Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next

Steffen Klassert says:

====================
1) Introduce skb_to_sgvec_nomark function to add further data to the sg list
   without calling sg_unmark_end first. Needed to add extended sequence
   number informations. From Fan Du.

2) Add IPsec extended sequence numbers support to the Authentication Header
   protocol for ipv4 and ipv6. From Fan Du.

3) Make the IPsec flowcache namespace aware, from Fan Du.

4) Avoid creating temporary SA for every packet when no key manager is
   registered. From Horia Geanta.

5) Support filtering of SA dumps to show only the SAs that match a
   given filter. From Nicolas Dichtel.

6) Remove caching of xfrm_policy_sk_bundles. The cached socket policy bundles
   are never used, instead we create a new cache entry whenever xfrm_lookup()
   is called on a socket policy. Most protocols cache the used routes to the
   socket, so this caching is not needed.

7)  Fix a forgotten SADB_X_EXT_FILTER length check in pfkey, from Nicolas
    Dichtel.

8) Cleanup error handling of xfrm_state_clone.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 83 insertions, 70 deletions

diff --git a/net/core/flow.c b/net/core/flow.c
index dfa602ceb8cd..344a184011fd 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -24,6 +24,7 @@
 #include <net/flow.h>
 #include <linux/atomic.h>
 #include <linux/security.h>
+#include <net/net_namespace.h>
 
 struct flow_cache_entry {
 	union {
@@ -38,37 +39,12 @@ struct flow_cache_entry {
 	struct flow_cache_object	*object;
 };
 
-struct flow_cache_percpu {
-	struct hlist_head		*hash_table;
-	int				hash_count;
-	u32				hash_rnd;
-	int				hash_rnd_recalc;
-	struct tasklet_struct		flush_tasklet;
-};
-
 struct flow_flush_info {
 	struct flow_cache		*cache;
 	atomic_t			cpuleft;
 	struct completion		completion;
 };
 
-struct flow_cache {
-	u32				hash_shift;
-	struct flow_cache_percpu __percpu *percpu;
-	struct notifier_block		hotcpu_notifier;
-	int				low_watermark;
-	int				high_watermark;
-	struct timer_list		rnd_timer;
-};
-
-atomic_t flow_cache_genid = ATOMIC_INIT(0);
-EXPORT_SYMBOL(flow_cache_genid);
-static struct flow_cache flow_cache_global;
-static struct kmem_cache *flow_cachep __read_mostly;
-
-static DEFINE_SPINLOCK(flow_cache_gc_lock);
-static LIST_HEAD(flow_cache_gc_list);
-
 #define flow_cache_hash_size(cache)	(1 << (cache)->hash_shift)
 #define FLOW_HASH_RND_PERIOD		(10 * 60 * HZ)
 
@@ -84,46 +60,50 @@ static void flow_cache_new_hashrnd(unsigned long arg)
 	add_timer(&fc->rnd_timer);
 }
 
-static int flow_entry_valid(struct flow_cache_entry *fle)
+static int flow_entry_valid(struct flow_cache_entry *fle,
+				struct netns_xfrm *xfrm)
 {
-	if (atomic_read(&flow_cache_genid) != fle->genid)
+	if (atomic_read(&xfrm->flow_cache_genid) != fle->genid)
 		return 0;
 	if (fle->object && !fle->object->ops->check(fle->object))
 		return 0;
 	return 1;
 }
 
-static void flow_entry_kill(struct flow_cache_entry *fle)
+static void flow_entry_kill(struct flow_cache_entry *fle,
+				struct netns_xfrm *xfrm)
 {
 	if (fle->object)
 		fle->object->ops->delete(fle->object);
-	kmem_cache_free(flow_cachep, fle);
+	kmem_cache_free(xfrm->flow_cachep, fle);
 }
 
 static void flow_cache_gc_task(struct work_struct *work)
 {
 	struct list_head gc_list;
 	struct flow_cache_entry *fce, *n;
+	struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
+						flow_cache_gc_work);
 
 	INIT_LIST_HEAD(&gc_list);
-	spin_lock_bh(&flow_cache_gc_lock);
-	list_splice_tail_init(&flow_cache_gc_list, &gc_list);
-	spin_unlock_bh(&flow_cache_gc_lock);
+	spin_lock_bh(&xfrm->flow_cache_gc_lock);
+	list_splice_tail_init(&xfrm->flow_cache_gc_list, &gc_list);
+	spin_unlock_bh(&xfrm->flow_cache_gc_lock);
 
 	list_for_each_entry_safe(fce, n, &gc_list, u.gc_list)
-		flow_entry_kill(fce);
+		flow_entry_kill(fce, xfrm);
 }
-static DECLARE_WORK(flow_cache_gc_work, flow_cache_gc_task);
 
