xfrm: configure policy hash table thresholds by netlink

Enable to specify local and remote prefix length thresholds for the
policy hash table via a netlink XFRM_MSG_NEWSPDINFO message.

prefix length thresholds are specified by XFRMA_SPD_IPV4_HTHRESH and
XFRMA_SPD_IPV6_HTHRESH optional attributes (struct xfrmu_spdhthresh).

example:

    struct xfrmu_spdhthresh thresh4 = {
        .lbits = 0;
        .rbits = 24;
    };
    struct xfrmu_spdhthresh thresh6 = {
        .lbits = 0;
        .rbits = 56;
    };
    struct nlmsghdr *hdr;
    struct nl_msg *msg;

    msg = nlmsg_alloc();
    hdr = nlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, XFRMA_SPD_IPV4_HTHRESH, sizeof(__u32), NLM_F_REQUEST);
    nla_put(msg, XFRMA_SPD_IPV4_HTHRESH, sizeof(thresh4), &thresh4);
    nla_put(msg, XFRMA_SPD_IPV6_HTHRESH, sizeof(thresh6), &thresh6);
    nla_send_auto(sk, msg);

The numbers are the policy selector minimum prefix lengths to put a
policy in the hash table.

- lbits is the local threshold (source address for out policies,
  destination address for in and fwd policies).

- rbits is the remote threshold (destination address for out
  policies, source address for in and fwd policies).

The default values are:

XFRMA_SPD_IPV4_HTHRESH: 32 32
XFRMA_SPD_IPV6_HTHRESH: 128 128

Dynamic re-building of the SPD is performed when the thresholds values
are changed.

The current thresholds can be read via a XFRM_MSG_GETSPDINFO request:
the kernel replies to XFRM_MSG_GETSPDINFO requests by an
XFRM_MSG_NEWSPDINFO message, with both attributes
XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH.

Signed-off-by: Christophe Gouault <christophe.gouault@6wind.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>

1 files changed, 87 insertions, 0 deletions

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index e6ff7b4046ea..55bcb8604bc6 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -566,6 +566,86 @@ static void xfrm_hash_resize(struct work_struct *work)
 	mutex_unlock(&hash_resize_mutex);
 }
 
+static void xfrm_hash_rebuild(struct work_struct *work)
+{
+	struct net *net = container_of(work, struct net,
+				       xfrm.policy_hthresh.work);
+	unsigned int hmask;
+	struct xfrm_policy *pol;
+	struct xfrm_policy *policy;
+	struct hlist_head *chain;
+	struct hlist_head *odst;
+	struct hlist_node *newpos;
+	int i;
+	int dir;
+	unsigned seq;
+	u8 lbits4, rbits4, lbits6, rbits6;
+
+	mutex_lock(&hash_resize_mutex);
+
+	/* read selector prefixlen thresholds */
+	do {
+		seq = read_seqbegin(&net->xfrm.policy_hthresh.lock);
+
+		lbits4 = net->xfrm.policy_hthresh.lbits4;
+		rbits4 = net->xfrm.policy_hthresh.rbits4;
+		lbits6 = net->xfrm.policy_hthresh.lbits6;
+		rbits6 = net->xfrm.policy_hthresh.rbits6;
+	} while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq));
+
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
+
+	/* reset the bydst and inexact table in all directions */
+	for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) {
+		INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]);
+		hmask = net->xfrm.policy_bydst[dir].hmask;
+		odst = net->xfrm.policy_bydst[dir].table;
+		for (i = hmask; i >= 0; i--)
+			INIT_HLIST_HEAD(odst + i);
+		if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
+			/* dir out => dst = remote, src = local */
+			net->xfrm.policy_bydst[dir].dbits4 = rbits4;
+			net->xfrm.policy_bydst[dir].sbits4 = lbits4;
+			net->xfrm.policy_bydst[dir].dbits6 = rbits6;
+			net->xfrm.policy_bydst[dir].sbits6 = lbits6;
+		} else {
+			/* dir in/fwd => dst = local, src = remote */
+			net->xfrm.policy_bydst[dir].dbits4 = lbits4;
+			net->xfrm.policy_bydst[dir].sbits4 = rbits4;
+			net->xfrm.policy_bydst[dir].dbits6 = lbits6;
+			net->xfrm.policy_bydst[dir].sbits6 = rbits6;
+		}
+	}
+
+	/* re-insert all policies by order of creation */
+	list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
+		newpos = NULL;
+		chain = policy_hash_bysel(net, &policy->selector,
+					  policy->family,
+					  xfrm_policy_id2dir(policy->index));
+		hlist_for_each_entry(pol, chain, bydst) {
+			if (policy->priority >= pol->priority)
+				newpos = &pol->bydst;
+			else
+				break;
+		}
+		if (newpos)
+			hlist_add_behind(&policy->bydst, newpos);
+		else
+			hlist_add_head(&policy->bydst, chain);
+	}
+
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
+
+	mutex_unlock(&hash_resize_mutex);
+}
+
+void xfrm_policy_hash_rebuild(struct net *net)
+{
+	schedule_work(&net->xfrm.policy_hthresh.work);
+}
+EXPORT_SYMBOL(xfrm_policy_hash_rebuild);
+
 /* Generate new index... KAME seems to generate them ordered by cost
  * of an absolute inpredictability of ordering of rules. This will not pass. */
 static u32 xfrm_gen_index(struct net *net, int dir, u32 index)
@@ -2872,9 +2952,16 @@ static int __net_init xfrm_policy_init(struct net *net)
 		htab->dbits6 = 128;
 		htab->sbits6 = 128;
 	}
+	net->xfrm.policy_hthresh.lbits4 = 32;
+	net->xfrm.policy_hthresh.rbits4 = 32;
+	net->xfrm.policy_hthresh.lbits6 = 128;
+	net->xfrm.policy_hthresh.rbits6 = 128;
+
+	seqlock_init(&net->xfrm.policy_hthresh.lock);
 
 	INIT_LIST_HEAD(&net->xfrm.policy_all);
 	INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize);
+	INIT_WORK(&net->xfrm.policy_hthresh.work, xfrm_hash_rebuild);
 	if (net_eq(net, &init_net))
 		register_netdevice_notifier(&xfrm_dev_notifier);
 	return 0;