@@ -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;
@@ -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;
@@ -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),
};
}
@@ -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;
@@ -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;
}
@@ -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);
@@ -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)))
@@ -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);
@@ -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);
@@ -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);
@@ -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)
@@ -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) {
@@ -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);
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(-)