sched_ext: Maintain an online cid mask in the scheduler arenagrafted

Schedulers on the default cid mapping treat [0, nr_online_cids) as the
online set and restart on hotplug. Schedulers that install their own mapping
with scx_bpf_cid_override() have no way to learn which cids are online: the
count no longer identifies members and the CPU-form cpumask is unusable from
cid programs. This is an obvious hole in the cid API.

Add scx_bpf_online_cmask(), a kernel-maintained cmask in the scheduler's
arena, allocated alongside the per-CPU scratch masks and populated after the
cid mapping is finalized and before ops.init(), for child schedulers too.
The pointer stays valid through ops.exit() with no reference to take. It is
the arena offset as a void pointer, the same form struct_ops arena arguments
arrive in. The verifier types the void return as a scalar for the program's
arena cast.

The mask follows the SCX hotplug notifications: seeded from cpu_active_mask
and updated before ops.cid_online/offline() runs, so it lags cpu_online_mask
only inside a hotplug transition. Updates walk the scheduler list under the
lock that also serializes unlinking. Reads are live, not atomic snapshots.
Root initialization excludes hotplug.

v2: Reworded the getter kerneldoc (Andrea Righi).

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>

1 files changed, 124 insertions, 0 deletions

diff --git a/include/drm/spsc_queue.h b/include/drm/spsc_queue.h
new file mode 100644
index 000000000..ee9df8cc6
--- /dev/null
+++ b/include/drm/spsc_queue.h
@@ -0,0 +1,124 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef DRM_SCHEDULER_SPSC_QUEUE_H_
+#define DRM_SCHEDULER_SPSC_QUEUE_H_
+
+#include <linux/atomic.h>
+#include <linux/preempt.h>
+
+/** SPSC lockless queue */
+
+struct spsc_node {
+
+	/* Stores spsc_node* */
+	struct spsc_node *next;
+};
+
+struct spsc_queue {
+
+	 struct spsc_node *head;
+
+	/* atomic pointer to struct spsc_node* */
+	atomic_long_t tail;
+
+	atomic_t job_count;
+};
+
+static inline void spsc_queue_init(struct spsc_queue *queue)
+{
+	queue->head = NULL;
+	atomic_long_set(&queue->tail, (long)&queue->head);
+	atomic_set(&queue->job_count, 0);
+}
+
+static inline struct spsc_node *spsc_queue_peek(struct spsc_queue *queue)
+{
+	return queue->head;
+}
+
+static inline int spsc_queue_count(struct spsc_queue *queue)
+{
+	return atomic_read(&queue->job_count);
+}
+
+static inline bool spsc_queue_push(struct spsc_queue *queue, struct spsc_node *node)
+{
+	struct spsc_node **tail;
+
+	node->next = NULL;
+
+	preempt_disable();
+
+	atomic_inc(&queue->job_count);
+	smp_mb__after_atomic();
+
+	tail = (struct spsc_node **)atomic_long_xchg(&queue->tail, (long)&node->next);
+	WRITE_ONCE(*tail, node);
+
+	/*
+	 * In case of first element verify new node will be visible to the consumer
+	 * thread when we ping the kernel thread that there is new work to do.
+	 */
+	smp_wmb();
+
+	preempt_enable();
+
+	return tail == &queue->head;
+}
+
+
+static inline struct spsc_node *spsc_queue_pop(struct spsc_queue *queue)
+{
+	struct spsc_node *next, *node;
+
+	/* Verify reading from memory and not the cache */
+	smp_rmb();
+
+	node = READ_ONCE(queue->head);
+
+	if (!node)
+		return NULL;
+
+	next = READ_ONCE(node->next);
+	WRITE_ONCE(queue->head, next);
+
+	if (unlikely(!next)) {
+		/* slowpath for the last element in the queue */
+
+		if (atomic_long_cmpxchg(&queue->tail,
+				(long)&node->next, (long) &queue->head) != (long)&node->next) {
+			/* Updating tail failed wait for new next to appear */
+			do {
+				smp_rmb();
+			} while (unlikely(!(queue->head = READ_ONCE(node->next))));
+		}
+	}
+
+	atomic_dec(&queue->job_count);
+	return node;
+}
+
+
+
+#endif /* DRM_SCHEDULER_SPSC_QUEUE_H_ */