| Message ID | 20250314094827.167563-7-arighi@nvidia.com (mailing list archive) |
|---|---|
| State | Not Applicable |
| Headers | show |
| Series | [1/8] sched_ext: idle: Honor idle flags in the built-in idle selection policy | expand |
| Context | Check | Description |
|---|---|---|
| netdev/tree_selection | success | Not a local patch |
Hi Andrea, Thank you for the great work! I like it. On 3/14/25 18:45, Andrea Righi wrote: > 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 <arighi@nvidia.com> > --- > kernel/sched/ext.c | 1 + > kernel/sched/ext_idle.c | 41 ++++++++++++++++++++++++ > tools/sched_ext/include/scx/common.bpf.h | 2 ++ > 3 files changed, 44 insertions(+) > > diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c > index f42352e8d889e..343f066c1185d 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() > * > diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c > index 549551bc97a7b..c0de7b64771d4 100644 > --- a/kernel/sched/ext_idle.c > +++ b/kernel/sched/ext_idle.c > @@ -914,6 +914,46 @@ __bpf_kfunc s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, > return prev_cpu; > } > > +/** > + * scx_bpf_select_cpu_and - Pick an idle CPU usable by task @p, > + * prioritizing those in @cpus_allowed > + * @p: task_struct to select a CPU for > + * @prev_cpu: CPU @p was on previously > + * @wake_flags: %SCX_WAKE_* flags > + * @cpus_allowed: cpumask of allowed CPUs > + * @flags: %SCX_PICK_IDLE* flags > + * > + * Can only be called from ops.select_cpu() if the built-in CPU selection is > + * enabled - ops.update_idle() is missing or %SCX_OPS_KEEP_BUILTIN_IDLE is set. > + * @p, @prev_cpu and @wake_flags match ops.select_cpu(). I think that scx_bpf_select_cpu_and () needs to be allowed to call from ops.enqueue(). That is because many scx schedulers have some logic similar to scx_bpf_select_cpu_dfl() to kick an idle CPU proactively. > + * > + * Returns the selected idle CPU, which will be automatically awakened upon > + * returning from ops.select_cpu() and can be used for direct dispatch, or > + * a negative value if no idle CPU is available. > + */ > +__bpf_kfunc s32 scx_bpf_select_cpu_and(struct task_struct *p, s32 prev_cpu, u64 wake_flags, > + const struct cpumask *cpus_allowed, u64 flags) > +{ > + s32 cpu; > + > + if (!ops_cpu_valid(prev_cpu, NULL)) > + return -EINVAL; > + > + if (!check_builtin_idle_enabled()) > + return -EBUSY; > + > + if (!scx_kf_allowed(SCX_KF_SELECT_CPU)) > + return -EPERM; > + > +#ifdef CONFIG_SMP > + cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags, cpus_allowed, flags); > +#else > + cpu = -EBUSY; > +#endif > + > + return cpu; > +} > + > /** > * scx_bpf_get_idle_cpumask_node - Get a referenced kptr to the > * idle-tracking per-CPU cpumask of a target NUMA node. > @@ -1222,6 +1262,7 @@ static const struct btf_kfunc_id_set scx_kfunc_set_idle = { > > BTF_KFUNCS_START(scx_kfunc_ids_select_cpu) > BTF_ID_FLAGS(func, scx_bpf_select_cpu_dfl, KF_RCU) > +BTF_ID_FLAGS(func, scx_bpf_select_cpu_and, KF_RCU) > BTF_KFUNCS_END(scx_kfunc_ids_select_cpu) > > static const struct btf_kfunc_id_set scx_kfunc_set_select_cpu = { > diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h > index dc4333d23189f..6f1da61cf7f17 100644 > --- a/tools/sched_ext/include/scx/common.bpf.h > +++ b/tools/sched_ext/include/scx/common.bpf.h > @@ -48,6 +48,8 @@ static inline void ___vmlinux_h_sanity_check___(void) > > s32 scx_bpf_create_dsq(u64 dsq_id, s32 node) __ksym; > s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool *is_idle) __ksym; > +s32 scx_bpf_select_cpu_and(struct task_struct *p, s32 prev_cpu, u64 wake_flags, > + const struct cpumask *cpus_allowed, u64 flags) __ksym __weak; > void scx_bpf_dsq_insert(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_flags) __ksym __weak; > void scx_bpf_dsq_insert_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym __weak; > u32 scx_bpf_dispatch_nr_slots(void) __ksym; Regards, Changwoo Min
Hi Changwoo, On Sat, Mar 15, 2025 at 10:35:03AM +0900, Changwoo Min wrote: > Hi Andrea, ... > > +/** > > + * scx_bpf_select_cpu_and - Pick an idle CPU usable by task @p, > > + * prioritizing those in @cpus_allowed > > + * @p: task_struct to select a CPU for > > + * @prev_cpu: CPU @p was on previously > > + * @wake_flags: %SCX_WAKE_* flags > > + * @cpus_allowed: cpumask of allowed CPUs > > + * @flags: %SCX_PICK_IDLE* flags > > + * > > + * Can only be called from ops.select_cpu() if the built-in CPU selection is > > + * enabled - ops.update_idle() is missing or %SCX_OPS_KEEP_BUILTIN_IDLE is set. > > + * @p, @prev_cpu and @wake_flags match ops.select_cpu(). > > I think that scx_bpf_select_cpu_and () needs to be allowed to > call from ops.enqueue(). That is because many scx schedulers have > some logic similar to scx_bpf_select_cpu_dfl() to kick an idle > CPU proactively. That's a valid point, it can be a good opportunity to consolidate the logic used in most schedulers, where the same "pick idle CPU" function is called from both ops.select_cpu() and ops.enqueue() and have a unified core API usable from both contexts. I'll extend the scope of this kfunc to include ops.enqueue() in the next version and run some tests with it. Thanks! -Andrea
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index f42352e8d889e..343f066c1185d 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() * diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c index 549551bc97a7b..c0de7b64771d4 100644 --- a/kernel/sched/ext_idle.c +++ b/kernel/sched/ext_idle.c @@ -914,6 +914,46 @@ __bpf_kfunc s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, return prev_cpu; } +/** + * scx_bpf_select_cpu_and - Pick an idle CPU usable by task @p, + * prioritizing those in @cpus_allowed + * @p: task_struct to select a CPU for + * @prev_cpu: CPU @p was on previously + * @wake_flags: %SCX_WAKE_* flags + * @cpus_allowed: cpumask of allowed CPUs + * @flags: %SCX_PICK_IDLE* flags + * + * Can only be called from ops.select_cpu() if the built-in CPU selection is + * enabled - ops.update_idle() is missing or %SCX_OPS_KEEP_BUILTIN_IDLE is set. + * @p, @prev_cpu and @wake_flags match ops.select_cpu(). + * + * Returns the selected idle CPU, which will be automatically awakened upon + * returning from ops.select_cpu() and can be used for direct dispatch, or + * a negative value if no idle CPU is available. + */ +__bpf_kfunc s32 scx_bpf_select_cpu_and(struct task_struct *p, s32 prev_cpu, u64 wake_flags, + const struct cpumask *cpus_allowed, u64 flags) +{ + s32 cpu; + + if (!ops_cpu_valid(prev_cpu, NULL)) + return -EINVAL; + + if (!check_builtin_idle_enabled()) + return -EBUSY; + + if (!scx_kf_allowed(SCX_KF_SELECT_CPU)) + return -EPERM; + +#ifdef CONFIG_SMP + cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags, cpus_allowed, flags); +#else + cpu = -EBUSY; +#endif + + return cpu; +} + /** * scx_bpf_get_idle_cpumask_node - Get a referenced kptr to the * idle-tracking per-CPU cpumask of a target NUMA node. @@ -1222,6 +1262,7 @@ static const struct btf_kfunc_id_set scx_kfunc_set_idle = { BTF_KFUNCS_START(scx_kfunc_ids_select_cpu) BTF_ID_FLAGS(func, scx_bpf_select_cpu_dfl, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_select_cpu_and, KF_RCU) BTF_KFUNCS_END(scx_kfunc_ids_select_cpu) static const struct btf_kfunc_id_set scx_kfunc_set_select_cpu = { diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index dc4333d23189f..6f1da61cf7f17 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -48,6 +48,8 @@ static inline void ___vmlinux_h_sanity_check___(void) s32 scx_bpf_create_dsq(u64 dsq_id, s32 node) __ksym; s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool *is_idle) __ksym; +s32 scx_bpf_select_cpu_and(struct task_struct *p, s32 prev_cpu, u64 wake_flags, + const struct cpumask *cpus_allowed, u64 flags) __ksym __weak; void scx_bpf_dsq_insert(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_flags) __ksym __weak; void scx_bpf_dsq_insert_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym __weak; u32 scx_bpf_dispatch_nr_slots(void) __ksym;
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 <arighi@nvidia.com> --- kernel/sched/ext.c | 1 + kernel/sched/ext_idle.c | 41 ++++++++++++++++++++++++ tools/sched_ext/include/scx/common.bpf.h | 2 ++ 3 files changed, 44 insertions(+)