| 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: <dfe033f1-cc61-4be3-a59d-e6b623591cc6@linux.dev>
Date: Thu, 29 Aug 2024 15:13:43 +0100
From: Vadim Fedorenko <vadim.fedorenko@...ux.dev>
To: Willem de Bruijn <willemdebruijn.kernel@...il.com>,
Vadim Fedorenko <vadfed@...a.com>, Jakub Kicinski <kuba@...nel.org>,
Willem de Bruijn <willemb@...gle.com>, Paolo Abeni <pabeni@...hat.com>,
David Ahern <dsahern@...nel.org>
Cc: netdev@...r.kernel.org
Subject: Re: [RFC PATCH] net_tstamp: add SCM_TS_OPT_ID to provide OPT_ID in
control message
On 29/08/2024 14:31, Willem de Bruijn wrote:
> Vadim Fedorenko wrote:
>> SOF_TIMESTAMPING_OPT_ID socket option flag gives a way to correlate TX
>> timestamps
>
> +1 on the feature. Few minor points only.
>
> Not a hard requirement, but would be nice if there was a test,
> e.g., as a tools/testing/../txtimestamp.c extension.
Sure, I'll add some tests in the next version.
>> and packets sent via socket. Unfortunately, there is no way
>> to reliably predict socket timestamp ID value in case of error returned
>> by sendmsg [1].
>
> Might be good to copy more context from the discussion to explain why
> reliable OPT_ID is infeasible. For UDP, it is as simple as lockless
> transmit. For RAW, things like MSG_MORE come into play.
Ok, I'll add it, thanks!
>> 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.
>> Also, there is no easy way to use 0 as provided ID, so this is value
>> treated as invalid.
>
> This is because the code branches on non-zero value in the cookie,
> else uses ts_key. Please make this explicit. Or perhaps better, add a
> bit in the cookie so that the full 32-bit space can be used.
Adding a bit in the cookie is not enough, I have to add another flag to
inet_cork. And we are running out of space for tx flags,
inet_cork::tx_flags is u8 and we have only 1 bit left for SKBTX* enum.
Do you think it's OK to use this last bit for OPT_ID feature?
>> [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 | 1 +
>> include/net/sock.h | 1 +
>> include/uapi/asm-generic/socket.h | 2 ++
>> net/core/sock.c | 14 ++++++++++++++
>> net/ipv4/ip_output.c | 11 +++++++++--
>> net/ipv6/ip6_output.c | 11 +++++++++--
>> 6 files changed, 36 insertions(+), 4 deletions(-)
>>
>> diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
>> index 394c3b66065e..7e8545311557 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;
>> };
>
> Ah there's a hole here. Nice!
>
>> 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/net/core/sock.c b/net/core/sock.c
>> index 468b1239606c..918cb6a0dcba 100644
>> --- a/net/core/sock.c
>> +++ b/net/core/sock.c
>> @@ -2859,6 +2859,20 @@ 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 = get_unaligned((u32 *)CMSG_DATA(cmsg));
>
> Is the get_unaligned here needed? I don't usually see that on
> CMSG_DATA accesses. Even though they are indeed likely to be
> unaligned.
Well, maybe you are right and we don't need get_unaligned for u32
here, at least SO_MARK uses direct access. I have no strong opinion.
>> + /* do not allow 0 as packet id for timestamp */
>> + if (!sockc->ts_opt_id)
>> + return -EINVAL;
>> + 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..f1e6695cafd2 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->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?
>> *
>> @@ -1324,6 +1330,7 @@ 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);
>>
>> diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
>> index f26841f1490f..602064250546 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.ts_opt_id = ipc6->sockc.ts_opt_id;
>> sock_tx_timestamp(sk, ipc6->sockc.tsflags, &cork->base.tx_flags);
>>
>> cork->base.length = 0;
>> @@ -1545,8 +1546,14 @@ 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->ts_opt_id) {
>> + hold_tskey = false;
>> + tskey = cork->ts_opt_id;
>> + } else {
>> + tskey = atomic_inc_return(&sk->sk_tskey) - 1;
>> + }
>> + }
>>
>> /*
>> * Let's try using as much space as possible.
>> --
>> 2.43.5
>>
>
>
Powered by blists - more mailing lists