uaccess: Add strict non-pagefault kernel-space read function

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

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

1 files changed, 24 insertions, 1 deletions

diff --git a/mm/maccess.c b/mm/maccess.c
index 2d3c3d01064c..3ca8d97e5010 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -43,11 +43,20 @@ probe_write_common(void __user *dst, const void *src, size_t size)
  * 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.
+ *
+ * probe_kernel_read_strict() is the same as probe_kernel_read() except for
+ * the case where architectures have non-overlapping user and kernel address
+ * ranges: probe_kernel_read_strict() will additionally return -EFAULT for
+ * probing memory on a user address range where probe_user_read() is supposed
+ * to be used instead.
  */
 
 long __weak probe_kernel_read(void *dst, const void *src, size_t size)
     __attribute__((alias("__probe_kernel_read")));
 
+long __weak probe_kernel_read_strict(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;
@@ -157,8 +166,22 @@ EXPORT_SYMBOL_GPL(probe_user_write);
  *
  * 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.
+ *
+ * strncpy_from_unsafe_strict() is the same as strncpy_from_unsafe() except
+ * for the case where architectures have non-overlapping user and kernel address
+ * ranges: strncpy_from_unsafe_strict() will additionally return -EFAULT for
+ * probing memory on a user address range where strncpy_from_unsafe_user() is
+ * supposed to be used instead.
  */
-long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)
+
+long __weak strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)
+    __attribute__((alias("__strncpy_from_unsafe")));
+
+long __weak strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr,
+				       long count)
+    __attribute__((alias("__strncpy_from_unsafe")));
+
+long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)
 {
 	mm_segment_t old_fs = get_fs();
 	const void *src = unsafe_addr;