Merge v6.16.2linux-rolling-stable

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

7 files changed, 98 insertions, 83 deletions

diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index a6c289858401..c7a1f080d2de 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -145,10 +145,6 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur
 		return NULL;
 	}
 
-	/* This skb was already validated on the upper/virtual dev */
-	if ((x->xso.dev != dev) && (x->xso.real_dev == dev))
-		return skb;
-
 	local_irq_save(flags);
 	sd = this_cpu_ptr(&softnet_data);
 	err = !skb_queue_empty(&sd->xfrm_backlog);
@@ -256,6 +252,11 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 		return -EINVAL;
 	}
 
+	if (xuo->flags & XFRM_OFFLOAD_INBOUND && x->if_id) {
+		NL_SET_ERR_MSG(extack, "XFRM if_id is not supported in RX path");
+		return -EINVAL;
+	}
+
 	is_packet_offload = xuo->flags & XFRM_OFFLOAD_PACKET;
 
 	/* We don't yet support TFC padding. */
diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
index fed96bedd54e..330a05286a56 100644
--- a/net/xfrm/xfrm_interface_core.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -947,32 +947,28 @@ static struct rtnl_link_ops xfrmi_link_ops __read_mostly = {
 	.get_link_net	= xfrmi_get_link_net,
 };
 
-static void __net_exit xfrmi_exit_batch_rtnl(struct list_head *net_exit_list,
-					     struct list_head *dev_to_kill)
+static void __net_exit xfrmi_exit_rtnl(struct net *net,
+				       struct list_head *dev_to_kill)
 {
-	struct net *net;
+	struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+	struct xfrm_if __rcu **xip;
+	struct xfrm_if *xi;
+	int i;
 
-	ASSERT_RTNL();
-	list_for_each_entry(net, net_exit_list, exit_list) {
-		struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
-		struct xfrm_if __rcu **xip;
-		struct xfrm_if *xi;
-		int i;
-
-		for (i = 0; i < XFRMI_HASH_SIZE; i++) {
-			for (xip = &xfrmn->xfrmi[i];
-			     (xi = rtnl_dereference(*xip)) != NULL;
-			     xip = &xi->next)
-				unregister_netdevice_queue(xi->dev, dev_to_kill);
-		}
-		xi = rtnl_dereference(xfrmn->collect_md_xfrmi);
-		if (xi)
+	for (i = 0; i < XFRMI_HASH_SIZE; i++) {
+		for (xip = &xfrmn->xfrmi[i];
+		     (xi = rtnl_net_dereference(net, *xip)) != NULL;
+		     xip = &xi->next)
 			unregister_netdevice_queue(xi->dev, dev_to_kill);
 	}
+
+	xi = rtnl_net_dereference(net, xfrmn->collect_md_xfrmi);
+	if (xi)
+		unregister_netdevice_queue(xi->dev, dev_to_kill);
 }
 
 static struct pernet_operations xfrmi_net_ops = {
-	.exit_batch_rtnl = xfrmi_exit_batch_rtnl,
+	.exit_rtnl = xfrmi_exit_rtnl,
 	.id   = &xfrmi_net_id,
 	.size = sizeof(struct xfrmi_net),
 };
diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c
index a38545413b80..43fdc6ed8dd1 100644
--- a/net/xfrm/xfrm_ipcomp.c
+++ b/net/xfrm/xfrm_ipcomp.c
@@ -313,7 +313,6 @@ void ipcomp_destroy(struct xfrm_state *x)
 	struct ipcomp_data *ipcd = x->data;
 	if (!ipcd)
 		return;
-	xfrm_state_delete_tunnel(x);
 	ipcomp_free_data(ipcd);
 	kfree(ipcd);
 }
diff --git a/net/xfrm/xfrm_nat_keepalive.c b/net/xfrm/xfrm_nat_keepalive.c
index 82f0a301683f..ebf95d48e86c 100644
--- a/net/xfrm/xfrm_nat_keepalive.c
+++ b/net/xfrm/xfrm_nat_keepalive.c
@@ -9,9 +9,13 @@
 #include <net/ip6_checksum.h>
 #include <net/xfrm.h>
 
-static DEFINE_PER_CPU(struct sock *, nat_keepalive_sk_ipv4);
+static DEFINE_PER_CPU(struct sock_bh_locked, nat_keepalive_sk_ipv4) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
 #if IS_ENABLED(CONFIG_IPV6)
-static DEFINE_PER_CPU(struct sock *, nat_keepalive_sk_ipv6);
+static DEFINE_PER_CPU(struct sock_bh_locked, nat_keepalive_sk_ipv6) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
 #endif
 
 struct nat_keepalive {
@@ -56,10 +60,12 @@ static int nat_keepalive_send_ipv4(struct sk_buff *skb,
 
 	skb_dst_set(skb, &rt->dst);
 
-	sk = *this_cpu_ptr(&nat_keepalive_sk_ipv4);
+	local_lock_nested_bh(&nat_keepalive_sk_ipv4.bh_lock);
+	sk = this_cpu_read(nat_keepalive_sk_ipv4.sock);
 	sock_net_set(sk, net);
 	err = ip_build_and_send_pkt(skb, sk, fl4.saddr, fl4.daddr, NULL, tos);
 	sock_net_set(sk, &init_net);
+	local_unlock_nested_bh(&nat_keepalive_sk_ipv4.bh_lock);
 	return err;
 }
 
@@ -89,15 +95,19 @@ static int nat_keepalive_send_ipv6(struct sk_buff *skb,
 	fl6.fl6_sport = ka->encap_sport;
 	fl6.fl6_dport = ka->encap_dport;
 
-	sk = *this_cpu_ptr(&nat_keepalive_sk_ipv6);
+	local_lock_nested_bh(&nat_keepalive_sk_ipv6.bh_lock);
+	sk = this_cpu_read(nat_keepalive_sk_ipv6.sock);
 	sock_net_set(sk, net);
 	dst = ipv6_stub->ipv6_dst_lookup_flow(net, sk, &fl6, NULL);
-	if (IS_ERR(dst))
+	if (IS_ERR(dst)) {
+		local_unlock_nested_bh(&nat_keepalive_sk_ipv6.bh_lock);
 		return PTR_ERR(dst);
+	}
 
 	skb_dst_set(skb, dst);
 	err = ipv6_stub->ip6_xmit(sk, skb, &fl6, skb->mark, NULL, 0, 0);
 	sock_net_set(sk, &init_net);
+	local_unlock_nested_bh(&nat_keepalive_sk_ipv6.bh_lock);
 	return err;
 }
 #endif
@@ -202,7 +212,7 @@ static void nat_keepalive_work(struct work_struct *work)
 				      (ctx.next_run - ctx.now) * HZ);
 }
 
-static int nat_keepalive_sk_init(struct sock * __percpu *socks,
+static int nat_keepalive_sk_init(struct sock_bh_locked __percpu *socks,
 				 unsigned short family)
 {
 	struct sock *sk;
@@ -214,22 +224,22 @@ static int nat_keepalive_sk_init(struct sock * __percpu *socks,
 		if (err < 0)
 			goto err;
 
-		*per_cpu_ptr(socks, i) = sk;
+		per_cpu_ptr(socks, i)->sock = sk;
 	}
 
 	return 0;
 err:
 	for_each_possible_cpu(i)
-		inet_ctl_sock_destroy(*per_cpu_ptr(socks, i));
+		inet_ctl_sock_destroy(per_cpu_ptr(socks, i)->sock);
 	return err;
 }
 
-static void nat_keepalive_sk_fini(struct sock * __percpu *socks)
+static void nat_keepalive_sk_fini(struct sock_bh_locked __percpu *socks)
 {
 	int i;
 
 	for_each_possible_cpu(i)
-		inet_ctl_sock_destroy(*per_cpu_ptr(socks, i));
+		inet_ctl_sock_destroy(per_cpu_ptr(socks, i)->sock);
 }
 
 void xfrm_nat_keepalive_state_updated(struct xfrm_state *x)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index f4bad8c895d6..094d2454602e 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -353,7 +353,7 @@ static inline unsigned long make_jiffies(long secs)
 
 static void xfrm_policy_timer(struct timer_list *t)
 {
-	struct xfrm_policy *xp = from_timer(xp, t, timer);
+	struct xfrm_policy *xp = timer_container_of(xp, t, timer);
 	time64_t now = ktime_get_real_seconds();
 	time64_t next = TIME64_MAX;
 	int warn = 0;
@@ -2898,7 +2898,7 @@ static void xfrm_policy_queue_process(struct timer_list *t)
 	struct sk_buff *skb;
 	struct sock *sk;
 	struct dst_entry *dst;
-	struct xfrm_policy *pol = from_timer(pol, t, polq.hold_timer);
+	struct xfrm_policy *pol = timer_container_of(pol, t, polq.hold_timer);
 	struct net *net = xp_net(pol);
 	struct xfrm_policy_queue *pq = &pol->polq;
 	struct flowi fl;
@@ -4633,7 +4633,7 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 		 struct xfrm_migrate *m, int num_migrate,
 		 struct xfrm_kmaddress *k, struct net *net,
 		 struct xfrm_encap_tmpl *encap, u32 if_id,
-		 struct netlink_ext_ack *extack)
+		 struct netlink_ext_ack *extack, struct xfrm_user_offload *xuo)
 {
 	int i, err, nx_cur = 0, nx_new = 0;
 	struct xfrm_policy *pol = NULL;
@@ -4666,7 +4666,7 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 		if ((x = xfrm_migrate_state_find(mp, net, if_id))) {
 			x_cur[nx_cur] = x;
 			nx_cur++;
-			xc = xfrm_state_migrate(x, mp, encap);
+			xc = xfrm_state_migrate(x, mp, encap, net, xuo, extack);
 			if (xc) {
 				x_new[nx_new] = xc;
 				nx_new++;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index f57bb78fb12a..86337453709b 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -592,15 +592,15 @@ void xfrm_state_free(struct xfrm_state *x)
 }
 EXPORT_SYMBOL(xfrm_state_free);
 
-static void ___xfrm_state_destroy(struct xfrm_state *x)
+static void xfrm_state_gc_destroy(struct xfrm_state *x)
 {
 	if (x->mode_cbs && x->mode_cbs->destroy_state)
 		x->mode_cbs->destroy_state(x);
 	hrtimer_cancel(&x->mtimer);
 	timer_delete_sync(&x->rtimer);
-	kfree(x->aead);
-	kfree(x->aalg);
-	kfree(x->ealg);
+	kfree_sensitive(x->aead);
+	kfree_sensitive(x->aalg);
+	kfree_sensitive(x->ealg);
 	kfree(x->calg);
 	kfree(x->encap);
 	kfree(x->coaddr);
@@ -631,7 +631,7 @@ static void xfrm_state_gc_task(struct work_struct *work)
 	synchronize_rcu();
 
 	hlist_for_each_entry_safe(x, tmp, &gc_list, gclist)
-		___xfrm_state_destroy(x);
+		xfrm_state_gc_destroy(x);
 }
 
 static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
@@ -795,22 +795,18 @@ void xfrm_dev_state_free(struct xfrm_state *x)
 }
 #endif
 
-void __xfrm_state_destroy(struct xfrm_state *x, bool sync)
+void __xfrm_state_destroy(struct xfrm_state *x)
 {
 	WARN_ON(x->km.state != XFRM_STATE_DEAD);
 
-	if (sync) {
-		synchronize_rcu();
-		___xfrm_state_destroy(x);
-	} else {
-		spin_lock_bh(&xfrm_state_gc_lock);
-		hlist_add_head(&x->gclist, &xfrm_state_gc_list);
-		spin_unlock_bh(&xfrm_state_gc_lock);
-		schedule_work(&xfrm_state_gc_work);
-	}
+	spin_lock_bh(&xfrm_state_gc_lock);
+	hlist_add_head(&x->gclist, &xfrm_state_gc_list);
+	spin_unlock_bh(&xfrm_state_gc_lock);
+	schedule_work(&xfrm_state_gc_work);
 }
 EXPORT_SYMBOL(__xfrm_state_destroy);
 
+static void xfrm_state_delete_tunnel(struct xfrm_state *x);
 int __xfrm_state_delete(struct xfrm_state *x)
 {
 	struct net *net = xs_net(x);
@@ -838,6 +834,8 @@ int __xfrm_state_delete(struct xfrm_state *x)
 
 		xfrm_dev_state_delete(x);
 
+		xfrm_state_delete_tunnel(x);
+
 		/* All xfrm_state objects are created by xfrm_state_alloc.
 		 * The xfrm_state_alloc call gives a reference, and that
 		 * is what we are dropping here.
@@ -919,7 +917,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool
 }
 #endif
 
-int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync)
+int xfrm_state_flush(struct net *net, u8 proto, bool task_valid)
 {
 	int i, err = 0, cnt = 0;
 
@@ -941,10 +939,7 @@ restart:
 				err = xfrm_state_delete(x);
 				xfrm_audit_state_delete(x, err ? 0 : 1,
 							task_valid);
-				if (sync)
-					xfrm_state_put_sync(x);
-				else
-					xfrm_state_put(x);
+				xfrm_state_put(x);
 				if (!err)
 					cnt++;
 
@@ -1969,8 +1964,9 @@ static inline int clone_security(struct xfrm_state *x, struct xfrm_sec_ctx *secu
 	return 0;
 }
 
-static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
-					   struct xfrm_encap_tmpl *encap)
+static struct xfrm_state *xfrm_state_clone_and_setup(struct xfrm_state *orig,
+					   struct xfrm_encap_tmpl *encap,
+					   struct xfrm_migrate *m)
 {
 	struct net *net = xs_net(orig);
 	struct xfrm_state *x = xfrm_state_alloc(net);
@@ -2069,6 +2065,11 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
 			goto error;
 	}
 
+
+	x->props.family = m->new_family;
+	memcpy(&x->id.daddr, &m->new_daddr, sizeof(x->id.daddr));
+	memcpy(&x->props.saddr, &m->new_saddr, sizeof(x->props.saddr));
+
 	return x;
 
  error:
@@ -2131,21 +2132,23 @@ EXPORT_SYMBOL(xfrm_migrate_state_find);
 
 struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
 				      struct xfrm_migrate *m,
-				      struct xfrm_encap_tmpl *encap)
+				      struct xfrm_encap_tmpl *encap,
+				      struct net *net,
+				      struct xfrm_user_offload *xuo,
+				      struct netlink_ext_ack *extack)
 {
 	struct xfrm_state *xc;
 
-	xc = xfrm_state_clone(x, encap);
+	xc = xfrm_state_clone_and_setup(x, encap, m);
 	if (!xc)
 		return NULL;
 
-	xc->props.family = m->new_family;
-
 	if (xfrm_init_state(xc) < 0)
 		goto error;
 
-	memcpy(&xc->id.daddr, &m->new_daddr, sizeof(xc->id.daddr));
-	memcpy(&xc->props.saddr, &m->new_saddr, sizeof(xc->props.saddr));
+	/* configure the hardware if offload is requested */
+	if (xuo && xfrm_dev_state_add(net, xc, xuo, extack))
+		goto error;
 
 	/* add state */
 	if (xfrm_addr_equal(&x->id.daddr, &m->new_daddr, m->new_family)) {
@@ -2694,7 +2697,7 @@ EXPORT_SYMBOL(xfrm_state_walk_done);
 
 static void xfrm_replay_timer_handler(struct timer_list *t)
 {
-	struct xfrm_state *x = from_timer(x, t, rtimer);
+	struct xfrm_state *x = timer_container_of(x, t, rtimer);
 
 	spin_lock(&x->lock);
 
@@ -3074,20 +3077,17 @@ void xfrm_flush_gc(void)
 }
 EXPORT_SYMBOL(xfrm_flush_gc);
 
-/* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */
-void xfrm_state_delete_tunnel(struct xfrm_state *x)
+static void xfrm_state_delete_tunnel(struct xfrm_state *x)
 {
 	if (x->tunnel) {
 		struct xfrm_state *t = x->tunnel;
 
-		if (atomic_read(&t->tunnel_users) == 2)
+		if (atomic_dec_return(&t->tunnel_users) == 1)
 			xfrm_state_delete(t);
-		atomic_dec(&t->tunnel_users);
-		xfrm_state_put_sync(t);
+		xfrm_state_put(t);
 		x->tunnel = NULL;
 	}
 }
-EXPORT_SYMBOL(xfrm_state_delete_tunnel);
 
 u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
 {
@@ -3292,8 +3292,8 @@ void xfrm_state_fini(struct net *net)
 	unsigned int sz;
 
 	flush_work(&net->xfrm.state_hash_work);
+	xfrm_state_flush(net, 0, false);
 	flush_work(&xfrm_state_gc_work);
-	xfrm_state_flush(net, 0, false, true);
 
 	WARN_ON(!list_empty(&net->xfrm.state_all));
 
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index d17ea437a158..684239018bec 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1206,7 +1206,7 @@ static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb)
 	if (!nla)
 		return -EMSGSIZE;
 	algo = nla_data(nla);
-	strscpy_pad(algo->alg_name, auth->alg_name, sizeof(algo->alg_name));
+	strscpy_pad(algo->alg_name, auth->alg_name);
 
 	if (redact_secret && auth->alg_key_len)
 		memset(algo->alg_key, 0, (auth->alg_key_len + 7) / 8);
@@ -1219,7 +1219,7 @@ static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb)
 	if (!nla)
 		return -EMSGSIZE;
 	ap = nla_data(nla);
-	strscpy_pad(ap->alg_name, auth->alg_name, sizeof(ap->alg_name));
+	strscpy_pad(ap->alg_name, auth->alg_name);
 	ap->alg_key_len = auth->alg_key_len;
 	ap->alg_trunc_len = auth->alg_trunc_len;
 	if (redact_secret && auth->alg_key_len)
@@ -1240,7 +1240,7 @@ static int copy_to_user_aead(struct xfrm_algo_aead *aead, struct sk_buff *skb)
 		return -EMSGSIZE;
 
 	ap = nla_data(nla);
-	strscpy_pad(ap->alg_name, aead->alg_name, sizeof(ap->alg_name));
+	strscpy_pad(ap->alg_name, aead->alg_name);
 	ap->alg_key_len = aead->alg_key_len;
 	ap->alg_icv_len = aead->alg_icv_len;
 
@@ -1262,7 +1262,7 @@ static int copy_to_user_ealg(struct xfrm_algo *ealg, struct sk_buff *skb)
 		return -EMSGSIZE;
 
 	ap = nla_data(nla);
-	strscpy_pad(ap->alg_name, ealg->alg_name, sizeof(ap->alg_name));
+	strscpy_pad(ap->alg_name, ealg->alg_name);
 	ap->alg_key_len = ealg->alg_key_len;
 
 	if (redact_secret && ealg->alg_key_len)
@@ -1283,7 +1283,7 @@ static int copy_to_user_calg(struct xfrm_algo *calg, struct sk_buff *skb)
 		return -EMSGSIZE;
 
 	ap = nla_data(nla);
-	strscpy_pad(ap->alg_name, calg->alg_name, sizeof(ap->alg_name));
+	strscpy_pad(ap->alg_name, calg->alg_name);
 	ap->alg_key_len = 0;
 
 	return 0;
@@ -2635,7 +2635,7 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct xfrm_usersa_flush *p = nlmsg_data(nlh);
 	int err;
 
-	err = xfrm_state_flush(net, p->proto, true, false);
+	err = xfrm_state_flush(net, p->proto, true);
 	if (err) {
 		if (err == -ESRCH) /* empty table */
 			return 0;
@@ -3102,6 +3102,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int n = 0;
 	struct net *net = sock_net(skb->sk);
 	struct xfrm_encap_tmpl  *encap = NULL;
+	struct xfrm_user_offload *xuo = NULL;
 	u32 if_id = 0;
 
 	if (!attrs[XFRMA_MIGRATE]) {
@@ -3132,11 +3133,19 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (attrs[XFRMA_IF_ID])
 		if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
 
+	if (attrs[XFRMA_OFFLOAD_DEV]) {
+		xuo = kmemdup(nla_data(attrs[XFRMA_OFFLOAD_DEV]),
+			      sizeof(*xuo), GFP_KERNEL);
+		if (!xuo) {
+			err = -ENOMEM;
+			goto error;
+		}
+	}
 	err = xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net, encap,
-			   if_id, extack);
-
+			   if_id, extack, xuo);
+error:
 	kfree(encap);
-
+	kfree(xuo);
 	return err;
 }
 #else