OpenCloudOS-Kernel/fs/binfmt_misc.c

841 lines
18 KiB
C
Raw Normal View History

// 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.
*/
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
#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>
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
#include <linux/uaccess.h>
#include "internal.h"
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
#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;
binfmt_misc: expand the register format limit to 1920 bytes The current code places a 256 byte limit on the registration format. This ends up being fairly limited when you try to do matching against a binary format like ELF: - the magic & mask formats cannot have any embedded NUL chars (string_unescape_inplace halts at the first NUL) - each escape sequence quadruples the size: \x00 is needed for NUL - trying to match bytes at the start of the file as well as further on leads to a lot of \x00 sequences in the mask - magic & mask have to be the same length (when decoded) - still need bytes for the other fields - impossible! Let's look at a concrete (and common) example: using QEMU to run MIPS ELFs. The name field uses 11 bytes "qemu-mipsel". The interp uses 20 bytes "/usr/bin/qemu-mipsel". The type & flags takes up 4 bytes. We need 7 bytes for the delimiter (usually ":"). We can skip offset. So already we're down to 107 bytes to use with the magic/mask instead of the real limit of 128 (BINPRM_BUF_SIZE). If people use shell code to register (which they do the majority of the time), they're down to ~26 possible bytes since the escape sequence must be \x##. The ELF format looks like (both 32 & 64 bit): e_ident: 16 bytes e_type: 2 bytes e_machine: 2 bytes Those 20 bytes are enough for most architectures because they have so few formats in the first place, thus they can be uniquely identified. That also means for shell users, since 20 is smaller than 26, they can sanely register a handler. But for some targets (like MIPS), we need to poke further. The ELF fields continue on: e_entry: 4 or 8 bytes e_phoff: 4 or 8 bytes e_shoff: 4 or 8 bytes e_flags: 4 bytes We only care about e_flags here as that includes the bits to identify whether the ELF is O32/N32/N64. But now we have to consume another 16 bytes (for 32 bit ELFs) or 28 bytes (for 64 bit ELFs) just to match the flags. If every byte is escaped, we send 288 more bytes to the kernel ((20 {e_ident,e_type,e_machine} + 12 {e_entry,e_phoff,e_shoff} + 4 {e_flags}) * 2 {mask,magic} * 4 {escape}) and we've clearly blown our budget. Even if we try to be clever and do the decoding ourselves (rather than relying on the kernel to process \x##), we still can't hit the mark -- string_unescape_inplace treats mask & magic as C strings so NUL cannot be embedded. That leaves us with having to pass \x00 for the 12/24 entry/phoff/shoff bytes (as those will be completely random addresses), and that is a minimum requirement of 48/96 bytes for the mask alone. Add up the rest and we blow through it (this is for 64 bit ELFs): magic: 20 {e_ident,e_type,e_machine} + 24 {e_entry,e_phoff,e_shoff} + 4 {e_flags} = 48 # ^^ See note below. mask: 20 {e_ident,e_type,e_machine} + 96 {e_entry,e_phoff,e_shoff} + 4 {e_flags} = 120 Remember above we had 107 left over, and now we're at 168. This is of course the *best* case scenario -- you'll also want to have NUL bytes in the magic & mask too to match literal zeros. Note: the reason we can use 24 in the magic is that we can work off of the fact that for bytes the mask would clobber, we can stuff any value into magic that we want. So when mask is \x00, we don't need the magic to also be \x00, it can be an unescaped raw byte like '!'. This lets us handle more formats (barely) under the current 256 limit, but that's a pretty tall hoop to force people to jump through. With all that said, let's bump the limit from 256 bytes to 1920. This way we support escaping every byte of the mask & magic field (which is 1024 bytes by themselves -- 128 * 4 * 2), and we leave plenty of room for other fields. Like long paths to the interpreter (when you have source in your /really/long/homedir/qemu/foo). Since the current code stuffs more than one structure into the same buffer, we leave a bit of space to easily round up to 2k. 1920 is just as arbitrary as 256 ;). Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-14 06:52:03 +08:00
/*
* 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;
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
/* Walk all the registered handlers. */
list_for_each(l, &entries) {
Node *e = list_entry(l, Node, list);
char *s;
int j;
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
/* Make sure this one is currently enabled. */
if (!test_bit(Enabled, &e->flags))
continue;
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
/* Do matching based on extension if applicable. */
if (!test_bit(Magic, &e->flags)) {
if (p && !strcmp(e->magic, p + 1))
return e;
continue;
}
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
/* 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;
syscalls: implement execveat() system call This patchset adds execveat(2) for x86, and is derived from Meredydd Luff's patch from Sept 2012 (https://lkml.org/lkml/2012/9/11/528). The primary aim of adding an execveat syscall is to allow an implementation of fexecve(3) that does not rely on the /proc filesystem, at least for executables (rather than scripts). The current glibc version of fexecve(3) is implemented via /proc, which causes problems in sandboxed or otherwise restricted environments. Given the desire for a /proc-free fexecve() implementation, HPA suggested (https://lkml.org/lkml/2006/7/11/556) that an execveat(2) syscall would be an appropriate generalization. Also, having a new syscall means that it can take a flags argument without back-compatibility concerns. The current implementation just defines the AT_EMPTY_PATH and AT_SYMLINK_NOFOLLOW flags, but other flags could be added in future -- for example, flags for new namespaces (as suggested at https://lkml.org/lkml/2006/7/11/474). Related history: - https://lkml.org/lkml/2006/12/27/123 is an example of someone realizing that fexecve() is likely to fail in a chroot environment. - http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=514043 covered documenting the /proc requirement of fexecve(3) in its manpage, to "prevent other people from wasting their time". - https://bugzilla.redhat.com/show_bug.cgi?id=241609 described a problem where a process that did setuid() could not fexecve() because it no longer had access to /proc/self/fd; this has since been fixed. This patch (of 4): Add a new execveat(2) system call. execveat() is to execve() as openat() is to open(): it takes a file descriptor that refers to a directory, and resolves the filename relative to that. In addition, if the filename is empty and AT_EMPTY_PATH is specified, execveat() executes the file to which the file descriptor refers. This replicates the functionality of fexecve(), which is a system call in other UNIXen, but in Linux glibc it depends on opening "/proc/self/fd/<fd>" (and so relies on /proc being mounted). The filename fed to the executed program as argv[0] (or the name of the script fed to a script interpreter) will be of the form "/dev/fd/<fd>" (for an empty filename) or "/dev/fd/<fd>/<filename>", effectively reflecting how the executable was found. This does however mean that execution of a script in a /proc-less environment won't work; also, script execution via an O_CLOEXEC file descriptor fails (as the file will not be accessible after exec). Based on patches by Meredydd Luff. Signed-off-by: David Drysdale <drysdale@google.com> Cc: Meredydd Luff <meredydd@senatehouse.org> Cc: Shuah Khan <shuah.kh@samsung.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Rich Felker <dalias@aerifal.cx> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-13 08:57:29 +08:00
/* Need to be able to load the file after exec */
retval = -ENOENT;
syscalls: implement execveat() system call This patchset adds execveat(2) for x86, and is derived from Meredydd Luff's patch from Sept 2012 (https://lkml.org/lkml/2012/9/11/528). The primary aim of adding an execveat syscall is to allow an implementation of fexecve(3) that does not rely on the /proc filesystem, at least for executables (rather than scripts). The current glibc version of fexecve(3) is implemented via /proc, which causes problems in sandboxed or otherwise restricted environments. Given the desire for a /proc-free fexecve() implementation, HPA suggested (https://lkml.org/lkml/2006/7/11/556) that an execveat(2) syscall would be an appropriate generalization. Also, having a new syscall means that it can take a flags argument without back-compatibility concerns. The current implementation just defines the AT_EMPTY_PATH and AT_SYMLINK_NOFOLLOW flags, but other flags could be added in future -- for example, flags for new namespaces (as suggested at https://lkml.org/lkml/2006/7/11/474). Related history: - https://lkml.org/lkml/2006/12/27/123 is an example of someone realizing that fexecve() is likely to fail in a chroot environment. - http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=514043 covered documenting the /proc requirement of fexecve(3) in its manpage, to "prevent other people from wasting their time". - https://bugzilla.redhat.com/show_bug.cgi?id=241609 described a problem where a process that did setuid() could not fexecve() because it no longer had access to /proc/self/fd; this has since been fixed. This patch (of 4): Add a new execveat(2) system call. execveat() is to execve() as openat() is to open(): it takes a file descriptor that refers to a directory, and resolves the filename relative to that. In addition, if the filename is empty and AT_EMPTY_PATH is specified, execveat() executes the file to which the file descriptor refers. This replicates the functionality of fexecve(), which is a system call in other UNIXen, but in Linux glibc it depends on opening "/proc/self/fd/<fd>" (and so relies on /proc being mounted). The filename fed to the executed program as argv[0] (or the name of the script fed to a script interpreter) will be of the form "/dev/fd/<fd>" (for an empty filename) or "/dev/fd/<fd>/<filename>", effectively reflecting how the executable was found. This does however mean that execution of a script in a /proc-less environment won't work; also, script execution via an O_CLOEXEC file descriptor fails (as the file will not be accessible after exec). Based on patches by Meredydd Luff. Signed-off-by: David Drysdale <drysdale@google.com> Cc: Meredydd Luff <meredydd@senatehouse.org> Cc: Shuah Khan <shuah.kh@samsung.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Rich Felker <dalias@aerifal.cx> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-13 08:57:29 +08:00
if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
goto ret;
syscalls: implement execveat() system call This patchset adds execveat(2) for x86, and is derived from Meredydd Luff's patch from Sept 2012 (https://lkml.org/lkml/2012/9/11/528). The primary aim of adding an execveat syscall is to allow an implementation of fexecve(3) that does not rely on the /proc filesystem, at least for executables (rather than scripts). The current glibc version of fexecve(3) is implemented via /proc, which causes problems in sandboxed or otherwise restricted environments. Given the desire for a /proc-free fexecve() implementation, HPA suggested (https://lkml.org/lkml/2006/7/11/556) that an execveat(2) syscall would be an appropriate generalization. Also, having a new syscall means that it can take a flags argument without back-compatibility concerns. The current implementation just defines the AT_EMPTY_PATH and AT_SYMLINK_NOFOLLOW flags, but other flags could be added in future -- for example, flags for new namespaces (as suggested at https://lkml.org/lkml/2006/7/11/474). Related history: - https://lkml.org/lkml/2006/12/27/123 is an example of someone realizing that fexecve() is likely to fail in a chroot environment. - http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=514043 covered documenting the /proc requirement of fexecve(3) in its manpage, to "prevent other