| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <66d1df11a42fc_3c08a2294a5@willemb.c.googlers.com.notmuch>
Date: Fri, 30 Aug 2024 11:02:41 -0400
From: Willem de Bruijn <willemdebruijn.kernel@...il.com>
To: Vadim Fedorenko <vadfed@...a.com>,
Vadim Fedorenko <vadim.fedorenko@...ux.dev>,
Willem de Bruijn <willemb@...gle.com>,
Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>,
David Ahern <dsahern@...nel.org>
Cc: Vadim Fedorenko <vadfed@...a.com>,
netdev@...r.kernel.org
Subject: Re: [PATCH net-next 1/2] net_tstamp: add SCM_TS_OPT_ID to provide
OPT_ID in control message
Vadim Fedorenko wrote:
> SOF_TIMESTAMPING_OPT_ID socket option flag gives a way to correlate TX
> timestamps and packets sent via socket. Unfortunately, there is no way
> to reliably predict socket timestamp ID value in case of error returned
> by sendmsg. For UDP sockets it's impossible because of lockless
> nature of UDP transmit, several threads may send packets in parallel. In
> case of RAW sockets MSG_MORE option makes things complicated. More
> details are in the conversation [1].
> This patch adds new control message type to give user-space
> software an opportunity to control the mapping between packets and
> values by providing ID with each sendmsg. This works fine for UDP
> sockets only, and explicit check is added to control message parser.
>
> [1] https://lore.kernel.org/netdev/CALCETrU0jB+kg0mhV6A8mrHfTE1D1pr1SD_B9Eaa9aDPfgHdtA@mail.gmail.com/
>
> Signed-off-by: Vadim Fedorenko <vadfed@...a.com>
> ---
> include/net/inet_sock.h | 4 +++-
> include/net/sock.h | 1 +
> include/uapi/asm-generic/socket.h | 2 ++
> include/uapi/linux/net_tstamp.h | 1 +
> net/core/sock.c | 12 ++++++++++++
> net/ipv4/ip_output.c | 13 +++++++++++--
> net/ipv6/ip6_output.c | 13 +++++++++++--
> 7 files changed, 41 insertions(+), 5 deletions(-)
>
> diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
> index 394c3b66065e..2161d50cf0fd 100644
> --- a/include/net/inet_sock.h
> +++ b/include/net/inet_sock.h
> @@ -174,6 +174,7 @@ struct inet_cork {
> __s16 tos;
> char priority;
> __u16 gso_size;
> + u32 ts_opt_id;
> u64 transmit_time;
> u32 mark;
> };
> @@ -241,7 +242,8 @@ struct inet_sock {
> struct inet_cork_full cork;
> };
>
> -#define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */
> +#define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */
> +#define IPCORK_TS_OPT_ID 2 /* timestmap opt id has been provided in cmsg */
>
> enum {
> INET_FLAGS_PKTINFO = 0,
> diff --git a/include/net/sock.h b/include/net/sock.h
> index f51d61fab059..73e21dad5660 100644
> --- a/include/net/sock.h
> +++ b/include/net/sock.h
> @@ -1794,6 +1794,7 @@ struct sockcm_cookie {
> u64 transmit_time;
> u32 mark;
> u32 tsflags;
> + u32 ts_opt_id;
> };
>
> static inline void sockcm_init(struct sockcm_cookie *sockc,
> diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
> index 8ce8a39a1e5f..db3df3e74b01 100644
> --- a/include/uapi/asm-generic/socket.h
> +++ b/include/uapi/asm-generic/socket.h
> @@ -135,6 +135,8 @@
> #define SO_PASSPIDFD 76
> #define SO_PEERPIDFD 77
>
> +#define SCM_TS_OPT_ID 78
> +
> #if !defined(__KERNEL__)
>
> #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
> diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
> index a2c66b3d7f0f..081b40a55a2e 100644
> --- a/include/uapi/linux/net_tstamp.h
> +++ b/include/uapi/linux/net_tstamp.h
> @@ -32,6 +32,7 @@ enum {
> SOF_TIMESTAMPING_OPT_TX_SWHW = (1<<14),
> SOF_TIMESTAMPING_BIND_PHC = (1 << 15),
> SOF_TIMESTAMPING_OPT_ID_TCP = (1 << 16),
> + SOF_TIMESTAMPING_OPT_ID_CMSG = (1 << 17),
>
> SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_ID_TCP,
> SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) |
Update SOF_TIMESTAMPING_LAST
> diff --git a/net/core/sock.c b/net/core/sock.c
> index 468b1239606c..560b075765fa 100644
> --- a/net/core/sock.c
> +++ b/net/core/sock.c
> @@ -2859,6 +2859,18 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
> return -EINVAL;
> sockc->transmit_time = get_unaligned((u64 *)CMSG_DATA(cmsg));
> break;
> + case SCM_TS_OPT_ID:
> + /* allow this option for UDP sockets only */
> + if (!sk_is_udp(sk))
> + return -EINVAL;
> + tsflags = READ_ONCE(sk->sk_tsflags);
> + if (!(tsflags & SOF_TIMESTAMPING_OPT_ID))
> + return -EINVAL;
> + if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
> + return -EINVAL;
> + sockc->ts_opt_id = *(u32 *)CMSG_DATA(cmsg);
> + sockc->tsflags |= SOF_TIMESTAMPING_OPT_ID_CMSG;
> + break;
> /* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */
> case SCM_RIGHTS:
> case SCM_CREDENTIALS:
> diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
> index b90d0f78ac80..65b5d9f53102 100644
> --- a/net/ipv4/ip_output.c
> +++ b/net/ipv4/ip_output.c
> @@ -1050,8 +1050,14 @@ static int __ip_append_data(struct sock *sk,
>
> hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP &&
> READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID;
> - if (hold_tskey)
> - tskey = atomic_inc_return(&sk->sk_tskey) - 1;
> + if (hold_tskey) {
> + if (cork->flags & IPCORK_TS_OPT_ID) {
> + hold_tskey = false;
> + tskey = cork->ts_opt_id;
> + } else {
> + tskey = atomic_inc_return(&sk->sk_tskey) - 1;
> + }
> + }
>
> /* So, what's going on in the loop below?
> *
> @@ -1324,8 +1330,11 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
> cork->mark = ipc->sockc.mark;
> cork->priority = ipc->priority;
> cork->transmit_time = ipc->sockc.transmit_time;
> + cork->ts_opt_id = ipc->sockc.ts_opt_id;
> cork->tx_flags = 0;
> sock_tx_timestamp(sk, ipc->sockc.tsflags, &cork->tx_flags);
> + if (ipc->sockc.tsflags & SOF_TIMESTAMPING_OPT_ID_CMSG)
> + cork->flags |= IPCORK_TS_OPT_ID;
>
> return 0;
> }
> diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
> index f26841f1490f..91eafef85c85 100644
> --- a/net/ipv6/ip6_output.c
> +++ b/net/ipv6/ip6_output.c
> @@ -1401,7 +1401,10 @@ 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.ts_opt_id = ipc6->sockc.ts_opt_id;
> sock_tx_timestamp(sk, ipc6->sockc.tsflags, &cork->base.tx_flags);
> + if (ipc6->sockc.tsflags & SOF_TIMESTAMPING_OPT_ID_CMSG)
> + cork->base.flags |= IPCORK_TS_OPT_ID;
>
> cork->base.length = 0;
> cork->base.transmit_time = ipc6->sockc.transmit_time;
> @@ -1545,8 +1548,14 @@ static int __ip6_append_data(struct sock *sk,
>
> hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP &&
> READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID;
> - if (hold_tskey)
> - tskey = atomic_inc_return(&sk->sk_tskey) - 1;
> + if (hold_tskey) {
> + if (cork->flags & IPCORK_TS_OPT_ID) {
> + hold_tskey = false;
> + tskey = cork->ts_opt_id;
> + } else {
> + tskey = atomic_inc_return(&sk->sk_tskey) - 1;
> + }
> + }
Setting, then clearing hold_tskey is a bit weird. How about
if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) {
if (cork->flags & IPCORK_TS_OPT_ID) {
tskey = cork->ts_opt_id;
} else {
tskey = atomic_inc_return(&sk->sk_tskey) - 1;
hold_tskey = true;
}
}
Powered by blists - more mailing lists