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

Conflicts:
	drivers/net/usb/asix_common.c
	drivers/net/usb/sr9800.c
	drivers/net/usb/usbnet.c
	include/linux/usb/usbnet.h
	net/ipv4/tcp_ipv4.c
	net/ipv6/tcp_ipv6.c

The TCP conflicts were overlapping changes.  In 'net' we added a
READ_ONCE() to the socket cached RX route read, whilst in 'net-next'
Eric Dumazet touched the surrounding code dealing with how mini
sockets are handled.

With USB, it's a case of the same bug fix first going into net-next
and then I cherry picked it back into net.

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

7 files changed, 94 insertions, 34 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 453ef61311d4..2fabc0627165 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4574,6 +4574,13 @@ static void perf_pending_event(struct irq_work *entry)
 {
 	struct perf_event *event = container_of(entry,
 			struct perf_event, pending);
+	int rctx;
+
+	rctx = perf_swevent_get_recursion_context();
+	/*
+	 * If we 'fail' here, that's OK, it means recursion is already disabled
+	 * and we won't recurse 'further'.
+	 */
 
 	if (event->pending_disable) {
 		event->pending_disable = 0;
@@ -4584,6 +4591,9 @@ static void perf_pending_event(struct irq_work *entry)
 		event->pending_wakeup = 0;
 		perf_event_wakeup(event);
 	}
+
+	if (rctx >= 0)
+		perf_swevent_put_recursion_context(rctx);
 }
 
 /*
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 88d0d4420ad2..ba77ab5f64dd 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -633,7 +633,7 @@ static int count_matching_names(struct lock_class *new_class)
 	if (!new_class->name)
 		return 0;
 
-	list_for_each_entry(class, &all_lock_classes, lock_entry) {
+	list_for_each_entry_rcu(class, &all_lock_classes, lock_entry) {
 		if (new_class->key - new_class->subclass == class->key)
 			return class->name_version;
 		if (class->name && !strcmp(class->name, new_class->name))
@@ -700,10 +700,12 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
 	hash_head = classhashentry(key);
 
 	/*
-	 * We can walk the hash lockfree, because the hash only
-	 * grows, and we are careful when adding entries to the end:
+	 * We do an RCU walk of the hash, see lockdep_free_key_range().
 	 */
-	list_for_each_entry(class, hash_head, hash_entry) {
+	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
+		return NULL;
+
+	list_for_each_entry_rcu(class, hash_head, hash_entry) {
 		if (class->key == key) {
 			/*
 			 * Huh! same key, different name? Did someone trample
@@ -728,7 +730,8 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	struct lockdep_subclass_key *key;
 	struct list_head *hash_head;
 	struct lock_class *class;
-	unsigned long flags;
+
+	DEBUG_LOCKS_WARN_ON(!irqs_disabled());
 
 	class = look_up_lock_class(lock, subclass);
 	if (likely(class))
@@ -750,28 +753,26 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	key = lock->key->subkeys + subclass;
 	hash_head = classhashentry(key);
 
-	raw_local_irq_save(flags);
 	if (!graph_lock()) {
-		raw_local_irq_restore(flags);
 		return NULL;
 	}
 	/*
 	 * We have to do the hash-walk again, to avoid races
 	 * with another CPU:
 	 */
-	list_for_each_entry(class, hash_head, hash_entry)
+	list_for_each_entry_rcu(class, hash_head, hash_entry) {
 		if (class->key == key)
 			goto out_unlock_set;
+	}
+
 	/*
 	 * Allocate a new key from the static array, and add it to
 	 * the hash:
 	 */
 	if (nr_lock_classes >= MAX_LOCKDEP_KEYS) {
 		if (!debug_locks_off_graph_unlock()) {
-			raw_local_irq_restore(flags);
 			return NULL;
 		}
-		raw_local_irq_restore(flags);
 
 		print_lockdep_off("BUG: MAX_LOCKDEP_KEYS too low!");
 		dump_stack();
@@ -798,7 +799,6 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 
 	if (verbose(class)) {
 		graph_unlock();
-		raw_local_irq_restore(flags);
 
 		printk("\nnew class %p: %s", class->key, class->name);
 		if (class->name_version > 1)
@@ -806,15 +806,12 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 		printk("\n");
 		dump_stack();
 
-		raw_local_irq_save(flags);
 		if (!graph_lock()) {
-			raw_local_irq_restore(flags);
 			return NULL;
 		}
 	}
 out_unlock_set:
 	graph_unlock();
-	raw_local_irq_restore(flags);
 
 out_set_class_cache:
 	if (!subclass || force)
@@ -870,11 +867,9 @@ static int add_lock_to_list(struct lock_class *class, struct lock_class *this,
 	entry->distance = distance;
 	entry->trace = *trace;
 	/*
-	 * Since we never remove from the dependency list, the list can
-	 * be walked lockless by other CPUs, it's only allocation
-	 * that must be protected by the spinlock. But this also means
-	 * we must make new entries visible only once writes to the
-	 * entry become visible - hence the RCU op:
+	 * Both allocation and removal are done under the graph lock; but
+	 * iteration is under RCU-sched; see look_up_lock_class() and
+	 * lockdep_free_key_range().
 	 */
 	list_add_tail_rcu(&entry->entry, head);
 
@@ -1025,7 +1020,9 @@ static int __bfs(struct lock_list *source_entry,
 		else
 			head = &lock->class->locks_before;
 
-		list_for_each_entry(entry, head, entry) {
+		DEBUG_LOCKS_WARN_ON(!irqs_disabled());
+
+		list_for_each_entry_rcu(entry, head, entry) {
 			if (!lock_accessed(entry)) {
 				unsigned int cq_depth;
 				mark_lock_accessed(entry, lock);
@@ -2022,7 +2019,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
 	 * We can walk it lock-free, because entries only get added
 	 * to the hash:
 	 */
-	list_for_each_entry(chain, hash_head, entry) {
+	list_for_each_entry_rcu(chain, hash_head, entry) {
 		if (chain->chain_key == chain_key) {
 cache_hit:
 			debug_atomic_inc(chain_lookup_hits);
@@ -2996,8 +2993,18 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name,
 	if (unlikely(!debug_locks))
 		return;
 
-	if (subclass)
+	if (subclass) {
+		unsigned long flags;
+
+		if (DEBUG_LOCKS_WARN_ON(current->lockdep_recursion))
+			return;
+
+		raw_local_irq_save(flags);
+		current->lockdep_recursion = 1;
 		register_lock_class(lock, subclass, 1);
+		current->lockdep_recursion = 0;
+		raw_local_irq_restore(flags);
+	}
 }
 EXPORT_SYMBOL_GPL(lockdep_init_map);
 
@@ -3887,9 +3894,17 @@ static inline int within(const void *addr, void *start, unsigned long size)
 	return addr >= start && addr < start + size;
 }
 
+/*
+ * Used in module.c to remove lock classes from memory that is going to be
+ * freed; and possibly re-used by other modules.
+ *
+ * We will have had one sync_sched() before getting here, so we're guaranteed
+ * nobody will look up these exact classes -- they're properly dead but still
+ * allocated.
+ */
 void lockdep_free_key_range(void *start, unsigned long size)
 {
-	struct lock_class *class, *next;
+	struct lock_class *class;
 	struct list_head *head;
 	unsigned long flags;
 	int i;
@@ -3905,7 +3920,7 @@ void lockdep_free_key_range(void *start, unsigned long size)
 		head = classhash_table + i;
 		if (list_empty(head))
 			continue;
-		list_for_each_entry_safe(class, next, head, hash_entry) {
+		list_for_each_entry_rcu(class, head, hash_entry) {
 			if (within(class->key, start, size))
 				zap_class(class);
 			else if (within(class->name, start, size))
@@ -3916,11 +3931,25 @@ void lockdep_free_key_range(void *start, unsigned long size)
 	if (locked)
 		graph_unlock();
 	raw_local_irq_restore(flags);
+
+	/*
+	 * Wait for any possible iterators from look_up_lock_class() to pass
+	 * before continuing to free the memory they refer to.
+	 *
+	 * sync_sched() is sufficient because the read-side is IRQ disable.
+	 */
+	synchronize_sched();
+
+	/*
+	 * XXX at this point we could return the resources to the pool;
+	 * instead we leak them. We would need to change to bitmap allocators
+	 * instead of the linear allocators we have now.
+	 */
 }
 
 void lockdep_reset_lock(struct lockdep_map *lock)
 {
-	struct lock_class *class, *next;
+	struct lock_class *class;
 	struct list_head *head;
 	unsigned long flags;
 	int i, j;
@@ -3948,7 +3977,7 @@ void lockdep_reset_lock(struct lockdep_map *lock)
 		head = classhash_table + i;
 		if (list_empty(head))
 			continue;
-		list_for_each_entry_safe(class, next, head, hash_entry) {
+		list_for_each_entry_rcu(class, head, hash_entry) {
 			int match = 0;
 
 			for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
diff --git a/kernel/module.c b/kernel/module.c
index b3d634ed06c9..99fdf94efce8 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1865,7 +1865,7 @@ static void free_module(struct module *mod)
 	kfree(mod->args);
 	percpu_modfree(mod);
 
-	/* Free lock-classes: */
+	/* Free lock-classes; relies on the preceding sync_rcu(). */
 	lockdep_free_key_range(mod->module_core, mod->core_size);
 
 	/* Finally, free the core (containing the module structure) */
@@ -3349,9 +3349,6 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	module_bug_cleanup(mod);
 	mutex_unlock(&module_mutex);
 
-	/* Free lock-classes: */
-	lockdep_free_key_range(mod->module_core, mod->core_size);
-
 	/* we can't deallocate the module until we clear memory protection */
 	unset_module_init_ro_nx(mod);
 	unset_module_core_ro_nx(mod);
@@ -3375,6 +3372,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	synchronize_rcu();
 	mutex_unlock(&module_mutex);
  free_module:
+	/* Free lock-classes; relies on the preceding sync_rcu() */
+	lockdep_free_key_range(mod->module_core, mod->core_size);
+
 	module_deallocate(mod, info);
  free_copy:
 	free_copy(info);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f0f831e8a345..62671f53202a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3034,6 +3034,8 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	} else {
 		if (dl_prio(oldprio))
 			p->dl.dl_boosted = 0;
+		if (rt_prio(oldprio))
+			p->rt.timeout = 0;
 		p->sched_class = &fair_sched_class;
 	}
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7ce18f3c097a..bcfe32088b37 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1609,9 +1609,11 @@ static void update_task_scan_period(struct task_struct *p,
 	/*
 	 * If there were no record hinting faults then either the task is
 	 * completely idle or all activity is areas that are not of interest
-	 * to automatic numa balancing. Scan slower
+	 * to automatic numa balancing. Related to that, if there were failed
+	 * migration then it implies we are migrating too quickly or the local
+	 * node is overloaded. In either case, scan slower
 	 */
-	if (local + shared == 0) {
+	if (local + shared == 0 || p->numa_faults_locality[2]) {
 		p->numa_scan_period = min(p->numa_scan_period_max,
 			p->numa_scan_period << 1);
 
@@ -2080,6 +2082,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 
 	if (migrated)
 		p->numa_pages_migrated += pages;
+	if (flags & TNF_MIGRATE_FAIL)
+		p->numa_faults_locality[2] += pages;
 
 	p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages;
 	p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 88ea2d6e0031..ce410bb9f2e1 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1228,6 +1228,14 @@ static struct ctl_table vm_table[] = {
 		.extra1		= &zero,
 	},
 	{
+		.procname	= "dirtytime_expire_seconds",
+		.data		= &dirtytime_expire_interval,
+		.maxlen		= sizeof(dirty_expire_interval),
+		.mode		= 0644,
+		.proc_handler	= dirtytime_interval_handler,
+		.extra1		= &zero,
+	},
+	{
 		.procname       = "nr_pdflush_threads",
 		.mode           = 0444 /* read-only */,
 		.proc_handler   = pdflush_proc_obsolete,
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index eb682d5c697c..6aac4beedbbe 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -49,6 +49,7 @@ static void bc_set_mode(enum clock_event_mode mode,
  */
 static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
 {
+	int bc_moved;
 	/*
 	 * We try to cancel the timer first. If the callback is on
 	 * flight on some other cpu then we let it handle it. If we
@@ -60,9 +61,15 @@ static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
 	 * restart the timer because we are in the callback, but we
 	 * can set the expiry time and let the callback return
 	 * HRTIMER_RESTART.
+	 *
+	 * Since we are in the idle loop at this point and because
+	 * hrtimer_{start/cancel} functions call into tracing,
+	 * calls to these functions must be bound within RCU_NONIDLE.
 	 */
-	if (hrtimer_try_to_cancel(&bctimer) >= 0) {
-		hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED);
+	RCU_NONIDLE(bc_moved = (hrtimer_try_to_cancel(&bctimer) >= 0) ?
+		!hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED) :
+			0);
+	if (bc_moved) {
 		/* Bind the "device" to the cpu */
 		bc->bound_on = smp_processor_id();
 	} else if (bc->bound_on == smp_processor_id()) {