mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-14 15:54:15 +08:00
6fa6d28051
do_strncpy_from_user() may copy some extra bytes after the NUL
terminator into the destination buffer. This usually does not matter for
normal string operations. However, when BPF programs key BPF maps with
strings, this matters a lot.
A BPF program may read strings from user memory by calling the
bpf_probe_read_user_str() helper which eventually calls
do_strncpy_from_user(). The program can then key a map with the
destination buffer. BPF map keys are fixed-width and string-agnostic,
meaning that map keys are treated as a set of bytes.
The issue is when do_strncpy_from_user() overcopies bytes after the NUL
terminator, it can result in seemingly identical strings occupying
multiple slots in a BPF map. This behavior is subtle and totally
unexpected by the user.
This commit masks out the bytes following the NUL while preserving
long-sized stride in the fast path.
Fixes: 6ae08ae3de
("bpf: Add probe_read_{user, kernel} and probe_read_{user, kernel}_str helpers")
Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/21efc982b3e9f2f7b0379eed642294caaa0c27a7.1605642949.git.dxu@dxuuu.xyz
147 lines
3.9 KiB
C
147 lines
3.9 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <linux/compiler.h>
|
|
#include <linux/export.h>
|
|
#include <linux/fault-inject-usercopy.h>
|
|
#include <linux/kasan-checks.h>
|
|
#include <linux/thread_info.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/mm.h>
|
|
|
|
#include <asm/byteorder.h>
|
|
#include <asm/word-at-a-time.h>
|
|
|
|
#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
|
|
#define IS_UNALIGNED(src, dst) 0
|
|
#else
|
|
#define IS_UNALIGNED(src, dst) \
|
|
(((long) dst | (long) src) & (sizeof(long) - 1))
|
|
#endif
|
|
|
|
/*
|
|
* Do a strncpy, return length of string without final '\0'.
|
|
* 'count' is the user-supplied count (return 'count' if we
|
|
* hit it), 'max' is the address space maximum (and we return
|
|
* -EFAULT if we hit it).
|
|
*/
|
|
static inline long do_strncpy_from_user(char *dst, const char __user *src,
|
|
unsigned long count, unsigned long max)
|
|
{
|
|
const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
|
|
unsigned long res = 0;
|
|
|
|
if (IS_UNALIGNED(src, dst))
|
|
goto byte_at_a_time;
|
|
|
|
while (max >= sizeof(unsigned long)) {
|
|
unsigned long c, data, mask;
|
|
|
|
/* Fall back to byte-at-a-time if we get a page fault */
|
|
unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time);
|
|
|
|
/*
|
|
* Note that we mask out the bytes following the NUL. This is
|
|
* important to do because string oblivious code may read past
|
|
* the NUL. For those routines, we don't want to give them
|
|
* potentially random bytes after the NUL in `src`.
|
|
*
|
|
* One example of such code is BPF map keys. BPF treats map keys
|
|
* as an opaque set of bytes. Without the post-NUL mask, any BPF
|
|
* maps keyed by strings returned from strncpy_from_user() may
|
|
* have multiple entries for semantically identical strings.
|
|
*/
|
|
if (has_zero(c, &data, &constants)) {
|
|
data = prep_zero_mask(c, data, &constants);
|
|
data = create_zero_mask(data);
|
|
mask = zero_bytemask(data);
|
|
*(unsigned long *)(dst+res) = c & mask;
|
|
return res + find_zero(data);
|
|
}
|
|
|
|
*(unsigned long *)(dst+res) = c;
|
|
|
|
res += sizeof(unsigned long);
|
|
max -= sizeof(unsigned long);
|
|
}
|
|
|
|
byte_at_a_time:
|
|
while (max) {
|
|
char c;
|
|
|
|
unsafe_get_user(c,src+res, efault);
|
|
dst[res] = c;
|
|
if (!c)
|
|
return res;
|
|
res++;
|
|
max--;
|
|
}
|
|
|
|
/*
|
|
* Uhhuh. We hit 'max'. But was that the user-specified maximum
|
|
* too? If so, that's ok - we got as much as the user asked for.
|
|
*/
|
|
if (res >= count)
|
|
return res;
|
|
|
|
/*
|
|
* Nope: we hit the address space limit, and we still had more
|
|
* characters the caller would have wanted. That's an EFAULT.
|
|
*/
|
|
efault:
|
|
return -EFAULT;
|
|
}
|
|
|
|
/**
|
|
* strncpy_from_user: - Copy a NUL terminated string from userspace.
|
|
* @dst: Destination address, in kernel space. This buffer must be at
|
|
* least @count bytes long.
|
|
* @src: Source address, in user space.
|
|
* @count: Maximum number of bytes to copy, including the trailing NUL.
|
|
*
|
|
* Copies a NUL-terminated string from userspace to kernel space.
|
|
*
|
|
* On success, returns the length of the string (not including the trailing
|
|
* NUL).
|
|
*
|
|
* If access to userspace fails, returns -EFAULT (some data may have been
|
|
* copied).
|
|
*
|
|
* If @count is smaller than the length of the string, copies @count bytes
|
|
* and returns @count.
|
|
*/
|
|
long strncpy_from_user(char *dst, const char __user *src, long count)
|
|
{
|
|
unsigned long max_addr, src_addr;
|
|
|
|
might_fault();
|
|
if (should_fail_usercopy())
|
|
return -EFAULT;
|
|
if (unlikely(count <= 0))
|
|
return 0;
|
|
|
|
max_addr = user_addr_max();
|
|
src_addr = (unsigned long)untagged_addr(src);
|
|
if (likely(src_addr < max_addr)) {
|
|
unsigned long max = max_addr - src_addr;
|
|
long retval;
|
|
|
|
/*
|
|
* Truncate 'max' to the user-specified limit, so that
|
|
* we only have one limit we need to check in the loop
|
|
*/
|
|
if (max > count)
|
|
max = count;
|
|
|
|
kasan_check_write(dst, count);
|
|
check_object_size(dst, count, false);
|
|
if (user_read_access_begin(src, max)) {
|
|
retval = do_strncpy_from_user(dst, src, count, max);
|
|
user_read_access_end();
|
|
return retval;
|
|
}
|
|
}
|
|
return -EFAULT;
|
|
}
|
|
EXPORT_SYMBOL(strncpy_from_user);
|