From 4fe205539c46ab0add34675ab037f49caa30607c Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Fri, 13 Dec 2024 11:25:50 +0000
Subject: [PATCH 01/16] netlink: specs: add phys-binding attr to rt_link spec

Add the missing phys-binding attr to the mctp-attrs in the rt_link spec.
This fixes commit 580db513b4a9 ("net: mctp: Expose transport binding
identifier via IFLA attribute").

Note that enum mctp_phys_binding is not currently uapi, but perhaps it
should be?

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20241213112551.33557-1-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/rt_link.yaml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml
index 9ffa13b77dcf..96465376d6fe 100644
--- a/Documentation/netlink/specs/rt_link.yaml
+++ b/Documentation/netlink/specs/rt_link.yaml
@@ -2086,6 +2086,9 @@ attribute-sets:
       -
         name: mctp-net
         type: u32
+      -
+        name: phys-binding
+        type: u8
   -
     name: stats-attrs
     name-prefix: ifla-stats-
-- 
2.50.1


From 77ec16be758ea65de641833149963bec39f311da Mon Sep 17 00:00:00 2001
From: Anna Emese Nyiri <annaemesenyiri@gmail.com>
Date: Fri, 13 Dec 2024 09:44:54 +0100
Subject: [PATCH 02/16] sock: Introduce sk_set_prio_allowed helper function

Simplify priority setting permissions with the 'sk_set_prio_allowed'
function, centralizing the validation logic. This change is made in
anticipation of a second caller in a following patch.
No functional changes.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Suggested-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Anna Emese Nyiri <annaemesenyiri@gmail.com>
Link: https://patch.msgid.link/20241213084457.45120-2-annaemesenyiri@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/sock.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 74729d20cd00..9016f984d44e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -454,6 +454,13 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen,
 	return 0;
 }
 
+static bool sk_set_prio_allowed(const struct sock *sk, int val)
+{
+	return ((val >= TC_PRIO_BESTEFFORT && val <= TC_PRIO_INTERACTIVE) ||
+		sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) ||
+		sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN));
+}
+
 static bool sock_needs_netstamp(const struct sock *sk)
 {
 	switch (sk->sk_family) {
@@ -1193,9 +1200,7 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 	/* handle options which do not require locking the socket. */
 	switch (optname) {
 	case SO_PRIORITY:
-		if ((val >= 0 && val <= 6) ||
-		    sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) ||
-		    sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+		if (sk_set_prio_allowed(sk, val)) {
 			sock_set_priority(sk, val);
 			return 0;
 		}
-- 
2.50.1


From a32f3e9d1ed146f81162702605d65447a319eb76 Mon Sep 17 00:00:00 2001
From: Anna Emese Nyiri <annaemesenyiri@gmail.com>
Date: Fri, 13 Dec 2024 09:44:55 +0100
Subject: [PATCH 03/16] sock: support SO_PRIORITY cmsg

The Linux socket API currently allows setting SO_PRIORITY at the
socket level, applying a uniform priority to all packets sent through
that socket. The exception to this is IP_TOS, when the priority value
is calculated during the handling of
ancillary data, as implemented in commit f02db315b8d8 ("ipv4: IP_TOS
and IP_TTL can be specified as ancillary data").
However, this is a computed
value, and there is currently no mechanism to set a custom priority
via control messages prior to this patch.

According to this patch, if SO_PRIORITY is specified as ancillary data,
the packet is sent with the priority value set through
sockc->priority, overriding the socket-level values
set via the traditional setsockopt() method. This is analogous to
the existing support for SO_MARK, as implemented in
commit c6af0c227a22 ("ip: support SO_MARK cmsg").

If both cmsg SO_PRIORITY and IP_TOS are passed, then the one that
takes precedence is the last one in the cmsg list.

This patch has the side effect that raw_send_hdrinc now interprets cmsg
IP_TOS.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Suggested-by: Ferenc Fejes <fejes@inf.elte.hu>
Signed-off-by: Anna Emese Nyiri <annaemesenyiri@gmail.com>
Link: https://patch.msgid.link/20241213084457.45120-3-annaemesenyiri@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/inet_sock.h | 2 +-
 include/net/ip.h        | 2 +-
 include/net/sock.h      | 4 +++-
 net/can/raw.c           | 2 +-
 net/core/sock.c         | 7 +++++++
 net/ipv4/ip_output.c    | 4 ++--
 net/ipv4/ip_sockglue.c  | 2 +-
 net/ipv4/raw.c          | 2 +-
 net/ipv6/ip6_output.c   | 3 ++-
 net/ipv6/ping.c         | 1 +
 net/ipv6/raw.c          | 3 ++-
 net/ipv6/udp.c          | 1 +
 net/packet/af_packet.c  | 2 +-
 13 files changed, 24 insertions(+), 11 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 56d8bc5593d3..3ccbad881d74 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -172,7 +172,7 @@ struct inet_cork {
 	u8			tx_flags;
 	__u8			ttl;
 	__s16			tos;
-	char			priority;
+	u32			priority;
 	__u16			gso_size;
 	u32			ts_opt_id;
 	u64			transmit_time;
diff --git a/include/net/ip.h b/include/net/ip.h
index 0e548c1f2a0e..9f5e33e371fc 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -81,7 +81,6 @@ struct ipcm_cookie {
 	__u8			protocol;
 	__u8			ttl;
 	__s16			tos;
-	char			priority;
 	__u16			gso_size;
 };
 
@@ -96,6 +95,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
 	ipcm_init(ipcm);
 
 	ipcm->sockc.mark = READ_ONCE(inet->sk.sk_mark);
+	ipcm->sockc.priority = READ_ONCE(inet->sk.sk_priority);
 	ipcm->sockc.tsflags = READ_ONCE(inet->sk.sk_tsflags);
 	ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
 	ipcm->addr = inet->inet_saddr;
diff --git a/include/net/sock.h b/include/net/sock.h
index 7464e9f9f47c..316a34d6c48b 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1814,13 +1814,15 @@ struct sockcm_cookie {
 	u32 mark;
 	u32 tsflags;
 	u32 ts_opt_id;
+	u32 priority;
 };
 
 static inline void sockcm_init(struct sockcm_cookie *sockc,
 			       const struct sock *sk)
 {
 	*sockc = (struct sockcm_cookie) {
-		.tsflags = READ_ONCE(sk->sk_tsflags)
+		.tsflags = READ_ONCE(sk->sk_tsflags),
+		.priority = READ_ONCE(sk->sk_priority),
 	};
 }
 
diff --git a/net/can/raw.c b/net/can/raw.c
index 255c0a8f39d6..46e8ed9d64da 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -962,7 +962,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	}
 
 	skb->dev = dev;
-	skb->priority = READ_ONCE(sk->sk_priority);
+	skb->priority = sockc.priority;
 	skb->mark = READ_ONCE(sk->sk_mark);
 	skb->tstamp = sockc.transmit_time;
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 9016f984d44e..a3d9941c1d32 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2947,6 +2947,13 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
 	case SCM_RIGHTS:
 	case SCM_CREDENTIALS:
 		break;
+	case SO_PRIORITY:
+		if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
+			return -EINVAL;
+		if (!sk_set_prio_allowed(sk, *(u32 *)CMSG_DATA(cmsg)))
+			return -EPERM;
+		sockc->priority = *(u32 *)CMSG_DATA(cmsg);
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index a59204a8d850..f45a083f2c13 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1333,7 +1333,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	cork->ttl = ipc->ttl;
 	cork->tos = ipc->tos;
 	cork->mark = ipc->sockc.mark;
-	cork->priority = ipc->priority;
+	cork->priority = ipc->sockc.priority;
 	cork->transmit_time = ipc->sockc.transmit_time;
 	cork->tx_flags = 0;
 	sock_tx_timestamp(sk, &ipc->sockc, &cork->tx_flags);
@@ -1470,7 +1470,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 		ip_options_build(skb, opt, cork->addr, rt);
 	}
 
