Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Merge in the left-over fixes before the net-next pull-request.

Conflicts:

drivers/net/ethernet/mediatek/mtk_ppe.c
  ae3ed15da588 ("net: ethernet: mtk_eth_soc: fix state in __mtk_foe_entry_clear")
  9d8cb4c096ab ("net: ethernet: mtk_eth_soc: add foe_entry_size to mtk_eth_soc")
https://lore.kernel.org/all/6cb6893b-4921-a068-4c30-1109795110bb@tessares.net/

kernel/bpf/helpers.c
  8addbfc7b308 ("bpf: Gate dynptr API behind CAP_BPF")
  5679ff2f138f ("bpf: Move bpf_loop and bpf_for_each_map_elem under CAP_BPF")
  8a67f2de9b1d ("bpf: expose bpf_strtol and bpf_strtoul to all program types")
https://lore.kernel.org/all/20221003201957.13149-1-daniel@iogearbox.net/

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

14 files changed, 88 insertions, 53 deletions

diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index 7889e1ef7fad..cbd0e2ac4ffe 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -251,6 +251,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 		return -EOPNOTSUPP;
 	}
 
+	if (!size)
+		return -EINVAL;
+
 	lock_sock(sk);
 	if (!sk->sk_bound_dev_if)
 		dev = dev_getfirstbyhwtype(sock_net(sk), ARPHRD_IEEE802154);
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 935026f4c807..170152772d33 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -110,7 +110,10 @@ static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x,
 						struct sk_buff *skb,
 						netdev_features_t features)
 {
-	return skb_eth_gso_segment(skb, features, htons(ETH_P_IP));
+	__be16 type = x->inner_mode.family == AF_INET6 ? htons(ETH_P_IPV6)
+						       : htons(ETH_P_IP);
+
+	return skb_eth_gso_segment(skb, features, type);
 }
 
 static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 648b5c54bb32..0c51abeee172 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3136,6 +3136,8 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
 	tcp_snd_cwnd_set(tp, TCP_INIT_CWND);
 	tp->snd_cwnd_cnt = 0;
+	tp->is_cwnd_limited = 0;
+	tp->max_packets_out = 0;
 	tp->window_clamp = 0;
 	tp->delivered = 0;
 	tp->delivered_ce = 0;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 290019de766d..c69f4d966024 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1875,15 +1875,20 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
 	const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* Track the maximum number of outstanding packets in each
-	 * window, and remember whether we were cwnd-limited then.
+	/* Track the strongest available signal of the degree to which the cwnd
+	 * is fully utilized. If cwnd-limited then remember that fact for the
+	 * current window. If not cwnd-limited then track the maximum number of
+	 * outstanding packets in the current window. (If cwnd-limited then we
+	 * chose to not update tp->max_packets_out to avoid an extra else
+	 * clause with no functional impact.)
 	 */
-	if (!before(tp->snd_una, tp->max_packets_seq) ||
-	    tp->packets_out > tp->max_packets_out ||
-	    is_cwnd_limited) {
-		tp->max_packets_out = tp->packets_out;
-		tp->max_packets_seq = tp->snd_nxt;
+	if (!before(tp->snd_una, tp->cwnd_usage_seq) ||
+	    is_cwnd_limited ||
+	    (!tp->is_cwnd_limited &&
+	     tp->packets_out > tp->max_packets_out)) {
 		tp->is_cwnd_limited = is_cwnd_limited;
+		tp->max_packets_out = tp->packets_out;
+		tp->cwnd_usage_seq = tp->snd_nxt;
 	}
 
 	if (tcp_is_cwnd_limited(sk)) {
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 3a293838a91d..79d43548279c 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -145,7 +145,10 @@ static struct sk_buff *xfrm6_tunnel_gso_segment(struct xfrm_state *x,
 						struct sk_buff *skb,
 						netdev_features_t features)
 {
-	return skb_eth_gso_segment(skb, features, htons(ETH_P_IPV6));
+	__be16 type = x->inner_mode.family == AF_INET ? htons(ETH_P_IP)
+						      : htons(ETH_P_IPV6);
+
+	return skb_eth_gso_segment(skb, features, type);
 }
 
 static struct sk_buff *xfrm6_transport_gso_segment(struct xfrm_state *x,
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index d8754366506a..4444fd82b66d 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -166,10 +166,10 @@ void rds_tcp_reset_callbacks(struct socket *sock,
 	 */
 	atomic_set(&cp->cp_state, RDS_CONN_RESETTING);
 	wait_event(cp->cp_waitq, !test_bit(RDS_IN_XMIT, &cp->cp_flags));
-	lock_sock(osock->sk);
 	/* reset receive side state for rds_tcp_data_recv() for osock  */
 	cancel_delayed_work_sync(&cp->cp_send_w);
 	cancel_delayed_work_sync(&cp->cp_recv_w);
+	lock_sock(osock->sk);
 	if (tc->t_tinc) {
 		rds_inc_put(&tc->t_tinc->ti_inc);
 		tc->t_tinc = NULL;
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index db6b7373d16c..34964145514e 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -863,12 +863,17 @@ int sctp_auth_set_key(struct sctp_endpoint *ep,
 	}
 
 	list_del_init(&shkey->key_list);
-	sctp_auth_shkey_release(shkey);
 	list_add(&cur_key->key_list, sh_keys);
 
-	if (asoc && asoc->active_key_id == auth_key->sca_keynumber)
-		sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL);
+	if (asoc && asoc->active_key_id == auth_key->sca_keynumber &&
+	    sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL)) {
+		list_del_init(&cur_key->key_list);
+		sctp_auth_shkey_release(cur_key);
+		list_add(&shkey->key_list, sh_keys);
+		return -ENOMEM;
+	}
 
+	sctp_auth_shkey_release(shkey);
 	return 0;
 }
 
@@ -902,8 +907,13 @@ int sctp_auth_set_active_key(struct sctp_endpoint *ep,
 		return -EINVAL;
 
 	if (asoc) {
+		__u16  active_key_id = asoc->active_key_id;
+
 		asoc->active_key_id = key_id;
-		sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL);
+		if (sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL)) {
+			asoc->active_key_id = active_key_id;
+			return -ENOMEM;
+		}
 	} else
 		ep->active_key_id = key_id;
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index c955c7253d4b..0f08c3177872 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -569,12 +569,6 @@ static void unix_sock_destructor(struct sock *sk)
 
 	skb_queue_purge(&sk->sk_receive_queue);
 
-#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
-	if (u->oob_skb) {
-		kfree_skb(u->oob_skb);
-		u->oob_skb = NULL;
-	}
-#endif
 	DEBUG_NET_WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc));
 	DEBUG_NET_WARN_ON_ONCE(!sk_unhashed(sk));
 	DEBUG_NET_WARN_ON_ONCE(sk->sk_socket);
@@ -620,6 +614,13 @@ static void unix_release_sock(struct sock *sk, int embrion)
 
 	unix_state_unlock(sk);
 
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+	if (u->oob_skb) {
+		kfree_skb(u->oob_skb);
+		u->oob_skb = NULL;
+	}
+#endif
+
 	wake_up_interruptible_all(&u->peer_wait);
 
 	if (skpair != NULL) {
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 35863132f4f1..a9980e9b9304 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -1339,7 +1339,7 @@ EXPORT_SYMBOL_GPL(virtio_transport_recv_pkt);
 
 void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt)
 {
-	kfree(pkt->buf);
+	kvfree(pkt->buf);
 	kfree(pkt);
 }
 EXPORT_SYMBOL_GPL(virtio_transport_free_pkt);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 5b4ce6ba1bc7..9f0561b67c12 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -355,16 +355,15 @@ static u32 xsk_tx_peek_release_fallback(struct xsk_buff_pool *pool, u32 max_entr
 	return nb_pkts;
 }
 
-u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max_entries)
+u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 nb_pkts)
 {
 	struct xdp_sock *xs;
-	u32 nb_pkts;
 
 	rcu_read_lock();
 	if (!list_is_singular(&pool->xsk_tx_list)) {
 		/* Fallback to the non-batched version */
 		rcu_read_unlock();
-		return xsk_tx_peek_release_fallback(pool, max_entries);
+		return xsk_tx_peek_release_fallback(pool, nb_pkts);
 	}
 
 	xs = list_first_or_null_rcu(&pool->xsk_tx_list, struct xdp_sock, tx_list);
@@ -373,12 +372,7 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max_entries)
 		goto out;
 	}
 
-	max_entries = xskq_cons_nb_entries(xs->tx, max_entries);
-	nb_pkts = xskq_cons_read_desc_batch(xs->tx, pool, max_entries);
-	if (!nb_pkts) {
-		xs->tx->queue_empty_descs++;
-		goto out;
-	}
+	nb_pkts = xskq_cons_nb_entries(xs->tx, nb_pkts);
 
 	/* This is the backpressure mechanism for the Tx path. Try to
 	 * reserve space in the completion queue for all packets, but
@@ -386,12 +380,18 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max_entries)
 	 * packets. This avoids having to implement any buffering in
 	 * the Tx path.
 	 */
-	nb_pkts = xskq_prod_reserve_addr_batch(pool->cq, pool->tx_descs, nb_pkts);
+	nb_pkts = xskq_prod_nb_free(pool->cq, nb_pkts);
 	if (!nb_pkts)
 		goto out;
 
-	xskq_cons_release_n(xs->tx, max_entries);
+	nb_pkts = xskq_cons_read_desc_batch(xs->tx, pool, nb_pkts);
+	if (!nb_pkts) {
+		xs->tx->queue_empty_descs++;
+		goto out;
+	}
+
 	__xskq_cons_release(xs->tx);
+	xskq_prod_write_addr_batch(pool->cq, pool->tx_descs, nb_pkts);
 	xs->sk.sk_write_space(&xs->sk);
 
 out:
@@ -954,8 +954,8 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 				goto out_unlock;
 			}
 
-			err = xp_assign_dev_shared(xs->pool, umem_xs->umem,
-						   dev, qid);
+			err = xp_assign_dev_shared(xs->pool, umem_xs, dev,
+						   qid);
 			if (err) {
 				xp_destroy(xs->pool);
 				xs->pool = NULL;
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index a71a8c6edf55..ed6c71826d31 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -212,17 +212,18 @@ err_unreg_pool:
 	return err;
 }
 
-int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem,
+int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_sock *umem_xs,
 			 struct net_device *dev, u16 queue_id)
 {
 	u16 flags;
+	struct xdp_umem *umem = umem_xs->umem;
 
 	/* One fill and completion ring required for each queue id. */
 	if (!pool->fq || !pool->cq)
 		return -EINVAL;
 
 	flags = umem->zc ? XDP_ZEROCOPY : XDP_COPY;
-	if (pool->uses_need_wakeup)
+	if (umem_xs->pool->uses_need_wakeup)
 		flags |= XDP_USE_NEED_WAKEUP;
 
 	return xp_assign_dev(pool, dev, queue_id, flags);
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index fb20bf7207cf..c6fb6b763658 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -205,6 +205,11 @@ static inline bool xskq_cons_read_desc(struct xsk_queue *q,
 	return false;
 }
 
+static inline void xskq_cons_release_n(struct xsk_queue *q, u32 cnt)
+{
+	q->cached_cons += cnt;
+}
+
 static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool,
 					    u32 max)
 {
@@ -226,6 +231,8 @@ static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q, struct xsk_buff
 		cached_cons++;
 	}
 
+	/* Release valid plus any invalid entries */
+	xskq_cons_release_n(q, cached_cons - q->cached_cons);
 	return nb_entries;
 }
 
@@ -291,11 +298,6 @@ static inline void xskq_cons_release(struct xsk_queue *q)
 	q->cached_cons++;
 }
 
-static inline void xskq_cons_release_n(struct xsk_queue *q, u32 cnt)
-{
-	q->cached_cons += cnt;
-}
-
 static inline u32 xskq_cons_present_entries(struct xsk_queue *q)
 {
 	/* No barriers needed since data is not accessed */
@@ -350,21 +352,17 @@ static inline int xskq_prod_reserve_addr(struct xsk_queue *q, u64 addr)
 	return 0;
 }
 
-static inline u32 xskq_prod_reserve_addr_batch(struct xsk_queue *q, struct xdp_desc *descs,
-					       u32 max)
+static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_desc *descs,
+					      u32 nb_entries)
 {
 	struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
-	u32 nb_entries, i, cached_prod;
-
-	nb_entries = xskq_prod_nb_free(q, max);
+	u32 i, cached_prod;
 
 	/* A, matches D */
 	cached_prod = q->cached_prod;
 	for (i = 0; i < nb_entries; i++)
 		ring->desc[cached_prod++ & q->ring_mask] = descs[i].addr;
 	q->cached_prod = cached_prod;
-
-	return nb_entries;
 }
 
 static inline int xskq_prod_reserve_desc(struct xsk_queue *q,
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index a3cf85d3f296..97074f6f2bde 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -25,7 +25,8 @@
 #include "xfrm_inout.h"
 
 struct xfrm_trans_tasklet {
-	struct tasklet_struct tasklet;
+	struct work_struct work;
+	spinlock_t queue_lock;
 	struct sk_buff_head queue;
 };
 
@@ -763,18 +764,22 @@ int xfrm_input_resume(struct sk_buff *skb, int nexthdr)
 }
 EXPORT_SYMBOL(xfrm_input_resume);
 
-static void xfrm_trans_reinject(struct tasklet_struct *t)
+static void xfrm_trans_reinject(struct work_struct *work)
 {
-	struct xfrm_trans_tasklet *trans = from_tasklet(trans, t, tasklet);
+	struct xfrm_trans_tasklet *trans = container_of(work, struct xfrm_trans_tasklet, work);
 	struct sk_buff_head queue;
 	struct sk_buff *skb;
 
 	__skb_queue_head_init(&queue);
+	spin_lock_bh(&trans->queue_lock);
 	skb_queue_splice_init(&trans->queue, &queue);
+	spin_unlock_bh(&trans->queue_lock);
 
+	local_bh_disable();
 	while ((skb = __skb_dequeue(&queue)))
 		XFRM_TRANS_SKB_CB(skb)->finish(XFRM_TRANS_SKB_CB(skb)->net,
 					       NULL, skb);
+	local_bh_enable();
 }
 
 int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
@@ -792,8 +797,10 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
 
 	XFRM_TRANS_SKB_CB(skb)->finish = finish;
 	XFRM_TRANS_SKB_CB(skb)->net = net;
+	spin_lock_bh(&trans->queue_lock);
 	__skb_queue_tail(&trans->queue, skb);
-	tasklet_schedule(&trans->tasklet);
+	spin_unlock_bh(&trans->queue_lock);
+	schedule_work(&trans->work);
 	return 0;
 }
 EXPORT_SYMBOL(xfrm_trans_queue_net);
@@ -820,7 +827,8 @@ void __init xfrm_input_init(void)
 		struct xfrm_trans_tasklet *trans;
 
 		trans = &per_cpu(xfrm_trans_tasklet, i);
+		spin_lock_init(&trans->queue_lock);
 		__skb_queue_head_init(&trans->queue);
-		tasklet_setup(&trans->tasklet, xfrm_trans_reinject);
+		INIT_WORK(&trans->work, xfrm_trans_reinject);
 	}
 }
diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c
index 656045a87606..80143360bf09 100644
--- a/net/xfrm/xfrm_ipcomp.c
+++ b/net/xfrm/xfrm_ipcomp.c
@@ -203,6 +203,7 @@ static void ipcomp_free_scratches(void)
 		vfree(*per_cpu_ptr(scratches, i));
 
 	free_percpu(scratches);
+	ipcomp_scratches = NULL;
 }
 
 static void * __percpu *ipcomp_alloc_scratches(void)