Merge branch 'smp' into misc

Conflicts:
	arch/arm/kernel/entry-armv.S
	arch/arm/mm/ioremap.c

23 files changed, 289 insertions, 103 deletions

diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 37755d6..a6e7297 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -82,7 +82,7 @@ static kdbtab_t kdb_base_commands[50];
 #define for_each_kdbcmd(cmd, num)					\
 	for ((cmd) = kdb_base_commands, (num) = 0;			\
 	     num < kdb_max_commands;					\
-	     num == KDB_BASE_CMD_MAX ? cmd = kdb_commands : cmd++, num++)
+	     num++, num == KDB_BASE_CMD_MAX ? cmd = kdb_commands : cmd++)
 
 typedef struct _kdbmsg {
 	int	km_diag;	/* kdb diagnostic */
@@ -646,7 +646,7 @@ static int kdb_defcmd2(const char *cmdstr, const char *argv0)
 	}
 	if (!s->usable)
 		return KDB_NOTIMP;
-	s->command = kmalloc((s->count + 1) * sizeof(*(s->command)), GFP_KDB);
+	s->command = kzalloc((s->count + 1) * sizeof(*(s->command)), GFP_KDB);
 	if (!s->command) {
 		kdb_printf("Could not allocate new kdb_defcmd table for %s\n",
 			   cmdstr);
@@ -2361,7 +2361,7 @@ static int kdb_pid(int argc, const char **argv)
  */
 static int kdb_ll(int argc, const char **argv)
 {
-	int diag;
+	int diag = 0;
 	unsigned long addr;
 	long offset = 0;
 	unsigned long va;
@@ -2400,20 +2400,21 @@ static int kdb_ll(int argc, const char **argv)
 		char buf[80];
 
 		if (KDB_FLAG(CMD_INTERRUPT))
-			return 0;
+			goto out;
 
 		sprintf(buf, "%s " kdb_machreg_fmt "\n", command, va);
 		diag = kdb_parse(buf);
 		if (diag)
-			return diag;
+			goto out;
 
 		addr = va + linkoffset;
 		if (kdb_getword(&va, addr, sizeof(va)))
-			return 0;
+			goto out;
 	}
-	kfree(command);
 
-	return 0;
+out:
+	kfree(command);
+	return diag;
 }
 
 static int kdb_kgdb(int argc, const char **argv)
@@ -2739,13 +2740,13 @@ int kdb_register_repeat(char *cmd,
 		}
 		if (kdb_commands) {
 			memcpy(new, kdb_commands,
-			       kdb_max_commands * sizeof(*new));
+			  (kdb_max_commands - KDB_BASE_CMD_MAX) * sizeof(*new));
 			kfree(kdb_commands);
 		}
 		memset(new + kdb_max_commands, 0,
 		       kdb_command_extend * sizeof(*new));
 		kdb_commands = new;
-		kp = kdb_commands + kdb_max_commands;
+		kp = kdb_commands + kdb_max_commands - KDB_BASE_CMD_MAX;
 		kdb_max_commands += kdb_command_extend;
 	}
 
diff --git a/kernel/exit.c b/kernel/exit.c
index b194feb..21aa7b3 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -96,6 +96,14 @@ static void __exit_signal(struct task_struct *tsk)
 		sig->tty = NULL;
 	} else {
 		/*
+		 * This can only happen if the caller is de_thread().
+		 * FIXME: this is the temporary hack, we should teach
+		 * posix-cpu-timers to handle this case correctly.
+		 */
+		if (unlikely(has_group_leader_pid(tsk)))
+			posix_cpu_timers_exit_group(tsk);
+
+		/*
 		 * If there is any task waiting for the group exit
 		 * then notify it:
 		 */
diff --git a/kernel/futex.c b/kernel/futex.c
index 6c683b3..40a8777 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2489,7 +2489,8 @@ void exit_robust_list(struct task_struct *curr)
 {
 	struct robust_list_head __user *head = curr->robust_list;
 	struct robust_list __user *entry, *next_entry, *pending;
-	unsigned int limit = ROBUST_LIST_LIMIT, pi, next_pi, pip;
+	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
+	unsigned int uninitialized_var(next_pi);
 	unsigned long futex_offset;
 	int rc;
 
