7 files changed, 113 insertions, 310 deletions
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index 3bf0487cf3b7..52d1808ee360 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -23,8 +23,5 @@ obj-$(CONFIG_X86_X2APIC)	+= x2apic_cluster.o
 obj-y				+= apic_flat_64.o
 endif
 
-# APIC probe will depend on the listing order here
-obj-$(CONFIG_X86_BIGSMP)	+= bigsmp_32.o
-
 # For 32bit, probe_32 need to be listed last
 obj-$(CONFIG_X86_LOCAL_APIC)	+= probe_$(BITS).o
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index e893dc6f11c1..62584a347931 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1371,8 +1371,6 @@ void __init apic_intr_mode_init(void)
 
 	x86_64_probe_apic();
 
-	x86_32_install_bigsmp();
-
 	if (x86_platform.apic_post_init)
 		x86_platform.apic_post_init();
 
@@ -1674,7 +1672,6 @@ static __init void apic_read_boot_cpu_id(bool x2apic)
 		boot_cpu_apic_version = GET_APIC_VERSION(apic_read(APIC_LVR));
 	}
 	topology_register_boot_apic(boot_cpu_physical_apicid);
-	x86_32_probe_bigsmp_early();
 }
 
 #ifdef CONFIG_X86_X2APIC
@@ -2014,8 +2011,8 @@ static bool __init detect_init_APIC(void)
 	case X86_VENDOR_HYGON:
 		break;
 	case X86_VENDOR_INTEL:
-		if (boot_cpu_data.x86 == 6 || boot_cpu_data.x86 == 15 ||
-		    (boot_cpu_data.x86 == 5 && boot_cpu_has(X86_FEATURE_APIC)))
+		if ((boot_cpu_data.x86 == 5 && boot_cpu_has(X86_FEATURE_APIC)) ||
+		    boot_cpu_data.x86_vfm >= INTEL_PENTIUM_PRO)
 			break;
 		goto no_apic;
 	default:
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
deleted file mode 100644
index 9285d500d5b4..000000000000
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ /dev/null
@@ -1,105 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * APIC driver for "bigsmp" xAPIC machines with more than 8 virtual CPUs.
- *
- * Drives the local APIC in "clustered mode".
- */
-#include <linux/cpumask.h>
-#include <linux/dmi.h>
-#include <linux/smp.h>
-
-#include <asm/apic.h>
-#include <asm/io_apic.h>
-
-#include "local.h"
-
-static u32 bigsmp_get_apic_id(u32 x)
-{
-	return (x >> 24) & 0xFF;
-}
-
-static void bigsmp_send_IPI_allbutself(int vector)
-{
-	default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
-}
-
-static void bigsmp_send_IPI_all(int vector)
-{
-	default_send_IPI_mask_sequence_phys(cpu_online_mask, vector);
-}
-
-static int dmi_bigsmp; /* can be set by dmi scanners */
-
-static int hp_ht_bigsmp(const struct dmi_system_id *d)
-{
-	printk(KERN_NOTICE "%s detected: force use of apic=bigsmp\n", d->ident);
-	dmi_bigsmp = 1;
-
-	return 0;
-}
-
-
-static const struct dmi_system_id bigsmp_dmi_table[] = {
-	{ hp_ht_bigsmp, "HP ProLiant DL760 G2",
-		{	DMI_MATCH(DMI_BIOS_VENDOR, "HP"),
-			DMI_MATCH(DMI_BIOS_VERSION, "P44-"),
-		}
-	},
-
-	{ hp_ht_bigsmp, "HP ProLiant DL740",
-		{	DMI_MATCH(DMI_BIOS_VENDOR, "HP"),
-			DMI_MATCH(DMI_BIOS_VERSION, "P47-"),
-		}
-	},
-	{ } /* NULL entry stops DMI scanning */
-};
-
-static int probe_bigsmp(void)
-{
-	return dmi_check_system(bigsmp_dmi_table);
-}
-
-static struct apic apic_bigsmp __ro_after_init = {
-
-	.name				= "bigsmp",
-	.probe				= probe_bigsmp,
-
-	.dest_mode_logical		= false,
-
-	.disable_esr			= 1,
-
-	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
-
-	.max_apic_id			= 0xFE,
-	.get_apic_id			= bigsmp_get_apic_id,
-
-	.calc_dest_apicid		= apic_default_calc_apicid,
-
-	.send_IPI			= default_send_IPI_single_phys,
-	.send_IPI_mask			= default_send_IPI_mask_sequence_phys,
-	.send_IPI_mask_allbutself	= NULL,
-	.send_IPI_allbutself		= bigsmp_send_IPI_allbutself,
-	.send_IPI_all			= bigsmp_send_IPI_all,
-	.send_IPI_self			= default_send_IPI_self,
-
-	.read				= native_apic_mem_read,
-	.write				= native_apic_mem_write,
-	.eoi				= native_apic_mem_eoi,
-	.icr_read			= native_apic_icr_read,
-	.icr_write			= native_apic_icr_write,
-	.wait_icr_idle			= apic_mem_wait_icr_idle,
-	.safe_wait_icr_idle		= apic_mem_wait_icr_idle_timeout,
-};
-
-bool __init apic_bigsmp_possible(bool cmdline_override)
-{
-	return apic == &apic_bigsmp || !cmdline_override;
-}
-
-void __init apic_bigsmp_force(void)
-{
-	if (apic != &apic_bigsmp)
-		apic_install_driver(&apic_bigsmp);
-}
-
-apic_driver(apic_bigsmp);
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 5da693d633b7..98a57cb4aa86 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -3,6 +3,7 @@
 #include <linux/cpumask.h>
 #include <linux/delay.h>
 #include <linux/smp.h>
+#include <linux/string_choices.h>
 
