Merge tag 'ipsec-next-2025-07-23' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next

Steffen Klassert says:

====================
pull request (net-next): ipsec-next 2025-07-23

1) Optimize to hold device only for the asynchronous decryption,
   where it is really needed.
   From Jianbo Liu.

2) Align our inbund SA lookup to RFC 4301. Only SPI and protocol
   should be used for an inbound SA lookup.
   From Aakash Kumar S.

3) Skip redundant statistics update for xfrm crypto offload.
   From Jianbo Liu.

Please pull or let me know if there are problems.

* tag 'ipsec-next-2025-07-23' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next:
  xfrm: Skip redundant statistics update for crypto offload
  xfrm: Duplicate SPI Handling
  xfrm: hold device only for the asynchronous decryption
====================

Link: https://patch.msgid.link/20250723080402.3439619-1-steffen.klassert@secunet.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

2 files changed, 58 insertions, 38 deletions

diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 7e6a71b9d6a3..c9ddef869aa5 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -503,6 +503,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		/* An encap_type of -1 indicates async resumption. */
 		if (encap_type == -1) {
 			async = 1;
+			dev_put(skb->dev);
 			seq = XFRM_SKB_CB(skb)->seq.input.low;
 			goto resume;
 		}
@@ -649,18 +650,18 @@ lock:
 		XFRM_SKB_CB(skb)->seq.input.low = seq;
 		XFRM_SKB_CB(skb)->seq.input.hi = seq_hi;
 
-		dev_hold(skb->dev);
-
-		if (crypto_done)
+		if (crypto_done) {
 			nexthdr = x->type_offload->input_tail(x, skb);
-		else
+		} else {
+			dev_hold(skb->dev);
+
 			nexthdr = x->type->input(x, skb);
+			if (nexthdr == -EINPROGRESS)
+				return 0;
 
-		if (nexthdr == -EINPROGRESS)
-			return 0;
+			dev_put(skb->dev);
+		}
 resume:
-		dev_put(skb->dev);
-
 		spin_lock(&x->lock);
 		if (nexthdr < 0) {
 			if (nexthdr == -EBADMSG) {
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 77cc418ad69e..f0f66405b39d 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1711,6 +1711,26 @@ struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi,
 }
 EXPORT_SYMBOL(xfrm_state_lookup_byspi);
 
+static struct xfrm_state *xfrm_state_lookup_spi_proto(struct net *net, __be32 spi, u8 proto)
+{
+	struct xfrm_state *x;
+	unsigned int i;
+
+	rcu_read_lock();
+	for (i = 0; i <= net->xfrm.state_hmask; i++) {
+		hlist_for_each_entry_rcu(x, &net->xfrm.state_byspi[i], byspi) {
+			if (x->id.spi == spi && x->id.proto == proto) {
+				if (!xfrm_state_hold_rcu(x))
+					continue;
+				rcu_read_unlock();
+				return x;
+			}
+		}
+	}
+	rcu_read_unlock();
+	return NULL;
+}
+
 static void __xfrm_state_insert(struct xfrm_state *x)
 {
 	struct net *net = xs_net(x);
@@ -2262,7 +2282,12 @@ EXPORT_SYMBOL(xfrm_state_update);
 
 int xfrm_state_check_expire(struct xfrm_state *x)
 {
-	xfrm_dev_state_update_stats(x);
+	/* All counters which are needed to decide if state is expired
+	 * are handled by SW for non-packet offload modes. Simply skip
+	 * the following update and save extra boilerplate in drivers.
+	 */
+	if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET)
+		xfrm_dev_state_update_stats(x);
 
 	if (!READ_ONCE(x->curlft.use_time))
 		WRITE_ONCE(x->curlft.use_time, ktime_get_real_seconds());
@@ -2555,10 +2580,8 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high,
 	unsigned int h;
 	struct xfrm_state *x0;
 	int err = -ENOENT;
-	__be32 minspi = htonl(low);
-	__be32 maxspi = htonl(high);
+	u32 range = high - low + 1;
 	__be32 newspi = 0;
-	u32 mark = x->mark.v & x->mark.m;
 
 	spin_lock_bh(&x->lock);
 	if (x->km.state == XFRM_STATE_DEAD) {
@@ -2572,38 +2595,34 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high,
 
 	err = -ENOENT;
 
-	if (minspi == maxspi) {
-		x0 = xfrm_state_lookup(net, mark, &x->id.daddr, minspi, x->id.proto, x->props.family);
-		if (x0) {
-			NL_SET_ERR_MSG(extack, "Requested SPI is already in use");
-			xfrm_state_put(x0);
+	for (h = 0; h < range; h++) {
+		u32 spi = (low == high) ? low : get_random_u32_inclusive(low, high);
+		newspi = htonl(spi);
+
+		spin_lock_bh(&net->xfrm.xfrm_state_lock);
+		x0 = xfrm_state_lookup_spi_proto(net, newspi, x->id.proto);
+		if (!x0) {
+			x->id.spi = newspi;
+			h = xfrm_spi_hash(net, &x->id.daddr, newspi, x->id.proto, x->props.family);
+			XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h, x->xso.type);
+			spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+			err = 0;
 			goto unlock;
 		}
-		newspi = minspi;
-	} else {
-		u32 spi = 0;
-		for (h = 0; h < high-low+1; h++) {
-			spi = get_random_u32_inclusive(low, high);
-			x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
-			if (x0 == NULL) {
-				newspi = htonl(spi);
-				break;
-			}
-			xfrm_state_put(x0);
+		xfrm_state_put(x0);
+		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+		if (signal_pending(current)) {
+			err = -ERESTARTSYS;
+			goto unlock;
 		}
+
+		if (low == high)
+			break;
 	}
-	if (newspi) {
-		spin_lock_bh(&net->xfrm.xfrm_state_lock);
-		x->id.spi = newspi;
-		h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family);
-		XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h,
-				  x->xso.type);
-		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
-		err = 0;
-	} else {
+	if (err)
 		NL_SET_ERR_MSG(extack, "No SPI available in the requested range");
-	}
 
 unlock:
 	spin_unlock_bh(&x->lock);