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index 06da4df..a7934ac 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -49,7 +49,8 @@ void compat_exit_robust_list(struct task_struct *curr)
 {
 	struct compat_robust_list_head __user *head = curr->compat_robust_list;
 	struct robust_list __user *entry, *next_entry, *pending;
-	unsigned int limit = ROBUST_LIST_LIMIT, pi, next_pi, pip;
+	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
+	unsigned int uninitialized_var(next_pi);
 	compat_uptr_t uentry, next_uentry, upending;
 	compat_long_t futex_offset;
 	int rc;
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index 2c9120f0..e532582 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -620,7 +620,7 @@ static struct pmu perf_breakpoint = {
 	.read		= hw_breakpoint_pmu_read,
 };
 
-static int __init init_hw_breakpoint(void)
+int __init init_hw_breakpoint(void)
 {
 	unsigned int **task_bp_pinned;
 	int cpu, err_cpu;
@@ -655,6 +655,5 @@ static int __init init_hw_breakpoint(void)
 
 	return -ENOMEM;
 }
-core_initcall(init_hw_breakpoint);
 
 
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index f16763f..90f8819 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -145,7 +145,9 @@ void irq_work_run(void)
 		 * Clear the BUSY bit and return to the free state if
 		 * no-one else claimed it meanwhile.
 		 */
-		cmpxchg(&entry->next, next_flags(NULL, IRQ_WORK_BUSY), NULL);
+		(void)cmpxchg(&entry->next,
+			      next_flags(NULL, IRQ_WORK_BUSY),
+			      NULL);
 	}
 }
 EXPORT_SYMBOL_GPL(irq_work_run);
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index 877fb30..17110a4 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -194,14 +194,7 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
 
 	account_global_scheduler_latency(tsk, &lat);
 
-	/*
-	 * short term hack; if we're > 32 we stop; future we recycle:
-	 */
-	tsk->latency_record_count++;
-	if (tsk->latency_record_count >= LT_SAVECOUNT)
-		goto out_unlock;
-
-	for (i = 0; i < LT_SAVECOUNT; i++) {
+	for (i = 0; i < tsk->latency_record_count; i++) {
 		struct latency_record *mylat;
 		int same = 1;
 
@@ -227,8 +220,14 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
 		}
 	}
 
+	/*
+	 * short term hack; if we're > 32 we stop; future we recycle:
+	 */
+	if (tsk->latency_record_count >= LT_SAVECOUNT)
+		goto out_unlock;
+
 	/* Allocated a new one: */
-	i = tsk->latency_record_count;
+	i = tsk->latency_record_count++;
 	memcpy(&tsk->latency_record[i], &lat, sizeof(struct latency_record));
 
 out_unlock:
diff --git a/kernel/module.c b/kernel/module.c
index 437a74a..d190664 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2326,6 +2326,18 @@ static void find_module_sections(struct module *mod, struct load_info *info)
 	kmemleak_scan_area(mod->trace_events, sizeof(*mod->trace_events) *
 			   mod->num_trace_events, GFP_KERNEL);
 #endif
+#ifdef CONFIG_TRACING
+	mod->trace_bprintk_fmt_start = section_objs(info, "__trace_printk_fmt",
+					 sizeof(*mod->trace_bprintk_fmt_start),
+					 &mod->num_trace_bprintk_fmt);
+	/*
+	 * This section contains pointers to allocated objects in the trace
+	 * code and not scanning it leads to false positives.
+	 */
+	kmemleak_scan_area(mod->trace_bprintk_fmt_start,
+			   sizeof(*mod->trace_bprintk_fmt_start) *
+			   mod->num_trace_bprintk_fmt, GFP_KERNEL);
+#endif
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 	/* sechdrs[0].sh_size is always zero */
 	mod->ftrace_callsites = section_objs(info, "__mcount_loc",
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 517d827..eac7e33 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -31,6 +31,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/perf_event.h>
 #include <linux/ftrace_event.h>
+#include <linux/hw_breakpoint.h>
 
