25 files changed, 239 insertions, 197 deletions

diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index d2e3c7866460..e683869365d9 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -144,9 +144,9 @@ int audit_watch_compare(struct audit_watch *watch, unsigned long ino, dev_t dev)
 }
 
 /* Initialize a parent watch entry. */
-static struct audit_parent *audit_init_parent(struct nameidata *ndp)
+static struct audit_parent *audit_init_parent(struct path *path)
 {
-        struct inode *inode = ndp->path.dentry->d_inode;
+        struct inode *inode = path->dentry->d_inode;
         struct audit_parent *parent;
         int ret;
 
@@ -353,53 +353,40 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
 }
 
 /* Get path information necessary for adding watches. */
-static int audit_get_nd(char *path, struct nameidata **ndp, struct nameidata **ndw)
+static int audit_get_nd(struct audit_watch *watch, struct path *parent)
 {
-        struct nameidata *ndparent, *ndwatch;
+        struct nameidata nd;
+        struct dentry *d;
         int err;
 
-        ndparent = kmalloc(sizeof(*ndparent), GFP_KERNEL);
-        if (unlikely(!ndparent))
-                return -ENOMEM;
+        err = kern_path_parent(watch->path, &nd);
+        if (err)
+                return err;
 
-        ndwatch = kmalloc(sizeof(*ndwatch), GFP_KERNEL);
-        if (unlikely(!ndwatch)) {
-                kfree(ndparent);
-                return -ENOMEM;
+        if (nd.last_type != LAST_NORM) {
+                path_put(&nd.path);
+                return -EINVAL;
         }
 
-        err = path_lookup(path, LOOKUP_PARENT, ndparent);
-        if (err) {
-                kfree(ndparent);
-                kfree(ndwatch);
-                return err;
+        mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+        d = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len);
+        if (IS_ERR(d)) {
+                mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+                path_put(&nd.path);
+                return PTR_ERR(d);
         }
-
-        err = path_lookup(path, 0, ndwatch);
-        if (err) {
-                kfree(ndwatch);
-                ndwatch = NULL;
+        if (d->d_inode) {
+                /* update watch filter fields */
+                watch->dev = d->d_inode->i_sb->s_dev;
+                watch->ino = d->d_inode->i_ino;
         }
+        mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
 
-        *ndp = ndparent;
-        *ndw = ndwatch;
-
+        *parent = nd.path;
+        dput(d);
         return 0;
 }
 
-/* Release resources used for watch path information. */
-static void audit_put_nd(struct nameidata *ndp, struct nameidata *ndw)
-{
-        if (ndp) {
-                path_put(&ndp->path);
-                kfree(ndp);
-        }
-        if (ndw) {
-                path_put(&ndw->path);
-                kfree(ndw);
-        }
-}
-
 /* Associate the given rule with an existing parent.
  * Caller must hold audit_filter_mutex. */
 static void audit_add_to_parent(struct audit_krule *krule,
@@ -440,31 +427,24 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
 {
         struct audit_watch *watch = krule->watch;
         struct audit_parent *parent;
-        struct nameidata *ndp = NULL, *ndw = NULL;
+        struct path parent_path;
         int h, ret = 0;
 
         mutex_unlock(&audit_filter_mutex);
 
         /* Avoid calling path_lookup under audit_filter_mutex. */
-        ret = audit_get_nd(watch->path, &ndp, &ndw);
-        if (ret) {
-                /* caller expects mutex locked */
-                mutex_lock(&audit_filter_mutex);
-                goto error;
-        }
+        ret = audit_get_nd(watch, &parent_path);
 
+        /* caller expects mutex locked */
         mutex_lock(&audit_filter_mutex);
 
-        /* update watch filter fields */
-        if (ndw) {
-                watch->dev = ndw->path.dentry->d_inode->i_sb->s_dev;
-                watch->ino = ndw->path.dentry->d_inode->i_ino;
-        }
+        if (ret)
+                return ret;
 
         /* either find an old parent or attach a new one */
-        parent = audit_find_parent(ndp->path.dentry->d_inode);
+        parent = audit_find_parent(parent_path.dentry->d_inode);
         if (!parent) {
-                parent = audit_init_parent(ndp);
+                parent = audit_init_parent(&parent_path);
                 if (IS_ERR(parent)) {
                         ret = PTR_ERR(parent);
                         goto error;
@@ -479,9 +459,8 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
         h = audit_hash_ino((u32)watch->ino);
         *list = &audit_inode_hash[h];
 error:
-        audit_put_nd(ndp, ndw);         /* NULL args OK */
+        path_put(&parent_path);
         return ret;
-
 }
 
 void audit_remove_watch_rule(struct audit_krule *krule)
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 4349935c2ad8..e92e98189032 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1575,8 +1575,10 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft,
                 return -ENODEV;
 
         trialcs = alloc_trial_cpuset(cs);
-        if (!trialcs)
-                return -ENOMEM;
+        if (!trialcs) {
+                retval = -ENOMEM;
+                goto out;
+        }
 
         switch (cft->private) {
         case FILE_CPULIST:
@@ -1591,6 +1593,7 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft,
         }
 
         free_trial_cpuset(trialcs);
+out:
         cgroup_unlock();
         return retval;
 }
diff --git a/kernel/futex.c b/kernel/futex.c
index 64c38115c7b6..bda415715382 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -381,15 +381,16 @@ static struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb,
         return NULL;
 }
 