 static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
-				     int deleted, struct list_head *gc_list)
+				     int deleted, struct list_head *gc_list,
+				     struct netns_xfrm *xfrm)
 {
 	if (deleted) {
 		fcp->hash_count -= deleted;
-		spin_lock_bh(&flow_cache_gc_lock);
-		list_splice_tail(gc_list, &flow_cache_gc_list);
-		spin_unlock_bh(&flow_cache_gc_lock);
-		schedule_work(&flow_cache_gc_work);
+		spin_lock_bh(&xfrm->flow_cache_gc_lock);
+		list_splice_tail(gc_list, &xfrm->flow_cache_gc_list);
+		spin_unlock_bh(&xfrm->flow_cache_gc_lock);
+		schedule_work(&xfrm->flow_cache_gc_work);
 	}
 }
 
@@ -135,6 +115,8 @@ static void __flow_cache_shrink(struct flow_cache *fc,
 	struct hlist_node *tmp;
 	LIST_HEAD(gc_list);
 	int i, deleted = 0;
+	struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
+						flow_cache_global);
 
 	for (i = 0; i < flow_cache_hash_size(fc); i++) {
 		int saved = 0;
@@ -142,7 +124,7 @@ static void __flow_cache_shrink(struct flow_cache *fc,
 		hlist_for_each_entry_safe(fle, tmp,
 					  &fcp->hash_table[i], u.hlist) {
 			if (saved < shrink_to &&
-			    flow_entry_valid(fle)) {
+			    flow_entry_valid(fle, xfrm)) {
 				saved++;
 			} else {
 				deleted++;
@@ -152,7 +134,7 @@ static void __flow_cache_shrink(struct flow_cache *fc,
 		}
 	}
 
-	flow_cache_queue_garbage(fcp, deleted, &gc_list);
+	flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm);
 }
 
 static void flow_cache_shrink(struct flow_cache *fc,
@@ -208,7 +190,7 @@ struct flow_cache_object *
 flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
 		  flow_resolve_t resolver, void *ctx)
 {
-	struct flow_cache *fc = &flow_cache_global;
+	struct flow_cache *fc = &net->xfrm.flow_cache_global;
 	struct flow_cache_percpu *fcp;
 	struct flow_cache_entry *fle, *tfle;
 	struct flow_cache_object *flo;
@@ -248,7 +230,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
 		if (fcp->hash_count > fc->high_watermark)
 			flow_cache_shrink(fc, fcp);
 
-		fle = kmem_cache_alloc(flow_cachep, GFP_ATOMIC);
+		fle = kmem_cache_alloc(net->xfrm.flow_cachep, GFP_ATOMIC);
 		if (fle) {
 			fle->net = net;
 			fle->family = family;
@@ -258,7 +240,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
 			hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]);
 			fcp->hash_count++;
 		}
-	} else if (likely(fle->genid == atomic_read(&flow_cache_genid))) {
+	} else if (likely(fle->genid == atomic_read(&net->xfrm.flow_cache_genid))) {
 		flo = fle->object;
 		if (!flo)
 			goto ret_object;
@@ -279,7 +261,7 @@ nocache:
 	}
 	flo = resolver(net, key, family, dir, flo, ctx);
 	if (fle) {
-		fle->genid = atomic_read(&flow_cache_genid);
+		fle->genid = atomic_read(&net->xfrm.flow_cache_genid);
 		if (!IS_ERR(flo))
 			fle->object = flo;
 		else
@@ -303,12 +285,14 @@ static void flow_cache_flush_tasklet(unsigned long data)
 	struct hlist_node *tmp;
 	LIST_HEAD(gc_list);
 	int i, deleted = 0;
+	struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
+						flow_cache_global);
 
 	fcp = this_cpu_ptr(fc->percpu);
 	for (i = 0; i < flow_cache_hash_size(fc); i++) {
 		hlist_for_each_entry_safe(fle, tmp,
 					  &fcp->hash_table[i], u.hlist) {
-			if (flow_entry_valid(fle))
+			if (flow_entry_valid(fle, xfrm))
 				continue;
 
 			deleted++;
@@ -317,7 +301,7 @@ static void flow_cache_flush_tasklet(unsigned long data)
 		}
 	}
 
-	flow_cache_queue_garbage(fcp, deleted, &gc_list);
+	flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm);
 
 	if (atomic_dec_and_test(&info->cpuleft))
 		complete(&info->completion);
@@ -351,10 +335,9 @@ static void flow_cache_flush_per_cpu(void *data)
 	tasklet_schedule(tasklet);
 }
 
-void flow_cache_flush(void)
+void flow_cache_flush(struct net *net)
 {
 	struct flow_flush_info info;
-	static DEFINE_MUTEX(flow_flush_sem);
 	cpumask_var_t mask;
 	int i, self;
 
