Merge tag 'x86-apic-2024-03-10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 APIC updates from Thomas Gleixner:
 "Rework of APIC enumeration and topology evaluation.

  The current implementation has a couple of shortcomings:

   - It fails to handle hybrid systems correctly.

   - The APIC registration code which handles CPU number assignents is
     in the middle of the APIC code and detached from the topology
     evaluation.

   - The various mechanisms which enumerate APICs, ACPI, MPPARSE and
     guest specific ones, tweak global variables as they see fit or in
     case of XENPV just hack around the generic mechanisms completely.

   - The CPUID topology evaluation code is sprinkled all over the vendor
     code and reevaluates global variables on every hotplug operation.

   - There is no way to analyze topology on the boot CPU before bringing
     up the APs. This causes problems for infrastructure like PERF which
     needs to size certain aspects upfront or could be simplified if
     that would be possible.

   - The APIC admission and CPU number association logic is
     incomprehensible and overly complex and needs to be kept around
     after boot instead of completing this right after the APIC
     enumeration.

  This update addresses these shortcomings with the following changes:

   - Rework the CPUID evaluation code so it is common for all vendors
     and provides information about the APIC ID segments in a uniform
     way independent of the number of segments (Thread, Core, Module,
     ..., Die, Package) so that this information can be computed instead
     of rewriting global variables of dubious value over and over.

   - A few cleanups and simplifcations of the APIC, IO/APIC and related
     interfaces to prepare for the topology evaluation changes.

   - Seperation of the parser stages so the early evaluation which tries
     to find the APIC address can be seperately overridden from the late
     evaluation which enumerates and registers the local APIC as further
     preparation for sanitizing the topology evaluation.

   - A new registration and admission logic which

       - encapsulates the inner workings so that parsers and guest logic
         cannot longer fiddle in it

       - uses the APIC ID segments to build topology bitmaps at
         registration time

       - provides a sane admission logic

       - allows to detect the crash kernel case, where CPU0 does not run
         on the real BSP, automatically. This is required to prevent
         sending INIT/SIPI sequences to the real BSP which would reset
         the whole machine. This was so far handled by a tedious command
         line parameter, which does not even work in nested crash
         scenarios.

       - Associates CPU number after the enumeration completed and
         prevents the late registration of APICs, which was somehow
         tolerated before.

   - Converting all parsers and guest enumeration mechanisms over to the
     new interfaces.

     This allows to get rid of all global variable tweaking from the
     parsers and enumeration mechanisms and sanitizes the XEN[PV]
     handling so it can use CPUID evaluation for the first time.

   - Mopping up existing sins by taking the information from the APIC ID
     segment bitmaps.

     This evaluates hybrid systems correctly on the boot CPU and allows
     for cleanups and fixes in the related drivers, e.g. PERF.

  The series has been extensively tested and the minimal late fallout
  due to a broken ACPI/MADT table has been addressed by tightening the
  admission logic further"

* tag 'x86-apic-2024-03-10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (76 commits)
  x86/topology: Ignore non-present APIC IDs in a present package
  x86/apic: Build the x86 topology enumeration functions on UP APIC builds too
  smp: Provide 'setup_max_cpus' definition on UP too
  smp: Avoid 'setup_max_cpus' namespace collision/shadowing
  x86/bugs: Use fixed addressing for VERW operand
  x86/cpu/topology: Get rid of cpuinfo::x86_max_cores
  x86/cpu/topology: Provide __num_[cores|threads]_per_package
  x86/cpu/topology: Rename topology_max_die_per_package()
  x86/cpu/topology: Rename smp_num_siblings
  x86/cpu/topology: Retrieve cores per package from topology bitmaps
  x86/cpu/topology: Use topology logical mapping mechanism
  x86/cpu/topology: Provide logical pkg/die mapping
  x86/cpu/topology: Simplify cpu_mark_primary_thread()
  x86/cpu/topology: Mop up primary thread mask handling
  x86/cpu/topology: Use topology bitmaps for sizing
  x86/cpu/topology: Let XEN/PV use topology from CPUID/MADT
  x86/xen/smp_pv: Count number of vCPUs early
  x86/cpu/topology: Assign hotpluggable CPUIDs during init
  x86/cpu/topology: Reject unknown APIC IDs on ACPI hotplug
  x86/topology: Add a mechanism to track topology via APIC IDs
  ...

