| Message ID | 20240110060037.4202-3-laoar.shao@gmail.com (mailing list archive) |
|---|---|
| State | Superseded |
| Delegated to: | BPF |
| Headers | show |
| Series | bpf: Add bpf_iter_cpumask | expand |
On Tue, Jan 9, 2024 at 10:00 PM Yafang Shao <laoar.shao@gmail.com> wrote: > + > +SEC("iter/cgroup") > +int BPF_PROG(cpu_cgroup, struct bpf_iter_meta *meta, struct cgroup *cgrp) > +{ > + u32 *cpu, nr_running = 0, psi_nr_running = 0, nr_cpus = 0; > + unsigned int tasks[NR_PSI_TASK_COUNTS]; > + struct psi_group_cpu *groupc; > + struct bpf_cpumask *mask; > + struct task_struct *p; > + struct rq *rq; > + > + /* epilogue */ > + if (cgrp == NULL) > + return 0; > + > + mask = bpf_cpumask_create(); > + if (!mask) > + return 1; > + > + p = bpf_task_from_pid(target_pid); > + if (!p) { > + bpf_cpumask_release(mask); > + return 1; > + } > + > + bpf_cpumask_copy(mask, p->cpus_ptr); > + bpf_for_each(cpumask, cpu, &mask->cpumask) { > + rq = (struct rq *)bpf_per_cpu_ptr(&runqueues, *cpu); > + if (!rq) > + continue; > + nr_running += rq->nr_running; > + nr_cpus += 1; > + > + groupc = (struct psi_group_cpu *)bpf_per_cpu_ptr(&system_group_pcpu, *cpu); > + if (!groupc) > + continue; > + bpf_probe_read_kernel(&tasks, sizeof(tasks), &groupc->tasks); > + psi_nr_running += tasks[NR_RUNNING]; > + } Instead of probe_read_kernel (which is not fast) please use bpf_rdonly_cast() and access groups->tasks. array should already be recognized by the verifier, but if not let's fix the verifier instead of fallback to probe_read.
On Thu, Jan 11, 2024 at 1:52 AM Alexei Starovoitov <alexei.starovoitov@gmail.com> wrote: > > On Tue, Jan 9, 2024 at 10:00 PM Yafang Shao <laoar.shao@gmail.com> wrote: > > + > > +SEC("iter/cgroup") > > +int BPF_PROG(cpu_cgroup, struct bpf_iter_meta *meta, struct cgroup *cgrp) > > +{ > > + u32 *cpu, nr_running = 0, psi_nr_running = 0, nr_cpus = 0; > > + unsigned int tasks[NR_PSI_TASK_COUNTS]; > > + struct psi_group_cpu *groupc; > > + struct bpf_cpumask *mask; > > + struct task_struct *p; > > + struct rq *rq; > > + > > + /* epilogue */ > > + if (cgrp == NULL) > > + return 0; > > + > > + mask = bpf_cpumask_create(); > > + if (!mask) > > + return 1; > > + > > + p = bpf_task_from_pid(target_pid); > > + if (!p) { > > + bpf_cpumask_release(mask); > > + return 1; > > + } > > + > > + bpf_cpumask_copy(mask, p->cpus_ptr); > > + bpf_for_each(cpumask, cpu, &mask->cpumask) { > > + rq = (struct rq *)bpf_per_cpu_ptr(&runqueues, *cpu); > > + if (!rq) > > + continue; > > + nr_running += rq->nr_running; > > + nr_cpus += 1; > > + > > + groupc = (struct psi_group_cpu *)bpf_per_cpu_ptr(&system_group_pcpu, *cpu); > > + if (!groupc) > > + continue; > > + bpf_probe_read_kernel(&tasks, sizeof(tasks), &groupc->tasks); > > + psi_nr_running += tasks[NR_RUNNING]; > > + } > > Instead of probe_read_kernel (which is not fast) please use > bpf_rdonly_cast() and access groups->tasks. > array should already be recognized by the verifier, but if not let's > fix the verifier instead of fallback to probe_read. Thanks for your suggestion. Will do it.
