[RFC PATCH 0/3] mptcp: fix MP_JOIN failure handling

[RFC PATCH 0/3] mptcp: fix MP_JOIN failure handling

[Paolo Abeni]

Currently if we hit an MP_JOIN failure on the third ack, the child socket is
closed with reset, but the request socket is not deleted, causing weird
behaviors.

The main problem is that MPTCP's MP_JOIN code needs to plug it's own
'valid 3rd ack' checks and the current TCP callbacks do not allow that.

This series tries to address the above shortcoming introducing a new MPTCP
specific bit in a 'struct sock' hole, and leveraging that to allow
tcp_check_req releasing the request socket when needed.

The above allows cleaning-up a bit current MPTCP hooking in tcp_check_req().

An alternative solution, possibly cleaner but more invasive, would be
changing the 'bool *own_req' syn_recv_sock() argument into 'int *req_status'
and let MPTCP set it to 'REQ_DROP'.

Paolo Abeni (3):
  mptcp: add new sock flag to deal with join subflows
  inet_connection_sock: factor out destroy helper.
  mptcp: cope better with MP_JOIN failure

 include/linux/tcp.h                |  1 +
 include/net/inet_connection_sock.h |  8 ++++++++
 include/net/mptcp.h                | 17 ++++++++++-------
 net/ipv4/inet_connection_sock.c    |  6 +-----
 net/ipv4/tcp_minisocks.c           |  2 +-
 net/mptcp/protocol.c               |  7 -------
 net/mptcp/subflow.c                | 17 +++++++++++------
 7 files changed, 32 insertions(+), 26 deletions(-)

-- 
2.21.3

[RFC PATCH 1/3] mptcp: add new sock flag to deal with join subflows

[Paolo Abeni]

MP_JOIN subflows must not land into the accept queue.
Currently tcp_check_req() calls an mptcp specific helper
to detect such scenario.

Such helper leverages the subflow context to check for
MP_JOIN subflows. We need to deal also with MP JOIN
failures, even when the subflow context is not available
due to allocation failure.

A possible solution would be changing the syn_recv_sock()
signature to allow returning a more descriptive action/
error code and deal with that in tcp_check_req().

Since the above need is MPTCP specific, this patch instead
uses a TCP socket hole to add an MPTCP specific flag.
Such flag is used by the MPTCP syn_recv_sock() to tell
tcp_check_req() how to deal with the request socket.

This change is a no-op for !MPTCP build, and makes the
MPTCP code simpler. It allows also the next patch to deal
correctly with MP JOIN failure.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/tcp.h      |  1 +
 include/net/mptcp.h      | 17 ++++++++++-------
 net/ipv4/tcp_minisocks.c |  2 +-
 net/mptcp/protocol.c     |  7 -------
 net/mptcp/subflow.c      |  2 ++
 5 files changed, 14 insertions(+), 15 deletions(-)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index e60db06ec28d..dc12c59db41e 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -385,6 +385,7 @@ struct tcp_sock {
 			   */
 #if IS_ENABLED(CONFIG_MPTCP)
 	bool	is_mptcp;
+	bool	drop_req;
 #endif
 
 #ifdef CONFIG_TCP_MD5SIG
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index e60275659de6..c4809c24a185 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -68,6 +68,11 @@ static inline bool rsk_is_mptcp(const struct request_sock *req)
 	return tcp_rsk(req)->is_mptcp;
 }
 
+static inline bool sk_drop_req(const struct sock *sk)
+{
+	return tcp_sk(sk)->is_mptcp && tcp_sk(sk)->drop_req;
+}
+
 void mptcp_space(const struct sock *ssk, int *space, int *full_space);
 bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
 		       unsigned int *size, struct mptcp_out_options *opts);
@@ -121,8 +126,6 @@ static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
 				 skb_ext_find(from, SKB_EXT_MPTCP));
 }
 
-bool mptcp_sk_is_subflow(const struct sock *sk);
-
 void mptcp_seq_show(struct seq_file *seq);
 #else
 
@@ -140,6 +143,11 @@ static inline bool rsk_is_mptcp(const struct request_sock *req)
 	return false;
 }
 
+static inline bool sk_drop_req(const struct sock *sk)
+{
+	return false;
+}
+
 static inline void mptcp_parse_option(const struct sk_buff *skb,
 				      const unsigned char *ptr, int opsize,
 				      struct tcp_options_received *opt_rx)
@@ -190,11 +198,6 @@ static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
 	return true;
 }
 
-static inline bool mptcp_sk_is_subflow(const struct sock *sk)
-{
-	return false;
-}
-
 static inline void mptcp_space(const struct sock *ssk, int *s, int *fs) { }
 static inline void mptcp_seq_show(struct seq_file *seq) { }
 #endif /* CONFIG_MPTCP */
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 7e40322cc5ec..ba7cfb22dc79 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -774,7 +774,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	if (!child)
 		goto listen_overflow;
 
-	if (own_req && sk_is_mptcp(child) && mptcp_sk_is_subflow(child)) {
+	if (own_req && sk_drop_req(child)) {
 		reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
 		inet_csk_reqsk_queue_drop_and_put(sk, req);
 		return child;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index e1f23016ed3f..a61e60e94137 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1638,13 +1638,6 @@ bool mptcp_finish_join(struct sock *sk)
 	return ret;
 }
 
-bool mptcp_sk_is_subflow(const struct sock *sk)
-{
-	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
-
-	return subflow->mp_join == 1;
-}
-
 static bool mptcp_memory_free(const struct sock *sk, int wake)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 009d5c478062..b39a66ffac7a 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -500,6 +500,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 			ctx->remote_key = mp_opt.sndr_key;
 			ctx->fully_established = mp_opt.mp_capable;
 			ctx->can_ack = mp_opt.mp_capable;
+			tcp_sk(child)->drop_req = false;
 		} else if (ctx->mp_join) {
 			struct mptcp_sock *owner;
 
@@ -512,6 +513,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 				goto close_child;
 
 			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
+			tcp_sk(child)->drop_req = true;
 		}
 	}
 
-- 
2.21.3

[RFC PATCH 2/3] inet_connection_sock: factor out destroy helper.

[Paolo Abeni]

Move the steps to prepare an inet_connection_sock for
forced disposal inside a separate helper. No functional
changes inteded, this will just simplify the next patch.

Suggested-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/inet_connection_sock.h | 8 ++++++++
 net/ipv4/inet_connection_sock.c    | 6 +-----
 2 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index a3f076befa4f..2f1f8c3efb26 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -287,6 +287,14 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
 void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req);
 void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req);
 
+static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk)
+{
+	/* The below has to be done to allow calling inet_csk_destroy_sock */
+	sock_set_flag(sk, SOCK_DEAD);
+	percpu_counter_inc(sk->sk_prot->orphan_count);
+	inet_sk(sk)->inet_num = 0;
+}
+
 void inet_csk_destroy_sock(struct sock *sk);
 void inet_csk_prepare_forced_close(struct sock *sk);
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 5f34eb951627..d6faf3702824 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -896,11 +896,7 @@ void inet_csk_prepare_forced_close(struct sock *sk)
 	/* sk_clone_lock locked the socket and set refcnt to 2 */
 	bh_unlock_sock(sk);
 	sock_put(sk);
-
-	/* The below has to be done to allow calling inet_csk_destroy_sock */
-	sock_set_flag(sk, SOCK_DEAD);
-	percpu_counter_inc(sk->sk_prot->orphan_count);
-	inet_sk(sk)->inet_num = 0;
+	inet_csk_prepare_for_destroy_sock(sk);
 }
 EXPORT_SYMBOL(inet_csk_prepare_forced_close);
 
-- 
2.21.3

[RFC PATCH 3/3] mptcp: cope better with MP_JOIN failure

[Paolo Abeni]

Currently, on MP_JOIN failure we reset the child
socket, but leave the request socket untouched.

tcp_check_req will deal with it according to the
'tcp_abort_on_overflow' sysctl value - by default the
req socket will stay alive.

The above leads to inconsistent behavior on MP JOIN
failure, and bad listener overflow accounting.

This patch addresses the issue leveraging the infrastructure
just introduced to ask the TCP stack to drop the req on
failure.

The child socket is not freed anymore by subflow_syn_recv_sock(),
instead it's moved to a dead state and will be disposed by the
next sock_put done by the TCP stack, so that listener overflow
accounting is not affected by MP JOIN failure.

Reported-by: Christoph Paasch <cpaasch@apple.com>
Fixes: f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/subflow.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index b39a66ffac7a..755cd9712216 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -476,7 +476,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 		 */
 		if (!ctx || fallback) {
 			if (fallback_is_fatal)
-				goto close_child;
+				goto dispose_child;
 
 			if (ctx) {
 				subflow_ulp_fallback(child, ctx);
@@ -506,11 +506,11 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 
 			owner = mptcp_token_get_sock(ctx->token);
 			if (!owner)
-				goto close_child;
+				goto dispose_child;
 
 			ctx->conn = (struct sock *)owner;
 			if (!mptcp_finish_join(child))
-				goto close_child;
+				goto dispose_child;
 
 			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
 			tcp_sk(child)->drop_req = true;
@@ -530,11 +530,14 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 		      !mptcp_subflow_ctx(child)->conn));
 	return child;
 
-close_child:
+dispose_child:
+	tcp_sk(child)->drop_req = true;
 	tcp_send_active_reset(child, GFP_ATOMIC);
-	inet_csk_prepare_forced_close(child);
+	inet_csk_prepare_for_destroy_sock(child);
 	tcp_done(child);
-	return NULL;
+
+	/* The last child reference will be released by the caller */
+	return child;
 }
 
 static struct inet_connection_sock_af_ops subflow_specific;
-- 
2.21.3

Re: [RFC PATCH 1/3] mptcp: add new sock flag to deal with join subflows

[Eric Dumazet]

On Tue, May 12, 2020 at 7:11 AM Paolo Abeni <pabeni@redhat.com> wrote:
>
> MP_JOIN subflows must not land into the accept queue.
> Currently tcp_check_req() calls an mptcp specific helper
> to detect such scenario.
>
> Such helper leverages the subflow context to check for
> MP_JOIN subflows. We need to deal also with MP JOIN
> failures, even when the subflow context is not available
> due to allocation failure.
>
> A possible solution would be changing the syn_recv_sock()
> signature to allow returning a more descriptive action/
> error code and deal with that in tcp_check_req().
>
> Since the above need is MPTCP specific, this patch instead
> uses a TCP socket hole to add an MPTCP specific flag.
> Such flag is used by the MPTCP syn_recv_sock() to tell
> tcp_check_req() how to deal with the request socket.
>
> This change is a no-op for !MPTCP build, and makes the
> MPTCP code simpler. It allows also the next patch to deal
> correctly with MP JOIN failure.
>
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> ---
>  include/linux/tcp.h      |  1 +
>  include/net/mptcp.h      | 17 ++++++++++-------
>  net/ipv4/tcp_minisocks.c |  2 +-
>  net/mptcp/protocol.c     |  7 -------
>  net/mptcp/subflow.c      |  2 ++
>  5 files changed, 14 insertions(+), 15 deletions(-)
>
> diff --git a/include/linux/tcp.h b/include/linux/tcp.h
> index e60db06ec28d..dc12c59db41e 100644
> --- a/include/linux/tcp.h
> +++ b/include/linux/tcp.h
> @@ -385,6 +385,7 @@ struct tcp_sock {
>                            */
>  #if IS_ENABLED(CONFIG_MPTCP)
>         bool    is_mptcp;
> +       bool    drop_req;
>  #endif

This looks like this should only be needed in struct tcp_request_sock ?

Does this information need to be kept in the TCP socket after accept() ?

>
>  #ifdef CONFIG_TCP_MD5SIG
> diff --git a/include/net/mptcp.h b/include/net/mptcp.h
> index e60275659de6..c4809c24a185 100644
> --- a/include/net/mptcp.h
> +++ b/include/net/mptcp.h
> @@ -68,6 +68,11 @@ static inline bool rsk_is_mptcp(const struct request_sock *req)
>         return tcp_rsk(req)->is_mptcp;
>  }
>
> +static inline bool sk_drop_req(const struct sock *sk)
> +{
> +       return tcp_sk(sk)->is_mptcp && tcp_sk(sk)->drop_req;
> +}
> +
>  void mptcp_space(const struct sock *ssk, int *space, int *full_space);
>  bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
>                        unsigned int *size, struct mptcp_out_options *opts);
> @@ -121,8 +126,6 @@ static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
>                                  skb_ext_find(from, SKB_EXT_MPTCP));
>  }
>
> -bool mptcp_sk_is_subflow(const struct sock *sk);
> -
>  void mptcp_seq_show(struct seq_file *seq);
>  #else
>
> @@ -140,6 +143,11 @@ static inline bool rsk_is_mptcp(const struct request_sock *req)
>         return false;
>  }
>
> +static inline bool sk_drop_req(const struct sock *sk)
> +{
> +       return false;
> +}
> +
>  static inline void mptcp_parse_option(const struct sk_buff *skb,
>                                       const unsigned char *ptr, int opsize,
>                                       struct tcp_options_received *opt_rx)
> @@ -190,11 +198,6 @@ static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
>         return true;
>  }
>
> -static inline bool mptcp_sk_is_subflow(const struct sock *sk)
> -{
> -       return false;
> -}
> -
>  static inline void mptcp_space(const struct sock *ssk, int *s, int *fs) { }
>  static inline void mptcp_seq_show(struct seq_file *seq) { }
>  #endif /* CONFIG_MPTCP */
> diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
> index 7e40322cc5ec..ba7cfb22dc79 100644
> --- a/net/ipv4/tcp_minisocks.c
> +++ b/net/ipv4/tcp_minisocks.c
> @@ -774,7 +774,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
>         if (!child)
>                 goto listen_overflow;
>
> -       if (own_req && sk_is_mptcp(child) && mptcp_sk_is_subflow(child)) {
> +       if (own_req && sk_drop_req(child)) {
>                 reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
>                 inet_csk_reqsk_queue_drop_and_put(sk, req);
>                 return child;
> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
> index e1f23016ed3f..a61e60e94137 100644
> --- a/net/mptcp/protocol.c
> +++ b/net/mptcp/protocol.c
> @@ -1638,13 +1638,6 @@ bool mptcp_finish_join(struct sock *sk)
>         return ret;
>  }
>
> -bool mptcp_sk_is_subflow(const struct sock *sk)
> -{
> -       struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
> -
> -       return subflow->mp_join == 1;
> -}
> -
>  static bool mptcp_memory_free(const struct sock *sk, int wake)
>  {
>         struct mptcp_sock *msk = mptcp_sk(sk);
> diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
> index 009d5c478062..b39a66ffac7a 100644
> --- a/net/mptcp/subflow.c
> +++ b/net/mptcp/subflow.c
> @@ -500,6 +500,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
>                         ctx->remote_key = mp_opt.sndr_key;
>                         ctx->fully_established = mp_opt.mp_capable;
>                         ctx->can_ack = mp_opt.mp_capable;
> +                       tcp_sk(child)->drop_req = false;
>                 } else if (ctx->mp_join) {
>                         struct mptcp_sock *owner;
>
> @@ -512,6 +513,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
>                                 goto close_child;
>
>                         SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
> +                       tcp_sk(child)->drop_req = true;
>                 }
>         }
>
> --
> 2.21.3
>

Re: [RFC PATCH 1/3] mptcp: add new sock flag to deal with join subflows

[Paolo Abeni]

Hi,

On Tue, 2020-05-12 at 07:46 -0700, Eric Dumazet wrote:
> On Tue, May 12, 2020 at 7:11 AM Paolo Abeni <pabeni@redhat.com> wrote:
> > MP_JOIN subflows must not land into the accept queue.
> > Currently tcp_check_req() calls an mptcp specific helper
> > to detect such scenario.
> > 
> > Such helper leverages the subflow context to check for
> > MP_JOIN subflows. We need to deal also with MP JOIN
> > failures, even when the subflow context is not available
> > due to allocation failure.
> > 
> > A possible solution would be changing the syn_recv_sock()
> > signature to allow returning a more descriptive action/
> > error code and deal with that in tcp_check_req().
> > 
> > Since the above need is MPTCP specific, this patch instead
> > uses a TCP socket hole to add an MPTCP specific flag.
> > Such flag is used by the MPTCP syn_recv_sock() to tell
> > tcp_check_req() how to deal with the request socket.
> > 
> > This change is a no-op for !MPTCP build, and makes the
> > MPTCP code simpler. It allows also the next patch to deal
> > correctly with MP JOIN failure.
> > 
> > Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> > ---
> >  include/linux/tcp.h      |  1 +
> >  include/net/mptcp.h      | 17 ++++++++++-------
> >  net/ipv4/tcp_minisocks.c |  2 +-
> >  net/mptcp/protocol.c     |  7 -------
> >  net/mptcp/subflow.c      |  2 ++
> >  5 files changed, 14 insertions(+), 15 deletions(-)
> > 
> > diff --git a/include/linux/tcp.h b/include/linux/tcp.h
> > index e60db06ec28d..dc12c59db41e 100644
> > --- a/include/linux/tcp.h
> > +++ b/include/linux/tcp.h
> > @@ -385,6 +385,7 @@ struct tcp_sock {
> >                            */
> >  #if IS_ENABLED(CONFIG_MPTCP)
> >         bool    is_mptcp;
> > +       bool    drop_req;
> >  #endif
> 
> This looks like this should only be needed in struct tcp_request_sock ?
> 
> Does this information need to be kept in the TCP socket after accept() ?

Thank you for the feedback, indeed you are right! this should be moved
inside tcp_request_sock. We still have 2 bytes hole there. I will keep
the flag under a CONFIG_MPTCP conditional.

Would you be ok with such approach, or do you think we should look for
some other schema (like the alternative mentioned in the cover letter)?

Cheers,

Paolo