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

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

diff --combined include/linux/sched.h
index 1f07040d28e36140a9fa265098dc7366df0364f2,7b1cafefb05ebf7eca34c67d769f0923e0de3575..b867a4dab38a2a4491f54b28b7aa2b809a4dad22
--- 1/include/linux/sched.h
--- 2/include/linux/sched.h
+++ b/include/linux/sched.h
@@@ -1903,8 -1903,6 +1903,6 @@@ extern void thread_group_cputime_adjust
  #define PF_KTHREAD    0x00200000      /* I am a kernel thread */
  #define PF_RANDOMIZE  0x00400000      /* randomize virtual address space */
  #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_MCE_EARLY    0x08000000      /* Early kill for mce process policy */
  #define PF_MUTEX_TESTER       0x20000000      /* Thread belongs to the rt mutex tester */
@@@ -1957,17 -1955,31 +1955,31 @@@ static inline void memalloc_noio_restor
  }
  
  /* Per-process atomic flags. */
- #define PFA_NO_NEW_PRIVS 0x00000001   /* May not gain new privileges. */
- 
- static inline bool task_no_new_privs(struct task_struct *p)
- {
-       return test_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags);
- }
- 
- static inline void task_set_no_new_privs(struct task_struct *p)
- {
-       set_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags);
- }
+ #define PFA_NO_NEW_PRIVS 0    /* May not gain new privileges. */
+ #define PFA_SPREAD_PAGE  1      /* Spread page cache over cpuset */
+ #define PFA_SPREAD_SLAB  2      /* Spread some slab caches over cpuset */
+ 
+ 
+ #define TASK_PFA_TEST(name, func)                                     \
+       static inline bool task_##func(struct task_struct *p)           \
+       { return test_bit(PFA_##name, &p->atomic_flags); }
+ #define TASK_PFA_SET(name, func)                                      \
+       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
@@@ -2608,22 -2620,9 +2620,22 @@@ static inline void setup_thread_stack(s
        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

diff --combined mm/slab.c
index b8b619bc84adab2535dd81e170030171fcfab1c4,881951e67f125ccb41b4bedc9fcb22cce77ca9a6..7c52b3890d25378198341101242c671e585649bf
--- 1/mm/slab.c
--- 2/mm/slab.c
+++ b/mm/slab.c
@@@ -2124,8 -2124,7 +2124,8 @@@ static int __init_refok setup_cpu_cache
  int
  __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
  {
 -      size_t left_over, freelist_size, ralign;
 +      size_t left_over, freelist_size;
 +      size_t ralign = BYTES_PER_WORD;
        gfp_t gfp;
        int err;
        size_t size = cachep->size;
@@@ -2158,6 -2157,14 +2158,6 @@@
                size &= ~(BYTES_PER_WORD - 1);
        }
  
 -      /*
 -       * Redzoning and user store require word alignment or possibly larger.
 -       * Note this will be overridden by architecture or caller mandated
 -       * alignment if either is greater than BYTES_PER_WORD.
 -       */
 -      if (flags & SLAB_STORE_USER)
 -              ralign = BYTES_PER_WORD;
 -
        if (flags & SLAB_RED_ZONE) {
                ralign = REDZONE_ALIGN;
                /* If redzoning, ensure that the second redzone is suitably
@@@ -2987,7 -2994,7 +2987,7 @@@ out
  
  #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
   * mempolicy, may not apply and should not be used for allocation policy.
@@@ -3219,7 -3226,7 +3219,7 @@@ __do_cache_alloc(struct kmem_cache *cac
  {
        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);
                if (objp)
                        goto out;