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, 36 insertions, 56 deletions

diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index e66c77529ca9..477b740b2f26 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1458,20 +1458,20 @@ void restore_boot_irq_mode(void)
  *
  * by Matt Domsch <Matt_Domsch@dell.com>  Tue Dec 21 12:25:05 CST 1999
  */
-void __init setup_ioapic_ids_from_mpc_nocheck(void)
+static void __init setup_ioapic_ids_from_mpc_nocheck(void)
 {
+	DECLARE_BITMAP(phys_id_present_map, MAX_LOCAL_APIC);
+	const u32 broadcast_id = 0xF;
 	union IO_APIC_reg_00 reg_00;
-	physid_mask_t phys_id_present_map;
-	int ioapic_idx;
-	int i;
 	unsigned char old_id;
 	unsigned long flags;
+	int ioapic_idx, i;
 
 	/*
 	 * This is broken; anything with a real cpu count has to
 	 * circumvent this idiocy regardless.
 	 */
-	apic->ioapic_phys_id_map(&phys_cpu_present_map, &phys_id_present_map);
+	copy_phys_cpu_present_map(phys_id_present_map);
 
 	/*
 	 * Set the IOAPIC ID to the value stored in the MPC table.
@@ -1484,11 +1484,10 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void)
 
 		old_id = mpc_ioapic_id(ioapic_idx);
 
-		if (mpc_ioapic_id(ioapic_idx) >= get_physical_broadcast()) {
-			printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the MPC table!...\n",
-				ioapic_idx, mpc_ioapic_id(ioapic_idx));
-			printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
-				reg_00.bits.ID);
+		if (mpc_ioapic_id(ioapic_idx) >= broadcast_id) {
+			pr_err(FW_BUG "IO-APIC#%d ID is %d in the MPC table!...\n",
+			       ioapic_idx, mpc_ioapic_id(ioapic_idx));
+			pr_err("... fixing up to %d. (tell your hw vendor)\n", reg_00.bits.ID);
 			ioapics[ioapic_idx].mp_config.apicid = reg_00.bits.ID;
 		}
 
@@ -1497,23 +1496,21 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void)
 		 * system must have a unique ID or we get lots of nice
 		 * 'stuck on smp_invalidate_needed IPI wait' messages.
 		 */
-		if (apic->check_apicid_used(&phys_id_present_map,
-					    mpc_ioapic_id(ioapic_idx))) {
-			printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n",
-				ioapic_idx, mpc_ioapic_id(ioapic_idx));
-			for (i = 0; i < get_physical_broadcast(); i++)
-				if (!physid_isset(i, phys_id_present_map))
+		if (test_bit(mpc_ioapic_id(ioapic_idx), phys_id_present_map)) {
+			pr_err(FW_BUG "IO-APIC#%d ID %d is already used!...\n",
+			       ioapic_idx, mpc_ioapic_id(ioapic_idx));
+			for (i = 0; i < broadcast_id; i++)
+				if (!test_bit(i, phys_id_present_map))
 					break;
-			if (i >= get_physical_broadcast())
+			if (i >= broadcast_id)
 				panic("Max APIC ID exceeded!\n");
-			printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
-				i);
-			physid_set(i, phys_id_present_map);
+			pr_err("... fixing up to %d. (tell your hw vendor)\n", i);
+			set_bit(i, phys_id_present_map);
 			ioapics[ioapic_idx].mp_config.apicid = i;
 		} else {
 			apic_printk(APIC_VERBOSE, "Setting %d in the phys_id_present_map\n",
 				    mpc_ioapic_id(ioapic_idx));
-			physid_set(mpc_ioapic_id(ioapic_idx), phys_id_present_map);
+			set_bit(mpc_ioapic_id(ioapic_idx), phys_id_present_map);
 		}
 
