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

[PATCH net-next] selftests/net: packetdrill: report benign debug flakes as xfail

by Willem de Bruijn

From: Willem de Bruijn <willemb(a)google.com> A few recently added packetdrill tests that are known time sensitive (e.g., because testing timestamping) occasionally fail in debug mode: https://netdev.bots.linux.dev/contest.html?executor=vmksft-packetdrill-dbg These failures are well understood. Correctness of the tests is verified in non-debug mode. Continue running in debug mode also, to keep coverage with debug instrumentation. But, only in debug mode, mark these tests with well understood timing issues as XFAIL (known failing) rather than FAIL when failing. Introduce an allow list xfail_list with known cases. Expand the ktap infrastructure with XFAIL support. Fixes: eab35989cc37 ("selftests/net: packetdrill: import tcp/fast_recovery, tcp/nagle, tcp/timestamping") Reported-by: Jakub Kicinski <kuba(a)kernel.org> Closes: https://lore.kernel.org/netdev/20241218100013.0c698629@kernel.org/ Signed-off-by: Willem de Bruijn <willemb(a)google.com> --- .../selftests/kselftest/ktap_helpers.sh | 15 ++++++++++-- .../selftests/net/packetdrill/ksft_runner.sh | 23 +++++++++++++++---- 2 files changed, 31 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/kselftest/ktap_helpers.sh b/tools/testing/selftests/kselftest/ktap_helpers.sh index 79a125eb24c2..05a461890671 100644 --- a/tools/testing/selftests/kselftest/ktap_helpers.sh +++ b/tools/testing/selftests/kselftest/ktap_helpers.sh @@ -7,6 +7,7 @@ KTAP_TESTNO=1 KTAP_CNT_PASS=0 KTAP_CNT_FAIL=0 +KTAP_CNT_XFAIL=0 KTAP_CNT_SKIP=0 KSFT_PASS=0 @@ -69,6 +70,16 @@ ktap_test_skip() { KTAP_CNT_SKIP=$((KTAP_CNT_SKIP+1)) } +ktap_test_xfail() { + description="$1" + + result="ok" + directive="XFAIL" + __ktap_test "$result" "$description" "$directive" + + KTAP_CNT_XFAIL=$((KTAP_CNT_XFAIL+1)) +} + ktap_test_fail() { description="$1" @@ -99,7 +110,7 @@ ktap_exit_fail_msg() { ktap_finished() { ktap_print_totals - if [ $((KTAP_CNT_PASS + KTAP_CNT_SKIP)) -eq "$KSFT_NUM_TESTS" ]; then + if [ $((KTAP_CNT_PASS + KTAP_CNT_SKIP + KTAP_CNT_XFAIL)) -eq "$KSFT_NUM_TESTS" ]; then exit "$KSFT_PASS" else exit "$KSFT_FAIL" @@ -107,5 +118,5 @@ ktap_finished() { } ktap_print_totals() { - echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:0 xpass:0 skip:$KTAP_CNT_SKIP error:0" + echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:$KTAP_CNT_XFAIL xpass:0 skip:$KTAP_CNT_SKIP error:0" } diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh index 4071c133f29e..ff989c325eef 100755 --- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh +++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh @@ -23,7 +23,7 @@ if [ $# -ne 1 ]; then ktap_exit_fail_msg "usage: $0 <script>" exit "$KSFT_FAIL" fi -script="$1" +script="$(basename $1)" if [ -z "$(which packetdrill)" ]; then ktap_skip_all "packetdrill not found in PATH" @@ -31,16 +31,29 @@ if [ -z "$(which packetdrill)" ]; then fi declare -a optargs +failfunc=ktap_test_fail + if [[ -n "${KSFT_MACHINE_SLOW}" ]]; then optargs+=('--tolerance_usecs=14000') + + # xfail tests that are known flaky with dbg config, not fixable. + # still run them for coverage (and expect 100% pass without dbg). + declare -ar xfail_list=( + "tcp_fast_recovery_prr-ss.*.pkt" + "tcp_timestamping.*.pkt" + "tcp_user_timeout_user-timeout-probe.pkt" + "tcp_zerocopy_epoll_.*.pkt" + ) + readonly xfail_regex="^($(printf '%s|' "${xfail_list[@]}"))$" + [[ "$script" =~ ${xfail_regex} ]] && failfunc=ktap_test_xfail fi ktap_print_header ktap_set_plan 2 -unshare -n packetdrill ${ipv4_args[@]} ${optargs[@]} $(basename $script) > /dev/null \ - && ktap_test_pass "ipv4" || ktap_test_fail "ipv4" -unshare -n packetdrill ${ipv6_args[@]} ${optargs[@]} $(basename $script) > /dev/null \ - && ktap_test_pass "ipv6" || ktap_test_fail "ipv6" +unshare -n packetdrill ${ipv4_args[@]} ${optargs[@]} $script > /dev/null \ + && ktap_test_pass "ipv4" || $failfunc "ipv4" +unshare -n packetdrill ${ipv6_args[@]} ${optargs[@]} $script > /dev/null \ + && ktap_test_pass "ipv6" || $failfunc "ipv6" ktap_finished -- 2.47.1.613.gc27f4b7a9f-goog

