Merge branch 'for-5.20/io_uring' into for-5.20/io_uring-zerocopy-send

* for-5.20/io_uring: (716 commits)
  io_uring: ensure REQ_F_ISREG is set async offload
  net: fix compat pointer in get_compat_msghdr()
  io_uring: Don't require reinitable percpu_ref
  io_uring: fix types in io_recvmsg_multishot_overflow
  io_uring: Use atomic_long_try_cmpxchg in __io_account_mem
  io_uring: support multishot in recvmsg
  net: copy from user before calling __get_compat_msghdr
  net: copy from user before calling __copy_msghdr
  io_uring: support 0 length iov in buffer select in compat
  io_uring: fix multishot ending when not polled
  io_uring: add netmsg cache
  io_uring: impose max limit on apoll cache
  io_uring: add abstraction around apoll cache
  io_uring: move apoll cache to poll.c
  io_uring: consolidate hash_locked io-wq handling
  io_uring: clear REQ_F_HASH_LOCKED on hash removal
  io_uring: don't race double poll setting REQ_F_ASYNC_DATA
  io_uring: don't miss setting REQ_F_DOUBLE_POLL
  io_uring: disable multishot recvmsg
  io_uring: only trace one of complete or overflow
  ...

Signed-off-by: Jens Axboe <axboe@kernel.dk>

4 files changed, 12 insertions, 9 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 8e6f22961206..30a1603a7225 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4863,7 +4863,10 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 }
 
 /* When doing generic XDP we have to bypass the qdisc layer and the
- * network taps in order to match in-driver-XDP behavior.
+ * network taps in order to match in-driver-XDP behavior. This also means
+ * that XDP packets are able to starve other packets going through a qdisc,
+ * and DDOS attacks will be more effective. In-driver-XDP use dedicated TX
+ * queues, so they do not have this starvation issue.
  */
 void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog)
 {
@@ -4875,7 +4878,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog)
 	txq = netdev_core_pick_tx(dev, skb, NULL);
 	cpu = smp_processor_id();
 	HARD_TX_LOCK(dev, txq, cpu);
-	if (!netif_xmit_stopped(txq)) {
+	if (!netif_xmit_frozen_or_drv_stopped(txq)) {
 		rc = netdev_start_xmit(skb, dev, txq, 0);
 		if (dev_xmit_complete(rc))
 			free_skb = false;
@@ -4883,6 +4886,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog)
 	HARD_TX_UNLOCK(dev, txq);
 	if (free_skb) {
 		trace_xdp_exception(dev, xdp_prog, XDP_TX);
+		dev_core_stats_tx_dropped_inc(dev);
 		kfree_skb(skb);
 	}
 }
diff --git a/net/core/filter.c b/net/core/filter.c
index 5d16d66727fc..7950f7520765 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6158,7 +6158,6 @@ static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len
 	if (err)
 		return err;
 
-	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
 	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
 
 	return seg6_lookup_nexthop(skb, NULL, 0);
@@ -7042,7 +7041,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
 	if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN)
 		return -EINVAL;
 
-	if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies)
+	if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies))
 		return -EINVAL;
 
 	if (!th->ack || th->rst || th->syn)
@@ -7117,7 +7116,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len,
 	if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN)
 		return -EINVAL;
 
-	if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies)
+	if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies))
 		return -ENOENT;
 
 	if (!th->syn || th->ack || th->fin || th->rst)
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 5f85e01d4093..b0ff6153be62 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -64,7 +64,7 @@ u32 secure_tcpv6_ts_off(const struct net *net,
 		.daddr = *(struct in6_addr *)daddr,
 	};
 
-	if (net->ipv4.sysctl_tcp_timestamps != 1)
+	if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1)
 		return 0;
 
 	ts_secret_init();
@@ -120,7 +120,7 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 #ifdef CONFIG_INET
 u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr)
 {
-	if (net->ipv4.sysctl_tcp_timestamps != 1)
+	if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1)
 		return 0;
 
 	ts_secret_init();
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 3f00a28fe762..5daa1fa54249 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -387,7 +387,7 @@ void reuseport_stop_listen_sock(struct sock *sk)
 		prog = rcu_dereference_protected(reuse->prog,
 						 lockdep_is_held(&reuseport_lock));
 
-		if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req ||
+		if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req) ||
 		    (prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) {
 			/* Migration capable, move sk from the listening section
 			 * to the closed section.
@@ -545,7 +545,7 @@ struct sock *reuseport_migrate_sock(struct sock *sk,
 	hash = migrating_sk->sk_hash;
 	prog = rcu_dereference(reuse->prog);
 	if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) {
-		if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req)
+		if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req))
 			goto select_by_hash;
 		goto failure;
 	}