- Aug 24, 2021
-
-
Yonglong Li authored
According to the MPTCP_ADD_ADDR_SIGNAL or MPTCP_ADD_ADDR_ECHO flag, build the ADD_ADDR/ADD_ADDR_ECHO option. In mptcp_pm_add_addr_signal(), use opts->addr to save the announced ADD_ADDR or ADD_ADDR_ECHO address. Co-developed-by:
Geliang Tang <geliangtang@gmail.com> Signed-off-by:
-
Yonglong Li authored
Use MPTCP_ADD_ADDR_SIGNAL only for the action of sending ADD_ADDR, and use MPTCP_ADD_ADDR_ECHO only for the action of sending ADD_ADDR echo. Use msk->pm.local to save the announced ADD_ADDR address only, and reuse msk->pm.remote to save the announced ADD_ADDR_ECHO address. To prepare for the next patch. Co-developed-by:
-
Yonglong Li authored
This patch moved the drop_other_suboptions check from mptcp_established_options_add_addr() into mptcp_pm_add_addr_signal(), do it under the PM lock to avoid the race between this check and mptcp_pm_add_addr_signal(). For this, added a new parameter for mptcp_pm_add_addr_signal() to get the drop_other_suboptions value. And drop the other suboptions after the option length check if drop_other_suboptions is true. Additionally, always drop the other suboption for TCP pure ack: that makes both the code simpler and the MPTCP behaviour more consistent. Co-developed-by:
-
- Aug 18, 2021
-
-
Geliang Tang authored
This patch added a new helper mptcp_pm_get_flags_and_ifindex_by_id(), and used it in __mptcp_subflow_connect() to get the flags and ifindex values. Then the two arguments flags and ifindex of __mptcp_subflow_connect() can be dropped. Signed-off-by:
-
- Aug 14, 2021
-
-
Paolo Abeni authored
The msk can use backup subflows to transmit in-sequence data only if there are no other active subflow. On active backup scenario, the MPTCP connection can do forward progress only due to MPTCP retransmissions - rtx can pick backup subflows. This patch introduces a new flag flow MPTCP subflows: if the underlying TCP connection made no progresses for long time, and there are other less problematic subflows available, the given subflow become stale. Stale subflows are not considered active: if all non backup subflows become stale, the MPTCP scheduler can pick backup subflows for plain transmissions. Stale subflows can return in active state, as soon as any reply from the peer is observed. Active backup scenarios can now leverage the available b/w with no restrinction. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/207 Signed-off-by:
-
Paolo Abeni authored
Reorder the data in mptcp_pernet to avoid wasting space with no reasons and constify the access helpers. No functional changes intended. Signed-off-by:
-
Paolo Abeni authored
The PM can close active subflow, e.g. due to ingress RM_ADDR option. Such subflow could carry data still unacked at the MPTCP-level, both in the write and the rtx_queue, which has never reached the other peer. Currently the mptcp-level retransmission will deliver such data, but at a very low rate (at most 1 DSM for each MPTCP rtx interval). We can speed-up the recovery a lot, moving all the unacked in the tcp write_queue, so that it will be pushed again via other subflows, at the speed allowed by them. Also make available the new helper for later patches. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/207 Signed-off-by:
-
Paolo Abeni authored
The current mptcp re-inject strategy is very aggressive, we have mptcp-level retransmissions even on single subflow connection, if the link in-use is lossy. Let's be a little more conservative: we do retransmit only if at least a subflow has write and rtx queue empty. Additionally use the backup subflows only if the active subflows are stale - no progresses in at least an rtx period and ignore stale subflows for rtx timeout update Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/207 Signed-off-by:
-
- Jul 10, 2021
-
-
Paolo Abeni authored