-	skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority);
+	skb->priority = cork->priority;
 	skb->mark = cork->mark;
 	if (sk_is_tcp(sk))
 		skb_set_delivery_time(skb, cork->transmit_time, SKB_CLOCK_MONOTONIC);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index cf377377b52d..f6a03b418dde 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -315,7 +315,7 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
 			if (val < 0 || val > 255)
 				return -EINVAL;
 			ipc->tos = val;
-			ipc->priority = rt_tos2priority(ipc->tos);
+			ipc->sockc.priority = rt_tos2priority(ipc->tos);
 			break;
 		case IP_PROTOCOL:
 			if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 0e9e01967ec9..4304a68d1db0 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -358,7 +358,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 	skb_reserve(skb, hlen);
 
 	skb->protocol = htons(ETH_P_IP);
-	skb->priority = READ_ONCE(sk->sk_priority);
+	skb->priority = sockc->priority;
 	skb->mark = sockc->mark;
 	skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid);
 	skb_dst_set(skb, &rt->dst);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 3d672dea9f56..993106876604 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1401,6 +1401,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 	cork->base.gso_size = ipc6->gso_size;
 	cork->base.tx_flags = 0;
 	cork->base.mark = ipc6->sockc.mark;
+	cork->base.priority = ipc6->sockc.priority;
 	sock_tx_timestamp(sk, &ipc6->sockc, &cork->base.tx_flags);
 	if (ipc6->sockc.tsflags & SOCKCM_FLAG_TS_OPT_ID) {
 		cork->base.flags |= IPCORK_TS_OPT_ID;
@@ -1942,7 +1943,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 	hdr->saddr = fl6->saddr;
 	hdr->daddr = *final_dst;
 
-	skb->priority = READ_ONCE(sk->sk_priority);
+	skb->priority = cork->base.priority;
 	skb->mark = cork->base.mark;
 	if (sk_is_tcp(sk))
 		skb_set_delivery_time(skb, cork->base.transmit_time, SKB_CLOCK_MONOTONIC);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 88b3fcacd4f9..46b8adf6e7f8 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -119,6 +119,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		return -EINVAL;
 
 	ipcm6_init_sk(&ipc6, sk);
+	ipc6.sockc.priority = READ_ONCE(sk->sk_priority);
 	ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
 	ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 8476a3944a88..a45aba090aa4 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -619,7 +619,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 	skb_reserve(skb, hlen);
 
 	skb->protocol = htons(ETH_P_IPV6);
-	skb->priority = READ_ONCE(sk->sk_priority);
+	skb->priority = sockc->priority;
 	skb->mark = sockc->mark;
 	skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid);
 
@@ -780,6 +780,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipcm6_init(&ipc6);
 	ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
 	ipc6.sockc.mark = fl6.flowi6_mark;
+	ipc6.sockc.priority = READ_ONCE(sk->sk_priority);
 
 	if (sin6) {
 		if (addr_len < SIN6_LEN_RFC2133)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d766fd798ecf..7c14c449804c 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1448,6 +1448,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipc6.gso_size = READ_ONCE(up->gso_size);
 	ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
 	ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
+	ipc6.sockc.priority = READ_ONCE(sk->sk_priority);
 
 	/* destination address check */
 	if (sin6) {
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 886c0dd47b66..f8d87d622699 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3126,7 +3126,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 
 	skb->protocol = proto;
 	skb->dev = dev;
-	skb->priority = READ_ONCE(sk->sk_priority);
+	skb->priority = sockc.priority;
 	skb->mark = sockc.mark;
 	skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid);
 
-- 
2.50.1


From cda7d5abe089cc8bd6d623cd6577627d8125d155 Mon Sep 17 00:00:00 2001
From: Anna Emese Nyiri <annaemesenyiri@gmail.com>
Date: Fri, 13 Dec 2024 09:44:56 +0100
Subject: [PATCH 04/16] selftests: net: test SO_PRIORITY ancillary data with
 cmsg_sender

Extend cmsg_sender.c with a new option '-Q' to send SO_PRIORITY
ancillary data.

cmsg_so_priority.sh script added to validate SO_PRIORITY behavior
by creating VLAN device with egress QoS mapping and testing packet
priorities using flower filters. Verify that packets with different
priorities are correctly matched and counted by filters for multiple
protocols and IP versions.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Ido Schimmel <idosch@nvidia.com>
Suggested-by: Ido Schimmel <idosch@idosch.org>
Signed-off-by: Anna Emese Nyiri <annaemesenyiri@gmail.com>
Link: https://patch.msgid.link/20241213084457.45120-4-annaemesenyiri@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile          |   1 +
 tools/testing/selftests/net/cmsg_sender.c     |  11 +-
 .../testing/selftests/net/cmsg_so_priority.sh | 151 ++++++++++++++++++
 3 files changed, 162 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/net/cmsg_so_priority.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index cb2fc601de66..f09bd96cc978 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -32,6 +32,7 @@ TEST_PROGS += ioam6.sh
 TEST_PROGS += gro.sh
 TEST_PROGS += gre_gso.sh
 TEST_PROGS += cmsg_so_mark.sh
+TEST_PROGS += cmsg_so_priority.sh
 TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh
 TEST_PROGS += netns-name.sh
 TEST_PROGS += nl_netdev.py
diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c
index 876c2db02a63..bc314382e4e1 100644
--- a/tools/testing/selftests/net/cmsg_sender.c
+++ b/tools/testing/selftests/net/cmsg_sender.c
@@ -59,6 +59,7 @@ struct options {
 		unsigned int proto;
 	} sock;
 	struct option_cmsg_u32 mark;
+	struct option_cmsg_u32 priority;
 	struct {
 		bool ena;
 		unsigned int delay;
@@ -97,6 +98,8 @@ static void __attribute__((noreturn)) cs_usage(const char *bin)
 	       "\n"
 	       "\t\t-m val  Set SO_MARK with given value\n"
 	       "\t\t-M val  Set SO_MARK via setsockopt\n"
+	       "\t\t-P val  Set SO_PRIORITY via setsockopt\n"
+	       "\t\t-Q val  Set SO_PRIORITY via cmsg\n"
 	       "\t\t-d val  Set SO_TXTIME with given delay (usec)\n"
 	       "\t\t-t      Enable time stamp reporting\n"
 	       "\t\t-f val  Set don't fragment via cmsg\n"
@@ -115,7 +118,7 @@ static void cs_parse_args(int argc, char *argv[])
 {
 	int o;
 
-	while ((o = getopt(argc, argv, "46sS:p:P:m:M:n:d:tf:F:c:C:l:L:H:")) != -1) {
+	while ((o = getopt(argc, argv, "46sS:p:P:m:M:n:d:tf:F:c:C:l:L:H:Q:")) != -1) {
 		switch (o) {
 		case 's':
 			opt.silent_send = true;
@@ -148,6 +151,10 @@ static void cs_parse_args(int argc, char *argv[])
 			opt.mark.ena = true;
 			opt.mark.val = atoi(optarg);
 			break;
+		case 'Q':
+			opt.priority.ena = true;
+			opt.priority.val = atoi(optarg);
+			break;
 		case 'M':
 			opt.sockopt.mark = atoi(optarg);
 			break;
@@ -252,6 +259,8 @@ cs_write_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz)
 
 	ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
 			  SOL_SOCKET, SO_MARK, &opt.mark);
+	ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
+			  SOL_SOCKET, SO_PRIORITY, &opt.priority);
 	ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
 			  SOL_IPV6, IPV6_DONTFRAG, &opt.v6.dontfrag);
 	ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
diff --git a/tools/testing/selftests/net/cmsg_so_priority.sh b/tools/testing/selftests/net/cmsg_so_priority.sh
new file mode 100755
index 000000000000..ee07d8653262
--- /dev/null
+++ b/tools/testing/selftests/net/cmsg_so_priority.sh
@@ -0,0 +1,151 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+
+readonly KSFT_SKIP=4
+
+IP4=192.0.2.1/24
+TGT4=192.0.2.2
+TGT4_RAW=192.0.2.3
+IP6=2001:db8::1/64
+TGT6=2001:db8::2
+TGT6_RAW=2001:db8::3
+PORT=1234
+TOTAL_TESTS=0
+FAILED_TESTS=0
+
+if ! command -v jq &> /dev/null; then
+    echo "SKIP cmsg_so_priroity.sh test: jq is not installed." >&2
+    exit "$KSFT_SKIP"
+fi
+
+check_result() {
+    ((TOTAL_TESTS++))
+    if [ "$1" -ne 0 ]; then
+        ((FAILED_TESTS++))
+    fi
+}
+
+cleanup()
+{
+    cleanup_ns $NS
+}
+
+trap cleanup EXIT
+
+setup_ns NS
+
+create_filter() {
+    local handle=$1
+    local vlan_prio=$2
+    local ip_type=$3
+    local proto=$4
+    local dst_ip=$5
+    local ip_proto
+
+    if [[ "$proto" == "u" ]]; then
+        ip_proto="udp"
+    elif [[ "$ip_type" == "ipv4" && "$proto" == "i" ]]; then
+        ip_proto="icmp"
+    elif [[ "$ip_type" == "ipv6" && "$proto" == "i" ]]; then
+        ip_proto="icmpv6"
+    fi
+
+    tc -n $NS filter add dev dummy1 \
+        egress pref 1 handle "$handle" proto 802.1q \
+        flower vlan_prio "$vlan_prio" vlan_ethtype "$ip_type" \
+        dst_ip "$dst_ip" ${ip_proto:+ip_proto $ip_proto} \
+        action pass
+}
+
+ip -n $NS link set dev lo up
+ip -n $NS link add name dummy1 up type dummy
+
+ip -n $NS link add link dummy1 name dummy1.10 up type vlan id 10 \
+    egress-qos-map 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
+
+ip -n $NS address add $IP4 dev dummy1.10
+ip -n $NS address add $IP6 dev dummy1.10 nodad
+
+ip netns exec $NS sysctl -wq net.ipv4.ping_group_range='0 2147483647'
+
+ip -n $NS neigh add $TGT4 lladdr 00:11:22:33:44:55 nud permanent \
+    dev dummy1.10
+ip -n $NS neigh add $TGT6 lladdr 00:11:22:33:44:55 nud permanent \
+    dev dummy1.10
+ip -n $NS neigh add $TGT4_RAW lladdr 00:11:22:33:44:66 nud permanent \
+    dev dummy1.10
+ip -n $NS neigh add $TGT6_RAW lladdr 00:11:22:33:44:66 nud permanent \
+    dev dummy1.10
+
+tc -n $NS qdisc add dev dummy1 clsact
+
+FILTER_COUNTER=10
+
+for i in 4 6; do
+    for proto in u i r; do
+        echo "Test IPV$i, prot: $proto"
+        for priority in {0..7}; do
+            if [[ $i == 4 && $proto == "r" ]]; then
+                TGT=$TGT4_RAW
+            elif [[ $i == 6 && $proto == "r" ]]; then
+                TGT=$TGT6_RAW
+            elif [ $i == 4 ]; then
+                TGT=$TGT4
+            else
+                TGT=$TGT6
+            fi
+
+            handle="${FILTER_COUNTER}${priority}"
+
+            create_filter $handle $priority ipv$i $proto $TGT
+
+            pkts=$(tc -n $NS -j -s filter show dev dummy1 egress \
+                | jq ".[] | select(.options.handle == ${handle}) | \
+                .options.actions[0].stats.packets")
+
+            if [[ $pkts == 0 ]]; then
+                check_result 0
+            else
+                echo "prio $priority: expected 0, got $pkts"
+                check_result 1
+            fi
+
+            ip netns exec $NS ./cmsg_sender -$i -Q $priority \
+	            -p $proto $TGT $PORT
+
+            pkts=$(tc -n $NS -j -s filter show dev dummy1 egress \
+                | jq ".[] | select(.options.handle == ${handle}) | \
+                .options.actions[0].stats.packets")
+            if [[ $pkts == 1 ]]; then
+                check_result 0
+            else
+                echo "prio $priority -Q: expected 1, got $pkts"
+                check_result 1
+            fi
+
+            ip netns exec $NS ./cmsg_sender -$i -P $priority \
+	            -p $proto $TGT $PORT
+
+            pkts=$(tc -n $NS -j -s filter show dev dummy1 egress \
+                | jq ".[] | select(.options.handle == ${handle}) | \
+                .options.actions[0].stats.packets")
+            if [[ $pkts == 2 ]]; then
+                check_result 0
+            else
+                echo "prio $priority -P: expected 2, got $pkts"
+                check_result 1
+            fi
+        done
+        FILTER_COUNTER=$((FILTER_COUNTER + 10))
+    done
+done
+
+if [ $FAILED_TESTS -ne 0 ]; then
+    echo "FAIL - $FAILED_TESTS/$TOTAL_TESTS tests failed"
+    exit 1
+else
+    echo "OK - All $TOTAL_TESTS tests passed"
+    exit 0
+fi
-- 
2.50.1


From e45469e594b255ef8d750ed5576698743450d2ac Mon Sep 17 00:00:00 2001
From: Anna Emese Nyiri <annaemesenyiri@gmail.com>
Date: Fri, 13 Dec 2024 09:44:57 +0100
Subject: [PATCH 05/16] sock: Introduce SO_RCVPRIORITY socket option

Add new socket option, SO_RCVPRIORITY, to include SO_PRIORITY in the
ancillary data returned by recvmsg().
This is analogous to the existing support for SO_RCVMARK,
as implemented in commit 6fd1d51cfa253 ("net: SO_RCVMARK socket option
for SO_MARK with recvmsg()").

Reviewed-by: Willem de Bruijn <willemb@google.com>
Suggested-by: Ferenc Fejes <fejes@inf.elte.hu>
Signed-off-by: Anna Emese Nyiri <annaemesenyiri@gmail.com>
Link: https://patch.msgid.link/20241213084457.45120-5-annaemesenyiri@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 arch/alpha/include/uapi/asm/socket.h    |  2 ++
 arch/mips/include/uapi/asm/socket.h     |  2 ++
 arch/parisc/include/uapi/asm/socket.h   |  2 ++
 arch/sparc/include/uapi/asm/socket.h    |  2 ++
 include/net/sock.h                      |  4 +++-
 include/uapi/asm-generic/socket.h       |  2 ++
 net/core/sock.c                         |  8 ++++++++
 net/socket.c                            | 11 +++++++++++
 tools/include/uapi/asm-generic/socket.h |  2 ++
 9 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index 302507bf9b5d..3df5f2dd4c0f 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -148,6 +148,8 @@
 
 #define SCM_TS_OPT_ID		81
 
+#define SO_RCVPRIORITY		82
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index d118d4731580..22fa8f19924a 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -159,6 +159,8 @@
 
 #define SCM_TS_OPT_ID		81
 
+#define SO_RCVPRIORITY		82
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index d268d69bfcd2..aa9cd4b951fe 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -140,6 +140,8 @@
 