-static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval)
+static int cmpxchg_futex_value_locked(u32 *curval, u32 __user *uaddr,
+                                      u32 uval, u32 newval)
 {
-        u32 curval;
+        int ret;
 
         pagefault_disable();
-        curval = futex_atomic_cmpxchg_inatomic(uaddr, uval, newval);
+        ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval);
         pagefault_enable();
 
-        return curval;
+        return ret;
 }
 
 static int get_futex_value_locked(u32 *dest, u32 __user *from)
@@ -674,7 +675,7 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
                                 struct task_struct *task, int set_waiters)
 {
         int lock_taken, ret, ownerdied = 0;
-        u32 uval, newval, curval;
+        u32 uval, newval, curval, vpid = task_pid_vnr(task);
 
 retry:
         ret = lock_taken = 0;
@@ -684,19 +685,17 @@ retry:
          * (by doing a 0 -> TID atomic cmpxchg), while holding all
          * the locks. It will most likely not succeed.
          */
-        newval = task_pid_vnr(task);
+        newval = vpid;
         if (set_waiters)
                 newval |= FUTEX_WAITERS;
 
-        curval = cmpxchg_futex_value_locked(uaddr, 0, newval);
-
-        if (unlikely(curval == -EFAULT))
+        if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, 0, newval)))
                 return -EFAULT;
 
         /*
          * Detect deadlocks.
          */
-        if ((unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(task))))
+        if ((unlikely((curval & FUTEX_TID_MASK) == vpid)))
                 return -EDEADLK;
 
         /*
@@ -723,14 +722,12 @@ retry:
          */
         if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) {
                 /* Keep the OWNER_DIED bit */
-                newval = (curval & ~FUTEX_TID_MASK) | task_pid_vnr(task);
+                newval = (curval & ~FUTEX_TID_MASK) | vpid;
                 ownerdied = 0;
                 lock_taken = 1;
         }
 
-        curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
-        if (unlikely(curval == -EFAULT))
+        if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
                 return -EFAULT;
         if (unlikely(curval != uval))
                 goto retry;
@@ -775,6 +772,24 @@ retry:
         return ret;
 }
 
+/**
+ * __unqueue_futex() - Remove the futex_q from its futex_hash_bucket
+ * @q:  The futex_q to unqueue
+ *
+ * The q->lock_ptr must not be NULL and must be held by the caller.
+ */
+static void __unqueue_futex(struct futex_q *q)
+{
+        struct futex_hash_bucket *hb;
+
+        if (WARN_ON(!q->lock_ptr || !spin_is_locked(q->lock_ptr)
+                        || plist_node_empty(&q->list)))
+                return;
+
+        hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock);
+        plist_del(&q->list, &hb->chain);
+}
+
 /*
  * The hash bucket lock must be held when this is called.
  * Afterwards, the futex_q must not be accessed.
@@ -792,7 +807,7 @@ static void wake_futex(struct futex_q *q)
          */
         get_task_struct(p);
 
-        plist_del(&q->list, &q->list.plist);
+        __unqueue_futex(q);
         /*
          * The waiting task can free the futex_q as soon as
          * q->lock_ptr = NULL is written, without taking any locks. A
@@ -843,9 +858,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
 
                 newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
 
-                curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
-                if (curval == -EFAULT)
+                if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
                         ret = -EFAULT;
                 else if (curval != uval)
                         ret = -EINVAL;
@@ -880,10 +893,8 @@ static int unlock_futex_pi(u32 __user *uaddr, u32 uval)
          * There is no waiter, so we unlock the futex. The owner died
          * bit has not to be preserved here. We are the owner:
          */
-        oldval = cmpxchg_futex_value_locked(uaddr, uval, 0);
-
-        if (oldval == -EFAULT)
-                return oldval;
+        if (cmpxchg_futex_value_locked(&oldval, uaddr, uval, 0))
+                return -EFAULT;
         if (oldval != uval)
                 return -EAGAIN;
 
@@ -1071,9 +1082,6 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
                 plist_del(&q->list, &hb1->chain);
                 plist_add(&q->list, &hb2->chain);
                 q->lock_ptr = &hb2->lock;
-#ifdef CONFIG_DEBUG_PI_LIST
-                q->list.plist.spinlock = &hb2->lock;
-#endif
         }
         get_futex_key_refs(key2);
         q->key = *key2;
@@ -1100,16 +1108,12 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
         get_futex_key_refs(key);
         q->key = *key;
 
-        WARN_ON(plist_node_empty(&q->list));
-        plist_del(&q->list, &q->list.plist);
+        __unqueue_futex(q);
 
         WARN_ON(!q->rt_waiter);
         q->rt_waiter = NULL;
 
         q->lock_ptr = &hb->lock;
-#ifdef CONFIG_DEBUG_PI_LIST
-        q->list.plist.spinlock = &hb->lock;
-#endif
 
         wake_up_state(q->task, TASK_NORMAL);
 }
@@ -1457,9 +1461,6 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
         prio = min(current->normal_prio, MAX_RT_PRIO);
 
         plist_node_init(&q->list, prio);
-#ifdef CONFIG_DEBUG_PI_LIST
-        q->list.plist.spinlock = &hb->lock;
-#endif
         plist_add(&q->list, &hb->chain);
         q->task = current;
         spin_unlock(&hb->lock);
@@ -1504,8 +1505,7 @@ retry:
                         spin_unlock(lock_ptr);
                         goto retry;
                 }
-                WARN_ON(plist_node_empty(&q->list));
-                plist_del(&q->list, &q->list.plist);
+                __unqueue_futex(q);
 
                 BUG_ON(q->pi_state);
 
@@ -1525,8 +1525,7 @@ retry:
 static void unqueue_me_pi(struct futex_q *q)
         __releases(q->lock_ptr)
 {
-        WARN_ON(plist_node_empty(&q->list));
-        plist_del(&q->list, &q->list.plist);
+        __unqueue_futex(q);
 
         BUG_ON(!q->pi_state);
         free_pi_state(q->pi_state);
@@ -1578,9 +1577,7 @@ retry:
         while (1) {
                 newval = (uval & FUTEX_OWNER_DIED) | newtid;
 
-                curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
-                if (curval == -EFAULT)
+                if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
                         goto handle_fault;
                 if (curval == uval)
                         break;
@@ -1783,13 +1780,14 @@ static int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
          *
          * The basic logical guarantee of a futex is that it blocks ONLY
          * if cond(var) is known to be true at the time of blocking, for
-         * any cond.  If we queued after testing *uaddr, that would open
-         * a race condition where we could block indefinitely with
+         * any cond.  If we locked the hash-bucket after testing *uaddr, that
+         * would open a race condition where we could block indefinitely with
          * cond(var) false, which would violate the guarantee.
          *
-         * A consequence is that futex_wait() can return zero and absorb
-         * a wakeup when *uaddr != val on entry to the syscall.  This is
-         * rare, but normal.
+         * On the other hand, we insert q and release the hash-bucket only
+         * after testing *uaddr.  This guarantees that futex_wait() will NOT
+         * absorb a wakeup if *uaddr does not match the desired values
+         * while the syscall executes.
          */
 retry:
         ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key);
@@ -2048,9 +2046,9 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 {
         struct futex_hash_bucket *hb;
         struct futex_q *this, *next;
-        u32 uval;
         struct plist_head *head;
         union futex_key key = FUTEX_KEY_INIT;
+        u32 uval, vpid = task_pid_vnr(current);
         int ret;
 
 retry:
@@ -2059,7 +2057,7 @@ retry:
         /*
          * We release only a lock we actually own:
          */
-        if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current))
+        if ((uval & FUTEX_TID_MASK) != vpid)
                 return -EPERM;
 
         ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key);
@@ -2074,17 +2072,14 @@ retry:
          * again. If it succeeds then we can return without waking
          * anyone else up:
          */
-        if (!(uval & FUTEX_OWNER_DIED))
-                uval = cmpxchg_futex_value_locked(uaddr, task_pid_vnr(current), 0);
-
-
-        if (unlikely(uval == -EFAULT))
+        if (!(uval & FUTEX_OWNER_DIED) &&
+            cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0))
                 goto pi_faulted;
         /*
          * Rare case: we managed to release the lock atomically,
          * no need to wake anyone else up:
          */
-        if (unlikely(uval == task_pid_vnr(current)))
+        if (unlikely(uval == vpid))
                 goto out_unlock;
 
         /*
@@ -2169,7 +2164,7 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
                  * We were woken prior to requeue by a timeout or a signal.
                  * Unqueue the futex_q and determine which it was.
                  */
-                plist_del(&q->list, &q->list.plist);
+                plist_del(&q->list, &hb->chain);
 
