x86/ioapic: Generate RTE directly from parent irqchip's MSI message

The I/O-APIC generates an MSI cycle with address/data bits taken from its
Redirection Table Entry in some combination which used to make sense, but
now is just a bunch of bits which get passed through in some seemingly
arbitrary order.

Instead of making IRQ remapping drivers directly frob the I/OA-PIC RTE, let
them just do their job and generate an MSI message. The bit swizzling to
turn that MSI message into the I/O-APIC's RTE is the same in all cases,
since it's a function of the I/O-APIC hardware. The IRQ remappers have no
real need to get involved with that.

The only slight caveat is that the I/OAPIC is interpreting some of those
fields too, and it does want the 'vector' field to be unique to make EOI
work. The AMD IOMMU happens to put its IRTE index in the bits that the
I/O-APIC thinks are the vector field, and accommodates this requirement by
reserving the first 32 indices for the I/O-APIC.  The Intel IOMMU doesn't
actually use the bits that the I/O-APIC thinks are the vector field, so it
fills in the 'pin' value there instead.

[ tglx: Replaced the unreadably macro maze with the cleaned up RTE/msi_msg
  	bitfields and added commentry to explain the mapping magic ]

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201024213535.443185-22-dwmw2@infradead.org

3 files changed, 6 insertions, 68 deletions

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 3d72ec7bbbf8..9744cdbefd88 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -3669,7 +3669,6 @@ static void irq_remapping_prepare_irte(struct amd_ir_data *data,
 				       int devid, int index, int sub_handle)
 {
 	struct irq_2_irte *irte_info = &data->irq_2_irte;
-	struct IO_APIC_route_entry *entry;
 	struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
 
 	if (!iommu)
@@ -3683,17 +3682,6 @@ static void irq_remapping_prepare_irte(struct amd_ir_data *data,
 
 	switch (info->type) {
 	case X86_IRQ_ALLOC_TYPE_IOAPIC:
-		/* Setup IOAPIC entry */
-		entry = info->ioapic.entry;
-		info->ioapic.entry = NULL;
-		memset(entry, 0, sizeof(*entry));
-		entry->vector		= index;
-		entry->is_level		= info->ioapic.is_level;
-		entry->active_low	= info->ioapic.active_low;
-		/* Mask level triggered irqs. */
-		entry->masked		= info->ioapic.is_level;
-		break;
-
 	case X86_IRQ_ALLOC_TYPE_HPET:
 	case X86_IRQ_ALLOC_TYPE_PCI_MSI:
 	case X86_IRQ_ALLOC_TYPE_PCI_MSIX:
diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c
index 1ab7eb918a5c..37dd485a5640 100644
--- a/drivers/iommu/hyperv-iommu.c
+++ b/drivers/iommu/hyperv-iommu.c
@@ -40,7 +40,6 @@ static int hyperv_ir_set_affinity(struct irq_data *data,
 {
 	struct irq_data *parent = data->parent_data;
 	struct irq_cfg *cfg = irqd_cfg(data);
-	struct IO_APIC_route_entry *entry;
 	int ret;
 
 	/* Return error If new irq affinity is out of ioapic_max_cpumask. */
@@ -51,9 +50,6 @@ static int hyperv_ir_set_affinity(struct irq_data *data,
 	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
 		return ret;
 
-	entry = data->chip_data;
-	entry->destid_0_7 = cfg->dest_apicid;
-	entry->vector = cfg->vector;
 	send_cleanup_vector(cfg);
 
 	return 0;
@@ -90,20 +86,6 @@ static int hyperv_irq_remapping_alloc(struct irq_domain *domain,
 	irq_data->chip = &hyperv_ir_chip;
 
