Merge tag 'v3.4-rc5' into next

Linux 3.4-rc5

Merge to pull in prerequisite change for Smack:
86812bb0de

Requested by Casey.

kernel/cred.c

@@ -386,6 +386,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 	struct cred *new;
 	int ret;
 
+	p->replacement_session_keyring = NULL;
+
 	if (
 #ifdef CONFIG_KEYS
 		!p->cred->thread_keyring &&

kernel/events/core.c

@@ -3183,7 +3183,7 @@ static void perf_event_for_each(struct perf_event *event,
 	perf_event_for_each_child(event, func);
 	func(event);
 	list_for_each_entry(sibling, &event->sibling_list, group_entry)
-		perf_event_for_each_child(event, func);
+		perf_event_for_each_child(sibling, func);
 	mutex_unlock(&ctx->mutex);
 }
 

kernel/irq/Kconfig

@@ -62,7 +62,7 @@ config IRQ_DOMAIN_DEBUG
 	help
 	  This option will show the mapping relationship between hardware irq
 	  numbers and Linux irq numbers. The mapping is exposed via debugfs
-	  in the file "virq_mapping".
+	  in the file "irq_domain_mapping".
 
 	  If you don't know what this means you don't need it.
 

kernel/irq/debug.h

@@ -4,10 +4,10 @@
 
 #include <linux/kallsyms.h>
 
-#define P(f) if (desc->status_use_accessors & f) printk("%14s set\n", #f)
-#define PS(f) if (desc->istate & f) printk("%14s set\n", #f)
+#define ___P(f) if (desc->status_use_accessors & f) printk("%14s set\n", #f)
+#define ___PS(f) if (desc->istate & f) printk("%14s set\n", #f)
 /* FIXME */
-#define PD(f) do { } while (0)
+#define ___PD(f) do { } while (0)
 
 static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 {
@@ -23,23 +23,23 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 		print_symbol("%s\n", (unsigned long)desc->action->handler);
 	}
 
-	P(IRQ_LEVEL);
-	P(IRQ_PER_CPU);
-	P(IRQ_NOPROBE);
-	P(IRQ_NOREQUEST);
-	P(IRQ_NOTHREAD);
-	P(IRQ_NOAUTOEN);
+	___P(IRQ_LEVEL);
+	___P(IRQ_PER_CPU);
+	___P(IRQ_NOPROBE);
+	___P(IRQ_NOREQUEST);
+	___P(IRQ_NOTHREAD);
+	___P(IRQ_NOAUTOEN);
 
-	PS(IRQS_AUTODETECT);
-	PS(IRQS_REPLAY);
-	PS(IRQS_WAITING);
-	PS(IRQS_PENDING);
+	___PS(IRQS_AUTODETECT);
+	___PS(IRQS_REPLAY);
+	___PS(IRQS_WAITING);
+	___PS(IRQS_PENDING);
 
-	PD(IRQS_INPROGRESS);
-	PD(IRQS_DISABLED);
-	PD(IRQS_MASKED);
+	___PD(IRQS_INPROGRESS);
+	___PD(IRQS_DISABLED);
+	___PD(IRQS_MASKED);
 }
 
-#undef P
-#undef PS
-#undef PD
+#undef ___P
+#undef ___PS
+#undef ___PD

kernel/irq/irqdomain.c

@@ -23,7 +23,6 @@ static LIST_HEAD(irq_domain_list);
 static DEFINE_MUTEX(irq_domain_mutex);
 
 static DEFINE_MUTEX(revmap_trees_mutex);
-static unsigned int irq_virq_count = NR_IRQS;
 static struct irq_domain *irq_default_domain;
 
 /**
@@ -184,13 +183,16 @@ struct irq_domain *irq_domain_add_linear(struct device_node *of_node,
 }
 
 struct irq_domain *irq_domain_add_nomap(struct device_node *of_node,
+					 unsigned int max_irq,
 					 const struct irq_domain_ops *ops,
 					 void *host_data)
 {
 	struct irq_domain *domain = irq_domain_alloc(of_node,
 					IRQ_DOMAIN_MAP_NOMAP, ops, host_data);
-	if (domain)
+	if (domain) {
+		domain->revmap_data.nomap.max_irq = max_irq ? max_irq : ~0;
 		irq_domain_add(domain);
+	}
 	return domain;
 }
 