                 /* Handle spurious wakeups gracefully */
                 ret = -EWOULDBLOCK;
@@ -2465,11 +2460,20 @@ retry:
                  * userspace.
                  */
                 mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
-                nval = futex_atomic_cmpxchg_inatomic(uaddr, uval, mval);
-
-                if (nval == -EFAULT)
-                        return -1;
-
+                /*
+                 * We are not holding a lock here, but we want to have
+                 * the pagefault_disable/enable() protection because
+                 * we want to handle the fault gracefully. If the
+                 * access fails we try to fault in the futex with R/W
+                 * verification via get_user_pages. get_user() above
+                 * does not guarantee R/W access. If that fails we
+                 * give up and leave the futex locked.
+                 */
+                if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) {
+                        if (fault_in_user_writeable(uaddr))
+                                return -1;
+                        goto retry;
+                }
                 if (nval != uval)
                         goto retry;
 
@@ -2680,8 +2684,7 @@ static int __init futex_init(void)
          * implementation, the non-functional ones will return
          * -ENOSYS.
          */
-        curval = cmpxchg_futex_value_locked(NULL, 0, 0);
-        if (curval == -EFAULT)
+        if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
                 futex_cmpxchg_enabled = 1;
 
         for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 0c8d7c048615..e38f5a073d01 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -334,6 +334,11 @@ EXPORT_SYMBOL_GPL(ktime_add_safe);
 
 static struct debug_obj_descr hrtimer_debug_descr;
 
+static void *hrtimer_debug_hint(void *addr)
+{
+        return ((struct hrtimer *) addr)->function;
+}
+
 /*
  * fixup_init is called when:
  * - an active object is initialized
@@ -393,6 +398,7 @@ static int hrtimer_fixup_free(void *addr, enum debug_obj_state state)
 
 static struct debug_obj_descr hrtimer_debug_descr = {
         .name           = "hrtimer",
+        .debug_hint     = hrtimer_debug_hint,
         .fixup_init     = hrtimer_fixup_init,
         .fixup_activate = hrtimer_fixup_activate,
         .fixup_free     = hrtimer_fixup_free,
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 4571ae7e085a..99c3bc8a6fb4 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -3,6 +3,12 @@
  */
 #include <linux/irqdesc.h>
 
+#ifdef CONFIG_SPARSE_IRQ
+# define IRQ_BITMAP_BITS        (NR_IRQS + 8196)
+#else
+# define IRQ_BITMAP_BITS        NR_IRQS
+#endif
+
 extern int noirqdebug;
 
 #define irq_data_to_desc(data)  container_of(data, struct irq_desc, irq_data)
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 282f20230e67..2039bea31bdf 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -94,7 +94,7 @@ int nr_irqs = NR_IRQS;
 EXPORT_SYMBOL_GPL(nr_irqs);
 
 static DEFINE_MUTEX(sparse_irq_lock);
-static DECLARE_BITMAP(allocated_irqs, NR_IRQS);
+static DECLARE_BITMAP(allocated_irqs, IRQ_BITMAP_BITS);
 
 #ifdef CONFIG_SPARSE_IRQ
 
@@ -217,6 +217,15 @@ int __init early_irq_init(void)
         initcnt = arch_probe_nr_irqs();
         printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d %d\n", NR_IRQS, nr_irqs, initcnt);
 
+        if (WARN_ON(nr_irqs > IRQ_BITMAP_BITS))
+                nr_irqs = IRQ_BITMAP_BITS;
+
+        if (WARN_ON(initcnt > IRQ_BITMAP_BITS))
+                initcnt = IRQ_BITMAP_BITS;
+
+        if (initcnt > nr_irqs)
+                nr_irqs = initcnt;
+
         for (i = 0; i < initcnt; i++) {
                 desc = alloc_desc(i, node);
                 set_bit(i, allocated_irqs);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 0caa59f747dd..2782bacdf494 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -282,8 +282,17 @@ EXPORT_SYMBOL(disable_irq);
 
 void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
 {
-        if (resume)
+        if (resume) {
+                if (!(desc->status & IRQ_SUSPENDED)) {
+                        if (!desc->action)
+                                return;
+                        if (!(desc->action->flags & IRQF_FORCE_RESUME))
+                                return;
+                        /* Pretend that it got disabled ! */
+                        desc->depth++;
+                }
                 desc->status &= ~IRQ_SUSPENDED;
+        }
 
         switch (desc->depth) {
         case 0:
@@ -1100,7 +1109,7 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
         if (retval)
                 kfree(action);
 
-#ifdef CONFIG_DEBUG_SHIRQ
+#ifdef CONFIG_DEBUG_SHIRQ_FIXME
         if (!retval && (irqflags & IRQF_SHARED)) {
                 /*
                  * It's a shared IRQ -- the driver ought to be prepared for it
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index 0d4005d85b03..d6bfb89cce91 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -53,9 +53,6 @@ void resume_device_irqs(void)
         for_each_irq_desc(irq, desc) {
                 unsigned long flags;
 
-                if (!(desc->status & IRQ_SUSPENDED))
-                        continue;
-
                 raw_spin_lock_irqsave(&desc->lock, flags);
                 __enable_irq(desc, irq, true);
                 raw_spin_unlock_irqrestore(&desc->lock, flags);
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 891115a929aa..dc49358b73fa 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -23,7 +23,7 @@
 #ifdef CONFIG_HARDIRQS_SW_RESEND
 