Hi Yafang, kernel test robot noticed the following build errors: [auto build test ERROR on bpf-next/master] url: https://github.com/intel-lab-lkp/linux/commits/Yafang-Shao/bpf-Add-bpf_iter_cpumask-kfuncs/20240110-140322 base: https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git master patch link: https://lore.kernel.org/r/20240110060037.4202-3-laoar.shao%40gmail.com patch subject: [PATCH v2 bpf-next 2/2] selftests/bpf: Add selftests for cpumask iter compiler: gcc-12 (Debian 12.2.0-14) 12.2.0 reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240115/202401150914.Rcl50Ct9-lkp@intel.com/reproduce) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp@intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202401150914.Rcl50Ct9-lkp@intel.com/ All errors (new ones prefixed by >>): >> progs/test_cpumask_iter.c:20:21: error: use of undeclared identifier 'NR_PSI_TASK_COUNTS' 20 | unsigned int tasks[NR_PSI_TASK_COUNTS]; | ^ >> progs/test_cpumask_iter.c:41:2: error: assigning to 'u32 *' (aka 'unsigned int *') from 'int *' converts between pointers to integer types with different sign [-Werror,-Wpointer-sign] 41 | bpf_for_each(cpumask, cpu, &mask->cpumask) { | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ /tools/include/bpf/bpf_helpers.h:348:10: note: expanded from macro 'bpf_for_each' 348 | (((cur) = bpf_iter_##type##_next(&___it))); \ | ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ >> progs/test_cpumask_iter.c:51:55: error: incomplete definition of type 'struct psi_group_cpu' 51 | bpf_probe_read_kernel(&tasks, sizeof(tasks), &groupc->tasks); | ~~~~~~^ progs/test_cpumask_iter.c:11:21: note: forward declaration of 'struct psi_group_cpu' 11 | extern const struct psi_group_cpu system_group_pcpu __ksym __weak; | ^ >> progs/test_cpumask_iter.c:52:27: error: use of undeclared identifier 'NR_RUNNING'; did you mean 'T_RUNNING'? 52 | psi_nr_running += tasks[NR_RUNNING]; | ^~~~~~~~~~ | T_RUNNING /tools/include/vmlinux.h:11216:3: note: 'T_RUNNING' declared here 11216 | T_RUNNING = 0, | ^ 4 errors generated.
diff --git a/tools/testing/selftests/bpf/prog_tests/cpumask_iter.c b/tools/testing/selftests/bpf/prog_tests/cpumask_iter.c new file mode 100644 index 000000000000..689ccc4d3c3b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cpumask_iter.c @@ -0,0 +1,134 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Yafang Shao <laoar.shao@gmail.com> */ + +#define _GNU_SOURCE +#include <sched.h> +#include <stdio.h> +#include <unistd.h> + +#include <test_progs.h> +#include "cgroup_helpers.h" +#include "test_cpumask_iter.skel.h" + +static void verify_percpu_data(struct bpf_link *link, int nr_cpu_exp, int nr_running_exp) +{ + int iter_fd, len, item, nr_running, psi_running, nr_cpus; + static char buf[128]; + size_t left; + char *p; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (!ASSERT_GE(iter_fd, 0, "iter_fd")) + return; + + memset(buf, 0, sizeof(buf)); + left = ARRAY_SIZE(buf); + p = buf; + while ((len = read(iter_fd, p, left)) > 0) { + p += len; + left -= len; + } + + item = sscanf(buf, "nr_running %u nr_cpus %u psi_running %u\n", + &nr_running, &nr_cpus, &psi_running); + if (nr_cpu_exp == -1) { + ASSERT_EQ(item, -1, "seq_format"); + goto out; + } + + ASSERT_EQ(item, 