Merge remote-tracking branch 'stable/linux-3.0.y' into android-3.0

Change-Id: I9685feb9277b450da10d78a455b3c0674d6cfe18
Signed-off-by: Todd Poynor <toddpoynor@google.com>

23 files changed, 508 insertions, 307 deletions

diff --git a/kernel/async.c b/kernel/async.c
index cd9dbb9..04f66e3 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -87,6 +87,13 @@ static async_cookie_t  __lowest_in_progress(struct list_head *running)
 {
 	struct async_entry *entry;
 
+	if (!running) { /* just check the entry count */
+		if (atomic_read(&entry_count))
+			return 0; /* smaller than any cookie */
+		else
+			return next_cookie;
+	}
+
 	if (!list_empty(running)) {
 		entry = list_first_entry(running,
 			struct async_entry, list);
@@ -236,9 +243,7 @@ EXPORT_SYMBOL_GPL(async_schedule_domain);
  */
 void async_synchronize_full(void)
 {
-	do {
-		async_synchronize_cookie(next_cookie);
-	} while (!list_empty(&async_running) || !list_empty(&async_pending));
+	async_synchronize_cookie_domain(next_cookie, NULL);
 }
 EXPORT_SYMBOL_GPL(async_synchronize_full);
 
@@ -258,7 +263,7 @@ EXPORT_SYMBOL_GPL(async_synchronize_full_domain);
 /**
  * async_synchronize_cookie_domain - synchronize asynchronous function calls within a certain domain with cookie checkpointing
  * @cookie: async_cookie_t to use as checkpoint
- * @running: running list to synchronize on
+ * @running: running list to synchronize on, NULL indicates all lists
  *
  * This function waits until all asynchronous function calls for the
  * synchronization domain specified by the running list @list submitted
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index e99dda0..f6b4ac7 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -256,7 +256,6 @@ static void untag_chunk(struct node *p)
 		spin_unlock(&hash_lock);
 		spin_unlock(&entry->lock);
 		fsnotify_destroy_mark(entry);
-		fsnotify_put_mark(entry);
 		goto out;
 	}
 
@@ -265,7 +264,7 @@ static void untag_chunk(struct node *p)
 
 	fsnotify_duplicate_mark(&new->mark, entry);
 	if (fsnotify_add_mark(&new->mark, new->mark.group, new->mark.i.inode, NULL, 1)) {
-		free_chunk(new);
+		fsnotify_put_mark(&new->mark);
 		goto Fallback;
 	}
 
@@ -299,7 +298,6 @@ static void untag_chunk(struct node *p)
 	spin_unlock(&hash_lock);
 	spin_unlock(&entry->lock);
 	fsnotify_destroy_mark(entry);
-	fsnotify_put_mark(entry);
 	goto out;
 
 Fallback:
@@ -328,7 +326,7 @@ static int create_chunk(struct inode *inode, struct audit_tree *tree)
 
 	entry = &chunk->mark;
 	if (fsnotify_add_mark(entry, audit_tree_group, inode, NULL, 0)) {
-		free_chunk(chunk);
+		fsnotify_put_mark(entry);
 		return -ENOSPC;
 	}
 
@@ -338,6 +336,7 @@ static int create_chunk(struct inode *inode, struct audit_tree *tree)
 		spin_unlock(&hash_lock);
 		chunk->dead = 1;
 		spin_unlock(&entry->lock);
+		fsnotify_get_mark(entry);
 		fsnotify_destroy_mark(entry);
 		fsnotify_put_mark(entry);
 		return 0;
@@ -402,7 +401,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 	fsnotify_duplicate_mark(chunk_entry, old_entry);
 	if (fsnotify_add_mark(chunk_entry, chunk_entry->group, chunk_entry->i.inode, NULL, 1)) {
 		spin_unlock(&old_entry->lock);
-		free_chunk(chunk);
+		fsnotify_put_mark(chunk_entry);
 		fsnotify_put_mark(old_entry);
 		return -ENOSPC;
 	}
@@ -418,6 +417,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 		spin_unlock(&chunk_entry->lock);
 		spin_unlock(&old_entry->lock);
 
+		fsnotify_get_mark(chunk_entry);
 		fsnotify_destroy_mark(chunk_entry);
 
 		fsnotify_put_mark(chunk_entry);
@@ -451,7 +451,6 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 	spin_unlock(&old_entry->lock);
 	fsnotify_destroy_mark(old_entry);
 	fsnotify_put_mark(old_entry); /* pair to fsnotify_find mark_entry */
-	fsnotify_put_mark(old_entry); /* and kill it */
 	return 0;
 }
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 5083a09..739553e 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1803,9 +1803,8 @@ static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
 	 * trading it for newcg is protected by cgroup_mutex, we're safe to drop
 	 * it here; it will be freed under RCU.
 	 */
-	put_css_set(oldcg);
-
 	set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
+	put_css_set(oldcg);
 	return 0;
 }
 
diff --git a/kernel/compat.c b/kernel/compat.c
index fc9eb093..3507c93 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -318,25 +318,54 @@ asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set)
 
 #ifdef __ARCH_WANT_SYS_SIGPROCMASK
 
-asmlinkage long compat_sys_sigprocmask(int how, compat_old_sigset_t __user *set,
-		compat_old_sigset_t __user *oset)
+/*
+ * sys_sigprocmask SIG_SETMASK sets the first (compat) word of the
+ * blocked set of signals to the supplied signal set
+ */
+static inline void compat_sig_setmask(sigset_t *blocked, compat_sigset_word set)
 {
-	old_sigset_t s;
-	long ret;
-	mm_segment_t old_fs;
+	memcpy(blocked->sig, &set, sizeof(set));
+}
 
-	if (set && get_user(s, set))
-		return -EFAULT;
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	ret = sys_sigprocmask(how,
-			      set ? (old_sigset_t __user *) &s : NULL,
-			      oset ? (old_sigset_t __user *) &s : NULL);
-	set_fs(old_fs);
-	if (ret == 0)
-		if (oset)
-			ret = put_user(s, oset);
-	return ret;
+asmlinkage long compat_sys_sigprocmask(int how,
+				       compat_old_sigset_t __user *nset,
+				       compat_old_sigset_t __user *oset)
+{
+	old_sigset_t old_set, new_set;
+	sigset_t new_blocked;
+
+	old_set = current->blocked.sig[0];
+
+	if (nset) {
+		if (get_user(new_set, nset))
+			return -EFAULT;
+		new_set &= ~(sigmask(SIGKILL) | sigmask(SIGSTOP));
+
+		new_blocked = current->blocked;
+
+		switch (how) {
+		case SIG_BLOCK:
+			sigaddsetmask(&new_blocked, new_set);
+			break;
+		case SIG_UNBLOCK:
+			sigdelsetmask(&new_blocked, new_set);
+			break;
+		case SIG_SETMASK:
+			compat_sig_setmask(&new_blocked, new_set);
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		set_current_blocked(&new_blocked);
+	}
+
+	if (oset) {
+		if (put_user(old_set, oset))
+			return -EFAULT;
+	}
+
+	return 0;
 }
 
 #endif
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 9c9b754..6cbe033 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -123,6 +123,19 @@ static inline struct cpuset *task_cs(struct task_struct *task)
 			    struct cpuset, css);
 }
 
+#ifdef CONFIG_NUMA
+static inline bool task_has_mempolicy(struct task_struct *task)
+{
+	return task->mempolicy;
+}
+#else
+static inline bool task_has_mempolicy(struct task_struct *task)
+{
+	return false;
+}
+#endif
+
+
 /* bits in struct cpuset flags field */
 typedef enum {
 	CS_CPU_EXCLUSIVE,
@@ -949,7 +962,8 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
 static void cpuset_change_task_nodemask(struct task_struct *tsk,
 					nodemask_t *newmems)
 {
-repeat:
+	bool need_loop;
+
 	/*
 	 * Allow tasks that have access to memory reserves because they have
 	 * been OOM killed to get memory anywhere.
@@ -960,46 +974,27 @@ repeat:
 		return;
 
 	task_lock(tsk);
-	nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
-	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
-
-
 	/*
-	 * ensure checking ->mems_allowed_change_disable after setting all new
-	 * allowed nodes.
-	 *
-	 * the read-side task can see an nodemask with new allowed nodes and
-	 * old allowed nodes. and if it allocates page when cpuset clears newly
-	 * disallowed ones continuous, it can see the new allowed bits.
-	 *
-	 * And if setting all new allowed nodes is after the checking, setting
-	 * all new allowed nodes and clearing newly disallowed ones will be done
-	 * continuous, and the read-side task may find no node to alloc page.
+	 * Determine if a loop is necessary if another thread is doing
+	 * get_mems_allowed().  If at least one node remains unchanged and
+	 * tsk does not have a mempolicy, then an empty nodemask will not be
+	 * possible when mems_allowed is larger than a word.
 	 */
-	smp_mb();
+	need_loop = task_has_mempolicy(tsk) ||
+			!nodes_intersects(*newmems, tsk->mems_allowed);
 
-	/*
-	 * Allocation of memory is very fast, we needn't sleep when waiting
-	 * for the read-side.
-	 */
-	while (ACCESS_ONCE(tsk->mems_allowed_change_disable)) {
-		task_unlock(tsk);
-		if (!task_curr(tsk))
-			yield();
-		goto repeat;
-	}
+	if (need_loop)
+		write_seqcount_begin(&tsk->mems_allowed_seq);
 
-	/*
-	 * ensure checking ->mems_allowed_change_disable before clearing all new
-	 * disallowed nodes.
-	 *
-	 * if clearing newly disallowed bits before the checking, the read-side
-	 * task may find no node to alloc page.
-	 */
-	smp_mb();
+	nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
+	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
 
 	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2);
 	tsk->mems_allowed = *newmems;
+
+	if (need_loop)
+		write_seqcount_end(&tsk->mems_allowed_seq);
+
 	task_unlock(tsk);
 }
 
@@ -2085,6 +2080,9 @@ static void scan_for_empty_cpusets(struct cpuset *root)
  * (of no affect) on systems that are actively using CPU hotplug
  * but making no active use of cpusets.
  *
+ * The only exception to this is suspend/resume, where we don't
+ * modify cpusets at all.
+ *
  * This routine ensures that top_cpuset.cpus_allowed tracks
  * cpu_active_mask on each CPU hotplug (cpuhp) event.
  *
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 32a6151..7b344be 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2969,12 +2969,12 @@ EXPORT_SYMBOL_GPL(perf_event_release_kernel);
 /*
  * Called when the last reference to the file is gone.
  */
-static int perf_release(struct inode *inode, struct file *file)
+static void put_event(struct perf_event *event)
 {
-	struct perf_event *event = file->private_data;
 	struct task_struct *owner;
 
-	file->private_data = NULL;
+	if (!atomic_long_dec_and_test(&event->refcount))
+		return;
 
 	rcu_read_lock();
 	owner = ACCESS_ONCE(event->owner);
@@ -3009,7 +3009,13 @@ static int perf_release(struct inode *inode, struct file *file)
 		put_task_struct(owner);
 	}
 
-	return perf_event_release_kernel(event);
+	perf_event_release_kernel(event);
+}
+
+static int perf_release(struct inode *inode, struct file *file)
+{
+	put_event(file->private_data);
+	return 0;
 }
 
 u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
@@ -3241,7 +3247,7 @@ unlock:
 
 static const struct file_operations perf_fops;
 
-static struct perf_event *perf_fget_light(int fd, int *fput_needed)
+static struct file *perf_fget_light(int fd, int *fput_needed)
 {
 	struct file *file;
 
@@ -3255,7 +3261,7 @@ static struct perf_event *perf_fget_light(int fd, int *fput_needed)
 		return ERR_PTR(-EBADF);
 	}
 
-	return file->private_data;
+	return file;
 }
 
 static int perf_event_set_output(struct perf_event *event,
@@ -3287,19 +3293,21 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 	case PERF_EVENT_IOC_SET_OUTPUT:
 	{
+		struct file *output_file = NULL;
 		struct perf_event *output_event = NULL;
 		int fput_needed = 0;
 		int ret;
 
 		if (arg != -1) {
-			output_event = perf_fget_light(arg, &fput_needed);
-			if (IS_ERR(output_event))
-				return PTR_ERR(output_event);
+			output_file = perf_fget_light(arg, &fput_needed);
+			if (IS_ERR(output_file))
+				return PTR_ERR(output_file);
+			output_event = output_file->private_data;
 		}
 
 		ret = perf_event_set_output(event, output_event);
 		if (output_event)
-			fput_light(output_event->filp, fput_needed);
+			fput_light(output_file, fput_needed);
 
 		return ret;
 	}
@@ -6181,6 +6189,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 	mutex_init(&event->mmap_mutex);
 
+	atomic_long_set(&event->refcount, 1);
 	event->cpu		= cpu;
 	event->attr		= *attr;
 	event->group_leader	= group_leader;
@@ -6455,12 +6464,12 @@ SYSCALL_DEFINE5(perf_event_open,
 		return event_fd;
 
 	if (group_fd != -1) {
-		group_leader = perf_fget_light(group_fd, &fput_needed);
-		if (IS_ERR(group_leader)) {
-			err = PTR_ERR(group_leader);
+		group_file = perf_fget_light(group_fd, &fput_needed);
+		if (IS_ERR(group_file)) {
+			err = PTR_ERR(group_file);
 			goto err_fd;
 		}
-		group_file = group_leader->filp;
+		group_leader = group_file->private_data;
 		if (flags & PERF_FLAG_FD_OUTPUT)
 			output_event = group_leader;
 		if (flags & PERF_FLAG_FD_NO_GROUP)
@@ -6594,7 +6603,6 @@ SYSCALL_DEFINE5(perf_event_open,
 		put_ctx(gctx);
 	}
 
-	event->filp = event_file;
 	WARN_ON_ONCE(ctx->parent_ctx);
 	mutex_lock(&ctx->mutex);
 
@@ -6682,7 +6690,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 		goto err_free;
 	}
 
-	event->filp = NULL;
 	WARN_ON_ONCE(ctx->parent_ctx);
 	mutex_lock(&ctx->mutex);
 	perf_install_in_context(ctx, event, cpu);
@@ -6731,7 +6738,7 @@ static void sync_child_event(struct perf_event *child_event,
 	 * Release the parent event, if this was the last
 	 * reference to it.
 	 */
-	fput(parent_event->filp);
+	put_event(parent_event);
 }
 
 static void
@@ -6807,9 +6814,8 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	 *
 	 *   __perf_event_exit_task()
 	 *     sync_child_event()
-	 *       fput(parent_event->filp)
-	 *         perf_release()
-	 *           mutex_lock(&ctx->mutex)
+	 *       put_event()
+	 *         mutex_lock(&ctx->mutex)
 	 *
 	 * But since its the parent context it won't be the same instance.
 	 */
@@ -6877,7 +6883,7 @@ static void perf_free_event(struct perf_event *event,
 	list_del_init(&event->child_list);
 	mutex_unlock(&parent->child_mutex);
 