 /* Bitmap to handle software resend of interrupts: */
-static DECLARE_BITMAP(irqs_resend, NR_IRQS);
+static DECLARE_BITMAP(irqs_resend, IRQ_BITMAP_BITS);
 
 /*
  * Run software resends of IRQ's
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 999835b6112b..656222fcf767 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -782,6 +782,10 @@ retry:
         raw_spin_unlock_irq(&ctx->lock);
 }
 
+#define MAX_INTERRUPTS (~0ULL)
+
+static void perf_log_throttle(struct perf_event *event, int enable);
+
 static int
 event_sched_in(struct perf_event *event,
                  struct perf_cpu_context *cpuctx,
@@ -794,6 +798,17 @@ event_sched_in(struct perf_event *event,
 
         event->state = PERF_EVENT_STATE_ACTIVE;
         event->oncpu = smp_processor_id();
+
+        /*
+         * Unthrottle events, since we scheduled we might have missed several
+         * ticks already, also for a heavily scheduling task there is little
+         * guarantee it'll get a tick in a timely manner.
+         */
+        if (unlikely(event->hw.interrupts == MAX_INTERRUPTS)) {
+                perf_log_throttle(event, 1);
+                event->hw.interrupts = 0;
+        }
+
         /*
          * The new state must be visible before we turn it on in the hardware:
          */
@@ -1596,10 +1611,6 @@ void __perf_event_task_sched_in(struct task_struct *task)
         }
 }
 
-#define MAX_INTERRUPTS (~0ULL)
-
-static void perf_log_throttle(struct perf_event *event, int enable);
-
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
 {
         u64 frequency = event->attr.sample_freq;
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 7b5db6a8561e..701853042c28 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -326,7 +326,7 @@ EXPORT_SYMBOL_GPL(pm_wq);
 
 static int __init pm_start_workqueue(void)
 {
-        pm_wq = alloc_workqueue("pm", WQ_FREEZEABLE, 0);
+        pm_wq = alloc_workqueue("pm", WQ_FREEZABLE, 0);
 
         return pm_wq ? 0 : -ENOMEM;
 }
diff --git a/kernel/power/process.c b/kernel/power/process.c
index d6d2a10320e0..0cf3a27a6c9d 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -22,7 +22,7 @@
  */
 #define TIMEOUT (20 * HZ)
 
-static inline int freezeable(struct task_struct * p)
+static inline int freezable(struct task_struct * p)
 {
         if ((p == current) ||
             (p->flags & PF_NOFREEZE) ||
@@ -53,7 +53,7 @@ static int try_to_freeze_tasks(bool sig_only)
                 todo = 0;
                 read_lock(&tasklist_lock);
                 do_each_thread(g, p) {
-                        if (frozen(p) || !freezeable(p))
+                        if (frozen(p) || !freezable(p))
                                 continue;
 
                         if (!freeze_task(p, sig_only))
@@ -167,7 +167,7 @@ static void thaw_tasks(bool nosig_only)
 
         read_lock(&tasklist_lock);
         do_each_thread(g, p) {
-                if (!freezeable(p))
+                if (!freezable(p))
                         continue;
 
                 if (nosig_only && should_send_signal(p))
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 0dac75ea4456..64db648ff911 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1519,11 +1519,8 @@ static int
 swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
                 unsigned int nr_pages, unsigned int nr_highmem)
 {
-        int error = 0;
-
         if (nr_highmem > 0) {
-                error = get_highmem_buffer(PG_ANY);
-                if (error)
+                if (get_highmem_buffer(PG_ANY))
                         goto err_out;
                 if (nr_highmem > alloc_highmem) {
                         nr_highmem -= alloc_highmem;
@@ -1546,7 +1543,7 @@ swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
 
  err_out:
         swsusp_free();
-        return error;
+        return -ENOMEM;
 }
 
 asmlinkage int swsusp_save(void)
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 1708b1e2972d..e2302e40b360 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -163,7 +163,7 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode)
         return !err;
 }
 
-int ptrace_attach(struct task_struct *task)
+static int ptrace_attach(struct task_struct *task)
 {
         int retval;
 
@@ -219,7 +219,7 @@ out:
  * Performs checks and sets PT_PTRACED.
  * Should be used by all ptrace implementations for PTRACE_TRACEME.
  */
-int ptrace_traceme(void)
+static int ptrace_traceme(void)
 {
         int ret = -EPERM;
 
@@ -293,7 +293,7 @@ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
         return false;
 }
 
-int ptrace_detach(struct task_struct *child, unsigned int data)
+static int ptrace_detach(struct task_struct *child, unsigned int data)
 {
         bool dead = false;
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 18d38e4ec7ba..42eab5a8437d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4213,6 +4213,7 @@ void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
 {
         __wake_up_common(q, mode, 1, 0, key);
 }
+EXPORT_SYMBOL_GPL(__wake_up_locked_key);
 
