Merge branches 'core-urgent-for-linus', 'perf-urgent-for-linus', 'sch…

…ed-urgent-for-linus' and 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

* 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  bugs, x86: Fix printk levels for panic, softlockups and stack dumps

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf top: Fix number of samples displayed
  perf tools: Fix strlen() bug in perf_event__synthesize_event_type()
  perf tools: Fix broken build by defining _GNU_SOURCE in Makefile
  x86/dumpstack: Remove unneeded check in dump_trace()
  perf: Fix broken interrupt rate throttling

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/rt: Fix task stack corruption under __ARCH_WANT_INTERRUPTS_ON_CTXSW
  sched: Fix ancient race in do_exit()
  sched/nohz: Fix nohz cpu idle load balancing state with cpu hotplug
  sched/s390: Fix compile error in sched/core.c
  sched: Fix rq->nr_uninterruptible update race

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/reboot: Remove VersaLogic Menlow reboot quirk
  x86/reboot: Skip DMI checks if reboot set by user
  x86: Properly parenthesize cmpxchg() macro arguments

arch/x86/include/asm/cmpxchg.h

@@ -145,13 +145,13 @@ extern void __add_wrong_size(void)
 
 #ifdef __HAVE_ARCH_CMPXCHG
 #define cmpxchg(ptr, old, new)						\
-	__cmpxchg((ptr), (old), (new), sizeof(*ptr))
+	__cmpxchg(ptr, old, new, sizeof(*(ptr)))
 
 #define sync_cmpxchg(ptr, old, new)					\
-	__sync_cmpxchg((ptr), (old), (new), sizeof(*ptr))
+	__sync_cmpxchg(ptr, old, new, sizeof(*(ptr)))
 
 #define cmpxchg_local(ptr, old, new)					\
-	__cmpxchg_local((ptr), (old), (new), sizeof(*ptr))
+	__cmpxchg_local(ptr, old, new, sizeof(*(ptr)))
 #endif
 
 /*

arch/x86/kernel/dumpstack.c

@@ -252,7 +252,8 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err)
 	unsigned short ss;
 	unsigned long sp;
 #endif
-	printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
+	printk(KERN_DEFAULT
+	       "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
 #ifdef CONFIG_PREEMPT
 	printk("PREEMPT ");
 #endif

arch/x86/kernel/dumpstack_64.c

@@ -129,7 +129,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	if (!stack) {
 		if (regs)
 			stack = (unsigned long *)regs->sp;
-		else if (task && task != current)
+		else if (task != current)
 			stack = (unsigned long *)task->thread.sp;
 		else
 			stack = &dummy;
@@ -269,11 +269,11 @@ void show_registers(struct pt_regs *regs)
 		unsigned char c;
 		u8 *ip;
 
-		printk(KERN_EMERG "Stack:\n");
+		printk(KERN_DEFAULT "Stack:\n");
 		show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
-				   0, KERN_EMERG);
+				   0, KERN_DEFAULT);
 
-		printk(KERN_EMERG "Code: ");
+		printk(KERN_DEFAULT "Code: ");
 
 		ip = (u8 *)regs->ip - code_prologue;
 		if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {

arch/x86/kernel/reboot.c

@@ -39,6 +39,14 @@ static int reboot_mode;
 enum reboot_type reboot_type = BOOT_ACPI;
 int reboot_force;
 
+/* This variable is used privately to keep track of whether or not
+ * reboot_type is still set to its default value (i.e., reboot= hasn't
+ * been set on the command line).  This is needed so that we can
+ * suppress DMI scanning for reboot quirks.  Without it, it's
+ * impossible to override a faulty reboot quirk without recompiling.
+ */
+static int reboot_default = 1;
+
 #if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
 static int reboot_cpu = -1;
 #endif
@@ -67,6 +75,12 @@ bool port_cf9_safe = false;
 static int __init reboot_setup(char *str)
 {
 	for (;;) {
+		/* Having anything passed on the command line via
+		 * reboot= will cause us to disable DMI checking
+		 * below.
+		 */
+		reboot_default = 0;
+
 		switch (*str) {
 		case 'w':
 			reboot_mode = 0x1234;
@@ -295,14 +309,6 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "P4S800"),
 		},
 	},
-	{	/* Handle problems with rebooting on VersaLogic Menlow boards */
-		.callback = set_bios_reboot,
-		.ident = "VersaLogic Menlow based board",
-		.matches = {
-			DMI_MATCH(DMI_BOARD_VENDOR, "VersaLogic Corporation"),
-			DMI_MATCH(DMI_BOARD_NAME, "VersaLogic Menlow board"),
-		},
-	},
 	{ /* Handle reboot issue on Acer Aspire one */
 		.callback = set_kbd_reboot,
 		.ident = "Acer Aspire One A110",
@@ -316,7 +322,12 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 
 static int __init reboot_init(void)
 {
-	dmi_check_system(reboot_dmi_table);
+	/* Only do the DMI check if reboot_type hasn't been overridden
+	 * on the command line
+	 */
+	if (reboot_default) {
+		dmi_check_system(reboot_dmi_table);
+	}
 	return 0;
 }
 core_initcall(reboot_init);
@@ -465,7 +476,12 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = {
 