 #include <asm/irq_regs.h>
 
@@ -674,6 +675,8 @@ event_sched_in(struct perf_event *event,
 
 	event->tstamp_running += ctx->time - event->tstamp_stopped;
 
+	event->shadow_ctx_time = ctx->time - ctx->timestamp;
+
 	if (!is_software_event(event))
 		cpuctx->active_oncpu++;
 	ctx->nr_active++;
@@ -1284,8 +1287,6 @@ void __perf_event_task_sched_out(struct task_struct *task,
 {
 	int ctxn;
 
-	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
-
 	for_each_task_context_nr(ctxn)
 		perf_event_context_sched_out(task, ctxn, next);
 }
@@ -1619,8 +1620,12 @@ static void rotate_ctx(struct perf_event_context *ctx)
 {
 	raw_spin_lock(&ctx->lock);
 
-	/* Rotate the first entry last of non-pinned groups */
-	list_rotate_left(&ctx->flexible_groups);
+	/*
+	 * Rotate the first entry last of non-pinned groups. Rotation might be
+	 * disabled by the inheritance code.
+	 */
+	if (!ctx->rotate_disable)
+		list_rotate_left(&ctx->flexible_groups);
 
 	raw_spin_unlock(&ctx->lock);
 }
@@ -2232,11 +2237,6 @@ int perf_event_release_kernel(struct perf_event *event)
 	raw_spin_unlock_irq(&ctx->lock);
 	mutex_unlock(&ctx->mutex);
 
-	mutex_lock(&event->owner->perf_event_mutex);
-	list_del_init(&event->owner_entry);
-	mutex_unlock(&event->owner->perf_event_mutex);
-	put_task_struct(event->owner);
-
 	free_event(event);
 
 	return 0;
@@ -2249,9 +2249,43 @@ EXPORT_SYMBOL_GPL(perf_event_release_kernel);
 static int perf_release(struct inode *inode, struct file *file)
 {
 	struct perf_event *event = file->private_data;
+	struct task_struct *owner;
 
 	file->private_data = NULL;
 
+	rcu_read_lock();
+	owner = ACCESS_ONCE(event->owner);
+	/*
+	 * Matches the smp_wmb() in perf_event_exit_task(). If we observe
+	 * !owner it means the list deletion is complete and we can indeed
+	 * free this event, otherwise we need to serialize on
+	 * owner->perf_event_mutex.
+	 */
+	smp_read_barrier_depends();
+	if (owner) {
+		/*
+		 * Since delayed_put_task_struct() also drops the last
+		 * task reference we can safely take a new reference
+		 * while holding the rcu_read_lock().
+		 */
+		get_task_struct(owner);
+	}
+	rcu_read_unlock();
+
+	if (owner) {
+		mutex_lock(&owner->perf_event_mutex);
+		/*
+		 * We have to re-check the event->owner field, if it is cleared
+		 * we raced with perf_event_exit_task(), acquiring the mutex
+		 * ensured they're done, and we can proceed with freeing the
+		 * event.
+		 */
+		if (event->owner)
+			list_del_init(&event->owner_entry);
+		mutex_unlock(&owner->perf_event_mutex);
+		put_task_struct(owner);
+	}
+
 	return perf_event_release_kernel(event);
 }
 
@@ -3396,7 +3430,8 @@ static u32 perf_event_tid(struct perf_event *event, struct task_struct *p)
 }
 
 static void perf_output_read_one(struct perf_output_handle *handle,
-				 struct perf_event *event)
+				 struct perf_event *event,
+				 u64 enabled, u64 running)
 {
 	u64 read_format = event->attr.read_format;
 	u64 values[4];
@@ -3404,11 +3439,11 @@ static void perf_output_read_one(struct perf_output_handle *handle,
 
 	values[n++] = perf_event_count(event);
 	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
-		values[n++] = event->total_time_enabled +
+		values[n++] = enabled +
 			atomic64_read(&event->child_total_time_enabled);
 	}
 	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
-		values[n++] = event->total_time_running +
+		values[n++] = running +
 			atomic64_read(&event->child_total_time_running);
 	}
 	if (read_format & PERF_FORMAT_ID)
@@ -3421,7 +3456,8 @@ static void perf_output_read_one(struct perf_output_handle *handle,
  * XXX PERF_FORMAT_GROUP vs inherited events seems difficult.
  */
 static void perf_output_read_group(struct perf_output_handle *handle,
-			    struct perf_event *event)
+			    struct perf_event *event,
+			    u64 enabled, u64 running)
 {
 	struct perf_event *leader = event->group_leader, *sub;
 	u64 read_format = event->attr.read_format;
@@ -3431,10 +3467,10 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 	values[n++] = 1 + leader->nr_siblings;
 
