Merge branch 'net-Kernel-side-filtering-for-route-dumps'

David Ahern says:

====================
net: Kernel side filtering for route dumps

Implement kernel side filtering of route dumps by protocol (e.g., which
routing daemon installed the route), route type (e.g., unicast), table
id and nexthop device.

iproute2 has been doing this filtering in userspace for years; pushing
the filters to the kernel side reduces the amount of data the kernel
sends and reduces wasted cycles on both sides processing unwanted data.
These initial options provide a huge improvement for efficiently
examining routes on large scale systems.

v2
- better handling of requests for a specific table. Rather than walking
  the hash of all tables, lookup the specific table and dump it
- refactor mr_rtm_dumproute moving the loop over the table into a
  helper that can be invoked directly
- add hook to return NLM_F_DUMP_FILTERED in DONE message to ensure
  it is returned even when the dump returns nothing
====================

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

4 files changed, 203 insertions, 59 deletions

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 0f1beceb47d5..5bf653f36911 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -802,10 +802,16 @@ errout:
 	return err;
 }
 
-int ip_valid_fib_dump_req(const struct nlmsghdr *nlh,
-			  struct netlink_ext_ack *extack)
+int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
+			  struct fib_dump_filter *filter,
+			  struct netlink_callback *cb)
 {
+	struct netlink_ext_ack *extack = cb->extack;
+	struct nlattr *tb[RTA_MAX + 1];
 	struct rtmsg *rtm;
+	int err, i;
+
+	ASSERT_RTNL();
 
 	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) {
 		NL_SET_ERR_MSG(extack, "Invalid header for FIB dump request");
@@ -814,8 +820,7 @@ int ip_valid_fib_dump_req(const struct nlmsghdr *nlh,
 
 	rtm = nlmsg_data(nlh);
 	if (rtm->rtm_dst_len || rtm->rtm_src_len  || rtm->rtm_tos   ||
-	    rtm->rtm_table   || rtm->rtm_protocol || rtm->rtm_scope ||
-	    rtm->rtm_type) {
+	    rtm->rtm_scope) {
 		NL_SET_ERR_MSG(extack, "Invalid values in header for FIB dump request");
 		return -EINVAL;
 	}
@@ -824,9 +829,42 @@ int ip_valid_fib_dump_req(const struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
-	if (nlmsg_attrlen(nlh, sizeof(*rtm))) {
-		NL_SET_ERR_MSG(extack, "Invalid data after header in FIB dump request");
-		return -EINVAL;
+	filter->flags    = rtm->rtm_flags;
+	filter->protocol = rtm->rtm_protocol;
+	filter->rt_type  = rtm->rtm_type;
+	filter->table_id = rtm->rtm_table;
+
+	err = nlmsg_parse_strict(nlh, sizeof(*rtm), tb, RTA_MAX,
+				 rtm_ipv4_policy, extack);
+	if (err < 0)
+		return err;
+
+	for (i = 0; i <= RTA_MAX; ++i) {
+		int ifindex;
+
+		if (!tb[i])
+			continue;
+
+		switch (i) {
+		case RTA_TABLE:
+			filter->table_id = nla_get_u32(tb[i]);
+			break;
+		case RTA_OIF:
+			ifindex = nla_get_u32(tb[i]);
+			filter->dev = __dev_get_by_index(net, ifindex);
+			if (!filter->dev)
+				return -ENODEV;
+			break;
+		default:
+			NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request");
+			return -EINVAL;
+		}
+	}
+
+	if (filter->flags || filter->protocol || filter->rt_type ||
+	    filter->table_id || filter->dev) {
+		filter->filter_set = 1;
+		cb->answer_flags = NLM_F_DUMP_FILTERED;
 	}
 
 	return 0;
@@ -837,6 +875,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	const struct nlmsghdr *nlh = cb->nlh;
 	struct net *net = sock_net(skb->sk);
+	struct fib_dump_filter filter = {};
 	unsigned int h, s_h;
 	unsigned int e = 0, s_e;
 	struct fib_table *tb;
@@ -844,15 +883,30 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	int dumped = 0, err;
 
 	if (cb->strict_check) {
-		err = ip_valid_fib_dump_req(nlh, cb->extack);
+		err = ip_valid_fib_dump_req(net, nlh, &filter, cb);
 		if (err < 0)
 			return err;
+	} else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) {
+		struct rtmsg *rtm = nlmsg_data(nlh);
+
+		filter.flags = rtm->rtm_flags & (RTM_F_PREFIX | RTM_F_CLONED);
 	}
 
-	if (nlmsg_len(nlh) >= sizeof(struct rtmsg) &&
-	    ((struct rtmsg *)nlmsg_data(nlh))->rtm_flags & RTM_F_CLONED)
+	/* fib entries are never clones and ipv4 does not use prefix flag */
+	if (filter.flags & (RTM_F_PREFIX | RTM_F_CLONED))
 		return skb->len;
 
+	if (filter.table_id) {
+		tb = fib_get_table(net, filter.table_id);
+		if (!tb) {
+			NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist");
+			return -ENOENT;
+		}
+
+		err = fib_table_dump(tb, skb, cb, &filter);
+		return skb->len ? : err;
+	}
+
 	s_h = cb->args[0];
 	s_e = cb->args[1];
 
@@ -867,7 +921,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 			if (dumped)
 				memset(&cb->args[2], 0, sizeof(cb->args) -
 						 2 * sizeof(cb->args[0]));
-			err = fib_table_dump(tb, skb, cb);
+			err = fib_table_dump(tb, skb, cb, &filter);
 			if (err < 0) {
 				if (likely(skb->len))
 					goto out;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 5bc0c89e81e4..237c9f72b265 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2003,12 +2003,17 @@ void fib_free_table(struct fib_table *tb)
 }
 
 static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb,
-			     struct sk_buff *skb, struct netlink_callback *cb)
+			     struct sk_buff *skb, struct netlink_callback *cb,
+			     struct fib_dump_filter *filter)
 {
+	unsigned int flags = NLM_F_MULTI;
 	__be32 xkey = htonl(l->key);
 	struct fib_alias *fa;
 	int i, s_i;
 
+	if (filter->filter_set)
+		flags |= NLM_F_DUMP_FILTERED;
+
 	s_i = cb->args[4];
 	i = 0;
 
@@ -2016,25 +2021,35 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb,
 	hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
 		int err;
 
-		if (i < s_i) {
-			i++;
-			continue;
-		}
+		if (i < s_i)
+			goto next;
 
-		if (tb->tb_id != fa->tb_id) {
-			i++;
-			continue;
+		if (tb->tb_id != fa->tb_id)
+			goto next;
+
+		if (filter->filter_set) {
+			if (filter->rt_type && fa->fa_type != filter->rt_type)
+				goto next;
+
+			if ((filter->protocol &&
+			     fa->fa_info->fib_protocol != filter->protocol))
+				goto next;
+
+			if (filter->dev &&
+			    !fib_info_nh_uses_dev(fa->fa_info, filter->dev))
+				goto next;
 		}
 
 		err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid,
 				    cb->nlh->nlmsg_seq, RTM_NEWROUTE,
 				    tb->tb_id, fa->fa_type,
 				    xkey, KEYLENGTH - fa->fa_slen,
-				    fa->fa_tos, fa->fa_info, NLM_F_MULTI);
+				    fa->fa_tos, fa->fa_info, flags);
 		if (err < 0) {
 			cb->args[4] = i;
 			return err;
 		}
+next:
 		i++;
 	}
 
@@ -2044,7 +2059,7 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb,
 
 /* rcu_read_lock needs to be hold by caller from readside */
 int fib_table_dump(struct fib_table *tb, struct sk_buff *skb,
-		   struct netlink_callback *cb)
+		   struct netlink_callback *cb, struct fib_dump_filter *filter)
 {
 	struct trie *t = (struct trie *)tb->tb_data;
 	struct key_vector *l, *tp = t->kv;
@@ -2057,7 +2072,7 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb,
 	while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
 		int err;
 
-		err = fn_trie_dump_leaf(l, tb, skb, cb);
+		err = fn_trie_dump_leaf(l, tb, skb, cb, filter);
 		if (err < 0) {
 			cb->args[3] = key;
 			cb->args[2] = count;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 91b0d5671649..7a3e2acda94c 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2527,15 +2527,31 @@ errout_free:
 
 static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	if (cb->strict_check) {
-		int err = ip_valid_fib_dump_req(cb->nlh, cb->extack);
+	struct fib_dump_filter filter = {};
+	int err;
 
+	if (cb->strict_check) {
+		err = ip_valid_fib_dump_req(sock_net(skb->sk), cb->nlh,
+					    &filter, cb);
 		if (err < 0)
 			return err;
 	}
 
+	if (filter.table_id) {
+		struct mr_table *mrt;
+
+		mrt = ipmr_get_table(sock_net(skb->sk), filter.table_id);
+		if (!mrt) {
+			NL_SET_ERR_MSG(cb->extack, "ipv4: MR table does not exist");
+			return -ENOENT;
+		}
+		err = mr_table_dump(mrt, skb, cb, _ipmr_fill_mroute,
+				    &mfc_unres_lock, &filter);
+		return skb->len ? : err;
+	}
+
 	return mr_rtm_dumproute(skb, cb, ipmr_mr_table_iter,
-				_ipmr_fill_mroute, &mfc_unres_lock);
+				_ipmr_fill_mroute, &mfc_unres_lock, &filter);
 }
 
 static const struct nla_policy rtm_ipmr_policy[RTA_MAX + 1] = {
diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c
index 1ad9aa62a97b..844806120f44 100644
--- a/net/ipv4/ipmr_base.c
+++ b/net/ipv4/ipmr_base.c
@@ -268,6 +268,83 @@ int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(mr_fill_mroute);
 
+static bool mr_mfc_uses_dev(const struct mr_table *mrt,
+			    const struct mr_mfc *c,
+			    const struct net_device *dev)
+{
+	int ct;
+
+	for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
+		if (VIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) {
+			const struct vif_device *vif;
+
+			vif = &mrt->vif_table[ct];
+			if (vif->dev == dev)
+				return true;
+		}
+	}
+	return false;
+}
+
+int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb,
+		  struct netlink_callback *cb,
+		  int (*fill)(struct mr_table *mrt, struct sk_buff *skb,
+			      u32 portid, u32 seq, struct mr_mfc *c,
+			      int cmd, int flags),
+		  spinlock_t *lock, struct fib_dump_filter *filter)
+{
+	unsigned int e = 0, s_e = cb->args[1];
+	unsigned int flags = NLM_F_MULTI;
+	struct mr_mfc *mfc;
+	int err;
+
+	if (filter->filter_set)
+		flags |= NLM_F_DUMP_FILTERED;
+
+	list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) {
+		if (e < s_e)
+			goto next_entry;
+		if (filter->dev &&
+		    !mr_mfc_uses_dev(mrt, mfc, filter->dev))
+			goto next_entry;
+
+		err = fill(mrt, skb, NETLINK_CB(cb->skb).portid,
+			   cb->nlh->nlmsg_seq, mfc, RTM_NEWROUTE, flags);
+		if (err < 0)
+			goto out;
+next_entry:
+		e++;
+	}
+	e = 0;
+	s_e = 0;
+
+	spin_lock_bh(lock);
+	list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) {
+		if (e < s_e)
+			goto next_entry2;
+		if (filter->dev &&
+		    !mr_mfc_uses_dev(mrt, mfc, filter->dev))
+			goto next_entry2;
+
+		err = fill(mrt, skb, NETLINK_CB(cb->skb).portid,
+			   cb->nlh->nlmsg_seq, mfc, RTM_NEWROUTE, flags);
+		if (err < 0) {
+			spin_unlock_bh(lock);
+			goto out;
+		}
+next_entry2:
+		e++;
+	}
+	spin_unlock_bh(lock);
+	err = 0;
+	e = 0;
+
+out:
+	cb->args[1] = e;
+	return err;
+}
+EXPORT_SYMBOL(mr_table_dump);
+
 int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb,
 		     struct mr_table *(*iter)(struct net *net,
 					      struct mr_table *mrt),
@@ -275,53 +352,35 @@ int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb,
 				 struct sk_buff *skb,
 				 u32 portid, u32 seq, struct mr_mfc *c,
 				 int cmd, int flags),
-		     spinlock_t *lock)
+		     spinlock_t *lock, struct fib_dump_filter *filter)
 {
-	unsigned int t = 0, e = 0, s_t = cb->args[0], s_e = cb->args[1];
+	unsigned int t = 0, s_t = cb->args[0];
 	struct net *net = sock_net(skb->sk);
 	struct mr_table *mrt;
-	struct mr_mfc *mfc;
+	int err;
+
+	/* multicast does not track protocol or have route type other
+	 * than RTN_MULTICAST
+	 */
+	if (filter->filter_set) {
+		if (filter->protocol || filter->flags ||
+		    (filter->rt_type && filter->rt_type != RTN_MULTICAST))
+			return skb->len;
+	}
 
 	rcu_read_lock();
 	for (mrt = iter(net, NULL); mrt; mrt = iter(net, mrt)) {
 		if (t < s_t)
 			goto next_table;
-		list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) {
-			if (e < s_e)
-				goto next_entry;
-			if (fill(mrt, skb, NETLINK_CB(cb->skb).portid,
-				 cb->nlh->nlmsg_seq, mfc,
-				 RTM_NEWROUTE, NLM_F_MULTI) < 0)
-				goto done;
-next_entry:
-			e++;
-		}
-		e = 0;
-		s_e = 0;
-
-		spin_lock_bh(lock);
-		list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) {
-			if (e < s_e)
-				goto next_entry2;
-			if (fill(mrt, skb, NETLINK_CB(cb->skb).portid,
-				 cb->nlh->nlmsg_seq, mfc,
-				 RTM_NEWROUTE, NLM_F_MULTI) < 0) {
-				spin_unlock_bh(lock);
-				goto done;
-			}
-next_entry2:
-			e++;
-		}
-		spin_unlock_bh(lock);
-		e = 0;
-		s_e = 0;
+
+		err = mr_table_dump(mrt, skb, cb, fill, lock, filter);
+		if (err < 0)
+			break;
 next_table:
 		t++;
 	}
-done:
 	rcu_read_unlock();
 
-	cb->args[1] = e;
 	cb->args[0] = t;
 
 	return skb->len;