[PATCHSET v5 sched_ext/for-6.11] sched_ext: Implement DSQ iterator

[PATCHSET v5 sched_ext/for-6.11] sched_ext: Implement DSQ iterator

[Tejun Heo]

DSQs are very opaque in the consumption path. The BPF scheduler has no way
of knowing which tasks are being considered and which is picked. This
patchset adds BPF DSQ iterator to allow BPF schedulers more flexibility in
how DSQs are used. See the 0002 patch for more details.

Changes from v4 (https://lore.kernel.org/all/Zn9oEjsm_1aWb35J@slm.duckdns.org/):

- Comment added to clarify use of naked list_empty(&dsq->list) test.

- scx_qmap changes separated into its own patch (0003).

There are no functional changes since v4. I'll apply these patches to
sched_ext/for-6.11 with the outstanding acks.

This patchset contains the following three patches:

 0001-sched_ext-Take-out-priq-and-flags-from-scx_dsq_node.patch
 0002-sched_ext-Implement-DSQ-iterator.patch
 0003-sched_ext-scx_qmap-Add-an-example-usage-of-DSQ-itera.patch

and is also availalbe in the following git branch:

 git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext.git scx-dsq-iter-v5

diffstat follows. Thanks.

 include/linux/sched/ext.h                |   13 +-
 init/init_task.c                         |    2
 kernel/sched/ext.c                       |  244 ++++++++++++++++++++++++++++++++++++++++++++++-------
 tools/sched_ext/include/scx/common.bpf.h |    3
 tools/sched_ext/scx_qmap.bpf.c           |   25 +++++
 tools/sched_ext/scx_qmap.c               |    8 +
 6 files changed, 259 insertions(+), 36 deletions(-)

--
tejun

[PATCH 1/3] sched_ext: Take out ->priq and ->flags from scx_dsq_node

[Tejun Heo]

struct scx_dsq_node contains two data structure nodes to link the containing
task to a DSQ and a flags field that is protected by the lock of the
associated DSQ. One reason why they are grouped into a struct is to use the
type independently as a cursor node when iterating tasks on a DSQ. However,
when iterating, the cursor only needs to be linked on the FIFO list and the
rb_node part ends up inflating the size of the iterator data structure
unnecessarily making it potentially too expensive to place it on stack.

Take ->priq and ->flags out of scx_dsq_node and put them in sched_ext_entity
as ->dsq_priq and ->dsq_flags, respectively. scx_dsq_node is renamed to
scx_dsq_list_node and the field names are renamed accordingly. This will
help implementing DSQ task iterator that can be allocated on stack.

No functional change intended.

Signed-off-by: Tejun Heo <tj@kernel.org>
Suggested-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: David Vernet <void@manifault.com>
---
 include/linux/sched/ext.h | 10 ++++----
 init/init_task.c          |  2 +-
 kernel/sched/ext.c        | 54 +++++++++++++++++++--------------------
 3 files changed, 33 insertions(+), 33 deletions(-)

diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index fe9a67ffe6b1..eb9cfd18a923 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -121,10 +121,8 @@ enum scx_kf_mask {
 	__SCX_KF_TERMINAL	= SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST,
 };
 
-struct scx_dsq_node {
-	struct list_head	list;		/* dispatch order */
-	struct rb_node		priq;		/* p->scx.dsq_vtime order */
-	u32			flags;		/* SCX_TASK_DSQ_* flags */
+struct scx_dsq_list_node {
+	struct list_head	node;
 };
 
 /*
@@ -133,7 +131,9 @@ struct scx_dsq_node {
  */
 struct sched_ext_entity {
 	struct scx_dispatch_q	*dsq;
-	struct scx_dsq_node	dsq_node;	/* protected by dsq lock */
+	struct scx_dsq_list_node dsq_list;	/* dispatch order */
+	struct rb_node		dsq_priq;	/* p->scx.dsq_vtime order */
+	u32			dsq_flags;	/* protected by DSQ lock */
 	u32			flags;		/* protected by rq lock */
 	u32			weight;
 	s32			sticky_cpu;
diff --git a/init/init_task.c b/init/init_task.c
index 5726b3a0eea9..e222722e790b 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -102,7 +102,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
 #endif
 #ifdef CONFIG_SCHED_CLASS_EXT
 	.scx		= {
-		.dsq_node.list	= LIST_HEAD_INIT(init_task.scx.dsq_node.list),
+		.dsq_list.node	= LIST_HEAD_INIT(init_task.scx.dsq_list.node),
 		.sticky_cpu	= -1,
 		.holding_cpu	= -1,
 		.runnable_node	= LIST_HEAD_INIT(init_task.scx.runnable_node),
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index b7fad9bf27ae..069c2f33883c 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1360,9 +1360,9 @@ static bool scx_dsq_priq_less(struct rb_node *node_a,
 			      const struct rb_node *node_b)
 {
 	const struct task_struct *a =
-		container_of(node_a, struct task_struct, scx.dsq_node.priq);
+		container_of(node_a, struct task_struct, scx.dsq_priq);
 	const struct task_struct *b =
-		container_of(node_b, struct task_struct, scx.dsq_node.priq);
+		container_of(node_b, struct task_struct, scx.dsq_priq);
 
 	return time_before64(a->scx.dsq_vtime, b->scx.dsq_vtime);
 }
@@ -1378,9 +1378,9 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p,
 {
 	bool is_local = dsq->id == SCX_DSQ_LOCAL;
 
-	WARN_ON_ONCE(p->scx.dsq || !list_empty(&p->scx.dsq_node.list));
-	WARN_ON_ONCE((p->scx.dsq_node.flags & SCX_TASK_DSQ_ON_PRIQ) ||
-		     !RB_EMPTY_NODE(&p->scx.dsq_node.priq));
+	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) {
 		raw_spin_lock(&dsq->lock);
@@ -1419,21 +1419,21 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p,
 			scx_ops_error("DSQ ID 0x%016llx already had FIFO-enqueued tasks",
 				      dsq->id);
 
-		p->scx.dsq_node.flags |= SCX_TASK_DSQ_ON_PRIQ;
-		rb_add(&p->scx.dsq_node.priq, &dsq->priq, scx_dsq_priq_less);
+		p->scx.dsq_flags |= SCX_TASK_DSQ_ON_PRIQ;
+		rb_add(&p->scx.dsq_priq, &dsq->priq, scx_dsq_priq_less);
 
 		/*
 		 * Find the previous task and insert after it on the list so
 		 * that @dsq->list is vtime ordered.
 		 */
-		rbp = rb_prev(&p->scx.dsq_node.priq);
+		rbp = rb_prev(&p->scx.dsq_priq);
 		if (rbp) {
 			struct task_struct *prev =
 				container_of(rbp, struct task_struct,
-					     scx.dsq_node.priq);
-			list_add(&p->scx.dsq_node.list, &prev->scx.dsq_node.list);
+					     scx.dsq_priq);
+			list_add(&p->scx.dsq_list.node, &prev->scx.dsq_list.node);
 		} else {
-			list_add(&p->scx.dsq_node.list, &dsq->list);
+			list_add(&p->scx.dsq_list.node, &dsq->list);
 		}
 	} else {
 		/* a FIFO DSQ shouldn't be using PRIQ enqueuing */
@@ -1442,9 +1442,9 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p,
 				      dsq->id);
 
 		if (enq_flags & (SCX_ENQ_HEAD | SCX_ENQ_PREEMPT))
-			list_add(&p->scx.dsq_node.list, &dsq->list);
+			list_add(&p->scx.dsq_list.node, &dsq->list);
 		else
-			list_add_tail(&p->scx.dsq_node.list, &dsq->list);
+			list_add_tail(&p->scx.dsq_list.node, &dsq->list);
 	}
 
