Merge x86 bugfixes from Linux 6.9-rc3

Pull fix for SEV-SNP late disable bugs.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

11 files changed, 131 insertions, 35 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 7d8090f109ef..3b38610958ee 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -203,8 +203,15 @@ static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2,
 				   kuid_t sk_uid, bool relax,
 				   bool reuseport_cb_ok, bool reuseport_ok)
 {
-	if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
-		return false;
+	if (ipv6_only_sock(sk2)) {
+		if (sk->sk_family == AF_INET)
+			return false;
+
+#if IS_ENABLED(CONFIG_IPV6)
+		if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+			return false;
+#endif
+	}
 
 	return inet_bind_conflict(sk, sk2, sk_uid, relax,
 				  reuseport_cb_ok, reuseport_ok);
@@ -287,6 +294,7 @@ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l
 	struct sock_reuseport *reuseport_cb;
 	struct inet_bind_hashbucket *head2;
 	struct inet_bind2_bucket *tb2;
+	bool conflict = false;
 	bool reuseport_cb_ok;
 
 	rcu_read_lock();
@@ -299,18 +307,20 @@ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l
 
 	spin_lock(&head2->lock);
 
-	inet_bind_bucket_for_each(tb2, &head2->chain)
-		if (inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk))
-			break;
+	inet_bind_bucket_for_each(tb2, &head2->chain) {
+		if (!inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk))
+			continue;
 
-	if (tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok,
-					reuseport_ok)) {
-		spin_unlock(&head2->lock);
-		return true;
+		if (!inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok,	reuseport_ok))
+			continue;
+
+		conflict = true;
+		break;
 	}
 
 	spin_unlock(&head2->lock);
-	return false;
+
+	return conflict;
 }
 
 /*
@@ -771,6 +781,20 @@ void inet_csk_clear_xmit_timers(struct sock *sk)
 }
 EXPORT_SYMBOL(inet_csk_clear_xmit_timers);
 
+void inet_csk_clear_xmit_timers_sync(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	/* ongoing timer handlers need to acquire socket lock. */
+	sock_not_owned_by_me(sk);
+
+	icsk->icsk_pending = icsk->icsk_ack.pending = 0;
+
+	sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer);
+	sk_stop_timer_sync(sk, &icsk->icsk_delack_timer);
+	sk_stop_timer_sync(sk, &sk->sk_timer);
+}
+
 void inet_csk_delete_keepalive_timer(struct sock *sk)
 {
 	sk_stop_timer(sk, &sk->sk_timer);
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 7072fc0783ef..c88c9034d630 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -24,6 +24,8 @@
 #include <net/ip.h>
 #include <net/ipv6.h>
 
+#include "../core/sock_destructor.h"
+
 /* Use skb->cb to track consecutive/adjacent fragments coming at
  * the end of the queue. Nodes in the rb-tree queue will
  * contain "runs" of one or more adjacent fragments.
@@ -39,6 +41,7 @@ struct ipfrag_skb_cb {
 	};
 	struct sk_buff		*next_frag;
 	int			frag_run_len;
+	int			ip_defrag_offset;
 };
 
 #define FRAG_CB(skb)		((struct ipfrag_skb_cb *)((skb)->cb))
@@ -396,12 +399,12 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
 	 */
 	if (!last)
 		fragrun_create(q, skb);  /* First fragment. */
-	else if (last->ip_defrag_offset + last->len < end) {
+	else if (FRAG_CB(last)->ip_defrag_offset + last->len < end) {
 		/* This is the common case: skb goes to the end. */
 		/* Detect and discard overlaps. */
-		if (offset < last->ip_defrag_offset + last->len)
+		if (offset < FRAG_CB(last)->ip_defrag_offset + last->len)
 			return IPFRAG_OVERLAP;
-		if (offset == last->ip_defrag_offset + last->len)
+		if (offset == FRAG_CB(last)->ip_defrag_offset + last->len)
 			fragrun_append_to_last(q, skb);
 		else
 			fragrun_create(q, skb);
@@ -418,13 +421,13 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
 
 			parent = *rbn;
 			curr = rb_to_skb(parent);
-			curr_run_end = curr->ip_defrag_offset +
+			curr_run_end = FRAG_CB(curr)->ip_defrag_offset +
 					FRAG_CB(curr)->frag_run_len;
-			if (end <= curr->ip_defrag_offset)
+			if (end <= FRAG_CB(curr)->ip_defrag_offset)
 				rbn = &parent->rb_left;
 			else if (offset >= curr_run_end)
 				rbn = &parent->rb_right;
-			else if (offset >= curr->ip_defrag_offset &&
+			else if (offset >= FRAG_CB(curr)->ip_defrag_offset &&
 				 end <= curr_run_end)
 				return IPFRAG_DUP;
 			else
@@ -438,7 +441,7 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
 		rb_insert_color(&skb->rbnode, &q->rb_fragments);
 	}
 
-	skb->ip_defrag_offset = offset;
+	FRAG_CB(skb)->ip_defrag_offset = offset;
 
 	return IPFRAG_OK;
 }
@@ -448,13 +451,28 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
 			      struct sk_buff *parent)
 {
 	struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments);
-	struct sk_buff **nextp;
+	void (*destructor)(struct sk_buff *);
+	unsigned int orig_truesize = 0;
+	struct sk_buff **nextp = NULL;
+	struct sock *sk = skb->sk;
 	int delta;
 
+	if (sk && is_skb_wmem(skb)) {
+		/* TX: skb->sk might have been passed as argument to
+		 * dst->output and must remain valid until tx completes.
+		 *
+		 * Move sk to reassembled skb and fix up wmem accounting.
+		 */
+		orig_truesize = skb->truesize;
+		destructor = skb->destructor;
+	}
+
 	if (head != skb) {
 		fp = skb_clone(skb, GFP_ATOMIC);
-		if (!fp)
-			return NULL;
+		if (!fp) {
+			head = skb;
+			goto out_restore_sk;
+		}
 		FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag;
 		if (RB_EMPTY_NODE(&skb->rbnode))
 			FRAG_CB(parent)->next_frag = fp;
@@ -463,6 +481,12 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
 					&q->rb_fragments);
 		if (q->fragments_tail == skb)
 			q->fragments_tail = fp;
+
+		if (orig_truesize) {
+			/* prevent skb_morph from releasing sk */
+			skb->sk = NULL;
+			skb->destructor = NULL;
+		}
 		skb_morph(skb, head);
 		FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag;
 		rb_replace_node(&head->rbnode, &skb->rbnode,
@@ -470,13 +494,13 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
 		consume_skb(head);
 		head = skb;
 	}
-	WARN_ON(head->ip_defrag_offset != 0);
+	WARN_ON(FRAG_CB(head)->ip_defrag_offset != 0);
 
 	delta = -head->truesize;
 
 	/* Head of list must not be cloned. */
 	if (skb_unclone(head, GFP_ATOMIC))
-		return NULL;
+		goto out_restore_sk;
 
 	delta += head->truesize;
 	if (delta)
@@ -492,7 +516,7 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
 
 		clone = alloc_skb(0, GFP_ATOMIC);
 		if (!clone)
-			return NULL;
+			goto out_restore_sk;
 		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
 		skb_frag_list_init(head);
 		for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
@@ -509,6 +533,21 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
 		nextp = &skb_shinfo(head)->frag_list;
 	}
 
+out_restore_sk:
+	if (orig_truesize) {
+		int ts_delta = head->truesize - orig_truesize;
+
+		/* if this reassembled skb is fragmented later,
+		 * fraglist skbs will get skb->sk assigned from head->sk,
+		 * and each frag skb will be released via sock_wfree.
+		 *
+		 * Update sk_wmem_alloc.
+		 */
+		head->sk = sk;
+		head->destructor = destructor;
+		refcount_add(ts_delta, &sk->sk_wmem_alloc);
+	}
+
 	return nextp;
 }
 EXPORT_SYMBOL(inet_frag_reasm_prepare);
@@ -516,6 +555,8 @@ EXPORT_SYMBOL(inet_frag_reasm_prepare);
 void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
 			    void *reasm_data, bool try_coalesce)
 {
+	struct sock *sk = is_skb_wmem(head) ? head->sk : NULL;
+	const unsigned int head_truesize = head->truesize;
 	struct sk_buff **nextp = reasm_data;
 	struct rb_node *rbn;
 	struct sk_buff *fp;
@@ -579,6 +620,9 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
 	head->prev = NULL;
 	head->tstamp = q->stamp;
 	head->mono_delivery_time = q->mono_delivery_time;
+
+	if (sk)
+		refcount_add(sum_truesize - head_truesize, &sk->sk_wmem_alloc);
 }
 EXPORT_SYMBOL(inet_frag_reasm_finish);
 
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index a4941f53b523..fb947d1613fe 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -384,6 +384,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	}
 
 	skb_dst_drop(skb);
+	skb_orphan(skb);
 	return -EINPROGRESS;
 
 insert_error:
@@ -487,7 +488,6 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
 	struct ipq *qp;
 
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS);
-	skb_orphan(skb);
 
 	/* Lookup (or create) queue header */
 	qp = ip_find(net, ip_hdr(skb), user, vif);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 7b16c211b904..57ddcd8c62f6 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -280,8 +280,13 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 					  tpi->flags | TUNNEL_NO_KEY,
 					  iph->saddr, iph->daddr, 0);
 	} else {
+		if (unlikely(!pskb_may_pull(skb,
+					    gre_hdr_len + sizeof(*ershdr))))
+			return PACKET_REJECT;
+
 		ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len);
 		ver = ershdr->ver;
+		iph = ip_hdr(skb);
 		tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex,
 					  tpi->flags | TUNNEL_KEY,
 					  iph->saddr, iph->daddr, tpi->key);
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 8f6e950163a7..1b991b889506 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -329,6 +329,7 @@ config NFT_COMPAT_ARP
 config IP_NF_ARPFILTER
 	tristate "arptables-legacy packet filtering support"
 	select IP_NF_ARPTABLES
+	select NETFILTER_FAMILY_ARP
 	depends on NETFILTER_XTABLES
 	help
 	  ARP packet filtering defines a table `filter', which has a series of
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 2407066b0fec..b150c9929b12 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -956,6 +956,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len)
 	void *loc_cpu_entry;
 	struct arpt_entry *iter;
 
+	if (len < sizeof(tmp))
+		return -EINVAL;
 	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
@@ -1254,6 +1256,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
 	void *loc_cpu_entry;
 	struct arpt_entry *iter;
 
+	if (len < sizeof(tmp))
+		return -EINVAL;
 	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 7da1df4997d0..487670759578 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1108,6 +1108,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len)
 	void *loc_cpu_entry;
 	struct ipt_entry *iter;
 
+	if (len < sizeof(tmp))
+		return -EINVAL;
 	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
@@ -1492,6 +1494,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
 	void *loc_cpu_entry;
 	struct ipt_entry *iter;
 
+	if (len < sizeof(tmp))
+		return -EINVAL;
 	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 74928a9d1aa4..535856b0f0ed 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -768,8 +768,10 @@ static int nh_grp_hw_stats_update(struct nexthop *nh, bool *hw_stats_used)
 	struct net *net = nh->net;
 	int err;
 
-	if (nexthop_notifiers_is_empty(net))
+	if (nexthop_notifiers_is_empty(net)) {
+		*hw_stats_used = false;
 		return 0;
+	}
 
 	err = nh_notifier_grp_hw_stats_init(&info, nh);
 	if (err)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d20b62d52171..e767721b3a58 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2931,6 +2931,8 @@ void tcp_close(struct sock *sk, long timeout)
 	lock_sock(sk);
 	__tcp_close(sk, timeout);
 	release_sock(sk);
+	if (!sk->sk_net_refcnt)
+		inet_csk_clear_xmit_timers_sync(sk);
 	sock_put(sk);
 }
 EXPORT_SYMBOL(tcp_close);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 661d0e0d273f..c02bf011d4a6 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -582,6 +582,13 @@ static inline bool __udp_is_mcast_sock(struct net *net, const struct sock *sk,
 }
 
 DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key);
+EXPORT_SYMBOL(udp_encap_needed_key);
+
+#if IS_ENABLED(CONFIG_IPV6)
+DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
+EXPORT_SYMBOL(udpv6_encap_needed_key);
+#endif
+
 void udp_encap_enable(void)
 {
 	static_branch_inc(&udp_encap_needed_key);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index b9880743765c..3498dd1d0694 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -449,8 +449,9 @@ static int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb)
 	NAPI_GRO_CB(p)->count++;
 	p->data_len += skb->len;
 
-	/* sk owenrship - if any - completely transferred to the aggregated packet */
+	/* sk ownership - if any - completely transferred to the aggregated packet */
 	skb->destructor = NULL;
+	skb->sk = NULL;
 	p->truesize += skb->truesize;
 	p->len += skb->len;
 
@@ -551,11 +552,19 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
 	unsigned int off = skb_gro_offset(skb);
 	int flush = 1;
 
-	/* we can do L4 aggregation only if the packet can't land in a tunnel
-	 * otherwise we could corrupt the inner stream
+	/* We can do L4 aggregation only if the packet can't land in a tunnel
+	 * otherwise we could corrupt the inner stream. Detecting such packets
+	 * cannot be foolproof and the aggregation might still happen in some
+	 * cases. Such packets should be caught in udp_unexpected_gso later.
 	 */
 	NAPI_GRO_CB(skb)->is_flist = 0;
 	if (!sk || !udp_sk(sk)->gro_receive) {
+		/* If the packet was locally encapsulated in a UDP tunnel that
+		 * wasn't detected above, do not GRO.
+		 */
+		if (skb->encapsulation)
+			goto out;
+
 		if (skb->dev->features & NETIF_F_GRO_FRAGLIST)
 			NAPI_GRO_CB(skb)->is_flist = sk ? !udp_test_bit(GRO_ENABLED, sk) : 1;
 
@@ -719,13 +728,7 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 		skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4);
 		skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
 
-		if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
-			if (skb->csum_level < SKB_MAX_CSUM_LEVEL)
-				skb->csum_level++;
-		} else {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			skb->csum_level = 0;
-		}
+		__skb_incr_checksum_unnecessary(skb);
 
 		return 0;
 	}