6 months

2
1
0 0

[PATCH v6 0/5] introduce PIDFD_SELF* sentinels

by Lorenzo Stoakes

If you wish to utilise a pidfd interface to refer to the current process or thread it is rather cumbersome, requiring something like: int pidfd = pidfd_open(getpid(), 0 or PIDFD_THREAD); ... close(pidfd); Or the equivalent call opening /proc/self. It is more convenient to use a sentinel value to indicate to an interface that accepts a pidfd that we simply wish to refer to the current process thread. This series introduces sentinels for this purposes which can be passed as the pidfd in this instance rather than having to establish a dummy fd for this purpose. It is useful to refer to both the current thread from the userland's perspective for which we use PIDFD_SELF, and the current process from the userland's perspective, for which we use PIDFD_SELF_PROCESS. There is unfortunately some confusion between the kernel and userland as to what constitutes a process - a thread from the userland perspective is a process in userland, and a userland process is a thread group (more specifically the thread group leader from the kernel perspective). We therefore alias things thusly: * PIDFD_SELF_THREAD aliased by PIDFD_SELF - use PIDTYPE_PID. * PIDFD_SELF_THREAD_GROUP alised by PIDFD_SELF_PROCESS - use PIDTYPE_TGID. In all of the kernel code we refer to PIDFD_SELF_THREAD and PIDFD_SELF_THREAD_GROUP. However we expect users to use PIDFD_SELF and PIDFD_SELF_PROCESS. This matters for cases where, for instance, a user unshare()'s FDs or does thread-specific signal handling and where the user would be hugely confused if the FDs referenced or signal processed referred to the thread group leader rather than the individual thread. We ensure that pidfd_send_signal() and pidfd_getfd() work correctly, and assert as much in selftests. All other interfaces except setns() will work implicitly with this new interface, however it doesn't make sense to test waitid(P_PIDFD, ...) as waiting on ourselves is a blocking operation. In the case of setns() we explicitly disallow use of PIDFD_SELF* as it doesn't make sense to obtain the namespaces of our own process, and it would require work to implement this functionality there that would be of no use. We also do not provide the ability to utilise PIDFD_SELF* in ordinary fd operations such as open() or poll(), as this would require extensive work and be of no real use. v6: * Avoid static inline in UAPI header as suggested by Pedro. * Place PIDFD_SELF values out of range of errors and any other sentinel as suggested by Pedro. v5: * Fixup self test dependencies on pidfd/pidfd.h. https://lore.kernel.org/linux-mm/cover.1729848252.git.lorenzo.stoakes@oracl… v4: * Avoid returning an fd in the __pidfd_get_pid() function as pointed out by Christian, instead simply always pin the pid and maintain fd scope in the helper alone. * Add wrapper header file in tools/include/linux to allow for import of UAPI pidfd.h header without encountering the collision between system fcntl.h and linux/fcntl.h as discussed with Shuah and John. * Fixup tests to import the UAPI pidfd.h header working around conflicts between system fcntl.h and linux/fcntl.h which the UAPI pidfd.h imports, as reported by Shuah. * Use an int for pidfd_is_self_sentinel() to avoid any dependency on stdbool.h in userland. https://lore.kernel.org/linux-mm/cover.1729198898.git.lorenzo.stoakes@oracl… v3: * Do not fput() an invalid fd as reported by kernel test bot. * Fix unintended churn from moving variable declaration. https://lore.kernel.org/linux-mm/cover.1729073310.git.lorenzo.stoakes@oracl… v2: * Fix tests as reported by Shuah. * Correct RFC version lore link. https://lore.kernel.org/linux-mm/cover.1728643714.git.lorenzo.stoakes@oracl… Non-RFC v1: * Removed RFC tag - there seems to be general consensus that this change is a good idea, but perhaps some debate to be had on implementation. It seems sensible then to move forward with the RFC flag removed. * Introduced PIDFD_SELF_THREAD, PIDFD_SELF_THREAD_GROUP and their aliases PIDFD_SELF and PIDFD_SELF_PROCESS respectively. * Updated testing accordingly. https://lore.kernel.org/linux-mm/cover.1728578231.git.lorenzo.stoakes@oracl… RFC version: https://lore.kernel.org/linux-mm/cover.1727644404.git.lorenzo.stoakes@oracl… Lorenzo Stoakes (5): pidfd: extend pidfd_get_pid() and de-duplicate pid lookup pidfd: add PIDFD_SELF_* sentinels to refer to own thread/process tools: testing: separate out wait_for_pid() into helper header selftests: pidfd: add pidfd.h UAPI wrapper selftests: pidfd: add tests for PIDFD_SELF_* include/linux/pid.h | 34 ++++- include/uapi/linux/pidfd.h | 10 ++ kernel/exit.c | 4 +- kernel/nsproxy.c | 1 + kernel/pid.c | 65 +++++--- kernel/signal.c | 29 +--- tools/include/linux/pidfd.h | 14 ++ tools/testing/selftests/cgroup/test_kill.c | 2 +- .../pid_namespace/regression_enomem.c | 2 +- tools/testing/selftests/pidfd/Makefile | 3 +- tools/testing/selftests/pidfd/pidfd.h | 28 +--- .../selftests/pidfd/pidfd_getfd_test.c | 141 ++++++++++++++++++ tools/testing/selftests/pidfd/pidfd_helpers.h | 39 +++++ .../selftests/pidfd/pidfd_setns_test.c | 11 ++ tools/testing/selftests/pidfd/pidfd_test.c | 76 ++++++++-- 15 files changed, 371 insertions(+), 88 deletions(-) create mode 100644 tools/include/linux/pidfd.h create mode 100644 tools/testing/selftests/pidfd/pidfd_helpers.h -- 2.47.0

6 months

3
13
0 0

[PATCH v4 00/14] iommufd: Add vIOMMU infrastructure (Part-3: vEVENTQ)

