irqchip/gic-v4: GICv4.1 architecture support

index 563e87ed0766..45969927cc81 100644
@@ -141,12 +141,17 @@ static int its_send_vpe_cmd(struct its_vpe *vpe, struct its_cmd_info *info)
 int its_schedule_vpe(struct its_vpe *vpe, bool on)
 {
 	struct its_cmd_info info;
+	int ret;
 
 	WARN_ON(preemptible());
 
 	info.cmd_type = on ? SCHEDULE_VPE : DESCHEDULE_VPE;
 
-	return its_send_vpe_cmd(vpe, &info);
+	ret = its_send_vpe_cmd(vpe, &info);
+	if (!ret)
+		vpe->resident = on;
+
+	return ret;
 }
 
 int its_invall_vpe(struct its_vpe *vpe)

index af4f09c02bf1..4dc58d7a0010 100644
@@ -396,7 +396,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int irq,
 int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq,
 				 struct kvm_kernel_irq_routing_entry *irq_entry);
 
-void kvm_vgic_v4_enable_doorbell(struct kvm_vcpu *vcpu);
-void kvm_vgic_v4_disable_doorbell(struct kvm_vcpu *vcpu);
+int vgic_v4_load(struct kvm_vcpu *vcpu);
+int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db);
 
 #endif /* __KVM_ARM_VGIC_H */

index e6b155713b47..ab1396afe08a 100644
@@ -35,6 +35,8 @@ struct its_vpe {
 	/* Doorbell interrupt */
 	int			irq;
 	irq_hw_number_t		vpe_db_lpi;
+	/* VPE resident */
+	bool			resident;
 	/* VPE proxy mapping */
 	int			vpe_proxy_event;
 	/*

index 86c6aa1cb58e..bd2afcf9a13f 100644
@@ -322,20 +322,24 @@ void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
 	/*
 	 * If we're about to block (most likely because we've just hit a
 	 * WFI), we need to sync back the state of the GIC CPU interface
-	 * so that we have the lastest PMR and group enables. This ensures
+	 * so that we have the latest PMR and group enables. This ensures
 	 * that kvm_arch_vcpu_runnable has up-to-date data to decide
 	 * whether we have pending interrupts.
+	 *
+	 * For the same reason, we want to tell GICv4 that we need
+	 * doorbells to be signalled, should an interrupt become pending.
 	 */
 	preempt_disable();
 	kvm_vgic_vmcr_sync(vcpu);
+	vgic_v4_put(vcpu, true);
 	preempt_enable();
-
-	kvm_vgic_v4_enable_doorbell(vcpu);
 }
 
 void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
 {
-	kvm_vgic_v4_disable_doorbell(vcpu);
+	preempt_disable();
+	vgic_v4_load(vcpu);
+	preempt_enable();
 }
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)

index 8d69f007dd0c..48307a9eb1d8 100644
@@ -664,6 +664,8 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
 
 	if (has_vhe())
 		__vgic_v3_activate_traps(vcpu);
+
+	WARN_ON(vgic_v4_load(vcpu));
 }
 
 void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu)

@@ -676,6 +678,8 @@ void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu)
 
 void vgic_v3_put(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(vgic_v4_put(vcpu, false));
+
 	vgic_v3_vmcr_sync(vcpu);
 
 	kvm_call_hyp(__vgic_v3_save_aprs, vcpu);

93 lines not on this page · raw message

index 45a870cb63f5..99b02ca730a8 100644
@@ -857,8 +857,6 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 
-	WARN_ON(vgic_v4_sync_hwstate(vcpu));
-
 	/* An empty ap_list_head implies used_lrs == 0 */
 	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
 		return;

@@ -882,8 +880,6 @@ static inline void vgic_restore_state(struct kvm_vcpu *vcpu)
 /* Flush our emulation state into the GIC hardware before entering the guest. */
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 {
-	WARN_ON(vgic_v4_flush_hwstate(vcpu));
-
 	/*
 	 * If there are no virtual interrupts active or pending for this
 	 * VCPU, then there is no work to do and we can bail out without

index 83066a81b16a..c7fefd6b1c80 100644
@@ -316,7 +316,5 @@ void vgic_its_invalidate_cache(struct kvm *kvm);
 bool vgic_supports_direct_msis(struct kvm *kvm);
 int vgic_v4_init(struct kvm *kvm);
 void vgic_v4_teardown(struct kvm *kvm);
-int vgic_v4_sync_hwstate(struct kvm_vcpu *vcpu);
-int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu);
 
 #endif

index 62e54f1a248b..58cb233cf138 100644
@@ -1075,6 +1075,12 @@ static void lpi_write_config(struct irq_data *d, u8 clr, u8 set)
 		dsb(ishst);
 }
 
+static void wait_for_syncr(void __iomem *rdbase)
+{
+	while (gic_read_lpir(rdbase + GICR_SYNCR) & 1)
+		cpu_relax();
+}
+
 static void lpi_update_config(struct irq_data *d, u8 clr, u8 set)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);

@@ -2757,8 +2763,7 @@ static void its_vpe_db_proxy_move(struct its_vpe *vpe, int from, int to)
 
 		rdbase = per_cpu_ptr(gic_rdists->rdist, from)->rd_base;
 		gic_write_lpir(vpe->vpe_db_lpi, rdbase + GICR_CLRLPIR);
-		while (gic_read_lpir(rdbase + GICR_SYNCR) & 1)
-			cpu_relax();
+		wait_for_syncr(rdbase);
 
 		return;
 	}

@@ -2914,8 +2919,7 @@ static void its_vpe_send_inv(struct irq_data *d)
 
 		rdbase = per_cpu_ptr(gic_rdists->rdist, vpe->col_idx)->rd_base;
 		gic_write_lpir(vpe->vpe_db_lpi, rdbase + GICR_INVLPIR);
-		while (gic_read_lpir(rdbase + GICR_SYNCR) & 1)
-			cpu_relax();
+		wait_for_syncr(rdbase);
 	} else {
 		its_vpe_send_cmd(vpe, its_send_inv);
 	}

@@ -2957,8 +2961,7 @@ static int its_vpe_set_irqchip_state(struct irq_data *d,
 			gic_write_lpir(vpe->vpe_db_lpi, rdbase + GICR_SETLPIR);
 		} else {
 			gic_write_lpir(vpe->vpe_db_lpi, rdbase + GICR_CLRLPIR);
-			while (gic_read_lpir(rdbase + GICR_SYNCR) & 1)
-				cpu_relax();
+			wait_for_syncr(rdbase);
 		}
 	} else {
 		if (state)

index 58cb233cf138..3e33cdc08200 100644
@@ -175,6 +175,12 @@ static DEFINE_IDA(its_vpeid_ida);
 #define gic_data_rdist_rd_base()	(gic_data_rdist()->rd_base)
 #define gic_data_rdist_vlpi_base()	(gic_data_rdist_rd_base() + SZ_128K)
 
