mptcp: introduce support for real multipath xmit
Subsystems (5)
Paolo Abeni
maintainercover mptcp: introduce support for real multipath xmit
This series enable MPTCP socket to transmit data on multiple subflows concurrently in a load balancing scenario.
First the receive code path is refactored to better deal with out-of-order data (patches 1-7). An RB-tree is introduced to queue MPTCP-level out-of-order data, closely resembling the TCP level OoO handling.
When data is sent on multiple subflows, the peer can easily see OoO - "future" data at the MPTCP level, especially if speeds, delay, or jitter are not symmetric.
The other major change regards the netlink PM, which is extended to allow creating non backup subflows in patches 9-11.
There are a few smaller additions, like the introduction of OoO related mibs, send buffer autotuning and better ack handling.
Finally a bunch of new self-tests is introduced. The new feature is tested ensuring that the B/W used by an MPTCP socket using multiple subflows matches the link aggregated B/W - we use low B/W virtual links, to ensure the tests are not CPU bounded.
Paolo Abeni (13):
mptcp: rethink 'is writable' conditional
mptcp: set data_ready status bit in subflow_check_data_avail()
mptcp: trigger msk processing even for OoO data
mptcp: basic sndbuf autotuning
mptcp: introduce and use mptcp_try_coalesce()
mptcp: move ooo skbs into msk out of order queue.
mptcp: cleanup mptcp_subflow_discard_data()
mptcp: add OoO related mibs
mptcp: move address attribute into mptcp_addr_info
mptcp: allow creating non-backup subflows
mptcp: allow picking different xmit subflows
mptcp: call tcp_cleanup_rbuf on subflows
mptcp: simult flow self-tests
include/net/tcp.h | 2 + net/ipv4/tcp.c | 2 +- net/mptcp/mib.c | 5 + net/mptcp/mib.h | 5 + net/mptcp/pm_netlink.c | 39 +- net/mptcp/protocol.c | 509 ++++++++++++++---- net/mptcp/protocol.h | 21 +- net/mptcp/subflow.c | 99 ++-- tools/testing/selftests/net/mptcp/Makefile | 3 +- .../selftests/net/mptcp/simult_flows.sh | 293 ++++++++++ 10 files changed, 796 insertions(+), 182 deletions(-) create mode 100755 tools/testing/selftests/net/mptcp/simult_flows.sh
Signature · 1 line
2.26.2
Paolo Abeni
maintainerPATCH 1/13 mptcp: rethink 'is writable' conditional
Currently, when checking for the 'msk is writable' condition, we look at the individual subflows write space.
That works well while we send data via a single subflow, but will not as soon as we will enable concurrent xmit on multiple subflows.
With this change msk becomes writable when the following conditions hold:
- the socket has some free write space
- there is at least a subflow with write free space
Additionally we need to set the NOSPACE bit on all subflows before blocking.
--- net/mptcp/protocol.c | 71 ++++++++++++++++++++++++++++---------------- net/mptcp/subflow.c | 6 ++-- 2 files changed, 50 insertions(+), 27 deletions(-)
net/mptcp/protocol.c +46 -25
@@ -472,7 +472,7 @@ void mptcp_data_acked(struct sock *sk) {mptcp_reset_timer (sk); -if ((!sk_stream_is_writeable (sk) || +if ((!test_bit (MPTCP_SEND_SPACE , &mptcp_sk (sk)->flags) || (inet_sk_state_load (sk) !=TCP_ESTABLISHED )) &&schedule_work (&mptcp_sk (sk)->work))sock_hold (sk);
@@ -567,6 +567,20 @@ static void dfrag_clear(struct sock *sk, struct mptcp_data_frag *dfrag)put_page (dfrag->page); } +static bool mptcp_is_writeable (struct mptcp_sock *msk) +{ +struct mptcp_subflow_context *subflow; + +if (!sk_stream_is_writeable ((struct sock *)msk)) +return false; + +mptcp_for_each_subflow (msk, subflow) { +if (sk_stream_is_writeable (subflow->tcp_sock)) +return true; + } +return false; +} +static void mptcp_clean_una (struct sock *sk) {struct mptcp_sock *msk =mptcp_sk (sk);
@@ -609,8 +623,15 @@ static void mptcp_clean_una(struct sock *sk)sk_mem_reclaim_partial (sk);/* Only wake up writers if a subflow is ready */ -if (test_bit (MPTCP_SEND_SPACE , &msk->flags)) +if (mptcp_is_writeable (msk)) { +set_bit (MPTCP_SEND_SPACE , &mptcp_sk (sk)->flags); +smp_mb__after_atomic (); + +/* set SEND_SPACE before sk_stream_write_space clears +* NOSPACE +*/ sk_stream_write_space (sk); + } } }
@@ -801,21 +822,31 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,return ret; } -static void mptcp_nospace (struct mptcp_sock *msk,struct socket *sock) +static void mptcp_nospace (struct mptcp_sock *msk) { +struct mptcp_subflow_context *subflow; +clear_bit (MPTCP_SEND_SPACE , &msk->flags);smp_mb__after_atomic ();/* msk->flags is changed by write_space cb */ -/* enables sk->write_space() callbacks */ -set_bit (SOCK_NOSPACE , &sock->flags); +mptcp_for_each_subflow (msk, subflow) { +struct sock *ssk =mptcp_subflow_tcp_sock (subflow); +struct socket *sock =READ_ONCE (ssk->sk_socket); + +/* enables ssk->write_space() callbacks */ +if (sock) +set_bit (SOCK_NOSPACE , &sock->flags); + } }static struct sock *mptcp_subflow_get_send (struct mptcp_sock *msk) {struct mptcp_subflow_context *subflow; +struct sock *sk = (struct sock *)msk;struct sock *backup =NULL ; +bool free; -sock_owned_by_me ((const struct sock *)msk); +sock_owned_by_me (sk);if (!mptcp_ext_cache_refill (msk))return NULL ;
@@ -823,12 +854,9 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)mptcp_for_each_subflow (msk, subflow) {struct sock *ssk =mptcp_subflow_tcp_sock (subflow); -if (!sk_stream_memory_free (ssk)) { -struct socket *sock = ssk->sk_socket; - -if (sock) -mptcp_nospace (msk, sock); - + free =sk_stream_is_writeable (subflow->tcp_sock); +if (!free) { +mptcp_nospace (msk);return NULL ; }
@@ -845,16 +873,10 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)return backup; } -static void ssk_check_wmem (struct mptcp_sock *msk,struct sock *ssk) +static void ssk_check_wmem (struct mptcp_sock *msk) { -struct socket *sock; - -if (likely (sk_stream_is_writeable (ssk))) -return ; - - sock =READ_ONCE (ssk->sk_socket); -if (sock) -mptcp_nospace (msk, sock); +if (unlikely (!mptcp_is_writeable (msk))) +mptcp_nospace (msk); }static int mptcp_sendmsg (struct sock *sk,struct msghdr *msg,size_t len)
@@ -907,6 +929,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)mptcp_reset_timer (sk); } +mptcp_nospace (msk); ret =sk_stream_wait_memory (sk, &timeo);if (ret) goto out;
@@ -945,7 +968,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)if (!sk_stream_memory_free (ssk) || !mptcp_page_frag_refill (ssk, pfrag) || !mptcp_ext_cache_refill (msk)) { -set_bit (SOCK_NOSPACE , &sk->sk_socket->flags);tcp_push (ssk, msg->msg_flags, mss_now,tcp_sk (ssk)->nonagle, size_goal);mptcp_set_timeout (sk, ssk);
@@ -993,9 +1015,9 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)mptcp_reset_timer (sk); } -ssk_check_wmem (msk, ssk);release_sock (ssk); out: +ssk_check_wmem (msk);release_sock (sk);return copied ? : ret; }
@@ -2291,8 +2313,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,if (state !=TCP_SYN_SENT && state !=TCP_SYN_RECV ) { mask |=mptcp_check_readable (msk); -if (sk_stream_is_writeable (sk) && -test_bit (MPTCP_SEND_SPACE , &msk->flags)) +if (test_bit (MPTCP_SEND_SPACE , &msk->flags)) mask |=EPOLLOUT |EPOLLWRNORM ; }if (sk->sk_shutdown &RCV_SHUTDOWN )
net/mptcp/subflow.c +4 -2
@@ -996,8 +996,10 @@ static void subflow_write_space(struct sock *sk)struct mptcp_subflow_context *subflow =mptcp_subflow_ctx (sk);struct sock *parent = subflow->conn; -sk_stream_write_space (sk); -if (sk_stream_is_writeable (sk)) { +if (!sk_stream_is_writeable (sk)) +return ; + +if (sk_stream_is_writeable (parent)) {set_bit (MPTCP_SEND_SPACE , &mptcp_sk (parent)->flags);smp_mb__after_atomic ();/* set SEND_SPACE before sk_stream_write_space clears NOSPACE */
Signature · 1 line
2.26.2
Paolo Abeni
maintainerPATCH 2/13 mptcp: set data_ready status bit in subflow_check_data_avail()
In reply to Paolo AbeniThis simplify mptcp_subflow_data_available() and will made follow-up patches simpler.
Additionally remove the unneeded checks on subflow copied_seq:
we always whole skbs out of subflows.
--- net/mptcp/subflow.c | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-)
net/mptcp/subflow.c +8 -11
@@ -825,6 +825,8 @@ static bool subflow_check_data_avail(struct sock *ssk)pr_debug ("msk=%p ssk=%p data_avail=%d skb=%p" , subflow->conn, ssk, subflow->data_avail,skb_peek (&ssk->sk_receive_queue)); +if (!skb_peek (&ssk->sk_receive_queue)) + subflow->data_avail =0 ;if (subflow->data_avail)return true;
@@ -849,6 +851,7 @@ static bool subflow_check_data_avail(struct sock *ssk) subflow->map_data_len = skb->len; subflow->map_subflow_seq =tcp_sk (ssk)->copied_seq - subflow->ssn_offset; + subflow->data_avail =1 ;return true; }
@@ -876,8 +879,10 @@ static bool subflow_check_data_avail(struct sock *ssk) ack_seq =mptcp_subflow_get_mapped_dsn (subflow);pr_debug ("msk ack_seq=%llx subflow ack_seq=%llx" , old_ack, ack_seq); -if (ack_seq == old_ack) +if (ack_seq == old_ack) { + subflow->data_avail =1 ;break ; + }/* only accept in-sequence mapping. Old values are spurious * retransmission; we can hit "future" values on active backup
@@ -922,13 +927,13 @@ static bool subflow_check_data_avail(struct sock *ssk) ssk->sk_error_report (ssk);tcp_set_state (ssk,TCP_CLOSE );tcp_send_active_reset (ssk,GFP_ATOMIC ); + subflow->data_avail =0 ;return false; }bool mptcp_subflow_data_available (struct sock *sk) {struct mptcp_subflow_context *subflow =mptcp_subflow_ctx (sk); -struct sk_buff *skb;/* check if current mapping is still valid */ if (subflow->map_valid &&
@@ -941,15 +946,7 @@ bool mptcp_subflow_data_available(struct sock *sk) subflow->map_data_len); } -if (!subflow_check_data_avail (sk)) { - subflow->data_avail =0 ; -return false; - } - - skb =skb_peek (&sk->sk_receive_queue); - subflow->data_avail = skb && -before (tcp_sk (sk)->copied_seq,TCP_SKB_CB (skb)->end_seq); -return subflow->data_avail; +return subflow_check_data_avail (sk); }/* If ssk has an mptcp parent socket, use the mptcp rcvbuf occupancy,
Signature · 1 line
2.26.2
Paolo Abeni
maintainerPATCH 3/13 mptcp: trigger msk processing even for OoO data
In reply to Paolo AbeniThis is a prerequisite to allow receiving data from multiple subflows without re-injection.
Instead of dropping the OoO - "future" data in subflow_check_data_avail(), call into __mptcp_move_skbs() and let the msk drop that.
To avoid code duplication factor out the mptcp_subflow_discard_data() helper.
Note that __mptcp_move_skbs() can now find multiple subflows with data avail (comprising to-be-discarded data), so must update the byte counter incrementally.
--- net/mptcp/protocol.c | 33 +++++++++++++++---- net/mptcp/protocol.h | 9 ++++- net/mptcp/subflow.c | 78 ++++++++++++++++++++++++-------------------- 3 files changed, 78 insertions(+), 42 deletions(-)
net/mptcp/protocol.c +27 -6
@@ -167,7 +167,8 @@ static bool mptcp_subflow_dsn_valid(const struct mptcp_sock *msk,return true; subflow->data_avail =0 ; -return mptcp_subflow_data_available (ssk); +mptcp_subflow_data_available (ssk); +return subflow->data_avail ==MPTCP_SUBFLOW_DATA_AVAIL ; }static void mptcp_check_data_fin_ack (struct sock *sk)
@@ -313,11 +314,18 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,struct tcp_sock *tp;bool done = false; -if (!mptcp_subflow_dsn_valid (msk, ssk)) { - *bytes =0 ; +pr_debug ("msk=%p ssk=%p data avail=%d valid=%d empty=%d" , + msk, ssk, subflow->data_avail, +mptcp_subflow_dsn_valid (msk, ssk), + !skb_peek (&ssk->sk_receive_queue)); +if (subflow->data_avail ==MPTCP_SUBFLOW_OOO_DATA ) { +mptcp_subflow_discard_data (ssk, subflow->map_data_len);return false; } +if (!mptcp_subflow_dsn_valid (msk, ssk)) +return false; + tp =tcp_sk (ssk); do { u32 map_remaining, offset;
@@ -376,7 +384,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, } }while (more_data_avail); - *bytes = moved; + *bytes += moved;/* If the moves have caught up with the DATA_FIN sequence number * it's time to ack the DATA_FIN and change socket state, but
@@ -415,9 +423,17 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)void mptcp_data_ready (struct sock *sk,struct sock *ssk) { +struct mptcp_subflow_context *subflow =mptcp_subflow_ctx (ssk);struct mptcp_sock *msk =mptcp_sk (sk); +bool wake; -set_bit (MPTCP_DATA_READY , &msk->flags); +/* move_skbs_to_msk below can legitly clear the data_avail flag, +* but we will need later to properly woke the reader, cache its +* value +*/ + wake = subflow->data_avail ==MPTCP_SUBFLOW_DATA_AVAIL ; +if (wake) +set_bit (MPTCP_DATA_READY , &msk->flags);if (atomic_read (&sk->sk_rmem_alloc) <READ_ONCE (sk->sk_rcvbuf) &&move_skbs_to_msk (msk, ssk))
@@ -438,7 +454,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)move_skbs_to_msk (msk, ssk); } wake: - sk->sk_data_ready (sk); +if (wake) + sk->sk_data_ready (sk); }static void __mptcp_flush_join_list (struct mptcp_sock *msk)
@@ -1281,6 +1298,9 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,set_bit (MPTCP_DATA_READY , &msk->flags); } out_err: +pr_debug ("msk=%p data_ready=%d rx queue empty=%d copied=%d" , + msk,test_bit (MPTCP_DATA_READY , &msk->flags), +skb_queue_empty (&sk->sk_receive_queue), copied);mptcp_rcv_space_adjust (msk, copied);release_sock (sk);
@@ -2308,6 +2328,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,sock_poll_wait (file, sock, wait); state =inet_sk_state_load (sk); +pr_debug ("msk=%p state=%d flags=%lx" , msk, state, msk->flags);if (state ==TCP_LISTEN )return mptcp_check_readable (msk);
net/mptcp/protocol.h +8 -1
@@ -268,6 +268,12 @@ mptcp_subflow_rsk(const struct request_sock *rsk)return (struct mptcp_subflow_request_sock *)rsk; } +enum mptcp_data_avail { +MPTCP_SUBFLOW_NODATA , +MPTCP_SUBFLOW_DATA_AVAIL , +MPTCP_SUBFLOW_OOO_DATA +}; +/* MPTCP subflow context */ struct mptcp_subflow_context {struct list_head node;/* conn_list of subflows */
@@ -292,10 +298,10 @@ struct mptcp_subflow_context { map_valid : 1, mpc_map : 1, backup : 1, - data_avail : 1, rx_eof : 1, use_64bit_ack : 1, /* Set when we received a 64-bit DSN */ can_ack : 1; /* only after processing the remote a key */ +enum mptcp_data_avail data_avail;u32 remote_nonce;u64 thmac;u32 local_nonce;
@@ -347,6 +353,7 @@ int mptcp_is_enabled(struct net *net);void mptcp_subflow_fully_established (struct mptcp_subflow_context *subflow,struct mptcp_options_received *mp_opt);bool mptcp_subflow_data_available (struct sock *sk); +int mptcp_subflow_discard_data (struct sock *sk,unsigned limit);void __init mptcp_subflow_init (void );/* called with sk socket lock held */
net/mptcp/subflow.c +43 -35
107 lines not on this page · raw message
Signature · 1 line
2.26.2
Paolo Abeni
maintainerPATCH 4/13 mptcp: basic sndbuf autotuning
In reply to Paolo AbeniLet the msk sendbuf track the size of the larger subflow's send window, so that we ensure mptcp_sendmsg() does not exceed MPTCP-level send window.
The update is performed just before try to send any data.
--- net/mptcp/protocol.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-)
net/mptcp/protocol.c +13 -4
@@ -856,7 +856,8 @@ static void mptcp_nospace(struct mptcp_sock *msk) } } -static struct sock *mptcp_subflow_get_send (struct mptcp_sock *msk) +static struct sock *mptcp_subflow_get_send (struct mptcp_sock *msk, +u32 *sndbuf) {struct mptcp_subflow_context *subflow;struct sock *sk = (struct sock *)msk;
@@ -865,6 +866,7 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)sock_owned_by_me (sk); + *sndbuf =0 ;if (!mptcp_ext_cache_refill (msk))return NULL ;
@@ -877,6 +879,7 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)return NULL ; } + *sndbuf =max (tcp_sk (ssk)->snd_wnd, *sndbuf);if (subflow->backup) {if (!backup) backup = ssk;
@@ -903,6 +906,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)struct page_frag *pfrag;size_t copied =0 ;struct sock *ssk; +u32 sndbuf;bool tx_ok;long timeo;
@@ -929,7 +933,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) }__mptcp_flush_join_list (msk); - ssk =mptcp_subflow_get_send (msk); + ssk =mptcp_subflow_get_send (msk, &sndbuf);while (!sk_stream_memory_free (sk) || !ssk || !mptcp_page_frag_refill (ssk, pfrag)) {
@@ -953,13 +957,18 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)mptcp_clean_una (sk); - ssk =mptcp_subflow_get_send (msk); + ssk =mptcp_subflow_get_send (msk, &sndbuf);if (list_empty (&msk->conn_list)) { ret = -ENOTCONN ; goto out; } } +/* do auto tuning */ +if (!(sk->sk_userlocks &SOCK_SNDBUF_LOCK ) && + sndbuf >READ_ONCE (sk->sk_sndbuf)) +WRITE_ONCE (sk->sk_sndbuf, sndbuf); +pr_debug ("conn_list->subflow=%p" , ssk);lock_sock (ssk);
@@ -1547,7 +1556,7 @@ static int mptcp_init_sock(struct sock *sk)sk_sockets_allocated_inc (sk); sk->sk_rcvbuf =sock_net (sk)->ipv4.sysctl_tcp_rmem[1 ]; - sk->sk_sndbuf =sock_net (sk)->ipv4.sysctl_tcp_wmem[2 ]; + sk->sk_sndbuf =sock_net (sk)->ipv4.sysctl_tcp_wmem[1 ];return 0 ; }
Signature · 1 line
2.26.2
Paolo Abeni
maintainerPATCH 5/13 mptcp: introduce and use mptcp_try_coalesce()
In reply to Paolo AbeniFactor-out existing code, will be re-used by the
next patch.
--- net/mptcp/protocol.c | 31 +++++++++++++++++++------------ 1 file changed, 19 insertions(+), 12 deletions(-)
net/mptcp/protocol.c +19 -12
@@ -110,6 +110,22 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)return 0 ; } +static bool mptcp_try_coalesce (struct sock *sk,struct sk_buff *to, +struct sk_buff *from) +{ +bool fragstolen; +int delta; + +if (MPTCP_SKB_CB (from)->offset || + !skb_try_coalesce (to, from, &fragstolen, &delta)) +return false; + +kfree_skb_partial (from, fragstolen); +atomic_add (delta, &sk->sk_rmem_alloc); +sk_mem_charge (sk, delta); +return true; +} +static void __mptcp_move_skb (struct mptcp_sock *msk,struct sock *ssk,struct sk_buff *skb,unsigned int offset,size_t copy_len)
@@ -121,24 +137,15 @@ static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,skb_ext_reset (skb);skb_orphan (skb); +MPTCP_SKB_CB (skb)->offset = offset; msk->ack_seq += copy_len; tail =skb_peek_tail (&sk->sk_receive_queue); -if (offset ==0 && tail) { -bool fragstolen; -int delta; - -if (skb_try_coalesce (tail, skb, &fragstolen, &delta)) { -kfree_skb_partial (skb, fragstolen); -atomic_add (delta, &sk->sk_rmem_alloc); -sk_mem_charge (sk, delta); -return ; - } - } +if (tail &&mptcp_try_coalesce (sk, tail, skb)) +return ;skb_set_owner_r (skb, sk);__skb_queue_tail (&sk->sk_receive_queue, skb); -MPTCP_SKB_CB (skb)->offset = offset; }static void mptcp_stop_timer (struct sock *sk)
Signature · 1 line
2.26.2
Paolo Abeni
maintainerPATCH 6/13 mptcp: move ooo skbs into msk out of order queue.
In reply to Paolo AbeniAdd an RB-tree to cope with OoO (at MPTCP level) data. __mptcp_move_skb() insert into the RB tree "future" data, eventually coalescing skb as allowed by the MPTCP DSN.
To simplify sequence accounting, move the DSN inside the cb.
After successfully enqueuing in sequence data, check if we can use any data from the RB tree.
Additionally move the data_fin check after spooling data from the OoO tree, otherwise we could miss shutdown events.
The RB tree code is copied as verbatim as possible from tcp_data_queue_ofo(), with a few simplifications due to the fact that MPTCP doesn't need to cope with sacks. All bugs here are added by me.
--- net/mptcp/protocol.c | 264 ++++++++++++++++++++++++++++++++++--------- net/mptcp/protocol.h | 2 + net/mptcp/subflow.c | 1 + 3 files changed, 211 insertions(+), 56 deletions(-)
net/mptcp/protocol.c +208 -56
@@ -32,6 +32,8 @@ struct mptcp6_sock {#endif struct mptcp_skb_cb { +u64 map_seq; +u64 end_seq;u32 offset; };
@@ -110,6 +112,12 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)return 0 ; } +static void mptcp_drop (struct sock *sk,struct sk_buff *skb) +{ +sk_drops_add (sk, skb); +__kfree_skb (skb); +} +static bool mptcp_try_coalesce (struct sock *sk,struct sk_buff *to,struct sk_buff *from) {
@@ -120,16 +128,127 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, !skb_try_coalesce(to, from, &fragstolen, &delta))return false; +MPTCP_SKB_CB (to)->end_seq =MPTCP_SKB_CB (from)->end_seq;kfree_skb_partial (from, fragstolen);atomic_add (delta, &sk->sk_rmem_alloc);sk_mem_charge (sk, delta);return true; } -static void __mptcp_move_skb (struct mptcp_sock *msk,struct sock *ssk, -struct sk_buff *skb, -unsigned int offset,size_t copy_len) +static bool mptcp_ooo_try_coalesce (struct mptcp_sock *msk,struct sk_buff *to, +struct sk_buff *from) +{ +if (MPTCP_SKB_CB (from)->map_seq !=MPTCP_SKB_CB (to)->end_seq) +return false; + +return mptcp_try_coalesce ((struct sock *)msk, to, from); +} + +/* "inspired" by tcp_data_queue_ofo(), main differences: +* - use mptcp seqs +* - don't cope with sacks +*/ +static void mptcp_data_queue_ofo (struct mptcp_sock *msk,struct sk_buff *skb) { +struct sock *sk = (struct sock *)msk; +struct rb_node **p, *parent; +u64 seq, end_seq, max_seq; +struct sk_buff *skb1; + + seq =MPTCP_SKB_CB (skb)->map_seq; + end_seq =MPTCP_SKB_CB (skb)->end_seq; + max_seq =tcp_space (sk); + max_seq = max_seq >0 ? max_seq + msk->ack_seq : msk->ack_seq; + +if (after64 (seq, max_seq)) { +/* out of window */ +mptcp_drop (sk, skb); +return ; + } + + p = &msk->out_of_order_queue.rb_node; +if (RB_EMPTY_ROOT (&msk->out_of_order_queue)) { +rb_link_node (&skb->rbnode,NULL , p); +rb_insert_color (&skb->rbnode, &msk->out_of_order_queue); + msk->ooo_last_skb = skb; + goto end; + } + +/* with 2 subflows, adding at end of ooo queue is quite likely +* Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. +*/ +if (mptcp_ooo_try_coalesce (msk, msk->ooo_last_skb, skb)) +return ; + +/* Can avoid an rbtree lookup if we are adding skb after ooo_last_skb */ +if (!before64 (seq,MPTCP_SKB_CB (msk->ooo_last_skb)->end_seq)) { + parent = &msk->ooo_last_skb->rbnode; + p = &parent->rb_right; + goto insert; + } + +/* Find place to insert this segment. Handle overlaps on the way. */ + parent =NULL ; +while (*p) { + parent = *p; + skb1 =rb_to_skb (parent); +if (before64 (seq,MPTCP_SKB_CB (skb1)->map_seq)) { + p = &parent->rb_left; +continue ; + } +if (before64 (seq,MPTCP_SKB_CB (skb1)->end_seq)) { +if (!after64 (end_seq,MPTCP_SKB_CB (skb1)->end_seq)) { +/* All the bits are present. Drop. */ +mptcp_drop (sk, skb); +return ; + } +if (after64 (seq,MPTCP_SKB_CB (skb1)->map_seq)) { +/* partial overlap: +* | skb | +* | skb1 | +* continue traversing +*/ + }else { +/* skb's seq == skb1's seq and skb covers skb1. +* Replace skb1 with skb. +*/ +rb_replace_node (&skb1->rbnode, &skb->rbnode, + &msk->out_of_order_queue); +mptcp_drop (sk, skb1); + goto merge_right; + } + }else if (mptcp_ooo_try_coalesce (msk, skb1, skb)) { +return ; + } + p = &parent->rb_right; + } +insert: +/* Insert segment into RB tree. */ +rb_link_node (&skb->rbnode, parent, p); +rb_insert_color (&skb->rbnode, &msk->out_of_order_queue); + +merge_right: +/* Remove other segments covered by skb. */ +while ((skb1 =skb_rb_next (skb)) !=NULL ) { +if (before64 (end_seq,MPTCP_SKB_CB (skb1)->end_seq)) +break ; +rb_erase (&skb1->rbnode, &msk->out_of_order_queue); +mptcp_drop (sk, skb1); + } +/* If there is no skb after us, we are the last_skb ! */ +if (!skb1) + msk->ooo_last_skb = skb; + +end: +skb_condense (skb); +skb_set_owner_r (skb, sk); +} + +static bool __mptcp_move_skb (struct mptcp_sock *msk,struct sock *ssk, +struct sk_buff *skb,unsigned int offset, +size_t copy_len) +{ +struct mptcp_subflow_context *subflow =mptcp_subflow_ctx (ssk);struct sock *sk = (struct sock *)msk;struct sk_buff *tail;
@@ -137,15 +256,35 @@ static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,skb_ext_reset (skb);skb_orphan (skb); + +/* the skb map_seq accounts for the skb offset: +* mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq +* value +*/ +MPTCP_SKB_CB (skb)->map_seq =mptcp_subflow_get_mapped_dsn (subflow); +MPTCP_SKB_CB (skb)->end_seq =MPTCP_SKB_CB (skb)->map_seq + copy_len;MPTCP_SKB_CB (skb)->offset = offset; - msk->ack_seq += copy_len; - tail =skb_peek_tail (&sk->sk_receive_queue); -if (tail &&mptcp_try_coalesce (sk, tail, skb)) -return ; +if (MPTCP_SKB_CB (skb)->map_seq == msk->ack_seq) { +/* in sequence */ + msk->ack_seq += copy_len; + tail =skb_peek_tail (&sk->sk_receive_queue); +if (tail &&mptcp_try_coalesce (sk, tail, skb)) +return true; -skb_set_owner_r (skb, sk); -__skb_queue_tail (&sk->sk_receive_queue, skb); +skb_set_owner_r (skb, sk); +__skb_queue_tail (&sk->sk_receive_queue, skb); +return true; + }else if (after64 (MPTCP_SKB_CB (skb)->map_seq, msk->ack_seq)) { +mptcp_data_queue_ofo (msk, skb); +return false; + } + +/* old data, keep it simple and drop the whole pkt, sender +* will retransmit as needed, if needed. +*/ +mptcp_drop (sk, skb); +return false; }static void mptcp_stop_timer (struct sock *sk)
@@ -156,28 +295,6 @@ static void mptcp_stop_timer(struct sock *sk)mptcp_sk (sk)->timer_ival =0 ; } -/* both sockets must be locked */ -static bool mptcp_subflow_dsn_valid (const struct mptcp_sock *msk, -struct sock *ssk) -{ -struct mptcp_subflow_context *subflow =mptcp_subflow_ctx (ssk); -u64 dsn =mptcp_subflow_get_mapped_dsn (subflow); - -/* revalidate data sequence number. -* -* mptcp_subflow_data_available() is usually called -* without msk lock. Its unlikely (but possible) -* that msk->ack_seq has been advanced since the last -* call found in-sequence data. -*/ -if (likely (dsn == msk->ack_seq)) -return true; - - subflow->data_avail =0 ; -mptcp_subflow_data_available (ssk); -return subflow->data_avail ==MPTCP_SUBFLOW_DATA_AVAIL ; -} -static void mptcp_check_data_fin_ack (struct sock *sk) {struct mptcp_sock *msk =mptcp_sk (sk);
@@ -321,18 +438,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,struct tcp_sock *tp;bool done = false; -pr_debug ("msk=%p ssk=%p data avail=%d valid=%d empty=%d" , - msk, ssk, subflow->data_avail, -mptcp_subflow_dsn_valid (msk, ssk), - !skb_peek (&ssk->sk_receive_queue)); -if (subflow->data_avail ==MPTCP_SUBFLOW_OOO_DATA ) { -mptcp_subflow_discard_data (ssk, subflow->map_data_len); -return false; - } - -if (!mptcp_subflow_dsn_valid (msk, ssk)) -return false; - +pr_debug ("msk=%p ssk=%p" , msk, ssk); tp =tcp_sk (ssk); do { u32 map_remaining, offset;
@@ -370,9 +476,9 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,if (tp->urg_data) done = true; -__mptcp_move_skb (msk, ssk, skb, offset, len); +if (__mptcp_move_skb (msk, ssk, skb, offset, len)) + moved += len; seq += len; - moved += len;if (WARN_ON_ONCE (map_remaining < len))break ;
@@ -393,18 +499,47 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, *bytes += moved; -/* If the moves have caught up with the DATA_FIN sequence number -* it's time to ack the DATA_FIN and change socket state, but -* this is not a good place to change state. Let the workqueue -* do it. -*/ -if (mptcp_pending_data_fin (sk,NULL ) && -schedule_work (&msk->work)) -sock_hold (sk); -return done; } +static bool mptcp_ofo_queue (struct mptcp_sock *msk) +{ +struct sock *sk = (struct sock *)msk; +struct sk_buff *skb, *tail; +bool moved = false; +struct rb_node *p; +u64 end_seq; + + p =rb_first (&msk->out_of_order_queue); +while (p) { + skb =rb_to_skb (p); +if (after64 (MPTCP_SKB_CB (skb)->map_seq, msk->ack_seq)) +break ; + + p =rb_next (p); +rb_erase (&skb->rbnode, &msk->out_of_order_queue); + +if (unlikely (!after64 (MPTCP_SKB_CB (skb)->end_seq, + msk->ack_seq))) { +mptcp_drop (sk, skb); +continue ; + } + + end_seq =MPTCP_SKB_CB (skb)->end_seq; + tail =skb_peek_tail (&sk->sk_receive_queue); +if (!tail || !mptcp_ooo_try_coalesce (msk, tail, skb)) { +int delta = msk->ack_seq -MPTCP_SKB_CB (skb)->map_seq; + +/* skip overlapping data, if any */ +MPTCP_SKB_CB (skb)->offset += delta; +__skb_queue_tail (&sk->sk_receive_queue, skb); + } + msk->ack_seq = end_seq; + moved = true; + } +return moved; +} +/* In most cases we will be able to lock the mptcp socket. If its already * owned, we need to defer to the work queue to avoid ABBA deadlock. */
@@ -420,8 +555,19 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)return false;/* must re-check after taking the lock */ -if (!READ_ONCE (sk->sk_lock.owned)) +if (!READ_ONCE (sk->sk_lock.owned)) {__mptcp_move_skbs_from_subflow (msk, ssk, &moved); +mptcp_ofo_queue (msk); + +/* If the moves have caught up with the DATA_FIN sequence number +* it's time to ack the DATA_FIN and change socket state, but +* this is not a good place to change state. Let the workqueue +* do it. +*/ +if (mptcp_pending_data_fin (sk,NULL ) && +schedule_work (&msk->work)) +sock_hold (sk); + }spin_unlock_bh (&sk->sk_lock.slock);
@@ -1218,7 +1364,11 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk)release_sock (ssk); }while (!done); -return moved >0 ; +if (mptcp_ofo_queue (msk) || moved >0 ) { +mptcp_check_data_fin ((struct sock *)msk); +return true; + } +return false; } static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
@@ -1530,6 +1680,7 @@ static int __mptcp_init_sock(struct sock *sk)INIT_LIST_HEAD (&msk->rtx_queue);__set_bit (MPTCP_SEND_SPACE , &msk->flags);INIT_WORK (&msk->work, mptcp_worker); + msk->out_of_order_queue =RB_ROOT ; msk->first =NULL ;inet_csk (sk)->icsk_sync_mss = mptcp_sync_mss;
@@ -1869,6 +2020,7 @@ static void mptcp_destroy(struct sock *sk) {struct mptcp_sock *msk =mptcp_sk (sk); +skb_rbtree_purge (&msk->out_of_order_queue);mptcp_token_destroy (msk);if (msk->cached_ext)__skb_ext_put (msk->cached_ext);
net/mptcp/protocol.h +2 -0
@@ -204,6 +204,8 @@ struct mptcp_sock {bool snd_data_fin_enable;spinlock_t join_list_lock;struct work_struct work; +struct sk_buff *ooo_last_skb; +struct rb_root out_of_order_queue;struct list_head conn_list;struct list_head rtx_queue;struct list_head join_list;
net/mptcp/subflow.c +1 -0
@@ -434,6 +434,7 @@ static void mptcp_sock_destruct(struct sock *sk)sock_orphan (sk); } +skb_rbtree_purge (&mptcp_sk (sk)->out_of_order_queue);mptcp_token_destroy (mptcp_sk (sk));inet_sock_destruct (sk); }
Signature · 1 line
2.26.2
Paolo Abeni
maintainerPATCH 7/13 mptcp: cleanup mptcp_subflow_discard_data()
In reply to Paolo AbeniThere is no need to use the tcp_read_sock(), we can simply drop the skb. Additionally try to look at the next buffer for in order data.
This both simplifies the code and avoid unneeded indirect calls.
--- net/mptcp/protocol.h | 1 - net/mptcp/subflow.c | 58 +++++++++++--------------------------------- 2 files changed, 14 insertions(+), 45 deletions(-)
net/mptcp/protocol.h +0 -1
@@ -355,7 +355,6 @@ int mptcp_is_enabled(struct net *net);void mptcp_subflow_fully_established (struct mptcp_subflow_context *subflow,struct mptcp_options_received *mp_opt);bool mptcp_subflow_data_available (struct sock *sk); -int mptcp_subflow_discard_data (struct sock *sk,unsigned limit);void __init mptcp_subflow_init (void );/* called with sk socket lock held */
net/mptcp/subflow.c +14 -44
73 lines not on this page · raw message
Signature · 1 line
2.26.2
Paolo Abeni
maintainerPATCH 8/13 mptcp: add OoO related mibs
In reply to Paolo AbeniAdd a bunch of MPTCP mibs related to MPTCP OoO data processing.
--- net/mptcp/mib.c | 5 +++++ net/mptcp/mib.h | 5 +++++ net/mptcp/protocol.c | 24 +++++++++++++++++++++++- net/mptcp/subflow.c | 1 + 4 files changed, 34 insertions(+), 1 deletion(-)
net/mptcp/mib.c +5 -0
@@ -22,6 +22,11 @@ static const struct snmp_mib mptcp_snmp_list[] = {SNMP_MIB_ITEM ("MPJoinAckHMacFailure" ,MPTCP_MIB_JOINACKMAC ),SNMP_MIB_ITEM ("DSSNotMatching" ,MPTCP_MIB_DSSNOMATCH ),SNMP_MIB_ITEM ("InfiniteMapRx" ,MPTCP_MIB_INFINITEMAPRX ), +SNMP_MIB_ITEM ("OFOQueueTail" ,MPTCP_MIB_OFOQUEUETAIL ), +SNMP_MIB_ITEM ("OFOQueue" ,MPTCP_MIB_OFOQUEUE ), +SNMP_MIB_ITEM ("OFOMerge" ,MPTCP_MIB_OFOMERGE ), +SNMP_MIB_ITEM ("NoDSSInWindow" ,MPTCP_MIB_NODSSWINDOW ), +SNMP_MIB_ITEM ("DuplicateData" ,MPTCP_MIB_DUPDATA ),SNMP_MIB_SENTINEL };
net/mptcp/mib.h +5 -0
@@ -15,6 +15,11 @@ enum linux_mptcp_mib_field {MPTCP_MIB_JOINACKMAC ,/* HMAC was wrong on ACK + MP_JOIN */ MPTCP_MIB_DSSNOMATCH ,/* Received a new mapping that did not match the previous one */ MPTCP_MIB_INFINITEMAPRX ,/* Received an infinite mapping */ +MPTCP_MIB_OFOQUEUETAIL ,/* Segments inserted into OoO queue tail */ +MPTCP_MIB_OFOQUEUE ,/* Segments inserted into OoO queue */ +MPTCP_MIB_OFOMERGE ,/* Segments merged in OoO queue */ +MPTCP_MIB_NODSSWINDOW ,/* Segments not in MPTCP windows */ +MPTCP_MIB_DUPDATA ,/* Segments discarded due to duplicate DSS */ __MPTCP_MIB_MAX };
net/mptcp/protocol.c +23 -1
@@ -128,6 +128,9 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, !skb_try_coalesce(to, from, &fragstolen, &delta))return false; +pr_debug ("colesced seq %llx into %llx new len %d new end seq %llx" , +MPTCP_SKB_CB (from)->map_seq,MPTCP_SKB_CB (to)->map_seq, + to->len,MPTCP_SKB_CB (from)->end_seq);MPTCP_SKB_CB (to)->end_seq =MPTCP_SKB_CB (from)->end_seq;kfree_skb_partial (from, fragstolen);atomic_add (delta, &sk->sk_rmem_alloc);
@@ -160,13 +163,17 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb) max_seq =tcp_space (sk); max_seq = max_seq >0 ? max_seq + msk->ack_seq : msk->ack_seq; +pr_debug ("msk=%p seq=%llx limit=%llx empty=%d" , msk, seq, max_seq, +RB_EMPTY_ROOT (&msk->out_of_order_queue));if (after64 (seq, max_seq)) {/* out of window */ mptcp_drop (sk, skb); +MPTCP_INC_STATS (sock_net (sk),MPTCP_MIB_NODSSWINDOW );return ; } p = &msk->out_of_order_queue.rb_node; +MPTCP_INC_STATS (sock_net (sk),MPTCP_MIB_OFOQUEUE );if (RB_EMPTY_ROOT (&msk->out_of_order_queue)) {rb_link_node (&skb->rbnode,NULL , p);rb_insert_color (&skb->rbnode, &msk->out_of_order_queue);
@@ -177,11 +184,15 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)/* with 2 subflows, adding at end of ooo queue is quite likely * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. */ -if (mptcp_ooo_try_coalesce (msk, msk->ooo_last_skb, skb)) +if (mptcp_ooo_try_coalesce (msk, msk->ooo_last_skb, skb)) { +MPTCP_INC_STATS (sock_net (sk),MPTCP_MIB_OFOMERGE ); +MPTCP_INC_STATS (sock_net (sk),MPTCP_MIB_OFOQUEUETAIL );return ; + }/* Can avoid an rbtree lookup if we are adding skb after ooo_last_skb */ if (!before64 (seq,MPTCP_SKB_CB (msk->ooo_last_skb)->end_seq)) { +MPTCP_INC_STATS (sock_net (sk),MPTCP_MIB_OFOQUEUETAIL ); parent = &msk->ooo_last_skb->rbnode; p = &parent->rb_right; goto insert;
@@ -200,6 +211,7 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)if (!after64 (end_seq,MPTCP_SKB_CB (skb1)->end_seq)) {/* All the bits are present. Drop. */ mptcp_drop (sk, skb); +MPTCP_INC_STATS (sock_net (sk),MPTCP_MIB_DUPDATA );return ; }if (after64 (seq,MPTCP_SKB_CB (skb1)->map_seq)) {
@@ -215,13 +227,16 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)rb_replace_node (&skb1->rbnode, &skb->rbnode, &msk->out_of_order_queue);mptcp_drop (sk, skb1); +MPTCP_INC_STATS (sock_net (sk),MPTCP_MIB_DUPDATA ); goto merge_right; } }else if (mptcp_ooo_try_coalesce (msk, skb1, skb)) { +MPTCP_INC_STATS (sock_net (sk),MPTCP_MIB_OFOMERGE );return ; } p = &parent->rb_right; } + insert:/* Insert segment into RB tree. */ rb_link_node (&skb->rbnode, parent, p);
@@ -234,6 +249,7 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)break ;rb_erase (&skb1->rbnode, &msk->out_of_order_queue);mptcp_drop (sk, skb1); +MPTCP_INC_STATS (sock_net (sk),MPTCP_MIB_DUPDATA ); }/* If there is no skb after us, we are the last_skb ! */ if (!skb1)
@@ -283,6 +299,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,/* old data, keep it simple and drop the whole pkt, sender * will retransmit as needed, if needed. */ +MPTCP_INC_STATS (sock_net (sk),MPTCP_MIB_DUPDATA );mptcp_drop (sk, skb);return false; }
@@ -511,6 +528,7 @@ static bool mptcp_ofo_queue(struct mptcp_sock *msk)u64 end_seq; p =rb_first (&msk->out_of_order_queue); +pr_debug ("msk=%p empty=%d" , msk,RB_EMPTY_ROOT (&msk->out_of_order_queue));while (p) { skb =rb_to_skb (p);if (after64 (MPTCP_SKB_CB (skb)->map_seq, msk->ack_seq))
@@ -522,6 +540,7 @@ static bool mptcp_ofo_queue(struct mptcp_sock *msk)if (unlikely (!after64 (MPTCP_SKB_CB (skb)->end_seq, msk->ack_seq))) {mptcp_drop (sk, skb); +MPTCP_INC_STATS (sock_net (sk),MPTCP_MIB_DUPDATA );continue ; }
@@ -531,6 +550,9 @@ static bool mptcp_ofo_queue(struct mptcp_sock *msk)int delta = msk->ack_seq -MPTCP_SKB_CB (skb)->map_seq;/* skip overlapping data, if any */ +pr_debug ("uncoalesced seq=%llx ack seq=%llx delta=%d" , +MPTCP_SKB_CB (skb)->map_seq, msk->ack_seq, + delta);MPTCP_SKB_CB (skb)->offset += delta;__skb_queue_tail (&sk->sk_receive_queue, skb); }
net/mptcp/subflow.c +1 -0
@@ -816,6 +816,7 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,pr_debug ("discarding=%d len=%d seq=%d" , incr, skb->len, subflow->map_subflow_seq); +MPTCP_INC_STATS (sock_net (ssk),MPTCP_MIB_DUPDATA );tcp_sk (ssk)->copied_seq += incr;if (!before (tcp_sk (ssk)->copied_seq,TCP_SKB_CB (skb)->end_seq))sk_eat_skb (ssk, skb);
Signature · 1 line
2.26.2
Paolo Abeni
maintainerPATCH 9/13 mptcp: move address attribute into mptcp_addr_info
In reply to Paolo AbeniSo that can be accessed easily from the subflow creation helper. No functional change intended.
--- net/mptcp/pm_netlink.c | 39 ++++++++++++++++++++------------------- net/mptcp/protocol.h | 5 +++-- net/mptcp/subflow.c | 5 ++--- 3 files changed, 25 insertions(+), 24 deletions(-)
net/mptcp/pm_netlink.c +20 -19
@@ -23,8 +23,6 @@ static int pm_nl_pernet_id;struct mptcp_pm_addr_entry {struct list_head list; -unsigned int flags; -int ifindex;struct mptcp_addr_info addr;struct rcu_head rcu; };
@@ -119,7 +117,7 @@ select_local_address(const struct pm_nl_pernet *pernet,rcu_read_lock ();spin_lock_bh (&msk->join_list_lock);list_for_each_entry_rcu (entry, &pernet->local_addr_list, list) { -if (!(entry->flags &MPTCP_PM_ADDR_FLAG_SUBFLOW )) +if (!(entry->addr.flags &MPTCP_PM_ADDR_FLAG_SUBFLOW ))continue ;/* avoid any address already in use by subflows and
@@ -150,7 +148,7 @@ select_signal_address(struct pm_nl_pernet *pernet, unsigned int pos)* can lead to additional addresses not being announced. */ list_for_each_entry_rcu (entry, &pernet->local_addr_list, list) { -if (!(entry->flags &MPTCP_PM_ADDR_FLAG_SIGNAL )) +if (!(entry->addr.flags &MPTCP_PM_ADDR_FLAG_SIGNAL ))continue ;if (i++ == pos) { ret = entry;
@@ -210,8 +208,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) msk->pm.subflows++;check_work_pending (msk);spin_unlock_bh (&msk->pm.lock); -__mptcp_subflow_connect (sk, local->ifindex, - &local->addr, &remote); +__mptcp_subflow_connect (sk, &local->addr, &remote);spin_lock_bh (&msk->pm.lock);return ; }
@@ -257,13 +254,13 @@ void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) local.family = remote.family;spin_unlock_bh (&msk->pm.lock); -__mptcp_subflow_connect ((struct sock *)msk,0 , &local, &remote); +__mptcp_subflow_connect ((struct sock *)msk, &local, &remote);spin_lock_bh (&msk->pm.lock); }static bool address_use_port (struct mptcp_pm_addr_entry *entry) { -return (entry->flags & +return (entry->addr.flags & (MPTCP_PM_ADDR_FLAG_SIGNAL |MPTCP_PM_ADDR_FLAG_SUBFLOW )) ==MPTCP_PM_ADDR_FLAG_SIGNAL ; }
@@ -293,9 +290,9 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, goto out; } -if (entry->flags &MPTCP_PM_ADDR_FLAG_SIGNAL ) +if (entry->addr.flags &MPTCP_PM_ADDR_FLAG_SIGNAL ) pernet->add_addr_signal_max++; -if (entry->flags &MPTCP_PM_ADDR_FLAG_SUBFLOW ) +if (entry->addr.flags &MPTCP_PM_ADDR_FLAG_SUBFLOW ) pernet->local_addr_max++; entry->addr.id = pernet->next_id++;
@@ -345,8 +342,9 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)if (!entry)return -ENOMEM ; - entry->flags =0 ; entry->addr = skc_local; + entry->addr.ifindex =0 ; + entry->addr.flags =0 ; ret =mptcp_pm_nl_append_new_local_addr (pernet, entry);if (ret <0 )kfree (entry);
@@ -460,14 +458,17 @@ static int mptcp_pm_parse_addr(struct nlattr *attr, struct genl_info *info, entry->addr.addr.s_addr =nla_get_in_addr (tb[addr_addr]); skip_family: -if (tb[MPTCP_PM_ADDR_ATTR_IF_IDX ]) - entry->ifindex =nla_get_s32 (tb[MPTCP_PM_ADDR_ATTR_IF_IDX ]); +if (tb[MPTCP_PM_ADDR_ATTR_IF_IDX ]) { +u32 val =nla_get_s32 (tb[MPTCP_PM_ADDR_ATTR_IF_IDX ]); + + entry->addr.ifindex = val; + }if (tb[MPTCP_PM_ADDR_ATTR_ID ]) entry->addr.id =nla_get_u8 (tb[MPTCP_PM_ADDR_ATTR_ID ]);if (tb[MPTCP_PM_ADDR_ATTR_FLAGS ]) - entry->flags =nla_get_u32 (tb[MPTCP_PM_ADDR_ATTR_FLAGS ]); + entry->addr.flags =nla_get_u32 (tb[MPTCP_PM_ADDR_ATTR_FLAGS ]);return 0 ; }
@@ -535,9 +536,9 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) ret = -EINVAL ; goto out; } -if (entry->flags &MPTCP_PM_ADDR_FLAG_SIGNAL ) +if (entry->addr.flags &MPTCP_PM_ADDR_FLAG_SIGNAL ) pernet->add_addr_signal_max--; -if (entry->flags &MPTCP_PM_ADDR_FLAG_SUBFLOW ) +if (entry->addr.flags &MPTCP_PM_ADDR_FLAG_SUBFLOW ) pernet->local_addr_max--; pernet->addrs--;
@@ -593,10 +594,10 @@ static int mptcp_nl_fill_addr(struct sk_buff *skb, goto nla_put_failure;if (nla_put_u8 (skb,MPTCP_PM_ADDR_ATTR_ID , addr->id)) goto nla_put_failure; -if (nla_put_u32 (skb,MPTCP_PM_ADDR_ATTR_FLAGS , entry->flags)) +if (nla_put_u32 (skb,MPTCP_PM_ADDR_ATTR_FLAGS , entry->addr.flags)) goto nla_put_failure; -if (entry->ifindex && -nla_put_s32 (skb,MPTCP_PM_ADDR_ATTR_IF_IDX , entry->ifindex)) +if (entry->addr.ifindex && +nla_put_s32 (skb,MPTCP_PM_ADDR_ATTR_IF_IDX , entry->addr.ifindex)) goto nla_put_failure; if (addr->family == AF_INET &&
net/mptcp/protocol.h +3 -2
@@ -140,6 +140,8 @@ struct mptcp_addr_info {sa_family_t family;__be16 port;u8 id; +u8 flags; +int ifindex;union {struct in_addr addr;#if IS_ENABLED (CONFIG_MPTCP_IPV6 )
@@ -358,8 +360,7 @@ bool mptcp_subflow_data_available(struct sock *sk);void __init mptcp_subflow_init (void );/* called with sk socket lock held */ -int __mptcp_subflow_connect (struct sock *sk,int ifindex, -const struct mptcp_addr_info *loc, +int __mptcp_subflow_connect (struct sock *sk,const struct mptcp_addr_info *loc,const struct mptcp_addr_info *remote);int mptcp_subflow_create_socket (struct sock *sk,struct socket **new_sock);
net/mptcp/subflow.c +2 -3
@@ -1035,8 +1035,7 @@ static void mptcp_info2sockaddr(const struct mptcp_addr_info *info,#endif } -int __mptcp_subflow_connect (struct sock *sk,int ifindex, -const struct mptcp_addr_info *loc, +int __mptcp_subflow_connect (struct sock *sk,const struct mptcp_addr_info *loc,const struct mptcp_addr_info *remote) {struct mptcp_sock *msk =mptcp_sk (sk);
@@ -1080,7 +1079,7 @@ int __mptcp_subflow_connect(struct sock *sk, int ifindex,if (loc->family ==AF_INET6 ) addrlen =sizeof (struct sockaddr_in6 );#endif - ssk->sk_bound_dev_if = ifindex; + ssk->sk_bound_dev_if = loc->ifindex; err =kernel_bind (sf, (struct sockaddr *)&addr, addrlen);if (err) goto failed;
Signature · 1 line
2.26.2
Paolo Abeni
maintainerPATCH 10/13 mptcp: allow creating non-backup subflows
In reply to Paolo AbeniCurrently the 'backup' attribute of local endpoint is ignored. Let's use it for the MP_JOIN handshake
--- net/mptcp/subflow.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
net/mptcp/subflow.c +2 -1
@@ -20,6 +20,7 @@#include <net/ip6_route.h> #endif #include <net/mptcp.h> +#include <uapi/linux/mptcp.h> #include "protocol.h" #include "mib.h"
@@ -1090,7 +1091,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, subflow->remote_token = remote_token; subflow->local_id = local_id; subflow->request_join =1 ; - subflow->request_bkup =1 ; + subflow->request_bkup = !!(loc->flags &MPTCP_PM_ADDR_FLAG_BACKUP );mptcp_info2sockaddr (remote, &addr); err =kernel_connect (sf, (struct sockaddr *)&addr, addrlen,O_NONBLOCK );
Signature · 1 line
2.26.2
Paolo Abeni
maintainerPATCH 11/13 mptcp: allow picking different xmit subflows
In reply to Paolo AbeniUpdate the scheduler to less trivial heuristic: cache the last used subflow, and try to send on it a reasonably long burst of data.
