1 files changed, 123 insertions, 77 deletions

diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 36e603c78ce..e70301eb7a4 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -4,6 +4,8 @@
  * Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/string.h>
@@ -22,6 +24,7 @@
 #include <linux/timer.h>
 #include <linux/bitops.h>
 #include <linux/slab.h>
+#include <linux/module.h>
 #include <net/genetlink.h>
 #include <net/netevent.h>
 
@@ -33,22 +36,19 @@
 #define TRACE_ON 1
 #define TRACE_OFF 0
 
-static void send_dm_alert(struct work_struct *unused);
-
-
 /*
  * Globals, our netlink socket pointer
  * and the work handle that will send up
  * 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;
-	atomic_t dm_hit_count;
-	struct timer_list send_timer;
+	spinlock_t		lock;
+	struct sk_buff		*skb;
+	struct work_struct	dm_alert_work;
+	struct timer_list	send_timer;
 };
 
 struct dm_hw_stat_delta {
@@ -64,7 +64,6 @@ static struct genl_family net_drop_monitor_family = {
 	.hdrsize        = 0,
 	.name           = "NET_DM",
 	.version        = 2,
-	.maxattr        = NET_DM_CMD_MAX,
 };
 
 static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data);
@@ -74,56 +73,64 @@ static int dm_delay = 1;
 static unsigned long dm_hw_check_delta = 2*HZ;
 static LIST_HEAD(hw_stats_list);
 
-static void reset_per_cpu_data(struct per_cpu_dm_data *data)
+static struct sk_buff *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;
+	unsigned long flags;
 
 	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 {
+		mod_timer(&data->send_timer, jiffies + HZ / 10);
+	}
+
+	spin_lock_irqsave(&data->lock, flags);
+	swap(data->skb, skb);
+	spin_unlock_irqrestore(&data->lock, flags);
+
+	return skb;
 }
 
-static void send_dm_alert(struct work_struct *unused)
+static struct genl_multicast_group dropmon_mcgrps[] = {
+	{ .name = "events", },
+};
+
+static void send_dm_alert(struct work_struct *work)
 {
 	struct sk_buff *skb;
-	struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data);
-
-	/*
-	 * Grab the skb we're about to send
-	 */
-	skb = data->skb;
+	struct per_cpu_dm_data *data;
 
-	/*
-	 * Replace it with a new one
-	 */
-	reset_per_cpu_data(data);
+	data = container_of(work, struct per_cpu_dm_data, dm_alert_work);
 
-	/*
-	 * Ship it!
-	 */
-	genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL);
+	skb = reset_per_cpu_data(data);
 
+	if (skb)
+		genlmsg_multicast(&net_drop_monitor_family, skb, 0,
+				  0, GFP_KERNEL);
 }
 
 /*
  * This is the timer function to delay the sending of an alert
  * in the event that more drops will arrive during the
- * hysteresis period.  Note that it operates under the timer interrupt
- * so we don't need to disable preemption here
+ * hysteresis period.
  */
-static void sched_send_work(unsigned long unused)
+static void sched_send_work(unsigned long _data)
 {
-	struct per_cpu_dm_data *data =  &__get_cpu_var(dm_cpu_data);
+	struct per_cpu_dm_data *data = (struct per_cpu_dm_data *)_data;
 
 	schedule_work(&data->dm_alert_work);
 }
@@ -134,17 +141,19 @@ 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;
+	unsigned long flags;
 
+	local_irq_save(flags);
+	data = &__get_cpu_var(dm_cpu_data);
+	spin_lock(&data->lock);
+	dskb = data->skb;
 
-	if (!atomic_add_unless(&data->dm_hit_count, -1, 0)) {
-		/*
-		 * we're already at zero, discard this hit
-		 */
+	if (!dskb)
 		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++) {
@@ -153,11 +162,12 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 			goto out;
 		}
 	}
-
+	if (msg->entries == dm_hit_limit)
+		goto out;
 	/*
 	 * 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;
@@ -165,11 +175,11 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 
 	if (!timer_pending(&data->send_timer)) {
 		data->send_timer.expires = jiffies + dm_delay * HZ;
-		add_timer_on(&data->send_timer, smp_processor_id());
+		add_timer(&data->send_timer);
 	}
 
 out:
-	return;
+	spin_unlock_irqrestore(&data->lock, flags);
 }
 
 static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location)
@@ -207,21 +217,13 @@ static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi)
 	rcu_read_unlock();
 }
 
-
-static void free_dm_hw_stat(struct rcu_head *head)
-{
-	struct dm_hw_stat_delta *n;
-	n = container_of(head, struct dm_hw_stat_delta, rcu);
-	kfree(n);
-}
-
 static int set_all_monitor_traces(int state)
 {
 	int rc = 0;
 	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;
@@ -230,9 +232,15 @@ static int set_all_monitor_traces(int state)
 
 	switch (state) {
 	case TRACE_ON:
+		if (!try_module_get(THIS_MODULE)) {
+			rc = -ENODEV;
+			break;
+		}
+
 		rc |= register_trace_kfree_skb(trace_kfree_skb_hit, NULL);
 		rc |= register_trace_napi_poll(trace_napi_poll_hit, NULL);
 		break;
+
 	case TRACE_OFF:
 		rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit, NULL);
 		rc |= unregister_trace_napi_poll(trace_napi_poll_hit, NULL);
@@ -245,9 +253,12 @@ static int set_all_monitor_traces(int state)
 		list_for_each_entry_safe(new_stat, temp, &hw_stats_list, list) {
 			if (new_stat->dev == NULL) {
 				list_del_rcu(&new_stat->list);
-				call_rcu(&new_stat->rcu, free_dm_hw_stat);
+				kfree_rcu(new_stat, rcu);
 			}
 		}
+
+		module_put(THIS_MODULE);
+
 		break;
 	default:
 		rc = 1;
@@ -260,7 +271,7 @@ static int set_all_monitor_traces(int state)
 		rc = -EINPROGRESS;
 
 out_unlock:
-	spin_unlock(&trace_state_lock);
+	mutex_unlock(&trace_state_mutex);
 
 	return rc;
 }
@@ -288,9 +299,9 @@ static int net_dm_cmd_trace(struct sk_buff *skb,
 }
 
 static int dropmon_net_event(struct notifier_block *ev_block,
-			unsigned long event, void *ptr)
+			     unsigned long event, void *ptr)
 {
-	struct net_device *dev = ptr;
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct dm_hw_stat_delta *new_stat = NULL;
 	struct dm_hw_stat_delta *tmp;
 
@@ -303,30 +314,30 @@ 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;
 				if (trace_state == TRACE_OFF) {
 					list_del_rcu(&new_stat->list);
-					call_rcu(&new_stat->rcu, free_dm_hw_stat);
+					kfree_rcu(new_stat, rcu);
 					break;
 				}
 			}
 		}
-		spin_unlock(&trace_state_lock);
+		mutex_unlock(&trace_state_mutex);
 		break;
 	}
 out:
 	return NOTIFY_DONE;
 }
 
-static struct genl_ops dropmon_ops[] = {
+static const struct genl_ops dropmon_ops[] = {
 	{
 		.cmd = NET_DM_CMD_CONFIG,
 		.doit = net_dm_cmd_config,
@@ -350,38 +361,40 @@ static int __init init_net_drop_monitor(void)
 	struct per_cpu_dm_data *data;
 	int cpu, rc;
 
-	printk(KERN_INFO "Initalizing network drop monitor service\n");
+	pr_info("Initializing network drop monitor service\n");
 
 	if (sizeof(void *) > 8) {
-		printk(KERN_ERR "Unable to store program counters on this arch, Drop monitor failed\n");
+		pr_err("Unable to store program counters on this arch, Drop monitor failed\n");
 		return -ENOSPC;
 	}
 
-	rc = genl_register_family_with_ops(&net_drop_monitor_family,
-					   dropmon_ops,
-					   ARRAY_SIZE(dropmon_ops));
+	rc = genl_register_family_with_ops_groups(&net_drop_monitor_family,
+						  dropmon_ops, dropmon_mcgrps);
 	if (rc) {
-		printk(KERN_ERR "Could not create drop monitor netlink family\n");
+		pr_err("Could not create drop monitor netlink family\n");
 		return rc;
 	}
+	WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT);
 
 	rc = register_netdevice_notifier(&dropmon_net_notifier);
 	if (rc < 0) {
-		printk(KERN_CRIT "Failed to register netdevice notifier\n");
+		pr_crit("Failed to register netdevice notifier\n");
 		goto out_unreg;
 	}
 
 	rc = 0;
 
-	for_each_present_cpu(cpu) {
+	for_each_possible_cpu(cpu) {
 		data = &per_cpu(dm_cpu_data, cpu);
-		reset_per_cpu_data(data);
 		INIT_WORK(&data->dm_alert_work, send_dm_alert);
 		init_timer(&data->send_timer);
-		data->send_timer.data = cpu;
+		data->send_timer.data = (unsigned long)data;
 		data->send_timer.function = sched_send_work;
+		spin_lock_init(&data->lock);
+		reset_per_cpu_data(data);
 	}
 
+
 	goto out;
 
 out_unreg:
@@ -390,4 +403,37 @@ out:
 	return rc;
 }
 
-late_initcall(init_net_drop_monitor);
+static void exit_net_drop_monitor(void)
+{
+	struct per_cpu_dm_data *data;
+	int cpu;
+
+	BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier));
+
+	/*
+	 * Because of the module_get/put we do in the trace state change path
+	 * we are guarnateed not to have any current users when we get here
+	 * all we need to do is make sure that we don't have any running timers
+	 * or pending schedule calls
+	 */
+
+	for_each_possible_cpu(cpu) {
+		data = &per_cpu(dm_cpu_data, cpu);
+		del_timer_sync(&data->send_timer);
+		cancel_work_sync(&data->dm_alert_work);
+		/*
+		 * At this point, we should have exclusive access
+		 * to this struct and can free the skb inside it
+		 */
+		kfree_skb(data->skb);
+	}
+
+	BUG_ON(genl_unregister_family(&net_drop_monitor_family));
+}
+
+module_init(init_net_drop_monitor);
+module_exit(exit_net_drop_monitor);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>");
+MODULE_ALIAS_GENL_FAMILY("NET_DM");