Commit 6111da34 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'for-3.17-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup 

Pull cgroup fixes from Tejun Heo:
 "This is quite late but these need to be backported anyway.

  This is the fix for a long-standing cpuset bug which existed from
  2009.  cpuset makes use of PF_SPREAD_{PAGE|SLAB} flags to modify the
  task's memory allocation behavior according to the settings of the
  cpuset it belongs to; unfortunately, when those flags have to be
  changed, cpuset did so directly even whlie the target task is running,
  which is obviously racy as task->flags may be modified by the task
  itself at any time.  This obscure bug manifested as corrupt
  PF_USED_MATH flag leading to a weird crash.

  The bug is fixed by moving the flag to task->atomic_flags.  The first
  two are prepatory ones to help defining atomic_flags accessors and the
  third one is the actual fix"

* 'for-3.17-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cpuset: PF_SPREAD_PAGE and PF_SPREAD_SLAB should be atomic flags
  sched: add macros to define bitops for task atomic flags
  sched: fix confusing PFA_NO_NEW_PRIVS constant
parents 83692898 2ad654bc

Documentation/cgroups/cpusets.txt

+3 −3
Original line number Original line Diff line number Diff line
@@ -345,14 +345,14 @@ the named feature on. 
The implementation is simple.

The implementation is simple.





Setting the flag 'cpuset.memory_spread_page' turns on a per-process flag

Setting the flag 'cpuset.memory_spread_page' turns on a per-process flag

PF_SPREAD_PAGE for each task that is in that cpuset or subsequently

PFA_SPREAD_PAGE for each task that is in that cpuset or subsequently

joins that cpuset.  The page allocation calls for the page cache

joins that cpuset.  The page allocation calls for the page cache

is modified to perform an inline check for this PF_SPREAD_PAGE task

is modified to perform an inline check for this PFA_SPREAD_PAGE task

flag, and if set, a call to a new routine cpuset_mem_spread_node()

flag, and if set, a call to a new routine cpuset_mem_spread_node()

returns the node to prefer for the allocation.

returns the node to prefer for the allocation.





Similarly, setting 'cpuset.memory_spread_slab' turns on the flag

Similarly, setting 'cpuset.memory_spread_slab' turns on the flag

PF_SPREAD_SLAB, and appropriately marked slab caches will allocate

PFA_SPREAD_SLAB, and appropriately marked slab caches will allocate

pages from the node returned by cpuset_mem_spread_node().

pages from the node returned by cpuset_mem_spread_node().





The cpuset_mem_spread_node() routine is also simple.  It uses the

The cpuset_mem_spread_node() routine is also simple.  It uses the

include/linux/cpuset.h

+2 −2
Original line number Original line Diff line number Diff line
@@ -93,12 +93,12 @@ extern int cpuset_slab_spread_node(void); 




static inline int cpuset_do_page_mem_spread(void)

static inline int cpuset_do_page_mem_spread(void)

{

{

	return current->flags & PF_SPREAD_PAGE;

	return task_spread_page(current);

}

}





static inline int cpuset_do_slab_mem_spread(void)

static inline int cpuset_do_slab_mem_spread(void)

{

{

	return current->flags & PF_SPREAD_SLAB;

	return task_spread_slab(current);

}

}





extern int current_cpuset_is_being_rebound(void);

extern int current_cpuset_is_being_rebound(void);

include/linux/sched.h

+25 −13
Original line number Original line Diff line number Diff line
@@ -1903,8 +1903,6 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, 
#define PF_KTHREAD	0x00200000	/* I am a kernel thread */

#define PF_KTHREAD	0x00200000	/* I am a kernel thread */

#define PF_RANDOMIZE	0x00400000	/* randomize virtual address space */

#define PF_RANDOMIZE	0x00400000	/* randomize virtual address space */

#define PF_SWAPWRITE	0x00800000	/* Allowed to write to swap */

#define PF_SWAPWRITE	0x00800000	/* Allowed to write to swap */

#define PF_SPREAD_PAGE	0x01000000	/* Spread page cache over cpuset */

#define PF_SPREAD_SLAB	0x02000000	/* Spread some slab caches over cpuset */

#define PF_NO_SETAFFINITY 0x04000000	/* Userland is not allowed to meddle with cpus_allowed */

#define PF_NO_SETAFFINITY 0x04000000	/* Userland is not allowed to meddle with cpus_allowed */

#define PF_MCE_EARLY    0x08000000      /* Early kill for mce process policy */

#define PF_MCE_EARLY    0x08000000      /* Early kill for mce process policy */

#define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */

#define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
@@ -1957,17 +1955,31 @@ static inline void memalloc_noio_restore(unsigned int flags) 
}

}





/* Per-process atomic flags. */

/* Per-process atomic flags. */

#define PFA_NO_NEW_PRIVS 0x00000001	/* May not gain new privileges. */

#define PFA_NO_NEW_PRIVS 0	/* May not gain new privileges. */



#define PFA_SPREAD_PAGE  1      /* Spread page cache over cpuset */

static inline bool task_no_new_privs(struct task_struct *p)

#define PFA_SPREAD_SLAB  2      /* Spread some slab caches over cpuset */

{



	return test_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags);



}

#define TASK_PFA_TEST(name, func)					\



	static inline bool task_##func(struct task_struct *p)		\

static inline void task_set_no_new_privs(struct task_struct *p)

	{ return test_bit(PFA_##name, &p->atomic_flags); }

{

#define TASK_PFA_SET(name, func)					\

	set_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags);

	static inline void task_set_##func(struct task_struct *p)	\

}

	{ set_bit(PFA_##name, &p->atomic_flags); }

#define TASK_PFA_CLEAR(name, func)					\

	static inline void task_clear_##func(struct task_struct *p)	\

	{ clear_bit(PFA_##name, &p->atomic_flags); }



TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs)

TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs)



TASK_PFA_TEST(SPREAD_PAGE, spread_page)

TASK_PFA_SET(SPREAD_PAGE, spread_page)

TASK_PFA_CLEAR(SPREAD_PAGE, spread_page)



TASK_PFA_TEST(SPREAD_SLAB, spread_slab)

TASK_PFA_SET(SPREAD_SLAB, spread_slab)

TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)





/*

/*

 * task->jobctl flags

 * task->jobctl flags

kernel/cpuset.c

+5 −4
Original line number Original line Diff line number Diff line
@@ -365,13 +365,14 @@ static void cpuset_update_task_spread_flag(struct cpuset *cs, 
					struct task_struct *tsk)

					struct task_struct *tsk)

{

{

	if (is_spread_page(cs))

	if (is_spread_page(cs))

		tsk->flags |= PF_SPREAD_PAGE;

		task_set_spread_page(tsk);

	else

	else

		tsk->flags &= ~PF_SPREAD_PAGE;

		task_clear_spread_page(tsk);



	if (is_spread_slab(cs))

	if (is_spread_slab(cs))

		tsk->flags |= PF_SPREAD_SLAB;

		task_set_spread_slab(tsk);

	else

	else

		tsk->flags &= ~PF_SPREAD_SLAB;

		task_clear_spread_slab(tsk);

}

}





/*

/*

mm/slab.c

+2 −2
Original line number Original line Diff line number Diff line
@@ -2987,7 +2987,7 @@ out: 




#ifdef CONFIG_NUMA

#ifdef CONFIG_NUMA

/*

/*

 * Try allocating on another node if PF_SPREAD_SLAB is a mempolicy is set.

 * Try allocating on another node if PFA_SPREAD_SLAB is a mempolicy is set.

 *

 *

 * If we are in_interrupt, then process context, including cpusets and

 * If we are in_interrupt, then process context, including cpusets and

 * mempolicy, may not apply and should not be used for allocation policy.

 * mempolicy, may not apply and should not be used for allocation policy.
@@ -3219,7 +3219,7 @@ __do_cache_alloc(struct kmem_cache *cache, gfp_t flags) 
{

{

	void *objp;

	void *objp;





	if (current->mempolicy || unlikely(current->flags & PF_SPREAD_SLAB)) {

	if (current->mempolicy || cpuset_do_slab_mem_spread()) {

		objp = alternate_node_alloc(cache, flags);

		objp = alternate_node_alloc(cache, flags);

		if (objp)

		if (objp)

			goto out;

			goto out;

CRA Git | Maintained and supported by SUSTech CRA and CCSE