BPF redundant scheduler
Subsystems (5)
v3 cover BPF redundant scheduler
v3:
- use new API.
- fix the link failure tests issue mentioned in ("https://patchwork.kernel.org/project/mptcp/cover/[email protected]/").
v2:
- add MPTCP_SUBFLOWS_MAX limit to avoid infinite loops when the scheduler always sets call_again to true.
- track the largest copied amount.
- deal with __mptcp_subflow_push_pending() and the retransmit loop.
- depends on "BPF round-robin scheduler" v14.
v1:
Implements the redundant BPF MPTCP scheduler, which sends all packets redundantly on all available subflows.
Geliang Tang (5):
Squash to "mptcp: add get_subflow wrappers"
mptcp: add __mptcp_sched_get_retrans wrapper
mptcp: add mptcp_sched_get_send wrapper
selftests/bpf: Add bpf_red scheduler
selftests/bpf: Add bpf_red test
net/mptcp/protocol.c | 105 +++++++++++------- net/mptcp/protocol.h | 3 +- net/mptcp/sched.c | 64 ++++++----- net/mptcp/subflow.c | 1 - .../testing/selftests/bpf/prog_tests/mptcp.c | 35 ++++++ .../selftests/bpf/progs/mptcp_bpf_red.c | 36 ++++++ 6 files changed, 175 insertions(+), 69 deletions(-) create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_red.c
Signature · 1 line
2.34.1
PATCH v3 1/5 Squash to "mptcp: add get_subflow wrappers"
'''
mptcp: add __mptcp_sched_get_send wrapper
This patch defines the wrapper __mptcp_sched_get_send(), invoke get_subflow() of msk->sched in it. Use this wrapper instead of using mptcp_subflow_get_send() directly in __mptcp_push_pending().
Set the subflow pointers array in struct mptcp_sched_data before invoking get_subflow(), then it can be used in get_subflow() in the BPF contexts.
Check the subflow scheduled flags in __mptcp_push_pending() to test which subflow or subflows are picked by the scheduler, use them to send data. '''
--- net/mptcp/protocol.c | 72 ++++++++++++++++++++++++-------------------- net/mptcp/protocol.h | 4 +-- net/mptcp/sched.c | 59 +++++++++--------------------------- net/mptcp/subflow.c | 1 - 4 files changed, 55 insertions(+), 81 deletions(-)
net/mptcp/protocol.c +40 -32
@@ -1551,7 +1551,6 @@ void mptcp_check_and_set_pending(struct sock *sk)void __mptcp_push_pending (struct sock *sk,unsigned int flags) { -struct sock *prev_ssk =NULL , *ssk =NULL ;struct mptcp_sock *msk =mptcp_sk (sk);struct mptcp_sendmsg_info info = { .flags = flags,
@@ -1564,45 +1563,49 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags) info.limit = dfrag->data_len; len = dfrag->data_len - dfrag->already_sent;while (len >0 ) { +struct mptcp_subflow_context *subflow; +struct sock *ssk =NULL ;int ret =0 ; +int max =0 ; +int err; - prev_ssk = ssk; - ssk =mptcp_sched_get_send (msk); - -/* First check. If the ssk has changed since -* the last round, release prev_ssk -*/ -if (ssk != prev_ssk && prev_ssk) -mptcp_push_release (prev_ssk, &info); -if (!ssk) + err =__mptcp_sched_get_send (msk); +if (err) goto out; -/* Need to lock the new subflow only if different -* from the previous one, otherwise we are still -* helding the relevant lock -*/ -if (ssk != prev_ssk) -lock_sock (ssk); +mptcp_for_each_subflow (msk, subflow) { +if (READ_ONCE (subflow->scheduled)) { + ssk =mptcp_subflow_tcp_sock (subflow); +if (!ssk) + goto out; - ret =mptcp_sendmsg_frag (sk, ssk, dfrag, &info); -if (ret <=0 ) { -mptcp_push_release (ssk, &info); - goto out; +lock_sock (ssk); + + ret =mptcp_sendmsg_frag (sk, ssk, dfrag, &info); +if (ret <=0 ) { +mptcp_push_release (ssk, &info); + goto out; + } + +if (ret > max) + max = ret; + +mptcp_push_release (ssk, &info); + + msk->last_snd = ssk; +mptcp_subflow_set_scheduled (subflow, false); + } } - info.sent += ret; - copied += ret; - len -= ret; + info.sent += max; + copied += max; + len -= max; -mptcp_update_post_push (msk, dfrag, ret); +mptcp_update_post_push (msk, dfrag, max); }WRITE_ONCE (msk->first_pending,mptcp_send_next (sk)); } -/* at this point we held the socket lock for the last subflow we used */ -if (ssk) -mptcp_push_release (ssk, &info); - out:/* ensure the rtx timer is running */ if (!mptcp_timer_pending (sk))
@@ -1634,7 +1637,7 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)* check for a different subflow usage only after * spooling the first chunk of data */ - xmit_ssk = first ? ssk :mptcp_sched_get_send (mptcp_sk (sk)); + xmit_ssk = first ? ssk :mptcp_subflow_get_send (mptcp_sk (sk));if (!xmit_ssk) goto out;if (xmit_ssk != ssk) {
@@ -2195,12 +2198,17 @@ static void mptcp_timeout_timer(struct timer_list *t)* * A backup subflow is returned only if that is the only kind available. */ -struct sock *mptcp_subflow_get_retrans (struct mptcp_sock *msk) +static struct sock *mptcp_subflow_get_retrans (struct mptcp_sock *msk) {struct sock *backup =NULL , *pick =NULL ;struct mptcp_subflow_context *subflow;int min_stale_count =INT_MAX ; +sock_owned_by_me ((const struct sock *)msk); + +if (__mptcp_check_fallback (msk)) +return NULL ; +mptcp_for_each_subflow (msk, subflow) {struct sock *ssk =mptcp_subflow_tcp_sock (subflow);
@@ -2453,7 +2461,7 @@ static void __mptcp_retrans(struct sock *sk)mptcp_clean_una_wakeup (sk);/* first check ssk: need to kick "stale" logic */ - ssk =mptcp_sched_get_retrans (msk); + ssk =mptcp_subflow_get_retrans (msk); dfrag =mptcp_rtx_head (sk);if (!dfrag) {if (mptcp_data_fin_enabled (msk)) {
@@ -3107,7 +3115,7 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk)return ;if (!sock_owned_by_user (sk)) { -struct sock *xmit_ssk =mptcp_sched_get_send (mptcp_sk (sk)); +struct sock *xmit_ssk =mptcp_subflow_get_send (mptcp_sk (sk));if (xmit_ssk == ssk)__mptcp_subflow_push_pending (sk, ssk);
net/mptcp/protocol.h +1 -3
@@ -632,9 +632,7 @@ void mptcp_release_sched(struct mptcp_sock *msk);void mptcp_subflow_set_scheduled (struct mptcp_subflow_context *subflow,bool scheduled);struct sock *mptcp_subflow_get_send (struct mptcp_sock *msk); -struct sock *mptcp_subflow_get_retrans (struct mptcp_sock *msk); -struct sock *mptcp_sched_get_send (struct mptcp_sock *msk); -struct sock *mptcp_sched_get_retrans (struct mptcp_sock *msk); +int __mptcp_sched_get_send (struct mptcp_sock *msk);static inline bool __mptcp_subflow_active (struct mptcp_subflow_context *subflow) {
net/mptcp/sched.c +14 -45
77 lines not on this page · raw message
net/mptcp/subflow.c +0 -1
@@ -881,7 +881,6 @@ static bool validate_mapping(struct sock *ssk, struct sk_buff *skb) subflow->map_data_len))) {/* Mapping does covers past subflow data, invalid */ dbg_bad_map (subflow, ssn); -return false; }return true; }
Signature · 1 line
2.34.1
PATCH v3 2/5 mptcp: add __mptcp_sched_get_retrans wrapper
In reply to Geliang TangThis patch defines the wrapper __mptcp_sched_get_retrans(), invoke get_subflow() of msk->sched in it. Use this wrapper instead of using mptcp_subflow_get_retrans() directly in __mptcp_retrans().
Check the subflow scheduled flags in __mptcp_retrans() to test which subflow or subflows are picked by the scheduler, use them to send data.
--- net/mptcp/protocol.c | 53 +++++++++++++++++++++++++++----------------- net/mptcp/protocol.h | 2 ++ net/mptcp/sched.c | 25 +++++++++++++++++++++ 3 files changed, 60 insertions(+), 20 deletions(-)
net/mptcp/protocol.c +33 -20
@@ -2198,17 +2198,12 @@ static void mptcp_timeout_timer(struct timer_list *t)* * A backup subflow is returned only if that is the only kind available. */ -static struct sock *mptcp_subflow_get_retrans (struct mptcp_sock *msk) +struct sock *mptcp_subflow_get_retrans (struct mptcp_sock *msk) {struct sock *backup =NULL , *pick =NULL ;struct mptcp_subflow_context *subflow;int min_stale_count =INT_MAX ; -sock_owned_by_me ((const struct sock *)msk); - -if (__mptcp_check_fallback (msk)) -return NULL ; -mptcp_for_each_subflow (msk, subflow) {struct sock *ssk =mptcp_subflow_tcp_sock (subflow);
@@ -2452,16 +2447,17 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)static void __mptcp_retrans (struct sock *sk) {struct mptcp_sock *msk =mptcp_sk (sk); +struct mptcp_subflow_context *subflow;struct mptcp_sendmsg_info info = {};struct mptcp_data_frag *dfrag;size_t copied =0 ;struct sock *ssk; -int ret; +int err;mptcp_clean_una_wakeup (sk);/* first check ssk: need to kick "stale" logic */ - ssk =mptcp_subflow_get_retrans (msk); + err =__mptcp_sched_get_retrans (msk); dfrag =mptcp_rtx_head (sk);if (!dfrag) {if (mptcp_data_fin_enabled (msk)) {
@@ -2480,32 +2476,49 @@ static void __mptcp_retrans(struct sock *sk) goto reset_timer; } -if (!ssk) +if (err) goto reset_timer; -lock_sock (ssk); -/* limit retransmission to the bytes already sent on some subflows */ info.sent =0 ; info.limit =READ_ONCE (msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent;while (info.sent < info.limit) { - ret =mptcp_sendmsg_frag (sk, ssk, dfrag, &info); -if (ret <=0 ) -break ; +int ret =0 ; +int max =0 ; +mptcp_for_each_subflow (msk, subflow) { +if (READ_ONCE (subflow->scheduled)) { + ssk =mptcp_subflow_tcp_sock (subflow); +if (!ssk) + goto reset_timer; + +lock_sock (ssk); + + ret =mptcp_sendmsg_frag (sk, ssk, dfrag, &info); +if (ret <=0 ) +break ; + +if (ret > max) + max = ret; + +tcp_push (ssk,0 , info.mss_now,tcp_sk (ssk)->nonagle, + info.size_goal); + +release_sock (ssk); + + msk->last_snd = ssk; +mptcp_subflow_set_scheduled (subflow, false); + } + }MPTCP_INC_STATS (sock_net (sk),MPTCP_MIB_RETRANSSEGS ); - copied += ret; - info.sent += ret; + copied += max; + info.sent += max; }if (copied) { dfrag->already_sent =max (dfrag->already_sent, info.sent); -tcp_push (ssk,0 , info.mss_now,tcp_sk (ssk)->nonagle, - info.size_goal);WRITE_ONCE (msk->allow_infinite_fallback, false); } -release_sock (ssk); - reset_timer:mptcp_check_and_set_pending (sk);
net/mptcp/protocol.h +2 -0
@@ -632,7 +632,9 @@ void mptcp_release_sched(struct mptcp_sock *msk);void mptcp_subflow_set_scheduled (struct mptcp_subflow_context *subflow,bool scheduled);struct sock *mptcp_subflow_get_send (struct mptcp_sock *msk); +struct sock *mptcp_subflow_get_retrans (struct mptcp_sock *msk);int __mptcp_sched_get_send (struct mptcp_sock *msk); +int __mptcp_sched_get_retrans (struct mptcp_sock *msk);static inline bool __mptcp_subflow_active (struct mptcp_subflow_context *subflow) {
net/mptcp/sched.c +25 -0
@@ -146,3 +146,28 @@ int __mptcp_sched_get_send(struct mptcp_sock *msk)return 0 ; } + +int __mptcp_sched_get_retrans (struct mptcp_sock *msk) +{ +struct mptcp_sched_data data; +struct sock *ssk =NULL ; + +sock_owned_by_me ((const struct sock *)msk); + +/* the following check is moved out of mptcp_subflow_get_retrans */ +if (__mptcp_check_fallback (msk)) +return -EINVAL ; + +if (!msk->sched) { + ssk =mptcp_subflow_get_retrans (msk); +if (!ssk) +return -EINVAL ; +mptcp_subflow_set_scheduled (mptcp_subflow_ctx (ssk), true); +return 0 ; + } + +mptcp_sched_data_init (msk, true, &data); + msk->sched->get_subflow (msk, &data); + +return 0 ; +}
Signature · 1 line
2.34.1
PATCH v3 3/5 mptcp: add mptcp_sched_get_send wrapper
In reply to Geliang TangThis patch defines the wrapper mptcp_sched_get_send(), invoke __mptcp_sched_get_send() in it. Use this wrapper instead of using mptcp_subflow_get_retrans() directly in __mptcp_subflow_push_pending().
--- net/mptcp/protocol.c | 4 ++-- net/mptcp/protocol.h | 1 + net/mptcp/sched.c | 20 ++++++++++++++++++++ 3 files changed, 23 insertions(+), 2 deletions(-)
net/mptcp/protocol.c +2 -2
@@ -1637,7 +1637,7 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)* check for a different subflow usage only after * spooling the first chunk of data */ - xmit_ssk = first ? ssk :mptcp_subflow_get_send (mptcp_sk (sk)); + xmit_ssk = first ? ssk :mptcp_sched_get_send (mptcp_sk (sk));if (!xmit_ssk) goto out;if (xmit_ssk != ssk) {
@@ -3128,7 +3128,7 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk)return ;if (!sock_owned_by_user (sk)) { -struct sock *xmit_ssk =mptcp_subflow_get_send (mptcp_sk (sk)); +struct sock *xmit_ssk =mptcp_sched_get_send (mptcp_sk (sk));if (xmit_ssk == ssk)__mptcp_subflow_push_pending (sk, ssk);
net/mptcp/protocol.h +1 -0
@@ -634,6 +634,7 @@ void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,struct sock *mptcp_subflow_get_send (struct mptcp_sock *msk);struct sock *mptcp_subflow_get_retrans (struct mptcp_sock *msk);int __mptcp_sched_get_send (struct mptcp_sock *msk); +struct sock *mptcp_sched_get_send (struct mptcp_sock *msk);int __mptcp_sched_get_retrans (struct mptcp_sock *msk);static inline bool __mptcp_subflow_active (struct mptcp_subflow_context *subflow)
net/mptcp/sched.c +20 -0
@@ -147,6 +147,26 @@ int __mptcp_sched_get_send(struct mptcp_sock *msk)return 0 ; } +struct sock *mptcp_sched_get_send (struct mptcp_sock *msk) +{ +struct mptcp_subflow_context *subflow; +struct sock *ssk =NULL ; +int err; + + err =__mptcp_sched_get_send (msk); +if (err) +return NULL ; + +mptcp_for_each_subflow (msk, subflow) { +if (READ_ONCE (subflow->scheduled)) { + ssk = subflow->tcp_sock; +break ; + } + } + +return ssk; +} +int __mptcp_sched_get_retrans (struct mptcp_sock *msk) {struct mptcp_sched_data data;
Signature · 1 line
2.34.1
PATCH v3 4/5 selftests/bpf: Add bpf_red scheduler
In reply to Geliang TangThis patch implements the redundant BPF MPTCP scheduler, named bpf_red, which sends all packets redundantly on all available subflows.
--- .../selftests/bpf/progs/mptcp_bpf_red.c | 36 +++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_red.c
tools/testing/selftests/bpf/progs/mptcp_bpf_red.c new file +36 -0
@@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022, SUSE. */ + +#include <linux/bpf.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; + +SEC("struct_ops/mptcp_sched_red_init") +void BPF_PROG (mptcp_sched_red_init ,const struct mptcp_sock *msk) +{ +} + +SEC("struct_ops/mptcp_sched_red_release") +void BPF_PROG (mptcp_sched_red_release ,const struct mptcp_sock *msk) +{ +} + +void BPF_STRUCT_OPS (bpf_red_get_subflow ,const struct mptcp_sock *msk, +struct mptcp_sched_data *data) +{ +for (int i =0 ; i <MPTCP_SUBFLOWS_MAX ; i++) { +if (!data->contexts[i]) +break ; + +mptcp_subflow_set_scheduled (data->contexts[i], true); + } +} + +SEC(".struct_ops") +struct mptcp_sched_ops red = { + .init = (void *)mptcp_sched_red_init, + .release = (void *)mptcp_sched_red_release, + .get_subflow = (void *)bpf_red_get_subflow, + .name ="bpf_red" , +};
Signature · 1 line
2.34.1
PATCH v3 5/5 selftests/bpf: Add bpf_red test
In reply to Geliang TangThis patch adds the redundant BPF MPTCP scheduler test. Use sysctl to set net.mptcp.scheduler to use this sched.
