diff options
| author | Ryan Newton <newton@meta.com> | 2025-10-15 11:50:35 -0400 |
|---|---|---|
| committer | Tejun Heo <tj@kernel.org> | 2025-10-15 06:46:25 -1000 |
| commit | 44f5c8ec5b9ad8ed4ade08d727f803b2bb07f1c3 (patch) | |
| tree | 23226ea58376f17c0ae7e357a75e32f5796f04ff /tools | |
| parent | 347ed2d566dabb06c7970fff01129c4f59995ed6 (diff) | |
sched_ext: Add lockless peek operation for DSQs
The builtin DSQ queue data structures are meant to be used by a wide
range of different sched_ext schedulers with different demands on these
data structures. They might be per-cpu with low-contention, or
high-contention shared queues. Unfortunately, DSQs have a coarse-grained
lock around the whole data structure. Without going all the way to a
lock-free, more scalable implementation, a small step we can take to
reduce lock contention is to allow a lockless, small-fixed-cost peek at
the head of the queue.
This change allows certain custom SCX schedulers to cheaply peek at
queues, e.g. during load balancing, before locking them. But it
represents a few extra memory operations to update the pointer each
time the DSQ is modified, including a memory barrier on ARM so the write
appears correctly ordered.
This commit adds a first_task pointer field which is updated
atomically when the DSQ is modified, and allows any thread to peek at
the head of the queue without holding the lock.
Signed-off-by: Ryan Newton <newton@meta.com>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Reviewed-by: Christian Loehle <christian.loehle@arm.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Diffstat (limited to 'tools')
| -rw-r--r-- | tools/sched_ext/include/scx/common.bpf.h | 1 | ||||
| -rw-r--r-- | tools/sched_ext/include/scx/compat.bpf.h | 18 |
2 files changed, 19 insertions, 0 deletions
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index eb3c99445cb3..e65b1eb668ea 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -74,6 +74,7 @@ u32 scx_bpf_reenqueue_local(void) __ksym; void scx_bpf_kick_cpu(s32 cpu, u64 flags) __ksym; s32 scx_bpf_dsq_nr_queued(u64 dsq_id) __ksym; void scx_bpf_destroy_dsq(u64 dsq_id) __ksym; +struct task_struct *scx_bpf_dsq_peek(u64 dsq_id) __ksym __weak; int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, u64 flags) __ksym __weak; struct task_struct *bpf_iter_scx_dsq_next(struct bpf_iter_scx_dsq *it) __ksym __weak; void bpf_iter_scx_dsq_destroy(struct bpf_iter_scx_dsq *it) __ksym __weak; diff --git a/tools/sched_ext/include/scx/compat.bpf.h b/tools/sched_ext/include/scx/compat.bpf.h index e487c10b5e07..619a16f0d39a 100644 --- a/tools/sched_ext/include/scx/compat.bpf.h +++ b/tools/sched_ext/include/scx/compat.bpf.h @@ -26,6 +26,24 @@ int bpf_cpumask_populate(struct cpumask *dst, void *src, size_t src__sz) __ksym (bpf_ksym_exists(bpf_cpumask_populate) ? \ (bpf_cpumask_populate(cpumask, src, size__sz)) : -EOPNOTSUPP) +/* + * v6.19: Introduce lockless peek API for user DSQs. + * + * Preserve the following macro until v6.21. + */ +static inline struct task_struct *__COMPAT_scx_bpf_dsq_peek(u64 dsq_id) +{ + struct task_struct *p = NULL; + struct bpf_iter_scx_dsq it; + + if (bpf_ksym_exists(scx_bpf_dsq_peek)) + return scx_bpf_dsq_peek(dsq_id); + if (!bpf_iter_scx_dsq_new(&it, dsq_id, 0)) + p = bpf_iter_scx_dsq_next(&it); + bpf_iter_scx_dsq_destroy(&it); + return p; +} + /** * __COMPAT_is_enq_cpu_selected - Test if SCX_ENQ_CPU_SELECTED is on * in a compatible way. We will preserve this __COMPAT helper until v6.16. |