9da3f2b740
There have been multiple kernel vulnerabilities that permitted userspace to
pass completely unchecked pointers through to userspace accessors:
- the waitid() bug - commit 96ca579a1e
("waitid(): Add missing
access_ok() checks")
- the sg/bsg read/write APIs
- the infiniband read/write APIs
These don't happen all that often, but when they do happen, it is hard to
test for them properly; and it is probably also hard to discover them with
fuzzing. Even when an unmapped kernel address is supplied to such buggy
code, it just returns -EFAULT instead of doing a proper BUG() or at least
WARN().
Try to make such misbehaving code a bit more visible by refusing to do a
fixup in the pagefault handler code when a userspace accessor causes a #PF
on a kernel address and the current context isn't whitelisted.
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Kees Cook <keescook@chromium.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: kernel-hardening@lists.openwall.com
Cc: dvyukov@google.com
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Cc: Borislav Petkov <bp@alien8.de>
Link: https://lkml.kernel.org/r/20180828201421.157735-7-jannh@google.com
114 lines
3.3 KiB
C
114 lines
3.3 KiB
C
/*
|
|
* Access kernel memory without faulting.
|
|
*/
|
|
#include <linux/export.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/uaccess.h>
|
|
|
|
/**
|
|
* probe_kernel_read(): safely attempt to read from a location
|
|
* @dst: pointer to the buffer that shall take the data
|
|
* @src: address to read from
|
|
* @size: size of the data chunk
|
|
*
|
|
* Safely read from address @src to the buffer at @dst. If a kernel fault
|
|
* happens, handle that and return -EFAULT.
|
|
*
|
|
* We ensure that the copy_from_user is executed in atomic context so that
|
|
* do_page_fault() doesn't attempt to take mmap_sem. This makes
|
|
* probe_kernel_read() suitable for use within regions where the caller
|
|
* already holds mmap_sem, or other locks which nest inside mmap_sem.
|
|
*/
|
|
|
|
long __weak probe_kernel_read(void *dst, const void *src, size_t size)
|
|
__attribute__((alias("__probe_kernel_read")));
|
|
|
|
long __probe_kernel_read(void *dst, const void *src, size_t size)
|
|
{
|
|
long ret;
|
|
mm_segment_t old_fs = get_fs();
|
|
|
|
set_fs(KERNEL_DS);
|
|
pagefault_disable();
|
|
current->kernel_uaccess_faults_ok++;
|
|
ret = __copy_from_user_inatomic(dst,
|
|
(__force const void __user *)src, size);
|
|
current->kernel_uaccess_faults_ok--;
|
|
pagefault_enable();
|
|
set_fs(old_fs);
|
|
|
|
return ret ? -EFAULT : 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(probe_kernel_read);
|
|
|
|
/**
|
|
* probe_kernel_write(): safely attempt to write to a location
|
|
* @dst: address to write to
|
|
* @src: pointer to the data that shall be written
|
|
* @size: size of the data chunk
|
|
*
|
|
* Safely write to address @dst from the buffer at @src. If a kernel fault
|
|
* happens, handle that and return -EFAULT.
|
|
*/
|
|
long __weak probe_kernel_write(void *dst, const void *src, size_t size)
|
|
__attribute__((alias("__probe_kernel_write")));
|
|
|
|
long __probe_kernel_write(void *dst, const void *src, size_t size)
|
|
{
|
|
long ret;
|
|
mm_segment_t old_fs = get_fs();
|
|
|
|
set_fs(KERNEL_DS);
|
|
pagefault_disable();
|
|
current->kernel_uaccess_faults_ok++;
|
|
ret = __copy_to_user_inatomic((__force void __user *)dst, src, size);
|
|
current->kernel_uaccess_faults_ok--;
|
|
pagefault_enable();
|
|
set_fs(old_fs);
|
|
|
|
return ret ? -EFAULT : 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(probe_kernel_write);
|
|
|
|
/**
|
|
* strncpy_from_unsafe: - Copy a NUL terminated string from unsafe address.
|
|
* @dst: Destination address, in kernel space. This buffer must be at
|
|
* least @count bytes long.
|
|
* @unsafe_addr: Unsafe address.
|
|
* @count: Maximum number of bytes to copy, including the trailing NUL.
|
|
*
|
|
* Copies a NUL-terminated string from unsafe address to kernel buffer.
|
|
*
|
|
* On success, returns the length of the string INCLUDING the trailing NUL.
|
|
*
|
|
* If access fails, returns -EFAULT (some data may have been copied
|
|
* and the trailing NUL added).
|
|
*
|
|
* If @count is smaller than the length of the string, copies @count-1 bytes,
|
|
* sets the last byte of @dst buffer to NUL and returns @count.
|
|
*/
|
|
long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)
|
|
{
|
|
mm_segment_t old_fs = get_fs();
|
|
const void *src = unsafe_addr;
|
|
long ret;
|
|
|
|
if (unlikely(count <= 0))
|
|
return 0;
|
|
|
|
set_fs(KERNEL_DS);
|
|
pagefault_disable();
|
|
current->kernel_uaccess_faults_ok++;
|
|
|
|
do {
|
|
ret = __get_user(*dst++, (const char __user __force *)src++);
|
|
} while (dst[-1] && ret == 0 && src - unsafe_addr < count);
|
|
|
|
current->kernel_uaccess_faults_ok--;
|
|
dst[-1] = '\0';
|
|
pagefault_enable();
|
|
set_fs(old_fs);
|
|
|
|
return ret ? -EFAULT : src - unsafe_addr;
|
|
}
|