February 2025 - Linux-kselftest-mirror

[PATCH sched_ext/for-6.15] selftests/sched_ext: Add NUMA-aware scheduler test

by Andrea Righi

Add a selftest to validate the behavior of the NUMA-aware scheduler functionalities, including idle CPU selection within nodes, per-node DSQs and CPU to node mapping. Signed-off-by: Andrea Righi <arighi(a)nvidia.com> --- tools/testing/selftests/sched_ext/Makefile | 1 + tools/testing/selftests/sched_ext/numa.bpf.c | 100 +++++++++++++++++++ tools/testing/selftests/sched_ext/numa.c | 59 +++++++++++ 3 files changed, 160 insertions(+) create mode 100644 tools/testing/selftests/sched_ext/numa.bpf.c create mode 100644 tools/testing/selftests/sched_ext/numa.c diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index 0117622246007..f4531327b8e76 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -172,6 +172,7 @@ auto-test-targets := \ maximal \ maybe_null \ minimal \ + numa \ prog_run \ reload_loop \ select_cpu_dfl \ diff --git a/tools/testing/selftests/sched_ext/numa.bpf.c b/tools/testing/selftests/sched_ext/numa.bpf.c new file mode 100644 index 0000000000000..a79d86ed54a1b --- /dev/null +++ b/tools/testing/selftests/sched_ext/numa.bpf.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A scheduler that validates the behavior of the NUMA-aware + * functionalities. + * + * The scheduler creates a separate DSQ for each NUMA node, ensuring tasks + * are exclusively processed by CPUs within their respective nodes. Idle + * CPUs are selected only within the same node, so task migration can only + * occurs between CPUs belonging to the same node. + * + * Copyright (c) 2025 Andrea Righi <arighi(a)nvidia.com> + */ + +#include <scx/common.bpf.h> + +char _license[] SEC("license") = "GPL"; + +UEI_DEFINE(uei); + +const volatile unsigned int __COMPAT_SCX_PICK_IDLE_IN_NODE; + +static bool is_cpu_idle(s32 cpu, int node) +{ + const struct cpumask *idle_cpumask; + bool idle; + + idle_cpumask = __COMPAT_scx_bpf_get_idle_cpumask_node(node); + idle = bpf_cpumask_test_cpu(cpu, idle_cpumask); + scx_bpf_put_cpumask(idle_cpumask); + + return idle; +} + +s32 BPF_STRUCT_OPS(numa_select_cpu, + struct task_struct *p, s32 prev_cpu, u64 wake_flags) +{ + int node = __COMPAT_scx_bpf_cpu_node(scx_bpf_task_cpu(p)); + s32 cpu; + + /* + * We could just use __COMPAT_scx_bpf_pick_any_cpu_node() here, + * since it already tries to pick an idle CPU within the node + * first, but let's use both functions for better testing coverage. + */ + cpu = __COMPAT_scx_bpf_pick_idle_cpu_node(p->cpus_ptr, node, + __COMPAT_SCX_PICK_IDLE_IN_NODE); + if (cpu < 0) + cpu = __COMPAT_scx_bpf_pick_any_cpu_node(p->cpus_ptr, node, + __COMPAT_SCX_PICK_IDLE_IN_NODE); + + if (is_cpu_idle(cpu, node)) + scx_bpf_error("CPU %d should be marked as busy", cpu); + + if (__COMPAT_scx_bpf_cpu_node(cpu) != node) + scx_bpf_error("CPU %d should be in node %d", cpu, node); + + return cpu; +} + +void BPF_STRUCT_OPS(numa_enqueue, struct task_struct *p, u64 enq_flags) +{ + int node = __COMPAT_scx_bpf_cpu_node(scx_bpf_task_cpu(p)); + + scx_bpf_dsq_insert(p, node, SCX_SLICE_DFL, enq_flags); +} + +void BPF_STRUCT_OPS(numa_dispatch, s32 cpu, struct task_struct *prev) +{ + int node = __COMPAT_scx_bpf_cpu_node(cpu); + + scx_bpf_dsq_move_to_local(node); +} + +s32 BPF_STRUCT_OPS_SLEEPABLE(numa_init) +{ + int node, err; + + bpf_for(node, 0, __COMPAT_scx_bpf_nr_node_ids()) { + err = scx_bpf_create_dsq(node, node); + if (err) + return err; + } + + return 0; +} + +void BPF_STRUCT_OPS(numa_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops numa_ops = { + .select_cpu = (void *)numa_select_cpu, + .enqueue = (void *)numa_enqueue, + .dispatch = (void *)numa_dispatch, + .init = (void *)numa_init, + .exit = (void *)numa_exit, + .name = "numa", +}; diff --git a/tools/testing/selftests/sched_ext/numa.c b/tools/testing/selftests/sched_ext/numa.c new file mode 100644 index 0000000000000..b060c3b65c82b --- /dev/null +++ b/tools/testing/selftests/sched_ext/numa.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2025 Andrea Righi <arighi(a)nvidia.com> + */ +#include <bpf/bpf.h> +#include <scx/common.h> +#include <sys/wait.h> +#include <unistd.h> +#include "numa.bpf.skel.h" +#include "scx_test.h" + +static enum scx_test_status setup(void **ctx) +{ + struct numa *skel; + + skel = numa__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + skel->rodata->__COMPAT_SCX_PICK_IDLE_IN_NODE = SCX_PICK_IDLE_IN_NODE; + skel->struct_ops.numa_ops->flags = SCX_OPS_BUILTIN_IDLE_PER_NODE; + SCX_FAIL_IF(numa__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct numa *skel = ctx; + struct bpf_link *link; + + link = bpf_map__attach_struct_ops(skel->maps.numa_ops); + SCX_FAIL_IF(!link, "Failed to attach scheduler"); + + /* Just sleeping is fine, plenty of scheduling events happening */ + sleep(1); + + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_NONE)); + bpf_link__destroy(link); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct numa *skel = ctx; + + numa__destroy(skel); +} + +struct scx_test numa = { + .name = "numa", + .description = "Verify NUMA-aware functionalities", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&numa) -- 2.48.1