 	/*
-	 * If there is interrupt remapping function of IOMMU, setting irq
-	 * affinity only needs to change IRTE of IOMMU. But Hyper-V doesn't
-	 * support interrupt remapping function, setting irq affinity of IO-APIC
-	 * interrupts still needs to change IO-APIC registers. But ioapic_
-	 * configure_entry() will ignore value of cfg->vector and cfg->
-	 * dest_apicid when IO-APIC's parent irq domain is not the vector
-	 * domain.(See ioapic_configure_entry()) In order to setting vector
-	 * and dest_apicid to IO-APIC register, IO-APIC entry pointer is saved
-	 * in the chip_data and hyperv_irq_remapping_activate()/hyperv_ir_set_
-	 * affinity() set vector and dest_apicid directly into IO-APIC entry.
-	 */
-	irq_data->chip_data = info->ioapic.entry;
-
-	/*
 	 * Hypver-V IO APIC irq affinity should be in the scope of
 	 * ioapic_max_cpumask because no irq remapping support.
 	 */
@@ -119,22 +101,9 @@ static void hyperv_irq_remapping_free(struct irq_domain *domain,
 	irq_domain_free_irqs_common(domain, virq, nr_irqs);
 }
 
-static int hyperv_irq_remapping_activate(struct irq_domain *domain,
-			  struct irq_data *irq_data, bool reserve)
-{
-	struct irq_cfg *cfg = irqd_cfg(irq_data);
-	struct IO_APIC_route_entry *entry = irq_data->chip_data;
-
-	entry->destid_0_7 = cfg->dest_apicid;
-	entry->vector = cfg->vector;
-
-	return 0;
-}
-
 static const struct irq_domain_ops hyperv_ir_domain_ops = {
 	.alloc = hyperv_irq_remapping_alloc,
 	.free = hyperv_irq_remapping_free,
-	.activate = hyperv_irq_remapping_activate,
 };
 
 static int __init hyperv_prepare_irq_remapping(void)
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index 625bdb9f1627..96c84b19940e 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -1280,9 +1280,9 @@ static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data,
 					     int index, int sub_handle)
 {
 	struct irte *irte = &data->irte_entry;
-	struct IO_APIC_route_entry *entry;
 
 	prepare_irte(irte, irq_cfg->vector, irq_cfg->dest_apicid);
+
 	switch (info->type) {
 	case X86_IRQ_ALLOC_TYPE_IOAPIC:
 		/* Set source-id of interrupt request */
@@ -1293,39 +1293,20 @@ static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data,
 			irte->trigger_mode, irte->dlvry_mode,
 			irte->avail, irte->vector, irte->dest_id,
 			irte->sid, irte->sq, irte->svt);
-
-		entry = info->ioapic.entry;
-		info->ioapic.entry = NULL;
-		memset(entry, 0, sizeof(*entry));
-		entry->ir_index_15	= !!(index & 0x8000);
-		entry->ir_format	= true;
-		entry->ir_index_0_14	= index & 0x7fff;
-		/*
-		 * IO-APIC RTE will be configured with virtual vector.
-		 * irq handler will do the explicit EOI to the io-apic.
-		 */
-		entry->vector		= info->ioapic.pin;
-		entry->is_level		= info->ioapic.is_level;
-		entry->active_low	= info->ioapic.active_low;
-		/* Mask level triggered irqs. */
-		entry->masked		= info->ioapic.is_level;
+		sub_handle = info->ioapic.pin;
 		break;
-
 	case X86_IRQ_ALLOC_TYPE_HPET:
+		set_hpet_sid(irte, info->devid);
+		break;
 	case X86_IRQ_ALLOC_TYPE_PCI_MSI:
 	case X86_IRQ_ALLOC_TYPE_PCI_MSIX:
-		if (info->type == X86_IRQ_ALLOC_TYPE_HPET)
-			set_hpet_sid(irte, info->devid);
-		else
-			set_msi_sid(irte, msi_desc_to_pci_dev(info->desc));
-
-		fill_msi_msg(&data->msi_entry, index, sub_handle);
+		set_msi_sid(irte, msi_desc_to_pci_dev(info->desc));
 		break;
-
 	default:
 		BUG_ON(1);
 		break;
 	}
+	fill_msi_msg(&data->msi_entry, index, sub_handle);
 }
 
 static void intel_free_irq_resources(struct irq_domain *domain,