@@ -365,8 +348,8 @@ void flow_cache_flush(void)
 
 	/* Don't want cpus going down or up during this. */
 	get_online_cpus();
-	mutex_lock(&flow_flush_sem);
-	info.cache = &flow_cache_global;
+	mutex_lock(&net->xfrm.flow_flush_sem);
+	info.cache = &net->xfrm.flow_cache_global;
 	for_each_online_cpu(i)
 		if (!flow_cache_percpu_empty(info.cache, i))
 			cpumask_set_cpu(i, mask);
@@ -386,21 +369,23 @@ void flow_cache_flush(void)
 	wait_for_completion(&info.completion);
 
 done:
-	mutex_unlock(&flow_flush_sem);
+	mutex_unlock(&net->xfrm.flow_flush_sem);
 	put_online_cpus();
 	free_cpumask_var(mask);
 }
 
 static void flow_cache_flush_task(struct work_struct *work)
 {
-	flow_cache_flush();
-}
+	struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
+						flow_cache_gc_work);
+	struct net *net = container_of(xfrm, struct net, xfrm);
 
-static DECLARE_WORK(flow_cache_flush_work, flow_cache_flush_task);
+	flow_cache_flush(net);
+}
 
-void flow_cache_flush_deferred(void)
+void flow_cache_flush_deferred(struct net *net)
 {
-	schedule_work(&flow_cache_flush_work);
+	schedule_work(&net->xfrm.flow_cache_flush_work);
 }
 
 static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu)
@@ -425,7 +410,8 @@ static int flow_cache_cpu(struct notifier_block *nfb,
 			  unsigned long action,
 			  void *hcpu)
 {
-	struct flow_cache *fc = container_of(nfb, struct flow_cache, hotcpu_notifier);
+	struct flow_cache *fc = container_of(nfb, struct flow_cache,
+						hotcpu_notifier);
 	int res, cpu = (unsigned long) hcpu;
 	struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
 
@@ -444,9 +430,20 @@ static int flow_cache_cpu(struct notifier_block *nfb,
 	return NOTIFY_OK;
 }
 
-static int __init flow_cache_init(struct flow_cache *fc)
+int flow_cache_init(struct net *net)
 {
 	int i;
+	struct flow_cache *fc = &net->xfrm.flow_cache_global;
+
+	/* Initialize per-net flow cache global variables here */
+	net->xfrm.flow_cachep = kmem_cache_create("flow_cache",
+					sizeof(struct flow_cache_entry),
+					0, SLAB_PANIC, NULL);
+	spin_lock_init(&net->xfrm.flow_cache_gc_lock);
+	INIT_LIST_HEAD(&net->xfrm.flow_cache_gc_list);
+	INIT_WORK(&net->xfrm.flow_cache_gc_work, flow_cache_gc_task);
+	INIT_WORK(&net->xfrm.flow_cache_flush_work, flow_cache_flush_task);
+	mutex_init(&net->xfrm.flow_flush_sem);
 
 	fc->hash_shift = 10;
 	fc->low_watermark = 2 * flow_cache_hash_size(fc);
@@ -484,14 +481,4 @@ err:
 
 	return -ENOMEM;
 }
-
-static int __init flow_cache_init_global(void)
-{
-	flow_cachep = kmem_cache_create("flow_cache",
-					sizeof(struct flow_cache_entry),
-					0, SLAB_PANIC, NULL);
-
-	return flow_cache_init(&flow_cache_global);
-}
-
-module_init(flow_cache_init_global);
+EXPORT_SYMBOL(flow_cache_init);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5976ef0846bd..f28c37996aad 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3281,6 +3281,32 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
 	return elt;
 }
 
+/* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given
+ * sglist without mark the sg which contain last skb data as the end.
+ * So the caller can mannipulate sg list as will when padding new data after
+ * the first call without calling sg_unmark_end to expend sg list.
+ *
+ * Scenario to use skb_to_sgvec_nomark:
+ * 1. sg_init_table
+ * 2. skb_to_sgvec_nomark(payload1)
+ * 3. skb_to_sgvec_nomark(payload2)
+ *
+ * This is equivalent to:
+ * 1. sg_init_table
+ * 2. skb_to_sgvec(payload1)
+ * 3. sg_unmark_end
+ * 4. skb_to_sgvec(payload2)
+ *
+ * When mapping mutilple payload conditionally, skb_to_sgvec_nomark
+ * is more preferable.
+ */
+int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg,
+			int offset, int len)
+{
+	return __skb_to_sgvec(skb, sg, offset, len);
+}
+EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark);
+
 int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
 {
 	int nsg = __skb_to_sgvec(skb, sg, offset, len);