- Linux-kselftest-mirror - lists.linaro.org

[PATCH] ksm_tests: Skip hugepage test when Transparent Hugepages are disabled

by Li Wang

Some systems (e.g. minimal or real-time kernels) may not enable Transparent Hugepages (THP), causing MADV_HUGEPAGE to return EINVAL. This patch introduces a runtime check using the existing THP sysfs interface and skips the hugepage merging test (`-H`) when THP is not available. To avoid those failures: # ----------------------------- # running ./ksm_tests -H -s 100 # ----------------------------- # ksm_tests: MADV_HUGEPAGE: Invalid argument # [FAIL] not ok 1 ksm_tests -H -s 100 # exit=2 # -------------------- # running ./khugepaged # -------------------- # Reading PMD pagesize failed# [FAIL] not ok 1 khugepaged # exit=1 # -------------------- # running ./soft-dirty # -------------------- # TAP version 13 # 1..15 # ok 1 Test test_simple # ok 2 Test test_vma_reuse dirty bit of allocated page # ok 3 Test test_vma_reuse dirty bit of reused address page # Bail out! Reading PMD pagesize failed# Planned tests != run tests (15 != 3) # # Totals: pass:3 fail:0 xfail:0 xpass:0 skip:0 error:0 # [FAIL] not ok 1 soft-dirty # exit=1 # SUMMARY: PASS=0 SKIP=0 FAIL=1 # ------------------- # running ./migration # ------------------- # TAP version 13 # 1..3 # # Starting 3 tests from 1 test cases. # # RUN migration.private_anon ... # # OK migration.private_anon # ok 1 migration.private_anon # # RUN migration.shared_anon ... # # OK migration.shared_anon # ok 2 migration.shared_anon # # RUN migration.private_anon_thp ... # # migration.c:196:private_anon_thp:Expected madvise(ptr, TWOMEG, MADV_HUGEPAGE) (-1) == 0 (0) # # private_anon_thp: Test terminated by assertion # # FAIL migration.private_anon_thp # not ok 3 migration.private_anon_thp # # FAILED: 2 / 3 tests passed. # # Totals: pass:2 fail:1 xfail:0 xpass:0 skip:0 error:0 # [FAIL] not ok 1 migration # exit=1 Signed-off-by: Li Wang <liwang(a)redhat.com> Cc: Aruna Ramakrishna <aruna.ramakrishna(a)oracle.com> Cc: Bagas Sanjaya <bagasdotme(a)gmail.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Joey Gouly <joey.gouly(a)arm.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Keith Lucas <keith.lucas(a)oracle.com> Cc: Ryan Roberts <ryan.roberts(a)arm.com> Cc: Shuah Khan <shuah(a)kernel.org> --- tools/testing/selftests/mm/khugepaged.c | 5 +++++ tools/testing/selftests/mm/ksm_tests.c | 6 ++++++ tools/testing/selftests/mm/migration.c | 8 ++++++++ tools/testing/selftests/mm/soft-dirty.c | 9 ++++++++- tools/testing/selftests/mm/thp_settings.c | 11 +++++++++++ tools/testing/selftests/mm/thp_settings.h | 2 ++ 6 files changed, 40 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/khugepaged.c b/tools/testing/selftests/mm/khugepaged.c index 8a4d34cce36b..6822eb7ea58e 100644 --- a/tools/testing/selftests/mm/khugepaged.c +++ b/tools/testing/selftests/mm/khugepaged.c @@ -1190,6 +1190,11 @@ int main(int argc, char **argv) .read_ahead_kb = 0, }; + if (!thp_is_enabled()) { + printf("Transparent Hugepages not available\n"); + return KSFT_SKIP; + } + parse_test_type(argc, argv); setbuf(stdout, NULL); diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c index dcdd5bb20f3d..1fb2263faa8d 100644 --- a/tools/testing/selftests/mm/ksm_tests.c +++ b/tools/testing/selftests/mm/ksm_tests.c @@ -15,6 +15,7 @@ #include "../kselftest.h" #include <include/vdso/time64.h> #include "vm_util.h" +#include "thp_settings.h" #define KSM_SYSFS_PATH "/sys/kernel/mm/ksm/" #define KSM_FP(s) (KSM_SYSFS_PATH s) @@ -555,6 +556,11 @@ static int ksm_merge_hugepages_time(int merge_type, int mapping, int prot, unsigned long scan_time_ns; int pagemap_fd, n_normal_pages, n_huge_pages; + if (!thp_is_enabled()) { + printf("Transparent Hugepages not available\n"); + return KSFT_SKIP; + } + map_size *= MB; size_t len = map_size; diff --git a/tools/testing/selftests/mm/migration.c b/tools/testing/selftests/mm/migration.c index 1e3a595fbf01..a306f8bab087 100644 --- a/tools/testing/selftests/mm/migration.c +++ b/tools/testing/selftests/mm/migration.c @@ -5,6 +5,8 @@ */ #include "../kselftest_harness.h" +#include "thp_settings.h" + #include <strings.h> #include <pthread.h> #include <numa.h> @@ -185,6 +187,9 @@ TEST_F_TIMEOUT(migration, private_anon_thp, 2*RUNTIME) uint64_t *ptr; int i; + if (!thp_is_enabled()) + SKIP(return, "Transparent Hugepages not available"); + if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0) SKIP(return, "Not enough threads or NUMA nodes available"); @@ -214,6 +219,9 @@ TEST_F_TIMEOUT(migration, shared_anon_thp, 2*RUNTIME) uint64_t *ptr; int i; + if (!thp_is_enabled()) + SKIP(return, "Transparent Hugepages not available"); + if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0) SKIP(return, "Not enough threads or NUMA nodes available"); diff --git a/tools/testing/selftests/mm/soft-dirty.c b/tools/testing/selftests/mm/soft-dirty.c index 8e1462ce0532..72d8ded87756 100644 --- a/tools/testing/selftests/mm/soft-dirty.c +++ b/tools/testing/selftests/mm/soft-dirty.c @@ -6,8 +6,10 @@ #include <stdint.h> #include <malloc.h> #include <sys/mman.h> + #include "../kselftest.h" #include "vm_util.h" +#include "thp_settings.h" #define PAGEMAP_FILE_PATH "/proc/self/pagemap" #define TEST_ITERATIONS 10000 @@ -78,8 +80,13 @@ static void test_hugepage(int pagemap_fd, int pagesize) { char *map; int i, ret; - size_t hpage_len = read_pmd_pagesize(); + if (!thp_is_enabled()) { + printf("Skipping test: Transparent Hugepages not available\n"); + return KSFT_SKIP; + } + + size_t hpage_len = read_pmd_pagesize(); if (!hpage_len) ksft_exit_fail_msg("Reading PMD pagesize failed"); diff --git a/tools/testing/selftests/mm/thp_settings.c b/tools/testing/selftests/mm/thp_settings.c index ad872af1c81a..bad60ac52874 100644 --- a/tools/testing/selftests/mm/thp_settings.c +++ b/tools/testing/selftests/mm/thp_settings.c @@ -381,3 +381,14 @@ unsigned long thp_shmem_supported_orders(void) { return __thp_supported_orders(true); } + +bool thp_is_enabled(void) +{ + if (access(THP_SYSFS, F_OK) != 0) + return false; + + int mode = thp_read_string("enabled", thp_enabled_strings); + + /* THP is considered enabled if it's either "always" or "madvise" */ + return mode == 1 || mode == 3; +} diff --git a/tools/testing/selftests/mm/thp_settings.h b/tools/testing/selftests/mm/thp_settings.h index fc131d23d593..6c07f70beee9 100644 --- a/tools/testing/selftests/mm/thp_settings.h +++ b/tools/testing/selftests/mm/thp_settings.h @@ -84,4 +84,6 @@ void thp_set_read_ahead_path(char *path); unsigned long thp_supported_orders(void); unsigned long thp_shmem_supported_orders(void); +bool thp_is_enabled(void); + #endif /* __THP_SETTINGS_H__ */ -- 2.49.0

5 months, 3 weeks

3
3
0 0

[PATCH v8 net-next 00/15] AccECN protocol patch series

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find the v8 AccECN protocol patch series, which covers the core functionality of Accurate ECN, AccECN negotiation, AccECN TCP options, and AccECN failure handling. The Accurate ECN draft can be found in https://datatracker.ietf.org/doc/html/draft-ietf-tcpm-accurate-ecn-28 This patch series is part of the full AccECN patch series, which is available at https://github.com/L4STeam/linux-net-next/commits/upstream_l4steam/ v8 (10-Jun-2025) - Add new helper function tcp_ecn_received_counters_payload() in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Set opts->num_sack_blocks=0 to avoid potential undefined value in #8 (Paolo Abeni <pabeni(a)redhat.com>) - Reset leftover_size to 2 once leftover_bytes is used in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_opt_demand_min() in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_saw_opt_fail_recv() in #11 (Paolo Abeni <pabeni(a)redhat.com>) - Update tcp_options_fit_accecn() to avoid using recursion in #14 (Paolo Abeni <pabeni(a)redhat.com>) v7 (14-May-2025) - Modify group sizes of tcp_sock_write_txrx and tcp_sock_write_rx in #3 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Fix the issue in #4 and #5 where the RFC3168 ECN behavior in tcp_ecn_send() is changed (Paolo Abeni <pabeni(a)redhat.com>) - Modify group size of tcp_sock_write_txrx in #4 and #6 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Update commit message for #9 to explain the increase in tcp_sock_write_rx group size - Modify group size of tcp_sock_write_tx in #10 based on pahole results v6 (09-May-2025) - Add #3 to utilize exisintg holes of tcp_sock_write_txrx group for later patches (#4, #9, #10) with new u8 members (Paolo Abeni <pabeni(a)redhat.com>) - Add pahole outcomes before and after commit in #4, #5, #6, #9, #10, #15 (Paolo Abeni <pabeni(a)redhat.com>) - Define new helper function tcp_send_ack_reflect_ect() for sending ACK with reflected ECT in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add comments for function tcp_ecn_rcv_synack() in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add enum/define to be used by sysctl_tcp_ecn in #5, sysctl_tcp_ecn_option in #9, and sysctl_tcp_ecn_option_beacon in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move accecn_fail_mode and saw_accecn_opt in #5 and #11 to use exisintg holes of tcp_sock (Paolo Abeni <pabeni(a)redhat.com>) - Change data type of new members of tcp_request_sock and move them to the end of struct in #5 and #11 (Paolo Abeni <pabeni(a)redhat.com>) - Move new members of tcp_info to the end of struct in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Merge previous #7 into #9 (Paolo Abeni <pabeni(a)redhat.com>) - Mask ecnfield with INET_ECN_MASK to remove WARN_ONCE in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Reduce the indentation levels for reabability in #9 and #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move delivered_ecn_bytes to the RX group in #9, accecn_opt_tstamp to the TX group in #10, pkts_acked_ewma to the RX group in #15 (Paolo Abeni <pabeni(a)redhat.com>) - Add changes in Documentation/networking/net_cachelines/tcp_sock.rst for new tcp_sock members in #3, #5, #6, #9, #10, #15 v5 (22-Apr-2025) - Further fix for 32-bit ARM alignment in tcp.c (Simon Horman <horms(a)kernel.org>) v4 (18-Apr-2025) - Fix 32-bit ARM assertion for alignment requirement (Simon Horman <horms(a)kernel.org>) v3 (14-Apr-2025) - Fix patch apply issue in v2 (Jakub Kicinski <kuba(a)kernel.org>) v2 (18-Mar-2025) - Add one missing patch from the previous AccECN protocol preparation patch series to this patch series. Best regards, Chia-Yu Chia-Yu Chang (3): tcp: reorganize tcp_sock_write_txrx group for variables later tcp: accecn: AccECN option failure handling tcp: accecn: try to fit AccECN option with SACK Ilpo Järvinen (12): tcp: reorganize SYN ECN code tcp: fast path functions later tcp: AccECN core tcp: accecn: AccECN negotiation tcp: accecn: add AccECN rx byte counters tcp: accecn: AccECN needs to know delivered bytes tcp: sack option handling improvements tcp: accecn: AccECN option tcp: accecn: AccECN option send control tcp: accecn: AccECN option ceb/cep heuristic tcp: accecn: AccECN ACE field multi-wrap heuristic tcp: try to avoid safer when ACKs are thinned .../networking/net_cachelines/tcp_sock.rst | 14 + include/linux/tcp.h | 34 +- include/net/netns/ipv4.h | 2 + include/net/tcp.h | 225 ++++++- include/uapi/linux/tcp.h | 7 + net/ipv4/syncookies.c | 3 + net/ipv4/sysctl_net_ipv4.c | 19 + net/ipv4/tcp.c | 30 +- net/ipv4/tcp_input.c | 611 +++++++++++++++++- net/ipv4/tcp_ipv4.c | 7 +- net/ipv4/tcp_minisocks.c | 91 ++- net/ipv4/tcp_output.c | 303 ++++++++- net/ipv6/syncookies.c | 1 + net/ipv6/tcp_ipv6.c | 1 + 14 files changed, 1250 insertions(+), 98 deletions(-) -- 2.34.1

5 months, 3 weeks

4
22
0 0

[PATCH net-next 0/2] selftests: drv-net: stats: use skip instead of xfail

by Jakub Kicinski

Alex posted support for configuring pause frames in fbnic. This flipped the pause stats test from xfail to fail. Because CI considered xfail as pass it now flags the test as failing. This shouldn't happen. Also we currently report pause and FEC tests as passing on virtio which doesn't make sense. Jakub Kicinski (2): selftests: drv-net: stats: fix pylint issues selftests: drv-net: stats: use skip instead of xfail for unsupported features tools/testing/selftests/drivers/net/stats.py | 45 +++++++++++++------- 1 file changed, 30 insertions(+), 15 deletions(-) -- 2.49.0

5 months, 3 weeks

2
3
0 0

[PATCH v3] rust: kunit: use crate-level mapping for `c_void`

by Jesung Yang

Remove `use core::ffi::c_void`, which shadows `kernel::ffi::c_void` brought in via `use crate::prelude::*`, to maintain consistency and centralize the abstraction. Since `kernel::ffi::c_void` is a straightforward re-export of `core::ffi::c_void`, both are functionally equivalent. However, using `kernel::ffi::c_void` improves consistency across the kernel's Rust code and provides a unified reference point in case the definition ever needs to change, even if such a change is unlikely. Reviewed-by: Benno Lossin <lossin(a)kernel.org> Signed-off-by: Jesung Yang <y.j3ms.n(a)gmail.com> Link: https://rust-for-linux.zulipchat.com/#narrow/channel/288089/topic/x/near/52… --- Changes in v3: - Rebase on a3b2347343e0 - Remove the explicit import of `kernel::ffi::c_void` - Reword the commit message accordingly - Link to v2: https://lore.kernel.org/rust-for-linux/20250528155147.2793921-1-y.j3ms.n@gm… Changes in v2: - Add "Link" tag to the related discussion on Zulip - Reword the commit message to clarify `kernel::ffi::c_void` is a re-export - Link to v1: https://lore.kernel.org/rust-for-linux/20250526162429.1114862-1-y.j3ms.n@gm… --- rust/kernel/kunit.rs | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/rust/kernel/kunit.rs b/rust/kernel/kunit.rs index 4b8cdcb21e77..603330f247c7 100644 --- a/rust/kernel/kunit.rs +++ b/rust/kernel/kunit.rs @@ -7,7 +7,7 @@ //! Reference: <https://docs.kernel.org/dev-tools/kunit/index.html> use crate::prelude::*; -use core::{ffi::c_void, fmt}; +use core::fmt; /// Prints a KUnit error-level message. /// base-commit: a3b2347343e077e81d3c169f32c9b2cb1364f4cc -- 2.39.5

5 months, 3 weeks

2
2
0 0

[PATCH v3 0/4] tools/nolibc: MIPS: entrypoint cleanups and N32/N64 ABIs

by Thomas Weißschuh

Introduce support for the N32 and N64 ABIs. As preparation, the entrypoint is first simplified significantly. Thanks to Maciej for all the valuable information. Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- Changes in v3: - Rebase onto latest nolibc-next - Link to v2: https://lore.kernel.org/r/20250225-nolibc-mips-n32-v2-0-664b47d87fa0@weisss… Changes in v2: - Clean up entrypoint first - Annotate #endifs - Link to v1: https://lore.kernel.org/r/20250212-nolibc-mips-n32-v1-1-6892e58d1321@weisss… --- Thomas Weißschuh (4): tools/nolibc: MIPS: drop $gp setup tools/nolibc: MIPS: drop manual stack pointer alignment tools/nolibc: MIPS: drop noreorder option tools/nolibc: MIPS: add support for N64 and N32 ABIs tools/include/nolibc/arch-mips.h | 117 +++++++++++++++++++------ tools/testing/selftests/nolibc/Makefile.nolibc | 26 ++++++ tools/testing/selftests/nolibc/run-tests.sh | 2 +- 3 files changed, 117 insertions(+), 28 deletions(-) --- base-commit: eb135311083100b6590a7545618cd9760d896a86 change-id: 20231105-nolibc-mips-n32-234901bd910d Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

5 months, 3 weeks

1
4
0 0

[PATCH 0/4] selftests/nolibc: integrate with kselftests

by Thomas Weißschuh

Hook up nolibc-test with the kselftests framework. This enables CI systems and developers to easily execute the tests. Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- Thomas Weißschuh (4): selftests/nolibc: drop implicit defconfig executions selftests/nolibc: split out CFLAGS logic selftests/nolibc: rename Makefile selftests/nolibc: integrate with kselftests tools/testing/selftests/Makefile | 1 + tools/testing/selftests/nolibc/Makefile | 346 +----------------------- tools/testing/selftests/nolibc/Makefile.include | 10 + tools/testing/selftests/nolibc/Makefile.nolibc | 340 +++++++++++++++++++++++ tools/testing/selftests/nolibc/run-tests.sh | 2 +- 5 files changed, 363 insertions(+), 336 deletions(-) --- base-commit: d7161bd24e41eee5a3cca5bd8caaf1afdf9120c9 change-id: 20250616-nolibc-selftests-39a774708272 Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