+static inline u32 its_get_event_id(struct irq_data *d)
+{
+	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+	return d->hwirq - its_dev->event_map.lpi_base;
+}
+
 static struct its_collection *dev_event_to_col(struct its_device *its_dev,
 					       u32 event)
 {

@@ -183,6 +189,13 @@ static struct its_collection *dev_event_to_col(struct its_device *its_dev,
 	return its->collections + its_dev->event_map.col_map[event];
 }
 
+static struct its_collection *irq_to_col(struct irq_data *d)
+{
+	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+
+	return dev_event_to_col(its_dev, its_get_event_id(d));
+}
+
 static struct its_collection *valid_col(struct its_collection *col)
 {
 	if (WARN_ON_ONCE(col->target_address & GENMASK_ULL(15, 0)))

@@ -1031,12 +1044,6 @@ static void its_send_vinvall(struct its_node *its, struct its_vpe *vpe)
  * irqchip functions - assumes MSI, mostly.
  */
 
-static inline u32 its_get_event_id(struct irq_data *d)
-{
-	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
-	return d->hwirq - its_dev->event_map.lpi_base;
-}
-
 static void lpi_write_config(struct irq_data *d, u8 clr, u8 set)
 {
 	irq_hw_number_t hwirq;

@@ -1081,12 +1088,28 @@ static void wait_for_syncr(void __iomem *rdbase)
 		cpu_relax();
 }
 
+static void direct_lpi_inv(struct irq_data *d)
+{
+	struct its_collection *col;
+	void __iomem *rdbase;
+
+	/* Target the redistributor this LPI is currently routed to */
+	col = irq_to_col(d);
+	rdbase = per_cpu_ptr(gic_rdists->rdist, col->col_id)->rd_base;
+	gic_write_lpir(d->hwirq, rdbase + GICR_INVLPIR);
+
+	wait_for_syncr(rdbase);
+}
+
 static void lpi_update_config(struct irq_data *d, u8 clr, u8 set)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 
 	lpi_write_config(d, clr, set);
-	its_send_inv(its_dev, its_get_event_id(d));
+	if (gic_rdists->has_direct_lpi && !irqd_is_forwarded_to_vcpu(d))
+		direct_lpi_inv(d);
+	else
+		its_send_inv(its_dev, its_get_event_id(d));
 }
 
 static void its_vlpi_set_doorbell(struct irq_data *d, bool enable)

@@ -2917,8 +2940,9 @@ static void its_vpe_send_inv(struct irq_data *d)
 	if (gic_rdists->has_direct_lpi) {
 		void __iomem *rdbase;
 
+		/* Target the redistributor this VPE is currently known on */
 		rdbase = per_cpu_ptr(gic_rdists->rdist, vpe->col_idx)->rd_base;
-		gic_write_lpir(vpe->vpe_db_lpi, rdbase + GICR_INVLPIR);
+		gic_write_lpir(d->parent_data->hwirq, rdbase + GICR_INVLPIR);
 		wait_for_syncr(rdbase);
 	} else {
 		its_vpe_send_cmd(vpe, its_send_inv);

index a47ed2ba2907..75ab3716a870 100644
@@ -702,6 +702,24 @@ static struct its_vpe *its_build_vmovp_cmd(struct its_node *its,
 	return valid_vpe(its, desc->its_vmovp_cmd.vpe);
 }
 
+static struct its_vpe *its_build_vinv_cmd(struct its_node *its,
+					  struct its_cmd_block *cmd,
+					  struct its_cmd_desc *desc)
+{
+	struct its_vlpi_map *map;
+
+	map = dev_event_to_vlpi_map(desc->its_inv_cmd.dev,
+				    desc->its_inv_cmd.event_id);
+
+	its_encode_cmd(cmd, GITS_CMD_INV);
+	its_encode_devid(cmd, desc->its_inv_cmd.dev->device_id);
+	its_encode_event_id(cmd, desc->its_inv_cmd.event_id);
+
+	its_fixup_cmd(cmd);
+
+	return valid_vpe(its, map->vpe);
+}
+
 static u64 its_cmd_ptr_to_offset(struct its_node *its,
 				 struct its_cmd_block *ptr)
 {

@@ -1068,6 +1086,20 @@ static void its_send_vinvall(struct its_node *its, struct its_vpe *vpe)
 	its_send_single_vcommand(its, its_build_vinvall_cmd, &desc);
 }
 
+static void its_send_vinv(struct its_device *dev, u32 event_id)
+{
+	struct its_cmd_desc desc;
+
+	/*
+	 * There is no real VINV command. This is just a normal INV,
+	 * with a VSYNC instead of a SYNC.
+	 */
+	desc.its_inv_cmd.dev = dev;
+	desc.its_inv_cmd.event_id = event_id;
+
+	its_send_single_vcommand(dev->its, its_build_vinv_cmd, &desc);
+}
+
 /*
  * irqchip functions - assumes MSI, mostly.
  */

@@ -1142,8 +1174,10 @@ static void lpi_update_config(struct irq_data *d, u8 clr, u8 set)
 	lpi_write_config(d, clr, set);
 	if (gic_rdists->has_direct_lpi && !irqd_is_forwarded_to_vcpu(d))
 		direct_lpi_inv(d);
-	else
+	else if (!irqd_is_forwarded_to_vcpu(d))
 		its_send_inv(its_dev, its_get_event_id(d));
+	else
+		its_send_vinv(its_dev, its_get_event_id(d));
 }
 
 static void its_vlpi_set_doorbell(struct irq_data *d, bool enable)

index 3e33cdc08200..b3c9bc0c3ecd 100644
@@ -102,6 +102,7 @@ struct its_node {
 	struct its_collection	*collections;
 	struct fwnode_handle	*fwnode_handle;
 	u64			(*get_msi_base)(struct its_device *its_dev);
+	u64			typer;
 	u64			cbaser_save;
 	u32			ctlr_save;
 	struct list_head	its_device_list;

@@ -112,10 +113,11 @@ struct its_node {
 	int			numa_node;
 	unsigned int		msi_domain_flags;
 	u32			pre_its_base; /* for Socionext Synquacer */
-	bool			is_v4;
 	int			vlpi_redist_offset;
 };
 