 /**
  * __wake_up_sync_key - wake up threads blocked on a waitqueue.
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index ad6267714c84..01f75a5f17af 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -210,11 +210,12 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se);
 
 static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 {
-        int this_cpu = smp_processor_id();
         struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
         struct sched_rt_entity *rt_se;
 
-        rt_se = rt_rq->tg->rt_se[this_cpu];
+        int cpu = cpu_of(rq_of_rt_rq(rt_rq));
+
+        rt_se = rt_rq->tg->rt_se[cpu];
 
         if (rt_rq->rt_nr_running) {
                 if (rt_se && !on_rt_rq(rt_se))
@@ -226,10 +227,10 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 
 static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 {
-        int this_cpu = smp_processor_id();
         struct sched_rt_entity *rt_se;
+        int cpu = cpu_of(rq_of_rt_rq(rt_rq));
 
-        rt_se = rt_rq->tg->rt_se[this_cpu];
+        rt_se = rt_rq->tg->rt_se[cpu];
 
         if (rt_se && on_rt_rq(rt_se))
                 dequeue_rt_entity(rt_se);
@@ -565,8 +566,11 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
                         if (rt_rq->rt_time || rt_rq->rt_nr_running)
                                 idle = 0;
                         raw_spin_unlock(&rt_rq->rt_runtime_lock);
-                } else if (rt_rq->rt_nr_running)
+                } else if (rt_rq->rt_nr_running) {
                         idle = 0;
+                        if (!rt_rq_throttled(rt_rq))
+                                enqueue = 1;
+                }
 
                 if (enqueue)
                         sched_rt_rq_enqueue(rt_rq);
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index c782fe9924c7..25cc41cd8f33 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -186,3 +186,8 @@ cond_syscall(sys_perf_event_open);
 /* fanotify! */
 cond_syscall(sys_fanotify_init);
 cond_syscall(sys_fanotify_mark);
+
+/* open by handle */
+cond_syscall(sys_name_to_handle_at);
+cond_syscall(sys_open_by_handle_at);
+cond_syscall(compat_sys_open_by_handle_at);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 0f1bd83db985..4eed0af5d144 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -194,9 +194,9 @@ static int sysrq_sysctl_handler(ctl_table *table, int write,
 static struct ctl_table root_table[];
 static struct ctl_table_root sysctl_table_root;
 static struct ctl_table_header root_table_header = {
-        .count = 1,
+        {{.count = 1,
         .ctl_table = root_table,
-        .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),
+        .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),}},
         .root = &sysctl_table_root,
         .set = &sysctl_table_root.default_set,
 };
@@ -1567,11 +1567,16 @@ void sysctl_head_get(struct ctl_table_header *head)
         spin_unlock(&sysctl_lock);
 }
 
+static void free_head(struct rcu_head *rcu)
+{
+        kfree(container_of(rcu, struct ctl_table_header, rcu));
+}
+
 void sysctl_head_put(struct ctl_table_header *head)
 {
         spin_lock(&sysctl_lock);
         if (!--head->count)
-                kfree(head);
+                call_rcu(&head->rcu, free_head);
         spin_unlock(&sysctl_lock);
 }
 
@@ -1948,10 +1953,10 @@ void unregister_sysctl_table(struct ctl_table_header * header)
         start_unregistering(header);
         if (!--header->parent->count) {
                 WARN_ON(1);
-                kfree(header->parent);
+                call_rcu(&header->parent->rcu, free_head);
         }
         if (!--header->count)
-                kfree(header);
+                call_rcu(&header->rcu, free_head);
         spin_unlock(&sysctl_lock);
 }
 
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index b875bedf7c9a..3b8e028b9601 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -1321,13 +1321,11 @@ static ssize_t binary_sysctl(const int *name, int nlen,
         void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
 {
         const struct bin_table *table = NULL;
-        struct nameidata nd;
         struct vfsmount *mnt;
         struct file *file;
         ssize_t result;
         char *pathname;
         int flags;
-        int acc_mode;
 
         pathname = sysctl_getname(name, nlen, &table);
         result = PTR_ERR(pathname);
@@ -1337,28 +1335,17 @@ static ssize_t binary_sysctl(const int *name, int nlen,
         /* How should the sysctl be accessed? */
         if (oldval && oldlen && newval && newlen) {
                 flags = O_RDWR;
-                acc_mode = MAY_READ | MAY_WRITE;
         } else if (newval && newlen) {
                 flags = O_WRONLY;
-                acc_mode = MAY_WRITE;
         } else if (oldval && oldlen) {
                 flags = O_RDONLY;
-                acc_mode = MAY_READ;
         } else {
                 result = 0;
                 goto out_putname;
         }
 
         mnt = current->nsproxy->pid_ns->proc_mnt;
-        result = vfs_path_lookup(mnt->mnt_root, mnt, pathname, 0, &nd);
-        if (result)
-                goto out_putname;
-
-        result = may_open(&nd.path, acc_mode, flags);
-        if (result)
-                goto out_putpath;
-
-        file = dentry_open(nd.path.dentry, nd.path.mnt, flags, current_cred());
+        file = file_open_root(mnt->mnt_root, mnt, pathname, flags);
         result = PTR_ERR(file);
         if (IS_ERR(file))
                 goto out_putname;
@@ -1370,10 +1357,6 @@ out_putname:
         putname(pathname);
 out:
         return result;
-
-out_putpath:
-        path_put(&nd.path);
-        goto out_putname;
 }
 
