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, 130 insertions, 0 deletions

diff --git a/arch/x86/hyperv/nested.c b/arch/x86/hyperv/nested.c
new file mode 100644
index 000000000..8ccbb7c4f
--- /dev/null
+++ b/arch/x86/hyperv/nested.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Hyper-V nested virtualization code.
+ *
+ * Copyright (C) 2018, Microsoft, Inc.
+ *
+ * Author : Lan Tianyu <Tianyu.Lan@microsoft.com>
+ */
+#define pr_fmt(fmt)  "Hyper-V: " fmt
+
+
+#include <linux/types.h>
+#include <linux/export.h>
+#include <hyperv/hvhdk.h>
+#include <asm/mshyperv.h>
+#include <asm/tlbflush.h>
+
+#include <asm/trace/hyperv.h>
+
+int hyperv_flush_guest_mapping(u64 as)
+{
+	struct hv_guest_mapping_flush *flush;
+	u64 status;
+	unsigned long flags;
+	int ret = -ENOTSUPP;
+
+	if (!hv_hypercall_pg)
+		goto fault;
+
+	local_irq_save(flags);
+
+	flush = *this_cpu_ptr(hyperv_pcpu_input_arg);
+
+	if (unlikely(!flush)) {
+		local_irq_restore(flags);
+		goto fault;
+	}
+
+	flush->address_space = as;
+	flush->flags = 0;
+
+	status = hv_do_hypercall(HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE,
+				 flush, NULL);
+	local_irq_restore(flags);
+
+	if (hv_result_success(status))
+		ret = 0;
+
+fault:
+	trace_hyperv_nested_flush_guest_mapping(as, ret);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hyperv_flush_guest_mapping);
+
+int hyperv_fill_flush_guest_mapping_list(
+		struct hv_guest_mapping_flush_list *flush,
+		u64 start_gfn, u64 pages)
+{
+	u64 cur = start_gfn;
+	u64 additional_pages;
+	int gpa_n = 0;
+
+	do {
+		/*
+		 * If flush requests exceed max flush count, go back to
+		 * flush tlbs without range.
+		 */
+		if (gpa_n >= HV_MAX_FLUSH_REP_COUNT)
+			return -ENOSPC;
+
+		additional_pages = min_t(u64, pages, HV_MAX_FLUSH_PAGES) - 1;
+
+		flush->gpa_list[gpa_n].page.additional_pages = additional_pages;
+		flush->gpa_list[gpa_n].page.largepage = false;
+		flush->gpa_list[gpa_n].page.basepfn = cur;
+
+		pages -= additional_pages + 1;
+		cur += additional_pages + 1;
+		gpa_n++;
+	} while (pages > 0);
+
+	return gpa_n;
+}
+EXPORT_SYMBOL_GPL(hyperv_fill_flush_guest_mapping_list);
+
+int hyperv_flush_guest_mapping_range(u64 as,
+		hyperv_fill_flush_list_func fill_flush_list_func, void *data)
+{
+	struct hv_guest_mapping_flush_list *flush;
+	u64 status;
+	unsigned long flags;
+	int ret = -ENOTSUPP;
+	int gpa_n = 0;
+
+	if (!hv_hypercall_pg || !fill_flush_list_func)
+		goto fault;
+
+	local_irq_save(flags);
+
+	flush = *this_cpu_ptr(hyperv_pcpu_input_arg);
+
+	if (unlikely(!flush)) {
+		local_irq_restore(flags);
+		goto fault;
+	}
+
+	flush->address_space = as;
+	flush->flags = 0;
+
+	gpa_n = fill_flush_list_func(flush, data);
+	if (gpa_n < 0) {
+		local_irq_restore(flags);
+		goto fault;
+	}
+
+	status = hv_do_rep_hypercall(HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST,
+				     gpa_n, 0, flush, NULL);
+
+	local_irq_restore(flags);
+
+	if (hv_result_success(status))
+		ret = 0;
+	else
+		ret = hv_result(status);
+fault:
+	trace_hyperv_nested_flush_guest_mapping_range(as, ret);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hyperv_flush_guest_mapping_range);