5 months, 3 weeks

2
9
0 0

[PATCH net-next RFC] selftests: net: add netpoll basic functionality test

by Breno Leitao

Add a basic selftest for the netpoll polling mechanism, specifically targeting the netpoll poll() side. The test creates a scenario where network transmission is running at maximum sppend, and netpoll needs to poll the NIC. This is achieved by: 1. Configuring a single RX/TX queue to create contention 2. Generating background traffic to saturate the interface 3. Sending netconsole messages to trigger netpoll polling 4. Using dynamic netconsole targets via configfs The test validates a critical netpoll code path by monitoring traffic flow and ensuring netpoll_poll_dev() is called when the normal TX path is blocked. Perf probing confirms this test successfully triggers netpoll_poll_dev() in typical test runs. This addresses a gap in netpoll test coverage for a path that is tricky for the network stack. Signed-off-by: Breno Leitao <leitao(a)debian.org> --- Sending as an RFC for your appreciation, but it dpends on [1] which is stil under review. Once [1] lands, I will send this officially. Link: https://lore.kernel.org/all/20250611-netdevsim_stat-v1-0-c11b657d96bf@debia… [1] --- tools/testing/selftests/drivers/net/Makefile | 1 + .../testing/selftests/drivers/net/netpoll_basic.py | 201 +++++++++++++++++++++ 2 files changed, 202 insertions(+) diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index be780bcb73a3b..70d6e3a920b7f 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -15,6 +15,7 @@ TEST_PROGS := \ netcons_fragmented_msg.sh \ netcons_overflow.sh \ netcons_sysdata.sh \ + netpoll_basic.py \ ping.py \ queues.py \ stats.py \ diff --git a/tools/testing/selftests/drivers/net/netpoll_basic.py b/tools/testing/selftests/drivers/net/netpoll_basic.py new file mode 100755 index 0000000000000..8abdfb2b1eb6e --- /dev/null +++ b/tools/testing/selftests/drivers/net/netpoll_basic.py @@ -0,0 +1,201 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +# This test aims to evaluate the netpoll polling mechanism (as in netpoll_poll_dev()). +# It presents a complex scenario where the network attempts to send a packet but fails, +# prompting it to poll the NIC from within the netpoll TX side. +# +# This has been a crucial path in netpoll that was previously untested. Jakub +# suggested using a single RX/TX queue, pushing traffic to the NIC, and then sending +# netpoll messages (via netconsole) to trigger the poll. `perf` probing of netpoll_poll_dev() +# showed that this test indeed triggers netpoll_poll_dev() once or twice in 10 iterations. + +# Author: Breno Leitao <leitao(a)debian.org> + +import errno +import os +import random +import string +import time + +from lib.py import ( + ethtool, + GenerateTraffic, + ksft_exit, + ksft_pr, + ksft_run, + KsftFailEx, + KsftSkipEx, + NetdevFamily, + NetDrvEpEnv, +) + +NETCONSOLE_CONFIGFS_PATH = "/sys/kernel/config/netconsole" +REMOTE_PORT = 6666 +LOCAL_PORT = 1514 +# Number of netcons messages to send. I usually see netpoll_poll_dev() +# being called at least once in 10 iterations. +ITERATIONS = 10 +DEBUG = False + + +def generate_random_netcons_name() -> str: + """Generate a random name starting with 'netcons'""" + random_suffix = "".join(random.choices(string.ascii_lowercase + string.digits, k=8)) + return f"netcons_{random_suffix}" + + +def get_stats(cfg: NetDrvEpEnv, netdevnl: NetdevFamily) -> dict[str, int]: + """Get the statistics for the interface""" + return netdevnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] + + +def set_single_rx_tx_queue(interface_name: str) -> None: + """Set the number of RX and TX queues to 1 using ethtool""" + try: + # This don't need to be reverted, since interfaces will be deleted after test + ethtool(f"-G {interface_name} rx 1 tx 1") + except Exception as e: + raise KsftSkipEx( + f"Failed to configure RX/TX queues: {e}. Ethtool not available?" + ) + + +def create_netconsole_target( + config_data: dict[str, str], + target_name: str, +) -> None: + """Create a netconsole dynamic target against the interfaces""" + ksft_pr(f"Using netconsole name: {target_name}") + try: + ksft_pr(f"Created target directory: {NETCONSOLE_CONFIGFS_PATH}/{target_name}") + os.makedirs(f"{NETCONSOLE_CONFIGFS_PATH}/{target_name}", exist_ok=True) + except OSError as e: + if e.errno != errno.EEXIST: + raise KsftFailEx(f"Failed to create netconsole target directory: {e}") + + try: + for key, value in config_data.items(): + if DEBUG: + ksft_pr(f"Setting {key} to {value}") + with open( + f"{NETCONSOLE_CONFIGFS_PATH}/{target_name}/{key}", + "w", + encoding="utf-8", + ) as f: + # Always convert to string to write to file + f.write(str(value)) + f.close() + + if DEBUG: + # Read all configuration values for debugging + for debug_key in config_data.keys(): + with open( + f"{NETCONSOLE_CONFIGFS_PATH}/{target_name}/{debug_key}", + "r", + encoding="utf-8", + ) as f: + content = f.read() + ksft_pr( + f"{NETCONSOLE_CONFIGFS_PATH}/{target_name}/{debug_key} {content}" + ) + + except Exception as e: + raise KsftFailEx(f"Failed to configure netconsole target: {e}") + + +def set_netconsole(cfg: NetDrvEpEnv, interface_name: str, target_name: str) -> None: + """Configure netconsole on the interface with the given target name""" + config_data = { + "extended": "1", + "dev_name": interface_name, + "local_port": LOCAL_PORT, + "remote_port": REMOTE_PORT, + "local_ip": cfg.addr_v["4"] if cfg.addr_ipver == "4" else cfg.addr_v["6"], + "remote_ip": ( + cfg.remote_addr_v["4"] if cfg.addr_ipver == "4" else cfg.remote_addr_v["6"] + ), + "remote_mac": "00:00:00:00:00:00", # Not important for this test + "enabled": "1", + } + + create_netconsole_target(config_data, target_name) + ksft_pr(f"Created netconsole target: {target_name} on interface {interface_name}") + + +def delete_netconsole_target(name: str) -> None: + """Delete a netconsole dynamic target""" + target_path = f"{NETCONSOLE_CONFIGFS_PATH}/{name}" + try: + if os.path.exists(target_path): + os.rmdir(target_path) + except OSError as e: + raise KsftFailEx(f"Failed to delete netconsole target: {e}") + + +def check_traffic_flowing(cfg: NetDrvEpEnv, netdevnl: NetdevFamily) -> int: + """Check if traffic is flowing on the interface""" + stat1 = get_stats(cfg, netdevnl) + time.sleep(1) + stat2 = get_stats(cfg, netdevnl) + pkts_per_sec = stat2["rx-packets"] - stat1["rx-packets"] + # Just make sure this will not fail even in slow/debug kernels + if pkts_per_sec < 10: + raise KsftFailEx(f"Traffic seems low: {pkts_per_sec}") + if DEBUG: + ksft_pr(f"Traffic per second {pkts_per_sec} ", pkts_per_sec) + + return pkts_per_sec + + +def do_netpoll_flush(cfg: NetDrvEpEnv, netdevnl: NetdevFamily) -> None: + """Print messages to the console, trying to trigger a netpoll poll""" + for i in range(int(ITERATIONS)): + pkts_per_s = check_traffic_flowing(cfg, netdevnl) + with open("/dev/kmsg", "w", encoding="utf-8") as kmsg: + kmsg.write(f"netcons test #{i}: ({pkts_per_s} packets/s)\n") + + +def test_netpoll(cfg: NetDrvEpEnv, netdevnl: NetdevFamily) -> None: + """Test netpoll by sending traffic to the interface and then sending netconsole messages to trigger a poll""" + target_name = generate_random_netcons_name() + ifname = cfg.dev["ifname"] + traffic = None + + try: + set_single_rx_tx_queue(ifname) + traffic = GenerateTraffic(cfg) + check_traffic_flowing(cfg, netdevnl) + set_netconsole(cfg, ifname, target_name) + do_netpoll_flush(cfg, netdevnl) + finally: + if traffic: + traffic.stop() + delete_netconsole_target(target_name) + + +def check_dependencies() -> None: + """Check if the dependencies are met""" + if not os.path.exists(NETCONSOLE_CONFIGFS_PATH): + raise KsftSkipEx( + f"Directory {NETCONSOLE_CONFIGFS_PATH} does not exist. CONFIG_NETCONSOLE_DYNAMIC might not be set." + ) + + +def main() -> None: + """Main function to run the test""" + check_dependencies() + netdevnl = NetdevFamily() + with NetDrvEpEnv(__file__, nsim_test=True) as cfg: + ksft_run( + [test_netpoll], + args=( + cfg, + netdevnl, + ), + ) + ksft_exit() + + +if __name__ == "__main__": + main() --- base-commit: 5d6d67c4cb10a4b4d3ae35758d5eeed6239afdc8 change-id: 20250612-netpoll_test-a1324d2057c8 Best regards, -- Breno Leitao <leitao(a)debian.org>

5 months, 3 weeks

3
10
0 0

[PATCH bpf-next] selftests/bpf: Support ppc64el in vmtest

by Luis Gerhorst

With a rootfs built using libbpf's BPF CI [1], we can run specific tests as follows: $ ../libbpf-ci/rootfs/mkrootfs_debian.sh --arch ppc64el --distro noble $ PLATFORM=ppc64el CROSS_COMPILE=powerpc64le-linux-gnu- \ tools/testing/selftests/bpf/vmtest.sh \ -l libbpf-vmtest-rootfs-*-noble-ppc64el.tar.zst \ -- ./test_progs -t verifier_array_access Does not include a DENYLIST or support for KVM for now. [1] https://github.com/libbpf/ci Signed-off-by: Luis Gerhorst <luis.gerhorst(a)fau.de> --- tools/testing/selftests/bpf/config.ppc64el | 93 ++++++++++++++++++++++ tools/testing/selftests/bpf/vmtest.sh | 9 +++ 2 files changed, 102 insertions(+) create mode 100644 tools/testing/selftests/bpf/config.ppc64el diff --git a/tools/testing/selftests/bpf/config.ppc64el b/tools/testing/selftests/bpf/config.ppc64el new file mode 100644 index 000000000000..9acf389dc4ce --- /dev/null +++ b/tools/testing/selftests/bpf/config.ppc64el @@ -0,0 +1,93 @@ +CONFIG_ALTIVEC=y +CONFIG_AUDIT=y +CONFIG_BLK_CGROUP=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BONDING=y +CONFIG_BPF_JIT_ALWAYS_ON=y +CONFIG_BPF_PRELOAD_UMD=y +CONFIG_BPF_PRELOAD=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_HUGETLB=y +CONFIG_CGROUP_NET_CLASSID=y +CONFIG_CGROUP_PERF=y +CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_SCHED=y +CONFIG_CGROUPS=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=hvc0 wg.success=hvc1 panic_on_warn=1" +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_CPUSETS=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_DEBUG_FS=y +CONFIG_DETECT_HUNG_TASK=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_DEVTMPFS=y +CONFIG_EXPERT=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_EXT4_FS=y +CONFIG_FRAME_POINTER=y +CONFIG_FRAME_WARN=1280 +CONFIG_HARDLOCKUP_DETECTOR=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_HUGETLBFS=y +CONFIG_HVC_CONSOLE=y +CONFIG_INET=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IPV6_SEG6_LWTUNNEL=y +CONFIG_JUMP_LABEL=y +CONFIG_KALLSYMS_ALL=y +CONFIG_KPROBES=y +CONFIG_MEMCG=y +CONFIG_NAMESPACES=y +CONFIG_NET_ACT_BPF=y +CONFIG_NETDEVICES=y +CONFIG_NETFILTER_XT_MATCH_BPF=y +CONFIG_NET_L3_MASTER_DEV=y +CONFIG_NET_VRF=y +CONFIG_NET=y +CONFIG_NO_HZ_IDLE=y +CONFIG_NONPORTABLE=y +CONFIG_NR_CPUS=256 +CONFIG_PACKET=y +CONFIG_PANIC_ON_OOPS=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_PCI_HOST_GENERIC=y +CONFIG_PCI=y +CONFIG_POSIX_MQUEUE=y +CONFIG_PPC64=y +CONFIG_PPC_OF_BOOT_TRAMPOLINE=y +CONFIG_PPC_PSERIES=y +CONFIG_PPC_RADIX_MMU=y +CONFIG_PRINTK_TIME=y +CONFIG_PROC_KCORE=y +CONFIG_PROFILING=y +CONFIG_RCU_CPU_STALL_TIMEOUT=60 +CONFIG_RT_GROUP_SCHED=y +CONFIG_SECTION_MISMATCH_WARN_ONLY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_OF_PLATFORM=y +CONFIG_SMP=y +CONFIG_SOC_VIRT=y +CONFIG_SYSVIPC=y +CONFIG_TCP_CONG_ADVANCED=y +CONFIG_THREAD_SHIFT=14 +CONFIG_TLS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_TMPFS=y +CONFIG_TUN=y +CONFIG_UNIX=y +CONFIG_UPROBES=y +CONFIG_USER_NS=y +CONFIG_VETH=y +CONFIG_VLAN_8021Q=y +CONFIG_VSOCKETS_LOOPBACK=y +CONFIG_VSX=y +CONFIG_XFRM_USER=y diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh index 79505d294c44..2f869daf8a06 100755 --- a/tools/testing/selftests/bpf/vmtest.sh +++ b/tools/testing/selftests/bpf/vmtest.sh @@ -43,6 +43,15 @@ riscv64) BZIMAGE="arch/riscv/boot/Image" ARCH="riscv" ;; +ppc64el) + QEMU_BINARY=qemu-system-ppc64 + QEMU_CONSOLE="hvc0" + # KVM could not be tested for powerpc, therefore not enabled for now. + HOST_FLAGS=(-machine pseries -cpu POWER9) + CROSS_FLAGS=(-machine pseries -cpu POWER9) + BZIMAGE="vmlinux" + ARCH="powerpc" + ;; *) echo "Unsupported architecture" exit 1 base-commit: cd7312a78f36e981939abe1cd1f21d355e083dfe -- 2.49.0

