arm/syscalls: Check address limit on user-mode return

Ensure the address limit is a user-mode segment before returning to
user-mode. Otherwise a process can corrupt kernel-mode memory and
elevate privileges [1].

The set_fs function sets the TIF_SETFS flag to force a slow path on
return. In the slow path, the address limit is checked to be USER_DS if
needed.

The TIF_SETFS flag is added to _TIF_WORK_MASK shifting _TIF_SYSCALL_WORK
for arm instruction immediate support. The global work mask is too big
to used on a single instruction so adapt ret_fast_syscall.

[1] https://bugs.chromium.org/p/project-zero/issues/detail?id=990

Signed-off-by: Thomas Garnier <thgarnie@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: kernel-hardening@lists.openwall.com
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Miroslav Benes <mbenes@suse.cz>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Pratyush Anand <panand@redhat.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Petr Mladek <pmladek@suse.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Will Drewry <wad@chromium.org>
Cc: linux-api@vger.kernel.org
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Link: http://lkml.kernel.org/r/20170615011203.144108-2-thgarnie@google.com
This commit is contained in:
Thomas Garnier 2017-06-14 18:12:02 -07:00 committed by Thomas Gleixner
parent 5ea0727b16
commit 73ac5d6a2b
4 changed files with 23 additions and 8 deletions

View file

@ -139,10 +139,11 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
#define TIF_NEED_RESCHED 1 /* rescheduling necessary */
#define TIF_NOTIFY_RESUME 2 /* callback before returning to user */
#define TIF_UPROBE 3 /* breakpointed or singlestepping */
#define TIF_SYSCALL_TRACE 4 /* syscall trace active */
#define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */
#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */
#define TIF_SECCOMP 7 /* seccomp syscall filtering active */
#define TIF_FSCHECK 4 /* Check FS is USER_DS on return */
#define TIF_SYSCALL_TRACE 5 /* syscall trace active */
#define TIF_SYSCALL_AUDIT 6 /* syscall auditing active */
#define TIF_SYSCALL_TRACEPOINT 7 /* syscall tracepoint instrumentation */
#define TIF_SECCOMP 8 /* seccomp syscall filtering active */
#define TIF_NOHZ 12 /* in adaptive nohz mode */
#define TIF_USING_IWMMXT 17
@ -153,6 +154,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
#define _TIF_UPROBE (1 << TIF_UPROBE)
#define _TIF_FSCHECK (1 << TIF_FSCHECK)
#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
@ -167,7 +169,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
* Change these and you break ASM code in entry-common.S
*/
#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
_TIF_NOTIFY_RESUME | _TIF_UPROBE)
_TIF_NOTIFY_RESUME | _TIF_UPROBE | \
_TIF_FSCHECK)
#endif /* __KERNEL__ */
#endif /* __ASM_ARM_THREAD_INFO_H */

View file

@ -77,6 +77,8 @@ static inline void set_fs(mm_segment_t fs)
{
current_thread_info()->addr_limit = fs;
modify_domain(DOMAIN_KERNEL, fs ? DOMAIN_CLIENT : DOMAIN_MANAGER);
/* On user-mode return, check fs is correct */
set_thread_flag(TIF_FSCHECK);
}
#define segment_eq(a, b) ((a) == (b))

View file

@ -41,7 +41,9 @@ ret_fast_syscall:
UNWIND(.cantunwind )
disable_irq_notrace @ disable interrupts
ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
tst r1, #_TIF_SYSCALL_WORK
bne fast_work_pending
tst r1, #_TIF_WORK_MASK
bne fast_work_pending
/* perform architecture specific actions before user return */
@ -67,12 +69,15 @@ ret_fast_syscall:
str r0, [sp, #S_R0 + S_OFF]! @ save returned r0
disable_irq_notrace @ disable interrupts
ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
tst r1, #_TIF_SYSCALL_WORK
bne fast_work_pending
tst r1, #_TIF_WORK_MASK
beq no_work_pending
UNWIND(.fnend )
ENDPROC(ret_fast_syscall)
/* Slower path - fall through to work_pending */
fast_work_pending:
#endif
tst r1, #_TIF_SYSCALL_WORK

View file

@ -14,6 +14,7 @@
#include <linux/uaccess.h>
#include <linux/tracehook.h>
#include <linux/uprobes.h>
#include <linux/syscalls.h>
#include <asm/elf.h>
#include <asm/cacheflush.h>
@ -571,6 +572,10 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
* Update the trace code with the current status.
*/
trace_hardirqs_off();
/* Check valid user FS if needed */
addr_limit_user_check();
do {
if (likely(thread_flags & _TIF_NEED_RESCHED)) {
schedule();