by Nicolin Chen

As the vIOMMU infrastructure series part-3, this introduces a new vEVENTQ object. The existing FAULT object provides a nice notification pathway to the user space with a queue already, so let vEVENTQ reuse that. Mimicing the HWPT structure, add a common EVENTQ structure to support its derivatives: IOMMUFD_OBJ_FAULT (existing) and IOMMUFD_OBJ_VEVENTQ (new). An IOMMUFD_CMD_VEVENTQ_ALLOC is introduced to allocate vEVENTQ object for vIOMMUs. One vIOMMU can have multiple vEVENTQs in different types but can not support multiple vEVENTQs in the same type. The forwarding part is fairly simple but might need to replace a physical device ID with a virtual device ID in a driver-level event data structure. So, this also adds some helpers for drivers to use. As usual, this series comes with the selftest coverage for this new ioctl and with a real world use case in the ARM SMMUv3 driver. This is on Github: https://github.com/nicolinc/iommufd/commits/iommufd_veventq-v4 Testing with RMR patches for MSI: https://github.com/nicolinc/iommufd/commits/iommufd_veventq-v4-with-rmr Paring QEMU branch for testing: https://github.com/nicolinc/qemu/commits/wip/for_iommufd_veventq-v4 Changelog v4 * Rename "vIRQ" to "vEVENTQ" * Use flexible array in struct iommufd_vevent * Add the new ioctl command to union ucmd_buffer * Fix the alphabetical order in union ucmd_buffer too * Rename _TYPE_NONE to _TYPE_DEFAULT aligning with vIOMMU naming v3 https://lore.kernel.org/all/cover.1734477608.git.nicolinc@nvidia.com/ * Rebase on Will's for-joerg/arm-smmu/updates for arm_smmu_event series * Add "Reviewed-by" lines from Kevin * Fix typos in comments, kdocs, and jump tags * Add a patch to sort struct iommufd_ioctl_op * Update iommufd's userpsace-api documentation * Update uAPI kdoc to quote SMMUv3 offical spec * Drop the unused workqueue in struct iommufd_virq * Drop might_sleep() in iommufd_viommu_report_irq() helper * Add missing "break" in iommufd_viommu_get_vdev_id() helper * Shrink the scope of the vmaster's read lock in SMMUv3 driver * Pass in two arguments to iommufd_eventq_virq_handler() helper * Move "!ops || !ops->read" validation into iommufd_eventq_init() * Move "fault->ictx = ictx" closer to iommufd_ctx_get(fault->ictx) * Update commit message for arm_smmu_attach_prepare/commit_vmaster() * Keep "iommufd_fault" as-is and rename "iommufd_eventq_virq" to just "iommufd_virq" v2 https://lore.kernel.org/all/cover.1733263737.git.nicolinc@nvidia.com/ * Rebase on v6.13-rc1 * Add IOPF and vIRQ in iommufd.rst (userspace-api) * Add a proper locking in iommufd_event_virq_destroy * Add iommufd_event_virq_abort with a lockdep_assert_held * Rename "EVENT_*" to "EVENTQ_*" to describe the objects better * Reorganize flows in iommufd_eventq_virq_alloc for abort() to work * Adde struct arm_smmu_vmaster to store vSID upon attaching to a nested domain, calling a newly added iommufd_viommu_get_vdev_id helper * Adde an arm_vmaster_report_event helper in arm-smmu-v3-iommufd file to simplify the routine in arm_smmu_handle_evt() of the main driver v1 https://lore.kernel.org/all/cover.1724777091.git.nicolinc@nvidia.com/ Thanks! Nicolin Nicolin Chen (14): iommufd: Keep IOCTL list in an alphabetical order iommufd/fault: Add an iommufd_fault_init() helper iommufd/fault: Move iommufd_fault_iopf_handler() to header iommufd: Abstract an iommufd_eventq from iommufd_fault iommufd: Rename fault.c to eventq.c iommufd: Add IOMMUFD_OBJ_VEVENTQ and IOMMUFD_CMD_VEVENTQ_ALLOC iommufd/viommu: Add iommufd_viommu_get_vdev_id helper iommufd/viommu: Add iommufd_viommu_report_event helper iommufd/selftest: Require vdev_id when attaching to a nested domain iommufd/selftest: Add IOMMU_TEST_OP_TRIGGER_VEVENT for vEVENTQ coverage iommufd/selftest: Add IOMMU_VEVENTQ_ALLOC test coverage Documentation: userspace-api: iommufd: Update FAULT and VEVENTQ iommu/arm-smmu-v3: Introduce struct arm_smmu_vmaster iommu/arm-smmu-v3: Report events that belong to devices attached to vIOMMU drivers/iommu/iommufd/Makefile | 2 +- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 30 ++ drivers/iommu/iommufd/iommufd_private.h | 116 ++++++- drivers/iommu/iommufd/iommufd_test.h | 10 + include/linux/iommufd.h | 22 ++ include/uapi/linux/iommufd.h | 46 +++ tools/testing/selftests/iommu/iommufd_utils.h | 65 ++++ .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 65 ++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 90 ++++-- drivers/iommu/iommufd/driver.c | 60 ++++ drivers/iommu/iommufd/{fault.c => eventq.c} | 298 ++++++++++++++---- drivers/iommu/iommufd/hw_pagetable.c | 6 +- drivers/iommu/iommufd/main.c | 23 +- drivers/iommu/iommufd/selftest.c | 53 ++++ drivers/iommu/iommufd/viommu.c | 2 + tools/testing/selftests/iommu/iommufd.c | 27 ++ .../selftests/iommu/iommufd_fail_nth.c | 7 + Documentation/userspace-api/iommufd.rst | 16 + 18 files changed, 820 insertions(+), 118 deletions(-) rename drivers/iommu/iommufd/{fault.c => eventq.c} (55%) base-commit: e94dc6ddda8dd3770879a132d577accd2cce25f9 -- 2.43.0

6 months

2
30
0 0

[PATCH] selftests/nolibc: start qemu with 1 GiB of memory

by Thomas Weißschuh

Recently the loongarch defconfig stopped working with the default 128 MiB of memory. The VM just spins infinitively. Increasing the available memory to 1 GiB, similar to s390, fixes the issue. To avoid having to do this for each architecture on its own, proactively apply to all architectures. Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- tools/testing/selftests/nolibc/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index 8de98ea7af8071caa0597aa7b86d91a2d1d50e68..e92e0b88586111072a0e043cb15f3b59cf42c3a6 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -130,9 +130,9 @@ QEMU_ARGS_ppc = -M g3beige -append "console=ttyS0 panic=-1 $(TEST:%=NOLIB QEMU_ARGS_ppc64 = -M powernv -append "console=hvc0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_ppc64le = -M powernv -append "console=hvc0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_riscv = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_s390 = -M s390-ccw-virtio -m 1G -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_s390 = -M s390-ccw-virtio -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_loongarch = -M virt -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS = $(QEMU_ARGS_$(XARCH)) $(QEMU_ARGS_BIOS) $(QEMU_ARGS_EXTRA) +QEMU_ARGS = -m 1G $(QEMU_ARGS_$(XARCH)) $(QEMU_ARGS_BIOS) $(QEMU_ARGS_EXTRA) # OUTPUT is only set when run from the main makefile, otherwise # it defaults to this nolibc directory. --- base-commit: 8cf0b93919e13d1e8d4466eb4080a4c4d9d66d7b change-id: 20241007-nolibc-qemu-mem-5ed605520472 Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