-	fput(parent->filp);
+	put_event(parent);
 
 	perf_group_detach(event);
 	list_del_event(event, ctx);
@@ -6957,6 +6963,12 @@ inherit_event(struct perf_event *parent_event,
 					   NULL);
 	if (IS_ERR(child_event))
 		return child_event;
+
+	if (!atomic_long_inc_not_zero(&parent_event->refcount)) {
+		free_event(child_event);
+		return NULL;
+	}
+
 	get_ctx(child_ctx);
 
 	/*
@@ -6996,14 +7008,6 @@ inherit_event(struct perf_event *parent_event,
 	raw_spin_unlock_irqrestore(&child_ctx->lock, flags);
 
 	/*
-	 * Get a reference to the parent filp - we will fput it
-	 * when the child event exits. This is safe to do because
-	 * we are in the parent and we know that the filp still
-	 * exists and has a nonzero count:
-	 */
-	atomic_long_inc(&parent_event->filp->f_count);
-
-	/*
 	 * Link this into the parent event's child list
 	 */
 	WARN_ON_ONCE(parent_event->ctx->parent_ctx);
diff --git a/kernel/exit.c b/kernel/exit.c
index 303bed2..97dd317 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1049,6 +1049,22 @@ NORET_TYPE void do_exit(long code)
 
 	preempt_disable();
 	exit_rcu();
+
+	/*
+	 * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
+	 * when the following two conditions become true.
+	 *   - There is race condition of mmap_sem (It is acquired by
+	 *     exit_mm()), and
+	 *   - SMI occurs before setting TASK_RUNINNG.
+	 *     (or hypervisor of virtual machine switches to other guest)
+	 *  As a result, we may become TASK_RUNNING after becoming TASK_DEAD
+	 *
+	 * To avoid it, we have to wait for releasing tsk->pi_lock which
+	 * is held by try_to_wake_up()
+	 */
+	smp_mb();
+	raw_spin_unlock_wait(&tsk->pi_lock);
+
 	/* causes final put_task_struct in finish_task_switch(). */
 	tsk->state = TASK_DEAD;
 	schedule();
diff --git a/kernel/fork.c b/kernel/fork.c
index 06909a9..158ca4f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -48,6 +48,7 @@
 #include <linux/audit.h>
 #include <linux/memcontrol.h>
 #include <linux/ftrace.h>
+#include <linux/proc_fs.h>
 #include <linux/profile.h>
 #include <linux/rmap.h>
 #include <linux/ksm.h>
@@ -1000,6 +1001,9 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 #ifdef CONFIG_CGROUPS
 	init_rwsem(&sig->threadgroup_fork_lock);
 #endif
+#ifdef CONFIG_CPUSETS
+	seqcount_init(&tsk->mems_allowed_seq);
+#endif
 
 	sig->oom_adj = current->signal->oom_adj;
 	sig->oom_score_adj = current->signal->oom_score_adj;
@@ -1394,6 +1398,8 @@ bad_fork_cleanup_io:
 	if (p->io_context)
 		exit_io_context(p);
 bad_fork_cleanup_namespaces:
+	if (unlikely(clone_flags & CLONE_NEWPID))
+		pid_ns_release_proc(p->nsproxy->pid_ns);
 	exit_task_namespaces(p);
 bad_fork_cleanup_mm:
 	if (p->mm) {
diff --git a/kernel/futex.c b/kernel/futex.c
index b2d51a7..e45efe7 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2231,11 +2231,11 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
  * @uaddr2:	the pi futex we will take prior to returning to user-space
  *
  * The caller will wait on uaddr and will be requeued by futex_requeue() to
- * uaddr2 which must be PI aware.  Normal wakeup will wake on uaddr2 and
- * complete the acquisition of the rt_mutex prior to returning to userspace.
- * This ensures the rt_mutex maintains an owner when it has waiters; without
- * one, the pi logic wouldn't know which task to boost/deboost, if there was a
- * need to.
+ * uaddr2 which must be PI aware and unique from uaddr.  Normal wakeup will wake
+ * on uaddr2 and complete the acquisition of the rt_mutex prior to returning to
+ * userspace.  This ensures the rt_mutex maintains an owner when it has waiters;
+ * without one, the pi logic would not know which task to boost/deboost, if
+ * there was a need to.
  *
  * We call schedule in futex_wait_queue_me() when we enqueue and return there
  * via the following:
@@ -2272,6 +2272,9 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	struct futex_q q = futex_q_init;
 	int res, ret;
 
+	if (uaddr == uaddr2)
+		return -EINVAL;
+
 	if (!bitset)
 		return -EINVAL;
 
@@ -2343,7 +2346,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		 * signal.  futex_unlock_pi() will not destroy the lock_ptr nor
 		 * the pi_state.
 		 */
-		WARN_ON(!&q.pi_state);
+		WARN_ON(!q.pi_state);
 		pi_mutex = &q.pi_state->pi_mutex;
 		ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1);
 		debug_rt_mutex_free_waiter(&rt_waiter);
@@ -2370,7 +2373,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	 * fault, unlock the rt_mutex and return the fault to userspace.
 	 */
 	if (ret == -EFAULT) {
-		if (rt_mutex_owner(pi_mutex) == current)
+		if (pi_mutex && rt_mutex_owner(pi_mutex) == current)
 			rt_mutex_unlock(pi_mutex);
 	} else if (ret == -EINTR) {
 		/*
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 2043c08..957869f 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -657,6 +657,14 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
 	return 0;
 }
 
+static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
+{
+	ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
+	ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
+
+	return ktime_get_update_offsets(offs_real, offs_boot);
+}
+
 /*
  * Retrigger next event is called after clock was set
  *
@@ -665,22 +673,12 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
 static void retrigger_next_event(void *arg)
 {
 	struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases);
-	struct timespec realtime_offset, xtim, wtm, sleep;
 
 	if (!hrtimer_hres_active())
 		return;
 
-	/* Optimized out for !HIGH_RES */
-	get_xtime_and_monotonic_and_sleep_offset(&xtim, &wtm, &sleep);
-	set_normalized_timespec(&realtime_offset, -wtm.tv_sec, -wtm.tv_nsec);
-
-	/* Adjust CLOCK_REALTIME offset */
 	raw_spin_lock(&base->lock);
-	base->clock_base[HRTIMER_BASE_REALTIME].offset =
-		timespec_to_ktime(realtime_offset);
-	base->clock_base[HRTIMER_BASE_BOOTTIME].offset =
-		timespec_to_ktime(sleep);
-
+	hrtimer_update_base(base);
 	hrtimer_force_reprogram(base, 0);
 	raw_spin_unlock(&base->lock);
 }
@@ -710,13 +708,25 @@ static int hrtimer_switch_to_hres(void)
 		base->clock_base[i].resolution = KTIME_HIGH_RES;
 
 	tick_setup_sched_timer();
-
 	/* "Retrigger" the interrupt to get things going */
 	retrigger_next_event(NULL);
 	local_irq_restore(flags);
 	return 1;
 }
 
+/*
+ * Called from timekeeping code to reprogramm the hrtimer interrupt
+ * device. If called from the timer interrupt context we defer it to
+ * softirq context.
+ */
+void clock_was_set_delayed(void)
+{
+	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+
+	cpu_base->clock_was_set = 1;
+	__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+}
+
 #else
 
 static inline int hrtimer_hres_active(void) { return 0; }
@@ -1250,11 +1260,10 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	cpu_base->nr_events++;
 	dev->next_event.tv64 = KTIME_MAX;
 
-	entry_time = now = ktime_get();
+	raw_spin_lock(&cpu_base->lock);
+	entry_time = now = hrtimer_update_base(cpu_base);
 retry:
 	expires_next.tv64 = KTIME_MAX;
-
-	raw_spin_lock(&cpu_base->lock);
 	/*
 	 * We set expires_next to KTIME_MAX here with cpu_base->lock
 	 * held to prevent that a timer is enqueued in our queue via
@@ -1330,8 +1339,12 @@ retry:
 	 * We need to prevent that we loop forever in the hrtimer
 	 * interrupt routine. We give it 3 attempts to avoid
 	 * overreacting on some spurious event.
+	 *
+	 * Acquire base lock for updating the offsets and retrieving
+	 * the current time.
 	 */
-	now = ktime_get();
+	raw_spin_lock(&cpu_base->lock);
+	now = hrtimer_update_base(cpu_base);
 	cpu_base->nr_retries++;
 	if (++retries < 3)
 		goto retry;
@@ -1343,6 +1356,7 @@ retry:
 	 */
 	cpu_base->nr_hangs++;
 	cpu_base->hang_detected = 1;
+	raw_spin_unlock(&cpu_base->lock);
 	delta = ktime_sub(now, entry_time);
 	if (delta.tv64 > cpu_base->max_hang_time.tv64)
 		cpu_base->max_hang_time = delta;
@@ -1395,6 +1409,13 @@ void hrtimer_peek_ahead_timers(void)
 
 static void run_hrtimer_softirq(struct softirq_action *h)
 {
+	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+
+	if (cpu_base->clock_was_set) {
+		cpu_base->clock_was_set = 0;
+		clock_was_set();
+	}
+
 	hrtimer_peek_ahead_timers();
 }
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 470d08c..10e0772 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -117,7 +117,7 @@ irqreturn_t
 handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
 {
 	irqreturn_t retval = IRQ_NONE;
-	unsigned int random = 0, irq = desc->irq_data.irq;
+	unsigned int flags = 0, irq = desc->irq_data.irq;
 
 	do {
 		irqreturn_t res;
@@ -145,7 +145,7 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
 
 			/* Fall through to add to randomness */
 		case IRQ_HANDLED:
-			random |= action->flags;
+			flags |= action->flags;
 			break;
 
 		default:
@@ -156,8 +156,7 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
 		action = action->next;
 	} while (action);
 
-	if (random & IRQF_SAMPLE_RANDOM)
-		add_interrupt_randomness(irq);
+	add_interrupt_randomness(irq, flags);
 
 	if (!noirqdebug)
 		note_interrupt(irq, desc, retval);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index df8136f..fa4a70e 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -886,22 +886,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 	if (desc->irq_data.chip == &no_irq_chip)
 		return -ENOSYS;
-	/*
-	 * Some drivers like serial.c use request_irq() heavily,
-	 * so we have to be careful not to interfere with a
-	 * running system.
-	 */
-	if (new->flags & IRQF_SAMPLE_RANDOM) {
-		/*
-		 * This function might sleep, we want to call it first,
-		 * outside of the atomic block.
-		 * Yes, this might clear the entropy pool if the wrong
-		 * driver is attempted to be loaded, without actually
-		 * installing a new handler, but is this really a problem,
-		 * only the sysadmin is able to do this.
-		 */
-		rand_initialize_irq(irq);
-	}
 
 	/*
 	 * Check whether the interrupt nests into another interrupt
@@ -1325,7 +1309,6 @@ EXPORT_SYMBOL(free_irq);
  *	Flags:
  *
  *	IRQF_SHARED		Interrupt is shared
- *	IRQF_SAMPLE_RANDOM	The interrupt can be used for entropy
  *	IRQF_TRIGGER_*		Specify active edge(s) or level
  *
  */
diff --git a/kernel/module.c b/kernel/module.c
index b9d0667..a8bd215 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2605,6 +2605,10 @@ static int check_module_license_and_versions(struct module *mod)
 	if (strcmp(mod->name, "driverloader") == 0)
 		add_taint_module(mod, TAINT_PROPRIETARY_MODULE);
 
+	/* lve claims to be GPL but upstream won't provide source */
+	if (strcmp(mod->name, "lve") == 0)
+		add_taint_module(mod, TAINT_PROPRIETARY_MODULE);
+
 #ifdef CONFIG_MODVERSIONS
 	if ((mod->num_syms && !mod->crcs)
 	    || (mod->num_gpl_syms && !mod->gpl_crcs)
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 8884c27..32f1590 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -344,6 +344,7 @@ int hibernation_snapshot(int platform_mode)
 		goto Complete_devices;
 
 	suspend_console();
+	ftrace_stop();
 	pm_restrict_gfp_mask();
 	error = dpm_suspend(PMSG_FREEZE);
 	if (error)
@@ -369,6 +370,7 @@ int hibernation_snapshot(int platform_mode)
 	if (error || !in_suspend)
 		pm_restore_gfp_mask();
 
+	ftrace_start();
 	resume_console();
 
  Complete_devices:
@@ -471,6 +473,7 @@ int hibernation_restore(int platform_mode)
 
 	pm_prepare_console();
 	suspend_console();
+	ftrace_stop();
 	pm_restrict_gfp_mask();
 	error = dpm_suspend_start(PMSG_QUIESCE);
 	if (!error) {
@@ -478,6 +481,7 @@ int hibernation_restore(int platform_mode)
 		dpm_resume_end(PMSG_RECOVER);
 	}
 	pm_restore_gfp_mask();
+	ftrace_start();
 	resume_console();
 	pm_restore_console();
 	return error;
@@ -504,6 +508,7 @@ int hibernation_platform_enter(void)
 
 	entering_platform_hibernation = true;
 	suspend_console();
+	ftrace_stop();
 	error = dpm_suspend_start(PMSG_HIBERNATE);
 	if (error) {
 		if (hibernation_ops->recover)
@@ -547,6 +552,7 @@ int hibernation_platform_enter(void)
  Resume_devices:
 	entering_platform_hibernation = false;
 	dpm_resume_end(PMSG_RESTORE);
+	ftrace_start();
 	resume_console();
 
  Close:
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 61e6347..f5adb6e 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/suspend.h>
 #include <linux/syscore_ops.h>
+#include <linux/ftrace.h>
 #include <trace/events/power.h>
 
 #include "power.h"
@@ -213,6 +214,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 			goto Close;
 	}
 	suspend_console();
+	ftrace_stop();
 	suspend_test_start();
 	error = dpm_suspend_start(PMSG_SUSPEND);
 	if (error) {
@@ -229,6 +231,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 	suspend_test_start();
 	dpm_resume_end(PMSG_RESUME);
 	suspend_test_finish("resume devices");
+	ftrace_start();
 	resume_console();
  Close:
 	if (suspend_ops->end)
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index ba06207..fe7a9b0 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -283,7 +283,9 @@ cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
 static int
 cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
 {
-	return *rdp->nxttail[RCU_DONE_TAIL] && !rcu_gp_in_progress(rsp);
+	return *rdp->nxttail[RCU_DONE_TAIL +
+			     ACCESS_ONCE(rsp->completed) != rdp->completed] &&
+	       !rcu_gp_in_progress(rsp);
 }
 
