3.12.22-stable review

index 5cd0f0949927..998f4dfedecf 100644
@@ -40,6 +40,7 @@ extern struct fs_struct init_fs;
 
 #define INIT_SIGNALS(sig) {						\
 	.nr_threads	= 1,						\
+	.thread_head	= LIST_HEAD_INIT(init_task.thread_node),	\
 	.wait_chldexit	= __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\
 	.shared_pending	= { 						\
 		.list = LIST_HEAD_INIT(sig.shared_pending.list),	\

@@ -213,6 +214,7 @@ extern struct task_group root_task_group;
 		[PIDTYPE_SID]  = INIT_PID_LINK(PIDTYPE_SID),		\
 	},								\
 	.thread_group	= LIST_HEAD_INIT(tsk.thread_group),		\
+	.thread_node	= LIST_HEAD_INIT(init_signals.thread_head),	\
 	INIT_IDS							\
 	INIT_PERF_EVENTS(tsk)						\
 	INIT_TRACE_IRQFLAGS						\

index 8594b065d3a8..0827bec7d82f 100644
@@ -470,6 +470,7 @@ struct signal_struct {
 	atomic_t		sigcnt;
 	atomic_t		live;
 	int			nr_threads;
+	struct list_head	thread_head;
 
 	wait_queue_head_t	wait_chldexit;	/* for wait4() */
 

@@ -1148,6 +1149,7 @@ struct task_struct {
 	/* PID/PID hash table linkage. */
 	struct pid_link pids[PIDTYPE_MAX];
 	struct list_head thread_group;
+	struct list_head thread_node;
 
 	struct completion *vfork_done;		/* for vfork() */
 	int __user *set_child_tid;		/* CLONE_CHILD_SETTID */

@@ -2181,6 +2183,16 @@ extern bool current_is_single_threaded(void);
 #define while_each_thread(g, t) \
 	while ((t = next_thread(t)) != g)
 
+#define __for_each_thread(signal, t)	\
+	list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node)
+
+#define for_each_thread(p, t)		\
+	__for_each_thread((p)->signal, t)
+
+/* Careful: this is a double loop, 'break' won't work as expected. */
+#define for_each_process_thread(p, t)	\
+	for_each_process(p) for_each_thread(p, t)
+
 static inline int get_nr_threads(struct task_struct *tsk)
 {
 	return tsk->signal->nr_threads;

index dcde2c4b61d0..81b3d6789ee8 100644
@@ -74,6 +74,7 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
 		__this_cpu_dec(process_counts);
 	}
 	list_del_rcu(&p->thread_group);
+	list_del_rcu(&p->thread_node);
 }
 
 /*

index 458953ca4d50..11a23afc6ee5 100644
@@ -1038,6 +1038,11 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->nr_threads = 1;
 	atomic_set(&sig->live, 1);
 	atomic_set(&sig->sigcnt, 1);
+
+	/* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */
+	sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node);
+	tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head);
+
 	init_waitqueue_head(&sig->wait_chldexit);
 	sig->curr_target = tsk;
 	init_sigpending(&sig->shared_pending);

@@ -1476,6 +1481,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 			atomic_inc(&current->signal->sigcnt);
 			list_add_tail_rcu(&p->thread_group,
 					  &p->group_leader->thread_group);
+			list_add_tail_rcu(&p->thread_node,
+					  &p->signal->thread_head);
 		}
 		attach_pid(p, PIDTYPE_PID);
 		nr_threads++;

index e73f01c56d10..cae791c15c51 100644
@@ -59,7 +59,7 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk,
 {
 	struct task_struct *start = tsk;
 
-	do {
+	for_each_thread(start, tsk) {
 		if (mask) {
 			/*
 			 * If this is a mempolicy constrained oom, tsk's

@@ -77,7 +77,7 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk,
 			if (cpuset_mems_allowed_intersects(current, tsk))
 				return true;
 		}
-	} while_each_thread(start, tsk);
+	}
 
 	return false;
 }

@@ -97,14 +97,14 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk,
  */
 struct task_struct *find_lock_task_mm(struct task_struct *p)
 {
-	struct task_struct *t = p;
+	struct task_struct *t;
 
-	do {
+	for_each_thread(p, t) {
 		task_lock(t);
 		if (likely(t->mm))
 			return t;
 		task_unlock(t);
-	} while_each_thread(p, t);
+	}
 
 	return NULL;
 }

@@ -301,7 +301,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 	unsigned long chosen_points = 0;
 
 	rcu_read_lock();
-	do_each_thread(g, p) {
+	for_each_process_thread(g, p) {
 		unsigned int points;
 
 		switch (oom_scan_process_thread(p, totalpages, nodemask,

@@ -323,7 +323,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 			chosen = p;
 			chosen_points = points;
 		}
-	} while_each_thread(g, p);
+	}
 	if (chosen)
 		get_task_struct(chosen);
 	rcu_read_unlock();

@@ -406,7 +406,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 {
 	struct task_struct *victim = p;
 	struct task_struct *child;
-	struct task_struct *t = p;
+	struct task_struct *t;
 	struct mm_struct *mm;
 	unsigned int victim_points = 0;
 	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,

@@ -437,7 +437,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	 * still freeing memory.
 	 */
 	read_lock(&tasklist_lock);
-	do {
+	for_each_thread(p, t) {
 		list_for_each_entry(child, &t->children, sibling) {
 			unsigned int child_points;
 

@@ -455,7 +455,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 				get_task_struct(victim);
 			}
 		}
-	} while_each_thread(p, t);
+	}
 	read_unlock(&tasklist_lock);
 
 	rcu_read_lock();

index cae791c15c51..7cdd05e685dc 100644
@@ -47,18 +47,20 @@ static DEFINE_SPINLOCK(zone_scan_lock);
 #ifdef CONFIG_NUMA
 /**
  * has_intersects_mems_allowed() - check task eligiblity for kill
- * @tsk: task struct of which task to consider
+ * @start: task struct of which task to consider
  * @mask: nodemask passed to page allocator for mempolicy ooms
  *
  * Task eligibility is determined by whether or not a candidate task, @tsk,
  * shares the same mempolicy nodes as current if it is bound by such a policy
  * and whether or not it has the same set of allowed cpuset nodes.
  */
-static bool has_intersects_mems_allowed(struct task_struct *tsk,
+static bool has_intersects_mems_allowed(struct task_struct *start,
 					const nodemask_t *mask)
 {
-	struct task_struct *start = tsk;
+	struct task_struct *tsk;
+	bool ret = false;
 
+	rcu_read_lock();
 	for_each_thread(start, tsk) {
 		if (mask) {
 			/*

@@ -67,19 +69,20 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk,
 			 * mempolicy intersects current, otherwise it may be
 			 * needlessly killed.
 			 */
-			if (mempolicy_nodemask_intersects(tsk, mask))
-				return true;
+			ret = mempolicy_nodemask_intersects(tsk, mask);
 		} else {
 			/*
 			 * This is not a mempolicy constrained oom, so only
 			 * check the mems of tsk's cpuset.
 			 */
-			if (cpuset_mems_allowed_intersects(current, tsk))
-				return true;
+			ret = cpuset_mems_allowed_intersects(current, tsk);
 		}
+		if (ret)
+			break;
 	}
+	rcu_read_unlock();
 
-	return false;
+	return ret;
 }
 #else
 static bool has_intersects_mems_allowed(struct task_struct *tsk,

index 7cdd05e685dc..f5bed7f17463 100644
@@ -102,14 +102,19 @@ struct task_struct *find_lock_task_mm(struct task_struct *p)
 {
 	struct task_struct *t;
 
+	rcu_read_lock();
+
 	for_each_thread(p, t) {
 		task_lock(t);
 		if (likely(t->mm))
-			return t;
+			goto found;
 		task_unlock(t);
 	}
+	t = NULL;
+found:
+	rcu_read_unlock();
 
-	return NULL;
+	return t;
 }
 
 /* return true if the task is not adequate as candidate victim task. */

@@ -461,10 +466,8 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	}
 	read_unlock(&tasklist_lock);
 
-	rcu_read_lock();
 	p = find_lock_task_mm(victim);
 	if (!p) {
-		rcu_read_unlock();
 		put_task_struct(victim);
 		return;
 	} else if (victim != p) {

