diff options
| author | Andrea Righi <arighi@nvidia.com> | 2025-02-14 20:40:05 +0100 |
|---|---|---|
| committer | Tejun Heo <tj@kernel.org> | 2025-02-16 06:52:20 -1000 |
| commit | 0aaaf89df86da28fa4928faa55a529beac1d6cab (patch) | |
| tree | d7bd7d003bcc123659cc30b6295b2c05c6ce27c7 /kernel/sched/ext.c | |
| parent | d73249f88743df63a2bdce0e3153369963113710 (diff) | |
sched_ext: idle: Introduce SCX_OPS_BUILTIN_IDLE_PER_NODE
Add the new scheduler flag SCX_OPS_BUILTIN_IDLE_PER_NODE, which allows
BPF schedulers to select between using a global flat idle cpumask or
multiple per-node cpumasks.
This only introduces the flag and the mechanism to enable/disable this
feature without affecting any scheduling behavior.
Cc: Yury Norov [NVIDIA] <yury.norov@gmail.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
Reviewed-by: Yury Norov [NVIDIA] <yury.norov@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Diffstat (limited to 'kernel/sched/ext.c')
| -rw-r--r-- | kernel/sched/ext.c | 21 |
1 files changed, 19 insertions, 2 deletions
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 7c17e05ed15b..330a359d7930 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -155,6 +155,12 @@ enum scx_ops_flags { SCX_OPS_ALLOW_QUEUED_WAKEUP = 1LLU << 5, /* + * If set, enable per-node idle cpumasks. If clear, use a single global + * flat idle cpumask. + */ + SCX_OPS_BUILTIN_IDLE_PER_NODE = 1LLU << 6, + + /* * CPU cgroup support flags */ SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* cpu.weight */ @@ -165,6 +171,7 @@ enum scx_ops_flags { SCX_OPS_ENQ_MIGRATION_DISABLED | SCX_OPS_ALLOW_QUEUED_WAKEUP | SCX_OPS_SWITCH_PARTIAL | + SCX_OPS_BUILTIN_IDLE_PER_NODE | SCX_OPS_HAS_CGROUP_WEIGHT, }; @@ -3427,7 +3434,7 @@ static void handle_hotplug(struct rq *rq, bool online) atomic_long_inc(&scx_hotplug_seq); if (scx_enabled()) - scx_idle_update_selcpu_topology(); + scx_idle_update_selcpu_topology(&scx_ops); if (online && SCX_HAS_OP(cpu_online)) SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, cpu); @@ -5228,6 +5235,16 @@ static int validate_ops(const struct sched_ext_ops *ops) return -EINVAL; } + /* + * SCX_OPS_BUILTIN_IDLE_PER_NODE requires built-in CPU idle + * selection policy to be enabled. + */ + if ((ops->flags & SCX_OPS_BUILTIN_IDLE_PER_NODE) && + (ops->update_idle && !(ops->flags & SCX_OPS_KEEP_BUILTIN_IDLE))) { + scx_ops_error("SCX_OPS_BUILTIN_IDLE_PER_NODE requires CPU idle selection enabled"); + return -EINVAL; + } + return 0; } @@ -5352,7 +5369,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) static_branch_enable_cpuslocked(&scx_has_op[i]); check_hotplug_seq(ops); - scx_idle_update_selcpu_topology(); + scx_idle_update_selcpu_topology(ops); cpus_read_unlock(); |