+#define is_v4(its)		(!!((its)->typer & GITS_TYPER_VLPIS))
+
 #define ITS_ITT_ALIGN		SZ_256
 
 /* The maximum number of VPEID bits supported by VLPI commands */

@@ -1019,7 +1021,7 @@ static void its_send_vmovp(struct its_vpe *vpe)
 
 	/* Emit VMOVPs */
 	list_for_each_entry(its, &its_nodes, entry) {
-		if (!its->is_v4)
+		if (!is_v4(its))
 			continue;
 
 		if (!vpe->its_vm->vlpi_count[its->list_nr])

@@ -1430,7 +1432,7 @@ static int its_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
 	struct its_cmd_info *info = vcpu_info;
 
 	/* Need a v4 ITS */
-	if (!its_dev->its->is_v4)
+	if (!is_v4(its_dev->its))
 		return -EINVAL;
 
 	/* Unmap request? */

@@ -2394,7 +2396,7 @@ static bool its_alloc_vpe_table(u32 vpe_id)
 	list_for_each_entry(its, &its_nodes, entry) {
 		struct its_baser *baser;
 
-		if (!its->is_v4)
+		if (!is_v4(its))
 			continue;
 
 		baser = its_get_baser(its, GITS_BASER_TYPE_VCPU);

@@ -2882,7 +2884,7 @@ static void its_vpe_invall(struct its_vpe *vpe)
 	struct its_node *its;
 
 	list_for_each_entry(its, &its_nodes, entry) {
-		if (!its->is_v4)
+		if (!is_v4(its))
 			continue;
 
 		if (its_list_map && !vpe->its_vm->vlpi_count[its->list_nr])

@@ -3150,7 +3152,7 @@ static int its_vpe_irq_domain_activate(struct irq_domain *domain,
 	vpe->col_idx = cpumask_first(cpu_online_mask);
 
 	list_for_each_entry(its, &its_nodes, entry) {
-		if (!its->is_v4)
+		if (!is_v4(its))
 			continue;
 
 		its_send_vmapp(its, vpe, true);

@@ -3176,7 +3178,7 @@ static void its_vpe_irq_domain_deactivate(struct irq_domain *domain,
 		return;
 
 	list_for_each_entry(its, &its_nodes, entry) {
-		if (!its->is_v4)
+		if (!is_v4(its))
 			continue;
 
 		its_send_vmapp(its, vpe, false);

@@ -3614,12 +3616,12 @@ static int __init its_probe_one(struct resource *res,
 	INIT_LIST_HEAD(&its->entry);
 	INIT_LIST_HEAD(&its->its_device_list);
 	typer = gic_read_typer(its_base + GITS_TYPER);
+	its->typer = typer;
 	its->base = its_base;
 	its->phys_base = res->start;
 	its->ite_size = GITS_TYPER_ITT_ENTRY_SIZE(typer);
 	its->device_ids = GITS_TYPER_DEVBITS(typer);
-	its->is_v4 = !!(typer & GITS_TYPER_VLPIS);
-	if (its->is_v4) {
+	if (is_v4(its)) {
 		if (!(typer & GITS_TYPER_VMOVP)) {
 			err = its_compute_its_list_map(res, its_base);
 			if (err < 0)

@@ -3686,7 +3688,7 @@ static int __init its_probe_one(struct resource *res,
 	gits_write_cwriter(0, its->base + GITS_CWRITER);
 	ctlr = readl_relaxed(its->base + GITS_CTLR);
 	ctlr |= GITS_CTLR_ENABLE;
-	if (its->is_v4)
+	if (is_v4(its))
 		ctlr |= GITS_CTLR_ImDe;
 	writel_relaxed(ctlr, its->base + GITS_CTLR);
 

@@ -4011,7 +4013,7 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists,
 		return err;
 
 	list_for_each_entry(its, &its_nodes, entry)
-		has_v4 |= its->is_v4;
+		has_v4 |= is_v4(its);
 
 	if (has_v4 & rdists->has_vlpis) {
 		if (its_init_vpe_domain() ||

index b3c9bc0c3ecd..3b046181ddfc 100644
@@ -6,6 +6,7 @@
 
 #include <linux/acpi.h>
 #include <linux/acpi_iort.h>
+#include <linux/bitfield.h>
 #include <linux/bitmap.h>
 #include <linux/cpu.h>
 #include <linux/crash_dump.h>

@@ -108,7 +109,6 @@ struct its_node {
 	struct list_head	its_device_list;
 	u64			flags;
 	unsigned long		list_nr;
-	u32			ite_size;
 	u32			device_ids;
 	int			numa_node;
 	unsigned int		msi_domain_flags;

@@ -2435,7 +2435,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	 * sized as a power of two (and you need at least one bit...).
 	 */
 	nr_ites = max(2, nvecs);
-	sz = nr_ites * its->ite_size;
+	sz = nr_ites * (FIELD_GET(GITS_TYPER_ITT_ENTRY_SIZE, its->typer) + 1);
 	sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1;
 	itt = kzalloc_node(sz, GFP_KERNEL, its->numa_node);
 	if (alloc_lpis) {

@@ -3250,7 +3250,8 @@ static bool __maybe_unused its_enable_quirk_qdf2400_e0065(void *data)
 	struct its_node *its = data;
 
 	/* On QDF2400, the size of the ITE is 16Bytes */
-	its->ite_size = 16;
+	its->typer &= ~GITS_TYPER_ITT_ENTRY_SIZE;
+	its->typer |= FIELD_PREP(GITS_TYPER_ITT_ENTRY_SIZE, 16 - 1);
 
 	return true;
 }

@@ -3619,7 +3620,6 @@ static int __init its_probe_one(struct resource *res,
 	its->typer = typer;
 	its->base = its_base;
 	its->phys_base = res->start;
-	its->ite_size = GITS_TYPER_ITT_ENTRY_SIZE(typer);
 	its->device_ids = GITS_TYPER_DEVBITS(typer);
 	if (is_v4(its)) {
 		if (!(typer & GITS_TYPER_VMOVP)) {

index 5cc10cf7cb3e..4bce7a904075 100644
@@ -334,7 +334,7 @@
 #define GITS_TYPER_PLPIS		(1UL << 0)
 #define GITS_TYPER_VLPIS		(1UL << 1)
 #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT	4
-#define GITS_TYPER_ITT_ENTRY_SIZE(r)	((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0xf) + 1)
+#define GITS_TYPER_ITT_ENTRY_SIZE	GENMASK_ULL(7, 4)
 #define GITS_TYPER_IDBITS_SHIFT		8
 #define GITS_TYPER_DEVBITS_SHIFT	13
 #define GITS_TYPER_DEVBITS(r)		((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1)

index 3b046181ddfc..6c91c7feadf3 100644
@@ -109,7 +109,6 @@ struct its_node {
 	struct list_head	its_device_list;
 	u64			flags;
 	unsigned long		list_nr;
-	u32			device_ids;
 	int			numa_node;
 	unsigned int		msi_domain_flags;
 	u32			pre_its_base; /* for Socionext Synquacer */

