April 2024 - Linux-kselftest-mirror

[PATCH 6.6.y] selftests/timers/posix_timers: Reimplement check_timer_distribution()

by Edward Liaw

From: Oleg Nesterov <oleg(a)redhat.com> check_timer_distribution() runs ten threads in a busy loop and tries to test that the kernel distributes a process posix CPU timer signal to every thread over time. There is not guarantee that this is true even after commit bcb7ee79029d ("posix-timers: Prefer delivery of signals to the current thread") because that commit only avoids waking up the sleeping process leader thread, but that has nothing to do with the actual signal delivery. As the signal is process wide the first thread which observes sigpending and wins the race to lock sighand will deliver the signal. Testing shows that this hangs on a regular base because some threads never win the race. The comment "This primarily tests that the kernel does not favour any one." is wrong. The kernel does favour a thread which hits the timer interrupt when CLOCK_PROCESS_CPUTIME_ID expires. Rewrite the test so it only checks that the group leader sleeping in join() never receives SIGALRM and the thread which burns CPU cycles receives all signals. In older kernels which do not have commit bcb7ee79029d ("posix-timers: Prefer delivery of signals to the current thread") the test-case fails immediately, the very 1st tick wakes the leader up. Otherwise it quickly succeeds after 100 ticks. CI testing wants to use newer selftest versions on stable kernels. In this case the test is guaranteed to fail. So check in the failure case whether the kernel version is less than v6.3 and skip the test result in that case. [ tglx: Massaged change log, renamed the version check helper ] [ edliaw: 071af0c9e582 ("selftests: timers: Convert posix_timers test to generate KTAP output") wasn't merged to 6.6.y, so resolved merge conflicts. ] Fixes: e797203fb3ba ("selftests/timers/posix_timers: Test delivery of signals across threads") Signed-off-by: Oleg Nesterov <oleg(a)redhat.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/20240409133802.GD29396@redhat.com (cherry picked from commit 6d029c25b71f2de2838a6f093ce0fa0e69336154) Signed-off-by: Edward Liaw <edliaw(a)google.com> --- tools/testing/selftests/kselftest.h | 13 +++ tools/testing/selftests/timers/posix_timers.c | 99 +++++++++---------- 2 files changed, 59 insertions(+), 53 deletions(-) diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 529d29a35900..68d5a93dff8d 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -49,6 +49,7 @@ #include <unistd.h> #include <stdarg.h> #include <stdio.h> +#include <sys/utsname.h> #endif #ifndef ARRAY_SIZE @@ -327,4 +328,16 @@ static inline int ksft_exit_skip(const char *msg, ...) exit(KSFT_SKIP); } +static inline int ksft_min_kernel_version(unsigned int min_major, + unsigned int min_minor) +{ + unsigned int major, minor; + struct utsname info; + + if (uname(&info) || sscanf(info.release, "%u.%u.", &major, &minor) != 2) + ksft_exit_fail_msg("Can't parse kernel version\n"); + + return major > min_major || (major == min_major && minor >= min_minor); +} + #endif /* __KSELFTEST_H */ diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index 9a42403eaff7..aaec7f9845c5 100644 --- a/tools/testing/selftests/timers/posix_timers.c +++ b/tools/testing/selftests/timers/posix_timers.c @@ -188,78 +188,71 @@ static int check_timer_create(int which) return 0; } -int remain; -__thread int got_signal; +static pthread_t ctd_thread; +static volatile int ctd_count, ctd_failed; -static void *distribution_thread(void *arg) +static void ctd_sighandler(int sig) { - while (__atomic_load_n(&remain, __ATOMIC_RELAXED)); - return NULL; + if (pthread_self() != ctd_thread) + ctd_failed = 1; + ctd_count--; } -static void distribution_handler(int nr) +static void *ctd_thread_func(void *arg) { - if (!__atomic_exchange_n(&got_signal, 1, __ATOMIC_RELAXED)) - __atomic_fetch_sub(&remain, 1, __ATOMIC_RELAXED); -} - -/* - * Test that all running threads _eventually_ receive CLOCK_PROCESS_CPUTIME_ID - * timer signals. This primarily tests that the kernel does not favour any one. - */ -static int check_timer_distribution(void) -{ - int err, i; - timer_t id; - const int nthreads = 10; - pthread_t threads[nthreads]; struct itimerspec val = { .it_value.tv_sec = 0, .it_value.tv_nsec = 1000 * 1000, .it_interval.tv_sec = 0, .it_interval.tv_nsec = 1000 * 1000, }; + timer_t id; - printf("Check timer_create() per process signal distribution... "); - fflush(stdout); + /* 1/10 seconds to ensure the leader sleeps */ + usleep(10000); - remain = nthreads + 1; /* worker threads + this thread */ - signal(SIGALRM, distribution_handler); - err = timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id); - if (err < 0) { - perror("Can't create timer\n"); - return -1; - } - err = timer_settime(id, 0, &val, NULL); - if (err < 0) { - perror("Can't set timer\n"); - return -1; - } + ctd_count = 100; + if (timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id)) + return "Can't create timer\n"; + if (timer_settime(id, 0, &val, NULL)) + return "Can't set timer\n"; - for (i = 0; i < nthreads; i++) { - if (pthread_create(&threads[i], NULL, distribution_thread, NULL)) { - perror("Can't create thread\n"); - return -1; - } - } + while (ctd_count > 0 && !ctd_failed) + ; - /* Wait for all threads to receive the signal. */ - while (__atomic_load_n(&remain, __ATOMIC_RELAXED)); + if (timer_delete(id)) + return "Can't delete timer\n"; - for (i = 0; i < nthreads; i++) { - if (pthread_join(threads[i], NULL)) { - perror("Can't join thread\n"); - return -1; - } - } + return NULL; +} - if (timer_delete(id)) { - perror("Can't delete timer\n"); - return -1; - } +/* + * Test that only the running thread receives the timer signal. + */ +static int check_timer_distribution(void) +{ + const char *errmsg; - printf("[OK]\n"); + signal(SIGALRM, ctd_sighandler); + + errmsg = "Can't create thread\n"; + if (pthread_create(&ctd_thread, NULL, ctd_thread_func, NULL)) + goto err; + + errmsg = "Can't join thread\n"; + if (pthread_join(ctd_thread, (void **)&errmsg) || errmsg) + goto err; + + if (!ctd_failed) + ksft_test_result_pass("check signal distribution\n"); + else if (ksft_min_kernel_version(6, 3)) + ksft_test_result_fail("check signal distribution\n"); + else + ksft_test_result_skip("check signal distribution (old kernel)\n"); return 0; +err: + ksft_print_msg(errmsg); + return -1; } int main(int argc, char **argv) -- 2.44.0.769.g3c40516874-goog

