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
  ...

3 files changed, 52 insertions, 27 deletions

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 330856803e90..9c848e36f209 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -4173,16 +4173,25 @@ static void irq_remapping_free(struct irq_domain *domain, unsigned int virq,
 	irq_domain_free_irqs_common(domain, virq, nr_irqs);
 }
 
+static void amd_ir_update_irte(struct irq_data *irqd, struct amd_iommu *iommu,
+			       struct amd_ir_data *ir_data,
+			       struct irq_2_irte *irte_info,
+			       struct irq_cfg *cfg);
+
 static int irq_remapping_activate(struct irq_domain *domain,
 				  struct irq_data *irq_data, bool early)
 {
 	struct amd_ir_data *data = irq_data->chip_data;
 	struct irq_2_irte *irte_info = &data->irq_2_irte;
 	struct amd_iommu *iommu = amd_iommu_rlookup_table[irte_info->devid];
+	struct irq_cfg *cfg = irqd_cfg(irq_data);
 
-	if (iommu)
-		iommu->irte_ops->activate(data->entry, irte_info->devid,
-					  irte_info->index);
+	if (!iommu)
+		return 0;
+
+	iommu->irte_ops->activate(data->entry, irte_info->devid,
+				  irte_info->index);
+	amd_ir_update_irte(irq_data, iommu, data, irte_info, cfg);
 	return 0;
 }
 
@@ -4270,6 +4279,22 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 	return modify_irte_ga(irte_info->devid, irte_info->index, irte, ir_data);
 }
 
+
+static void amd_ir_update_irte(struct irq_data *irqd, struct amd_iommu *iommu,
+			       struct amd_ir_data *ir_data,
+			       struct irq_2_irte *irte_info,
+			       struct irq_cfg *cfg)
+{
+
+	/*
+	 * Atomically updates the IRTE with the new destination, vector
+	 * and flushes the interrupt entry cache.
+	 */
+	iommu->irte_ops->set_affinity(ir_data->entry, irte_info->devid,
+				      irte_info->index, cfg->vector,
+				      cfg->dest_apicid);
+}
+
 static int amd_ir_set_affinity(struct irq_data *data,
 			       const struct cpumask *mask, bool force)
 {
@@ -4287,13 +4312,7 @@ static int amd_ir_set_affinity(struct irq_data *data,
 	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
 		return ret;
 
-	/*
-	 * Atomically updates the IRTE with the new destination, vector
-	 * and flushes the interrupt entry cache.
-	 */
-	iommu->irte_ops->set_affinity(ir_data->entry, irte_info->devid,
-			    irte_info->index, cfg->vector, cfg->dest_apicid);
-
+	amd_ir_update_irte(data, iommu, ir_data, irte_info, cfg);
 	/*
 	 * After this point, all the interrupts will start arriving
 	 * at the new destination. So, time to cleanup the previous
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 324163330eaa..76a193c7fcfc 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -1122,6 +1122,24 @@ struct irq_remap_ops intel_irq_remap_ops = {
 	.get_irq_domain		= intel_get_irq_domain,
 };
 
+static void intel_ir_reconfigure_irte(struct irq_data *irqd, bool force)
+{
+	struct intel_ir_data *ir_data = irqd->chip_data;
+	struct irte *irte = &ir_data->irte_entry;
+	struct irq_cfg *cfg = irqd_cfg(irqd);
+
+	/*
+	 * Atomically updates the IRTE with the new destination, vector
+	 * and flushes the interrupt entry cache.
+	 */
+	irte->vector = cfg->vector;
+	irte->dest_id = IRTE_DEST(cfg->dest_apicid);
+
+	/* Update the hardware only if the interrupt is in remapped mode. */
+	if (!force || ir_data->irq_2_iommu.mode == IRQ_REMAPPING)
+		modify_irte(&ir_data->irq_2_iommu, irte);
+}
+
 /*
  * Migrate the IO-APIC irq in the presence of intr-remapping.
  *
@@ -1140,27 +1158,15 @@ static int
 intel_ir_set_affinity(struct irq_data *data, const struct cpumask *mask,
 		      bool force)
 {
-	struct intel_ir_data *ir_data = data->chip_data;
-	struct irte *irte = &ir_data->irte_entry;
-	struct irq_cfg *cfg = irqd_cfg(data);
 	struct irq_data *parent = data->parent_data;
+	struct irq_cfg *cfg = irqd_cfg(data);
 	int ret;
 
 	ret = parent->chip->irq_set_affinity(parent, mask, force);
 	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
 		return ret;
 
-	/*
-	 * Atomically updates the IRTE with the new destination, vector
-	 * and flushes the interrupt entry cache.
-	 */
-	irte->vector = cfg->vector;
-	irte->dest_id = IRTE_DEST(cfg->dest_apicid);
-
-	/* Update the hardware only if the interrupt is in remapped mode. */
-	if (ir_data->irq_2_iommu.mode == IRQ_REMAPPING)
-		modify_irte(&ir_data->irq_2_iommu, irte);
-
+	intel_ir_reconfigure_irte(data, false);
 	/*
 	 * After this point, all the interrupts will start arriving
 	 * at the new destination. So, time to cleanup the previous
@@ -1393,9 +1399,7 @@ static void intel_irq_remapping_free(struct irq_domain *domain,
 static int intel_irq_remapping_activate(struct irq_domain *domain,
 					struct irq_data *irq_data, bool early)
 {
-	struct intel_ir_data *data = irq_data->chip_data;
-
-	modify_irte(&data->irq_2_iommu, &data->irte_entry);
+	intel_ir_reconfigure_irte(irq_data, true);
 	return 0;
 }
 
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 496ed9130600..e06607167858 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1441,6 +1441,8 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
 		pci_msi_domain_update_chip_ops(info);
 
 	info->flags |= MSI_FLAG_ACTIVATE_EARLY;
+	if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE))
+		info->flags |= MSI_FLAG_MUST_REACTIVATE;
 
 	domain = msi_create_irq_domain(fwnode, info, parent);
 	if (!domain)