 	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
-		values[n++] = leader->total_time_enabled;
+		values[n++] = enabled;
 
 	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
-		values[n++] = leader->total_time_running;
+		values[n++] = running;
 
 	if (leader != event)
 		leader->pmu->read(leader);
@@ -3459,13 +3495,35 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 	}
 }
 
+#define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\
+				 PERF_FORMAT_TOTAL_TIME_RUNNING)
+
 static void perf_output_read(struct perf_output_handle *handle,
 			     struct perf_event *event)
 {
+	u64 enabled = 0, running = 0, now, ctx_time;
+	u64 read_format = event->attr.read_format;
+
+	/*
+	 * compute total_time_enabled, total_time_running
+	 * based on snapshot values taken when the event
+	 * was last scheduled in.
+	 *
+	 * we cannot simply called update_context_time()
+	 * because of locking issue as we are called in
+	 * NMI context
+	 */
+	if (read_format & PERF_FORMAT_TOTAL_TIMES) {
+		now = perf_clock();
+		ctx_time = event->shadow_ctx_time + now;
+		enabled = ctx_time - event->tstamp_enabled;
+		running = ctx_time - event->tstamp_running;
+	}
+
 	if (event->attr.read_format & PERF_FORMAT_GROUP)
-		perf_output_read_group(handle, event);
+		perf_output_read_group(handle, event, enabled, running);
 	else
-		perf_output_read_one(handle, event);
+		perf_output_read_one(handle, event, enabled, running);
 }
 
 void perf_output_sample(struct perf_output_handle *handle,
@@ -5651,7 +5709,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	mutex_unlock(&ctx->mutex);
 
 	event->owner = current;
-	get_task_struct(current);
+
 	mutex_lock(&current->perf_event_mutex);
 	list_add_tail(&event->owner_entry, &current->perf_event_list);
 	mutex_unlock(&current->perf_event_mutex);
@@ -5719,12 +5777,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	++ctx->generation;
 	mutex_unlock(&ctx->mutex);
 
-	event->owner = current;
-	get_task_struct(current);
-	mutex_lock(&current->perf_event_mutex);
-	list_add_tail(&event->owner_entry, &current->perf_event_list);
-	mutex_unlock(&current->perf_event_mutex);
-
 	return event;
 
 err_free:
@@ -5875,8 +5927,24 @@ again:
  */
 void perf_event_exit_task(struct task_struct *child)
 {
+	struct perf_event *event, *tmp;
 	int ctxn;
 
+	mutex_lock(&child->perf_event_mutex);
+	list_for_each_entry_safe(event, tmp, &child->perf_event_list,
+				 owner_entry) {
+		list_del_init(&event->owner_entry);
+
+		/*
+		 * Ensure the list deletion is visible before we clear
+		 * the owner, closes a race against perf_release() where
+		 * we need to serialize on the owner->perf_event_mutex.
+		 */
+		smp_wmb();
+		event->owner = NULL;
+	}
+	mutex_unlock(&child->perf_event_mutex);
+
 	for_each_task_context_nr(ctxn)
 		perf_event_exit_task_context(child, ctxn);
 }
@@ -6096,6 +6164,7 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 	struct perf_event *event;
 	struct task_struct *parent = current;
 	int inherited_all = 1;
+	unsigned long flags;
 	int ret = 0;
 
 	child->perf_event_ctxp[ctxn] = NULL;
@@ -6136,6 +6205,15 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 			break;
 	}
 
+	/*
+	 * We can't hold ctx->lock when iterating the ->flexible_group list due
+	 * to allocations, but we need to prevent rotation because
+	 * rotate_ctx() will change the list from interrupt context.
+	 */
+	raw_spin_lock_irqsave(&parent_ctx->lock, flags);
+	parent_ctx->rotate_disable = 1;
+	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+
 	list_for_each_entry(event, &parent_ctx->flexible_groups, group_entry) {
 		ret = inherit_task_group(event, parent, parent_ctx,
 					 child, ctxn, &inherited_all);
@@ -6143,6 +6221,10 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 			break;
 	}
 
+	raw_spin_lock_irqsave(&parent_ctx->lock, flags);
+	parent_ctx->rotate_disable = 0;
+	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+
 	child_ctx = child->perf_event_ctxp[ctxn];
 
 	if (child_ctx && inherited_all) {
@@ -6295,6 +6377,8 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 
 void __init perf_event_init(void)
 {
+	int ret;
+
 	perf_event_init_all_cpus();
 	init_srcu_struct(&pmus_srcu);
 	perf_pmu_register(&perf_swevent);
@@ -6302,4 +6386,7 @@ void __init perf_event_init(void)
 	perf_pmu_register(&perf_task_clock);
 	perf_tp_register();
 	perf_cpu_notifier(perf_cpu_notify);
+
+	ret = init_hw_breakpoint();
+	WARN(ret, "hw_breakpoint initialization failed with: %d", ret);
 }
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index c7a8f45..aeaa7f8 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -121,10 +121,10 @@ static inline int pm_qos_get_value(struct pm_qos_object *o)
 
 	switch (o->type) {
 	case PM_QOS_MIN:
-		return plist_last(&o->requests)->prio;
+		return plist_first(&o->requests)->prio;
 
 	case PM_QOS_MAX:
-		return plist_first(&o->requests)->prio;
+		return plist_last(&o->requests)->prio;
 
 	default:
 		/* runtime check for not using enum */
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 6842eeb..05bb717 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -37,13 +37,13 @@ static int check_clock(const clockid_t which_clock)
 	if (pid == 0)
 		return 0;
 
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	p = find_task_by_vpid(pid);
 	if (!p || !(CPUCLOCK_PERTHREAD(which_clock) ?
-		   same_thread_group(p, current) : thread_group_leader(p))) {
+		   same_thread_group(p, current) : has_group_leader_pid(p))) {
 		error = -EINVAL;
 	}
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 
 	return error;
 }
@@ -390,7 +390,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
 
 	INIT_LIST_HEAD(&new_timer->it.cpu.entry);
 
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	if (CPUCLOCK_PERTHREAD(new_timer->it_clock)) {
 		if (pid == 0) {
 			p = current;
@@ -404,7 +404,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
 			p = current->group_leader;
 		} else {
 			p = find_task_by_vpid(pid);
-			if (p && !thread_group_leader(p))
+			if (p && !has_group_leader_pid(p))
 				p = NULL;
 		}
 	}
@@ -414,7 +414,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
 	} else {
 		ret = -EINVAL;
 	}
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 
 	return ret;
 }
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 29bff61..a5aff3e 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -246,9 +246,13 @@ config PM_OPS
 	depends on PM_SLEEP || PM_RUNTIME
 	default y
 
+config ARCH_HAS_OPP
+	bool
+
 config PM_OPP
 	bool "Operating Performance Point (OPP) Layer library"
 	depends on PM
+	depends on ARCH_HAS_OPP
 	---help---
 	  SOCs have a standard set of tuples consisting of frequency and
 	  voltage pairs that the device will support per voltage domain. This
diff --git a/kernel/printk.c b/kernel/printk.c
index b2ebaee..9a2264f 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -261,6 +261,12 @@ static inline void boot_delay_msec(void)
 }
 #endif
 
+#ifdef CONFIG_SECURITY_DMESG_RESTRICT
+int dmesg_restrict = 1;
+#else
+int dmesg_restrict;
+#endif
+
 int do_syslog(int type, char __user *buf, int len, bool from_file)
 {
 	unsigned i, j, limit, count;
@@ -268,7 +274,20 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
 	char c;
 	int error = 0;
 
-	error = security_syslog(type, from_file);
+	/*
+	 * If this is from /proc/kmsg we only do the capabilities checks
+	 * at open time.
+	 */
+	if (type == SYSLOG_ACTION_OPEN || !from_file) {
+		if (dmesg_restrict && !capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		if ((type != SYSLOG_ACTION_READ_ALL &&
+		     type != SYSLOG_ACTION_SIZE_BUFFER) &&
+		    !capable(CAP_SYS_ADMIN))
+			return -EPERM;
+	}
+
+	error = security_syslog(type);
 	if (error)
 		return error;
 
diff --git a/kernel/range.c b/kernel/range.c
index 471b66a..37fa9b9 100644
--- a/kernel/range.c
+++ b/kernel/range.c
@@ -119,7 +119,7 @@ static int cmp_range(const void *x1, const void *x2)
 
 int clean_sort_range(struct range *range, int az)
 {
-	int i, j, k = az - 1, nr_range = 0;
+	int i, j, k = az - 1, nr_range = az;
 
 	for (i = 0; i < k; i++) {
 		if (range[i].end)
diff --git a/kernel/relay.c b/kernel/relay.c
index c7cf397..859ea5a 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -70,17 +70,10 @@ static const struct vm_operations_struct relay_file_mmap_ops = {
  */
 static struct page **relay_alloc_page_array(unsigned int n_pages)
 {
-	struct page **array;
-	size_t pa_size = n_pages * sizeof(struct page *);
-
-	if (pa_size > PAGE_SIZE) {
-		array = vmalloc(pa_size);
-		if (array)
-			memset(array, 0, pa_size);
-	} else {
-		array = kzalloc(pa_size, GFP_KERNEL);
-	}
-	return array;
+	const size_t pa_size = n_pages * sizeof(struct page *);
+	if (pa_size > PAGE_SIZE)
+		return vzalloc(pa_size);
+	return kzalloc(pa_size, GFP_KERNEL);
 }
 
 /*
diff --git a/kernel/sched.c b/kernel/sched.c
index aa14a56..dc91a4d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -560,18 +560,8 @@ struct rq {
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
-static inline
-void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
-{
-	rq->curr->sched_class->check_preempt_curr(rq, p, flags);
 
-	/*
-	 * A queue event has occurred, and we're going to schedule.  In
-	 * this case, we can save a useless back to back clock update.
-	 */
-	if (test_tsk_need_resched(p))
-		rq->skip_clock_update = 1;
-}
+static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
 
 static inline int cpu_of(struct rq *rq)
 {
@@ -2118,6 +2108,31 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 		p->sched_class->prio_changed(rq, p, oldprio, running);
 }
 
+static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
+{
+	const struct sched_class *class;
+
+	if (p->sched_class == rq->curr->sched_class) {
+		rq->curr->sched_class->check_preempt_curr(rq, p, flags);
+	} else {
+		for_each_class(class) {
+			if (class == rq->curr->sched_class)
+				break;
+			if (class == p->sched_class) {
+				resched_task(rq->curr);
+				break;
+			}
+		}
+	}
+
+	/*
+	 * A queue event has occurred, and we're going to schedule.  In
+	 * this case, we can save a useless back to back clock update.
+	 */
+	if (test_tsk_need_resched(rq->curr))
+		rq->skip_clock_update = 1;
+}
+
 #ifdef CONFIG_SMP
 /*
  * Is this task likely cache-hot:
@@ -6960,6 +6975,8 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 	if (cpu != group_first_cpu(sd->groups))
 		return;
 
+	sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups));
+
 	child = sd->child;
 
 	sd->groups->cpu_power = 0;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index f4f6a83..00ebd76 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1654,12 +1654,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
 	int scale = cfs_rq->nr_running >= sched_nr_latency;
 
-	if (unlikely(rt_prio(p->prio)))
-		goto preempt;
-
-	if (unlikely(p->sched_class != &fair_sched_class))
-		return;
-
 	if (unlikely(se == pse))
 		return;
 
@@ -1764,10 +1758,6 @@ static void pull_task(struct rq *src_rq, struct task_struct *p,
 	set_task_cpu(p, this_cpu);
 	activate_task(this_rq, p, 0);
 	check_preempt_curr(this_rq, p, 0);
-
-	/* re-arm NEWIDLE balancing when moving tasks */
-	src_rq->avg_idle = this_rq->avg_idle = 2*sysctl_sched_migration_cost;
-	this_rq->idle_stamp = 0;
 }
 