8 months, 1 week

2
1
0 0

[PATCH v3 0/2] selftests: sched: Add default target support for sched

by Sinadin Shan

This patch series introduces changes to add default build support for the sched tests in selftests. The only test under sched is cs_prctl_test which validates cookies when core scheduling is in effect. This test fails on systems where core scheduling is disabled. The patch series also modifies this behaviour to gracefully skip the test on such systems. A system with core scheduling disabled would skip the test like: ~# ./run_kselftest.sh TAP version 13 1..1 timeout set to 45 selftests: sched: cs_prctl_test prctl failed: Invalid argument Core sched not supported, hence skipping tests ok 1 selftests: sched: cs_prctl_test # SKIP Signed-off-by: Sinadin Shan <sinadin.shan(a)oracle.com> --- v3: * Use prctl to check core sched support instead of config * v2 link: https://lore.kernel.org/all/20250221115750.631990-1-sinadin.shan@oracle.com/ v2: * Add patch to skip cs_prctl_test on core scheduling disabled systems * v1 link: https://lore.kernel.org/all/20250219064658.449069-1-sinadin.shan@oracle.com --- Sinadin Shan (2): selftests: sched: add sched as a default selftest target selftests: sched: skip cs_prctl_test for systems with core scheduling disabled tools/testing/selftests/Makefile | 1 + tools/testing/selftests/sched/cs_prctl_test.c | 34 ++++++++++++++++++- 2 files changed, 34 insertions(+), 1 deletion(-) -- 2.43.5

8 months, 1 week

3
4
0 0

[PATCH net-next v5 0/9] Device memory TCP TX

by Mina Almasry

v5: https://lore.kernel.org/netdev/20250220020914.895431-1-almasrymina@google.c… === v5 has no major changes; it clears up the relatively minor issues pointed out to in v4, and rebases the series on top of net-next to resolve the conflict with a patch that raced to the tree. It also collects the review tags from v4. Changes: - Rebase to net-next - Fix issues in selftest (Stan). - Address comments in the devmem and netmem driver docs (Stan and Bagas) - Fix zerocopy_fill_skb_from_devmem return error code (Stan). v4: https://lore.kernel.org/netdev/20250203223916.1064540-1-almasrymina@google.… === v4 mainly addresses the critical driver support issue surfaced in v3 by Paolo and Stan. Drivers aiming to support netmem_tx should make sure not to pass the netmem dma-addrs to the dma-mapping APIs, as these dma-addrs may come from dma-bufs. Additionally other feedback from v3 is addressed. Major changes: - Add helpers to handle netmem dma-addrs. Add GVE support for netmem_tx. - Fix binding->tx_vec not being freed on error paths during the tx binding. - Add a minimal devmem_tx test to devmem.py. - Clean up everything obsolete from the cover letter (Paolo). v3: https://patchwork.kernel.org/project/netdevbpf/list/?series=929401&state=* === Address minor comments from RFCv2 and fix a few build warnings and ynl-regen issues. No major changes. RFC v2: https://patchwork.kernel.org/project/netdevbpf/list/?series=920056&state=* ======= RFC v2 addresses much of the feedback from RFC v1. I plan on sending something close to this as net-next reopens, sending it slightly early to get feedback if any. Major changes: -------------- - much improved UAPI as suggested by Stan. We now interpret the iov_base of the passed in iov from userspace as the offset into the dmabuf to send from. This removes the need to set iov.iov_base = NULL which may be confusing to users, and enables us to send multiple iovs in the same sendmsg() call. ncdevmem and the docs show a sample use of that. - Removed the duplicate dmabuf iov_iter in binding->iov_iter. I think this is good improvment as it was confusing to keep track of 2 iterators for the same sendmsg, and mistracking both iterators caused a couple of bugs reported in the last iteration that are now resolved with this streamlining. - Improved test coverage in ncdevmem. Now multiple sendmsg() are tested, and sending multiple iovs in the same sendmsg() is tested. - Fixed issue where dmabuf unmapping was happening in invalid context (Stan). ==================================================================== The TX path had been dropped from the Device Memory TCP patch series post RFCv1 [1], to make that series slightly easier to review. This series rebases the implementation of the TX path on top of the net_iov/netmem framework agreed upon and merged. The motivation for the feature is thoroughly described in the docs & cover letter of the original proposal, so I don't repeat the lengthy descriptions here, but they are available in [1]. Full outline on usage of the TX path is detailed in the documentation included with this series. Test example is available via the kselftest included in the series as well. The series is relatively small, as the TX path for this feature largely piggybacks on the existing MSG_ZEROCOPY implementation. Patch Overview: --------------- 1. Documentation & tests to give high level overview of the feature being added. 1. Add netmem refcounting needed for the TX path. 2. Devmem TX netlink API. 3. Devmem TX net stack implementation. 4. Make dma-buf unbinding scheduled work to handle TX cases where it gets freed from contexts where we can't sleep. 5. Add devmem TX documentation. 6. Add scaffolding enabling driver support for netmem_tx. Add helpers, driver feature flag, and docs to enable drivers to declare netmem_tx support. 7. Guard netmem_tx against being enabled against drivers that don't support it. 8. Add devmem_tx selftests. Add TX path to ncdevmem and add a test to devmem.py. Testing: -------- Testing is very similar to devmem TCP RX path. The ncdevmem test used for the RX path is now augemented with client functionality to test TX path. * Test Setup: Kernel: net-next with this RFC and memory provider API cherry-picked locally. Hardware: Google Cloud A3 VMs. NIC: GVE with header split & RSS & flow steering support. Performance results are not included with this version, unfortunately. I'm having issues running the dma-buf exporter driver against the upstream kernel on my test setup. The issues are specific to that dma-buf exporter and do not affect this patch series. I plan to follow up this series with perf fixes if the tests point to issues once they're up and running. Special thanks to Stan who took a stab at rebasing the TX implementation on top of the netmem/net_iov framework merged. Parts of his proposal [2] that are reused as-is are forked off into their own patches to give full credit. [1] https://lore.kernel.org/netdev/20240909054318.1809580-1-almasrymina@google.… [2] https://lore.kernel.org/netdev/20240913150913.1280238-2-sdf@fomichev.me/T/#… Cc: sdf(a)fomichev.me Cc: asml.silence(a)gmail.com Cc: dw(a)davidwei.uk Cc: Jamal Hadi Salim <jhs(a)mojatatu.com> Cc: Victor Nogueira <victor(a)mojatatu.com> Cc: Pedro Tammela <pctammela(a)mojatatu.com> Cc: Samiullah Khawaja <skhawaja(a)google.com> Mina Almasry (8): net: add get_netmem/put_netmem support net: devmem: Implement TX path net: devmem: make dmabuf unbinding scheduled work net: add devmem TCP TX documentation net: enable driver support for netmem TX gve: add netmem TX support to GVE DQO-RDA mode net: check for driver support in netmem TX selftests: ncdevmem: Implement devmem TCP TX Stanislav Fomichev (1): net: devmem: TCP tx netlink api Documentation/netlink/specs/netdev.yaml | 12 + Documentation/networking/devmem.rst | 150 ++++++++- .../networking/net_cachelines/net_device.rst | 1 + Documentation/networking/netdev-features.rst | 5 + Documentation/networking/netmem.rst | 23 +- drivers/net/ethernet/google/gve/gve_main.c | 4 + drivers/net/ethernet/google/gve/gve_tx_dqo.c | 8 +- include/linux/netdevice.h | 2 + include/linux/skbuff.h | 17 +- include/linux/skbuff_ref.h | 4 +- include/net/netmem.h | 23 ++ include/net/sock.h | 1 + include/uapi/linux/netdev.h | 1 + net/core/datagram.c | 48 ++- net/core/dev.c | 3 + net/core/devmem.c | 113 ++++++- net/core/devmem.h | 69 +++- net/core/netdev-genl-gen.c | 13 + net/core/netdev-genl-gen.h | 1 + net/core/netdev-genl.c | 73 ++++- net/core/skbuff.c | 48 ++- net/core/sock.c | 6 + net/ipv4/ip_output.c | 3 +- net/ipv4/tcp.c | 46 ++- net/ipv6/ip6_output.c | 3 +- net/vmw_vsock/virtio_transport_common.c | 5 +- tools/include/uapi/linux/netdev.h | 1 + .../selftests/drivers/net/hw/devmem.py | 26 +- .../selftests/drivers/net/hw/ncdevmem.c | 300 +++++++++++++++++- 29 files changed, 938 insertions(+), 71 deletions(-) base-commit: b66e19dcf684b21b6d3a1844807bd1df97ad197a -- 2.48.1.601.g30ceb7b040-goog

8 months, 1 week

5
22
0 0

[PATCHv2 net 0/3] bond: fix xfrm offload issues

by Hangbin Liu

The first patch fixes the incorrect locks using in bond driver. The second patch fixes the xfrm offload feature during setup active-backup mode. The third patch add a ipsec offload testing. v2: move the mutex lock to a work queue (Cosmin Ratiu) Hangbin Liu (3): bonding: move mutex lock to a work queue for XFRM GC tasks bonding: fix xfrm offload feature setup on active-backup mode selftests: bonding: add ipsec offload test drivers/net/bonding/bond_main.c | 43 +++-- drivers/net/bonding/bond_netlink.c | 16 +- include/net/bonding.h | 7 + .../selftests/drivers/net/bonding/Makefile | 3 +- .../drivers/net/bonding/bond_ipsec_offload.sh | 155 ++++++++++++++++++ .../selftests/drivers/net/bonding/config | 4 + 6 files changed, 209 insertions(+), 19 deletions(-) create mode 100755 tools/testing/selftests/drivers/net/bonding/bond_ipsec_offload.sh -- 2.46.0

8 months, 1 week

3
12
0 0

[PATCH RFC 0/4] mm: KUnit tests for the page allocator

by Brendan Jackman

The page allocator does a lot of stuff that is not visible to the user in any deterministic way. But this stuff is still important and it would be nice to test that behaviour. KUnit is a tool for unit-testing kernel-internal APIs. This is an attempt to adopt it the page allocator. I have been hacking on this as a way to try and test the code I'm writing for my ASI page_alloc integration proposal [0]. It's been extremely useful to be able to "just call it and see what it does". So I wanna gather some feedback on whether this basic idea is of interest before I invest too much more time in it. You can run these tests like this: tools/testing/kunit/kunit.py run \ --arch=x86_64 --kernel_args="movablecore=2G" \ --qemu_args="-m 4G" --kunitconfig mm/.kunitconfig Unit-testing code that has mutable global variables can be a pain. Unit-testing code with mutable global variables _that can change concurrently with the tests_ is basically impossible. So, we need some way to isolate an "instance" of the allocator that doesn't refer to any such concurrently-mutated state. Luckily, the allocator only has one really important global variable: node_data. So, the approach here is to carve out a subset of that variable which is as isolated as possible from the rest of rthe system, which can be used for deterministic testing. This is achieved by crating a fake "isolated" node at boot, and plugging in memory at test init time. This is an RFC and not a PATCH because: 1. I have not taken much care to ensure the isolation is complete. There are probably sources of flakiness and nondeterminism in here. 2. I suspect the the basic idea might be over-complicated: do we really need memory hotplug here? Do we even need the instance of the allocator we're testing to actual memory behind the pages it's allocating, or could we just hallucinate a new region of vmemmap without any of that awkwardness? One significant downside of relying on memory hotplug is that the test won't run if we can't hotplug anything out. That means you have to fiddle with the platform to even run the tests - see the --kernel_args and --qemu_args I had to add to my kunit.py command above. So yeah, other suggestions welcome. 2b. I'm not very confident I'm using the hotplug API properly. 3. There's no point in merging this without actually having at least a few tests that are actually interesting! Maybe a "build it and they will come" approach can be justified to some extent, but there's a nonzero cost to the infrastructure so we should probably have some confidence that they will indeed come. [0] https://lore.kernel.org/linux-mm/20250129144320.2675822-1-jackmanb@google.c… Signed-off-by: Brendan Jackman <jackmanb(a)google.com> --- Brendan Jackman (4): kunit: Allocate assertion data with GFP_ATOMIC mm/page_alloc_test: Add empty KUnit boilerplate mm/page_alloc_test: Add logic to isolate a node for testing mm/page_alloc_test: Add smoke-test for page allocation drivers/base/memory.c | 5 +- include/linux/memory.h | 4 + include/linux/nodemask.h | 13 +++ kernel/kthread.c | 3 + lib/kunit/assert.c | 2 +- lib/kunit/resource.c | 2 +- lib/kunit/test.c | 2 +- mm/.kunitconfig | 10 ++ mm/Kconfig | 8 ++ mm/Makefile | 2 + mm/internal.h | 11 ++ mm/memory_hotplug.c | 26 +++-- mm/numa_memblks.c | 22 ++++ mm/page_alloc.c | 37 +++++- mm/page_alloc_test.c | 296 +++++++++++++++++++++++++++++++++++++++++++++++ 15 files changed, 429 insertions(+), 14 deletions(-) --- base-commit: d082ecbc71e9e0bf49883ee4afd435a77a5101b6 change-id: 20250219-page-alloc-kunit-df76ef8d8eb9 Best regards, -- Brendan Jackman <jackmanb(a)google.com>

