Merge tag 'ipsec-2025-01-27' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec

Steffen Klassert says:

====================
pull request (net): ipsec 2025-01-27

1) Fix incrementing the upper 32 bit sequence numbers for GSO skbs.
   From Jianbo Liu.

2) Fix an out-of-bounds read on xfrm state lookup.
   From Florian Westphal.

3) Fix secpath handling on packet offload mode.
   From Alexandre Cassen.

4) Fix the usage of skb->sk in the xfrm layer.

5) Don't disable preemption while looking up cache state
   to fix PREEMPT_RT.
   From Sebastian Sewior.

* tag 'ipsec-2025-01-27' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec:
  xfrm: Don't disable preemption while looking up cache state.
  xfrm: Fix the usage of skb->sk
  xfrm: delete intermediate secpath entry in packet offload mode
  xfrm: state: fix out-of-bounds read during lookup
  xfrm: replay: Fix the update of replay_esn->oseq_hi for GSO
====================

Link: https://patch.msgid.link/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

include/net/xfrm.h

@@ -1268,9 +1268,19 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir,
 
 	if (xo) {
 		x = xfrm_input_state(skb);
-		if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET)
-			return (xo->flags & CRYPTO_DONE) &&
-			       (xo->status & CRYPTO_SUCCESS);
+		if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) {
+			bool check = (xo->flags & CRYPTO_DONE) &&
+				     (xo->status & CRYPTO_SUCCESS);
+
+			/* The packets here are plain ones and secpath was
+			 * needed to indicate that hardware already handled
+			 * them and there is no need to do nothing in addition.
+			 *
+			 * Consume secpath which was set by drivers.
+			 */
+			secpath_reset(skb);
+			return check;
+		}
 	}
 
 	return __xfrm_check_nopolicy(net, skb, dir) ||

net/ipv4/esp4.c

@@ -279,7 +279,7 @@ static void esp_output_done(void *data, int err)
 		    x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
 			esp_output_tail_tcp(x, skb);
 		else
-			xfrm_output_resume(skb->sk, skb, err);
+			xfrm_output_resume(skb_to_full_sk(skb), skb, err);
 	}
 }
 

net/ipv6/esp6.c

@@ -315,7 +315,7 @@ static void esp_output_done(void *data, int err)
 		    x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
 			esp_output_tail_tcp(x, skb);
 		else
-			xfrm_output_resume(skb->sk, skb, err);
+			xfrm_output_resume(skb_to_full_sk(skb), skb, err);
 	}
 }
 

net/ipv6/xfrm6_output.c

@@ -82,14 +82,14 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 
 	toobig = skb->len > mtu && !skb_is_gso(skb);
 
-	if (toobig && xfrm6_local_dontfrag(skb->sk)) {
+	if (toobig && xfrm6_local_dontfrag(sk)) {
 		xfrm6_local_rxpmtu(skb, mtu);
 		kfree_skb(skb);
 		return -EMSGSIZE;
 	} else if (toobig && xfrm6_noneed_fragment(skb)) {
 		skb->ignore_df = 1;
 		goto skip_frag;
-	} else if (!skb->ignore_df && toobig && skb->sk) {
+	} else if (!skb->ignore_df && toobig && sk) {
 		xfrm_local_error(skb, mtu);
 		kfree_skb(skb);
 		return -EMSGSIZE;

net/xfrm/xfrm_interface_core.c

@@ -506,7 +506,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 	skb_dst_set(skb, dst);
 	skb->dev = tdev;
 
-	err = dst_output(xi->net, skb->sk, skb);
+	err = dst_output(xi->net, skb_to_full_sk(skb), skb);
 	if (net_xmit_eval(err) == 0) {
 		dev_sw_netstats_tx_add(dev, 1, length);
 	} else {

net/xfrm/xfrm_output.c

@@ -802,7 +802,7 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb)
 	     !skb_gso_validate_network_len(skb, ip_skb_dst_mtu(skb->sk, skb)))) {
 		skb->protocol = htons(ETH_P_IP);
 
-		if (skb->sk)
+		if (skb->sk && sk_fullsock(skb->sk))
 			xfrm_local_error(skb, mtu);
 		else
 			icmp_send(skb, ICMP_DEST_UNREACH,
@@ -838,6 +838,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb)
 {
 	int mtu, ret = 0;
 	struct dst_entry *dst = skb_dst(skb);
+	struct sock *sk = skb_to_full_sk(skb);
 
 	if (skb->ignore_df)
 		goto out;
@@ -852,9 +853,9 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb)
 		skb->dev = dst->dev;
 		skb->protocol = htons(ETH_P_IPV6);
 
-		if (xfrm6_local_dontfrag(skb->sk))
+		if (xfrm6_local_dontfrag(sk))
 			ipv6_stub->xfrm6_local_rxpmtu(skb, mtu);
-		else if (skb->sk)
+		else if (sk)
 			xfrm_local_error(skb, mtu);
 		else
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);

net/xfrm/xfrm_policy.c

@@ -2964,7 +2964,7 @@ static void xfrm_policy_queue_process(struct timer_list *t)
 		skb_dst_drop(skb);
 		skb_dst_set(skb, dst);
 
-		dst_output(net, skb->sk, skb);
+		dst_output(net, skb_to_full_sk(skb), skb);
 	}
 
 out:

net/xfrm/xfrm_replay.c

@@ -714,10 +714,12 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff
 			oseq += skb_shinfo(skb)->gso_segs;
 		}
 
-		if (unlikely(xo->seq.low < replay_esn->oseq)) {
-			XFRM_SKB_CB(skb)->seq.output.hi = ++oseq_hi;
-			xo->seq.hi = oseq_hi;
-			replay_esn->oseq_hi = oseq_hi;
+		if (unlikely(oseq < replay_esn->oseq)) {
+			replay_esn->oseq_hi = ++oseq_hi;
+			if (xo->seq.low < replay_esn->oseq) {
+				XFRM_SKB_CB(skb)->seq.output.hi = oseq_hi;
+				xo->seq.hi = oseq_hi;
+			}
 			if (replay_esn->oseq_hi == 0) {
 				replay_esn->oseq--;
 				replay_esn->oseq_hi--;

net/xfrm/xfrm_state.c

@@ -34,6 +34,8 @@
 
 #define xfrm_state_deref_prot(table, net) \
 	rcu_dereference_protected((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock))
+#define xfrm_state_deref_check(table, net) \
+	rcu_dereference_check((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock))
 
 static void xfrm_state_gc_task(struct work_struct *work);
 
@@ -62,6 +64,8 @@ static inline unsigned int xfrm_dst_hash(struct net *net,
 					 u32 reqid,
 					 unsigned short family)
 {
+	lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
 	return __xfrm_dst_hash(daddr, saddr, reqid, family, net->xfrm.state_hmask);
 }
 
@@ -70,18 +74,24 @@ static inline unsigned int xfrm_src_hash(struct net *net,
 					 const xfrm_address_t *saddr,
 					 unsigned short family)
 {
+	lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
 	return __xfrm_src_hash(daddr, saddr, family, net->xfrm.state_hmask);
 }
 
 static inline unsigned int
 xfrm_spi_hash(struct net *net, const xfrm_address_t *daddr,
 	      __be32 spi, u8 proto, unsigned short family)
 {
+	lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
 	return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask);
 }
 
 static unsigned int xfrm_seq_hash(struct net *net, u32 seq)
 {
+	lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
 	return __xfrm_seq_hash(seq, net->xfrm.state_hmask);
 }
 
@@ -1108,16 +1118,38 @@ xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl,
 	x->props.family = tmpl->encap_family;
 }
 
-static struct xfrm_state *__xfrm_state_lookup_all(struct net *net, u32 mark,
+struct xfrm_hash_state_ptrs {
+	const struct hlist_head *bydst;
+	const struct hlist_head *bysrc;
+	const struct hlist_head *byspi;
+	unsigned int hmask;
+};
+
+static void xfrm_hash_ptrs_get(const struct net *net, struct xfrm_hash_state_ptrs *ptrs)
+{
+	unsigned int sequence;
+
+	do {
+		sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation);
+
+		ptrs->bydst = xfrm_state_deref_check(net->xfrm.state_bydst, net);
+		ptrs->bysrc = xfrm_state_deref_check(net->xfrm.state_bysrc, net);
+		ptrs->byspi = xfrm_state_deref_check(net->xfrm.state_byspi, net);
+		ptrs->hmask = net->xfrm.state_hmask;
+	} while (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence));
+}
+
+static struct xfrm_state *__xfrm_state_lookup_all(const struct xfrm_hash_state_ptrs *state_ptrs,
+						  u32 mark,
 						  const xfrm_address_t *daddr,
 						  __be32 spi, u8 proto,
 						  unsigned short family,
 						  struct xfrm_dev_offload *xdo)
 {
-	unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family);
+	unsigned int h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs->hmask);
 	struct xfrm_state *x;
 
-	hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) {
+	hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) {
 #ifdef CONFIG_XFRM_OFFLOAD
 		if (xdo->type == XFRM_DEV_OFFLOAD_PACKET) {
 			if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
@@ -1151,15 +1183,16 @@ static struct xfrm_state *__xfrm_state_lookup_all(struct net *net, u32 mark,
 	return NULL;
 }
 
-static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark,
+static struct xfrm_state *__xfrm_state_lookup(const struct xfrm_hash_state_ptrs *state_ptrs,
+					      u32 mark,
 					      const xfrm_address_t *daddr,
 					      __be32 spi, u8 proto,
 					      unsigned short family)
 {
-	unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family);
+	unsigned int h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs->hmask);
 	struct xfrm_state *x;
 
-	hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) {
+	hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) {
 		if (x->props.family != family ||
 		    x->id.spi       != spi ||
 		    x->id.proto     != proto ||
@@ -1181,11 +1214,11 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
 					   __be32 spi, u8 proto,
 					   unsigned short family)
 {
+	struct xfrm_hash_state_ptrs state_ptrs;
 	struct hlist_head *state_cache_input;
 	struct xfrm_state *x = NULL;
-	int cpu = get_cpu();
 
-	state_cache_input =  per_cpu_ptr(net->xfrm.state_cache_input, cpu);
+	state_cache_input = raw_cpu_ptr(net->xfrm.state_cache_input);
 
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(x, state_cache_input, state_cache_input) {
@@ -1202,7 +1235,9 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
 		goto out;
 	}
 
-	x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family);
+	xfrm_hash_ptrs_get(net, &state_ptrs);
+
+	x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family);
 
 	if (x && x->km.state == XFRM_STATE_VALID) {
 		spin_lock_bh(&net->xfrm.xfrm_state_lock);
@@ -1217,20 +1252,20 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
 
 out:
 	rcu_read_unlock();
-	put_cpu();
 	return x;
 }
 EXPORT_SYMBOL(xfrm_input_state_lookup);
 
-static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark,
+static struct xfrm_state *__xfrm_state_lookup_byaddr(const struct xfrm_hash_state_ptrs *state_ptrs,
+						     u32 mark,
 						     const xfrm_address_t *daddr,
 						     const xfrm_address_t *saddr,
 						     u8 proto, unsigned short family)
 {
-	unsigned int h = xfrm_src_hash(net, daddr, saddr, family);
+	unsigned int h = __xfrm_src_hash(daddr, saddr, family, state_ptrs->hmask);
 	struct xfrm_state *x;
 
-	hlist_for_each_entry_rcu(x, net->xfrm.state_bysrc + h, bysrc) {
+	hlist_for_each_entry_rcu(x, state_ptrs->bysrc + h, bysrc) {
 		if (x->props.family != family ||
 		    x->id.proto     != proto ||
 		    !xfrm_addr_equal(&x->id.daddr, daddr, family) ||
@@ -1250,14 +1285,17 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark,
 static inline struct xfrm_state *
 __xfrm_state_locate(struct xfrm_state *x, int use_spi, int family)
 {
+	struct xfrm_hash_state_ptrs state_ptrs;
 	struct net *net = xs_net(x);
 	u32 mark = x->mark.v & x->mark.m;
 
+	xfrm_hash_ptrs_get(net, &state_ptrs);
+
 	if (use_spi)
-		return __xfrm_state_lookup(net, mark, &x->id.daddr,
+		return __xfrm_state_lookup(&state_ptrs, mark, &x->id.daddr,
 					   x->id.spi, x->id.proto, family);
 	else
-		return __xfrm_state_lookup_byaddr(net, mark,
+		return __xfrm_state_lookup_byaddr(&state_ptrs, mark,
 						  &x->id.daddr,
 						  &x->props.saddr,
 						  x->id.proto, family);
@@ -1331,6 +1369,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 		unsigned short family, u32 if_id)
 {
 	static xfrm_address_t saddr_wildcard = { };
+	struct xfrm_hash_state_ptrs state_ptrs;
 	struct net *net = xp_net(pol);
 	unsigned int h, h_wildcard;
 	struct xfrm_state *x, *x0, *to_put;
@@ -1395,8 +1434,10 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 	else if (acquire_in_progress) /* XXX: acquire_in_progress should not happen */
 		WARN_ON(1);
 
-	h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
-	hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) {
+	xfrm_hash_ptrs_get(net, &state_ptrs);
+
+	h = __xfrm_dst_hash(daddr, saddr, tmpl->reqid, encap_family, state_ptrs.hmask);
+	hlist_for_each_entry_rcu(x, state_ptrs.bydst + h, bydst) {
 #ifdef CONFIG_XFRM_OFFLOAD
 		if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
 			if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
@@ -1429,8 +1470,9 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 	if (best || acquire_in_progress)
 		goto found;
 
-	h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family);
-	hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h_wildcard, bydst) {
+	h_wildcard = __xfrm_dst_hash(daddr, &saddr_wildcard, tmpl->reqid,
+				     encap_family, state_ptrs.hmask);
+	hlist_for_each_entry_rcu(x, state_ptrs.bydst + h_wildcard, bydst) {
 #ifdef CONFIG_XFRM_OFFLOAD
 		if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
 			if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
@@ -1468,7 +1510,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 
 	if (!x && !error && !acquire_in_progress) {
 		if (tmpl->id.spi &&
-		    (x0 = __xfrm_state_lookup_all(net, mark, daddr,
+		    (x0 = __xfrm_state_lookup_all(&state_ptrs, mark, daddr,
 						  tmpl->id.spi, tmpl->id.proto,
 						  encap_family,
 						  &pol->xdo)) != NULL) {
@@ -2253,10 +2295,13 @@ struct xfrm_state *
 xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi,
 		  u8 proto, unsigned short family)
 {
+	struct xfrm_hash_state_ptrs state_ptrs;
 	struct xfrm_state *x;
 
 	rcu_read_lock();
-	x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family);
+	xfrm_hash_ptrs_get(net, &state_ptrs);
+
+	x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family);
 	rcu_read_unlock();
 	return x;
 }
@@ -2267,10 +2312,14 @@ xfrm_state_lookup_byaddr(struct net *net, u32 mark,
 			 const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 			 u8 proto, unsigned short family)
 {
+	struct xfrm_hash_state_ptrs state_ptrs;
 	struct xfrm_state *x;
 
 	spin_lock_bh(&net->xfrm.xfrm_state_lock);
-	x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family);
+
+	xfrm_hash_ptrs_get(net, &state_ptrs);
+
+	x = __xfrm_state_lookup_byaddr(&state_ptrs, mark, daddr, saddr, proto, family);
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	return x;
 }