 /*
diff --git a/kernel/sched.c b/kernel/sched.c
index d488880..e788b66 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -606,22 +606,19 @@ static inline int cpu_of(struct rq *rq)
 /*
  * Return the group to which this tasks belongs.
  *
- * We use task_subsys_state_check() and extend the RCU verification with
- * pi->lock and rq->lock because cpu_cgroup_attach() holds those locks for each
- * task it moves into the cgroup. Therefore by holding either of those locks,
- * we pin the task to the current cgroup.
+ * We cannot use task_subsys_state() and friends because the cgroup
+ * subsystem changes that value before the cgroup_subsys::attach() method
+ * is called, therefore we cannot pin it and might observe the wrong value.
+ *
+ * The same is true for autogroup's p->signal->autogroup->tg, the autogroup
+ * core changes this before calling sched_move_task().
+ *
+ * Instead we use a 'copy' which is updated from sched_move_task() while
+ * holding both task_struct::pi_lock and rq::lock.
  */
 static inline struct task_group *task_group(struct task_struct *p)
 {
-	struct task_group *tg;
-	struct cgroup_subsys_state *css;
-
-	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
-			lockdep_is_held(&p->pi_lock) ||
-			lockdep_is_held(&task_rq(p)->lock));
-	tg = container_of(css, struct task_group, css);
-
-	return autogroup_task_group(p, tg);
+	return p->sched_task_group;
 }
 
 /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
@@ -2207,7 +2204,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	 * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
 	 *
 	 * sched_move_task() holds both and thus holding either pins the cgroup,
-	 * see set_task_rq().
+	 * see task_group().
 	 *
 	 * Furthermore, all task_rq users should acquire both locks, see
 	 * task_rq_lock().
@@ -7221,11 +7218,8 @@ int sched_domain_level_max;
 
 static int __init setup_relax_domain_level(char *str)
 {
-	unsigned long val;
-
-	val = simple_strtoul(str, NULL, 0);
-	if (val < sched_domain_level_max)
-		default_relax_domain_level = val;
+	if (kstrtoint(str, 0, &default_relax_domain_level))
+		pr_warn("Unable to set relax_domain_level\n");
 
 	return 1;
 }
@@ -7418,7 +7412,6 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
 	if (!sd)
 		return child;
 
-	set_domain_attribute(sd, attr);
 	cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
 	if (child) {
 		sd->level = child->level + 1;
@@ -7426,6 +7419,7 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
 		child->parent = sd;
 	}
 	sd->child = child;
+	set_domain_attribute(sd, attr);
 
 	return sd;
 }
@@ -7784,34 +7778,66 @@ int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
 }
 #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
 
+static int num_cpus_frozen;	/* used to mark begin/end of suspend/resume */
+
 /*
  * Update cpusets according to cpu_active mask.  If cpusets are
  * disabled, cpuset_update_active_cpus() becomes a simple wrapper
  * around partition_sched_domains().
+ *
+ * If we come here as part of a suspend/resume, don't touch cpusets because we
+ * want to restore it back to its original state upon resume anyway.
  */
 static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
 			     void *hcpu)
 {
-	switch (action & ~CPU_TASKS_FROZEN) {
+	switch (action) {
+	case CPU_ONLINE_FROZEN:
+	case CPU_DOWN_FAILED_FROZEN:
+
+		/*
+		 * num_cpus_frozen tracks how many CPUs are involved in suspend
+		 * resume sequence. As long as this is not the last online
+		 * operation in the resume sequence, just build a single sched
+		 * domain, ignoring cpusets.
+		 */
+		num_cpus_frozen--;
+		if (likely(num_cpus_frozen)) {
+			partition_sched_domains(1, NULL, NULL);
+			break;
+		}
+
+		/*
+		 * This is the last CPU online operation. So fall through and
+		 * restore the original sched domains by considering the
+		 * cpuset configurations.
+		 */
+
 	case CPU_ONLINE:
 	case CPU_DOWN_FAILED:
 		cpuset_update_active_cpus();
-		return NOTIFY_OK;
+		break;
 	default:
 		return NOTIFY_DONE;
 	}
+	return NOTIFY_OK;
 }
 
 static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
 			       void *hcpu)
 {
-	switch (action & ~CPU_TASKS_FROZEN) {
+	switch (action) {
 	case CPU_DOWN_PREPARE:
 		cpuset_update_active_cpus();
-		return NOTIFY_OK;
+		break;
+	case CPU_DOWN_PREPARE_FROZEN:
+		num_cpus_frozen++;
+		partition_sched_domains(1, NULL, NULL);
+		break;
 	default:
 		return NOTIFY_DONE;
 	}
+	return NOTIFY_OK;
 }
 
 static int update_runtime(struct notifier_block *nfb,
@@ -8560,6 +8586,7 @@ void sched_destroy_group(struct task_group *tg)
  */
 void sched_move_task(struct task_struct *tsk)
 {
+	struct task_group *tg;
 	int on_rq, running;
 	unsigned long flags;
 	struct rq *rq;
@@ -8574,6 +8601,12 @@ void sched_move_task(struct task_struct *tsk)
 	if (unlikely(running))
 		tsk->sched_class->put_prev_task(rq, tsk);
 
+	tg = container_of(task_subsys_state_check(tsk, cpu_cgroup_subsys_id,
+				lockdep_is_held(&tsk->sighand->siglock)),
+			  struct task_group, css);
+	tg = autogroup_task_group(tsk, tg);
+	tsk->sched_task_group = tg;
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	if (tsk->sched_class->task_move_group)
 		tsk->sched_class->task_move_group(tsk, on_rq);
diff --git a/kernel/sys.c b/kernel/sys.c
index f88dadc..84e353b 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -334,6 +334,7 @@ void kernel_restart_prepare(char *cmd)
 void kernel_restart(char *cmd)
 {
 	kernel_restart_prepare(cmd);
+	disable_nonboot_cpus();
 	if (!cmd)
 		printk(KERN_EMERG "Restarting system.\n");
 	else
@@ -1132,15 +1133,16 @@ DECLARE_RWSEM(uts_sem);
  * Work around broken programs that cannot handle "Linux 3.0".
  * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40
  */
-static int override_release(char __user *release, int len)
+static int override_release(char __user *release, size_t len)
 {
 	int ret = 0;
-	char buf[65];
 
 	if (current->personality & UNAME26) {
-		char *rest = UTS_RELEASE;
+		const char *rest = UTS_RELEASE;
+		char buf[65] = { 0 };
 		int ndots = 0;
 		unsigned v;
+		size_t copy;
 
 		while (*rest) {
 			if (*rest == '.' && ++ndots >= 3)
@@ -1150,8 +1152,9 @@ static int override_release(char __user *release, int len)
 			rest++;
 		}
 		v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 40;
-		snprintf(buf, len, "2.6.%u%s", v, rest);
-		ret = copy_to_user(release, buf, len);
+		copy = clamp_t(size_t, len, 1, sizeof(buf));
+		copy = scnprintf(buf, copy, "2.6.%u%s", v, rest);
+		ret = copy_to_user(release, buf, copy + 1);
 	}
 	return ret;
 }
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 4b85a7a..61fc450 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -31,8 +31,6 @@ unsigned long			tick_nsec;
 u64				tick_length;
 static u64			tick_length_base;
 
-static struct hrtimer		leap_timer;
-
 #define MAX_TICKADJ		500LL		/* usecs */
 #define MAX_TICKADJ_SCALED \
 	(((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
@@ -350,60 +348,64 @@ void ntp_clear(void)
 }
 