6 months

3
2
0 0

[PATCH v2 0/8] mm/damon: remove DAMON debugfs interface

by SeongJae Park

DAMON debugfs interface was the only user interface of DAMON at the beginning[1]. However, it turned out the interface would be not good enough for long-term flexibility and stability. In Feb 2022[2], we therefore introduced DAMON sysfs interface as an alternative user interface that aims long-term flexibility and stability. With its introduction, DAMON debugfs interface has announced to be deprecated in near future. In Feb 2023[3], we announced the official deprecation of DAMON debugfs interface. In Jan 2024[4], we further made the deprecation difficult to be ignored. In Oct 2024[5], we posted an RFC version of this patch series as the last notice. And as of this writing, no problem or concerns about the removal plan have reported. Apparently users are already moved to the alternative, or made good plans for the change. Remove the DAMON debugfs interface code from the tree. Given the past timeline and the absence of reported problems or concerns, it is safe enough to be done. [1] https://lore.kernel.org/20210716081449.22187-1-sj38.park@gmail.com [2] https://lore.kernel.org/20220228081314.5770-1-sj@kernel.org [3] https://lore.kernel.org/20230209192009.7885-1-sj@kernel.org [4] https://lore.kernel.org/20240130013549.89538-1-sj@kernel.org [5] https://lore.kernel.org/20241015175412.60563-1-sj@kernel.org Revision History ---------------- Changes from v1 (https://lore.kernel.org/20250101213527.74203-1-sj@kernel.org) - Remove debugfs usage section and references from translations (https://lore.kernel.org/20250106183944.103569-1-sj@kernel.org) Changes from RFC (https://lore.kernel.org/20241015175412.60563-1-sj@kernel.org) - Rebased on latest mm-unstable - Update and wordsmith commit messages SeongJae Park (8): Docs/translations/*/admin-guide/mm/damon/usage: remove DAMON debugfs interface documentation Docs/admin-guide/mm/damon/usage: remove DAMON debugfs interface documentation Docs/mm/damon/design: update for removal of DAMON debugfs interface selftests/damon/config: remove configs for DAMON debugfs interface selftests selftests/damon: remove tests for DAMON debugfs interface kunit: configs: remove configs for DAMON debugfs interface tests mm/damon: remove DAMON debugfs interface kunit tests mm/damon: remove DAMON debugfs interface Documentation/admin-guide/mm/damon/usage.rst | 309 ----- Documentation/mm/damon/design.rst | 23 +- .../zh_CN/admin-guide/mm/damon/usage.rst | 248 +--- .../zh_TW/admin-guide/mm/damon/usage.rst | 248 +--- mm/damon/Kconfig | 30 - mm/damon/Makefile | 1 - mm/damon/dbgfs.c | 1148 ----------------- mm/damon/tests/.kunitconfig | 7 - mm/damon/tests/dbgfs-kunit.h | 173 --- tools/testing/kunit/configs/all_tests.config | 3 - tools/testing/selftests/damon/.gitignore | 3 - tools/testing/selftests/damon/Makefile | 11 +- tools/testing/selftests/damon/config | 1 - .../testing/selftests/damon/debugfs_attrs.sh | 17 - .../debugfs_duplicate_context_creation.sh | 27 - .../selftests/damon/debugfs_empty_targets.sh | 21 - .../damon/debugfs_huge_count_read_write.sh | 22 - .../damon/debugfs_rm_non_contexts.sh | 19 - .../selftests/damon/debugfs_schemes.sh | 19 - .../selftests/damon/debugfs_target_ids.sh | 19 - .../damon/debugfs_target_ids_pid_leak.c | 68 - .../damon/debugfs_target_ids_pid_leak.sh | 22 - ...fs_target_ids_read_before_terminate_race.c | 80 -- ...s_target_ids_read_before_terminate_race.sh | 14 - .../selftests/damon/huge_count_read_write.c | 46 - 25 files changed, 13 insertions(+), 2566 deletions(-) delete mode 100644 mm/damon/dbgfs.c delete mode 100644 mm/damon/tests/dbgfs-kunit.h delete mode 100755 tools/testing/selftests/damon/debugfs_attrs.sh delete mode 100755 tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh delete mode 100755 tools/testing/selftests/damon/debugfs_empty_targets.sh delete mode 100755 tools/testing/selftests/damon/debugfs_huge_count_read_write.sh delete mode 100755 tools/testing/selftests/damon/debugfs_rm_non_contexts.sh delete mode 100755 tools/testing/selftests/damon/debugfs_schemes.sh delete mode 100755 tools/testing/selftests/damon/debugfs_target_ids.sh delete mode 100644 tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c delete mode 100755 tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh delete mode 100644 tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c delete mode 100755 tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh delete mode 100644 tools/testing/selftests/damon/huge_count_read_write.c -- 2.39.5

6 months

1
4
0 0

[RFC PATCH 0/2] ptp: add PTP_SYS_OFFSET_STAT ioctl, support it in virtio_rtc

by Peter Hilber

This RFC patch series proposes a new ioctl PTP_SYS_OFFSET_STAT and adds support for it in the proposed virtio_rtc driver [1]. The new PTP_SYS_OFFSET_STAT ioctl provides a cross-timestamp like PTP_SYS_OFFSET_PRECISE2, plus any the following status information (for now): - for UTC timescale clocks: leap second related status, - clock accuracy. The second commit adds support for the ioctl in the proposed virtio_rtc driver, and hence depends on the patch series "Add virtio_rtc module" [1]. [1] https://lore.kernel.org/lkml/20241219201118.2233-1-quic_philber@quicinc.com… Signed-off-by: Peter Hilber <quic_philber(a)quicinc.com> Peter Hilber (2): ptp: add PTP_SYS_OFFSET_STAT for xtstamping with status virtio_rtc: Support PTP_SYS_OFFSET_STAT ioctl drivers/ptp/ptp_chardev.c | 39 ++++++++ drivers/ptp/ptp_clock.c | 9 ++ drivers/virtio/Kconfig | 4 +- drivers/virtio/virtio_rtc_driver.c | 122 +++++++++++++++++++++++- drivers/virtio/virtio_rtc_internal.h | 3 +- drivers/virtio/virtio_rtc_ptp.c | 25 +++-- include/linux/ptp_clock_kernel.h | 31 ++++++ include/uapi/linux/ptp_clock.h | 130 +++++++++++++++++++++++++- tools/testing/selftests/ptp/Makefile | 2 +- tools/testing/selftests/ptp/testptp.c | 126 ++++++++++++++++++++++++- 10 files changed, 471 insertions(+), 20 deletions(-) base-commit: 8a8009abbfa04e58f1b01b20534cac9e8fe61a46 -- 2.43.0

