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>

9 files changed, 26 insertions, 31 deletions

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 70564ddccc46..6f354f8be2c5 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -226,7 +226,7 @@ lookup_protocol:
 	RCU_INIT_POINTER(inet->mc_list, NULL);
 	inet->rcv_tos	= 0;
 
-	if (net->ipv4.sysctl_ip_no_pmtu_disc)
+	if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc))
 		inet->pmtudisc = IP_PMTUDISC_DONT;
 	else
 		inet->pmtudisc = IP_PMTUDISC_WANT;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 61770220774e..9d92d51c4757 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -925,7 +925,7 @@ static int icmpv6_rcv(struct sk_buff *skb)
 		break;
 	case ICMPV6_EXT_ECHO_REQUEST:
 		if (!net->ipv6.sysctl.icmpv6_echo_ignore_all &&
-		    net->ipv4.sysctl_icmp_echo_enable_probe)
+		    READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe))
 			icmpv6_echo_reply(skb);
 		break;
 
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 0322cc86b84e..e1ebf5e42ebe 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -45,20 +45,23 @@
 #include <net/inet_ecn.h>
 #include <net/dst_metadata.h>
 
-INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *));
 static void ip6_rcv_finish_core(struct net *net, struct sock *sk,
 				struct sk_buff *skb)
 {
-	void (*edemux)(struct sk_buff *skb);
-
-	if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
-		const struct inet6_protocol *ipprot;
-
-		ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
-		if (ipprot && (edemux = READ_ONCE(ipprot->early_demux)))
-			INDIRECT_CALL_2(edemux, tcp_v6_early_demux,
-					udp_v6_early_demux, skb);
+	if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) &&
+	    !skb_dst(skb) && !skb->sk) {
+		switch (ipv6_hdr(skb)->nexthdr) {
+		case IPPROTO_TCP:
+			if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux))
+				tcp_v6_early_demux(skb);
+			break;
+		case IPPROTO_UDP:
+			if (READ_ONCE(net->ipv4.sysctl_udp_early_demux))
+				udp_v6_early_demux(skb);
+			break;
+		}
 	}
+
 	if (!skb_valid_dst(skb))
 		ip6_route_input(skb);
 }
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 828355710c57..916417944ec8 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -5741,7 +5741,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 		if (nexthop_is_blackhole(rt->nh))
 			rtm->rtm_type = RTN_BLACKHOLE;
 
-		if (net->ipv4.sysctl_nexthop_compat_mode &&
+		if (READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode) &&
 		    rt6_fill_node_nexthop(skb, rt->nh, &nh_flags) < 0)
 			goto nla_put_failure;
 
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index d64855010948..e756ba705fd9 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -189,6 +189,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
 	}
 #endif
 
+	hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+
 	skb_postpush_rcsum(skb, hdr, tot_len);
 
 	return 0;
@@ -241,6 +243,8 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
 	}
 #endif
 
+	hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+
 	skb_postpush_rcsum(skb, hdr, sizeof(struct ipv6hdr) + hdrlen);
 
 	return 0;
@@ -302,7 +306,6 @@ static int seg6_do_srh(struct sk_buff *skb)
 		break;
 	}
 
-	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
 	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
 	nf_reset_ct(skb);
 
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index 98a34287439c..2cd4a8d3b30a 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -826,7 +826,6 @@ static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt)
 	if (err)
 		goto drop;
 
-	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
 	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
 
 	seg6_lookup_nexthop(skb, NULL, 0);
@@ -858,7 +857,6 @@ static int input_action_end_b6_encap(struct sk_buff *skb,
 	if (err)
 		goto drop;
 
-	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
 	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
 
 	seg6_lookup_nexthop(skb, NULL, 0);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 9cc123f000fb..5014aa663452 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -141,7 +141,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	__u8 rcv_wscale;
 	u32 tsoff = 0;
 
-	if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
+	if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) ||
+	    !th->ack || th->rst)
 		goto out;
 
 	if (tcp_synq_no_recent_overflow(sk))
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index f37dd4aa91c6..9d3ede293258 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1822,7 +1822,7 @@ do_time_wait:
 	goto discard_it;
 }
 
-INDIRECT_CALLABLE_SCOPE void tcp_v6_early_demux(struct sk_buff *skb)
+void tcp_v6_early_demux(struct sk_buff *skb)
 {
 	const struct ipv6hdr *hdr;
 	const struct tcphdr *th;
@@ -2176,12 +2176,7 @@ struct proto tcpv6_prot = {
 };
 EXPORT_SYMBOL_GPL(tcpv6_prot);
 
-/* thinking of making this const? Don't.
- * early_demux can change based on sysctl.
- */
-static struct inet6_protocol tcpv6_protocol = {
-	.early_demux	=	tcp_v6_early_demux,
-	.early_demux_handler =  tcp_v6_early_demux,
+static const struct inet6_protocol tcpv6_protocol = {
 	.handler	=	tcp_v6_rcv,
 	.err_handler	=	tcp_v6_err,
 	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 55afd7f39c04..e2f2e087a753 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1052,7 +1052,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net,
 	return NULL;
 }
 
-INDIRECT_CALLABLE_SCOPE void udp_v6_early_demux(struct sk_buff *skb)
+void udp_v6_early_demux(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
 	const struct udphdr *uh;
@@ -1660,12 +1660,7 @@ int udpv6_getsockopt(struct sock *sk, int level, int optname,
 	return ipv6_getsockopt(sk, level, optname, optval, optlen);
 }
 
-/* thinking of making this const? Don't.
- * early_demux can change based on sysctl.
- */
-static struct inet6_protocol udpv6_protocol = {
-	.early_demux	=	udp_v6_early_demux,
-	.early_demux_handler =  udp_v6_early_demux,
+static const struct inet6_protocol udpv6_protocol = {
 	.handler	=	udpv6_rcv,
 	.err_handler	=	udpv6_err,
 	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,