 #define SCM_TS_OPT_ID		0x404C
 
+#define SO_RCVPRIORITY		0x404D
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 113cd9f353e3..5b464a568664 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -141,6 +141,8 @@
 
 #define SCM_TS_OPT_ID            0x005a
 
+#define SO_RCVPRIORITY           0x005b
+
 #if !defined(__KERNEL__)
 
 
diff --git a/include/net/sock.h b/include/net/sock.h
index 316a34d6c48b..d4bdd3286e03 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -953,6 +953,7 @@ enum sock_flags {
 	SOCK_XDP, /* XDP is attached */
 	SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */
 	SOCK_RCVMARK, /* Receive SO_MARK  ancillary data with packet */
+	SOCK_RCVPRIORITY, /* Receive SO_PRIORITY ancillary data with packet */
 };
 
 #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
@@ -2660,7 +2661,8 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
 {
 #define FLAGS_RECV_CMSGS ((1UL << SOCK_RXQ_OVFL)			| \
 			   (1UL << SOCK_RCVTSTAMP)			| \
-			   (1UL << SOCK_RCVMARK))
+			   (1UL << SOCK_RCVMARK)			|\
+			   (1UL << SOCK_RCVPRIORITY))
 #define TSFLAGS_ANY	  (SOF_TIMESTAMPING_SOFTWARE			| \
 			   SOF_TIMESTAMPING_RAW_HARDWARE)
 
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index deacfd6dd197..aa5016ff3d91 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -143,6 +143,8 @@
 
 #define SCM_TS_OPT_ID		81
 
+#define SO_RCVPRIORITY		82
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
diff --git a/net/core/sock.c b/net/core/sock.c
index a3d9941c1d32..e7bcc8952248 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1519,6 +1519,10 @@ set_sndbuf:
 		sock_valbool_flag(sk, SOCK_RCVMARK, valbool);
 		break;
 
+	case SO_RCVPRIORITY:
+		sock_valbool_flag(sk, SOCK_RCVPRIORITY, valbool);
+		break;
+
 	case SO_RXQ_OVFL:
 		sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool);
 		break;
@@ -1947,6 +1951,10 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		v.val = sock_flag(sk, SOCK_RCVMARK);
 		break;
 
+	case SO_RCVPRIORITY:
+		v.val = sock_flag(sk, SOCK_RCVPRIORITY);
+		break;
+
 	case SO_RXQ_OVFL:
 		v.val = sock_flag(sk, SOCK_RXQ_OVFL);
 		break;
diff --git a/net/socket.c b/net/socket.c
index 9a117248f18f..16402b8be5a7 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1008,12 +1008,23 @@ static void sock_recv_mark(struct msghdr *msg, struct sock *sk,
 	}
 }
 
+static void sock_recv_priority(struct msghdr *msg, struct sock *sk,
+			       struct sk_buff *skb)
+{
+	if (sock_flag(sk, SOCK_RCVPRIORITY) && skb) {
+		__u32 priority = skb->priority;
+
+		put_cmsg(msg, SOL_SOCKET, SO_PRIORITY, sizeof(__u32), &priority);
+	}
+}
+
 void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
 		       struct sk_buff *skb)
 {
 	sock_recv_timestamp(msg, sk, skb);
 	sock_recv_drops(msg, sk, skb);
 	sock_recv_mark(msg, sk, skb);
+	sock_recv_priority(msg, sk, skb);
 }
 EXPORT_SYMBOL_GPL(__sock_recv_cmsgs);
 
diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h
index 281df9139d2b..ffff554a5230 100644
--- a/tools/include/uapi/asm-generic/socket.h
+++ b/tools/include/uapi/asm-generic/socket.h
@@ -126,6 +126,8 @@
 
 #define SCM_TS_OPT_ID		78
 
+#define SO_RCVPRIORITY		79
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
-- 
2.50.1


From b299ea0069284186b0d3d54aebe87f0d195d457a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 13 Dec 2024 20:01:41 +0100
Subject: [PATCH 06/16] r8169: adjust version numbering for RTL8126

Adjust version numbering for RTL8126, so that it doesn't overlap with
new RTL8125 versions.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/6a354364-20e9-48ad-a198-468264288757@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169.h          |  4 +-
 drivers/net/ethernet/realtek/r8169_main.c     | 62 +++++++++----------
 .../net/ethernet/realtek/r8169_phy_config.c   |  4 +-
 3 files changed, 35 insertions(+), 35 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.h b/drivers/net/ethernet/realtek/r8169.h
index 8904aae41aca..00d74e76c6f2 100644
--- a/drivers/net/ethernet/realtek/r8169.h
+++ b/drivers/net/ethernet/realtek/r8169.h
@@ -69,8 +69,8 @@ enum mac_version {
 	RTL_GIGA_MAC_VER_61,
 	RTL_GIGA_MAC_VER_63,
 	RTL_GIGA_MAC_VER_64,
-	RTL_GIGA_MAC_VER_65,
-	RTL_GIGA_MAC_VER_66,
+	RTL_GIGA_MAC_VER_70,
+	RTL_GIGA_MAC_VER_71,
 	RTL_GIGA_MAC_NONE
 };
 
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 6934bdee2a91..d153fa5598d5 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -140,8 +140,8 @@ static const struct {
 	/* reserve 62 for CFG_METHOD_4 in the vendor driver */
 	[RTL_GIGA_MAC_VER_63] = {"RTL8125B",		FIRMWARE_8125B_2},
 	[RTL_GIGA_MAC_VER_64] = {"RTL8125D",		FIRMWARE_8125D_1},
-	[RTL_GIGA_MAC_VER_65] = {"RTL8126A",		FIRMWARE_8126A_2},
-	[RTL_GIGA_MAC_VER_66] = {"RTL8126A",		FIRMWARE_8126A_3},
+	[RTL_GIGA_MAC_VER_70] = {"RTL8126A",		FIRMWARE_8126A_2},
+	[RTL_GIGA_MAC_VER_71] = {"RTL8126A",		FIRMWARE_8126A_3},
 };
 
 static const struct pci_device_id rtl8169_pci_tbl[] = {
@@ -1228,7 +1228,7 @@ static void rtl_writephy(struct rtl8169_private *tp, int location, int val)
 	case RTL_GIGA_MAC_VER_31:
 		r8168dp_2_mdio_write(tp, location, val);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71:
 		r8168g_mdio_write(tp, location, val);
 		break;
 	default:
@@ -1243,7 +1243,7 @@ static int rtl_readphy(struct rtl8169_private *tp, int location)
 	case RTL_GIGA_MAC_VER_28:
 	case RTL_GIGA_MAC_VER_31:
 		return r8168dp_2_mdio_read(tp, location);
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71:
 		return r8168g_mdio_read(tp, location);
 	default:
 		return r8169_mdio_read(tp, location);
@@ -1574,7 +1574,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 		break;
 	case RTL_GIGA_MAC_VER_34:
 	case RTL_GIGA_MAC_VER_37:
-	case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_71:
 		r8169_mod_reg8_cond(tp, Config2, PME_SIGNAL, wolopts);
 		break;
 	default:
@@ -2047,7 +2047,7 @@ static void rtl_set_eee_txidle_timer(struct rtl8169_private *tp)
 		tp->tx_lpi_timer = timer_val;
 		r8168_mac_ocp_write(tp, 0xe048, timer_val);
 		break;
-	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71:
 		tp->tx_lpi_timer = timer_val;
 		RTL_W16(tp, EEE_TXIDLE_TIMER_8125, timer_val);
 		break;
@@ -2255,8 +2255,8 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii)
 		enum mac_version ver;
 	} mac_info[] = {
 		/* 8126A family. */
-		{ 0x7cf, 0x64a,	RTL_GIGA_MAC_VER_66 },
-		{ 0x7cf, 0x649,	RTL_GIGA_MAC_VER_65 },
+		{ 0x7cf, 0x64a,	RTL_GIGA_MAC_VER_71 },
+		{ 0x7cf, 0x649,	RTL_GIGA_MAC_VER_70 },
 