6 months

2
8
0 0

[PATCH net-next] selftests: drv-net: test drivers sleeping in ndo_get_stats64

by Jakub Kicinski

Most of our tests use rtnetlink to read device stats, so they don't expose the drivers much to paths in which device stats are read under RCU. Add tests which hammer profcs reads to make sure drivers: - don't sleep while reporting stats, - can handle parallel reads, - can handle device going down while reading. Set ifname on the env class in NetDrvEnv, we already do that in NetDrvEpEnv. KTAP version 1 1..7 ok 1 stats.check_pause ok 2 stats.check_fec ok 3 stats.pkt_byte_sum ok 4 stats.qstat_by_ifindex ok 5 stats.check_down ok 6 stats.procfs_hammer # completed up/down cycles: 6 ok 7 stats.procfs_downup_hammer # Totals: pass:7 fail:0 xfail:0 xpass:0 skip:0 error:0 Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: willemb(a)google.com CC: petrm(a)nvidia.com CC: linux-kselftest(a)vger.kernel.org --- .../selftests/drivers/net/lib/py/env.py | 1 + tools/testing/selftests/drivers/net/stats.py | 94 ++++++++++++++++++- tools/testing/selftests/net/lib/py/ksft.py | 5 + 3 files changed, 97 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py index fea343f209ea..987e452d3a45 100644 --- a/tools/testing/selftests/drivers/net/lib/py/env.py +++ b/tools/testing/selftests/drivers/net/lib/py/env.py @@ -48,6 +48,7 @@ from .remote import Remote else: self._ns = NetdevSimDev(**kwargs) self.dev = self._ns.nsims[0].dev + self.ifname = self.dev['ifname'] self.ifindex = self.dev['ifindex'] def __enter__(self): diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py index 031ac9def6c0..55d647c006ed 100755 --- a/tools/testing/selftests/drivers/net/stats.py +++ b/tools/testing/selftests/drivers/net/stats.py @@ -2,12 +2,15 @@ # SPDX-License-Identifier: GPL-2.0 import errno +import subprocess +import time from lib.py import ksft_run, ksft_exit, ksft_pr -from lib.py import ksft_ge, ksft_eq, ksft_in, ksft_true, ksft_raises, KsftSkipEx, KsftXfailEx +from lib.py import ksft_ge, ksft_eq, ksft_is, ksft_in, ksft_lt, ksft_true, ksft_raises +from lib.py import KsftSkipEx, KsftXfailEx from lib.py import ksft_disruptive from lib.py import EthtoolFamily, NetdevFamily, RtnlFamily, NlError from lib.py import NetDrvEnv -from lib.py import ip, defer +from lib.py import cmd, ip, defer ethnl = EthtoolFamily() netfam = NetdevFamily() @@ -174,10 +177,95 @@ rtnl = RtnlFamily() netfam.qstats_get({"ifindex": cfg.ifindex, "scope": "queue"}, dump=True) +def __run_inf_loop(body): + body = body.strip() + if body[-1] != ';': + body += ';' + + return subprocess.Popen(f"while true; do {body} done", shell=True, + stdout=subprocess.PIPE, stderr=subprocess.PIPE) + + +def __stats_increase_sanely(old, new) -> None: + for k in old.keys(): + ksft_ge(new[k], old[k]) + ksft_lt(new[k] - old[k], 1 << 31, comment="likely wrapping error") + + +def procfs_hammer(cfg) -> None: + """ + Reading stats via procfs only holds the RCU lock, which is not an exclusive + lock, make sure drivers can handle parallel reads of stats. + """ + one = __run_inf_loop("cat /proc/net/dev") + defer(one.kill) + two = __run_inf_loop("cat /proc/net/dev") + defer(two.kill) + + time.sleep(1) + # Make sure the processes are running + ksft_is(one.poll(), None) + ksft_is(two.poll(), None) + + rtstat1 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + time.sleep(2) + rtstat2 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + __stats_increase_sanely(rtstat1, rtstat2) + # defers will kill the loops + + +@ksft_disruptive +def procfs_downup_hammer(cfg) -> None: + """ + Reading stats via procfs only holds the RCU lock, drivers often try + to sleep when reading the stats, or don't protect against races. + """ + # Max out the queues, we'll flip between max an 1 + channels = ethnl.channels_get({'header': {'dev-index': cfg.ifindex}}) + if channels['combined-count'] == 0: + rx_type = 'rx' + else: + rx_type = 'combined' + cur_queue_cnt = channels[f'{rx_type}-count'] + max_queue_cnt = channels[f'{rx_type}-max'] + + cmd(f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}") + defer(cmd, f"ethtool -L {cfg.ifname} {rx_type} {cur_queue_cnt}") + + # Real test stats + stats = __run_inf_loop("cat /proc/net/dev") + defer(stats.kill) + + ipset = f"ip link set dev {cfg.ifname}" + defer(ip, f"link set dev {cfg.ifname} up") + # The "echo -n 1" lets us count iterations below + updown = f"{ipset} down; sleep 0.05; {ipset} up; sleep 0.05; " + \ + f"ethtool -L {cfg.ifname} {rx_type} 1; " + \ + f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}; " + \ + "echo -n 1" + updown = __run_inf_loop(updown) + kill_updown = defer(updown.kill) + + time.sleep(1) + # Make sure the processes are running + ksft_is(stats.poll(), None) + ksft_is(updown.poll(), None) + + rtstat1 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + # We're looking for crashes, give it extra time + time.sleep(9) + rtstat2 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + __stats_increase_sanely(rtstat1, rtstat2) + + kill_updown.exec() + stdout, _ = updown.communicate(timeout=5) + ksft_pr("completed up/down cycles:", len(stdout.decode('utf-8'))) + + def main() -> None: with NetDrvEnv(__file__, queue_count=100) as cfg: ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex, - check_down], + check_down, procfs_hammer, procfs_downup_hammer], args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index 477ae76de93d..3efe005436cd 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -71,6 +71,11 @@ KSFT_DISRUPTIVE = True _fail("Check failed", a, "not in", b, comment) +def ksft_is(a, b, comment=""): + if a is not b: + _fail("Check failed", a, "is not", b, comment) + + def ksft_ge(a, b, comment=""): if a < b: _fail("Check failed", a, "<", b, comment) -- 2.47.1