8 months, 1 week

3
14
0 0

[PATCH 0/9] selftests/x86/xstate: Introduce common code for testing extended states

by Chang S. Bae

Hi all, This series proposes a rework of xstate-related tests to improve maintainability and expand test coverage. == Motivation: Addressing Missing and New XSTATE Tests == With the introduction of AMX, a new test suite [1] was created to verify dynamic state handling by the kernel as observed from userspace. However, previous tests for non-dynamic states like AVX lacked ABI validation, leaving gaps in coverage. While these states currently function without major issues (following the alternate sigstack fix [2]), xstate testing in the x86 selftest suite has been largely overlooked. Now, with Intel introducing another extended state, Advanced Performance Extensions (APX) [3], a correspondent test case is need. The APX enabling series will follow shortly and will leverage this refactored selftest framework. == Selftest Code Rework == To ensure ABI validation and core functionality across various xstates, refactoring the test code is necessary. Without this, existing code from amx.c would need to be duplicated, compromising the structural quality of xstate tests. This series introduces a shared test framework for extended state validation, applicable to both existing and new xstates. The test cases cover: * Context switching * ABI compatibility for signal handling * ABI compatibility for ptrace interactions == Patch Organization == The patchset is structured as follows: * PATCH1: Preparatory cleanup — removing redundant signal handler registration code. * PATCH2/3: Introduce low-level XSAVE helpers and xstate component enumeration. * PATCH4/5: Refactor existing test code. * PATCH6: Introduce a new signal test case. * PATCH7/8: Consolidate test invocations and clarify the list of supported features. * PATCH9: Add test coverage for AVX. == Coverage and Future Work Considerations == Currently, these tests are aligned with 64-bit mode only. Support for 32-bit cases will be considered when necessary, but only after this phase of rework is finalized. FWIW, the AMX TILECFG state is trivial, requiring almost constant values. Additionally, various PKRU tests are already established in tools/selftests/mm. This series is based on the tip/master branch. You can also find it in the following repository: git://github.com/intel/apx.git selftest-xstate_v1 Thanks, Chang [1] https://lore.kernel.org/all/20211026122523.AFB99C1F@davehans-spike.ostc.int… [2] https://lore.kernel.org/lkml/20210518200320.17239-1-chang.seok.bae@intel.co… [3] https://www.intel.com/content/www/us/en/developer/articles/technical/advanc… Chang S. Bae (9): selftests/x86: Consolidate redundant signal helper functions selftests/x86/xstate: Refactor XSAVE helpers for general use selftests/x86/xstate: Enumerate and name xstate components selftests/x86/xstate: Refactor context switching test selftests/x86/xstate: Refactor ptrace ABI test selftests/x86/xstate: Introduce signal ABI test selftests/x86/xstate: Consolidate test invocations into a single entry selftests/x86/xstate: Clarify supported xstates selftests/x86/avx: Add AVX test tools/testing/selftests/x86/Makefile | 6 +- tools/testing/selftests/x86/amx.c | 442 +--------------- tools/testing/selftests/x86/avx.c | 12 + .../selftests/x86/corrupt_xstate_header.c | 14 +- tools/testing/selftests/x86/entry_from_vm86.c | 24 +- tools/testing/selftests/x86/fsgsbase.c | 24 +- tools/testing/selftests/x86/helpers.h | 28 + tools/testing/selftests/x86/ioperm.c | 25 +- tools/testing/selftests/x86/iopl.c | 25 +- tools/testing/selftests/x86/ldt_gdt.c | 18 +- tools/testing/selftests/x86/mov_ss_trap.c | 14 +- tools/testing/selftests/x86/ptrace_syscall.c | 24 +- tools/testing/selftests/x86/sigaltstack.c | 26 +- tools/testing/selftests/x86/sigreturn.c | 24 +- .../selftests/x86/single_step_syscall.c | 22 - .../testing/selftests/x86/syscall_arg_fault.c | 12 - tools/testing/selftests/x86/syscall_nt.c | 12 - tools/testing/selftests/x86/sysret_rip.c | 24 +- tools/testing/selftests/x86/test_vsyscall.c | 13 - tools/testing/selftests/x86/unwind_vdso.c | 12 - tools/testing/selftests/x86/xstate.c | 477 ++++++++++++++++++ tools/testing/selftests/x86/xstate.h | 195 +++++++ 22 files changed, 753 insertions(+), 720 deletions(-) create mode 100644 tools/testing/selftests/x86/avx.c create mode 100644 tools/testing/selftests/x86/xstate.c create mode 100644 tools/testing/selftests/x86/xstate.h base-commit: 5bff053d066ba892464995ae4a7246f7a78fce2d -- 2.45.2