1 year, 4 months

1
0
0 0

[PATCH v2 0/1] selftest mm/mseal compile warning

by jeffxu＠chromium.org

From: Jeff Xu <jeffxu(a)chromium.org> fix compile warning reported by test robot [1] Please apply on top of patch titled: "selftest mm/mseal: style change" (which already in mm-unstable) [1] https://lore.kernel.org/all/202404190226.OfJOewV8-lkp@intel.com/ History: V2: fix as suggested by Pedro Falcato v1: https://lore.kernel.org/linux-mm/20240419034350.127838-2-jeffxu@chromium.or… Thanks! -Jeff Jeff Xu (1): selftest mm/mseal: fix compile warning tools/testing/selftests/mm/mseal_test.c | 3 +-- tools/testing/selftests/mm/seal_elf.c | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) -- 2.44.0.769.g3c40516874-goog

1 year, 4 months

2
2
0 0

[PATCH] selftests: mm: fix linker error for inline function

by Amer Al Shanawany

add 'static' keyword to 'sys_mprotect()' to link properly, otherwise the test won't build. gcc (Ubuntu 12.3.0-1ubuntu1~22.04) 12.3.0 /usr/bin/ld: /tmp/cc7yeABp.o: in function `test_seal_elf': seal_elf.c:(.text+0x7af): undefined reference to `sys_mprotect' /usr/bin/ld: seal_elf.c:(.text+0x82c): undefined reference to `sys_mprotect' /usr/bin/ld: seal_elf.c:(.text+0xa4e): undefined reference to `sys_mprotect' Signed-off-by: Amer Al Shanawany <amer.shanawany(a)gmail.com> --- tools/testing/selftests/mm/seal_elf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/seal_elf.c b/tools/testing/selftests/mm/seal_elf.c index 7143dc4f1b10..f0cf96625e58 100644 --- a/tools/testing/selftests/mm/seal_elf.c +++ b/tools/testing/selftests/mm/seal_elf.c @@ -72,7 +72,7 @@ static void *sys_mmap(void *addr, unsigned long len, unsigned long prot, return sret; } -inline int sys_mprotect(void *ptr, size_t size, unsigned long prot) +static inline int sys_mprotect(void *ptr, size_t size, unsigned long prot) { int sret; -- 2.34.1

1 year, 4 months

1
0
0 0

[PATCH bpf-next v5 0/6] use network helpers, part 1

by Geliang Tang

From: Geliang Tang <tanggeliang(a)kylinos.cn> v5: - address Martin's comments for v4. (thanks) - drop start_server_addr_opts, add opts as a argument of start_server_addr. - add opts argument for connect_to_addr too. - move some patches out of this set, stay with start_server_addr() and connect_to_addr() only in it. v4: - add more patches using make_sockaddr and get_socket_local_port helpers. v3: - address comments of Martin and Eduard in v2. (thanks) - move "int type" to the first argument of start_server_addr and connect_to_addr. - add start_server_addr_opts. - using "sockaddr_storage" instead of "sockaddr". - move start_server_setsockopt patches out of this series. v2: - update patch 6 only, fix errors reported by CI. This patchset uses public helpers start_server_* and connect_to_* defined in network_helpers.c to drop duplicate code. Geliang Tang (6): selftests/bpf: Add start_server_addr helper selftests/bpf: Use start_server_addr in cls_redirect selftests/bpf: Use start_server_addr in sk_assign selftests/bpf: Update arguments of connect_to_addr selftests/bpf: Use connect_to_addr in cls_redirect selftests/bpf: Use connect_to_addr in sk_assign tools/testing/selftests/bpf/network_helpers.c | 27 +++++++-- tools/testing/selftests/bpf/network_helpers.h | 5 +- .../selftests/bpf/prog_tests/cls_redirect.c | 38 +------------ .../selftests/bpf/prog_tests/sk_assign.c | 55 ++----------------- .../selftests/bpf/prog_tests/sock_addr.c | 6 +- 5 files changed, 37 insertions(+), 94 deletions(-) -- 2.40.1

1 year, 4 months

2
7
0 0

[PATCH 0/1] selftest mm/mseal compile warning

by jeffxu＠chromium.org

From: Jeff Xu <jeffxu(a)chromium.org> fix compile warning reported by test robot [1] Please apply on top of patch titled: "selftest mm/mseal: style change" (which already in mm-unstable) [1] https://lore.kernel.org/all/202404190226.OfJOewV8-lkp@intel.com/ Thanks! -Jeff Jeff Xu (1): selftest mm/mseal: fix compile warning tools/testing/selftests/mm/mseal_test.c | 3 +-- tools/testing/selftests/mm/seal_elf.c | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) -- 2.44.0.769.g3c40516874-goog

1 year, 4 months

4
4
0 0

[PATCH 2/2] KVM: selftests: Add KVM/PV clock selftest to prove timer drift correction

by Jack Allister

This test proves that there is an inherent KVM/PV clock drift away from the guest TSC when KVM decides to update the PV time information structure due to a KVM_REQ_MASTERCLOCK_UPDATE. This drift is exascerbated when a guest is using TSC scaling and running at a different frequency to the host TSC [1]. It also proves that KVM_[GS]ET_CLOCK_GUEST API is working to mitigate the drift from TSC to within ±1ns. The test simply records the PVTI (PV time information) at time of guest creation, after KVM has updated it's mapped PVTI structure and once the correction has taken place. A singular point in time is then recorded via the guest TSC and is used to calculate the a PV clock value using each of the 3 PVTI structures. As seen below a drift of ~3500ns is observed if no correction has taken place after KVM has updated the PVTI via master clock update. However, after the correction a delta of at most 1ns can be seen. * selftests: kvm: pvclock_test * scaling tsc from 2999999KHz to 1499999KHz * before=5038374946 uncorrected=5038371437 corrected=5038374945 * delta_uncorrected=3509 delta_corrected=1 Clocksource check code has been borrowed from [2]. [1]: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… [2]: https://lore.kernel.org/kvm/20240106083346.29180-1-dongli.zhang@oracle.com/ Signed-off-by: Jack Allister <jalliste(a)amazon.com> CC: David Woodhouse <dwmw2(a)infradead.org> CC: Paul Durrant <paul(a)xen.org> --- tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/x86_64/pvclock_test.c | 223 ++++++++++++++++++ 2 files changed, 224 insertions(+) create mode 100644 tools/testing/selftests/kvm/x86_64/pvclock_test.c diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 741c7dc16afc..02ee1205bbed 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -87,6 +87,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/pmu_counters_test TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test TEST_GEN_PROGS_x86_64 += x86_64/private_mem_conversions_test TEST_GEN_PROGS_x86_64 += x86_64/private_mem_kvm_exits_test +TEST_GEN_PROGS_x86_64 += x86_64/pvclock_test TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test TEST_GEN_PROGS_x86_64 += x86_64/smaller_maxphyaddr_emulation_test diff --git a/tools/testing/selftests/kvm/x86_64/pvclock_test.c b/tools/testing/selftests/kvm/x86_64/pvclock_test.c new file mode 100644 index 000000000000..172ef4d19c60 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/pvclock_test.c @@ -0,0 +1,223 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright © 2024, Amazon.com, Inc. or its affiliates. + * + * Tests for pvclock API + * KVM_SET_CLOCK_GUEST/KVM_GET_CLOCK_GUEST + */ +#include <asm/pvclock.h> +#include <asm/pvclock-abi.h> +#include <sys/stat.h> +#include <stdint.h> +#include <stdio.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +enum { + STAGE_FIRST_BOOT, + STAGE_UNCORRECTED, + STAGE_CORRECTED, + NUM_STAGES +}; + +#define KVMCLOCK_GPA 0xc0000000ull +#define KVMCLOCK_SIZE sizeof(struct pvclock_vcpu_time_info) + +static void trigger_pvti_update(vm_paddr_t pvti_pa) +{ + /* + * We need a way to trigger KVM to update the fields + * in the PV time info. The easiest way to do this is + * to temporarily switch to the old KVM system time + * method and then switch back to the new one. + */ + wrmsr(MSR_KVM_SYSTEM_TIME, pvti_pa | KVM_MSR_ENABLED); + wrmsr(MSR_KVM_SYSTEM_TIME_NEW, pvti_pa | KVM_MSR_ENABLED); +} + +static void guest_code(vm_paddr_t pvti_pa) +{ + struct pvclock_vcpu_time_info *pvti_va = + (struct pvclock_vcpu_time_info *)pvti_pa; + + struct pvclock_vcpu_time_info pvti_boot; + struct pvclock_vcpu_time_info pvti_uncorrected; + struct pvclock_vcpu_time_info pvti_corrected; + uint64_t cycles_boot; + uint64_t cycles_uncorrected; + uint64_t cycles_corrected; + uint64_t tsc_guest; + + /* + * Setup the KVMCLOCK in the guest & store the original + * PV time structure that is used. + */ + wrmsr(MSR_KVM_SYSTEM_TIME_NEW, pvti_pa | KVM_MSR_ENABLED); + pvti_boot = *pvti_va; + GUEST_SYNC(STAGE_FIRST_BOOT); + + /* + * Trigger an update of the PVTI, if we calculate + * the KVM clock using this structure we'll see + * a drift