linux_dsm_epyc7002/include/linux/sched/task_stack.h
Elena Reshetova f0b89d3958 sched/core: Convert task_struct.stack_refcount to refcount_t
atomic_t variables are currently used to implement reference
counters with the following properties:

 - counter is initialized to 1 using atomic_set()
 - a resource is freed upon counter reaching zero
 - once counter reaches zero, its further
   increments aren't allowed
 - counter schema uses basic atomic operations
   (set, inc, inc_not_zero, dec_and_test, etc.)

Such atomic variables should be converted to a newly provided
refcount_t type and API that prevents accidental counter overflows
and underflows. This is important since overflows and underflows
can lead to use-after-free situation and be exploitable.

The variable task_struct.stack_refcount is used as pure reference counter.
Convert it to refcount_t and fix up the operations.

** Important note for maintainers:

Some functions from refcount_t API defined in lib/refcount.c
have different memory ordering guarantees than their atomic
counterparts.

The full comparison can be seen in
https://lkml.org/lkml/2017/11/15/57 and it is hopefully soon
in state to be merged to the documentation tree.

Normally the differences should not matter since refcount_t provides
enough guarantees to satisfy the refcounting use cases, but in
some rare cases it might matter.

Please double check that you don't have some undocumented
memory guarantees for this variable usage.

For the task_struct.stack_refcount it might make a difference
in following places:

 - try_get_task_stack(): increment in refcount_inc_not_zero() only
   guarantees control dependency on success vs. fully ordered
   atomic counterpart
 - put_task_stack(): decrement in refcount_dec_and_test() only
   provides RELEASE ordering and control dependency on success
   vs. fully ordered atomic counterpart

Suggested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: David Windsor <dwindsor@gmail.com>
Reviewed-by: Hans Liljestrand <ishkamiel@gmail.com>
Reviewed-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: akpm@linux-foundation.org
Cc: viro@zeniv.linux.org.uk
Link: https://lkml.kernel.org/r/1547814450-18902-6-git-send-email-elena.reshetova@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-02-04 08:53:56 +01:00

123 lines
2.9 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SCHED_TASK_STACK_H
#define _LINUX_SCHED_TASK_STACK_H
/*
* task->stack (kernel stack) handling interfaces:
*/
#include <linux/sched.h>
#include <linux/magic.h>
#ifdef CONFIG_THREAD_INFO_IN_TASK
/*
* When accessing the stack of a non-current task that might exit, use
* try_get_task_stack() instead. task_stack_page will return a pointer
* that could get freed out from under you.
*/
static inline void *task_stack_page(const struct task_struct *task)
{
return task->stack;
}
#define setup_thread_stack(new,old) do { } while(0)
static inline unsigned long *end_of_stack(const struct task_struct *task)
{
return task->stack;
}
#elif !defined(__HAVE_THREAD_FUNCTIONS)
#define task_stack_page(task) ((void *)(task)->stack)
static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org)
{
*task_thread_info(p) = *task_thread_info(org);
task_thread_info(p)->task = p;
}
/*
* Return the address of the last usable long on the stack.
*
* When the stack grows down, this is just above the thread
* info struct. Going any lower will corrupt the threadinfo.
*
* When the stack grows up, this is the highest address.
* Beyond that position, we corrupt data on the next page.
*/
static inline unsigned long *end_of_stack(struct task_struct *p)
{
#ifdef CONFIG_STACK_GROWSUP
return (unsigned long *)((unsigned long)task_thread_info(p) + THREAD_SIZE) - 1;
#else
return (unsigned long *)(task_thread_info(p) + 1);
#endif
}
#endif
#ifdef CONFIG_THREAD_INFO_IN_TASK
static inline void *try_get_task_stack(struct task_struct *tsk)
{
return refcount_inc_not_zero(&tsk->stack_refcount) ?
task_stack_page(tsk) : NULL;
}
extern void put_task_stack(struct task_struct *tsk);
#else
static inline void *try_get_task_stack(struct task_struct *tsk)
{
return task_stack_page(tsk);
}
static inline void put_task_stack(struct task_struct *tsk) {}
#endif
#define task_stack_end_corrupted(task) \
(*(end_of_stack(task)) != STACK_END_MAGIC)
static inline int object_is_on_stack(const void *obj)
{
void *stack = task_stack_page(current);
return (obj >= stack) && (obj < (stack + THREAD_SIZE));
}
extern void thread_stack_cache_init(void);
#ifdef CONFIG_DEBUG_STACK_USAGE
static inline unsigned long stack_not_used(struct task_struct *p)
{
unsigned long *n = end_of_stack(p);
do { /* Skip over canary */
# ifdef CONFIG_STACK_GROWSUP
n--;
# else
n++;
# endif
} while (!*n);
# ifdef CONFIG_STACK_GROWSUP
return (unsigned long)end_of_stack(p) - (unsigned long)n;
# else
return (unsigned long)n - (unsigned long)end_of_stack(p);
# endif
}
#endif
extern void set_task_stack_end_magic(struct task_struct *tsk);
#ifndef __HAVE_ARCH_KSTACK_END
static inline int kstack_end(void *addr)
{
/* Reliable end of stack detection:
* Some APM bios versions misalign the stack
*/
return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*)));
}
#endif
#endif /* _LINUX_SCHED_TASK_STACK_H */