 /*
- * Leap second processing. If in leap-insert state at the end of the
- * day, the system clock is set back one second; if in leap-delete
- * state, the system clock is set ahead one second.
+ * this routine handles the overflow of the microsecond field
+ *
+ * The tricky bits of code to handle the accurate clock support
+ * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame.
+ * They were originally developed for SUN and DEC kernels.
+ * All the kudos should go to Dave for this stuff.
+ *
+ * Also handles leap second processing, and returns leap offset
  */
-static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
+int second_overflow(unsigned long secs)
 {
-	enum hrtimer_restart res = HRTIMER_NORESTART;
-
-	write_seqlock(&xtime_lock);
+	int leap = 0;
+	s64 delta;
 
+	/*
+	 * Leap second processing. If in leap-insert state at the end of the
+	 * day, the system clock is set back one second; if in leap-delete
+	 * state, the system clock is set ahead one second.
+	 */
 	switch (time_state) {
 	case TIME_OK:
+		if (time_status & STA_INS)
+			time_state = TIME_INS;
+		else if (time_status & STA_DEL)
+			time_state = TIME_DEL;
 		break;
 	case TIME_INS:
-		timekeeping_leap_insert(-1);
-		time_state = TIME_OOP;
-		printk(KERN_NOTICE
-			"Clock: inserting leap second 23:59:60 UTC\n");
-		hrtimer_add_expires_ns(&leap_timer, NSEC_PER_SEC);
-		res = HRTIMER_RESTART;
+		if (!(time_status & STA_INS))
+			time_state = TIME_OK;
+		else if (secs % 86400 == 0) {
+			leap = -1;
+			time_state = TIME_OOP;
+			time_tai++;
+			printk(KERN_NOTICE
+				"Clock: inserting leap second 23:59:60 UTC\n");
+		}
 		break;
 	case TIME_DEL:
-		timekeeping_leap_insert(1);
-		time_tai--;
-		time_state = TIME_WAIT;
-		printk(KERN_NOTICE
-			"Clock: deleting leap second 23:59:59 UTC\n");
+		if (!(time_status & STA_DEL))
+			time_state = TIME_OK;
+		else if ((secs + 1) % 86400 == 0) {
+			leap = 1;
+			time_tai--;
+			time_state = TIME_WAIT;
+			printk(KERN_NOTICE
+				"Clock: deleting leap second 23:59:59 UTC\n");
+		}
 		break;
 	case TIME_OOP:
-		time_tai++;
 		time_state = TIME_WAIT;
-		/* fall through */
+		break;
+
 	case TIME_WAIT:
 		if (!(time_status & (STA_INS | STA_DEL)))
 			time_state = TIME_OK;
 		break;
 	}
 
-	write_sequnlock(&xtime_lock);
-
-	return res;
-}
-
-/*
- * this routine handles the overflow of the microsecond field
- *
- * The tricky bits of code to handle the accurate clock support
- * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame.
- * They were originally developed for SUN and DEC kernels.
- * All the kudos should go to Dave for this stuff.
- */
-void second_overflow(void)
-{
-	s64 delta;
 
 	/* Bump the maxerror field */
 	time_maxerror += MAXFREQ / NSEC_PER_USEC;
@@ -423,23 +425,25 @@ void second_overflow(void)
 	pps_dec_valid();
 
 	if (!time_adjust)
-		return;
+		goto out;
 
 	if (time_adjust > MAX_TICKADJ) {
 		time_adjust -= MAX_TICKADJ;
 		tick_length += MAX_TICKADJ_SCALED;
-		return;
+		goto out;
 	}
 
 	if (time_adjust < -MAX_TICKADJ) {
 		time_adjust += MAX_TICKADJ;
 		tick_length -= MAX_TICKADJ_SCALED;
-		return;
+		goto out;
 	}
 
 	tick_length += (s64)(time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ)
 							 << NTP_SCALE_SHIFT;
 	time_adjust = 0;
+out:
+	return leap;
 }
 
 #ifdef CONFIG_GENERIC_CMOS_UPDATE
@@ -501,27 +505,6 @@ static void notify_cmos_timer(void)
 static inline void notify_cmos_timer(void) { }
 #endif
 
-/*
- * Start the leap seconds timer:
- */
-static inline void ntp_start_leap_timer(struct timespec *ts)
-{
-	long now = ts->tv_sec;
-
-	if (time_status & STA_INS) {
-		time_state = TIME_INS;
-		now += 86400 - now % 86400;
-		hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS);
-
-		return;
-	}
-
-	if (time_status & STA_DEL) {
-		time_state = TIME_DEL;
-		now += 86400 - (now + 1) % 86400;
-		hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS);
-	}
-}
 
 /*
  * Propagate a new txc->status value into the NTP state:
@@ -546,22 +529,6 @@ static inline void process_adj_status(struct timex *txc, struct timespec *ts)
 	time_status &= STA_RONLY;
 	time_status |= txc->status & ~STA_RONLY;
 
-	switch (time_state) {
-	case TIME_OK:
-		ntp_start_leap_timer(ts);
-		break;
-	case TIME_INS:
-	case TIME_DEL:
-		time_state = TIME_OK;
-		ntp_start_leap_timer(ts);
-	case TIME_WAIT:
-		if (!(time_status & (STA_INS | STA_DEL)))
-			time_state = TIME_OK;
-		break;
-	case TIME_OOP:
-		hrtimer_restart(&leap_timer);
-		break;
-	}
 }
 /*
  * Called with the xtime lock held, so we can access and modify
@@ -643,9 +610,6 @@ int do_adjtimex(struct timex *txc)
 		    (txc->tick <  900000/USER_HZ ||
 		     txc->tick > 1100000/USER_HZ))
 			return -EINVAL;
-
-		if (txc->modes & ADJ_STATUS && time_state != TIME_OK)
-			hrtimer_cancel(&leap_timer);
 	}
 
 	if (txc->modes & ADJ_SETOFFSET) {
@@ -967,6 +931,4 @@ __setup("ntp_tick_adj=", ntp_tick_adj_setup);
 void __init ntp_init(void)
 {
 	ntp_clear();
-	hrtimer_init(&leap_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
-	leap_timer.function = ntp_leap_second;
 }
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 06a5f31..5928f95 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -161,23 +161,43 @@ static struct timespec xtime __attribute__ ((aligned (16)));
 static struct timespec wall_to_monotonic __attribute__ ((aligned (16)));
 static struct timespec total_sleep_time;
 
+/* Offset clock monotonic -> clock realtime */
+static ktime_t offs_real;
+
+/* Offset clock monotonic -> clock boottime */
+static ktime_t offs_boot;
+
 /*
  * The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock.
  */
 static struct timespec raw_time;
 
-/* flag for if timekeeping is suspended */
-int __read_mostly timekeeping_suspended;
+/* must hold write on xtime_lock */
+static void update_rt_offset(void)
+{
+	struct timespec tmp, *wtm = &wall_to_monotonic;
+
+	set_normalized_timespec(&tmp, -wtm->tv_sec, -wtm->tv_nsec);
+	offs_real = timespec_to_ktime(tmp);
+}
 
-/* must hold xtime_lock */
-void timekeeping_leap_insert(int leapsecond)
+/* must hold write on xtime_lock */
+static void timekeeping_update(bool clearntp)
 {
-	xtime.tv_sec += leapsecond;
-	wall_to_monotonic.tv_sec -= leapsecond;
-	update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
-			timekeeper.mult);
+	if (clearntp) {
+		timekeeper.ntp_error = 0;
+		ntp_clear();
+	}
+	update_rt_offset();
+	update_vsyscall(&xtime, &wall_to_monotonic,
+			 timekeeper.clock, timekeeper.mult);
 }
 
