Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel os linux

proc: protect mm start_code/end_code in /proc/pid/stat

While mm->start_stack was protected from cross-uid viewing (commit
f83ce3e6b02d5 ("proc: avoid information leaks to non-privileged
processes")), the start_code and end_code values were not. This would
allow the text location of a PIE binary to leak, defeating ASLR.

Note that the value "1" is used instead of "0" for a protected value since
"ps", "killall", and likely other readers of /proc/pid/stat, take
start_code of "0" to mean a kernel thread and will misbehave. Thanks to
Brad Spengler for pointing this out.

Addresses CVE-2011-0726

Signed-off-by: Kees Cook <kees.cook@canonical.com>
Cc: <stable@kernel.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Eugene Teo <eugeneteo@kernel.sg>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Brad Spengler <spender@grsecurity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

authored by

Kees Cook and committed by
Linus Torvalds
5883f57c 312ec7e5

+2 -2
+2 -2
fs/proc/array.c
··· 489 489 vsize, 490 490 mm ? get_mm_rss(mm) : 0, 491 491 rsslim, 492 - mm ? mm->start_code : 0, 493 - mm ? mm->end_code : 0, 492 + mm ? (permitted ? mm->start_code : 1) : 0, 493 + mm ? (permitted ? mm->end_code : 1) : 0, 494 494 (permitted && mm) ? mm->start_stack : 0, 495 495 esp, 496 496 eip,