Select Git revision
Search by author
- Any Author
- authors
-
Angus Ainslie
angus.ainslie
-
Eric Kuzmenko
eric.kuzmenko
-
Evangelos Ribeiro Tzaras
evangelos.tzaras
-
Francois Techene
francois.techene
-
Guido Gunther
guido.gunther
-
JC Staudt
jcstaudt
-
Jonathon Hall
jonathon.hall
-
Julian Sparber
julian.sparber
-
Martin Kepplinger
martin.kepplinger
-
Mohammed Sadiq
mohammed.sadiq
-
Richard Kolla
richard.kolla
-
Sam Hewitt sam.hewitt
-
Sebastian Krzyszkowiak
sebastian.krzyszkowiak
- 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:
-
Yonglong Li authored
ADD_ADDR shares pm.addr_signal with RM_ADDR, so after RM_ADDR/ADD_ADDR has done, we should not clean ADD_ADDR/RM_ADDR's addr_signal. Co-developed-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 19, 2021
-
-
Matthieu Baerts authored
If directly after an MP_CAPABLE 3WHS, the client receives an ADD_ADDR with HMAC from the server, it is enough to switch to a "fully established" mode because it has received more MPTCP options. It was then OK to enable the "fully_established" flag on the MPTCP socket. Still, best to check if the ADD_ADDR looks valid by looking if it contains an HMAC (no 'echo' bit). If an ADD_ADDR echo is received while we are not in "fully established" mode, it is strange and then we should not switch to this mode now. But that is not enough. On one hand, the path-manager has be notified the state has changed. On the other hand, the "fully_established" flag on the subflow socket should be turned on as well not to re-send the MP_CAPABLE 3rd ACK content with the next ACK. Fixes: 84dfe367 ("mptcp: send out dedicated ADD_ADDR packet") Signed-off-by:
-
Paolo Abeni authored
The endpoint cleanup path is prone to a memory leak, as reported by syzkaller: BUG: memory leak unreferenced object 0xffff88810680ea00 (size 64): comm "syz-executor.6", pid 6191, jiffies 4295756280 (age 24.138s) hex dump (first 32 bytes): 58 75 7d 3c 80 88 ff ff 22 01 00 00 00 00 ad de Xu}<...."....... 01 00 02 00 00 00 00 00 ac 1e 00 07 00 00 00 00 ................ backtrace: [<0000000072a9f72a>] kmalloc include/linux/slab.h:591 [inline] [<0000000072a9f72a>] mptcp_nl_cmd_add_addr+0x287/0x9f0 net/mptcp/pm_netlink.c:1170 [<00000000f6e931bf>] genl_family_rcv_msg_doit.isra.0+0x225/0x340 net/netlink/genetlink.c:731 [<00000000f1504a2c>] genl_family_rcv_msg net/netlink/genetlink.c:775 [inline] [<00000000f1504a2c>] genl_rcv_msg+0x341/0x5b0 net/netlink/genetlink.c:792 [<0000000097e76f6a>] netlink_rcv_skb+0x148/0x430 net/netlink/af_netlink.c:2504 [<00000000ceefa2b8>] genl_rcv+0x24/0x40 net/netlink/genetlink.c:803 [<000000008ff91aec>] netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline] [<000000008ff91aec>] netlink_unicast+0x537/0x750 net/netlink/af_netlink.c:1340 [<0000000041682c35>] netlink_sendmsg+0x846/0xd80 net/netlink/af_netlink.c:1929 [<00000000df3aa8e7>] sock_sendmsg_nosec net/socket.c:704 [inline] [<00000000df3aa8e7>] sock_sendmsg+0x14e/0x190 net/socket.c:724 [<000000002154c54c>] ____sys_sendmsg+0x709/0x870 net/socket.c:2403 [<000000001aab01d7>] ___sys_sendmsg+0xff/0x170 net/socket.c:2457 [<00000000fa3b1446>] __sys_sendmsg+0xe5/0x1b0 net/socket.c:2486 [<00000000db2ee9c7>] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [<00000000db2ee9c7>] do_syscall_64+0x38/0x90 arch/x86/entry/common.c:80 [<000000005873517d>] entry_SYSCALL_64_after_hwframe+0x44/0xae We should not require an allocation to cleanup stuff. Rework the code a bit so that the additional RCU work is no more needed. Fixes: 1729cf18 ("mptcp: create the listening socket for new port") Signed-off-by:
-
- Aug 18, 2021
-
-
Geliang Tang authored
In mptcp_pm_nl_add_addr_received(), fill a temporary allocate array of all local address corresponding to the fullmesh endpoint. If such array is empty, keep the current behavior. Elsewhere loop on such array and create a subflow for each local address towards the given remote address Suggested-by:
-
Geliang Tang authored
This patch added and managed a new per endpoint flag, named MPTCP_PM_ADDR_FLAG_FULLMESH. In mptcp_pm_create_subflow_or_signal_addr(), if such flag is set, instead of: remote_address((struct sock_common *)sk, &remote); fill a temporary allocated array of all known remote address. After releaseing the pm lock loop on such array and create a subflow for each remote address from the given local. Note that the we could still use an array even for non 'fullmesh' endpoint: with a single entry corresponding to the primary MPC subflow remote address. Suggested-by: -
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 parsed incoming backup flag is not propagated to the subflow itself, the client may end-up using it to send data. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/191 Signed-off-by:
-
Paolo Abeni authored
This allows monitoring exceptional events like active backup scenarios. Signed-off-by:
-
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:
-
Paolo Abeni authored
As reported by Maxim, we have a lot of MPTCP-level retransmissions when multilple links with different latencies are in use. This patch refactor the mptcp-level timeout accounting so that the maximum of all the active subflow timeout is used. To avoid traversing the subflow list multiple times, the update is performed inside the packet scheduler. Additionally clean-up a bit timeout handling. Signed-off-by:
-
- Aug 03, 2021
-
-
Geliang Tang authored
kfree_rcu() had been removed from pm_netlink.c, so this rcu field in struct mptcp_pm_addr_entry became useless. Let's drop it. Signed-off-by:
-
- Jul 13, 2021
-
-
Yajun Deng authored
It has 'if (err >0 )' statement in nlmsg_unicast(), so use nlmsg_unicast() instead of netlink_unicast(), this looks more concise. v2: remove the change in netfilter. 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:
-
Jianguo Wu authored
If check_fully_established() causes a subflow reset, it should not continue to process the packet in tcp_data_queue(). Add a return value to mptcp_incoming_options(), and return false if a subflow has been reset, else return true. Then drop the packet in tcp_data_queue()/tcp_rcv_state_process() if mptcp_incoming_options() return false. Fixes: d5824847 ("mptcp: fix fallback for MP_JOIN subflows") Signed-off-by:
-
Jianguo Wu authored
Lots of "TCP: tcp_fin: Impossible, sk->sk_state=7" in client side when doing stress testing using wrk and webfsd. There are at least two cases may trigger this warning: 1.mptcp is in syncookie, and server recv MP_JOIN SYN request, in subflow_check_req(), the mptcp_can_accept_new_subflow() return false, so subflow_init_req_cookie_join_save() isn't called, i.e. not store the data present in the MP_JOIN syn request and the random nonce in hash table - join_entries[], but still send synack. When recv 3rd-ack, mptcp_token_join_cookie_init_state() will return false, and 3rd-ack is dropped, then if mptcp conn is closed by client, client will send a DATA_FIN and a MPTCP FIN, the DATA_FIN doesn't have MP_CAPABLE or MP_JOIN, so mptcp_subflow_init_cookie_req() will return 0, and pass the cookie check, MP_JOIN request is fallback to normal TCP. Server will send a TCP FIN if closed, in client side, when process TCP FIN, it will do reset, the code path is: tcp_data_queue()->mptcp_incoming_options() ->check_fully_established()->mptcp_subflow_reset(). mptcp_subflow_reset() will set sock state to TCP_CLOSE, so tcp_fin will hit TCP_CLOSE, and print the warning. 