Merge branch 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 APIC updates from Thomas Gleixner:
 "This update provides a major overhaul of the APIC initialization and
  vector allocation code:

   - Unification of the APIC and interrupt mode setup which was
     scattered all over the place and was hard to follow. This also
     distangles the timer setup from the APIC initialization which
     brings a clear separation of functionality.

     Great detective work from Dou Lyiang!

   - Refactoring of the x86 vector allocation mechanism. The existing
     code was based on nested loops and rather convoluted APIC callbacks
     which had a horrible worst case behaviour and tried to serve all
     different use cases in one go. This led to quite odd hacks when
     supporting the new managed interupt facility for multiqueue devices
     and made it more or less impossible to deal with the vector space
     exhaustion which was a major roadblock for server hibernation.

     Aside of that the code dealing with cpu hotplug and the system
     vectors was disconnected from the actual vector management and
     allocation code, which made it hard to follow and maintain.

     Utilizing the new bitmap matrix allocator core mechanism, the new
     allocator and management code consolidates the handling of system
     vectors, legacy vectors, cpu hotplug mechanisms and the actual
     allocation which needs to be aware of system and legacy vectors and
     hotplug constraints into a single consistent entity.

     This has one visible change: The support for multi CPU targets of
     interrupts, which is only available on a certain subset of
     CPUs/APIC variants has been removed in favour of single interrupt
     targets. A proper analysis of the multi CPU target feature revealed
     that there is no real advantage as the vast majority of interrupts
     end up on the CPU with the lowest APIC id in the set of target CPUs
     anyway. That change was agreed on by the relevant folks and allowed
     to simplify the implementation significantly and to replace rather
     fragile constructs like the vector cleanup IPI with straight
     forward and solid code.

     Furthermore this allowed to cleanly separate the allocation details
     for legacy, normal and managed interrupts:

      * Legacy interrupts are not longer wasting 16 vectors
        unconditionally

      * Managed interrupts have now a guaranteed vector reservation, but
        the actual vector assignment happens when the interrupt is
        requested. It's guaranteed not to fail.

      * Normal interrupts no longer allocate vectors unconditionally
        when the interrupt is set up (IO/APIC init or MSI(X) enable).
        The mechanism has been switched to a best effort reservation
        mode. The actual allocation happens when the interrupt is
        requested. Contrary to managed interrupts the request can fail
        due to vector space exhaustion, but drivers must handle a fail
        of request_irq() anyway. When the interrupt is freed, the vector
        is handed back as well.

        This solves a long standing problem with large unconditional
        vector allocations for a certain class of enterprise devices
        which prevented server hibernation due to vector space
        exhaustion when the unused allocated vectors had to be migrated
        to CPU0 while unplugging all non boot CPUs.

     The code has been equipped with trace points and detailed debugfs
     information to aid analysis of the vector space"

* 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (60 commits)
  x86/vector/msi: Select CONFIG_GENERIC_IRQ_RESERVATION_MODE
  PCI/MSI: Set MSI_FLAG_MUST_REACTIVATE in core code
  genirq: Add config option for reservation mode
  x86/vector: Use correct per cpu variable in free_moved_vector()
  x86/apic/vector: Ignore set_affinity call for inactive interrupts
  x86/apic: Fix spelling mistake: "symmectic" -> "symmetric"
  x86/apic: Use dead_cpu instead of current CPU when cleaning up
  ACPI/init: Invoke early ACPI initialization earlier
  x86/vector: Respect affinity mask in irq descriptor
  x86/irq: Simplify hotplug vector accounting
  x86/vector: Switch IOAPIC to global reservation mode
  x86/vector/msi: Switch to global reservation mode
  x86/vector: Handle managed interrupts proper
  x86/io_apic: Reevaluate vector configuration on activate()
  iommu/amd: Reevaluate vector configuration on activate()
  iommu/vt-d: Reevaluate vector configuration on activate()
  x86/apic/msi: Force reactivation of interrupts at startup time
  x86/vector: Untangle internal state from irq_cfg
  x86/vector: Compile SMP only code conditionally
  x86/apic: Remove unused callbacks
  ...

1 files changed, 32 insertions, 67 deletions

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c58e81a58722..5f59e6bee123 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -256,14 +256,14 @@ static void notrace start_secondary(void *unused)
 	check_tsc_sync_target();
 
 	/*
-	 * Lock vector_lock and initialize the vectors on this cpu
-	 * before setting the cpu online. We must set it online with
-	 * vector_lock held to prevent a concurrent setup/teardown
-	 * from seeing a half valid vector space.
+	 * Lock vector_lock, set CPU online and bring the vector
+	 * allocator online. Online must be set with vector_lock held
+	 * to prevent a concurrent irq setup/teardown from seeing a
+	 * half valid vector space.
 	 */
 	lock_vector_lock();
-	setup_vector_irq(smp_processor_id());
 	set_cpu_online(smp_processor_id(), true);
+	lapic_online();
 	unlock_vector_lock();
 	cpu_set_state_online(smp_processor_id());
 	x86_platform.nmi_init();
@@ -1191,17 +1191,10 @@ static __init void disable_smp(void)
 	cpumask_set_cpu(0, topology_core_cpumask(0));
 }
 
