[PATCH net-next v2 2/2] support SO_PRIORITY cmsg
From: Anna Emese Nyiri <hidden>
Date: 2024-11-02 12:52:10
Subsystem:
can network layer, networking [general], networking [ipv4/ipv6], networking [sockets], packet sockets, the rest · Maintainers:
Oliver Hartkopp, Marc Kleine-Budde, "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, David Ahern, Ido Schimmel, Kuniyuki Iwashima, Willem de Bruijn, Linus Torvalds
The Linux socket API currently supports setting SO_PRIORITY at the
socket level, which applies a uniform priority to all packets sent
through that socket. The only exception is IP_TOS; if specified as
ancillary data, the packet does not inherit the socket's priority.
Instead, the priority value is computed when handling the ancillary
data (as implemented in commit <f02db315b8d88>
("ipv4: IP_TOS and IP_TTL can be specified as ancillary data")). If
the priority is set via IP_TOS, then skb->priority derives its value
from the rt_tos2priority function, which calculates the priority
based on the value of ipc->tos obtained from IP_TOS. However, if
IP_TOS is not used and the priority has been set through a control
message, skb->priority will take the value provided by that control
message. Therefore, when both options are available, the primary
source for skb->priority is the value set via IP_TOS.
Currently, there is no option to set the priority directly from
userspace on a per-packet basis. The following changes allow
SO_PRIORITY to be set through control messages (CMSG), giving
userspace applications more granular control over packet priorities.
This patch enables setting skb->priority using CMSG. If SO_PRIORITY
is specified as ancillary data, the packet is sent with the priority
value set through sockc->priority_cmsg_value, overriding the
socket-level values set via the traditional setsockopt() method. This
is analogous to existing support for SO_MARK (as implemented in commit
<c6af0c227a22> ("ip: support SO_MARK cmsg")).
Suggested-by: Ferenc Fejes <redacted>
Signed-off-by: Anna Emese Nyiri <redacted>
---
include/net/inet_sock.h | 2 +-
include/net/ip.h | 3 ++-
include/net/sock.h | 4 +++-
net/can/raw.c | 2 +-
net/core/sock.c | 8 ++++++++
net/ipv4/ip_output.c | 7 +++++--
net/ipv4/raw.c | 2 +-
net/ipv6/ip6_output.c | 3 ++-
net/ipv6/raw.c | 2 +-
net/packet/af_packet.c | 2 +-
10 files changed, 25 insertions(+), 10 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..e8f71a191277 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h@@ -81,7 +81,7 @@ struct ipcm_cookie { __u8 protocol; __u8 ttl; __s16 tos; - char priority; + u32 priority; __u16 gso_size; };
@@ -96,6 +96,7 @@ 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 5ecf6f1a470c..d5586b9212dd 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c@@ -2941,6 +2941,14 @@ 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))) { + sockc->priority = *(u32 *)CMSG_DATA(cmsg); + break; + } + return -EPERM; default: return -EINVAL; }
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 0065b1996c94..72b37321c0ea 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c@@ -1328,7 +1328,10 @@ 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; + if (cork->tos != -1) + cork->priority = ipc->priority; + else + 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 +1468,7 @@ 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/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/raw.c b/net/ipv6/raw.c
index 8476a3944a88..c82cc6cfdbd2 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);
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);
--
2.43.0