 #include <asm/io_apic.h>
 
@@ -23,7 +24,7 @@ __setup("no_ipi_broadcast=", apic_ipi_shorthand);
 static int __init print_ipi_mode(void)
 {
 	pr_info("IPI shorthand broadcast: %s\n",
-		apic_ipi_shorthand_off ? "disabled" : "enabled");
+		str_disabled_enabled(apic_ipi_shorthand_off));
 	return 0;
 }
 late_initcall(print_ipi_mode);
@@ -287,34 +288,4 @@ void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector)
 	__default_send_IPI_dest_field(mask, vector, APIC_DEST_LOGICAL);
 	local_irq_restore(flags);
 }
-
-#ifdef CONFIG_SMP
-static int convert_apicid_to_cpu(u32 apic_id)
-{
-	int i;
-
-	for_each_possible_cpu(i) {
-		if (per_cpu(x86_cpu_to_apicid, i) == apic_id)
-			return i;
-	}
-	return -1;
-}
-
-int safe_smp_processor_id(void)
-{
-	u32 apicid;
-	int cpuid;
-
-	if (!boot_cpu_has(X86_FEATURE_APIC))
-		return 0;
-
-	apicid = read_apic_id();
-	if (apicid == BAD_APICID)
-		return 0;
-
-	cpuid = convert_apicid_to_cpu(apicid);
-
-	return cpuid >= 0 ? cpuid : 0;
-}
-#endif
 #endif
diff --git a/arch/x86/kernel/apic/local.h b/arch/x86/kernel/apic/local.h
index 842fe28496be..bdcf609eb283 100644
--- a/arch/x86/kernel/apic/local.h
+++ b/arch/x86/kernel/apic/local.h
@@ -65,17 +65,4 @@ void default_send_IPI_self(int vector);
 void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, int vector);
 void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask, int vector);
 void default_send_IPI_mask_logical(const struct cpumask *mask, int vector);
-void x86_32_probe_bigsmp_early(void);
-void x86_32_install_bigsmp(void);
-#else
-static inline void x86_32_probe_bigsmp_early(void) { }
-static inline void x86_32_install_bigsmp(void) { }
-#endif
-
-#ifdef CONFIG_X86_BIGSMP
-bool apic_bigsmp_possible(bool cmdline_selected);
-void apic_bigsmp_force(void);
-#else
-static inline bool apic_bigsmp_possible(bool cmdline_selected) { return false; };
-static inline void apic_bigsmp_force(void) { }
 #endif
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index f75ee345c02d..87bc9e7ca5d6 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -93,35 +93,6 @@ static int __init parse_apic(char *arg)
 }
 early_param("apic", parse_apic);
 
-void __init x86_32_probe_bigsmp_early(void)
-{
-	if (nr_cpu_ids <= 8 || xen_pv_domain())
-		return;
-
-	if (IS_ENABLED(CONFIG_X86_BIGSMP)) {
-		switch (boot_cpu_data.x86_vendor) {
-		case X86_VENDOR_INTEL:
-			if (!APIC_XAPIC(boot_cpu_apic_version))
-				break;
-			/* P4 and above */
-			fallthrough;
-		case X86_VENDOR_HYGON:
-		case X86_VENDOR_AMD:
-			if (apic_bigsmp_possible(cmdline_apic))
-				return;
-			break;
-		}
-	}
-	pr_info("Limiting to 8 possible CPUs\n");
-	set_nr_cpu_ids(8);
-}
-
-void __init x86_32_install_bigsmp(void)
-{
-	if (nr_cpu_ids > 8 && !xen_pv_domain())
-		apic_bigsmp_force();
-}
-
 void __init x86_32_probe_apic(void)
 {
 	if (!cmdline_apic) {
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 736f62812f5c..fee42a73d64a 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -799,7 +799,7 @@ int __init arch_early_irq_init(void)
 	x86_vector_domain = irq_domain_create_tree(fn, &x86_vector_domain_ops,
 						   NULL);
 	BUG_ON(x86_vector_domain == NULL);
-	irq_set_default_host(x86_vector_domain);
+	irq_set_default_domain(x86_vector_domain);
 
 	BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL));
 
@@ -888,8 +888,109 @@ static int apic_set_affinity(struct irq_data *irqd,
 	return err ? err : IRQ_SET_MASK_OK;
 }
 
+static void free_moved_vector(struct apic_chip_data *apicd)
+{
+	unsigned int vector = apicd->prev_vector;
+	unsigned int cpu = apicd->prev_cpu;
+	bool managed = apicd->is_managed;
+
+	/*
+	 * Managed interrupts are usually not migrated away
+	 * from an online CPU, but CPU isolation 'managed_irq'
+	 * can make that happen.
+	 * 1) Activation does not take the isolation into account
+	 *    to keep the code simple
+	 * 2) Migration away from an isolated CPU can happen when
+	 *    a non-isolated CPU which is in the calculated
+	 *    affinity mask comes online.
+	 */
+	trace_vector_free_moved(apicd->irq, cpu, vector, managed);
+	irq_matrix_free(vector_matrix, cpu, vector, managed);
+	per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
+	hlist_del_init(&apicd->clist);
+	apicd->prev_vector = 0;
+	apicd->move_in_progress = 0;
+}
+
+/*
+ * Called from fixup_irqs() with @desc->lock held and interrupts disabled.
+ */
+static void apic_force_complete_move(struct irq_data *irqd)
+{
+	unsigned int cpu = smp_processor_id();
+	struct apic_chip_data *apicd;
+	unsigned int vector;
+
+	guard(raw_spinlock)(&vector_lock);
+	apicd = apic_chip_data(irqd);
+	if (!apicd)
+		return;
+
+	/*
+	 * If prev_vector is empty or the descriptor is neither currently
+	 * nor previously on the outgoing CPU no action required.
+	 */
+	vector = apicd->prev_vector;
+	if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu))
+		return;
+
+	/*
+	 * This is tricky. If the cleanup of the old vector has not been
+	 * done yet, then the following setaffinity call will fail with
+	 * -EBUSY. This can leave the interrupt in a stale state.
+	 *
+	 * All CPUs are stuck in stop machine with interrupts disabled so
+	 * calling __irq_complete_move() would be completely pointless.
+	 *
+	 * 1) The interrupt is in move_in_progress state. That means that we
+	 *    have not seen an interrupt since the io_apic was reprogrammed to
+	 *    the new vector.
+	 *
+	 * 2) The interrupt has fired on the new vector, but the cleanup IPIs
+	 *    have not been processed yet.
+	 */
+	if (apicd->move_in_progress) {
+		/*
+		 * In theory there is a race:
+		 *
+		 * set_ioapic(new_vector) <-- Interrupt is raised before update
+		 *			      is effective, i.e. it's raised on
+		 *			      the old vector.
+		 *
+		 * So if the target cpu cannot handle that interrupt before
+		 * the old vector is cleaned up, we get a spurious interrupt
+		 * and in the worst case the ioapic irq line becomes stale.
+		 *
+		 * But in case of cpu hotplug this should be a non issue
+		 * because if the affinity update happens right before all
+		 * cpus rendezvous in stop machine, there is no way that the
+		 * interrupt can be blocked on the target cpu because all cpus
+		 * loops first with interrupts enabled in stop machine, so the
+		 * old vector is not yet cleaned up when the interrupt fires.
+		 *
+		 * So the only way to run into this issue is if the delivery
+		 * of the interrupt on the apic/system bus would be delayed
+		 * beyond the point where the target cpu disables interrupts
+		 * in stop machine. I doubt that it can happen, but at least
+		 * there is a theoretical chance. Virtualization might be
+		 * able to expose this, but AFAICT the IOAPIC emulation is not
+		 * as stupid as the real hardware.
+		 *
+		 * Anyway, there is nothing we can do about that at this point
+		 * w/o refactoring the whole fixup_irq() business completely.
+		 * We print at least the irq number and the old vector number,
+		 * so we have the necessary information when a problem in that
+		 * area arises.
+		 */
+		pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n",
+			irqd->irq, vector);
+	}
+	free_moved_vector(apicd);
+}
+
 #else
-# define apic_set_affinity	NULL
+# define apic_set_affinity		NULL
+# define apic_force_complete_move	NULL
 #endif
 
 static int apic_retrigger_irq(struct irq_data *irqd)
@@ -923,39 +1024,16 @@ static void x86_vector_msi_compose_msg(struct irq_data *data,
 }
 
 static struct irq_chip lapic_controller = {
-	.name			= "APIC",
-	.irq_ack		= apic_ack_edge,
-	.irq_set_affinity	= apic_set_affinity,
-	.irq_compose_msi_msg	= x86_vector_msi_compose_msg,
-	.irq_retrigger		= apic_retrigger_irq,
+	.name				= "APIC",
+	.irq_ack			= apic_ack_edge,
+	.irq_set_affinity		= apic_set_affinity,
+	.irq_compose_msi_msg		= x86_vector_msi_compose_msg,
+	.irq_force_complete_move	= apic_force_complete_move,
+	.irq_retrigger			= apic_retrigger_irq,
 };
 
 #ifdef CONFIG_SMP
 
-static void free_moved_vector(struct apic_chip_data *apicd)
-{
-	unsigned int vector = apicd->prev_vector;
-	unsigned int cpu = apicd->prev_cpu;
-	bool managed = apicd->is_managed;
-
-	/*
-	 * Managed interrupts are usually not migrated away
-	 * from an online CPU, but CPU isolation 'managed_irq'
-	 * can make that happen.
-	 * 1) Activation does not take the isolation into account
-	 *    to keep the code simple
-	 * 2) Migration away from an isolated CPU can happen when
-	 *    a non-isolated CPU which is in the calculated
-	 *    affinity mask comes online.
-	 */
-	trace_vector_free_moved(apicd->irq, cpu, vector, managed);
-	irq_matrix_free(vector_matrix, cpu, vector, managed);
-	per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
-	hlist_del_init(&apicd->clist);
-	apicd->prev_vector = 0;
-	apicd->move_in_progress = 0;
-}
-
 static void __vector_cleanup(struct vector_cleanup *cl, bool check_irr)
 {
 	struct apic_chip_data *apicd;
@@ -1068,99 +1146,6 @@ void irq_complete_move(struct irq_cfg *cfg)
 		__vector_schedule_cleanup(apicd);
 }
 
-/*
- * Called from fixup_irqs() with @desc->lock held and interrupts disabled.
- */
-void irq_force_complete_move(struct irq_desc *desc)
-{
-	unsigned int cpu = smp_processor_id();
-	struct apic_chip_data *apicd;
-	struct irq_data *irqd;
-	unsigned int vector;
-
-	/*
-	 * The function is called for all descriptors regardless of which
-	 * irqdomain they belong to. For example if an IRQ is provided by
-	 * an irq_chip as part of a GPIO driver, the chip data for that
-	 * descriptor is specific to the irq_chip in question.
-	 *
-	 * Check first that the chip_data is what we expect
-	 * (apic_chip_data) before touching it any further.
-	 */
-	irqd = irq_domain_get_irq_data(x86_vector_domain,
-				       irq_desc_get_irq(desc));
-	if (!irqd)
-		return;
-
-	raw_spin_lock(&vector_lock);
-	apicd = apic_chip_data(irqd);
-	if (!apicd)
-		goto unlock;
-
-	/*
-	 * If prev_vector is empty or the descriptor is neither currently
-	 * nor previously on the outgoing CPU no action required.
-	 */
-	vector = apicd->prev_vector;
-	if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu))
-		goto unlock;
-
-	/*
-	 * This is tricky. If the cleanup of the old vector has not been
-	 * done yet, then the following setaffinity call will fail with
-	 * -EBUSY. This can leave the interrupt in a stale state.
-	 *
-	 * All CPUs are stuck in stop machine with interrupts disabled so
-	 * calling __irq_complete_move() would be completely pointless.
-	 *
-	 * 1) The interrupt is in move_in_progress state. That means that we
-	 *    have not seen an interrupt since the io_apic was reprogrammed to
-	 *    the new vector.
-	 *
-	 * 2) The interrupt has fired on the new vector, but the cleanup IPIs
-	 *    have not been processed yet.
-	 */
-	if (apicd->move_in_progress) {
-		/*
-		 * In theory there is a race:
-		 *
-		 * set_ioapic(new_vector) <-- Interrupt is raised before update
-		 *			      is effective, i.e. it's raised on
-		 *			      the old vector.
-		 *
-		 * So if the target cpu cannot handle that interrupt before
-		 * the old vector is cleaned up, we get a spurious interrupt
-		 * and in the worst case the ioapic irq line becomes stale.
-		 *
-		 * But in case of cpu hotplug this should be a non issue
-		 * because if the affinity update happens right before all
-		 * cpus rendezvous in stop machine, there is no way that the
-		 * interrupt can be blocked on the target cpu because all cpus
-		 * loops first with interrupts enabled in stop machine, so the
-		 * old vector is not yet cleaned up when the interrupt fires.
-		 *
-		 * So the only way to run into this issue is if the delivery
-		 * of the interrupt on the apic/system bus would be delayed
-		 * beyond the point where the target cpu disables interrupts
-		 * in stop machine. I doubt that it can happen, but at least
-		 * there is a theoretical chance. Virtualization might be
-		 * able to expose this, but AFAICT the IOAPIC emulation is not
-		 * as stupid as the real hardware.
-		 *
-		 * Anyway, there is nothing we can do about that at this point
-		 * w/o refactoring the whole fixup_irq() business completely.
-		 * We print at least the irq number and the old vector number,
-		 * so we have the necessary information when a problem in that
-		 * area arises.
-		 */
-		pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n",
-			irqd->irq, vector);
-	}
-	free_moved_vector(apicd);
-unlock:
-	raw_spin_unlock(&vector_lock);
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 /*
  * Note, this is not accurate accounting, but at least good enough to