2.mptcp is in syncookie, and server recv 3rd-ack, in mptcp_subflow_init_cookie_req(), mptcp_can_accept_new_subflow() return false, and subflow_req->mp_join is not set to 1, so in subflow_syn_recv_sock() will not reset the MP_JOIN subflow, but fallback to normal TCP, and then the same thing happens when server will send a TCP FIN if closed. For case1, subflow_check_req() return -EPERM, then tcp_conn_request() will drop MP_JOIN SYN. For case2, let subflow_syn_recv_sock() call mptcp_can_accept_new_subflow(), and do fatal fallback, send reset. Fixes: 9466a1cc ("mptcp: enable JOIN requests even if cookies are in use") Signed-off-by: -
Jianguo Wu authored
In subflow_check_req(), if subflow sport is mismatch, will put msk, destroy token, and destruct req, then return -EPERM, which can be done by subflow_req_destructor() via: tcp_conn_request() |--__reqsk_free() |--subflow_req_destructor() So we should remove these redundant code, otherwise will call tcp_v4_reqsk_destructor() twice, and may double free inet_rsk(req)->ireq_opt. Fixes: 5bc56388 ("mptcp: add port number check for MP_JOIN") Signed-off-by: -
Jianguo Wu authored
I did stress test with wrk[1] and webfsd[2] with the assistance of mptcp-tools[3]: Server side: ./use_mptcp.sh webfsd -4 -R /tmp/ -p 8099 Client side: ./use_mptcp.sh wrk -c 200 -d 30 -t 4 http://192.168.174.129:8099/ and got the following warning message: [ 55.552626] TCP: request_sock_subflow: Possible SYN flooding on port 8099. Sending cookies. Check SNMP counters. [ 55.553024] ------------[ cut here ]------------ [ 55.553027] WARNING: CPU: 0 PID: 10 at net/core/flow_dissector.c:984 __skb_flow_dissect+0x280/0x1650 ... [ 55.553117] CPU: 0 PID: 10 Comm: ksoftirqd/0 Not tainted 5.12.0+ #18 [ 55.553121] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 02/27/2020 [ 55.553124] RIP: 0010:__skb_flow_dissect+0x280/0x1650 ... [ 55.553133] RSP: 0018:ffffb79580087770 EFLAGS: 00010246 [ 55.553137] RAX: 0000000000000000 RBX: ffffffff8ddb58e0 RCX: ffffb79580087888 [ 55.553139] RDX: ffffffff8ddb58e0 RSI: ffff8f7e4652b600 RDI: 0000000000000000 [ 55.553141] RBP: ffffb79580087858 R08: 0000000000000000 R09: 0000000000000008 [ 55.553143] R10: 000000008c622965 R11: 00000000d3313a5b R12: ffff8f7e4652b600 [ 55.553146] R13: ffff8f7e465c9062 R14: 0000000000000000 R15: ffffb79580087888 [ 55.553149] FS: 0000000000000000(0000) GS:ffff8f7f75e00000(0000) knlGS:0000000000000000 [ 55.553152] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 55.553154] CR2: 00007f73d1d19000 CR3: 0000000135e10004 CR4: 00000000003706f0 [ 55.553160] Call Trace: [ 55.553166] ? __sha256_final+0x67/0xd0 [ 55.553173] ? sha256+0x7e/0xa0 [ 55.553177] __skb_get_hash+0x57/0x210 [ 55.553182] subflow_init_req_cookie_join_save+0xac/0xc0 [ 55.553189] subflow_check_req+0x474/0x550 [ 55.553195] ? ip_route_output_key_hash+0x67/0x90 [ 55.553200] ? xfrm_lookup_route+0x1d/0xa0 [ 55.553207] subflow_v4_route_req+0x8e/0xd0 [ 55.553212] tcp_conn_request+0x31e/0xab0 [ 55.553218] ? selinux_socket_sock_rcv_skb+0x116/0x210 [ 55.553224] ? tcp_rcv_state_process+0x179/0x6d0 [ 55.553229] tcp_rcv_state_process+0x179/0x6d0 [ 55.553235] tcp_v4_do_rcv+0xaf/0x220 [ 55.553239] tcp_v4_rcv+0xce4/0xd80 [ 55.553243] ? ip_route_input_rcu+0x246/0x260 [ 55.553248] ip_protocol_deliver_rcu+0x35/0x1b0 [ 55.553253] ip_local_deliver_finish+0x44/0x50 [ 55.553258] ip_local_deliver+0x6c/0x110 [ 55.553262] ? ip_rcv_finish_core.isra.19+0x5a/0x400 [ 55.553267] ip_rcv+0xd1/0xe0 ... After debugging, I found in __skb_flow_dissect(), skb->dev and skb->sk are both NULL, then net is NULL, and trigger WARN_ON_ONCE(!net), actually net is always NULL in this code path, as skb->dev is set to NULL in tcp_v4_rcv(), and skb->sk is never set. Code snippet in __skb_flow_dissect() that trigger warning: 975 if (skb) { 976 if (!net) { 977 if (skb->dev) 978 net = dev_net(skb->dev); 979 else if (skb->sk) 980 net = sock_net(skb->sk); 981 } 982 } 983 984 WARN_ON_ONCE(!net); So, using seq and transport header derived hash. [1] https://github.com/wg/wrk [2] https://github.com/ourway/webfsd [3] https://github.com/pabeni/mptcp-tools Fixes: 9466a1cc ("mptcp: enable JOIN requests even if cookies are in use") Suggested-by:
-
- Jul 01, 2021
-
-
Yangbo Lu authored
Since PTP virtual clock support is added, there can be several PTP virtual clocks based on one PTP physical clock for timestamping. This patch is to extend SO_TIMESTAMPING API to support PHC (PTP Hardware Clock) binding by adding a new flag SOF_TIMESTAMPING_BIND_PHC. When PTP virtual clocks are in use, user space can configure to bind one for timestamping, but PTP physical clock is not supported and not needed to bind. This patch is preparation for timestamp conversion from raw timestamp to a specific PTP virtual clock time in core net. Signed-off-by:
-
Yangbo Lu authored
Split timestamping handling into a new function mptcp_setsockopt_sol_socket_timestamping(). This is preparation for extending SO_TIMESTAMPING for PHC binding, since optval will no longer be integer. Signed-off-by:
-
- Jun 29, 2021
-
-
Alexander Aring authored
This patch introduces a function wrapper to call the sk_error_report callback. That will prepare to add additional handling whenever sk_error_report is called, for example to trace socket errors. Signed-off-by:
-
- Jun 28, 2021
-
-
Matthieu Baerts authored
Dan Carpenter reported an issue introduced in commit fde56eea ("mptcp: refine mptcp_cleanup_rbuf") where a new boolean (ack_pending) is masked with 0x9. This is not the intention to ignore values by using a boolean. This variable should not have a 'bool' type: we should keep the 'u8' to allow this comparison. Fixes: fde56eea ("mptcp: refine mptcp_cleanup_rbuf") Reported-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
Account this exceptional events for better introspection. Signed-off-by:
-
Paolo Abeni authored
Currently we check the msk state to avoid enqueuing new skbs at msk shutdown time. Such test is racy - as we can't acquire the msk socket lock - and useless, as the caller already checked the subflow field 'disposable', covering the same scenario in a race free manner - read and updated under the ssk socket lock. Signed-off-by:
-
Paolo Abeni authored
If we don't flush entirely the receive queue, we need set again such bit later. We can simply avoid clearing it. Signed-off-by:
-
Paolo Abeni authored
There are a bunch of callsite where the ssk socket lock is acquired using the full-blown version eligible for the fast variant. Let's move to the latter. 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
The current implementation of 32 bit DSN expansion is buggy. After the previous patch, we can simply reuse the newly introduced helper to do the expansion safely. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/120 Fixes: 648ef4b8 ("mptcp: Implement MPTCP receive path") Reviewed-by:
-
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:
-