@@ -262,22 +264,6 @@ void irq_set_default_host(struct irq_domain *domain)
 	irq_default_domain = domain;
 }
 
-/**
- * irq_set_virq_count() - Set the maximum number of linux irqs
- * @count: number of linux irqs, capped with NR_IRQS
- *
- * This is mainly for use by platforms like iSeries who want to program
- * the virtual irq number in the controller to avoid the reverse mapping
- */
-void irq_set_virq_count(unsigned int count)
-{
-	pr_debug("irq: Trying to set virq count to %d\n", count);
-
-	BUG_ON(count < NUM_ISA_INTERRUPTS);
-	if (count < NR_IRQS)
-		irq_virq_count = count;
-}
-
 static int irq_setup_virq(struct irq_domain *domain, unsigned int virq,
 			    irq_hw_number_t hwirq)
 {
@@ -320,13 +306,12 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
 		pr_debug("irq: create_direct virq allocation failed\n");
 		return 0;
 	}
-	if (virq >= irq_virq_count) {
+	if (virq >= domain->revmap_data.nomap.max_irq) {
 		pr_err("ERROR: no free irqs available below %i maximum\n",
-			irq_virq_count);
+			domain->revmap_data.nomap.max_irq);
 		irq_free_desc(virq);
 		return 0;
 	}
-
 	pr_debug("irq: create_direct obtained virq %d\n", virq);
 
 	if (irq_setup_virq(domain, virq, virq)) {
@@ -350,7 +335,8 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
 unsigned int irq_create_mapping(struct irq_domain *domain,
 				irq_hw_number_t hwirq)
 {
-	unsigned int virq, hint;
+	unsigned int hint;
+	int virq;
 
 	pr_debug("irq: irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq);
 
@@ -377,13 +363,13 @@ unsigned int irq_create_mapping(struct irq_domain *domain,
 		return irq_domain_legacy_revmap(domain, hwirq);
 
 	/* Allocate a virtual interrupt number */
-	hint = hwirq % irq_virq_count;
+	hint = hwirq % nr_irqs;
 	if (hint == 0)
 		hint++;
 	virq = irq_alloc_desc_from(hint, 0);
-	if (!virq)
+	if (virq <= 0)
 		virq = irq_alloc_desc_from(1, 0);
-	if (!virq) {
+	if (virq <= 0) {
 		pr_debug("irq: -> virq allocation failed\n");
 		return 0;
 	}
@@ -515,7 +501,7 @@ unsigned int irq_find_mapping(struct irq_domain *domain,
 			      irq_hw_number_t hwirq)
 {
 	unsigned int i;
-	unsigned int hint = hwirq % irq_virq_count;
+	unsigned int hint = hwirq % nr_irqs;
 
 	/* Look for default domain if nececssary */
 	if (domain == NULL)
@@ -536,7 +522,7 @@ unsigned int irq_find_mapping(struct irq_domain *domain,
 		if (data && (data->domain == domain) && (data->hwirq == hwirq))
 			return i;
 		i++;
-		if (i >= irq_virq_count)
+		if (i >= nr_irqs)
 			i = 1;
 	} while(i != hint);
 	return 0;
@@ -642,8 +628,9 @@ static int virq_debug_show(struct seq_file *m, void *private)
 	void *data;
 	int i;
 
-	seq_printf(m, "%-5s  %-7s  %-15s  %-18s  %s\n", "virq", "hwirq",
-		      "chip name", "chip data", "domain name");
+	seq_printf(m, "%-5s  %-7s  %-15s  %-*s  %s\n", "irq", "hwirq",
+		      "chip name", (int)(2 * sizeof(void *) + 2), "chip data",
+		      "domain name");
 
 	for (i = 1; i < nr_irqs; i++) {
 		desc = irq_to_desc(i);
@@ -666,7 +653,7 @@ static int virq_debug_show(struct seq_file *m, void *private)
 			seq_printf(m, "%-15s  ", p);
 
 			data = irq_desc_get_chip_data(desc);
-			seq_printf(m, "0x%16p  ", data);
+			seq_printf(m, data ? "0x%p  " : "  %p  ", data);
 
 			if (desc->irq_data.domain && desc->irq_data.domain->of_node)
 				p = desc->irq_data.domain->of_node->full_name;

kernel/irq_work.c

@@ -11,6 +11,7 @@
 #include <linux/irq_work.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
+#include <linux/irqflags.h>
 #include <asm/processor.h>
 
 /*

kernel/itimer.c

@@ -284,8 +284,12 @@ SYSCALL_DEFINE3(setitimer, int, which, struct itimerval __user *, value,
 	if (value) {
 		if(copy_from_user(&set_buffer, value, sizeof(set_buffer)))
 			return -EFAULT;
-	} else
-		memset((char *) &set_buffer, 0, sizeof(set_buffer));
+	} else {
+		memset(&set_buffer, 0, sizeof(set_buffer));
+		printk_once(KERN_WARNING "%s calls setitimer() with new_value NULL pointer."
+			    " Misfeature support will be removed\n",
+			    current->comm);
+	}
 
 	error = do_setitimer(which, &set_buffer, ovalue ? &get_buffer : NULL);
 	if (error || !ovalue)

kernel/panic.c

@@ -97,7 +97,7 @@ void panic(const char *fmt, ...)
 	/*
 	 * Avoid nested stack-dumping if a panic occurs during oops processing
 	 */
-	if (!oops_in_progress)
+	if (!test_taint(TAINT_DIE) && oops_in_progress <= 1)
 		dump_stack();
 #endif
 

kernel/power/swap.c

@@ -51,6 +51,23 @@
 
 #define MAP_PAGE_ENTRIES	(PAGE_SIZE / sizeof(sector_t) - 1)
 
+/*
+ * Number of free pages that are not high.
+ */
+static inline unsigned long low_free_pages(void)
+{
+	return nr_free_pages() - nr_free_highpages();
+}
+
+/*
+ * Number of pages required to be kept free while writing the image. Always
+ * half of all available low pages before the writing starts.
+ */
+static inline unsigned long reqd_free_pages(void)
+{
+	return low_free_pages() / 2;
+}
+
 struct swap_map_page {
 	sector_t entries[MAP_PAGE_ENTRIES];
 	sector_t next_swap;
@@ -72,7 +89,7 @@ struct swap_map_handle {
 	sector_t cur_swap;
 	sector_t first_sector;
 	unsigned int k;
-	unsigned long nr_free_pages, written;
+	unsigned long reqd_free_pages;
 	u32 crc32;
 };
 
@@ -316,8 +333,7 @@ static int get_swap_writer(struct swap_map_handle *handle)
 		goto err_rel;
 	}
 	handle->k = 0;
-	handle->nr_free_pages = nr_free_pages() >> 1;
-	handle->written = 0;
+	handle->reqd_free_pages = reqd_free_pages();
 	handle->first_sector = handle->cur_swap;
 	return 0;
 err_rel:
@@ -352,11 +368,11 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf,
 		handle->cur_swap = offset;
 		handle->k = 0;
 	}
-	if (bio_chain && ++handle->written > handle->nr_free_pages) {
+	if (bio_chain && low_free_pages() <= handle->reqd_free_pages) {
 		error = hib_wait_on_bio_chain(bio_chain);
 		if (error)
 			goto out;
-		handle->written = 0;
+		handle->reqd_free_pages = reqd_free_pages();
 	}
  out:
 	return error;
@@ -618,7 +634,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
 	 * Adjust number of free pages after all allocations have been done.
 	 * We don't want to run out of pages when writing.
 	 */
-	handle->nr_free_pages = nr_free_pages() >> 1;
+	handle->reqd_free_pages = reqd_free_pages();
 
 	/*
 	 * Start the CRC32 thread.

kernel/rcutree.c

@@ -1820,7 +1820,6 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	 * a quiescent state betweentimes.
 	 */
 	local_irq_save(flags);
-	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
 	rdp = this_cpu_ptr(rsp->rda);
 
 	/* Add the callback to our list. */

kernel/sched/core.c

@@ -6405,16 +6405,26 @@ static void __sdt_free(const struct cpumask *cpu_map)
 		struct sd_data *sdd = &tl->data;
 
 		for_each_cpu(j, cpu_map) {
-			struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j);
-			if (sd && (sd->flags & SD_OVERLAP))
-				free_sched_groups(sd->groups, 0);
-			kfree(*per_cpu_ptr(sdd->sd, j));
-			kfree(*per_cpu_ptr(sdd->sg, j));
-			kfree(*per_cpu_ptr(sdd->sgp, j));
+			struct sched_domain *sd;
+
+			if (sdd->sd) {
+				sd = *per_cpu_ptr(sdd->sd, j);
+				if (sd && (sd->flags & SD_OVERLAP))
+					free_sched_groups(sd->groups, 0);
+				kfree(*per_cpu_ptr(sdd->sd, j));
+			}
+
+			if (sdd->sg)
+				kfree(*per_cpu_ptr(sdd->sg, j));
+			if (sdd->sgp)
+				kfree(*per_cpu_ptr(sdd->sgp, j));
 		}
 		free_percpu(sdd->sd);
+		sdd->sd = NULL;
 		free_percpu(sdd->sg);
+		sdd->sg = NULL;
 		free_percpu(sdd->sgp);
+		sdd->sgp = NULL;
 	}
 }
 

kernel/sched/fair.c

@@ -784,7 +784,7 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		update_load_add(&rq_of(cfs_rq)->load, se->load.weight);
 #ifdef CONFIG_SMP
 	if (entity_is_task(se))
-		list_add_tail(&se->group_node, &rq_of(cfs_rq)->cfs_tasks);
+		list_add(&se->group_node, &rq_of(cfs_rq)->cfs_tasks);
 #endif
 	cfs_rq->nr_running++;
 }
@@ -3215,6 +3215,8 @@ static int move_one_task(struct lb_env *env)
 
 static unsigned long task_h_load(struct task_struct *p);
 
+static const unsigned int sched_nr_migrate_break = 32;
+
 /*
  * move_tasks tries to move up to load_move weighted load from busiest to
  * this_rq, as part of a balancing operation within domain "sd".
@@ -3242,7 +3244,7 @@ static int move_tasks(struct lb_env *env)
 
 		/* take a breather every nr_migrate tasks */
 		if (env->loop > env->loop_break) {
-			env->loop_break += sysctl_sched_nr_migrate;
+			env->loop_break += sched_nr_migrate_break;
 			env->flags |= LBF_NEED_BREAK;
 			break;
 		}
@@ -3252,7 +3254,7 @@ static int move_tasks(struct lb_env *env)
 
 		load = task_h_load(p);
 
-		if (load < 16 && !env->sd->nr_balance_failed)
+		if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
 			goto next;
 
 		if ((load / 2) > env->load_move)
@@ -4407,7 +4409,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		.dst_cpu	= this_cpu,
 		.dst_rq		= this_rq,
 		.idle		= idle,
-		.loop_break	= sysctl_sched_nr_migrate,
+		.loop_break	= sched_nr_migrate_break,
 	};
 
 	cpumask_copy(cpus, cpu_active_mask);
@@ -4445,10 +4447,10 @@ redo:
 		 * correctly treated as an imbalance.
 		 */
 		env.flags |= LBF_ALL_PINNED;
-		env.load_move = imbalance;
-		env.src_cpu = busiest->cpu;
-		env.src_rq = busiest;
-		env.loop_max = busiest->nr_running;
+		env.load_move	= imbalance;
+		env.src_cpu	= busiest->cpu;
+		env.src_rq	= busiest;
+		env.loop_max	= min_t(unsigned long, sysctl_sched_nr_migrate, busiest->nr_running);
 
 more_balance:
 		local_irq_save(flags);

kernel/sched/features.h

@@ -68,3 +68,4 @@ SCHED_FEAT(TTWU_QUEUE, true)
 
 SCHED_FEAT(FORCE_SD_OVERLAP, false)
 SCHED_FEAT(RT_RUNTIME_SHARE, true)
+SCHED_FEAT(LB_MIN, false)

kernel/time/Kconfig

@@ -1,6 +1,10 @@
 #
 # Timer subsystem related configuration options
 #
+
+# Core internal switch. Selected by NO_HZ / HIGH_RES_TIMERS. This is
+# only related to the tick functionality. Oneshot clockevent devices
+# are supported independ of this.
 config TICK_ONESHOT
 	bool
 

kernel/time/tick-broadcast.c

@@ -346,7 +346,8 @@ int tick_resume_broadcast(void)
 						     tick_get_broadcast_mask());
 			break;
 		case TICKDEV_MODE_ONESHOT:
-			broadcast = tick_resume_broadcast_oneshot(bc);
+			if (!cpumask_empty(tick_get_broadcast_mask()))
+				broadcast = tick_resume_broadcast_oneshot(bc);
 			break;
 		}
 	}
@@ -373,6 +374,9 @@ static int tick_broadcast_set_event(ktime_t expires, int force)
 {
 	struct clock_event_device *bc = tick_broadcast_device.evtdev;
 