5 months, 3 weeks

2
1
0 0

[PATCH] selftests/mm: add test for (BATCH_PROCESS)MADV_DONTNEED

by wang lian

From: Lian Wang <lianux.mm(a)gmail.com> Let's add a simple test for MADV_DONTNEED and PROCESS_MADV_DONTNEED, and inspired by SeongJae Park's test at GitHub[1] add batch test for PROCESS_MADV_DONTNEED,but for now it influence by workload and need add some race conditions test.We can add it later. Signed-off-by: Lian Wang <lianux.mm(a)gmail.com> References ========== [1] https://github.com/sjp38/eval_proc_madvise --- tools/testing/selftests/mm/.gitignore | 1 + tools/testing/selftests/mm/Makefile | 1 + tools/testing/selftests/mm/madv_dontneed.c | 220 +++++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 5 + 4 files changed, 227 insertions(+) create mode 100644 tools/testing/selftests/mm/madv_dontneed.c diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 824266982aa3..911f39d634be 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -25,6 +25,7 @@ pfnmap protection_keys protection_keys_32 protection_keys_64 +madv_dontneed madv_populate uffd-stress uffd-unit-tests diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index ae6f994d3add..2352252f3914 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -67,6 +67,7 @@ TEST_GEN_FILES += hugepage-mremap TEST_GEN_FILES += hugepage-shm TEST_GEN_FILES += hugepage-vmemmap TEST_GEN_FILES += khugepaged +TEST_GEN_FILES += madv_dontneed TEST_GEN_FILES += madv_populate TEST_GEN_FILES += map_fixed_noreplace TEST_GEN_FILES += map_hugetlb diff --git a/tools/testing/selftests/mm/madv_dontneed.c b/tools/testing/selftests/mm/madv_dontneed.c new file mode 100644 index 000000000000..b88444da7f9e --- /dev/null +++ b/tools/testing/selftests/mm/madv_dontneed.c @@ -0,0 +1,220 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * MADV_DONTNEED and PROCESS_MADV_DONTNEED tests + * + * Copyright (C) 2025, Linx Software Corp. + * + * Author(s): Lian Wang <lianux.mm(a)gmail.com> + */ +#define _GNU_SOURCE +#include <stdlib.h> +#include <string.h> +#include <stdbool.h> +#include <stdint.h> +#include <unistd.h> +#include <errno.h> +#include <fcntl.h> +#include <linux/mman.h> +#include <sys/mman.h> +#include <sys/syscall.h> +#include "vm_util.h" +#include <time.h> + +#include "../kselftest.h" + +/* + * For now, we're using 2 MiB of private anonymous memory for all tests. + */ +#define SIZE (256 * 1024 * 1024) + +static size_t pagesize; + +static void sense_support(void) +{ + char *addr; + int ret; + + addr = mmap(0, pagesize, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); + if (!addr) + ksft_exit_fail_msg("mmap failed\n"); + + ret = madvise(addr, pagesize, MADV_DONTNEED); + if (ret) + ksft_exit_skip("MADV_DONTNEED is not available\n"); + + munmap(addr, pagesize); +} + +/* + * Read pagemap to check page is present in mermory + */ +static bool is_page_present(void *addr) +{ + uintptr_t vaddr = (uintptr_t)addr; + uintptr_t offset = (vaddr / pagesize) * sizeof(uint64_t); + ssize_t bytes_read; + uint64_t entry; + bool ret; + int fd; + + fd = open("/proc/self/pagemap", O_RDONLY); + if (fd < 0) { + ksft_exit_fail_msg("opening pagemap failed\n"); + ret = false; + } + + if ((lseek(fd, offset, SEEK_SET)) == -1) { + close(fd); + ret = false; + } + + bytes_read = read(fd, &entry, sizeof(entry)); + close(fd); + + if (bytes_read != sizeof(entry)) { + perror("read failed"); + return false; + } + + if (entry & (1ULL << 63)) + ret = true; + + return ret; +} + +/* + * test madvsise_dontneed + */ +static void test_madv_dontneed(void) +{ + unsigned long rss_anon_before, rss_anon_after; + bool present, rss; + char *addr; + int ret; + + ksft_print_msg("[RUN] %s\n", __func__); + + addr = mmap(0, SIZE, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); + if (!addr) + ksft_exit_fail_msg("mmap failed\n"); + + memset(addr, 0x7A, SIZE); + + rss_anon_before = rss_anon(); + if (!rss_anon_before) + ksft_exit_fail_msg("No RssAnon is allocated before dontneed\n"); + ret = madvise(addr, SIZE, MADV_DONTNEED); + ksft_test_result(!ret, "MADV_DONTNEED\n"); + + rss_anon_after = rss_anon(); + if (rss_anon_after < rss_anon_before) + rss = true; + ksft_test_result(rss, "MADV_DONTNEED rss is correct\n"); + + for (size_t i = 0; i < SIZE; i += pagesize) { + present = is_page_present(addr + i); + if (present) { + ksft_print_msg("Page not zero at offset %zu\n", + (size_t)i); + } + } + + ksft_test_result(!present, "MADV_DONTNEED page is present\n"); + munmap(addr, SIZE); +} + +/* + * Measure performance of batched process_madvise vs madvise + */ +static int measure_process_madvise_batching(int hint, int total_size, + int single_unit, int batch_size) +{ + struct iovec *vec = malloc(sizeof(*vec) * batch_size); + struct timespec start, end; + unsigned long elapsed_ns = 0; + unsigned long nr_measures = 0; + pid_t pid = getpid(); + char *buf; + int pidfd; + + pidfd = syscall(SYS_pidfd_open, pid, 0); + if (pidfd == -1) { + perror("pidfd_open fail"); + return -1; + } + + buf = mmap(NULL, total_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (buf == MAP_FAILED) { + perror("mmap fail"); + goto out; + } + + if (!vec) { + perror("malloc vec failed"); + goto unmap_out; + } + + while (elapsed_ns < 5UL * 1000 * 1000 * 1000) { + memset(buf, 0x7A, total_size); + + clock_gettime(CLOCK_MONOTONIC, &start); + + for (int off = 0; off < total_size; + off += single_unit * batch_size) { + for (int i = 0; i < batch_size; i++) { + vec[i].iov_base = buf + off + i * single_unit; + vec[i].iov_len = single_unit; + } + syscall(SYS_process_madvise, pidfd, vec, batch_size, + hint, 0); + } + + clock_gettime(CLOCK_MONOTONIC, &end); + elapsed_ns += (end.tv_sec - start.tv_sec) * 1e9 + + (end.tv_nsec - start.tv_nsec); + nr_measures++; + } + + ksft_print_msg("[RESULT] batch=%d time=%.3f us/op\n", batch_size, + (double)(elapsed_ns / nr_measures) / + (total_size / single_unit)); + + free(vec); +unmap_out: + munmap(buf, total_size); +out: + close(pidfd); + return 0; +} + +static void test_perf_batch_process(void) +{ + ksft_print_msg("[RUN] %s\n", __func__); + measure_process_madvise_batching(MADV_DONTNEED, SIZE, pagesize, 1); + measure_process_madvise_batching(MADV_DONTNEED, SIZE, pagesize, 2); + measure_process_madvise_batching(MADV_DONTNEED, SIZE, pagesize, 4); + ksft_test_result(1, "All test were done\n"); +} + +int main(int argc, char **argv) +{ + int err; + + pagesize = getpagesize(); + + ksft_print_header(); + ksft_set_plan(4); + + sense_support(); + test_madv_dontneed(); + test_perf_batch_process(); + + err = ksft_get_fail_cnt(); + if (err) + ksft_exit_fail_msg("%d out of %d tests failed\n", err, + ksft_test_num()); + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index dddd1dd8af14..f96d43153fc0 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -47,6 +47,8 @@ separated by spaces: hmm smoke tests - madv_guard test madvise(2) MADV_GUARD_INSTALL and MADV_GUARD_REMOVE options +- madv_dontneed + test memadvise(2) MADV_DONTNEED and PROCESS_MADV_DONTNEED options - madv_populate test memadvise(2) MADV_POPULATE_{READ,WRITE} options - memfd_secret @@ -422,6 +424,9 @@ CATEGORY="hmm" run_test bash ./test_hmm.sh smoke # MADV_GUARD_INSTALL and MADV_GUARD_REMOVE tests CATEGORY="madv_guard" run_test ./guard-regions +# MADV_DONTNEED and PROCESS_DONTNEED tests +CATEGORY="madv_dontneed" run_test ./madv_dontneed + # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate -- 2.43.0