 	dsq_mod_nr(dsq, 1);
@@ -1487,18 +1487,18 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p,
 static void task_unlink_from_dsq(struct task_struct *p,
 				 struct scx_dispatch_q *dsq)
 {
-	if (p->scx.dsq_node.flags & SCX_TASK_DSQ_ON_PRIQ) {
-		rb_erase(&p->scx.dsq_node.priq, &dsq->priq);
-		RB_CLEAR_NODE(&p->scx.dsq_node.priq);
-		p->scx.dsq_node.flags &= ~SCX_TASK_DSQ_ON_PRIQ;
+	if (p->scx.dsq_flags & SCX_TASK_DSQ_ON_PRIQ) {
+		rb_erase(&p->scx.dsq_priq, &dsq->priq);
+		RB_CLEAR_NODE(&p->scx.dsq_priq);
+		p->scx.dsq_flags &= ~SCX_TASK_DSQ_ON_PRIQ;
 	}
 
-	list_del_init(&p->scx.dsq_node.list);
+	list_del_init(&p->scx.dsq_list.node);
 }
 
 static bool task_linked_on_dsq(struct task_struct *p)
 {
-	return !list_empty(&p->scx.dsq_node.list);
+	return !list_empty(&p->scx.dsq_list.node);
 }
 
 static void dispatch_dequeue(struct rq *rq, struct task_struct *p)
@@ -1523,8 +1523,8 @@ static void dispatch_dequeue(struct rq *rq, struct task_struct *p)
 		raw_spin_lock(&dsq->lock);
 
 	/*
-	 * Now that we hold @dsq->lock, @p->holding_cpu and @p->scx.dsq_node
-	 * can't change underneath us.
+	 * Now that we hold @dsq->lock, @p->holding_cpu and @p->scx.dsq_* can't
+	 * change underneath us.
 	*/
 	if (p->scx.holding_cpu < 0) {
 		/* @p must still be on @dsq, dequeue */
@@ -2034,7 +2034,7 @@ static void consume_local_task(struct rq *rq, struct scx_dispatch_q *dsq,
 	/* @dsq is locked and @p is on this rq */
 	WARN_ON_ONCE(p->scx.holding_cpu >= 0);
 	task_unlink_from_dsq(p, dsq);
-	list_add_tail(&p->scx.dsq_node.list, &rq->scx.local_dsq.list);
+	list_add_tail(&p->scx.dsq_list.node, &rq->scx.local_dsq.list);
 	dsq_mod_nr(dsq, -1);
 	dsq_mod_nr(&rq->scx.local_dsq, 1);
 	p->scx.dsq = &rq->scx.local_dsq;
@@ -2109,7 +2109,7 @@ static bool consume_dispatch_q(struct rq *rq, struct rq_flags *rf,
 
 	raw_spin_lock(&dsq->lock);
 
-	list_for_each_entry(p, &dsq->list, scx.dsq_node.list) {
+	list_for_each_entry(p, &dsq->list, scx.dsq_list.node) {
 		struct rq *task_rq = task_rq(p);
 
 		if (rq == task_rq) {
@@ -2628,7 +2628,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p)
 static struct task_struct *first_local_task(struct rq *rq)
 {
 	return list_first_entry_or_null(&rq->scx.local_dsq.list,
-					struct task_struct, scx.dsq_node.list);
+					struct task_struct, scx.dsq_list.node);
 }
 
 static struct task_struct *pick_next_task_scx(struct rq *rq)
@@ -3309,8 +3309,8 @@ void init_scx_entity(struct sched_ext_entity *scx)
 	 */
 	memset(scx, 0, offsetof(struct sched_ext_entity, tasks_node));
 
