From 683d2d0faba12a0e7d4c3b85a62ac8298977e17b Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Sat, 5 Apr 2025 15:39:24 +0200 Subject: sched_ext: idle: Introduce scx_bpf_select_cpu_and() Provide a new kfunc, scx_bpf_select_cpu_and(), that can be used to apply the built-in idle CPU selection policy to a subset of allowed CPU. This new helper is basically an extension of scx_bpf_select_cpu_dfl(). However, when an idle CPU can't be found, it returns a negative value instead of @prev_cpu, aligning its behavior more closely with scx_bpf_pick_idle_cpu(). It also accepts %SCX_PICK_IDLE_* flags, which can be used to enforce strict selection to @prev_cpu's node (%SCX_PICK_IDLE_IN_NODE), or to request only a full-idle SMT core (%SCX_PICK_IDLE_CORE), while applying the built-in selection logic. With this helper, BPF schedulers can apply the built-in idle CPU selection policy restricted to any arbitrary subset of CPUs. Example usage ============= Possible usage in ops.select_cpu(): s32 BPF_STRUCT_OPS(foo_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) { const struct cpumask *cpus = task_allowed_cpus(p) ?: p->cpus_ptr; s32 cpu; cpu = scx_bpf_select_cpu_and(p, prev_cpu, wake_flags, cpus, 0); if (cpu >= 0) { scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0); return cpu; } return prev_cpu; } Results ======= Load distribution on a 4 sockets, 4 cores per socket system, simulated using virtme-ng, running a modified version of scx_bpfland that uses scx_bpf_select_cpu_and() with 0xff00 as the allowed subset of CPUs: $ vng --cpu 16,sockets=4,cores=4,threads=1 ... $ stress-ng -c 16 ... $ htop ... 0[ 0.0%] 8[||||||||||||||||||||||||100.0%] 1[ 0.0%] 9[||||||||||||||||||||||||100.0%] 2[ 0.0%] 10[||||||||||||||||||||||||100.0%] 3[ 0.0%] 11[||||||||||||||||||||||||100.0%] 4[ 0.0%] 12[||||||||||||||||||||||||100.0%] 5[ 0.0%] 13[||||||||||||||||||||||||100.0%] 6[ 0.0%] 14[||||||||||||||||||||||||100.0%] 7[ 0.0%] 15[||||||||||||||||||||||||100.0%] With scx_bpf_select_cpu_dfl() tasks would be distributed evenly across all the available CPUs. Signed-off-by: Andrea Righi Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/sched/ext.c') diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index ac3fd7a409e9..eae16108f8d6 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -465,6 +465,7 @@ struct sched_ext_ops { * idle CPU tracking and the following helpers become unavailable: * * - scx_bpf_select_cpu_dfl() + * - scx_bpf_select_cpu_and() * - scx_bpf_test_and_clear_cpu_idle() * - scx_bpf_pick_idle_cpu() * -- cgit v1.2.3