from the TSC. + */ + trigger_pvti_update(pvti_pa); + pvti_uncorrected = *pvti_va; + GUEST_SYNC(STAGE_UNCORRECTED); + + /* + * The test should have triggered the correction by this + * point in time. We have a copy of each of the PVTI structs + * at each stage now. + * + * Let's sample the timestamp at a SINGLE point in time and + * then calculate what the KVM clock would be using the PVTI + * from each stage. + * + * Then return each of these values to the tester. + */ + pvti_corrected = *pvti_va; + tsc_guest = rdtsc(); + + cycles_boot = __pvclock_read_cycles(&pvti_boot, tsc_guest); + cycles_uncorrected = __pvclock_read_cycles(&pvti_uncorrected, tsc_guest); + cycles_corrected = __pvclock_read_cycles(&pvti_corrected, tsc_guest); + + GUEST_SYNC_ARGS(STAGE_CORRECTED, cycles_boot, cycles_uncorrected, + cycles_corrected, 0); +} + +static void run_test(struct kvm_vm *vm, struct kvm_vcpu *vcpu) +{ + struct ucall uc; + uint64_t ucall_reason; + struct pvclock_vcpu_time_info pvti_before; + uint64_t before, uncorrected, corrected; + int64_t delta_uncorrected, delta_corrected; + + /* Loop through each stage of the test. */ + while (true) { + + /* Start/restart the running vCPU code. */ + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + + /* Retrieve and verify our stage. */ + ucall_reason = get_ucall(vcpu, &uc); + TEST_ASSERT(ucall_reason == UCALL_SYNC, + "Unhandled ucall reason=%lu", + ucall_reason); + + /* Run host specific code relating to stage. */ + switch (uc.args[1]) { + case STAGE_FIRST_BOOT: + /* Store the KVM clock values before an update. */ + vm_ioctl(vm, KVM_GET_CLOCK_GUEST, &pvti_before); + + /* Sleep for a set amount of time to induce drift. */ + sleep(5); + break; + + case STAGE_UNCORRECTED: + /* Restore the KVM clock values. */ + vm_ioctl(vm, KVM_SET_CLOCK_GUEST, &pvti_before); + break; + + case STAGE_CORRECTED: + /* Query the clock information and verify delta. */ + before = uc.args[2]; + uncorrected = uc.args[3]; + corrected = uc.args[4]; + + delta_uncorrected = before - uncorrected; + delta_corrected = before - corrected; + + pr_info("before=%lu uncorrected=%lu corrected=%lu\n", + before, uncorrected, corrected); + + pr_info("delta_uncorrected=%ld delta_corrected=%ld\n", + delta_uncorrected, delta_corrected); + + TEST_ASSERT((delta_corrected <= 1) && (delta_corrected >= -1), + "larger than expected delta detected = %ld", delta_corrected); + return; + } + } +} + +#define CLOCKSOURCE_PATH "/sys/devices/system/clocksource/clocksource0/current_clocksource" + +static void check_clocksource(void) +{ + char *clk_name; + struct stat st; + FILE *fp; + + fp = fopen(CLOCKSOURCE_PATH, "r"); + if (!fp) { + pr_info("failed to open clocksource file: %d; assuming TSC.\n", + errno); + return; + } + + if (fstat(fileno(fp), &st)) { + pr_info("failed to stat clocksource file: %d; assuming TSC.\n", + errno); + goto out; + } + + clk_name = malloc(st.st_size); + TEST_ASSERT(clk_name, "failed to allocate buffer to read file\n"); + + if (!fgets(clk_name, st.st_size, fp)) { + pr_info("failed to read clocksource file: %d; assuming TSC.\n", + ferror(fp)); + goto out; + } + + TEST_ASSERT(!strncmp(clk_name, "tsc\n", st.st_size), + "clocksource not supported: %s", clk_name); +out: + fclose(fp); +} + +static void configure_pvclock(struct kvm_vm *vm, struct kvm_vcpu *vcpu) +{ + unsigned int gpages; + + gpages = vm_calc_num_guest_pages(VM_MODE_DEFAULT, KVMCLOCK_SIZE); + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + KVMCLOCK_GPA, 1, gpages, 0); + virt_map(vm, KVMCLOCK_GPA, KVMCLOCK_GPA, gpages); + + vcpu_args_set(vcpu, 1, KVMCLOCK_GPA); +} + +static void configure_scaled_tsc(struct kvm_vcpu *vcpu) +{ + uint64_t tsc_khz; + + tsc_khz = __vcpu_ioctl(vcpu, KVM_GET_TSC_KHZ, NULL); + pr_info("scaling tsc from %ldKHz to %ldKHz\n", tsc_khz, tsc_khz / 2); + tsc_khz /= 2; + vcpu_ioctl(vcpu, KVM_SET_TSC_KHZ, (void *)tsc_khz); +} + +int main(void) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + + check_clocksource(); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + configure_pvclock(vm, vcpu); + configure_scaled_tsc(vcpu); + + run_test(vm, vcpu); + + return 0; +} -- 2.40.1