@@ -490,6 +493,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	 * That thread will now get access to memory reserves since it has a
 	 * pending fatal signal.
 	 */
+	rcu_read_lock();
 	for_each_process(p)
 		if (p->mm == mm && !same_thread_group(p, victim) &&
 		    !(p->flags & PF_KTHREAD)) {

index 15429b92ff98..213d1b4aafd7 100644
@@ -1820,13 +1820,18 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 				break;
 			};
 			points = oom_badness(task, memcg, NULL, totalpages);
-			if (points > chosen_points) {
-				if (chosen)
-					put_task_struct(chosen);
-				chosen = task;
-				chosen_points = points;
-				get_task_struct(chosen);
-			}
+			if (!points || points < chosen_points)
+				continue;
+			/* Prefer thread group leaders for display purposes */
+			if (points == chosen_points &&
+			    thread_group_leader(chosen))
+				continue;
+
+			if (chosen)
+				put_task_struct(chosen);
+			chosen = task;
+			chosen_points = points;
+			get_task_struct(chosen);
 		}
 		css_task_iter_end(&it);
 	}

index f5bed7f17463..a9b5b7ffc476 100644
@@ -327,10 +327,14 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 			break;
 		};
 		points = oom_badness(p, NULL, nodemask, totalpages);
-		if (points > chosen_points) {
-			chosen = p;
-			chosen_points = points;
-		}
+		if (!points || points < chosen_points)
+			continue;
+		/* Prefer thread group leaders for display purposes */
+		if (points == chosen_points && thread_group_leader(chosen))
+			continue;
+
+		chosen = p;
+		chosen_points = points;
 	}
 	if (chosen)
 		get_task_struct(chosen);

index ab0fbb458c11..23c13165ce83 100644
@@ -311,6 +311,7 @@ struct ieee80211_roc_work {
 
 	bool started, abort, hw_begun, notified;
 	bool to_be_freed;
+	bool on_channel;
 
 	unsigned long hw_start_time;
 

index 6fb38558a5e6..7a17decd27f9 100644
@@ -333,7 +333,7 @@ void ieee80211_sw_roc_work(struct work_struct *work)
 		container_of(work, struct ieee80211_roc_work, work.work);
 	struct ieee80211_sub_if_data *sdata = roc->sdata;
 	struct ieee80211_local *local = sdata->local;
-	bool started;
+	bool started, on_channel;
 
 	mutex_lock(&local->mtx);
 

@@ -354,14 +354,26 @@ void ieee80211_sw_roc_work(struct work_struct *work)
 	if (!roc->started) {
 		struct ieee80211_roc_work *dep;
 
-		/* start this ROC */
-		ieee80211_offchannel_stop_vifs(local);
+		WARN_ON(local->use_chanctx);
+
+		/* If actually operating on the desired channel (with at least
+		 * 20 MHz channel width) don't stop all the operations but still
+		 * treat it as though the ROC operation started properly, so
+		 * other ROC operations won't interfere with this one.
+		 */
+		roc->on_channel = roc->chan == local->_oper_chandef.chan &&
+				  local->_oper_chandef.width != NL80211_CHAN_WIDTH_5 &&
+				  local->_oper_chandef.width != NL80211_CHAN_WIDTH_10;
 
-		/* switch channel etc */
+		/* start this ROC */
 		ieee80211_recalc_idle(local);
 
-		local->tmp_channel = roc->chan;
-		ieee80211_hw_config(local, 0);
+		if (!roc->on_channel) {
+			ieee80211_offchannel_stop_vifs(local);
+
+			local->tmp_channel = roc->chan;
+			ieee80211_hw_config(local, 0);
+		}
 
 		/* tell userspace or send frame */
 		ieee80211_handle_roc_started(roc);

@@ -380,9 +392,10 @@ void ieee80211_sw_roc_work(struct work_struct *work)
  finish:
 		list_del(&roc->list);
 		started = roc->started;
+		on_channel = roc->on_channel;
 		ieee80211_roc_notify_destroy(roc, !roc->abort);
 
-		if (started) {
+		if (started && !on_channel) {
 			ieee80211_flush_queues(local, NULL);
 
 			local->tmp_channel = NULL;

index 95f3f1da0d7f..d38e6a8d8b9f 100644
@@ -30,13 +30,15 @@ int ip6_route_me_harder(struct sk_buff *skb)
 		.daddr = iph->daddr,
 		.saddr = iph->saddr,
 	};
+	int err;
 
 	dst = ip6_route_output(net, skb->sk, &fl6);
-	if (dst->error) {
+	err = dst->error;
+	if (err) {
 		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
 		LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
 		dst_release(dst);
-		return dst->error;
+		return err;
 	}
 
 	/* Drop old route. */

index 7ed681a714a5..6c0a542e8ec1 100644
@@ -151,6 +151,21 @@ static const struct usb_device_id id_table[] = {
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 0)},	/* Netgear AirCard 340U Device Management */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 2)},	/* Netgear AirCard 340U NMEA */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 3)},	/* Netgear AirCard 340U Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 0)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 2)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 3)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 0)},	/* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 2)},	/* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 3)},	/* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 0)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 2)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 3)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 0)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 2)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 3)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 0)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 2)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 3)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card Modem */
 
 	{ }				/* Terminating entry */
 };

index 197074a57754..e09f09ce44f8 100644
@@ -1587,11 +1587,13 @@ struct clk *tegra_clk_register_plle_tegra114(const char *name,
 	val_aux = pll_readl(pll_params->aux_reg, pll);
 
 	if (val & PLL_BASE_ENABLE) {
-		if (!(val_aux & PLLE_AUX_PLLRE_SEL))
+		if ((val_aux & PLLE_AUX_PLLRE_SEL) ||
+			(val_aux & PLLE_AUX_PLLP_SEL))
 			WARN(1, "pll_e enabled with unsupported parent %s\n",
-			  (val & PLLE_AUX_PLLP_SEL) ? "pllp_out0" : "pll_ref");
+			  (val_aux & PLLE_AUX_PLLP_SEL) ? "pllp_out0" :
+					"pll_re_vco");
 	} else {
-		val_aux |= PLLE_AUX_PLLRE_SEL;
+		val_aux &= ~(PLLE_AUX_PLLRE_SEL | PLLE_AUX_PLLP_SEL);
 		pll_writel(val, pll_params->aux_reg, pll);
 	}
 

index 9467da7dee49..406929d4ce2f 100644
@@ -673,6 +673,7 @@ static struct tegra_clk_pll_freq_table pll_e_freq_table[] = {
 	/* PLLE special case: use cpcon field to store cml divider value */
 	{336000000, 100000000, 100, 21, 16, 11},
 	{312000000, 100000000, 200, 26, 24, 13},
+	{12000000, 100000000, 200,  1,  24, 13},
 	{0, 0, 0, 0, 0, 0},
 };
 

@@ -1501,7 +1502,7 @@ static void __init tegra114_pll_init(void __iomem *clk_base,
 	clks[pll_re_out] = clk;
 
 	/* PLLE */
-	clk = tegra_clk_register_plle_tegra114("pll_e_out0", "pll_re_vco",
+	clk = tegra_clk_register_plle_tegra114("pll_e_out0", "pll_ref",
 				      clk_base, 0, 100000000, &pll_e_params,
 				      pll_e_freq_table, NULL);
 	clk_register_clkdev(clk, "pll_e_out0", NULL);

index 5708e44376fe..d2e069044a0f 100644
@@ -836,7 +836,7 @@ acpi_video_init_brightness(struct acpi_video_device *device)
 		 * or an index). Set the backlight to max_level in this case.
 		 */
 		for (i = 2; i < br->count; i++)
-			if (level_old == br->levels[i])
+			if (level == br->levels[i])
 				break;
 		if (i == br->count || !level)
 			level = max_level;

index d8347b7a064f..470729dfe192 100644
@@ -596,7 +596,8 @@ void exit_pi_state_list(struct task_struct *curr)
 
 static int
 lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
-		union futex_key *key, struct futex_pi_state **ps)
+		union futex_key *key, struct futex_pi_state **ps,
+		struct task_struct *task)
 {
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_q *this, *next;

@@ -640,6 +641,16 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 					return -EINVAL;
 			}
 
+			/*
+			 * Protect against a corrupted uval. If uval
+			 * is 0x80000000 then pid is 0 and the waiter
+			 * bit is set. So the deadlock check in the
+			 * calling code has failed and we did not fall
+			 * into the check above due to !pid.
+			 */
+			if (task && pi_state->owner == task)
+				return -EDEADLK;
+
 			atomic_inc(&pi_state->refcount);
 			*ps = pi_state;
 

@@ -789,7 +800,7 @@ retry:
 	 * We dont have the lock. Look up the PI state (or create it if
 	 * we are the first waiter):
 	 */
-	ret = lookup_pi_state(uval, hb, key, ps);
+	ret = lookup_pi_state(uval, hb, key, ps, task);
 
 	if (unlikely(ret)) {
 		switch (ret) {

@@ -1199,7 +1210,7 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
  *
  * Return:
  *  0 - failed to acquire the lock atomically;
- *  1 - acquired the lock;
+ * >0 - acquired the lock, return value is vpid of the top_waiter
  * <0 - error
  */
 static int futex_proxy_trylock_atomic(u32 __user *pifutex,

@@ -1210,7 +1221,7 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
 {
 	struct futex_q *top_waiter = NULL;
 	u32 curval;
-	int ret;
+	int ret, vpid;
 
 	if (get_futex_value_locked(&curval, pifutex))
 		return -EFAULT;

@@ -1238,11 +1249,13 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
 	 * the contended case or if set_waiters is 1.  The pi_state is returned
 	 * in ps in contended cases.
 	 */
+	vpid = task_pid_vnr(top_waiter->task);
 	ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
 				   set_waiters);
-	if (ret == 1)
+	if (ret == 1) {
 		requeue_pi_wake_futex(top_waiter, key2, hb2);
-
+		return vpid;
+	}
 	return ret;
 }
 

@@ -1274,7 +1287,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	struct futex_hash_bucket *hb1, *hb2;
 	struct plist_head *head1;
 	struct futex_q *this, *next;
-	u32 curval2;
 
 	if (requeue_pi) {
 		/*

@@ -1360,16 +1372,25 @@ retry_private:
 		 * At this point the top_waiter has either taken uaddr2 or is
 		 * waiting on it.  If the former, then the pi_state will not
 		 * exist yet, look it up one more time to ensure we have a
-		 * reference to it.
+		 * reference to it. If the lock was taken, ret contains the
+		 * vpid of the top waiter task.
 		 */
-		if (ret == 1) {
+		if (ret > 0) {
 			WARN_ON(pi_state);
 			drop_count++;
 			task_count++;
-			ret = get_futex_value_locked(&curval2, uaddr2);
-			if (!ret)
-				ret = lookup_pi_state(curval2, hb2, &key2,
-						      &pi_state);
+			/*
+			 * If we acquired the lock, then the user
+			 * space value of uaddr2 should be vpid. It
+			 * cannot be changed by the top waiter as it
+			 * is blocked on hb2 lock if it tries to do
+			 * so. If something fiddled with it behind our
+			 * back the pi state lookup might unearth
+			 * it. So we rather use the known value than
+			 * rereading and handing potential crap to
+			 * lookup_pi_state.
+			 */
+			ret = lookup_pi_state(ret, hb2, &key2, &pi_state, NULL);
 		}
 
 		switch (ret) {

index 470729dfe192..6c7975b3f291 100644
@@ -668,6 +668,11 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	if (!p)
 		return -ESRCH;
 
+	if (!p->mm) {
+		put_task_struct(p);
+		return -EPERM;
+	}
+
 	/*
 	 * We need to look at the task state flags to figure out,
 	 * whether the task is exiting. To protect against the do_exit

index 9f15c0064c50..e68db4d534cb 100644
@@ -524,6 +524,7 @@ static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_a
 extern int ftrace_arch_read_dyn_info(char *buf, int size);
 
 extern int skip_trace(unsigned long ip);
+extern void ftrace_module_init(struct module *mod);
 
 extern void ftrace_disable_daemon(void);
 extern void ftrace_enable_daemon(void);

@@ -533,6 +534,7 @@ static inline int ftrace_force_update(void) { return 0; }
 static inline void ftrace_disable_daemon(void) { }
 static inline void ftrace_enable_daemon(void) { }
 static inline void ftrace_release_mod(struct module *mod) {}
+static inline void ftrace_module_init(struct module *mod) {}
 static inline int register_ftrace_command(struct ftrace_func_command *cmd)
 {
 	return -EINVAL;

index dc582749fa13..7b15ff67c5aa 100644
@@ -3296,6 +3296,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
 
 	dynamic_debug_setup(info->debug, info->num_debug);
 
+	/* Ftrace init must be called in the MODULE_STATE_UNFORMED state */
+	ftrace_module_init(mod);
+
 	/* Finally it's fully formed, ready to start executing. */
 	err = complete_formation(mod, info);
 	if (err)

index e66411fb55b3..a8642bac843e 100644
@@ -4252,16 +4252,11 @@ static void ftrace_init_module(struct module *mod,
 	ftrace_process_locs(mod, start, end);
 }
 
-static int ftrace_module_notify_enter(struct notifier_block *self,
-				      unsigned long val, void *data)
+void ftrace_module_init(struct module *mod)
 {
-	struct module *mod = data;
-
-	if (val == MODULE_STATE_COMING)
-		ftrace_init_module(mod, mod->ftrace_callsites,
-				   mod->ftrace_callsites +
-				   mod->num_ftrace_callsites);
-	return 0;
+	ftrace_init_module(mod, mod->ftrace_callsites,
+			   mod->ftrace_callsites +
+			   mod->num_ftrace_callsites);
 }
 
 static int ftrace_module_notify_exit(struct notifier_block *self,

@@ -4275,11 +4270,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self,
 	return 0;
 }
 #else
-static int ftrace_module_notify_enter(struct notifier_block *self,
-				      unsigned long val, void *data)
-{
-	return 0;
-}
 static int ftrace_module_notify_exit(struct notifier_block *self,
 				     unsigned long val, void *data)
 {

@@ -4287,11 +4277,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self,
 }
 #endif /* CONFIG_MODULES */
 
-struct notifier_block ftrace_module_enter_nb = {
-	.notifier_call = ftrace_module_notify_enter,
-	.priority = INT_MAX,	/* Run before anything that can use kprobes */
-};
-
 struct notifier_block ftrace_module_exit_nb = {
 	.notifier_call = ftrace_module_notify_exit,
 	.priority = INT_MIN,	/* Run after anything that can remove kprobes */

@@ -4328,10 +4313,6 @@ void __init ftrace_init(void)
 				  __start_mcount_loc,
 				  __stop_mcount_loc);
 
-	ret = register_module_notifier(&ftrace_module_enter_nb);
-	if (ret)
-		pr_warning("Failed to register trace ftrace module enter notifier\n");
-
 	ret = register_module_notifier(&ftrace_module_exit_nb);
 	if (ret)
 		pr_warning("Failed to register trace ftrace module exit notifier\n");

index d0e948084eaf..86df97f6fd27 100644
@@ -246,10 +246,14 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
 	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + (gic_irq(d) & ~3);
-	unsigned int shift = (gic_irq(d) % 4) * 8;
-	unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
+	unsigned int cpu, shift = (gic_irq(d) % 4) * 8;
 	u32 val, mask, bit;
 
+	if (!force)
+		cpu = cpumask_any_and(mask_val, cpu_online_mask);
+	else
+		cpu = cpumask_first(mask_val);
+
 	if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
 		return -EINVAL;
 

index 25fbfae06c1f..ab7dc01ad8c3 100644
@@ -635,7 +635,7 @@ static void octeon_irq_cpu_offline_ciu(struct irq_data *data)
 		cpumask_clear(&new_affinity);
 		cpumask_set_cpu(cpumask_first(cpu_online_mask), &new_affinity);
 	}
-	__irq_set_affinity_locked(data, &new_affinity);
+	irq_set_affinity_locked(data, &new_affinity, false);
 }
 
 static int octeon_irq_ciu_set_affinity(struct irq_data *data,

index 5e865b554940..e7777c940972 100644
@@ -198,7 +198,40 @@ static inline int check_wakeup_irqs(void) { return 0; }
 
 extern cpumask_var_t irq_default_affinity;
 
-extern int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask);
+/* Internal implementation. Use the helpers below */
+extern int __irq_set_affinity(unsigned int irq, const struct cpumask *cpumask,
+			      bool force);
+
+/**
+ * irq_set_affinity - Set the irq affinity of a given irq
+ * @irq:	Interrupt to set affinity
+ * @mask:	cpumask
+ *
+ * Fails if cpumask does not contain an online CPU
+ */
+static inline int
+irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
+{
+	return __irq_set_affinity(irq, cpumask, false);
+}
+
+/**
+ * irq_force_affinity - Force the irq affinity of a given irq
+ * @irq:	Interrupt to set affinity
+ * @mask:	cpumask
+ *
+ * Same as irq_set_affinity, but without checking the mask against
+ * online cpus.
+ *
+ * Solely for low level cpu hotplug code, where we need to make per
+ * cpu interrupts affine before the cpu becomes online.
+ */
+static inline int
+irq_force_affinity(unsigned int irq, const struct cpumask *cpumask)
+{
+	return __irq_set_affinity(irq, cpumask, true);
+}
+
 extern int irq_can_set_affinity(unsigned int irq);
 extern int irq_select_affinity(unsigned int irq);
 

index 56bb0dc8b7d4..896824eeacf1 100644
@@ -380,7 +380,8 @@ extern void remove_percpu_irq(unsigned int irq, struct irqaction *act);
 
 extern void irq_cpu_online(void);
 extern void irq_cpu_offline(void);
-extern int __irq_set_affinity_locked(struct irq_data *data,  const struct cpumask *cpumask);
+extern int irq_set_affinity_locked(struct irq_data *data,
+				   const struct cpumask *cpumask, bool force);
 
 #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
 void irq_move_irq(struct irq_data *data);

index 4c84746a840b..9e31fa71908d 100644
@@ -150,7 +150,7 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 	int ret;
 
-	ret = chip->irq_set_affinity(data, mask, false);
+	ret = chip->irq_set_affinity(data, mask, force);
 	switch (ret) {
 	case IRQ_SET_MASK_OK:
 		cpumask_copy(data->affinity, mask);

@@ -162,7 +162,8 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	return ret;
 }
 
-int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
+int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
+			    bool force)
 {
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 	struct irq_desc *desc = irq_data_to_desc(data);

@@ -172,7 +173,7 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
 		return -EINVAL;
 
 	if (irq_can_move_pcntxt(data)) {
-		ret = irq_do_set_affinity(data, mask, false);
+		ret = irq_do_set_affinity(data, mask, force);
 	} else {
 		irqd_set_move_pending(data);
 		irq_copy_pending(desc, mask);

@@ -187,13 +188,7 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
 	return ret;
 }
 
-/**
- *	irq_set_affinity - Set the irq affinity of a given irq
- *	@irq:		Interrupt to set affinity
- *	@mask:		cpumask
- *
- */
-int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
+int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;

@@ -203,7 +198,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
 		return -EINVAL;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	ret =  __irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask);
+	ret = irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask, force);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	return ret;
 }

index 62b0de6a1837..b17b3e0981f0 100644
@@ -428,6 +428,7 @@ static int exynos4_local_timer_setup(struct clock_event_device *evt)
 				evt->irq);
 			return -EIO;
 		}
+		irq_force_affinity(mct_irqs[MCT_L0_IRQ + cpu], cpumask_of(cpu));
 	} else {
 		enable_percpu_irq(mct_irqs[MCT_L0_IRQ], 0);
 	}

@@ -448,7 +449,6 @@ static int exynos4_mct_cpu_notify(struct notifier_block *self,
 					   unsigned long action, void *hcpu)
 {
 	struct mct_clock_event_device *mevt;
-	unsigned int cpu;
 
 	/*
 	 * Grab cpu pointer in each case to avoid spurious

@@ -459,12 +459,6 @@ static int exynos4_mct_cpu_notify(struct notifier_block *self,
 		mevt = this_cpu_ptr(&percpu_mct_tick);
 		exynos4_local_timer_setup(&mevt->evt);
 		break;
-	case CPU_ONLINE:
-		cpu = (unsigned long)hcpu;
-		if (mct_int_type == MCT_INT_SPI)
-			irq_set_affinity(mct_irqs[MCT_L0_IRQ + cpu],
-						cpumask_of(cpu));
-		break;
 	case CPU_DYING:
 		mevt = this_cpu_ptr(&percpu_mct_tick);
 		exynos4_local_timer_stop(&mevt->evt);

index b17b3e0981f0..70f3a597ec57 100644
@@ -414,8 +414,6 @@ static int exynos4_local_timer_setup(struct clock_event_device *evt)
 	evt->set_mode = exynos4_tick_set_mode;
 	evt->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
 	evt->rating = 450;
-	clockevents_config_and_register(evt, clk_rate / (TICK_BASE_CNT + 1),
-					0xf, 0x7fffffff);
 
 	exynos4_mct_write(TICK_BASE_CNT, mevt->base + MCT_L_TCNTB_OFFSET);
 

@@ -432,6 +430,8 @@ static int exynos4_local_timer_setup(struct clock_event_device *evt)
 	} else {
 		enable_percpu_irq(mct_irqs[MCT_L0_IRQ], 0);
 	}
+	clockevents_config_and_register(evt, clk_rate / (TICK_BASE_CNT + 1),
+					0xf, 0x7fffffff);
 
 	return 0;
 }

index d63ee8f41a4f..e3a49df958a3 100644
@@ -408,12 +408,13 @@ static int pata_at91_probe(struct platform_device *pdev)
 
 	host->private_data = info;
 
-	return ata_host_activate(host, gpio_is_valid(irq) ? gpio_to_irq(irq) : 0,
-			gpio_is_valid(irq) ? ata_sff_interrupt : NULL,
-			irq_flags, &pata_at91_sht);
+	ret = ata_host_activate(host, gpio_is_valid(irq) ? gpio_to_irq(irq) : 0,
+				gpio_is_valid(irq) ? ata_sff_interrupt : NULL,
+				irq_flags, &pata_at91_sht);
+	if (ret)
+		goto err_put;
 
-	if (!ret)
-		return 0;
+	return 0;
 
 err_put:
 	clk_put(info->mck);

index 9bdeca12ae0e..02db009d1531 100644
@@ -74,10 +74,15 @@ static int expand_corename(struct core_name *cn, int size)
 static int cn_vprintf(struct core_name *cn, const char *fmt, va_list arg)
 {
 	int free, need;
+	va_list arg_copy;
 
 again:
 	free = cn->size - cn->used;
-	need = vsnprintf(cn->corename + cn->used, free, fmt, arg);
+
+	va_copy(arg_copy, arg);
+	need = vsnprintf(cn->corename + cn->used, free, fmt, arg_copy);
+	va_end(arg_copy);
+
 	if (need < free) {
 		cn->used += need;
 		return 0;

index 22e67a2c955b..99fe3aa1035c 100644
@@ -1929,12 +1929,17 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 		     unsigned long address, unsigned int fault_flags)
 {
 	struct vm_area_struct *vma;
+	vm_flags_t vm_flags;
 	int ret;
 
 	vma = find_extend_vma(mm, address);
 	if (!vma || address < vma->vm_start)
 		return -EFAULT;
 
+	vm_flags = (fault_flags & FAULT_FLAG_WRITE) ? VM_WRITE : VM_READ;
+	if (!(vm_flags & vma->vm_flags))
+		return -EFAULT;
+
 	ret = handle_mm_fault(mm, vma, address, fault_flags);
 	if (ret & VM_FAULT_ERROR) {
 		if (ret & VM_FAULT_OOM)

index 7046769608d4..ab9096dc3849 100644
@@ -20,12 +20,15 @@ static void __dma_tx_complete(void *param)
 	struct uart_8250_port	*p = param;
 	struct uart_8250_dma	*dma = p->dma;
 	struct circ_buf		*xmit = &p->port.state->xmit;
-
-	dma->tx_running = 0;
+	unsigned long	flags;
 
 	dma_sync_single_for_cpu(dma->txchan->device->dev, dma->tx_addr,
 				UART_XMIT_SIZE, DMA_TO_DEVICE);
 
+	spin_lock_irqsave(&p->port.lock, flags);
+
+	dma->tx_running = 0;
+
 	xmit->tail += dma->tx_size;
 	xmit->tail &= UART_XMIT_SIZE - 1;
 	p->port.icount.tx += dma->tx_size;

@@ -35,6 +38,8 @@ static void __dma_tx_complete(void *param)
 
 	if (!uart_circ_empty(xmit) && !uart_tx_stopped(&p->port))
 		serial8250_tx_dma(p);
+
+	spin_unlock_irqrestore(&p->port.lock, flags);
 }
 
 static void __dma_rx_complete(void *param)

index aa6db8f4ee18..bf9d2ac9c9ed 100644
@@ -1520,7 +1520,7 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir)
 			status = serial8250_rx_chars(up, status);
 	}
 	serial8250_modem_status(up);
-	if (status & UART_LSR_THRE)
+	if (!up->dma && (status & UART_LSR_THRE))
 		serial8250_tx_chars(up);
 
 	spin_unlock_irqrestore(&port->lock, flags);

index b592eef1efcb..b083509325e4 100644
@@ -48,7 +48,7 @@ static irqreturn_t syncpt_thresh_isr(int irq, void *dev_id)
 	unsigned long reg;
 	int i, id;
 
-	for (i = 0; i <= BIT_WORD(host->info->nb_pts); i++) {
+	for (i = 0; i < DIV_ROUND_UP(host->info->nb_pts, 32); i++) {
 		reg = host1x_sync_readl(host,
 			HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(i));
 		for_each_set_bit(id, &reg, BITS_PER_LONG) {

@@ -65,7 +65,7 @@ static void _host1x_intr_disable_all_syncpt_intrs(struct host1x *host)
 {
 	u32 i;
 
-	for (i = 0; i <= BIT_WORD(host->info->nb_pts); ++i) {
+	for (i = 0; i < DIV_ROUND_UP(host->info->nb_pts, 32); ++i) {
 		host1x_sync_writel(host, 0xffffffffu,
 			HOST1X_SYNC_SYNCPT_THRESH_INT_DISABLE(i));
 		host1x_sync_writel(host, 0xffffffffu,

index 4296d13db3d1..4addfa27f67d 100644
@@ -822,7 +822,7 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
 
 	bit = find_last_bit(&mask, BITS_PER_LONG);
 
-	mask = (1 << bit) - 1;
+	mask = (1UL << bit) - 1;
 
 	expires_limit = expires_limit & ~(mask);
 

index e53fc24c6af3..e1ddcf938519 100644
@@ -251,8 +251,9 @@ static inline int check_obf(struct si_sm_data *kcs, unsigned char status,
 	if (!GET_STATUS_OBF(status)) {
 		kcs->obf_timeout -= time;
 		if (kcs->obf_timeout < 0) {
-		    start_error_recovery(kcs, "OBF not ready in time");
-		    return 1;
+			kcs->obf_timeout = OBF_RETRY_TIMEOUT;
+			start_error_recovery(kcs, "OBF not ready in time");
+			return 1;
 		}
 		return 0;
 	}

index 20e86a95dc4e..2f844eec9c6d 100644
@@ -242,7 +242,6 @@ void cfg80211_conn_work(struct work_struct *work)
 					NULL, 0, NULL, 0,
 					WLAN_STATUS_UNSPECIFIED_FAILURE,
 					false, NULL);
-			cfg80211_sme_free(wdev);
 		}
 		wdev_unlock(wdev);
 	}

@@ -646,6 +645,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 			cfg80211_unhold_bss(bss_from_pub(bss));
 			cfg80211_put_bss(wdev->wiphy, bss);
 		}
+		cfg80211_sme_free(wdev);
 		return;
 	}
 

index e41c477c6d9f..cd8d55c99ceb 100644
@@ -3691,18 +3691,24 @@ void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata)
 
 	sdata_lock(sdata);
 
