Add two new probe_kernel_read_strict() and strncpy_from_unsafe_strict()
helpers which by default alias to the __probe_kernel_read() and the
__strncpy_from_unsafe(), respectively, but can be overridden by archs
which have non-overlapping address ranges for kernel space and user
space in order to bail out with -EFAULT when attempting to probe user
memory including non-canonical user access addresses [0]:
4-level page tables:
user-space mem: 0x0000000000000000 - 0x00007fffffffffff
non-canonical: 0x0000800000000000 - 0xffff7fffffffffff
5-level page tables:
user-space mem: 0x0000000000000000 - 0x00ffffffffffffff
non-canonical: 0x0100000000000000 - 0xfeffffffffffffff
The idea is that these helpers are complementary to the probe_user_read()
and strncpy_from_unsafe_user() which probe user-only memory. Both added
helpers here do the same, but for kernel-only addresses.
Both set of helpers are going to be used for BPF tracing. They also
explicitly avoid throwing the splat for non-canonical user addresses from
00c42373d397 ("x86-64: add warning for non-canonical user access address
dereferences").
For compat, the current probe_kernel_read() and strncpy_from_unsafe() are
left as-is.
[0] Documentation/x86/x86_64/mm.txt
Change-Id: I1256fa00e1869a14519e186a89d5ab65f9fcbc29
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: x86@kernel.org
Link: https://lore.kernel.org/bpf/eefeefd769aa5a013531f491a71f0936779e916b.1572649915.git.daniel@iogearbox.net
Signed-off-by: Sorayukii <sorayukii69@gmail.com>
154 lines
5 KiB
C
154 lines
5 KiB
C
#ifndef __LINUX_UACCESS_H__
|
|
#define __LINUX_UACCESS_H__
|
|
|
|
#include <linux/sched.h>
|
|
|
|
#define uaccess_kernel() segment_eq(get_fs(), KERNEL_DS)
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
static __always_inline void pagefault_disabled_inc(void)
|
|
{
|
|
current->pagefault_disabled++;
|
|
}
|
|
|
|
static __always_inline void pagefault_disabled_dec(void)
|
|
{
|
|
current->pagefault_disabled--;
|
|
WARN_ON(current->pagefault_disabled < 0);
|
|
}
|
|
|
|
/*
|
|
* These routines enable/disable the pagefault handler. If disabled, it will
|
|
* not take any locks and go straight to the fixup table.
|
|
*
|
|
* User access methods will not sleep when called from a pagefault_disabled()
|
|
* environment.
|
|
*/
|
|
static inline void pagefault_disable(void)
|
|
{
|
|
pagefault_disabled_inc();
|
|
/*
|
|
* make sure to have issued the store before a pagefault
|
|
* can hit.
|
|
*/
|
|
barrier();
|
|
}
|
|
|
|
static inline void pagefault_enable(void)
|
|
{
|
|
/*
|
|
* make sure to issue those last loads/stores before enabling
|
|
* the pagefault handler again.
|
|
*/
|
|
barrier();
|
|
pagefault_disabled_dec();
|
|
}
|
|
|
|
/*
|
|
* Is the pagefault handler disabled? If so, user access methods will not sleep.
|
|
*/
|
|
#define pagefault_disabled() (current->pagefault_disabled != 0)
|
|
|
|
/*
|
|
* The pagefault handler is in general disabled by pagefault_disable() or
|
|
* when in irq context (via in_atomic()).
|
|
*
|
|
* This function should only be used by the fault handlers. Other users should
|
|
* stick to pagefault_disabled().
|
|
* Please NEVER use preempt_disable() to disable the fault handler. With
|
|
* !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled.
|
|
* in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT.
|
|
*/
|
|
#define faulthandler_disabled() (pagefault_disabled() || in_atomic())
|
|
|
|
#ifndef ARCH_HAS_NOCACHE_UACCESS
|
|
|
|
static inline unsigned long __copy_from_user_inatomic_nocache(void *to,
|
|
const void __user *from, unsigned long n)
|
|
{
|
|
return __copy_from_user_inatomic(to, from, n);
|
|
}
|
|
|
|
static inline unsigned long __copy_from_user_nocache(void *to,
|
|
const void __user *from, unsigned long n)
|
|
{
|
|
return __copy_from_user(to, from, n);
|
|
}
|
|
|
|
#endif /* ARCH_HAS_NOCACHE_UACCESS */
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
extern long probe_kernel_read(void *dst, const void *src, size_t size);
|
|
extern long probe_kernel_read_strict(void *dst, const void *src, size_t size);
|
|
extern long __probe_kernel_read(void *dst, const void *src, size_t size);
|
|
|
|
/*
|
|
* probe_user_read(): safely attempt to read from a location in user space
|
|
* @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.
|
|
*/
|
|
extern long probe_user_read(void *dst, const void __user *src, size_t size);
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
extern long notrace probe_kernel_write(void *dst, const void *src, size_t size);
|
|
extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size);
|
|
|
|
/*
|
|
* probe_user_write(): safely attempt to write to a location in user space
|
|
* @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.
|
|
*/
|
|
extern long notrace probe_user_write(void __user *dst, const void *src, size_t size);
|
|
extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size);
|
|
|
|
extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
|
|
extern long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr,
|
|
long count);
|
|
extern long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
|
|
extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr,
|
|
long count);
|
|
extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count);
|
|
|
|
/**
|
|
* probe_kernel_address(): safely attempt to read from a location
|
|
* @addr: address to read from
|
|
* @retval: read into this variable
|
|
*
|
|
* Returns 0 on success, or -EFAULT.
|
|
*/
|
|
#define probe_kernel_address(addr, retval) \
|
|
probe_kernel_read(&retval, addr, sizeof(retval))
|
|
|
|
#ifndef user_access_begin
|
|
#define user_access_begin(ptr,len) access_ok(VERIFY_READ, ptr, len)
|
|
#define user_access_end() do { } while (0)
|
|
#define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0)
|
|
#define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0)
|
|
#endif
|
|
|
|
#endif /* __LINUX_UACCESS_H__ */
|