Merge tag 'ipsec-next-2025-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next

Steffen Klassert says:

====================
pull request (net-next): ipsec-next 2025-11-18

1) Relax a lock contention bottleneck to improve IPsec crypto
   offload performance. From Jianbo Liu.

2) Deprecate pfkey, the interface will be removed in 2027.

3) Update xfrm documentation and move it to ipsec maintainance.
   From Bagas Sanjaya.

* tag 'ipsec-next-2025-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next:
  MAINTAINERS: Add entry for XFRM documentation
  net: Move XFRM documentation into its own subdirectory
  Documentation: xfrm_sync: Number the fifth section
  Documentation: xfrm_sysctl: Trim trailing colon in section heading
  Documentation: xfrm_sync: Trim excess section heading characters
  Documentation: xfrm_sync: Properly reindent list text
  Documentation: xfrm_device: Separate hardware offload sublists
  Documentation: xfrm_device: Use numbered list for offloading steps
  Documentation: xfrm_device: Wrap iproute2 snippets in literal code block
  pfkey: Deprecate pfkey
  xfrm: Skip redundant replay recheck for the hardware offload path
  xfrm: Refactor xfrm_input lock to reduce contention with RSS
====================

Link: https://patch.msgid.link/20251118092610.2223552-1-steffen.klassert@secunet.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 24 insertions, 19 deletions

diff --git a/net/key/af_key.c b/net/key/af_key.c
index 2ebde0352245..571200433aa9 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3903,6 +3903,8 @@ static int __init ipsec_pfkey_init(void)
 {
 	int err = proto_register(&key_proto, 0);
 
+	pr_warn_once("PFKEY is deprecated and scheduled to be removed in 2027, "
+	             "please contact the netdev mailing list\n");
 	if (err != 0)
 		goto out;
 
diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig
index f0157702718f..4a62817a88f8 100644
--- a/net/xfrm/Kconfig
+++ b/net/xfrm/Kconfig
@@ -110,14 +110,17 @@ config XFRM_IPCOMP
 	select CRYPTO_DEFLATE
 
 config NET_KEY
-	tristate "PF_KEY sockets"
+	tristate "PF_KEY sockets (deprecated)"
 	select XFRM_ALGO
 	help
 	  PF_KEYv2 socket family, compatible to KAME ones.
-	  They are required if you are going to use IPsec tools ported
-	  from KAME.
 
-	  Say Y unless you know what you are doing.
+	  The PF_KEYv2 socket interface is deprecated and
+	  scheduled for removal. All maintained IKE daemons
+	  no longer need PF_KEY sockets. Please use the netlink
+	  interface (XFRM_USER) to configure IPsec.
+
+	  If unsure, say N.
 
 config NET_KEY_MIGRATE
 	bool "PF_KEY MIGRATE"
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index c9ddef869aa5..4ed346e682c7 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -505,6 +505,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 			async = 1;
 			dev_put(skb->dev);
 			seq = XFRM_SKB_CB(skb)->seq.input.low;
+			spin_lock(&x->lock);
 			goto resume;
 		}
 		/* GRO call */
@@ -541,9 +542,11 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 				XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
 				goto drop;
 			}
+
+			nexthdr = x->type_offload->input_tail(x, skb);
 		}
 
-		goto lock;
+		goto process;
 	}
 
 	family = XFRM_SPI_SKB_CB(skb)->family;
@@ -611,7 +614,12 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 			goto drop;
 		}
 
-lock:
+process:
+		seq_hi = htonl(xfrm_replay_seqhi(x, seq));
+
+		XFRM_SKB_CB(skb)->seq.input.low = seq;
+		XFRM_SKB_CB(skb)->seq.input.hi = seq_hi;
+
 		spin_lock(&x->lock);
 
 		if (unlikely(x->km.state != XFRM_STATE_VALID)) {
@@ -638,21 +646,13 @@ lock:
 			goto drop_unlock;
 		}
 
-		spin_unlock(&x->lock);
-
 		if (xfrm_tunnel_check(skb, x, family)) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
-			goto drop;
+			goto drop_unlock;
 		}
 
-		seq_hi = htonl(xfrm_replay_seqhi(x, seq));
-
-		XFRM_SKB_CB(skb)->seq.input.low = seq;
-		XFRM_SKB_CB(skb)->seq.input.hi = seq_hi;
-
-		if (crypto_done) {
-			nexthdr = x->type_offload->input_tail(x, skb);
-		} else {
+		if (!crypto_done) {
+			spin_unlock(&x->lock);
 			dev_hold(skb->dev);
 
 			nexthdr = x->type->input(x, skb);
@@ -660,9 +660,9 @@ lock:
 				return 0;
 
 			dev_put(skb->dev);
+			spin_lock(&x->lock);
 		}
 resume:
-		spin_lock(&x->lock);
 		if (nexthdr < 0) {
 			if (nexthdr == -EBADMSG) {
 				xfrm_audit_state_icvfail(x, skb,
@@ -676,7 +676,7 @@ resume:
 		/* only the first xfrm gets the encap type */
 		encap_type = 0;
 
-		if (xfrm_replay_recheck(x, skb, seq)) {
+		if (!crypto_done && xfrm_replay_recheck(x, skb, seq)) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR);
 			goto drop_unlock;
 		}