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, 153 insertions, 0 deletions

diff --git a/include/drm/drm_managed.h b/include/drm/drm_managed.h
new file mode 100644
index 000000000..72bfac002
--- /dev/null
+++ b/include/drm/drm_managed.h
@@ -0,0 +1,153 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _DRM_MANAGED_H_
+#define _DRM_MANAGED_H_
+
+#include <linux/gfp.h>
+#include <linux/overflow.h>
+#include <linux/types.h>
+
+struct drm_device;
+struct mutex;
+
+typedef void (*drmres_release_t)(struct drm_device *dev, void *res);
+
+/**
+ * drmm_add_action - add a managed release action to a &drm_device
+ * @dev: DRM device
+ * @action: function which should be called when @dev is released
+ * @data: opaque pointer, passed to @action
+ *
+ * This function adds the @release action with optional parameter @data to the
+ * list of cleanup actions for @dev. The cleanup actions will be run in reverse
+ * order in the final drm_dev_put() call for @dev.
+ */
+#define drmm_add_action(dev, action, data) \
+	__drmm_add_action(dev, action, data, #action)
+
+int __must_check __drmm_add_action(struct drm_device *dev,
+				   drmres_release_t action,
+				   void *data, const char *name);
+
+/**
+ * drmm_add_action_or_reset - add a managed release action to a &drm_device
+ * @dev: DRM device
+ * @action: function which should be called when @dev is released
+ * @data: opaque pointer, passed to @action
+ *
+ * Similar to drmm_add_action(), with the only difference that upon failure
+ * @action is directly called for any cleanup work necessary on failures.
+ */
+#define drmm_add_action_or_reset(dev, action, data) \
+	__drmm_add_action_or_reset(dev, action, data, #action)
+
+int __must_check __drmm_add_action_or_reset(struct drm_device *dev,
+					    drmres_release_t action,
+					    void *data, const char *name);
+
+void drmm_release_action(struct drm_device *dev,
+			 drmres_release_t action,
+			 void *data);
+
+void *drmm_kmalloc(struct drm_device *dev, size_t size, gfp_t gfp) __malloc;
+
+/**
+ * drmm_kzalloc - &drm_device managed kzalloc()
+ * @dev: DRM device
+ * @size: size of the memory allocation
+ * @gfp: GFP allocation flags
+ *
+ * This is a &drm_device managed version of kzalloc(). The allocated memory is
+ * automatically freed on the final drm_dev_put(). Memory can also be freed
+ * before the final drm_dev_put() by calling drmm_kfree().
+ */
+static inline void *drmm_kzalloc(struct drm_device *dev, size_t size, gfp_t gfp)
+{
+	return drmm_kmalloc(dev, size, gfp | __GFP_ZERO);
+}
+
+/**
+ * drmm_kmalloc_array - &drm_device managed kmalloc_array()
+ * @dev: DRM device
+ * @n: number of array elements to allocate
+ * @size: size of array member
+ * @flags: GFP allocation flags
+ *
+ * This is a &drm_device managed version of kmalloc_array(). The allocated
+ * memory is automatically freed on the final drm_dev_put() and works exactly
+ * like a memory allocation obtained by drmm_kmalloc().
+ */
+static inline void *drmm_kmalloc_array(struct drm_device *dev,
+				       size_t n, size_t size, gfp_t flags)
+{
+	size_t bytes;
+
+	if (unlikely(check_mul_overflow(n, size, &bytes)))
+		return NULL;
+
+	return drmm_kmalloc(dev, bytes, flags);
+}
+
+/**
+ * drmm_kcalloc - &drm_device managed kcalloc()
+ * @dev: DRM device
+ * @n: number of array elements to allocate
+ * @size: size of array member
+ * @flags: GFP allocation flags
+ *
+ * This is a &drm_device managed version of kcalloc(). The allocated memory is
+ * automatically freed on the final drm_dev_put() and works exactly like a
+ * memory allocation obtained by drmm_kmalloc().
+ */
+static inline void *drmm_kcalloc(struct drm_device *dev,
+				 size_t n, size_t size, gfp_t flags)
+{
+	return drmm_kmalloc_array(dev, n, size, flags | __GFP_ZERO);
+}
+
+char *drmm_kstrdup(struct drm_device *dev, const char *s, gfp_t gfp);
+
+void drmm_kfree(struct drm_device *dev, void *data);
+
+void __drmm_mutex_release(struct drm_device *dev, void *res);
+
+/**
+ * drmm_mutex_init - &drm_device-managed mutex_init()
+ * @dev: DRM device
+ * @lock: lock to be initialized
+ *
+ * Returns:
+ * 0 on success, or a negative errno code otherwise.
+ *
+ * This is a &drm_device-managed version of mutex_init(). The initialized
+ * lock is automatically destroyed on the final drm_dev_put().
+ */
+#define drmm_mutex_init(dev, lock) ({					     \
+	mutex_init(lock);						     \
+	drmm_add_action_or_reset(dev, __drmm_mutex_release, lock);	     \
+})									     \
+
+void __drmm_workqueue_release(struct drm_device *device, void *wq);
+
+/**
+ * drmm_alloc_ordered_workqueue - &drm_device managed alloc_ordered_workqueue()
+ * @dev: DRM device
+ * @fmt: printf format for the name of the workqueue
+ * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful)
+ * @args: args for @fmt
+ *
+ * This is a &drm_device-managed version of alloc_ordered_workqueue(). The
+ * allocated workqueue is automatically destroyed on the final drm_dev_put().
+ *
+ * Returns: workqueue on success, negative ERR_PTR otherwise.
+ */
+#define drmm_alloc_ordered_workqueue(dev, fmt, flags, args...)					\
+	({											\
+		struct workqueue_struct *wq = alloc_ordered_workqueue(fmt, flags, ##args);	\
+		wq ? ({										\
+			int ret = drmm_add_action_or_reset(dev, __drmm_workqueue_release, wq);	\
+			ret ? ERR_PTR(ret) : wq;						\
+		}) : ERR_PTR(-ENOMEM);								\
+	})
+
+#endif