-	INIT_LIST_HEAD(&scx->dsq_node.list);
-	RB_CLEAR_NODE(&scx->dsq_node.priq);
+	INIT_LIST_HEAD(&scx->dsq_list.node);
+	RB_CLEAR_NODE(&scx->dsq_priq);
 	scx->sticky_cpu = -1;
 	scx->holding_cpu = -1;
 	INIT_LIST_HEAD(&scx->runnable_node);
@@ -4160,7 +4160,7 @@ static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx,
 		  jiffies_delta_msecs(p->scx.runnable_at, dctx->at_jiffies));
 	dump_line(s, "      scx_state/flags=%u/0x%x dsq_flags=0x%x ops_state/qseq=%lu/%lu",
 		  scx_get_task_state(p), p->scx.flags & ~SCX_TASK_STATE_MASK,
-		  p->scx.dsq_node.flags, ops_state & SCX_OPSS_STATE_MASK,
+		  p->scx.dsq_flags, ops_state & SCX_OPSS_STATE_MASK,
 		  ops_state >> SCX_OPSS_QSEQ_SHIFT);
 	dump_line(s, "      sticky/holding_cpu=%d/%d dsq_id=%s dsq_vtime=%llu",
 		  p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf,
-- 
2.45.2

[PATCH 2/3] sched_ext: Implement DSQ iterator

[Tejun Heo]

DSQs are very opaque in the consumption path. The BPF scheduler has no way
of knowing which tasks are being considered and which is picked. This patch
adds BPF DSQ iterator.

- Allows iterating tasks queued on a DSQ in the dispatch order or reverse
  from anywhere using bpf_for_each(scx_dsq) or calling the iterator kfuncs
  directly.

- Has ordering guarantee where only tasks which were already queued when the
  iteration started are visible and consumable during the iteration.

v5: - Add a comment to the naked list_empty(&dsq->list) test in
      consume_dispatch_q() to explain the reasoning behind the lockless test
      and by extension why nldsq_next_task() isn't used there.

    - scx_qmap changes separated into its own patch.

v4: - bpf_iter_scx_dsq_new() declaration in common.bpf.h was using the wrong
      type for the last argument (bool rev instead of u64 flags). Fix it.

v3: - Alexei pointed out that the iterator is too big to allocate on stack.
      Added a prep patch to reduce the size of the cursor. Now
      bpf_iter_scx_dsq is 48 bytes and bpf_iter_scx_dsq_kern is 40 bytes on
      64bit.

    - u32_before() comparison factored out.

v2: - scx_bpf_consume_task() is separated out into a separate patch.

    - DSQ seq and iter flags don't need to be u64. Use u32.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: David Vernet <dvernet@meta.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: bpf@vger.kernel.org
---
 include/linux/sched/ext.h                |   3 +
 kernel/sched/ext.c                       | 192 ++++++++++++++++++++++-
 tools/sched_ext/include/scx/common.bpf.h |   3 +
 3 files changed, 196 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index eb9cfd18a923..593d2f4909dd 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -61,6 +61,7 @@ struct scx_dispatch_q {
 	struct list_head	list;	/* tasks in dispatch order */
 	struct rb_root		priq;	/* used to order by p->scx.dsq_vtime */
 	u32			nr;
+	u32			seq;	/* used by BPF iter */
 	u64			id;
 	struct rhash_head	hash_node;
 	struct llist_node	free_node;
@@ -123,6 +124,7 @@ enum scx_kf_mask {
 
 struct scx_dsq_list_node {
 	struct list_head	node;
+	bool			is_bpf_iter_cursor;
 };
 
 /*
@@ -133,6 +135,7 @@ struct sched_ext_entity {
 	struct scx_dispatch_q	*dsq;
 	struct scx_dsq_list_node dsq_list;	/* dispatch order */
 	struct rb_node		dsq_priq;	/* p->scx.dsq_vtime order */
+	u32			dsq_seq;
 	u32			dsq_flags;	/* protected by DSQ lock */
 	u32			flags;		/* protected by rq lock */
 	u32			weight;
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 069c2f33883c..f16d72d72635 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -926,6 +926,11 @@ static u32 highest_bit(u32 flags)
 	return ((u64)1 << bit) >> 1;
 }
 
+static bool u32_before(u32 a, u32 b)
+{
+	return (s32)(a - b) < 0;
+}
+
 /*
  * scx_kf_mask enforcement. Some kfuncs can only be called from specific SCX
  * ops. When invoking SCX ops, SCX_CALL_OP[_RET]() should be used to indicate
@@ -1066,6 +1071,73 @@ static __always_inline bool scx_kf_allowed_on_arg_tasks(u32 mask,
 	return true;
 }
 
+/**
+ * nldsq_next_task - Iterate to the next task in a non-local DSQ
+ * @dsq: user dsq being interated
+ * @cur: current position, %NULL to start iteration
+ * @rev: walk backwards
+ *
+ * Returns %NULL when iteration is finished.
+ */
+static struct task_struct *nldsq_next_task(struct scx_dispatch_q *dsq,
+					   struct task_struct *cur, bool rev)
+{
+	struct list_head *list_node;
+	struct scx_dsq_list_node *dsq_lnode;
+
+	lockdep_assert_held(&dsq->lock);
+
+	if (cur)
+		list_node = &cur->scx.dsq_list.node;
+	else
+		list_node = &dsq->list;
+
+	/* find the next task, need to skip BPF iteration cursors */
+	do {
+		if (rev)
+			list_node = list_node->prev;
+		else
+			list_node = list_node->next;
+
+		if (list_node == &dsq->list)
+			return NULL;
+
+		dsq_lnode = container_of(list_node, struct scx_dsq_list_node,
+					 node);
+	} while (dsq_lnode->is_bpf_iter_cursor);
+
+	return container_of(dsq_lnode, struct task_struct, scx.dsq_list);
+}
+
+#define nldsq_for_each_task(p, dsq)						\
+	for ((p) = nldsq_next_task((dsq), NULL, false); (p);			\
+	     (p) = nldsq_next_task((dsq), (p), false))
+
+
+/*
+ * BPF DSQ iterator. Tasks in a non-local DSQ can be iterated in [reverse]
+ * dispatch order. BPF-visible iterator is opaque and larger to allow future
+ * changes without breaking backward compatibility. Can be used with
+ * bpf_for_each(). See bpf_iter_scx_dsq_*().
+ */
+enum scx_dsq_iter_flags {
+	/* iterate in the reverse dispatch order */
+	SCX_DSQ_ITER_REV		= 1U << 0,
+
+	__SCX_DSQ_ITER_ALL_FLAGS	= SCX_DSQ_ITER_REV,
+};
+
+struct bpf_iter_scx_dsq_kern {
+	struct scx_dsq_list_node	cursor;
+	struct scx_dispatch_q		*dsq;
+	u32				dsq_seq;
+	u32				flags;
+} __attribute__((aligned(8)));
+
+struct bpf_iter_scx_dsq {
+	u64				__opaque[6];
+} __attribute__((aligned(8)));
+
 
 /*
  * SCX task iterator.
@@ -1415,7 +1487,7 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p,
 		 * tested easily when adding the first task.
 		 */
 		if (unlikely(RB_EMPTY_ROOT(&dsq->priq) &&
-			     !list_empty(&dsq->list)))
+			     nldsq_next_task(dsq, NULL, false)))
 			scx_ops_error("DSQ ID 0x%016llx already had FIFO-enqueued tasks",
 				      dsq->id);
 
@@ -1447,6 +1519,10 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p,
 			list_add_tail(&p->scx.dsq_list.node, &dsq->list);
 	}
 
+	/* seq records the order tasks are queued, used by BPF DSQ iterator */
+	dsq->seq++;
+	p->scx.dsq_seq = dsq->seq;
+
 	dsq_mod_nr(dsq, 1);
 	p->scx.dsq = dsq;
 
@@ -2104,12 +2180,17 @@ static bool consume_dispatch_q(struct rq *rq, struct rq_flags *rf,
 {
 	struct task_struct *p;
 retry:
+	/*
+	 * The caller can't expect to successfully consume a task if the task's
+	 * addition to @dsq isn't guaranteed to be visible somehow. Test
+	 * @dsq->list without locking and skip if it seems empty.
+	 */
 	if (list_empty(&dsq->list))
 		return false;
 
 	raw_spin_lock(&dsq->lock);
 