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 48b2761b5668..a3b5aff62606 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -600,4 +600,14 @@ int tick_broadcast_oneshot_active(void)
         return tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT;
 }
 
+/*
+ * Check whether the broadcast device supports oneshot.
+ */
+bool tick_broadcast_oneshot_available(void)
+{
+        struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+        return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false;
+}
+
 #endif
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 051bc80a0c43..ed228ef6f6b8 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -51,7 +51,11 @@ int tick_is_oneshot_available(void)
 {
         struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
 
-        return dev && (dev->features & CLOCK_EVT_FEAT_ONESHOT);
+        if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+                return 0;
+        if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
+                return 1;
+        return tick_broadcast_oneshot_available();
 }
 
 /*
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 290eefbc1f60..f65d3a723a64 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -36,6 +36,7 @@ extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
 extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
 extern int tick_broadcast_oneshot_active(void);
 extern void tick_check_oneshot_broadcast(int cpu);
+bool tick_broadcast_oneshot_available(void);
 # else /* BROADCAST */
 static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
@@ -46,6 +47,7 @@ static inline void tick_broadcast_switch_to_oneshot(void) { }
 static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
 static inline void tick_check_oneshot_broadcast(int cpu) { }
+static inline bool tick_broadcast_oneshot_available(void) { return true; }
 # endif /* !BROADCAST */
 
 #else /* !ONESHOT */
@@ -76,6 +78,7 @@ static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
         return 0;
 }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
+static inline bool tick_broadcast_oneshot_available(void) { return false; }
 #endif /* !TICK_ONESHOT */
 
 /*
diff --git a/kernel/timer.c b/kernel/timer.c
index 5f40c2e0a94e..3503c17ac1d3 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -404,6 +404,11 @@ static void timer_stats_account_timer(struct timer_list *timer) {}
 
 static struct debug_obj_descr timer_debug_descr;
 
+static void *timer_debug_hint(void *addr)
+{
+        return ((struct timer_list *) addr)->function;
+}
+
 /*
  * fixup_init is called when:
  * - an active object is initialized
@@ -477,6 +482,7 @@ static int timer_fixup_free(void *addr, enum debug_obj_state state)
 
 static struct debug_obj_descr timer_debug_descr = {
         .name           = "timer_list",
+        .debug_hint     = timer_debug_hint,
         .fixup_init     = timer_fixup_init,
         .fixup_activate = timer_fixup_activate,
         .fixup_free     = timer_fixup_free,
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index d95721f33702..cbafed7d4f38 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1827,21 +1827,5 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
         rwbs[i] = '\0';
 }
 
-void blk_fill_rwbs_rq(char *rwbs, struct request *rq)
-{
-        int rw = rq->cmd_flags & 0x03;
-        int bytes;
-
-        if (rq->cmd_flags & REQ_DISCARD)
-                rw |= REQ_DISCARD;
-
-        if (rq->cmd_flags & REQ_SECURE)
-                rw |= REQ_SECURE;
-
-        bytes = blk_rq_bytes(rq);
-
-        blk_fill_rwbs(rwbs, rw, bytes);
-}
-
 #endif /* CONFIG_EVENT_TRACING */
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 11869faa6819..b5fe4c00eb3c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -79,7 +79,9 @@ enum {
         MAX_IDLE_WORKERS_RATIO  = 4,            /* 1/4 of busy can be idle */
         IDLE_WORKER_TIMEOUT     = 300 * HZ,     /* keep idle ones for 5 mins */
 
-        MAYDAY_INITIAL_TIMEOUT  = HZ / 100,     /* call for help after 10ms */
+        MAYDAY_INITIAL_TIMEOUT  = HZ / 100 >= 2 ? HZ / 100 : 2,
+                                                /* call for help after 10ms
+                                                   (min two ticks) */
         MAYDAY_INTERVAL         = HZ / 10,      /* and then every 100ms */
         CREATE_COOLDOWN         = HZ,           /* time to breath after fail */
         TRUSTEE_COOLDOWN        = HZ / 10,      /* for trustee draining */
@@ -314,6 +316,11 @@ static inline int __next_wq_cpu(int cpu, const struct cpumask *mask,
 
 static struct debug_obj_descr work_debug_descr;
 