When the burst or the subflow send space is exhausted, pick the subflow with the lower ratio between write space and send buffer - that is, the subflow with the greater relative amount of free space.
--- net/mptcp/protocol.c | 109 ++++++++++++++++++++++++++++++++++++------- net/mptcp/protocol.h | 6 ++- 2 files changed, 97 insertions(+), 18 deletions(-)
net/mptcp/protocol.c +93 -16
@@ -1031,41 +1031,103 @@ static void mptcp_nospace(struct mptcp_sock *msk) } } +static bool mptcp_subflow_active (struct mptcp_subflow_context *subflow) +{ +struct sock *ssk =mptcp_subflow_tcp_sock (subflow); + +/* can't send if JOIN hasn't completed yet (i.e. is usable for mptcp) */ +if (subflow->request_join && !subflow->fully_established) +return false; + +/* only send if our side has not closed yet */ +return ((1 << ssk->sk_state) & (TCPF_ESTABLISHED |TCPF_CLOSE_WAIT )); +} + +#define MPTCP_SEND_BURST_SIZE ((1 << 16) - \ + sizeof(struct tcphdr) - \ + MAX_TCP_OPTION_SPACE - \ + sizeof(struct ipv6hdr) - \ + sizeof(struct frag_hdr)) + +struct subflow_send_info { +struct sock *ssk; +uint64_t ratio; +}; +static struct sock *mptcp_subflow_get_send (struct mptcp_sock *msk,u32 *sndbuf) { +struct subflow_send_info send_info[2 ];struct mptcp_subflow_context *subflow; -struct sock *sk = (struct sock *)msk; -struct sock *backup =NULL ; -bool free; +int i, nr_active =0 ; +int64_t ratio, pace; +struct sock *ssk; -sock_owned_by_me (sk); +sock_owned_by_me ((struct sock *)msk); *sndbuf =0 ;if (!mptcp_ext_cache_refill (msk))return NULL ; -mptcp_for_each_subflow (msk, subflow) { -struct sock *ssk =mptcp_subflow_tcp_sock (subflow); - - free =sk_stream_is_writeable (subflow->tcp_sock); -if (!free) { -mptcp_nospace (msk); +if (__mptcp_check_fallback (msk)) { +if (!msk->first)return NULL ; + *sndbuf = msk->first->sk_sndbuf; +return sk_stream_memory_free (msk->first) ? msk->first :NULL ; + } + +/* re-use last subflow, if the burst allow that */ +if (msk->last_snd && msk->snd_burst >0 && +sk_stream_memory_free (msk->last_snd) && +mptcp_subflow_active (mptcp_subflow_ctx (msk->last_snd))) { +mptcp_for_each_subflow (msk, subflow) { + ssk =mptcp_subflow_tcp_sock (subflow); + *sndbuf =max (tcp_sk (ssk)->snd_wnd, *sndbuf); } +return msk->last_snd; + } + +/* pick the subflow with the lower wmem/wspace ratio */ +for (i =0 ; i <2 ; ++i) { + send_info[i].ssk =NULL ; + send_info[i].ratio =-1 ; + } +mptcp_for_each_subflow (msk, subflow) { + ssk =mptcp_subflow_tcp_sock (subflow); +if (!mptcp_subflow_active (subflow)) +continue ; + nr_active += !subflow->backup; *sndbuf =max (tcp_sk (ssk)->snd_wnd, *sndbuf); -if (subflow->backup) { -if (!backup) - backup = ssk; +if (!sk_stream_memory_free (subflow->tcp_sock)) +continue ; + pace =READ_ONCE (ssk->sk_pacing_rate); +if (!pace)continue ; - } -return ssk; + ratio = (int64_t )READ_ONCE (ssk->sk_wmem_queued) <<32 / pace; +if (ratio < send_info[subflow->backup].ratio) { + send_info[subflow->backup].ssk = ssk; + send_info[subflow->backup].ratio = ratio; + } } -return backup; +pr_debug ("msk=%p nr_active=%d ssk=%p:%lld backup=%p:%lld" , + msk, nr_active, send_info[0 ].ssk, send_info[0 ].ratio, + send_info[1 ].ssk, send_info[1 ].ratio); + +/* pick the best backup if no other subflow is active */ +if (!nr_active) + send_info[0 ].ssk = send_info[1 ].ssk; + +if (send_info[0 ].ssk) { + msk->last_snd = send_info[0 ].ssk; + msk->snd_burst =min_t (int,MPTCP_SEND_BURST_SIZE , +sk_stream_wspace (msk->last_snd)); +return msk->last_snd; + } +return NULL ; }static void ssk_check_wmem (struct mptcp_sock *msk)
@@ -1160,6 +1222,10 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)break ; } +/* burst can be negative, we will try move to the next subflow +* at selection time, if possible. +*/ + msk->snd_burst -= ret; copied += ret; tx_ok =msg_data_left (msg);
@@ -1375,6 +1441,11 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk)unsigned int moved =0 ;bool done; +/* avoid looping forever below on racing close */ +if (((struct sock *)msk)->sk_state ==TCP_CLOSE ) +return false; + +__mptcp_flush_join_list (msk); do { struct sock *ssk = mptcp_subflow_recv_lookup(msk);
@@ -1539,9 +1610,15 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk)sock_owned_by_me ((const struct sock *)msk); +if (__mptcp_check_fallback (msk)) +return msk->first; +mptcp_for_each_subflow (msk, subflow) {struct sock *ssk =mptcp_subflow_tcp_sock (subflow); +if (!mptcp_subflow_active (subflow)) +continue ; +/* still data outstanding at TCP level? Don't retransmit. */ if (!tcp_write_queue_empty (ssk))return NULL ;
net/mptcp/protocol.h +4 -2
@@ -196,6 +196,8 @@ struct mptcp_sock {u64 write_seq;u64 ack_seq;u64 rcv_data_fin_seq; +struct sock *last_snd; +int snd_burst;atomic64_t snd_una;unsigned long timer_ival;u32 token;
@@ -473,12 +475,12 @@ static inline bool before64(__u64 seq1, __u64 seq2)void mptcp_diag_subflow_init (struct tcp_ulp_ops *ops); -static inline bool __mptcp_check_fallback (struct mptcp_sock *msk) +static inline bool __mptcp_check_fallback (const struct mptcp_sock *msk) {return test_bit (MPTCP_FALLBACK_DONE , &msk->flags); } -static inline bool mptcp_check_fallback (struct sock *sk) +static inline bool mptcp_check_fallback (const struct sock *sk) {struct mptcp_subflow_context *subflow =mptcp_subflow_ctx (sk);struct mptcp_sock *msk =mptcp_sk (subflow->conn);
Signature · 1 line
2.26.2
Paolo Abeni
maintainerPATCH 12/13 mptcp: call tcp_cleanup_rbuf on subflows
In reply to Paolo AbeniThat is needed to let the subflows announce promptly when new space is available in the receive buffer.
tcp_cleanup_rbuf() is currently a static function, drop the scope modifier and add a declaration in the TCP header.
--- include/net/tcp.h | 2 ++ net/ipv4/tcp.c | 2 +- net/mptcp/protocol.c | 6 ++++++ net/mptcp/subflow.c | 2 ++ 4 files changed, 11 insertions(+), 1 deletion(-)
include/net/tcp.h +2 -0
@@ -1414,6 +1414,8 @@ static inline int tcp_full_space(const struct sock *sk)return tcp_win_from_space (sk,READ_ONCE (sk->sk_rcvbuf)); } +void tcp_cleanup_rbuf (struct sock *sk,int copied); +/* We provision sk_rcvbuf around 200% of sk_rcvlowat. * If 87.5 % (7/8) of the space has been consumed, we want to override * SO_RCVLOWAT constraint, since we are receiving skbs with too small
net/ipv4/tcp.c +1 -1
@@ -1527,7 +1527,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)* calculation of whether or not we must ACK for the sake of * a window update. */ -static void tcp_cleanup_rbuf (struct sock *sk,int copied) +void tcp_cleanup_rbuf (struct sock *sk,int copied) {struct tcp_sock *tp =tcp_sk (sk);bool time_to_ack = false;
net/mptcp/protocol.c +6 -0
@@ -515,6 +515,8 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, }while (more_data_avail); *bytes += moved; +if (moved) +tcp_cleanup_rbuf (ssk, moved);return done; }
@@ -1422,10 +1424,14 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)*/ mptcp_for_each_subflow (msk, subflow) {struct sock *ssk; +bool slow; ssk =mptcp_subflow_tcp_sock (subflow); + slow =lock_sock_fast (ssk);WRITE_ONCE (ssk->sk_rcvbuf, rcvbuf);tcp_sk (ssk)->window_clamp = window_clamp; +tcp_cleanup_rbuf (ssk,1 ); +unlock_sock_fast (ssk, slow); } } }
net/mptcp/subflow.c +2 -0
@@ -823,6 +823,8 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,sk_eat_skb (ssk, skb);if (mptcp_subflow_get_map_offset (subflow) >= subflow->map_data_len) subflow->map_valid =0 ; +if (incr) +tcp_cleanup_rbuf (ssk, incr); }static bool subflow_check_data_avail (struct sock *ssk)
Signature · 1 line
2.26.2
Paolo Abeni
maintainerPATCH 13/13 mptcp: simult flow self-tests
In reply to Paolo AbeniAdd a bunch of test-cases for multiple subflow xmit:
create multiple subflows simulating different links condition via netem and verify that the msk is able to use completely the aggregated bandwidth.
--- tools/testing/selftests/net/mptcp/Makefile | 3 +- .../selftests/net/mptcp/simult_flows.sh | 293 ++++++++++++++++++ 2 files changed, 295 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/net/mptcp/simult_flows.sh
tools/testing/selftests/net/mptcp/Makefile +2 -1
@@ -5,7 +5,8 @@ KSFT_KHDR_INSTALL := 1 CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include -TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh +TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ + simult_flows.sh TEST_GEN_FILES = mptcp_connect pm_nl_ctl
tools/testing/selftests/net/mptcp/simult_flows.sh new file +293 -0
293 lines not on this page · raw message
Signature · 1 line
2.26.2
Paolo Abeni
maintainerRe: [PATCH net-next 11/13] mptcp: allow picking different xmit subflows
In reply to Paolo AbeniOn Fri, 2020-09-11 at 15:52 +0200, Paolo Abeni wrote:
[...]
Quoted 69 lines
net/mptcp/protocol.c +42
-13+#define MPTCP_SEND_BURST_SIZE ((1 << 16) - \ + sizeof(struct tcphdr) - \ + MAX_TCP_OPTION_SPACE - \ + sizeof(struct ipv6hdr) - \ + sizeof(struct frag_hdr)) + +struct subflow_send_info { +struct sock *ssk; +uint64_t ratio; +}; +static struct sock *mptcp_subflow_get_send (struct mptcp_sock *msk,u32 *sndbuf) { +struct subflow_send_info send_info[2 ];struct mptcp_subflow_context *subflow; -struct sock *sk = (struct sock *)msk; -struct sock *backup =NULL ; -bool free; +int i, nr_active =0 ; +int64_t ratio, pace; +struct sock *ssk; -sock_owned_by_me (sk); +sock_owned_by_me ((struct sock *)msk); *sndbuf =0 ;if (!mptcp_ext_cache_refill (msk))return NULL ; -mptcp_for_each_subflow (msk, subflow) { -struct sock *ssk =mptcp_subflow_tcp_sock (subflow); - - free =sk_stream_is_writeable (subflow->tcp_sock); -if (!free) { -mptcp_nospace (msk); +if (__mptcp_check_fallback (msk)) { +if (!msk->first)return NULL ; + *sndbuf = msk->first->sk_sndbuf; +return sk_stream_memory_free (msk->first) ? msk->first :NULL ; + } + +/* re-use last subflow, if the burst allow that */ +if (msk->last_snd && msk->snd_burst >0 && +sk_stream_memory_free (msk->last_snd) && +mptcp_subflow_active (mptcp_subflow_ctx (msk->last_snd))) { +mptcp_for_each_subflow (msk, subflow) { + ssk =mptcp_subflow_tcp_sock (subflow); + *sndbuf =max (tcp_sk (ssk)->snd_wnd, *sndbuf); } +return msk->last_snd; + } + +/* pick the subflow with the lower wmem/wspace ratio */ +for (i =0 ; i <2 ; ++i) { + send_info[i].ssk =NULL ; + send_info[i].ratio =-1 ; + } +mptcp_for_each_subflow (msk, subflow) { + ssk =mptcp_subflow_tcp_sock (subflow); +if (!mptcp_subflow_active (subflow)) +continue ; + nr_active += !subflow->backup; *sndbuf =max (tcp_sk (ssk)->snd_wnd, *sndbuf); -if (subflow->backup) { -if (!backup) - backup = ssk;
net/mptcp/protocol.c static void mptcp_nospace(struct mptcp_sock *msk) · line 1109
Quoted 10 lines
net/mptcp/protocol.c +5
-2+if (!sk_stream_memory_free (subflow->tcp_sock)) +continue ; + pace =READ_ONCE (ssk->sk_pacing_rate); +if (!pace)continue ; - } -return ssk; + ratio = (int64_t )READ_ONCE (ssk->sk_wmem_queued) <<32 / pace;
Kbuild bot on our devel branch just noted that the above division breaks 32 bits build.
I'll fix that in v2.
Cheers,
Paolo
kernel test robot
build botRe: [PATCH net-next 11/13] mptcp: allow picking different xmit subflows
In reply to Paolo AbeniThank you for the patch! Yet something to improve:
Hi Paolo,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on net-next/master]
url: https://github.com/0day-ci/linux/commits/Paolo-Abeni/mptcp-introduce-support-for-real-multipath-xmit/20200912-005157 base: https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git 9984c0bb22dcae688ef8588e2621133850ff49bc config: arm-randconfig-c003-20200911 (attached as .config) compiler: arm-linux-gnueabi-gcc (GCC) 9.3.0
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-9.3.0 make.cross ARCH=arm
If you fix the issue, kindly add following tag as appropriate
All errors (new ones prefixed by >>):
arm-linux-gnueabi-ld: net/mptcp/protocol.o: in function `mptcp_subflow_get_send':
>> net/mptcp/protocol.c:1109: undefined reference to `__aeabi_ldivmod'
# https://github.com/0day-ci/linux/commit/d7f1745bcd6815d03c0fcf621b988118301bc269
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Paolo-Abeni/mptcp-introduce-support-for-real-multipath-xmit/20200912-005157 git checkout d7f1745bcd6815d03c0fcf621b988118301bc269
vim +1109 net/mptcp/protocol.c
1056
1057 static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk,
1058 u32 *sndbuf)
1059 {
1060 struct subflow_send_info send_info[2];
1061 struct mptcp_subflow_context *subflow;
1062 int i, nr_active = 0;
1063 int64_t ratio, pace;
1064 struct sock *ssk;
1065
1066 sock_owned_by_me((struct sock *)msk);
1067
1068 *sndbuf = 0;
1069 if (!mptcp_ext_cache_refill(msk))
1070 return NULL;
1071
1072 if (__mptcp_check_fallback(msk)) {
1073 if (!msk->first)
1074 return NULL;
1075 *sndbuf = msk->first->sk_sndbuf;
1076 return sk_stream_memory_free(msk->first) ? msk->first : NULL;
1077 }
1078
1079 /* re-use last subflow, if the burst allow that */
1080 if (msk->last_snd && msk->snd_burst > 0 &&
1081 sk_stream_memory_free(msk->last_snd) &&
1082 mptcp_subflow_active(mptcp_subflow_ctx(msk->last_snd))) {
1083 mptcp_for_each_subflow(msk, subflow) {
1084 ssk = mptcp_subflow_tcp_sock(subflow);
1085 *sndbuf = max(tcp_sk(ssk)->snd_wnd, *sndbuf);
1086 }
1087 return msk->last_snd;
1088 }
1089
1090 /* pick the subflow with the lower wmem/wspace ratio */
1091 for (i = 0; i < 2; ++i) {
1092 send_info[i].ssk = NULL;
1093 send_info[i].ratio = -1;
1094 }
1095 mptcp_for_each_subflow(msk, subflow) {
1096 ssk = mptcp_subflow_tcp_sock(subflow);
1097 if (!mptcp_subflow_active(subflow))
1098 continue;
1099
1100 nr_active += !subflow->backup;
1101 *sndbuf = max(tcp_sk(ssk)->snd_wnd, *sndbuf);
1102 if (!sk_stream_memory_free(subflow->tcp_sock))
1103 continue;
1104
1105 pace = READ_ONCE(ssk->sk_pacing_rate);
1106 if (!pace)
1107 continue;
1108
> 1109 ratio = (int64_t)READ_ONCE(ssk->sk_wmem_queued) << 32 / pace;
1110 if (ratio < send_info[subflow->backup].ratio) {
1111 send_info[subflow->backup].ssk = ssk;
1112 send_info[subflow->backup].ratio = ratio;
1113 }
1114 }
1115
1116 pr_debug("msk=%p nr_active=%d ssk=%p:%lld backup=%p:%lld",
1117 msk, nr_active, send_info[0].ssk, send_info[0].ratio,
1118 send_info[1].ssk, send_info[1].ratio);
1119
1120 /* pick the best backup if no other subflow is active */
1121 if (!nr_active)
1122 send_info[0].ssk = send_info[1].ssk;
1123
1124 if (send_info[0].ssk) {
1125 msk->last_snd = send_info[0].ssk;
1126 msk->snd_burst = min_t(int, MPTCP_SEND_BURST_SIZE,
1127 sk_stream_wspace(msk->last_snd));
1128 return msk->last_snd;
1129 }
1130 return NULL;
1131 }
1132
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all(a)lists.01.org