-	list_for_each_entry(p, &dsq->list, scx.dsq_list.node) {
+	nldsq_for_each_task(p, dsq) {
 		struct rq *task_rq = task_rq(p);
 
 		if (rq == task_rq) {
@@ -5705,6 +5786,110 @@ __bpf_kfunc void scx_bpf_destroy_dsq(u64 dsq_id)
 	destroy_dsq(dsq_id);
 }
 
+/**
+ * bpf_iter_scx_dsq_new - Create a DSQ iterator
+ * @it: iterator to initialize
+ * @dsq_id: DSQ to iterate
+ * @flags: %SCX_DSQ_ITER_*
+ *
+ * Initialize BPF iterator @it which can be used with bpf_for_each() to walk
+ * tasks in the DSQ specified by @dsq_id. Iteration using @it only includes
+ * tasks which are already queued when this function is invoked.
+ */
+__bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id,
+				     u64 flags)
+{
+	struct bpf_iter_scx_dsq_kern *kit = (void *)it;
+
+	BUILD_BUG_ON(sizeof(struct bpf_iter_scx_dsq_kern) >
+		     sizeof(struct bpf_iter_scx_dsq));
+	BUILD_BUG_ON(__alignof__(struct bpf_iter_scx_dsq_kern) !=
+		     __alignof__(struct bpf_iter_scx_dsq));
+
+	if (flags & ~__SCX_DSQ_ITER_ALL_FLAGS)
+		return -EINVAL;
+
+	kit->dsq = find_non_local_dsq(dsq_id);
+	if (!kit->dsq)
+		return -ENOENT;
+
+	INIT_LIST_HEAD(&kit->cursor.node);
+	kit->cursor.is_bpf_iter_cursor = true;
+	kit->dsq_seq = READ_ONCE(kit->dsq->seq);
+	kit->flags = flags;
+
+	return 0;
+}
+
+/**
+ * bpf_iter_scx_dsq_next - Progress a DSQ iterator
+ * @it: iterator to progress
+ *
+ * Return the next task. See bpf_iter_scx_dsq_new().
+ */
+__bpf_kfunc struct task_struct *bpf_iter_scx_dsq_next(struct bpf_iter_scx_dsq *it)
+{
+	struct bpf_iter_scx_dsq_kern *kit = (void *)it;
+	bool rev = kit->flags & SCX_DSQ_ITER_REV;
+	struct task_struct *p;
+	unsigned long flags;
+
+	if (!kit->dsq)
+		return NULL;
+
+	raw_spin_lock_irqsave(&kit->dsq->lock, flags);
+
+	if (list_empty(&kit->cursor.node))
+		p = NULL;
+	else
+		p = container_of(&kit->cursor, struct task_struct, scx.dsq_list);
+
+	/*
+	 * Only tasks which were queued before the iteration started are
+	 * visible. This bounds BPF iterations and guarantees that vtime never
+	 * jumps in the other direction while iterating.
+	 */
+	do {
+		p = nldsq_next_task(kit->dsq, p, rev);
+	} while (p && unlikely(u32_before(kit->dsq_seq, p->scx.dsq_seq)));
+
+	if (p) {
+		if (rev)
+			list_move_tail(&kit->cursor.node, &p->scx.dsq_list.node);
+		else
+			list_move(&kit->cursor.node, &p->scx.dsq_list.node);
+	} else {
+		list_del_init(&kit->cursor.node);
+	}
+
+	raw_spin_unlock_irqrestore(&kit->dsq->lock, flags);
+
+	return p;
+}
+
+/**
+ * bpf_iter_scx_dsq_destroy - Destroy a DSQ iterator
+ * @it: iterator to destroy
+ *
+ * Undo scx_iter_scx_dsq_new().
+ */
+__bpf_kfunc void bpf_iter_scx_dsq_destroy(struct bpf_iter_scx_dsq *it)
+{
+	struct bpf_iter_scx_dsq_kern *kit = (void *)it;
+
+	if (!kit->dsq)
+		return;
+
+	if (!list_empty(&kit->cursor.node)) {
+		unsigned long flags;
+
+		raw_spin_lock_irqsave(&kit->dsq->lock, flags);
+		list_del_init(&kit->cursor.node);
+		raw_spin_unlock_irqrestore(&kit->dsq->lock, flags);
+	}
+	kit->dsq = NULL;
+}
+
 __bpf_kfunc_end_defs();
 
 static s32 __bstr_format(u64 *data_buf, char *line_buf, size_t line_size,
@@ -6138,6 +6323,9 @@ BTF_KFUNCS_START(scx_kfunc_ids_any)
 BTF_ID_FLAGS(func, scx_bpf_kick_cpu)
 BTF_ID_FLAGS(func, scx_bpf_dsq_nr_queued)
 BTF_ID_FLAGS(func, scx_bpf_destroy_dsq)
+BTF_ID_FLAGS(func, bpf_iter_scx_dsq_new, KF_ITER_NEW | KF_RCU_PROTECTED)
+BTF_ID_FLAGS(func, bpf_iter_scx_dsq_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_scx_dsq_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, scx_bpf_exit_bstr, KF_TRUSTED_ARGS)
 BTF_ID_FLAGS(func, scx_bpf_error_bstr, KF_TRUSTED_ARGS)
 BTF_ID_FLAGS(func, scx_bpf_dump_bstr, KF_TRUSTED_ARGS)
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
index 965d20324114..20280df62857 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -39,6 +39,9 @@ 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;
+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;
 void scx_bpf_exit_bstr(s64 exit_code, char *fmt, unsigned long long *data, u32 data__sz) __ksym __weak;
 void scx_bpf_error_bstr(char *fmt, unsigned long long *data, u32 data_len) __ksym;
 void scx_bpf_dump_bstr(char *fmt, unsigned long long *data, u32 data_len) __ksym __weak;
-- 
2.45.2

[PATCH 3/3] sched_ext/scx_qmap: Add an example usage of DSQ iterator

[Tejun Heo]

Implement periodic dumping of the shared DSQ to demonstrate the use of the
newly added DSQ iterator.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: David Vernet <dvernet@meta.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: bpf@vger.kernel.org
---
 tools/sched_ext/scx_qmap.bpf.c | 25 +++++++++++++++++++++++++
 tools/sched_ext/scx_qmap.c     |  8 ++++++--
 2 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index b1d0b09c966e..27e35066a602 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -36,6 +36,7 @@ const volatile u32 stall_user_nth;
 const volatile u32 stall_kernel_nth;
 const volatile u32 dsp_inf_loop_after;
 const volatile u32 dsp_batch;
+const volatile bool print_shared_dsq;
 const volatile s32 disallow_tgid;
 const volatile bool suppress_dump;
 
@@ -604,10 +605,34 @@ static void monitor_cpuperf(void)
 	scx_bpf_put_cpumask(online);
 }
 
+/*
+ * Dump the currently queued tasks in the shared DSQ to demonstrate the usage of
+ * scx_bpf_dsq_nr_queued() and DSQ iterator. Raise the dispatch batch count to
+ * see meaningful dumps in the trace pipe.
+ */
+static void dump_shared_dsq(void)
+{
+	struct task_struct *p;
+	s32 nr;
+
+	if (!(nr = scx_bpf_dsq_nr_queued(SHARED_DSQ)))
+		return;
+
+	bpf_printk("Dumping %d tasks in SHARED_DSQ in reverse order", nr);
+
+	bpf_rcu_read_lock();
+	bpf_for_each(scx_dsq, p, SHARED_DSQ, SCX_DSQ_ITER_REV)
+		bpf_printk("%s[%d]", p->comm, p->pid);
+	bpf_rcu_read_unlock();
+}
+
 static int monitor_timerfn(void *map, int *key, struct bpf_timer *timer)
 {
 	monitor_cpuperf();
 
+	if (print_shared_dsq)
+		dump_shared_dsq();
+
 	bpf_timer_start(timer, ONE_SEC_IN_NS, 0);
 	return 0;
 }
diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c
index e4e3ecffc4cf..304f0488a386 100644
--- a/tools/sched_ext/scx_qmap.c
+++ b/tools/sched_ext/scx_qmap.c
@@ -20,7 +20,7 @@ const char help_fmt[] =
 "See the top-level comment in .bpf.c for more details.\n"
 "\n"
 "Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-l COUNT] [-b COUNT]\n"
-"       [-d PID] [-D LEN] [-p] [-v]\n"
+"       [-P] [-d PID] [-D LEN] [-p] [-v]\n"
 "\n"
 "  -s SLICE_US   Override slice duration\n"
 "  -e COUNT      Trigger scx_bpf_error() after COUNT enqueues\n"
@@ -28,6 +28,7 @@ const char help_fmt[] =
 "  -T COUNT      Stall every COUNT'th kernel thread\n"
 "  -l COUNT      Trigger dispatch infinite looping after COUNT dispatches\n"
 "  -b COUNT      Dispatch upto COUNT tasks together\n"
+"  -P            Print out DSQ content to trace_pipe every second, use with -b\n"
 "  -d PID        Disallow a process from switching into SCHED_EXT (-1 for self)\n"
 "  -D LEN        Set scx_exit_info.dump buffer length\n"
 "  -S            Suppress qmap-specific debug dump\n"
@@ -62,7 +63,7 @@ int main(int argc, char **argv)
 
 	skel = SCX_OPS_OPEN(qmap_ops, scx_qmap);
 
-	while ((opt = getopt(argc, argv, "s:e:t:T:l:b:d:D:Spvh")) != -1) {
+	while ((opt = getopt(argc, argv, "s:e:t:T:l:b:Pd:D:Spvh")) != -1) {
 		switch (opt) {
 		case 's':
 			skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000;
@@ -82,6 +83,9 @@ int main(int argc, char **argv)
 		case 'b':
 			skel->rodata->dsp_batch = strtoul(optarg, NULL, 0);
 			break;
+		case 'P':
+			skel->rodata->print_shared_dsq = true;
+			break;
 		case 'd':
 			skel->rodata->disallow_tgid = strtol(optarg, NULL, 0);
 			if (skel->rodata->disallow_tgid < 0)
-- 
2.45.2

Re: [PATCH 1/3] sched_ext: Take out ->priq and ->flags from scx_dsq_node

[David Vernet]

[-- Attachment #1: Type: text/plain, Size: 1183 bytes --]

On Mon, Jul 08, 2024 at 02:40:22PM -1000, Tejun Heo wrote:
> struct scx_dsq_node contains two data structure nodes to link the containing
> task to a DSQ and a flags field that is protected by the lock of the
> associated DSQ. One reason why they are grouped into a struct is to use the
> type independently as a cursor node when iterating tasks on a DSQ. However,
> when iterating, the cursor only needs to be linked on the FIFO list and the
> rb_node part ends up inflating the size of the iterator data structure
> unnecessarily making it potentially too expensive to place it on stack.
> 
> Take ->priq and ->flags out of scx_dsq_node and put them in sched_ext_entity
> as ->dsq_priq and ->dsq_flags, respectively. scx_dsq_node is renamed to
> scx_dsq_list_node and the field names are renamed accordingly. This will
> help implementing DSQ task iterator that can be allocated on stack.
> 
> No functional change intended.
> 
> Signed-off-by: Tejun Heo <tj@kernel.org>
> Suggested-by: Alexei Starovoitov <ast@kernel.org>
> Acked-by: Alexei Starovoitov <ast@kernel.org>
> Cc: David Vernet <void@manifault.com>

Reviewed-by: David Vernet <void@manifault.com>

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]