8 months, 1 week

2
10
0 0

[PATCH v5 0/3] Enable Zicbom in usermode

by Yunhui Cui

v1/v2: There is only the first patch: RISC-V: Enable cbo.clean/flush in usermode, which mainly removes the enabling of cbo.inval in user mode. v3: Add the functionality of Expose Zicbom and selftests for Zicbom. v4: Modify the order of macros, The test_no_cbo_inval function is added separately. v5: 1. Modify the order of RISCV_HWPROBE_KEY_ZICBOM_BLOCK_SIZE in hwprobe.rst 2. "TEST_NO_ZICBOINVAL" -> "TEST_NO_CBO_INVAL" Yunhui Cui (3): RISC-V: Enable cbo.clean/flush in usermode RISC-V: hwprobe: Expose Zicbom extension and its block size RISC-V: selftests: Add TEST_ZICBOM into CBO tests Documentation/arch/riscv/hwprobe.rst | 6 ++ arch/riscv/include/asm/hwprobe.h | 2 +- arch/riscv/include/uapi/asm/hwprobe.h | 2 + arch/riscv/kernel/cpufeature.c | 8 +++ arch/riscv/kernel/sys_hwprobe.c | 6 ++ tools/testing/selftests/riscv/hwprobe/cbo.c | 66 +++++++++++++++++---- 6 files changed, 78 insertions(+), 12 deletions(-) -- 2.39.2

8 months, 1 week

6
12
0 0

[PATCH 0/3] selftests: add ublk selftests

by Ming Lei

Hello Guys, The 1st patch adds one ublk utility and one entry test. The 2nd patch adds test over file backed ublk. The 3rd patch adds test for ublk zero copy. How to run: - make install - make headers_install INSTALL_HDR_PATH=/usr - reboot - make -C tools/testing/selftests TARGETS=ublk run_test Thanks, Ming Lei (3): selftests: ublk: add kernel selftests for ublk selftests: ublk: add file backed ublk selftests: ublk: add ublk zero copy test MAINTAINERS | 1 + tools/testing/selftests/Makefile | 1 + tools/testing/selftests/ublk/.gitignore | 3 + tools/testing/selftests/ublk/Makefile | 14 + tools/testing/selftests/ublk/config | 1 + tools/testing/selftests/ublk/kublk.c | 1671 ++++++++++++++++++ tools/testing/selftests/ublk/test_common.sh | 112 ++ tools/testing/selftests/ublk/test_loop_01.sh | 30 + tools/testing/selftests/ublk/test_loop_02.sh | 21 + tools/testing/selftests/ublk/test_loop_03.sh | 32 + tools/testing/selftests/ublk/test_null_01.sh | 18 + 11 files changed, 1904 insertions(+) create mode 100644 tools/testing/selftests/ublk/.gitignore create mode 100644 tools/testing/selftests/ublk/Makefile create mode 100644 tools/testing/selftests/ublk/config create mode 100644 tools/testing/selftests/ublk/kublk.c create mode 100755 tools/testing/selftests/ublk/test_common.sh create mode 100755 tools/testing/selftests/ublk/test_loop_01.sh create mode 100755 tools/testing/selftests/ublk/test_loop_02.sh create mode 100755 tools/testing/selftests/ublk/test_loop_03.sh create mode 100755 tools/testing/selftests/ublk/test_null_01.sh -- 2.47.0

