Merge tag 'v3.4-rc6' into drm-intel-next

Conflicts:
	drivers/gpu/drm/i915/intel_display.c

Ok, this is a fun story of git totally messing things up. There
/shouldn't/ be any conflict in here, because the fixes in -rc6 do only
touch functions that have not been changed in -next.

The offending commits in drm-next are 14415745b2..1fa611065 which
simply move a few functions from intel_display.c to intel_pm.c. The
problem seems to be that git diff gets completely confused:

$ git diff 14415745b2..1fa611065

is a nice mess in intel_display.c, and the diff leaks into totally
unrelated functions, whereas

$git diff --minimal  14415745b2..1fa611065

is exactly what we want.

Unfortunately there seems to be no way to teach similar smarts to the
merge diff and conflict generation code, because with the minimal diff
there really shouldn't be any conflicts. For added hilarity, every
time something in that area changes the + and - lines in the diff move
around like crazy, again resulting in new conflicts. So I fear this
mess will stay with us for a little longer (and might result in
another backmerge down the road).

Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

1 files changed, 65 insertions, 24 deletions

diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 7f36b38e060..a7cad741df0 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -42,13 +42,14 @@ static void send_dm_alert(struct work_struct *unused);
  * netlink alerts
  */
 static int trace_state = TRACE_OFF;
-static DEFINE_SPINLOCK(trace_state_lock);
+static DEFINE_MUTEX(trace_state_mutex);
 
 struct per_cpu_dm_data {
 	struct work_struct dm_alert_work;
-	struct sk_buff *skb;
+	struct sk_buff __rcu *skb;
 	atomic_t dm_hit_count;
 	struct timer_list send_timer;
+	int cpu;
 };
 
 struct dm_hw_stat_delta {
@@ -79,29 +80,53 @@ static void reset_per_cpu_data(struct per_cpu_dm_data *data)
 	size_t al;
 	struct net_dm_alert_msg *msg;
 	struct nlattr *nla;
+	struct sk_buff *skb;
+	struct sk_buff *oskb = rcu_dereference_protected(data->skb, 1);
 
 	al = sizeof(struct net_dm_alert_msg);
 	al += dm_hit_limit * sizeof(struct net_dm_drop_point);
 	al += sizeof(struct nlattr);
 
-	data->skb = genlmsg_new(al, GFP_KERNEL);
-	genlmsg_put(data->skb, 0, 0, &net_drop_monitor_family,
-			0, NET_DM_CMD_ALERT);
-	nla = nla_reserve(data->skb, NLA_UNSPEC, sizeof(struct net_dm_alert_msg));
-	msg = nla_data(nla);
-	memset(msg, 0, al);
-	atomic_set(&data->dm_hit_count, dm_hit_limit);
+	skb = genlmsg_new(al, GFP_KERNEL);
+
+	if (skb) {
+		genlmsg_put(skb, 0, 0, &net_drop_monitor_family,
+				0, NET_DM_CMD_ALERT);
+		nla = nla_reserve(skb, NLA_UNSPEC,
+				  sizeof(struct net_dm_alert_msg));
+		msg = nla_data(nla);
+		memset(msg, 0, al);
+	} else
+		schedule_work_on(data->cpu, &data->dm_alert_work);
+
+	/*
+	 * Don't need to lock this, since we are guaranteed to only
+	 * run this on a single cpu at a time.
+	 * Note also that we only update data->skb if the old and new skb
+	 * pointers don't match.  This ensures that we don't continually call
+	 * synchornize_rcu if we repeatedly fail to alloc a new netlink message.
+	 */
+	if (skb != oskb) {
+		rcu_assign_pointer(data->skb, skb);
+
+		synchronize_rcu();
+
+		atomic_set(&data->dm_hit_count, dm_hit_limit);
+	}
+
 }
 
 static void send_dm_alert(struct work_struct *unused)
 {
 	struct sk_buff *skb;
-	struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data);
+	struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data);
+
+	WARN_ON_ONCE(data->cpu != smp_processor_id());
 
 	/*
 	 * Grab the skb we're about to send
 	 */
-	skb = data->skb;
+	skb = rcu_dereference_protected(data->skb, 1);
 
 	/*
 	 * Replace it with a new one
@@ -111,8 +136,10 @@ static void send_dm_alert(struct work_struct *unused)
 	/*
 	 * Ship it!
 	 */
-	genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL);
+	if (skb)
+		genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL);
 
+	put_cpu_var(dm_cpu_data);
 }
 
 /*
@@ -123,9 +150,11 @@ static void send_dm_alert(struct work_struct *unused)
  */
 static void sched_send_work(unsigned long unused)
 {
-	struct per_cpu_dm_data *data =  &__get_cpu_var(dm_cpu_data);
+	struct per_cpu_dm_data *data =  &get_cpu_var(dm_cpu_data);
+
+	schedule_work_on(smp_processor_id(), &data->dm_alert_work);
 
-	schedule_work(&data->dm_alert_work);
+	put_cpu_var(dm_cpu_data);
 }
 
 static void trace_drop_common(struct sk_buff *skb, void *location)
@@ -134,8 +163,15 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 	struct nlmsghdr *nlh;
 	struct nlattr *nla;
 	int i;
-	struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data);
+	struct sk_buff *dskb;
+	struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data);
+
+
+	rcu_read_lock();
+	dskb = rcu_dereference(data->skb);
 
+	if (!dskb)
+		goto out;
 
 	if (!atomic_add_unless(&data->dm_hit_count, -1, 0)) {
 		/*
@@ -144,12 +180,13 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 		goto out;
 	}
 
-	nlh = (struct nlmsghdr *)data->skb->data;
+	nlh = (struct nlmsghdr *)dskb->data;
 	nla = genlmsg_data(nlmsg_data(nlh));
 	msg = nla_data(nla);
 	for (i = 0; i < msg->entries; i++) {
 		if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) {
 			msg->points[i].count++;
+			atomic_inc(&data->dm_hit_count);
 			goto out;
 		}
 	}
@@ -157,7 +194,7 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 	/*
 	 * We need to create a new entry
 	 */
-	__nla_reserve_nohdr(data->skb, sizeof(struct net_dm_drop_point));
+	__nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point));
 	nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point));
 	memcpy(msg->points[msg->entries].pc, &location, sizeof(void *));
 	msg->points[msg->entries].count = 1;
@@ -169,6 +206,8 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 	}
 
 out:
+	rcu_read_unlock();
+	put_cpu_var(dm_cpu_data);
 	return;
 }
 
@@ -213,7 +252,7 @@ static int set_all_monitor_traces(int state)
 	struct dm_hw_stat_delta *new_stat = NULL;
 	struct dm_hw_stat_delta *temp;
 
-	spin_lock(&trace_state_lock);
+	mutex_lock(&trace_state_mutex);
 
 	if (state == trace_state) {
 		rc = -EAGAIN;
@@ -252,7 +291,7 @@ static int set_all_monitor_traces(int state)
 		rc = -EINPROGRESS;
 
 out_unlock:
-	spin_unlock(&trace_state_lock);
+	mutex_unlock(&trace_state_mutex);
 
 	return rc;
 }
@@ -295,12 +334,12 @@ static int dropmon_net_event(struct notifier_block *ev_block,
 
 		new_stat->dev = dev;
 		new_stat->last_rx = jiffies;
-		spin_lock(&trace_state_lock);
+		mutex_lock(&trace_state_mutex);
 		list_add_rcu(&new_stat->list, &hw_stats_list);
-		spin_unlock(&trace_state_lock);
+		mutex_unlock(&trace_state_mutex);
 		break;
 	case NETDEV_UNREGISTER:
-		spin_lock(&trace_state_lock);
+		mutex_lock(&trace_state_mutex);
 		list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) {
 			if (new_stat->dev == dev) {
 				new_stat->dev = NULL;
@@ -311,7 +350,7 @@ static int dropmon_net_event(struct notifier_block *ev_block,
 				}
 			}
 		}
-		spin_unlock(&trace_state_lock);
+		mutex_unlock(&trace_state_mutex);
 		break;
 	}
 out:
@@ -367,13 +406,15 @@ static int __init init_net_drop_monitor(void)
 
 	for_each_present_cpu(cpu) {
 		data = &per_cpu(dm_cpu_data, cpu);
-		reset_per_cpu_data(data);
+		data->cpu = cpu;
 		INIT_WORK(&data->dm_alert_work, send_dm_alert);
 		init_timer(&data->send_timer);
 		data->send_timer.data = cpu;
 		data->send_timer.function = sched_send_work;
+		reset_per_cpu_data(data);
 	}
 
+
 	goto out;
 
 out_unreg: