net: fib6: convert cfg metric to u32 outside of table write lock

Do the nla validation earlier, outside the write lock.

This is needed by followup patch which needs to be able to call
request_module (which can sleep) if needed.

Joint work with Daniel Borkmann.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/ip6_fib.h

@@ -74,6 +74,11 @@ struct fib6_node {
 #define FIB6_SUBTREE(fn)	((fn)->subtree)
 #endif
 
+struct mx6_config {
+	const u32 *mx;
+	DECLARE_BITMAP(mx_valid, RTAX_MAX);
+};
+
 /*
  *	routing information
  *
@@ -291,9 +296,8 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
 void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
 		    void *arg);
 
-int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
-	     struct nlattr *mx, int mx_len);
-
+int fib6_add(struct fib6_node *root, struct rt6_info *rt,
+	     struct nl_info *info, struct mx6_config *mxc);
 int fib6_del(struct rt6_info *rt, struct nl_info *info);
 
 void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info);

net/ipv6/ip6_fib.c

@@ -630,31 +630,35 @@ static bool rt6_qualify_for_ecmp(struct rt6_info *rt)
 	       RTF_GATEWAY;
 }
 
-static int fib6_commit_metrics(struct dst_entry *dst,
-			       struct nlattr *mx, int mx_len)
+static void fib6_copy_metrics(u32 *mp, const struct mx6_config *mxc)
 {
-	bool dst_host = dst->flags & DST_HOST;
-	struct nlattr *nla;
-	int remaining;
-	u32 *mp;
+	int i;
 
-	mp = dst_host ? dst_metrics_write_ptr(dst) :
-			kzalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC);
-	if (unlikely(!mp))
-		return -ENOMEM;
-	if (!dst_host)
-		dst_init_metrics(dst, mp, 0);
+	for (i = 0; i < RTAX_MAX; i++) {
+		if (test_bit(i, mxc->mx_valid))
+			mp[i] = mxc->mx[i];
+	}
+}
+
+static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc)
+{
+	if (!mxc->mx)
+		return 0;
 
-	nla_for_each_attr(nla, mx, mx_len, remaining) {
-		int type = nla_type(nla);
+	if (dst->flags & DST_HOST) {
+		u32 *mp = dst_metrics_write_ptr(dst);
 
-		if (type) {
-			if (type > RTAX_MAX)
-				return -EINVAL;
+		if (unlikely(!mp))
+			return -ENOMEM;
 
-			mp[type - 1] = nla_get_u32(nla);
-		}
+		fib6_copy_metrics(mp, mxc);
+	} else {
+		dst_init_metrics(dst, mxc->mx, false);
+
+		/* We've stolen mx now. */
+		mxc->mx = NULL;
 	}
+
 	return 0;
 }
 
@@ -663,7 +667,7 @@ static int fib6_commit_metrics(struct dst_entry *dst,
  */
 
 static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
-			    struct nl_info *info, struct nlattr *mx, int mx_len)
+			    struct nl_info *info, struct mx6_config *mxc)
 {
 	struct rt6_info *iter = NULL;
 	struct rt6_info **ins;
@@ -772,11 +776,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 			pr_warn("NLM_F_CREATE should be set when creating new route\n");
 
 add:
-		if (mx) {
-			err = fib6_commit_metrics(&rt->dst, mx, mx_len);
-			if (err)
-				return err;
-		}
+		err = fib6_commit_metrics(&rt->dst, mxc);
+		if (err)
+			return err;
+
 		rt->dst.rt6_next = iter;
 		*ins = rt;
 		rt->rt6i_node = fn;
@@ -796,11 +799,11 @@ add:
 			pr_warn("NLM_F_REPLACE set, but no existing node found!\n");
 			return -ENOENT;
 		}
-		if (mx) {
-			err = fib6_commit_metrics(&rt->dst, mx, mx_len);
-			if (err)
-				return err;
-		}
+
+		err = fib6_commit_metrics(&rt->dst, mxc);
+		if (err)
+			return err;
+
 		*ins = rt;
 		rt->rt6i_node = fn;
 		rt->dst.rt6_next = iter->dst.rt6_next;
@@ -837,8 +840,8 @@ void fib6_force_start_gc(struct net *net)
  *	with source addr info in sub-trees
  */
 
-int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
-	     struct nlattr *mx, int mx_len)
+int fib6_add(struct fib6_node *root, struct rt6_info *rt,
+	     struct nl_info *info, struct mx6_config *mxc)
 {
 	struct fib6_node *fn, *pn = NULL;
 	int err = -ENOMEM;
@@ -933,7 +936,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
 	}
 #endif
 
-	err = fib6_add_rt2node(fn, rt, info, mx, mx_len);
+	err = fib6_add_rt2node(fn, rt, info, mxc);
 	if (!err) {
 		fib6_start_gc(info->nl_net, rt);
 		if (!(rt->rt6i_flags & RTF_CACHE))

net/ipv6/route.c

@@ -853,14 +853,14 @@ EXPORT_SYMBOL(rt6_lookup);
  */
 
 static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
-			struct nlattr *mx, int mx_len)
+			struct mx6_config *mxc)
 {
 	int err;
 	struct fib6_table *table;
 
 	table = rt->rt6i_table;
 	write_lock_bh(&table->tb6_lock);
-	err = fib6_add(&table->tb6_root, rt, info, mx, mx_len);
+	err = fib6_add(&table->tb6_root, rt, info, mxc);
 	write_unlock_bh(&table->tb6_lock);
 
 	return err;
@@ -868,10 +868,10 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
 
 int ip6_ins_rt(struct rt6_info *rt)
 {
-	struct nl_info info = {
-		.nl_net = dev_net(rt->dst.dev),
-	};
-	return __ip6_ins_rt(rt, &info, NULL, 0);
+	struct nl_info info = {	.nl_net = dev_net(rt->dst.dev), };
+	struct mx6_config mxc = { .mx = NULL, };
+
+	return __ip6_ins_rt(rt, &info, &mxc);
 }
 
 static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
@@ -1470,9 +1470,39 @@ out:
 	return entries > rt_max_size;
 }
 
-/*
- *
- */
+static int ip6_convert_metrics(struct mx6_config *mxc,
+			       const struct fib6_config *cfg)
+{
+	struct nlattr *nla;
+	int remaining;
+	u32 *mp;
+
+	if (cfg->fc_mx == NULL)
+		return 0;
+
+	mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
+	if (unlikely(!mp))
+		return -ENOMEM;
+
+	nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
+		int type = nla_type(nla);
+
+		if (type) {
+			if (unlikely(type > RTAX_MAX))
+				goto err;
+
+			mp[type - 1] = nla_get_u32(nla);
+			__set_bit(type - 1, mxc->mx_valid);
+		}
+	}
+
+	mxc->mx = mp;
+
+	return 0;
+ err:
+	kfree(mp);
+	return -EINVAL;
+}
 
 int ip6_route_add(struct fib6_config *cfg)
 {
@@ -1482,6 +1512,7 @@ int ip6_route_add(struct fib6_config *cfg)
 	struct net_device *dev = NULL;
 	struct inet6_dev *idev = NULL;
 	struct fib6_table *table;
+	struct mx6_config mxc = { .mx = NULL, };
 	int addr_type;
 
 	if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
@@ -1677,8 +1708,14 @@ install_route:
 
 	cfg->fc_nlinfo.nl_net = dev_net(dev);
 
-	return __ip6_ins_rt(rt, &cfg->fc_nlinfo, cfg->fc_mx, cfg->fc_mx_len);
+	err = ip6_convert_metrics(&mxc, cfg);
+	if (err)
+		goto out;
+
+	err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc);
 
+	kfree(mxc.mx);
+	return err;
 out:
 	if (dev)
 		dev_put(dev);