All of lore.kernel.org
 help / color / mirror / Atom feed
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 sched_ext/for-7.3 20/32] sched_ext: Generalize local-DSQ handling to rq-owned DSQs
Date: Thu,  2 Jul 2026 22:01:47 -1000	[thread overview]
Message-ID: <20260703080159.2314350-21-tj@kernel.org> (raw)
In-Reply-To: <20260703080159.2314350-1-tj@kernel.org>

The local DSQ is synchronized by the containing rq lock rather than its own
dsq->lock. A later patch adds a second such DSQ. In preparation, factor the
"rq owns the lock" test into dsq_is_rq_owned() and rename
local_dsq_post_enq() to rq_owned_post_enq(), taking @rq explicitly.

No behavior change.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext/ext.c | 34 ++++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 4f0d72658fd8..7d8846cea425 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -96,6 +96,17 @@ static atomic_long_t scx_hotplug_seq = ATOMIC_LONG_INIT(0);
 /* Global cursor for the per-CPU tid allocator. Starts at 1; tid 0 is reserved. */
 static atomic64_t scx_tid_cursor = ATOMIC64_INIT(1);
 
+/* is @dsq synchronized by the containing rq lock instead of dsq->lock? */
+static bool dsq_is_rq_owned(struct scx_dispatch_q *dsq)
+{
+	switch (dsq->id) {
+	case SCX_DSQ_LOCAL:
+		return true;
+	default:
+		return false;
+	}
+}
+
 #ifdef CONFIG_EXT_SUB_SCHED
 /*
  * The sub sched being enabled. Used by scx_disable_and_exit_task() to exit
@@ -1263,11 +1274,10 @@ static void call_task_dequeue(struct scx_sched *sch, struct rq *rq,
 	p->scx.flags &= ~SCX_TASK_IN_CUSTODY;
 }
 
-static void local_dsq_post_enq(struct scx_sched *sch, struct scx_dispatch_q *dsq,
-			       struct task_struct *p, u64 enq_flags)
+static void rq_owned_post_enq(struct scx_sched *sch, struct rq *rq,
+			      struct scx_dispatch_q *dsq, struct task_struct *p,
+			      u64 enq_flags)
 {
-	struct rq *rq = container_of(dsq, struct rq, scx.local_dsq);
-
 	call_task_dequeue(sch, rq, p, 0);
 
 	/*
@@ -1327,13 +1337,13 @@ static void scx_dispatch_enqueue(struct scx_sched *sch, struct rq *rq,
 				 struct scx_dispatch_q *dsq, struct task_struct *p,
 				 u64 enq_flags)
 {
-	bool is_local = dsq->id == SCX_DSQ_LOCAL;
+	bool is_rq_owned = dsq_is_rq_owned(dsq);
 
 	WARN_ON_ONCE(p->scx.dsq || !list_empty(&p->scx.dsq_list.node));
 	WARN_ON_ONCE((p->scx.dsq_flags & SCX_TASK_DSQ_ON_PRIQ) ||
 		     !RB_EMPTY_NODE(&p->scx.dsq_priq));
 
-	if (!is_local) {
+	if (!is_rq_owned) {
 		raw_spin_lock_nested(&dsq->lock,
 			(enq_flags & SCX_ENQ_NESTED) ? SINGLE_DEPTH_NESTING : 0);
 
@@ -1428,8 +1438,8 @@ static void scx_dispatch_enqueue(struct scx_sched *sch, struct rq *rq,
 	 * ops_state first, both sides would modify p->scx.flags
 	 * concurrently in a non-atomic way.
 	 */
-	if (is_local) {
-		local_dsq_post_enq(sch, dsq, p, enq_flags);
+	if (is_rq_owned) {
+		rq_owned_post_enq(sch, rq, dsq, p, enq_flags);
 	} else {
 		/*
 		 * Task on global/bypass DSQ: leave custody, task on
@@ -1476,7 +1486,7 @@ static void task_unlink_from_dsq(struct task_struct *p,
 static void scx_dispatch_dequeue(struct rq *rq, struct task_struct *p)
 {
 	struct scx_dispatch_q *dsq = p->scx.dsq;
-	bool is_local = dsq == &rq->scx.local_dsq;
+	bool is_rq_owned = dsq && dsq_is_rq_owned(dsq);
 
 	lockdep_assert_rq_held(rq);
 
@@ -1500,7 +1510,7 @@ static void scx_dispatch_dequeue(struct rq *rq, struct task_struct *p)
 		return;
 	}
 