@@ -117,6 +116,7 @@ struct its_node {
 };
 
 #define is_v4(its)		(!!((its)->typer & GITS_TYPER_VLPIS))
+#define device_ids(its)		(FIELD_GET(GITS_TYPER_DEVBITS, (its)->typer) + 1)
 
 #define ITS_ITT_ALIGN		SZ_256
 

@@ -1938,9 +1938,9 @@ static bool its_parse_indirect_baser(struct its_node *its,
 	if (new_order >= MAX_ORDER) {
 		new_order = MAX_ORDER - 1;
 		ids = ilog2(PAGE_ORDER_TO_SIZE(new_order) / (int)esz);
-		pr_warn("ITS@%pa: %s Table too large, reduce ids %u->%u\n",
+		pr_warn("ITS@%pa: %s Table too large, reduce ids %llu->%u\n",
 			&its->phys_base, its_base_type_string[type],
-			its->device_ids, ids);
+			device_ids(its), ids);
 	}
 
 	*order = new_order;

@@ -1986,7 +1986,7 @@ static int its_alloc_tables(struct its_node *its)
 		case GITS_BASER_TYPE_DEVICE:
 			indirect = its_parse_indirect_baser(its, baser,
 							    psz, &order,
-							    its->device_ids);
+							    device_ids(its));
 			break;
 
 		case GITS_BASER_TYPE_VCPU:

@@ -2377,7 +2377,7 @@ static bool its_alloc_device_table(struct its_node *its, u32 dev_id)
 
 	/* Don't allow device id that exceeds ITS hardware limit */
 	if (!baser)
-		return (ilog2(dev_id) < its->device_ids);
+		return (ilog2(dev_id) < device_ids(its));
 
 	return its_alloc_table_entry(its, baser, dev_id);
 }

@@ -3229,8 +3229,9 @@ static bool __maybe_unused its_enable_quirk_cavium_22375(void *data)
 {
 	struct its_node *its = data;
 
-	/* erratum 22375: only alloc 8MB table size */
-	its->device_ids = 0x14;		/* 20 bits, 8MB */
+	/* erratum 22375: only alloc 8MB table size (20 bits) */
+	its->typer &= ~GITS_TYPER_DEVBITS;
+	its->typer |= FIELD_PREP(GITS_TYPER_DEVBITS, 20 - 1);
 	its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_22375;
 
 	return true;

@@ -3285,8 +3286,10 @@ static bool __maybe_unused its_enable_quirk_socionext_synquacer(void *data)
 		its->get_msi_base = its_irq_get_msi_base_pre_its;
 
 		ids = ilog2(pre_its_window[1]) - 2;
-		if (its->device_ids > ids)
-			its->device_ids = ids;
+		if (device_ids(its) > ids) {
+			its->typer &= ~GITS_TYPER_DEVBITS;
+			its->typer |= FIELD_PREP(GITS_TYPER_DEVBITS, ids - 1);
+		}
 
 		/* the pre-ITS breaks isolation, so disable MSI remapping */
 		its->msi_domain_flags &= ~IRQ_DOMAIN_FLAG_MSI_REMAP;

@@ -3519,7 +3522,7 @@ static int its_init_vpe_domain(void)
 	}
 
 	/* Use the last possible DevID */
-	devid = GENMASK(its->device_ids - 1, 0);
+	devid = GENMASK(device_ids(its) - 1, 0);
 	vpe_proxy.dev = its_create_device(its, devid, entries, false);
 	if (!vpe_proxy.dev) {
 		kfree(vpe_proxy.vpes);

@@ -3620,7 +3623,6 @@ static int __init its_probe_one(struct resource *res,
 	its->typer = typer;
 	its->base = its_base;
 	its->phys_base = res->start;
-	its->device_ids = GITS_TYPER_DEVBITS(typer);
 	if (is_v4(its)) {
 		if (!(typer & GITS_TYPER_VMOVP)) {
 			err = its_compute_its_list_map(res, its_base);

index 4bce7a904075..b6514e8893bf 100644
@@ -337,7 +337,7 @@
 #define GITS_TYPER_ITT_ENTRY_SIZE	GENMASK_ULL(7, 4)
 #define GITS_TYPER_IDBITS_SHIFT		8
 #define GITS_TYPER_DEVBITS_SHIFT	13
-#define GITS_TYPER_DEVBITS(r)		((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1)
+#define GITS_TYPER_DEVBITS		GENMASK_ULL(17, 13)
 #define GITS_TYPER_PTA			(1UL << 19)
 #define GITS_TYPER_HCC_SHIFT		24
 #define GITS_TYPER_HCC(r)		(((r) >> GITS_TYPER_HCC_SHIFT) & 0xff)

index 6c91c7feadf3..94c9c2e9f917 100644
@@ -1045,20 +1045,26 @@ static void its_send_vinvall(struct its_node *its, struct its_vpe *vpe)
 /*
  * irqchip functions - assumes MSI, mostly.
  */
+static struct its_vlpi_map *get_vlpi_map(struct irq_data *d)
+{
+	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+	u32 event = its_get_event_id(d);
+
+	if (!irqd_is_forwarded_to_vcpu(d))
+		return NULL;
+
+	return &its_dev->event_map.vlpi_maps[event];
+}
 
 static void lpi_write_config(struct irq_data *d, u8 clr, u8 set)
 {
+	struct its_vlpi_map *map = get_vlpi_map(d);
 	irq_hw_number_t hwirq;
 	void *va;
 	u8 *cfg;
 
-	if (irqd_is_forwarded_to_vcpu(d)) {
-		struct its_device *its_dev = irq_data_get_irq_chip_data(d);
-		u32 event = its_get_event_id(d);
-		struct its_vlpi_map *map;
-
-		va = page_address(its_dev->event_map.vm->vprop_page);
-		map = &its_dev->event_map.vlpi_maps[event];
+	if (map) {
+		va = page_address(map->vm->vprop_page);
 		hwirq = map->vintid;
 
 		/* Remember the updated property */

@@ -1351,19 +1357,18 @@ static int its_vlpi_map(struct irq_data *d, struct its_cmd_info *info)
 static int its_vlpi_get(struct irq_data *d, struct its_cmd_info *info)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
-	u32 event = its_get_event_id(d);
+	struct its_vlpi_map *map = get_vlpi_map(d);
 	int ret = 0;
 
 	mutex_lock(&its_dev->event_map.vlpi_lock);
 
-	if (!its_dev->event_map.vm ||
-	    !its_dev->event_map.vlpi_maps[event].vm) {
+	if (!its_dev->event_map.vm || !map->vm) {
 		ret = -EINVAL;
 		goto out;
 	}
 
 	/* Copy our mapping information to the incoming request */
-	*info->map = its_dev->event_map.vlpi_maps[event];
+	*info->map = *map;
 
 out:
 	mutex_unlock(&its_dev->event_map.vlpi_lock);

index 1edc99335a94..4f20caf9bc88 100644
@@ -849,8 +849,21 @@ static int __gic_update_rdist_properties(struct redist_region *region,
 					 void __iomem *ptr)
 {
 	u64 typer = gic_read_typer(ptr + GICR_TYPER);
+
 	gic_data.rdists.has_vlpis &= !!(typer & GICR_TYPER_VLPIS);
-	gic_data.rdists.has_direct_lpi &= !!(typer & GICR_TYPER_DirectLPIS);
+
+	/* RVPEID implies some form of DirectLPI, no matter what the doc says... :-/ */
+	gic_data.rdists.has_rvpeid &= !!(typer & GICR_TYPER_RVPEID);
+	gic_data.rdists.has_direct_lpi &= (!!(typer & GICR_TYPER_DirectLPIS) |
+					   gic_data.rdists.has_rvpeid);
+
+	/* Detect non-sensical configurations */
+	if (WARN_ON_ONCE(gic_data.rdists.has_rvpeid && !gic_data.rdists.has_vlpis)) {
+		gic_data.rdists.has_direct_lpi = false;
+		gic_data.rdists.has_vlpis = false;
+		gic_data.rdists.has_rvpeid = false;
+	}
+
 	gic_data.ppi_nr = min(GICR_TYPER_NR_PPIS(typer), gic_data.ppi_nr);
 
 	return 1;

@@ -863,9 +876,10 @@ static void gic_update_rdist_properties(void)
 	if (WARN_ON(gic_data.ppi_nr == UINT_MAX))
 		gic_data.ppi_nr = 0;
 	pr_info("%d PPIs implemented\n", gic_data.ppi_nr);
-	pr_info("%sVLPI support, %sdirect LPI support\n",
+	pr_info("%sVLPI support, %sdirect LPI support, %sRVPEID support\n",
 		!gic_data.rdists.has_vlpis ? "no " : "",
-		!gic_data.rdists.has_direct_lpi ? "no " : "");
+		!gic_data.rdists.has_direct_lpi ? "no " : "",
+		!gic_data.rdists.has_rvpeid ? "no " : "");
 }
 
 /* Check whether it's single security state view */

@@ -1546,6 +1560,7 @@ static int __init gic_init_bases(void __iomem *dist_base,
 						 &gic_data);
 	irq_domain_update_bus_token(gic_data.domain, DOMAIN_BUS_WIRED);
 	gic_data.rdists.rdist = alloc_percpu(typeof(*gic_data.rdists.rdist));
+	gic_data.rdists.has_rvpeid = true;
 	gic_data.rdists.has_vlpis = true;
 	gic_data.rdists.has_direct_lpi = true;
 

index b6514e8893bf..c98f34296599 100644
@@ -234,6 +234,7 @@
 #define GICR_TYPER_VLPIS		(1U << 1)
 #define GICR_TYPER_DirectLPIS		(1U << 3)
 #define GICR_TYPER_LAST			(1U << 4)
+#define GICR_TYPER_RVPEID		(1U << 7)
 
 #define GIC_V3_REDIST_SIZE		0x20000
 

@@ -613,6 +614,7 @@ struct rdists {
 	u64			flags;
 	u32			gicd_typer;
 	bool			has_vlpis;
+	bool			has_rvpeid;
 	bool			has_direct_lpi;
 };
 

index 94c9c2e9f917..40912b3fb0e1 100644
@@ -121,7 +121,16 @@ struct its_node {
 #define ITS_ITT_ALIGN		SZ_256
 
 /* The maximum number of VPEID bits supported by VLPI commands */
-#define ITS_MAX_VPEID_BITS	(16)
+#define ITS_MAX_VPEID_BITS						\
+	({								\
+		int nvpeid = 16;					\
+		if (gic_rdists->has_rvpeid &&				\
+		    gic_rdists->gicd_typer2 & GICD_TYPER2_VIL)		\
+			nvpeid = 1 + (gic_rdists->gicd_typer2 &		\
+				      GICD_TYPER2_VID);			\
+									\
+		nvpeid;							\
+	})
 #define ITS_MAX_VPEID		(1 << (ITS_MAX_VPEID_BITS))
 
 /* Convert page order to size in bytes */

index 4f20caf9bc88..50538709bd49 100644
@@ -1556,6 +1556,9 @@ static int __init gic_init_bases(void __iomem *dist_base,
 
 	pr_info("%d SPIs implemented\n", GIC_LINE_NR - 32);
 	pr_info("%d Extended SPIs implemented\n", GIC_ESPI_NR);
+
+	gic_data.rdists.gicd_typer2 = readl_relaxed(gic_data.dist_base + GICD_TYPER2);
+
 	gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops,
 						 &gic_data);
 	irq_domain_update_bus_token(gic_data.domain, DOMAIN_BUS_WIRED);

index c98f34296599..8c6be56da7e9 100644
@@ -13,6 +13,7 @@
 #define GICD_CTLR			0x0000
 #define GICD_TYPER			0x0004
 #define GICD_IIDR			0x0008
+#define GICD_TYPER2			0x000C
 #define GICD_STATUSR			0x0010
 #define GICD_SETSPI_NSR			0x0040
 #define GICD_CLRSPI_NSR			0x0048

@@ -89,6 +90,9 @@
 #define GICD_TYPER_ESPIS(typer)						\
 	(((typer) & GICD_TYPER_ESPI) ? GICD_TYPER_SPIS((typer) >> 27) : 0)
 
+#define GICD_TYPER2_VIL			(1U << 7)
+#define GICD_TYPER2_VID			GENMASK(4, 0)
+
 #define GICD_IROUTER_SPI_MODE_ONE	(0U << 31)
 #define GICD_IROUTER_SPI_MODE_ANY	(1U << 31)
 

@@ -613,6 +617,7 @@ struct rdists {
 	void			*prop_table_va;
 	u64			flags;
 	u32			gicd_typer;
+	u32			gicd_typer2;
 	bool			has_vlpis;
 	bool			has_rvpeid;
 	bool			has_direct_lpi;

index 50538709bd49..f0d33ac64a99 100644
@@ -34,6 +34,7 @@
 #define GICD_INT_NMI_PRI	(GICD_INT_DEF_PRI & ~0x80)
 
 #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996	(1ULL << 0)
+#define FLAGS_WORKAROUND_GICD_TYPER2_TX1	(1ULL << 1)
 
 struct redist_region {
 	void __iomem		*redist_base;

@@ -1455,6 +1456,15 @@ static bool gic_enable_quirk_msm8996(void *data)
 	return true;
 }
 
+static bool gic_enable_quirk_tx1(void *data)
+{
+	struct gic_chip_data *d = data;
+
+	d->flags |= FLAGS_WORKAROUND_GICD_TYPER2_TX1;
+
+	return true;
+}
+
 static bool gic_enable_quirk_hip06_07(void *data)
 {
 	struct gic_chip_data *d = data;

@@ -1493,6 +1503,12 @@ static const struct gic_quirk gic_quirks[] = {
 		.mask	= 0xffffffff,
 		.init	= gic_enable_quirk_hip06_07,
 	},
+	{
+		.desc	= "GICv3: Cavium TX1 GICD_TYPER2 erratum",
+		.iidr	= 0xa100034c,
+		.mask	= 0xfff00fff,
+		.init	= gic_enable_quirk_tx1,
+	},
 	{
 	}
 };

@@ -1557,7 +1573,12 @@ static int __init gic_init_bases(void __iomem *dist_base,
 	pr_info("%d SPIs implemented\n", GIC_LINE_NR - 32);
 	pr_info("%d Extended SPIs implemented\n", GIC_ESPI_NR);
 
-	gic_data.rdists.gicd_typer2 = readl_relaxed(gic_data.dist_base + GICD_TYPER2);
+	/*
+	 * ThunderX1 explodes on reading GICD_TYPER2, in total violation
+	 * of the spec (which says that reserved addresses are RES0).
+	 */
+	if (!(gic_data.flags & FLAGS_WORKAROUND_GICD_TYPER2_TX1))
+		gic_data.rdists.gicd_typer2 = readl_relaxed(gic_data.dist_base + GICD_TYPER2);
 
 	gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops,
 						 &gic_data);

index 0555f14cc8be..20bacab1d791 100644
@@ -10,6 +10,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/io.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
 #include <asm/barrier.h>
 #include <asm/cacheflush.h>
 #include <asm/cp15.h>

@@ -327,6 +328,7 @@ static inline u64 __gic_readq_nonatomic(const volatile void __iomem *addr)
 /*
  * GITS_VPROPBASER - hi and lo bits may be accessed independently.
  */
+#define gits_read_vpropbaser(c)		__gic_readq_nonatomic(c)
 #define gits_write_vpropbaser(v, c)	__gic_writeq_nonatomic(v, c)
 
 /*

index 89e4c8b79349..4750fc8030c3 100644
@@ -141,6 +141,7 @@ static inline u32 gic_read_rpr(void)
 #define gicr_read_pendbaser(c)		readq_relaxed(c)
 
 #define gits_write_vpropbaser(v, c)	writeq_relaxed(v, c)
+#define gits_read_vpropbaser(c)		readq_relaxed(c)
 
 #define gits_write_vpendbaser(v, c)	writeq_relaxed(v, c)
 #define gits_read_vpendbaser(c)		readq_relaxed(c)

371 lines not on this page · raw message

index 8c6be56da7e9..f1d6de53e09b 100644
@@ -102,6 +102,11 @@
 
 #define GIC_V3_DIST_SIZE		0x10000
 
+#define GIC_PAGE_SIZE_4K		0ULL
+#define GIC_PAGE_SIZE_16K		1ULL
+#define GIC_PAGE_SIZE_64K		2ULL
+#define GIC_PAGE_SIZE_MASK		3ULL
+
 /*
  * Re-Distributor registers, offsets from RD_base
  */

@@ -239,6 +244,8 @@
 #define GICR_TYPER_DirectLPIS		(1U << 3)
 #define GICR_TYPER_LAST			(1U << 4)
 #define GICR_TYPER_RVPEID		(1U << 7)
+#define GICR_TYPER_COMMON_LPI_AFF	GENMASK_ULL(25, 24)
+#define GICR_TYPER_AFFINITY		GENMASK_ULL(63, 32)
 
 #define GIC_V3_REDIST_SIZE		0x20000
 

@@ -277,6 +284,18 @@
 #define GICR_VPROPBASER_RaWaWt	GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWt)
 #define GICR_VPROPBASER_RaWaWb	GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWb)
 
+/*
+ * GICv4.1 VPROPBASER reinvention. A subtle mix between the old
+ * VPROPBASER and ITS_BASER. Just not quite any of the two.
+ */
+#define GICR_VPROPBASER_4_1_VALID	(1ULL << 63)
+#define GICR_VPROPBASER_4_1_ENTRY_SIZE	GENMASK_ULL(61, 59)
+#define GICR_VPROPBASER_4_1_INDIRECT	(1ULL << 55)
+#define GICR_VPROPBASER_4_1_PAGE_SIZE	GENMASK_ULL(54, 53)
+#define GICR_VPROPBASER_4_1_Z		(1ULL << 52)
+#define GICR_VPROPBASER_4_1_ADDR	GENMASK_ULL(51, 12)
+#define GICR_VPROPBASER_4_1_SIZE	GENMASK_ULL(6, 0)
+
 #define GICR_VPENDBASER			0x0078
 
 #define GICR_VPENDBASER_SHAREABILITY_SHIFT		(10)

@@ -314,6 +333,7 @@
 #define GITS_CTLR			0x0000
 #define GITS_IIDR			0x0004
 #define GITS_TYPER			0x0008
+#define GITS_MPIDR			0x0018
 #define GITS_CBASER			0x0080
 #define GITS_CWRITER			0x0088
 #define GITS_CREADR			0x0090

@@ -347,6 +367,8 @@
 #define GITS_TYPER_HCC_SHIFT		24
 #define GITS_TYPER_HCC(r)		(((r) >> GITS_TYPER_HCC_SHIFT) & 0xff)
 #define GITS_TYPER_VMOVP		(1ULL << 37)
+#define GITS_TYPER_VMAPP		(1ULL << 40)
+#define GITS_TYPER_SVPET		GENMASK_ULL(42, 41)
 
 #define GITS_IIDR_REV_SHIFT		12
 #define GITS_IIDR_REV_MASK		(0xf << GITS_IIDR_REV_SHIFT)

@@ -417,10 +439,11 @@
 #define GITS_BASER_InnerShareable					\
 	GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)
 #define GITS_BASER_PAGE_SIZE_SHIFT	(8)
-#define GITS_BASER_PAGE_SIZE_4K		(0ULL << GITS_BASER_PAGE_SIZE_SHIFT)
-#define GITS_BASER_PAGE_SIZE_16K	(1ULL << GITS_BASER_PAGE_SIZE_SHIFT)
-#define GITS_BASER_PAGE_SIZE_64K	(2ULL << GITS_BASER_PAGE_SIZE_SHIFT)
-#define GITS_BASER_PAGE_SIZE_MASK	(3ULL << GITS_BASER_PAGE_SIZE_SHIFT)
+#define __GITS_BASER_PSZ(sz)		(GIC_PAGE_SIZE_ ## sz << GITS_BASER_PAGE_SIZE_SHIFT)
+#define GITS_BASER_PAGE_SIZE_4K		__GITS_BASER_PSZ(4K)
+#define GITS_BASER_PAGE_SIZE_16K	__GITS_BASER_PSZ(16K)
+#define GITS_BASER_PAGE_SIZE_64K	__GITS_BASER_PSZ(64K)
+#define GITS_BASER_PAGE_SIZE_MASK	__GITS_BASER_PSZ(MASK)
 #define GITS_BASER_PAGES_MAX		256
 #define GITS_BASER_PAGES_SHIFT		(0)
 #define GITS_BASER_NR_PAGES(r)		(((r) & 0xff) + 1)

@@ -610,8 +633,10 @@ struct rdists {
 	struct {
 		void __iomem	*rd_base;
 		struct page	*pend_page;
+		struct page	*vpe_l1_page;
 		phys_addr_t	phys_base;
 		bool		lpi_enabled;
+		cpumask_t	*vpe_table_mask;
 	} __percpu		*rdist;
 	phys_addr_t		prop_table_pa;
 	void			*prop_table_va;

index e1f8d5f9a0e3..3234bb9fbdbe 100644
@@ -2433,7 +2433,7 @@ static u64 inherit_vpe_l1_table_from_its(void)
 	aff = compute_common_aff(val);
 
 	list_for_each_entry(its, &its_nodes, entry) {
-		u64 baser;
+		u64 baser, addr;
 
 		if (!is_v4_1(its))
 			continue;

@@ -2455,8 +2455,15 @@ static u64 inherit_vpe_l1_table_from_its(void)
 			val |= GICR_VPROPBASER_4_1_INDIRECT;
 		val |= FIELD_PREP(GICR_VPROPBASER_4_1_PAGE_SIZE,
 				  FIELD_GET(GITS_BASER_PAGE_SIZE_MASK, baser));
-		val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR,
-				  GITS_BASER_ADDR_48_to_52(baser) >> 12);
+		switch (FIELD_GET(GITS_BASER_PAGE_SIZE_MASK, baser)) {
+		case GIC_PAGE_SIZE_64K:
+			addr = GITS_BASER_ADDR_48_to_52(baser);
+			break;
+		default:
+			addr = baser & GENMASK_ULL(47, 12);
+			break;
+		}
+		val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, addr >> 12);
 		val |= FIELD_PREP(GICR_VPROPBASER_SHAREABILITY_MASK,
 				  FIELD_GET(GITS_BASER_SHAREABILITY_MASK, baser));
 		val |= FIELD_PREP(GICR_VPROPBASER_INNER_CACHEABILITY_MASK,

index 478d3678850c..220d490d516e 100644
@@ -422,6 +422,27 @@ static void its_encode_vpt_size(struct its_cmd_block *cmd, u8 vpt_size)
 	its_mask_encode(&cmd->raw_cmd[3], vpt_size, 4, 0);
 }
 
+static void its_encode_vconf_addr(struct its_cmd_block *cmd, u64 vconf_pa)
+{
+	its_mask_encode(&cmd->raw_cmd[0], vconf_pa >> 16, 51, 16);
+}
+
+static void its_encode_alloc(struct its_cmd_block *cmd, bool alloc)
+{
+	its_mask_encode(&cmd->raw_cmd[0], alloc, 8, 8);
+}
+
+static void its_encode_ptz(struct its_cmd_block *cmd, bool ptz)
+{
+	its_mask_encode(&cmd->raw_cmd[0], ptz, 9, 9);
+}
+
+static void its_encode_vmapp_default_db(struct its_cmd_block *cmd,
+					u32 vpe_db_lpi)
+{
+	its_mask_encode(&cmd->raw_cmd[1], vpe_db_lpi, 31, 0);
+}
+
 static inline void its_fixup_cmd(struct its_cmd_block *cmd)
 {
 	/* Let's fixup BE commands */

@@ -605,19 +626,45 @@ static struct its_vpe *its_build_vmapp_cmd(struct its_node *its,
 					   struct its_cmd_block *cmd,
 					   struct its_cmd_desc *desc)
 {
-	unsigned long vpt_addr;
+	unsigned long vpt_addr, vconf_addr;
 	u64 target;
-
-	vpt_addr = virt_to_phys(page_address(desc->its_vmapp_cmd.vpe->vpt_page));
-	target = desc->its_vmapp_cmd.col->target_address + its->vlpi_redist_offset;
+	bool alloc;
 
 	its_encode_cmd(cmd, GITS_CMD_VMAPP);
 	its_encode_vpeid(cmd, desc->its_vmapp_cmd.vpe->vpe_id);
 	its_encode_valid(cmd, desc->its_vmapp_cmd.valid);
+
+	if (!desc->its_vmapp_cmd.valid) {
+		if (is_v4_1(its)) {
+			alloc = !atomic_dec_return(&desc->its_vmapp_cmd.vpe->vmapp_count);
+			its_encode_alloc(cmd, alloc);
+		}
+
+		goto out;
+	}
+
+	vpt_addr = virt_to_phys(page_address(desc->its_vmapp_cmd.vpe->vpt_page));
+	target = desc->its_vmapp_cmd.col->target_address + its->vlpi_redist_offset;
+
 	its_encode_target(cmd, target);
 	its_encode_vpt_addr(cmd, vpt_addr);
 	its_encode_vpt_size(cmd, LPI_NRBITS - 1);
 
+	if (!is_v4_1(its))
+		goto out;
+
+	vconf_addr = virt_to_phys(page_address(desc->its_vmapp_cmd.vpe->its_vm->vprop_page));
+
+	alloc = atomic_inc_and_test(&desc->its_vmapp_cmd.vpe->vmapp_count);
+
+	its_encode_alloc(cmd, alloc);
+
+	/* We can only signal PTZ when alloc==1. Why do we have two bits? */
+	its_encode_ptz(cmd, alloc);
+	its_encode_vconf_addr(cmd, vconf_addr);
+	its_encode_vmapp_default_db(cmd, desc->its_vmapp_cmd.vpe->vpe_db_lpi);
+
+out:
 	its_fixup_cmd(cmd);
 
 	return valid_vpe(its, desc->its_vmapp_cmd.vpe);

@@ -3349,7 +3396,10 @@ static int its_vpe_init(struct its_vpe *vpe)
 
 	vpe->vpe_id = vpe_id;
 	vpe->vpt_page = vpt_page;
-	vpe->vpe_proxy_event = -1;
+	if (gic_rdists->has_rvpeid)
+		atomic_set(&vpe->vmapp_count, 0);
+	else
+		vpe->vpe_proxy_event = -1;
 
 	return 0;
 }

index ab1396afe08a..6213ced6f199 100644
@@ -37,8 +37,20 @@ struct its_vpe {
 	irq_hw_number_t		vpe_db_lpi;
 	/* VPE resident */
 	bool			resident;
-	/* VPE proxy mapping */
-	int			vpe_proxy_event;
+	union {
+		/* GICv4.0 implementations */
+		struct {
+			/* VPE proxy mapping */
+			int	vpe_proxy_event;
+			/* Implementation Defined Area Invalid */
+			bool	idai;
+		};
+		/* GICv4.1 implementations */
+		struct {
+			atomic_t vmapp_count;
+		};
+	};
+
 	/*
 	 * This collection ID is used to indirect the target
 	 * redistributor for this VPE. The ID itself isn't involved in

@@ -47,8 +59,6 @@ struct its_vpe {
 	u16			col_idx;
 	/* Unique (system-wide) VPE identifier */
 	u16			vpe_id;
-	/* Implementation Defined Area Invalid */
-	bool			idai;
 	/* Pending VLPIs on schedule out? */
 	bool			pending_last;
 };

index 220d490d516e..999e61a9b2c3 100644
@@ -3069,7 +3069,7 @@ static const struct irq_domain_ops its_domain_ops = {
 /*
  * This is insane.
  *
- * If a GICv4 doesn't implement Direct LPIs (which is extremely
+ * If a GICv4.0 doesn't implement Direct LPIs (which is extremely
  * likely), the only way to perform an invalidate is to use a fake
  * device to issue an INV command, implying that the LPI has first
  * been mapped to some event on that device. Since this is not exactly

@@ -3077,9 +3077,18 @@ static const struct irq_domain_ops its_domain_ops = {
  * only issue an UNMAP if we're short on available slots.
  *
  * Broken by design(tm).
+ *
+ * GICv4.1 actually mandates that we're able to invalidate by writing to a
+ * MMIO register. It doesn't implement the whole of DirectLPI, but that's
+ * good enough. And most of the time, we don't even have to invalidate
+ * anything, so that's actually pretty good!
  */
 static void its_vpe_db_proxy_unmap_locked(struct its_vpe *vpe)
 {
+	/* GICv4.1 doesn't use a proxy, so nothing to do here */
+	if (gic_rdists->has_rvpeid)
+		return;
+
 	/* Already unmapped? */
 	if (vpe->vpe_proxy_event == -1)
 		return;

@@ -3102,6 +3111,10 @@ static void its_vpe_db_proxy_unmap_locked(struct its_vpe *vpe)
 
 static void its_vpe_db_proxy_unmap(struct its_vpe *vpe)
 {
+	/* GICv4.1 doesn't use a proxy, so nothing to do here */
+	if (gic_rdists->has_rvpeid)
+		return;
+
 	if (!gic_rdists->has_direct_lpi) {
 		unsigned long flags;
 

@@ -3113,6 +3126,10 @@ static void its_vpe_db_proxy_unmap(struct its_vpe *vpe)
 
 static void its_vpe_db_proxy_map_locked(struct its_vpe *vpe)
 {
+	/* GICv4.1 doesn't use a proxy, so nothing to do here */
+	if (gic_rdists->has_rvpeid)
+		return;
+
 	/* Already mapped? */
 	if (vpe->vpe_proxy_event != -1)
 		return;

@@ -3135,6 +3152,10 @@ static void its_vpe_db_proxy_move(struct its_vpe *vpe, int from, int to)
 	unsigned long flags;
 	struct its_collection *target_col;
 
+	/* GICv4.1 doesn't use a proxy, so nothing to do here */
+	if (gic_rdists->has_rvpeid)
+		return;
+
 	if (gic_rdists->has_direct_lpi) {
 		void __iomem *rdbase;
 

index 999e61a9b2c3..b5a122093a46 100644
@@ -443,6 +443,17 @@ static void its_encode_vmapp_default_db(struct its_cmd_block *cmd,
 	its_mask_encode(&cmd->raw_cmd[1], vpe_db_lpi, 31, 0);
 }
 
+static void its_encode_vmovp_default_db(struct its_cmd_block *cmd,
+					u32 vpe_db_lpi)
+{
+	its_mask_encode(&cmd->raw_cmd[3], vpe_db_lpi, 31, 0);
+}
+
+static void its_encode_db(struct its_cmd_block *cmd, bool db)
+{
+	its_mask_encode(&cmd->raw_cmd[2], db, 63, 63);
+}
+
 static inline void its_fixup_cmd(struct its_cmd_block *cmd)
 {
 	/* Let's fixup BE commands */

@@ -729,6 +740,11 @@ static struct its_vpe *its_build_vmovp_cmd(struct its_node *its,
 	its_encode_vpeid(cmd, desc->its_vmovp_cmd.vpe->vpe_id);
 	its_encode_target(cmd, target);
 
+	if (is_v4_1(its)) {
+		its_encode_db(cmd, true);
+		its_encode_vmovp_default_db(cmd, desc->its_vmovp_cmd.vpe->vpe_db_lpi);
+	}
+
 	its_fixup_cmd(cmd);
 
 	return valid_vpe(its, desc->its_vmovp_cmd.vpe);