6 months

3
3
0 0

[PATCH v3 00/14] iommufd: Add vIOMMU infrastructure (Part-3: vIRQ)

by Nicolin Chen

As the part-3 of the vIOMMU infrastructure, this series introduces a vIRQ object. The existing FAULT object provides a nice notification pathway to the user space already, so let vIRQ reuse the infrastructure. Mimicing the HWPT structure, add a common EVENTQ structure to support its derivatives: IOMMUFD_OBJ_FAULT (existing) and IOMMUFD_OBJ_VIRQ (new). IOMMUFD_CMD_VIRQ_ALLOC is introduced to allocate vIRQ objects for vIOMMUs. One vIOMMU can have multiple vIRQs in different types but can not support multiple vIRQs with the same types. The forwarding part is fairly simple but might need to replace a physical device ID with a virtual device ID in a driver-level IRQ data structure. So, this comes with some helpers for drivers to use. As usual, this series comes with the selftest coverage for this new vIRQ, and with a real world use case in the ARM SMMUv3 driver. This is on Github: https://github.com/nicolinc/iommufd/commits/iommufd_virq-v3 Testing with RMR patches for MSI: https://github.com/nicolinc/iommufd/commits/iommufd_virq-v3-with-rmr Paring QEMU branch for testing: https://github.com/nicolinc/qemu/commits/wip/for_iommufd_virq-v3 Changelog v3 * Rebase on Will's for-joerg/arm-smmu/updates for arm_smmu_event series * Add "Reviewed-by" lines from Kevin * Fix typos in comments, kdocs, and jump tags * Add a patch to sort struct iommufd_ioctl_op * Update iommufd's userpsace-api documentation * Update uAPI kdoc to quote SMMUv3 offical spec * Drop the unused workqueue in struct iommufd_virq * Drop might_sleep() in iommufd_viommu_report_irq() helper * Add missing "break" in iommufd_viommu_get_vdev_id() helper * Shrink the scope of the vmaster's read lock in SMMUv3 driver * Pass in two arguments to iommufd_eventq_virq_handler() helper * Move "!ops || !ops->read" validation into iommufd_eventq_init() * Move "fault->ictx = ictx" closer to iommufd_ctx_get(fault->ictx) * Update commit message for arm_smmu_attach_prepare/commit_vmaster() * Keep "iommufd_fault" as-is and rename "iommufd_eventq_virq" to just "iommufd_virq" v2 https://lore.kernel.org/all/cover.1733263737.git.nicolinc@nvidia.com/ * Rebase on v6.13-rc1 * Add IOPF and vIRQ in iommufd.rst (userspace-api) * Add a proper locking in iommufd_event_virq_destroy * Add iommufd_event_virq_abort with a lockdep_assert_held * Rename "EVENT_*" to "EVENTQ_*" to describe the objects better * Reorganize flows in iommufd_eventq_virq_alloc for abort() to work * Adde struct arm_smmu_vmaster to store vSID upon attaching to a nested domain, calling a newly added iommufd_viommu_get_vdev_id helper * Adde an arm_vmaster_report_event helper in arm-smmu-v3-iommufd file to simplify the routine in arm_smmu_handle_evt() of the main driver v1 https://lore.kernel.org/all/cover.1724777091.git.nicolinc@nvidia.com/ Thanks! Nicolin Nicolin Chen (14): iommufd: Keep IOCTL list in an alphabetical order iommufd/fault: Add an iommufd_fault_init() helper iommufd/fault: Move iommufd_fault_iopf_handler() to header iommufd: Abstract an iommufd_eventq from iommufd_fault iommufd: Rename fault.c to eventq.c iommufd: Add IOMMUFD_OBJ_VIRQ and IOMMUFD_CMD_VIRQ_ALLOC iommufd/viommu: Add iommufd_viommu_get_vdev_id helper iommufd/viommu: Add iommufd_viommu_report_irq helper iommufd/selftest: Require vdev_id when attaching to a nested domain iommufd/selftest: Add IOMMU_TEST_OP_TRIGGER_VIRQ for vIRQ coverage iommufd/selftest: Add IOMMU_VIRQ_ALLOC test coverage Documentation: userspace-api: iommufd: Update FAULT and VIRQ iommu/arm-smmu-v3: Introduce struct arm_smmu_vmaster iommu/arm-smmu-v3: Report IRQs that belong to devices attached to vIOMMU drivers/iommu/iommufd/Makefile | 2 +- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 30 ++ drivers/iommu/iommufd/iommufd_private.h | 115 ++++++- drivers/iommu/iommufd/iommufd_test.h | 10 + include/linux/iommufd.h | 20 ++ include/uapi/linux/iommufd.h | 46 +++ tools/testing/selftests/iommu/iommufd_utils.h | 63 ++++ .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 65 ++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 90 ++++-- drivers/iommu/iommufd/driver.c | 57 ++++ drivers/iommu/iommufd/{fault.c => eventq.c} | 298 ++++++++++++++---- drivers/iommu/iommufd/hw_pagetable.c | 6 +- drivers/iommu/iommufd/main.c | 20 +- drivers/iommu/iommufd/selftest.c | 53 ++++ drivers/iommu/iommufd/viommu.c | 2 + tools/testing/selftests/iommu/iommufd.c | 27 ++ .../selftests/iommu/iommufd_fail_nth.c | 6 + Documentation/userspace-api/iommufd.rst | 16 + 18 files changed, 809 insertions(+), 117 deletions(-) rename drivers/iommu/iommufd/{fault.c => eventq.c} (55%) base-commit: 376ce8b35ed15d5deee57bdecd8449f6a4df4c42 -- 2.43.0

6 months

3
27
0 0

[PATCH AUTOSEL 6.12 1/8] selftests/sched_ext: fix build after renames in sched_ext API