people from wasting their time". - https://bugzilla.redhat.com/show_bug.cgi?id=241609 described a problem where a process that did setuid() could not fexecve() because it no longer had access to /proc/self/fd; this has since been fixed. This patch (of 4): Add a new execveat(2) system call. execveat() is to execve() as openat() is to open(): it takes a file descriptor that refers to a directory, and resolves the filename relative to that. In addition, if the filename is empty and AT_EMPTY_PATH is specified, execveat() executes the file to which the file descriptor refers. This replicates the functionality of fexecve(), which is a system call in other UNIXen, but in Linux glibc it depends on opening "/proc/self/fd/<fd>" (and so relies on /proc being mounted). The filename fed to the executed program as argv[0] (or the name of the script fed to a script interpreter) will be of the form "/dev/fd/<fd>" (for an empty filename) or "/dev/fd/<fd>/<filename>", effectively reflecting how the executable was found. This does however mean that execution of a script in a /proc-less environment won't work; also, script execution via an O_CLOEXEC file descriptor fails (as the file will not be accessible after exec). Based on patches by Meredydd Luff. Signed-off-by: David Drysdale <drysdale@google.com> Cc: Meredydd Luff <meredydd@senatehouse.org> Cc: Shuah Khan <shuah.kh@samsung.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Rich Felker <dalias@aerifal.cx> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-13 08:57:29 +08:00
if (fmt->flags & MISC_FMT_PRESERVE_ARGV0) {
bprm->interp_flags |= BINPRM_FLAGS_PRESERVE_ARGV0;
} else {
retval = remove_arg_zero(bprm);
if (retval)
goto ret;
}
exec: Remove recursion from search_binary_handler Recursion in kernel code is generally a bad idea as it can overflow the kernel stack. Recursion in exec also hides that the code is looping and that the loop changes bprm->file. Instead of recursing in search_binary_handler have the methods that would recurse set bprm->interpreter and return 0. Modify exec_binprm to loop when bprm->interpreter is set. Consolidate all of the reassignments of bprm->file in that loop to make it clear what is going on. The structure of the new loop in exec_binprm is that all errors return immediately, while successful completion (ret == 0 && !bprm->interpreter) just breaks out of the loop and runs what exec_bprm has always run upon successful completion. Fail if the an interpreter is being call after execfd has been set. The code has never properly handled an interpreter being called with execfd being set and with reassignments of bprm->file and the assignment of bprm->executable in generic code it has finally become possible to test and fail when if this problematic condition happens. With the reassignments of bprm->file and the assignment of bprm->executable moved into the generic code add a test to see if bprm->executable is being reassigned. In search_binary_handler remove the test for !bprm->file. With all reassignments of bprm->file moved to exec_binprm bprm->file can never be NULL in search_binary_handler. Link: https://lkml.kernel.org/r/87sgfwyd84.fsf_-_@x220.int.ebiederm.org Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2020-05-19 07:43:20 +08:00
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++;
exec: do not leave bprm->interp on stack If a series of scripts are executed, each triggering module loading via unprintable bytes in the script header, kernel stack contents can leak into the command line. Normally execution of binfmt_script and binfmt_misc happens recursively. However, when modules are enabled, and unprintable bytes exist in the bprm->buf, execution will restart after attempting to load matching binfmt modules. Unfortunately, the logic in binfmt_script and binfmt_misc does not expect to get restarted. They leave bprm->interp pointing to their local stack. This means on restart bprm->interp is left pointing into unused stack memory which can then be copied into the userspace argv areas. After additional study, it seems that both recursion and restart remains the desirable way to handle exec with scripts, misc, and modules. As such, we need to protect the changes to interp. This changes the logic to require allocation for any changes to the bprm->interp. To avoid adding a new kmalloc to every exec, the default value is left as-is. Only when passing through binfmt_script or binfmt_misc does an allocation take place. For a proof of concept, see DoTest.sh from: http://www.halfdog.net/Security/2012/LinuxKernelBinfmtScriptStackDataDisclosure/ Signed-off-by: Kees Cook <keescook@chromium.org> Cc: halfdog <me@halfdog.net> Cc: P J P <ppandit@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-21 07:05:16 +08:00
/* Update interp in case binfmt_script needs it. */
retval = bprm_change_interp(fmt->interpreter, bprm);
exec: do not leave bprm->interp on stack If a series of scripts are executed, each triggering module loading via unprintable bytes in the script header, kernel stack contents can leak into the command line. Normally execution of binfmt_script and binfmt_misc happens recursively. However, when modules are enabled, and unprintable bytes exist in the bprm->buf, execution will restart after attempting to load matching binfmt modules. Unfortunately, the logic in binfmt_script and binfmt_misc does not expect to get restarted. They leave bprm->interp pointing to their local stack. This means on restart bprm->interp is left pointing into unused stack memory which can then be copied into the userspace argv areas. After additional study, it seems that both recursion and restart remains the desirable way to handle exec with scripts, misc, and modules. As such, we need to protect the changes to interp. This changes the logic to require allocation for any changes to the bprm->interp. To avoid adding a new kmalloc to every exec, the default value is left as-is. Only when passing through binfmt_script or binfmt_misc does an allocation take place. For a proof of concept, see DoTest.sh from: http://www.halfdog.net/Security/2012/LinuxKernelBinfmtScriptStackDataDisclosure/ Signed-off-by: Kees Cook <keescook@chromium.org> Cc: halfdog <me@halfdog.net> Cc: P J P <ppandit@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-21 07:05:16 +08:00
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;
exec: Remove recursion from search_binary_handler Recursion in kernel code is generally a bad idea as it can overflow the kernel stack. Recursion in exec also hides that the code is looping and that the loop changes bprm->file. Instead of recursing in search_binary_handler have the methods that would recurse set bprm->interpreter and return 0. Modify exec_binprm to loop when bprm->interpreter is set. Consolidate all of the reassignments of bprm->file in that loop to make it clear what is going on. The structure of the new loop in exec_binprm is that all errors return immediately, while successful completion (ret == 0 && !bprm->interpreter) just breaks out of the loop and runs what exec_bprm has always run upon successful completion. Fail if the an interpreter is being call after execfd has been set. The code has never properly handled an interpreter being called with execfd being set and with reassignments of bprm->file and the assignment of bprm->executable in generic code it has finally become possible to test and fail when if this problematic condition happens. With the reassignments of bprm->file and the assignment of bprm->executable moved into the generic code add a test to see if bprm->executable is being reassigned. In search_binary_handler remove the test for !bprm->file. With all reassignments of bprm->file moved to exec_binprm bprm->file can never be NULL in search_binary_handler. Link: https://lkml.kernel.org/r/87sgfwyd84.fsf_-_@x220.int.ebiederm.org Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2020-05-19 07:43:20 +08:00
bprm->interpreter = interp_file;
if (fmt->flags & MISC_FMT_CREDENTIALS)
exec: Compute file based creds only once Move the computation of creds from prepare_binfmt into begin_new_exec so that the creds need only be computed once. This is just code reorganization no semantic changes of any kind are made. Moving the computation is safe. I have looked through the kernel and verified none of the binfmts look at bprm->cred directly, and that there are no helpers that look at bprm->cred indirectly. Which means that it is not a problem to compute the bprm->cred later in the execution flow as it is not used until it becomes current->cred. A new function bprm_creds_from_file is added to contain the work that needs to be done. bprm_creds_from_file first computes which file bprm->executable or most likely bprm->file that the bprm->creds will be computed from. The funciton bprm_fill_uid is updated to receive the file instead of accessing bprm->file. The now unnecessary work needed to reset the bprm->cred->euid, and bprm->cred->egid is removed from brpm_fill_uid. A small comment to document that bprm_fill_uid now only deals with the work to handle suid and sgid files. The default case is already heandled by prepare_exec_creds. The function security_bprm_repopulate_creds is renamed security_bprm_creds_from_file and now is explicitly passed the file from which to compute the creds. The documentation of the bprm_creds_from_file security hook is updated to explain when the hook is called and what it needs to do. The file is passed from cap_bprm_creds_from_file into get_file_caps so that the caps are computed for the appropriate file. The now unnecessary work in cap_bprm_creds_from_file to reset the ambient capabilites has been removed. A small comment to document that the work of cap_bprm_creds_from_file is to read capabilities from the files secureity attribute and derive capabilities from the fact the user had uid 0 has been added. Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2020-05-30 11:00:54 +08:00
bprm->execfd_creds = 1;
exec: Remove recursion from search_binary_handler Recursion in kernel code is generally a bad idea as it can overflow the kernel stack. Recursion in exec also hides that the code is looping and that the loop changes bprm->file. Instead of recursing in search_binary_handler have the methods that would recurse set bprm->interpreter and return 0. Modify exec_binprm to loop when bprm->interpreter is set. Consolidate all of the reassignments of bprm->file in that loop to make it clear what is going on. The structure of the new loop in exec_binprm is that all errors return immediately, while successful completion (ret == 0 && !bprm->interpreter) just breaks out of the loop and runs what exec_bprm has always run upon successful completion. Fail if the an interpreter is being call after execfd has been set. The code has never properly handled an interpreter being called with execfd being set and with reassignments of bprm->file and the assignment of bprm->executable in generic code it has finally become possible to test and fail when if this problematic condition happens. With the reassignments of bprm->file and the assignment of bprm->executable moved into the generic code add a test to see if bprm->executable is being reassigned. In search_binary_handler remove the test for !bprm->file. With all reassignments of bprm->file moved to exec_binprm bprm->file can never be NULL in search_binary_handler. Link: https://lkml.kernel.org/r/87sgfwyd84.fsf_-_@x220.int.ebiederm.org Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2020-05-19 07:43:20 +08:00
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;
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
pr_debug("register: received %zu bytes\n", count);
/* some sanity checks */
err = -EINVAL;
binfmt_misc: expand the register format limit to 1920 bytes The current code places a 256 byte limit on the registration format. This ends up being fairly limited when you try to do matching against a binary format like ELF: - the magic & mask formats cannot have any embedded NUL chars (string_unescape_inplace halts at the first NUL) - each escape sequence quadruples the size: \x00 is needed for NUL - trying to match bytes at the start of the file as well as further on leads to a lot of \x00 sequences in the mask - magic & mask have to be the same length (when decoded) - still need bytes for the other fields - impossible! Let's look at a concrete (and common) example: using QEMU to run MIPS ELFs. The name field uses 11 bytes "qemu-mipsel". The interp uses 20 bytes "/usr/bin/qemu-mipsel". The type & flags takes up 4 bytes. We need 7 bytes for the delimiter (usually ":"). We can skip offset. So already we're down to 107 bytes to use with the magic/mask instead of the real limit of 128 (BINPRM_BUF_SIZE). If people use shell code to register (which they do the majority of the time), they're down to ~26 possible bytes since the escape sequence must be \x##. The ELF format looks like (both 32 & 64 bit): e_ident: 16 bytes e_type: 2 bytes e_machine: 2 bytes Those 20 bytes are enough for most architectures because they have so few formats in the first place, thus they can be uniquely identified. That also means for shell users, since 20 is smaller than 26, they can sanely register a handler. But for some targets (like MIPS), we need to poke further. The ELF fields continue on: e_entry: 4 or 8 bytes e_phoff: 4 or 8 bytes e_shoff: 4 or 8 bytes e_flags: 4 bytes We only care about e_flags here as that includes the bits to identify whether the ELF is O32/N32/N64. But now we have to consume another 16 bytes (for 32 bit ELFs) or 28 bytes (for 64 bit ELFs) just to match the flags. If every byte is escaped, we send 288 more bytes to the kernel ((20 {e_ident,e_type,e_machine} + 12 {e_entry,e_phoff,e_shoff} + 4 {e_flags}) * 2 {mask,magic} * 4 {escape}) and we've clearly blown our budget. Even if we try to be clever and do the decoding ourselves (rather than relying on the kernel to process \x##), we still can't hit the mark -- string_unescape_inplace treats mask & magic as C strings so NUL cannot be embedded. That leaves us with having to pass \x00 for the 12/24 entry/phoff/shoff bytes (as those will be completely random addresses), and that is a minimum requirement of 48/96 bytes for the mask alone. Add up the rest and we blow through it (this is for 64 bit ELFs): magic: 20 {e_ident,e_type,e_machine} + 24 {e_entry,e_phoff,e_shoff} + 4 {e_flags} = 48 # ^^ See note below. mask: 20 {e_ident,e_type,e_machine} + 96 {e_entry,e_phoff,e_shoff} + 4 {e_flags} = 120 Remember above we had 107 left over, and now we're at 168. This is of course the *best* case scenario -- you'll also want to have NUL bytes in the magic & mask too to match literal zeros. Note: the reason we can use 24 in the magic is that we can work off of the fact that for bytes the mask would clobber, we can stuff any value into magic that we want. So when mask is \x00, we don't need the magic to also be \x00, it can be an unescaped raw byte like '!'. This lets us handle more formats (barely) under the current 256 limit, but that's a pretty tall hoop to force people to jump through. With all that said, let's bump the limit from 256 bytes to 1920. This way we support escaping every byte of the mask & magic field (which is 1024 bytes by themselves -- 128 * 4 * 2), and we leave plenty of room for other fields. Like long paths to the interpreter (when you have source in your /really/long/homedir/qemu/foo). Since the current code stuffs more than one structure into the same buffer, we leave a bit of space to easily round up to 2k. 1920 is just as arbitrary as 256 ;). Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-14 06:52:03 +08:00
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 */
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
pr_debug("register: delim: %#x {%c}\n", del, del);
/* Pad the buffer with the delim to simplify parsing below. */
memset(buf + count, del, 8);
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
/* 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;
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
pr_debug("register: name: {%s}\n", e->name);
/* Parse the 'type' field. */
switch (*p++) {
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
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;
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
if (test_bit(Magic, &e->flags)) {
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
/* Handle the 'M' (magic) format. */
char *s;
/* Parse the 'offset' field. */
s = strchr(p, del);
if (!s)
goto einval;
fs/binfmt_misc.c: do not allow offset overflow WHen registering a new binfmt_misc handler, it is possible to overflow the offset to get a negative value, which might crash the system, or possibly leak kernel data. Here is a crash log when 2500000000 was used as an offset: BUG: unable to handle kernel paging request at ffff989cfd6edca0 IP: load_misc_binary+0x22b/0x470 [binfmt_misc] PGD 1ef3e067 P4D 1ef3e067 PUD 0 Oops: 0000 [#1] SMP NOPTI Modules linked in: binfmt_misc kvm_intel ppdev kvm irqbypass joydev input_leds serio_raw mac_hid parport_pc qemu_fw_cfg parpy CPU: 0 PID: 2499 Comm: bash Not tainted 4.15.0-22-generic #24-Ubuntu Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.1-1 04/01/2014 RIP: 0010:load_misc_binary+0x22b/0x470 [binfmt_misc] Call Trace: search_binary_handler+0x97/0x1d0 do_execveat_common.isra.34+0x667/0x810 SyS_execve+0x31/0x40 do_syscall_64+0x73/0x130 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Use kstrtoint instead of simple_strtoul. It will work as the code already set the delimiter byte to '\0' and we only do it when the field is not empty. Tested with offsets -1, 2500000000, UINT_MAX and INT_MAX. Also tested with examples documented at Documentation/admin-guide/binfmt-misc.rst and other registrations from packages on Ubuntu. Link: http://lkml.kernel.org/r/20180529135648.14254-1-cascardo@canonical.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-06-08 08:11:01 +08:00
*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;
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
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;
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
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;
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
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;
fs/binfmt_misc.c: do not allow offset overflow WHen registering a new binfmt_misc handler, it is possible to overflow the offset to get a negative value, which might crash the system, or possibly leak kernel data. Here is a crash log when 2500000000 was used as an offset: BUG: unable to handle kernel paging request at ffff989cfd6edca0 IP: load_misc_binary+0x22b/0x470 [binfmt_misc] PGD 1ef3e067 P4D 1ef3e067 PUD 0 Oops: 0000 [#1] SMP NOPTI Modules linked in: binfmt_misc kvm_intel ppdev kvm irqbypass joydev input_leds serio_raw mac_hid parport_pc qemu_fw_cfg parpy CPU: 0 PID: 2499 Comm: bash Not tainted 4.15.0-22-generic #24-Ubuntu Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.1-1 04/01/2014 RIP: 0010:load_misc_binary+0x22b/0x470 [binfmt_misc] Call Trace: search_binary_handler+0x97/0x1d0 do_execveat_common.isra.34+0x667/0x810 SyS_execve+0x31/0x40 do_syscall_64+0x73/0x130 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Use kstrtoint instead of simple_strtoul. It will work as the code already set the delimiter byte to '\0' and we only do it when the field is not empty. Tested with offsets -1, 2500000000, UINT_MAX and INT_MAX. Also tested with examples documented at Documentation/admin-guide/binfmt-misc.rst and other registrations from packages on Ubuntu. Link: http://lkml.kernel.org/r/20180529135648.14254-1-cascardo@canonical.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-06-08 08:11:01 +08:00
if (e->size > BINPRM_BUF_SIZE ||
BINPRM_BUF_SIZE - e->size < e->offset)
goto einval;
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
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);
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
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 {
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
/* Handle the 'E' (extension) format. */
/* Skip the 'offset' field. */
p = strchr(p, del);
if (!p)
goto einval;
*p++ = '\0';
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
/* 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;
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
pr_debug("register: extension: {%s}\n", e->magic);
/* Skip the 'mask' field. */
p = strchr(p, del);
if (!p)
goto einval;
*p++ = '\0';
}
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
/* Parse the 'interpreter' field. */
e->interpreter = p;
p = strchr(p, del);
if (!p)
goto einval;
*p++ = '\0';
if (!e->interpreter[0])
goto einval;
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
pr_debug("register: interpreter: {%s}\n", e->interpreter);
binfmt_misc: add comments & debug logs When trying to develop a custom format handler, the errors returned all effectively get bucketed as EINVAL with no kernel messages. The other errors (ENOMEM/EFAULT) are internal/obvious and basic. Thus any time a bad handler is rejected, the developer has to walk the dense code and try to guess where it went wrong. Needing to dive into kernel code is itself a fairly high barrier for a lot of people. To improve this situation, let's deploy extensive pr_debug markers at logical parse points, and add comments to the dense parsing logic. It let's you see exactly where the parsing aborts, the string the kernel received (useful when dealing with shell code), how it translated the buffers to binary data, and how it will apply the mask at runtime. Some example output: $ echo ':qemu-foo:M::\x7fELF\xAD\xAD\x01\x00:\xff\xff\xff\xff\xff\x00\xff\x00:/usr/bin/qemu-foo:POC' > register $ dmesg binfmt_misc: register: received 92 bytes binfmt_misc: register: delim: 0x3a {:} binfmt_misc: register: name: {qemu-foo} binfmt_misc: register: type: M (magic) binfmt_misc: register: offset: 0x0 binfmt_misc: register: magic[raw]: 5c 78 37 66 45 4c 46 5c 78 41 44 5c 78 41 44 5c \x7fELF\xAD\xAD\ binfmt_misc: register: magic[raw]: 78 30 31 5c 78 30 30 00 x01\x00. binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 66 66 5c 78 66 66 5c 78 66 66 \xff\xff\xff\xff binfmt_misc: register: mask[raw]: 5c 78 66 66 5c 78 30 30 5c 78 66 66 5c 78 30 30 \xff\x00\xff\x00 binfmt_misc: register: mask[raw]: 00 . binfmt_misc: register: magic/mask length: 8 binfmt_misc: register: magic[decoded]: 7f 45 4c 46 ad ad 01 00 .ELF.... binfmt_misc: register: mask[decoded]: ff ff ff ff ff 00 ff 00 ........ binfmt_misc: register: magic[masked]: 7f 45 4c 46 ad 00 01 00 .ELF.... binfmt_misc: register: interpreter: {/usr/bin/qemu-foo} binfmt_misc: register: flag: P (preserve argv0) binfmt_misc: register: flag: O (open binary) binfmt_misc: register: flag: C (preserve creds) The [raw] lines show us exactly what was received from userspace. The lines after that show us how the kernel has decoded things. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:52:08 +08:00
/* 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;
fs/binfmt_misc.c: node could be NULL when evicting inode inode->i_private is assigned by a Node pointer only after registering a new binary format, so it could be NULL if inode was created by bm_fill_super() (or iput() was called by the error path in bm_register_write()), and this could result in NULL pointer dereference when evicting such an inode. e.g. mount binfmt_misc filesystem then umount it immediately: mount -t binfmt_misc binfmt_misc /proc/sys/fs/binfmt_misc umount /proc/sys/fs/binfmt_misc will result in BUG: unable to handle kernel NULL pointer dereference at 0000000000000013 IP: bm_evict_inode+0x16/0x40 [binfmt_misc] ... Call Trace: evict+0xd3/0x1a0 iput+0x17d/0x1d0 dentry_unlink_inode+0xb9/0xf0 __dentry_kill+0xc7/0x170 shrink_dentry_list+0x122/0x280 shrink_dcache_parent+0x39/0x90 do_one_tree+0x12/0x40 shrink_dcache_for_umount+0x2d/0x90 generic_shutdown_super+0x1f/0x120 kill_litter_super+0x29/0x40 deactivate_locked_super+0x43/0x70 deactivate_super+0x45/0x60 cleanup_mnt+0x3f/0x70 __cleanup_mnt+0x12/0x20 task_work_run+0x86/0xa0 exit_to_usermode_loop+0x6d/0x99 syscall_return_slowpath+0xba/0xf0 entry_SYSCALL_64_fastpath+0xa3/0xa Fix it by making sure Node (e) is not NULL. Link: http://lkml.kernel.org/r/20171010100642.31786-1-eguan@redhat.com Fixes: 83f918274e4b ("exec: binfmt_misc: shift filp_close(interp_file) from kill_node() to bm_evict_inode()") Signed-off-by: Eryu Guan <eguan@redhat.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-10-14 06:58:18 +08:00
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: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Julia Lawall <julia@diku.dk> Cc: Christoph Hellwig <hch@infradead.org>
2010-08-16 00:52:59 +08:00
.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;
binfmt_misc: fix possible deadlock in bm_register_write There is a deadlock in bm_register_write: First, in the begining of the function, a lock is taken on the binfmt_misc root inode with inode_lock(d_inode(root)). Then, if the user used the MISC_FMT_OPEN_FILE flag, the function will call open_exec on the user-provided interpreter. open_exec will call a path lookup, and if the path lookup process includes the root of binfmt_misc, it will try to take a shared lock on its inode again, but it is already locked, and the code will get stuck in a deadlock To reproduce the bug: $ echo ":iiiii:E::ii::/proc/sys/fs/binfmt_misc/bla:F" > /proc/sys/fs/binfmt_misc/register backtrace of where the lock occurs (#5): 0 schedule () at ./arch/x86/include/asm/current.h:15 1 0xffffffff81b51237 in rwsem_down_read_slowpath (sem=0xffff888003b202e0, count=<optimized out>, state=state@entry=2) at kernel/locking/rwsem.c:992 2 0xffffffff81b5150a in __down_read_common (state=2, sem=<optimized out>) at kernel/locking/rwsem.c:1213 3 __down_read (sem=<optimized out>) at kernel/locking/rwsem.c:1222 4 down_read (sem=<optimized out>) at kernel/locking/rwsem.c:1355 5 0xffffffff811ee22a in inode_lock_shared (inode=<optimized out>) at ./include/linux/fs.h:783 6 open_last_lookups (op=0xffffc9000022fe34, file=0xffff888004098600, nd=0xffffc9000022fd10) at fs/namei.c:3177 7 path_openat (nd=nd@entry=0xffffc9000022fd10, op=op@entry=0xffffc9000022fe34, flags=flags@entry=65) at fs/namei.c:3366 8 0xffffffff811efe1c in do_filp_open (dfd=<optimized out>, pathname=pathname@entry=0xffff8880031b9000, op=op@entry=0xffffc9000022fe34) at fs/namei.c:3396 9 0xffffffff811e493f in do_open_execat (fd=fd@entry=-100, name=name@entry=0xffff8880031b9000, flags=<optimized out>, flags@entry=0) at fs/exec.c:913 10 0xffffffff811e4a92 in open_exec (name=<optimized out>) at fs/exec.c:948 11 0xffffffff8124aa84 in bm_register_write (file=<optimized out>, buffer=<optimized out>, count=19, ppos=<optimized out>) at fs/binfmt_misc.c:682 12 0xffffffff811decd2 in vfs_write (file=file@entry=0xffff888004098500, buf=buf@entry=0xa758d0 ":iiiii:E::ii::i:CF ", count=count@entry=19, pos=pos@entry=0xffffc9000022ff10) at fs/read_write.c:603 13 0xffffffff811defda in ksys_write (fd=<optimized out>, buf=0xa758d0 ":iiiii:E::ii::i:CF ", count=19) at fs/read_write.c:658 14 0xffffffff81b49813 in do_syscall_64 (nr=<optimized out>, regs=0xffffc9000022ff58) at arch/x86/entry/common.c:46 15 0xffffffff81c0007c in entry_SYSCALL_64 () at arch/x86/entry/entry_64.S:120 To solve the issue, the open_exec call is moved to before the write lock is taken by bm_register_write Link: https://lkml.kernel.org/r/20210228224414.95962-1-liorribak@gmail.com Fixes: 948b701a607f1 ("binfmt_misc: add persistent opened binary handler for containers") Signed-off-by: Lior Ribak <liorribak@gmail.com> Acked-by: Helge Deller <deller@gmx.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-03-13 13:07:41 +08:00
struct file *f = NULL;
e = create_entry(buffer, count);
if (IS_ERR(e))
return PTR_ERR(e);
binfmt_misc: fix possible deadlock in bm_register_write There is a deadlock in bm_register_write: First, in the begining of the function, a lock is taken on the binfmt_misc root inode with inode_lock(d_inode(root)). Then, if the user used the MISC_FMT_OPEN_FILE flag, the function will call open_exec on the user-provided interpreter. open_exec will call a path lookup, and if the path lookup process includes the root of binfmt_misc, it will try to take a shared lock on its inode again, but it is already locked, and the code will get stuck in a deadlock To reproduce the bug: $ echo ":iiiii:E::ii::/proc/sys/fs/binfmt_misc/bla:F" > /proc/sys/fs/binfmt_misc/register backtrace of where the lock occurs (#5): 0 schedule () at ./arch/x86/include/asm/current.h:15 1 0xffffffff81b51237 in rwsem_down_read_slowpath (sem=0xffff888003b202e0, count=<optimized out>, state=state@entry=2) at kernel/locking/rwsem.c:992 2 0xffffffff81b5150a in __down_read_common (state=2, sem=<optimized out>) at kernel/locking/rwsem.c:1213 3 __down_read (sem=<optimized out>) at kernel/locking/rwsem.c:1222 4 down_read (sem=<optimized out>) at kernel/locking/rwsem.c:1355 5 0xffffffff811ee22a in inode_lock_shared (inode=<optimized out>) at ./include/linux/fs.h:783 6 open_last_lookups (op=0xffffc9000022fe34, file=0xffff888004098600, nd=0xffffc9000022fd10) at fs/namei.c:3177 7 path_openat (nd=nd@entry=0xffffc9000022fd10, op=op@entry=0xffffc9000022fe34, flags=flags@entry=65) at fs/namei.c:3366 8 0xffffffff811efe1c in do_filp_open (dfd=<optimized out>, pathname=pathname@entry=0xffff8880031b9000, op=op@entry=0xffffc9000022fe34) at fs/namei.c:3396 9 0xffffffff811e493f in do_open_execat (fd=fd@entry=-100, name=name@entry=0xffff8880031b9000, flags=<optimized out>, flags@entry=0) at fs/exec.c:913 10 0xffffffff811e4a92 in open_exec (name=<optimized out>) at fs/exec.c:948 11 0xffffffff8124aa84 in bm_register_write (file=<optimized out>, buffer=<optimized out>, count=19, ppos=<optimized out>) at fs/binfmt_misc.c:682 12 0xffffffff811decd2 in vfs_write (file=file@entry=0xffff888004098500, buf=buf@entry=0xa758d0 ":iiiii:E::ii::i:CF ", count=count@entry=19, pos=pos@entry=0xffffc9000022ff10) at fs/read_write.c:603 13 0xffffffff811defda in ksys_write (fd=<optimized out>, buf=0xa758d0 ":iiiii:E::ii::i:CF ", count=19) at fs/read_write.c:658 14 0xffffffff81b49813 in do_syscall_64 (nr=<optimized out>, regs=0xffffc9000022ff58) at arch/x86/entry/common.c:46 15 0xffffffff81c0007c in entry_SYSCALL_64 () at arch/x86/entry/entry_64.S:120 To solve the issue, the open_exec call is moved to before the write lock is taken by bm_register_write Link: https://lkml.kernel.org/r/20210228224414.95962-1-liorribak@gmail.com Fixes: 948b701a607f1 ("binfmt_misc: add persistent opened binary handler for containers") Signed-off-by: Lior Ribak <liorribak@gmail.com> Acked-by: Helge Deller <deller@gmx.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-03-13 13:07:41 +08:00
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) {
binfmt_misc: fix possible deadlock in bm_register_write There is a deadlock in bm_register_write: First, in the begining of the function, a lock is taken on the binfmt_misc root inode with inode_lock(d_inode(root)). Then, if the user used the MISC_FMT_OPEN_FILE flag, the function will call open_exec on the user-provided interpreter. open_exec will call a path lookup, and if the path lookup process includes the root of binfmt_misc, it will try to take a shared lock on its inode again, but it is already locked, and the code will get stuck in a deadlock To reproduce the bug: $ echo ":iiiii:E::ii::/proc/sys/fs/binfmt_misc/bla:F" > /proc/sys/fs/binfmt_misc/register backtrace of where the lock occurs (#5): 0 schedule () at ./arch/x86/include/asm/current.h:15 1 0xffffffff81b51237 in rwsem_down_read_slowpath (sem=0xffff888003b202e0, count=<optimized out>, state=state@entry=2) at kernel/locking/rwsem.c:992 2 0xffffffff81b5150a in __down_read_common (state=2, sem=<optimized out>) at kernel/locking/rwsem.c:1213 3 __down_read (sem=<optimized out>) at kernel/locking/rwsem.c:1222 4 down_read (sem=<optimized out>) at kernel/locking/rwsem.c:1355 5 0xffffffff811ee22a in inode_lock_shared (inode=<optimized out>) at ./include/linux/fs.h:783 6 open_last_lookups (op=0xffffc9000022fe34, file=0xffff888004098600, nd=0xffffc9000022fd10) at fs/namei.c:3177 7 path_openat (nd=nd@entry=0xffffc9000022fd10, op=op@entry=0xffffc9000022fe34, flags=flags@entry=65) at fs/namei.c:3366 8 0xffffffff811efe1c in do_filp_open (dfd=<optimized out>, pathname=pathname@entry=0xffff8880031b9000, op=op@entry=0xffffc9000022fe34) at fs/namei.c:3396 9 0xffffffff811e493f in do_open_execat (fd=fd@entry=-100, name=name@entry=0xffff8880031b9000, flags=<optimized out>, flags@entry=0) at fs/exec.c:913 10 0xffffffff811e4a92 in open_exec (name=<optimized out>) at fs/exec.c:948 11 0xffffffff8124aa84 in bm_register_write (file=<optimized out>, buffer=<optimized out>, count=19, ppos=<optimized out>) at fs/binfmt_misc.c:682 12 0xffffffff811decd2 in vfs_write (file=file@entry=0xffff888004098500, buf=buf@entry=0xa758d0 ":iiiii:E::ii::i:CF ", count=count@entry=19, pos=pos@entry=0xffffc9000022ff10) at fs/read_write.c:603 13 0xffffffff811defda in ksys_write (fd=<optimized out>, buf=0xa758d0 ":iiiii:E::ii::i:CF ", count=19) at fs/read_write.c:658 14 0xffffffff81b49813 in do_syscall_64 (nr=<optimized out>, regs=0xffffc9000022ff58) at arch/x86/entry/common.c:46 15 0xffffffff81c0007c in entry_SYSCALL_64 () at arch/x86/entry/entry_64.S:120 To solve the issue, the open_exec call is moved to before the write lock is taken by bm_register_write Link: https://lkml.kernel.org/r/20210228224414.95962-1-liorribak@gmail.com Fixes: 948b701a607f1 ("binfmt_misc: add persistent opened binary handler for containers") Signed-off-by: Lior Ribak <liorribak@gmail.com> Acked-by: Helge Deller <deller@gmx.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-03-13 13:07:41 +08:00
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: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Julia Lawall <julia@diku.dk> Cc: Christoph Hellwig <hch@infradead.org>
2010-08-16 00:52:59 +08:00
.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: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Julia Lawall <julia@diku.dk> Cc: Christoph Hellwig <hch@infradead.org>
2010-08-16 00:52:59 +08:00
.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,
};
fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2013-03-03 11:39:14 +08:00
MODULE_ALIAS_FS("binfmt_misc");
2022-01-30 05:40:55 +08:00
static struct ctl_table_header *binfmt_misc_header;
static int __init init_misc_binfmt(void)
{
int err = register_filesystem(&bm_fs_type);
if (!err)
insert_binfmt(&misc_format);
2022-01-30 05:40:55 +08:00
binfmt_misc_header = register_sysctl_mount_point("fs/binfmt_misc");
fs: move binfmt_misc sysctl to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. This moves the binfmt_misc sysctl to its own file to help remove clutter from kernel/sysctl.c. Link: https://lkml.kernel.org/r/20211124231435.1445213-5-mcgrof@kernel.org Signed-off-by: Luis Chamberlain <mcgrof@kernel.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Amir Goldstein <amir73il@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Antti Palosaari <crope@iki.fi> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Benjamin LaHaise <bcrl@kvack.org> Cc: Clemens Ladisch <clemens@ladisch.de> Cc: David Airlie <airlied@linux.ie> Cc: Douglas Gilbert <dgilbert@interlog.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Iurii Zaikin <yzaikin@google.com> Cc: James E.J. Bottomley <jejb@linux.ibm.com> Cc: Jani Nikula <jani.nikula@intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Joel Becker <jlbec@evilplan.org> Cc: John Ogness <john.ogness@linutronix.de> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Joseph Qi <joseph.qi@linux.alibaba.com> Cc: Julia Lawall <julia.lawall@inria.fr> Cc: Kees Cook <keescook@chromium.org> Cc: Lukas Middendorf <kernel@tuxforce.de> Cc: Mark Fasheh <mark@fasheh.com> Cc: Martin K. Petersen <martin.petersen@oracle.com> Cc: Paul Turner <pjt@google.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Phillip Potter <phil@philpotter.co.uk> Cc: Qing Wang <wangqing@vivo.com> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Sebastian Reichel <sre@kernel.org> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Stephen Kitt <steve@sk2.org> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Xiaoming Ni <nixiaoming@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-22 14:12:28 +08:00
return 0;
}
static void __exit exit_misc_binfmt(void)
{
2022-01-30 05:40:55 +08:00
unregister_sysctl_table(binfmt_misc_header);
unregister_binfmt(&misc_format);
unregister_filesystem(&bm_fs_type);
}
core_initcall(init_misc_binfmt);
module_exit(exit_misc_binfmt);
MODULE_LICENSE("GPL");