All of lore.kernel.org
 help / color / mirror / Atom feed
From: Geliang Tang <geliangtang@gmail.com>
To: Paolo Abeni <pabeni@redhat.com>
Cc: mptcp@lists.linux.dev
Subject: Re: [PATCH mptcp-next 1/2] mptcp: optimize out option generation
Date: Mon, 26 Jul 2021 11:21:49 +0800	[thread overview]
Message-ID: <CA+WQbwsKBpXVVqDX32EDROX8kjo1efcgoPd10kDOt9hCHHNvdA@mail.gmail.com> (raw)
In-Reply-To: <b886e46981b5f02c726f92655fabd054f4dc9217.1627059686.git.pabeni@redhat.com>

Hi Paolo,

Thanks for this patchset, and I have some small comments.

Paolo Abeni <pabeni@redhat.com> 于2021年7月24日周六 上午1:06写道:
>
> Currently we have several protocol contraint on MPTCP option
> generation (e.g. MPC and MPJ subopt are mutually exclusive)
> and some additionall ones required by our implementation
> (e.g. almost all ADD_ADDR variant are mutually exclusive with
> everything else).
>
> We can leverage the above to optimize the out option generation:
> we check DSS/MPC/MPJ presencence in a mutually exclusive way,
> avoiding many unneeded conditionals in the common case.
>
> Additionally extend the existing constraint on ADD_ADDR opt on
> all subvariant, so that it become fully mutually exclusive with
> the above and we can skip another conditional statement the common
> case.
>
> This change is also need by the next patch.
>
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> --
> side node: we could probably optimize the conditionals in
> mptcp_established_options()
> ---
>  net/mptcp/options.c  | 225 ++++++++++++++++++++++---------------------
>  net/mptcp/pm.c       |   9 +-
>  net/mptcp/protocol.h |   1 +
>  3 files changed, 122 insertions(+), 113 deletions(-)
>
> diff --git a/net/mptcp/options.c b/net/mptcp/options.c
> index eafdb9408f3a..38f324667761 100644
> --- a/net/mptcp/options.c
> +++ b/net/mptcp/options.c
> @@ -592,6 +592,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
>                 dss_size = map_size;
>                 if (skb && snd_data_fin_enable)
>                         mptcp_write_data_fin(subflow, skb, &opts->ext_copy);
> +               opts->suboptions = OPTION_MPTCP_DSS;
>                 ret = true;
>         }
>
> @@ -615,6 +616,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
>                 opts->ext_copy.ack64 = 0;
>         }
>         opts->ext_copy.use_ack = 1;
> +       opts->suboptions = OPTION_MPTCP_DSS;
>         WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk));
>
>         /* Add kind/length/subtype/flag overhead if mapping is not populated */
> @@ -663,9 +665,9 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *

I think no need to modify the code in mptcp_established_options_add_addr.

>         struct mptcp_sock *msk = mptcp_sk(subflow->conn);
>         bool drop_other_suboptions = false;
>         unsigned int opt_size = *size;
> +       unsigned int len;
>         bool echo;
>         bool port;
> -       int len;

I prefer to keep the type of len unchanged.

>
>         if (!mptcp_pm_should_add_signal(msk) ||
>             !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, opts,
> @@ -687,11 +689,12 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
>                 *size -= opt_size;
>         }
>         opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
> -       if (!echo) {
> +       if (!echo)
>                 opts->ahmac = add_addr_generate_hmac(msk->local_key,
>                                                      msk->remote_key,
>                                                      &opts->addr);
> -       }
> +       else
> +               opts->ahmac = 0;

opts->ahmac had been set to zero in mptcp_get_options, no need to clear it
again.

>         pr_debug("addr_id=%d, addr_port=%d, ahmac=%llu, echo=%d",
>                  opts->addr.id, ntohs(opts->addr.port), opts->ahmac, echo);
>
> @@ -735,7 +738,12 @@ static bool mptcp_established_options_mp_prio(struct sock *sk,
>  {
>         struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
>
> -       if (!subflow->send_mp_prio)
> +       /* can't send MP_PRIO with MPC, as they share the same option space:
> +        * 'backup'. Also it makes no sense at all
> +        */
> +       if (!subflow->send_mp_prio ||
> +            ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK |
> +              OPTION_MPTCP_MPC_ACK) & opts->suboptions))
>                 return false;
>
>         /* account for the trailing 'nop' option */
> @@ -1198,7 +1206,73 @@ static u16 mptcp_make_csum(const struct mptcp_ext *mpext)
>  void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
>                          struct mptcp_out_options *opts)
>  {
> -       if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK |
> +       /* RST is mutually exclusive with everything else */
> +       if (unlikely(OPTION_MPTCP_RST & opts->suboptions)) {
> +               *ptr++ = mptcp_option(MPTCPOPT_RST,
> +                                     TCPOLEN_MPTCP_RST,
> +                                     opts->reset_transient,
> +                                     opts->reset_reason);
> +               return;
> +       }
> +
> +       /* DSS, MPC, MPJ and ADD_ADDR are mutually exclusive, see
> +        * mptcp_established_options*()
> +        */
> +       if (likely(OPTION_MPTCP_DSS & opts->suboptions)) {
> +               struct mptcp_ext *mpext = &opts->ext_copy;
> +               u8 len = TCPOLEN_MPTCP_DSS_BASE;
> +               u8 flags = 0;
> +
> +               if (mpext->use_ack) {
> +                       flags = MPTCP_DSS_HAS_ACK;
> +                       if (mpext->ack64) {
> +                               len += TCPOLEN_MPTCP_DSS_ACK64;
> +                               flags |= MPTCP_DSS_ACK64;
> +                       } else {
> +                               len += TCPOLEN_MPTCP_DSS_ACK32;
> +                       }
> +               }
> +
> +               if (mpext->use_map) {
> +                       len += TCPOLEN_MPTCP_DSS_MAP64;
> +
> +                       /* Use only 64-bit mapping flags for now, add
> +                        * support for optional 32-bit mappings later.
> +                        */
> +                       flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64;
> +                       if (mpext->data_fin)
> +                               flags |= MPTCP_DSS_DATA_FIN;
> +
> +                       if (opts->csum_reqd)
> +                               len += TCPOLEN_MPTCP_DSS_CHECKSUM;
> +               }
> +
> +               *ptr++ = mptcp_option(MPTCPOPT_DSS, len, 0, flags);
> +
> +               if (mpext->use_ack) {
> +                       if (mpext->ack64) {
> +                               put_unaligned_be64(mpext->data_ack, ptr);
> +                               ptr += 2;
> +                       } else {
> +                               put_unaligned_be32(mpext->data_ack32, ptr);
> +                               ptr += 1;
> +                       }
> +               }
> +
> +               if (mpext->use_map) {
> +                       put_unaligned_be64(mpext->data_seq, ptr);
> +                       ptr += 2;
> +                       put_unaligned_be32(mpext->subflow_seq, ptr);
> +                       ptr += 1;
> +                       if (opts->csum_reqd) {
> +                               put_unaligned_be32(mpext->data_len << 16 |
> +                                                  mptcp_make_csum(mpext), ptr);
> +                       } else {
> +                               put_unaligned_be32(mpext->data_len << 16 |
> +                                                  TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
> +                       }
> +               }
> +       } else if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK |
>              OPTION_MPTCP_MPC_ACK) & opts->suboptions) {
>                 u8 len, flag = MPTCP_CAP_HMAC_SHA256;
>
> @@ -1246,10 +1320,31 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
>                                            TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
>                 }
>                 ptr += 1;
> -       }
>
> -mp_capable_done:
> -       if (OPTION_MPTCP_ADD_ADDR & opts->suboptions) {
> +               /* MPC is additionally mutually exclusive with MP_PRIO */
> +               goto mp_capable_done;
> +       } else if (OPTION_MPTCP_MPJ_SYN & opts->suboptions) {
> +               *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
> +                                     TCPOLEN_MPTCP_MPJ_SYN,
> +                                     opts->backup, opts->join_id);
> +               put_unaligned_be32(opts->token, ptr);
> +               ptr += 1;
> +               put_unaligned_be32(opts->nonce, ptr);
> +               ptr += 1;
> +       } else if (OPTION_MPTCP_MPJ_SYNACK & opts->suboptions) {
> +               *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
> +                                     TCPOLEN_MPTCP_MPJ_SYNACK,
> +                                     opts->backup, opts->join_id);
> +               put_unaligned_be64(opts->thmac, ptr);
> +               ptr += 2;
> +               put_unaligned_be32(opts->nonce, ptr);
> +               ptr += 1;
> +       } else if (OPTION_MPTCP_MPJ_ACK & opts->suboptions) {
> +               *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
> +                                     TCPOLEN_MPTCP_MPJ_ACK, 0, 0);
> +               memcpy(ptr, opts->hmac, MPTCPOPT_HMAC_LEN);
> +               ptr += 5;
> +       } else if (OPTION_MPTCP_ADD_ADDR & opts->suboptions) {
>                 struct mptcp_addr_info *addr = &opts->addr;
>                 u8 len = TCPOLEN_MPTCP_ADD_ADDR_BASE;
>                 u8 echo = MPTCP_ADDR_ECHO;
> @@ -1308,6 +1403,19 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
>                 }
>         }
>
> +       if (OPTION_MPTCP_PRIO & opts->suboptions) {
> +               const struct sock *ssk = (const struct sock *)tp;
> +               struct mptcp_subflow_context *subflow;
> +
> +               subflow = mptcp_subflow_ctx(ssk);
> +               subflow->send_mp_prio = 0;
> +
> +               *ptr++ = mptcp_option(MPTCPOPT_MP_PRIO,
> +                                     TCPOLEN_MPTCP_PRIO,
> +                                     opts->backup, TCPOPT_NOP);
> +       }
> +
> +mp_capable_done:
>         if (OPTION_MPTCP_RM_ADDR & opts->suboptions) {
>                 u8 i = 1;
>
> @@ -1328,107 +1436,6 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
>                 }
>         }
>
> -       if (OPTION_MPTCP_PRIO & opts->suboptions) {
> -               const struct sock *ssk = (const struct sock *)tp;
> -               struct mptcp_subflow_context *subflow;
> -
> -               subflow = mptcp_subflow_ctx(ssk);
> -               subflow->send_mp_prio = 0;
> -
> -               *ptr++ = mptcp_option(MPTCPOPT_MP_PRIO,
> -                                     TCPOLEN_MPTCP_PRIO,
> -                                     opts->backup, TCPOPT_NOP);
> -       }
> -
> -       if (OPTION_MPTCP_MPJ_SYN & opts->suboptions) {
> -               *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
> -                                     TCPOLEN_MPTCP_MPJ_SYN,
> -                                     opts->backup, opts->join_id);
> -               put_unaligned_be32(opts->token, ptr);
> -               ptr += 1;
> -               put_unaligned_be32(opts->nonce, ptr);
> -               ptr += 1;
> -       }
> -
> -       if (OPTION_MPTCP_MPJ_SYNACK & opts->suboptions) {
> -               *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
> -                                     TCPOLEN_MPTCP_MPJ_SYNACK,
> -                                     opts->backup, opts->join_id);
> -               put_unaligned_be64(opts->thmac, ptr);
> -               ptr += 2;
> -               put_unaligned_be32(opts->nonce, ptr);
> -               ptr += 1;
> -       }
> -
> -       if (OPTION_MPTCP_MPJ_ACK & opts->suboptions) {
> -               *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
> -                                     TCPOLEN_MPTCP_MPJ_ACK, 0, 0);
> -               memcpy(ptr, opts->hmac, MPTCPOPT_HMAC_LEN);
> -               ptr += 5;
> -       }
> -
> -       if (OPTION_MPTCP_RST & opts->suboptions)
> -               *ptr++ = mptcp_option(MPTCPOPT_RST,
> -                                     TCPOLEN_MPTCP_RST,
> -                                     opts->reset_transient,
> -                                     opts->reset_reason);
> -
> -       if (opts->ext_copy.use_ack || opts->ext_copy.use_map) {
> -               struct mptcp_ext *mpext = &opts->ext_copy;
> -               u8 len = TCPOLEN_MPTCP_DSS_BASE;
> -               u8 flags = 0;
> -
> -               if (mpext->use_ack) {
> -                       flags = MPTCP_DSS_HAS_ACK;
> -                       if (mpext->ack64) {
> -                               len += TCPOLEN_MPTCP_DSS_ACK64;
> -                               flags |= MPTCP_DSS_ACK64;
> -                       } else {
> -                               len += TCPOLEN_MPTCP_DSS_ACK32;
> -                       }
> -               }
> -
> -               if (mpext->use_map) {
> -                       len += TCPOLEN_MPTCP_DSS_MAP64;
> -
> -                       /* Use only 64-bit mapping flags for now, add
> -                        * support for optional 32-bit mappings later.
> -                        */
> -                       flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64;
> -                       if (mpext->data_fin)
> -                               flags |= MPTCP_DSS_DATA_FIN;
> -
> -                       if (opts->csum_reqd)
> -                               len += TCPOLEN_MPTCP_DSS_CHECKSUM;
> -               }
> -
> -               *ptr++ = mptcp_option(MPTCPOPT_DSS, len, 0, flags);
> -
> -               if (mpext->use_ack) {
> -                       if (mpext->ack64) {
> -                               put_unaligned_be64(mpext->data_ack, ptr);
> -                               ptr += 2;
> -                       } else {
> -                               put_unaligned_be32(mpext->data_ack32, ptr);
> -                               ptr += 1;
> -                       }
> -               }
> -
> -               if (mpext->use_map) {
> -                       put_unaligned_be64(mpext->data_seq, ptr);
> -                       ptr += 2;
> -                       put_unaligned_be32(mpext->subflow_seq, ptr);
> -                       ptr += 1;
> -                       if (opts->csum_reqd) {
> -                               put_unaligned_be32(mpext->data_len << 16 |
> -                                                  mptcp_make_csum(mpext), ptr);
> -                       } else {
> -                               put_unaligned_be32(mpext->data_len << 16 |
> -                                                  TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
> -                       }
> -               }
> -       }
> -
>         if (tp)
>                 mptcp_set_rwin(tp);
>  }
> diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
> index 4d1828fd2482..baf2d6e524bd 100644
> --- a/net/mptcp/pm.c
> +++ b/net/mptcp/pm.c
> @@ -266,10 +266,11 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, struct sk_buff *skb,
>         if (!mptcp_pm_should_add_signal(msk))
>                 goto out_unlock;
>
> -       if (((msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_ECHO)) ||
> -            ((msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL)) &&
> -             (msk->pm.local.family == AF_INET6 || msk->pm.local.port))) &&
> -           skb && skb_is_tcp_pure_ack(skb)) {
> +       /* always drop every other options for pure ack ADD_ADDR; this is
> +        * plain dup-ack from TCP perspective. The other MPTCP-relevant info,
> +        * if any, will be carried by the other pure ack
> +        */
> +       if (skb && skb_is_tcp_pure_ack(skb)) {
>                 remaining += opt_size;
>                 *drop_other_suboptions = true;
>         }

This part in pm.c should be squashed to the patch "mptcp: move
drop_other_suboptions check under pm lock".

WDYT?

Thanks,
-Geliang

> diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
> index 34ad1c4bc29f..d960d8b8a8ce 100644
> --- a/net/mptcp/protocol.h
> +++ b/net/mptcp/protocol.h
> @@ -26,6 +26,7 @@
>  #define OPTION_MPTCP_FASTCLOSE BIT(8)
>  #define OPTION_MPTCP_PRIO      BIT(9)
>  #define OPTION_MPTCP_RST       BIT(10)
> +#define OPTION_MPTCP_DSS       BIT(11)
>
>  /* MPTCP option subtypes */
>  #define MPTCPOPT_MP_CAPABLE    0
> --
> 2.26.3
>
>

  reply	other threads:[~2021-07-26  3:22 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-23 17:06 [PATCH mptcp-next 0/2] mptcp: minor out optimization Paolo Abeni
2021-07-23 17:06 ` [PATCH mptcp-next 1/2] mptcp: optimize out option generation Paolo Abeni
2021-07-26  3:21   ` Geliang Tang [this message]
2021-07-26  9:44     ` Paolo Abeni
2021-07-26 10:02       ` Geliang Tang
2021-07-26 10:06     ` Paolo Abeni
2021-07-23 17:06 ` [PATCH mptcp-next 2/2] mptcp: shrink mptcp_out_options struct Paolo Abeni

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CA+WQbwsKBpXVVqDX32EDROX8kjo1efcgoPd10kDOt9hCHHNvdA@mail.gmail.com \
    --to=geliangtang@gmail.com \
    --cc=mptcp@lists.linux.dev \
    --cc=pabeni@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.