 		/*
@@ -2209,7 +2206,7 @@ static inline void __init check_timer(void)
 	 * 8259A.
 	 */
 	if (pin1 == -1) {
-		panic_if_irq_remap("BIOS bug: timer not connected to IO-APIC");
+		panic_if_irq_remap(FW_BUG "Timer not connected to IO-APIC");
 		pin1 = pin2;
 		apic1 = apic2;
 		no_pin1 = 1;
@@ -2494,56 +2491,41 @@ unsigned int arch_dynirq_lower_bound(unsigned int from)
 #ifdef CONFIG_X86_32
 static int io_apic_get_unique_id(int ioapic, int apic_id)
 {
+	static DECLARE_BITMAP(apic_id_map, MAX_LOCAL_APIC);
+	const u32 broadcast_id = 0xF;
 	union IO_APIC_reg_00 reg_00;
-	static physid_mask_t apic_id_map = PHYSID_MASK_NONE;
-	physid_mask_t tmp;
 	unsigned long flags;
 	int i = 0;
 
-	/*
-	 * The P4 platform supports up to 256 APIC IDs on two separate APIC
-	 * buses (one for LAPICs, one for IOAPICs), where predecessors only
-	 * supports up to 16 on one shared APIC bus.
-	 *
-	 * TBD: Expand LAPIC/IOAPIC support on P4-class systems to take full
-	 *      advantage of new APIC bus architecture.
-	 */
-
-	if (physids_empty(apic_id_map))
-		apic->ioapic_phys_id_map(&phys_cpu_present_map, &apic_id_map);
+	/* Initialize the ID map */
+	if (bitmap_empty(apic_id_map, MAX_LOCAL_APIC))
+		copy_phys_cpu_present_map(apic_id_map);
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	reg_00.raw = io_apic_read(ioapic, 0);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
-	if (apic_id >= get_physical_broadcast()) {
-		printk(KERN_WARNING "IOAPIC[%d]: Invalid apic_id %d, trying "
-			"%d\n", ioapic, apic_id, reg_00.bits.ID);
+	if (apic_id >= broadcast_id) {
+		pr_warn("IOAPIC[%d]: Invalid apic_id %d, trying %d\n",
+			ioapic, apic_id, reg_00.bits.ID);
 		apic_id = reg_00.bits.ID;
 	}
 
-	/*
-	 * Every APIC in a system must have a unique ID or we get lots of nice
-	 * 'stuck on smp_invalidate_needed IPI wait' messages.
-	 */
-	if (apic->check_apicid_used(&apic_id_map, apic_id)) {
-
-		for (i = 0; i < get_physical_broadcast(); i++) {
-			if (!apic->check_apicid_used(&apic_id_map, i))
+	/* Every APIC in a system must have a unique ID */
+	if (test_bit(apic_id, apic_id_map)) {
+		for (i = 0; i < broadcast_id; i++) {
+			if (!test_bit(i, apic_id_map))
 				break;
 		}
 
-		if (i == get_physical_broadcast())
+		if (i == broadcast_id)
 			panic("Max apic_id exceeded!\n");
 
-		printk(KERN_WARNING "IOAPIC[%d]: apic_id %d already used, "
-			"trying %d\n", ioapic, apic_id, i);
-
+		pr_warn("IOAPIC[%d]: apic_id %d already used, trying %d\n", ioapic, apic_id, i);
 		apic_id = i;
 	}
 
-	physid_set_mask_of_physid(apic_id, &tmp);
-	physids_or(apic_id_map, apic_id_map, tmp);
+	set_bit(apic_id, apic_id_map);
 
 	if (reg_00.bits.ID != apic_id) {
 		reg_00.bits.ID = apic_id;
@@ -2569,11 +2551,9 @@ static int io_apic_get_unique_id(int ioapic, int apic_id)
 
 static u8 io_apic_unique_id(int idx, u8 id)
 {
-	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
-	    !APIC_XAPIC(boot_cpu_apic_version))
+	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && !APIC_XAPIC(boot_cpu_apic_version))
 		return io_apic_get_unique_id(idx, id);
-	else
-		return id;
+	return id;
 }
 #else
 static u8 io_apic_unique_id(int idx, u8 id)