1 files changed, 4 insertions, 203 deletions

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 4667bc4b00ab..a42d8a6f7149 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -19,6 +19,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/mc146818rtc.h>
 #include <linux/acpi_pmtmr.h>
+#include <linux/bitmap.h>
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
 #include <linux/memblock.h>
@@ -67,10 +68,6 @@
 
 #include "local.h"
 
-unsigned int num_processors;
-
-unsigned disabled_cpus;
-
 /* Processor that is doing the boot up */
 u32 boot_cpu_physical_apicid __ro_after_init = BAD_APICID;
 EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid);
@@ -78,18 +75,6 @@ EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid);
 u8 boot_cpu_apic_version __ro_after_init;
 
 /*
- * Bitmask of physically existing CPUs:
- */
-physid_mask_t phys_cpu_present_map;
-
-/*
- * Processor to be disabled specified by kernel parameter
- * disable_cpu_apicid=<int>, mostly used for the kdump 2nd kernel to
- * avoid undefined behaviour caused by sending INIT from AP to BSP.
- */
-static u32 disabled_cpu_apicid __ro_after_init = BAD_APICID;
-
-/*
  * This variable controls which CPUs receive external NMIs.  By default,
  * external NMIs are delivered only to the BSP.
  */
@@ -108,14 +93,6 @@ static inline bool apic_accessible(void)
 	return x2apic_mode || apic_mmio_base;
 }
 
-/*
- * Map cpu index to physical APIC ID
- */
-DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_apicid, BAD_APICID);
-DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid, U32_MAX);
-EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
-EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_acpiid);
-
 #ifdef CONFIG_X86_32
 /* Local APIC was disabled by the BIOS and enabled by the kernel */
 static int enabled_via_apicbase __ro_after_init;
@@ -261,16 +238,6 @@ u64 native_apic_icr_read(void)
 	return icr1 | ((u64)icr2 << 32);
 }
 
-#ifdef CONFIG_X86_32
-/**
- * get_physical_broadcast - Get number of physical broadcast IDs
- */
-int get_physical_broadcast(void)
-{
-	return modern_apic() ? 0xff : 0xf;
-}
-#endif
-
 /**
  * lapic_get_maxlvt - get the maximum number of local vector table entries
  */
@@ -1549,9 +1516,6 @@ static void setup_local_APIC(void)
 		apic_write(APIC_ESR, 0);
 	}
 #endif
-	/* Validate that the APIC is registered if required */
-	BUG_ON(apic->apic_id_registered && !apic->apic_id_registered());
-
 	/*
 	 * Intel recommends to set DFR, LDR and TPR before enabling
 	 * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
@@ -1690,8 +1654,6 @@ void apic_ap_setup(void)
 	end_local_APIC_setup();
 }
 
-static __init void cpu_set_boot_apic(void);
-
 static __init void apic_read_boot_cpu_id(bool x2apic)
 {
 	/*
@@ -1706,7 +1668,8 @@ static __init void apic_read_boot_cpu_id(bool x2apic)
 		boot_cpu_physical_apicid = read_apic_id();
 		boot_cpu_apic_version = GET_APIC_VERSION(apic_read(APIC_LVR));
 	}
-	cpu_set_boot_apic();
+	topology_register_boot_apic(boot_cpu_physical_apicid);
+	x86_32_probe_bigsmp_early();
 }
 
 #ifdef CONFIG_X86_X2APIC
@@ -2091,7 +2054,6 @@ void __init init_apic_mappings(void)
 			pr_info("APIC: disable apic facility\n");
 			apic_disable();
 		}
-		num_processors = 1;
 	}
 }
 
@@ -2305,155 +2267,6 @@ void disconnect_bsp_APIC(int virt_wire_setup)
 	apic_write(APIC_LVT1, value);
 }
 
-/*
- * The number of allocated logical CPU IDs. Since logical CPU IDs are allocated
- * contiguously, it equals to current allocated max logical CPU ID plus 1.
- * All allocated CPU IDs should be in the [0, nr_logical_cpuids) range,
- * so the maximum of nr_logical_cpuids is nr_cpu_ids.
- *
- * NOTE: Reserve 0 for BSP.
- */
-static int nr_logical_cpuids = 1;
-
-/*
- * Used to store mapping between logical CPU IDs and APIC IDs.
- */
-u32 cpuid_to_apicid[] = { [0 ... NR_CPUS - 1] = BAD_APICID, };
-
-bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
-{
-	return phys_id == (u64)cpuid_to_apicid[cpu];
-}
-
-#ifdef CONFIG_SMP
-static void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid)
-{
-	/* Isolate the SMT bit(s) in the APICID and check for 0 */
-	u32 mask = (1U << (fls(smp_num_siblings) - 1)) - 1;
-
-	if (smp_num_siblings == 1 || !(apicid & mask))
-		cpumask_set_cpu(cpu, &__cpu_primary_thread_mask);
-}
-
-/*
- * Due to the utter mess of CPUID evaluation smp_num_siblings is not valid
- * during early boot. Initialize the primary thread mask before SMP
- * bringup.
- */
-static int __init smp_init_primary_thread_mask(void)
-{
-	unsigned int cpu;
-
-	/*
-	 * XEN/PV provides either none or useless topology information.
-	 * Pretend that all vCPUs are primary threads.
-	 */
-	if (xen_pv_domain()) {
-		cpumask_copy(&__cpu_primary_thread_mask, cpu_possible_mask);
-		return 0;
-	}
-
-	for (cpu = 0; cpu < nr_logical_cpuids; cpu++)
-		cpu_mark_primary_thread(cpu, cpuid_to_apicid[cpu]);
-	return 0;
-}
-early_initcall(smp_init_primary_thread_mask);
-#else
-static inline void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid) { }
-#endif
-
-/*
- * Should use this API to allocate logical CPU IDs to keep nr_logical_cpuids
- * and cpuid_to_apicid[] synchronized.
- */
-static int allocate_logical_cpuid(int apicid)
-{
-	int i;
-
-	/*
-	 * cpuid <-> apicid mapping is persistent, so when a cpu is up,
-	 * check if the kernel has allocated a cpuid for it.
-	 */
-	for (i = 0; i < nr_logical_cpuids; i++) {
-		if (cpuid_to_apicid[i] == apicid)
-			return i;
-	}
-
-	/* Allocate a new cpuid. */
-	if (nr_logical_cpuids >= nr_cpu_ids) {
-		WARN_ONCE(1, "APIC: NR_CPUS/possible_cpus limit of %u reached. "
-			     "Processor %d/0x%x and the rest are ignored.\n",
-			     nr_cpu_ids, nr_logical_cpuids, apicid);
-		return -EINVAL;
-	}
-
-	cpuid_to_apicid[nr_logical_cpuids] = apicid;
-	return nr_logical_cpuids++;
-}
-
-static void cpu_update_apic(int cpu, u32 apicid)
-{
-#if defined(CONFIG_SMP) || defined(CONFIG_X86_64)
-	early_per_cpu(x86_cpu_to_apicid, cpu) = apicid;
-#endif
-	set_cpu_possible(cpu, true);
-	physid_set(apicid, phys_cpu_present_map);
-	set_cpu_present(cpu, true);
-	num_processors++;
-
-	if (system_state != SYSTEM_BOOTING)
-		cpu_mark_primary_thread(cpu, apicid);
-}
-
-static __init void cpu_set_boot_apic(void)
-{
-	cpuid_to_apicid[0] = boot_cpu_physical_apicid;
-	cpu_update_apic(0, boot_cpu_physical_apicid);
-	x86_32_probe_bigsmp_early();
-}
-
-int generic_processor_info(int apicid)
-{
-	int cpu, max = nr_cpu_ids;
-
-	/* The boot CPU must be set before MADT/MPTABLE parsing happens */
-	if (cpuid_to_apicid[0] == BAD_APICID)
-		panic("Boot CPU APIC not registered yet\n");
-
-	if (apicid == boot_cpu_physical_apicid)
-		return 0;
-
-	if (disabled_cpu_apicid == apicid) {
-		int thiscpu = num_processors + disabled_cpus;
-
-		pr_warn("APIC: Disabling requested cpu. Processor %d/0x%x ignored.\n",
-			thiscpu, apicid);
-
-		disabled_cpus++;
-		return -ENODEV;
-	}
-
-	if (num_processors >= nr_cpu_ids) {
-		int thiscpu = max + disabled_cpus;
-
-		pr_warn("APIC: NR_CPUS/possible_cpus limit of %i reached. "
-			"Processor %d/0x%x ignored.\n", max, thiscpu, apicid);
-
-		disabled_cpus++;
-		return -EINVAL;
-	}
-
-	cpu = allocate_logical_cpuid(apicid);
-	if (cpu < 0) {
-		disabled_cpus++;
-		return -EINVAL;
-	}
-
-	cpu_update_apic(cpu, apicid);
-	return cpu;
-}
-
-
 void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg,
 			   bool dmar)
 {
@@ -2496,10 +2309,7 @@ EXPORT_SYMBOL_GPL(x86_msi_msg_get_destid);
 
 static void __init apic_bsp_up_setup(void)
 {
-#ifdef CONFIG_X86_64
-	apic_write(APIC_ID, apic->set_apic_id(boot_cpu_physical_apicid));
-#endif
-	physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
+	reset_phys_cpu_present_map(boot_cpu_physical_apicid);
 }
 
 /**
@@ -2845,15 +2655,6 @@ static int __init lapic_insert_resource(void)
  */
 late_initcall(lapic_insert_resource);
 
-static int __init apic_set_disabled_cpu_apicid(char *arg)
-{
-	if (!arg || !get_option(&arg, &disabled_cpu_apicid))
-		return -EINVAL;
-
-	return 0;
-}
-early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid);
-
 static int __init apic_set_extnmi(char *arg)
 {
 	if (!arg)