 		/* 8125D family. */
 		{ 0x7cf, 0x688,	RTL_GIGA_MAC_VER_64 },
@@ -2526,7 +2526,7 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_61:
 		RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST);
 		break;
-	case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_71:
 		RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST |
 			RX_PAUSE_SLOT_ON);
 		break;
@@ -2658,7 +2658,7 @@ static void rtl_wait_txrx_fifo_empty(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_61:
 		rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42);
 		break;
-	case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_71:
 		RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
 		rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42);
 		rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond_2, 100, 42);
@@ -2901,7 +2901,7 @@ static void rtl_enable_exit_l1(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_37 ... RTL_GIGA_MAC_VER_38:
 		rtl_eri_set_bits(tp, 0xd4, 0x0c00);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71:
 		r8168_mac_ocp_modify(tp, 0xc0ac, 0, 0x1f80);
 		break;
 	default:
@@ -2915,7 +2915,7 @@ static void rtl_disable_exit_l1(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38:
 		rtl_eri_clear_bits(tp, 0xd4, 0x1f00);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71:
 		r8168_mac_ocp_modify(tp, 0xc0ac, 0x1f80, 0);
 		break;
 	default:
@@ -2941,8 +2941,8 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 
 		rtl_mod_config5(tp, 0, ASPM_en);
 		switch (tp->mac_version) {
-		case RTL_GIGA_MAC_VER_65:
-		case RTL_GIGA_MAC_VER_66:
+		case RTL_GIGA_MAC_VER_70:
+		case RTL_GIGA_MAC_VER_71:
 			val8 = RTL_R8(tp, INT_CFG0_8125) | INT_CFG0_CLKREQEN;
 			RTL_W8(tp, INT_CFG0_8125, val8);
 			break;
@@ -2953,7 +2953,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 
 		switch (tp->mac_version) {
 		case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48:
-		case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66:
+		case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71:
 			/* reset ephy tx/rx disable timer */
 			r8168_mac_ocp_modify(tp, 0xe094, 0xff00, 0);
 			/* chip can trigger L1.2 */
@@ -2965,7 +2965,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 	} else {
 		switch (tp->mac_version) {
 		case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48:
-		case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66:
+		case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71:
 			r8168_mac_ocp_modify(tp, 0xe092, 0x00ff, 0);
 			break;
 		default:
@@ -2973,8 +2973,8 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 		}
 
 		switch (tp->mac_version) {
-		case RTL_GIGA_MAC_VER_65:
-		case RTL_GIGA_MAC_VER_66:
+		case RTL_GIGA_MAC_VER_70:
+		case RTL_GIGA_MAC_VER_71:
 			val8 = RTL_R8(tp, INT_CFG0_8125) & ~INT_CFG0_CLKREQEN;
 			RTL_W8(tp, INT_CFG0_8125, val8);
 			break;
@@ -3694,12 +3694,12 @@ static void rtl_hw_start_8125_common(struct rtl8169_private *tp)
 	/* disable new tx descriptor format */
 	r8168_mac_ocp_modify(tp, 0xeb58, 0x0001, 0x0000);
 
-	if (tp->mac_version == RTL_GIGA_MAC_VER_65 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_66)
+	if (tp->mac_version == RTL_GIGA_MAC_VER_70 ||
+	    tp->mac_version == RTL_GIGA_MAC_VER_71)
 		RTL_W8(tp, 0xD8, RTL_R8(tp, 0xD8) & ~0x02);
 
-	if (tp->mac_version == RTL_GIGA_MAC_VER_65 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_66)
+	if (tp->mac_version == RTL_GIGA_MAC_VER_70 ||
+	    tp->mac_version == RTL_GIGA_MAC_VER_71)
 		r8168_mac_ocp_modify(tp, 0xe614, 0x0700, 0x0400);
 	else if (tp->mac_version == RTL_GIGA_MAC_VER_63)
 		r8168_mac_ocp_modify(tp, 0xe614, 0x0700, 0x0200);
@@ -3717,8 +3717,8 @@ static void rtl_hw_start_8125_common(struct rtl8169_private *tp)
 	r8168_mac_ocp_modify(tp, 0xe056, 0x00f0, 0x0030);
 	r8168_mac_ocp_modify(tp, 0xe040, 0x1000, 0x0000);
 	r8168_mac_ocp_modify(tp, 0xea1c, 0x0003, 0x0001);
-	if (tp->mac_version == RTL_GIGA_MAC_VER_65 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_66)
+	if (tp->mac_version == RTL_GIGA_MAC_VER_70 ||
+	    tp->mac_version == RTL_GIGA_MAC_VER_71)
 		r8168_mac_ocp_modify(tp, 0xea1c, 0x0300, 0x0000);
 	else
 		r8168_mac_ocp_modify(tp, 0xea1c, 0x0004, 0x0000);
@@ -3837,8 +3837,8 @@ static void rtl_hw_config(struct rtl8169_private *tp)
 		[RTL_GIGA_MAC_VER_61] = rtl_hw_start_8125a_2,
 		[RTL_GIGA_MAC_VER_63] = rtl_hw_start_8125b,
 		[RTL_GIGA_MAC_VER_64] = rtl_hw_start_8125d,
-		[RTL_GIGA_MAC_VER_65] = rtl_hw_start_8126a,
-		[RTL_GIGA_MAC_VER_66] = rtl_hw_start_8126a,
+		[RTL_GIGA_MAC_VER_70] = rtl_hw_start_8126a,
+		[RTL_GIGA_MAC_VER_71] = rtl_hw_start_8126a,
 	};
 
 	if (hw_configs[tp->mac_version])
@@ -3859,8 +3859,8 @@ static void rtl_hw_start_8125(struct rtl8169_private *tp)
 			RTL_W32(tp, i, 0);
 		break;
 	case RTL_GIGA_MAC_VER_63:
-	case RTL_GIGA_MAC_VER_65:
-	case RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_70:
+	case RTL_GIGA_MAC_VER_71:
 		for (i = 0xa00; i < 0xa80; i += 4)
 			RTL_W32(tp, i, 0);
 		RTL_W16(tp, INT_CFG1_8125, 0x0000);
@@ -4092,7 +4092,7 @@ static void rtl8169_cleanup(struct rtl8169_private *tp)
 		RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
 		rtl_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 666);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71:
 		rtl_enable_rxdvgate(tp);
 		fsleep(2000);
 		break;
@@ -4249,7 +4249,7 @@ static unsigned int rtl_quirk_packet_padto(struct rtl8169_private *tp,
 
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_34:
-	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71:
 		padto = max_t(unsigned int, padto, ETH_ZLEN);
 		break;
 	default:
@@ -5267,7 +5267,7 @@ static void rtl_hw_initialize(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_48:
 		rtl_hw_init_8168g(tp);
 		break;
-	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71:
 		rtl_hw_init_8125(tp);
 		break;
 	default:
diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c
index b28b30390e84..bc498ea78034 100644
--- a/drivers/net/ethernet/realtek/r8169_phy_config.c
+++ b/drivers/net/ethernet/realtek/r8169_phy_config.c
@@ -1162,8 +1162,8 @@ void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev,
 		[RTL_GIGA_MAC_VER_61] = rtl8125a_2_hw_phy_config,
 		[RTL_GIGA_MAC_VER_63] = rtl8125b_hw_phy_config,
 		[RTL_GIGA_MAC_VER_64] = rtl8125d_hw_phy_config,
-		[RTL_GIGA_MAC_VER_65] = rtl8126a_hw_phy_config,
-		[RTL_GIGA_MAC_VER_66] = rtl8126a_hw_phy_config,
+		[RTL_GIGA_MAC_VER_70] = rtl8126a_hw_phy_config,
+		[RTL_GIGA_MAC_VER_71] = rtl8126a_hw_phy_config,
 	};
 
 	if (phy_configs[ver])
-- 
2.50.1


From b3593df26ab19f114d613693fa8a92ab202803d0 Mon Sep 17 00:00:00 2001
From: ChunHao Lin <hau@realtek.com>
Date: Fri, 13 Dec 2024 20:02:58 +0100
Subject: [PATCH 07/16] r8169: add support for RTL8125D rev.b

Add support for RTL8125D rev.b. Its XID is 0x689. It is basically
based on the one with XID 0x688, but with different firmware file.

Signed-off-by: ChunHao Lin <hau@realtek.com>
[hkallweit1@gmail.com: rebased after adjusted version numbering]
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/75e5e9ec-d01f-43ac-b0f4-e7456baf18d1@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169.h            | 1 +
 drivers/net/ethernet/realtek/r8169_main.c       | 6 ++++++
 drivers/net/ethernet/realtek/r8169_phy_config.c | 1 +
 3 files changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169.h b/drivers/net/ethernet/realtek/r8169.h
index 00d74e76c6f2..e0817f2a311a 100644
--- a/drivers/net/ethernet/realtek/r8169.h
+++ b/drivers/net/ethernet/realtek/r8169.h
@@ -69,6 +69,7 @@ enum mac_version {
 	RTL_GIGA_MAC_VER_61,
 	RTL_GIGA_MAC_VER_63,
 	RTL_GIGA_MAC_VER_64,
+	RTL_GIGA_MAC_VER_65,
 	RTL_GIGA_MAC_VER_70,
 	RTL_GIGA_MAC_VER_71,
 	RTL_GIGA_MAC_NONE
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index d153fa5598d5..5724f650f9c6 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -57,6 +57,7 @@
 #define FIRMWARE_8125A_3	"rtl_nic/rtl8125a-3.fw"
 #define FIRMWARE_8125B_2	"rtl_nic/rtl8125b-2.fw"
 #define FIRMWARE_8125D_1	"rtl_nic/rtl8125d-1.fw"
+#define FIRMWARE_8125D_2	"rtl_nic/rtl8125d-2.fw"
 #define FIRMWARE_8126A_2	"rtl_nic/rtl8126a-2.fw"
 #define FIRMWARE_8126A_3	"rtl_nic/rtl8126a-3.fw"
 
@@ -140,6 +141,7 @@ static const struct {
 	/* reserve 62 for CFG_METHOD_4 in the vendor driver */
 	[RTL_GIGA_MAC_VER_63] = {"RTL8125B",		FIRMWARE_8125B_2},
 	[RTL_GIGA_MAC_VER_64] = {"RTL8125D",		FIRMWARE_8125D_1},
+	[RTL_GIGA_MAC_VER_65] = {"RTL8125D",		FIRMWARE_8125D_2},
 	[RTL_GIGA_MAC_VER_70] = {"RTL8126A",		FIRMWARE_8126A_2},
 	[RTL_GIGA_MAC_VER_71] = {"RTL8126A",		FIRMWARE_8126A_3},
 };
@@ -706,6 +708,7 @@ MODULE_FIRMWARE(FIRMWARE_8107E_2);
 MODULE_FIRMWARE(FIRMWARE_8125A_3);
 MODULE_FIRMWARE(FIRMWARE_8125B_2);
 MODULE_FIRMWARE(FIRMWARE_8125D_1);
+MODULE_FIRMWARE(FIRMWARE_8125D_2);
 MODULE_FIRMWARE(FIRMWARE_8126A_2);
 MODULE_FIRMWARE(FIRMWARE_8126A_3);
 
@@ -2259,6 +2262,7 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii)
 		{ 0x7cf, 0x649,	RTL_GIGA_MAC_VER_70 },
 
 		/* 8125D family. */
+		{ 0x7cf, 0x689,	RTL_GIGA_MAC_VER_65 },
 		{ 0x7cf, 0x688,	RTL_GIGA_MAC_VER_64 },
 
 		/* 8125B family. */
@@ -3837,6 +3841,7 @@ static void rtl_hw_config(struct rtl8169_private *tp)
 		[RTL_GIGA_MAC_VER_61] = rtl_hw_start_8125a_2,
 		[RTL_GIGA_MAC_VER_63] = rtl_hw_start_8125b,
 		[RTL_GIGA_MAC_VER_64] = rtl_hw_start_8125d,
+		[RTL_GIGA_MAC_VER_65] = rtl_hw_start_8125d,
 		[RTL_GIGA_MAC_VER_70] = rtl_hw_start_8126a,
 		[RTL_GIGA_MAC_VER_71] = rtl_hw_start_8126a,
 	};
@@ -3855,6 +3860,7 @@ static void rtl_hw_start_8125(struct rtl8169_private *tp)
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_61:
 	case RTL_GIGA_MAC_VER_64:
+	case RTL_GIGA_MAC_VER_65:
 		for (i = 0xa00; i < 0xb00; i += 4)
 			RTL_W32(tp, i, 0);
 		break;
diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c
index bc498ea78034..968c8a2185a4 100644
--- a/drivers/net/ethernet/realtek/r8169_phy_config.c
+++ b/drivers/net/ethernet/realtek/r8169_phy_config.c
@@ -1162,6 +1162,7 @@ void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev,
 		[RTL_GIGA_MAC_VER_61] = rtl8125a_2_hw_phy_config,
 		[RTL_GIGA_MAC_VER_63] = rtl8125b_hw_phy_config,
 		[RTL_GIGA_MAC_VER_64] = rtl8125d_hw_phy_config,
+		[RTL_GIGA_MAC_VER_65] = rtl8125d_hw_phy_config,
 		[RTL_GIGA_MAC_VER_70] = rtl8126a_hw_phy_config,
 		[RTL_GIGA_MAC_VER_71] = rtl8126a_hw_phy_config,
 	};
-- 
2.50.1


From 34c899af6c1a9d65aa85c765b2eecb1b9a88e8b8 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 13 Dec 2024 20:08:39 +0900
Subject: [PATCH 08/16] af_unix: Set error only when needed in
 unix_stream_connect().

We will introduce skb drop reason for AF_UNIX, then we need to
set an errno and a drop reason for each path.

Let's set an error only when it's needed in unix_stream_connect().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 6b1762300443..23f419f561b8 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1575,12 +1575,12 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		goto out;
 	}
 
-	err = -ENOMEM;
-
 	/* Allocate skb for sending to listening sock */
 	skb = sock_wmalloc(newsk, 1, 0, GFP_KERNEL);
-	if (skb == NULL)
+	if (!skb) {
+		err = -ENOMEM;
 		goto out;
+	}
 
 restart:
 	/*  Find listening sock. */
@@ -1600,16 +1600,17 @@ restart:
 		goto restart;
 	}
 
-	err = -ECONNREFUSED;
-	if (other->sk_state != TCP_LISTEN)
-		goto out_unlock;
-	if (other->sk_shutdown & RCV_SHUTDOWN)
+	if (other->sk_state != TCP_LISTEN ||
+	    other->sk_shutdown & RCV_SHUTDOWN) {
+		err = -ECONNREFUSED;
 		goto out_unlock;
+	}
 
 	if (unix_recvq_full_lockless(other)) {
-		err = -EAGAIN;
-		if (!timeo)
+		if (!timeo) {
+			err = -EAGAIN;
 			goto out_unlock;
+		}
 
 		timeo = unix_wait_for_peer(other, timeo);
 
-- 
2.50.1


From e26ee0a736bd949ce6fa51829fd0a2f6381391de Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 13 Dec 2024 20:08:40 +0900
Subject: [PATCH 09/16] af_unix: Clean up error paths in unix_stream_connect().

The label order is weird in unix_stream_connect(), and all NULL checks
are unnecessary if reordered.

Let's clean up the error paths to make it easy to set a drop reason
for each path.

While at it, a comment with the old style is updated.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 29 +++++++++++++----------------
 1 file changed, 13 insertions(+), 16 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 23f419f561b8..21e17e739f88 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1563,15 +1563,14 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	timeo = sock_sndtimeo(sk, flags & O_NONBLOCK);
 
 	/* First of all allocate resources.
-	   If we will make it after state is locked,
-	   we will have to recheck all again in any case.
+	 * If we will make it after state is locked,
+	 * we will have to recheck all again in any case.
 	 */
 
 	/* create new sock for complete connection */
 	newsk = unix_create1(net, NULL, 0, sock->type);
 	if (IS_ERR(newsk)) {
 		err = PTR_ERR(newsk);
-		newsk = NULL;
 		goto out;
 	}
 
@@ -1579,7 +1578,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	skb = sock_wmalloc(newsk, 1, 0, GFP_KERNEL);
 	if (!skb) {
 		err = -ENOMEM;
-		goto out;
+		goto out_free_sk;
 	}
 
 restart:
@@ -1587,8 +1586,7 @@ restart:
 	other = unix_find_other(net, sunaddr, addr_len, sk->sk_type);
 	if (IS_ERR(other)) {
 		err = PTR_ERR(other);
-		other = NULL;
-		goto out;
+		goto out_free_skb;
 	}
 
 	unix_state_lock(other);
@@ -1613,11 +1611,12 @@ restart:
 		}
 
 		timeo = unix_wait_for_peer(other, timeo);
+		sock_put(other);
 
 		err = sock_intr_errno(timeo);
 		if (signal_pending(current))
-			goto out;
-		sock_put(other);
+			goto out_free_skb;
+
 		goto restart;
 	}
 
@@ -1702,15 +1701,13 @@ restart:
 	return 0;
 
 out_unlock:
-	if (other)
-		unix_state_unlock(other);
-
-out:
+	unix_state_unlock(other);
+	sock_put(other);
+out_free_skb:
 	kfree_skb(skb);
-	if (newsk)
-		unix_release_sock(newsk, 0);
-	if (other)
-		sock_put(other);
+out_free_sk:
+	unix_release_sock(newsk, 0);
+out:
 	return err;
 }
 
-- 
2.50.1


From 6c444255b193b5b9c5a18c3784d960e10e1833a2 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 13 Dec 2024 20:08:41 +0900
Subject: [PATCH 10/16] af_unix: Set error only when needed in
 unix_stream_sendmsg().

We will introduce skb drop reason for AF_UNIX, then we need to
set an errno and a drop reason for each path.

Let's set an error only when it's needed in unix_stream_sendmsg().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 21e17e739f88..660d8b8130ca 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2254,8 +2254,8 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	wait_for_unix_gc(scm.fp);
 
-	err = -EOPNOTSUPP;
 	if (msg->msg_flags & MSG_OOB) {
+		err = -EOPNOTSUPP;
 #if IS_ENABLED(CONFIG_AF_UNIX_OOB)
 		if (len)
 			len--;
@@ -2268,10 +2268,11 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 		err = READ_ONCE(sk->sk_state) == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
 		goto out_err;
 	} else {
-		err = -ENOTCONN;
 		other = unix_peer(sk);
-		if (!other)
+		if (!other) {
+			err = -ENOTCONN;
 			goto out_err;
+		}
 	}
 
 	if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
-- 
2.50.1


From d460b04bc452cf15810b79c15381fffd9d201915 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 13 Dec 2024 20:08:42 +0900
Subject: [PATCH 11/16] af_unix: Clean up error paths in unix_stream_sendmsg().

If we move send_sig() to the SEND_SHUTDOWN check before
the while loop, then we can reuse the same kfree_skb()
after the pipe_err_free label.

Let's gather the scattered kfree_skb()s in error paths.

While at it, some style issues are fixed, and the pipe_err_free
label is renamed to out_pipe to match other label names.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 39 ++++++++++++++++++++-------------------
 1 file changed, 20 insertions(+), 19 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 660d8b8130ca..d30bcd50527e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2275,8 +2275,13 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 		}
 	}
 
-	if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
-		goto pipe_err;
+	if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) {
+		if (!(msg->msg_flags & MSG_NOSIGNAL))
+			send_sig(SIGPIPE, current, 0);
+
+		err = -EPIPE;
+		goto out_err;
+	}
 
 	while (sent < len) {
 		size = len - sent;
@@ -2305,20 +2310,18 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 		/* Only send the fds in the first buffer */
 		err = unix_scm_to_skb(&scm, skb, !fds_sent);
-		if (err < 0) {
-			kfree_skb(skb);
-			goto out_err;
-		}
+		if (err < 0)
+			goto out_free;
+
 		fds_sent = true;
 
 		if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) {
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 			err = skb_splice_from_iter(skb, &msg->msg_iter, size,
 						   sk->sk_allocation);
-			if (err < 0) {
-				kfree_skb(skb);
-				goto out_err;
-			}
+			if (err < 0)
+				goto out_free;
+
 			size = err;
 			refcount_add(size, &sk->sk_wmem_alloc);
 		} else {
@@ -2326,17 +2329,15 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 			skb->data_len = data_len;
 			skb->len = size;
 			err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
-			if (err) {
-				kfree_skb(skb);
-				goto out_err;
-			}
+			if (err)
+				goto out_free;
 		}
 
 		unix_state_lock(other);
 
 		if (sock_flag(other, SOCK_DEAD) ||
 		    (other->sk_shutdown & RCV_SHUTDOWN))
-			goto pipe_err_free;
+			goto out_pipe;
 
 		maybe_add_creds(skb, sock, other);
 		scm_stat_add(other, skb);
@@ -2359,13 +2360,13 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	return sent;
 
-pipe_err_free:
+out_pipe:
 	unix_state_unlock(other);
-	kfree_skb(skb);
-pipe_err:
-	if (sent == 0 && !(msg->msg_flags&MSG_NOSIGNAL))
+	if (!sent && !(msg->msg_flags & MSG_NOSIGNAL))
 		send_sig(SIGPIPE, current, 0);
 	err = -EPIPE;
+out_free:
+	kfree_skb(skb);
 out_err:
 	scm_destroy(&scm);
 	return sent ? : err;
-- 
2.50.1


From 001a25088c35ab69bd4b2f208e47eb8acbce6353 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 13 Dec 2024 20:08:43 +0900
Subject: [PATCH 12/16] af_unix: Set error only when needed in
 unix_dgram_sendmsg().

We will introduce skb drop reason for AF_UNIX, then we need to
set an errno and a drop reason for each path.

Let's set an error only when it's needed in unix_dgram_sendmsg().

