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, 46 insertions, 0 deletions

diff --git a/include/hyperv/hvgdk_ext.h b/include/hyperv/hvgdk_ext.h
new file mode 100644
index 000000000..641b591ee
--- /dev/null
+++ b/include/hyperv/hvgdk_ext.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Type definitions for the Microsoft Hypervisor.
+ */
+#ifndef _HV_HVGDK_EXT_H
+#define _HV_HVGDK_EXT_H
+
+#include "hvgdk_mini.h"
+
+/* Extended hypercalls */
+#define HV_EXT_CALL_QUERY_CAPABILITIES		0x8001
+#define HV_EXT_CALL_MEMORY_HEAT_HINT		0x8003
+
+/* Extended hypercalls */
+enum {		/* HV_EXT_CALL */
+	HV_EXTCALL_QUERY_CAPABILITIES = 0x8001,
+	HV_EXTCALL_MEMORY_HEAT_HINT   = 0x8003,
+};
+
+/* HV_EXT_OUTPUT_QUERY_CAPABILITIES */
+#define HV_EXT_CAPABILITY_MEMORY_COLD_DISCARD_HINT BIT(8)
+
+enum {		/* HV_EXT_MEMORY_HEAT_HINT_TYPE */
+	HV_EXTMEM_HEAT_HINT_COLD = 0,
+	HV_EXTMEM_HEAT_HINT_HOT = 1,
+	HV_EXTMEM_HEAT_HINT_COLD_DISCARD = 2,
+	HV_EXTMEM_HEAT_HINT_MAX
+};
+
+/*
+ * The whole argument should fit in a page to be able to pass to the hypervisor
+ * in one hypercall.
+ */
+#define HV_MEMORY_HINT_MAX_GPA_PAGE_RANGES  \
+	((HV_HYP_PAGE_SIZE - sizeof(struct hv_memory_hint)) / \
+		sizeof(union hv_gpa_page_range))
+
+/* HvExtCallMemoryHeatHint hypercall */
+#define HV_EXT_MEMORY_HEAT_HINT_TYPE_COLD_DISCARD	2
+struct hv_memory_hint {		/* HV_EXT_INPUT_MEMORY_HEAT_HINT */
+	u64 heat_type : 2;	/* HV_EXTMEM_HEAT_HINT_* */
+	u64 reserved : 62;
+	union hv_gpa_page_range ranges[];
+} __packed;
+
+#endif /* _HV_HVGDK_EXT_H */