diff options
Diffstat (limited to 'tools/testing/selftests/sched_ext')
34 files changed, 2994 insertions, 98 deletions
diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index 5fe45f9c5f8f..4e06d0baaeec 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -93,6 +93,8 @@ BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) \ $(CLANG_SYS_INCLUDES) \ -Wall -Wno-compare-distinct-pointer-types \ -Wno-incompatible-function-pointer-types \ + -Wno-microsoft-anon-tag \ + -fms-extensions \ -O2 -mcpu=v3 # sort removes libbpf duplicates when not cross-building @@ -161,10 +163,13 @@ all_test_bpfprogs := $(foreach prog,$(wildcard *.bpf.c),$(INCLUDE_DIR)/$(patsubs auto-test-targets := \ create_dsq \ + dequeue \ + dequeue_iter \ enq_last_no_enq_fails \ ddsp_bogus_dsq_fail \ ddsp_vtimelocal_fail \ dsp_local_on \ + enable_cmask \ enq_select_cpu \ exit \ hotplug \ @@ -172,6 +177,8 @@ auto-test-targets := \ maximal \ maybe_null \ minimal \ + non_scx_kfunc_deny \ + nohz_tick \ numa \ allowed_cpus \ peek_dsq \ @@ -183,7 +190,10 @@ auto-test-targets := \ select_cpu_dispatch_bad_dsq \ select_cpu_dispatch_dbl_dsp \ select_cpu_vtime \ + rt_stall \ test_example \ + total_bw \ + cyclic_kick_wait \ testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets))) diff --git a/tools/testing/selftests/sched_ext/allowed_cpus.bpf.c b/tools/testing/selftests/sched_ext/allowed_cpus.bpf.c index 35923e74a2ec..9dd72d0da29b 100644 --- a/tools/testing/selftests/sched_ext/allowed_cpus.bpf.c +++ b/tools/testing/selftests/sched_ext/allowed_cpus.bpf.c @@ -15,15 +15,48 @@ UEI_DEFINE(uei); private(PREF_CPUS) struct bpf_cpumask __kptr * allowed_cpumask; static void -validate_idle_cpu(const struct task_struct *p, const struct cpumask *allowed, s32 cpu) +validate_local_idle_state(void) { - if (scx_bpf_test_and_clear_cpu_idle(cpu)) - scx_bpf_error("CPU %d should be marked as busy", cpu); + const struct cpumask *idle; + struct task_struct *curr; + s32 cpu = bpf_get_smp_processor_id(); + bool cpu_is_idle, curr_is_idle; - if (bpf_cpumask_subset(allowed, p->cpus_ptr) && - !bpf_cpumask_test_cpu(cpu, allowed)) + bpf_rcu_read_lock(); + curr = scx_bpf_cpu_curr(cpu); + curr_is_idle = curr && (curr->flags & PF_IDLE); + bpf_rcu_read_unlock(); + + idle = scx_bpf_get_idle_cpumask(); + cpu_is_idle = bpf_cpumask_test_cpu(cpu, idle); + scx_bpf_put_idle_cpumask(idle); + + /* + * Unlike a remote selected CPU, the local CPU cannot go through an + * idle re-pick while this callback is running. If it is running a + * non-idle scheduling context, it must not be advertised as idle. + */ + if (!curr_is_idle && cpu_is_idle) + scx_bpf_error("running CPU %d should be marked as busy", cpu); +} + +static void +validate_selected_cpu(const struct task_struct *p, s32 cpu) +{ + const struct cpumask *allowed = cast_mask(allowed_cpumask); + + if (!allowed) { + scx_bpf_error("allowed domain not initialized"); + return; + } + + if (!bpf_cpumask_test_cpu(cpu, allowed)) scx_bpf_error("CPU %d not in the allowed domain for %d (%s)", cpu, p->pid, p->comm); + + if (!bpf_cpumask_test_cpu(cpu, p->cpus_ptr)) + scx_bpf_error("CPU %d not in the affinity mask for %d (%s)", + cpu, p->pid, p->comm); } s32 BPF_STRUCT_OPS(allowed_cpus_select_cpu, @@ -32,6 +65,7 @@ s32 BPF_STRUCT_OPS(allowed_cpus_select_cpu, const struct cpumask *allowed; s32 cpu; + validate_local_idle_state(); allowed = cast_mask(allowed_cpumask); if (!allowed) { scx_bpf_error("allowed domain not initialized"); @@ -43,7 +77,7 @@ s32 BPF_STRUCT_OPS(allowed_cpus_select_cpu, */ cpu = scx_bpf_select_cpu_and(p, prev_cpu, wake_flags, allowed, 0); if (cpu >= 0) { - validate_idle_cpu(p, allowed, cpu); + validate_selected_cpu(p, cpu); scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0); return cpu; @@ -59,6 +93,7 @@ void BPF_STRUCT_OPS(allowed_cpus_enqueue, struct task_struct *p, u64 enq_flags) scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + validate_local_idle_state(); allowed = cast_mask(allowed_cpumask); if (!allowed) { scx_bpf_error("allowed domain not initialized"); @@ -71,7 +106,7 @@ void BPF_STRUCT_OPS(allowed_cpus_enqueue, struct task_struct *p, u64 enq_flags) */ cpu = scx_bpf_select_cpu_and(p, prev_cpu, 0, allowed, 0); if (cpu >= 0) { - validate_idle_cpu(p, allowed, cpu); + validate_selected_cpu(p, cpu); scx_bpf_kick_cpu(cpu, SCX_KICK_IDLE); } } diff --git a/tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c b/tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c new file mode 100644 index 000000000000..cb34d3335917 --- /dev/null +++ b/tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Stress concurrent SCX_KICK_WAIT calls to reproduce wait-cycle deadlock. + * + * Three CPUs are designated from userspace. Every enqueue from one of the + * three CPUs kicks the next CPU in the ring with SCX_KICK_WAIT, creating a + * persistent A -> B -> C -> A wait cycle pressure. + */ +#include <scx/common.bpf.h> + +char _license[] SEC("license") = "GPL"; + +const volatile s32 test_cpu_a; +const volatile s32 test_cpu_b; +const volatile s32 test_cpu_c; + +u64 nr_enqueues; +u64 nr_wait_kicks; + +UEI_DEFINE(uei); + +static s32 target_cpu(s32 cpu) +{ + if (cpu == test_cpu_a) + return test_cpu_b; + if (cpu == test_cpu_b) + return test_cpu_c; + if (cpu == test_cpu_c) + return test_cpu_a; + return -1; +} + +void BPF_STRUCT_OPS(cyclic_kick_wait_enqueue, struct task_struct *p, + u64 enq_flags) +{ + s32 this_cpu = bpf_get_smp_processor_id(); + s32 tgt; + + __sync_fetch_and_add(&nr_enqueues, 1); + + if (p->flags & PF_KTHREAD) { + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_INF, + enq_flags | SCX_ENQ_PREEMPT); + return; + } + + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + + tgt = target_cpu(this_cpu); + if (tgt < 0 || tgt == this_cpu) + return; + + __sync_fetch_and_add(&nr_wait_kicks, 1); + scx_bpf_kick_cpu(tgt, SCX_KICK_WAIT); +} + +void BPF_STRUCT_OPS(cyclic_kick_wait_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops cyclic_kick_wait_ops = { + .enqueue = cyclic_kick_wait_enqueue, + .exit = cyclic_kick_wait_exit, + .name = "cyclic_kick_wait", + .timeout_ms = 1000U, +}; diff --git a/tools/testing/selftests/sched_ext/cyclic_kick_wait.c b/tools/testing/selftests/sched_ext/cyclic_kick_wait.c new file mode 100644 index 000000000000..c2e5aa9de715 --- /dev/null +++ b/tools/testing/selftests/sched_ext/cyclic_kick_wait.c @@ -0,0 +1,194 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Test SCX_KICK_WAIT forward progress under cyclic wait pressure. + * + * SCX_KICK_WAIT busy-waits until the target CPU enters the scheduling path. + * If multiple CPUs form a wait cycle (A waits for B, B waits for C, C waits + * for A), all CPUs deadlock unless the implementation breaks the cycle. + * + * This test creates that scenario: three CPUs are arranged in a ring. The BPF + * scheduler's ops.enqueue() kicks the next CPU in the ring with SCX_KICK_WAIT + * on every enqueue. Userspace pins 4 worker threads per CPU that loop calling + * sched_yield(), generating a steady stream of enqueues and thus sustained + * A->B->C->A kick_wait cycle pressure. The test passes if the system remains + * responsive for 5 seconds without the scheduler being killed by the watchdog. + */ +#define _GNU_SOURCE + +#include <bpf/bpf.h> +#include <errno.h> +#include <pthread.h> +#include <sched.h> +#include <scx/common.h> +#include <stdint.h> +#include <string.h> +#include <time.h> +#include <unistd.h> + +#include "scx_test.h" +#include "cyclic_kick_wait.bpf.skel.h" + +#define WORKERS_PER_CPU 4 +#define NR_TEST_CPUS 3 +#define NR_WORKERS (NR_TEST_CPUS * WORKERS_PER_CPU) + +struct worker_ctx { + pthread_t tid; + int cpu; + volatile bool stop; + volatile __u64 iters; + bool started; +}; + +static void *worker_fn(void *arg) +{ + struct worker_ctx *worker = arg; + cpu_set_t mask; + + CPU_ZERO(&mask); + CPU_SET(worker->cpu, &mask); + + if (sched_setaffinity(0, sizeof(mask), &mask)) + return (void *)(uintptr_t)errno; + + while (!worker->stop) { + sched_yield(); + worker->iters++; + } + + return NULL; +} + +static int join_worker(struct worker_ctx *worker) +{ + void *ret; + struct timespec ts; + int err; + + if (!worker->started) + return 0; + + if (clock_gettime(CLOCK_REALTIME, &ts)) + return -errno; + + ts.tv_sec += 2; + err = pthread_timedjoin_np(worker->tid, &ret, &ts); + if (err == ETIMEDOUT) + pthread_detach(worker->tid); + if (err) + return -err; + + if ((uintptr_t)ret) + return -(int)(uintptr_t)ret; + + return 0; +} + +static enum scx_test_status setup(void **ctx) +{ + struct cyclic_kick_wait *skel; + + skel = cyclic_kick_wait__open(); + SCX_FAIL_IF(!skel, "Failed to open skel"); + SCX_ENUM_INIT(skel); + + *ctx = skel; + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct cyclic_kick_wait *skel = ctx; + struct worker_ctx workers[NR_WORKERS] = {}; + struct bpf_link *link = NULL; + enum scx_test_status status = SCX_TEST_PASS; + int test_cpus[NR_TEST_CPUS]; + int nr_cpus = 0; + cpu_set_t mask; + int ret, i; + + if (sched_getaffinity(0, sizeof(mask), &mask)) { + SCX_ERR("Failed to get affinity (%d)", errno); + return SCX_TEST_FAIL; + } + + for (i = 0; i < CPU_SETSIZE; i++) { + if (CPU_ISSET(i, &mask)) + test_cpus[nr_cpus++] = i; + if (nr_cpus == NR_TEST_CPUS) + break; + } + + if (nr_cpus < NR_TEST_CPUS) + return SCX_TEST_SKIP; + + skel->rodata->test_cpu_a = test_cpus[0]; + skel->rodata->test_cpu_b = test_cpus[1]; + skel->rodata->test_cpu_c = test_cpus[2]; + + if (cyclic_kick_wait__load(skel)) { + SCX_ERR("Failed to load skel"); + return SCX_TEST_FAIL; + } + + link = bpf_map__attach_struct_ops(skel->maps.cyclic_kick_wait_ops); + if (!link) { + SCX_ERR("Failed to attach scheduler"); + return SCX_TEST_FAIL; + } + + for (i = 0; i < NR_WORKERS; i++) + workers[i].cpu = test_cpus[i / WORKERS_PER_CPU]; + + for (i = 0; i < NR_WORKERS; i++) { + ret = pthread_create(&workers[i].tid, NULL, worker_fn, &workers[i]); + if (ret) { + SCX_ERR("Failed to create worker thread %d (%d)", i, ret); + status = SCX_TEST_FAIL; + goto out; + } + workers[i].started = true; + } + + sleep(5); + + if (skel->data->uei.kind != EXIT_KIND(SCX_EXIT_NONE)) { + SCX_ERR("Scheduler exited unexpectedly (kind=%llu code=%lld)", + (unsigned long long)skel->data->uei.kind, + (long long)skel->data->uei.exit_code); + status = SCX_TEST_FAIL; + } + +out: + for (i = 0; i < NR_WORKERS; i++) + workers[i].stop = true; + + for (i = 0; i < NR_WORKERS; i++) { + ret = join_worker(&workers[i]); + if (ret && status == SCX_TEST_PASS) { + SCX_ERR("Failed to join worker thread %d (%d)", i, ret); + status = SCX_TEST_FAIL; + } + } + + if (link) + bpf_link__destroy(link); + + return status; +} + +static void cleanup(void *ctx) +{ + struct cyclic_kick_wait *skel = ctx; + + cyclic_kick_wait__destroy(skel); +} + +struct scx_test cyclic_kick_wait = { + .name = "cyclic_kick_wait", + .description = "Verify SCX_KICK_WAIT forward progress under a 3-CPU wait cycle", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&cyclic_kick_wait) 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 6f4c3f5a1c5d..7ef9de7b27eb 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 @@ -14,18 +14,16 @@ s32 BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) { s32 cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0); + if (cpu < 0) + cpu = prev_cpu; - if (cpu >= 0) { - /* - * If we dispatch to a bogus DSQ that will fall back to the - * builtin global DSQ, we fail gracefully. - */ - scx_bpf_dsq_insert_vtime(p, 0xcafef00d, SCX_SLICE_DFL, - p->scx.dsq_vtime, 0); - return cpu; - } - - return prev_cpu; + /* + * If we dispatch to a bogus DSQ that will fall back to the + * builtin global DSQ, we fail gracefully. + */ + scx_bpf_dsq_insert_vtime(p, 0xcafef00d, SCX_SLICE_DFL, + p->scx.dsq_vtime, 0); + return cpu; } void BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_exit, struct scx_exit_info *ei) 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 e4a55027778f..82dca4cdc0a6 100644 --- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c @@ -14,15 +14,14 @@ s32 BPF_STRUCT_OPS(ddsp_vtimelocal_fail_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) { s32 cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0); + if (cpu < 0) + cpu = prev_cpu; - if (cpu >= 0) { - /* Shouldn't be allowed to vtime dispatch