+static void *work_debug_hint(void *addr)
+{
+        return ((struct work_struct *) addr)->func;
+}
+
 /*
  * fixup_init is called when:
  * - an active object is initialized
@@ -385,6 +392,7 @@ static int work_fixup_free(void *addr, enum debug_obj_state state)
 
 static struct debug_obj_descr work_debug_descr = {
         .name           = "work_struct",
+        .debug_hint     = work_debug_hint,
         .fixup_init     = work_fixup_init,
         .fixup_activate = work_fixup_activate,
         .fixup_free     = work_fixup_free,
@@ -2047,6 +2055,15 @@ repeat:
                                 move_linked_works(work, scheduled, &n);
 
                 process_scheduled_works(rescuer);
+
+                /*
+                 * Leave this gcwq.  If keep_working() is %true, notify a
+                 * regular worker; otherwise, we end up with 0 concurrency
+                 * and stalling the execution.
+                 */
+                if (keep_working(gcwq))
+                        wake_up_worker(gcwq);
+
                 spin_unlock_irq(&gcwq->lock);
         }
 
@@ -2956,7 +2973,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name,
          */
         spin_lock(&workqueue_lock);
 
-        if (workqueue_freezing && wq->flags & WQ_FREEZEABLE)
+        if (workqueue_freezing && wq->flags & WQ_FREEZABLE)
                 for_each_cwq_cpu(cpu, wq)
                         get_cwq(cpu, wq)->max_active = 0;
 
@@ -3068,7 +3085,7 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
 
                 spin_lock_irq(&gcwq->lock);
 
-                if (!(wq->flags & WQ_FREEZEABLE) ||
+                if (!(wq->flags & WQ_FREEZABLE) ||
                     !(gcwq->flags & GCWQ_FREEZING))
                         get_cwq(gcwq->cpu, wq)->max_active = max_active;
 
@@ -3318,7 +3335,7 @@ static int __cpuinit trustee_thread(void *__gcwq)
          * want to get it over with ASAP - spam rescuers, wake up as
          * many idlers as necessary and create new ones till the
          * worklist is empty.  Note that if the gcwq is frozen, there
-         * may be frozen works in freezeable cwqs.  Don't declare
+         * may be frozen works in freezable cwqs.  Don't declare
          * completion while frozen.
          */
         while (gcwq->nr_workers != gcwq->nr_idle ||
@@ -3576,9 +3593,9 @@ EXPORT_SYMBOL_GPL(work_on_cpu);
 /**
  * freeze_workqueues_begin - begin freezing workqueues
  *
- * Start freezing workqueues.  After this function returns, all
- * freezeable workqueues will queue new works to their frozen_works
- * list instead of gcwq->worklist.
+ * Start freezing workqueues.  After this function returns, all freezable
+ * workqueues will queue new works to their frozen_works list instead of
+ * gcwq->worklist.
  *
  * CONTEXT:
  * Grabs and releases workqueue_lock and gcwq->lock's.
@@ -3604,7 +3621,7 @@ void freeze_workqueues_begin(void)
                 list_for_each_entry(wq, &workqueues, list) {
                         struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
-                        if (cwq && wq->flags & WQ_FREEZEABLE)
+                        if (cwq && wq->flags & WQ_FREEZABLE)
                                 cwq->max_active = 0;
                 }
 
@@ -3615,7 +3632,7 @@ void freeze_workqueues_begin(void)
 }
 
 /**
- * freeze_workqueues_busy - are freezeable workqueues still busy?
+ * freeze_workqueues_busy - are freezable workqueues still busy?
  *
  * Check whether freezing is complete.  This function must be called
  * between freeze_workqueues_begin() and thaw_workqueues().
@@ -3624,8 +3641,8 @@ void freeze_workqueues_begin(void)
  * Grabs and releases workqueue_lock.
  *
  * RETURNS:
- * %true if some freezeable workqueues are still busy.  %false if
- * freezing is complete.
+ * %true if some freezable workqueues are still busy.  %false if freezing
+ * is complete.
  */
 bool freeze_workqueues_busy(void)
 {
@@ -3645,7 +3662,7 @@ bool freeze_workqueues_busy(void)
                 list_for_each_entry(wq, &workqueues, list) {
                         struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
-                        if (!cwq || !(wq->flags & WQ_FREEZEABLE))
+                        if (!cwq || !(wq->flags & WQ_FREEZABLE))
                                 continue;
 
                         BUG_ON(cwq->nr_active < 0);
@@ -3690,7 +3707,7 @@ void thaw_workqueues(void)
                 list_for_each_entry(wq, &workqueues, list) {
                         struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
-                        if (!cwq || !(wq->flags & WQ_FREEZEABLE))
+                        if (!cwq || !(wq->flags & WQ_FREEZABLE))
                                 continue;
 
                         /* restore max_active and repopulate worklist */