add bpf_stale scheduler
Subsystems (5)
cover add bpf_stale scheduler
This patchset adds the new bpf_stale scheduler. Use sk_storage to save the stale map instead of using subflow->stale flag to manage it.
Geliang Tang (3):
Squash to "bpf: Add bpf_mptcp_sched_ops"
selftests/bpf: Add bpf_stale scheduler
selftests/bpf: Add bpf_stale test
net/mptcp/bpf.c | 3 - .../testing/selftests/bpf/prog_tests/mptcp.c | 38 +++++ .../selftests/bpf/progs/mptcp_bpf_stale.c | 155 ++++++++++++++++++ 3 files changed, 193 insertions(+), 3 deletions(-) create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_stale.c
Signature · 1 line
2.35.3
PATCH 1/3 Squash to "bpf: Add bpf_mptcp_sched_ops"
No need to change subflow->stale bit-filed now, so drop the writing access of it.
--- net/mptcp/bpf.c | 3 --- 1 file changed, 3 deletions(-)
net/mptcp/bpf.c +0 -3
@@ -52,9 +52,6 @@ static int bpf_mptcp_sched_btf_struct_access(struct bpf_verifier_log *log,case offsetof(struct mptcp_subflow_context , scheduled): end = offsetofend(struct mptcp_subflow_context, scheduled);break ; - case offsetofend(struct mptcp_subflow_context, map_csum_len): - end = offsetof(struct mptcp_subflow_context , data_avail); -break ;case offsetof(struct mptcp_subflow_context , avg_pacing_rate): end = offsetofend(struct mptcp_subflow_context, avg_pacing_rate);break ;
Signature · 1 line
2.35.3
Mat Martineau
maintainerRe: [PATCH mptcp-next 1/3] Squash to "bpf: Add bpf_mptcp_sched_ops"
Quoted 7 lines · Geliang Tang
No need to change
subflow->stalebit-filed now, so drop the writing access of it.Signed-off-by Geliang Tang <[email protected]>---
net/mptcp/bpf.c| 3 ---1 file changed, 3 deletions(-)
This looks ok to squash, thanks Geliang.
- Mat
Quoted 20 lines
net/mptcp/bpf.c +0
-3@@ -52,9 +52,6 @@ static int bpf_mptcp_sched_btf_struct_access(struct bpf_verifier_log *log,case offsetof(struct mptcp_subflow_context , scheduled): end = offsetofend(struct mptcp_subflow_context, scheduled);break ; - case offsetofend(struct mptcp_subflow_context, map_csum_len): - end = offsetof(struct mptcp_subflow_context , data_avail); -break ;case offsetof(struct mptcp_subflow_context , avg_pacing_rate): end = offsetofend(struct mptcp_subflow_context, avg_pacing_rate);break ;Signature · 1 line
2.35.3
Re: [PATCH mptcp-next 1/3] Squash to "bpf: Add bpf_mptcp_sched_ops"
In reply to Geliang TangHi Geliang,
Quoted 2 lines · Geliang Tang
No need to change
subflow->stalebit-filed now, so drop the writing access of it.
Just to be sure, do I still need to apply this patch that is no longer part of the v2 series?
Cheers,
Matt
Quoted 19 lines
Signed-off-by Geliang Tang <[email protected]>--- net/mptcp/bpf.c | 3 --- 1 file changed, 3 deletions(-)net/mptcp/bpf.c +0
-3@@ -52,9 +52,6 @@ static int bpf_mptcp_sched_btf_struct_access(struct bpf_verifier_log *log,case offsetof(struct mptcp_subflow_context , scheduled): end = offsetofend(struct mptcp_subflow_context, scheduled);break ; - case offsetofend(struct mptcp_subflow_context, map_csum_len): - end = offsetof(struct mptcp_subflow_context , data_avail); -break ;case offsetof(struct mptcp_subflow_context , avg_pacing_rate): end = offsetofend(struct mptcp_subflow_context, avg_pacing_rate);break ;
Signature · 2 lines
Tessares | Belgium | Hybrid Access Solutions www.tessares.net
Re: [PATCH mptcp-next 1/3] Squash to "bpf: Add bpf_mptcp_sched_ops"
Quoted 8 lines · Matthieu Baerts
Hi Geliang,
Quoted 2 lines · Geliang Tang
No need to change
subflow->stalebit-filed now, so drop the writing access of it.Just to be sure, do I still need to apply this patch that is no longer part of the v2 series?
Yes, this patch is still needed. Please apply it to the export branch.
Thanks,
-Geliang
Quoted 27 lines
Cheers,
MattQuoted 19 lines
Signed-off-by Geliang Tang <[email protected]>--- net/mptcp/bpf.c | 3 --- 1 file changed, 3 deletions(-)net/mptcp/bpf.c +0
-3@@ -52,9 +52,6 @@ static int bpf_mptcp_sched_btf_struct_access(struct bpf_verifier_log *log,case offsetof(struct mptcp_subflow_context , scheduled): end = offsetofend(struct mptcp_subflow_context, scheduled);break ; - case offsetofend(struct mptcp_subflow_context, map_csum_len): - end = offsetof(struct mptcp_subflow_context , data_avail); -break ;case offsetof(struct mptcp_subflow_context , avg_pacing_rate): end = offsetofend(struct mptcp_subflow_context, avg_pacing_rate);break ;Signature · 2 lines
Tessares | Belgium | Hybrid Access Solutions www.tessares.net
Re: [PATCH mptcp-next 1/3] Squash to "bpf: Add bpf_mptcp_sched_ops"
Hi Geliang, Mat,
Quoted 9 lines · Geliang Tang
Quoted 6 lines · Matthieu Baerts
Quoted 2 lines · Geliang Tang
No need to change
subflow->stalebit-filed now, so drop the writing access of it.Just to be sure, do I still need to apply this patch that is no longer part of the v2 series?
Yes, this patch is still needed. Please apply it to the export branch.
Thank you for the confirmation, the patch and the review!
Now in our tree:
New patches for t/upstream:
- e8eec68a01f0: "squashed" patch 1/3 in "bpf: Add bpf_mptcp_sched_ops"
- Results: e54740d33eef..49d27f1d2549 (export)
Tests are now in progress:
https://cirrus-ci.com/github/multipath-tcp/mptcp_net-next/export/20230804T122556
Cheers,
Matt
Signature · 2 lines
Tessares | Belgium | Hybrid Access Solutions www.tessares.net
PATCH 2/3 selftests/bpf: Add bpf_stale scheduler
In reply to Geliang TangThis patch implements the setting a subflow as stale/unstale in BPF MPTCP scheduler, named bpf_stale. The staled subflow will be added into a stale map in sk_storage. Two helper mptcp_subflow_set_stale() and mptcp_subflow_unstale() are added. The subflow will be set as stale in bpf_stale_data_init() and will be checked in bpf_stale_get_subflow().
--- .../selftests/bpf/progs/mptcp_bpf_stale.c | 155 ++++++++++++++++++ 1 file changed, 155 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_stale.c
tools/testing/selftests/bpf/progs/mptcp_bpf_stale.c new file +155 -0
@@ -0,0 +1,155 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023, SUSE. */ + +#include <linux/bpf.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; + +struct mptcp_stale_storage { +__u8 nr; +struct mptcp_subflow_context *stale[MPTCP_SUBFLOWS_MAX ]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct mptcp_stale_storage); +} mptcp_stale_map SEC(".maps"); + +static void mptcp_subflow_set_stale (struct mptcp_stale_storage *storage, +struct mptcp_subflow_context *subflow) +{ +for (int i =0 ; i < storage->nr && i <MPTCP_SUBFLOWS_MAX ; i++) { +if (storage->stale[i] == subflow) +return ; + } + +if (storage->nr <MPTCP_SUBFLOWS_MAX -1 ) + storage->stale[storage->nr++] = subflow; +} + +static void mptcp_subflow_unstale (struct mptcp_stale_storage *storage, +struct mptcp_subflow_context *subflow) +{ +for (int i =0 ; i < storage->nr && i <MPTCP_SUBFLOWS_MAX ; i++) { +if (storage->stale[i] == subflow) { +for (int j = i; j <MPTCP_SUBFLOWS_MAX -1 ; j++) { +if (!storage->stale[j +1 ]) +break ; + storage->stale[j] = storage->stale[j +1 ]; + storage->stale[j +1 ] =NULL ; + } + storage->nr--; +return ; + } + } +} + +static bool mptcp_subflow_is_stale (struct mptcp_stale_storage *storage, +struct mptcp_subflow_context *subflow) +{ +for (int i =0 ; i < storage->nr && i <MPTCP_SUBFLOWS_MAX ; i++) { +if (storage->stale[i] == subflow) +return true; + } + +return false; +} + +static bool mptcp_subflow_is_active (struct mptcp_sched_data *data, +struct mptcp_subflow_context *stale) +{ +for (int i =0 ; i < data->subflows && i <MPTCP_SUBFLOWS_MAX ; i++) { +struct mptcp_subflow_context *subflow; + + subflow =mptcp_subflow_ctx_by_pos (data, i); +if (!subflow) +break ; +if (subflow == stale) +return true; + } + +return false; +} + +SEC("struct_ops/mptcp_sched_stale_init") +void BPF_PROG (mptcp_sched_stale_init ,struct mptcp_sock *msk) +{ +} + +SEC("struct_ops/mptcp_sched_stale_release") +void BPF_PROG (mptcp_sched_stale_release ,struct mptcp_sock *msk) +{ +} + +void BPF_STRUCT_OPS (bpf_stale_data_init ,struct mptcp_sock *msk, +struct mptcp_sched_data *data) +{ +struct mptcp_subflow_context *subflow; +struct mptcp_stale_storage *storage; + +mptcp_sched_data_set_contexts (msk, data); + + storage =bpf_sk_storage_get (&mptcp_stale_map, msk,0 , +BPF_LOCAL_STORAGE_GET_F_CREATE ); +if (!storage) +return ; + +for (int i =0 ; i < storage->nr && i <MPTCP_SUBFLOWS_MAX ; i++) { +if (!mptcp_subflow_is_active (data, storage->stale[i])) +mptcp_subflow_unstale (storage, storage->stale[i]); + } + + subflow =mptcp_subflow_ctx_by_pos (data,0 ); +if (subflow) { +mptcp_subflow_set_stale (storage, subflow); +mptcp_subflow_unstale (storage, subflow); + } + + subflow =mptcp_subflow_ctx_by_pos (data,1 ); +if (subflow) { +mptcp_subflow_set_stale (storage, subflow); +mptcp_subflow_unstale (storage, subflow); +mptcp_subflow_set_stale (storage, subflow); + } +} + +int BPF_STRUCT_OPS (bpf_stale_get_subflow ,struct mptcp_sock *msk, +const struct mptcp_sched_data *data) +{ +struct mptcp_stale_storage *storage; +int nr =-1 ; + + storage =bpf_sk_storage_get (&mptcp_stale_map, msk,0 , +BPF_LOCAL_STORAGE_GET_F_CREATE ); +if (!storage) +return -1 ; + +for (int i =0 ; i < data->subflows && i <MPTCP_SUBFLOWS_MAX ; i++) { +struct mptcp_subflow_context *subflow; + + subflow =mptcp_subflow_ctx_by_pos (data, i); +if (!subflow) +break ; + +if (mptcp_subflow_is_stale (storage, subflow)) +continue ; + + nr = i; + } + +if (nr !=-1 ) +mptcp_subflow_set_scheduled (mptcp_subflow_ctx_by_pos (data, nr), true); +return 0 ; +} + +SEC(".struct_ops") +struct mptcp_sched_ops stale = { + .init = (void *)mptcp_sched_stale_init, + .release = (void *)mptcp_sched_stale_release, + .data_init = (void *)bpf_stale_data_init, + .get_subflow = (void *)bpf_stale_get_subflow, + .name ="bpf_stale" , +};
Signature · 1 line
2.35.3
Mat Martineau
maintainerRe: [PATCH mptcp-next 2/3] selftests/bpf: Add bpf_stale scheduler
Quoted 19 lines · Geliang Tang
This patch implements the setting a subflow as stale/unstale in BPF MPTCP scheduler, named
bpf_stale. The staled subflow will be added into a stale map insk_storage. Two helpermptcp_subflow_set_stale()andmptcp_subflow_unstale()are added. The subflow will be set as stale inbpf_stale_data_init()and will be checked inbpf_stale_get_subflow().Signed-off-by Geliang Tang <[email protected]>---
.../selftests/bpf/progs/mptcp_bpf_stale.c| 155 ++++++++++++++++++1 file changed, 155 insertions(+)create mode 100644
tools/testing/selftests/bpf/progs/mptcp_bpf_stale.ctools/testing/selftests/bpf/progs/mptcp_bpf_stale.c new file +1
-0@@ -0,0 +1,155 @@ +// SPDX-License-Identifier: GPL-2.0
tools/testing/selftests/bpf/progs/mptcp_bpf_stale.c line 11
Quoted 10 lines
tools/testing/selftests/bpf/progs/mptcp_bpf_stale.c new file +10
-0+/* Copyright (c) 2023, SUSE. */ + +#include <linux/bpf.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; + +struct mptcp_stale_storage { +__u8 nr; +struct mptcp_subflow_context *stale[MPTCP_SUBFLOWS_MAX ];
Hi Geliang -
How about storing an array of u32 subflow_id values instead? That way there's no chance we have old/invalid pointers stored when subflows are removed.
I realize we're only comparing against these subflow pointers and not dereferencing them, but scheduler developers will be looking at these test programs as examples and the subflow_id would be a better fit as example code.
Thanks,
Mat
Quoted 149 lines
tools/testing/selftests/bpf/progs/mptcp_bpf_stale.c new file +144
-0+}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct mptcp_stale_storage); +} mptcp_stale_map SEC(".maps"); + +static void mptcp_subflow_set_stale (struct mptcp_stale_storage *storage, +struct mptcp_subflow_context *subflow) +{ +for (int i =0 ; i < storage->nr && i <MPTCP_SUBFLOWS_MAX ; i++) { +if (storage->stale[i] == subflow) +return ; + } + +if (storage->nr <MPTCP_SUBFLOWS_MAX -1 ) + storage->stale[storage->nr++] = subflow; +} + +static void mptcp_subflow_unstale (struct mptcp_stale_storage *storage, +struct mptcp_subflow_context *subflow) +{ +for (int i =0 ; i < storage->nr && i <MPTCP_SUBFLOWS_MAX ; i++) { +if (storage->stale[i] == subflow) { +for (int j = i; j <MPTCP_SUBFLOWS_MAX -1 ; j++) { +if (!storage->stale[j +1 ]) +break ; + storage->stale[j] = storage->stale[j +1 ]; + storage->stale[j +1 ] =NULL ; + } + storage->nr--; +return ; + } + } +} + +static bool mptcp_subflow_is_stale (struct mptcp_stale_storage *storage, +struct mptcp_subflow_context *subflow) +{ +for (int i =0 ; i < storage->nr && i <MPTCP_SUBFLOWS_MAX ; i++) { +if (storage->stale[i] == subflow) +return true; + } + +return false; +} + +static bool mptcp_subflow_is_active (struct mptcp_sched_data *data, +struct mptcp_subflow_context *stale) +{ +for (int i =0 ; i < data->subflows && i <MPTCP_SUBFLOWS_MAX ; i++) { +struct mptcp_subflow_context *subflow; + + subflow =mptcp_subflow_ctx_by_pos (data, i); +if (!subflow) +break ; +if (subflow == stale) +return true; + } + +return false; +} + +SEC("struct_ops/mptcp_sched_stale_init") +void BPF_PROG (mptcp_sched_stale_init ,struct mptcp_sock *msk) +{ +} + +SEC("struct_ops/mptcp_sched_stale_release") +void BPF_PROG (mptcp_sched_stale_release ,struct mptcp_sock *msk) +{ +} + +void BPF_STRUCT_OPS (bpf_stale_data_init ,struct mptcp_sock *msk, +struct mptcp_sched_data *data) +{ +struct mptcp_subflow_context *subflow; +struct mptcp_stale_storage *storage; + +mptcp_sched_data_set_contexts (msk, data); + + storage =bpf_sk_storage_get (&mptcp_stale_map, msk,0 , +BPF_LOCAL_STORAGE_GET_F_CREATE ); +if (!storage) +return ; + +for (int i =0 ; i < storage->nr && i <MPTCP_SUBFLOWS_MAX ; i++) { +if (!mptcp_subflow_is_active (data, storage->stale[i])) +mptcp_subflow_unstale (storage, storage->stale[i]); + } + + subflow =mptcp_subflow_ctx_by_pos (data,0 ); +if (subflow) { +mptcp_subflow_set_stale (storage, subflow); +mptcp_subflow_unstale (storage, subflow); + } + + subflow =mptcp_subflow_ctx_by_pos (data,1 ); +if (subflow) { +mptcp_subflow_set_stale (storage, subflow); +mptcp_subflow_unstale (storage, subflow); +mptcp_subflow_set_stale (storage, subflow); + } +} + +int BPF_STRUCT_OPS (bpf_stale_get_subflow ,struct mptcp_sock *msk, +const struct mptcp_sched_data *data) +{ +struct mptcp_stale_storage *storage; +int nr =-1 ; + + storage =bpf_sk_storage_get (&mptcp_stale_map, msk,0 , +BPF_LOCAL_STORAGE_GET_F_CREATE ); +if (!storage) +return -1 ; + +for (int i =0 ; i < data->subflows && i <MPTCP_SUBFLOWS_MAX ; i++) { +struct mptcp_subflow_context *subflow; + + subflow =mptcp_subflow_ctx_by_pos (data, i); +if (!subflow) +break ; + +if (mptcp_subflow_is_stale (storage, subflow)) +continue ; + + nr = i; + } + +if (nr !=-1 ) +mptcp_subflow_set_scheduled (mptcp_subflow_ctx_by_pos (data, nr), true); +return 0 ; +} + +SEC(".struct_ops") +struct mptcp_sched_ops stale = { + .init = (void *)mptcp_sched_stale_init, + .release = (void *)mptcp_sched_stale_release, + .data_init = (void *)bpf_stale_data_init, + .get_subflow = (void *)bpf_stale_get_subflow, + .name ="bpf_stale" , +};Signature · 1 line
2.35.3
PATCH 3/3 selftests/bpf: Add bpf_stale test
In reply to Geliang TangThis patch adds the bpf_stale scheduler test: test_stale(). Use sysctl to set net.mptcp.scheduler to use this sched. Add two veth net devices to simulate the multiple addresses case. Use 'ip mptcp endpoint' command to add the new endpoint ADDR_2 to PM netlink. Send data and check bytes_sent of 'ss' output after it to make sure the data has been only sent on ADDR_1 since ADDR_2 is set as stale.
