Files
kernel_google_wahoo/include/linux/thread_info.h
Kees Cook 1e40064214 fork: unconditionally clear stack on fork
commit e01e80634ecdde1dd113ac43b3adad21b47f3957 upstream.

One of the classes of kernel stack content leaks[1] is exposing the
contents of prior heap or stack contents when a new process stack is
allocated.  Normally, those stacks are not zeroed, and the old contents
remain in place.  In the face of stack content exposure flaws, those
contents can leak to userspace.

Fixing this will make the kernel no longer vulnerable to these flaws, as
the stack will be wiped each time a stack is assigned to a new process.
There's not a meaningful change in runtime performance; it almost looks
like it provides a benefit.

Performing back-to-back kernel builds before:
	Run times: 157.86 157.09 158.90 160.94 160.80
	Mean: 159.12
	Std Dev: 1.54

and after:
	Run times: 159.31 157.34 156.71 158.15 160.81
	Mean: 158.46
	Std Dev: 1.46

Instead of making this a build or runtime config, Andy Lutomirski
recommended this just be enabled by default.

[1] A noisy search for many kinds of stack content leaks can be seen here:
https://cve.mitre.org/cgi-bin/cvekey.cgi?keyword=linux+kernel+stack+leak

I did some more with perf and cycle counts on running 100,000 execs of
/bin/true.

before:
Cycles: 218858861551 218853036130 214727610969 227656844122 224980542841
Mean:  221015379122.60
Std Dev: 4662486552.47

after:
Cycles: 213868945060 213119275204 211820169456 224426673259 225489986348
Mean:  217745009865.40
Std Dev: 5935559279.99

It continues to look like it's faster, though the deviation is rather
wide, but I'm not sure what I could do that would be less noisy.  I'm
open to ideas!

Link: http://lkml.kernel.org/r/20180221021659.GA37073@beast
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Laura Abbott <labbott@redhat.com>
Cc: Rasmus Villemoes <rasmus.villemoes@prevas.dk>
Cc: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ Srivatsa: Backported to 4.4.y ]
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Srinidhi Rao <srinidhir@vmware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-08-15 17:42:05 +02:00

147 lines
3.8 KiB
C

/* thread_info.h: common low-level thread information accessors
*
* Copyright (C) 2002 David Howells (dhowells@redhat.com)
* - Incorporating suggestions made by Linus Torvalds
*/
#ifndef _LINUX_THREAD_INFO_H
#define _LINUX_THREAD_INFO_H
#include <linux/types.h>
#include <linux/bug.h>
struct timespec;
struct compat_timespec;
/*
* System call restart block.
*/
struct restart_block {
long (*fn)(struct restart_block *);
union {
/* For futex_wait and futex_wait_requeue_pi */
struct {
u32 __user *uaddr;
u32 val;
u32 flags;
u32 bitset;
u64 time;
u32 __user *uaddr2;
} futex;
/* For nanosleep */
struct {
clockid_t clockid;
struct timespec __user *rmtp;
#ifdef CONFIG_COMPAT
struct compat_timespec __user *compat_rmtp;
#endif
u64 expires;
} nanosleep;
/* For poll */
struct {
struct pollfd __user *ufds;
int nfds;
int has_timeout;
unsigned long tv_sec;
unsigned long tv_nsec;
} poll;
};
};
extern long do_no_restart_syscall(struct restart_block *parm);
#include <linux/bitops.h>
#include <asm/thread_info.h>
#ifdef __KERNEL__
#define THREADINFO_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
/*
* flag set/clear/test wrappers
* - pass TIF_xxxx constants to these functions
*/
static inline void set_ti_thread_flag(struct thread_info *ti, int flag)
{
set_bit(flag, (unsigned long *)&ti->flags);
}
static inline void clear_ti_thread_flag(struct thread_info *ti, int flag)
{
clear_bit(flag, (unsigned long *)&ti->flags);
}
static inline int test_and_set_ti_thread_flag(struct thread_info *ti, int flag)
{
return test_and_set_bit(flag, (unsigned long *)&ti->flags);
}
static inline int test_and_clear_ti_thread_flag(struct thread_info *ti, int flag)
{
return test_and_clear_bit(flag, (unsigned long *)&ti->flags);
}
static inline int test_ti_thread_flag(struct thread_info *ti, int flag)
{
return test_bit(flag, (unsigned long *)&ti->flags);
}
#define set_thread_flag(flag) \
set_ti_thread_flag(current_thread_info(), flag)
#define clear_thread_flag(flag) \
clear_ti_thread_flag(current_thread_info(), flag)
#define test_and_set_thread_flag(flag) \
test_and_set_ti_thread_flag(current_thread_info(), flag)
#define test_and_clear_thread_flag(flag) \
test_and_clear_ti_thread_flag(current_thread_info(), flag)
#define test_thread_flag(flag) \
test_ti_thread_flag(current_thread_info(), flag)
#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
#if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK
/*
* An arch can define its own version of set_restore_sigmask() to get the
* job done however works, with or without TIF_RESTORE_SIGMASK.
*/
#define HAVE_SET_RESTORE_SIGMASK 1
/**
* set_restore_sigmask() - make sure saved_sigmask processing gets done
*
* This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code
* will run before returning to user mode, to process the flag. For
* all callers, TIF_SIGPENDING is already set or it's no harm to set
* it. TIF_RESTORE_SIGMASK need not be in the set of bits that the
* arch code will notice on return to user mode, in case those bits
* are scarce. We set TIF_SIGPENDING here to ensure that the arch
* signal code always gets run when TIF_RESTORE_SIGMASK is set.
*/
static inline void set_restore_sigmask(void)
{
set_thread_flag(TIF_RESTORE_SIGMASK);
WARN_ON(!test_thread_flag(TIF_SIGPENDING));
}
static inline void clear_restore_sigmask(void)
{
clear_thread_flag(TIF_RESTORE_SIGMASK);
}
static inline bool test_restore_sigmask(void)
{
return test_thread_flag(TIF_RESTORE_SIGMASK);
}
static inline bool test_and_clear_restore_sigmask(void)
{
return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK);
}
#endif /* TIF_RESTORE_SIGMASK && !HAVE_SET_RESTORE_SIGMASK */
#ifndef HAVE_SET_RESTORE_SIGMASK
#error "no set_restore_sigmask() provided and default one won't work"
#endif
#endif /* __KERNEL__ */
#endif /* _LINUX_THREAD_INFO_H */