 static int __init pci_reboot_init(void)
 {
-	dmi_check_system(pci_reboot_dmi_table);
+	/* Only do the DMI check if reboot_type hasn't been overridden
+	 * on the command line
+	 */
+	if (reboot_default) {
+		dmi_check_system(pci_reboot_dmi_table);
+	}
 	return 0;
 }
 core_initcall(pci_reboot_init);

arch/x86/mm/fault.c

@@ -673,7 +673,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 
 	stackend = end_of_stack(tsk);
 	if (tsk != &init_task && *stackend != STACK_END_MAGIC)
-		printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
+		printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
 
 	tsk->thread.cr2		= address;
 	tsk->thread.trap_no	= 14;
@@ -684,7 +684,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 		sig = 0;
 
 	/* Executive summary in case the body of the oops scrolled away */
-	printk(KERN_EMERG "CR2: %016lx\n", address);
+	printk(KERN_DEFAULT "CR2: %016lx\n", address);
 
 	oops_end(flags, regs, sig);
 }

include/linux/perf_event.h

@@ -587,6 +587,7 @@ struct hw_perf_event {
 	u64				sample_period;
 	u64				last_period;
 	local64_t			period_left;
+	u64                             interrupts_seq;
 	u64				interrupts;
 
 	u64				freq_time_stamp;

kernel/events/core.c

@@ -2300,6 +2300,9 @@ do {					\
 	return div64_u64(dividend, divisor);
 }
 
+static DEFINE_PER_CPU(int, perf_throttled_count);
+static DEFINE_PER_CPU(u64, perf_throttled_seq);
+
 static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -2325,16 +2328,29 @@ static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
 	}
 }
 
-static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period)
+/*
+ * combine freq adjustment with unthrottling to avoid two passes over the
+ * events. At the same time, make sure, having freq events does not change
+ * the rate of unthrottling as that would introduce bias.
+ */
+static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
+					   int needs_unthr)
 {
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
-	u64 interrupts, now;
+	u64 now, period = TICK_NSEC;
 	s64 delta;
 
-	if (!ctx->nr_freq)
+	/*
+	 * only need to iterate over all events iff:
+	 * - context have events in frequency mode (needs freq adjust)
+	 * - there are events to unthrottle on this cpu
+	 */
+	if (!(ctx->nr_freq || needs_unthr))
 		return;
 
+	raw_spin_lock(&ctx->lock);
+
 	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
 		if (event->state != PERF_EVENT_STATE_ACTIVE)
 			continue;
@@ -2344,28 +2360,35 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period)
 
 		hwc = &event->hw;
 
-		interrupts = hwc->interrupts;
-		hwc->interrupts = 0;
-
-		/*
-		 * unthrottle events on the tick
-		 */
-		if (interrupts == MAX_INTERRUPTS) {
+		if (needs_unthr && hwc->interrupts == MAX_INTERRUPTS) {
+			hwc->interrupts = 0;
 			perf_log_throttle(event, 1);
 			event->pmu->start(event, 0);
 		}
 
 		if (!event->attr.freq || !event->attr.sample_freq)
 			continue;
 
-		event->pmu->read(event);
+		/*
+		 * stop the event and update event->count
+		 */
+		event->pmu->stop(event, PERF_EF_UPDATE);
+
 		now = local64_read(&event->count);
 		delta = now - hwc->freq_count_stamp;
 		hwc->freq_count_stamp = now;
 
+		/*
+		 * restart the event
+		 * reload only if value has changed
+		 */
 		if (delta > 0)
 			perf_adjust_period(event, period, delta);
+
+		event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0);
 	}
+
+	raw_spin_unlock(&ctx->lock);
 }
 
 /*
@@ -2388,54 +2411,40 @@ static void rotate_ctx(struct perf_event_context *ctx)
  */
 static void perf_rotate_context(struct perf_cpu_context *cpuctx)
 {
-	u64 interval = (u64)cpuctx->jiffies_interval * TICK_NSEC;
 	struct perf_event_context *ctx = NULL;
-	int rotate = 0, remove = 1, freq = 0;
+	int rotate = 0, remove = 1;
 
 	if (cpuctx->ctx.nr_events) {
 		remove = 0;
 		if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
 			rotate = 1;
-		if (cpuctx->ctx.nr_freq)
-			freq = 1;
 	}
 
 	ctx = cpuctx->task_ctx;
 	if (ctx && ctx->nr_events) {
 		remove = 0;
 		if (ctx->nr_events != ctx->nr_active)
 			rotate = 1;
-		if (ctx->nr_freq)
-			freq = 1;
 	}
 
-	if (!rotate && !freq)
+	if (!rotate)
 		goto done;
 
 	perf_ctx_lock(cpuctx, cpuctx->task_ctx);
 	perf_pmu_disable(cpuctx->ctx.pmu);
 
-	if (freq) {
-		perf_ctx_adjust_freq(&cpuctx->ctx, interval);
-		if (ctx)
-			perf_ctx_adjust_freq(ctx, interval);
-	}
-
-	if (rotate) {
-		cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
-		if (ctx)
-			ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);
+	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
+	if (ctx)
+		ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);
 
-		rotate_ctx(&cpuctx->ctx);
-		if (ctx)
-			rotate_ctx(ctx);
+	rotate_ctx(&cpuctx->ctx);
+	if (ctx)
+		rotate_ctx(ctx);
 
-		perf_event_sched_in(cpuctx, ctx, current);
-	}
+	perf_event_sched_in(cpuctx, ctx, current);
 
 	perf_pmu_enable(cpuctx->ctx.pmu);
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
-
 done:
 	if (remove)
 		list_del_init(&cpuctx->rotation_list);
@@ -2445,10 +2454,22 @@ void perf_event_task_tick(void)
 {
 	struct list_head *head = &__get_cpu_var(rotation_list);
 	struct perf_cpu_context *cpuctx, *tmp;
+	struct perf_event_context *ctx;
+	int throttled;
 
 	WARN_ON(!irqs_disabled());
 
+	__this_cpu_inc(perf_throttled_seq);
+	throttled = __this_cpu_xchg(perf_throttled_count, 0);
+
 	list_for_each_entry_safe(cpuctx, tmp, head, rotation_list) {
+		ctx = &cpuctx->ctx;
+		perf_adjust_freq_unthr_context(ctx, throttled);
+
+		ctx = cpuctx->task_ctx;
+		if (ctx)
+			perf_adjust_freq_unthr_context(ctx, throttled);
+
 		if (cpuctx->jiffies_interval == 1 ||
 				!(jiffies % cpuctx->jiffies_interval))
 			perf_rotate_context(cpuctx);
@@ -4509,6 +4530,7 @@ static int __perf_event_overflow(struct perf_event *event,
 {
 	int events = atomic_read(&event->event_limit);
 	struct hw_perf_event *hwc = &event->hw;
+	u64 seq;
 	int ret = 0;
 
 	/*
@@ -4518,14 +4540,20 @@ static int __perf_event_overflow(struct perf_event *event,
 	if (unlikely(!is_sampling_event(event)))
 		return 0;
 
-	if (unlikely(hwc->interrupts >= max_samples_per_tick)) {
-		if (throttle) {
+	seq = __this_cpu_read(perf_throttled_seq);
+	if (seq != hwc->interrupts_seq) {
+		hwc->interrupts_seq = seq;
+		hwc->interrupts = 1;
+	} else {
+		hwc->interrupts++;
+		if (unlikely(throttle
+			     && hwc->interrupts >= max_samples_per_tick)) {
+			__this_cpu_inc(perf_throttled_count);
 			hwc->interrupts = MAX_INTERRUPTS;
 			perf_log_throttle(event, 0);
 			ret = 1;
 		}
-	} else
-		hwc->interrupts++;
+	}
 
 	if (event->attr.freq) {
 		u64 now = perf_clock();

kernel/exit.c

@@ -1038,6 +1038,22 @@ void do_exit(long code)
 	if (tsk->nr_dirtied)
 		__this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied);
 	exit_rcu();
+
+	/*
+	 * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
+	 * when the following two conditions become true.
+	 *   - There is race condition of mmap_sem (It is acquired by
+	 *     exit_mm()), and
+	 *   - SMI occurs before setting TASK_RUNINNG.
+	 *     (or hypervisor of virtual machine switches to other guest)
+	 *  As a result, we may become TASK_RUNNING after becoming TASK_DEAD
+	 *
+	 * To avoid it, we have to wait for releasing tsk->pi_lock which
+	 * is held by try_to_wake_up()
+	 */
+	smp_mb();
+	raw_spin_unlock_wait(&tsk->pi_lock);
+
 	/* causes final put_task_struct in finish_task_switch(). */
 	tsk->state = TASK_DEAD;
 	tsk->flags |= PF_NOFREEZE;	/* tell freezer to ignore us */