[PART2 PATCH v4 08/11] iommu/amd: Implements irq_set_vcpu_affinity() hook to setup vapic mode for pass-through devices

[Suravee Suthikulpanit]

From: Suravee Suthikulpanit <Suravee.Suthikulpanit@xxxxxxx>

This patch implements irq_set_vcpu_affinity() function to set up interrupt
remapping table entry with vapic mode for pass-through devices.

In case requirements for vapic mode are not met, it falls back to set up
the IRTE in legacy mode.

Signed-off-by: Suravee Suthikulpanit <Suravee.Suthikulpanit@xxxxxxx>
---
 drivers/iommu/amd_iommu.c | 68 ++++++++++++++++++++++++++++++++++++++++++++---
 include/linux/amd-iommu.h |  6 +++++
 2 files changed, 70 insertions(+), 4 deletions(-)

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 4a337dc..1b81af8 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -3907,7 +3907,8 @@ out:
 	return index;
 }
 
-static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte)
+static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
+			  struct amd_ir_data *data)
 {
 	struct irq_remap_table *table;
 	struct amd_iommu *iommu;
@@ -3933,6 +3934,8 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte)
 	entry->hi.fields.ga_root_ptr = tmp.hi.fields.ga_root_ptr;
 	entry->lo.val = irte->lo.val;
 	entry->lo.fields_remap.valid = 1;
+	if (data)
+		data->ref = entry;
 
 	spin_unlock_irqrestore(&table->lock, flags);
 
@@ -4031,7 +4034,7 @@ static void irte_ga_activate(void *entry, u16 devid, u16 index)
 	struct irte_ga *irte = (struct irte_ga *) entry;
 
 	irte->lo.fields_remap.valid = 1;
-	modify_irte_ga(devid, index, irte);
+	modify_irte_ga(devid, index, irte, NULL);
 }
 
 static void irte_deactivate(void *entry, u16 devid, u16 index)
@@ -4047,7 +4050,7 @@ static void irte_ga_deactivate(void *entry, u16 devid, u16 index)
 	struct irte_ga *irte = (struct irte_ga *) entry;
 
 	irte->lo.fields_remap.valid = 0;
-	modify_irte_ga(devid, index, irte);
+	modify_irte_ga(devid, index, irte, NULL);
 }
 
 static void irte_set_affinity(void *entry, u16 devid, u16 index,
@@ -4068,7 +4071,7 @@ static void irte_ga_set_affinity(void *entry, u16 devid, u16 index,
 	irte->hi.fields.vector = vector;
 	irte->lo.fields_remap.destination = dest_apicid;
 	irte->lo.fields_remap.guest_mode = 0;
-	modify_irte_ga(devid, index, irte);
+	modify_irte_ga(devid, index, irte, NULL);
 }
 
 #define IRTE_ALLOCATED (~1U)
@@ -4403,6 +4406,62 @@ static struct irq_domain_ops amd_ir_domain_ops = {
 	.deactivate = irq_remapping_deactivate,
 };
 
+static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
+{
+	unsigned long flags;
+	struct amd_iommu *iommu;
+	struct amd_iommu_pi_data *pi_data = vcpu_info;
+	struct vcpu_data *vcpu_pi_info = pi_data->vcpu_data;
+	struct amd_ir_data *ir_data = data->chip_data;
+	struct irte_ga *irte = (struct irte_ga *) ir_data->entry;
+	struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
+
+	/* Note:
+	 * SVM tries to set up for VAPIC mode, but we are in
+	 * legacy mode. So, we force legacy mode instead.
+	 */
+	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)) {
+		pr_debug("AMD-Vi: %s: Fall back to using intr legacy remap\n",
+			 __func__);
+		vcpu_pi_info = NULL;
+	}
+
+	iommu = amd_iommu_rlookup_table[irte_info->devid];
+	if (iommu == NULL)
+		return -EINVAL;
+
+	spin_lock_irqsave(&iommu->gatag_ir_hash_lock, flags);
+
+	if (vcpu_pi_info) {
+		/* Setting */
+		irte->hi.fields.vector = vcpu_pi_info->vector;
+		irte->lo.fields_vapic.guest_mode = 1;
+		irte->lo.fields_vapic.ga_tag =
+			AMD_IOMMU_GATAG(pi_data->vm_id, pi_data->vcpu_id);
+
+		if (!hash_hashed(&ir_data->hnode))
+			hash_add(iommu->gatag_ir_hash, &ir_data->hnode,
+				 (u16)(irte->lo.fields_vapic.ga_tag));
+	} else {
+		/* Un-Setting */
+		struct irq_cfg *cfg = irqd_cfg(data);
+
+		irte->hi.val = 0;
+		irte->lo.val = 0;
+		irte->hi.fields.vector = cfg->vector;
+		irte->lo.fields_remap.guest_mode = 0;
+		irte->lo.fields_remap.destination = cfg->dest_apicid;
+		irte->lo.fields_remap.int_type = apic->irq_delivery_mode;
+		irte->lo.fields_remap.dm = apic->irq_dest_mode;
+
+		hash_del(&ir_data->hnode);
+	}
+
+	spin_unlock_irqrestore(&iommu->gatag_ir_hash_lock, flags);
+
+	return modify_irte_ga(irte_info->devid, irte_info->index, irte, ir_data);
+}
+
 static int amd_ir_set_affinity(struct irq_data *data,
 			       const struct cpumask *mask, bool force)
 {
@@ -4447,6 +4506,7 @@ static void ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg)
 static struct irq_chip amd_ir_chip = {
 	.irq_ack = ir_ack_apic_edge,
 	.irq_set_affinity = amd_ir_set_affinity,
+	.irq_set_vcpu_affinity = amd_ir_set_vcpu_affinity,
 	.irq_compose_msi_msg = ir_compose_msi_msg,
 };
 
diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h
index a6fc022..0928c26 100644
--- a/include/linux/amd-iommu.h
+++ b/include/linux/amd-iommu.h
@@ -22,6 +22,12 @@
 
 #include <linux/types.h>
 
+struct amd_iommu_pi_data {
+	u32 vcpu_id;
+	u32 vm_id;
+	struct vcpu_data *vcpu_data;
+};
+
 #ifdef CONFIG_AMD_IOMMU
 
 struct task_struct;
-- 
1.9.1