-	if (!is_local)
+	if (!is_rq_owned)
 		raw_spin_lock(&dsq->lock);
 
 	/*
@@ -1522,7 +1532,7 @@ static void scx_dispatch_dequeue(struct rq *rq, struct task_struct *p)
 	}
 	p->scx.dsq = NULL;
 
-	if (!is_local)
+	if (!is_rq_owned)
 		raw_spin_unlock(&dsq->lock);
 }
 
@@ -2074,7 +2084,7 @@ static void move_local_task_to_local_dsq(struct scx_sched *sch,
 	dsq_inc_nr(dst_dsq, p, enq_flags);
 	p->scx.dsq = dst_dsq;
 
-	local_dsq_post_enq(sch, dst_dsq, p, enq_flags);
+	rq_owned_post_enq(sch, dst_rq, dst_dsq, p, enq_flags);
 }
 
 /**
-- 
2.54.0


  parent reply	other threads:[~2026-07-03  8:02 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-07-03  8:01 [PATCHSET sched_ext/for-7.3] sched_ext: Capability-based CPU delegation for sub-schedulers Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 01/32] sched_ext: Fix premature ops->priv publication in scx_alloc_and_add_sched() Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 02/32] tools/sched_ext: scx - Fix cmask_subset(), cmask_equal() and cmask_weight() Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 03/32] sched_ext: Use READ_ONCE/WRITE_ONCE in cmask word ops and drop _RACY variants Tejun Heo
2026-07-03  8:33   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 04/32] tools/sched_ext: scx_qmap - Use bare u64/u32/s32 integer types Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 05/32] sched_ext: Reject direct slice and dsq_vtime writes for cid-form schedulers Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 06/32] sched_ext: Make scx_bpf_kick_cid() return void Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 07/32] sched_ext: Make the kick machinery per-sched Tejun Heo
2026-07-03  9:02   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 08/32] sched_ext: Add ops.init_cids() to finalize the cid layout before init Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 09/32] sched_ext: Add CID sharding Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 10/32] sched_ext: Add shard boundaries to scx_bpf_cid_override() Tejun Heo
2026-07-03  9:51   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 11/32] sched_ext: Defer scx_sched kobj sysfs add into the enable workfns Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 12/32] sched_ext: Add per-shard scx_sched storage scaffolding Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 13/32] sched_ext: Add scx_cmask_ref for validated arena cmask access Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 14/32] sched_ext: RCU-protect the sub-sched tree's children/sibling lists Tejun Heo
2026-07-03 10:49   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 15/32] sched_ext: Add scx_skip_subtree_pre() Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 16/32] sched_ext: Add per-shard cap delegation for sub-schedulers Tejun Heo
2026-07-03 11:17   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 17/32] sched_ext: Add coalescing sub_caps_updated() notifier " Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 18/32] sched_ext: Maintain per-cpu effective cap copies for single-read checks Tejun Heo
2026-07-03 12:05   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 19/32] sched_ext: Add sub_ecaps_updated() effective-cap change notifier Tejun Heo
2026-07-03 12:25   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` Tejun Heo [this message]
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 21/32] sched_ext: Add reject DSQ for cap-rejected dispatches Tejun Heo
2026-07-03 12:57   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 22/32] sched_ext: Add the SCX_CAP_ENQ_IMMED cap Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 23/32] sched_ext: Assign a unique id to each scheduler instance Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 24/32] sched_ext: Route task slice writes through set_task_slice() Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 25/32] sched_ext: Tie cpu occupancy to SCX_CAP_BASE through the task slice Tejun Heo
2026-07-03 13:34   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 26/32] sched_ext: Add the SCX_CAP_ENQ cap Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 27/32] sched_ext: Gate kicks on SCX_CAP_BASE and preemption on SCX_CAP_PREEMPT Tejun Heo
2026-07-03 14:01   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 28/32] sched_ext: Route ops.update_idle() to sub-schedulers and re-notify owed scheds Tejun Heo
2026-07-03 14:14   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 29/32] sched_ext: Replay ecaps notifications suppressed by bypass Tejun Heo
2026-07-03 14:28   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 30/32] sched_ext: Add scx_bpf_sub_kill() to evict a child sub-scheduler Tejun Heo
2026-07-03 14:45   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 31/32] tools/sched_ext: scx_qmap - Expand hierarchical sub-scheduling Tejun Heo
2026-07-03 14:57   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 32/32] 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=20260703080159.2314350-21-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.