1 year, 4 months

5
7
0 0

[PATCH v7 00/24] RISC-V SBI v2.0 PMU improvements and Perf sampling in KVM guest

by Atish Patra

This series implements SBI PMU improvements done in SBI v2.0[1] i.e. PMU snapshot and fw_read_hi() functions. SBI v2.0 introduced PMU snapshot feature which allows the SBI implementation to provide counter information (i.e. values/overflow status) via a shared memory between the SBI implementation and supervisor OS. This allows to minimize the number of traps in when perf being used inside a kvm guest as it relies on SBI PMU + trap/emulation of the counters. The current set of ratified RISC-V specification also doesn't allow scountovf to be trap/emulated by the hypervisor. The SBI PMU snapshot bridges the gap in ISA as well and enables perf sampling in the guest. However, LCOFI in the guest only works via IRQ filtering in AIA specification. That's why, AIA has to be enabled in the hardware (at least the Ssaia extension) in order to use the sampling support in the perf. Here are the patch wise implementation details. PATCH 1,4,7,8,9,10,11,15 : Generic cleanups/improvements. PATCH 2,3,14 : FW_READ_HI function implementation PATCH 5-6: Add PMU snapshot feature in sbi pmu driver PATCH 12-13: KVM implementation for snapshot and sampling in kvm guests PATCH 16-17: Generic improvements for kvm selftests PATCH 18-22: KVM selftests for SBI PMU extension The series is based on v6.9-rc4 and is available at: https://github.com/atishp04/linux/tree/kvm_pmu_snapshot_v7 The kvmtool patch is also available at: https://github.com/atishp04/kvmtool/tree/sscofpmf It also requires Ssaia ISA extension to be present in the hardware in order to get perf sampling support in the guest. In Qemu virt machine, it can be done by the following config. ``` -cpu rv64,sscofpmf=true,x-ssaia=true ``` There is no other dependencies on AIA apart from that. Thus, Ssaia must be disabled for the guest if AIA patches are not available. Here is the example command. ``` ./lkvm-static run -m 256 -c2 --console serial -p "console=ttyS0 earlycon" --disable-ssaia -k ./Image --debug ``` The series has been tested only in Qemu. Here is the snippet of the perf running inside a kvm guest. =================================================== $ perf record -e cycles -e instructions perf bench sched messaging -g 5 ... $ Running 'sched/messaging' benchmark: ... [ 45.928723] perf_duration_warn: 2 callbacks suppressed [ 45.929000] perf: interrupt took too long (484426 > 483186), lowering kernel.perf_event_max_sample_rate to 250 $ 20 sender and receiver processes per group $ 5 groups == 200 processes run Total time: 14.220 [sec] [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.117 MB perf.data (1942 samples) ] $ perf report --stdio $ To display the perf.data header info, please use --header/--header-only optio> $ $ $ Total Lost Samples: 0 $ $ Samples: 943 of event 'cycles' $ Event count (approx.): 5128976844 $ $ Overhead Command Shared Object Symbol > $ ........ ............... ........................... .....................> $ 7.59% sched-messaging [kernel.kallsyms] [k] memcpy 5.48% sched-messaging [kernel.kallsyms] [k] percpu_counter_ad> 5.24% sched-messaging [kernel.kallsyms] [k] __sbi_rfence_v02_> 4.00% sched-messaging [kernel.kallsyms] [k] _raw_spin_unlock_> 3.79% sched-messaging [kernel.kallsyms] [k] set_pte_range 3.72% sched-messaging [kernel.kallsyms] [k] next_uptodate_fol> 3.46% sched-messaging [kernel.kallsyms] [k] filemap_map_pages 3.31% sched-messaging [kernel.kallsyms] [k] handle_mm_fault 3.20% sched-messaging [kernel.kallsyms] [k] finish_task_switc> 3.16% sched-messaging [kernel.kallsyms] [k] clear_page 3.03% sched-messaging [kernel.kallsyms] [k] mtree_range_walk 2.42% sched-messaging [kernel.kallsyms] [k] flush_icache_pte =================================================== [1] https://github.com/riscv-non-isa/riscv-sbi-doc Changes from v6->v7: 1. Used SBI_SHMEM_DISABLE in the driver. 2. Added RB Tags. 3. Improved the sbi_pmu_test commandline to allow disabling multiple tests. Changes from v5->v6: 1. Added a patch for command line option for the sbi pmu tests. 2. Removed redundant prints and restructure the code little bit. 3. Added a patch for computing the sbi minor version correctly. 4. Addressed all other comments on v5. Changes from v4->v5: 1. Moved sbi related definitions to its own header file from processor.h 2. Added few helper functions for selftests. 3. Improved firmware counter read and RV32 start/stop functions. 4. Converted all the shifting operations to use BIT macro 5. Addressed all other comments on v4. Changes from v3->v4: 1. Added selftests. 2. Fixed an issue to clear the interrupt pending bits. 3. Fixed the counter index in snapshot memory start function. Changes from v2->v3: 1. Fixed a patchwork warning on patch6. 2. Fixed a comment formatting & nit fix in PATCH 3 & 5. 3. Moved the hvien update and sscofpmf enabling to PATCH 9 from PATCH 8. Changes from v1->v2: 1. Fixed warning/errors from patchwork CI. 2. Rebased on top of kvm-next. 3. Added Acked-by tags. Changes from RFC->v1: 1. Addressed all the comments on RFC series. 2. Removed PATCH2 and merged into later patches. 3. Added 2 more patches for minor fixes. 4. Fixed KVM boot issue without Ssaia and made sscofpmf in guest dependent on Ssaia in the host. Atish Patra (24): RISC-V: Fix the typo in Scountovf CSR name RISC-V: Add FIRMWARE_READ_HI definition drivers/perf: riscv: Read upper bits of a firmware counter drivers/perf: riscv: Use BIT macro for shifting operations RISC-V: Add SBI PMU snapshot definitions RISC-V: KVM: Rename the SBI_STA_SHMEM_DISABLE to a generic name RISC-V: Use the minor version mask while computing sbi version drivers/perf: riscv: Implement SBI PMU snapshot function drivers/perf: riscv: Fix counter mask iteration for RV32 RISC-V: KVM: Fix the initial sample period value RISC-V: KVM: No need to update the counter value during reset RISC-V: KVM: No need to exit to the user space if perf event failed RISC-V: KVM: Implement SBI PMU Snapshot feature RISC-V: KVM: Add perf sampling support for guests RISC-V: KVM: Support 64 bit firmware counters on RV32 RISC-V: KVM: Improve firmware counter read function KVM: riscv: selftests: Move sbi definitions to its own header file KVM: riscv: selftests: Add helper functions for extension checks KVM: riscv: selftests: Add Sscofpmf to get-reg-list test KVM: riscv: selftests: Add SBI PMU extension definitions KVM: riscv: selftests: Add SBI PMU selftest KVM: riscv: selftests: Add a test for PMU snapshot functionality KVM: riscv: selftests: Add a test for counter overflow KVM: riscv: selftests: Add commandline option for SBI PMU test arch/riscv/include/asm/csr.h | 5 +- arch/riscv/include/asm/kvm_vcpu_pmu.h | 16 +- arch/riscv/include/asm/sbi.h | 38 +- arch/riscv/include/uapi/asm/kvm.h | 1 + arch/riscv/kernel/paravirt.c | 6 +- arch/riscv/kvm/aia.c | 5 + arch/riscv/kvm/vcpu.c | 15 +- arch/riscv/kvm/vcpu_onereg.c | 6 + arch/riscv/kvm/vcpu_pmu.c | 260 ++++++- arch/riscv/kvm/vcpu_sbi_pmu.c | 17 +- arch/riscv/kvm/vcpu_sbi_sta.c | 4 +- drivers/perf/riscv_pmu.c | 1 + drivers/perf/riscv_pmu_sbi.c | 272 ++++++- include/linux/perf/riscv_pmu.h | 6 + tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/include/riscv/processor.h | 49 +- .../testing/selftests/kvm/include/riscv/sbi.h | 141 ++++ .../selftests/kvm/include/riscv/ucall.h | 1 + .../selftests/kvm/lib/riscv/processor.c | 12 + .../testing/selftests/kvm/riscv/arch_timer.c | 2 +- .../selftests/kvm/riscv/get-reg-list.c | 4 + .../selftests/kvm/riscv/sbi_pmu_test.c | 681 ++++++++++++++++++ tools/testing/selftests/kvm/steal_time.c | 4 +- 23 files changed, 1433 insertions(+), 114 deletions(-) create mode 100644 tools/testing/selftests/kvm/include/riscv/sbi.h create mode 100644 tools/testing/selftests/kvm/riscv/sbi_pmu_test.c -- 2.34.1

1 year, 4 months

4
29
0 0

Re: [PATCH v4 00/14] security: digest_cache LSM

by Bagas Sanjaya

On 4/18/24 02:02, Roberto Sassu wrote: > > 72374d71c315 > > Roberto > Still FTA (fail to apply), unfortunately. -- An old man doll... just what I always wanted! - Clara

1 year, 4 months

3
2
0 0

[PATCH] selftests: Fix asan linkage to work with clang

by Ryan Roberts

Both fchmodat2 and openat2 statically link against libasan (for explanation of why, look at the fixes commit). This is done using `-static-libasan`. However, it turns out that clang uses a different option, `-static-libsan`. This caused clang to fail to compile the tests. Fix this by using cc-option to figure out which variant to use. While we are at it, stop passing helpers.h as a compilation unit. This was causing another clang error due to name conflict with helpers.c's object file. This header shouldn't be directly compiled anyway. Fixes: c652df8a4a9d ("selftests: link libasan statically for tests with -fsanitize=address") Reported-by: kernel test robot <yujie.liu(a)intel.com> Closes: https://lore.kernel.org/r/202404141807.LgsqXPY5-lkp@intel.com/ Suggested-by: Arnd Bergmann <arnd(a)arndb.de> Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com> --- Applies on v6.9-rc4. Thanks, Ryan tools/testing/selftests/fchmodat2/Makefile | 5 ++++- tools/testing/selftests/openat2/Makefile | 7 +++++-- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/fchmodat2/Makefile b/tools/testing/selftests/fchmodat2/Makefile index 71ec34bf1501..a68bb5a00797 100644 --- a/tools/testing/selftests/fchmodat2/Makefile +++ b/tools/testing/selftests/fchmodat2/Makefile @@ -1,6 +1,9 @@ # SPDX-License-Identifier: GPL-2.0-or-later +# We need this for the "cc-option" macro. +include ../../../build/Build.include -CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined -static-libasan $(KHDR_INCLUDES) +CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined $(KHDR_INCLUDES) +CFLAGS += $(call cc-option, -static-libasan) $(call cc-option, -static-libsan) TEST_GEN_PROGS := fchmodat2_test include ../lib.mk diff --git a/tools/testing/selftests/openat2/Makefile b/tools/testing/selftests/openat2/Makefile index 254d676a2689..02af9b6ca5eb 100644 --- a/tools/testing/selftests/openat2/Makefile +++ b/tools/testing/selftests/openat2/Makefile @@ -1,8 +1,11 @@ # SPDX-License-Identifier: GPL-2.0-or-later +# We need this for the "cc-option" macro. +include ../../../build/Build.include -CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined -static-libasan +CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined +CFLAGS += $(call cc-option, -static-libasan) $(call cc-option, -static-libsan) TEST_GEN_PROGS := openat2_test resolve_test rename_attack_test include ../lib.mk -$(TEST_GEN_PROGS): helpers.c helpers.h +$(TEST_GEN_PROGS): helpers.c -- 2.25.1

1 year, 4 months

2
1
0 0

[PATCH bpf-next 00/18] Introduce bpf_wq

by Benjamin Tissoires

This is a followup of sleepable bpf_timer[0]. When discussing sleepable bpf_timer, it was thought that we should give a try to bpf_wq, as the 2 APIs are similar but distinct enough to justify a new one. So here it is. I tried to keep as much as possible common code in kernel/bpf/helpers.c but I couldn't get away with code duplication in kernel/bpf/verifier.c. This series introduces a basic bpf_wq support: - creation is supported - assignment is supported - running a simple bpf_wq is also supported. We will probably need to extend the API further with: - a full delayed_work API (can be piggy backed on top with a correct flag) - bpf_wq_cancel() - bpf_wq_cancel_sync() (for sleepable programs) - documentation But for now, let's focus on what we currently have to see if it's worth it compared to sleepable bpf_timer. FWIW, I still have a couple of concerns with this implementation: - I'm explicitely declaring the async callback as sleepable or not (BPF_F_WQ_SLEEPABLE) through a flag. Is it really worth it? Or should I just consider that any wq is running in a sleepable context? - bpf_wq_work() access ->prog without protection, but I think this might be racing with bpf_wq_set_callback(): if we have the following: CPU 0 CPU 1 bpf_wq_set_callback() bpf_start() bpf_wq_work(): prog = cb->prog; bpf_wq_set_callback() cb->prog = prog; bpf_prog_put(prev) rcu_assign_ptr(cb->callback_fn, callback_fn); callback = READ_ONCE(w->cb.callback_fn); As I understand callback_fn is fine, prog might be, but we clearly have an inconstency between "prog" and "callback_fn" as they can come from 2 different bpf_wq_set_callback() calls. IMO we should protect this by the async->lock, but I'm not sure if it's OK or not. --- For reference, the use cases I have in mind: --- Basically, I need to be able to defer a HID-BPF program for the following reasons (from the aforementioned patch): 1. defer an event: Sometimes we receive an out of proximity event, but the device can not be trusted enough, and we need to ensure that we won't receive another one in the following n milliseconds. So we need to wait those n milliseconds, and eventually re-inject that event in the stack. 2. inject new events in reaction to one given event: We might want to transform one given event into several. This is the case for macro keys where a single key press is supposed to send a sequence of key presses. But this could also be used to patch a faulty behavior, if a device forgets to send a release event. 3. communicate with the device in reaction to one event: We might want to communicate back to the device after a given event. For example a device might send us an event saying that it came back from sleeping state and needs to be re-initialized. Currently we can achieve that by keeping a userspace program around, raise a bpf event, and let that userspace program inject the events and commands. However, we are just keeping that program alive as a daemon for just scheduling commands. There is no logic in it, so it doesn't really justify an actual userspace wakeup. So a kernel workqueue seems simpler to handle. bpf_timers are currently running in a soft IRQ context, this patch series implements a sleppable context for them. Cheers, Benjamin To: Alexei Starovoitov <ast(a)kernel.org> To: Daniel Borkmann <daniel(a)iogearbox.net> To: Andrii Nakryiko <andrii(a)kernel.org> To: Martin KaFai Lau <martin.lau(a)linux.dev> To: Eduard Zingerman <eddyz87(a)gmail.com> To: Song Liu <song(a)kernel.org> To: Yonghong Song <yonghong.song(a)linux.dev> To: John Fastabend <john.fastabend(a)gmail.com> To: KP Singh <kpsingh(a)kernel.org> To: Stanislav Fomichev <sdf(a)google.com> To: Hao Luo <haoluo(a)google.com> To: Jiri Olsa <jolsa(a)kernel.org> To: Mykola Lysenko <mykolal(a)fb.com> To: Shuah Khan <shuah(a)kernel.org> Cc: <bpf(a)vger.kernel.org> Cc: <linux-kernel(a)vger.kernel.org> Cc: <linux-kselftest(a)vger.kernel.org> Signed-off-by: Benjamin Tissoires <bentiss(a)kernel.org> [0] https://lore.kernel.org/all/20240408-hid-bpf-sleepable-v6-0-0499ddd91b94@ke… --- Benjamin Tissoires (18): bpf: trampoline: export __bpf_prog_enter/exit_recur bpf: make timer data struct more generic bpf: replace bpf_timer_init with a generic helper bpf: replace bpf_timer_set_callback with a generic helper bpf: replace bpf_timer_cancel_and_free with a generic helper bpf: add support for bpf_wq user type tools: sync include/uapi/linux/bpf.h bpf: add support for KF_ARG_PTR_TO_WORKQUEUE bpf: allow struct bpf_wq to be embedded in arraymaps and hashmaps selftests/bpf: add bpf_wq tests bpf: wq: add bpf_wq_init tools: sync include/uapi/linux/bpf.h selftests/bpf: wq: add bpf_wq_init() checks bpf/verifier: add is_sleepable argument to push_callback_call bpf: wq: add bpf_wq_set_callback_impl selftests/bpf: add checks for bpf_wq_set_callback() bpf: add bpf_wq_start selftests/bpf: wq: add bpf_wq_start() checks include/linux/bpf.h | 17 +- include/linux/bpf_verifier.h | 1 + include/uapi/linux/bpf.h | 13 + kernel/bpf/arraymap.c | 18 +- kernel/bpf/btf.c | 17 + kernel/bpf/hashtab.c | 55 ++- kernel/bpf/helpers.c | 371 ++++++++++++++++----- kernel/bpf/syscall.c | 16 +- kernel/bpf/trampoline.c | 6 +- kernel/bpf/verifier.c | 195 ++++++++++- tools/include/uapi/linux/bpf.h | 13 + tools/testing/selftests/bpf/bpf_experimental.h | 7 + .../selftests/bpf/bpf_testmod/bpf_testmod.c | 5 + .../selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h | 1 + tools/testing/selftests/bpf/prog_tests/wq.c | 41 +++ tools/testing/selftests/bpf/progs/wq.c | 192 +++++++++++ tools/testing/selftests/bpf/progs/wq_failures.c | 197 +++++++++++ 17 files changed, 1052 insertions(+), 113 deletions(-) --- base-commit: ffa6b26b4d8a0520b78636ca9373ab842cb3b1a8 change-id: 20240411-bpf_wq-fe24e8d24f5e Best regards, -- Benjamin Tissoires <bentiss(a)kernel.org>

1 year, 4 months

4
31
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror April 2024