 /*
@@ -2035,13 +2025,16 @@ struct sd_lb_stats {
 	unsigned long this_load_per_task;
 	unsigned long this_nr_running;
 	unsigned long this_has_capacity;
+	unsigned int  this_idle_cpus;
 
 	/* Statistics of the busiest group */
+	unsigned int  busiest_idle_cpus;
 	unsigned long max_load;
 	unsigned long busiest_load_per_task;
 	unsigned long busiest_nr_running;
 	unsigned long busiest_group_capacity;
 	unsigned long busiest_has_capacity;
+	unsigned int  busiest_group_weight;
 
 	int group_imb; /* Is there imbalance in this sd */
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
@@ -2063,6 +2056,8 @@ struct sg_lb_stats {
 	unsigned long sum_nr_running; /* Nr tasks running in the group */
 	unsigned long sum_weighted_load; /* Weighted load of group's tasks */
 	unsigned long group_capacity;
+	unsigned long idle_cpus;
+	unsigned long group_weight;
 	int group_imb; /* Is there an imbalance in the group ? */
 	int group_has_capacity; /* Is there extra capacity in the group? */
 };
@@ -2431,7 +2426,8 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 		sgs->group_load += load;
 		sgs->sum_nr_running += rq->nr_running;
 		sgs->sum_weighted_load += weighted_cpuload(i);
-
+		if (idle_cpu(i))
+			sgs->idle_cpus++;
 	}
 
 	/*
@@ -2469,6 +2465,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
 	if (!sgs->group_capacity)
 		sgs->group_capacity = fix_small_capacity(sd, group);
+	sgs->group_weight = group->group_weight;
 
 	if (sgs->group_capacity > sgs->sum_nr_running)
 		sgs->group_has_capacity = 1;
@@ -2576,13 +2573,16 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 			sds->this_nr_running = sgs.sum_nr_running;
 			sds->this_load_per_task = sgs.sum_weighted_load;
 			sds->this_has_capacity = sgs.group_has_capacity;
+			sds->this_idle_cpus = sgs.idle_cpus;
 		} else if (update_sd_pick_busiest(sd, sds, sg, &sgs, this_cpu)) {
 			sds->max_load = sgs.avg_load;
 			sds->busiest = sg;
 			sds->busiest_nr_running = sgs.sum_nr_running;
+			sds->busiest_idle_cpus = sgs.idle_cpus;
 			sds->busiest_group_capacity = sgs.group_capacity;
 			sds->busiest_load_per_task = sgs.sum_weighted_load;
 			sds->busiest_has_capacity = sgs.group_has_capacity;
+			sds->busiest_group_weight = sgs.group_weight;
 			sds->group_imb = sgs.group_imb;
 		}
 
@@ -2860,8 +2860,26 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 	if (sds.this_load >= sds.avg_load)
 		goto out_balanced;
 
-	if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
-		goto out_balanced;
+	/*
+	 * In the CPU_NEWLY_IDLE, use imbalance_pct to be conservative.
+	 * And to check for busy balance use !idle_cpu instead of
+	 * CPU_NOT_IDLE. This is because HT siblings will use CPU_NOT_IDLE
+	 * even when they are idle.
+	 */
+	if (idle == CPU_NEWLY_IDLE || !idle_cpu(this_cpu)) {
+		if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
+			goto out_balanced;
+	} else {
+		/*
+		 * This cpu is idle. If the busiest group load doesn't
+		 * have more tasks than the number of available cpu's and
+		 * there is no imbalance between this and busiest group
+		 * wrt to idle cpu's, it is balanced.
+		 */
+		if ((sds.this_idle_cpus  <= sds.busiest_idle_cpus + 1) &&
+		    sds.busiest_nr_running <= sds.busiest_group_weight)
+			goto out_balanced;
+	}
 
