From 0b04758b002bde9434053be2fff8064ac3d9d8bb Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 4 Mar 2020 20:33:08 +0000
Subject: [PATCH 01/16] irqchip/gic-v3: Use SGIs without active state if
 offered

To allow the direct injection of SGIs into a guest, the GICv4.1
architecture has to sacrifice the Active state so that SGIs look
a lot like LPIs (they are injected by the same mechanism).

In order not to break existing software, the architecture gives
offers guests OSs the choice: SGIs with or without an active
state. It is the hypervisors duty to honor the guest's choice.

For this, the architecture offers a discovery bit indicating whether
the GIC supports GICv4.1 SGIs (GICD_TYPER2.nASSGIcap), and another
bit indicating whether the guest wants Active-less SGIs or not
(controlled by GICD_CTLR.nASSGIreq).

A hypervisor not supporting GICv4.1 SGIs would leave nASSGIcap
clear, and a guest not knowing about GICv4.1 SGIs (or definitely
wanting an Active state) would leave nASSGIreq clear (both being
thankfully backward compatible with older revisions of the GIC).

Since Linux is perfectly happy without an active state on SGIs,
inform the hypervisor that we'll use that if offered.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Link: https://lore.kernel.org/r/20200304203330.4967-2-maz@kernel.org
---
 drivers/irqchip/irq-gic-v3.c       | 10 ++++++++--
 include/linux/irqchip/arm-gic-v3.h |  2 ++
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index c1f7af9d9ae7..b6b0f86584d6 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -723,6 +723,7 @@ static void __init gic_dist_init(void)
 	unsigned int i;
 	u64 affinity;
 	void __iomem *base = gic_data.dist_base;
+	u32 val;
 
 	/* Disable the distributor */
 	writel_relaxed(0, base + GICD_CTLR);
@@ -755,9 +756,14 @@ static void __init gic_dist_init(void)
 	/* Now do the common stuff, and wait for the distributor to drain */
 	gic_dist_config(base, GIC_LINE_NR, gic_dist_wait_for_rwp);
 
+	val = GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1;
+	if (gic_data.rdists.gicd_typer2 & GICD_TYPER2_nASSGIcap) {
+		pr_info("Enabling SGIs without active state\n");
+		val |= GICD_CTLR_nASSGIreq;
+	}
+
 	/* Enable distributor with ARE, Group1 */
-	writel_relaxed(GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1,
-		       base + GICD_CTLR);
+	writel_relaxed(val, base + GICD_CTLR);
 
 	/*
 	 * Set all global interrupts to the boot CPU only. ARE must be
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 83439bfb6c5b..c29a02678a6f 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -57,6 +57,7 @@
 #define GICD_SPENDSGIR			0x0F20
 
 #define GICD_CTLR_RWP			(1U << 31)
+#define GICD_CTLR_nASSGIreq		(1U << 8)
 #define GICD_CTLR_DS			(1U << 6)
 #define GICD_CTLR_ARE_NS		(1U << 4)
 #define GICD_CTLR_ENABLE_G1A		(1U << 1)
@@ -90,6 +91,7 @@
 #define GICD_TYPER_ESPIS(typer)						\
 	(((typer) & GICD_TYPER_ESPI) ? GICD_TYPER_SPIS((typer) >> 27) : 0)
 
+#define GICD_TYPER2_nASSGIcap		(1U << 8)
 #define GICD_TYPER2_VIL			(1U << 7)
 #define GICD_TYPER2_VID			GENMASK(4, 0)
 

From 28d160de5194c68ff534443d2a8b6f1d10d57c58 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 4 Mar 2020 20:33:09 +0000
Subject: [PATCH 02/16] irqchip/gic-v4.1: Skip absent CPUs while iterating over
 redistributors

In a system that is only sparsly populated with CPUs, we can end-up with
redistributors structures that are not initialized. Let's make sure we
don't try and access those when iterating over them (in this case when
checking we have a L2 VPE table).

Fixes: 4e6437f12d6e ("irqchip/gic-v4.1: Ensure L2 vPE table is allocated at RD level")
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/20200304203330.4967-3-maz@kernel.org
---
 drivers/irqchip/irq-gic-v3-its.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 83b1186ffcad..da883a691028 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -2452,6 +2452,10 @@ static bool allocate_vpe_l2_table(int cpu, u32 id)
 	if (!gic_rdists->has_rvpeid)
 		return true;
 
+	/* Skip non-present CPUs */
+	if (!base)
+		return true;
+
 	val  = gicr_read_vpropbaser(base + SZ_128K + GICR_VPROPBASER);
 
 	esz  = FIELD_GET(GICR_VPROPBASER_4_1_ENTRY_SIZE, val) + 1;

From f3a059219bc718ccc3bf3ff894f089b7e9a93139 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 4 Mar 2020 20:33:10 +0000
Subject: [PATCH 03/16] irqchip/gic-v4.1: Ensure mutual exclusion between vPE
 affinity change and RD access

Before GICv4.1, all operations would be serialized with the affinity
changes by virtue of using the same ITS command queue. With v4.1, things
change, as invalidations (and a number of other operations) are issued
using the redistributor MMIO frame.

We must thus make sure that these redistributor accesses cannot race
against aginst the affinity change, or we may end-up talking to the
wrong redistributor.

To ensure this, we expand the irq_to_cpuid() helper to take a spinlock
when the LPI is mapped to a vLPI (a new per-VPE lock) on each operation
that requires mutual exclusion.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Link: https://lore.kernel.org/r/20200304203330.4967-4-maz@kernel.org
---
 drivers/irqchip/irq-gic-v3-its.c   | 56 +++++++++++++++++++++++++-----
 include/linux/irqchip/arm-gic-v4.h |  5 +++
 2 files changed, 53 insertions(+), 8 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index da883a691028..1af713990123 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -239,15 +239,41 @@ static struct its_vlpi_map *get_vlpi_map(struct irq_data *d)
 	return NULL;
 }
 
-static int irq_to_cpuid(struct irq_data *d)
+static int vpe_to_cpuid_lock(struct its_vpe *vpe, unsigned long *flags)
+{
+	raw_spin_lock_irqsave(&vpe->vpe_lock, *flags);
+	return vpe->col_idx;
+}
+
+static void vpe_to_cpuid_unlock(struct its_vpe *vpe, unsigned long flags)
+{
+	raw_spin_unlock_irqrestore(&vpe->vpe_lock, flags);
+}
+
+static int irq_to_cpuid_lock(struct irq_data *d, unsigned long *flags)
+{
+	struct its_vlpi_map *map = get_vlpi_map(d);
+	int cpu;
+
+	if (map) {
+		cpu = vpe_to_cpuid_lock(map->vpe, flags);
+	} else {
+		/* Physical LPIs are already locked via the irq_desc lock */
+		struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+		cpu = its_dev->event_map.col_map[its_get_event_id(d)];
+		/* Keep GCC quiet... */
+		*flags = 0;
+	}
+
+	return cpu;
+}
+
+static void irq_to_cpuid_unlock(struct irq_data *d, unsigned long flags)
 {
-	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	struct its_vlpi_map *map = get_vlpi_map(d);
 
 	if (map)
-		return map->vpe->col_idx;
-
-	return its_dev->event_map.col_map[its_get_event_id(d)];
+		vpe_to_cpuid_unlock(map->vpe, flags);
 }
 
 static struct its_collection *valid_col(struct its_collection *col)
@@ -1329,7 +1355,9 @@ static void direct_lpi_inv(struct irq_data *d)
 {
 	struct its_vlpi_map *map = get_vlpi_map(d);
 	void __iomem *rdbase;
+	unsigned long flags;
 	u64 val;
+	int cpu;
 
 	if (map) {
 		struct its_device *its_dev = irq_data_get_irq_chip_data(d);
@@ -1344,10 +1372,12 @@ static void direct_lpi_inv(struct irq_data *d)
 	}
 
 	/* Target the redistributor this LPI is currently routed to */
-	rdbase = per_cpu_ptr(gic_rdists->rdist, irq_to_cpuid(d))->rd_base;
+	cpu = irq_to_cpuid_lock(d, &flags);
+	rdbase = per_cpu_ptr(gic_rdists->rdist, cpu)->rd_base;
 	gic_write_lpir(val, rdbase + GICR_INVLPIR);
 
 	wait_for_syncr(rdbase);
+	irq_to_cpuid_unlock(d, flags);
 }
 
 static void lpi_update_config(struct irq_data *d, u8 clr, u8 set)
@@ -3486,17 +3516,25 @@ static int its_vpe_set_affinity(struct irq_data *d,
 {
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
 	int from, cpu = cpumask_first(mask_val);
+	unsigned long flags;
 
 	/*
 	 * Changing affinity is mega expensive, so let's be as lazy as
 	 * we can and only do it if we really have to. Also, if mapped
 	 * into the proxy device, we need to move the doorbell
 	 * interrupt to its new location.
+	 *
+	 * Another thing is that changing the affinity of a vPE affects
+	 * *other interrupts* such as all the vLPIs that are routed to
+	 * this vPE. This means that the irq_desc lock is not enough to
+	 * protect us, and that we must ensure nobody samples vpe->col_idx
+	 * during the update, hence the lock below which must also be
+	 * taken on any vLPI handling path that evaluates vpe->col_idx.
 	 */
-	if (vpe->col_idx == cpu)
+	from = vpe_to_cpuid_lock(vpe, &flags);
+	if (from == cpu)
 		goto out;
 
-	from = vpe->col_idx;
 	vpe->col_idx = cpu;
 
 	/*
@@ -3512,6 +3550,7 @@ static int its_vpe_set_affinity(struct irq_data *d,
 
 out:
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
+	vpe_to_cpuid_unlock(vpe, flags);
 
 	return IRQ_SET_MASK_OK_DONE;
 }
@@ -3855,6 +3894,7 @@ static int its_vpe_init(struct its_vpe *vpe)
 		return -ENOMEM;
 	}
 
+	raw_spin_lock_init(&vpe->vpe_lock);
 	vpe->vpe_id = vpe_id;
 	vpe->vpt_page = vpt_page;
 	if (gic_rdists->has_rvpeid)
diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h
index d9c34968467a..439963f4c66a 100644
--- a/include/linux/irqchip/arm-gic-v4.h
+++ b/include/linux/irqchip/arm-gic-v4.h
@@ -53,6 +53,11 @@ struct its_vpe {
 		};
 	};
 
+	/*
+	 * Ensures mutual exclusion between affinity setting of the
+	 * vPE and vLPI operations using vpe->col_idx.
+	 */
+	raw_spinlock_t		vpe_lock;
 	/*
 	 * This collection ID is used to indirect the target
 	 * redistributor for this VPE. The ID itself isn't involved in

From b978c25f6ee7d4c79cbe918eed684e53887ec001 Mon Sep 17 00:00:00 2001
From: Zenghui Yu <yuzenghui@huawei.com>
Date: Wed, 4 Mar 2020 20:33:11 +0000
Subject: [PATCH 04/16] irqchip/gic-v4.1: Wait for completion of
 redistributor's INVALL operation

In GICv4.1, we emulate a guest-issued INVALL command by a direct write
to GICR_INVALLR.  Before we finish the emulation and go back to guest,
let's make sure the physical invalidate operation is actually completed
and no stale data will be left in redistributor. Per the specification,
this can be achieved by polling the GICR_SYNCR.Busy bit (to zero).

Signed-off-by: Zenghui Yu <yuzenghui@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/20200302092145.899-1-yuzenghui@huawei.com
Link: https://lore.kernel.org/r/20200304203330.4967-5-maz@kernel.org
---
 drivers/irqchip/irq-gic-v3-its.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 1af713990123..c84370245bea 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -3827,6 +3827,8 @@ static void its_vpe_4_1_invall(struct its_vpe *vpe)
 	/* Target the redistributor this vPE is currently known on */
 	rdbase = per_cpu_ptr(gic_rdists->rdist, vpe->col_idx)->rd_base;
 	gic_write_lpir(val, rdbase + GICR_INVALLR);
+
+	wait_for_syncr(rdbase);
 }
 
 static int its_vpe_4_1_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)

From 9058a4e980648e7d068a7f7726a8ea4c67d0e88a Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 4 Mar 2020 20:33:12 +0000
Subject: [PATCH 05/16] irqchip/gic-v4.1: Ensure mutual exclusion betwen
 invalidations on the same RD

The GICv4.1 spec says that it is CONTRAINED UNPREDICTABLE to write to
any of the GICR_INV{LPI,ALL}R registers if GICR_SYNCR.Busy == 1.

To deal with it, we must ensure that only a single invalidation can
happen at a time for a given redistributor. Add a per-RD lock to that
effect and take it around the invalidation/syncr-read to deal with this.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/20200304203330.4967-6-maz@kernel.org
---
 drivers/irqchip/irq-gic-v3-its.c   | 6 ++++++
 drivers/irqchip/irq-gic-v3.c       | 1 +
 include/linux/irqchip/arm-gic-v3.h | 1 +
 3 files changed, 8 insertions(+)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index c84370245bea..fc5788584df7 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -1373,10 +1373,12 @@ static void direct_lpi_inv(struct irq_data *d)
 
 	/* Target the redistributor this LPI is currently routed to */
 	cpu = irq_to_cpuid_lock(d, &flags);
+	raw_spin_lock(&gic_data_rdist_cpu(cpu)->rd_lock);
 	rdbase = per_cpu_ptr(gic_rdists->rdist, cpu)->rd_base;
 	gic_write_lpir(val, rdbase + GICR_INVLPIR);
 
 	wait_for_syncr(rdbase);
+	raw_spin_unlock(&gic_data_rdist_cpu(cpu)->rd_lock);
 	irq_to_cpuid_unlock(d, flags);
 }
 
@@ -3662,9 +3664,11 @@ static void its_vpe_send_inv(struct irq_data *d)
 		void __iomem *rdbase;
 
 		/* Target the redistributor this VPE is currently known on */
+		raw_spin_lock(&gic_data_rdist_cpu(vpe->col_idx)->rd_lock);
 		rdbase = per_cpu_ptr(gic_rdists->rdist, vpe->col_idx)->rd_base;
 		gic_write_lpir(d->parent_data->hwirq, rdbase + GICR_INVLPIR);
 		wait_for_syncr(rdbase);
+		raw_spin_unlock(&gic_data_rdist_cpu(vpe->col_idx)->rd_lock);
 	} else {
 		its_vpe_send_cmd(vpe, its_send_inv);
 	}
@@ -3825,10 +3829,12 @@ static void its_vpe_4_1_invall(struct its_vpe *vpe)
 	val |= FIELD_PREP(GICR_INVALLR_VPEID, vpe->vpe_id);
 
 	/* Target the redistributor this vPE is currently known on */
+	raw_spin_lock(&gic_data_rdist_cpu(vpe->col_idx)->rd_lock);
 	rdbase = per_cpu_ptr(gic_rdists->rdist, vpe->col_idx)->rd_base;
 	gic_write_lpir(val, rdbase + GICR_INVALLR);
 
 	wait_for_syncr(rdbase);
+	raw_spin_unlock(&gic_data_rdist_cpu(vpe->col_idx)->rd_lock);
 }
 
 static int its_vpe_4_1_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index b6b0f86584d6..0f716c2647fd 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -834,6 +834,7 @@ static int __gic_populate_rdist(struct redist_region *region, void __iomem *ptr)
 	typer = gic_read_typer(ptr + GICR_TYPER);
 	if ((typer >> 32) == aff) {
 		u64 offset = ptr - region->redist_base;
+		raw_spin_lock_init(&gic_data_rdist()->rd_lock);
 		gic_data_rdist_rd_base() = ptr;
 		gic_data_rdist()->phys_base = region->phys_base + offset;
 
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index c29a02678a6f..b28acfa71f82 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -652,6 +652,7 @@
 
 struct rdists {
 	struct {
+		raw_spinlock_t	rd_lock;
 		void __iomem	*rd_base;
 		struct page	*pend_page;
 		phys_addr_t	phys_base;

From 3c40706d05fdea421e991da50e72a29d41131a66 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 4 Mar 2020 20:33:13 +0000
Subject: [PATCH 06/16] irqchip/gic-v4.1: Advertise support v4.1 to KVM

Tell KVM that we support v4.1. Nothing uses this information so far.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/20200304203330.4967-7-maz@kernel.org
---
 drivers/irqchip/irq-gic-v3-its.c       | 9 ++++++++-
 drivers/irqchip/irq-gic-v3.c           | 2 ++
 include/linux/irqchip/arm-gic-common.h | 2 ++
 3 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index fc5788584df7..bcc1a0957cda 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -4870,6 +4870,7 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists,
 	struct device_node *of_node;
 	struct its_node *its;
 	bool has_v4 = false;
+	bool has_v4_1 = false;
 	int err;
 
 	gic_rdists = rdists;
@@ -4890,8 +4891,14 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists,
 	if (err)
 		return err;
 
-	list_for_each_entry(its, &its_nodes, entry)
+	list_for_each_entry(its, &its_nodes, entry) {
 		has_v4 |= is_v4(its);
+		has_v4_1 |= is_v4_1(its);
+	}
+
+	/* Don't bother with inconsistent systems */
+	if (WARN_ON(!has_v4_1 && rdists->has_rvpeid))
+		rdists->has_rvpeid = false;
 
 	if (has_v4 & rdists->has_vlpis) {
 		if (its_init_vpe_domain() ||
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 0f716c2647fd..8c5de59c5213 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -1764,6 +1764,7 @@ static void __init gic_of_setup_kvm_info(struct device_node *node)
 		gic_v3_kvm_info.vcpu = r;
 
 	gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis;
+	gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid;
 	gic_set_kvm_info(&gic_v3_kvm_info);
 }
 
@@ -2079,6 +2080,7 @@ static void __init gic_acpi_setup_kvm_info(void)
 	}
 
 	gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis;
+	gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid;
 	gic_set_kvm_info(&gic_v3_kvm_info);
 }
 
diff --git a/include/linux/irqchip/arm-gic-common.h b/include/linux/irqchip/arm-gic-common.h
index b9850f5f1906..fa8c0455c352 100644
--- a/include/linux/irqchip/arm-gic-common.h
+++ b/include/linux/irqchip/arm-gic-common.h
@@ -32,6 +32,8 @@ struct gic_kvm_info {
 	struct resource vctrl;
 	/* vlpi support */
 	bool		has_v4;
+	/* rvpeid support */
+	bool		has_v4_1;
 };
 
 const struct gic_kvm_info *gic_get_kvm_info(void);

From 5e46a48413a6660955de7e56f9f364f2b890381c Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 4 Mar 2020 20:33:14 +0000
Subject: [PATCH 07/16] irqchip/gic-v4.1: Map the ITS SGIR register page

One of the new features of GICv4.1 is to allow virtual SGIs to be
directly signaled to a VPE. For that, the ITS has grown a new
64kB page containing only a single register that is used to
signal a SGI to a given VPE.

Add a second mapping covering this new 64kB range, and take this
opportunity to limit the original mapping to 64kB, which is enough
to cover the span of the ITS registers.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/20200304203330.4967-8-maz@kernel.org
---
 drivers/irqchip/irq-gic-v3-its.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index bcc1a0957cda..54d6fdf7a28e 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -96,6 +96,7 @@ struct its_node {
 	struct mutex		dev_alloc_lock;
 	struct list_head	entry;
 	void __iomem		*base;
+	void __iomem		*sgir_base;
 	phys_addr_t		phys_base;
 	struct its_cmd_block	*cmd_base;
 	struct its_cmd_block	*cmd_write;
@@ -4456,7 +4457,7 @@ static int __init its_probe_one(struct resource *res,
 	struct page *page;
 	int err;
 
-	its_base = ioremap(res->start, resource_size(res));
+	its_base = ioremap(res->start, SZ_64K);
 	if (!its_base) {
 		pr_warn("ITS@%pa: Unable to map ITS registers\n", &res->start);
 		return -ENOMEM;
@@ -4507,6 +4508,13 @@ static int __init its_probe_one(struct resource *res,
 
 		if (is_v4_1(its)) {
 			u32 svpet = FIELD_GET(GITS_TYPER_SVPET, typer);
+
+			its->sgir_base = ioremap(res->start + SZ_128K, SZ_64K);
+			if (!its->sgir_base) {
+				err = -ENOMEM;
+				goto out_free_its;
+			}
+
 			its->mpidr = readl_relaxed(its_base + GITS_MPIDR);
 
 			pr_info("ITS@%pa: Using GICv4.1 mode %08x %08x\n",
@@ -4520,7 +4528,7 @@ static int __init its_probe_one(struct resource *res,
 				get_order(ITS_CMD_QUEUE_SZ));
 	if (!page) {
 		err = -ENOMEM;
-		goto out_free_its;
+		goto out_unmap_sgir;
 	}
 	its->cmd_base = (void *)page_address(page);
 	its->cmd_write = its->cmd_base;
@@ -4587,6 +4595,9 @@ static int __init its_probe_one(struct resource *res,
 	its_free_tables(its);
 out_free_cmd:
 	free_pages((unsigned long)its->cmd_base, get_order(ITS_CMD_QUEUE_SZ));
+out_unmap_sgir:
+	if (its->sgir_base)
+		iounmap(its->sgir_base);
 out_free_its:
 	kfree(its);
 out_unmap:

From 166cba71818cd49d7d815fdc6f97c63395e94fc5 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 4 Mar 2020 20:33:15 +0000
Subject: [PATCH 08/16] irqchip/gic-v4.1: Plumb skeletal VSGI irqchip

Since GICv4.1 has the capability to inject 16 SGIs into each VPE,
and that I'm keen not to invent too many specific interfaces to
manipulate these interrupts, let's pretend that each of these SGIs
is an actual Linux interrupt.

For that matter, let's introduce a minimal irqchip and irqdomain
setup that will get fleshed up in the following patches.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/20200304203330.4967-9-maz@kernel.org
---
 drivers/irqchip/irq-gic-v3-its.c   | 75 +++++++++++++++++++++++++++++-
 drivers/irqchip/irq-gic-v4.c       |  8 +++-
 include/linux/irqchip/arm-gic-v4.h |  9 +++-
 3 files changed, 88 insertions(+), 4 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 54d6fdf7a28e..c9c812191796 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -3870,6 +3870,72 @@ static struct irq_chip its_vpe_4_1_irq_chip = {
 	.irq_set_vcpu_affinity	= its_vpe_4_1_set_vcpu_affinity,
 };
 
+static int its_sgi_set_affinity(struct irq_data *d,
+				const struct cpumask *mask_val,
+				bool force)
+{
+	/*
+	 * There is no notion of affinity for virtual SGIs, at least
+	 * not on the host (since they can only be targetting a vPE).
+	 * Tell the kernel we've done whatever it asked for.
+	 */
+	return IRQ_SET_MASK_OK;
+}
+
+static struct irq_chip its_sgi_irq_chip = {
+	.name			= "GICv4.1-sgi",
+	.irq_set_affinity	= its_sgi_set_affinity,
+};
+
+static int its_sgi_irq_domain_alloc(struct irq_domain *domain,
+				    unsigned int virq, unsigned int nr_irqs,
+				    void *args)
+{
+	struct its_vpe *vpe = args;
+	int i;
+
+	/* Yes, we do want 16 SGIs */
+	WARN_ON(nr_irqs != 16);
+
+	for (i = 0; i < 16; i++) {
+		vpe->sgi_config[i].priority = 0;
+		vpe->sgi_config[i].enabled = false;
+		vpe->sgi_config[i].group = false;
+
+		irq_domain_set_hwirq_and_chip(domain, virq + i, i,
+					      &its_sgi_irq_chip, vpe);
+		irq_set_status_flags(virq + i, IRQ_DISABLE_UNLAZY);
+	}
+
+	return 0;
+}
+
+static void its_sgi_irq_domain_free(struct irq_domain *domain,
+				    unsigned int virq,
+				    unsigned int nr_irqs)
+{
+	/* Nothing to do */
+}
+
+static int its_sgi_irq_domain_activate(struct irq_domain *domain,
+				       struct irq_data *d, bool reserve)
+{
+	return 0;
+}
+
+static void its_sgi_irq_domain_deactivate(struct irq_domain *domain,
+					  struct irq_data *d)
+{
+	/* Nothing to do */
+}
+
+static const struct irq_domain_ops its_sgi_domain_ops = {
+	.alloc		= its_sgi_irq_domain_alloc,
+	.free		= its_sgi_irq_domain_free,
+	.activate	= its_sgi_irq_domain_activate,
+	.deactivate	= its_sgi_irq_domain_deactivate,
+};
+
 static int its_vpe_id_alloc(void)
 {
 	return ida_simple_get(&its_vpeid_ida, 0, ITS_MAX_VPEID, GFP_KERNEL);
@@ -4912,8 +4978,15 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists,
 		rdists->has_rvpeid = false;
 
 	if (has_v4 & rdists->has_vlpis) {
+		const struct irq_domain_ops *sgi_ops;
+
+		if (has_v4_1)
+			sgi_ops = &its_sgi_domain_ops;
+		else
+			sgi_ops = NULL;
+
 		if (its_init_vpe_domain() ||
-		    its_init_v4(parent_domain, &its_vpe_domain_ops)) {
+		    its_init_v4(parent_domain, &its_vpe_domain_ops, sgi_ops)) {
 			rdists->has_vlpis = false;
 			pr_err("ITS: Disabling GICv4 support\n");
 		}
diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c
index 45969927cc81..c01910d53f9e 100644
--- a/drivers/irqchip/irq-gic-v4.c
+++ b/drivers/irqchip/irq-gic-v4.c
@@ -85,6 +85,7 @@
 
 static struct irq_domain *gic_domain;
 static const struct irq_domain_ops *vpe_domain_ops;
+static const struct irq_domain_ops *sgi_domain_ops;
 
 int its_alloc_vcpu_irqs(struct its_vm *vm)
 {
@@ -216,12 +217,15 @@ int its_prop_update_vlpi(int irq, u8 config, bool inv)
 	return irq_set_vcpu_affinity(irq, &info);
 }
 
-int its_init_v4(struct irq_domain *domain, const struct irq_domain_ops *ops)
+int its_init_v4(struct irq_domain *domain,
+		const struct irq_domain_ops *vpe_ops,
+		const struct irq_domain_ops *sgi_ops)
 {
 	if (domain) {
 		pr_info("ITS: Enabling GICv4 support\n");
 		gic_domain = domain;
-		vpe_domain_ops = ops;
+		vpe_domain_ops = vpe_ops;
+		sgi_domain_ops = sgi_ops;
 		return 0;
 	}
 
diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h
index 439963f4c66a..44e8c19e3d56 100644
--- a/include/linux/irqchip/arm-gic-v4.h
+++ b/include/linux/irqchip/arm-gic-v4.h
@@ -49,6 +49,11 @@ struct its_vpe {
 		};
 		/* GICv4.1 implementations */
 		struct {
+			struct {
+				u8	priority;
+				bool	enabled;
+				bool	group;
+			}			sgi_config[16];
 			atomic_t vmapp_count;
 		};
 	};
@@ -123,6 +128,8 @@ int its_unmap_vlpi(int irq);
 int its_prop_update_vlpi(int irq, u8 config, bool inv);
 
 struct irq_domain_ops;
-int its_init_v4(struct irq_domain *domain, const struct irq_domain_ops *ops);
+int its_init_v4(struct irq_domain *domain,
+		const struct irq_domain_ops *vpe_ops,
+		const struct irq_domain_ops *sgi_ops);
 
 #endif

From e252cf8a34d92adf41124cb59b19b49d25395548 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 4 Mar 2020 20:33:16 +0000
Subject: [PATCH 09/16] irqchip/gic-v4.1: Add initial SGI configuration

The GICv4.1 ITS has yet another new command (VSGI) which allows
a VPE-targeted SGI to be configured (or have its pending state
cleared). Add support for this command and plumb it into the
activate irqdomain callback so that it is ready to be used.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Link: https://lore.kernel.org/r/20200304203330.4967-10-maz@kernel.org
---
 drivers/irqchip/irq-gic-v3-its.c   | 92 +++++++++++++++++++++++++++++-
 include/linux/irqchip/arm-gic-v3.h |  3 +-
 2 files changed, 93 insertions(+), 2 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index c9c812191796..28c856a148f2 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -380,6 +380,15 @@ struct its_cmd_desc {
 		struct {
 			struct its_vpe *vpe;
 		} its_invdb_cmd;
+
+		struct {
+			struct its_vpe *vpe;
+			u8 sgi;
+			u8 priority;
+			bool enable;
+			bool group;
+			bool clear;
+		} its_vsgi_cmd;
 	};
 };
 
@@ -528,6 +537,31 @@ static void its_encode_db(struct its_cmd_block *cmd, bool db)
 	its_mask_encode(&cmd->raw_cmd[2], db, 63, 63);
 }
 
+static void its_encode_sgi_intid(struct its_cmd_block *cmd, u8 sgi)
+{
+	its_mask_encode(&cmd->raw_cmd[0], sgi, 35, 32);
+}
+
+static void its_encode_sgi_priority(struct its_cmd_block *cmd, u8 prio)
+{
+	its_mask_encode(&cmd->raw_cmd[0], prio >> 4, 23, 20);
+}
+
+static void its_encode_sgi_group(struct its_cmd_block *cmd, bool grp)
+{
+	its_mask_encode(&cmd->raw_cmd[0], grp, 10, 10);
+}
+
+static void its_encode_sgi_clear(struct its_cmd_block *cmd, bool clr)
+{
+	its_mask_encode(&cmd->raw_cmd[0], clr, 9, 9);
+}
+
+static void its_encode_sgi_enable(struct its_cmd_block *cmd, bool en)
+{
+	its_mask_encode(&cmd->raw_cmd[0], en, 8, 8);
+}
+
 static inline void its_fixup_cmd(struct its_cmd_block *cmd)
 {
 	/* Let's fixup BE commands */
@@ -893,6 +927,26 @@ static struct its_vpe *its_build_invdb_cmd(struct its_node *its,
 	return valid_vpe(its, desc->its_invdb_cmd.vpe);
 }
 
+static struct its_vpe *its_build_vsgi_cmd(struct its_node *its,
+					  struct its_cmd_block *cmd,
+					  struct its_cmd_desc *desc)
+{
+	if (WARN_ON(!is_v4_1(its)))
+		return NULL;
+
+	its_encode_cmd(cmd, GITS_CMD_VSGI);
+	its_encode_vpeid(cmd, desc->its_vsgi_cmd.vpe->vpe_id);
+	its_encode_sgi_intid(cmd, desc->its_vsgi_cmd.sgi);
+	its_encode_sgi_priority(cmd, desc->its_vsgi_cmd.priority);
+	its_encode_sgi_group(cmd, desc->its_vsgi_cmd.group);
+	its_encode_sgi_clear(cmd, desc->its_vsgi_cmd.clear);
+	its_encode_sgi_enable(cmd, desc->its_vsgi_cmd.enable);
+
+	its_fixup_cmd(cmd);
+
+	return valid_vpe(its, desc->its_vsgi_cmd.vpe);
+}
+
 static u64 its_cmd_ptr_to_offset(struct its_node *its,
 				 struct its_cmd_block *ptr)
 {
@@ -3870,6 +3924,26 @@ static struct irq_chip its_vpe_4_1_irq_chip = {
 	.irq_set_vcpu_affinity	= its_vpe_4_1_set_vcpu_affinity,
 };
 