After commit 87952603 ("mptcp: protect the rx path with the msk socket spinlock") the rmem currently used by a given msk is really sk_rmem_alloc - rmem_released. The safety check in mptcp_data_ready() does not take the above in due account, as a result legit incoming data is kept in subflow receive queue with no reason, delaying or blocking MPTCP-level ack generation. This change addresses the issue introducing a new helper to fetch the rmem memory and using it as needed. Additionally add a MIB counter for the exceptional event described above - the peer is misbehaving. Finally, introduce the required annotation when rmem_released is updated. Fixes: 87952603 ("mptcp: protect the rx path with the msk socket spinlock") Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/211 Signed-off-by:
-
- Jun 22, 2021
-
-
Paolo Abeni authored
The current cleanup rbuf tries a bit too hard to avoid acquiring the subflow socket lock. We may end-up delaying the needed ack, or skip acking a blocked subflow. Address the above extending the conditions used to trigger the cleanup to reflect more closely what TCP does and invoking tcp_cleanup_rbuf() on all the active subflows. Note that we can't replicate the exact tests implemented in tcp_cleanup_rbuf(), as MPTCP lacks some of the required info - e.g. ping-pong mode. Signed-off-by:
-
Geliang Tang authored
This patch added a new flag named deny_join_id0 in struct mptcp_options_received. Set it when MP_CAPABLE with the flag MPTCP_CAP_DENYJOIN_ID0 is received. Also add a new flag remote_deny_join_id0 in struct mptcp_pm_data. When the flag deny_join_id0 is set, set this remote_deny_join_id0 flag. In mptcp_pm_create_subflow_or_signal_addr, if the remote_deny_join_id0 flag is set, and the remote address id is zero, stop this connection. Suggested-by:
-
Geliang Tang authored
This patch defined a new flag MPTCP_CAP_DENY_JOIN_ID0 for the third bit, labeled "C" of the MP_CAPABLE option. Add a new flag allow_join_id0 in struct mptcp_out_options. If this flag is set, send out the MP_CAPABLE option with the flag MPTCP_CAP_DENY_JOIN_ID0. Acked-by:
-
Geliang Tang authored
This patch added a new sysctl, named allow_join_initial_addr_port, to control whether allow peers to send join requests to the IP address and port number used by the initial subflow. Suggested-by:
-
Paolo Abeni authored
commit 78962489 ("mptcp: add skeleton to sync msk socket options to subflows") introduced a duplicate declaration of mptcp_setsockopt(), just drop it. Reported-by:
-
Paolo Abeni authored
The msk socket state is currently updated in a few spots without owning the msk socket lock itself. Some of such operations are safe, as they happens before exposing the msk socket to user-space and can't race with other changes. A couple of them, at connect time, can actually race with close() or shutdown(), leaving breaking the socket state machine. This change addresses the issue moving such update under the msk socket lock with the usual: <acquire spinlock> <check sk lock onwers> <ev defer to release_cb> scheme. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/56 Fixes: 8fd73804 ("mptcp: fallback in case of simultaneous connect") Fixes: c3c123d1 ("net: mptcp: don't hang in mptcp_sendmsg() after TCP fallback") Signed-off-by:
-
Paolo Abeni authored
The mentioned cache was introduced to reduce the number of skb allocation in atomic context, but the required complexity is excessive. This change remove the mentioned cache. Signed-off-by:
-
- Jun 21, 2021
-
-
Paolo Abeni authored
When receiving 32 bits DSS ack from the peer, the MPTCP need to expand them to 64 bits value. The current code is buggy WRT detecting 32 bits ack wrap-around: when the wrap-around happens the current unsigned 32 bit ack value is lower than the previous one. Additionally check for possible reverse wrap and make the helper visible, so that we could re-use it for the next patch. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/204 Fixes: cc9d2566 ("mptcp: update per unacked sequence on pkt reception") Reviewed-by:
