1 files changed, 67 insertions, 233 deletions

diff --git a/net/core/dst.c b/net/core/dst.c
index 960e503b5a52..00aa972ad1a1 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -42,108 +42,6 @@
  * to dirty as few cache lines as possible in __dst_free().
  * As this is not a very strong hint, we dont force an alignment on SMP.
  */
-static struct {
-	spinlock_t		lock;
-	struct dst_entry	*list;
-	unsigned long		timer_inc;
-	unsigned long		timer_expires;
-} dst_garbage = {
-	.lock = __SPIN_LOCK_UNLOCKED(dst_garbage.lock),
-	.timer_inc = DST_GC_MAX,
-};
-static void dst_gc_task(struct work_struct *work);
-static void ___dst_free(struct dst_entry *dst);
-
-static DECLARE_DELAYED_WORK(dst_gc_work, dst_gc_task);
-
-static DEFINE_MUTEX(dst_gc_mutex);
-/*
- * long lived entries are maintained in this list, guarded by dst_gc_mutex
- */
-static struct dst_entry         *dst_busy_list;
-
-static void dst_gc_task(struct work_struct *work)
-{
-	int    delayed = 0;
-	int    work_performed = 0;
-	unsigned long expires = ~0L;
-	struct dst_entry *dst, *next, head;
-	struct dst_entry *last = &head;
-
-	mutex_lock(&dst_gc_mutex);
-	next = dst_busy_list;
-
-loop:
-	while ((dst = next) != NULL) {
-		next = dst->next;
-		prefetch(&next->next);
-		cond_resched();
-		if (likely(atomic_read(&dst->__refcnt))) {
-			last->next = dst;
-			last = dst;
-			delayed++;
-			continue;
-		}
-		work_performed++;
-
-		dst = dst_destroy(dst);
-		if (dst) {
-			/* NOHASH and still referenced. Unless it is already
-			 * on gc list, invalidate it and add to gc list.
-			 *
-			 * Note: this is temporary. Actually, NOHASH dst's
-			 * must be obsoleted when parent is obsoleted.
-			 * But we do not have state "obsoleted, but
-			 * referenced by parent", so it is right.
-			 */
-			if (dst->obsolete > 0)
-				continue;
-
-			___dst_free(dst);
-			dst->next = next;
-			next = dst;
-		}
-	}
-
-	spin_lock_bh(&dst_garbage.lock);
-	next = dst_garbage.list;
-	if (next) {
-		dst_garbage.list = NULL;
-		spin_unlock_bh(&dst_garbage.lock);
-		goto loop;
-	}
-	last->next = NULL;
-	dst_busy_list = head.next;
-	if (!dst_busy_list)
-		dst_garbage.timer_inc = DST_GC_MAX;
-	else {
-		/*
-		 * if we freed less than 1/10 of delayed entries,
-		 * we can sleep longer.
-		 */
-		if (work_performed <= delayed/10) {
-			dst_garbage.timer_expires += dst_garbage.timer_inc;
-			if (dst_garbage.timer_expires > DST_GC_MAX)
-				dst_garbage.timer_expires = DST_GC_MAX;
-			dst_garbage.timer_inc += DST_GC_INC;
-		} else {
-			dst_garbage.timer_inc = DST_GC_INC;
-			dst_garbage.timer_expires = DST_GC_MIN;
-		}
-		expires = dst_garbage.timer_expires;
-		/*
-		 * if the next desired timer is more than 4 seconds in the
-		 * future then round the timer to whole seconds
-		 */
-		if (expires > 4*HZ)
-			expires = round_jiffies_relative(expires);
-		schedule_delayed_work(&dst_gc_work, expires);
-	}
-
-	spin_unlock_bh(&dst_garbage.lock);
-	mutex_unlock(&dst_gc_mutex);
-}
-
 int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	kfree_skb(skb);
@@ -151,13 +49,13 @@ int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(dst_discard_out);
 
-const u32 dst_default_metrics[RTAX_MAX + 1] = {
+const struct dst_metrics dst_default_metrics = {
 	/* This initializer is needed to force linker to place this variable
 	 * into const section. Otherwise it might end into bss section.
 	 * We really want to avoid false sharing on this variable, and catch
 	 * any writes on it.
 	 */
-	[RTAX_MAX] = 0xdeadbeef,
+	.refcnt = ATOMIC_INIT(1),
 };
 
 void dst_init(struct dst_entry *dst, struct dst_ops *ops,
@@ -169,7 +67,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops,
 	if (dev)
 		dev_hold(dev);
 	dst->ops = ops;
-	dst_init_metrics(dst, dst_default_metrics, true);
+	dst_init_metrics(dst, dst_default_metrics.metrics, true);
 	dst->expires = 0UL;
 	dst->path = dst;
 	dst->from = NULL;
@@ -216,41 +114,12 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
 }
 EXPORT_SYMBOL(dst_alloc);
 
-static void ___dst_free(struct dst_entry *dst)
-{
-	/* The first case (dev==NULL) is required, when
-	   protocol module is unloaded.
-	 */
-	if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) {
-		dst->input = dst_discard;
-		dst->output = dst_discard_out;
-	}
-	dst->obsolete = DST_OBSOLETE_DEAD;
-}
-
-void __dst_free(struct dst_entry *dst)
-{
-	spin_lock_bh(&dst_garbage.lock);
-	___dst_free(dst);
-	dst->next = dst_garbage.list;
-	dst_garbage.list = dst;
-	if (dst_garbage.timer_inc > DST_GC_INC) {
-		dst_garbage.timer_inc = DST_GC_INC;
-		dst_garbage.timer_expires = DST_GC_MIN;
-		mod_delayed_work(system_wq, &dst_gc_work,
-				 dst_garbage.timer_expires);
-	}
-	spin_unlock_bh(&dst_garbage.lock);
-}
-EXPORT_SYMBOL(__dst_free);
-
 struct dst_entry *dst_destroy(struct dst_entry * dst)
 {
 	struct dst_entry *child;
 
 	smp_rmb();
 
-again:
 	child = dst->child;
 
 	if (!(dst->flags & DST_NOCOUNT))
@@ -269,20 +138,8 @@ again:
 		kmem_cache_free(dst->ops->kmem_cachep, dst);
 
 	dst = child;
-	if (dst) {
-		int nohash = dst->flags & DST_NOHASH;
-
-		if (atomic_dec_and_test(&dst->__refcnt)) {
-			/* We were real parent of this dst, so kill child. */
-			if (nohash)
-				goto again;
-		} else {
-			/* Child is still referenced, return it for freeing. */
-			if (nohash)
-				return dst;
-			/* Child is still in his hash table */
-		}
-	}
+	if (dst)
+		dst_release_immediate(dst);
 	return NULL;
 }
 EXPORT_SYMBOL(dst_destroy);
@@ -292,47 +149,88 @@ static void dst_destroy_rcu(struct rcu_head *head)
 	struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head);
 
 	dst = dst_destroy(dst);
-	if (dst)
-		__dst_free(dst);
 }
 
+/* Operations to mark dst as DEAD and clean up the net device referenced
+ * by dst:
+ * 1. put the dst under loopback interface and discard all tx/rx packets
+ *    on this route.
+ * 2. release the net_device
+ * This function should be called when removing routes from the fib tree
+ * in preparation for a NETDEV_DOWN/NETDEV_UNREGISTER event and also to
+ * make the next dst_ops->check() fail.
+ */
+void dst_dev_put(struct dst_entry *dst)
+{
+	struct net_device *dev = dst->dev;
+
+	dst->obsolete = DST_OBSOLETE_DEAD;
+	if (dst->ops->ifdown)
+		dst->ops->ifdown(dst, dev, true);
+	dst->input = dst_discard;
+	dst->output = dst_discard_out;
+	dst->dev = dev_net(dst->dev)->loopback_dev;
+	dev_hold(dst->dev);
+	dev_put(dev);
+}
+EXPORT_SYMBOL(dst_dev_put);
+
 void dst_release(struct dst_entry *dst)
 {
 	if (dst) {
 		int newrefcnt;
-		unsigned short nocache = dst->flags & DST_NOCACHE;
 
 		newrefcnt = atomic_dec_return(&dst->__refcnt);
 		if (unlikely(newrefcnt < 0))
 			net_warn_ratelimited("%s: dst:%p refcnt:%d\n",
 					     __func__, dst, newrefcnt);
-		if (!newrefcnt && unlikely(nocache))
+		if (!newrefcnt)
 			call_rcu(&dst->rcu_head, dst_destroy_rcu);
 	}
 }
 EXPORT_SYMBOL(dst_release);
 
+void dst_release_immediate(struct dst_entry *dst)
+{
+	if (dst) {
+		int newrefcnt;
+
+		newrefcnt = atomic_dec_return(&dst->__refcnt);
+		if (unlikely(newrefcnt < 0))
+			net_warn_ratelimited("%s: dst:%p refcnt:%d\n",
+					     __func__, dst, newrefcnt);
+		if (!newrefcnt)
+			dst_destroy(dst);
+	}
+}
+EXPORT_SYMBOL(dst_release_immediate);
+
 u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old)
 {
-	u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC);
+	struct dst_metrics *p = kmalloc(sizeof(*p), GFP_ATOMIC);
 
 	if (p) {
-		u32 *old_p = __DST_METRICS_PTR(old);
+		struct dst_metrics *old_p = (struct dst_metrics *)__DST_METRICS_PTR(old);
 		unsigned long prev, new;
 
-		memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
+		atomic_set(&p->refcnt, 1);
+		memcpy(p->metrics, old_p->metrics, sizeof(p->metrics));
 
 		new = (unsigned long) p;
 		prev = cmpxchg(&dst->_metrics, old, new);
 
 		if (prev != old) {
 			kfree(p);
-			p = __DST_METRICS_PTR(prev);
+			p = (struct dst_metrics *)__DST_METRICS_PTR(prev);
 			if (prev & DST_METRICS_READ_ONLY)
 				p = NULL;
+		} else if (prev & DST_METRICS_REFCOUNTED) {
+			if (atomic_dec_and_test(&old_p->refcnt))
+				kfree(old_p);
 		}
 	}
-	return p;
+	BUILD_BUG_ON(offsetof(struct dst_metrics, metrics) != 0);
+	return (u32 *)p;
 }
 EXPORT_SYMBOL(dst_cow_metrics_generic);
 
@@ -341,7 +239,7 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
 {
 	unsigned long prev, new;
 
-	new = ((unsigned long) dst_default_metrics) | DST_METRICS_READ_ONLY;
+	new = ((unsigned long) &dst_default_metrics) | DST_METRICS_READ_ONLY;
 	prev = cmpxchg(&dst->_metrics, old, new);
 	if (prev == old)
 		kfree(__DST_METRICS_PTR(old));
@@ -366,21 +264,25 @@ static int dst_md_discard(struct sk_buff *skb)
 	return 0;
 }
 
-static void __metadata_dst_init(struct metadata_dst *md_dst, u8 optslen)
+static void __metadata_dst_init(struct metadata_dst *md_dst,
+				enum metadata_type type, u8 optslen)
+
 {
 	struct dst_entry *dst;
 
 	dst = &md_dst->dst;
 	dst_init(dst, &md_dst_ops, NULL, 1, DST_OBSOLETE_NONE,
-		 DST_METADATA | DST_NOCACHE | DST_NOCOUNT);
+		 DST_METADATA | DST_NOCOUNT);
 
 	dst->input = dst_md_discard;
 	dst->output = dst_md_discard_out;
 
 	memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst));
+	md_dst->type = type;
 }
 
-struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags)
+struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type,
+					gfp_t flags)
 {
 	struct metadata_dst *md_dst;
 
@@ -388,7 +290,7 @@ struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags)
 	if (!md_dst)
 		return NULL;
 
-	__metadata_dst_init(md_dst, optslen);
+	__metadata_dst_init(md_dst, type, optslen);
 
 	return md_dst;
 }
@@ -402,7 +304,8 @@ void metadata_dst_free(struct metadata_dst *md_dst)
 	kfree(md_dst);
 }
 
-struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags)
+struct metadata_dst __percpu *
+metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags)
 {
 	int cpu;
 	struct metadata_dst __percpu *md_dst;
@@ -413,77 +316,8 @@ struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags)
 		return NULL;
 
 	for_each_possible_cpu(cpu)
-		__metadata_dst_init(per_cpu_ptr(md_dst, cpu), optslen);
+		__metadata_dst_init(per_cpu_ptr(md_dst, cpu), type, optslen);
 
 	return md_dst;
 }
 EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu);
-
-/* Dirty hack. We did it in 2.2 (in __dst_free),
- * we have _very_ good reasons not to repeat
- * this mistake in 2.3, but we have no choice
- * now. _It_ _is_ _explicit_ _deliberate_
- * _race_ _condition_.
- *
- * Commented and originally written by Alexey.
- */
-static void dst_ifdown(struct dst_entry *dst, struct net_device *dev,
-		       int unregister)
-{
-	if (dst->ops->ifdown)
-		dst->ops->ifdown(dst, dev, unregister);
-
-	if (dev != dst->dev)
-		return;
-
-	if (!unregister) {
-		dst->input = dst_discard;
-		dst->output = dst_discard_out;
-	} else {
-		dst->dev = dev_net(dst->dev)->loopback_dev;
-		dev_hold(dst->dev);
-		dev_put(dev);
-	}
-}
-
-static int dst_dev_event(struct notifier_block *this, unsigned long event,
-			 void *ptr)
-{
-	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-	struct dst_entry *dst, *last = NULL;
-
-	switch (event) {
-	case NETDEV_UNREGISTER_FINAL:
-	case NETDEV_DOWN:
-		mutex_lock(&dst_gc_mutex);
-		for (dst = dst_busy_list; dst; dst = dst->next) {
-			last = dst;
-			dst_ifdown(dst, dev, event != NETDEV_DOWN);
-		}
-
-		spin_lock_bh(&dst_garbage.lock);
-		dst = dst_garbage.list;
-		dst_garbage.list = NULL;
-		spin_unlock_bh(&dst_garbage.lock);
-
-		if (last)
-			last->next = dst;
-		else
-			dst_busy_list = dst;
-		for (; dst; dst = dst->next)
-			dst_ifdown(dst, dev, event != NETDEV_DOWN);
-		mutex_unlock(&dst_gc_mutex);
-		break;
-	}
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block dst_dev_notifier = {
-	.notifier_call	= dst_dev_event,
-	.priority = -10, /* must be called after other network notifiers */
-};
-
-void __init dst_subsys_init(void)
-{
-	register_netdevice_notifier(&dst_dev_notifier);
-}