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, 136 insertions, 0 deletions

diff --git a/arch/arm64/hyperv/mshyperv.c b/arch/arm64/hyperv/mshyperv.c
new file mode 100644
index 000000000..4fdc26ade
--- /dev/null
+++ b/arch/arm64/hyperv/mshyperv.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Core routines for interacting with Microsoft's Hyper-V hypervisor,
+ * including hypervisor initialization.
+ *
+ * Copyright (C) 2021, Microsoft, Inc.
+ *
+ * Author : Michael Kelley <mikelley@microsoft.com>
+ */
+
+#include <linux/types.h>
+#include <linux/acpi.h>
+#include <linux/export.h>
+#include <linux/errno.h>
+#include <linux/version.h>
+#include <linux/cpuhotplug.h>
+#include <asm/mshyperv.h>
+
+static bool hyperv_initialized;
+
+int hv_get_hypervisor_version(union hv_hypervisor_version_info *info)
+{
+	hv_get_vpreg_128(HV_REGISTER_HYPERVISOR_VERSION,
+			 (struct hv_get_vp_registers_output *)info);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(hv_get_hypervisor_version);
+
+#ifdef CONFIG_ACPI
+
+static bool __init hyperv_detect_via_acpi(void)
+{
+	if (acpi_disabled)
+		return false;
+	/*
+	 * Hypervisor ID is only available in ACPI v6+, and the
+	 * structure layout was extended in v6 to accommodate that
+	 * new field.
+	 *
+	 * At the very minimum, this check makes sure not to read
+	 * past the FADT structure.
+	 *
+	 * It is also needed to catch running in some unknown
+	 * non-Hyper-V environment that has ACPI 5.x or less.
+	 * In such a case, it can't be Hyper-V.
+	 */
+	if (acpi_gbl_FADT.header.revision < 6)
+		return false;
+	return strncmp((char *)&acpi_gbl_FADT.hypervisor_id, "MsHyperV", 8) == 0;
+}
+
+#else
+
+static bool __init hyperv_detect_via_acpi(void)
+{
+	return false;
+}
+
+#endif
+
+static bool __init hyperv_detect_via_smccc(void)
+{
+	uuid_t hyperv_uuid = UUID_INIT(
+		0x58ba324d, 0x6447, 0x24cd,
+		0x75, 0x6c, 0xef, 0x8e,
+		0x24, 0x70, 0x59, 0x16);
+
+	return arm_smccc_hypervisor_has_uuid(&hyperv_uuid);
+}
+
+static int __init hyperv_init(void)
+{
+	struct hv_get_vp_registers_output	result;
+	u64	guest_id;
+	int	ret;
+
+	/*
+	 * Allow for a kernel built with CONFIG_HYPERV to be running in
+	 * a non-Hyper-V environment.
+	 *
+	 * In such cases, do nothing and return success.
+	 */
+	if (!hyperv_detect_via_acpi() && !hyperv_detect_via_smccc())
+		return 0;
+
+	/* Setup the guest ID */
+	guest_id = hv_generate_guest_id(LINUX_VERSION_CODE);
+	hv_set_vpreg(HV_REGISTER_GUEST_OS_ID, guest_id);
+
+	/* Get the features and hints from Hyper-V */
+	hv_get_vpreg_128(HV_REGISTER_PRIVILEGES_AND_FEATURES_INFO, &result);
+	ms_hyperv.features = result.as32.a;
+	ms_hyperv.priv_high = result.as32.b;
+	ms_hyperv.misc_features = result.as32.c;
+
+	hv_get_vpreg_128(HV_REGISTER_FEATURES_INFO, &result);
+	ms_hyperv.hints = result.as32.a;
+
+	pr_info("Hyper-V: privilege flags low 0x%x, high 0x%x, hints 0x%x, misc 0x%x\n",
+		ms_hyperv.features, ms_hyperv.priv_high, ms_hyperv.hints,
+		ms_hyperv.misc_features);
+
+	hv_identify_partition_type();
+
+	ret = hv_common_init();
+	if (ret)
+		return ret;
+
+	ret = cpuhp_setup_state(CPUHP_AP_HYPERV_ONLINE, "arm64/hyperv_init:online",
+				hv_common_cpu_init, hv_common_cpu_die);
+	if (ret < 0) {
+		hv_common_free();
+		return ret;
+	}
+
+	if (ms_hyperv.priv_high & HV_ACCESS_PARTITION_ID)
+		hv_get_partition_id();
+	ms_hyperv.vtl = get_vtl();
+	if (ms_hyperv.vtl > 0) /* non default VTL */
+		pr_info("Linux runs in Hyper-V Virtual Trust Level %d\n", ms_hyperv.vtl);
+
+	ms_hyperv_late_init();
+
+	hyperv_initialized = true;
+	return 0;
+}
+
+early_initcall(hyperv_init);
+
+bool hv_is_hyperv_initialized(void)
+{
+	return hyperv_initialized;
+}
+EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized);