Merge branches 'core-urgent-for-linus', 'perf-urgent-for-linus', 'sched-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
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 0c9fa27..b3b7332 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -145,13 +145,13 @@
 
 #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
 
 /*
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 1aae78f..4025fe4 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -252,7 +252,8 @@
 	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
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 6d728d9..17107bd 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -129,7 +129,7 @@
 	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 @@
 		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)) {
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 37a458b..d840e69 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -39,6 +39,14 @@
 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 @@
 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 @@
 			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 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 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);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9d74824..f0b4caf 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -673,7 +673,7 @@
 
 	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 @@
 		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);
 }
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 0885561..abb2776 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -587,6 +587,7 @@
 	u64				sample_period;
 	u64				last_period;
 	local64_t			period_left;
+	u64                             interrupts_seq;
 	u64				interrupts;
 
 	u64				freq_time_stamp;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 32b48c8..ba36013 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2300,6 +2300,9 @@
 	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_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;
@@ -2344,13 +2360,8 @@
 
 		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);
 		}
@@ -2358,14 +2369,26 @@
 		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);
 }
 
 /*
@@ -2388,16 +2411,13 @@
  */
 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;
@@ -2405,37 +2425,26 @@
 		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);
-	}
+	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
+	if (ctx)
+		ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);
 
-	if (rotate) {
-		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 @@
 {
 	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 @@
 {
 	int events = atomic_read(&event->event_limit);
 	struct hw_perf_event *hwc = &event->hw;
+	u64 seq;
 	int ret = 0;
 
 	/*
@@ -4518,14 +4540,20 @@
 	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();
diff --git a/kernel/exit.c b/kernel/exit.c
index 294b170..4b4042f 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1038,6 +1038,22 @@
 	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 */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index df00cb0..5255c9d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -74,6 +74,7 @@
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
+#include <asm/mutex.h>
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #endif
@@ -723,9 +724,6 @@
 	p->sched_class->dequeue_task(rq, p, flags);
 }
 
-/*
- * activate_task - move a task to the runqueue.
- */
 void activate_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (task_contributes_to_load(p))
@@ -734,9 +732,6 @@
 	enqueue_task(rq, p, flags);
 }
 
-/*
- * deactivate_task - remove a task from the runqueue.
- */
 void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (task_contributes_to_load(p))
@@ -4134,7 +4129,7 @@
 	on_rq = p->on_rq;
 	running = task_current(rq, p);
 	if (on_rq)
-		deactivate_task(rq, p, 0);
+		dequeue_task(rq, p, 0);
 	if (running)
 		p->sched_class->put_prev_task(rq, p);
 
@@ -4147,7 +4142,7 @@
 	if (running)
 		p->sched_class->set_curr_task(rq);
 	if (on_rq)
-		activate_task(rq, p, 0);
+		enqueue_task(rq, p, 0);
 
 	check_class_changed(rq, p, prev_class, oldprio);
 	task_rq_unlock(rq, p, &flags);
@@ -4998,9 +4993,9 @@
 	 * placed properly.
 	 */
 	if (p->on_rq) {
-		deactivate_task(rq_src, p, 0);
+		dequeue_task(rq_src, p, 0);
 		set_task_cpu(p, dest_cpu);
-		activate_task(rq_dest, p, 0);
+		enqueue_task(rq_dest, p, 0);
 		check_preempt_curr(rq_dest, p, 0);
 	}
 done:
@@ -7032,10 +7027,10 @@
 
 	on_rq = p->on_rq;
 	if (on_rq)
-		deactivate_task(rq, p, 0);
+		dequeue_task(rq, p, 0);
 	__setscheduler(rq, p, SCHED_NORMAL, 0);
 	if (on_rq) {
-		activate_task(rq, p, 0);
+		enqueue_task(rq, p, 0);
 		resched_task(rq->curr);
 	}
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 84adb2d..7c6414f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4866,6 +4866,15 @@
 	return;
 }
 
+static inline void clear_nohz_tick_stopped(int cpu)
+{
+	if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) {
+		cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
+		atomic_dec(&nohz.nr_cpus);
+		clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
+	}
+}
+
 static inline void set_cpu_sd_state_busy(void)
 {
 	struct sched_domain *sd;
@@ -4904,6 +4913,12 @@
 {
 	int cpu = smp_processor_id();
 
+	/*
+	 * If this cpu is going down, then nothing needs to be done.
+	 */
+	if (!cpu_active(cpu))
+		return;
+
 	if (stop_tick) {
 		if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))
 			return;
@@ -4914,6 +4929,18 @@
 	}
 	return;
 }
+
+static int __cpuinit sched_ilb_notifier(struct notifier_block *nfb,
+					unsigned long action, void *hcpu)
+{
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_DYING:
+		clear_nohz_tick_stopped(smp_processor_id());
+		return NOTIFY_OK;
+	default:
+		return NOTIFY_DONE;
+	}
+}
 #endif
 
 static DEFINE_SPINLOCK(balancing);
@@ -5070,11 +5097,7 @@
 	* busy tick after returning from idle, we will update the busy stats.
 	*/
 	set_cpu_sd_state_busy();
-	if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) {
-		clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
-		cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
-		atomic_dec(&nohz.nr_cpus);
-	}
+	clear_nohz_tick_stopped(cpu);
 
 	/*
 	 * None are in tickless mode and hence no need for NOHZ idle load
@@ -5590,6 +5613,7 @@
 
 #ifdef CONFIG_NO_HZ
 	zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
+	cpu_notifier(sched_ilb_notifier, 0);
 #endif
 #endif /* SMP */
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 3640ebb..f42ae7f 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1587,6 +1587,11 @@
 	if (!next_task)
 		return 0;
 
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+       if (unlikely(task_running(rq, next_task)))
+               return 0;
+#endif
+
 retry:
 	if (unlikely(next_task == rq->curr)) {
 		WARN_ON(1);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 1d7bca7..d117262 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -296,7 +296,7 @@
 		if (__this_cpu_read(soft_watchdog_warn) == true)
 			return HRTIMER_RESTART;
 
-		printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
+		printk(KERN_EMERG "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
 			smp_processor_id(), duration,
 			current->comm, task_pid_nr(current));
 		print_modules();
diff --git a/lib/bug.c b/lib/bug.c
index 1955209..a28c141 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -169,7 +169,7 @@
 		return BUG_TRAP_TYPE_WARN;
 	}
 
-	printk(KERN_EMERG "------------[ cut here ]------------\n");
+	printk(KERN_DEFAULT "------------[ cut here ]------------\n");
 
 	if (file)
 		printk(KERN_CRIT "kernel BUG at %s:%u!\n",
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index ac86d67..7c12650 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -104,7 +104,7 @@
 
 CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 EXTLIBS = -lpthread -lrt -lelf -lm
-ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
+ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 ALL_LDFLAGS = $(LDFLAGS)
 STRIP ?= strip
 
@@ -168,10 +168,7 @@
 
 ### --- END CONFIGURATION SECTION ---
 
-# Those must not be GNU-specific; they are shared with perl/ which may
-# be built by a different compiler. (Note that this is an artifact now
-# but it still might be nice to keep that distinction.)
-BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include
+BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 BASIC_LDFLAGS =
 
 # Guard against environment variables
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 59d43ab..fb85661 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -20,7 +20,6 @@
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  */
-#define _GNU_SOURCE
 #include <sys/utsname.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -31,7 +30,6 @@
 #include <stdlib.h>
 #include <string.h>
 
-#undef _GNU_SOURCE
 #include "perf.h"
 #include "builtin.h"
 #include "util/util.h"
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 8f80df8..dd162aa 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -89,8 +89,6 @@
 
 static void perf_top__update_print_entries(struct perf_top *top)
 {
-	top->print_entries = top->winsize.ws_row;
-
 	if (top->print_entries > 9)
 		top->print_entries -= 9;
 }
@@ -100,6 +98,13 @@
 	struct perf_top *top = arg;
 
 	get_term_dimensions(&top->winsize);
+	if (!top->print_entries
+	    || (top->print_entries+4) > top->winsize.ws_row) {
+		top->print_entries = top->winsize.ws_row;
+	} else {
+		top->print_entries += 4;
+		top->winsize.ws_row = top->print_entries;
+	}
 	perf_top__update_print_entries(top);
 }
 
@@ -453,8 +458,10 @@
 				};
 				perf_top__sig_winch(SIGWINCH, NULL, top);
 				sigaction(SIGWINCH, &act, NULL);
-			} else
+			} else {
+				perf_top__sig_winch(SIGWINCH, NULL, top);
 				signal(SIGWINCH, SIG_DFL);
+			}
 			break;
 		case 'E':
 			if (top->evlist->nr_entries > 1) {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 3e7e0b0..ecd7f4d 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2105,7 +2105,7 @@
 	strncpy(ev.event_type.event_type.name, name, MAX_EVENT_NAME - 1);
 
 	ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE;
-	size = strlen(name);
+	size = strlen(ev.event_type.event_type.name);
 	size = ALIGN(size, sizeof(u64));
 	ev.event_type.header.size = sizeof(ev.event_type) -
 		(sizeof(ev.event_type.event_type.name) - size);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index eb25900..29cb654 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -19,7 +19,6 @@
  *
  */
 
-#define _GNU_SOURCE
 #include <sys/utsname.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -33,7 +32,6 @@
 #include <limits.h>
 #include <elf.h>
 
-#undef _GNU_SOURCE
 #include "util.h"
 #include "event.h"
 #include "string.h"
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 215d50f..0975438 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1,4 +1,3 @@
-#define _GNU_SOURCE
 #include <ctype.h>
 #include <dirent.h>
 #include <errno.h>
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 6c164dc..1a8d4dc 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -21,14 +21,13 @@
  *  The parts for function graph printing was taken and modified from the
  *  Linux Kernel that were written by Frederic Weisbecker.
  */
-#define _GNU_SOURCE
+
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <ctype.h>
 #include <errno.h>
 
-#undef _GNU_SOURCE
 #include "../perf.h"
 #include "util.h"
 #include "trace-event.h"
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index 1212a38..e81aef1 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -1,6 +1,4 @@
-#define _GNU_SOURCE
 #include <stdio.h>
-#undef _GNU_SOURCE
 #include "../libslang.h"
 #include <stdlib.h>
 #include <string.h>
diff --git a/tools/perf/util/ui/helpline.c b/tools/perf/util/ui/helpline.c
index 6ef3c56..4f48f59 100644
--- a/tools/perf/util/ui/helpline.c
+++ b/tools/perf/util/ui/helpline.c
@@ -1,4 +1,3 @@
-#define _GNU_SOURCE
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index b9c530c..ecf9898 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -40,7 +40,6 @@
 #define decimal_length(x)	((int)(sizeof(x) * 2.56 + 0.5) + 1)
 
 #define _ALL_SOURCE 1
-#define _GNU_SOURCE 1
 #define _BSD_SOURCE 1
 #define HAS_BOOL