf, buffer, count))
		goto efault;

	del = *p++;	/* delimeter */

	pr_debug("register: delim: %#x {%c}\n", del, del);

	/* Pad the buffer with the delim to simplify parsing below. */
	memset(buf + count, del, 8);

	/* Parse the 'name' field. */
	e->name = p;
	p = strchr(p, del);
	if (!p)
		goto einval;
	*p++ = '\0';
	if (!e->name[0] ||
	    !strcmp(e->name, ".") ||
	    !strcmp(e->name, "..") ||
	    strchr(e->name, '/'))
		goto einval;

	pr_debug("register: name: {%s}\n", e->name);

	/* Parse the 'type' field. */
	switch (*p++) {
	case 'E':
		pr_debug("register: type: E (extension)\n");
		e->flags = 1 << Enabled;
		break;
	case 'M':
		pr_debug("register: type: M (magic)\n");
		e->flags = (1 << Enabled) | (1 << Magic);
		break;
	default:
		goto 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);

				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';
	}

	/* Parse the 'interpreter' field. */
	e->interpreter = p;
	p = strchr(p, del);
	if (!p)
		goto einval;
	*p++ = '\0';
	if (!e->interpreter[0])
		goto einval;
	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;

out:
	return ERR_PTR(err);

efault:
	kfree(e);
	return ERR_PTR(-EFAULT);
einval:
	kfree(e);
	return ERR_PTR(-EINVAL);
}

/*
 * Set status of entry/binfmt_misc:
 * '1' enables, '0' disables and '-1' clears entry/binfmt_misc
 */
static int parse_command(const char __user *buffer, size_t count)
{
	char s[4];

	if (count > 3)
		return -EINVAL;
	if (copy_from_user(s, buffer, count))
		return -EFAULT;
	if (!count)
		return 0;
	if (s[count - 1] == '\n')
		count--;
	if (count == 1 && s[0] == '0')
		return 1;
	if (count == 1 && s[0] == '1')
		return 2;
	if (count == 2 && s[0] == '-' && s[1] == '1')
		return 3;
	return -EINVAL;
}

/* generic stuff */

static void entry_status(Node *e, char *page)
{
	char *dp = page;
	const char *status = "disabled";

	if (test_bit(Enabled, &e->flags))
		status = "enabled";

	if (!VERBOSE_STATUS) {
		sprintf(page, "%s\n", status);
		return;
	}

	dp += sprintf(dp, "%s\ninterpreter %s\n", status, e->interpreter);

	/* print the special flags */
	dp += sprintf(dp, "flags: ");
	if (e->flags & MISC_FMT_PRESERVE_ARGV0)
		*dp++ = 'P';
	if (e->flags & MISC_FMT_OPEN_BINARY)
		*dp++ = 'O';
	if (e->flags & MISC_FMT_CREDENTIALS)
		*dp++ = 'C';
	if (e->flags & MISC_FMT_OPEN_FILE)
		*dp++ = 'F';
	*dp++ = '\n';

	if (!test_bit(Magic, &e->flags)) {
		sprintf(dp, "extension .%s\n", e->magic);
	} else {
		dp += sprintf(dp, "offset %i\nmagic ", e->offset);
		dp = bin2hex(dp, e->magic, e->size);
		if (e->mask) {
			dp += sprintf(dp, "\nmask ");
			dp = bin2hex(dp, e->mask, e->size);
		}
		*dp++ = '\n';
		*dp = '\0';
	}
}

static struct inode *bm_get_inode(struct super_block *sb, int mode)
{
	struct inode *inode = new_inode(sb);

	if (inode) {
		inode->i_ino = get_next_ino();
		inode->i_mode = mode;
		inode->i_atime = inode->i_mtime = inode->i_ctime =
			current_time(inode);
	}
	return inode;
}

static void bm_evict_inode(struct inode *inode)
{
	Node *e = inode->i_private;

	if (e && e->flags & MISC_FMT_OPEN_FILE)
		filp_close(e->interp_file, NULL);

	clear_inode(inode);
	kfree(e);
}

static void kill_node(Node *e)
{
	struct dentry *dentry;

	write_lock(&entries_lock);
	list_del_init(&e->list);
	write_unlock(&entries_lock);

	dentry = e->dentry;
	drop_nlink(d_inode(dentry));
	d_drop(dentry);
	dput(dentry);
	simple_release_fs(&bm_mnt, &entry_count);
}