+
+
+/* flag for if timekeeping is suspended */
+int __read_mostly timekeeping_suspended;
+
 /**
  * timekeeping_forward_now - update clock to the current time
  *
@@ -362,7 +382,7 @@ int do_settimeofday(const struct timespec *tv)
 	struct timespec ts_delta;
 	unsigned long flags;
 
-	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
+	if (!timespec_valid_strict(tv))
 		return -EINVAL;
 
 	write_seqlock_irqsave(&xtime_lock, flags);
@@ -375,11 +395,7 @@ int do_settimeofday(const struct timespec *tv)
 
 	xtime = *tv;
 
-	timekeeper.ntp_error = 0;
-	ntp_clear();
-
-	update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
-				timekeeper.mult);
+	timekeeping_update(true);
 
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 
@@ -401,6 +417,8 @@ EXPORT_SYMBOL(do_settimeofday);
 int timekeeping_inject_offset(struct timespec *ts)
 {
 	unsigned long flags;
+	struct timespec tmp;
+	int ret = 0;
 
 	if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
 		return -EINVAL;
@@ -409,21 +427,24 @@ int timekeeping_inject_offset(struct timespec *ts)
 
 	timekeeping_forward_now();
 
+	tmp = timespec_add(xtime,  *ts);
+	if (!timespec_valid_strict(&tmp)) {
+		ret = -EINVAL;
+		goto error;
+	}
+
 	xtime = timespec_add(xtime, *ts);
 	wall_to_monotonic = timespec_sub(wall_to_monotonic, *ts);
 
-	timekeeper.ntp_error = 0;
-	ntp_clear();
-
-	update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
-				timekeeper.mult);
+error: /* even if we error out, we forwarded the time, so call update */
+	timekeeping_update(true);
 
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 
 	/* signal hrtimers about time change */
 	clock_was_set();
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(timekeeping_inject_offset);
 
@@ -570,7 +591,20 @@ void __init timekeeping_init(void)
 	struct timespec now, boot;
 
 	read_persistent_clock(&now);
+	if (!timespec_valid_strict(&now)) {
+		pr_warn("WARNING: Persistent clock returned invalid value!\n"
+			"         Check your CMOS/BIOS settings.\n");
+		now.tv_sec = 0;
+		now.tv_nsec = 0;
+	}
+
 	read_boot_clock(&boot);
+	if (!timespec_valid_strict(&boot)) {
+		pr_warn("WARNING: Boot clock returned invalid value!\n"
+			"         Check your CMOS/BIOS settings.\n");
+		boot.tv_sec = 0;
+		boot.tv_nsec = 0;
+	}
 
 	write_seqlock_irqsave(&xtime_lock, flags);
 
@@ -591,6 +625,7 @@ void __init timekeeping_init(void)
 	}
 	set_normalized_timespec(&wall_to_monotonic,
 				-boot.tv_sec, -boot.tv_nsec);
+	update_rt_offset();
 	total_sleep_time.tv_sec = 0;
 	total_sleep_time.tv_nsec = 0;
 	write_sequnlock_irqrestore(&xtime_lock, flags);
@@ -599,6 +634,12 @@ void __init timekeeping_init(void)
 /* time in seconds when suspend began */
 static struct timespec timekeeping_suspend_time;
 
+static void update_sleep_time(struct timespec t)
+{
+	total_sleep_time = t;
+	offs_boot = timespec_to_ktime(t);
+}
+
 /**
  * __timekeeping_inject_sleeptime - Internal function to add sleep interval
  * @delta: pointer to a timespec delta value
@@ -608,7 +649,7 @@ static struct timespec timekeeping_suspend_time;
  */
 static void __timekeeping_inject_sleeptime(struct timespec *delta)
 {
-	if (!timespec_valid(delta)) {
+	if (!timespec_valid_strict(delta)) {
 		printk(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid "
 					"sleep delta value!\n");
 		return;
@@ -616,7 +657,7 @@ static void __timekeeping_inject_sleeptime(struct timespec *delta)
 
 	xtime = timespec_add(xtime, *delta);
 	wall_to_monotonic = timespec_sub(wall_to_monotonic, *delta);
-	total_sleep_time = timespec_add(total_sleep_time, *delta);
+	update_sleep_time(timespec_add(total_sleep_time, *delta));
 }
 
 
@@ -645,10 +686,7 @@ void timekeeping_inject_sleeptime(struct timespec *delta)
 
 	__timekeeping_inject_sleeptime(delta);
 
-	timekeeper.ntp_error = 0;
-	ntp_clear();
-	update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
-				timekeeper.mult);
+	timekeeping_update(true);
 
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 
@@ -683,6 +721,7 @@ static void timekeeping_resume(void)
 	timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
 	timekeeper.ntp_error = 0;
 	timekeeping_suspended = 0;
+	timekeeping_update(false);
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 
 	touch_softlockup_watchdog();
@@ -834,9 +873,14 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
 
 	timekeeper.xtime_nsec += timekeeper.xtime_interval << shift;
 	while (timekeeper.xtime_nsec >= nsecps) {
+		int leap;
 		timekeeper.xtime_nsec -= nsecps;
 		xtime.tv_sec++;
-		second_overflow();
+		leap = second_overflow(xtime.tv_sec);
+		xtime.tv_sec += leap;
+		wall_to_monotonic.tv_sec -= leap;
+		if (leap)
+			clock_was_set_delayed();
 	}
 
 	/* Accumulate raw time */
@@ -881,6 +925,10 @@ static void update_wall_time(void)
 #else
 	offset = (clock->read(clock) - clock->cycle_last) & clock->mask;
 #endif
+	/* Check if there's really nothing to do */
+	if (offset < timekeeper.cycle_interval)
+		return;
+
 	timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift;
 
 	/*
@@ -942,14 +990,17 @@ static void update_wall_time(void)
 	 * xtime.tv_nsec isn't larger then NSEC_PER_SEC
 	 */
 	if (unlikely(xtime.tv_nsec >= NSEC_PER_SEC)) {
+		int leap;
 		xtime.tv_nsec -= NSEC_PER_SEC;
 		xtime.tv_sec++;
-		second_overflow();
+		leap = second_overflow(xtime.tv_sec);
+		xtime.tv_sec += leap;
+		wall_to_monotonic.tv_sec -= leap;
+		if (leap)
+			clock_was_set_delayed();
 	}
 
-	/* check to see if there is a new clocksource to use */
-	update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
-				timekeeper.mult);
+	timekeeping_update(false);
 }
 
 /**
@@ -1108,6 +1159,40 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
 	} while (read_seqretry(&xtime_lock, seq));
 }
 
