Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	drivers/net/wireless/ath/ath9k/Kconfig
	drivers/net/xen-netback/netback.c
	net/batman-adv/bat_iv_ogm.c
	net/wireless/nl80211.c

The ath9k Kconfig conflict was a change of a Kconfig option name right
next to the deletion of another option.

The xen-netback conflict was overlapping changes involving the
handling of the notify list in xen_netbk_rx_action().

Batman conflict resolution provided by Antonio Quartulli, basically
keep everything in both conflict hunks.

The nl80211 conflict is a little more involved.  In 'net' we added a
dynamic memory allocation to nl80211_dump_wiphy() to fix a race that
Linus reported.  Meanwhile in 'net-next' the handlers were converted
to use pre and post doit handlers which use a flag to determine
whether to hold the RTNL mutex around the operation.

However, the dump handlers to not use this logic.  Instead they have
to explicitly do the locking.  There were apparent bugs in the
conversion of nl80211_dump_wiphy() in that we were not dropping the
RTNL mutex in all the return paths, and it seems we very much should
be doing so.  So I fixed that whilst handling the overlapping changes.

To simplify the initial returns, I take the RTNL mutex after we try
to allocate 'tb'.

Signed-off-by: David S. Miller <davem@davemloft.net>

17 files changed, 175 insertions, 107 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index 21c7fa6..91e53d0 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1056,7 +1056,7 @@ static inline void audit_get_stamp(struct audit_context *ctx,
 static void wait_for_auditd(unsigned long sleep_time)
 {
 	DECLARE_WAITQUEUE(wait, current);
-	set_current_state(TASK_INTERRUPTIBLE);
+	set_current_state(TASK_UNINTERRUPTIBLE);
 	add_wait_queue(&audit_backlog_wait, &wait);
 
 	if (audit_backlog_limit &&
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index a291aa2..43c307d 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -658,6 +658,7 @@ int audit_add_tree_rule(struct audit_krule *rule)
 	struct vfsmount *mnt;
 	int err;
 
+	rule->tree = NULL;
 	list_for_each_entry(tree, &tree_list, list) {
 		if (!strcmp(seed->pathname, tree->pathname)) {
 			put_tree(seed);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index b5e4ab2..198a388 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -133,6 +133,27 @@ static void cpu_hotplug_done(void)
 	mutex_unlock(&cpu_hotplug.lock);
 }
 
+/*
+ * Wait for currently running CPU hotplug operations to complete (if any) and
+ * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects
+ * the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the
+ * hotplug path before performing hotplug operations. So acquiring that lock
+ * guarantees mutual exclusion from any currently running hotplug operations.
+ */
+void cpu_hotplug_disable(void)
+{
+	cpu_maps_update_begin();
+	cpu_hotplug_disabled = 1;
+	cpu_maps_update_done();
+}
+
+void cpu_hotplug_enable(void)
+{
+	cpu_maps_update_begin();
+	cpu_hotplug_disabled = 0;
+	cpu_maps_update_done();
+}
+
 #else /* #if CONFIG_HOTPLUG_CPU */
 static void cpu_hotplug_begin(void) {}
 static void cpu_hotplug_done(void) {}
@@ -541,36 +562,6 @@ static int __init alloc_frozen_cpus(void)
 core_initcall(alloc_frozen_cpus);
 
 /*
- * Prevent regular CPU hotplug from racing with the freezer, by disabling CPU
- * hotplug when tasks are about to be frozen. Also, don't allow the freezer
- * to continue until any currently running CPU hotplug operation gets
- * completed.
- * To modify the 'cpu_hotplug_disabled' flag, we need to acquire the
- * 'cpu_add_remove_lock'. And this same lock is also taken by the regular
- * CPU hotplug path and released only after it is complete. Thus, we
- * (and hence the freezer) will block here until any currently running CPU
- * hotplug operation gets completed.
- */
-void cpu_hotplug_disable_before_freeze(void)
-{
-	cpu_maps_update_begin();
-	cpu_hotplug_disabled = 1;
-	cpu_maps_update_done();
-}
-
-
-/*
- * When tasks have been thawed, re-enable regular CPU hotplug (which had been
- * disabled while beginning to freeze tasks).
- */
-void cpu_hotplug_enable_after_thaw(void)
-{
-	cpu_maps_update_begin();
-	cpu_hotplug_disabled = 0;
-	cpu_maps_update_done();
-}
-
-/*
  * When callbacks for CPU hotplug notifications are being executed, we must
  * ensure that the state of the system with respect to the tasks being frozen
  * or not, as reported by the notification, remains unchanged *throughout the
@@ -589,12 +580,12 @@ cpu_hotplug_pm_callback(struct notifier_block *nb,
 
 	case PM_SUSPEND_PREPARE:
 	case PM_HIBERNATION_PREPARE:
-		cpu_hotplug_disable_before_freeze();
+		cpu_hotplug_disable();
 		break;
 
 	case PM_POST_SUSPEND:
 	case PM_POST_HIBERNATION:
-		cpu_hotplug_enable_after_thaw();
+		cpu_hotplug_enable();
 		break;
 
 	default:
diff --git a/kernel/exit.c b/kernel/exit.c
index af2eb3c..7bb73f9 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -649,7 +649,6 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
 	 *	jobs, send them a SIGHUP and then a SIGCONT.  (POSIX 3.2.2.2)
 	 */
 	forget_original_parent(tsk);
-	exit_task_namespaces(tsk);
 
 	write_lock_irq(&tasklist_lock);
 	if (group_dead)
@@ -795,6 +794,7 @@ void do_exit(long code)
 	exit_shm(tsk);
 	exit_files(tsk);
 	exit_fs(tsk);
+	exit_task_namespaces(tsk);
 	exit_task_work(tsk);
 	check_stack_usage();
 	exit_thread();
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 5a83dde..54a4d52 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -143,7 +143,10 @@ static unsigned int irq_domain_legacy_revmap(struct irq_domain *domain,
  * irq_domain_add_simple() - Allocate and register a simple irq_domain.
  * @of_node: pointer to interrupt controller's device tree node.
  * @size: total number of irqs in mapping
- * @first_irq: first number of irq block assigned to the domain
+ * @first_irq: first number of irq block assigned to the domain,
+ *	pass zero to assign irqs on-the-fly. This will result in a
+ *	linear IRQ domain so it is important to use irq_create_mapping()
+ *	for each used IRQ, especially when SPARSE_IRQ is enabled.
  * @ops: map/unmap domain callbacks
  * @host_data: Controller private data pointer
  *
@@ -191,6 +194,7 @@ struct irq_domain *irq_domain_add_simple(struct device_node *of_node,
 	/* A linear domain is the default */
 	return irq_domain_add_linear(of_node, size, ops, host_data);
 }
+EXPORT_SYMBOL_GPL(irq_domain_add_simple);
 
 /**
  * irq_domain_add_legacy() - Allocate and register a legacy revmap irq_domain.
@@ -397,11 +401,12 @@ static void irq_domain_disassociate_many(struct irq_domain *domain,
 	while (count--) {
 		int irq = irq_base + count;
 		struct irq_data *irq_data = irq_get_irq_data(irq);
-		irq_hw_number_t hwirq = irq_data->hwirq;
+		irq_hw_number_t hwirq;
 
 		if (WARN_ON(!irq_data || irq_data->domain != domain))
 			continue;
 
+		hwirq = irq_data->hwirq;
 		irq_set_status_flags(irq, IRQ_NOREQUEST);
 
 		/* remove chip and handler */
diff --git a/kernel/printk.c b/kernel/printk.c
index fa36e14..8212c1a 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -363,6 +363,53 @@ static void log_store(int facility, int level,
 	log_next_seq++;
 }
 