3, "seq_format"); + ASSERT_GE(nr_running, nr_running_exp, "nr_running"); + ASSERT_GE(psi_running, nr_running_exp, "nr_running"); + ASSERT_EQ(nr_cpus, nr_cpu_exp, "nr_cpus"); + + /* read() after iter finishes should be ok. */ + if (len == 0) + ASSERT_OK(read(iter_fd, buf, sizeof(buf)), "second_read"); + +out: + close(iter_fd); +} + +void test_cpumask_iter(void) +{ + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); + int nr_possible, cgrp_fd, pid, err, cnt, i; + struct test_cpumask_iter *skel = NULL; + union bpf_iter_link_info linfo; + int cpu_ids[] = {1, 3, 4, 5}; + struct bpf_link *link; + cpu_set_t set; + + skel = test_cpumask_iter__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_for_each_cpu__open_and_load")) + return; + + if (setup_cgroup_environment()) + goto destroy; + + /* Utilize the cgroup iter */ + cgrp_fd = get_root_cgroup(); + if (!ASSERT_GE(cgrp_fd, 0, "create cgrp")) + goto cleanup; + + memset(&linfo, 0, sizeof(linfo)); + linfo.cgroup.cgroup_fd = cgrp_fd; + linfo.cgroup.order = BPF_CGROUP_ITER_SELF_ONLY; + opts.link_info = &linfo; + opts.link_info_len = sizeof(linfo); + + link = bpf_program__attach_iter(skel->progs.cpu_cgroup, &opts); + if (!ASSERT_OK_PTR(link, "attach_iter")) + goto close_fd; + + skel->bss->target_pid = 1; + /* In case init task is set CPU affinity */ + err = sched_getaffinity(1, sizeof(set), &set); + if (!ASSERT_OK(err, "setaffinity")) + goto close_fd; + + cnt = CPU_COUNT(&set); + nr_possible = bpf_num_possible_cpus(); + if (test__start_subtest("init_pid")) + /* curent task is running. */ + verify_percpu_data(link, cnt, cnt == nr_possible ? 1 : 0); + + skel->bss->target_pid = -1; + if (test__start_subtest("invalid_pid")) + verify_percpu_data(link, -1, -1); + + pid = getpid(); + skel->bss->target_pid = pid; + CPU_ZERO(&set); + CPU_SET(0, &set); + err = sched_setaffinity(pid, sizeof(set), &set); + if (!ASSERT_OK(err, "setaffinity")) + goto free_link; + + if (test__start_subtest("self_pid_one_cpu")) + verify_percpu_data(link, 1, 1); + + /* Assume there are at least 8 CPUs on the testbed */ + if (nr_possible < 8) + goto free_link; + + CPU_ZERO(&set); + /* Set the CPU affinitiy: 1,3-5 */ + for (i = 0; i < ARRAY_SIZE(cpu_ids); i++) + CPU_SET(cpu_ids[i], &set); + err = sched_setaffinity(pid, sizeof(set), &set); + if (!ASSERT_OK(err, "setaffinity")) + goto free_link; + + if (test__start_subtest("self_pid_multi_cpus")) + verify_percpu_data(link, ARRAY_SIZE(cpu_ids), 1); + +free_link: + bpf_link__destroy(link); +close_fd: + close(cgrp_fd); +cleanup: + cleanup_cgroup_environment(); +destroy: + test_cpumask_iter__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/cpumask_common.h b/tools/testing/selftests/bpf/progs/cpumask_common.h index 0cd4aebb97cf..5f2f44eca4c4 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_common.h +++ b/tools/testing/selftests/bpf/progs/cpumask_common.h @@ -55,6 +55,9 @@ void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) __ksym u32 bpf_cpumask_any_distribute(const struct cpumask *src) __ksym; u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1, const struct cpumask *src2) __ksym; u32 bpf_cpumask_weight(const struct cpumask *cpumask) __ksym; +int bpf_iter_cpumask_new(struct bpf_iter_cpumask *it, struct cpumask *mask) __ksym; +int *bpf_iter_cpumask_next(struct bpf_iter_cpumask *it) __ksym; +void bpf_iter_cpumask_destroy(struct bpf_iter_cpumask *it) __ksym; void bpf_rcu_read_lock(void) __ksym; void bpf_rcu_read_unlock(void) __ksym; diff --git a/tools/testing/selftests/bpf/progs/test_cpumask_iter.c b/tools/testing/selftests/bpf/progs/test_cpumask_iter.c new file mode 100644 index 000000000000..68ebfa0963c7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_cpumask_iter.