+#ifdef CONFIG_HIGH_RES_TIMERS
+/**
+ * ktime_get_update_offsets - hrtimer helper
+ * @real:	pointer to storage for monotonic -> realtime offset
+ * @_boot:	pointer to storage for monotonic -> boottime offset
+ *
+ * Returns current monotonic time and updates the offsets
+ * Called from hrtimer_interupt() or retrigger_next_event()
+ */
+ktime_t ktime_get_update_offsets(ktime_t *real, ktime_t *boot)
+{
+	ktime_t now;
+	unsigned int seq;
+	u64 secs, nsecs;
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+
+		secs = xtime.tv_sec;
+		nsecs = xtime.tv_nsec;
+		nsecs += timekeeping_get_ns();
+		/* If arch requires, add in gettimeoffset() */
+		nsecs += arch_gettimeoffset();
+
+		*real = offs_real;
+		*boot = offs_boot;
+	} while (read_seqretry(&xtime_lock, seq));
+
+	now = ktime_add_ns(ktime_set(secs, 0), nsecs);
+	now = ktime_sub(now, *real);
+	return now;
+}
+#endif
+
 /**
  * ktime_get_monotonic_offset() - get wall_to_monotonic in ktime_t format
  */
diff --git a/kernel/timer.c b/kernel/timer.c
index 8cff361..27982d9 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -63,6 +63,7 @@ EXPORT_SYMBOL(jiffies_64);
 #define TVR_SIZE (1 << TVR_BITS)
 #define TVN_MASK (TVN_SIZE - 1)
 #define TVR_MASK (TVR_SIZE - 1)
+#define MAX_TVAL ((unsigned long)((1ULL << (TVR_BITS + 4*TVN_BITS)) - 1))
 
 struct tvec {
 	struct list_head vec[TVN_SIZE];
@@ -356,11 +357,12 @@ static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 		vec = base->tv1.vec + (base->timer_jiffies & TVR_MASK);
 	} else {
 		int i;
-		/* If the timeout is larger than 0xffffffff on 64-bit
-		 * architectures then we use the maximum timeout:
+		/* If the timeout is larger than MAX_TVAL (on 64-bit
+		 * architectures or with CONFIG_BASE_SMALL=1) then we
+		 * use the maximum timeout.
 		 */
-		if (idx > 0xffffffffUL) {
-			idx = 0xffffffffUL;
+		if (idx > MAX_TVAL) {
+			idx = MAX_TVAL;
 			expires = idx + base->timer_jiffies;
 		}
 		i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0731e81a..672a749 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2432,10 +2432,12 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 		if (cpumask_test_cpu(cpu, tracing_cpumask) &&
 				!cpumask_test_cpu(cpu, tracing_cpumask_new)) {
 			atomic_inc(&global_trace.data[cpu]->disabled);
+			ring_buffer_record_disable_cpu(global_trace.buffer, cpu);
 		}
 		if (!cpumask_test_cpu(cpu, tracing_cpumask) &&
 				cpumask_test_cpu(cpu, tracing_cpumask_new)) {
 			atomic_dec(&global_trace.data[cpu]->disabled);
+			ring_buffer_record_enable_cpu(global_trace.buffer, cpu);
 		}
 	}
 	arch_spin_unlock(&ftrace_max_lock);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 1456dab..aef9452 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1214,8 +1214,13 @@ static void worker_enter_idle(struct worker *worker)
 	} else
 		wake_up_all(&gcwq->trustee_wait);
 
-	/* sanity check nr_running */
-	WARN_ON_ONCE(gcwq->nr_workers == gcwq->nr_idle &&
+	/*
+	 * Sanity check nr_running.  Because trustee releases gcwq->lock
+	 * between setting %WORKER_ROGUE and zapping nr_running, the
+	 * warning may trigger spuriously.  Check iff trustee is idle.
+	 */
+	WARN_ON_ONCE(gcwq->trustee_state == TRUSTEE_DONE &&
+		     gcwq->nr_workers == gcwq->nr_idle &&
 		     atomic_read(get_gcwq_nr_running(gcwq->cpu)));
 }
 
@@ -1863,7 +1868,9 @@ __acquires(&gcwq->lock)
 
 	spin_unlock_irq(&gcwq->lock);
 
+	smp_wmb();	/* paired with test_and_set_bit(PENDING) */
 	work_clear_pending(work);
+
 	lock_map_acquire_read(&cwq->wq->lockdep_map);
 	lock_map_acquire(&lockdep_map);
 	trace_workqueue_execute_start(work);
@@ -3407,14 +3414,17 @@ static int __cpuinit trustee_thread(void *__gcwq)
 
 	for_each_busy_worker(worker, i, pos, gcwq) {
 		struct work_struct *rebind_work = &worker->rebind_work;
+		unsigned long worker_flags = worker->flags;
 
 		/*
 		 * Rebind_work may race with future cpu hotplug
 		 * operations.  Use a separate flag to mark that
-		 * rebinding is scheduled.
+		 * rebinding is scheduled.  The morphing should
+		 * be atomic.
 		 */
-		worker->flags |= WORKER_REBIND;
-		worker->flags &= ~WORKER_ROGUE;
+		worker_flags |= WORKER_REBIND;
+		worker_flags &= ~WORKER_ROGUE;
+		ACCESS_ONCE(worker->flags) = worker_flags;
 
 		/* queue rebind_work, wq doesn't matter, use the default one */
 		if (test_and_set_bit(WORK_STRUCT_PENDING_BIT,
@@ -3556,21 +3566,55 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
 	return notifier_from_errno(0);
 }
 
+/*
+ * Workqueues should be brought up before normal priority CPU notifiers.
+ * This will be registered high priority CPU notifier.
+ */
+static int __devinit workqueue_cpu_up_callback(struct notifier_block *nfb,
+					       unsigned long action,
+					       void *hcpu)
+{
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_UP_PREPARE:
+	case CPU_UP_CANCELED:
+	case CPU_DOWN_FAILED:
+	case CPU_ONLINE:
+		return workqueue_cpu_callback(nfb, action, hcpu);
+	}
+	return NOTIFY_OK;
+}
+
+/*
+ * Workqueues should be brought down after normal priority CPU notifiers.
+ * This will be registered as low priority CPU notifier.
+ */
+static int __devinit workqueue_cpu_down_callback(struct notifier_block *nfb,
+						 unsigned long action,
+						 void *hcpu)
+{
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_DOWN_PREPARE:
+	case CPU_DYING:
+	case CPU_POST_DEAD:
+		return workqueue_cpu_callback(nfb, action, hcpu);
+	}
+	return NOTIFY_OK;
+}
+
 #ifdef CONFIG_SMP
 
 struct work_for_cpu {
-	struct completion completion;
+	struct work_struct work;
 	long (*fn)(void *);
 	void *arg;
 	long ret;
 };
 
-static int do_work_for_cpu(void *_wfc)
+static void work_for_cpu_fn(struct work_struct *work)
 {
-	struct work_for_cpu *wfc = _wfc;
+	struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work);
+
 	wfc->ret = wfc->fn(wfc->arg);
-	complete(&wfc->completion);
-	return 0;
 }
 
 /**
@@ -3585,19 +3629,11 @@ static int do_work_for_cpu(void *_wfc)
  */
 long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
 {
-	struct task_struct *sub_thread;
-	struct work_for_cpu wfc = {
-		.completion = COMPLETION_INITIALIZER_ONSTACK(wfc.completion),
-		.fn = fn,
-		.arg = arg,
-	};
+	struct work_for_cpu wfc = { .fn = fn, .arg = arg };
 
-	sub_thread = kthread_create(do_work_for_cpu, &wfc, "work_for_cpu");
-	if (IS_ERR(sub_thread))
-		return PTR_ERR(sub_thread);
-	kthread_bind(sub_thread, cpu);
-	wake_up_process(sub_thread);
-	wait_for_completion(&wfc.completion);
+	INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn);
+	schedule_work_on(cpu, &wfc.work);
+	flush_work(&wfc.work);
 	return wfc.ret;
 }
 EXPORT_SYMBOL_GPL(work_on_cpu);
@@ -3749,7 +3785,8 @@ static int __init init_workqueues(void)
 	unsigned int cpu;
 	int i;
 
-	cpu_notifier(workqueue_cpu_callback, CPU_PRI_WORKQUEUE);
+	cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_UP);
+	cpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_DOWN);
 
 	/* initialize gcwqs */
 	for_each_gcwq_cpu(cpu) {