+	if (bc->mode != CLOCK_EVT_MODE_ONESHOT)
+		clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+
 	return clockevents_program_event(bc, expires, force);
 }
 
@@ -531,7 +535,6 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 		int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
 
 		bc->event_handler = tick_handle_oneshot_broadcast;
-		clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
 
 		/* Take the do_timer update */
 		tick_do_timer_cpu = cpu;
@@ -549,6 +552,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 			   to_cpumask(tmpmask));
 
 		if (was_periodic && !cpumask_empty(to_cpumask(tmpmask))) {
+			clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
 			tick_broadcast_init_next_event(to_cpumask(tmpmask),
 						       tick_next_period);
 			tick_broadcast_set_event(tick_next_period, 1);
@@ -575,15 +579,12 @@ void tick_broadcast_switch_to_oneshot(void)
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
-	if (cpumask_empty(tick_get_broadcast_mask()))
-		goto end;
 
 	tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT;
 	bc = tick_broadcast_device.evtdev;
 	if (bc)
 		tick_broadcast_setup_oneshot(bc);
 
-end:
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 

kernel/time/tick-sched.c

@@ -534,9 +534,9 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
 				hrtimer_get_expires(&ts->sched_timer), 0))
 				break;
 		}
-		/* Update jiffies and reread time */
-		tick_do_update_jiffies64(now);
+		/* Reread time and update jiffies */
 		now = ktime_get();
+		tick_do_update_jiffies64(now);
 	}
 }
 

kernel/trace/trace.c

@@ -4629,7 +4629,8 @@ static ssize_t
 rb_simple_read(struct file *filp, char __user *ubuf,
 	       size_t cnt, loff_t *ppos)
 {
-	struct ring_buffer *buffer = filp->private_data;
+	struct trace_array *tr = filp->private_data;
+	struct ring_buffer *buffer = tr->buffer;
 	char buf[64];
 	int r;
 
@@ -4647,7 +4648,8 @@ static ssize_t
 rb_simple_write(struct file *filp, const char __user *ubuf,
 		size_t cnt, loff_t *ppos)
 {
-	struct ring_buffer *buffer = filp->private_data;
+	struct trace_array *tr = filp->private_data;
+	struct ring_buffer *buffer = tr->buffer;
 	unsigned long val;
 	int ret;
 
@@ -4734,7 +4736,7 @@ static __init int tracer_init_debugfs(void)
 			  &trace_clock_fops);
 
 	trace_create_file("tracing_on", 0644, d_tracer,
-			    global_trace.buffer, &rb_simple_fops);
+			    &global_trace, &rb_simple_fops);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 	trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,

kernel/trace/trace.h

@@ -836,11 +836,11 @@ extern const char *__stop___trace_bprintk_fmt[];
 		     filter)
 #include "trace_entries.h"
 
-#ifdef CONFIG_FUNCTION_TRACER
+#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_FUNCTION_TRACER)
 int perf_ftrace_event_register(struct ftrace_event_call *call,
 			       enum trace_reg type, void *data);
 #else
 #define perf_ftrace_event_register NULL
-#endif /* CONFIG_FUNCTION_TRACER */
+#endif
 
 #endif /* _LINUX_KERNEL_TRACE_H */

kernel/trace/trace_output.c

@@ -652,6 +652,8 @@ int trace_print_lat_context(struct trace_iterator *iter)
 {
 	u64 next_ts;
 	int ret;
+	/* trace_find_next_entry will reset ent_size */
+	int ent_size = iter->ent_size;
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *entry = iter->ent,
 			   *next_entry = trace_find_next_entry(iter, NULL,
@@ -660,6 +662,9 @@ int trace_print_lat_context(struct trace_iterator *iter)
 	unsigned long abs_usecs = ns2usecs(iter->ts - iter->tr->time_start);
 	unsigned long rel_usecs;
 
+	/* Restore the original ent_size */
+	iter->ent_size = ent_size;
+
 	if (!next_entry)
 		next_ts = iter->ts;
 	rel_usecs = ns2usecs(next_ts - iter->ts);