-	if (ifmgd->auth_data) {
+	if (ifmgd->auth_data || ifmgd->assoc_data) {
+		const u8 *bssid = ifmgd->auth_data ?
+				ifmgd->auth_data->bss->bssid :
+				ifmgd->assoc_data->bss->bssid;
+
 		/*
-		 * If we are trying to authenticate while suspending, cfg80211
-		 * won't know and won't actually abort those attempts, thus we
-		 * need to do that ourselves.
+		 * If we are trying to authenticate / associate while suspending,
+		 * cfg80211 won't know and won't actually abort those attempts,
+		 * thus we need to do that ourselves.
 		 */
-		ieee80211_send_deauth_disassoc(sdata,
-					       ifmgd->auth_data->bss->bssid,
+		ieee80211_send_deauth_disassoc(sdata, bssid,
 					       IEEE80211_STYPE_DEAUTH,
 					       WLAN_REASON_DEAUTH_LEAVING,
 					       false, frame_buf);
-		ieee80211_destroy_auth_data(sdata, false);
+		if (ifmgd->assoc_data)
+			ieee80211_destroy_assoc_data(sdata, false);
+		if (ifmgd->auth_data)
+			ieee80211_destroy_auth_data(sdata, false);
 		cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
 				      IEEE80211_DEAUTH_FRAME_LEN);
 	}

index 0843feb66f3d..05f1180e9f21 100644
@@ -194,10 +194,17 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 			break;
 		if (pmd_trans_huge(*old_pmd)) {
 			int err = 0;
-			if (extent == HPAGE_PMD_SIZE)
+			if (extent == HPAGE_PMD_SIZE) {
+				VM_BUG_ON(vma->vm_file || !vma->anon_vma);
+				/* See comment in move_ptes() */
+				if (need_rmap_locks)
+					anon_vma_lock_write(vma->anon_vma);
 				err = move_huge_pmd(vma, new_vma, old_addr,
 						    new_addr, old_end,
 						    old_pmd, new_pmd);
+				if (need_rmap_locks)
+					anon_vma_unlock_write(vma->anon_vma);
+			}
 			if (err > 0) {
 				need_flush = true;
 				continue;

index a8091216963b..68c05398bba9 100644
@@ -52,6 +52,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
+	ptep_clear_flush(vma, addr, ptep);
 }
 
 static inline int huge_pte_none(pte_t pte)

index 5e9aec358306..31eb959e9aa8 100644
@@ -51,7 +51,11 @@ int pmd_huge(pmd_t pmd)
 
 int pud_huge(pud_t pud)
 {
+#ifndef __PAGETABLE_PMD_FOLDED
 	return !(pud_val(pud) & PUD_TABLE_BIT);
+#else
+	return 0;
+#endif
 }
 
 int pmd_huge_support(void)

index 5ea3cf734138..9f1b0ff6cb65 100644
@@ -1085,15 +1085,16 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 			return 0;
 		} else if (PageHuge(hpage)) {
 			/*
-			 * Check "just unpoisoned", "filter hit", and
-			 * "race with other subpage."
+			 * Check "filter hit" and "race with other subpage."
 			 */
 			lock_page(hpage);
-			if (!PageHWPoison(hpage)
-			    || (hwpoison_filter(p) && TestClearPageHWPoison(p))
-			    || (p != hpage && TestSetPageHWPoison(hpage))) {
-				atomic_long_sub(nr_pages, &num_poisoned_pages);
-				return 0;
+			if (PageHWPoison(hpage)) {
+				if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
+				    || (p != hpage && TestSetPageHWPoison(hpage))) {
+					atomic_long_sub(nr_pages, &num_poisoned_pages);
+					unlock_page(hpage);
+					return 0;
+				}
 			}
 			set_page_hwpoison_huge_page(hpage);
 			res = dequeue_hwpoisoned_huge_page(hpage);

index 12a3de0ee6da..04cd7686555d 100644
@@ -1299,10 +1299,8 @@ rw_common:
 						&iovec, compat)
 			: aio_setup_single_vector(req, rw, buf, &nr_segs,
 						  iovec);
-		if (ret)
-			return ret;
-
-		ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes);
+		if (!ret)
+			ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes);
 		if (ret < 0) {
 			if (iovec != &inline_vec)
 				kfree(iovec);

index 142e1cb8dea7..62fba71ef3c5 100644
@@ -162,7 +162,7 @@ static ssize_t store_hyst(struct device *dev,
 	if (retval < 0)
 		goto fail;
 
-	hyst = val - retval * 1000;
+	hyst = retval * 1000 - val;
 	hyst = DIV_ROUND_CLOSEST(hyst, 1000);
 	if (hyst < 0 || hyst > 255) {
 		retval = -ERANGE;

index 62fba71ef3c5..361f50b221bd 100644
@@ -295,7 +295,7 @@ static int emc1403_detect(struct i2c_client *client,
 	}
 
 	id = i2c_smbus_read_byte_data(client, THERMAL_REVISION_REG);
-	if (id != 0x01)
+	if (id < 0x01 || id > 0x04)
 		return -ENODEV;
 
 	return 0;

index 06051767393f..8a8d611f2021 100644
@@ -52,6 +52,7 @@ static DEFINE_MUTEX(deferred_probe_mutex);
 static LIST_HEAD(deferred_probe_pending_list);
 static LIST_HEAD(deferred_probe_active_list);
 static struct workqueue_struct *deferred_wq;
+static atomic_t deferred_trigger_count = ATOMIC_INIT(0);
 
 /**
  * deferred_probe_work_func() - Retry probing devices in the active list.

@@ -135,6 +136,17 @@ static bool driver_deferred_probe_enable = false;
  * This functions moves all devices from the pending list to the active
  * list and schedules the deferred probe workqueue to process them.  It
  * should be called anytime a driver is successfully bound to a device.
+ *
+ * Note, there is a race condition in multi-threaded probe. In the case where
+ * more than one device is probing at the same time, it is possible for one
+ * probe to complete successfully while another is about to defer. If the second
+ * depends on the first, then it will get put on the pending list after the
+ * trigger event has already occured and will be stuck there.
+ *
+ * The atomic 'deferred_trigger_count' is used to determine if a successful
+ * trigger has occurred in the midst of probing a driver. If the trigger count
+ * changes in the midst of a probe, then deferred processing should be triggered
+ * again.
  */
 static void driver_deferred_probe_trigger(void)
 {

@@ -147,6 +159,7 @@ static void driver_deferred_probe_trigger(void)
 	 * into the active list so they can be retried by the workqueue
 	 */
 	mutex_lock(&deferred_probe_mutex);
+	atomic_inc(&deferred_trigger_count);
 	list_splice_tail_init(&deferred_probe_pending_list,
 			      &deferred_probe_active_list);
 	mutex_unlock(&deferred_probe_mutex);

@@ -265,6 +278,7 @@ static DECLARE_WAIT_QUEUE_HEAD(probe_waitqueue);
 static int really_probe(struct device *dev, struct device_driver *drv)
 {
 	int ret = 0;
+	int local_trigger_count = atomic_read(&deferred_trigger_count);
 
 	atomic_inc(&probe_count);
 	pr_debug("bus: '%s': %s: probing driver %s with device %s\n",

@@ -310,6 +324,9 @@ probe_failed:
 		/* Driver requested deferred probing */
 		dev_info(dev, "Driver %s requests probe deferral\n", drv->name);
 		driver_deferred_probe_add(dev);
+		/* Did a trigger occur while probing? Need to re-trigger if yes */
+		if (local_trigger_count != atomic_read(&deferred_trigger_count))
+			driver_deferred_probe_trigger();
 	} else if (ret != -ENODEV && ret != -ENXIO) {
 		/* driver matched but the probe failed */
 		printk(KERN_WARNING

index 383319bae3f7..0d6df7b8cf46 100644
@@ -581,6 +581,23 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 
 	cpu_base->expires_next.tv64 = expires_next.tv64;
 
+	/*
+	 * If a hang was detected in the last timer interrupt then we
+	 * leave the hang delay active in the hardware. We want the
+	 * system to make progress. That also prevents the following
+	 * scenario:
+	 * T1 expires 50ms from now
+	 * T2 expires 5s from now
+	 *
+	 * T1 is removed, so this code is called and would reprogram
+	 * the hardware to 5s from now. Any hrtimer_start after that
+	 * will not reprogram the hardware due to hang_detected being
+	 * set. So we'd effectivly block all timers until the T2 event
+	 * fires.
+	 */
+	if (cpu_base->hang_detected)
+		return;
+
 	if (cpu_base->expires_next.tv64 != KTIME_MAX)
 		tick_program_event(cpu_base->expires_next, 1);
 }

index 0d6df7b8cf46..6de65d8a70e2 100644
@@ -246,6 +246,11 @@ again:
 			goto again;
 		}
 		timer->base = new_base;
+	} else {
+		if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
+			cpu = this_cpu;
+			goto again;
+		}
 	}
 	return new_base;
 }

index 6de65d8a70e2..aa149222cd8e 100644
@@ -1002,11 +1002,8 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	/* Remove an active timer from the queue: */
 	ret = remove_hrtimer(timer, base);
 
-	/* Switch the timer base, if necessary: */
-	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
-
 	if (mode & HRTIMER_MODE_REL) {
-		tim = ktime_add_safe(tim, new_base->get_time());
+		tim = ktime_add_safe(tim, base->get_time());
 		/*
 		 * CONFIG_TIME_LOW_RES is a temporary way for architectures
 		 * to signal that they simply return xtime in

@@ -1021,6 +1018,9 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 
 	hrtimer_set_expires_range_ns(timer, tim, delta_ns);
 
+	/* Switch the timer base, if necessary: */
+	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
+
 	timer_stats_hrtimer_set_start_info(timer);
 
 	leftmost = enqueue_hrtimer(timer, new_base);

index 015bc455cf1c..0ed6daf3b1e4 100644
@@ -8520,7 +8520,8 @@ static int md_notify_reboot(struct notifier_block *this,
 		if (mddev_trylock(mddev)) {
 			if (mddev->pers)
 				__md_stop_writes(mddev);
-			mddev->safemode = 2;
+			if (mddev->persistent)
+				mddev->safemode = 2;
 			mddev_unlock(mddev);
 		}
 		need_delay = 1;

index 5aa836e6e190..48a4faf5e63a 100644
@@ -8688,11 +8688,22 @@ intel_pipe_config_compare(struct drm_device *dev,
 	PIPE_CONF_CHECK_I(requested_mode.hdisplay);
 	PIPE_CONF_CHECK_I(requested_mode.vdisplay);
 
-	PIPE_CONF_CHECK_I(gmch_pfit.control);
-	/* pfit ratios are autocomputed by the hw on gen4+ */
-	if (INTEL_INFO(dev)->gen < 4)
-		PIPE_CONF_CHECK_I(gmch_pfit.pgm_ratios);
-	PIPE_CONF_CHECK_I(gmch_pfit.lvds_border_bits);
+	/*
+	 * FIXME: BIOS likes to set up a cloned config with lvds+external
+	 * screen. Since we don't yet re-compute the pipe config when moving
+	 * just the lvds port away to another pipe the sw tracking won't match.
+	 *
+	 * Proper atomic modesets with recomputed global state will fix this.
+	 * Until then just don't check gmch state for inherited modes.
+	 */
+	if (!PIPE_CONF_QUIRK(PIPE_CONFIG_QUIRK_INHERITED_MODE)) {
+		PIPE_CONF_CHECK_I(gmch_pfit.control);
+		/* pfit ratios are autocomputed by the hw on gen4+ */
+		if (INTEL_INFO(dev)->gen < 4)
+			PIPE_CONF_CHECK_I(gmch_pfit.pgm_ratios);
+		PIPE_CONF_CHECK_I(gmch_pfit.lvds_border_bits);
+	}
+
 	PIPE_CONF_CHECK_I(pch_pfit.enabled);
 	if (current_config->pch_pfit.enabled) {
 		PIPE_CONF_CHECK_I(pch_pfit.pos);

@@ -10443,6 +10454,8 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 			    base.head) {
 		memset(&crtc->config, 0, sizeof(crtc->config));
 
+		crtc->config.quirks |= PIPE_CONFIG_QUIRK_INHERITED_MODE;
+
 		crtc->active = dev_priv->display.get_pipe_config(crtc,
 								 &crtc->config);
 

index 7f2b384ac939..569c0c5ca450 100644
@@ -204,7 +204,8 @@ struct intel_crtc_config {
 	 * tracked with quirk flags so that fastboot and state checker can act
 	 * accordingly.
 	 */
-#define PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS (1<<0) /* unreliable sync mode.flags */
+#define PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS	(1<<0) /* unreliable sync mode.flags */
+#define PIPE_CONFIG_QUIRK_INHERITED_MODE	(1<<1) /* mode inherited from firmware */
 	unsigned long quirks;
 
 	struct drm_display_mode requested_mode;

index 48a4faf5e63a..c74bf330d290 100644
@@ -10239,15 +10239,6 @@ void intel_modeset_init(struct drm_device *dev)
 	intel_disable_fbc(dev);
 }
 
-static void
-intel_connector_break_all_links(struct intel_connector *connector)
-{
-	connector->base.dpms = DRM_MODE_DPMS_OFF;
-	connector->base.encoder = NULL;
-	connector->encoder->connectors_active = false;
-	connector->encoder->base.crtc = NULL;
-}
-
 static void intel_enable_pipe_a(struct drm_device *dev)
 {
 	struct intel_connector *connector;

@@ -10329,8 +10320,17 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc)
 			if (connector->encoder->base.crtc != &crtc->base)
 				continue;
 
-			intel_connector_break_all_links(connector);
+			connector->base.dpms = DRM_MODE_DPMS_OFF;
+			connector->base.encoder = NULL;
 		}
+		/* multiple connectors may have the same encoder:
+		 *  handle them and break crtc link separately */
+		list_for_each_entry(connector, &dev->mode_config.connector_list,
+				    base.head)
+			if (connector->encoder->base.crtc == &crtc->base) {
+				connector->encoder->base.crtc = NULL;
+				connector->encoder->connectors_active = false;
+			}
 
 		WARN_ON(crtc->active);
 		crtc->base.enabled = false;

@@ -10401,6 +10401,8 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 				      drm_get_encoder_name(&encoder->base));
 			encoder->disable(encoder);
 		}
+		encoder->base.crtc = NULL;
+		encoder->connectors_active = false;
 
 		/* Inconsistent output/port/pipe state happens presumably due to
 		 * a bug in one of the get_hw_state functions. Or someplace else

@@ -10411,8 +10413,8 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 				    base.head) {
 			if (connector->encoder != encoder)
 				continue;
-
-			intel_connector_break_all_links(connector);
+			connector->base.dpms = DRM_MODE_DPMS_OFF;
+			connector->base.encoder = NULL;
 		}
 	}
 	/* Enabled encoders without active connectors will be fixed in

index 51e947a97edf..79682ff51b63 100644
@@ -5098,6 +5098,10 @@ int ci_dpm_init(struct radeon_device *rdev)
 	pi->mclk_dpm_key_disabled = 0;
 	pi->pcie_dpm_key_disabled = 0;
 
+	/* mclk dpm is unstable on some R7 260X cards */
+	if (rdev->pdev->device == 0x6658)
+		pi->mclk_dpm_key_disabled = 1;
+
 	pi->caps_sclk_ds = true;
 
 	pi->mclk_strobe_mode_threshold = 40000;

index 33858364fe89..7e48c359b04c 100644
@@ -57,6 +57,9 @@
 #define BTC_MC_UCODE_SIZE            6024
 #define CAYMAN_MC_UCODE_SIZE         6037
 #define SI_MC_UCODE_SIZE             7769
+#define TAHITI_MC_UCODE_SIZE         7808
+#define PITCAIRN_MC_UCODE_SIZE       7775
+#define VERDE_MC_UCODE_SIZE          7875
 #define OLAND_MC_UCODE_SIZE          7863
 #define CIK_MC_UCODE_SIZE            7866
 

index 873e0a608948..de0c2bfcc7fc 100644
@@ -39,30 +39,35 @@ MODULE_FIRMWARE("radeon/TAHITI_pfp.bin");
 MODULE_FIRMWARE("radeon/TAHITI_me.bin");
 MODULE_FIRMWARE("radeon/TAHITI_ce.bin");
 MODULE_FIRMWARE("radeon/TAHITI_mc.bin");
+MODULE_FIRMWARE("radeon/TAHITI_mc2.bin");
 MODULE_FIRMWARE("radeon/TAHITI_rlc.bin");
 MODULE_FIRMWARE("radeon/TAHITI_smc.bin");
 MODULE_FIRMWARE("radeon/PITCAIRN_pfp.bin");
 MODULE_FIRMWARE("radeon/PITCAIRN_me.bin");
 MODULE_FIRMWARE("radeon/PITCAIRN_ce.bin");
 MODULE_FIRMWARE("radeon/PITCAIRN_mc.bin");
+MODULE_FIRMWARE("radeon/PITCAIRN_mc2.bin");
 MODULE_FIRMWARE("radeon/PITCAIRN_rlc.bin");
 MODULE_FIRMWARE("radeon/PITCAIRN_smc.bin");
 MODULE_FIRMWARE("radeon/VERDE_pfp.bin");
 MODULE_FIRMWARE("radeon/VERDE_me.bin");
 MODULE_FIRMWARE("radeon/VERDE_ce.bin");
 MODULE_FIRMWARE("radeon/VERDE_mc.bin");
+MODULE_FIRMWARE("radeon/VERDE_mc2.bin");
 MODULE_FIRMWARE("radeon/VERDE_rlc.bin");
 MODULE_FIRMWARE("radeon/VERDE_smc.bin");
 MODULE_FIRMWARE("radeon/OLAND_pfp.bin");
 MODULE_FIRMWARE("radeon/OLAND_me.bin");
 MODULE_FIRMWARE("radeon/OLAND_ce.bin");
 MODULE_FIRMWARE("radeon/OLAND_mc.bin");
+MODULE_FIRMWARE("radeon/OLAND_mc2.bin");
 MODULE_FIRMWARE("radeon/OLAND_rlc.bin");
 MODULE_FIRMWARE("radeon/OLAND_smc.bin");
 MODULE_FIRMWARE("radeon/HAINAN_pfp.bin");
 MODULE_FIRMWARE("radeon/HAINAN_me.bin");
 MODULE_FIRMWARE("radeon/HAINAN_ce.bin");
 MODULE_FIRMWARE("radeon/HAINAN_mc.bin");
+MODULE_FIRMWARE("radeon/HAINAN_mc2.bin");
 MODULE_FIRMWARE("radeon/HAINAN_rlc.bin");
 MODULE_FIRMWARE("radeon/HAINAN_smc.bin");
 

@@ -1470,7 +1475,7 @@ static int si_mc_load_microcode(struct radeon_device *rdev)
 	const __be32 *fw_data;
 	u32 running, blackout = 0;
 	u32 *io_mc_regs;
-	int i, ucode_size, regs_size;
+	int i, regs_size, ucode_size = rdev->mc_fw->size / 4;
 
 	if (!rdev->mc_fw)
 		return -EINVAL;

@@ -1478,28 +1483,23 @@ static int si_mc_load_microcode(struct radeon_device *rdev)
 	switch (rdev->family) {
 	case CHIP_TAHITI:
 		io_mc_regs = (u32 *)&tahiti_io_mc_regs;
-		ucode_size = SI_MC_UCODE_SIZE;
 		regs_size = TAHITI_IO_MC_REGS_SIZE;
 		break;
 	case CHIP_PITCAIRN:
 		io_mc_regs = (u32 *)&pitcairn_io_mc_regs;
-		ucode_size = SI_MC_UCODE_SIZE;
 		regs_size = TAHITI_IO_MC_REGS_SIZE;
 		break;
 	case CHIP_VERDE:
 	default:
 		io_mc_regs = (u32 *)&verde_io_mc_regs;
-		ucode_size = SI_MC_UCODE_SIZE;
 		regs_size = TAHITI_IO_MC_REGS_SIZE;
 		break;
 	case CHIP_OLAND:
 		io_mc_regs = (u32 *)&oland_io_mc_regs;
-		ucode_size = OLAND_MC_UCODE_SIZE;
 		regs_size = TAHITI_IO_MC_REGS_SIZE;
 		break;
 	case CHIP_HAINAN:
 		io_mc_regs = (u32 *)&hainan_io_mc_regs;
-		ucode_size = OLAND_MC_UCODE_SIZE;
 		regs_size = TAHITI_IO_MC_REGS_SIZE;
 		break;
 	}

@@ -1555,7 +1555,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 	const char *chip_name;
 	const char *rlc_chip_name;
 	size_t pfp_req_size, me_req_size, ce_req_size, rlc_req_size, mc_req_size;
-	size_t smc_req_size;
+	size_t smc_req_size, mc2_req_size;
 	char fw_name[30];
 	int err;
 

@@ -1570,6 +1570,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 		ce_req_size = SI_CE_UCODE_SIZE * 4;
 		rlc_req_size = SI_RLC_UCODE_SIZE * 4;
 		mc_req_size = SI_MC_UCODE_SIZE * 4;
+		mc2_req_size = TAHITI_MC_UCODE_SIZE * 4;
 		smc_req_size = ALIGN(TAHITI_SMC_UCODE_SIZE, 4);
 		break;
 	case CHIP_PITCAIRN:

@@ -1580,6 +1581,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 		ce_req_size = SI_CE_UCODE_SIZE * 4;
 		rlc_req_size = SI_RLC_UCODE_SIZE * 4;
 		mc_req_size = SI_MC_UCODE_SIZE * 4;
+		mc2_req_size = PITCAIRN_MC_UCODE_SIZE * 4;
 		smc_req_size = ALIGN(PITCAIRN_SMC_UCODE_SIZE, 4);
 		break;
 	case CHIP_VERDE:

@@ -1590,6 +1592,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 		ce_req_size = SI_CE_UCODE_SIZE * 4;
 		rlc_req_size = SI_RLC_UCODE_SIZE * 4;
 		mc_req_size = SI_MC_UCODE_SIZE * 4;
+		mc2_req_size = VERDE_MC_UCODE_SIZE * 4;
 		smc_req_size = ALIGN(VERDE_SMC_UCODE_SIZE, 4);
 		break;
 	case CHIP_OLAND:

@@ -1599,7 +1602,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 		me_req_size = SI_PM4_UCODE_SIZE * 4;
 		ce_req_size = SI_CE_UCODE_SIZE * 4;
 		rlc_req_size = SI_RLC_UCODE_SIZE * 4;
-		mc_req_size = OLAND_MC_UCODE_SIZE * 4;
+		mc_req_size = mc2_req_size = OLAND_MC_UCODE_SIZE * 4;
 		smc_req_size = ALIGN(OLAND_SMC_UCODE_SIZE, 4);
 		break;
 	case CHIP_HAINAN:

@@ -1609,7 +1612,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 		me_req_size = SI_PM4_UCODE_SIZE * 4;
 		ce_req_size = SI_CE_UCODE_SIZE * 4;
 		rlc_req_size = SI_RLC_UCODE_SIZE * 4;
-		mc_req_size = OLAND_MC_UCODE_SIZE * 4;
+		mc_req_size = mc2_req_size = OLAND_MC_UCODE_SIZE * 4;
 		smc_req_size = ALIGN(HAINAN_SMC_UCODE_SIZE, 4);
 		break;
 	default: BUG();

@@ -1662,16 +1665,22 @@ static int si_init_microcode(struct radeon_device *rdev)
 		err = -EINVAL;
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc2.bin", chip_name);
 	err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev);
-	if (err)
-		goto out;
-	if (rdev->mc_fw->size != mc_req_size) {
+	if (err) {
+		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
+		err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev);
+		if (err)
+			goto out;
+	}
+	if ((rdev->mc_fw->size != mc_req_size) &&
+	    (rdev->mc_fw->size != mc2_req_size)) {
 		printk(KERN_ERR
 		       "si_mc: Bogus length %zu in firmware \"%s\"\n",
 		       rdev->mc_fw->size, fw_name);
 		err = -EINVAL;
 	}
+	DRM_INFO("%s: %zu bytes\n", fw_name, rdev->mc_fw->size);
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name);
 	err = request_firmware(&rdev->smc_fw, fw_name, rdev->dev);

index de0c2bfcc7fc..bbd83f5aa75d 100644
@@ -1475,11 +1475,13 @@ static int si_mc_load_microcode(struct radeon_device *rdev)
 	const __be32 *fw_data;
 	u32 running, blackout = 0;
 	u32 *io_mc_regs;
-	int i, regs_size, ucode_size = rdev->mc_fw->size / 4;
+	int i, regs_size, ucode_size;
 
 	if (!rdev->mc_fw)
 		return -EINVAL;
 
+	ucode_size = rdev->mc_fw->size / 4;
+
 	switch (rdev->family) {
 	case CHIP_TAHITI:
 		io_mc_regs = (u32 *)&tahiti_io_mc_regs;

index b8db0d7b5089..7c6e3fd70e65 100644
@@ -525,6 +525,13 @@ static bool radeon_atpx_detect(void)
 		has_atpx |= (radeon_atpx_pci_probe_handle(pdev) == true);
 	}
 
+	/* some newer PX laptops mark the dGPU as a non-VGA display device */
+	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) {
+		vga_count++;
+
+		has_atpx |= (radeon_atpx_pci_probe_handle(pdev) == true);
+	}
+
 	if (has_atpx && vga_count == 2) {
 		acpi_get_name(radeon_atpx_priv.atpx.handle, ACPI_FULL_PATHNAME, &buffer);
 		printk(KERN_INFO "VGA switcheroo: detected switching method %s handle\n",

index 5513d8f06252..2df683aab9e9 100644
@@ -158,16 +158,18 @@ u32 r600_dpm_get_vblank_time(struct radeon_device *rdev)
 	u32 line_time_us, vblank_lines;
 	u32 vblank_time_us = 0xffffffff; /* if the displays are off, vblank time is max */
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-		radeon_crtc = to_radeon_crtc(crtc);
-		if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) {
-			line_time_us = (radeon_crtc->hw_mode.crtc_htotal * 1000) /
-				radeon_crtc->hw_mode.clock;
-			vblank_lines = radeon_crtc->hw_mode.crtc_vblank_end -
-				radeon_crtc->hw_mode.crtc_vdisplay +
-				(radeon_crtc->v_border * 2);
-			vblank_time_us = vblank_lines * line_time_us;
-			break;
+	if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) {
+		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+			radeon_crtc = to_radeon_crtc(crtc);
+			if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) {
+				line_time_us = (radeon_crtc->hw_mode.crtc_htotal * 1000) /
+					radeon_crtc->hw_mode.clock;
+				vblank_lines = radeon_crtc->hw_mode.crtc_vblank_end -
+					radeon_crtc->hw_mode.crtc_vdisplay +
+					(radeon_crtc->v_border * 2);
+				vblank_time_us = vblank_lines * line_time_us;
+				break;
+			}
 		}
 	}
 

@@ -181,14 +183,15 @@ u32 r600_dpm_get_vrefresh(struct radeon_device *rdev)
 	struct radeon_crtc *radeon_crtc;
 	u32 vrefresh = 0;
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-		radeon_crtc = to_radeon_crtc(crtc);
-		if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) {
-			vrefresh = radeon_crtc->hw_mode.vrefresh;
-			break;
+	if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) {
+		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+			radeon_crtc = to_radeon_crtc(crtc);
+			if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) {
+				vrefresh = radeon_crtc->hw_mode.vrefresh;
+				break;
+			}
 		}
 	}
-
 	return vrefresh;
 }
 

index a0ec4bb9d896..10fc97749a81 100644
@@ -1362,12 +1362,14 @@ static void radeon_pm_compute_clocks_old(struct radeon_device *rdev)
 
 	rdev->pm.active_crtcs = 0;
 	rdev->pm.active_crtc_count = 0;
-	list_for_each_entry(crtc,
-		&ddev->mode_config.crtc_list, head) {
-		radeon_crtc = to_radeon_crtc(crtc);
-		if (radeon_crtc->enabled) {
-			rdev->pm.active_crtcs |= (1 << radeon_crtc->crtc_id);
-			rdev->pm.active_crtc_count++;
+	if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) {
+		list_for_each_entry(crtc,
+				    &ddev->mode_config.crtc_list, head) {
+			radeon_crtc = to_radeon_crtc(crtc);
+			if (radeon_crtc->enabled) {
+				rdev->pm.active_crtcs |= (1 << radeon_crtc->crtc_id);
+				rdev->pm.active_crtc_count++;
+			}
 		}
 	}
 

@@ -1431,12 +1433,14 @@ static void radeon_pm_compute_clocks_dpm(struct radeon_device *rdev)
 	/* update active crtc counts */
 	rdev->pm.dpm.new_active_crtcs = 0;
 	rdev->pm.dpm.new_active_crtc_count = 0;
-	list_for_each_entry(crtc,
-		&ddev->mode_config.crtc_list, head) {
-		radeon_crtc = to_radeon_crtc(crtc);
-		if (crtc->enabled) {
-			rdev->pm.dpm.new_active_crtcs |= (1 << radeon_crtc->crtc_id);
-			rdev->pm.dpm.new_active_crtc_count++;
+	if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) {
+		list_for_each_entry(crtc,
+				    &ddev->mode_config.crtc_list, head) {
+			radeon_crtc = to_radeon_crtc(crtc);
+			if (crtc->enabled) {
+				rdev->pm.dpm.new_active_crtcs |= (1 << radeon_crtc->crtc_id);
+				rdev->pm.dpm.new_active_crtc_count++;
+			}
 		}
 	}
 

index d565f4076a23..0c6784f52410 100644
@@ -512,7 +512,7 @@ int cik_sdma_ring_test(struct radeon_device *rdev,
 	tmp = 0xCAFEDEAD;
 	writel(tmp, ptr);
 
-	r = radeon_ring_lock(rdev, ring, 4);
+	r = radeon_ring_lock(rdev, ring, 5);
 	if (r) {
 		DRM_ERROR("radeon: dma failed to lock ring %d (%d).\n", ring->idx, r);
 		return r;

index 7266805d9786..f680f5ffbdeb 100644
@@ -83,7 +83,10 @@ int uvd_v1_0_init(struct radeon_device *rdev)
 	int r;
 
 	/* raise clocks while booting up the VCPU */
-	radeon_set_uvd_clocks(rdev, 53300, 40000);
+	if (rdev->family < CHIP_RV740)
+		radeon_set_uvd_clocks(rdev, 10000, 10000);
+	else
+		radeon_set_uvd_clocks(rdev, 53300, 40000);
 
 	r = uvd_v1_0_start(rdev);
 	if (r)

@@ -405,7 +408,10 @@ int uvd_v1_0_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 	struct radeon_fence *fence = NULL;
 	int r;
 
-	r = radeon_set_uvd_clocks(rdev, 53300, 40000);
+	if (rdev->family < CHIP_RV740)
+		r = radeon_set_uvd_clocks(rdev, 10000, 10000);
+	else
+		r = radeon_set_uvd_clocks(rdev, 53300, 40000);
 	if (r) {
 		DRM_ERROR("radeon: failed to raise UVD clocks (%d).\n", r);
 		return r;

index bcefa1de3e97..bb7f2ae7683d 100644
@@ -5956,6 +5956,19 @@ static void cik_disable_interrupt_state(struct radeon_device *rdev)
 		WREG32(LB_INTERRUPT_MASK + EVERGREEN_CRTC4_REGISTER_OFFSET, 0);
 		WREG32(LB_INTERRUPT_MASK + EVERGREEN_CRTC5_REGISTER_OFFSET, 0);
 	}
+	/* pflip */
+	if (rdev->num_crtc >= 2) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, 0);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, 0);
+	}
+	if (rdev->num_crtc >= 4) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, 0);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, 0);
+	}
+	if (rdev->num_crtc >= 6) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, 0);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, 0);
+	}
 
 	/* dac hotplug */
 	WREG32(DAC_AUTODETECT_INT_CONTROL, 0);

@@ -6312,6 +6325,25 @@ int cik_irq_set(struct radeon_device *rdev)
 		WREG32(LB_INTERRUPT_MASK + EVERGREEN_CRTC5_REGISTER_OFFSET, crtc6);
 	}
 
+	if (rdev->num_crtc >= 2) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+	}
+	if (rdev->num_crtc >= 4) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+	}
+	if (rdev->num_crtc >= 6) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+	}
+
 	WREG32(DC_HPD1_INT_CONTROL, hpd1);
 	WREG32(DC_HPD2_INT_CONTROL, hpd2);
 	WREG32(DC_HPD3_INT_CONTROL, hpd3);

@@ -6348,6 +6380,29 @@ static inline void cik_irq_ack(struct radeon_device *rdev)
 	rdev->irq.stat_regs.cik.disp_int_cont5 = RREG32(DISP_INTERRUPT_STATUS_CONTINUE5);
 	rdev->irq.stat_regs.cik.disp_int_cont6 = RREG32(DISP_INTERRUPT_STATUS_CONTINUE6);
 
+	rdev->irq.stat_regs.cik.d1grph_int = RREG32(GRPH_INT_STATUS +
+		EVERGREEN_CRTC0_REGISTER_OFFSET);
+	rdev->irq.stat_regs.cik.d2grph_int = RREG32(GRPH_INT_STATUS +
+		EVERGREEN_CRTC1_REGISTER_OFFSET);
+	if (rdev->num_crtc >= 4) {
+		rdev->irq.stat_regs.cik.d3grph_int = RREG32(GRPH_INT_STATUS +
+			EVERGREEN_CRTC2_REGISTER_OFFSET);
+		rdev->irq.stat_regs.cik.d4grph_int = RREG32(GRPH_INT_STATUS +
+			EVERGREEN_CRTC3_REGISTER_OFFSET);
+	}
+	if (rdev->num_crtc >= 6) {
+		rdev->irq.stat_regs.cik.d5grph_int = RREG32(GRPH_INT_STATUS +
+			EVERGREEN_CRTC4_REGISTER_OFFSET);
+		rdev->irq.stat_regs.cik.d6grph_int = RREG32(GRPH_INT_STATUS +
+			EVERGREEN_CRTC5_REGISTER_OFFSET);
+	}
+
+	if (rdev->irq.stat_regs.cik.d1grph_int & GRPH_PFLIP_INT_OCCURRED)
+		WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC0_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_CLEAR);
+	if (rdev->irq.stat_regs.cik.d2grph_int & GRPH_PFLIP_INT_OCCURRED)
+		WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC1_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_CLEAR);
 	if (rdev->irq.stat_regs.cik.disp_int & LB_D1_VBLANK_INTERRUPT)
 		WREG32(LB_VBLANK_STATUS + EVERGREEN_CRTC0_REGISTER_OFFSET, VBLANK_ACK);
 	if (rdev->irq.stat_regs.cik.disp_int & LB_D1_VLINE_INTERRUPT)

@@ -6358,6 +6413,12 @@ static inline void cik_irq_ack(struct radeon_device *rdev)
 		WREG32(LB_VLINE_STATUS + EVERGREEN_CRTC1_REGISTER_OFFSET, VLINE_ACK);
 
 	if (rdev->num_crtc >= 4) {
+		if (rdev->irq.stat_regs.cik.d3grph_int & GRPH_PFLIP_INT_OCCURRED)
+			WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC2_REGISTER_OFFSET,
+			       GRPH_PFLIP_INT_CLEAR);
+		if (rdev->irq.stat_regs.cik.d4grph_int & GRPH_PFLIP_INT_OCCURRED)
+			WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC3_REGISTER_OFFSET,
+			       GRPH_PFLIP_INT_CLEAR);
 		if (rdev->irq.stat_regs.cik.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT)
 			WREG32(LB_VBLANK_STATUS + EVERGREEN_CRTC2_REGISTER_OFFSET, VBLANK_ACK);
 		if (rdev->irq.stat_regs.cik.disp_int_cont2 & LB_D3_VLINE_INTERRUPT)

@@ -6369,6 +6430,12 @@ static inline void cik_irq_ack(struct radeon_device *rdev)
 	}
 
 	if (rdev->num_crtc >= 6) {
+		if (rdev->irq.stat_regs.cik.d5grph_int & GRPH_PFLIP_INT_OCCURRED)
+			WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC4_REGISTER_OFFSET,
+			       GRPH_PFLIP_INT_CLEAR);
+		if (rdev->irq.stat_regs.cik.d6grph_int & GRPH_PFLIP_INT_OCCURRED)
+			WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC5_REGISTER_OFFSET,
+			       GRPH_PFLIP_INT_CLEAR);
 		if (rdev->irq.stat_regs.cik.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT)
 			WREG32(LB_VBLANK_STATUS + EVERGREEN_CRTC4_REGISTER_OFFSET, VBLANK_ACK);
 		if (rdev->irq.stat_regs.cik.disp_int_cont4 & LB_D5_VLINE_INTERRUPT)