From: Tejun Heo <tj@kernel.org>
To: David Vernet <void@manifault.com>,
Andrea Righi <arighi@nvidia.com>,
Changwoo Min <changwoo@igalia.com>
Cc: sched-ext@lists.linux.dev, Emil Tsalapatis <emil@etsalapatis.com>,
linux-kernel@vger.kernel.org, Tejun Heo <tj@kernel.org>
Subject: [PATCH 03/12] sched_ext: Factor out __scx_bpf_now()
Date: Sun, 2 Aug 2026 11:54:38 -1000 [thread overview]
Message-ID: <20260802215447.3134509-4-tj@kernel.org> (raw)
In-Reply-To: <20260802215447.3134509-1-tj@kernel.org>
scx_bpf_now() couples the valid-or-fresh rq clock read to the current rq.
The read is useful for kernel-internal timing against a specific rq,
including a remotely locked one. Factor it out into __scx_bpf_now().
Signed-off-by: Tejun Heo <tj@kernel.org>
---
kernel/sched/ext/ext.c | 59 ++++++++++++++++++-------------------
kernel/sched/ext/internal.h | 1 +
2 files changed, 30 insertions(+), 30 deletions(-)
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 4245a737592a..777ae515c88e 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -10160,6 +10160,27 @@ __bpf_kfunc struct task_struct *scx_bpf_tid_to_task(u64 tid)
return container_of(scx, struct task_struct, scx);
}
+u64 __scx_bpf_now(struct rq *rq)
+{
+ /* the caller must be on @rq's cpu or hold its lock */
+ lockdep_assert((rq == this_rq() && !preemptible()) ||
+ lockdep_is_held(__rq_lockp(rq)));
+
+ if (smp_load_acquire(&rq->scx.flags) & SCX_RQ_CLK_VALID) {
+ /* if the rq clock is valid, use the cached rq clock */
+ return READ_ONCE(rq->scx.clock);
+ } else {
+ /*
+ * Otherwise, return a fresh rq clock.
+ *
+ * The rq clock is updated outside of the rq lock.
+ * In this case, keep the updated rq clock invalid so the next
+ * read outside the rq lock gets a fresh rq clock.
+ */
+ return sched_clock_cpu(cpu_of(rq));
+ }
+}
+
/**
* scx_bpf_now - Returns a high-performance monotonically non-decreasing
* clock for the current CPU. The clock returned is in nanoseconds.
@@ -10190,36 +10211,14 @@ __bpf_kfunc struct task_struct *scx_bpf_tid_to_task(u64 tid)
*/
__bpf_kfunc u64 scx_bpf_now(void)
{
- struct rq *rq;
- u64 clock;
-
- preempt_disable();
-
- rq = this_rq();
- if (smp_load_acquire(&rq->scx.flags) & SCX_RQ_CLK_VALID) {
- /*
- * If the rq clock is valid, use the cached rq clock.
- *
- * Note that scx_bpf_now() is re-entrant between a process
- * context and an interrupt context (e.g., timer interrupt).
- * However, we don't need to consider the race between them
- * because such race is not observable from a caller.
- */
- clock = READ_ONCE(rq->scx.clock);
- } else {
- /*
- * Otherwise, return a fresh rq clock.
- *
- * The rq clock is updated outside of the rq lock.
- * In this case, keep the updated rq clock invalid so the next
- * kfunc call outside the rq lock gets a fresh rq clock.
- */
- clock = sched_clock_cpu(cpu_of(rq));
- }
-
- preempt_enable();
-
- return clock;
+ /*
+ * Note that scx_bpf_now() is re-entrant between a process context and
+ * an interrupt context (e.g., timer interrupt). However, we don't need
+ * to consider the race between them because such race is not observable
+ * from a caller.
+ */
+ guard(preempt)();
+ return __scx_bpf_now(this_rq());
}
static void scx_read_events(struct scx_sched *sch, struct scx_event_stats *events)
diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h
index 1d226aa8a003..a0a2294f1dc2 100644
--- a/kernel/sched/ext/internal.h
+++ b/kernel/sched/ext/internal.h
@@ -1984,6 +1984,7 @@ void scx_flush_dispatch_buf(struct scx_sched *sch, struct rq *rq);
s32 scx_init_dsq(struct scx_dispatch_q *dsq, u64 dsq_id, struct scx_sched *sch);
__printf(2, 3) void scx_dump_line(struct seq_buf *s, const char *fmt, ...);
void scx_kick_cpu(struct scx_sched *sch, s32 cpu, u64 flags);
+u64 __scx_bpf_now(struct rq *rq);
void schedule_dsq_reenq(struct scx_sched *sch, struct scx_dispatch_q *dsq,
u64 reenq_flags, struct rq *locked_rq);
int __scx_init_task(struct scx_sched *sch, struct task_struct *p,
--
2.55.0
next prev parent reply other threads:[~2026-08-02 21:54 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-02 21:54 [PATCHSET v2 sched_ext/for-7.3] sched_ext: Bandwidth-limited rescue execution for stranded tasks Tejun Heo
2026-08-02 21:54 ` [PATCH 01/12] sched_ext: Rename scx_local_or_reject_dsq() to scx_resolve_local_dsq() Tejun Heo
2026-08-02 21:54 ` [PATCH 02/12] sched_ext: Make several ext.c helpers available outside ext.c Tejun Heo
2026-08-02 21:54 ` Tejun Heo [this message]
2026-08-02 21:54 ` [PATCH 04/12] sched_ext: Reject internal enq_flags in the dsq move kfuncs Tejun Heo
2026-08-02 21:54 ` [PATCH 05/12] sched_ext: Make SCX_ENQ_IGNORE_CAPS waive the preemption cap too Tejun Heo
2026-08-02 21:54 ` [PATCH 06/12] sched_ext: Synchronize slice and dsq_vtime writes Tejun Heo
2026-08-02 21:54 ` [PATCH 07/12] sched_ext: Add SCX_TASK_PROTECTED Tejun Heo
2026-08-02 21:54 ` [PATCH 08/12] sched_ext: Add bandwidth-limited rescue execution for stranded tasks Tejun Heo
2026-08-03 8:10 ` Andrea Righi
2026-08-03 18:59 ` [PATCH v2 " Tejun Heo
2026-08-02 21:54 ` [PATCH 09/12] sched_ext: Eject the top rescue consumer on overload Tejun Heo
2026-08-02 21:54 ` [PATCH 10/12] sched_ext: Sync tools autogen enum headers Tejun Heo
2026-08-02 21:54 ` [PATCH 11/12] sched_ext: scx_qmap - Idle-check pinned tasks before direct dispatch Tejun Heo
2026-08-02 21:54 ` [PATCH 12/12] sched_ext: scx_qmap - Add rescue support Tejun Heo
2026-08-03 20:42 ` [PATCHSET v2 sched_ext/for-7.3] sched_ext: Bandwidth-limited rescue execution for stranded tasks Andrea Righi
2026-08-03 21:37 ` Tejun Heo
-- strict thread matches above, loose matches on Subject: below --
2026-08-01 8:51 [PATCHSET " Tejun Heo
2026-08-01 8:51 ` [PATCH 03/12] sched_ext: Factor out __scx_bpf_now() Tejun Heo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260802215447.3134509-4-tj@kernel.org \
--to=tj@kernel.org \
--cc=arighi@nvidia.com \
--cc=changwoo@igalia.com \
--cc=emil@etsalapatis.com \
--cc=linux-kernel@vger.kernel.org \
--cc=sched-ext@lists.linux.dev \
--cc=void@manifault.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.