8 months, 1 week

1
3
0 0

[PATCH v10 3/3] selftests/rseq: Add test for mm_cid compaction

by Gabriele Monaco

A task in the kernel (task_mm_cid_work) runs somewhat periodically to compact the mm_cid for each process. Add a test to validate that it runs correctly and timely. The test spawns 1 thread pinned to each CPU, then each thread, including the main one, runs in short bursts for some time. During this period, the mm_cids should be spanning all numbers between 0 and nproc. At the end of this phase, a thread with high enough mm_cid (>= nproc/2) is selected to be the new leader, all other threads terminate. After some time, the only running thread should see 0 as mm_cid, if that doesn't happen, the compaction mechanism didn't work and the test fails. The test never fails if only 1 core is available, in which case, we cannot test anything as the only available mm_cid is 0. Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Signed-off-by: Gabriele Monaco <gmonaco(a)redhat.com> --- tools/testing/selftests/rseq/.gitignore | 1 + tools/testing/selftests/rseq/Makefile | 2 +- .../selftests/rseq/mm_cid_compaction_test.c | 200 ++++++++++++++++++ 3 files changed, 202 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/rseq/mm_cid_compaction_test.c diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore index 16496de5f6ce4..2c89f97e4f737 100644 --- a/tools/testing/selftests/rseq/.gitignore +++ b/tools/testing/selftests/rseq/.gitignore @@ -3,6 +3,7 @@ basic_percpu_ops_test basic_percpu_ops_mm_cid_test basic_test basic_rseq_op_test +mm_cid_compaction_test param_test param_test_benchmark param_test_compare_twice diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 5a3432fceb586..ce1b38f46a355 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -16,7 +16,7 @@ OVERRIDE_TARGETS = 1 TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ param_test_benchmark param_test_compare_twice param_test_mm_cid \ - param_test_mm_cid_benchmark param_test_mm_cid_compare_twice + param_test_mm_cid_benchmark param_test_mm_cid_compare_twice mm_cid_compaction_test TEST_GEN_PROGS_EXTENDED = librseq.so diff --git a/tools/testing/selftests/rseq/mm_cid_compaction_test.c b/tools/testing/selftests/rseq/mm_cid_compaction_test.c new file mode 100644 index 0000000000000..7ddde3b657dd6 --- /dev/null +++ b/tools/testing/selftests/rseq/mm_cid_compaction_test.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: LGPL-2.1 +#define _GNU_SOURCE +#include <assert.h> +#include <pthread.h> +#include <sched.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stddef.h> + +#include "../kselftest.h" +#include "rseq.h" + +#define VERBOSE 0 +#define printf_verbose(fmt, ...) \ + do { \ + if (VERBOSE) \ + printf(fmt, ##__VA_ARGS__); \ + } while (0) + +/* 0.5 s */ +#define RUNNER_PERIOD 500000 +/* Number of runs before we terminate or get the token */ +#define THREAD_RUNS 5 + +/* + * Number of times we check that the mm_cid were compacted. + * Checks are repeated every RUNNER_PERIOD. + */ +#define MM_CID_COMPACT_TIMEOUT 10 + +struct thread_args { + int cpu; + int num_cpus; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + pthread_t *tinfo; + struct thread_args *args_head; +}; + +static void __noreturn *thread_runner(void *arg) +{ + struct thread_args *args = arg; + int i, ret, curr_mm_cid; + cpu_set_t cpumask; + + CPU_ZERO(&cpumask); + CPU_SET(args->cpu, &cpumask); + ret = pthread_setaffinity_np(pthread_self(), sizeof(cpumask), &cpumask); + if (ret) { + errno = ret; + perror("Error: failed to set affinity"); + abort(); + } + pthread_barrier_wait(args->barrier); + + for (i = 0; i < THREAD_RUNS; i++) + usleep(RUNNER_PERIOD); + curr_mm_cid = rseq_current_mm_cid(); + /* + * We select one thread with high enough mm_cid to be the new leader. + * All other threads (including the main thread) will terminate. + * After some time, the mm_cid of the only remaining thread should + * converge to 0, if not, the test fails. + */ + if (curr_mm_cid >= args->num_cpus / 2 && + !pthread_mutex_trylock(args->token)) { + printf_verbose( + "cpu%d has mm_cid=%d and will be the new leader.\n", + sched_getcpu(), curr_mm_cid); + for (i = 0; i < args->num_cpus; i++) { + if (args->tinfo[i] == pthread_self()) + continue; + ret = pthread_join(args->tinfo[i], NULL); + if (ret) { + errno = ret; + perror("Error: failed to join thread"); + abort(); + } + } + pthread_barrier_destroy(args->barrier); + free(args->tinfo); + free(args->token); + free(args->barrier); + free(args->args_head); + + for (i = 0; i < MM_CID_COMPACT_TIMEOUT; i++) { + curr_mm_cid = rseq_current_mm_cid(); + printf_verbose("run %d: mm_cid=%d on cpu%d.\n", i, + curr_mm_cid, sched_getcpu()); + if (curr_mm_cid == 0) + exit(EXIT_SUCCESS); + usleep(RUNNER_PERIOD); + } + exit(EXIT_FAILURE); + } + printf_verbose("cpu%d has mm_cid=%d and is going to terminate.\n", + sched_getcpu(), curr_mm_cid); + pthread_exit(NULL); +} + +int test_mm_cid_compaction(void) +{ + cpu_set_t affinity; + int i, j, ret = 0, num_threads; + pthread_t *tinfo; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + struct thread_args *args; + + sched_getaffinity(0, sizeof(affinity), &affinity); + num_threads = CPU_COUNT(&affinity); + tinfo = calloc(num_threads, sizeof(*tinfo)); + if (!tinfo) { + perror("Error: failed to allocate tinfo"); + return -1; + } + args = calloc(num_threads, sizeof(*args)); + if (!args) { + perror("Error: failed to allocate args"); + ret = -1; + goto out_free_tinfo; + } + token = malloc(sizeof(*token)); + if (!token) { + perror("Error: failed to allocate token"); + ret = -1; + goto out_free_args; + } + barrier = malloc(sizeof(*barrier)); + if (!barrier) { + perror("Error: failed to allocate barrier"); + ret = -1; + goto out_free_token; + } + if (num_threads == 1) { + fprintf(stderr, "Cannot test on a single cpu. " + "Skipping mm_cid_compaction test.\n"); + /* only skipping the test, this is not a failure */ + goto out_free_barrier; + } + pthread_mutex_init(token, NULL); + ret = pthread_barrier_init(barrier, NULL, num_threads); + if (ret) { + errno = ret; + perror("Error: failed to initialise barrier"); + goto out_free_barrier; + } + for (i = 0, j = 0; i < CPU_SETSIZE && j < num_threads; i++) { + if (!CPU_ISSET(i, &affinity)) + continue; + args[j].num_cpus = num_threads; + args[j].tinfo = tinfo; + args[j].token = token; + args[j].barrier = barrier; + args[j].cpu = i; + args[j].args_head = args; + if (!j) { + /* The first thread is the main one */ + tinfo[0] = pthread_self(); + ++j; + continue; + } + ret = pthread_create(&tinfo[j], NULL, thread_runner, &args[j]); + if (ret) { + errno = ret; + perror("Error: failed to create thread"); + abort(); + } + ++j; + } + printf_verbose("Started %d threads.\n", num_threads); + + /* Also main thread will terminate if it is not selected as leader */ + thread_runner(&args[0]); + + /* only reached in case of errors */ +out_free_barrier: + free(barrier); +out_free_token: + free(token); +out_free_args: + free(args); +out_free_tinfo: + free(tinfo); + + return ret; +} + +int main(int argc, char **argv) +{ + if (!rseq_mm_cid_available()) { + fprintf(stderr, "Error: rseq_mm_cid unavailable\n"); + return -1; + } + if (test_mm_cid_compaction()) + return -1; + return 0; +} -- 2.48.1