--- .../testing/selftests/bpf/prog_tests/mptcp.c | 35 +++++++++++++++++++ 1 file changed, 35 insertions(+)
tools/testing/selftests/bpf/prog_tests/mptcp.c +35 -0
@@ -9,6 +9,7 @@#include "mptcp_bpf_first.skel.h" #include "mptcp_bpf_bkup.skel.h" #include "mptcp_bpf_rr.skel.h" +#include "mptcp_bpf_red.skel.h" #ifndef TCP_CA_NAME_MAX #define TCP_CA_NAME_MAX 16
@@ -362,6 +363,38 @@ static void test_rr(void)mptcp_bpf_rr__destroy (rr_skel); } +static void test_red (void ) +{ +struct mptcp_bpf_red *red_skel; +int server_fd, client_fd; +struct bpf_link *link; + + red_skel =mptcp_bpf_red__open_and_load (); +if (!ASSERT_OK_PTR (red_skel,"bpf_red__open_and_load" )) +return ; + + link =bpf_map__attach_struct_ops (red_skel->maps.red); +if (!ASSERT_OK_PTR (link,"bpf_map__attach_struct_ops" )) { +mptcp_bpf_red__destroy (red_skel); +return ; + } + +add_veth (); +system ("ip mptcp endpoint add 10.0.1.1 subflow" ); +system ("sysctl -qw net.mptcp.scheduler=bpf_red" ); + server_fd =start_mptcp_server (AF_INET ,NULL ,0 ,0 ); + client_fd =connect_to_fd (server_fd,0 ); + +send_data (server_fd, client_fd); +ASSERT_OK (system ("ss -MOenita | grep '10.0.1.1' | grep -q 'bytes_sent:'" ),"ss" ); + +close (client_fd); +close (server_fd); +cleanup (); +bpf_link__destroy (link); +mptcp_bpf_red__destroy (red_skel); +} +void test_mptcp (void ) {if (test__start_subtest ("base" ))
@@ -372,4 +405,6 @@ void test_mptcp(void)test_bkup ();if (test__start_subtest ("rr" ))test_rr (); +if (test__start_subtest ("red" )) +test_red (); }
Signature · 1 line
2.34.1
Re: selftests/bpf: Add bpf_red test: Tests Results
Hi Geliang,
Thank you for your modifications, that's great!
Our CI did some validations and here is its report:
- {"code":404,"message":
- "Can't find artifacts containing file conclusion.txt"}:
- Task: https://cirrus-ci.com/task/5542041579945984
- Summary: https://api.cirrus-ci.com/v1/artifact/task/5542041579945984/summary/summary.txt
- {"code":404,"message":
- "Can't find artifacts containing file conclusion.txt"}:
- Task: https://cirrus-ci.com/task/6667941486788608
- Summary: https://api.cirrus-ci.com/v1/artifact/task/6667941486788608/summary/summary.txt
Initiator: Patchew Applier
Commits: https://github.com/multipath-tcp/mptcp_net-next/commits/a242888c8f2a
If there are some issues, you can reproduce them using the same environment as the one used by the CI thanks to a docker image, e.g.:
$ cd [kernel source code]
$ docker run -v "${PWD}:${PWD}:rw" -w "${PWD}" --privileged --rm -it \
--pull always mptcp/mptcp-upstream-virtme-docker:latest \
auto-debugFor more details:
https://github.com/multipath-tcp/mptcp-upstream-virtme-docker
Please note that despite all the efforts that have been already done to have a stable tests suite when executed on a public CI like here, it is possible some reported issues are not due to your modifications. Still, do not hesitate to help us improve that ;-)
Cheers,
MPTCP GH Action bot
Bot operated by Matthieu Baerts (Tessares)