5 months, 3 weeks

3
3
0 0

[RFC PATCH v2 nf-next] selftests: netfilter: Add bridge_fastpath.sh

by Eric Woudstra

Add a script to test various scenarios where a bridge is involved in the fastpath. It runs tests in the forward path, and also in a bridged path. The setup is similar to a basic home router with multiple lan ports. It uses 3 pairs of veth-devices. Each or all pairs can be replaced by a pair of real interfaces, interconnected by wire. This is necessary to test the behavior when dealing with dsa ports, foreign (dsa) ports and switchdev userports that support SWITCHDEV_OBJ_ID_PORT_VLAN. See the head of the script for a detailed description. Run without arguments to perform all tests on veth-devices. Signed-off-by: Eric Woudstra <ericwouds(a)gmail.com> --- This test script is written first for the proposed bridge-fastpath patch-sets, but it's use is more general and can easily be expanded. Changes in v2: - Moved test-series to functions - Moved code to set_pair_link() up/down - Added conntrack zone to bridged traffic - Test bridge chain prerouting in test without fastpath and bridge chain forward in tests with fastpath Some example outputs of this last version of patches from different hardware, without and with patches: ALL VETH: ========= ./bridge_fastpath.sh -t Setup: CLIENT 0 veth0cl | veth0rt WAN ROUTER LAN1 LAN2 veth1rt veth2rt | | veth1cl veth2cl CLIENT 1 CLIENT 2 Without patches: PASS: unaware bridge, without encaps, without fastpath PASS: unaware bridge, with single vlan encap, without fastpath ERROR: unaware bridge, with double q vlan encaps, without fastpath: ipv4/6: established bytes 0 < 4194304 ERROR: unaware bridge, with 802.1ad vlan encaps, without fastpath: ipv4/6: established bytes 0 < 4194304 PASS: aware bridge, without/without vlan encap, without fastpath PASS: aware bridge, with/without vlan encap, without fastpath PASS: aware bridge, with/with vlan encap, without fastpath PASS: aware bridge, without/with vlan encap, without fastpath PASS: forward, without vlan-device, without vlan encap, client1, without fastpath PASS: forward, without vlan-device, without vlan encap, client1, with fastpath PASS: forward, without vlan-device, with vlan encap, client1, without fastpath ERROR: forward, without vlan-device, with vlan encap, client1, with fastpath: ipv4/6: tcp broken PASS: forward, with vlan-device, with vlan encap, client1, without fastpath PASS: forward, with vlan-device, with vlan encap, client1, with fastpath PASS: forward, with vlan-device, without vlan encap, client1, without fastpath PASS: forward, with vlan-device, without vlan encap, client1, with fastpath ERROR: bridge fastpath test has failed With patches: PASS: unaware bridge, without encaps, without fastpath PASS: unaware bridge, without encaps, with fastpath PASS: unaware bridge, with single vlan encap, without fastpath PASS: unaware bridge, with single vlan encap, with fastpath PASS: unaware bridge, with double q vlan encaps, without fastpath PASS: unaware bridge, with double q vlan encaps, with fastpath PASS: unaware bridge, with 802.1ad vlan encaps, without fastpath PASS: unaware bridge, with 802.1ad vlan encaps, with fastpath PASS: aware bridge, without/without vlan encap, without fastpath PASS: aware bridge, without/without vlan encap, with fastpath PASS: aware bridge, with/without vlan encap, without fastpath PASS: aware bridge, with/without vlan encap, with fastpath PASS: aware bridge, with/with vlan encap, without fastpath PASS: aware bridge, with/with vlan encap, with fastpath PASS: aware bridge, without/with vlan encap, without fastpath PASS: aware bridge, without/with vlan encap, with fastpath PASS: forward, without vlan-device, without vlan encap, client1, without fastpath PASS: forward, without vlan-device, without vlan encap, client1, with fastpath PASS: forward, without vlan-device, with vlan encap, client1, without fastpath PASS: forward, without vlan-device, with vlan encap, client1, with fastpath PASS: forward, with vlan-device, with vlan encap, client1, without fastpath PASS: forward, with vlan-device, with vlan encap, client1, with fastpath PASS: forward, with vlan-device, without vlan encap, client1, without fastpath PASS: forward, with vlan-device, without vlan encap, client1, with fastpath PASS: all tests passed BANANAPI-R3 (lan1 & lan2 are dsa): ============ Without patches: ./bridge_fastpath.sh -t -0 enu1u2,lan2 -1 enu1u1,lan1 -2 lan4,eth1 Setup: CLIENT 0 enu1u2 | lan2 WAN ROUTER LAN1 LAN2 lan1 eth1 | | enu1u1 lan4 CLIENT 1 CLIENT 2 PASS: unaware bridge, without encaps, without fastpath PASS: unaware bridge, with single vlan encap, without fastpath PASS: aware bridge, without/without vlan encap, without fastpath PASS: aware bridge, with/without vlan encap, without fastpath PASS: aware bridge, with/with vlan encap, without fastpath PASS: aware bridge, without/with vlan encap, without fastpath PASS: forward, without vlan-device, without vlan encap, client1, without fastpath ERROR: forward, without vlan-device, without vlan encap, client1, with fastpath: ipv4: counted bytes 2118540 > 2097152 ERROR: forward, without vlan-device, without vlan encap, client1, with fastpath: ipv6: counted bytes 2117904 > 2097152 PASS: forward, without vlan-device, without vlan encap, client2, without fastpath PASS: forward, without vlan-device, without vlan encap, client2, with fastpath PASS: forward, without vlan-device, without vlan encap, client2, with hw_fastpath PASS: forward, without vlan-device, with vlan encap, client1, without fastpath ERROR: forward, without vlan-device, with vlan encap, client1, with fastpath: ipv4/6: tcp broken PASS: forward, without vlan-device, with vlan encap, client2, without fastpath ERROR: forward, without vlan-device, with vlan encap, client2, with fastpath: ipv4/6: tcp broken PASS: forward, with vlan-device, with vlan encap, client1, without fastpath PASS: forward, with vlan-device, with vlan encap, client1, with fastpath PASS: forward, with vlan-device, with vlan encap, client1, with hw_fastpath PASS: forward, with vlan-device, with vlan encap, client2, without fastpath PASS: forward, with vlan-device, with vlan encap, client2, with fastpath PASS: forward, with vlan-device, with vlan encap, client2, with hw_fastpath PASS: forward, with vlan-device, without vlan encap, client1, without fastpath PASS: forward, with vlan-device, without vlan encap, client1, with fastpath PASS: forward, with vlan-device, without vlan encap, client1, with hw_fastpath PASS: forward, with vlan-device, without vlan encap, client2, without fastpath ERROR: forward, with vlan-device, without vlan encap, client2, with fastpath: ipv4: counted bytes 2109596 > 2097152 ERROR: forward, with vlan-device, without vlan encap, client2, with fastpath: ipv6: counted bytes 2121432 > 2097152 ERROR: bridge fastpath test has failed With patches: PASS: unaware bridge, without encaps, without fastpath PASS: unaware bridge, without encaps, with fastpath PASS: unaware bridge, without encaps, with hw_fastpath PASS: unaware bridge, with single vlan encap, without fastpath PASS: unaware bridge, with single vlan encap, with fastpath PASS: unaware bridge, with single vlan encap, with hw_fastpath PASS: aware bridge, without/without vlan encap, without fastpath PASS: aware bridge, without/without vlan encap, with fastpath PASS: aware bridge, without/without vlan encap, with hw_fastpath PASS: aware bridge, with/without vlan encap, without fastpath PASS: aware bridge, with/without vlan encap, with fastpath PASS: aware bridge, with/without vlan encap, with hw_fastpath PASS: aware bridge, with/with vlan encap, without fastpath PASS: aware bridge, with/with vlan encap, with fastpath PASS: aware bridge, with/with vlan encap, with hw_fastpath PASS: aware bridge, without/with vlan encap, without fastpath PASS: aware bridge, without/with vlan encap, with fastpath PASS: aware bridge, without/with vlan encap, with hw_fastpath PASS: forward, without vlan-device, without vlan encap, client1, without fastpath PASS: forward, without vlan-device, without vlan encap, client1, with fastpath PASS: forward, without vlan-device, without vlan encap, client1, with hw_fastpath PASS: forward, without vlan-device, without vlan encap, client2, without fastpath PASS: forward, without vlan-device, without vlan encap, client2, with fastpath PASS: forward, without vlan-device, without vlan encap, client2, with hw_fastpath PASS: forward, without vlan-device, with vlan encap, client1, without fastpath PASS: forward, without vlan-device, with vlan encap, client1, with fastpath PASS: forward, without vlan-device, with vlan encap, client1, with hw_fastpath PASS: forward, without vlan-device, with vlan encap, client2, without fastpath PASS: forward, without vlan-device, with vlan encap, client2, with fastpath PASS: forward, without vlan-device, with vlan encap, client2, with hw_fastpath PASS: forward, with vlan-device, with vlan encap, client1, without fastpath PASS: forward, with vlan-device, with vlan encap, client1, with fastpath PASS: forward, with vlan-device, with vlan encap, client1, with hw_fastpath PASS: forward, with vlan-device, with vlan encap, client2, without fastpath PASS: forward, with vlan-device, with vlan encap, client2, with fastpath PASS: forward, with vlan-device, with vlan encap, client2, with hw_fastpath PASS: forward, with vlan-device, without vlan encap, client1, without fastpath PASS: forward, with vlan-device, without vlan encap, client1, with fastpath PASS: forward, with vlan-device, without vlan encap, client1, with hw_fastpath PASS: forward, with vlan-device, without vlan encap, client2, without fastpath PASS: forward, with vlan-device, without vlan encap, client2, with fastpath PASS: forward, with vlan-device, without vlan encap, client2, with hw_fastpath PASS: all tests passed AM3359 (end1 supports SWITCHDEV_OBJ_ID_PORT_VLAN, ipv4 only for now): ======= ./bridge_fastpath.sh -t -a -4 -d -1 enu1u4c2,end1 Without patches: Setup: CLIENT 0 veth0cl | veth0rt WAN ROUTER LAN1 LAN2 end1 veth2rt | | enu1u4c2 veth2cl CLIENT 1 CLIENT 2 INFO: Skipping unaware bridge PASS: aware bridge, without/without vlan encap, without fastpath PASS: aware bridge, with/without vlan encap, without fastpath PASS: aware bridge, with/with vlan encap, without fastpath PASS: aware bridge, without/with vlan encap, without fastpath PASS: forward, without vlan-device, without vlan encap, client1, without fastpath ERROR: forward, without vlan-device, without vlan encap, client1, with fastpath: ipv4: counted bytes 2190092 > 2097152 PASS: forward, without vlan-device, without vlan encap, client2, without fastpath PASS: forward, without vlan-device, without vlan encap, client2, with fastpath PASS: forward, without vlan-device, with vlan encap, client1, without fastpath ERROR: forward, without vlan-device, with vlan encap, client1, with fastpath: ipv4: tcp broken PASS: forward, without vlan-device, with vlan encap, client2, without fastpath ERROR: forward, without vlan-device, with vlan encap, client2, with fastpath: ipv4: tcp broken PASS: forward, with vlan-device, with vlan encap, client1, without fastpath PASS: forward, with vlan-device, with vlan encap, client1, with fastpath PASS: forward, with vlan-device, with vlan encap, client2, without fastpath PASS: forward, with vlan-device, with vlan encap, client2, with fastpath PASS: forward, with vlan-device, without vlan encap, client1, without fastpath PASS: forward, with vlan-device, without vlan encap, client1, with fastpath PASS: forward, with vlan-device, without vlan encap, client2, without fastpath PASS: forward, with vlan-device, without vlan encap, client2, with fastpath ERROR: bridge fastpath test has failed With patches: INFO: Skipping unaware bridge PASS: aware bridge, without/without vlan encap, without fastpath PASS: aware bridge, without/without vlan encap, with fastpath PASS: aware bridge, with/without vlan encap, without fastpath PASS: aware bridge, with/without vlan encap, with fastpath PASS: aware bridge, with/with vlan encap, without fastpath PASS: aware bridge, with/with vlan encap, with fastpath PASS: aware bridge, without/with vlan encap, without fastpath PASS: aware bridge, without/with vlan encap, with fastpath PASS: forward, without vlan-device, without vlan encap, client1, without fastpath PASS: forward, without vlan-device, without vlan encap, client1, with fastpath PASS: forward, without vlan-device, without vlan encap, client2, without fastpath PASS: forward, without vlan-device, without vlan encap, client2, with fastpath PASS: forward, without vlan-device, with vlan encap, client1, without fastpath PASS: forward, without vlan-device, with vlan encap, client1, with fastpath PASS: forward, without vlan-device, with vlan encap, client2, without fastpath PASS: forward, without vlan-device, with vlan encap, client2, with fastpath PASS: forward, with vlan-device, with vlan encap, client1, without fastpath PASS: forward, with vlan-device, with vlan encap, client1, with fastpath PASS: forward, with vlan-device, with vlan encap, client2, without fastpath PASS: forward, with vlan-device, with vlan encap, client2, with fastpath PASS: forward, with vlan-device, without vlan encap, client1, without fastpath PASS: forward, with vlan-device, without vlan encap, client1, with fastpath PASS: forward, with vlan-device, without vlan encap, client2, without fastpath PASS: forward, with vlan-device, without vlan encap, client2, with fastpath PASS: all tests passed (Some problem still to figure out for my AM3359 hardware: On the second run of the command the tcp traffic is ok on all tests ipv4. On the first run the hardware is not setup correctly, some tests report broken tcp even without fastpath. Also ipv6 tcp broken even on second run even without fastpath. This may be a problem with my hardware or the test-script, but anyway it shows the fastpath is functional) .../testing/selftests/net/netfilter/Makefile | 1 + .../net/netfilter/bridge_fastpath.sh | 1008 +++++++++++++++++ 2 files changed, 1009 insertions(+) create mode 100755 tools/testing/selftests/net/netfilter/bridge_fastpath.sh diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile index 3bdcbbdba925..50afe91bc3e2 100644 --- a/tools/testing/selftests/net/netfilter/Makefile +++ b/tools/testing/selftests/net/netfilter/Makefile @@ -8,6 +8,7 @@ MNL_LDLIBS := $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl) TEST_PROGS := br_netfilter.sh bridge_brouter.sh TEST_PROGS += br_netfilter_queue.sh +TEST_PROGS += bridge_fastpath.sh TEST_PROGS += conntrack_dump_flush.sh TEST_PROGS += conntrack_icmp_related.sh TEST_PROGS += conntrack_ipip_mtu.sh diff --git a/tools/testing/selftests/net/netfilter/bridge_fastpath.sh b/tools/testing/selftests/net/netfilter/bridge_fastpath.sh new file mode 100755 index 000000000000..82f2ddc946b8 --- /dev/null +++ b/tools/testing/selftests/net/netfilter/bridge_fastpath.sh @@ -0,0 +1,1008 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Check if conntrack, nft chain and fastpath is functional in setups +# where a bridge is in the fastpath. +# +# Commandline options make it possible to use real ethernet pairs +# instead of veth-device pairs. Any, or all, pairs can be tested using +# real hardware pairs. This is can be useful to test dsa-ports, +# switchdev (dsa) foreign ports and switchdev ports supporting +# SWITCHDEV_OBJ_ID_PORT_VLAN. +# +# First tcp is tested. Conntrack and nft chain are tested using a counter. +# When there is a fastpath possible between the interfaces then the +# fastpath is also tested. +# When there is a hardware offloaded fastpath possible between the +# interfaces then the hardware offloaded path is also tested. +# +# Setup is as a typical router: +# +# nsclientwan +# | +# nsrt +# | | +# nsclient1 nsclient2 +# +# Masquerading for ipv4 only. +# +# First check if a bridge table forward chain can be setup, skip +# these tests if this is not possible. +# Then check if a inet table forward chain can be setup, skip +# these tests if this is not possible. +# +# Different setups of paths are tested that involve a bridge in the +# fastpath. This can be in the forward-fastpath or in the bridge-fastpath. +# +# The first series, in the bridge-fastpath, using a vlan-unaware bridge. +# Traffic with the following vlan-tags is checked: +# a. without vlan +# b. single vlan +# c. double q vlan (only on veth-devices) +# d. 802.1ad vlan (only on veth-devices) +# e. pppoe (when available) +# f. pppoe-in-q (when available) +# +# (for items c to f fastpath can only work when a conntrack zone is set) +# (double tag testing results in broken tcp traffic on most hardware, +# in this test setup, use '-a' argument to test it anyway) +# (pppoe testing takes place if pppd and pppoe-server are installed) +# +# The second series, in the bridge-fastpath, using a vlan-aware bridge. +# Here we test all combinations of ingress/egress with or without single +# vlan encaps. +# +# The third series, in the forward-fastpath, using a vlan-aware bridge, +# without a vlan-device linked to the master port. We test the same combinations +# of ingress/egress with or without single vlan encaps. +# +# The fourth series, in the forward-fastpath, using a vlan-aware bridge, +# with a vlan-device linked to the master port. We test the same combinations +# of ingress/egress with or without single vlan encaps. +# +# Note 1: Using dsa userports on both sides of eth-pairs client1 or client2 +# gives erratic and unpredictable results. Use, for example, an usb-eth device +# on the client side to test a dsa-userport. +# +# Note 2: Testing the hardware offloaded fastpath, it is not checked if the +# packets do not follow the software fastpath instead. A universal way to +# check this should be added at some point. +# +# Note 3: Some interfaces to test on the router side, are netns immutable. +# Use the -d or --defaultnsrouter option so that the interfaces of the router +# do not have to change netns. The router is build up in the default netns. +# + +source lib.sh + +checktool "nft --version" "run test without nft" +checktool "socat -h" "run test without socat" +checktool "bridge -V" "run test without bridge" + +NR_OF_TESTS=4 +VID1=100 +VID2=101 +BRWAN=brwan +BRLAN=brlan +BRCL=brcl +LINKUP_TIMEOUT=10 +PING_TIMEOUT=10 +SOCAT_TIMEOUT=10 +filesize=2 # MiB + +filein=$(mktemp) +file1out=$(mktemp) +file2out=$(mktemp) +pppoeserveroptions=$(mktemp) +pppoeserverpid=$(mktemp) + +setup_ns nsclientwan nsclientlan1 nsclientlan2 + + WAN=0 ; LAN1=1 ; LAN2=2 ; ADWAN=3 ; ADLAN=4 +nsa=( $nsclientwan $nsclientlan1 $nsclientlan2 ) # $nsrt $nsrt +AD4=( '192.168.1.1' '192.168.2.101' '192.168.2.102' '192.168.1.2' '192.168.2.1' ) +AD6=( 'dead:1::1' 'dead:2::101' 'dead:2::102' 'dead:1::2' 'dead:2::1' ) + +tests_string=$(seq 1 $NR_OF_TESTS) + +while [ "${1:-}" != '' ]; do + case "$1" in + '-0' | '--pairwan') + shift + vethcl[$WAN]="${1%,*}" + vethrt[$WAN]="${1#*,}" + ;; + '-1' | '--pairlan1') + shift + vethcl[$LAN1]="${1%,*}" + vethrt[$LAN1]="${1#*,}" + ;; + '-2' | '--pairlan2') + shift + vethcl[$LAN2]="${1%,*}" + vethrt[$LAN2]="${1#*,}" + ;; + '-s' | '--filesize') + shift + filesize=$1 + ;; + '-p' | '--parts') + shift + tests_string=$1 + ;; + '-4' | '--ipv4') + do_ipv4=1 + ;; + '-6' | '--ipv6') + do_ipv6=1 + ;; + '-n' | '--noskip') + noskip=1 + ;; + '-d' | '--defaultnsrouter') + defaultnsrouter=1 + ;; + '-f' | '--fixmac') + fixmac=1 + ;; + '-t' | '--showtree') + showtree=1 + ;; + *) + cat <<-EOF + Usage: $(basename $0) [OPTION]... + -0 --pairwan eth0cl,eth0rt pair of real interfaces to use on wan side + -1 --pairlan1 eth1cl,eth1rt pair of real interfaces to use on lan1 side + -2 --pairlan2 eth2cl,eth2rt pair of real interfaces to use on lan2 side + -s --filesize filesize to use for testing + -p --parts partnumbers of tests to run, comma separated + -4|-6 --ipv4|--ipv6 test ipv4/6 only + -d --defaultnsrouter router in default network namespace, caution! + -f --fixmac change mac address when conflict found + -n --noskip also perform the normally skipped tests + -t --showtree show the tree of used interfaces + EOF + exit $ksft_skip + ;; + esac + shift +done + +for i in ${tests_string//','/' '}; do + tests[$i]="yes" +done + +if [ -n "$defaultnsrouter" ]; then + nsrt="nsrt-$(mktemp -u XXXXXX)" + touch /var/run/netns/$nsrt + mount --bind /proc/1/ns/net /var/run/netns/$nsrt +else + setup_ns nsrt +fi +nsa+=($nsrt $nsrt) + +cleanup() { + if [ -n "$defaultnsrouter" ]; then + umount /var/run/netns/$nsrt + rm -f /var/run/netns/$nsrt + fi + cleanup_all_ns + rm -f "$filein" "$file1out" "$file2out" "$pppoeserveroptions" "$pppoeserverpid" +} + +trap cleanup EXIT + +head -c $(($filesize * 1024 * 1024)) < /dev/urandom > "$filein" + +check_mac() +{ + local ns=$1 + local dev=$2 + local othermacs=$3 + local mac + + mac=$(ip -net "$ns" -br link show dev "$dev" | \ + grep -o -E '([[:xdigit:]]{1,2}:){5}[[:xdigit:]]{1,2}') + + if [[ ! "$othermacs" =~ "$mac" ]]; then + echo $mac + return 0 + fi + echo "WARN: Conflicting mac address $dev $mac" 1>&2 + + [ -z "$fixmac" ] && return 1 + + for (( j = 0 ; j < 10 ; j++ )); do + mac="${mac::6}$(printf %02x:%02x:%02x:%02x $(($RANDOM%256)) \ + $(($RANDOM%256)) $(($RANDOM%256)) $(($RANDOM%256)))" + [[ "$othermacs" =~ "$mac" ]] && continue + echo $mac + ip -net "$ns" link set dev "$dev" address "$mac" 1>&2 + return $? + done + return 1 +} + +is_linkup() +{ + local ns=$1 + local dev=$2 + + if [ -n "$(ip -net "$ns" link show dev "$dev" up 2>/dev/null | \ + grep 'state UP')" ]; then + return 0 + fi + return 1 +} + +set_pair_link() +{ + local arg=$1 + local all="${@:2}" + local lret=0 + local i j + + for i in $WAN $LAN1 $LAN2; do + ns="${nsa[$i]}" + ip -net "$ns" link set "${vethcl[$i]}" $arg + lret=$(($lret | $?)) + ip -net "$nsrt" link set "${vethrt[$i]}" $arg + lret=$(($lret | $?)) + done + [ $lret -ne 0 ] && return 1 + + [[ "$arg" != "up" ]] && return 0 + + for j in $(seq 1 $(($LINKUP_TIMEOUT * 5 ))); do + lret=0 + for i in $all; do + ns="${nsa[$i]}" + is_linkup $ns "${vethcl[$i]}" + lret=$(($lret | $?)) + is_linkup $nsrt "${vethrt[$i]}" + lret=$(($lret | $?)) + done + [ $lret -eq 0 ] && break + sleep 0.2 + done + return $lret +} + +wait_ping() +{ + local i1=$1 + local i2=$2 + local ns1=${nsa[$i1]} + local j + + for j in $(seq 1 $(($PING_TIMEOUT * 5 ))); do + ip netns exec "$ns1" ping -c 1 -w $PING_TIMEOUT -i 0.2 \ + -q "${AD4[$i2]}" >/dev/null 2>&1 + [ $? -le 1 ] && return $? + sleep 0.2 + done + return 1 +} + +add_addr() +{ + local i=$1 + local dev=$2 + local ns=${nsa[$i]} + local ad4=${AD4[$i]} + local ad6=${AD6[$i]} + + ip -net "$ns" addr add "${ad4}/24" dev "$dev" + ip -net "$ns" addr add "${ad6}/64" dev "$dev" nodad + if [[ "$ns" == "nsclientlan"* ]]; then + ip -net "$ns" route add default via "${AD4[$ADLAN]}" + ip -net "$ns" route add default via "${AD6[$ADLAN]}" + elif [[ "$ns" == "nsclientwan"* ]]; then + ip -net "$ns" route add default via "${AD6[$ADWAN]}" + fi + +} + +del_addr() +{ + local i=$1 + local dev=$2 + local ns=${nsa[$i]} + local ad4=${AD4[$i]} + local ad6=${AD6[$i]} + + if [[ "$ns" == "nsclientlan"* ]]; then + ip -net "$ns" route del default via "${AD6[$ADLAN]}" + ip -net "$ns" route del default via "${AD4[$ADLAN]}" + elif [[ "$ns" == "nsclientwan"* ]]; then + ip -net "$ns" route del default via "${AD6[$ADWAN]}" + fi + ip -net "$ns" addr del "${ad6}/64" dev "$dev" nodad + ip -net "$ns" addr del "${ad4}/24" dev "$dev" +} + +set_client() +{ + local i=$1 + local vlan=$2 + local arg=$3 + local ns=${nsa[$i]} + local vdev="${vethcl[$i]}" + local brdev="$BRCL" + local proto="" + local pvidslave="" + + unset_client $i + + if [[ "$vlan" == "qq" ]]; then + ip -net "$ns" link add link "$vdev" name "$vdev.$VID1" type vlan id $VID1 + ip -net "$ns" link add link "$vdev.$VID1" name "$vdev.$VID1.$VID2" \ + type vlan id $VID2 + ip -net "$ns" link set "$vdev.$VID1" up + ip -net "$ns" link set "$vdev.$VID1.$VID2" up + add_addr $i "$vdev.$VID1.$VID2" + return + fi + + [[ "$vlan" == "none" ]] && pvidslave="pvid untagged" + [[ "$vlan" == "ad" ]] && proto="vlan_protocol 802.1ad" + + ip -net "$ns" link add "$brdev" type bridge vlan_filtering 1 vlan_default_pvid 0 $proto + ip -net "$ns" link set "$vdev" master "$brdev" + ip -net "$ns" link set "$brdev" up + + bridge -net "$ns" vlan add dev "$brdev" vid $VID1 pvid untagged self + bridge -net "$ns" vlan add dev "$vdev" vid $VID1 $pvidslave + + if [[ "$vlan" == "ad" ]]; then + ip -net "$ns" link add link "$brdev" name "$brdev.$VID2" type vlan id $VID2 + brdev="$brdev.$VID2" + ip -net "$ns" link set "$brdev" up + fi + + if [[ "$arg" != "noaddress" ]]; then + add_addr $i "$brdev" + fi +} + +unset_client() +{ + local i=$1 + local ns=${nsa[$i]} + local vdev="${vethcl[$i]}" + local brdev="$BRCL" + + ip -net "$ns" link del "$brdev" type bridge 2>/dev/null + ip -net "$ns" link del "$vdev.$VID1" 2>/dev/null +} + +add_pppoe() +{ + local i1=$1 + local i2=$2 + local dev1=$3 + local dev2=$4 + local desc=$5 + local ns1=${nsa[$i1]} + local ns2=${nsa[$i2]} + + ppp1=0 + while [ -n "$(ip -net "$ns1" link show ppp$ppp1 2>/dev/null)" ] + do ((ppp1++)); done + echo "noauth defaultroute noipdefault unit $ppp1" >"$pppoeserveroptions" + ppp1="ppp$ppp1" + + if ! ip netns exec "$ns1" pppoe-server -k -L "${AD4[$i1]}" -R "${AD4[$i2]}" \ + -I $dev1 -X "$pppoeserverpid" -O "$pppoeserveroptions" >/dev/null; then + echo "ERROR: $desc: failed to setup pppoe server" 1>&2 + return 1 + fi + + if ! ip netns exec "$ns2" pppd plugin pppoe.so nic-$dev2 persist holdoff 0 noauth \ + defaultroute noipdefault noaccomp nodeflate noproxyarp nopcomp \ + novj novjccomp linkname "selftest-$$" >/dev/null; then + echo "ERROR: $desc: failed to setup pppoe client" 1>&2 + return 1 + fi + + if ! wait_ping $i1 $i2; then + echo "ERROR: $desc: failed to setup functional pppoe connection" 1>&2 + return 1 + fi + + ppp2=$(cat "/run/pppd/ppp-selftest-$$.pid" | tail -n 1) + + ip -net "$ns1" addr add "${AD6[$i1]}/64" dev "$ppp1" nodad + ip -net "$ns2" addr add "${AD6[$i2]}/64" dev "$ppp2" nodad + + return 0 +} + +del_pppoe() +{ + local i1=$1 + local i2=$2 + local dev1=$3 + local dev2=$4 + local ns1=${nsa[$i1]} + local ns2=${nsa[$i2]} + + [[ -n "$ppp1" ]] && ip -net "$ns1" addr del "${AD6[$i1]}/64" dev "$ppp1" + [[ -n "$ppp2" ]] && ip -net "$ns2" addr del "${AD6[$i2]}/64" dev "$ppp2" + + kill -9 $(cat "/run/pppd/ppp-selftest-$$.pid" | head -n 1) \ + $(cat "$pppoeserverpid" | head -n 1) +} + +listener_ready() +{ + local ns=$1 + local ipv=$2 + + ss -N "$ns" --ipv$ipv -lnt -o "sport = :8080" | grep -q 8080 +} + +test_tcp() { + local i1=$1 + local i2=$2 + local dofast=$3 + local desc=$4 + local ns1=${nsa[$i1]} + local ns2=${nsa[$i2]} + local i=-1 + local lret=0 + local ads="" + local ipv ad a lpid bytes limit error + + if [ -n "$do_ipv4" ]; then ads="${AD4[$i2]}" + elif [ -n "$do_ipv6" ]; then ads="${AD6[$i2]}" + else ads="${AD4[$i2]} ${AD6[$i2]}" + fi + for ad in $ads; do + ((i++)) + if [[ "$ad" =~ ":" ]] + then ipv="6"; a="[${ad}]" + else ipv="4"; a="${ad}" + fi + + rm -f "$file1out" "$file2out" + + # ip netns exec "$nsrt" nft reset counters >/dev/null + # But on some systems this results in 4GB values in packet and byte count, so: + (echo "flush ruleset"; ip netns exec "$nsrt" nft --stateless list ruleset) | \ + ip netns exec "$nsrt" nft -f - + + timeout "$SOCAT_TIMEOUT" ip netns exec "$ns2" socat TCP$ipv-LISTEN:8080,reuseaddr \ + STDIO <"$filein" >"$file2out" 2>/dev/null & + lpid=$! + busywait 1000 listener_ready "$ns2" "$ipv" + + timeout "$SOCAT_TIMEOUT" ip netns exec "$ns1" socat TCP$ipv:$a:8080 \ + STDIO <"$filein" >"$file1out" 2>/dev/null + wait $lpid + + if [ $? -ne 0 ]; then + error[$i]="ipv$ipv: tcp broken" + continue + fi + if ! cmp "$filein" "$file1out" >/dev/null 2>&1; then + error[$i]="ipv$ipv: file mismatch to ${ad}" + continue + fi + if ! cmp "$filein" "$file2out" >/dev/null 2>&1; then + error[$i]="ipv$ipv: file mismatch from ${ad}" + continue + fi + + limit=$((2 * $filesize * 1024 * 1024)) + bytes=$(ip netns exec "$nsrt" nft list counter $family filter "check" | \ + grep "packets" | cut -d' ' -f4) + if [ -z "$dofast" ] && [ "$bytes" -lt "$limit" ]; then + + error[$i]="ipv$ipv: established bytes $bytes < $limit" + continue + fi + if [ -n "$dofast" ] && [ "$bytes" -gt "$((limit/2))" ]; then + # Significant reduction of bytes expected + error[$i]="ipv$ipv: counted bytes $bytes > $((limit/2))" + continue + fi + done + + if [ -n "${error[0]}" ]; then + if [[ "${error[0]#*:}" == "${error[1]#*:}" ]]; then + echo "ERROR: $desc: ipv4/6:${error[0]#*:}" 1>&2 + return 1 + fi + echo "ERROR: $desc: ${error[0]}" 1>&2 + lret=1 + fi + if [ -n "${error[1]}" ]; then + echo "ERROR: $desc: ${error[1]}" 1>&2 + lret=1 + fi + if [ $lret -eq 0 ]; then + echo "PASS: $desc" + fi + return $lret +} + +test_paths() { + local i1=$1 + local i2=$2 + local desc=$3 + local ns1=${nsa[$i1]} + local ns2=${nsa[$i2]} + + + if ! setup_nftables $i1 $i2; then + echo "ERROR: $desc: cannot setup nftables" 1>&2 + return 1 + fi + if ! test_tcp $i1 $i2 "" "$desc without fastpath"; then + return 1 + fi + + if ! setup_fastpath $i1 $i2 "" 2>/dev/null; then + return 0 + fi + if ! test_tcp $i1 $i2 "fast" "$desc with fastpath"; then + return 1 + fi + + if ! setup_fastpath $i1 $i2 "hw" 2>/dev/null; then + return 0 + fi + if ! test_tcp $i1 $i2 "fast" "$desc with hw_fastpath"; then + return 1 + fi + + return 0 + +} + +add_masq() +{ + if [[ $family != "bridge" ]]; then + ip netns exec "$nsrt" nft -f - <<-EOF + table ip nat { + chain postrouting { + type nat hook postrouting priority 0; + oifname ${BRWAN} masquerade + } + } + EOF + else + return 0 + fi +} + +add_zone() +{ + local devs=$1 + + if [[ $family == "bridge" ]]; then + ip netns exec "$nsrt" nft -f - <<-EOF + table ${family} filter { + chain preroutingzones { + type filter hook prerouting priority -300; + iif ${devs} ct zone set 23 + } + } + EOF + fi +} + +setup_nftables() +{ + local devs="{ ${vethrt[$1]} , ${vethrt[$2]} }" + local i1=$1 + local i2=$2 + + ip netns exec "$nsrt" nft flush ruleset + + if ! add_masq; then + return 1 + fi + + add_zone "${devs}" 2>/dev/null + + ip netns exec "$nsrt" nft -f - <<-EOF + table ${family} filter { + counter check { } + chain prerouting { + type filter hook prerouting priority 0; policy accept; + ct state established ip saddr ${AD4[$i1]} tcp dport 8080 counter name "check" + ct state established ip saddr ${AD4[$i2]} tcp sport 8080 counter name "check" + ct state established ip6 saddr ${AD6[$i1]} tcp dport 8080 counter name "check" + ct state established ip6 saddr ${AD6[$i2]} tcp sport 8080 counter name "check" + } + } + EOF +} + +setup_fastpath() +{ + local devs="{ ${vethrt[$1]} , ${vethrt[$2]} }" + local arg=$3 + local flags="" + + [[ "$arg" == "hw" ]] && flags="flags offload" + + ip netns exec "$nsrt" nft flush ruleset + + if ! add_masq; then + return 1 + fi + + add_zone "${devs}" 2>/dev/null + + ip netns exec "$nsrt" nft -f - <<-EOF + table ${family} filter { + counter check { } + flowtable f { + hook ingress priority filter + devices = ${devs} + ${flags} + } + chain forward { + type filter hook forward priority 0; policy accept; + counter name "check" + ct state established flow add @f + } + } + EOF +} + +test_1_unaware_bridge() +{ + local lret=0 + local i + + for i in $LAN1 $LAN2; do + set_client $i none + done + + test_paths $LAN1 $LAN2 "unaware bridge, without encaps, " + lret=$(($lret | $?)) + + for i in $LAN1 $LAN2; do + set_client $i q + done + + test_paths $LAN1 $LAN2 "unaware bridge, with single vlan encap, " + lret=$(($lret | $?)) + + for i in $LAN1 $LAN2; do + set_client $i qq + done + + # Skip testing double tagged packets on real hardware + if [ -n "$lan_all_veth" ] || [ -n "$noskip" ]; then + + test_paths $LAN1 $LAN2 "unaware bridge, with double q vlan encaps," + lret=$(($lret | $?)) + + for i in $LAN1 $LAN2; do + set_client $i ad + done + + test_paths $LAN1 $LAN2 "unaware bridge, with 802.1ad vlan encaps, " + lret=$(($lret | $?)) + + fi + # End Skip testing double tagged packets + + if [ -n "$(command -v pppd 2>/dev/null)" ] && + [ -n "$(command -v pppoe-server 2>/dev/null)" ]; then + # Start pppoe + + for i in $LAN1 $LAN2; do + set_client $i none noaddress + done + + if add_pppoe $LAN1 $LAN2 "$BRCL" "$BRCL" "unaware bridge, with pppoe encap"; then + test_paths $LAN1 $LAN2 "unaware bridge, with pppoe encap, " + lret=$(($lret | $?)) + fi + + del_pppoe $LAN1 $LAN2 "$BRCL" "$BRCL" + + for i in $LAN1 $LAN2; do + set_client $i q noaddress + done + + if add_pppoe $LAN1 $LAN2 "$BRCL" "$BRCL" "unaware bridge, with pppoe-in-q encaps"; then + test_paths $LAN1 $LAN2 "unaware bridge, with pppoe-in-q encaps, " + lret=$(($lret | $?)) + fi + + del_pppoe $LAN1 $LAN2 "$BRCL" "$BRCL" + + # End pppoe + fi + + for i in $LAN1 $LAN2; do + unset_client $i + done + return $lret +} + +test_2_aware_bridge() +{ + local lret=0 + local i + + for i in $LAN1 $LAN2; do + bridge -net "$nsrt" vlan add dev "${vethrt[$i]}" vid $VID1 pvid untagged + set_client $i none + done + test_paths $LAN1 $LAN2 "aware bridge, without/without vlan encap," + lret=$(($lret | $?)) + + i=$LAN1 + bridge -net "$nsrt" vlan del dev "${vethrt[$i]}" vid $VID1 pvid untagged + bridge -net "$nsrt" vlan add dev "${vethrt[$i]}" vid $VID1 + set_client $i q + + test_paths $LAN1 $LAN2 "aware bridge, with/without vlan encap, " + lret=$(($lret | $?)) + + i=$LAN2 + bridge -net "$nsrt" vlan del dev "${vethrt[$i]}" vid $VID1 pvid untagged + bridge -net "$nsrt" vlan add dev "${vethrt[$i]}" vid $VID1 + set_client $i q + + test_paths $LAN1 $LAN2 "aware bridge, with/with vlan encap, " + lret=$(($lret | $?)) + + i=$LAN1 + bridge -net "$nsrt" vlan del dev "${vethrt[$i]}" vid $VID1 + bridge -net "$nsrt" vlan add dev "${vethrt[$i]}" vid $VID1 pvid untagged + set_client $i none + + test_paths $LAN1 $LAN2 "aware bridge, without/with vlan encap, " + lret=$(($lret | $?)) + + i=$LAN1 + bridge -net "$nsrt" vlan del dev "${vethrt[$i]}" vid $VID1 pvid untagged + unset_client $i + i=$LAN2 + bridge -net "$nsrt" vlan del dev "${vethrt[$i]}" vid $VID1 + unset_client $i + + return $lret +} + +test_3_forward_without_vlandev() +{ + local wo=$1 + local lret=0 + local i + + [[ "$wo" == "" ]] && wo="without" + + for i in $LAN1 $LAN2; do + bridge -net "$nsrt" vlan add dev "${vethrt[$i]}" vid $VID1 pvid untagged + set_client $i none + done + + test_paths $LAN1 $WAN "forward, $wo vlan-device, without vlan encap, client1," + lret=$(($lret | $?)) + if [ -z "$lan_all_veth" ] || [ -n "$noskip" ]; then + test_paths $LAN2 $WAN "forward, $wo vlan-device, without vlan encap, client2," + lret=$(($lret | $?)) + fi + + for i in $LAN1 $LAN2; do + bridge -net "$nsrt" vlan del dev "${vethrt[$i]}" vid $VID1 pvid untagged + bridge -net "$nsrt" vlan add dev "${vethrt[$i]}" vid $VID1 + set_client $i q + done + + test_paths $LAN1 $WAN "forward, $wo vlan-device, with vlan encap, client1," + lret=$(($lret | $?)) + if [ -z "$lan_all_veth" ] || [ -n "$noskip" ]; then + test_paths $LAN2 $WAN "forward, $wo vlan-device, with vlan encap, client2," + lret=$(($lret | $?)) + fi + + for i in $LAN1 $LAN2; do + bridge -net "$nsrt" vlan del dev "${vethrt[$i]}" vid $VID1 + unset_client $i + done + return $lret +} + +test_4_forward_with_vlandev() +{ + test_3_forward_without_vlandev "with" + return $? +} + +test_5_bond() +{ + local lret=0 + local i + + for i in $LAN1; do + unset_client $i + done + return $lret +} + +ret=0 +### Start Initial Setup ### + +for i in 4 6; do + ip netns exec "$nsrt" sysctl -q net.ipv$i.conf.all.forwarding=1 +done + +### Use brwan to make sure software fastpath is ### +### direct xmit in other direction also ### + +ip -net "$nsrt" link add $BRWAN type bridge +ret=$(($ret | $?)) +ip -net "$nsrt" link set $BRWAN up +ret=$(($ret | $?)) +if [ $ret -ne 0 ]; then + echo "SKIP: Can't create bridge" + exit $ksft_skip +fi + +# If both lan clients are veth-devices, only test 1 in the forward path +if [ -z "${vethcl[$LAN1]}" ] && [ -z "${vethcl[$LAN2]}" ]; then + lan_all_veth=1 +fi + +for i in $WAN $LAN1 $LAN2; do + ns="${nsa[$i]}" + if [ -z "${vethcl[$i]}" ]; then + vethcl[$i]="veth${i}cl" + vethrt[$i]="veth${i}rt" + ip link add "${vethcl[$i]}" netns "$ns" type veth \ + peer name "${vethrt[$i]}" netns "$nsrt" + ret=$(($ret | $?)) + else # Use pair of interconnected hardware interfaces + ip link set "${vethrt[$i]}" netns "$nsrt" + ret=$(($ret | $?)) + ip link set "${vethcl[$i]}" netns "$ns" + ret=$(($ret | $?)) + fi +done +if [ $ret -ne 0 ]; then + echo "SKIP: (v)eth pairs cannot be used" + exit $ksft_skip +fi + +if [ -n "$showtree" ]; then + cat <<-EOF + Setup: + CLIENT 0 + ${vethcl[$WAN]} + | + ${vethrt[$WAN]} + WAN + ROUTER + LAN1 LAN2 + $(printf "%14.14s" ${vethrt[$LAN1]}) ${vethrt[$LAN2]} + | | + $(printf "%14.14s" ${vethcl[$LAN1]}) ${vethcl[$LAN2]} + CLIENT 1 CLIENT 2 + + EOF +fi + +for n in nsclientwan nsclientlan; do + routerside=""; clientside="" + for i in $WAN $LAN1 $LAN2; do + ns="${nsa[$i]}" + [[ "$ns" != "$n"* ]] && continue + mac=$(check_mac $ns ${vethcl[$i]} "$routerside $clientside") + ret=$(($ret | $?)) + clientside+=" $mac" + mac=$(check_mac $nsrt ${vethrt[$i]} "$clientside") + ret=$(($ret | $?)) + routerside+=" $mac" + done +done +if [ $ret -ne 0 ]; then + echo "SKIP: conflicting mac address" + exit $ksft_skip +fi + +set_pair_link up $WAN $LAN1 $LAN2 +ret=$(($ret | $?)) +if [ $ret -ne 0 ]; then + echo "SKIP: setting (v)eth pairs link up failed" + exit $ksft_skip +fi + +i=$WAN +ip -net "$nsrt" link set "${vethrt[$i]}" master $BRWAN +set_client $i none +add_addr $ADWAN "$BRWAN" + +family="bridge" +setup_nftables $LAN1 $LAN2 2>/dev/null +if [ $? -ne 0 ]; then + echo "INFO: Cannot add nftables table $family" + tests[1]=""; test[2]="" +fi +family="inet" +if ! setup_nftables $WAN $LAN1 2>/dev/null; then + echo "INFO: Cannot add nftables table $family" + tests[3]=""; test[4]=""; tests[5]="" +fi + +### End Initial Setup ### + +if [ -n "${tests[1]}" ]; then + # Setup brlan as vlan unaware bridge + family="bridge" + ip -net "$nsrt" link add $BRLAN type bridge + ip -net "$nsrt" link set $BRLAN up + for i in $LAN1 $LAN2; do + ip -net "$nsrt" link set "${vethrt[$i]}" master $BRLAN + done + test_1_unaware_bridge + ret=$(($ret | $?)) + ip -net "$nsrt" link del $BRLAN type bridge +fi + +if [ -n "${tests[2]}" ] || [ -n "${tests[3]}" ] || [ -n "${tests[4]}" ]; then + # Setup brlan as vlan aware bridge + family="bridge" + + ip -net "$nsrt" link add $BRLAN type bridge vlan_filtering 1 vlan_default_pvid 0 + ip -net "$nsrt" link set $BRLAN up + bridge -net "$nsrt" vlan add dev $BRLAN vid $VID1 pvid untagged self + add_addr $ADLAN "$BRLAN" + for i in $LAN1 $LAN2; do + ip -net "$nsrt" link set "${vethrt[$i]}" master $BRLAN + done + + if [ -n "${tests[2]}" ]; then + test_2_aware_bridge + ret=$(($ret | $?)) + fi + + family="inet" + + if [ -n "${tests[3]}" ]; then + test_3_forward_without_vlandev + ret=$(($ret | $?)) + fi + + if [ -n "${tests[4]}" ]; then + # Setup vlan-device linked to brlan master port + del_addr $ADLAN "$BRLAN" + ip -net "$nsrt" link set $BRLAN down + bridge -net "$nsrt" vlan del dev $BRLAN vid $VID1 pvid untagged self + bridge -net "$nsrt" vlan add dev $BRLAN vid $VID1 self + ip -net "$nsrt" link add link $BRLAN name $BRLAN.$VID1 type vlan id $VID1 + ip -net "$nsrt" link set $BRLAN up + ip -net "$nsrt" link set "$BRLAN.$VID1" up + add_addr $ADLAN "$BRLAN.$VID1" + test_4_forward_with_vlandev + ret=$(($ret | $?)) + fi + + ip -net "$nsrt" link del $BRLAN type bridge +fi + +### Finish tests ### + +ip -net "$nsrt" link del $BRWAN type bridge + +for i in $WAN $LAN1 $LAN2; do + unset_client $i +done + +if [ $ret -eq 0 ]; then + echo "PASS: all tests passed" +else + echo "ERROR: bridge fastpath test has failed" +fi + +exit $ret -- 2.47.1

5 months, 3 weeks

3
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror