Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <20230807135028.590964892@linutronix.de>
From:   Thomas Gleixner <tglx@linutronix.de>
To:     LKML <linux-kernel@vger.kernel.org>
Cc:     x86@kernel.org, Tom Lendacky <thomas.lendacky@amd.com>,
        Andrew Cooper <andrew.cooper3@citrix.com>,
        Arjan van de Ven <arjan@linux.intel.com>,
        Huang Rui <ray.huang@amd.com>, Juergen Gross <jgross@suse.com>,
        Dimitri Sivanich <dimitri.sivanich@hpe.com>,
        Michael Kelley <mikelley@microsoft.com>,
        Sohil Mehta <sohil.mehta@intel.com>,
        K Prateek Nayak <kprateek.nayak@amd.com>,
        Kan Liang <kan.liang@linux.intel.com>,
        Zhang Rui <rui.zhang@intel.com>,
        "Paul E. McKenney" <paulmck@kernel.org>,
        Feng Tang <feng.tang@intel.com>,
        Andy Shevchenko <andy@infradead.org>
Subject: [patch 41/53] x86/xen/smp_pv: Count number of vCPUs early
References: <20230807130108.853357011@linutronix.de>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Date:   Mon,  7 Aug 2023 15:53:37 +0200 (CEST)
Precedence: bulk

XEN/PV has a completely broken vCPU enumeration scheme, which just works by
chance and provides zero topology information. Each vCPU ends up being a
single core package.

Dom0 provides MADT which can be used for topology information, but that
table is the unmodified host table, which means that there can be more CPUs
registered than the number of vCPUs XEN provides for the dom0 guest.

DomU does not have ACPI and both rely on counting the possible vCPUs via an
hypercall.

To prepare for using CPUID topology information either via MADT or via fake
APIC IDs count the number of possible CPUs during early boot and adjust
nr_cpu_ids() accordingly.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/enlighten_pv.c |    3 +++
 arch/x86/xen/smp.h          |    2 ++
 arch/x86/xen/smp_pv.c       |   14 ++++++++++++++
 3 files changed, 19 insertions(+)

--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -189,6 +189,9 @@ static void __init xen_pv_init_platform(
 		xen_set_mtrr_data();
 	else
 		mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK);
+
+	/* Adjust nr_cpu_ids before "enumeration" happens */
+	xen_smp_count_cpus();
 }
 
 static void __init xen_pv_guest_late_init(void)
--- a/arch/x86/xen/smp.h
+++ b/arch/x86/xen/smp.h
@@ -19,6 +19,7 @@ extern void xen_smp_intr_free(unsigned i
 int xen_smp_intr_init_pv(unsigned int cpu);
 void xen_smp_intr_free_pv(unsigned int cpu);
 
+void xen_smp_count_cpus(void);
 void xen_smp_cpus_done(unsigned int max_cpus);
 
 void xen_smp_send_reschedule(int cpu);
@@ -44,6 +45,7 @@ static inline int xen_smp_intr_init_pv(u
 	return 0;
 }
 static inline void xen_smp_intr_free_pv(unsigned int cpu) {}
+static inline void xen_smp_count_cpus(void) { }
 #endif /* CONFIG_SMP */
 
 #endif
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -411,6 +411,20 @@ static irqreturn_t xen_irq_work_interrup
 	return IRQ_HANDLED;
 }
 
+void __init xen_smp_count_cpus(void)
+{
+	unsigned int cpus;
+
+	for (cpus = 0; cpus < nr_cpu_ids; cpus++) {
+		if (HYPERVISOR_vcpu_op(VCPUOP_is_up, cpus, NULL) < 0)
+			break;
+	}
+
+	pr_info("Xen PV: Detected %u vCPUS\n", cpus);
+	if (cpus < nr_cpu_ids)
+		set_nr_cpu_ids(cpus);
+}
+
 static const struct smp_ops xen_smp_ops __initconst = {
 	.smp_prepare_boot_cpu = xen_pv_smp_prepare_boot_cpu,
 	.smp_prepare_cpus = xen_pv_smp_prepare_cpus,