--- .../testing/selftests/bpf/prog_tests/mptcp.c | 38 +++++++++++++++++++ 1 file changed, 38 insertions(+)
tools/testing/selftests/bpf/prog_tests/mptcp.c +38 -0
@@ -12,6 +12,7 @@#include "mptcp_bpf_rr.skel.h" #include "mptcp_bpf_red.skel.h" #include "mptcp_bpf_burst.skel.h" +#include "mptcp_bpf_stale.skel.h" char NS_TEST [32 ];
@@ -524,6 +525,41 @@ static void test_burst(void)mptcp_bpf_burst__destroy (burst_skel); } +static void test_stale (void ) +{ +struct mptcp_bpf_stale *stale_skel; +int server_fd, client_fd; +struct nstoken *nstoken; +struct bpf_link *link; + + stale_skel =mptcp_bpf_stale__open_and_load (); +if (!ASSERT_OK_PTR (stale_skel,"bpf_stale__open_and_load" )) +return ; + + link =bpf_map__attach_struct_ops (stale_skel->maps.stale); +if (!ASSERT_OK_PTR (link,"bpf_map__attach_struct_ops" )) { +mptcp_bpf_stale__destroy (stale_skel); +return ; + } + + nstoken =sched_init ("subflow" ,"bpf_stale" ); +if (!ASSERT_OK_PTR (nstoken,"sched_init:bpf_stale" )) + goto fail; + server_fd =start_mptcp_server (AF_INET ,ADDR_1 ,PORT_1 ,0 ); + client_fd =connect_to_fd (server_fd,0 ); + +send_data (server_fd, client_fd,"bpf_stale" ); +ASSERT_OK (has_bytes_sent (ADDR_1 ),"has_bytes_sent addr_1" ); +ASSERT_GT (has_bytes_sent (ADDR_2 ),0 ,"has_bytes_sent addr_2" ); + +close (client_fd); +close (server_fd); +fail: +cleanup_netns (nstoken); +bpf_link__destroy (link); +mptcp_bpf_stale__destroy (stale_skel); +} +void test_mptcp (void ) {if (test__start_subtest ("base" ))
@@ -540,4 +576,6 @@ void test_mptcp(void)test_red ();if (test__start_subtest ("burst" ))test_burst (); +if (test__start_subtest ("stale" )) +test_stale (); }
Signature · 1 line
2.35.3
Re: selftests/bpf: Add bpf_stale test: Tests Results
Hi Geliang,
Thank you for your modifications, that's great!
Our CI did some validations and here is its report:
- KVM Validation: normal (except selftest_mptcp_join):
- Success! ✅:
- Task: https://cirrus-ci.com/task/6597383929200640
- Summary: https://api.cirrus-ci.com/v1/artifact/task/6597383929200640/summary/summary.txt
- KVM Validation: normal (only selftest_mptcp_join):
- Success! ✅:
- Task: https://cirrus-ci.com/task/4767796580581376
- Summary: https://api.cirrus-ci.com/v1/artifact/task/4767796580581376/summary/summary.txt
- KVM Validation: debug (only selftest_mptcp_join):
- Success! ✅:
- Task: https://cirrus-ci.com/task/5330746534002688
- Summary: https://api.cirrus-ci.com/v1/artifact/task/5330746534002688/summary/summary.txt
- KVM Validation: debug (except selftest_mptcp_join):
- Success! ✅:
- Task: https://cirrus-ci.com/task/5893696487424000
- Summary: https://api.cirrus-ci.com/v1/artifact/task/5893696487424000/summary/summary.txt
Initiator: Patchew Applier
Commits: https://github.com/multipath-tcp/mptcp_net-next/commits/b56b7cd37f92
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)