/* /<entry> */

static ssize_t
bm_entry_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
{
	Node *e = file_inode(file)->i_private;
	ssize_t res;
	char *page;

	page = (char *) __get_free_page(GFP_KERNEL);
	if (!page)
		return -ENOMEM;

	entry_status(e, page);

	res = simple_read_from_buffer(buf, nbytes, ppos, page, strlen(page));

	free_page((unsigned long) page);
	return res;
}

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;
	int res = parse_command(buffer, count);

	switch (res) {
	case 1:
		/* Disable this handler. */
		clear_bit(Enabled, &e->flags);
		break;
	case 2:
		/* Enable this handler. */
		set_bit(Enabled, &e->flags);
		break;
	case 3:
		/* Delete this handler. */
		root = file_inode(file)->i_sb->s_root;
		inode_lock(d_inode(root));

		if (!list_empty(&e->list))
			kill_node(e);

		inode_unlock(d_inode(root));
		break;
	default:
		return res;
	}

	return count;
}

static const struct file_operations bm_entry_operations = {
	.read		= bm_entry_read,
	.write		= bm_entry_write,
	.llseek		= default_llseek,
};

/* /register */

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);

	if (e->flags & MISC_FMT_OPEN_FILE) {
		f = open_exec(e->interpreter);
		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;
	}

	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;
	}

	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));

	if (err) {
		if (f)
			filp_close(f, NULL);
		kfree(e);
		return err;
	}
	return count;
}

static const struct file_operations bm_register_operations = {
	.write		= bm_register_write,
	.llseek		= noop_llseek,
};

/* /status */

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";

	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)
{
	int res = parse_command(buffer, count);
	struct dentry *root;

	switch (res) {
	case 1:
		/* Disable all handlers. */
		enabled = 0;
		break;
	case 2:
		/* Enable all handlers. */
		enabled = 1;
		break;
	case 3:
		/* Delete all handlers. */
		root = file_inode(file)->i_sb->s_root;
		inode_lock(d_inode(root));

		while (!list_empty(&entries))
			kill_node(list_first_entry(&entries, Node, list));

		inode_unlock(d_inode(root));
		break;
	default:
		return res;
	}

	return count;
}

static const struct file_operations bm_status_operations = {
	.read		= bm_status_read,
	.write		= bm_status_write,
	.llseek		= default_llseek,
};

/* Superblock handling */

static const struct super_operations s_ops = {
	.statfs		= simple_statfs,
	.evict_inode	= bm_evict_inode,
};

static int bm_fill_super(struct super_block *sb, struct fs_context *fc)
{
	int err;
	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 */ {""}
	};

	err = simple_fill_super(sb, BINFMTFS_MAGIC, bm_files);
	if (!err)
		sb->s_op = &s_ops;
	return err;
}

static int bm_get_tree(struct fs_context *fc)
{
	return get_tree_single(fc, bm_fill_super);
}

static const struct fs_context_operations bm_context_ops = {
	.get_tree	= bm_get_tree,
};

static int bm_init_fs_context(struct fs_context *fc)
{
	fc->ops = &bm_context_ops;
	return 0;
}

static struct linux_binfmt misc_format = {
	.module = THIS_MODULE,
	.load_binary = load_misc_binary,
};

static struct file_system_type bm_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "binfmt_misc",
	.init_fs_context = bm_init_fs_context,
	.kill_sb	= kill_litter_super,
};
MODULE_ALIAS_FS("binfmt_misc");

static int __init init_misc_binfmt(void)
{
	int err = register_filesystem(&bm_fs_type);
	if (!err)
		insert_binfmt(&misc_format);
	return err;
}

static void __exit exit_misc_binfmt(void)
{
	unregister_binfmt(&misc_format);
	unregister_filesystem(&bm_fs_type);
}

core_initcall(init_misc_binfmt);
module_exit(exit_misc_binfmt);
MODULE_LICENSE("GPL");
back to top