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, 70 insertions, 0 deletions

diff --git a/io_uring/alloc_cache.h b/io_uring/alloc_cache.h
new file mode 100644
index 000000000..962b6e2d0
--- /dev/null
+++ b/io_uring/alloc_cache.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef IOU_ALLOC_CACHE_H
+#define IOU_ALLOC_CACHE_H
+
+#include <linux/io_uring_types.h>
+#include <linux/kasan.h>
+
+/*
+ * Don't allow the cache to grow beyond this size.
+ */
+#define IO_ALLOC_CACHE_MAX	128
+
+void io_alloc_cache_free(struct io_alloc_cache *cache,
+			 void (*free)(const void *));
+bool io_alloc_cache_init(struct io_alloc_cache *cache,
+			 unsigned max_nr, unsigned int size,
+			 unsigned int init_bytes);
+
+void *io_cache_alloc_new(struct io_alloc_cache *cache, gfp_t gfp);
+
+static inline bool io_alloc_cache_put(struct io_alloc_cache *cache,
+				      void *entry)
+{
+	if (cache->nr_cached < cache->max_cached) {
+		if (!kasan_mempool_poison_object(entry))
+			return false;
+		cache->entries[cache->nr_cached++] = entry;
+		return true;
+	}
+	return false;
+}
+
+static inline void *io_alloc_cache_get(struct io_alloc_cache *cache)
+{
+	if (cache->nr_cached) {
+		void *entry = cache->entries[--cache->nr_cached];
+
+		/*
+		 * If KASAN is enabled, always clear the initial bytes that
+		 * must be zeroed post alloc, in case any of them overlap
+		 * with KASAN storage.
+		 */
+#if defined(CONFIG_KASAN)
+		kasan_mempool_unpoison_object(entry, cache->elem_size);
+		if (cache->init_clear)
+			memset(entry, 0, cache->init_clear);
+#endif
+		return entry;
+	}
+
+	return NULL;
+}
+
+static inline void *io_cache_alloc(struct io_alloc_cache *cache, gfp_t gfp)
+{
+	void *obj;
+
+	obj = io_alloc_cache_get(cache);
+	if (obj)
+		return obj;
+	return io_cache_alloc_new(cache, gfp);
+}
+
+static inline void io_cache_free(struct io_alloc_cache *cache, void *obj)
+{
+	if (!io_alloc_cache_put(cache, obj))
+		kvfree(obj);
+}
+
+#endif