x86/cpu/topology: Let XEN/PV use topology from CPUID/MADT

It turns out that XEN/PV Dom0 has halfways usable CPUID/MADT enumeration
except that it cannot deal with CPUs which are enumerated as disabled in
MADT.

DomU has no MADT and provides at least rudimentary topology information in
CPUID leaves 1 and 4.

For both it's important that there are not more possible Linux CPUs than
vCPUs provided by the hypervisor.

As this is ensured by counting the vCPUs before enumeration happens:

  - lift the restrictions in the CPUID evaluation and the MADT parser

  - Utilize MADT registration for Dom0

  - Keep the fake APIC ID registration for DomU

  - Fix the XEN APIC fake so the readout of the local APIC ID works for
    Dom0 via the hypercall and for DomU by returning the registered
    fake APIC IDs.

With that the XEN/PV fake approximates usefulness.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Sohil Mehta <sohil.mehta@intel.com>
Link: https://lore.kernel.org/r/20240213210252.626195405@linutronix.de

Author: KAGA-KOKO

arch/x86/kernel/acpi/boot.c

@@ -23,8 +23,6 @@
 #include <linux/serial_core.h>
 #include <linux/pgtable.h>
 
-#include <xen/xen.h>
-
 #include <asm/e820/api.h>
 #include <asm/irqdomain.h>
 #include <asm/pci_x86.h>
@@ -166,12 +164,6 @@ static int __init acpi_parse_madt(struct acpi_table_header *table)
 	return 0;
 }
 
-static __init void acpi_register_lapic(u32 apic_id, u32 acpi_id, bool present)
-{
-	if (!xen_pv_domain())
-		topology_register_apic(apic_id, acpi_id, present);
-}
-
 static bool __init acpi_is_processor_usable(u32 lapic_flags)
 {
 	if (lapic_flags & ACPI_MADT_ENABLED)
@@ -233,7 +225,7 @@ acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end)
 		return 0;
 	}
 
-	acpi_register_lapic(apic_id, processor->uid, enabled);
+	topology_register_apic(apic_id, processor->uid, enabled);
 #else
 	pr_warn("x2apic entry ignored\n");
 #endif
@@ -268,9 +260,9 @@ acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end)
 	 * to not preallocating memory for all NR_CPUS
 	 * when we use CPU hotplug.
 	 */
-	acpi_register_lapic(processor->id,	/* APIC ID */
-			    processor->processor_id, /* ACPI ID */
-			    processor->lapic_flags & ACPI_MADT_ENABLED);
+	topology_register_apic(processor->id,	/* APIC ID */
+			       processor->processor_id, /* ACPI ID */
+			       processor->lapic_flags & ACPI_MADT_ENABLED);
 
 	has_lapic_cpus = true;
 	return 0;
@@ -288,9 +280,9 @@ acpi_parse_sapic(union acpi_subtable_headers *header, const unsigned long end)
 
 	acpi_table_print_madt_entry(&header->common);
 
-	acpi_register_lapic((processor->id << 8) | processor->eid,/* APIC ID */
-			    processor->processor_id, /* ACPI ID */
-			    processor->lapic_flags & ACPI_MADT_ENABLED);
+	topology_register_apic((processor->id << 8) | processor->eid,/* APIC ID */
+			       processor->processor_id, /* ACPI ID */
+			       processor->lapic_flags & ACPI_MADT_ENABLED);
 
 	return 0;
 }
@@ -1090,8 +1082,7 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void)
 		return count;
 	}
 
-	if (!xen_pv_domain())
-		register_lapic_address(acpi_lapic_addr);
+	register_lapic_address(acpi_lapic_addr);
 
 	return count;
 }

arch/x86/kernel/cpu/topology_common.c

@@ -77,7 +77,7 @@ static bool fake_topology(struct topo_scan *tscan)
 	topology_set_dom(tscan, TOPO_SMT_DOMAIN, 0, 1);
 	topology_set_dom(tscan, TOPO_CORE_DOMAIN, 0, 1);
 
-	return tscan->c->cpuid_level < 1 || xen_pv_domain();
+	return tscan->c->cpuid_level < 1;
 }
 
 static void parse_topology(struct topo_scan *tscan, bool early)

arch/x86/xen/apic.c

@@ -43,20 +43,20 @@ static u32 xen_apic_read(u32 reg)
 	struct xen_platform_op op = {
 		.cmd = XENPF_get_cpuinfo,
 		.interface_version = XENPF_INTERFACE_VERSION,
-		.u.pcpu_info.xen_cpuid = 0,
 	};
-	int ret;
-
-	/* Shouldn't need this as APIC is turned off for PV, and we only
-	 * get called on the bootup processor. But just in case. */
-	if (!xen_initial_domain() || smp_processor_id())
-		return 0;
+	int ret, cpu;
 
 	if (reg == APIC_LVR)
 		return 0x14;
 	if (reg != APIC_ID)
 		return 0;
 
+	cpu = smp_processor_id();
+	if (!xen_initial_domain())
+		return cpu ? cpuid_to_apicid[cpu] << 24 : 0;
+
+	op.u.pcpu_info.xen_cpuid = cpu;
+
 	ret = HYPERVISOR_platform_op(&op);
 	if (ret)
 		op.u.pcpu_info.apic_id = BAD_APICID;

arch/x86/xen/smp_pv.c

@@ -156,11 +156,9 @@ static void __init xen_pv_smp_config(void)
 
 	topology_register_boot_apic(apicid++);
 
-	for (i = 1; i < nr_cpu_ids; i++) {
-		if (HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL) < 0)
-			break;
+	for (i = 1; i < nr_cpu_ids; i++)
 		topology_register_apic(apicid++, CPU_ACPIID_INVALID, true);
-	}
+
 	/* Pretend to be a proper enumerated system */
 	smp_found_config = 1;
 }
@@ -451,5 +449,10 @@ void __init xen_smp_init(void)
 	/* Avoid searching for BIOS MP tables */
 	x86_init.mpparse.find_mptable		= x86_init_noop;
 	x86_init.mpparse.early_parse_smp_cfg	= x86_init_noop;
-	x86_init.mpparse.parse_smp_cfg		= xen_pv_smp_config;
+
+	/* XEN/PV Dom0 has halfways sane topology information via CPUID/MADT */
+	if (xen_initial_domain())
+		x86_init.mpparse.parse_smp_cfg	= x86_init_noop;
+	else
+		x86_init.mpparse.parse_smp_cfg	= xen_pv_smp_config;
 }