Merge branch 'linus' into irq/core

Reason: Get upstream fixes integrated before further modifications.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

12 files changed, 144 insertions, 55 deletions

diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index b7971d6f38b..ee706ce44aa 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -651,10 +651,10 @@ int __init init_hw_breakpoint(void)
 
  err_alloc:
 	for_each_possible_cpu(err_cpu) {
-		if (err_cpu == cpu)
-			break;
 		for (i = 0; i < TYPE_MAX; i++)
 			kfree(per_cpu(nr_task_bp_pinned[i], cpu));
+		if (err_cpu == cpu)
+			break;
 	}
 
 	return -ENOMEM;
diff --git a/kernel/fork.c b/kernel/fork.c
index b77fd559c78..26a7a6707fa 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -66,6 +66,7 @@
 #include <linux/user-return-notifier.h>
 #include <linux/oom.h>
 #include <linux/khugepaged.h>
+#include <linux/signalfd.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -667,6 +668,38 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 	return mm;
 }
 
+static void complete_vfork_done(struct task_struct *tsk)
+{
+	struct completion *vfork;
+
+	task_lock(tsk);
+	vfork = tsk->vfork_done;
+	if (likely(vfork)) {
+		tsk->vfork_done = NULL;
+		complete(vfork);
+	}
+	task_unlock(tsk);
+}
+
+static int wait_for_vfork_done(struct task_struct *child,
+				struct completion *vfork)
+{
+	int killed;
+
+	freezer_do_not_count();
+	killed = wait_for_completion_killable(vfork);
+	freezer_count();
+
+	if (killed) {
+		task_lock(child);
+		child->vfork_done = NULL;
+		task_unlock(child);
+	}
+
+	put_task_struct(child);
+	return killed;
+}
+
 /* Please note the differences between mmput and mm_release.
  * mmput is called whenever we stop holding onto a mm_struct,
  * error success whatever.
@@ -682,8 +715,6 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
  */
 void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 {
-	struct completion *vfork_done = tsk->vfork_done;
-
 	/* Get rid of any futexes when releasing the mm */
 #ifdef CONFIG_FUTEX
 	if (unlikely(tsk->robust_list)) {
@@ -703,17 +734,15 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 	/* Get rid of any cached register state */
 	deactivate_mm(tsk, mm);
 
-	/* notify parent sleeping on vfork() */
-	if (vfork_done) {
-		tsk->vfork_done = NULL;
-		complete(vfork_done);
-	}
+	if (tsk->vfork_done)
+		complete_vfork_done(tsk);
 
 	/*
 	 * If we're exiting normally, clear a user-space tid field if
 	 * requested.  We leave this alone when dying by signal, to leave
 	 * the value intact in a core dump, and to save the unnecessary
-	 * trouble otherwise.  Userland only wants this done for a sys_exit.
+	 * trouble, say, a killed vfork parent shouldn't touch this mm.
+	 * Userland only wants this done for a sys_exit.
 	 */
 	if (tsk->clear_child_tid) {
 		if (!(tsk->flags & PF_SIGNALED) &&
@@ -935,8 +964,10 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
 
 void __cleanup_sighand(struct sighand_struct *sighand)
 {
-	if (atomic_dec_and_test(&sighand->count))
+	if (atomic_dec_and_test(&sighand->count)) {
+		signalfd_cleanup(sighand);
 		kmem_cache_free(sighand_cachep, sighand);
+	}
 }
 
 
@@ -1015,7 +1046,6 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p)
 
 	new_flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
 	new_flags |= PF_FORKNOEXEC;
-	new_flags |= PF_STARTING;
 	p->flags = new_flags;
 }
 
@@ -1545,16 +1575,9 @@ long do_fork(unsigned long clone_flags,
 		if (clone_flags & CLONE_VFORK) {
 			p->vfork_done = &vfork;
 			init_completion(&vfork);
+			get_task_struct(p);
 		}
 
-		/*
-		 * We set PF_STARTING at creation in case tracing wants to
-		 * use this to distinguish a fully live task from one that
-		 * hasn't finished SIGSTOP raising yet.  Now we clear it
-		 * and set the child going.
-		 */
-		p->flags &= ~PF_STARTING;
-
 		wake_up_new_task(p);
 
 		/* forking complete and child started to run, tell ptracer */
@@ -1562,10 +1585,8 @@ long do_fork(unsigned long clone_flags,
 			ptrace_event(trace, nr);
 
 		if (clone_flags & CLONE_VFORK) {
-			freezer_do_not_count();
-			wait_for_completion(&vfork);
-			freezer_count();
-			ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
+			if (!wait_for_vfork_done(p, &vfork))
+				ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
 		}
 	} else {
 		nr = PTR_ERR(p);
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 2e48ec0c2e9..c21449f85a2 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -119,15 +119,20 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
  * For preemptible RCU it is sufficient to call rcu_read_unlock in order
  * to exit the grace period. For classic RCU, a reschedule is required.
  */
-static void rcu_lock_break(struct task_struct *g, struct task_struct *t)
+static bool rcu_lock_break(struct task_struct *g, struct task_struct *t)
 {
+	bool can_cont;
+
 	get_task_struct(g);
 	get_task_struct(t);
 	rcu_read_unlock();
 	cond_resched();
 	rcu_read_lock();
+	can_cont = pid_alive(g) && pid_alive(t);
 	put_task_struct(t);
 	put_task_struct(g);
+
+	return can_cont;
 }
 
 /*
@@ -154,9 +159,7 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
 			goto unlock;
 		if (!--batch_count) {
 			batch_count = HUNG_TASK_BATCHING;
-			rcu_lock_break(g, t);
-			/* Exit if t or g was unhashed during refresh. */
-			if (t->state == TASK_DEAD || g->state == TASK_DEAD)
+			if (!rcu_lock_break(g, t))
 				goto unlock;
 		}
 		/* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 342d8f44e40..0119b9d467a 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -53,7 +53,7 @@ unsigned long probe_irq_on(void)
 			if (desc->irq_data.chip->irq_set_type)
 				desc->irq_data.chip->irq_set_type(&desc->irq_data,
 							 IRQ_TYPE_PROBE);
-			irq_startup(desc);
+			irq_startup(desc, false);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
@@ -70,7 +70,7 @@ unsigned long probe_irq_on(void)
 		raw_spin_lock_irq(&desc->lock);
 		if (!desc->action && irq_settings_can_probe(desc)) {
 			desc->istate |= IRQS_AUTODETECT | IRQS_WAITING;
-			if (irq_startup(desc))
+			if (irq_startup(desc, false))
 				desc->istate |= IRQS_PENDING;
 		}
 		raw_spin_unlock_irq(&desc->lock);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 4dbc9c9d641..25784d630a1 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -156,19 +156,22 @@ static void irq_state_set_masked(struct irq_desc *desc)
 	irqd_set(&desc->irq_data, IRQD_IRQ_MASKED);
 }
 
-int irq_startup(struct irq_desc *desc)
+int irq_startup(struct irq_desc *desc, bool resend)
 {
+	int ret = 0;
+
 	irq_state_clr_disabled(desc);
 	desc->depth = 0;
 
 	if (desc->irq_data.chip->irq_startup) {
-		int ret = desc->irq_data.chip->irq_startup(&desc->irq_data);
+		ret = desc->irq_data.chip->irq_startup(&desc->irq_data);
 		irq_state_clr_masked(desc);
-		return ret;
+	} else {
+		irq_enable(desc);
 	}
-
-	irq_enable(desc);
-	return 0;
+	if (resend)
+		check_irq_resend(desc, desc->irq_data.irq);
+	return ret;
 }
 
 void irq_shutdown(struct irq_desc *desc)
@@ -329,6 +332,24 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(handle_simple_irq);
 
+/*
+ * Called unconditionally from handle_level_irq() and only for oneshot
+ * interrupts from handle_fasteoi_irq()
+ */
+static void cond_unmask_irq(struct irq_desc *desc)
+{
+	/*
+	 * We need to unmask in the following cases:
+	 * - Standard level irq (IRQF_ONESHOT is not set)
+	 * - Oneshot irq which did not wake the thread (caused by a
+	 *   spurious interrupt or a primary handler handling it
+	 *   completely).
+	 */
+	if (!irqd_irq_disabled(&desc->irq_data) &&
+	    irqd_irq_masked(&desc->irq_data) && !desc->threads_oneshot)
+		unmask_irq(desc);
+}
+
 /**
  *	handle_level_irq - Level type irq handler
  *	@irq:	the interrupt number
@@ -361,8 +382,8 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 
 	handle_irq_event(desc);
 
-	if (!irqd_irq_disabled(&desc->irq_data) && !(desc->istate & IRQS_ONESHOT))
-		unmask_irq(desc);
+	cond_unmask_irq(desc);
+
 out_unlock:
 	raw_spin_unlock(&desc->lock);
 }
@@ -416,6 +437,9 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 	preflow_handler(desc);
 	handle_irq_event(desc);
 
+	if (desc->istate & IRQS_ONESHOT)
+		cond_unmask_irq(desc);
+
 out_eoi:
 	desc->irq_data.chip->irq_eoi(&desc->irq_data);
 out_unlock:
@@ -624,7 +648,7 @@ __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		irq_settings_set_noprobe(desc);
 		irq_settings_set_norequest(desc);
 		irq_settings_set_nothread(desc);
-		irq_startup(desc);
+		irq_startup(desc, true);
 	}
 out:
 	irq_put_desc_busunlock(desc, flags);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 5c233e0ea2c..8e5c56b3b7d 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -65,7 +65,7 @@ extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 extern void __disable_irq(struct irq_desc *desc, unsigned int irq, bool susp);
 extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume);
 
-extern int irq_startup(struct irq_desc *desc);
+extern int irq_startup(struct irq_desc *desc, bool resend);
 extern void irq_shutdown(struct irq_desc *desc);
 extern void irq_enable(struct irq_desc *desc);
 extern void irq_disable(struct irq_desc *desc);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index a94466db73b..1786cf7dac5 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -979,6 +979,11 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 		/* add new interrupt at end of irq queue */
 		do {
+			/*
+			 * Or all existing action->thread_mask bits,
+			 * so we can find the next zero bit for this
+			 * new action.
+			 */
 			thread_mask |= old->thread_mask;
 			old_ptr = &old->next;
 			old = *old_ptr;
@@ -987,14 +992,41 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	}
 
 	/*
-	 * Setup the thread mask for this irqaction. Unlikely to have
-	 * 32 resp 64 irqs sharing one line, but who knows.
+	 * Setup the thread mask for this irqaction for ONESHOT. For
+	 * !ONESHOT irqs the thread mask is 0 so we can avoid a
+	 * conditional in irq_wake_thread().
 	 */
-	if (new->flags & IRQF_ONESHOT && thread_mask == ~0UL) {
-		ret = -EBUSY;
-		goto out_mask;
+	if (new->flags & IRQF_ONESHOT) {
+		/*
+		 * Unlikely to have 32 resp 64 irqs sharing one line,
+		 * but who knows.
+		 */
+		if (thread_mask == ~0UL) {
+			ret = -EBUSY;
+			goto out_mask;
+		}
+		/*
+		 * The thread_mask for the action is or'ed to
+		 * desc->thread_active to indicate that the
+		 * IRQF_ONESHOT thread handler has been woken, but not
+		 * yet finished. The bit is cleared when a thread
+		 * completes. When all threads of a shared interrupt
+		 * line have completed desc->threads_active becomes
+		 * zero and the interrupt line is unmasked. See
+		 * handle.c:irq_wake_thread() for further information.
+		 *
+		 * If no thread is woken by primary (hard irq context)
+		 * interrupt handlers, then desc->threads_active is
+		 * also checked for zero to unmask the irq line in the
+		 * affected hard irq flow handlers
+		 * (handle_[fasteoi|level]_irq).
+		 *
+		 * The new action gets the first zero bit of
+		 * thread_mask assigned. See the loop above which or's
+		 * all existing action->thread_mask bits.
+		 */
+		new->thread_mask = 1 << ffz(thread_mask);
 	}
-	new->thread_mask = 1 << ffz(thread_mask);
 
 	if (!shared) {
 		init_waitqueue_head(&desc->wait_for_threads);
@@ -1021,7 +1053,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 			desc->istate |= IRQS_ONESHOT;
 
 		if (irq_settings_can_autoenable(desc))
-			irq_startup(desc);
+			irq_startup(desc, true);
 		else
 			/* Undo nested disables: */
 			desc->depth = 1;
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 9788c0ec6f4..c62b8546cc9 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1334,8 +1334,10 @@ int __kprobes register_kprobe(struct kprobe *p)
 	if (!kernel_text_address((unsigned long) p->addr) ||
 	    in_kprobes_functions((unsigned long) p->addr) ||
 	    ftrace_text_reserved(p->addr, p->addr) ||
-	    jump_label_text_reserved(p->addr, p->addr))
-		goto fail_with_jump_label;
+	    jump_label_text_reserved(p->addr, p->addr)) {
+		ret = -EINVAL;
+		goto cannot_probe;
+	}
 
 	/* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */
 	p->flags &= KPROBE_FLAG_DISABLED;
@@ -1352,7 +1354,7 @@ int __kprobes register_kprobe(struct kprobe *p)
 		 * its code to prohibit unexpected unloading.
 		 */
 		if (unlikely(!try_module_get(probed_mod)))
-			goto fail_with_jump_label;
+			goto cannot_probe;
 
 		/*
 		 * If the module freed .init.text, we couldn't insert
@@ -1361,7 +1363,7 @@ int __kprobes register_kprobe(struct kprobe *p)
 		if (within_module_init((unsigned long)p->addr, probed_mod) &&
 		    probed_mod->state != MODULE_STATE_COMING) {
 			module_put(probed_mod);
-			goto fail_with_jump_label;
+			goto cannot_probe;
 		}
 		/* ret will be updated by following code */
 	}
@@ -1409,7 +1411,7 @@ out:
 
 	return ret;
 
-fail_with_jump_label:
+cannot_probe:
 	preempt_enable();
 	jump_label_unlock();
 	return ret;
diff --git a/kernel/pid.c b/kernel/pid.c
index ce8e00deacc..9f08dfabaf1 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -543,12 +543,12 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
  */
 void __init pidhash_init(void)
 {
-	int i, pidhash_size;
+	unsigned int i, pidhash_size;
 
 	pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18,
 					   HASH_EARLY | HASH_SMALL,
 					   &pidhash_shift, NULL, 4096);
-	pidhash_size = 1 << pidhash_shift;
+	pidhash_size = 1U << pidhash_shift;
 
 	for (i = 0; i < pidhash_size; i++)
 		INIT_HLIST_HEAD(&pid_hash[i]);
diff --git a/kernel/printk.c b/kernel/printk.c
index 13c0a1143f4..32690a0b7a1 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -702,6 +702,9 @@ static bool printk_time = 0;
 #endif
 module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR);
 
+static bool always_kmsg_dump;
+module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR);
+
 /* Check if we have any console registered that can be called early in boot. */
 static int have_callable_console(void)
 {
@@ -1732,6 +1735,9 @@ void kmsg_dump(enum kmsg_dump_reason reason)
 	unsigned long l1, l2;
 	unsigned long flags;
 
+	if ((reason > KMSG_DUMP_OOPS) && !always_kmsg_dump)
+		return;
+
 	/* Theoretically, the log could move on after we do this, but
 	   there's not a lot we can do about that. The new messages
 	   will overwrite the start of what we dump. */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5255c9d2e05..b342f57879e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1932,7 +1932,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	local_irq_enable();
 #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
 	finish_lock_switch(rq, prev);
-	trace_sched_stat_sleeptime(current, rq->clock);
 
 	fire_sched_in_preempt_notifiers(current);
 	if (mm)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7c6414fc669..aca16b843b7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1003,6 +1003,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		if (unlikely(delta > se->statistics.sleep_max))
 			se->statistics.sleep_max = delta;
 
+		se->statistics.sleep_start = 0;
 		se->statistics.sum_sleep_runtime += delta;
 
 		if (tsk) {
@@ -1019,6 +1020,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		if (unlikely(delta > se->statistics.block_max))
 			se->statistics.block_max = delta;
 
+		se->statistics.block_start = 0;
 		se->statistics.sum_sleep_runtime += delta;
 
 		if (tsk) {