-
- Jun 18, 2021
-
-
Geliang Tang authored
This patch added a new sysctl, named checksum_enabled, to control whether DSS checksum can be enabled. Acked-by:
-
Paolo Abeni authored
This patch added three new members named data_csum, csum_len and map_csum in struct mptcp_subflow_context, implemented a new function named mptcp_validate_data_checksum(). If the current mapping is valid and csum is enabled traverse the later pending skbs and compute csum incrementally till the whole mapping has been covered. If not enough data is available in the rx queue, return MAPPING_EMPTY - that is, no data. Next subflow_data_ready invocation will trigger again csum computation. When the full DSS is available, validate the csum and return to the caller an appropriate error code, to trigger subflow reset of fallback as required by the RFC. Additionally: - if the csum prevence in the DSS don't match the negotiated value e.g. csum present, but not requested, return invalid mapping to trigger subflow reset. - keep some csum state, to avoid re-compute the csum on the same data when multiple rx queue traversal are required. - clean-up the uncompleted mapping from the receive queue on close, to allow proper subflow disposal Co-developed-by:
-
Geliang Tang authored
This patch added a new member named csum in struct mptcp_options_received. When parsing the MP_CAPABLE with data, if the checksum is enabled, adjust the expected_opsize. If the receiving option length matches the length with the data checksum, get the checksum value and save it in mp_opt->csum. And in mptcp_incoming_options, pass it to mpext->csum. We always parse any csum/nocsum combination and delay the presence check to later code, to allow reset if missing. Additionally, in the TX path, use the newly introduce ext field to avoid MPTCP csum recomputation on TCP retransmission and unneeded csum update on when setting the data fin_flag. Co-developed-by:
-
Geliang Tang authored
This patch added a new flag csum_reqd in struct mptcp_options_received, if the flag MPTCP_CAP_CHECKSUM_REQD is set in the receiving MP_CAPABLE suboption, set this flag. In mptcp_sk_clone and subflow_finish_connect, if the csum_reqd flag is set, enable the msk->csum_enabled flag. Acked-by:
-
Geliang Tang authored
This patch added a new parameter name sk in mptcp_get_options(). Acked-by:
-
Geliang Tang authored
This patch added a new member csum_reqd in struct mptcp_out_options and struct mptcp_subflow_request_sock. Initialized it with the helper function mptcp_is_checksum_enabled(). In mptcp_write_options, if this field is enabled, send out the MP_CAPABLE suboption with the MPTCP_CAP_CHECKSUM_REQD flag. Acked-by:
-
Geliang Tang authored
This patch added a new member named csum in struct mptcp_ext, implemented a new function named mptcp_generate_data_checksum(). Generate the data checksum in mptcp_sendmsg_frag, save it in mpext->csum. Note that we must generate the csum for zero window probe, too. Do the csum update incrementally, to avoid multiple csum computation when the data is appended to existing skb. Note that in a later patch we will skip unneeded csum related operation. Changes not included here to keep the delta small. Co-developed-by:
-
Geliang Tang authored
This patch added a new member named csum_enabled in struct mptcp_sock, used a dummy mptcp_is_checksum_enabled() helper to initialize it. Also added a new member named mptcpi_csum_enabled in struct mptcp_info to expose the csum_enabled flag. Acked-by:
-
- Jun 10, 2021
-
-
Paolo Abeni authored
Currently we rely on the subflow->data_avail field, which is subject to races: ssk1 skb len = 500 DSS(seq=1, len=1000, off=0) # data_avail == MPTCP_SUBFLOW_DATA_AVAIL ssk2 skb len = 500 DSS(seq = 501, len=1000) # data_avail == MPTCP_SUBFLOW_DATA_AVAIL ssk1 skb len = 500 DSS(seq = 1, len=1000, off =500) # still data_avail == MPTCP_SUBFLOW_DATA_AVAIL, # as the skb is covered by a pre-existing map, # which was in-sequence at reception time. Instead we can explicitly check if some has been received in-sequence, propagating the info from __mptcp_move_skbs_from_subflow(). Additionally add the 'ONCE' annotation to the 'data_avail' memory access, as msk will read it outside the subflow socket lock. Fixes: 648ef4b8 ("mptcp: Implement MPTCP receive path") Signed-off-by:
-
- May 28, 2021
-
-
Jianguo Wu authored
We have macro TOKEN_MAX_RETRIES for the number of token generate retries, so using TOKEN_MAX_RETRIES in subflow_check_req(). And rename TOKEN_MAX_RETRIES to MPTCP_TOKEN_MAX_RETRIES as it is now exposed. Fixes: 535fb815 ("mptcp: token: move retry to caller") Reviewed-by:
-
- May 25, 2021
-
-
Davide Caratti authored
when Linux receives an echo-ed ADD_ADDR, it checks the IP address against the list of "announced" addresses. In case of a positive match, the timer that handles retransmissions is stopped regardless of the 'Address Id' in the received packet: this behaviour does not comply with RFC8684 3.4.1. Fix it by validating the 'Address Id' in received echo-ed ADD_ADDRs. Tested using packetdrill, with the following captured output: unpatched kernel: Out <...> Flags [.], ack 1, win 256, options [mptcp add-addr v1 id 1 198.51.100.2 hmac 0xfd2e62517888fe29,mptcp dss ack 3007449509], length 0 In <...> Flags [.], ack 1, win 257, options [mptcp add-addr v1-echo id 1 1.2.3.4,mptcp dss ack 3013740213], length 0 Out <...> Flags [.], ack 1, win 256, options [mptcp add-addr v1 id 1 198.51.100.2 hmac 0xfd2e62517888fe29,mptcp dss ack 3007449509], length 0 In <...> Flags [.], ack 1, win 257, options [mptcp add-addr v1-echo id 90 198.51.100.2,mptcp dss ack 3013740213], length 0 ^^^ retransmission is stopped here, but 'Address Id' is 90 patched kernel: Out <...> Flags [.], ack 1, win 256, options [mptcp add-addr v1 id 1 198.51.100.2 hmac 0x1cf372d59e05f4b8,mptcp dss ack 3007449509], length 0 In <...> Flags [.], ack 1, win 257, options [mptcp add-addr v1-echo id 1 1.2.3.4,mptcp dss ack 1672384568], length 0 Out <...> Flags [.], ack 1, win 256, options [mptcp add-addr v1 id 1 198.51.100.2 hmac 0x1cf372d59e05f4b8,mptcp dss ack 3007449509], length 0 In <...> Flags [.], ack 1, win 257, options [mptcp add-addr v1-echo id 90 198.51.100.2,mptcp dss ack 1672384568], length 0 Out <...> Flags [.], ack 1, win 256, options [mptcp add-addr v1 id 1 198.51.100.2 hmac 0x1cf372d59e05f4b8,mptcp dss ack 3007449509], length 0 In <...> Flags [.], ack 1, win 257, options [mptcp add-addr v1-echo id 1 198.51.100.2,mptcp dss ack 1672384568], length 0 ^^^ retransmission is stopped here, only when both 'Address Id' and 'IP Address' match Fixes: 00cfd77b ("mptcp: retransmit ADD_ADDR when timeout") Signed-off-by: -
Paolo Abeni authored
We can't use tcp_set_congestion_control() on an mptcp socket, as such function can end-up accessing a tcp-specific field - prior_ssthresh - causing an OOB access. To allow propagating the correct ca algo on subflow, cache the ca name at initialization time. Additionally avoid overriding the user-selected CA (if any) at clone time. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/182 Fixes: aa1fbd94 ("mptcp: sockopt: add TCP_CONGESTION and TCP_INFO") Acked-by:
-
- Apr 17, 2021
-
-
Geliang Tang authored
This patch moved the static function mptcp_subflow_active to protocol.h as an inline one. Acked-by:
-
- Apr 16, 2021
-
-
Florian Westphal authored
Paolo Abeni suggested to avoid re-syncing new subflows because they inherit options from listener. In case options were set on listener but are not set on mptcp-socket there is no need to do any synchronisation for new subflows. This change sets sockopt_seq of new mptcp sockets to the seq of the mptcp listener sock. Subflow sequence is set to the embedded tcp listener sk. Add a comment explaing why sk_state is involved in sockopt_seq generation. Acked-by:
-
Florian Westphal authored
Handle following cases: 1. setsockopt is called with multiple subflows. Change might have to be mirrored to all of them. This is done directly in process context/setsockopt call. 2. Outgoing subflow is created after one or several setsockopt() calls have been made. Old setsockopt changes should be synced to the new socket. 3. Incoming subflow, after setsockopt call(s). Cases 2 and 3 are handled right after the join list is spliced to the conn list. Not all sockopt values can be just be copied by value, some require helper calls. Those can acquire socket lock (which can sleep). If the join->conn list splicing is done from preemptible context, synchronization can be done right away, otherwise its deferred to work queue. Acked-by:
-
Paolo Abeni authored
The MPTCP sockopt implementation is going to be much more big and complex soon. Let's move it to a different source file. No functional change intended. Signed-off-by:
-
- Apr 07, 2021
-
-
Geliang Tang authored
Since the type of the address family in struct mptcp_options_received became sa_family_t, we should set AF_INET/AF_INET6 to it, instead of using MPTCP_ADDR_IPVERSION_4/6. Signed-off-by:
-
Geliang Tang authored
This patch added a new struct mptcp_addr_info member addr in struct mptcp_options_received, and dropped the original family, addr_id, addr, addr6 and port fields in it. Then we can pass the parameter mp_opt.addr directly to mptcp_pm_add_addr_received and mptcp_pm_add_addr_echoed. Since the port number became big-endian now, use htons to convert the incoming port number to it. Also use ntohs to convert it when passing it to add_addr_generate_hmac or printing it out. Co-developed-by:
-
Geliang Tang authored
Since the family field was added in struct mptcp_out_options, no need to use OPTION_MPTCP_ADD_ADDR6 to identify the IPv6 address. Drop it. Signed-off-by:
-
Geliang Tang authored
This patch moved the mptcp_addr_info struct from protocol.h to mptcp.h, added a new struct mptcp_addr_info member addr in struct mptcp_out_options, and dropped the original addr, addr6, addr_id and port fields in it. Then we can use opts->addr to get the adding address from PM directly using mptcp_pm_add_addr_signal. Since the port number became big-endian now, use ntohs to convert it before sending it out with the ADD_ADDR suboption. Also convert it when passing it to add_addr_generate_hmac or printing it out. Co-developed-by:
-
Geliang Tang authored
This patch moved the flags and ifindex fields from struct mptcp_addr_info to struct mptcp_pm_addr_entry. Add the flags and ifindex values as two new parameters to __mptcp_subflow_connect. In mptcp_pm_create_subflow_or_signal_addr, pass the local address entry's flags and ifindex fields to __mptcp_subflow_connect. In mptcp_pm_nl_add_addr_received, just pass two zeros to it. Signed-off-by:
-
- Apr 02, 2021
-
-
Florian Westphal authored
The MPTCP reset option allows to carry a mptcp-specific error code that provides more information on the nature of a connection reset. Reset option data received gets stored in the subflow context so it can be sent to userspace via the 'subflow closed' netlink event. When a subflow is closed, the desired error code that should be sent to the peer is also placed in the subflow context structure. If a reset is sent before subflow establishment could complete, e.g. on HMAC failure during an MP_JOIN operation, the mptcp skb extension is used to store the reset information. Signed-off-by:
-
- Mar 26, 2021
-
-
Geliang Tang authored
Since mptcp_pm_nl_add_addr_send_ack is now used for both ADD_ADDR and RM_ADDR cases, rename it to mptcp_pm_nl_addr_send_ack. Signed-off-by:
-