Then, we need not (re)set 0 to err.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 32 +++++++++++++++++++-------------
 1 file changed, 19 insertions(+), 13 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index d30bcd50527e..07d6fba99a7c 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1978,9 +1978,10 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	wait_for_unix_gc(scm.fp);
 
-	err = -EOPNOTSUPP;
-	if (msg->msg_flags&MSG_OOB)
+	if (msg->msg_flags & MSG_OOB) {
+		err = -EOPNOTSUPP;
 		goto out;
+	}
 
 	if (msg->msg_namelen) {
 		err = unix_validate_addr(sunaddr, msg->msg_namelen);
@@ -1995,10 +1996,11 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 			goto out;
 	} else {
 		sunaddr = NULL;
-		err = -ENOTCONN;
 		other = unix_peer_get(sk);
-		if (!other)
+		if (!other) {
+			err = -ENOTCONN;
 			goto out;
+		}
 	}
 
 	if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
@@ -2009,9 +2011,10 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 			goto out;
 	}
 
-	err = -EMSGSIZE;
-	if (len > READ_ONCE(sk->sk_sndbuf) - 32)
+	if (len > READ_ONCE(sk->sk_sndbuf) - 32) {
+		err = -EMSGSIZE;
 		goto out;
+	}
 
 	if (len > SKB_MAX_ALLOC) {
 		data_len = min_t(size_t,
@@ -2043,9 +2046,10 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 
 restart:
 	if (!other) {
-		err = -ECONNRESET;
-		if (sunaddr == NULL)
+		if (!sunaddr) {
+			err = -ECONNRESET;
 			goto out_free;
+		}
 
 		other = unix_find_other(sock_net(sk), sunaddr, msg->msg_namelen,
 					sk->sk_type);
@@ -2065,9 +2069,11 @@ restart:
 	sk_locked = 0;
 	unix_state_lock(other);
 restart_locked:
-	err = -EPERM;
-	if (!unix_may_send(sk, other))
+
+	if (!unix_may_send(sk, other)) {
+		err = -EPERM;
 		goto out_unlock;
+	}
 
 	if (unlikely(sock_flag(other, SOCK_DEAD))) {
 		/*
@@ -2080,7 +2086,6 @@ restart_locked:
 		if (!sk_locked)
 			unix_state_lock(sk);
 
-		err = 0;
 		if (sk->sk_type == SOCK_SEQPACKET) {
 			/* We are here only when racing with unix_release_sock()
 			 * is clearing @other. Never change state to TCP_CLOSE
@@ -2108,9 +2113,10 @@ restart_locked:
 		goto restart;
 	}
 
-	err = -EPIPE;
-	if (other->sk_shutdown & RCV_SHUTDOWN)
+	if (other->sk_shutdown & RCV_SHUTDOWN) {
+		err = -EPIPE;
 		goto out_unlock;
+	}
 
 	if (sk->sk_type != SOCK_SEQPACKET) {
 		err = security_unix_may_send(sk->sk_socket, other->sk_socket);
-- 
2.50.1


From f4dd63165b08ba3b72117973d5daea456f36377d Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 13 Dec 2024 20:08:44 +0900
Subject: [PATCH 13/16] af_unix: Move !sunaddr case in unix_dgram_sendmsg().

When other is NULL in unix_dgram_sendmsg(), we check if sunaddr
is NULL before looking up a receiver socket.

There are three paths going through the check, but it's always
false for 2 out of the 3 paths: the first socket lookup and the
second 'goto restart'.

The condition can be true for the first 'goto restart' only when
SOCK_DEAD is flagged for the socket found with msg->msg_name.

Let's move the check to the single appropriate path.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 07d6fba99a7c..111f95384990 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2046,11 +2046,6 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 
 restart:
 	if (!other) {
-		if (!sunaddr) {
-			err = -ECONNRESET;
-			goto out_free;
-		}
-
 		other = unix_find_other(sock_net(sk), sunaddr, msg->msg_namelen,
 					sk->sk_type);
 		if (IS_ERR(other)) {
@@ -2105,6 +2100,9 @@ restart_locked:
 			err = -ECONNREFUSED;
 		} else {
 			unix_state_unlock(sk);
+
+			if (!sunaddr)
+				err = -ECONNRESET;
 		}
 
 		other = NULL;
-- 
2.50.1


From 3c05329a2abe312ed85a60a325b930063f61e817 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 13 Dec 2024 20:08:45 +0900
Subject: [PATCH 14/16] af_unix: Use msg->{msg_name,msg_namelen} in
 unix_dgram_sendmsg().

In unix_dgram_sendmsg(), we use a local variable sunaddr pointing
NULL or msg->msg_name based on msg->msg_namelen.

Let's remove sunaddr and simplify the usage.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 111f95384990..ae74fdcf5dcd 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1962,7 +1962,6 @@ static void scm_stat_del(struct sock *sk, struct sk_buff *skb)
 static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 			      size_t len)
 {
-	DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name);
 	struct sock *sk = sock->sk, *other = NULL;
 	struct unix_sock *u = unix_sk(sk);
 	struct scm_cookie scm;
@@ -1984,7 +1983,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 	}
 
 	if (msg->msg_namelen) {
-		err = unix_validate_addr(sunaddr, msg->msg_namelen);
+		err = unix_validate_addr(msg->msg_name, msg->msg_namelen);
 		if (err)
 			goto out;
 
@@ -1995,7 +1994,6 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 		if (err)
 			goto out;
 	} else {
-		sunaddr = NULL;
 		other = unix_peer_get(sk);
 		if (!other) {
 			err = -ENOTCONN;
@@ -2046,8 +2044,8 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 
 restart:
 	if (!other) {
-		other = unix_find_other(sock_net(sk), sunaddr, msg->msg_namelen,
-					sk->sk_type);
+		other = unix_find_other(sock_net(sk), msg->msg_name,
+					msg->msg_namelen, sk->sk_type);
 		if (IS_ERR(other)) {
 			err = PTR_ERR(other);
 			other = NULL;
@@ -2101,7 +2099,7 @@ restart_locked:
 		} else {
 			unix_state_unlock(sk);
 
-			if (!sunaddr)
+			if (!msg->msg_namelen)
 				err = -ECONNRESET;
 		}
 
-- 
2.50.1


From a700b43358ccc3c5ae857eeea37ff50ce0529b1c Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 13 Dec 2024 20:08:46 +0900
Subject: [PATCH 15/16] af_unix: Split restart label in unix_dgram_sendmsg().

There are two paths jumping to the restart label in unix_dgram_sendmsg().

One requires another lookup and sk_filter(), but the other doesn't.

Let's split the label to make each flow more straightforward.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index ae74fdcf5dcd..513d0fd12e6a 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2042,8 +2042,8 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
-restart:
 	if (!other) {
+lookup:
 		other = unix_find_other(sock_net(sk), msg->msg_name,
 					msg->msg_namelen, sk->sk_type);
 		if (IS_ERR(other)) {
@@ -2059,6 +2059,7 @@ restart:
 		goto out_free;
 	}
 
+restart:
 	sk_locked = 0;
 	unix_state_lock(other);
 restart_locked:
@@ -2106,7 +2107,8 @@ restart_locked:
 		other = NULL;
 		if (err)
 			goto out_free;
-		goto restart;
+
+		goto lookup;
 	}
 
 	if (other->sk_shutdown & RCV_SHUTDOWN) {
-- 
2.50.1


From 689c398885cc27d2a5bb2ad5d70324107d4a78ec Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 13 Dec 2024 20:08:47 +0900
Subject: [PATCH 16/16] af_unix: Defer sock_put() to clean up path in
 unix_dgram_sendmsg().

When other has SOCK_DEAD in unix_dgram_sendmsg(), we call sock_put() for
it first and then set NULL to other before jumping to the error path.

This is to skip sock_put() in the error path.

Let's not set NULL to other and defer the sock_put() to the error path
to clean up the labels later.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 513d0fd12e6a..b8adfb41d11b 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2075,7 +2075,6 @@ restart_locked:
 		 *	datagram error
 		 */
 		unix_state_unlock(other);
-		sock_put(other);
 
 		if (!sk_locked)
 			unix_state_lock(sk);
@@ -2104,7 +2103,6 @@ restart_locked:
 				err = -ECONNRESET;
 		}
 
-		other = NULL;
 		if (err)
 			goto out_free;
 
-- 
2.50.1