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2023 Yafang Shao <laoar.shao@gmail.com> */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#include "task_kfunc_common.h" +#include "cpumask_common.h" + +extern const struct psi_group_cpu system_group_pcpu __ksym __weak; +extern const struct rq runqueues __ksym __weak; + +int target_pid; + +SEC("iter/cgroup") +int BPF_PROG(cpu_cgroup, struct bpf_iter_meta *meta, struct cgroup *cgrp) +{ + u32 *cpu, nr_running = 0, psi_nr_running = 0, nr_cpus = 0; + unsigned int tasks[NR_PSI_TASK_COUNTS]; + struct psi_group_cpu *groupc; + struct bpf_cpumask *mask; + struct task_struct *p; + struct rq *rq; + + /* epilogue */ + if (cgrp == NULL) + return 0; + + mask = bpf_cpumask_create(); + if (!mask) + return 1; + + p = bpf_task_from_pid(target_pid); + if (!p) { + bpf_cpumask_release(mask); + return 1; + } + + bpf_cpumask_copy(mask, p->cpus_ptr); + bpf_for_each(cpumask, cpu, &mask->cpumask) { + rq = (struct rq *)bpf_per_cpu_ptr(&runqueues, *cpu); + if (!rq) + continue; + nr_running += rq->nr_running; + nr_cpus += 1; + + groupc = (struct psi_group_cpu *)bpf_per_cpu_ptr(&system_group_pcpu, *cpu); + if (!groupc) + continue; + bpf_probe_read_kernel(&tasks, sizeof(tasks), &groupc->tasks); + psi_nr_running += tasks[NR_RUNNING]; + } + BPF_SEQ_PRINTF(meta->seq, "nr_running %u nr_cpus %u psi_running %u\n", + nr_running, nr_cpus, psi_nr_running); + + bpf_task_release(p); + bpf_cpumask_release(mask); + return 0; +} + +char _license[] SEC("license") = "GPL";
Within the BPF program, we leverage the cgroup iterator to iterate through percpu runqueue data, specifically the 'nr_running' metric. Subsequently we expose this data to userspace by means of a sequence file. The CPU affinity for the cpumask is determined by the PID of a task: - PID of the init task (PID 1) We typically don't set CPU affinity for init task and thus we can iterate across all possible CPUs. However, in scenarios where you've set CPU affinity for the init task, you should set the cpumask of your current task to full-F. Then proceed to iterate through all possible CPUs using the current task. - PID of a task with defined CPU affinity The aim here is to iterate through a specific cpumask. This scenario aligns with tasks residing within a cpuset cgroup. - Invalid PID (e.g., PID -1) No cpumask is available in this case. The result as follows, #62/1 cpumask_iter/init_pid:OK #62/2 cpumask_iter/invalid_pid:OK #62/3 cpumask_iter/self_pid_one_cpu:OK #62/4 cpumask_iter/self_pid_multi_cpus:OK #62 cpumask_iter:OK Summary: 1/4 PASSED, 0 SKIPPED, 0 FAILED Signed-off-by: Yafang Shao <laoar.shao@gmail.com> --- .../selftests/bpf/prog_tests/cpumask_iter.c | 134 ++++++++++++++++++ .../selftests/bpf/progs/cpumask_common.h | 3 + .../selftests/bpf/progs/test_cpumask_iter.c | 62 ++++++++ 3 files changed, 199 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/cpumask_iter.c create mode 100644 tools/testing/selftests/bpf/progs/test_cpumask_iter.c