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

7 files changed, 169 insertions, 86 deletions

diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index e6a9c36470ee..82b8b18ee1eb 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1726,25 +1726,14 @@ static int irq_domain_debug_show(struct seq_file *m, void *p)
 	irq_domain_debug_show_one(m, d, 0);
 	return 0;
 }
-
-static int irq_domain_debug_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, irq_domain_debug_show, inode->i_private);
-}
-
-static const struct file_operations dfs_domain_ops = {
-	.open		= irq_domain_debug_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(irq_domain_debug);
 
 static void debugfs_add_domain_dir(struct irq_domain *d)
 {
 	if (!d->name || !domain_dir || d->debugfs_file)
 		return;
 	d->debugfs_file = debugfs_create_file(d->name, 0444, domain_dir, d,
-					      &dfs_domain_ops);
+					      &irq_domain_debug_fops);
 }
 
 static void debugfs_remove_domain_dir(struct irq_domain *d)
@@ -1760,7 +1749,8 @@ void __init irq_domain_debugfs_init(struct dentry *root)
 	if (!domain_dir)
 		return;
 
-	debugfs_create_file("default", 0444, domain_dir, NULL, &dfs_domain_ops);
+	debugfs_create_file("default", 0444, domain_dir, NULL,
+			    &irq_domain_debug_fops);
 	mutex_lock(&irq_domain_mutex);
 	list_for_each_entry(d, &irq_domain_list, link)
 		debugfs_add_domain_dir(d);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index da2ccf142358..102160ff5c66 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -978,67 +978,90 @@ static int prepare_kprobe(struct kprobe *p)
 }
 
 /* Caller must lock kprobe_mutex */
-static void arm_kprobe_ftrace(struct kprobe *p)
+static int arm_kprobe_ftrace(struct kprobe *p)
 {
-	int ret;
+	int ret = 0;
 
 	ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
 				   (unsigned long)p->addr, 0, 0);
-	WARN(ret < 0, "Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret);
-	kprobe_ftrace_enabled++;
-	if (kprobe_ftrace_enabled == 1) {
+	if (ret) {
+		pr_debug("Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret);
+		return ret;
+	}
+
+	if (kprobe_ftrace_enabled == 0) {
 		ret = register_ftrace_function(&kprobe_ftrace_ops);
-		WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret);
+		if (ret) {
+			pr_debug("Failed to init kprobe-ftrace (%d)\n", ret);
+			goto err_ftrace;
+		}
 	}
+
+	kprobe_ftrace_enabled++;
+	return ret;
+
+err_ftrace:
+	/*
+	 * Note: Since kprobe_ftrace_ops has IPMODIFY set, and ftrace requires a
+	 * non-empty filter_hash for IPMODIFY ops, we're safe from an accidental
+	 * empty filter_hash which would undesirably trace all functions.
+	 */
+	ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 1, 0);
+	return ret;
 }
 
 /* Caller must lock kprobe_mutex */
-static void disarm_kprobe_ftrace(struct kprobe *p)
+static int disarm_kprobe_ftrace(struct kprobe *p)
 {
-	int ret;
+	int ret = 0;
 
-	kprobe_ftrace_enabled--;
-	if (kprobe_ftrace_enabled == 0) {
+	if (kprobe_ftrace_enabled == 1) {
 		ret = unregister_ftrace_function(&kprobe_ftrace_ops);
-		WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret);
+		if (WARN(ret < 0, "Failed to unregister kprobe-ftrace (%d)\n", ret))
+			return ret;
 	}
+
+	kprobe_ftrace_enabled--;
+
 	ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
 			   (unsigned long)p->addr, 1, 0);
 	WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret);
+	return ret;
 }
 #else	/* !CONFIG_KPROBES_ON_FTRACE */
 #define prepare_kprobe(p)	arch_prepare_kprobe(p)
-#define arm_kprobe_ftrace(p)	do {} while (0)
-#define disarm_kprobe_ftrace(p)	do {} while (0)
+#define arm_kprobe_ftrace(p)	(-ENODEV)
+#define disarm_kprobe_ftrace(p)	(-ENODEV)
 #endif
 
 /* Arm a kprobe with text_mutex */
-static void arm_kprobe(struct kprobe *kp)
+static int arm_kprobe(struct kprobe *kp)
 {
-	if (unlikely(kprobe_ftrace(kp))) {
-		arm_kprobe_ftrace(kp);
-		return;
-	}
+	if (unlikely(kprobe_ftrace(kp)))
+		return arm_kprobe_ftrace(kp);
+
 	cpus_read_lock();
 	mutex_lock(&text_mutex);
 	__arm_kprobe(kp);
 	mutex_unlock(&text_mutex);
 	cpus_read_unlock();
+
+	return 0;
 }
 
 /* Disarm a kprobe with text_mutex */
-static void disarm_kprobe(struct kprobe *kp, bool reopt)
+static int disarm_kprobe(struct kprobe *kp, bool reopt)
 {
-	if (unlikely(kprobe_ftrace(kp))) {
-		disarm_kprobe_ftrace(kp);
-		return;
-	}
+	if (unlikely(kprobe_ftrace(kp)))
+		return disarm_kprobe_ftrace(kp);
 
 	cpus_read_lock();
 	mutex_lock(&text_mutex);
 	__disarm_kprobe(kp, reopt);
 	mutex_unlock(&text_mutex);
 	cpus_read_unlock();
+
+	return 0;
 }
 
 /*
@@ -1362,9 +1385,15 @@ out:
 
 	if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) {
 		ap->flags &= ~KPROBE_FLAG_DISABLED;
-		if (!kprobes_all_disarmed)
+		if (!kprobes_all_disarmed) {
 			/* Arm the breakpoint again. */
-			arm_kprobe(ap);
+			ret = arm_kprobe(ap);
+			if (ret) {
+				ap->flags |= KPROBE_FLAG_DISABLED;
+				list_del_rcu(&p->list);
+				synchronize_sched();
+			}
+		}
 	}
 	return ret;
 }
@@ -1573,8 +1602,14 @@ int register_kprobe(struct kprobe *p)
 	hlist_add_head_rcu(&p->hlist,
 		       &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]);
 
-	if (!kprobes_all_disarmed && !kprobe_disabled(p))
-		arm_kprobe(p);
+	if (!kprobes_all_disarmed && !kprobe_disabled(p)) {
+		ret = arm_kprobe(p);
+		if (ret) {
+			hlist_del_rcu(&p->hlist);
+			synchronize_sched();
+			goto out;
+		}
+	}
 
 	/* Try to optimize kprobe */
 	try_to_optimize_kprobe(p);
@@ -1608,11 +1643,12 @@ static int aggr_kprobe_disabled(struct kprobe *ap)
 static struct kprobe *__disable_kprobe(struct kprobe *p)
 {
 	struct kprobe *orig_p;
+	int ret;
 
 	/* Get an original kprobe for return */
 	orig_p = __get_valid_kprobe(p);
 	if (unlikely(orig_p == NULL))
-		return NULL;
+		return ERR_PTR(-EINVAL);
 
 	if (!kprobe_disabled(p)) {
 		/* Disable probe if it is a child probe */
@@ -1626,8 +1662,13 @@ static struct kprobe *__disable_kprobe(struct kprobe *p)
 			 * should have already been disarmed, so
 			 * skip unneed disarming process.
 			 */
-			if (!kprobes_all_disarmed)
-				disarm_kprobe(orig_p, true);
+			if (!kprobes_all_disarmed) {
+				ret = disarm_kprobe(orig_p, true);
+				if (ret) {
+					p->flags &= ~KPROBE_FLAG_DISABLED;
+					return ERR_PTR(ret);
+				}
+			}
 			orig_p->flags |= KPROBE_FLAG_DISABLED;
 		}
 	}
@@ -1644,8 +1685,8 @@ static int __unregister_kprobe_top(struct kprobe *p)
 
 	/* Disable kprobe. This will disarm it if needed. */
 	ap = __disable_kprobe(p);
-	if (ap == NULL)
-		return -EINVAL;
+	if (IS_ERR(ap))
+		return PTR_ERR(ap);
 
 	if (ap == p)
 		/*
@@ -2078,12 +2119,14 @@ static void kill_kprobe(struct kprobe *p)
 int disable_kprobe(struct kprobe *kp)
 {
 	int ret = 0;
+	struct kprobe *p;
 
 	mutex_lock(&kprobe_mutex);
 
 	/* Disable this kprobe */
-	if (__disable_kprobe(kp) == NULL)
-		ret = -EINVAL;
+	p = __disable_kprobe(kp);
+	if (IS_ERR(p))
+		ret = PTR_ERR(p);
 
 	mutex_unlock(&kprobe_mutex);
 	return ret;
@@ -2116,7 +2159,9 @@ int enable_kprobe(struct kprobe *kp)
 
 	if (!kprobes_all_disarmed && kprobe_disabled(p)) {
 		p->flags &= ~KPROBE_FLAG_DISABLED;
-		arm_kprobe(p);
+		ret = arm_kprobe(p);
+		if (ret)
+			p->flags |= KPROBE_FLAG_DISABLED;
 	}
 out:
 	mutex_unlock(&kprobe_mutex);
@@ -2407,11 +2452,12 @@ static const struct file_operations debugfs_kprobe_blacklist_ops = {
 	.release        = seq_release,
 };
 
-static void arm_all_kprobes(void)
+static int arm_all_kprobes(void)
 {
 	struct hlist_head *head;
 	struct kprobe *p;
-	unsigned int i;
+	unsigned int i, total = 0, errors = 0;
+	int err, ret = 0;
 
 	mutex_lock(&kprobe_mutex);
 
@@ -2428,46 +2474,74 @@ static void arm_all_kprobes(void)
 	/* Arming kprobes doesn't optimize kprobe itself */
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
-		hlist_for_each_entry_rcu(p, head, hlist)
-			if (!kprobe_disabled(p))
-				arm_kprobe(p);
+		/* Arm all kprobes on a best-effort basis */
+		hlist_for_each_entry_rcu(p, head, hlist) {
+			if (!kprobe_disabled(p)) {
+				err = arm_kprobe(p);
+				if (err)  {
+					errors++;
+					ret = err;
+				}
+				total++;
+			}
+		}
 	}
 
-	printk(KERN_INFO "Kprobes globally enabled\n");
+	if (errors)
+		pr_warn("Kprobes globally enabled, but failed to arm %d out of %d probes\n",
+			errors, total);
+	else
+		pr_info("Kprobes globally enabled\n");
 
 already_enabled:
 	mutex_unlock(&kprobe_mutex);
-	return;
+	return ret;
 }
 
-static void disarm_all_kprobes(void)
+static int disarm_all_kprobes(void)
 {
 	struct hlist_head *head;
 	struct kprobe *p;
-	unsigned int i;
+	unsigned int i, total = 0, errors = 0;
+	int err, ret = 0;
 
 	mutex_lock(&kprobe_mutex);
 
 	/* If kprobes are already disarmed, just return */
 	if (kprobes_all_disarmed) {
 		mutex_unlock(&kprobe_mutex);
-		return;
+		return 0;
 	}
 
 	kprobes_all_disarmed = true;
-	printk(KERN_INFO "Kprobes globally disabled\n");
 
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
+		/* Disarm all kprobes on a best-effort basis */
 		hlist_for_each_entry_rcu(p, head, hlist) {
-			if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p))
-				disarm_kprobe(p, false);
+			if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) {
+				err = disarm_kprobe(p, false);
+				if (err) {
+					errors++;
+					ret = err;
+				}
+				total++;
+			}
 		}
 	}
+
+	if (errors)
+		pr_warn("Kprobes globally disabled, but failed to disarm %d out of %d probes\n",
+			errors, total);
+	else
+		pr_info("Kprobes globally disabled\n");
+
 	mutex_unlock(&kprobe_mutex);
 
 	/* Wait for disarming all kprobes by optimizer */
 	wait_for_kprobe_optimizer();
+
+	return ret;
 }
 
 /*
@@ -2494,6 +2568,7 @@ static ssize_t write_enabled_file_bool(struct file *file,
 {
 	char buf[32];
 	size_t buf_size;
+	int ret = 0;
 
 	buf_size = min(count, (sizeof(buf)-1));
 	if (copy_from_user(buf, user_buf, buf_size))
@@ -2504,17 +2579,20 @@ static ssize_t write_enabled_file_bool(struct file *file,
 	case 'y':
 	case 'Y':
 	case '1':
-		arm_all_kprobes();
+		ret = arm_all_kprobes();
 		break;
 	case 'n':
 	case 'N':
 	case '0':
-		disarm_all_kprobes();
+		ret = disarm_all_kprobes();
 		break;
 	default:
 		return -EINVAL;
 	}
 
+	if (ret)
+		return ret;
+
 	return count;
 }
 
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 38ece035039e..d880296245c5 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -379,6 +379,14 @@ queue:
 	tail = encode_tail(smp_processor_id(), idx);
 
 	node += idx;
+
+	/*
+	 * Ensure that we increment the head node->count before initialising
+	 * the actual node. If the compiler is kind enough to reorder these
+	 * stores, then an IRQ could overwrite our assignments.
+	 */
+	barrier();
+
 	node->locked = 0;
 	node->next = NULL;
 	pv_init_node(node);
@@ -408,14 +416,15 @@ queue:
 	 */
 	if (old & _Q_TAIL_MASK) {
 		prev = decode_tail(old);
+
 		/*
-		 * The above xchg_tail() is also a load of @lock which
-		 * generates, through decode_tail(), a pointer.  The address
-		 * dependency matches the RELEASE of xchg_tail() such that
-		 * the subsequent access to @prev happens after.
+		 * We must ensure that the stores to @node are observed before
+		 * the write to prev->next. The address dependency from
+		 * xchg_tail is not sufficient to ensure this because the read
+		 * component of xchg_tail is unordered with respect to the
+		 * initialisation of @node.
 		 */
-
-		WRITE_ONCE(prev->next, node);
+		smp_store_release(&prev->next, node);
 
 		pv_wait_node(node, prev);
 		arch_mcs_spin_lock_contended(&node->locked);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bf724c1952ea..e7c535eee0a6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2601,19 +2601,31 @@ static inline void finish_task(struct task_struct *prev)
 #endif
 }
 
-static inline void finish_lock_switch(struct rq *rq)
+static inline void
+prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf)
 {
+	/*
+	 * Since the runqueue lock will be released by the next
+	 * task (which is an invalid locking op but in the case
+	 * of the scheduler it's an obvious special-case), so we
+	 * do an early lockdep release here:
+	 */
+	rq_unpin_lock(rq, rf);
+	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
 #ifdef CONFIG_DEBUG_SPINLOCK
 	/* this is a valid case when another task releases the spinlock */
-	rq->lock.owner = current;
+	rq->lock.owner = next;
 #endif
+}
+
+static inline void finish_lock_switch(struct rq *rq)
+{
 	/*
 	 * If we are tracking spinlock dependencies then we have to
 	 * fix up the runqueue lock - which gets 'carried over' from
 	 * prev into current:
 	 */
 	spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
-
 	raw_spin_unlock_irq(&rq->lock);
 }
 
@@ -2844,14 +2856,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 
 	rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
 
-	/*
-	 * Since the runqueue lock will be released by the next
-	 * task (which is an invalid locking op but in the case
-	 * of the scheduler it's an obvious special-case), so we
-	 * do an early lockdep release here:
-	 */
-	rq_unpin_lock(rq, rf);
-	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
+	prepare_lock_switch(rq, next, rf);
 
 	/* Here we just switch the register state and the stack. */
 	switch_to(prev, next, prev);
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index dd062a1c8cf0..7936f548e071 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -19,8 +19,6 @@
 
 #include "sched.h"
 
-#define SUGOV_KTHREAD_PRIORITY	50
-
 struct sugov_tunables {
 	struct gov_attr_set attr_set;
 	unsigned int rate_limit_us;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 9bb0e0c412ec..9df09782025c 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1153,6 +1153,7 @@ static void update_curr_dl(struct rq *rq)
 	struct sched_dl_entity *dl_se = &curr->dl;
 	u64 delta_exec, scaled_delta_exec;
 	int cpu = cpu_of(rq);
+	u64 now;
 
 	if (!dl_task(curr) || !on_dl_rq(dl_se))
 		return;
@@ -1165,7 +1166,8 @@ static void update_curr_dl(struct rq *rq)
 	 * natural solution, but the full ramifications of this
 	 * approach need further study.
 	 */
-	delta_exec = rq_clock_task(rq) - curr->se.exec_start;
+	now = rq_clock_task(rq);
+	delta_exec = now - curr->se.exec_start;
 	if (unlikely((s64)delta_exec <= 0)) {
 		if (unlikely(dl_se->dl_yielded))
 			goto throttle;
@@ -1178,7 +1180,7 @@ static void update_curr_dl(struct rq *rq)
 	curr->se.sum_exec_runtime += delta_exec;
 	account_group_exec_runtime(curr, delta_exec);
 
-	curr->se.exec_start = rq_clock_task(rq);
+	curr->se.exec_start = now;
 	cgroup_account_cputime(curr, delta_exec);
 
 	sched_rt_avg_update(rq, delta_exec);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 663b2355a3aa..aad49451584e 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -950,12 +950,13 @@ static void update_curr_rt(struct rq *rq)
 {
 	struct task_struct *curr = rq->curr;
 	struct sched_rt_entity *rt_se = &curr->rt;
-	u64 now = rq_clock_task(rq);
 	u64 delta_exec;
+	u64 now;
 
 	if (curr->sched_class != &rt_sched_class)
 		return;
 
+	now = rq_clock_task(rq);
 	delta_exec = now - curr->se.exec_start;
 	if (unlikely((s64)delta_exec <= 0))
 		return;