 force_balance:
 	/* Looks like there is an imbalance. Compute it */
@@ -3197,8 +3215,10 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 		interval = msecs_to_jiffies(sd->balance_interval);
 		if (time_after(next_balance, sd->last_balance + interval))
 			next_balance = sd->last_balance + interval;
-		if (pulled_task)
+		if (pulled_task) {
+			this_rq->idle_stamp = 0;
 			break;
+		}
 	}
 
 	raw_spin_lock(&this_rq->lock);
diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
index 45bddc0..2bf6b47 100644
--- a/kernel/sched_stoptask.c
+++ b/kernel/sched_stoptask.c
@@ -19,14 +19,14 @@ select_task_rq_stop(struct rq *rq, struct task_struct *p,
 static void
 check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
 {
-	resched_task(rq->curr); /* we preempt everything */
+	/* we're never preempted */
 }
 
 static struct task_struct *pick_next_task_stop(struct rq *rq)
 {
 	struct task_struct *stop = rq->stop;
 
-	if (stop && stop->state == TASK_RUNNING)
+	if (stop && stop->se.on_rq)
 		return stop;
 
 	return NULL;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c33a1ed..5abfa15 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -702,6 +702,15 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &zero,
 		.extra2		= &ten_thousand,
 	},
+	{
+		.procname	= "dmesg_restrict",
+		.data		= &dmesg_restrict,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 #endif
 	{
 		.procname	= "ngroups_max",
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e04b8bc..ea37e2f 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -126,7 +126,7 @@ if FTRACE
 config FUNCTION_TRACER
 	bool "Kernel Function Tracer"
 	depends on HAVE_FUNCTION_TRACER
-	select FRAME_POINTER if (!ARM_UNWIND)
+	select FRAME_POINTER if !ARM_UNWIND && !S390
 	select KALLSYMS
 	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index bc251ed..7b8ec02 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -168,7 +168,6 @@ static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
 static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
 				 BLK_TC_ACT(BLK_TC_WRITE) };
 
-#define BLK_TC_HARDBARRIER	BLK_TC_BARRIER
 #define BLK_TC_RAHEAD		BLK_TC_AHEAD
 
 /* The ilog2() calls fall out because they're constant */
@@ -196,7 +195,6 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 		return;
 
 	what |= ddir_act[rw & WRITE];
-	what |= MASK_TC_BIT(rw, HARDBARRIER);
 	what |= MASK_TC_BIT(rw, SYNC);
 	what |= MASK_TC_BIT(rw, RAHEAD);
 	what |= MASK_TC_BIT(rw, META);
@@ -1807,8 +1805,6 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
 
 	if (rw & REQ_RAHEAD)
 		rwbs[i++] = 'A';
-	if (rw & REQ_HARDBARRIER)
-		rwbs[i++] = 'B';
 	if (rw & REQ_SYNC)
 		rwbs[i++] = 'S';
 	if (rw & REQ_META)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 82d9b81..c38061227 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -17,7 +17,6 @@
 #include <linux/writeback.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
 #include <linux/notifier.h>
 #include <linux/irqflags.h>
 #include <linux/debugfs.h>
@@ -1284,6 +1283,8 @@ void trace_dump_stack(void)
 	__ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count());
 }
 
+static DEFINE_PER_CPU(int, user_stack_count);
+
 void
 ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 {
@@ -1302,6 +1303,18 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 	if (unlikely(in_nmi()))
 		return;
 
+	/*
+	 * prevent recursion, since the user stack tracing may
+	 * trigger other kernel events.
+	 */
+	preempt_disable();
+	if (__this_cpu_read(user_stack_count))
+		goto out;
+
+	__this_cpu_inc(user_stack_count);
+
+
+
 	event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
 					  sizeof(*entry), flags, pc);
 	if (!event)
@@ -1319,6 +1332,11 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 	save_stack_trace_user(&trace);
 	if (!filter_check_discard(call, entry, buffer, event))
 		ring_buffer_unlock_commit(buffer, event);
+
+	__this_cpu_dec(user_stack_count);
+
+ out:
+	preempt_enable();
 }
 
 #ifdef UNUSED
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index bafba68..6e3c41a 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -43,7 +43,7 @@ static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
 #endif
 
-static int __initdata no_watchdog;
+static int no_watchdog;
 
 
 /* boot commands */