to a builtin DSQ. */ - scx_bpf_dsq_insert_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, - p->scx.dsq_vtime, 0); - return cpu; - } + /* Shouldn't be allowed to vtime dispatch to a builtin DSQ. */ + scx_bpf_dsq_insert_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, + p->scx.dsq_vtime, 0); - return prev_cpu; + return cpu; } void BPF_STRUCT_OPS(ddsp_vtimelocal_fail_exit, struct scx_exit_info *ei) diff --git a/tools/testing/selftests/sched_ext/dequeue.bpf.c b/tools/testing/selftests/sched_ext/dequeue.bpf.c new file mode 100644 index 000000000000..624e2ccb0688 --- /dev/null +++ b/tools/testing/selftests/sched_ext/dequeue.bpf.c @@ -0,0 +1,389 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A scheduler that validates ops.dequeue() is called correctly: + * - Tasks dispatched to terminal DSQs (local, global) bypass the BPF + * scheduler entirely: no ops.dequeue() should be called + * - Tasks dispatched to user DSQs from ops.enqueue() enter BPF custody: + * ops.dequeue() must be called when they leave custody + * - Every ops.enqueue() dispatch to non-terminal DSQs is followed by + * exactly one ops.dequeue() (validate 1:1 pairing and state machine) + * + * Copyright (c) 2026 NVIDIA Corporation. + */ + +#include <scx/common.bpf.h> + +#define SHARED_DSQ 0 + +/* + * BPF internal queue. + * + * Tasks are stored here and consumed from ops.dispatch(), validating that + * tasks on BPF internal structures still get ops.dequeue() when they + * leave. + */ +struct { + __uint(type, BPF_MAP_TYPE_QUEUE); + __uint(max_entries, 32768); + __type(value, s32); +} global_queue SEC(".maps"); + +char _license[] SEC("license") = "GPL"; + +UEI_DEFINE(uei); + +/* + * Counters to track the lifecycle of tasks: + * - enqueue_cnt: Number of times ops.enqueue() was called + * - dequeue_cnt: Number of times ops.dequeue() was called (any type) + * - dispatch_dequeue_cnt: Number of regular dispatch dequeues (no flag) + * - change_dequeue_cnt: Number of property change dequeues + * - bpf_queue_full: Number of times the BPF internal queue was full + */ +u64 enqueue_cnt, dequeue_cnt, dispatch_dequeue_cnt, change_dequeue_cnt, bpf_queue_full; + +/* + * Test scenarios: + * 0) Dispatch to local DSQ from ops.select_cpu() (terminal DSQ, bypasses BPF + * scheduler, no dequeue callbacks) + * 1) Dispatch to global DSQ from ops.select_cpu() (terminal DSQ, bypasses BPF + * scheduler, no dequeue callbacks) + * 2) Dispatch to shared user DSQ from ops.select_cpu() (enters BPF scheduler, + * dequeue callbacks expected) + * 3) Dispatch to local DSQ from ops.enqueue() (terminal DSQ, bypasses BPF + * scheduler, no dequeue callbacks) + * 4) Dispatch to global DSQ from ops.enqueue() (terminal DSQ, bypasses BPF + * scheduler, no dequeue callbacks) + * 5) Dispatch to shared user DSQ from ops.enqueue() (enters BPF scheduler, + * dequeue callbacks expected) + * 6) BPF internal queue from ops.enqueue(): store task PIDs in ops.enqueue(), + * consume in ops.dispatch() and dispatch to local DSQ (validates dequeue + * for tasks stored in internal BPF data structures) + */ +u32 test_scenario; + +/* + * Per-task state to track lifecycle and validate workflow semantics. + * State transitions: + * NONE -> ENQUEUED (on enqueue) + * NONE -> DISPATCHED (on direct dispatch to terminal DSQ) + * ENQUEUED -> DISPATCHED (on dispatch dequeue) + * DISPATCHED -> NONE (on property change dequeue or re-enqueue) + * ENQUEUED -> NONE (on property change dequeue before dispatch) + */ +enum task_state { + TASK_NONE = 0, + TASK_ENQUEUED, + TASK_DISPATCHED, +}; + +struct task_ctx { + enum task_state state; /* Current state in the workflow */ + u64 enqueue_seq; /* Sequence number for debugging */ +}; + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct task_ctx); +} task_ctx_stor SEC(".maps"); + +static struct task_ctx *try_lookup_task_ctx(struct task_struct *p) +{ + return bpf_task_storage_get(&task_ctx_stor, p, 0, 0); +} + +s32 BPF_STRUCT_OPS(dequeue_select_cpu, struct task_struct *p, + s32 prev_cpu, u64 wake_flags) +{ + struct task_ctx *tctx; + + tctx = try_lookup_task_ctx(p); + if (!tctx) + return prev_cpu; + + switch (test_scenario) { + case 0: + /* + * Direct dispatch to the local DSQ. + * + * Task bypasses BPF scheduler entirely: no enqueue + * tracking, no ops.dequeue() callbacks. + */ + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0); + tctx->state = TASK_DISPATCHED; + break; + case 1: + /* + * Direct dispatch to the global DSQ. + * + * Task bypasses BPF scheduler entirely: no enqueue + * tracking, no ops.dequeue() callbacks. + */ + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + tctx->state = TASK_DISPATCHED; + break; + case 2: + /* + * Dispatch to a shared user DSQ. + * + * Task enters BPF scheduler management: track + * enqueue/dequeue lifecycle and validate state + * transitions. + */ + if (tctx->state == TASK_ENQUEUED) + scx_bpf_error("%d (%s): enqueue while in ENQUEUED state seq=%llu", + p->pid, p->comm, tctx->enqueue_seq); + + scx_bpf_dsq_insert(p, SHARED_DSQ, SCX_SLICE_DFL, 0); + + __sync_fetch_and_add(&enqueue_cnt, 1); + + tctx->state = TASK_ENQUEUED; + tctx->enqueue_seq++; + break; + } + + return prev_cpu; +} + +void BPF_STRUCT_OPS(dequeue_enqueue, struct task_struct *p, u64 enq_flags) +{ + struct task_ctx *tctx; + s32 pid = p->pid; + + tctx = try_lookup_task_ctx(p); + if (!tctx) + return; + + switch (test_scenario) { + case 3: + /* + * Direct dispatch to the local DSQ. + * + * Task bypasses BPF scheduler entirely: no enqueue + * tracking, no ops.dequeue() callbacks. + */ + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, enq_flags); + tctx->state = TASK_DISPATCHED; + break; + case 4: + /* + * Direct dispatch to the global DSQ. + * + * Task bypasses BPF scheduler entirely: no enqueue + * tracking, no ops.dequeue() callbacks. + */ + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + tctx->state = TASK_DISPATCHED; + break; + case 5: + /* + * Dispatch to shared user DSQ. + * + * Task enters BPF scheduler management: track + * enqueue/dequeue lifecycle and validate state + * transitions. + */ + if (tctx->state == TASK_ENQUEUED) + scx_bpf_error("%d (%s): enqueue while in ENQUEUED state seq=%llu", + p->pid, p->comm, tctx->enqueue_seq); + + scx_bpf_dsq_insert(p, SHARED_DSQ, SCX_SLICE_DFL, enq_flags); + + __sync_fetch_and_add(&enqueue_cnt, 1); + + tctx->state = TASK_ENQUEUED; + tctx->enqueue_seq++; + break; + case 6: + /* + * Store task in BPF internal queue. + * + * Task enters BPF scheduler management: track + * enqueue/dequeue lifecycle and validate state + * transitions. + */ + if (tctx->state == TASK_ENQUEUED) + scx_bpf_error("%d (%s): enqueue while in ENQUEUED state seq=%llu", + p->pid, p->comm, tctx->enqueue_seq); + + if (bpf_map_push_elem(&global_queue, &pid, 0)) { + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + __sync_fetch_and_add(&bpf_queue_full, 1); + + tctx->state = TASK_DISPATCHED; + } else { + __sync_fetch_and_add(&enqueue_cnt, 1); + + tctx->state = TASK_ENQUEUED; + tctx->enqueue_seq++; + } + break; + default: + /* For all other scenarios, dispatch to the global DSQ */ + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + tctx->state = TASK_DISPATCHED; + break; + } + + scx_bpf_kick_cpu(scx_bpf_task_cpu(p), SCX_KICK_IDLE); +} + +void BPF_STRUCT_OPS(dequeue_dequeue, struct task_struct *p, u64 deq_flags) +{ + struct task_ctx *tctx; + + __sync_fetch_and_add(&dequeue_cnt, 1); + + tctx = try_lookup_task_ctx(p); + if (!tctx) + return; + + /* + * For scenarios 0, 1, 3, and 4 (terminal DSQs: local and global), + * ops.dequeue() should never be called because tasks bypass the + * BPF scheduler entirely. If we get here, it's a kernel bug. + */ + if (test_scenario == 0 || test_scenario == 3) { + scx_bpf_error("%d (%s): dequeue called for local DSQ scenario", + p->pid, p->comm); + return; + } + + if (test_scenario == 1 || test_scenario == 4) { + scx_bpf_error("%d (%s): dequeue called for global DSQ scenario", + p->pid, p->comm); + return; + } + + if (deq_flags & SCX_DEQ_SCHED_CHANGE) { + /* + * Property change interrupting the workflow. Valid from + * both ENQUEUED and DISPATCHED states. Transitions task + * back to NONE state. + */ + __sync_fetch_and_add(&change_dequeue_cnt, 1); + + /* Validate state transition */ + if (tctx->state != TASK_ENQUEUED && tctx->state != TASK_DISPATCHED) + scx_bpf_error("%d (%s): invalid property change dequeue state=%d seq=%llu", + p->pid, p->comm, tctx->state, tctx->enqueue_seq); + + /* + * Transition back to NONE: task outside scheduler control. + * + * Scenario 6: dispatch() checks tctx->state after popping a + * PID, if the task is in state NONE, it was dequeued by + * property change and must not be dispatched (this + * prevents "target CPU not allowed"). + */ + tctx->state = TASK_NONE; + } else { + /* + * Regular dispatch dequeue: kernel is moving the task from + * BPF custody to a terminal DSQ. Normally we come from + * ENQUEUED state. We can also see TASK_NONE if the task + * was dequeued by property change (SCX_DEQ_SCHED_CHANGE) + * while it was already on a DSQ (dispatched but not yet + * consumed); in that case we just leave state as NONE. + */ + __sync_fetch_and_add(&dispatch_dequeue_cnt, 1); + + /* + * Must be ENQUEUED (normal path) or NONE (already dequeued + * by property change while on a DSQ). + */ + if (tctx->state != TASK_ENQUEUED && tctx->state != TASK_NONE) + scx_bpf_error("%d (%s): dispatch dequeue from state %d seq=%llu", + p->pid, p->comm, tctx->state, tctx->enqueue_seq); + + if (tctx->state == TASK_ENQUEUED) + tctx->state = TASK_DISPATCHED; + + /* NONE: leave as-is, task was already property-change dequeued */ + } +} + +void BPF_STRUCT_OPS(dequeue_dispatch, s32 cpu, struct task_struct *prev) +{ + if (test_scenario == 6) { + struct task_ctx *tctx; + struct task_struct *p; + s32 pid; + + if (bpf_map_pop_elem(&global_queue, &pid)) + return; + + p = bpf_task_from_pid(pid); + if (!p) + return; + + /* + * If the task was dequeued by property change + * (ops.dequeue() set tctx->state = TASK_NONE), skip + * dispatch. + */ + tctx = try_lookup_task_ctx(p); + if (!tctx || tctx->state == TASK_NONE) { + bpf_task_release(p); + return; + } + + /* + * Dispatch to this CPU's local DSQ if allowed, otherwise + * fallback to the global DSQ. + */ + if (bpf_cpumask_test_cpu(cpu, p->cpus_ptr)) + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | cpu, SCX_SLICE_DFL, 0); + else + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + + bpf_task_release(p); + } else { + scx_bpf_dsq_move_to_local(SHARED_DSQ, 0); + } +} + +s32 BPF_STRUCT_OPS(dequeue_init_task, struct task_struct *p, + struct scx_init_task_args *args) +{ + struct task_ctx *tctx; + + tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!tctx) + return -ENOMEM; + + return 0; +} + +s32 BPF_STRUCT_OPS_SLEEPABLE(dequeue_init) +{ + s32 ret; + + ret = scx_bpf_create_dsq(SHARED_DSQ, -1); + if (ret) + return ret; + + return 0; +} + +void BPF_STRUCT_OPS(dequeue_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops dequeue_ops = { + .select_cpu = (void *)dequeue_select_cpu, + .enqueue = (void *)dequeue_enqueue, + .dequeue = (void *)dequeue_dequeue, + .dispatch = (void *)dequeue_dispatch, + .init_task = (void *)dequeue_init_task, + .init = (void *)dequeue_init, + .exit = (void *)dequeue_exit, + .flags = SCX_OPS_ENQ_LAST, + .name = "dequeue_test", +}; diff --git a/tools/testing/selftests/sched_ext/dequeue.c b/tools/testing/selftests/sched_ext/dequeue.c new file mode 100644 index 000000000000..383d06e972a4 --- /dev/null +++ b/tools/testing/selftests/sched_ext/dequeue.c @@ -0,0 +1,275 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2025 NVIDIA Corporation. + */ +#define _GNU_SOURCE +#include <stdio.h> +#include <unistd.h> +#include <signal.h> +#include <time.h> +#include <bpf/bpf.h> +#include <scx/common.h> +#include <sys/wait.h> +#include <sched.h> +#include <pthread.h> +#include "scx_test.h" +#include "dequeue.bpf.skel.h" + +#define NUM_WORKERS 8 +#define AFFINITY_HAMMER_MS 500 + +/* + * Worker function that creates enqueue/dequeue events via CPU work and + * sleep. + */ +static void worker_fn(int id) +{ + int i; + volatile int sum = 0; + + for (i = 0; i < 1000; i++) { + volatile int j; + + /* Do some work