+#ifdef CONFIG_SECURITY_DMESG_RESTRICT
+int dmesg_restrict = 1;
+#else
+int dmesg_restrict;
+#endif
+
+static int syslog_action_restricted(int type)
+{
+	if (dmesg_restrict)
+		return 1;
+	/*
+	 * Unless restricted, we allow "read all" and "get buffer size"
+	 * for everybody.
+	 */
+	return type != SYSLOG_ACTION_READ_ALL &&
+	       type != SYSLOG_ACTION_SIZE_BUFFER;
+}
+
+static int check_syslog_permissions(int type, bool from_file)
+{
+	/*
+	 * If this is from /proc/kmsg and we've already opened it, then we've
+	 * already done the capabilities checks at open time.
+	 */
+	if (from_file && type != SYSLOG_ACTION_OPEN)
+		return 0;
+
+	if (syslog_action_restricted(type)) {
+		if (capable(CAP_SYSLOG))
+			return 0;
+		/*
+		 * For historical reasons, accept CAP_SYS_ADMIN too, with
+		 * a warning.
+		 */
+		if (capable(CAP_SYS_ADMIN)) {
+			pr_warn_once("%s (%d): Attempt to access syslog with "
+				     "CAP_SYS_ADMIN but no CAP_SYSLOG "
+				     "(deprecated).\n",
+				 current->comm, task_pid_nr(current));
+			return 0;
+		}
+		return -EPERM;
+	}
+	return security_syslog(type);
+}
+
+
 /* /dev/kmsg - userspace message inject/listen interface */
 struct devkmsg_user {
 	u64 seq;
@@ -620,7 +667,8 @@ static int devkmsg_open(struct inode *inode, struct file *file)
 	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
 		return 0;
 
-	err = security_syslog(SYSLOG_ACTION_READ_ALL);
+	err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL,
+				       SYSLOG_FROM_READER);
 	if (err)
 		return err;
 
@@ -813,45 +861,6 @@ static inline void boot_delay_msec(int level)
 }
 #endif
 
-#ifdef CONFIG_SECURITY_DMESG_RESTRICT
-int dmesg_restrict = 1;
-#else
-int dmesg_restrict;
-#endif
-
-static int syslog_action_restricted(int type)
-{
-	if (dmesg_restrict)
-		return 1;
-	/* Unless restricted, we allow "read all" and "get buffer size" for everybody */
-	return type != SYSLOG_ACTION_READ_ALL && type != SYSLOG_ACTION_SIZE_BUFFER;
-}
-
-static int check_syslog_permissions(int type, bool from_file)
-{
-	/*
-	 * If this is from /proc/kmsg and we've already opened it, then we've
-	 * already done the capabilities checks at open time.
-	 */
-	if (from_file && type != SYSLOG_ACTION_OPEN)
-		return 0;
-
-	if (syslog_action_restricted(type)) {
-		if (capable(CAP_SYSLOG))
-			return 0;
-		/* For historical reasons, accept CAP_SYS_ADMIN too, with a warning */
-		if (capable(CAP_SYS_ADMIN)) {
-			printk_once(KERN_WARNING "%s (%d): "
-				 "Attempt to access syslog with CAP_SYS_ADMIN "
-				 "but no CAP_SYSLOG (deprecated).\n",
-				 current->comm, task_pid_nr(current));
-			return 0;
-		}
-		return -EPERM;
-	}
-	return 0;
-}
-
 #if defined(CONFIG_PRINTK_TIME)
 static bool printk_time = 1;
 #else
@@ -1249,7 +1258,7 @@ out:
 
 SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len)
 {
-	return do_syslog(type, buf, len, SYSLOG_FROM_CALL);
+	return do_syslog(type, buf, len, SYSLOG_FROM_READER);
 }
 
 /*
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 16ea679..3538001 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1451,9 +1451,9 @@ static int rcu_gp_init(struct rcu_state *rsp)
 					    rnp->grphi, rnp->qsmask);
 		raw_spin_unlock_irq(&rnp->lock);
 #ifdef CONFIG_PROVE_RCU_DELAY
-		if ((prandom_u32() % (rcu_num_nodes * 8)) == 0 &&
+		if ((prandom_u32() % (rcu_num_nodes + 1)) == 0 &&
 		    system_state == SYSTEM_RUNNING)
-			schedule_timeout_uninterruptible(2);
+			udelay(200);
 #endif /* #ifdef CONFIG_PROVE_RCU_DELAY */
 		cond_resched();
 	}
@@ -1613,6 +1613,14 @@ static int __noreturn rcu_gp_kthread(void *arg)
 	}
 }
 
+static void rsp_wakeup(struct irq_work *work)
+{
+	struct rcu_state *rsp = container_of(work, struct rcu_state, wakeup_work);
+
+	/* Wake up rcu_gp_kthread() to start the grace period. */
+	wake_up(&rsp->gp_wq);
+}
+
 /*
  * Start a new RCU grace period if warranted, re-initializing the hierarchy
  * in preparation for detecting the next grace period.  The caller must hold
@@ -1637,8 +1645,12 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 	}
 	rsp->gp_flags = RCU_GP_FLAG_INIT;
 
-	/* Wake up rcu_gp_kthread() to start the grace period. */
-	wake_up(&rsp->gp_wq);
+	/*
+	 * We can't do wakeups while holding the rnp->lock, as that
+	 * could cause possible deadlocks with the rq->lock. Deter
+	 * the wakeup to interrupt context.
+	 */
+	irq_work_queue(&rsp->wakeup_work);
 }
 
 /*
@@ -3235,6 +3247,7 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 
 	rsp->rda = rda;
 	init_waitqueue_head(&rsp->gp_wq);
+	init_irq_work(&rsp->wakeup_work, rsp_wakeup);
 	rnp = rsp->level[rcu_num_lvls - 1];
 	for_each_possible_cpu(i) {
 		while (i > rnp->grphi)
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index da77a8f..4df5034 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -27,6 +27,7 @@
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/seqlock.h>
+#include <linux/irq_work.h>
 
 /*
  * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
@@ -442,6 +443,7 @@ struct rcu_state {
 	char *name;				/* Name of structure. */
 	char abbr;				/* Abbreviated name. */
 	struct list_head flavors;		/* List of RCU flavors. */
+	struct irq_work wakeup_work;		/* Postponed wakeups */
 };
 
 /* Values for rcu_state structure's gp_flags field. */
diff --git a/kernel/softirq.c b/kernel/softirq.c
index b5197dc..3d6833f 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -195,8 +195,12 @@ void local_bh_enable_ip(unsigned long ip)
 EXPORT_SYMBOL(local_bh_enable_ip);
 
 /*
- * We restart softirq processing for at most 2 ms,
- * and if need_resched() is not set.
+ * We restart softirq processing for at most MAX_SOFTIRQ_RESTART times,
+ * but break the loop if need_resched() is set or after 2 ms.
+ * The MAX_SOFTIRQ_TIME provides a nice upper bound in most cases, but in
+ * certain cases, such as stop_machine(), jiffies may cease to
+ * increment and so we need the MAX_SOFTIRQ_RESTART limit as
+ * well to make sure we eventually return from this method.
  *
  * These limits have been established via experimentation.
  * The two things to balance is latency against fairness -
@@ -204,6 +208,7 @@ EXPORT_SYMBOL(local_bh_enable_ip);
  * should not be able to lock up the box.
  */
 #define MAX_SOFTIRQ_TIME  msecs_to_jiffies(2)
+#define MAX_SOFTIRQ_RESTART 10
 
 asmlinkage void __do_softirq(void)
 {
@@ -212,6 +217,7 @@ asmlinkage void __do_softirq(void)
 	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
 	int cpu;
 	unsigned long old_flags = current->flags;
+	int max_restart = MAX_SOFTIRQ_RESTART;
 
 	/*
 	 * Mask out PF_MEMALLOC s current task context is borrowed for the
@@ -265,7 +271,8 @@ restart:
 
 	pending = local_softirq_pending();
 	if (pending) {
-		if (time_before(jiffies, end) && !need_resched())
+		if (time_before(jiffies, end) && !need_resched() &&
+		    --max_restart)
 			goto restart;
 
 		wakeup_softirqd();
diff --git a/kernel/sys.c b/kernel/sys.c
index b95d3c7..2bbd9a7 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -362,6 +362,29 @@ int unregister_reboot_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_reboot_notifier);
 
+/* Add backwards compatibility for stable trees. */
+#ifndef PF_NO_SETAFFINITY
+#define PF_NO_SETAFFINITY		PF_THREAD_BOUND
+#endif
+
+static void migrate_to_reboot_cpu(void)
+{
+	/* The boot cpu is always logical cpu 0 */
+	int cpu = 0;
+
+	cpu_hotplug_disable();
+
+	/* Make certain the cpu I'm about to reboot on is online */
+	if (!cpu_online(cpu))
+		cpu = cpumask_first(cpu_online_mask);
+
+	/* Prevent races with other tasks migrating this task */
+	current->flags |= PF_NO_SETAFFINITY;
+
+	/* Make certain I only run on the appropriate processor */
+	set_cpus_allowed_ptr(current, cpumask_of(cpu));
+}
+
 /**
  *	kernel_restart - reboot the system
  *	@cmd: pointer to buffer containing command to execute for restart
@@ -373,7 +396,7 @@ EXPORT_SYMBOL(unregister_reboot_notifier);
 void kernel_restart(char *cmd)
 {
 	kernel_restart_prepare(cmd);
-	disable_nonboot_cpus();
+	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	if (!cmd)
 		printk(KERN_EMERG "Restarting system.\n");
@@ -400,7 +423,7 @@ static void kernel_shutdown_prepare(enum system_states state)
 void kernel_halt(void)
 {
 	kernel_shutdown_prepare(SYSTEM_HALT);
-	disable_nonboot_cpus();
+	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	printk(KERN_EMERG "System halted.\n");
 	kmsg_dump(KMSG_DUMP_HALT);
@@ -419,7 +442,7 @@ void kernel_power_off(void)
 	kernel_shutdown_prepare(SYSTEM_POWER_OFF);
 	if (pm_power_off_prepare)
 		pm_power_off_prepare();
-	disable_nonboot_cpus();
+	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	printk(KERN_EMERG "Power down.\n");
 	kmsg_dump(KMSG_DUMP_POWEROFF);
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 12ff13a..8f5b3b9 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -874,7 +874,6 @@ static void hardpps_update_phase(long error)
 void __hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
 {
 	struct pps_normtime pts_norm, freq_norm;
-	unsigned long flags;
 
 	pts_norm = pps_normalize_ts(*phase_ts);
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 24938d5..0c73942 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -511,6 +511,12 @@ again:
 		}
 	}
 
+	/*
+	 * Remove the current cpu from the pending mask. The event is
+	 * delivered immediately in tick_do_broadcast() !
+	 */
+	cpumask_clear_cpu(smp_processor_id(), tick_broadcast_pending_mask);
+
 	/* Take care of enforced broadcast requests */
 	cpumask_or(tmpmask, tmpmask, tick_broadcast_force_mask);
 	cpumask_clear(tick_broadcast_force_mask);
@@ -575,8 +581,8 @@ void tick_broadcast_oneshot_control(unsigned long reason)
 
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 	if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
-		WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
 		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
+			WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
 			clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
 			/*
 			 * We only reprogram the broadcast timer if we
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 98cd470..baeeb5c8 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -975,6 +975,14 @@ static int timekeeping_suspend(void)
 
 	read_persistent_clock(&timekeeping_suspend_time);
 
+	/*
+	 * On some systems the persistent_clock can not be detected at
+	 * timekeeping_init by its return value, so if we see a valid
+	 * value returned, update the persistent_clock_exists flag.
+	 */
+	if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec)
+		persistent_clock_exist = true;
+
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&timekeeper_seq);
 	timekeeping_forward_now(tk);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b549b0f..6c508ff 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -120,22 +120,22 @@ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip);
 
 /*
  * Traverse the ftrace_global_list, invoking all entries.  The reason that we
- * can use rcu_dereference_raw() is that elements removed from this list
+ * can use rcu_dereference_raw_notrace() is that elements removed from this list
  * are simply leaked, so there is no need to interact with a grace-period
- * mechanism.  The rcu_dereference_raw() calls are needed to handle
+ * mechanism.  The rcu_dereference_raw_notrace() calls are needed to handle
  * concurrent insertions into the ftrace_global_list.
  *
  * Silly Alpha and silly pointer-speculation compiler optimizations!
  */
 #define do_for_each_ftrace_op(op, list)			\
-	op = rcu_dereference_raw(list);			\
+	op = rcu_dereference_raw_notrace(list);			\
 	do
 
 /*
  * Optimized for just a single item in the list (as that is the normal case).
  */
 #define while_for_each_ftrace_op(op)				\
-	while (likely(op = rcu_dereference_raw((op)->next)) &&	\
+	while (likely(op = rcu_dereference_raw_notrace((op)->next)) &&	\
 	       unlikely((op) != &ftrace_list_end))
 
 static inline void ftrace_ops_init(struct ftrace_ops *ops)
@@ -779,7 +779,7 @@ ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip)
 	if (hlist_empty(hhd))
 		return NULL;
 
-	hlist_for_each_entry_rcu(rec, hhd, node) {
+	hlist_for_each_entry_rcu_notrace(rec, hhd, node) {
 		if (rec->ip == ip)
 			return rec;
 	}
@@ -1165,7 +1165,7 @@ ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip)
 
 	hhd = &hash->buckets[key];
 
-	hlist_for_each_entry_rcu(entry, hhd, hlist) {
+	hlist_for_each_entry_rcu_notrace(entry, hhd, hlist) {
 		if (entry->ip == ip)
 			return entry;
 	}
@@ -1422,8 +1422,8 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
 	struct ftrace_hash *notrace_hash;
 	int ret;
 
-	filter_hash = rcu_dereference_raw(ops->filter_hash);
-	notrace_hash = rcu_dereference_raw(ops->notrace_hash);
+	filter_hash = rcu_dereference_raw_notrace(ops->filter_hash);
+	notrace_hash = rcu_dereference_raw_notrace(ops->notrace_hash);
 
 	if ((ftrace_hash_empty(filter_hash) ||
 	     ftrace_lookup_ip(filter_hash, ip)) &&
@@ -2920,7 +2920,7 @@ static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip,
 	 * on the hash. rcu_read_lock is too dangerous here.
 	 */
 	preempt_disable_notrace();
-	hlist_for_each_entry_rcu(entry, hhd, node) {
+	hlist_for_each_entry_rcu_notrace(entry, hhd, node) {
 		if (entry->ip == ip)
 			entry->ops->func(ip, parent_ip, &entry->data);
 	}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4d79485..e71a8be 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -652,8 +652,6 @@ static struct {
 	ARCH_TRACE_CLOCKS
 };
 
-int trace_clock_id;
-
 /*
  * trace_parser_get_init - gets the buffer for trace parser
  */
@@ -843,7 +841,15 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 	memcpy(max_data->comm, tsk->comm, TASK_COMM_LEN);
 	max_data->pid = tsk->pid;
-	max_data->uid = task_uid(tsk);
+	/*
+	 * If tsk == current, then use current_uid(), as that does not use
+	 * RCU. The irq tracer can be called out of RCU scope.
+	 */
+	if (tsk == current)
+		max_data->uid = current_uid();
+	else
+		max_data->uid = task_uid(tsk);
+
 	max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
 	max_data->policy = tsk->policy;
 	max_data->rt_priority = tsk->rt_priority;
@@ -2818,7 +2824,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
 		iter->iter_flags |= TRACE_FILE_ANNOTATE;
 
 	/* Output in nanoseconds only if we are using a clock in nanoseconds. */
-	if (trace_clocks[trace_clock_id].in_ns)
+	if (trace_clocks[tr->clock_id].in_ns)
 		iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
 
 	/* stop the trace while dumping if we are not opening "snapshot" */
@@ -3817,7 +3823,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 		iter->iter_flags |= TRACE_FILE_LAT_FMT;
 
 	/* Output in nanoseconds only if we are using a clock in nanoseconds. */
-	if (trace_clocks[trace_clock_id].in_ns)
+	if (trace_clocks[tr->clock_id].in_ns)
 		iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
 
 	iter->cpu_file = tc->cpu;
@@ -5087,7 +5093,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 	cnt = ring_buffer_bytes_cpu(trace_buf->buffer, cpu);
 	trace_seq_printf(s, "bytes: %ld\n", cnt);
 
-	if (trace_clocks[trace_clock_id].in_ns) {
+	if (trace_clocks[tr->clock_id].in_ns) {
 		/* local or global for trace_clock */
 		t = ns2usecs(ring_buffer_oldest_event_ts(trace_buf->buffer, cpu));
 		usec_rem = do_div(t, USEC_PER_SEC);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 711ca7d..20572ed 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -700,8 +700,6 @@ enum print_line_t print_trace_line(struct trace_iterator *iter);
 
 extern unsigned long trace_flags;
 
-extern int trace_clock_id;
-
 /* Standard output formatting function used for function return traces */
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 55e2cf6..2901e3b 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -1159,7 +1159,7 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr)
 	/* stop the tracing. */
 	tracing_stop();
 	/* check the trace buffer */
-	ret = trace_test_buffer(tr, &count);
+	ret = trace_test_buffer(&tr->trace_buffer, &count);
 	trace->reset(tr);
 	tracing_start();