[PATCH v2 23/52] irqchip/gic-v3-its: Add VPE scheduling

[Marc Zyngier]

When a VPE is scheduled to run, the corresponding redistributor must
be told so, by setting VPROPBASER to the VM's property table, and
VPENDBASER to the vcpu's pending table.

When scheduled out, we preserve the IDAI and PendingLast bits. The
latter is specially important, as it tells the hypervisor that
there are pending interrupts for this vcpu.

Reviewed-by: Eric Auger <eric.auger@xxxxxxxxxx>
Signed-off-by: Marc Zyngier <marc.zyngier@xxxxxxx>
---
 drivers/irqchip/irq-gic-v3-its.c   | 73 ++++++++++++++++++++++++++++++++++++++
 include/linux/irqchip/arm-gic-v3.h | 58 ++++++++++++++++++++++++++++++
 2 files changed, 131 insertions(+)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 276602efdfa0..be8598354d5a 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -154,6 +154,7 @@ static DEFINE_IDA(its_vpeid_ida);
 
 #define gic_data_rdist()		(raw_cpu_ptr(gic_rdists->rdist))
 #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 struct its_collection *dev_event_to_col(struct its_device *its_dev,
 					       u32 event)
@@ -2144,8 +2145,80 @@ static const struct irq_domain_ops its_domain_ops = {
 	.deactivate		= its_irq_domain_deactivate,
 };
 
+static void its_vpe_schedule(struct its_vpe *vpe)
+{
+	void * __iomem vlpi_base = gic_data_rdist_vlpi_base();
+	u64 val;
+
+	/* Schedule the VPE */
+	val  = virt_to_phys(page_address(vpe->its_vm->vprop_page)) &
+		GENMASK_ULL(51, 12);
+	val |= (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK;
+	val |= GICR_VPROPBASER_RaWb;
+	val |= GICR_VPROPBASER_InnerShareable;
+	gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
+
+	val  = virt_to_phys(page_address(vpe->vpt_page)) &
+		GENMASK_ULL(51, 16);
+	val |= GICR_VPENDBASER_RaWaWb;
+	val |= GICR_VPENDBASER_NonShareable;
+	/*
+	 * There is no good way of finding out if the pending table is
+	 * empty as we can race against the doorbell interrupt very
+	 * easily. So in the end, vpe->pending_last is only an
+	 * indication that the vcpu has something pending, not one
+	 * that the pending table is empty. A good implementation
+	 * would be able to read its coarse map pretty quickly anyway,
+	 * making this a tolerable issue.
+	 */
+	val |= GICR_VPENDBASER_PendingLast;
+	val |= vpe->idai ? GICR_VPENDBASER_IDAI : 0;
+	val |= GICR_VPENDBASER_Valid;
+	gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+}
+
+static void its_vpe_deschedule(struct its_vpe *vpe)
+{
+	void * __iomem vlpi_base = gic_data_rdist_vlpi_base();
+	u64 val;
+
+	/* We're being scheduled out */
+	val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
+	val &= ~GICR_VPENDBASER_Valid;
+	gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+
+	val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
+	while (val & GICR_VPENDBASER_Dirty) {
+		cpu_relax();
+		val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
+	}
+
+	vpe->idai = !!(val & GICR_VPENDBASER_IDAI);
+	vpe->pending_last = !!(val & GICR_VPENDBASER_PendingLast);
+}
+
+static int its_vpe_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 SCHEDULE_VPE:
+		its_vpe_schedule(vpe);
+		return 0;
+
+	case DESCHEDULE_VPE:
+		its_vpe_deschedule(vpe);
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+}
+
 static struct irq_chip its_vpe_irq_chip = {
 	.name			= "GICv4-vpe",
+	.irq_set_vcpu_affinity	= its_vpe_set_vcpu_affinity,
 };
 
 static int its_vpe_id_alloc(void)
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 17ba0d732f12..6bc142cfa616 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -212,6 +212,64 @@
 #define LPI_PROP_GROUP1			(1 << 1)
 #define LPI_PROP_ENABLED		(1 << 0)
 
+/*
+ * Re-Distributor registers, offsets from VLPI_base
+ */
+#define GICR_VPROPBASER			0x0070
+
+#define GICR_VPROPBASER_IDBITS_MASK	0x1f
+
+#define GICR_VPROPBASER_SHAREABILITY_SHIFT		(10)
+#define GICR_VPROPBASER_INNER_CACHEABILITY_SHIFT	(7)
+#define GICR_VPROPBASER_OUTER_CACHEABILITY_SHIFT	(56)
+
+#define GICR_VPROPBASER_SHAREABILITY_MASK				\
+	GIC_BASER_SHAREABILITY(GICR_VPROPBASER, SHAREABILITY_MASK)
+#define GICR_VPROPBASER_INNER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, MASK)
+#define GICR_VPROPBASER_OUTER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GICR_VPROPBASER, OUTER, MASK)
+#define GICR_VPROPBASER_CACHEABILITY_MASK				\
+	GICR_VPROPBASER_INNER_CACHEABILITY_MASK
+
+#define GICR_VPROPBASER_InnerShareable					\
+	GIC_BASER_SHAREABILITY(GICR_VPROPBASER, InnerShareable)
+
+#define GICR_VPROPBASER_nCnB	GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, nCnB)
+#define GICR_VPROPBASER_nC 	GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, nC)
+#define GICR_VPROPBASER_RaWt	GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWt)
+#define GICR_VPROPBASER_RaWb	GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWt)
+#define GICR_VPROPBASER_WaWt	GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, WaWt)
+#define GICR_VPROPBASER_WaWb	GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, WaWb)
+#define GICR_VPROPBASER_RaWaWt	GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWt)
+#define GICR_VPROPBASER_RaWaWb	GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWb)
+
+#define GICR_VPENDBASER			0x0078
+
+#define GICR_VPENDBASER_SHAREABILITY_SHIFT		(10)
+#define GICR_VPENDBASER_INNER_CACHEABILITY_SHIFT	(7)
+#define GICR_VPENDBASER_OUTER_CACHEABILITY_SHIFT	(56)
+#define GICR_VPENDBASER_SHAREABILITY_MASK				\
+	GIC_BASER_SHAREABILITY(GICR_VPENDBASER, SHAREABILITY_MASK)
+#define GICR_VPENDBASER_INNER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, MASK)
+#define GICR_VPENDBASER_OUTER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GICR_VPENDBASER, OUTER, MASK)
+#define GICR_VPENDBASER_CACHEABILITY_MASK				\
+	GICR_VPENDBASER_INNER_CACHEABILITY_MASK
+
+#define GICR_VPENDBASER_NonShareable					\
+	GIC_BASER_SHAREABILITY(GICR_VPENDBASER, NonShareable)
+
+#define GICR_VPENDBASER_nCnB	GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, nCnB)
+#define GICR_VPENDBASER_nC 	GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, nC)
+#define GICR_VPENDBASER_RaWt	GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWt)
+#define GICR_VPENDBASER_RaWb	GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWt)
+#define GICR_VPENDBASER_WaWt	GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, WaWt)
+#define GICR_VPENDBASER_WaWb	GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, WaWb)
+#define GICR_VPENDBASER_RaWaWt	GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWaWt)
+#define GICR_VPENDBASER_RaWaWb	GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWaWb)
+
 #define GICR_VPENDBASER_Dirty		(1ULL << 60)
 #define GICR_VPENDBASER_PendingLast	(1ULL << 61)
 #define GICR_VPENDBASER_IDAI		(1ULL << 62)
-- 
2.11.0