8 months, 1 week

1
0
0 0

[PATCH net-next] selftests/net: ensure mptcp is enabled in netns

by Hangbin Liu

Some distributions may not enable MPTCP by default. All other MPTCP tests source mptcp_lib.sh to ensure MPTCP is enabled before testing. However, the ip_local_port_range test is the only one that does not include this step. Let's also ensure MPTCP is enabled in netns for ip_local_port_range so that it passes on all distributions. Suggested-by: Davide Caratti <dcaratti(a)redhat.com> Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com> --- tools/testing/selftests/net/ip_local_port_range.sh | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/ip_local_port_range.sh b/tools/testing/selftests/net/ip_local_port_range.sh index 6c6ad346eaa0..4ff746db1256 100755 --- a/tools/testing/selftests/net/ip_local_port_range.sh +++ b/tools/testing/selftests/net/ip_local_port_range.sh @@ -2,4 +2,6 @@ # SPDX-License-Identifier: GPL-2.0 ./in_netns.sh \ - sh -c 'sysctl -q -w net.ipv4.ip_local_port_range="40000 49999" && ./ip_local_port_range' + sh -c 'sysctl -q -w net.mptcp.enabled=1 && \ + sysctl -q -w net.ipv4.ip_local_port_range="40000 49999" && \ + ./ip_local_port_range' -- 2.46.0

8 months, 1 week

3
3
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror February 2025