Merge 4.1-rc7 into driver-core-next

We want the fixes in this branch as well for testing and merge
resolution.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

kernel/compat.c

@@ -912,7 +912,8 @@ long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask,
 			 * bitmap. We must however ensure the end of the
 			 * kernel bitmap is zeroed.
 			 */
-			if (nr_compat_longs-- > 0) {
+			if (nr_compat_longs) {
+				nr_compat_longs--;
 				if (__get_user(um, umask))
 					return -EFAULT;
 			} else {
@@ -954,7 +955,8 @@ long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask,
 			 * We dont want to write past the end of the userspace
 			 * bitmap.
 			 */
-			if (nr_compat_longs-- > 0) {
+			if (nr_compat_longs) {
+				nr_compat_longs--;
 				if (__put_user(um, umask))
 					return -EFAULT;
 			}

kernel/events/core.c

@@ -3442,7 +3442,6 @@ static void free_event_rcu(struct rcu_head *head)
 	if (event->ns)
 		put_pid_ns(event->ns);
 	perf_event_free_filter(event);
-	perf_event_free_bpf_prog(event);
 	kfree(event);
 }
 
@@ -3573,6 +3572,8 @@ static void __free_event(struct perf_event *event)
 			put_callchain_buffers();
 	}
 
+	perf_event_free_bpf_prog(event);
+
 	if (event->destroy)
 		event->destroy(event);
 

kernel/events/ring_buffer.c

@@ -493,6 +493,20 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
 			rb->aux_pages[rb->aux_nr_pages] = page_address(page++);
 	}
 
+	/*
+	 * In overwrite mode, PMUs that don't support SG may not handle more
+	 * than one contiguous allocation, since they rely on PMI to do double
+	 * buffering. In this case, the entire buffer has to be one contiguous
+	 * chunk.
+	 */
+	if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG) &&
+	    overwrite) {
+		struct page *page = virt_to_page(rb->aux_pages[0]);
+
+		if (page_private(page) != max_order)
+			goto out;
+	}
+
 	rb->aux_priv = event->pmu->setup_aux(event->cpu, rb->aux_pages, nr_pages,
 					     overwrite);
 	if (!rb->aux_priv)

kernel/module.c

@@ -3380,6 +3380,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	module_bug_cleanup(mod);
 	mutex_unlock(&module_mutex);
 
+	blocking_notifier_call_chain(&module_notify_list,
+				     MODULE_STATE_GOING, mod);
+
 	/* we can't deallocate the module until we clear memory protection */
 	unset_module_init_ro_nx(mod);
 	unset_module_core_ro_nx(mod);

kernel/sched/core.c

@@ -4389,10 +4389,7 @@ long __sched io_schedule_timeout(long timeout)
 	long ret;
 
 	current->in_iowait = 1;
-	if (old_iowait)
-		blk_schedule_flush_plug(current);
-	else
-		blk_flush_plug(current);
+	blk_schedule_flush_plug(current);
 
 	delayacct_blkio_start();
 	rq = raw_rq();

kernel/time/hrtimer.c

@@ -266,21 +266,23 @@ lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
 /*
  * Divide a ktime value by a nanosecond value
  */
-u64 __ktime_divns(const ktime_t kt, s64 div)
+s64 __ktime_divns(const ktime_t kt, s64 div)
 {
-	u64 dclc;
 	int sft = 0;
+	s64 dclc;
+	u64 tmp;
 
 	dclc = ktime_to_ns(kt);
+	tmp = dclc < 0 ? -dclc : dclc;
+
 	/* Make sure the divisor is less than 2^32: */
 	while (div >> 32) {
 		sft++;
 		div >>= 1;
 	}
-	dclc >>= sft;
-	do_div(dclc, (unsigned long) div);
-
-	return dclc;
+	tmp >>= sft;
+	do_div(tmp, (unsigned long) div);
+	return dclc < 0 ? -tmp : tmp;
 }
 EXPORT_SYMBOL_GPL(__ktime_divns);
 #endif /* BITS_PER_LONG >= 64 */

kernel/watchdog.c

@@ -621,7 +621,7 @@ void watchdog_nmi_enable_all(void)
 	put_online_cpus();
 
 unlock:
-	mutex_lock(&watchdog_proc_mutex);
+	mutex_unlock(&watchdog_proc_mutex);
 }
 
 void watchdog_nmi_disable_all(void)