to trigger scheduling events */ + for (j = 0; j < 10000; j++) + sum += j; + asm volatile("" : : "r"(sum)); + + /* Sleep to trigger dequeue */ + usleep(1000 + (id * 100)); + } + + exit(0); +} + +/* + * This thread changes workers' affinity from outside so that some changes + * hit tasks while they are still in the scheduler's queue and trigger + * property-change dequeues. + */ +static void *affinity_hammer_fn(void *arg) +{ + pid_t *pids = arg; + cpu_set_t cpuset; + int i = 0, n = NUM_WORKERS; + struct timespec start, now; + + clock_gettime(CLOCK_MONOTONIC, &start); + while (1) { + int w = i % n; + int cpu = (i / n) % 4; + + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); + sched_setaffinity(pids[w], sizeof(cpuset), &cpuset); + i++; + + /* Check elapsed time every 256 iterations to limit gettime cost */ + if ((i & 255) == 0) { + long long elapsed_ms; + + clock_gettime(CLOCK_MONOTONIC, &now); + elapsed_ms = (now.tv_sec - start.tv_sec) * 1000LL + + (now.tv_nsec - start.tv_nsec) / 1000000; + if (elapsed_ms >= AFFINITY_HAMMER_MS) + break; + } + } + return NULL; +} + +static enum scx_test_status run_scenario(struct dequeue *skel, u32 scenario, + const char *scenario_name) +{ + struct bpf_link *link; + pid_t pids[NUM_WORKERS]; + pthread_t hammer; + + int i, status; + u64 enq_start, deq_start, + dispatch_deq_start, change_deq_start, bpf_queue_full_start; + u64 enq_delta, deq_delta, + dispatch_deq_delta, change_deq_delta, bpf_queue_full_delta; + + /* Set the test scenario */ + skel->bss->test_scenario = scenario; + + /* Record starting counts */ + enq_start = skel->bss->enqueue_cnt; + deq_start = skel->bss->dequeue_cnt; + dispatch_deq_start = skel->bss->dispatch_dequeue_cnt; + change_deq_start = skel->bss->change_dequeue_cnt; + bpf_queue_full_start = skel->bss->bpf_queue_full; + + link = bpf_map__attach_struct_ops(skel->maps.dequeue_ops); + SCX_FAIL_IF(!link, "Failed to attach struct_ops for scenario %s", scenario_name); + + /* Fork worker processes to generate enqueue/dequeue events */ + for (i = 0; i < NUM_WORKERS; i++) { + pids[i] = fork(); + SCX_FAIL_IF(pids[i] < 0, "Failed to fork worker %d", i); + + if (pids[i] == 0) { + worker_fn(i); + /* Should not reach here */ + exit(1); + } + } + + /* + * Run an "affinity hammer" so that some property changes hit tasks + * while they are still in BPF custody (e.g., in user DSQ or BPF + * queue), triggering SCX_DEQ_SCHED_CHANGE dequeues. + */ + SCX_FAIL_IF(pthread_create(&hammer, NULL, affinity_hammer_fn, pids) != 0, + "Failed to create affinity hammer thread"); + pthread_join(hammer, NULL); + + /* Wait for all workers to complete */ + for (i = 0; i < NUM_WORKERS; i++) { + SCX_FAIL_IF(waitpid(pids[i], &status, 0) != pids[i], + "Failed to wait for worker %d", i); + SCX_FAIL_IF(status != 0, "Worker %d exited with status %d", i, status); + } + + bpf_link__destroy(link); + + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG)); + + /* Calculate deltas */ + enq_delta = skel->bss->enqueue_cnt - enq_start; + deq_delta = skel->bss->dequeue_cnt - deq_start; + dispatch_deq_delta = skel->bss->dispatch_dequeue_cnt - dispatch_deq_start; + change_deq_delta = skel->bss->change_dequeue_cnt - change_deq_start; + bpf_queue_full_delta = skel->bss->bpf_queue_full - bpf_queue_full_start; + + printf("%s:\n", scenario_name); + printf(" enqueues: %lu\n", (unsigned long)enq_delta); + printf(" dequeues: %lu (dispatch: %lu, property_change: %lu)\n", + (unsigned long)deq_delta, + (unsigned long)dispatch_deq_delta, + (unsigned long)change_deq_delta); + printf(" BPF queue full: %lu\n", (unsigned long)bpf_queue_full_delta); + + /* + * Validate enqueue/dequeue lifecycle tracking. + * + * For scenarios 0, 1, 3, 4 (local and global DSQs from + * ops.select_cpu() and ops.enqueue()), both enqueues and dequeues + * should be 0 because tasks bypass the BPF scheduler entirely: + * tasks never enter BPF scheduler's custody. + * + * For scenarios 2, 5, 6 (user DSQ or BPF internal queue) we expect + * both enqueues and dequeues. + * + * The BPF code does strict state machine validation with + * scx_bpf_error() to ensure the workflow semantics are correct. + * + * If we reach this point without errors, the semantics are + * validated correctly. + */ + if (scenario == 0 || scenario == 1 || + scenario == 3 || scenario == 4) { + /* Tasks bypass BPF scheduler completely */ + SCX_EQ(enq_delta, 0); + SCX_EQ(deq_delta, 0); + SCX_EQ(dispatch_deq_delta, 0); + SCX_EQ(change_deq_delta, 0); + } else { + /* + * User DSQ from ops.enqueue() or ops.select_cpu(): tasks + * enter BPF scheduler's custody. + * + * Also validate 1:1 enqueue/dequeue pairing. + */ + SCX_GT(enq_delta, 0); + SCX_GT(deq_delta, 0); + SCX_EQ(enq_delta, deq_delta); + } + + return SCX_TEST_PASS; +} + +static enum scx_test_status setup(void **ctx) +{ + struct dequeue *skel; + + skel = dequeue__open(); + SCX_FAIL_IF(!skel, "Failed to open skel"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(dequeue__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct dequeue *skel = ctx; + enum scx_test_status status; + + status = run_scenario(skel, 0, "Scenario 0: Local DSQ from ops.select_cpu()"); + if (status != SCX_TEST_PASS) + return status; + + status = run_scenario(skel, 1, "Scenario 1: Global DSQ from ops.select_cpu()"); + if (status != SCX_TEST_PASS) + return status; + + status = run_scenario(skel, 2, "Scenario 2: User DSQ from ops.select_cpu()"); + if (status != SCX_TEST_PASS) + return status; + + status = run_scenario(skel, 3, "Scenario 3: Local DSQ from ops.enqueue()"); + if (status != SCX_TEST_PASS) + return status; + + status = run_scenario(skel, 4, "Scenario 4: Global DSQ from ops.enqueue()"); + if (status != SCX_TEST_PASS) + return status; + + status = run_scenario(skel, 5, "Scenario 5: User DSQ from ops.enqueue()"); + if (status != SCX_TEST_PASS) + return status; + + status = run_scenario(skel, 6, "Scenario 6: BPF queue from ops.enqueue()"); + if (status != SCX_TEST_PASS) + return status; + + printf("\n=== Summary ===\n"); + printf("Total enqueues: %lu\n", (unsigned long)skel->bss->enqueue_cnt); + printf("Total dequeues: %lu\n", (unsigned long)skel->bss->dequeue_cnt); + printf(" Dispatch dequeues: %lu (no flag, normal workflow)\n", + (unsigned long)skel->bss->dispatch_dequeue_cnt); + printf(" Property change dequeues: %lu (SCX_DEQ_SCHED_CHANGE flag)\n", + (unsigned long)skel->bss->change_dequeue_cnt); + printf(" BPF queue full: %lu\n", + (unsigned long)skel->bss->bpf_queue_full); + printf("\nAll scenarios passed - no state machine violations detected\n"); + printf("-> Validated: Local DSQ dispatch bypasses BPF scheduler\n"); + printf("-> Validated: Global DSQ dispatch bypasses BPF scheduler\n"); + printf("-> Validated: User DSQ dispatch triggers ops.dequeue() callbacks\n"); + printf("-> Validated: Dispatch dequeues have no flags (normal workflow)\n"); + printf("-> Validated: Property change dequeues have SCX_DEQ_SCHED_CHANGE flag\n"); + printf("-> Validated: No duplicate enqueues or invalid state transitions\n"); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct dequeue *skel = ctx; + + dequeue__destroy(skel); +} + +struct scx_test dequeue_test = { + .name = "dequeue", + .description = "Verify ops.dequeue() semantics", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; + +REGISTER_SCX_TEST(&dequeue_test) diff --git a/tools/testing/selftests/sched_ext/dequeue_iter.bpf.c b/tools/testing/selftests/sched_ext/dequeue_iter.bpf.c new file mode 100644 index 000000000000..76c2c71a90b6 --- /dev/null +++ b/tools/testing/selftests/sched_ext/dequeue_iter.bpf.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ops.dequeue() of this scheduler iterates the user DSQ it consumes + * tasks from with bpf_iter_scx_dsq, which takes the DSQ lock. + * On a kernel that still runs ops.dequeue() with that lock held, the + * iteration self-deadlocks the CPU - this test wedges the system on + * unfixed kernels instead of failing cleanly. + * + * Copyright (c) 2026 fangqiurong <fangqiurong@kylinos.cn> + */ + +#include <scx/common.bpf.h> + +char _license[] SEC("license") = "GPL"; + +UEI_DEFINE(uei); + +#define TEST_DSQ_ID 1000 + +u64 dq_count; + +s32 BPF_STRUCT_OPS_SLEEPABLE(dequeue_iter_init) +{ + return scx_bpf_create_dsq(TEST_DSQ_ID, -1); +} + +s32 BPF_STRUCT_OPS(dequeue_iter_select_cpu, struct task_struct *p, + s32 prev_cpu, u64 wake_flags) +{ + return prev_cpu; +} + +void BPF_STRUCT_OPS(dequeue_iter_enqueue, struct task_struct *p, u64 enq_flags) +{ + scx_bpf_dsq_insert(p, TEST_DSQ_ID, SCX_SLICE_DFL, enq_flags); +} + +void BPF_STRUCT_OPS(dequeue_iter_dispatch, s32 cpu, struct task_struct *task) +{ + scx_bpf_dsq_move_to_local(TEST_DSQ_ID, 0); +} + +void BPF_STRUCT_OPS(dequeue_iter_dequeue, struct task_struct *p, u64 deq_flags) +{ + struct bpf_iter_scx_dsq it; + struct task_struct *t; + + if (!bpf_iter_scx_dsq_new(&it, TEST_DSQ_ID, 0)) { + while ((t = bpf_iter_scx_dsq_next(&it))) + ; + } + bpf_iter_scx_dsq_destroy(&it); + + __sync_fetch_and_add(&dq_count, 1); +} + +void BPF_STRUCT_OPS(dequeue_iter_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); + scx_bpf_destroy_dsq(TEST_DSQ_ID); +} + +SEC(".struct_ops.link") +struct sched_ext_ops dequeue_iter_ops = { + .init = (void *)dequeue_iter_init, + .select_cpu = (void *)dequeue_iter_select_cpu, + .enqueue = (void *)dequeue_iter_enqueue, + .dispatch = (void *)dequeue_iter_dispatch, + .dequeue = (void *)dequeue_iter_dequeue, + .exit = (void *)dequeue_iter_exit, + .timeout_ms = 1000U, + .name = "dequeue_iter", +}; diff --git a/tools/testing/selftests/sched_ext/dequeue_iter.c b/tools/testing/selftests/sched_ext/dequeue_iter.c new file mode 100644 index 000000000000..f60711bf3b39 --- /dev/null +++ b/tools/testing/selftests/sched_ext/dequeue_iter.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2026 fangqiurong <fangqiurong@kylinos.cn> + */ +#include <bpf/bpf.h> +#include <scx/common.h> +#include <time.h> +#include <unistd.h> +#include "dequeue_iter.bpf.skel.h" +#include "scx_test.h" + +#define DQ_TARGET 10 +#define DQ_DEADLINE_MS 3000 + +static unsigned long long now_ms(void) +{ + struct timespec ts; + + clock_gettime(CLOCK_MONOTONIC, &ts); + + return ts.tv_sec * 1000ULL + ts.tv_nsec / 1000000; +} + +static enum scx_test_status setup(void **ctx) +{ + struct dequeue_iter *skel; + + skel = dequeue_iter__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(dequeue_iter__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct dequeue_iter *skel = ctx; + struct bpf_link *link; + unsigned long long end; + + link = bpf_map__attach_struct_ops(skel->maps.dequeue_iter_ops); + SCX_FAIL_IF(!link, "Failed to attach scheduler"); + + end = now_ms() + DQ_DEADLINE_MS; + while (skel->bss->dq_count < DQ_TARGET && !UEI_EXITED(skel, uei) && + now_ms() < end) + usleep(100); + + bpf_link__destroy(link); + + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG)); + + if (skel->bss->dq_count < DQ_TARGET) { + SCX_ERR("ops.dequeue() fired only %llu times", + (unsigned long long)skel->bss->dq_count); + return SCX_TEST_FAIL; + } + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct dequeue_iter *skel = ctx; + + dequeue_iter__destroy(skel); +} + +struct scx_test dequeue_iter = { + .name = "dequeue_iter", + .description = "Verify ops.dequeue() can iterate its source user DSQ", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&dequeue_iter) diff --git a/tools/testing/selftests/sched_ext/enable_cmask.bpf.c b/tools/testing/selftests/sched_ext/enable_cmask.bpf.c new file mode 100644 index 000000000000..0068f3c7ab3c --- /dev/null +++ b/tools/testing/selftests/sched_ext/enable_cmask.bpf.c @@ -0,0 +1,217 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A cid-form scheduler checking the cmask cid-form ops.enable() receives: the + * header, every cid bit against p->cpus_ptr, and that set_cmask() follows with + * the same mask before set_weight() and before the task first becomes runnable, + * and never runs before enable(). + * + * Copyright (c) 2026 Tejun Heo <tj@kernel.org> + */ +#include <scx/common.bpf.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_ARENA); + __uint(map_flags, BPF_F_MMAPABLE); + __uint(max_entries, 1 << 16); +} arena SEC(".maps"); + +struct task_ctx { + u64 enable_fp; /* fingerprint of the mask enable() received */ + bool enabled; + bool pending; /* enable() ran, the initial set_cmask() hasn't */ +}; + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct task_ctx); +} task_ctx_stor SEC(".maps"); + +/* details of a cid bit mismatch, filled by check_mask() */ +struct mask_mismatch { + s32 cid; + bool want; + bool got; +}; + +u64 nr_enable, nr_initial_set_cmask, nr_set_cmask, nr_set_weight; + +UEI_DEFINE(uei); + +static struct task_ctx *lookup_task_ctx(struct task_struct *p) +{ + struct task_ctx *tctx; + + tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0); + if (!tctx) + scx_bpf_error("task_ctx lookup failed for %s[%d]", p->comm, p->pid); + return tctx; +} + +/* + * Verify @m's header and every cid bit against @p's cpumask and fingerprint the + * bits into @fp. Return 0 on success, -EINVAL on a bad header, -ENOENT on a cid + * without a cpu and -EIO on a bit mismatch with the details in @mm. + */ +static int check_mask(struct task_struct *p, const struct scx_cmask __arena *m, u64 *fp, + struct mask_mismatch *mm) +{ + u32 nr_cids = scx_bpf_nr_cids(); + u64 h = 0; + s32 cid; + + if (m->base || m->nr_cids != nr_cids || m->alloc_words != CMASK_NR_WORDS(nr_cids)) + return -EINVAL; + + bpf_for(cid, 0, nr_cids) { + bool want, got; + s32 cpu; + + cpu = scx_bpf_cid_to_cpu(cid); + if (cpu < 0) + return -ENOENT; + want = bpf_cpumask_test_cpu(cpu, p->cpus_ptr); + got = cmask_test(cid, m); + if (want != got) { + mm->cid = cid; + mm->want = want; + mm->got = got; + return -EIO; + } + h = h * 31 + got; + } + + *fp = h; + return 0; +} + +s32 BPF_STRUCT_OPS_SLEEPABLE(enable_cmask_init_task, struct task_struct *p, + struct scx_init_task_args *args) +{ + if (!bpf_task_storage_get(&task_ctx_stor, p, 0, BPF_LOCAL_STORAGE_GET_F_CREATE)) + return -ENOMEM; + return 0; +} + +void BPF_STRUCT_OPS(enable_cmask_enable, struct task_struct *p, struct scx_enable_args *args) +{ + struct scx_cmask __arena *m = (struct scx_cmask __arena *)args->cmask_arena_addr; + struct mask_mismatch mm = {}; + struct task_ctx *tctx; + int ret; + + asm volatile("" :: "r"(&arena)); + tctx = lookup_task_ctx(p); + if (!tctx) + return; + + __sync_fetch_and_add(&nr_enable, 1); + if (tctx->enabled || tctx->pending) { + scx_bpf_error("enable: %s[%d] enabled twice", p->comm, p->pid); + return; + } + + ret = check_mask(p, m, &tctx->enable_fp, &mm); + if (ret) { + scx_bpf_error("enable: %s[%d] cmask check failed %d cid=%d want=%d got=%d", + p->comm, p->pid, ret, mm.cid, mm.want, mm.got); + return; + } + tctx->enabled = true; + tctx->pending = true; +} + +void BPF_STRUCT_OPS(enable_cmask_set_cmask, struct task_struct *p, + struct scx_cmask __arena *m) +{ + struct mask_mismatch mm = {}; + struct task_ctx *tctx; + u64 fp; + int ret; + + asm volatile("" :: "r"(&arena)); + tctx = lookup_task_ctx(p); + if (!tctx) + return; + + __sync_fetch_and_add(&nr_set_cmask, 1); + if (!tctx->enabled) { + scx_bpf_error("set_cmask: %s[%d] not enabled", p->comm, p->pid); + return; + } + + ret = check_mask(p, m, &fp, &mm); + if (ret) { + scx_bpf_error("set_cmask: %s[%d] cmask check failed %d cid=%d want=%d got=%d", + p->comm, p->pid, ret, mm.cid, mm.want, mm.got); + return; + } + + if (tctx->pending) { + if (fp != tctx->enable_fp) { + scx_bpf_error("set_cmask: %s[%d] initial mask differs from enable()", + p->comm, p->pid); + return; + } + tctx->pending = false; + __sync_fetch_and_add(&nr_initial_set_cmask, 1); + } +} + +void BPF_STRUCT_OPS(enable_cmask_set_weight, struct task_struct *p, u32 weight) +{ + struct task_ctx *tctx; + + tctx = lookup_task_ctx(p); + if (!tctx) + return; + + __sync_fetch_and_add(&nr_set_weight, 1); + if (tctx->pending) + scx_bpf_error("set_weight: %s[%d] before the initial set_cmask()", p->comm, + p->pid); +} + +void BPF_STRUCT_OPS(enable_cmask_runnable, struct task_struct *p, u64 enq_flags) +{ + struct task_ctx *tctx; + + tctx = lookup_task_ctx(p); + if (!tctx) + return; + + if (tctx->pending) + scx_bpf_error("runnable: %s[%d] before the initial set_cmask()", p->comm, + p->pid); +} + +void BPF_STRUCT_OPS(enable_cmask_disable, struct task_struct *p) +{ + struct task_ctx *tctx; + + tctx = lookup_task_ctx(p); + if (!tctx) + return; + + tctx->enabled = false; + tctx->pending = false; +} + +void BPF_STRUCT_OPS(enable_cmask_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SCX_OPS_CID_DEFINE(enable_cmask_ops, + .init_task = (void *)enable_cmask_init_task, + .enable = (void *)enable_cmask_enable, + .set_cmask = (void *)enable_cmask_set_cmask, + .set_weight = (void *)enable_cmask_set_weight, + .runnable = (void *)enable_cmask_runnable, + .disable = (void *)enable_cmask_disable, + .exit = (void *)enable_cmask_exit, + .flags = SCX_OPS_SWITCH_PARTIAL, + .name = "enable_cmask"); diff --git a/tools/testing/selftests/sched_ext/enable_cmask.c b/tools/testing/selftests/sched_ext/enable_cmask.c new file mode 100644 index 000000000000..556bcad4431d --- /dev/null +++ b/tools/testing/selftests/sched_ext/enable_cmask.c @@ -0,0 +1,138 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2026 Tejun Heo <tj@kernel.org> */ +#define _GNU_SOURCE +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <unistd.h> +#include <sys/wait.h> +#include <bpf/bpf.h> +#include <scx/common.h> +#include "enable_cmask.bpf.skel.h" +#include "scx_test.h" + +#define SCHED_EXT 7 +#define NR_CHILDREN 8 +#define MAX_CPUS 1024 + +static int cpus[MAX_CPUS]; +static int nr_cpus; + +static void spin_ms(int ms) +{ + struct timespec start, now; + + clock_gettime(CLOCK_MONOTONIC, &start); + do { + clock_gettime(CLOCK_MONOTONIC, &now); + } while ((now.tv_sec - start.tv_sec) * 1000 + + (now.tv_nsec - start.tv_nsec) / 1000000 < ms); +} + +static int pin(pid_t pid, int idx) +{ + cpu_set_t set; + + CPU_ZERO(&set); + CPU_SET(cpus[idx % nr_cpus], &set); + return sched_setaffinity(pid, sizeof(set), &set); +} + +/* + * Pin, switch to SCHED_EXT for a class-switch enable, fork a grandchild that + * inherits the policy for a fork-path enable, then change affinity a few times + * while running for set_cmask() on live tasks. + */ +static int child(int idx) +{ + struct sched_param param = {}; + int i, status; + pid_t pid; + + if (pin(0, idx) || sched_setscheduler(0, SCHED_EXT, ¶m)) + return 1; + + pid = fork(); + if (pid < 0) + return 1; + if (!pid) { + spin_ms(20); + return 0; + } + + for (i = 1; i <= 4; i++) { + if (pin(0, idx + i)) + return 1; + spin_ms(5); + } + + return waitpid(pid, &status, 0) == pid && !status ? 0 : 1; +} + +static enum scx_test_status run(void *ctx) +{ + struct enable_cmask *skel; + struct bpf_link *link; + pid_t pids[NR_CHILDREN]; + cpu_set_t set; + int i, status, failed = 0; + + if (!__COMPAT_struct_has_field("scx_enable_args", "cmask_arena_addr")) + return SCX_TEST_SKIP; + + SCX_FAIL_IF(sched_getaffinity(0, sizeof(set), &set), "Failed to read affinity"); + for (i = 0; i < MAX_CPUS && i < CPU_SETSIZE; i++) + if (CPU_ISSET(i, &set)) + cpus[nr_cpus++] = i; + if (nr_cpus < 2) + return SCX_TEST_SKIP; + + skel = enable_cmask__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(enable_cmask__load(skel), "Failed to load skel"); + + link = bpf_map__attach_struct_ops(skel->maps.enable_cmask_ops); + SCX_FAIL_IF(!link, "Failed to attach struct_ops"); + + for (i = 0; i < NR_CHILDREN; i++) { + pids[i] = fork(); + SCX_FAIL_IF(pids[i] < 0, "Failed to fork"); + if (!pids[i]) + exit(child(i)); + } + + /* affinity changes from the outside race with the children's own */ + for (i = 0; i < NR_CHILDREN; i++) + pin(pids[i], i + NR_CHILDREN); + + for (i = 0; i < NR_CHILDREN; i++) { + if (waitpid(pids[i], &status, 0) != pids[i] || status) + failed++; + } + + bpf_link__destroy(link); + + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG)); + SCX_EQ(failed, 0); + SCX_GE(skel->bss->nr_enable, 2 * NR_CHILDREN); + SCX_EQ(skel->bss->nr_initial_set_cmask, skel->bss->nr_enable); + SCX_GT(skel->bss->nr_set_cmask, skel->bss->nr_initial_set_cmask); + SCX_GE(skel->bss->nr_set_weight, skel->bss->nr_enable); + printf("enable=%lu initial_set_cmask=%lu set_cmask=%lu set_weight=%lu\n", + (unsigned long)skel->bss->nr_enable, + (unsigned long)skel->bss->nr_initial_set_cmask, + (unsigned long)skel->bss->nr_set_cmask, + (unsigned long)skel->bss->nr_set_weight); + + enable_cmask__destroy(skel); + return SCX_TEST_PASS; +} + +struct scx_test enable_cmask = { + .name = "enable_cmask", + .description = "Check the cid-form ops.enable() cmask and the set_cmask() after it", + .run = run, +}; +REGISTER_SCX_TEST(&enable_cmask) diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c index 4bc36182d3ff..2e848820a44b 100644 --- a/tools/testing/selftests/sched_ext/exit.bpf.c +++ b/tools/testing/selftests/sched_ext/exit.bpf.c @@ -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_dsq_move_to_local(DSQ_ID); + scx_bpf_dsq_move_to_local(DSQ_ID, 0); } void BPF_STRUCT_OPS(exit_enable, struct task_struct *p) diff --git a/tools/testing/selftests/sched_ext/exit.c b/tools/testing/selftests/sched_ext/exit.c index ee25824b1cbe..01b17092d5c8 100644 --- a/tools/testing/selftests/sched_ext/exit.c +++ b/tools/testing/selftests/sched_ext/exit.c @@ -31,9 +31,10 @@ static enum scx_test_status run(void *ctx) continue; skel = exit__open(); + SCX_FAIL_IF(!skel, "Failed to open"); SCX_ENUM_INIT(skel); skel->rodata->exit_point = tc; - exit__load(skel); + SCX_FAIL_IF(exit__load(skel), "Failed to load skel"); link = bpf_map__attach_struct_ops(skel->maps.exit_ops); if (!link) { SCX_ERR("Failed to attach scheduler"); diff --git a/tools/testing/selftests/sched_ext/exit_test.h b/tools/testing/selftests/sched_ext/exit_test.h index 94f0268b9cb8..2723e0fda801 100644 --- a/tools/testing/selftests/sched_ext/exit_test.h +++ b/tools/testing/selftests/sched_ext/exit_test.h @@ -17,4 +17,4 @@ enum exit_test_case { NUM_EXITS, }; -#endif // # __EXIT_TEST_H__ +#endif // __EXIT_TEST_H__ diff --git a/tools/testing/selftests/sched_ext/init_enable_count.c b/tools/testing/selftests/sched_ext/init_enable_count.c index eddf9e0e26e7..44577e30e764 100644 --- a/tools/testing/selftests/sched_ext/init_enable_count.c +++ b/tools/testing/selftests/sched_ext/init_enable_count.c @@ -4,6 +4,7 @@ * Copyright (c) 2023 David Vernet <dvernet@meta.com> * Copyright (c) 2023 Tejun Heo <tj@kernel.org> */ +#include <signal.h> #include <stdio.h> #include <unistd.h> #include <sched.h> @@ -23,6 +24,9 @@ static enum scx_test_status run_test(bool global) int ret, i, status; struct sched_param param = {}; pid_t pids[num_pre_forks]; + int pipe_fds[2]; + + SCX_FAIL_IF(pipe(pipe_fds) < 0, "Failed to create pipe"); skel = init_enable_count__open(); SCX_FAIL_IF(!skel, "Failed to open"); @@ -38,26 +42,35 @@ static enum scx_test_status run_test(bool global) * ensure (at least in practical terms) that there are more tasks that * transition from SCHED_OTHER -> SCHED_EXT than there are tasks that * take the fork() path either below or in other processes. + * + * All children will block on read() on the pipe until the parent closes + * the write end after attaching the scheduler, which signals all of + * them to exit simultaneously. Auto-reap so we don't have to wait on + * them. */ + signal(SIGCHLD, SIG_IGN); for (i = 0; i < num_pre_forks; i++) { - pids[i] = fork(); - SCX_FAIL_IF(pids[i] < 0, "Failed to fork child"); - if (pids[i] == 0) { - sleep(1); + pid_t pid = fork(); + + SCX_FAIL_IF(pid < 0, "Failed to fork child"); + if (pid == 0) { + char buf; + + close(pipe_fds[1]); + if (read(pipe_fds[0], &buf, 1) < 0) + exit(1); + close(pipe_fds[0]); exit(0); } } + close(pipe_fds[0]); link = bpf_map__attach_struct_ops(skel->maps.init_enable_count_ops); SCX_FAIL_IF(!link, "Failed to attach struct_ops"); - for (i = 0; i < num_pre_forks; i++) { - SCX_FAIL_IF(waitpid(pids[i], &status, 0) != pids[i], - "Failed to wait for pre-forked child\n"); - - SCX_FAIL_IF(status != 0, "Pre-forked child %d exited with status %d\n", i, - status); - } + /* Signal all pre-forked children to exit. */ + close(pipe_fds[1]); + signal(SIGCHLD, SIG_DFL); bpf_link__destroy(link); SCX_GE(skel->bss->init_task_cnt, num_pre_forks); diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c index 01cf4f3da4e0..04a369078aac 100644 --- a/tools/testing/selftests/sched_ext/maximal.bpf.c +++ b/tools/testing/selftests/sched_ext/maximal.bpf.c @@ -30,7 +30,7 @@ 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_dsq_move_to_local(DSQ_ID); + scx_bpf_dsq_move_to_local(DSQ_ID, 0); } void BPF_STRUCT_OPS(maximal_runnable, struct task_struct *p, u64 enq_flags) @@ -67,13 +67,12 @@ void BPF_STRUCT_OPS(maximal_set_cpumask, struct task_struct *p, void BPF_STRUCT_OPS(maximal_update_idle, s32 cpu, bool idle) {} -void BPF_STRUCT_OPS(maximal_cpu_acquire, s32 cpu, - struct scx_cpu_acquire_args *args) -{} - -void BPF_STRUCT_OPS(maximal_cpu_release, s32 cpu, - struct scx_cpu_release_args *args) -{} +SEC("tp_btf/sched_switch") +int BPF_PROG(maximal_sched_switch, bool preempt, struct task_struct *prev, + struct task_struct *next, unsigned int prev_state) +{ + return 0; +} void BPF_STRUCT_OPS(maximal_cpu_online, s32 cpu) {} @@ -150,8 +149,6 @@ struct sched_ext_ops maximal_ops = { .set_weight = (void *) maximal_set_weight, .set_cpumask = (void *) maximal_set_cpumask, .update_idle = (void *) maximal_update_idle, - .cpu_acquire = (void *) maximal_cpu_acquire, - .cpu_release = (void *) maximal_cpu_release, .cpu_online = (void *) maximal_cpu_online, .cpu_offline = (void *) maximal_cpu_offline, .init_task = (void *) maximal_init_task, diff --git a/tools/testing/selftests/sched_ext/maximal.c b/tools/testing/selftests/sched_ext/maximal.c index c6be50a9941d..1dc369224670 100644 --- a/tools/testing/selftests/sched_ext/maximal.c +++ b/tools/testing/selftests/sched_ext/maximal.c @@ -19,6 +19,9 @@ static enum scx_test_status setup(void **ctx) SCX_ENUM_INIT(skel); SCX_FAIL_IF(maximal__load(skel), "Failed to load skel"); + bpf_map__set_autoattach(skel->maps.maximal_ops, false); + SCX_FAIL_IF(maximal__attach(skel), "Failed to attach skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/nohz_tick.bpf.c b/tools/testing/selftests/sched_ext/nohz_tick.bpf.c new file mode 100644 index 000000000000..6998c5dd6bcb --- /dev/null +++ b/tools/testing/selftests/sched_ext/nohz_tick.bpf.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES + * + * Exercise tick dependency transitions between infinite and finite slices. + */ +#include <scx/common.bpf.h> + +char _license[] SEC("license") = "GPL"; + +const volatile s32 test_cpu; +bool finite_phase; +u64 nr_inf_running; +u64 nr_finite_running; +u64 nr_finite_ticks; + +UEI_DEFINE(uei); + +s32 BPF_STRUCT_OPS(nohz_tick_select_cpu, struct task_struct *p, s32 prev_cpu, + u64 wake_flags) +{ + return prev_cpu; +} + +void BPF_STRUCT_OPS(nohz_tick_enqueue, struct task_struct *p, u64 enq_flags) +{ + u64 slice = finite_phase ? 1000000ULL : SCX_SLICE_INF; + + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, slice, enq_flags); + if (enq_flags & SCX_ENQ_LAST) + scx_bpf_kick_cpu(test_cpu, SCX_KICK_IDLE); +} + +void BPF_STRUCT_OPS(nohz_tick_running, struct task_struct *p) +{ + if (bpf_get_smp_processor_id() != test_cpu) + return; + + if (finite_phase) + __sync_fetch_and_add(&nr_finite_running, 1); + else + __sync_fetch_and_add(&nr_inf_running, 1); +} + +void BPF_STRUCT_OPS(nohz_tick_tick, struct task_struct *p) +{ + if (bpf_get_smp_processor_id() == test_cpu && finite_phase) + __sync_fetch_and_add(&nr_finite_ticks, 1); +} + +void BPF_STRUCT_OPS(nohz_tick_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops nohz_tick_ops = { + .select_cpu = (void *)nohz_tick_select_cpu, + .enqueue = (void *)nohz_tick_enqueue, + .running = (void *)nohz_tick_running, + .tick = (void *)nohz_tick_tick, + .exit = (void *)nohz_tick_exit, + .name = "nohz_tick", + .timeout_ms = 1000U, +}; diff --git a/tools/testing/selftests/sched_ext/nohz_tick.c b/tools/testing/selftests/sched_ext/nohz_tick.c new file mode 100644 index 000000000000..028f54391c2c --- /dev/null +++ b/tools/testing/selftests/sched_ext/nohz_tick.c @@ -0,0 +1,347 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES + * + * Validate that a finite-slice EXT task restarts the scheduler tick when it + * follows an infinite-slice EXT task and an idle interval on a NOHZ_FULL CPU. + */ +#define _GNU_SOURCE + +#include <bpf/bpf.h> +#include <errno.h> +#include <sched.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/prctl.h> +#include <sys/wait.h> +#include <unistd.h> + +#include <scx/common.h> + +#include "nohz_tick.bpf.skel.h" +#include "scx_test.h" + +#ifndef SCHED_EXT +#define SCHED_EXT 7 +#endif + +#define MIN_FINITE_TICKS 3 +#define PHASE_TIMEOUT_MS 1000 + +struct nohz_tick_ctx { + struct nohz_tick *skel; + cpu_set_t original_mask; + int test_cpu; +}; + +static int first_allowed_cpu(const cpu_set_t *mask, int first, int last) +{ + int cpu; + + for (cpu = first; cpu <= last && cpu < CPU_SETSIZE; cpu++) + if (CPU_ISSET(cpu, mask)) + return cpu; + + return -1; +} + +static int find_nohz_full_cpu(const cpu_set_t *allowed) +{ + char buf[4096], *cur, *end; + FILE *file; + + file = fopen("/sys/devices/system/cpu/nohz_full", "r"); + if (!file) + return -1; + if (!fgets(buf, sizeof(buf), file)) { + fclose(file); + return -1; + } + fclose(file); + + cur = buf; + while (*cur) { + long first, last; + int cpu; + + while (*cur == ' ' || *cur == '\t' || *cur == ',') + cur++; + if (*cur < '0' || *cur > '9') + break; + + errno = 0; + first = strtol(cur, &end, 10); + if (errno || end == cur || first < 0 || first >= CPU_SETSIZE) + return -1; + cur = end; + last = first; + if (*cur == '-') { + cur++; + errno = 0; + last = strtol(cur, &end, 10); + if (errno || end == cur || last < first) + return -1; + cur = end; + } + + cpu = first_allowed_cpu(allowed, first, last); + if (cpu >= 0) + return cpu; + } + + return -1; +} + +static pid_t start_worker(int cpu) +{ + struct sched_param param = {}; + cpu_set_t mask; + pid_t parent; + pid_t pid; + + parent = getpid(); + pid = fork(); + if (pid != 0) + return pid; + if (prctl(PR_SET_PDEATHSIG, SIGKILL) || getppid() != parent) + _exit(1); + + /* + * Become EXT before touching the target so it stays idle until wakeup. + */ + if (sched_setscheduler(0, SCHED_EXT, ¶m)) + _exit(1); + + CPU_ZERO(&mask); + CPU_SET(cpu, &mask); + if (sched_setaffinity(0, sizeof(mask), &mask)) + _exit(1); + + for (;;) + asm volatile("" ::: "memory"); +} + +static void stop_worker(pid_t pid) +{ + if (pid <= 0) + return; + + kill(pid, SIGKILL); + waitpid(pid, NULL, 0); +} + +static int pause_worker(pid_t pid) +{ + int status; + + if (kill(pid, SIGSTOP)) + return -errno; + if (waitpid(pid, &status, WUNTRACED) != pid) + return -errno; + if (!WIFSTOPPED(status)) + return -ECHILD; + + return 0; +} + +static bool wait_for_counter(const u64 *counter, u64 value, int timeout_ms) +{ + int elapsed; + + for (elapsed = 0; elapsed < timeout_ms; elapsed++) { + if (__atomic_load_n(counter, __ATOMIC_RELAXED) >= value) + return true; + usleep(1000); + } + + return false; +} + +static enum scx_test_status setup(void **ctx_ptr) +{ + struct nohz_tick_ctx *ctx; + cpu_set_t controller_mask; + int cpu; + + ctx = calloc(1, sizeof(*ctx)); + SCX_FAIL_IF(!ctx, "Failed to allocate context"); + if (sched_getaffinity(0, sizeof(ctx->original_mask), + &ctx->original_mask)) { + free(ctx); + SCX_FAIL("Failed to get affinity (%d)", errno); + } + + cpu = find_nohz_full_cpu(&ctx->original_mask); + if (cpu < 0) { + fprintf(stderr, "SKIP: no allowed NOHZ_FULL CPU\n"); + free(ctx); + return SCX_TEST_SKIP; + } + + controller_mask = ctx->original_mask; + CPU_CLR(cpu, &controller_mask); + if (CPU_COUNT(&controller_mask) == 0) { + fprintf(stderr, "SKIP: no housekeeping CPU available\n"); + free(ctx); + return SCX_TEST_SKIP; + } + + ctx->test_cpu = cpu; + ctx->skel = nohz_tick__open(); + if (!ctx->skel) { + free(ctx); + SCX_FAIL("Failed to open skeleton"); + } + + SCX_ENUM_INIT(ctx->skel); + ctx->skel->rodata->test_cpu = cpu; + ctx->skel->struct_ops.nohz_tick_ops->flags |= SCX_OPS_SWITCH_PARTIAL | + SCX_OPS_ENQ_LAST; + if (nohz_tick__load(ctx->skel)) { + nohz_tick__destroy(ctx->skel); + free(ctx); + SCX_FAIL("Failed to load skeleton"); + } + + if (sched_setaffinity(0, sizeof(controller_mask), &controller_mask)) { + nohz_tick__destroy(ctx->skel); + free(ctx); + SCX_FAIL("Failed to move controller off CPU %d (%d)", cpu, errno); + } + + *ctx_ptr = ctx; + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx_ptr) +{ + struct nohz_tick_ctx *ctx = ctx_ptr; + struct nohz_tick *skel = ctx->skel; + struct bpf_link *link = NULL; + enum scx_test_status status = SCX_TEST_FAIL; + pid_t finite_worker = -1; + pid_t inf_worker = -1; + u64 finite_running; + u64 finite_ticks; + int ret; + + link = bpf_map__attach_struct_ops(skel->maps.nohz_tick_ops); + if (!link) { + SCX_ERR("Failed to attach scheduler"); + goto out; + } + + /* + * Establish SCX_RQ_CAN_STOP_TICK with an infinite-slice task. + */ + inf_worker = start_worker(ctx->test_cpu); + if (inf_worker < 0) { + SCX_ERR("Failed to start infinite-slice worker (%d)", errno); + goto out; + } + if (!wait_for_counter(&skel->bss->nr_inf_running, 1, + PHASE_TIMEOUT_MS)) { + SCX_ERR("Infinite-slice worker was not scheduled"); + goto out; + } + + /* Block without exiting so the rq retains the infinite-slice state. */ + ret = pause_worker(inf_worker); + if (ret) { + SCX_ERR("Failed to stop infinite-slice worker (%d)", ret); + goto out; + } + + /* Let the target enter idle with its tick stopped. */ + usleep(100000); + + /* + * The next EXT task receives a finite slice and must restart the tick. + */ + __atomic_store_n(&skel->bss->finite_phase, true, __ATOMIC_RELEASE); + finite_worker = start_worker(ctx->test_cpu); + if (finite_worker < 0) { + SCX_ERR("Failed to start finite-slice worker (%d)", errno); + goto out; + } + if (!wait_for_counter(&skel->bss->nr_finite_running, 1, + PHASE_TIMEOUT_MS)) { + SCX_ERR("Finite-slice worker was not scheduled"); + goto out; + } + if (!wait_for_counter(&skel->bss->nr_finite_ticks, MIN_FINITE_TICKS, + PHASE_TIMEOUT_MS)) { + SCX_ERR("Finite-slice worker received only %llu scheduler ticks", + (unsigned long long)skel->bss->nr_finite_ticks); + goto out; + } + stop_worker(finite_worker); + finite_worker = -1; + + /* + * Leave the CPU idle after a finite-slice task. The next finite-slice + * task must restart the tick even though the slice type is unchanged. + */ + usleep(100000); + finite_running = __atomic_load_n(&skel->bss->nr_finite_running, + __ATOMIC_RELAXED); + finite_ticks = __atomic_load_n(&skel->bss->nr_finite_ticks, + __ATOMIC_RELAXED); + + finite_worker = start_worker(ctx->test_cpu); + if (finite_worker < 0) { + SCX_ERR("Failed to start second finite-slice worker (%d)", errno); + goto out; + } + if (!wait_for_counter(&skel->bss->nr_finite_running, + finite_running + 1, PHASE_TIMEOUT_MS)) { + SCX_ERR("Second finite-slice worker was not scheduled"); + goto out; + } + if (!wait_for_counter(&skel->bss->nr_finite_ticks, + finite_ticks + MIN_FINITE_TICKS, + PHASE_TIMEOUT_MS)) { + SCX_ERR("Second finite-slice worker received only %llu scheduler ticks", + (unsigned long long)(skel->bss->nr_finite_ticks - + finite_ticks)); + goto out; + } + + if (skel->data->uei.kind != EXIT_KIND(SCX_EXIT_NONE)) { + SCX_ERR("Scheduler exited unexpectedly (kind=%llu code=%lld)", + (unsigned long long)skel->data->uei.kind, + (long long)skel->data->uei.exit_code); + goto out; + } + + fprintf(stderr, "CPU %d received %llu finite-slice ticks\n", + ctx->test_cpu, + (unsigned long long)skel->bss->nr_finite_ticks); + status = SCX_TEST_PASS; +out: + stop_worker(finite_worker); + stop_worker(inf_worker); + if (link) + bpf_link__destroy(link); + return status; +} + +static void cleanup(void *ctx_ptr) +{ + struct nohz_tick_ctx *ctx = ctx_ptr; + + sched_setaffinity(0, sizeof(ctx->original_mask), &ctx->original_mask); + nohz_tick__destroy(ctx->skel); + free(ctx); +} + +struct scx_test nohz_tick = { + .name = "nohz_tick", + .description = "Verify finite EXT slices restart the NOHZ_FULL tick", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&nohz_tick) diff --git a/tools/testing/selftests/sched_ext/non_scx_kfunc_deny.bpf.c b/tools/testing/selftests/sched_ext/non_scx_kfunc_deny.bpf.c new file mode 100644 index 000000000000..0d6fcc8e5eb6 --- /dev/null +++ b/tools/testing/selftests/sched_ext/non_scx_kfunc_deny.bpf.c @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Verify that context-sensitive SCX kfuncs (even "unlocked" ones) are + * restricted to only SCX struct_ops