-enum {
-	SMP_OK,
-	SMP_NO_CONFIG,
-	SMP_NO_APIC,
-	SMP_FORCE_UP,
-};
-
 /*
  * Various sanity checks.
  */
-static int __init smp_sanity_check(unsigned max_cpus)
+static void __init smp_sanity_check(void)
 {
 	preempt_disable();
 
@@ -1239,16 +1232,6 @@ static int __init smp_sanity_check(unsigned max_cpus)
 	}
 
 	/*
-	 * If we couldn't find an SMP configuration at boot time,
-	 * get out of here now!
-	 */
-	if (!smp_found_config && !acpi_lapic) {
-		preempt_enable();
-		pr_notice("SMP motherboard not detected\n");
-		return SMP_NO_CONFIG;
-	}
-
-	/*
 	 * Should not be necessary because the MP table should list the boot
 	 * CPU too, but we do it for the sake of robustness anyway.
 	 */
@@ -1258,29 +1241,6 @@ static int __init smp_sanity_check(unsigned max_cpus)
 		physid_set(hard_smp_processor_id(), phys_cpu_present_map);
 	}
 	preempt_enable();
-
-	/*
-	 * If we couldn't find a local APIC, then get out of here now!
-	 */
-	if (APIC_INTEGRATED(boot_cpu_apic_version) &&
-	    !boot_cpu_has(X86_FEATURE_APIC)) {
-		if (!disable_apic) {
-			pr_err("BIOS bug, local APIC #%d not detected!...\n",
-				boot_cpu_physical_apicid);
-			pr_err("... forcing use of dummy APIC emulation (tell your hw vendor)\n");
-		}
-		return SMP_NO_APIC;
-	}
-
-	/*
-	 * If SMP should be disabled, then really disable it!
-	 */
-	if (!max_cpus) {
-		pr_info("SMP mode deactivated\n");
-		return SMP_FORCE_UP;
-	}
-
-	return SMP_OK;
 }
 
 static void __init smp_cpu_index_default(void)
@@ -1295,9 +1255,18 @@ static void __init smp_cpu_index_default(void)
 	}
 }
 
+static void __init smp_get_logical_apicid(void)
+{
+	if (x2apic_mode)
+		cpu0_logical_apicid = apic_read(APIC_LDR);
+	else
+		cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
+}
+
 /*
- * Prepare for SMP bootup.  The MP table or ACPI has been read
- * earlier.  Just do some sanity checking here and enable APIC mode.
+ * Prepare for SMP bootup.
+ * @max_cpus: configured maximum number of CPUs, It is a legacy parameter
+ *            for common interface support.
  */
 void __init native_smp_prepare_cpus(unsigned int max_cpus)
 {
@@ -1329,31 +1298,27 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 
 	set_cpu_sibling_map(0);
 
-	switch (smp_sanity_check(max_cpus)) {
-	case SMP_NO_CONFIG:
-		disable_smp();
-		if (APIC_init_uniprocessor())
-			pr_notice("Local APIC not detected. Using dummy APIC emulation.\n");
-		return;
-	case SMP_NO_APIC:
+	smp_sanity_check();
+
+	switch (apic_intr_mode) {
+	case APIC_PIC:
+	case APIC_VIRTUAL_WIRE_NO_CONFIG:
 		disable_smp();
 		return;
-	case SMP_FORCE_UP:
+	case APIC_SYMMETRIC_IO_NO_ROUTING:
 		disable_smp();
-		apic_bsp_setup(false);
+		/* Setup local timer */
+		x86_init.timers.setup_percpu_clockev();
 		return;
-	case SMP_OK:
+	case APIC_VIRTUAL_WIRE:
+	case APIC_SYMMETRIC_IO:
 		break;
 	}
 
-	if (read_apic_id() != boot_cpu_physical_apicid) {
-		panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
-		     read_apic_id(), boot_cpu_physical_apicid);
-		/* Or can we switch back to PIC here? */
-	}
+	/* Setup local timer */
+	x86_init.timers.setup_percpu_clockev();
 
-	default_setup_apic_routing();
-	cpu0_logical_apicid = apic_bsp_setup(false);
+	smp_get_logical_apicid();
 
 	pr_info("CPU0: ");
 	print_cpu_info(&cpu_data(0));
@@ -1398,7 +1363,6 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 
 	nmi_selftest();
 	impress_friends();
-	setup_ioapic_dest();
 	mtrr_aps_init();
 }
 
@@ -1557,13 +1521,14 @@ void cpu_disable_common(void)
 	remove_cpu_from_maps(cpu);
 	unlock_vector_lock();
 	fixup_irqs();
+	lapic_offline();
 }
 
 int native_cpu_disable(void)
 {
 	int ret;
 
-	ret = check_irq_vectors_for_cpu_disable();
+	ret = lapic_can_unplug_cpu();
 	if (ret)
 		return ret;