+static void its_configure_sgi(struct irq_data *d, bool clear)
+{
+	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+	struct its_cmd_desc desc;
+
+	desc.its_vsgi_cmd.vpe = vpe;
+	desc.its_vsgi_cmd.sgi = d->hwirq;
+	desc.its_vsgi_cmd.priority = vpe->sgi_config[d->hwirq].priority;
+	desc.its_vsgi_cmd.enable = vpe->sgi_config[d->hwirq].enabled;
+	desc.its_vsgi_cmd.group = vpe->sgi_config[d->hwirq].group;
+	desc.its_vsgi_cmd.clear = clear;
+
+	/*
+	 * GICv4.1 allows us to send VSGI commands to any ITS as long as the
+	 * destination VPE is mapped there. Since we map them eagerly at
+	 * activation time, we're pretty sure the first GICv4.1 ITS will do.
+	 */
+	its_send_single_vcommand(find_4_1_its(), its_build_vsgi_cmd, &desc);
+}
+
 static int its_sgi_set_affinity(struct irq_data *d,
 				const struct cpumask *mask_val,
 				bool force)
@@ -3920,13 +3994,29 @@ static void its_sgi_irq_domain_free(struct irq_domain *domain,
 static int its_sgi_irq_domain_activate(struct irq_domain *domain,
 				       struct irq_data *d, bool reserve)
 {
+	/* Write out the initial SGI configuration */
+	its_configure_sgi(d, false);
 	return 0;
 }
 
 static void its_sgi_irq_domain_deactivate(struct irq_domain *domain,
 					  struct irq_data *d)
 {
-	/* Nothing to do */
+	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+
+	/*
+	 * The VSGI command is awkward:
+	 *
+	 * - To change the configuration, CLEAR must be set to false,
+	 *   leaving the pending bit unchanged.
+	 * - To clear the pending bit, CLEAR must be set to true, leaving
+	 *   the configuration unchanged.
+	 *
+	 * You just can't do both at once, hence the two commands below.
+	 */
+	vpe->sgi_config[d->hwirq].enabled = false;
+	its_configure_sgi(d, false);
+	its_configure_sgi(d, true);
 }
 
 static const struct irq_domain_ops its_sgi_domain_ops = {
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index b28acfa71f82..fd3be49ac9a5 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -502,8 +502,9 @@
 #define GITS_CMD_VMAPTI			GITS_CMD_GICv4(GITS_CMD_MAPTI)
 #define GITS_CMD_VMOVI			GITS_CMD_GICv4(GITS_CMD_MOVI)
 #define GITS_CMD_VSYNC			GITS_CMD_GICv4(GITS_CMD_SYNC)
-/* VMOVP and INVDB are the odd ones, as they dont have a physical counterpart */
+/* VMOVP, VSGI and INVDB are the odd ones, as they dont have a physical counterpart */
 #define GITS_CMD_VMOVP			GITS_CMD_GICv4(2)
+#define GITS_CMD_VSGI			GITS_CMD_GICv4(3)
 #define GITS_CMD_INVDB			GITS_CMD_GICv4(0xe)
 
 /*

From b4e8d644ec623cbb66f192a7fefbd0a66e314be8 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 4 Mar 2020 20:33:17 +0000
Subject: [PATCH 10/16] irqchip/gic-v4.1: Plumb mask/unmask SGI callbacks

Implement mask/unmask for virtual SGIs by calling into the
configuration helper.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/20200304203330.4967-11-maz@kernel.org
---
 drivers/irqchip/irq-gic-v3-its.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 28c856a148f2..bc6666aed1cb 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -3944,6 +3944,22 @@ static void its_configure_sgi(struct irq_data *d, bool clear)
 	its_send_single_vcommand(find_4_1_its(), its_build_vsgi_cmd, &desc);
 }
 
+static void its_sgi_mask_irq(struct irq_data *d)
+{
+	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+
+	vpe->sgi_config[d->hwirq].enabled = false;
+	its_configure_sgi(d, false);
+}
+
+static void its_sgi_unmask_irq(struct irq_data *d)
+{
+	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+
+	vpe->sgi_config[d->hwirq].enabled = true;
+	its_configure_sgi(d, false);
+}
+
 static int its_sgi_set_affinity(struct irq_data *d,
 				const struct cpumask *mask_val,
 				bool force)
@@ -3958,6 +3974,8 @@ static int its_sgi_set_affinity(struct irq_data *d,
 
 static struct irq_chip its_sgi_irq_chip = {
 	.name			= "GICv4.1-sgi",
+	.irq_mask		= its_sgi_mask_irq,
+	.irq_unmask		= its_sgi_unmask_irq,
 	.irq_set_affinity	= its_sgi_set_affinity,
 };
 

From 7017ff0ee1de9d45fafee88a4e7890cce92f482e Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 4 Mar 2020 20:33:18 +0000
Subject: [PATCH 11/16] irqchip/gic-v4.1: Plumb get/set_irqchip_state SGI
 callbacks

To implement the get/set_irqchip_state callbacks (limited to the
PENDING state), we have to use a particular set of hacks:

- Reading the pending state is done by using a pair of new redistributor
  registers (GICR_VSGIR, GICR_VSGIPENDR), which allow the 16 interrupts
  state to be retrieved.
- Setting the pending state is done by generating it as we'd otherwise do
  for a guest (writing to GITS_SGIR).
- Clearing the pending state is done by emitting a VSGI command with the
  "clear" bit set.

This requires some interesting locking though:
- When talking to the redistributor, we must make sure that the VPE
  affinity doesn't change, hence taking the VPE lock.
- At the same time, we must ensure that nobody accesses the same
  redistributor's GICR_VSGIR registers for a different VPE, which
  would corrupt the reading of the pending bits. We thus take the
  per-RD spinlock. Much fun.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Link: https://lore.kernel.org/r/20200304203330.4967-12-maz@kernel.org
---
 drivers/irqchip/irq-gic-v3-its.c   | 77 ++++++++++++++++++++++++++++++
 include/linux/irqchip/arm-gic-v3.h | 14 ++++++
 2 files changed, 91 insertions(+)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index bc6666aed1cb..c614f0c19807 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -3972,11 +3972,88 @@ static int its_sgi_set_affinity(struct irq_data *d,
 	return IRQ_SET_MASK_OK;
 }
 
+static int its_sgi_set_irqchip_state(struct irq_data *d,
+				     enum irqchip_irq_state which,
+				     bool state)
+{
+	if (which != IRQCHIP_STATE_PENDING)
+		return -EINVAL;
+
+	if (state) {
+		struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+		struct its_node *its = find_4_1_its();
+		u64 val;
+
+		val  = FIELD_PREP(GITS_SGIR_VPEID, vpe->vpe_id);
+		val |= FIELD_PREP(GITS_SGIR_VINTID, d->hwirq);
+		writeq_relaxed(val, its->sgir_base + GITS_SGIR - SZ_128K);
+	} else {
+		its_configure_sgi(d, true);
+	}
+
+	return 0;
+}
+
+static int its_sgi_get_irqchip_state(struct irq_data *d,
+				     enum irqchip_irq_state which, bool *val)
+{
+	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+	void __iomem *base;
+	unsigned long flags;
+	u32 count = 1000000;	/* 1s! */
+	u32 status;
+	int cpu;
+
+	if (which != IRQCHIP_STATE_PENDING)
+		return -EINVAL;
+
+	/*
+	 * Locking galore! We can race against two different events:
+	 *
+	 * - Concurent vPE affinity change: we must make sure it cannot
+	 *   happen, or we'll talk to the wrong redistributor. This is
+	 *   identical to what happens with vLPIs.
+	 *
+	 * - Concurrent VSGIPENDR access: As it involves accessing two
+	 *   MMIO registers, this must be made atomic one way or another.
+	 */
+	cpu = vpe_to_cpuid_lock(vpe, &flags);
+	raw_spin_lock(&gic_data_rdist_cpu(cpu)->rd_lock);
+	base = gic_data_rdist_cpu(cpu)->rd_base + SZ_128K;
+	writel_relaxed(vpe->vpe_id, base + GICR_VSGIR);
+	do {
+		status = readl_relaxed(base + GICR_VSGIPENDR);
+		if (!(status & GICR_VSGIPENDR_BUSY))
+			goto out;
+
+		count--;
+		if (!count) {
+			pr_err_ratelimited("Unable to get SGI status\n");
+			goto out;
+		}
+		cpu_relax();
+		udelay(1);
+	} while (count);
+
+out:
+	raw_spin_unlock(&gic_data_rdist_cpu(cpu)->rd_lock);
+	vpe_to_cpuid_unlock(vpe, flags);
+
+	if (!count)
+		return -ENXIO;
+
+	*val = !!(status & (1 << d->hwirq));
+
+	return 0;
+}
+
 static struct irq_chip its_sgi_irq_chip = {
 	.name			= "GICv4.1-sgi",
 	.irq_mask		= its_sgi_mask_irq,
 	.irq_unmask		= its_sgi_unmask_irq,
 	.irq_set_affinity	= its_sgi_set_affinity,
+	.irq_set_irqchip_state	= its_sgi_set_irqchip_state,
+	.irq_get_irqchip_state	= its_sgi_get_irqchip_state,
 };
 
 static int its_sgi_irq_domain_alloc(struct irq_domain *domain,
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index fd3be49ac9a5..590cdbeba9d5 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -345,6 +345,15 @@
 #define GICR_VPENDBASER_4_1_VGRP1EN	(1ULL << 58)
 #define GICR_VPENDBASER_4_1_VPEID	GENMASK_ULL(15, 0)
 
+#define GICR_VSGIR			0x0080
+
+#define GICR_VSGIR_VPEID		GENMASK(15, 0)
+
+#define GICR_VSGIPENDR			0x0088
+
+#define GICR_VSGIPENDR_BUSY		(1U << 31)
+#define GICR_VSGIPENDR_PENDING		GENMASK(15, 0)
+
 /*
  * ITS registers, offsets from ITS_base
  */
@@ -368,6 +377,11 @@
 
 #define GITS_TRANSLATER			0x10040
 
+#define GITS_SGIR			0x20020
+
+#define GITS_SGIR_VPEID			GENMASK_ULL(47, 32)
+#define GITS_SGIR_VINTID		GENMASK_ULL(3, 0)
+
 #define GITS_CTLR_ENABLE		(1U << 0)
 #define GITS_CTLR_ImDe			(1U << 1)
 #define	GITS_CTLR_ITS_NUMBER_SHIFT	4

From 05d32df13c6b3c0850b68928048536e9a736d520 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 4 Mar 2020 20:33:19 +0000
Subject: [PATCH 12/16] irqchip/gic-v4.1: Plumb set_vcpu_affinity SGI callbacks

Just like for vLPIs, there is some configuration information that cannot
be directly communicated through the normal irqchip API, and we have to
use our good old friend set_vcpu_affinity as a side-band communication
mechanism.

This is used to configure group and priority for a given vSGI.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/20200304203330.4967-13-maz@kernel.org
---
 drivers/irqchip/irq-gic-v3-its.c   | 18 ++++++++++++++++++
 include/linux/irqchip/arm-gic-v4.h |  5 +++++
 2 files changed, 23 insertions(+)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index c614f0c19807..aae53326d26f 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -4047,6 +4047,23 @@ static int its_sgi_get_irqchip_state(struct irq_data *d,
 	return 0;
 }
 
+static int its_sgi_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
+{
+	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+	struct its_cmd_info *info = vcpu_info;
+
+	switch (info->cmd_type) {
+	case PROP_UPDATE_VSGI:
+		vpe->sgi_config[d->hwirq].priority = info->priority;
+		vpe->sgi_config[d->hwirq].group = info->group;
+		its_configure_sgi(d, false);
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+}
+
 static struct irq_chip its_sgi_irq_chip = {
 	.name			= "GICv4.1-sgi",
 	.irq_mask		= its_sgi_mask_irq,
@@ -4054,6 +4071,7 @@ static struct irq_chip its_sgi_irq_chip = {
 	.irq_set_affinity	= its_sgi_set_affinity,
 	.irq_set_irqchip_state	= its_sgi_set_irqchip_state,
 	.irq_get_irqchip_state	= its_sgi_get_irqchip_state,
+	.irq_set_vcpu_affinity	= its_sgi_set_vcpu_affinity,
 };
 
 static int its_sgi_irq_domain_alloc(struct irq_domain *domain,
diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h
index 44e8c19e3d56..1b34100e3536 100644
--- a/include/linux/irqchip/arm-gic-v4.h
+++ b/include/linux/irqchip/arm-gic-v4.h
@@ -103,6 +103,7 @@ enum its_vcpu_info_cmd_type {
 	SCHEDULE_VPE,
 	DESCHEDULE_VPE,
 	INVALL_VPE,
+	PROP_UPDATE_VSGI,
 };
 
 struct its_cmd_info {
@@ -115,6 +116,10 @@ struct its_cmd_info {
 			bool		g0en;
 			bool		g1en;
 		};
+		struct {
+			u8		priority;
+			bool		group;
+		};
 	};
 };
 

From ae699ad348cdcd416cbf28e8a02fc468780161f7 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 4 Mar 2020 20:33:20 +0000
Subject: [PATCH 13/16] irqchip/gic-v4.1: Move doorbell management to the GICv4
 abstraction layer

In order to hide some of the differences between v4.0 and v4.1, move
the doorbell management out of the KVM code, and into the GICv4-specific
layer. This allows the calling code to ask for the doorbell when blocking,
and otherwise to leave the doorbell permanently disabled.

This matches the v4.1 code perfectly, and only results in a minor
refactoring of the v4.0 code.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Link: https://lore.kernel.org/r/20200304203330.4967-14-maz@kernel.org
---
 drivers/irqchip/irq-gic-v4.c       | 45 +++++++++++++++++++++++++++---
 include/kvm/arm_vgic.h             |  1 +
 include/linux/irqchip/arm-gic-v4.h |  3 +-
 virt/kvm/arm/vgic/vgic-v3.c        |  4 ++-
 virt/kvm/arm/vgic/vgic-v4.c        | 34 ++++++++++------------
 5 files changed, 61 insertions(+), 26 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c
index c01910d53f9e..117ba6db023d 100644
--- a/drivers/irqchip/irq-gic-v4.c
+++ b/drivers/irqchip/irq-gic-v4.c
@@ -87,6 +87,11 @@ static struct irq_domain *gic_domain;
 static const struct irq_domain_ops *vpe_domain_ops;
 static const struct irq_domain_ops *sgi_domain_ops;
 
+static bool has_v4_1(void)
+{
+	return !!sgi_domain_ops;
+}
+
 int its_alloc_vcpu_irqs(struct its_vm *vm)
 {
 	int vpe_base_irq, i;
@@ -139,18 +144,50 @@ static int its_send_vpe_cmd(struct its_vpe *vpe, struct its_cmd_info *info)
 	return irq_set_vcpu_affinity(vpe->irq, info);
 }
 
-int its_schedule_vpe(struct its_vpe *vpe, bool on)
+int its_make_vpe_non_resident(struct its_vpe *vpe, bool db)
 {
-	struct its_cmd_info info;
+	struct irq_desc *desc = irq_to_desc(vpe->irq);
+	struct its_cmd_info info = { };
 	int ret;
 
 	WARN_ON(preemptible());
 
-	info.cmd_type = on ? SCHEDULE_VPE : DESCHEDULE_VPE;
+	info.cmd_type = DESCHEDULE_VPE;
+	if (has_v4_1()) {
+		/* GICv4.1 can directly deal with doorbells */
+		info.req_db = db;
+	} else {
+		/* Undo the nested disable_irq() calls... */
+		while (db && irqd_irq_disabled(&desc->irq_data))
+			enable_irq(vpe->irq);
+	}
 
 	ret = its_send_vpe_cmd(vpe, &info);
 	if (!ret)
-		vpe->resident = on;
+		vpe->resident = false;
+
+	return ret;
+}
+
+int its_make_vpe_resident(struct its_vpe *vpe, bool g0en, bool g1en)
+{
+	struct its_cmd_info info = { };
+	int ret;
+
+	WARN_ON(preemptible());
+
+	info.cmd_type = SCHEDULE_VPE;
+	if (has_v4_1()) {
+		info.g0en = g0en;
+		info.g1en = g1en;
+	} else {
+		/* Disabled the doorbell, as we're about to enter the guest */
+		disable_irq_nosync(vpe->irq);
+	}
+
+	ret = its_send_vpe_cmd(vpe, &info);
+	if (!ret)
+		vpe->resident = true;
 
 	return ret;
 }
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 9d53f545a3d5..63457908c9c4 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -70,6 +70,7 @@ struct vgic_global {
 
 	/* Hardware has GICv4? */
 	bool			has_gicv4;
+	bool			has_gicv4_1;
 
 	/* GIC system register CPU interface */
 	struct static_key_false gicv3_cpuif;
diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h
index 1b34100e3536..34ed4b5754dd 100644
--- a/include/linux/irqchip/arm-gic-v4.h
+++ b/include/linux/irqchip/arm-gic-v4.h
@@ -125,7 +125,8 @@ struct its_cmd_info {
 
 int its_alloc_vcpu_irqs(struct its_vm *vm);
 void its_free_vcpu_irqs(struct its_vm *vm);
-int its_schedule_vpe(struct its_vpe *vpe, bool on);
+int its_make_vpe_resident(struct its_vpe *vpe, bool g0en, bool g1en);
+int its_make_vpe_non_resident(struct its_vpe *vpe, bool db);
 int its_invall_vpe(struct its_vpe *vpe);
 int its_map_vlpi(int irq, struct its_vlpi_map *map);
 int its_get_vlpi(int irq, struct its_vlpi_map *map);
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index f45635a6f0ec..1bc09b523486 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -595,7 +595,9 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 	/* GICv4 support? */
 	if (info->has_v4) {
 		kvm_vgic_global_state.has_gicv4 = gicv4_enable;
-		kvm_info("GICv4 support %sabled\n",
+		kvm_vgic_global_state.has_gicv4_1 = info->has_v4_1 && gicv4_enable;
+		kvm_info("GICv4%s support %sabled\n",
+			 kvm_vgic_global_state.has_gicv4_1 ? ".1" : "",
 			 gicv4_enable ? "en" : "dis");
 	}
 
diff --git a/virt/kvm/arm/vgic/vgic-v4.c b/virt/kvm/arm/vgic/vgic-v4.c
index 46f875589c47..1eb0f8c76219 100644
--- a/virt/kvm/arm/vgic/vgic-v4.c
+++ b/virt/kvm/arm/vgic/vgic-v4.c
@@ -67,10 +67,10 @@
  * it. And if we've migrated our vcpu from one CPU to another, we must
  * tell the ITS (so that the messages reach the right redistributor).
  * This is done in two steps: first issue a irq_set_affinity() on the
- * irq corresponding to the vcpu, then call its_schedule_vpe(). You
- * must be in a non-preemptible context. On exit, another call to
- * its_schedule_vpe() tells the redistributor that we're done with the
- * vcpu.
+ * irq corresponding to the vcpu, then call its_make_vpe_resident().
+ * You must be in a non-preemptible context. On exit, a call to
+ * its_make_vpe_non_resident() tells the redistributor that we're done
+ * with the vcpu.
  *
  * Finally, the doorbell handling: Each vcpu is allocated an interrupt
  * which will fire each time a VLPI is made pending whilst the vcpu is
@@ -86,7 +86,8 @@ static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info)
 	struct kvm_vcpu *vcpu = info;
 
 	/* We got the message, no need to fire again */
-	if (!irqd_irq_disabled(&irq_to_desc(irq)->irq_data))
+	if (!kvm_vgic_global_state.has_gicv4_1 &&
+	    !irqd_irq_disabled(&irq_to_desc(irq)->irq_data))
 		disable_irq_nosync(irq);
 
 	vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true;
@@ -199,19 +200,11 @@ void vgic_v4_teardown(struct kvm *kvm)
 int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db)
 {
 	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
-	struct irq_desc *desc = irq_to_desc(vpe->irq);
 
 	if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident)
 		return 0;
 
-	/*
-	 * If blocking, a doorbell is required. Undo the nested
-	 * disable_irq() calls...
-	 */
-	while (need_db && irqd_irq_disabled(&desc->irq_data))
-		enable_irq(vpe->irq);
-
-	return its_schedule_vpe(vpe, false);
+	return its_make_vpe_non_resident(vpe, need_db);
 }
 
 int vgic_v4_load(struct kvm_vcpu *vcpu)
@@ -232,18 +225,19 @@ int vgic_v4_load(struct kvm_vcpu *vcpu)
 	if (err)
 		return err;
 
-	/* Disabled the doorbell, as we're about to enter the guest */
-	disable_irq_nosync(vpe->irq);
-
-	err = its_schedule_vpe(vpe, true);
+	err = its_make_vpe_resident(vpe, false, vcpu->kvm->arch.vgic.enabled);
 	if (err)
 		return err;
 
 	/*
 	 * Now that the VPE is resident, let's get rid of a potential
-	 * doorbell interrupt that would still be pending.
+	 * doorbell interrupt that would still be pending. This is a
+	 * GICv4.0 only "feature"...
 	 */
-	return irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false);
+	if (!kvm_vgic_global_state.has_gicv4_1)
+		err = irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false);
+
+	return err;
 }
 
 static struct vgic_its *vgic_get_its(struct kvm *kvm,

From 6d31b6ff985dbd144b2c4d519cf573b8f81865d9 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 4 Mar 2020 20:33:21 +0000
Subject: [PATCH 14/16] irqchip/gic-v4.1: Add VSGI allocation/teardown

Allocate per-VPE SGIs when initializing the GIC-specific part of the
VPE data structure.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Link: https://lore.kernel.org/r/20200304203330.4967-15-maz@kernel.org
---
 drivers/irqchip/irq-gic-v4.c       | 68 +++++++++++++++++++++++++++++-
 include/linux/irqchip/arm-gic-v4.h |  2 +
 2 files changed, 69 insertions(+), 1 deletion(-)

diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c
index 117ba6db023d..99b33f60ac63 100644
--- a/drivers/irqchip/irq-gic-v4.c
+++ b/drivers/irqchip/irq-gic-v4.c
@@ -92,6 +92,47 @@ static bool has_v4_1(void)
 	return !!sgi_domain_ops;
 }
 
+static int its_alloc_vcpu_sgis(struct its_vpe *vpe, int idx)
+{
+	char *name;
+	int sgi_base;
+
+	if (!has_v4_1())
+		return 0;
+
+	name = kasprintf(GFP_KERNEL, "GICv4-sgi-%d", task_pid_nr(current));
+	if (!name)
+		goto err;
+
+	vpe->fwnode = irq_domain_alloc_named_id_fwnode(name, idx);
+	if (!vpe->fwnode)
+		goto err;
+
+	kfree(name);
+	name = NULL;
+
+	vpe->sgi_domain = irq_domain_create_linear(vpe->fwnode, 16,
+						   sgi_domain_ops, vpe);
+	if (!vpe->sgi_domain)
+		goto err;
+
+	sgi_base = __irq_domain_alloc_irqs(vpe->sgi_domain, -1, 16,
+					       NUMA_NO_NODE, vpe,
+					       false, NULL);
+	if (sgi_base <= 0)
+		goto err;
+
+	return 0;
+
+err:
+	if (vpe->sgi_domain)
+		irq_domain_remove(vpe->sgi_domain);
+	if (vpe->fwnode)
+		irq_domain_free_fwnode(vpe->fwnode);
+	kfree(name);
+	return -ENOMEM;
+}
+
 int its_alloc_vcpu_irqs(struct its_vm *vm)
 {
 	int vpe_base_irq, i;
@@ -118,8 +159,13 @@ int its_alloc_vcpu_irqs(struct its_vm *vm)
 	if (vpe_base_irq <= 0)
 		goto err;
 
-	for (i = 0; i < vm->nr_vpes; i++)
+	for (i = 0; i < vm->nr_vpes; i++) {
+		int ret;
 		vm->vpes[i]->irq = vpe_base_irq + i;
+		ret = its_alloc_vcpu_sgis(vm->vpes[i], i);
+		if (ret)
+			goto err;
+	}
 
 	return 0;
 
@@ -132,8 +178,28 @@ int its_alloc_vcpu_irqs(struct its_vm *vm)
 	return -ENOMEM;
 }
 
+static void its_free_sgi_irqs(struct its_vm *vm)
+{
+	int i;
+
+	if (!has_v4_1())
+		return;
+
+	for (i = 0; i < vm->nr_vpes; i++) {
+		unsigned int irq = irq_find_mapping(vm->vpes[i]->sgi_domain, 0);
+
+		if (WARN_ON(!irq))
+			continue;
+
+		irq_domain_free_irqs(irq, 16);
+		irq_domain_remove(vm->vpes[i]->sgi_domain);
+		irq_domain_free_fwnode(vm->vpes[i]->fwnode);
+	}
+}
+
 void its_free_vcpu_irqs(struct its_vm *vm)
 {
+	its_free_sgi_irqs(vm);
 	irq_domain_free_irqs(vm->vpes[0]->irq, vm->nr_vpes);
 	irq_domain_remove(vm->domain);
 	irq_domain_free_fwnode(vm->fwnode);
diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h
index 34ed4b5754dd..b120a01952fe 100644
--- a/include/linux/irqchip/arm-gic-v4.h
+++ b/include/linux/irqchip/arm-gic-v4.h
@@ -49,6 +49,8 @@ struct its_vpe {
 		};
 		/* GICv4.1 implementations */
 		struct {
+			struct fwnode_handle	*fwnode;
+			struct irq_domain	*sgi_domain;
 			struct {
 				u8	priority;
 				bool	enabled;

From d50676f5ce8481b98f9bbc1514b5d3f8747dd3c2 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 4 Mar 2020 20:33:22 +0000
Subject: [PATCH 15/16] irqchip/gic-v4.1: Add VSGI property setup

Add the SGI configuration entry point for KVM to use.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Link: https://lore.kernel.org/r/20200304203330.4967-16-maz@kernel.org
---
 drivers/irqchip/irq-gic-v4.c       | 13 +++++++++++++
 include/linux/irqchip/arm-gic-v4.h |  1 +
 2 files changed, 14 insertions(+)

diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c
index 99b33f60ac63..0c18714ae13e 100644
--- a/drivers/irqchip/irq-gic-v4.c
+++ b/drivers/irqchip/irq-gic-v4.c
@@ -320,6 +320,19 @@ int its_prop_update_vlpi(int irq, u8 config, bool inv)
 	return irq_set_vcpu_affinity(irq, &info);
 }
 
+int its_prop_update_vsgi(int irq, u8 priority, bool group)
+{
+	struct its_cmd_info info = {
+		.cmd_type = PROP_UPDATE_VSGI,
+		{
+			.priority	= priority,
+			.group		= group,
+		},
+	};
+
+	return irq_set_vcpu_affinity(irq, &info);
+}
+
 int its_init_v4(struct irq_domain *domain,
 		const struct irq_domain_ops *vpe_ops,
 		const struct irq_domain_ops *sgi_ops)
diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h
index b120a01952fe..6976b8331b60 100644
--- a/include/linux/irqchip/arm-gic-v4.h
+++ b/include/linux/irqchip/arm-gic-v4.h
@@ -134,6 +134,7 @@ int its_map_vlpi(int irq, struct its_vlpi_map *map);
 int its_get_vlpi(int irq, struct its_vlpi_map *map);
 int its_unmap_vlpi(int irq);
 int its_prop_update_vlpi(int irq, u8 config, bool inv);
+int its_prop_update_vsgi(int irq, u8 priority, bool group);
 
 struct irq_domain_ops;
 int its_init_v4(struct irq_domain *domain,

From 009384b38034111bf2c0c7bfb2740f5bd45c176c Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 4 Mar 2020 20:33:23 +0000
Subject: [PATCH 16/16] irqchip/gic-v4.1: Eagerly vmap vPEs

Now that we have HW-accelerated SGIs being delivered to VPEs, it
becomes required to map the VPEs on all ITSs instead of relying
on the lazy approach that we would use when using the ITS-list
mechanism.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Link: https://lore.kernel.org/r/20200304203330.4967-17-maz@kernel.org
---
 drivers/irqchip/irq-gic-v3-its.c | 52 ++++++++++++++++++++++++++------
 1 file changed, 42 insertions(+), 10 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index aae53326d26f..1259f7f86a21 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -189,6 +189,15 @@ 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)
 
+/*
+ * Skip ITSs that have no vLPIs mapped, unless we're on GICv4.1, as we
+ * always have vSGIs mapped.
+ */
+static bool require_its_list_vmovp(struct its_vm *vm, struct its_node *its)
+{
+	return (gic_rdists->has_rvpeid || vm->vlpi_count[its->list_nr]);
+}
+
 static u16 get_its_list(struct its_vm *vm)
 {
 	struct its_node *its;
@@ -198,7 +207,7 @@ static u16 get_its_list(struct its_vm *vm)
 		if (!is_v4(its))
 			continue;
 
-		if (vm->vlpi_count[its->list_nr])
+		if (require_its_list_vmovp(vm, its))
 			__set_bit(its->list_nr, &its_list);
 	}
 
@@ -1295,7 +1304,7 @@ static void its_send_vmovp(struct its_vpe *vpe)
 		if (!is_v4(its))
 			continue;
 
-		if (!vpe->its_vm->vlpi_count[its->list_nr])
+		if (!require_its_list_vmovp(vpe->its_vm, its))
 			continue;
 
 		desc.its_vmovp_cmd.col = &its->collections[col_id];
@@ -1586,12 +1595,31 @@ static int its_irq_set_irqchip_state(struct irq_data *d,
 	return 0;
 }
 
+/*
+ * Two favourable cases:
+ *
+ * (a) Either we have a GICv4.1, and all vPEs have to be mapped at all times
+ *     for vSGI delivery
+ *
+ * (b) Or the ITSs do not use a list map, meaning that VMOVP is cheap enough
+ *     and we're better off mapping all VPEs always
+ *
+ * If neither (a) nor (b) is true, then we map vPEs on demand.
+ *
+ */
+static bool gic_requires_eager_mapping(void)
+{
+	if (!its_list_map || gic_rdists->has_rvpeid)
+		return true;
+
+	return false;
+}
+
 static void its_map_vm(struct its_node *its, struct its_vm *vm)
 {
 	unsigned long flags;
 
-	/* Not using the ITS list? Everything is always mapped. */
-	if (!its_list_map)
+	if (gic_requires_eager_mapping())
 		return;
 
 	raw_spin_lock_irqsave(&vmovp_lock, flags);
@@ -1625,7 +1653,7 @@ static void its_unmap_vm(struct its_node *its, struct its_vm *vm)
 	unsigned long flags;
 
 	/* Not using the ITS list? Everything is always mapped. */
-	if (!its_list_map)
+	if (gic_requires_eager_mapping())
 		return;
 
 	raw_spin_lock_irqsave(&vmovp_lock, flags);
@@ -4282,8 +4310,12 @@ static int its_vpe_irq_domain_activate(struct irq_domain *domain,
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
 	struct its_node *its;
 
-	/* If we use the list map, we issue VMAPP on demand... */
-	if (its_list_map)
+	/*
+	 * If we use the list map, we issue VMAPP on demand... Unless
+	 * we're on a GICv4.1 and we eagerly map the VPE on all ITSs
+	 * so that VSGIs can work.
+	 */
+	if (!gic_requires_eager_mapping())
 		return 0;
 
 	/* Map the VPE to the first possible CPU */
@@ -4309,10 +4341,10 @@ static void its_vpe_irq_domain_deactivate(struct irq_domain *domain,
 	struct its_node *its;
 
 	/*
-	 * If we use the list map, we unmap the VPE once no VLPIs are
-	 * associated with the VM.
+	 * If we use the list map on GICv4.0, we unmap the VPE once no
+	 * VLPIs are associated with the VM.
 	 */
-	if (its_list_map)
+	if (!gic_requires_eager_mapping())
 		return;
 
 	list_for_each_entry(its, &its_nodes, entry) {