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 v3 sched_ext/for-7.3 31/36] sched_ext: Authorize remote-move inserts against the placing scheduler
Date: Mon, 6 Jul 2026 14:12:24 -1000 [thread overview]
Message-ID: <20260707001229.1410929-32-tj@kernel.org> (raw)
In-Reply-To: <20260707001229.1410929-1-tj@kernel.org>
scx_local_or_reject_dsq() authorizes a local-DSQ insert against the caps
of the scheduler doing the insert. On the consume/dispatch paths that is
the scheduler running balance_one(), passed down through
scx_consume_dispatch_q() and move_local_task_to_local_dsq(), so the check
is correct.
The remote-move path loses it. move_remote_task_to_local_dsq()
re-activates @p on the destination rq through enqueue_task_scx(), which
reconstructs the scheduler from the task, i.e. @p's owner. When an
ancestor places a descendant's task - e.g. draining a bypassed
sub-scheduler - the owner is a sub-scheduler of the placer, so
authorizing against the owner checks a narrower cap set and can
spuriously reject a task the placer is entitled to run.
Carry the placing scheduler across the activate_task() boundary the same
way enq_flags already are, via a per-rq field set only for the duration
of the re-activation, and have scx_local_or_reject_dsq() authorize
against it. The placer's caps are a superset of the owner's, so this
admits what the placer may run and keeps rejecting what it may not.
Signed-off-by: Tejun Heo <tj@kernel.org>
---
kernel/sched/ext/ext.c | 27 +++++++++++++++------------
kernel/sched/ext/sub.c | 9 +++++++--
kernel/sched/sched.h | 3 ++-
3 files changed, 24 insertions(+), 15 deletions(-)
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index c6e9a26213f4..1f0c371a8df7 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -2248,7 +2248,8 @@ static void move_local_task_to_local_dsq(struct scx_sched *sch,
*
* Move @p which is currently on @src_rq to @dst_rq's local DSQ.
*/
-static void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags,
+static void move_remote_task_to_local_dsq(struct scx_sched *sch,
+ struct task_struct *p, u64 enq_flags,
struct rq *src_rq, struct rq *dst_rq)
{
lockdep_assert_rq_held(src_rq);
@@ -2265,15 +2266,19 @@ static void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags,
raw_spin_rq_lock(dst_rq);
/*
- * We want to pass scx-specific enq_flags but activate_task() will
- * truncate the upper 32 bit. As we own @rq, we can pass them through
- * @rq->scx.remote_activate_enq_flags instead.
+ * activate_task() below truncates enq_flags to 32 bits and re-derives
+ * @p's owner, dropping our scx flags and the placing @sch. We own @rq,
+ * so stash both across the call. The enqueue reads them back, keeping
+ * the scx flags and checking caps against the placer, not the owner.
*/
WARN_ON_ONCE(!cpumask_test_cpu(cpu_of(dst_rq), p->cpus_ptr));
- WARN_ON_ONCE(dst_rq->scx.remote_activate_enq_flags);
+ WARN_ON_ONCE(dst_rq->scx.remote_activate_enq_flags ||
+ dst_rq->scx.remote_activate_sch);
dst_rq->scx.remote_activate_enq_flags = enq_flags;
+ dst_rq->scx.remote_activate_sch = sch;
activate_task(dst_rq, p, 0);
dst_rq->scx.remote_activate_enq_flags = 0;
+ dst_rq->scx.remote_activate_sch = NULL;
}
/*
@@ -2402,14 +2407,14 @@ static bool unlink_dsq_and_lock_src_rq(struct task_struct *p,
!WARN_ON_ONCE(src_rq != task_rq(p));
}
-static bool consume_remote_task(struct rq *this_rq,
+static bool consume_remote_task(struct scx_sched *sch, struct rq *this_rq,
struct task_struct *p, u64 enq_flags,
struct scx_dispatch_q *dsq, struct rq *src_rq)
{
raw_spin_rq_unlock(this_rq);
if (unlink_dsq_and_lock_src_rq(p, dsq, src_rq)) {
- move_remote_task_to_local_dsq(p, enq_flags, src_rq, this_rq);
+ move_remote_task_to_local_dsq(sch, p, enq_flags, src_rq, this_rq);
return true;
} else {
raw_spin_rq_unlock(src_rq);
@@ -2471,8 +2476,7 @@ static struct rq *move_task_between_dsqs(struct scx_sched *sch,
raw_spin_unlock(&src_dsq->lock);
} else {
raw_spin_unlock(&src_dsq->lock);
- move_remote_task_to_local_dsq(p, enq_flags,
- src_rq, dst_rq);
+ move_remote_task_to_local_dsq(sch, p, enq_flags, src_rq, dst_rq);
}
} else {
/*
@@ -2525,7 +2529,7 @@ bool scx_consume_dispatch_q(struct scx_sched *sch, struct rq *rq,
}
if (task_can_run_on_remote_rq(sch, p, rq, false)) {
- if (likely(consume_remote_task(rq, p, enq_flags, dsq, task_rq)))
+ if (likely(consume_remote_task(sch, rq, p, enq_flags, dsq, task_rq)))
return true;
goto retry;
}
@@ -2619,8 +2623,7 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
scx_dispatch_enqueue(sch, src_rq, find_global_dsq(sch, task_cpu(p)),
p, enq_flags | SCX_ENQ_GDSQ_FALLBACK);
} else {
- move_remote_task_to_local_dsq(p, enq_flags,
- src_rq, dst_rq);
+ move_remote_task_to_local_dsq(sch, p, enq_flags, src_rq, dst_rq);
/* task has been moved to dst_rq, which is now locked */
locked_rq = dst_rq;
}
diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c
index bd133ad014a0..fac596cf350f 100644
--- a/kernel/sched/ext/sub.c
+++ b/kernel/sched/ext/sub.c
@@ -237,12 +237,17 @@ struct scx_dispatch_q *scx_local_or_reject_dsq(struct scx_sched *sch, struct rq
struct task_struct *p, u64 *enq_flags)
{
s32 cid = __scx_cpu_to_cid(cpu_of(rq));
+ struct scx_sched *asch = rq->scx.remote_activate_sch ?: sch;
u64 needed = scx_caps_for_enq(*enq_flags);
u64 missing;
+ /*
+ * On a remote activation the scheduling sched (@asch) differs from
+ * @p's owner (@sch). Check caps against the scheduling sched.
+ */
if (*enq_flags & SCX_ENQ_PREEMPT)
- needed |= scx_caps_for_preempt(sch, rq);
- missing = scx_missing_caps(sch, cpu_of(rq), needed);
+ needed |= scx_caps_for_preempt(asch, rq);
+ missing = scx_missing_caps(asch, cpu_of(rq), needed);
/* requirements met */
if (likely(!missing))
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c0a4699a6c0a..cdd21c814008 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -800,8 +800,9 @@ struct scx_rq {
struct list_head runnable_list; /* runnable tasks on this rq */
struct list_head ddsp_deferred_locals; /* deferred ddsps from enq */
unsigned long ops_qseq;
- /* see move_remote_task_to_local_dsq() */
+ /* both stashed across the activate_task() in move_remote_task_to_local_dsq() */
u64 remote_activate_enq_flags;
+ struct scx_sched *remote_activate_sch;
u32 nr_running;
u32 cpuperf_target; /* [0, SCHED_CAPACITY_SCALE] */
bool in_select_cpu;
--
2.54.0
next prev parent reply other threads:[~2026-07-07 0:13 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-07 0:11 [PATCHSET v3 sched_ext/for-7.3] sched_ext: Capability-based CPU delegation for sub-schedulers Tejun Heo
2026-07-07 0:11 ` [PATCH v3 sched_ext/for-7.3 01/36] sched_ext: Add SCX_CALL_CID_OP_TASK() for cid-form op dispatch Tejun Heo
2026-07-07 0:11 ` [PATCH v3 sched_ext/for-7.3 02/36] sched_ext: Rename extra_enq_flags to remote_activate_enq_flags Tejun Heo
2026-07-07 0:11 ` [PATCH v3 sched_ext/for-7.3 03/36] sched_ext: Fix premature ops->priv publication in scx_alloc_and_add_sched() Tejun Heo
2026-07-07 0:11 ` [PATCH v3 sched_ext/for-7.3 04/36] tools/sched_ext: scx - Fix cmask_subset(), cmask_equal() and cmask_weight() Tejun Heo
2026-07-07 0:11 ` [PATCH v3 sched_ext/for-7.3 05/36] sched_ext: Use READ_ONCE/WRITE_ONCE in cmask word ops and drop _RACY variants Tejun Heo
2026-07-07 0:11 ` [PATCH v3 sched_ext/for-7.3 06/36] tools/sched_ext: scx_qmap - Use bare u64/u32/s32 integer types Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 07/36] sched_ext: Reject direct slice and dsq_vtime writes for cid-form schedulers Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 08/36] sched_ext: Make scx_bpf_kick_cid() return void Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 09/36] sched_ext: Make the kick machinery per-sched Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 10/36] sched_ext: Add ops.init_cids() to finalize the cid layout before init Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 11/36] sched_ext: Add CID sharding Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 12/36] sched_ext: Add shard boundaries to scx_bpf_cid_override() Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 13/36] sched_ext: Defer scx_sched kobj sysfs add into the enable workfns Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 14/36] sched_ext: Add per-shard scx_sched storage scaffolding Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 15/36] sched_ext: Add scx_cmask_ref for validated arena cmask access Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 16/36] sched_ext: Build the set_cmask scratch from trusted geometry Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 17/36] sched_ext: RCU-protect the sub-sched tree's children/sibling lists Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 18/36] sched_ext: Add scx_skip_subtree_pre() Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 19/36] sched_ext: Add per-shard cap delegation for sub-schedulers Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 20/36] sched_ext: Add coalescing sub_caps_updated() notifier " Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 21/36] sched_ext: Maintain per-cpu effective cap copies for single-read checks Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 22/36] sched_ext: Add sub_ecaps_updated() effective-cap change notifier Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 23/36] sched_ext: Generalize local-DSQ handling to rq-owned DSQs Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 24/36] sched_ext: Add reject DSQ for cap-rejected dispatches Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 25/36] sched_ext: Add the SCX_CAP_ENQ_IMMED cap Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 26/36] sched_ext: Assign a unique id to each scheduler instance Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 27/36] sched_ext: Route task slice writes through set_task_slice() Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 28/36] sched_ext: Tie cpu occupancy to SCX_CAP_BASE through the task slice Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 29/36] sched_ext: Add the SCX_CAP_ENQ cap Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 30/36] sched_ext: Gate kicks on SCX_CAP_BASE and preemption on SCX_CAP_PREEMPT Tejun Heo
2026-07-07 0:12 ` Tejun Heo [this message]
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 32/36] sched_ext: Route ops.update_idle() to sub-schedulers and re-notify owed scheds Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 33/36] sched_ext: Replay ecaps notifications suppressed by bypass Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 34/36] sched_ext: Add scx_bpf_sub_kill() to evict a child sub-scheduler Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 35/36] tools/sched_ext: scx_qmap - Expand hierarchical sub-scheduling Tejun Heo
2026-07-07 0:12 ` [PATCH v3 sched_ext/for-7.3 36/36] tools/sched_ext: scx_qmap - Add sub-sched cap fault injection 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=20260707001229.1410929-32-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox