mptcp: infinite mapping sending

This patch adds the infinite mapping sending logic.

Add a new flag send_infinite_map in struct mptcp_subflow_context. Set
it true when a single contiguous subflow is in use and the
allow_infinite_fallback flag is true in mptcp_pm_mp_fail_received().

In mptcp_sendmsg_frag(), if this flag is true, call the new function
mptcp_update_infinite_map() to set the infinite mapping.

Add a new flag infinite_map in struct mptcp_ext, set it true in
mptcp_update_infinite_map(), and check this flag in a new helper
mptcp_check_infinite_map().

In mptcp_update_infinite_map(), set data_len to 0, and clear the
send_infinite_map flag, then do fallback.

In mptcp_established_options(), use the helper mptcp_check_infinite_map()
to let the infinite mapping DSS can be sent out in the fallback mode.

Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 0a3b0fb..8b1afd6 100644 (file)
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -35,7 +35,8 @@ struct mptcp_ext {
                        frozen:1,
                        reset_transient:1;
        u8              reset_reason:4,
-                       csum_reqd:1;
+                       csum_reqd:1,
+                       infinite_map:1;
 };
 
 #define MPTCP_RM_IDS_MAX       8

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 3253836..88f4ebb 100644 (file)
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -825,7 +825,7 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 
        opts->suboptions = 0;
 
-       if (unlikely(__mptcp_check_fallback(msk)))
+       if (unlikely(__mptcp_check_fallback(msk) && !mptcp_check_infinite_map(skb)))
                return false;
 
        if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) {
@@ -1340,8 +1340,12 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
                        put_unaligned_be32(mpext->subflow_seq, ptr);
                        ptr += 1;
                        if (opts->csum_reqd) {
+                               /* data_len == 0 is reserved for the infinite mapping,
+                                * the checksum will also be set to 0.
+                                */
                                put_unaligned_be32(mpext->data_len << 16 |
-                                                  mptcp_make_csum(mpext), ptr);
+                                                  (mpext->data_len ? mptcp_make_csum(mpext) : 0),
+                                                  ptr);
                        } else {
                                put_unaligned_be32(mpext->data_len << 16 |
                                                   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 8aa0cdb..5c36870 100644 (file)
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -285,7 +285,13 @@ void mptcp_pm_mp_prio_received(struct sock *ssk, u8 bkup)
 
 void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq)
 {
+       struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+       struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+
        pr_debug("fail_seq=%llu", fail_seq);
+
+       if (!mptcp_has_another_subflow(sk) && READ_ONCE(msk->allow_infinite_fallback))
+               subflow->send_infinite_map = 1;
 }
 
 /* path manager helpers */

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 6d65391..161c07f 100644 (file)
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1229,6 +1229,21 @@ static void mptcp_update_data_checksum(struct sk_buff *skb, int added)
        mpext->csum = csum_fold(csum_block_add(csum, skb_checksum(skb, offset, added, 0), offset));
 }
 
+static void mptcp_update_infinite_map(struct mptcp_sock *msk,
+                                     struct sock *ssk,
+                                     struct mptcp_ext *mpext)
+{
+       if (!mpext)
+               return;
+
+       mpext->infinite_map = 1;
+       mpext->data_len = 0;
+
+       mptcp_subflow_ctx(ssk)->send_infinite_map = 0;
+       pr_fallback(msk);
+       __mptcp_do_fallback(msk);
+}
+
 static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
                              struct mptcp_data_frag *dfrag,
                              struct mptcp_sendmsg_info *info)
@@ -1360,6 +1375,8 @@ alloc_skb:
 out:
        if (READ_ONCE(msk->csum_enabled))
                mptcp_update_data_checksum(skb, copy);
+       if (mptcp_subflow_ctx(ssk)->send_infinite_map)
+               mptcp_update_infinite_map(msk, ssk, mpext);
        trace_mptcp_sendmsg_frag(mpext);
        mptcp_subflow_ctx(ssk)->rel_write_seq += copy;
        return copy;

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 88d2923..61d6006 100644 (file)
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -441,6 +441,7 @@ struct mptcp_subflow_context {
                send_mp_prio : 1,
                send_mp_fail : 1,
                send_fastclose : 1,
+               send_infinite_map : 1,
                rx_eof : 1,
                can_ack : 1,        /* only after processing the remote a key */
                disposable : 1,     /* ctx can be free at ulp release time */
@@ -877,6 +878,17 @@ static inline void mptcp_do_fallback(struct sock *sk)
 
 #define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a)
 
+static inline bool mptcp_check_infinite_map(struct sk_buff *skb)
+{
+       struct mptcp_ext *mpext;
+
+       mpext = skb ? mptcp_get_ext(skb) : NULL;
+       if (mpext && mpext->infinite_map)
+               return true;
+
+       return false;
+}
+
 static inline bool subflow_simultaneous_connect(struct sock *sk)
 {
        struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);