by Sasha Levin

From: Ihor Solodrai <ihor.solodrai(a)pm.me> [ Upstream commit ef7009decc30eb2515a64253791d61b72229c119 ] The selftests are falining to build on current tip of bpf-next and sched_ext [1]. This has broken BPF CI [2] after merge from upstream. Use appropriate function names in the selftests according to the recent changes in the sched_ext API [3]. [1] https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit/?id… [2] https://github.com/kernel-patches/bpf/actions/runs/11959327258/job/33340923… [3] https://lore.kernel.org/all/20241109194853.580310-1-tj@kernel.org/ Signed-off-by: Ihor Solodrai <ihor.solodrai(a)pm.me> Acked-by: Andrea Righi <arighi(a)nvidia.com> Acked-by: David Vernet <void(a)manifault.com> Signed-off-by: Tejun Heo <tj(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- .../testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c | 2 +- .../selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c | 4 ++-- tools/testing/selftests/sched_ext/dsp_local_on.bpf.c | 2 +- .../selftests/sched_ext/enq_select_cpu_fails.bpf.c | 2 +- tools/testing/selftests/sched_ext/exit.bpf.c | 4 ++-- tools/testing/selftests/sched_ext/maximal.bpf.c | 4 ++-- tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c | 2 +- .../selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c | 2 +- .../testing/selftests/sched_ext/select_cpu_dispatch.bpf.c | 2 +- .../selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c | 2 +- .../selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c | 4 ++-- tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c | 8 ++++---- 12 files changed, 19 insertions(+), 19 deletions(-) diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c index 37d9bf6fb745..6f4c3f5a1c5d 100644 --- a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c @@ -20,7 +20,7 @@ s32 BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_select_cpu, struct task_struct *p, * If we dispatch to a bogus DSQ that will fall back to the * builtin global DSQ, we fail gracefully. */ - scx_bpf_dispatch_vtime(p, 0xcafef00d, SCX_SLICE_DFL, + scx_bpf_dsq_insert_vtime(p, 0xcafef00d, SCX_SLICE_DFL, p->scx.dsq_vtime, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c index dffc97d9cdf1..e4a55027778f 100644 --- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c @@ -17,8 +17,8 @@ s32 BPF_STRUCT_OPS(ddsp_vtimelocal_fail_select_cpu, struct task_struct *p, if (cpu >= 0) { /* Shouldn't be allowed to vtime dispatch to a builtin DSQ. */ - scx_bpf_dispatch_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, - p->scx.dsq_vtime, 0); + scx_bpf_dsq_insert_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, + p->scx.dsq_vtime, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c index 6a7db1502c29..6325bf76f47e 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c @@ -45,7 +45,7 @@ void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev) target = bpf_get_prandom_u32() % nr_cpus; - scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0); bpf_task_release(p); } diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c index 1efb50d61040..a7cf868d5e31 100644 --- a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c +++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c @@ -31,7 +31,7 @@ void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p, /* Can only call from ops.select_cpu() */ scx_bpf_select_cpu_dfl(p, 0, 0, &found); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); } SEC(".struct_ops.link") diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c index d75d4faf07f6..4bc36182d3ff 100644 --- a/tools/testing/selftests/sched_ext/exit.bpf.c +++ b/tools/testing/selftests/sched_ext/exit.bpf.c @@ -33,7 +33,7 @@ void BPF_STRUCT_OPS(exit_enqueue, struct task_struct *p, u64 enq_flags) if (exit_point == EXIT_ENQUEUE) EXIT_CLEANLY(); - scx_bpf_dispatch(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); } void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) @@ -41,7 +41,7 @@ void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) if (exit_point == EXIT_DISPATCH) EXIT_CLEANLY(); - scx_bpf_consume(DSQ_ID); + scx_bpf_dsq_move_to_local(DSQ_ID); } void BPF_STRUCT_OPS(exit_enable, struct task_struct *p) diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c index 4d4cd8d966db..4c005fa71810 100644 --- a/tools/testing/selftests/sched_ext/maximal.bpf.c +++ b/tools/testing/selftests/sched_ext/maximal.bpf.c @@ -20,7 +20,7 @@ s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu, void BPF_STRUCT_OPS(maximal_enqueue, struct task_struct *p, u64 enq_flags) { - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); } void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags) @@ -28,7 +28,7 @@ void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags) void BPF_STRUCT_OPS(maximal_dispatch, s32 cpu, struct task_struct *prev) { - scx_bpf_consume(SCX_DSQ_GLOBAL); + scx_bpf_dsq_move_to_local(SCX_DSQ_GLOBAL); } void BPF_STRUCT_OPS(maximal_runnable, struct task_struct *p, u64 enq_flags) diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c index f171ac470970..13d0f5be788d 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c @@ -30,7 +30,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p, } scx_bpf_put_idle_cpumask(idle_mask); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); } SEC(".struct_ops.link") diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c index 9efdbb7da928..815f1d5d61ac 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c @@ -67,7 +67,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_enqueue, struct task_struct *p, saw_local = true; } - scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, enq_flags); } s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task, diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c index 59bfc4f36167..4bb99699e920 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c @@ -29,7 +29,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_select_cpu, struct task_struct *p, cpu = prev_cpu; dispatch: - scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c index 3bbd5fcdfb18..2a75de11b2cf 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c @@ -18,7 +18,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_select_cpu, struct task_struct *p s32 prev_cpu, u64 wake_flags) { /* Dispatching to a random DSQ should fail. */ - scx_bpf_dispatch(p, 0xcafef00d, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, 0xcafef00d, SCX_SLICE_DFL, 0); return prev_cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c index 0fda57fe0ecf..99d075695c97 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c @@ -18,8 +18,8 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_select_cpu, struct task_struct *p s32 prev_cpu, u64 wake_flags) { /* Dispatching twice in a row is disallowed. */ - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); return prev_cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c index e6c67bcf5e6e..bfcb96cd4954 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c @@ -2,8 +2,8 @@ /* * A scheduler that validates that enqueue flags are properly stored and * applied at dispatch time when a task is directly dispatched from - * ops.select_cpu(). We validate this by using scx_bpf_dispatch_vtime(), and - * making the test a very basic vtime scheduler. + * ops.select_cpu(). We validate this by using scx_bpf_dsq_insert_vtime(), + * and making the test a very basic vtime scheduler. * * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. * Copyright (c) 2024 David Vernet <dvernet(a)meta.com> @@ -47,13 +47,13 @@ s32 BPF_STRUCT_OPS(select_cpu_vtime_select_cpu, struct task_struct *p, cpu = prev_cpu; scx_bpf_test_and_clear_cpu_idle(cpu); ddsp: - scx_bpf_dispatch_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0); + scx_bpf_dsq_insert_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0); return cpu; } void BPF_STRUCT_OPS(select_cpu_vtime_dispatch, s32 cpu, struct task_struct *p) { - if (scx_bpf_consume(VTIME_DSQ)) + if (scx_bpf_dsq_move_to_local(VTIME_DSQ)) consumed = true; } -- 2.39.5

6 months

1
2
0 0

[PATCH bpf-next v4 4/4] igc: Add launch time support to XDP ZC

by Song Yoong Siang

Enable Launch Time Control (LTC) support to XDP zero copy via XDP Tx metadata framework. This patch is tested with tools/testing/selftests/bpf/xdp_hw_metadata on Intel Tiger Lake platform. Below are the test steps and result. Test Steps: 1. Add mqprio qdisc: $ sudo tc qdisc add dev enp2s0 handle 8001: parent root mqprio num_tc 4 map 3 2 1 0 0 0 0 0 0 0 0 0 0 0 0 0 queues 1@0 1@1 1@2 1@3 hw 0 2. Enable launch time hardware offload on hardware queue 1: $ sudo tc qdisc replace dev enp2s0 parent 8001:2 etf offload clockid CLOCK_TAI delta 500000 3. Change RSS to route all incoming IP packets into hardware queue 1: $ sudo ethtool -X enp2s0 start 1 equal 1 4. Start xdp_hw_metadata selftest application: $ sudo ./xdp_hw_metadata enp2s0 -l 1000000000 5. Send an UDP packet to port 9091 of DUT. $ echo -n xdp | nc -u -q0 169.254.1.1 9091 When launch time is set to 1s in the future, the delta between launch time and transmit hardware timestamp is equal to 0.016us, as shown in result below: 0x562ff5dc8880: rx_desc[4]->addr=84110 addr=84110 comp_addr=84110 EoP rx_hash: 0xE343384 with RSS type:0x1 HW RX-time: 1734578015467548904 (sec:1734578015.4675) delta to User RX-time sec:0.0002 (183.103 usec) XDP RX-time: 1734578015467651698 (sec:1734578015.4677) delta to User RX-time sec:0.0001 (80.309 usec) No rx_vlan_tci or rx_vlan_proto, err=-95 0x562ff5dc8880: ping-pong with csum=561c (want c7dd) csum_start=34 csum_offset=6 HW RX-time: 1734578015467548904 (sec:1734578015.4675) delta to HW Launch-time sec:1.0000 (1000000.000 usec) 0x562ff5dc8880: complete tx idx=4 addr=4018 HW Launch-time: 1734578016467548904 (sec:1734578016.4675) delta to HW TX-complete-time sec:0.0000 (0.016 usec) HW TX-complete-time: 1734578016467548920 (sec:1734578016.4675) delta to User TX-complete-time sec:0.0000 (32.546 usec) XDP RX-time: 1734578015467651698 (sec:1734578015.4677) delta to User TX-complete-time sec:0.9999 (999929.768 usec) HW RX-time: 1734578015467548904 (sec:1734578015.4675) delta to HW TX-complete-time sec:1.0000 (1000000.016 usec) 0x562ff5dc8880: complete rx idx=132 addr=84110 Signed-off-by: Song Yoong Siang <yoong.siang.song(a)intel.com> --- drivers/net/ethernet/intel/igc/igc_main.c | 78 ++++++++++++++++------- 1 file changed, 56 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 27872bdea9bd..6857f5f5b4b2 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -1566,6 +1566,26 @@ static bool igc_request_tx_tstamp(struct igc_adapter *adapter, struct sk_buff *s return false; } +static void igc_insert_empty_packet(struct igc_ring *tx_ring) +{ + struct igc_tx_buffer *empty_info; + struct sk_buff *empty; + void *data; + + empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + empty = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC); + if (!empty) + return; + + data = skb_put(empty, IGC_EMPTY_FRAME_SIZE); + memset(data, 0, IGC_EMPTY_FRAME_SIZE); + + igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0); + + if (igc_init_tx_empty_descriptor(tx_ring, empty, empty_info) < 0) + dev_kfree_skb_any(empty); +} + static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, struct igc_ring *tx_ring) { @@ -1603,26 +1623,8 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, skb->tstamp = ktime_set(0, 0); launch_time = igc_tx_launchtime(tx_ring, txtime, &first_flag, &insert_empty); - if (insert_empty) { - struct igc_tx_buffer *empty_info; - struct sk_buff *empty; - void *data; - - empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; - empty = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC); - if (!empty) - goto done; - - data = skb_put(empty, IGC_EMPTY_FRAME_SIZE); - memset(data, 0, IGC_EMPTY_FRAME_SIZE); - - igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0); - - if (igc_init_tx_empty_descriptor(tx_ring, - empty, - empty_info) < 0) - dev_kfree_skb_any(empty); - } + if (insert_empty) + igc_insert_empty_packet(tx_ring); done: /* record the location of the first descriptor for this packet */ @@ -2955,9 +2957,33 @@ static u64 igc_xsk_fill_timestamp(void *_priv) return *(u64 *)_priv; } +static void igc_xsk_request_launch_time(u64 launch_time, void *_priv) +{ + struct igc_metadata_request *meta_req = _priv; + struct igc_ring *tx_ring = meta_req->tx_ring; + __le32 launch_time_offset; + bool insert_empty = false; + bool first_flag = false; + + if (!tx_ring->launchtime_enable) + return; + + launch_time_offset = igc_tx_launchtime(tx_ring, + ns_to_ktime(launch_time), + &first_flag, &insert_empty); + if (insert_empty) { + igc_insert_empty_packet(tx_ring); + meta_req->tx_buffer = + &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + } + + igc_tx_ctxtdesc(tx_ring, launch_time_offset, first_flag, 0, 0, 0); +} + const struct xsk_tx_metadata_ops igc_xsk_tx_metadata_ops = { .tmo_request_timestamp = igc_xsk_request_timestamp, .tmo_fill_timestamp = igc_xsk_fill_timestamp, + .tmo_request_launch_time = igc_xsk_request_launch_time, }; static void igc_xdp_xmit_zc(struct igc_ring *ring) @@ -2980,7 +3006,7 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) ntu = ring->next_to_use; budget = igc_desc_unused(ring); - while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) { + while (xsk_tx_peek_desc(pool, &xdp_desc) && budget >= 4) { struct igc_metadata_request meta_req; struct xsk_tx_metadata *meta = NULL; struct igc_tx_buffer *bi; @@ -3004,6 +3030,12 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) xsk_tx_metadata_request(meta, &igc_xsk_tx_metadata_ops, &meta_req); + /* xsk_tx_metadata_request() may have updated next_to_use */ + ntu = ring->next_to_use; + + /* xsk_tx_metadata_request() may have updated Tx buffer info */ + bi = meta_req.tx_buffer; + tx_desc = IGC_TX_DESC(ring, ntu); tx_desc->read.cmd_type_len = cpu_to_le32(meta_req.cmd_type); tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); @@ -3021,9 +3053,11 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) ntu++; if (ntu == ring->count) ntu = 0; + + ring->next_to_use = ntu; + budget = igc_desc_unused(ring); } - ring->next_to_use = ntu; if (tx_desc) { igc_flush_tx_descriptors(ring); xsk_tx_release(pool); -- 2.34.1

6 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror