diff mbox series

[v5,mptcp-next,1/5] mptcp: MP_FAIL suboption sending

Message ID fce3d982e418e791fc38dd2e9f116de84e429d21.1627281326.git.geliangtang@xiaomi.com (mailing list archive)
State Superseded, archived
Delegated to: Mat Martineau
Headers show
Series MP_FAIL support | expand

Commit Message

Geliang Tang July 26, 2021, 6:45 a.m. UTC
From: Geliang Tang <geliangtang@xiaomi.com>

This patch added the MP_FAIL suboption sending support.

Add a new flag named send_mp_fail in struct mptcp_subflow_context. If
this flag is set, send out MP_FAIL suboption.

Add a new member fail_seq in struct mptcp_out_options to save the data
sequence number to put into the MP_FAIL suboption.

An MP_FAIL option could be included in a RST or on the subflow-level
ACK.

Signed-off-by: Geliang Tang <geliangtang@xiaomi.com>
---
 include/net/mptcp.h  |  5 +++-
 net/mptcp/options.c  | 61 +++++++++++++++++++++++++++++++++++++++++---
 net/mptcp/protocol.h |  3 +++
 3 files changed, 64 insertions(+), 5 deletions(-)

Comments

Paolo Abeni July 26, 2021, 11:10 a.m. UTC | #1
On Mon, 2021-07-26 at 14:45 +0800, Geliang Tang wrote:
> From: Geliang Tang <geliangtang@xiaomi.com>
> 
> This patch added the MP_FAIL suboption sending support.
> 
> Add a new flag named send_mp_fail in struct mptcp_subflow_context. If
> this flag is set, send out MP_FAIL suboption.
> 
> Add a new member fail_seq in struct mptcp_out_options to save the data
> sequence number to put into the MP_FAIL suboption.
> 
> An MP_FAIL option could be included in a RST or on the subflow-level
> ACK.
> 
> Signed-off-by: Geliang Tang <geliangtang@xiaomi.com>
> ---
>  include/net/mptcp.h  |  5 +++-
>  net/mptcp/options.c  | 61 +++++++++++++++++++++++++++++++++++++++++---
>  net/mptcp/protocol.h |  3 +++
>  3 files changed, 64 insertions(+), 5 deletions(-)
> 
> diff --git a/include/net/mptcp.h b/include/net/mptcp.h
> index d0b9e4a7121f..6c8c8592153d 100644
> --- a/include/net/mptcp.h
> +++ b/include/net/mptcp.h
> @@ -60,7 +60,10 @@ struct mptcp_out_options {
>  	u16 suboptions;
>  	u64 sndr_key;
>  	u64 rcvr_key;
> -	u64 ahmac;
> +	union {
> +		u64 ahmac;
> +		u64 fail_seq;
> +	};
>  	struct mptcp_addr_info local;
>  	struct mptcp_addr_info remote;
>  	struct mptcp_rm_list rm_list;

This will conflict with: "mptcp: shrink mptcp_out_options struct". If
this series is merged before the "mptcp: shrink mptcp_out_options
struct" series, I think we can just add the new field here without any
union and do the aliasing the the shirnk' patch.

Otherwise ("mptcp: shrink mptcp_out_options struct" merged first), I
think:

		struct mptcp_ext ext_copy;

should be replace with:
		struct {
			struct mptcp_ext ext_copy;
			u64 ahmac;
		};

mptcp_out_options should not change size that way.

Cheers

Paolo
Geliang Tang July 28, 2021, 2:43 a.m. UTC | #2
Hi Paolo,

Paolo Abeni <pabeni@redhat.com> 于2021年7月26日周一 下午7:10写道:
>
> On Mon, 2021-07-26 at 14:45 +0800, Geliang Tang wrote:
> > From: Geliang Tang <geliangtang@xiaomi.com>
> >
> > This patch added the MP_FAIL suboption sending support.
> >
> > Add a new flag named send_mp_fail in struct mptcp_subflow_context. If
> > this flag is set, send out MP_FAIL suboption.
> >
> > Add a new member fail_seq in struct mptcp_out_options to save the data
> > sequence number to put into the MP_FAIL suboption.
> >
> > An MP_FAIL option could be included in a RST or on the subflow-level
> > ACK.
> >
> > Signed-off-by: Geliang Tang <geliangtang@xiaomi.com>
> > ---
> >  include/net/mptcp.h  |  5 +++-
> >  net/mptcp/options.c  | 61 +++++++++++++++++++++++++++++++++++++++++---
> >  net/mptcp/protocol.h |  3 +++
> >  3 files changed, 64 insertions(+), 5 deletions(-)
> >
> > diff --git a/include/net/mptcp.h b/include/net/mptcp.h
> > index d0b9e4a7121f..6c8c8592153d 100644
> > --- a/include/net/mptcp.h
> > +++ b/include/net/mptcp.h
> > @@ -60,7 +60,10 @@ struct mptcp_out_options {
> >       u16 suboptions;
> >       u64 sndr_key;
> >       u64 rcvr_key;
> > -     u64 ahmac;
> > +     union {
> > +             u64 ahmac;
> > +             u64 fail_seq;
> > +     };
> >       struct mptcp_addr_info local;
> >       struct mptcp_addr_info remote;
> >       struct mptcp_rm_list rm_list;
>
> This will conflict with: "mptcp: shrink mptcp_out_options struct". If
> this series is merged before the "mptcp: shrink mptcp_out_options
> struct" series, I think we can just add the new field here without any
> union and do the aliasing the the shirnk' patch.
>
> Otherwise ("mptcp: shrink mptcp_out_options struct" merged first), I
> think:
>
>                 struct mptcp_ext ext_copy;
>
> should be replace with:
>                 struct {
>                         struct mptcp_ext ext_copy;
>                         u64 ahmac;
>                 };

Do you mean that:

                struct mptcp_ext ext_copy;
should be replaced with:
                 struct {
                         struct mptcp_ext ext_copy;
                         u64 fail_seq;
                 };
?

Then the whole union is like this:

       union {
               struct {
                       u64 sndr_key;
                       u64 rcvr_key;
               };
               struct {
                       struct mptcp_addr_info addr;
                       u64 ahmac;
               };
               struct {
                       struct mptcp_ext ext_copy;
                       u64 fail_seq;
               };
               struct {
                       u32 nonce;
                       u32 token;
                       u64 thmac;
                       u8 hmac[20];
               };
       };

Do I understand correctly?

Thanks,
-Geliang






>
> mptcp_out_options should not change size that way.
>
> Cheers
>
> Paolo
>
diff mbox series

Patch

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index d0b9e4a7121f..6c8c8592153d 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -60,7 +60,10 @@  struct mptcp_out_options {
 	u16 suboptions;
 	u64 sndr_key;
 	u64 rcvr_key;
-	u64 ahmac;
+	union {
+		u64 ahmac;
+		u64 fail_seq;
+	};
 	struct mptcp_addr_info local;
 	struct mptcp_addr_info remote;
 	struct mptcp_rm_list rm_list;
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 6803de5d4209..a7365379096d 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -754,7 +754,7 @@  static bool mptcp_established_options_mp_prio(struct sock *sk,
 	return true;
 }
 
-static noinline void mptcp_established_options_rst(struct sock *sk, struct sk_buff *skb,
+static noinline bool mptcp_established_options_rst(struct sock *sk, struct sk_buff *skb,
 						   unsigned int *size,
 						   unsigned int remaining,
 						   struct mptcp_out_options *opts)
@@ -762,12 +762,36 @@  static noinline void mptcp_established_options_rst(struct sock *sk, struct sk_bu
 	const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 
 	if (remaining < TCPOLEN_MPTCP_RST)
-		return;
+		return false;
 
 	*size = TCPOLEN_MPTCP_RST;
 	opts->suboptions |= OPTION_MPTCP_RST;
 	opts->reset_transient = subflow->reset_transient;
 	opts->reset_reason = subflow->reset_reason;
+
+	return true;
+}
+
+static bool mptcp_established_options_mp_fail(struct sock *sk,
+					      unsigned int *size,
+					      unsigned int remaining,
+					      struct mptcp_out_options *opts)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+
+	if (!subflow->send_mp_fail)
+		return false;
+
+	if (remaining < TCPOLEN_MPTCP_FAIL)
+		return false;
+
+	*size = TCPOLEN_MPTCP_FAIL;
+	opts->suboptions |= OPTION_MPTCP_FAIL;
+	opts->fail_seq = subflow->map_seq;
+
+	pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq);
+
+	return true;
 }
 
 bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
@@ -786,15 +810,30 @@  bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 		return false;
 
 	if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) {
-		mptcp_established_options_rst(sk, skb, size, remaining, opts);
+		if (mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) {
+			*size += opt_size;
+			remaining -= opt_size;
+		}
+		if (mptcp_established_options_rst(sk, skb, &opt_size, remaining, opts)) {
+			*size += opt_size;
+			remaining -= opt_size;
+		}
 		return true;
 	}
 
 	snd_data_fin = mptcp_data_fin_enabled(msk);
 	if (mptcp_established_options_mp(sk, skb, snd_data_fin, &opt_size, remaining, opts))
 		ret = true;
-	else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, remaining, opts))
+	else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, remaining, opts)) {
 		ret = true;
+		if (opts->ext_copy.use_ack) {
+			if (mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) {
+				*size += opt_size;
+				remaining -= opt_size;
+				return true;
+			}
+		}
+	}
 
 	/* we reserved enough space for the above options, and exceeding the
 	 * TCP option space would be fatal
@@ -1343,6 +1382,20 @@  void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 				      opts->backup, TCPOPT_NOP);
 	}
 
+	if (OPTION_MPTCP_FAIL & opts->suboptions) {
+		const struct sock *ssk = (const struct sock *)tp;
+		struct mptcp_subflow_context *subflow;
+
+		subflow = mptcp_subflow_ctx(ssk);
+		subflow->send_mp_fail = 0;
+
+		*ptr++ = mptcp_option(MPTCPOPT_MP_FAIL,
+				      TCPOLEN_MPTCP_FAIL,
+				      0, 0);
+		put_unaligned_be64(opts->fail_seq, ptr);
+		ptr += 2;
+	}
+
 	if (OPTION_MPTCP_MPJ_SYN & opts->suboptions) {
 		*ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
 				      TCPOLEN_MPTCP_MPJ_SYN,
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 34ad1c4bc29f..ea4ab9b9d6db 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_FAIL	BIT(11)
 
 /* MPTCP option subtypes */
 #define MPTCPOPT_MP_CAPABLE	0
@@ -67,6 +68,7 @@ 
 #define TCPOLEN_MPTCP_PRIO_ALIGN	4
 #define TCPOLEN_MPTCP_FASTCLOSE		12
 #define TCPOLEN_MPTCP_RST		4
+#define TCPOLEN_MPTCP_FAIL		12
 
 #define TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM	(TCPOLEN_MPTCP_DSS_CHECKSUM + TCPOLEN_MPTCP_MPC_ACK_DATA)
 
@@ -428,6 +430,7 @@  struct mptcp_subflow_context {
 		mpc_map : 1,
 		backup : 1,
 		send_mp_prio : 1,
+		send_mp_fail : 1,
 		rx_eof : 1,
 		can_ack : 1,        /* only after processing the remote a key */
 		disposable : 1,	    /* ctx can be free at ulp release time */