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

6 files changed, 138 insertions, 70 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 22cc734aa1b2..faf073d0287f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -903,17 +903,14 @@ list_update_cgroup_event(struct perf_event *event,
 	 */
 	cpuctx = __get_cpu_context(ctx);
 
-	/* Only set/clear cpuctx->cgrp if current task uses event->cgrp. */
-	if (perf_cgroup_from_task(current, ctx) != event->cgrp) {
-		/*
-		 * We are removing the last cpu event in this context.
-		 * If that event is not active in this cpu, cpuctx->cgrp
-		 * should've been cleared by perf_cgroup_switch.
-		 */
-		WARN_ON_ONCE(!add && cpuctx->cgrp);
-		return;
-	}
-	cpuctx->cgrp = add ? event->cgrp : NULL;
+	/*
+	 * cpuctx->cgrp is NULL until a cgroup event is sched in or
+	 * ctx->nr_cgroup == 0 .
+	 */
+	if (add && perf_cgroup_from_task(current, ctx) == event->cgrp)
+		cpuctx->cgrp = event->cgrp;
+	else if (!add)
+		cpuctx->cgrp = NULL;
 }
 
 #else /* !CONFIG_CGROUP_PERF */
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 30e6d05aa5a9..3cbb0c879705 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -7,6 +7,7 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/printk.h>
+#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/vmalloc.h>
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 589d763a49b3..4d7ffc0a0d00 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -506,13 +506,13 @@ static void __print_lock_name(struct lock_class *class)
 	name = class->name;
 	if (!name) {
 		name = __get_key_name(class->key, str);
-		printk("%s", name);
+		printk(KERN_CONT "%s", name);
 	} else {
-		printk("%s", name);
+		printk(KERN_CONT "%s", name);
 		if (class->name_version > 1)
-			printk("#%d", class->name_version);
+			printk(KERN_CONT "#%d", class->name_version);
 		if (class->subclass)
-			printk("/%d", class->subclass);
+			printk(KERN_CONT "/%d", class->subclass);
 	}
 }
 
@@ -522,9 +522,9 @@ static void print_lock_name(struct lock_class *class)
 
 	get_usage_chars(class, usage);
 
-	printk(" (");
+	printk(KERN_CONT " (");
 	__print_lock_name(class);
-	printk("){%s}", usage);
+	printk(KERN_CONT "){%s}", usage);
 }
 
 static void print_lockdep_cache(struct lockdep_map *lock)
@@ -536,7 +536,7 @@ static void print_lockdep_cache(struct lockdep_map *lock)
 	if (!name)
 		name = __get_key_name(lock->key->subkeys, str);
 
-	printk("%s", name);
+	printk(KERN_CONT "%s", name);
 }
 
 static void print_lock(struct held_lock *hlock)
@@ -551,13 +551,13 @@ static void print_lock(struct held_lock *hlock)
 	barrier();
 
 	if (!class_idx || (class_idx - 1) >= MAX_LOCKDEP_KEYS) {
-		printk("<RELEASED>\n");
+		printk(KERN_CONT "<RELEASED>\n");
 		return;
 	}
 
 	print_lock_name(lock_classes + class_idx - 1);
-	printk(", at: ");
-	print_ip_sym(hlock->acquire_ip);
+	printk(KERN_CONT ", at: [<%p>] %pS\n",
+		(void *)hlock->acquire_ip, (void *)hlock->acquire_ip);
 }
 
 static void lockdep_print_held_locks(struct task_struct *curr)
@@ -792,8 +792,8 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 
 		printk("\nnew class %p: %s", class->key, class->name);
 		if (class->name_version > 1)
-			printk("#%d", class->name_version);
-		printk("\n");
+			printk(KERN_CONT "#%d", class->name_version);
+		printk(KERN_CONT "\n");
 		dump_stack();
 
 		if (!graph_lock()) {
@@ -1071,7 +1071,7 @@ print_circular_bug_entry(struct lock_list *target, int depth)
 		return 0;
 	printk("\n-> #%u", depth);
 	print_lock_name(target->class);
-	printk(":\n");
+	printk(KERN_CONT ":\n");
 	print_stack_trace(&target->trace, 6);
 
 	return 0;
@@ -1102,11 +1102,11 @@ print_circular_lock_scenario(struct held_lock *src,
 	if (parent != source) {
 		printk("Chain exists of:\n  ");
 		__print_lock_name(source);
-		printk(" --> ");
+		printk(KERN_CONT " --> ");
 		__print_lock_name(parent);
-		printk(" --> ");
+		printk(KERN_CONT " --> ");
 		__print_lock_name(target);
-		printk("\n\n");
+		printk(KERN_CONT "\n\n");
 	}
 
 	printk(" Possible unsafe locking scenario:\n\n");
@@ -1114,16 +1114,16 @@ print_circular_lock_scenario(struct held_lock *src,
 	printk("       ----                    ----\n");
 	printk("  lock(");
 	__print_lock_name(target);
-	printk(");\n");
+	printk(KERN_CONT ");\n");
 	printk("                               lock(");
 	__print_lock_name(parent);
-	printk(");\n");
+	printk(KERN_CONT ");\n");
 	printk("                               lock(");
 	__print_lock_name(target);
-	printk(");\n");
+	printk(KERN_CONT ");\n");
 	printk("  lock(");
 	__print_lock_name(source);
-	printk(");\n");
+	printk(KERN_CONT ");\n");
 	printk("\n *** DEADLOCK ***\n\n");
 }
 
@@ -1359,22 +1359,22 @@ static void print_lock_class_header(struct lock_class *class, int depth)
 
 	printk("%*s->", depth, "");
 	print_lock_name(class);
-	printk(" ops: %lu", class->ops);
-	printk(" {\n");
+	printk(KERN_CONT " ops: %lu", class->ops);
+	printk(KERN_CONT " {\n");
 
 	for (bit = 0; bit < LOCK_USAGE_STATES; bit++) {
 		if (class->usage_mask & (1 << bit)) {
 			int len = depth;
 
 			len += printk("%*s   %s", depth, "", usage_str[bit]);
-			len += printk(" at:\n");
+			len += printk(KERN_CONT " at:\n");
 			print_stack_trace(class->usage_traces + bit, len);
 		}
 	}
 	printk("%*s }\n", depth, "");
 
-	printk("%*s ... key      at: ",depth,"");
-	print_ip_sym((unsigned long)class->key);
+	printk("%*s ... key      at: [<%p>] %pS\n",
+		depth, "", class->key, class->key);
 }
 
 /*
@@ -1437,11 +1437,11 @@ print_irq_lock_scenario(struct lock_list *safe_entry,
 	if (middle_class != unsafe_class) {
 		printk("Chain exists of:\n  ");
 		__print_lock_name(safe_class);
-		printk(" --> ");
+		printk(KERN_CONT " --> ");
 		__print_lock_name(middle_class);
-		printk(" --> ");
+		printk(KERN_CONT " --> ");
 		__print_lock_name(unsafe_class);
-		printk("\n\n");
+		printk(KERN_CONT "\n\n");
 	}
 
 	printk(" Possible interrupt unsafe locking scenario:\n\n");
@@ -1449,18 +1449,18 @@ print_irq_lock_scenario(struct lock_list *safe_entry,
 	printk("       ----                    ----\n");
 	printk("  lock(");
 	__print_lock_name(unsafe_class);
-	printk(");\n");
+	printk(KERN_CONT ");\n");
 	printk("                               local_irq_disable();\n");
 	printk("                               lock(");
 	__print_lock_name(safe_class);
-	printk(");\n");
+	printk(KERN_CONT ");\n");
 	printk("                               lock(");
 	__print_lock_name(middle_class);
-	printk(");\n");
+	printk(KERN_CONT ");\n");
 	printk("  <Interrupt>\n");
 	printk("    lock(");
 	__print_lock_name(safe_class);
-	printk(");\n");
+	printk(KERN_CONT ");\n");
 	printk("\n *** DEADLOCK ***\n\n");
 }
 
@@ -1497,9 +1497,9 @@ print_bad_irq_dependency(struct task_struct *curr,
 	print_lock(prev);
 	printk("which would create a new lock dependency:\n");
 	print_lock_name(hlock_class(prev));
-	printk(" ->");
+	printk(KERN_CONT " ->");
 	print_lock_name(hlock_class(next));
-	printk("\n");
+	printk(KERN_CONT "\n");
 
 	printk("\nbut this new dependency connects a %s-irq-safe lock:\n",
 		irqclass);
@@ -1521,8 +1521,7 @@ print_bad_irq_dependency(struct task_struct *curr,
 
 	lockdep_print_held_locks(curr);
 
-	printk("\nthe dependencies between %s-irq-safe lock", irqclass);
-	printk(" and the holding lock:\n");
+	printk("\nthe dependencies between %s-irq-safe lock and the holding lock:\n", irqclass);
 	if (!save_trace(&prev_root->trace))
 		return 0;
 	print_shortest_lock_dependencies(backwards_entry, prev_root);
@@ -1694,10 +1693,10 @@ print_deadlock_scenario(struct held_lock *nxt,
 	printk("       ----\n");
 	printk("  lock(");
 	__print_lock_name(prev);
-	printk(");\n");
+	printk(KERN_CONT ");\n");
 	printk("  lock(");
 	__print_lock_name(next);
-	printk(");\n");
+	printk(KERN_CONT ");\n");
 	printk("\n *** DEADLOCK ***\n\n");
 	printk(" May be due to missing lock nesting notation\n\n");
 }
@@ -1891,9 +1890,9 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 		graph_unlock();
 		printk("\n new dependency: ");
 		print_lock_name(hlock_class(prev));
-		printk(" => ");
+		printk(KERN_CONT " => ");
 		print_lock_name(hlock_class(next));
-		printk("\n");
+		printk(KERN_CONT "\n");
 		dump_stack();
 		return graph_lock();
 	}
@@ -2343,11 +2342,11 @@ print_usage_bug_scenario(struct held_lock *lock)
 	printk("       ----\n");
 	printk("  lock(");
 	__print_lock_name(class);
-	printk(");\n");
+	printk(KERN_CONT ");\n");
 	printk("  <Interrupt>\n");
 	printk("    lock(");
 	__print_lock_name(class);
-	printk(");\n");
+	printk(KERN_CONT ");\n");
 	printk("\n *** DEADLOCK ***\n\n");
 }
 
@@ -2522,14 +2521,18 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this,
 void print_irqtrace_events(struct task_struct *curr)
 {
 	printk("irq event stamp: %u\n", curr->irq_events);
-	printk("hardirqs last  enabled at (%u): ", curr->hardirq_enable_event);
-	print_ip_sym(curr->hardirq_enable_ip);
-	printk("hardirqs last disabled at (%u): ", curr->hardirq_disable_event);
-	print_ip_sym(curr->hardirq_disable_ip);
-	printk("softirqs last  enabled at (%u): ", curr->softirq_enable_event);
-	print_ip_sym(curr->softirq_enable_ip);
-	printk("softirqs last disabled at (%u): ", curr->softirq_disable_event);
-	print_ip_sym(curr->softirq_disable_ip);
+	printk("hardirqs last  enabled at (%u): [<%p>] %pS\n",
+		curr->hardirq_enable_event, (void *)curr->hardirq_enable_ip,
+		(void *)curr->hardirq_enable_ip);
+	printk("hardirqs last disabled at (%u): [<%p>] %pS\n",
+		curr->hardirq_disable_event, (void *)curr->hardirq_disable_ip,
+		(void *)curr->hardirq_disable_ip);
+	printk("softirqs last  enabled at (%u): [<%p>] %pS\n",
+		curr->softirq_enable_event, (void *)curr->softirq_enable_ip,
+		(void *)curr->softirq_enable_ip);
+	printk("softirqs last disabled at (%u): [<%p>] %pS\n",
+		curr->softirq_disable_event, (void *)curr->softirq_disable_ip,
+		(void *)curr->softirq_disable_ip);
 }
 
 static int HARDIRQ_verbose(struct lock_class *class)
@@ -3235,8 +3238,8 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	if (very_verbose(class)) {
 		printk("\nacquire class [%p] %s", class->key, class->name);
 		if (class->name_version > 1)
-			printk("#%d", class->name_version);
-		printk("\n");
+			printk(KERN_CONT "#%d", class->name_version);
+		printk(KERN_CONT "\n");
 		dump_stack();
 	}
 
@@ -3378,7 +3381,7 @@ print_unlock_imbalance_bug(struct task_struct *curr, struct lockdep_map *lock,
 	printk("%s/%d is trying to release lock (",
 		curr->comm, task_pid_nr(curr));
 	print_lockdep_cache(lock);
-	printk(") at:\n");
+	printk(KERN_CONT ") at:\n");
 	print_ip_sym(ip);
 	printk("but there are no more locks to release!\n");
 	printk("\nother info that might help us debug this:\n");
@@ -3871,7 +3874,7 @@ print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock,
 	printk("%s/%d is trying to contend lock (",
 		curr->comm, task_pid_nr(curr));
 	print_lockdep_cache(lock);
-	printk(") at:\n");
+	printk(KERN_CONT ") at:\n");
 	print_ip_sym(ip);
 	printk("but there are no locks held!\n");
 	printk("\nother info that might help us debug this:\n");
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 1ec0f48962b3..2c49d76f96c3 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -65,8 +65,72 @@ static inline void clear_rt_mutex_waiters(struct rt_mutex *lock)
 
 static void fixup_rt_mutex_waiters(struct rt_mutex *lock)
 {
-	if (!rt_mutex_has_waiters(lock))
-		clear_rt_mutex_waiters(lock);
+	unsigned long owner, *p = (unsigned long *) &lock->owner;
+
+	if (rt_mutex_has_waiters(lock))
+		return;
+
+	/*
+	 * The rbtree has no waiters enqueued, now make sure that the
+	 * lock->owner still has the waiters bit set, otherwise the
+	 * following can happen:
+	 *
+	 * CPU 0	CPU 1		CPU2
+	 * l->owner=T1
+	 *		rt_mutex_lock(l)
+	 *		lock(l->lock)
+	 *		l->owner = T1 | HAS_WAITERS;
+	 *		enqueue(T2)
+	 *		boost()
+	 *		  unlock(l->lock)
+	 *		block()
+	 *
+	 *				rt_mutex_lock(l)
+	 *				lock(l->lock)
+	 *				l->owner = T1 | HAS_WAITERS;
+	 *				enqueue(T3)
+	 *				boost()
+	 *				  unlock(l->lock)
+	 *				block()
+	 *		signal(->T2)	signal(->T3)
+	 *		lock(l->lock)
+	 *		dequeue(T2)
+	 *		deboost()
+	 *		  unlock(l->lock)
+	 *				lock(l->lock)
+	 *				dequeue(T3)
+	 *				 ==> wait list is empty
+	 *				deboost()
+	 *				 unlock(l->lock)
+	 *		lock(l->lock)
+	 *		fixup_rt_mutex_waiters()
+	 *		  if (wait_list_empty(l) {
+	 *		    l->owner = owner
+	 *		    owner = l->owner & ~HAS_WAITERS;
+	 *		      ==> l->owner = T1
+	 *		  }
+	 *				lock(l->lock)
+	 * rt_mutex_unlock(l)		fixup_rt_mutex_waiters()
+	 *				  if (wait_list_empty(l) {
+	 *				    owner = l->owner & ~HAS_WAITERS;
+	 * cmpxchg(l->owner, T1, NULL)
+	 *  ===> Success (l->owner = NULL)
+	 *
+	 *				    l->owner = owner
+	 *				      ==> l->owner = T1
+	 *				  }
+	 *
+	 * With the check for the waiter bit in place T3 on CPU2 will not
+	 * overwrite. All tasks fiddling with the waiters bit are
+	 * serialized by l->lock, so nothing else can modify the waiters
+	 * bit. If the bit is set then nothing can change l->owner either
+	 * so the simple RMW is safe. The cmpxchg() will simply fail if it
+	 * happens in the middle of the RMW because the waiters bit is
+	 * still set.
+	 */
+	owner = READ_ONCE(*p);
+	if (owner & RT_MUTEX_HAS_WAITERS)
+		WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS);
 }
 
 /*
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 4f5f83c7d2d3..e317e1cbb3eb 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -75,8 +75,9 @@ task_top_pi_waiter(struct task_struct *p)
 
 static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
 {
-	return (struct task_struct *)
-		((unsigned long)lock->owner & ~RT_MUTEX_OWNER_MASKALL);
+	unsigned long owner = (unsigned long) READ_ONCE(lock->owner);
+
+	return (struct task_struct *) (owner & ~RT_MUTEX_OWNER_MASKALL);
 }
 
 /*
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index f1c8fd566246..da39489d2d80 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -212,6 +212,7 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
 {
 	static unsigned long next = INITIAL_JIFFIES;
 	struct autogroup *ag;
+	unsigned long shares;
 	int err;
 
 	if (nice < MIN_NICE || nice > MAX_NICE)
@@ -230,9 +231,10 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
 
 	next = HZ / 10 + jiffies;
 	ag = autogroup_task_get(p);
+	shares = scale_load(sched_prio_to_weight[nice + 20]);
 
 	down_write(&ag->lock);
-	err = sched_group_set_shares(ag->tg, sched_prio_to_weight[nice + 20]);
+	err = sched_group_set_shares(ag->tg, shares);
 	if (!err)
 		ag->nice = nice;
 	up_write(&ag->lock);