programs. Non-SCX struct_ops programs, + * such as TCP congestion control programs, should be rejected by the BPF + * verifier when attempting to call these kfuncs. + * + * Copyright (C) 2026 Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw> + * Copyright (C) 2026 Cheng-Yang Chou <yphbchou0911@gmail.com> + */ + +#include <scx/common.bpf.h> + +SEC("struct_ops/ssthresh") +__u32 BPF_PROG(tcp_ca_ssthresh, struct sock *sk) +{ + /* + * This call should be rejected by the verifier because this is a + * TCP congestion control program (non-SCX struct_ops). + */ + scx_bpf_kick_cpu(0, 0); + return 2; +} + +SEC("struct_ops/cong_avoid") +void BPF_PROG(tcp_ca_cong_avoid, struct sock *sk, __u32 ack, __u32 acked) {} + +SEC("struct_ops/undo_cwnd") +__u32 BPF_PROG(tcp_ca_undo_cwnd, struct sock *sk) { return 2; } + +SEC(".struct_ops") +struct tcp_congestion_ops tcp_non_scx_ca = { + .ssthresh = (void *)tcp_ca_ssthresh, + .cong_avoid = (void *)tcp_ca_cong_avoid, + .undo_cwnd = (void *)tcp_ca_undo_cwnd, + .name = "tcp_kfunc_deny", +}; + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/sched_ext/non_scx_kfunc_deny.c b/tools/testing/selftests/sched_ext/non_scx_kfunc_deny.c new file mode 100644 index 000000000000..1c031575fb87 --- /dev/null +++ b/tools/testing/selftests/sched_ext/non_scx_kfunc_deny.c @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Verify that context-sensitive SCX kfuncs (even "unlocked" ones) are + * restricted to only SCX struct_ops programs. Non-SCX struct_ops programs, + * such as TCP congestion control programs, should be rejected by the BPF + * verifier when attempting to call these kfuncs. + * + * Copyright (C) 2026 Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw> + * Copyright (C) 2026 Cheng-Yang Chou <yphbchou0911@gmail.com> + */ + +#include <bpf/bpf.h> +#include <scx/common.h> +#include <unistd.h> +#include <errno.h> +#include <stdio.h> +#include "non_scx_kfunc_deny.bpf.skel.h" +#include "scx_test.h" + +static enum scx_test_status run(void *ctx) +{ + struct non_scx_kfunc_deny *skel; + int err; + + skel = non_scx_kfunc_deny__open(); + if (!skel) { + SCX_ERR("Failed to open skel"); + return SCX_TEST_FAIL; + } + + err = non_scx_kfunc_deny__load(skel); + non_scx_kfunc_deny__destroy(skel); + + if (err == 0) { + SCX_ERR("non-SCX BPF program loaded when it should have been rejected"); + return SCX_TEST_FAIL; + } + + return SCX_TEST_PASS; +} + +struct scx_test non_scx_kfunc_deny = { + .name = "non_scx_kfunc_deny", + .description = "Verify that non-SCX struct_ops programs cannot call SCX kfuncs", + .run = run, +}; +REGISTER_SCX_TEST(&non_scx_kfunc_deny) diff --git a/tools/testing/selftests/sched_ext/numa.bpf.c b/tools/testing/selftests/sched_ext/numa.bpf.c index a79d86ed54a1..679b51d38089 100644 --- a/tools/testing/selftests/sched_ext/numa.bpf.c +++ b/tools/testing/selftests/sched_ext/numa.bpf.c @@ -19,24 +19,42 @@ UEI_DEFINE(uei); const volatile unsigned int __COMPAT_SCX_PICK_IDLE_IN_NODE; -static bool is_cpu_idle(s32 cpu, int node) +static void validate_local_idle_state(void) { const struct cpumask *idle_cpumask; - bool idle; + struct task_struct *curr; + s32 cpu = bpf_get_smp_processor_id(); + int node = __COMPAT_scx_bpf_cpu_node(cpu); + bool cpu_is_idle, curr_is_idle; + + bpf_rcu_read_lock(); + curr = scx_bpf_cpu_curr(cpu); + curr_is_idle = curr && (curr->flags & PF_IDLE); + bpf_rcu_read_unlock(); idle_cpumask = __COMPAT_scx_bpf_get_idle_cpumask_node(node); - idle = bpf_cpumask_test_cpu(cpu, idle_cpumask); + cpu_is_idle = bpf_cpumask_test_cpu(cpu, idle_cpumask); scx_bpf_put_cpumask(idle_cpumask); - return idle; + /* + * Unlike a remote picked CPU, the local CPU cannot go through an + * idle re-pick while this callback is running. If it is running a + * non-idle scheduling context, it must not be advertised as idle + * in its node's idle cpumask. + */ + if (!curr_is_idle && cpu_is_idle) + scx_bpf_error("running CPU %d should be marked as busy", cpu); } 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 task_cpu = scx_bpf_task_cpu(p); + int node = __COMPAT_scx_bpf_cpu_node(task_cpu); s32 cpu; + validate_local_idle_state(); + /* * We could just use __COMPAT_scx_bpf_pick_any_cpu_node() here, * since it already tries to pick an idle CPU within the node @@ -48,8 +66,15 @@ s32 BPF_STRUCT_OPS(numa_select_cpu, 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); + /* + * @task_cpu may be outside of p->cpus_ptr if @p's affinity + * changed while it was sleeping. This means it's possible for + * p->cpus_ptr to not include any CPUs from @node. + * If we failed to find a cpu in @node, check if @task_cpu + * is outside of p->cpus_ptr and just return @prev_cpu if it is. + */ + if (cpu < 0 && !bpf_cpumask_test_cpu(task_cpu, p->cpus_ptr)) + return prev_cpu; if (__COMPAT_scx_bpf_cpu_node(cpu) != node) scx_bpf_error("CPU %d should be in node %d", cpu, node); @@ -68,7 +93,7 @@ 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); + scx_bpf_dsq_move_to_local(node, 0); } s32 BPF_STRUCT_OPS_SLEEPABLE(numa_init) diff --git a/tools/testing/selftests/sched_ext/peek_dsq.bpf.c b/tools/testing/selftests/sched_ext/peek_dsq.bpf.c index a3faf5bb49d6..9e802b52b29e 100644 --- a/tools/testing/selftests/sched_ext/peek_dsq.bpf.c +++ b/tools/testing/selftests/sched_ext/peek_dsq.bpf.c @@ -58,14 +58,14 @@ static void record_peek_result(long pid) { u32 slot_key; long *slot_pid_ptr; - int ix; + u32 ix; if (pid <= 0) return; /* Find an empty slot or one with the same PID */ bpf_for(ix, 0, 10) { - slot_key = (pid + ix) % MAX_SAMPLES; + slot_key = ((u64)pid + ix) % MAX_SAMPLES; slot_pid_ptr = bpf_map_lookup_elem(&peek_results, &slot_key); if (!slot_pid_ptr) continue; @@ -95,7 +95,7 @@ static int scan_dsq_pool(void) record_peek_result(task->pid); /* Try to move this task to local */ - if (!moved && scx_bpf_dsq_move_to_local(dsq_id) == 0) { + if (!moved && scx_bpf_dsq_move_to_local(dsq_id, 0)) { moved = 1; break; } @@ -156,19 +156,19 @@ void BPF_STRUCT_OPS(peek_dsq_dispatch, s32 cpu, struct task_struct *prev) dsq_peek_result2_pid = peek_result ? peek_result->pid : -1; /* Now consume the task since we've peeked at it */ - scx_bpf_dsq_move_to_local(test_dsq_id); + scx_bpf_dsq_move_to_local(test_dsq_id, 0); /* Mark phase 1 as complete */ phase1_complete = 1; bpf_printk("Phase 1 complete, starting phase 2 stress testing"); } else if (!phase1_complete) { /* Still in phase 1, use real DSQ */ - scx_bpf_dsq_move_to_local(real_dsq_id); + scx_bpf_dsq_move_to_local(real_dsq_id, 0); } else { /* Phase 2: Scan all DSQs in the pool and try to move a task */ if (!scan_dsq_pool()) { /* No tasks found in DSQ pool, fall back to real DSQ */ - scx_bpf_dsq_move_to_local(real_dsq_id); + scx_bpf_dsq_move_to_local(real_dsq_id, 0); } } } @@ -197,7 +197,7 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(peek_dsq_init) } err = scx_bpf_create_dsq(real_dsq_id, -1); if (err) { - scx_bpf_error("Failed to create DSQ %d: %d", test_dsq_id, err); + scx_bpf_error("Failed to create DSQ %d: %d", real_dsq_id, err); return err; } diff --git a/tools/testing/selftests/sched_ext/prog_run.c b/tools/testing/selftests/sched_ext/prog_run.c index 05974820ca69..1129ec2aaddc 100644 --- a/tools/testing/selftests/sched_ext/prog_run.c +++ b/tools/testing/selftests/sched_ext/prog_run.c @@ -28,7 +28,8 @@ static enum scx_test_status setup(void **ctx) static enum scx_test_status run(void *ctx) { struct prog_run *skel = ctx; - struct bpf_link *link; + struct bpf_link *link = NULL; + enum scx_test_status status = SCX_TEST_PASS; int prog_fd, err = 0; prog_fd = bpf_program__fd(skel->progs.prog_run_syscall); @@ -42,23 +43,40 @@ static enum scx_test_status run(void *ctx) link = bpf_map__attach_struct_ops(skel->maps.prog_run_ops); if (!link) { SCX_ERR("Failed to attach scheduler"); - close(prog_fd); - return SCX_TEST_FAIL; + status = SCX_TEST_FAIL; + goto out; } err = bpf_prog_test_run_opts(prog_fd, &topts); - SCX_EQ(err, 0); + if (err) { + SCX_ERR("BPF_PROG_RUN failed (%d)", err); + status = SCX_TEST_FAIL; + goto out; + } /* Assumes uei.kind is written last */ while (skel->data->uei.kind == EXIT_KIND(SCX_EXIT_NONE)) sched_yield(); - SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG_BPF)); - SCX_EQ(skel->data->uei.exit_code, 0xdeadbeef); + if (skel->data->uei.kind != EXIT_KIND(SCX_EXIT_UNREG_BPF)) { + SCX_ERR("Unexpected exit kind: %llu", + (unsigned long long)skel->data->uei.kind); + status = SCX_TEST_FAIL; + goto out; + } + if (skel->data->uei.exit_code != 0xdeadbeef) { + SCX_ERR("Unexpected exit code: %lld", + (long long)skel->data->uei.exit_code); + status = SCX_TEST_FAIL; + goto out; + } + +out: close(prog_fd); - bpf_link__destroy(link); + if (link) + bpf_link__destroy(link); - return SCX_TEST_PASS; + return status; } static void cleanup(void *ctx) diff --git a/tools/testing/selftests/sched_ext/reload_loop.c b/tools/testing/selftests/sched_ext/reload_loop.c index 308211d80436..49297b83d748 100644 --- a/tools/testing/selftests/sched_ext/reload_loop.c +++ b/tools/testing/selftests/sched_ext/reload_loop.c @@ -23,6 +23,9 @@ static enum scx_test_status setup(void **ctx) SCX_ENUM_INIT(skel); SCX_FAIL_IF(maximal__load(skel), "Failed to load skel"); + bpf_map__set_autoattach(skel->maps.maximal_ops, false); + SCX_FAIL_IF(maximal__attach(skel), "Failed to attach skel"); + return SCX_TEST_PASS; } diff --git a/tools/testing/selftests/sched_ext/rt_stall.bpf.c b/tools/testing/selftests/sched_ext/rt_stall.bpf.c new file mode 100644 index 000000000000..80086779dd1e --- /dev/null +++ b/tools/testing/selftests/sched_ext/rt_stall.bpf.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A scheduler that verified if RT tasks can stall SCHED_EXT tasks. + * + * Copyright (c) 2025 NVIDIA Corporation. + */ + +#include <scx/common.bpf.h> + +char _license[] SEC("license") = "GPL"; + +UEI_DEFINE(uei); + +void BPF_STRUCT_OPS(rt_stall_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops rt_stall_ops = { + .exit = (void *)rt_stall_exit, + .name = "rt_stall", +}; diff --git a/tools/testing/selftests/sched_ext/rt_stall.c b/tools/testing/selftests/sched_ext/rt_stall.c new file mode 100644 index 000000000000..a5041fc2e44f --- /dev/null +++ b/tools/testing/selftests/sched_ext/rt_stall.c @@ -0,0 +1,293 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2025 NVIDIA Corporation. + */ +#define _GNU_SOURCE +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <sched.h> +#include <sys/prctl.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <time.h> +#include <linux/sched.h> +#include <signal.h> +#include <bpf/bpf.h> +#include <scx/common.h> +#include "rt_stall.bpf.skel.h" +#include "scx_test.h" +#include "../kselftest.h" + +#define CORE_ID 0 /* CPU to pin tasks to */ +#define RUN_TIME 5 /* How long to run the test in seconds */ + +/* Signal the parent that setup is complete by writing to a pipe */ +static void signal_ready(int fd) +{ + char c = 1; + + if (write(fd, &c, 1) != 1) { + perror("write to ready pipe"); + exit(EXIT_FAILURE); + } + close(fd); +} + +/* Wait for a child to signal readiness via a pipe */ +static void wait_ready(int fd) +{ + char c; + + if (read(fd, &c, 1) != 1) { + perror("read from ready pipe"); + exit(EXIT_FAILURE); + } + close(fd); +} + +/* Simple busy-wait function for test tasks */ +static void process_func(void) +{ + while (1) { + /* Busy wait */ + for (volatile unsigned long i = 0; i < 10000000UL; i++) + ; + } +} + +/* Set CPU affinity to a specific core */ +static void set_affinity(int cpu) +{ + cpu_set_t mask; + + CPU_ZERO(&mask); + CPU_SET(cpu, &mask); + if (sched_setaffinity(0, sizeof(mask), &mask) != 0) { + perror("sched_setaffinity"); + exit(EXIT_FAILURE); + } +} + +/* Set task scheduling policy and priority */ +static void set_sched(int policy, int priority) +{ + struct sched_param param; + + param.sched_priority = priority; + if (sched_setscheduler(0, policy, ¶m) != 0) { + perror("sched_setscheduler"); + exit(EXIT_FAILURE); + } +} + +/* Get process runtime from /proc/<pid>/stat */ +static float get_process_runtime(int pid) +{ + char path[256]; + FILE *file; + long utime, stime; + int fields; + + snprintf(path, sizeof(path), "/proc/%d/stat", pid); + file = fopen(path, "r"); + if (file == NULL) { + perror("Failed to open stat file"); + return -1; + } + + /* Skip the first 13 fields and read the 14th and 15th */ + fields = fscanf(file, + "%*d %*s %*c %*d %*d %*d %*d %*d %*u %*u %*u %*u %*u %lu %lu", + &utime, &stime); + fclose(file); + + if (fields != 2) { + fprintf(stderr, "Failed to read stat file\n"); + return -1; + } + + /* Calculate the total time spent in the process */ + long total_time = utime + stime; + long ticks_per_second = sysconf(_SC_CLK_TCK); + float runtime_seconds = total_time * 1.0 / ticks_per_second; + + return runtime_seconds; +} + +static enum scx_test_status setup(void **ctx) +{ + struct rt_stall *skel; + + if (!__COMPAT_struct_has_field("rq", "ext_server")) { + fprintf(stderr, "SKIP: ext DL server not supported\n"); + return SCX_TEST_SKIP; + } + + skel = rt_stall__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(rt_stall__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static bool sched_stress_test(bool is_ext) +{ + /* + * We're expecting the EXT task to get around 5% of CPU time when + * competing with the RT task (small 1% fluctuations are expected). + * + * However, the EXT task should get at least 4% of the CPU to prove + * that the EXT deadline server is working correctly. A percentage + * less than 4% indicates a bug where RT tasks can potentially + * stall SCHED_EXT tasks, causing the test to fail. + */ + const float expected_min_ratio = 0.04; /* 4% */ + const char *class_str = is_ext ? "EXT" : "FAIR"; + + float ext_runtime, rt_runtime, actual_ratio; + int ext_pid, rt_pid; + int ext_ready[2], rt_ready[2]; + + ksft_print_header(); + ksft_set_plan(1); + + if (pipe(ext_ready) || pipe(rt_ready)) { + perror("pipe"); + ksft_exit_fail(); + } + + /* Create and set up a EXT task */ + ext_pid = fork(); + if (ext_pid == 0) { + close(ext_ready[0]); + close(rt_ready[0]); + close(rt_ready[1]); + set_affinity(CORE_ID); + signal_ready(ext_ready[1]); + process_func(); + exit(0); + } else if (ext_pid < 0) { + perror("fork task"); + ksft_exit_fail(); + } + + /* Create an RT task */ + rt_pid = fork(); + if (rt_pid == 0) { + close(ext_ready[0]); + close(ext_ready[1]); + close(rt_ready[0]); + set_affinity(CORE_ID); + set_sched(SCHED_FIFO, 50); + signal_ready(rt_ready[1]); + process_func(); + exit(0); + } else if (rt_pid < 0) { + perror("fork for RT task"); + ksft_exit_fail(); + } + + /* + * Wait for both children to complete their setup (affinity and + * scheduling policy) before starting the measurement window. + * This prevents flaky failures caused by the RT child's setup + * time eating into the measurement period. + */ + close(ext_ready[1]); + close(rt_ready[1]); + wait_ready(ext_ready[0]); + wait_ready(rt_ready[0]); + + /* Let the processes run for the specified time */ + sleep(RUN_TIME); + + /* Get runtime for the EXT task */ + ext_runtime = get_process_runtime(ext_pid); + if (ext_runtime == -1) + ksft_exit_fail_msg("Error getting runtime for %s task (PID %d)\n", + class_str, ext_pid); + ksft_print_msg("Runtime of %s task (PID %d) is %f seconds\n", + class_str, ext_pid, ext_runtime); + + /* Get runtime for the RT task */ + rt_runtime = get_process_runtime(rt_pid); + if (rt_runtime == -1) + ksft_exit_fail_msg("Error getting runtime for RT task (PID %d)\n", rt_pid); + ksft_print_msg("Runtime of RT task (PID %d) is %f seconds\n", rt_pid, rt_runtime); + + /* Kill the processes */ + kill(ext_pid, SIGKILL); + kill(rt_pid, SIGKILL); + waitpid(ext_pid, NULL, 0); + waitpid(rt_pid, NULL, 0); + + /* Verify that the scx task got enough runtime */ + actual_ratio = ext_runtime / (ext_runtime + rt_runtime); + ksft_print_msg("%s task got %.2f%% of total runtime\n", + class_str, actual_ratio * 100); + + if (actual_ratio >= expected_min_ratio) { + ksft_test_result_pass("PASS: %s task got more than %.2f%% of runtime\n", + class_str, expected_min_ratio * 100); + return true; + } + ksft_test_result_fail("FAIL: %s task got less than %.2f%% of runtime\n", + class_str, expected_min_ratio * 100); + return false; +} + +static enum scx_test_status run(void *ctx) +{ + struct rt_stall *skel = ctx; + struct bpf_link *link = NULL; + bool res; + int i; + + /* + * Test if the dl_server is working both with and without the + * sched_ext scheduler attached. + * + * This ensures all the scenarios are covered: + * - fair_server stop -> ext_server start + * - ext_server stop -> fair_server stop + */ + for (i = 0; i < 4; i++) { + bool is_ext = i % 2; + + if (is_ext) { + memset(&skel->data->uei, 0, sizeof(skel->data->uei)); + link = bpf_map__attach_struct_ops(skel->maps.rt_stall_ops); + SCX_FAIL_IF(!link, "Failed to attach scheduler"); + } + res = sched_stress_test(is_ext); + if (is_ext) { + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_NONE)); + bpf_link__destroy(link); + } + + if (!res) + ksft_exit_fail(); + } + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct rt_stall *skel = ctx; + + rt_stall__destroy(skel); +} + +struct scx_test rt_stall = { + .name = "rt_stall", + .description = "Verify that RT tasks cannot stall SCHED_EXT tasks", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&rt_stall) diff --git a/tools/testing/selftests/sched_ext/runner.c b/tools/testing/selftests/sched_ext/runner.c index aa2d7d32dda9..c264807caa91 100644 --- a/tools/testing/selftests/sched_ext/runner.c +++ b/tools/testing/selftests/sched_ext/runner.c @@ -18,7 +18,7 @@ const char help_fmt[] = "It's required for the testcases to be serial, as only a single host-wide sched_ext\n" "scheduler may be loaded at any given time." "\n" -"Usage: %s [-t TEST] [-h]\n" +"Usage: %s [-t TEST] [-s] [-l] [-q]\n" "\n" " -t TEST Only run tests whose name includes this string\n" " -s Include print output for skipped tests\n" @@ -46,6 +46,14 @@ static void print_test_preamble(const struct scx_test *test, bool quiet) if (!quiet) printf("DESCRIPTION: %s\n", test->description); printf("OUTPUT:\n"); + + /* + * The tests may fork with the preamble buffered + * in the children's stdout. Flush before the test + * to avoid printing the message multiple times. + */ + fflush(stdout); + fflush(stderr); } static const char *status_to_result(enum scx_test_status status) @@ -125,6 +133,8 @@ static bool test_valid(const struct scx_test *test) int main(int argc, char **argv) { const char *filter = NULL; + const char *failed_tests[MAX_SCX_TESTS]; + const char *skipped_tests[MAX_SCX_TESTS]; unsigned testnum = 0, i; unsigned passed = 0, skipped = 0, failed = 0; int opt; @@ -154,10 +164,33 @@ int main(int argc, char **argv) } } + if (optind < argc) { + fprintf(stderr, "Unexpected argument '%s'. Use -t to filter tests.\n", + argv[optind]); + return 1; + } + + if (filter) { + for (i = 0; i < __scx_num_tests; i++) { + if (!should_skip_test(&__scx_tests[i], filter)) + break; + } + if (i == __scx_num_tests) { + fprintf(stderr, "No tests matched filter '%s'\n", filter); + fprintf(stderr, "Available tests (use -l to list):\n"); + for (i = 0; i < __scx_num_tests; i++) + fprintf(stderr, " %s\n", __scx_tests[i].name); + return 1; + } + } + for (i = 0; i < __scx_num_tests; i++) { enum scx_test_status status; struct scx_test *test = &__scx_tests[i]; + if (exit_req) + break; + if (list) { printf("%s\n", test->name); if (i == (__scx_num_tests - 1)) @@ -187,10 +220,10 @@ int main(int argc, char **argv) passed++; break; case SCX_TEST_SKIP: - skipped++; + skipped_tests[skipped++] = test->name; break; case SCX_TEST_FAIL: - failed++; + failed_tests[failed++] = test->name; break; } } @@ -199,8 +232,18 @@ int main(int argc, char **argv) printf("PASSED: %u\n", passed); printf("SKIPPED: %u\n", skipped); printf("FAILED: %u\n", failed); + if (skipped > 0) { + printf("\nSkipped tests:\n"); + for (i = 0; i < skipped; i++) + printf(" - %s\n", skipped_tests[i]); + } + if (failed > 0) { + printf("\nFailed tests:\n"); + for (i = 0; i < failed; i++) + printf(" - %s\n", failed_tests[i]); + } - return 0; + return failed > 0 ? 1 : 0; } void scx_test_register(struct scx_test *test) diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.c index 5b6e045e1109..7e342c0cec65 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.c @@ -6,6 +6,7 @@ */ #include <bpf/bpf.h> #include <scx/common.h> +#include <stdlib.h> #include <sys/wait.h> #include <unistd.h> #include "select_cpu_dfl.bpf.skel.h" @@ -13,29 +14,44 @@ #define NUM_CHILDREN 1028 +struct select_cpu_dfl_ctx { + struct select_cpu_dfl *skel; + struct bpf_link *link; +}; + static enum scx_test_status setup(void **ctx) { - struct select_cpu_dfl *skel; + struct select_cpu_dfl_ctx *tctx; + + tctx = malloc(sizeof(*tctx)); + SCX_FAIL_IF(!tctx, "Failed to allocate test context"); + tctx->link = NULL; - skel = select_cpu_dfl__open(); - SCX_FAIL_IF(!skel, "Failed to open"); - SCX_ENUM_INIT(skel); - SCX_FAIL_IF(select_cpu_dfl__load(skel), "Failed to load skel"); + tctx->skel = select_cpu_dfl__open(); + if (!tctx->skel) { + free(tctx); + SCX_FAIL("Failed to open"); + } + SCX_ENUM_INIT(tctx->skel); + if (select_cpu_dfl__load(tctx->skel)) { + select_cpu_dfl__destroy(tctx->skel); + free(tctx); + SCX_FAIL("Failed to load skel"); + } - *ctx = skel; + *ctx = tctx; return SCX_TEST_PASS; } static enum scx_test_status run(void *ctx) { - struct select_cpu_dfl *skel = ctx; - struct bpf_link *link; + struct select_cpu_dfl_ctx *tctx = ctx; pid_t pids[NUM_CHILDREN]; - int i, status; + int i, status, nforked = 0; - link = bpf_map__attach_struct_ops(skel->maps.select_cpu_dfl_ops); - SCX_FAIL_IF(!link, "Failed to attach scheduler"); + tctx->link = bpf_map__attach_struct_ops(tctx->skel->maps.select_cpu_dfl_ops); + SCX_FAIL_IF(!tctx->link, "Failed to attach scheduler"); for (i = 0; i < NUM_CHILDREN; i++) { pids[i] = fork(); @@ -43,25 +59,31 @@ static enum scx_test_status run(void *ctx) sleep(1); exit(0); } + if (pids[i] > 0) + nforked++; } for (i = 0; i < NUM_CHILDREN; i++) { + if (pids[i] <= 0) + continue; SCX_EQ(waitpid(pids[i], &status, 0), pids[i]); SCX_EQ(status, 0); } - SCX_ASSERT(!skel->bss->saw_local); - - bpf_link__destroy(link); + SCX_GT(nforked, 0); + SCX_ASSERT(!tctx->skel->bss->saw_local); return SCX_TEST_PASS; } static void cleanup(void *ctx) { - struct select_cpu_dfl *skel = ctx; + struct select_cpu_dfl_ctx *tctx = ctx; - select_cpu_dfl__destroy(skel); + if (tctx->link) + bpf_link__destroy(tctx->link); + select_cpu_dfl__destroy(tctx->skel); + free(tctx); } struct scx_test select_cpu_dfl = { 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 bfcb96cd4954..eec70d388cbf 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c @@ -53,7 +53,7 @@ ddsp: void BPF_STRUCT_OPS(select_cpu_vtime_dispatch, s32 cpu, struct task_struct *p) { - if (scx_bpf_dsq_move_to_local(VTIME_DSQ)) + if (scx_bpf_dsq_move_to_local(VTIME_DSQ, 0)) consumed = true; } @@ -66,12 +66,14 @@ void BPF_STRUCT_OPS(select_cpu_vtime_running, struct task_struct *p) void BPF_STRUCT_OPS(select_cpu_vtime_stopping, struct task_struct *p, bool runnable) { - p->scx.dsq_vtime += (SCX_SLICE_DFL - p->scx.slice) * 100 / p->scx.weight; + u64 delta = scale_by_task_weight_inverse(p, SCX_SLICE_DFL - p->scx.slice); + + scx_bpf_task_set_dsq_vtime(p, p->scx.dsq_vtime + delta); } void BPF_STRUCT_OPS(select_cpu_vtime_enable, struct task_struct *p) { - p->scx.dsq_vtime = vtime_now; + scx_bpf_task_set_dsq_vtime(p, vtime_now); } s32 BPF_STRUCT_OPS_SLEEPABLE(select_cpu_vtime_init) diff --git a/tools/testing/selftests/sched_ext/total_bw.c b/tools/testing/selftests/sched_ext/total_bw.c new file mode 100644 index 000000000000..2af01cee90cc --- /dev/null +++ b/tools/testing/selftests/sched_ext/total_bw.c @@ -0,0 +1,480 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test to verify that total_bw value remains consistent across all CPUs + * in different BPF program states. + * + * Copyright (C) 2025 NVIDIA Corporation. + */ +#include <bpf/bpf.h> +#include <errno.h> +#include <pthread.h> +#include <scx/common.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/wait.h> +#include <unistd.h> +#include "minimal.bpf.skel.h" +#include "scx_test.h" + +#define MAX_CPUS 512 +#define STRESS_DURATION_SEC 5 + +struct total_bw_ctx { + struct minimal *skel; + long baseline_bw[MAX_CPUS]; + int nr_cpus; +}; + +static void *cpu_stress_thread(void *arg) +{ + volatile int i; + time_t end_time = time(NULL) + STRESS_DURATION_SEC; + + while (time(NULL) < end_time) + for (i = 0; i < 1000000; i++) + ; + + return NULL; +} + +/* + * The first enqueue on a CPU causes the DL server to start, for that + * reason run stressor threads in the hopes it schedules on all CPUs. + */ +static int run_cpu_stress(int nr_cpus) +{ + pthread_t *threads; + int i, ret = 0; + + threads = calloc(nr_cpus, sizeof(pthread_t)); + if (!threads) + return -ENOMEM; + + /* Create threads to run on each CPU */ + for (i = 0; i < nr_cpus; i++) { + if (pthread_create(&threads[i], NULL, cpu_stress_thread, NULL)) { + ret = -errno; + fprintf(stderr, "Failed to create thread %d: %s\n", i, strerror(-ret)); + break; + } + } + + /* Wait for all threads to complete */ + for (i = 0; i < nr_cpus; i++) { + if (threads[i]) + pthread_join(threads[i], NULL); + } + + free(threads); + return ret; +} + +static int read_total_bw_values(long *bw_values, int max_cpus) +{ + FILE *fp; + char line[256]; + int cpu_count = 0; + + fp = fopen("/sys/kernel/debug/sched/debug", "r"); + if (!fp) { + SCX_ERR("Failed to open debug file"); + return -1; + } + + while (fgets(line, sizeof(line), fp)) { + char *bw_str = strstr(line, "total_bw"); + + if (bw_str) { + bw_str = strchr(bw_str, ':'); + if (bw_str) { + /* Only store up to max_cpus values */ + if (cpu_count < max_cpus) + bw_values[cpu_count] = atol(bw_str + 1); + cpu_count++; + } + } + } + + fclose(fp); + return cpu_count; +} + +/* + * Read a per-CPU dl_server param (runtime or period) from debugfs. + * Returns the value in nanoseconds, or -1 on failure. + */ +static long read_server_param(const char *server, const char *param, int cpu) +{ + char path[128]; + long value = -1; + FILE *fp; + + snprintf(path, sizeof(path), + "/sys/kernel/debug/sched/%s_server/cpu%d/%s", + server, cpu, param); + fp = fopen(path, "r"); + if (!fp) + return -1; + if (fscanf(fp, "%ld", &value) != 1) + value = -1; + fclose(fp); + + return value; +} + +/* + * Write a per-CPU dl_server param to debugfs. Returns 0 on success. + */ +static int write_server_param(const char *server, const char *param, + int cpu, long value) +{ + char path[128]; + FILE *fp; + int ret = 0; + + snprintf(path, sizeof(path), + "/sys/kernel/debug/sched/%s_server/cpu%d/%s", + server, cpu, param); + fp = fopen(path, "w"); + if (!fp) + return -1; + if (fprintf(fp, "%ld", value) < 0) + ret = -1; + if (fclose(fp) != 0) + ret = -1; + + return ret; +} + +static int read_fair_runtime_all(int nr_cpus, long *runtimes) +{ + int i; + + for (i = 0; i < nr_cpus; i++) { + runtimes[i] = read_server_param("fair", "runtime", i); + if (runtimes[i] <= 0) + return -1; + } + + return 0; +} + +static int write_fair_runtime_all(int nr_cpus, long value) +{ + int i; + + for (i = 0; i < nr_cpus; i++) { + if (write_server_param("fair", "runtime", i, value) < 0) { + SCX_ERR("Failed to write fair_server runtime on CPU %d", i); + return -1; + } + } + + return 0; +} + +/* + * Restore per-CPU fair_server runtimes. + */ +static int restore_fair_runtime_all(int nr_cpus, const long *runtimes) +{ + int ret = 0; + int i; + + for (i = 0; i < nr_cpus; i++) { + if (write_server_param("fair", "runtime", i, runtimes[i]) < 0) { + SCX_ERR("Failed to restore fair_server runtime on CPU %d", i); + ret = -1; + } + } + + return ret; +} + +static bool verify_total_bw_consistency(long *bw_values, int count) +{ + int i; + long first_value; + + if (count <= 0) + return false; + + first_value = bw_values[0]; + + for (i = 1; i < count; i++) { + if (bw_values[i] != first_value) { + SCX_ERR("Inconsistent total_bw: CPU0=%ld, CPU%d=%ld", + first_value, i, bw_values[i]); + return false; + } + } + + return true; +} + +static int fetch_verify_total_bw(long *bw_values, int nr_cpus) +{ + int attempts = 0; + int max_attempts = 10; + int count; + + /* + * The first enqueue on a CPU causes the DL server to start, for that + * reason run stressor threads in the hopes it schedules on all CPUs. + */ + if (run_cpu_stress(nr_cpus) < 0) { + SCX_ERR("Failed to run CPU stress"); + return -1; + } + + /* Try multiple times to get stable values */ + while (attempts < max_attempts) { + count = read_total_bw_values(bw_values, nr_cpus); + fprintf(stderr, "Read %d total_bw values (testing %d CPUs)\n", count, nr_cpus); + /* If system has more CPUs than we're testing, that's OK */ + if (count < nr_cpus) { + SCX_ERR("Expected at least %d CPUs, got %d", nr_cpus, count); + attempts++; + sleep(1); + continue; + } + + /* Only verify the CPUs we're testing */ + if (verify_total_bw_consistency(bw_values, nr_cpus)) { + fprintf(stderr, "Values are consistent: %ld\n", bw_values[0]); + return 0; + } + + attempts++; + sleep(1); + } + + return -1; +} + +static enum scx_test_status setup(void **ctx) +{ + struct total_bw_ctx *test_ctx; + + if (access("/sys/kernel/debug/sched/debug", R_OK) != 0) { + fprintf(stderr, "Skipping test: debugfs sched/debug not accessible\n"); + return SCX_TEST_SKIP; + } + + test_ctx = calloc(1, sizeof(*test_ctx)); + if (!test_ctx) + return SCX_TEST_FAIL; + + test_ctx->nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + if (test_ctx->nr_cpus <= 0) { + free(test_ctx); + return SCX_TEST_FAIL; + } + + /* If system has more CPUs than MAX_CPUS, just test the first MAX_CPUS */ + if (test_ctx->nr_cpus > MAX_CPUS) + test_ctx->nr_cpus = MAX_CPUS; + + /* Test scenario 1: BPF program not loaded */ + /* Read and verify baseline total_bw before loading BPF program */ + fprintf(stderr, "BPF prog initially not loaded, reading total_bw values\n"); + if (fetch_verify_total_bw(test_ctx->baseline_bw, test_ctx->nr_cpus) < 0) { + SCX_ERR("Failed to get stable baseline values"); + free(test_ctx); + return SCX_TEST_FAIL; + } + + /* Load the BPF skeleton */ + test_ctx->skel = minimal__open(); + if (!test_ctx->skel) { + free(test_ctx); + return SCX_TEST_FAIL; + } + + SCX_ENUM_INIT(test_ctx->skel); + if (minimal__load(test_ctx->skel)) { + minimal__destroy(test_ctx->skel); + free(test_ctx); + return SCX_TEST_FAIL; + } + + *ctx = test_ctx; + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct total_bw_ctx *test_ctx = ctx; + struct bpf_link *link; + long loaded_bw[MAX_CPUS]; + long unloaded_bw[MAX_CPUS]; + long doubled_bw[MAX_CPUS]; + long original_runtime[MAX_CPUS], doubled_runtime; + enum scx_test_status ret; + int i; + + /* Test scenario 2: BPF program loaded */ + link = bpf_map__attach_struct_ops(test_ctx->skel->maps.minimal_ops); + if (!link) { + SCX_ERR("Failed to attach scheduler"); + return SCX_TEST_FAIL; + } + + fprintf(stderr, "BPF program loaded, reading total_bw values\n"); + if (fetch_verify_total_bw(loaded_bw, test_ctx->nr_cpus) < 0) { + SCX_ERR("Failed to get stable values with BPF loaded"); + bpf_link__destroy(link); + return SCX_TEST_FAIL; + } + bpf_link__destroy(link); + + /* Test scenario 3: BPF program unloaded */ + fprintf(stderr, "BPF program unloaded, reading total_bw values\n"); + if (fetch_verify_total_bw(unloaded_bw, test_ctx->nr_cpus) < 0) { + SCX_ERR("Failed to get stable values after BPF unload"); + return SCX_TEST_FAIL; + } + + /* Verify all three scenarios have the same total_bw values */ + for (i = 0; i < test_ctx->nr_cpus; i++) { + if (test_ctx->baseline_bw[i] != loaded_bw[i]) { + SCX_ERR("CPU%d: baseline_bw=%ld != loaded_bw=%ld", + i, test_ctx->baseline_bw[i], loaded_bw[i]); + return SCX_TEST_FAIL; + } + + if (test_ctx->baseline_bw[i] != unloaded_bw[i]) { + SCX_ERR("CPU%d: baseline_bw=%ld != unloaded_bw=%ld", + i, test_ctx->baseline_bw[i], unloaded_bw[i]); + return SCX_TEST_FAIL; + } + } + + fprintf(stderr, "All total_bw values are consistent across all scenarios\n"); + + /* + * Validate auto-register/unregister of dl_server bandwidth reservations. + * + * Doubling fair_server's runtime doubles its bw contribution. With a + * full-mode BPF scheduler (minimal_ops), the kernel should detach + * fair_server and attach ext_server, dropping total_bw back to its + * pre-customization (default ext_server-only) value. On unload, the + * fair_server reservation should come back with its customized runtime + * preserved, so total_bw doubles again. + */ + if (read_fair_runtime_all(test_ctx->nr_cpus, original_runtime) < 0) { + fprintf(stderr, "Skipping attach/detach validation: debugfs not accessible\n"); + return SCX_TEST_PASS; + } + doubled_runtime = original_runtime[0] * 2; + + fprintf(stderr, + "Setting fair_server runtime to %ld ns on all CPUs (orig %ld)\n", + doubled_runtime, original_runtime[0]); + + if (write_fair_runtime_all(test_ctx->nr_cpus, doubled_runtime) < 0) { + ret = SCX_TEST_FAIL; + goto restore; + } + + if (fetch_verify_total_bw(doubled_bw, test_ctx->nr_cpus) < 0) { + SCX_ERR("Failed to get stable values after doubling fair runtime"); + ret = SCX_TEST_FAIL; + goto restore; + } + + /* + * After doubling the runtime, fair_server's bw contribution must grow. + * We don't assert exactly 2x, because the kernel's to_ratio() truncates + * the value, so 2 * to_ratio(period, runtime) and + * to_ratio(period, 2 * runtime) can differ. + */ + for (i = 0; i < test_ctx->nr_cpus; i++) { + if (doubled_bw[i] <= test_ctx->baseline_bw[i]) { + SCX_ERR("CPU%d: fair did not increase total_bw (baseline=%ld, doubled=%ld)", + i, test_ctx->baseline_bw[i], doubled_bw[i]); + ret = SCX_TEST_FAIL; + goto restore; + } + } + + link = bpf_map__attach_struct_ops(test_ctx->skel->maps.minimal_ops); + if (!link) { + SCX_ERR("Failed to attach scheduler for detach test"); + ret = SCX_TEST_FAIL; + goto restore; + } + + if (fetch_verify_total_bw(loaded_bw, test_ctx->nr_cpus) < 0) { + SCX_ERR("Failed to get stable values with BPF loaded (detach test)"); + bpf_link__destroy(link); + ret = SCX_TEST_FAIL; + goto restore; + } + + /* + * In full mode the customized fair_server is detached and ext_server is + * attached at its default runtime, total_bw must match baseline. + */ + for (i = 0; i < test_ctx->nr_cpus; i++) { + if (loaded_bw[i] != test_ctx->baseline_bw[i]) { + SCX_ERR("CPU%d: expected bw %ld (fair detached, ext default), got %ld", + i, test_ctx->baseline_bw[i], loaded_bw[i]); + bpf_link__destroy(link); + ret = SCX_TEST_FAIL; + goto restore; + } + } + + bpf_link__destroy(link); + + if (fetch_verify_total_bw(unloaded_bw, test_ctx->nr_cpus) < 0) { + SCX_ERR("Failed to get stable values after BPF unload (detach test)"); + ret = SCX_TEST_FAIL; + goto restore; + } + + /* + * After unload, fair_server is re-attached with its preserved 2x + * runtime, so total_bw should return to the doubled value. + */ + for (i = 0; i < test_ctx->nr_cpus; i++) { + if (unloaded_bw[i] != doubled_bw[i]) { + SCX_ERR("CPU%d: BPF unloaded: expected %ld (fair restored at 2x), got %ld", + i, doubled_bw[i], unloaded_bw[i]); + ret = SCX_TEST_FAIL; + goto restore; + } + } + + fprintf(stderr, + "dl_server attach/detach with customized fair runtime verified\n"); + ret = SCX_TEST_PASS; + +restore: + if (restore_fair_runtime_all(test_ctx->nr_cpus, original_runtime) < 0) + SCX_ERR("Failed to fully restore per-CPU fair_server runtimes"); + + return ret; +} + +static void cleanup(void *ctx) +{ + struct total_bw_ctx *test_ctx = ctx; + + if (test_ctx) { + if (test_ctx->skel) + minimal__destroy(test_ctx->skel); + free(test_ctx); + } +} + +struct scx_test total_bw = { + .name = "total_bw", + .description = "Verify total_bw consistency across BPF program states", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&total_bw) diff --git a/tools/testing/selftests/sched_ext/util.c b/tools/testing/selftests/sched_ext/util.c index e47769c91918..2111329ed289 100644 --- a/tools/testing/selftests/sched_ext/util.c +++ b/tools/testing/selftests/sched_ext/util.c @@ -60,11 +60,11 @@ int file_write_long(const char *path, long val) char buf[64]; int ret; - ret = sprintf(buf, "%lu", val); + ret = sprintf(buf, "%ld", val); if (ret < 0) return ret; - if (write_text(path, buf, sizeof(buf)) <= 0) + if (write_text(path, buf, ret) <= 0) return -1; return 0; diff --git a/tools/testing/selftests/sched_ext/util.h b/tools/testing/selftests/sched_ext/util.h index bc13dfec1267..681cec04b439 100644 --- a/tools/testing/selftests/sched_ext/util.h +++ b/tools/testing/selftests/sched_ext/util.h @@ -10,4 +10,4 @@ long file_read_long(const char *path); int file_write_long(const char *path, long val); -#endif // __SCX_TEST_H__ +#endif // __SCX_TEST_UTIL_H__ |