diff mbox series

[net-next,v5,2/4] sock: support SO_PRIORITY cmsg

Message ID 20241205133112.17903-3-annaemesenyiri@gmail.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series Add support for SO_PRIORITY cmsg | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next, async
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 17 this patch: 17
netdev/build_tools success Errors and warnings before: 0 (+23) this patch: 0 (+23)
netdev/cc_maintainers warning 5 maintainers not CCed: linux-can@vger.kernel.org horms@kernel.org socketcan@hartkopp.net mkl@pengutronix.de dsahern@kernel.org
netdev/build_clang success Errors and warnings before: 29 this patch: 29
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 2898 this patch: 2898
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 143 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 18 this patch: 18
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2024-12-06--18-00 (tests: 764)

Commit Message

Anna Nyiri Dec. 5, 2024, 1:31 p.m. UTC 
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 <f02db315b8d88>
("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>
---
 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 mbox series

Patch

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 0065b1996c94..cd3e788600cc 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1328,7 +1328,7 @@  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);
@@ -1465,7 +1465,7 @@  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 f7b4608bb316..ec9673b7ab16 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;
@@ -1939,7 +1940,7 @@  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);