Merge tag 'hyperv-next-signed-20210216' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull Hyper-V updates from Wei Liu:

 - VMBus hardening patches from Andrea Parri and Andres Beltran.

 - Patches to make Linux boot as the root partition on Microsoft
   Hypervisor from Wei Liu.

 - One patch to add a new sysfs interface to support hibernation on
   Hyper-V from Dexuan Cui.

 - Two miscellaneous clean-up patches from Colin and Gustavo.

* tag 'hyperv-next-signed-20210216' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux: (31 commits)
  Revert "Drivers: hv: vmbus: Copy packets sent by Hyper-V out of the ring buffer"
  iommu/hyperv: setup an IO-APIC IRQ remapping domain for root partition
  x86/hyperv: implement an MSI domain for root partition
  asm-generic/hyperv: import data structures for mapping device interrupts
  asm-generic/hyperv: introduce hv_device_id and auxiliary structures
  asm-generic/hyperv: update hv_interrupt_entry
  asm-generic/hyperv: update hv_msi_entry
  x86/hyperv: implement and use hv_smp_prepare_cpus
  x86/hyperv: provide a bunch of helper functions
  ACPI / NUMA: add a stub function for node_to_pxm()
  x86/hyperv: handling hypercall page setup for root
  x86/hyperv: extract partition ID from Microsoft Hypervisor if necessary
  x86/hyperv: allocate output arg pages if required
  clocksource/hyperv: use MSR-based access if running as root
  Drivers: hv: vmbus: skip VMBus initialization if Linux is root
  x86/hyperv: detect if Linux is the root partition
  asm-generic/hyperv: change HV_CPU_POWER_MANAGEMENT to HV_CPU_MANAGEMENT
  hv: hyperv.h: Replace one-element array with flexible-array in struct icmsg_negotiate
  hv_netvsc: Restrict configurations on isolated guests
  Drivers: hv: vmbus: Enforce 'VMBus version >= 5.2' on isolated guests
  ...

1 files changed, 174 insertions, 3 deletions

diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c
index 1d21a0b5f724..e285a220c913 100644
--- a/drivers/iommu/hyperv-iommu.c
+++ b/drivers/iommu/hyperv-iommu.c
@@ -20,6 +20,7 @@
 #include <asm/io_apic.h>
 #include <asm/irq_remapping.h>
 #include <asm/hypervisor.h>
+#include <asm/mshyperv.h>
 
 #include "irq_remapping.h"
 
@@ -115,30 +116,43 @@ static const struct irq_domain_ops hyperv_ir_domain_ops = {
 	.free = hyperv_irq_remapping_free,
 };
 
+static const struct irq_domain_ops hyperv_root_ir_domain_ops;
 static int __init hyperv_prepare_irq_remapping(void)
 {
 	struct fwnode_handle *fn;
 	int i;
+	const char *name;
+	const struct irq_domain_ops *ops;
 
 	if (!hypervisor_is_type(X86_HYPER_MS_HYPERV) ||
 	    x86_init.hyper.msi_ext_dest_id() ||
 	    !x2apic_supported())
 		return -ENODEV;
 
-	fn = irq_domain_alloc_named_id_fwnode("HYPERV-IR", 0);
+	if (hv_root_partition) {
+		name = "HYPERV-ROOT-IR";
+		ops = &hyperv_root_ir_domain_ops;
+	} else {
+		name = "HYPERV-IR";
+		ops = &hyperv_ir_domain_ops;
+	}
+
+	fn = irq_domain_alloc_named_id_fwnode(name, 0);
 	if (!fn)
 		return -ENOMEM;
 
 	ioapic_ir_domain =
 		irq_domain_create_hierarchy(arch_get_ir_parent_domain(),
-				0, IOAPIC_REMAPPING_ENTRY, fn,
-				&hyperv_ir_domain_ops, NULL);
+				0, IOAPIC_REMAPPING_ENTRY, fn, ops, NULL);
 
 	if (!ioapic_ir_domain) {
 		irq_domain_free_fwnode(fn);
 		return -ENOMEM;
 	}
 
+	if (hv_root_partition)
+		return 0; /* The rest is only relevant to guests */
+
 	/*
 	 * Hyper-V doesn't provide irq remapping function for
 	 * IO-APIC and so IO-APIC only accepts 8-bit APIC ID.
@@ -166,4 +180,161 @@ struct irq_remap_ops hyperv_irq_remap_ops = {
 	.enable			= hyperv_enable_irq_remapping,
 };
 
+/* IRQ remapping domain when Linux runs as the root partition */
+struct hyperv_root_ir_data {
+	u8 ioapic_id;
+	bool is_level;
+	struct hv_interrupt_entry entry;
+};
+
+static void
+hyperv_root_ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg)
+{
+	u64 status;
+	u32 vector;
+	struct irq_cfg *cfg;
+	int ioapic_id;
+	struct cpumask *affinity;
+	int cpu;
+	struct hv_interrupt_entry entry;
+	struct hyperv_root_ir_data *data = irq_data->chip_data;
+	struct IO_APIC_route_entry e;
+
+	cfg = irqd_cfg(irq_data);
+	affinity = irq_data_get_effective_affinity_mask(irq_data);
+	cpu = cpumask_first_and(affinity, cpu_online_mask);
+
+	vector = cfg->vector;
+	ioapic_id = data->ioapic_id;
+
+	if (data->entry.source == HV_DEVICE_TYPE_IOAPIC
+	    && data->entry.ioapic_rte.as_uint64) {
+		entry = data->entry;
+
+		status = hv_unmap_ioapic_interrupt(ioapic_id, &entry);
+
+		if (status != HV_STATUS_SUCCESS)
+			pr_debug("%s: unexpected unmap status %lld\n", __func__, status);
+
+		data->entry.ioapic_rte.as_uint64 = 0;
+		data->entry.source = 0; /* Invalid source */
+	}
+
+
+	status = hv_map_ioapic_interrupt(ioapic_id, data->is_level, cpu,
+					vector, &entry);
+
+	if (status != HV_STATUS_SUCCESS) {
+		pr_err("%s: map hypercall failed, status %lld\n", __func__, status);
+		return;
+	}
+
+	data->entry = entry;
+
+	/* Turn it into an IO_APIC_route_entry, and generate MSI MSG. */
+	e.w1 = entry.ioapic_rte.low_uint32;
+	e.w2 = entry.ioapic_rte.high_uint32;
+
+	memset(msg, 0, sizeof(*msg));
+	msg->arch_data.vector = e.vector;
+	msg->arch_data.delivery_mode = e.delivery_mode;
+	msg->arch_addr_lo.dest_mode_logical = e.dest_mode_logical;
+	msg->arch_addr_lo.dmar_format = e.ir_format;
+	msg->arch_addr_lo.dmar_index_0_14 = e.ir_index_0_14;
+}
+
+static int hyperv_root_ir_set_affinity(struct irq_data *data,
+		const struct cpumask *mask, bool force)
+{
+	struct irq_data *parent = data->parent_data;
+	struct irq_cfg *cfg = irqd_cfg(data);
+	int ret;
+
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+		return ret;
+
+	send_cleanup_vector(cfg);
+
+	return 0;
+}
+
+static struct irq_chip hyperv_root_ir_chip = {
+	.name			= "HYPERV-ROOT-IR",
+	.irq_ack		= apic_ack_irq,
+	.irq_set_affinity	= hyperv_root_ir_set_affinity,
+	.irq_compose_msi_msg	= hyperv_root_ir_compose_msi_msg,
+};
+
+static int hyperv_root_irq_remapping_alloc(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs,
+				     void *arg)
+{
+	struct irq_alloc_info *info = arg;
+	struct irq_data *irq_data;
+	struct hyperv_root_ir_data *data;
+	int ret = 0;
+
+	if (!info || info->type != X86_IRQ_ALLOC_TYPE_IOAPIC || nr_irqs > 1)
+		return -EINVAL;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+	if (ret < 0)
+		return ret;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data) {
+		irq_domain_free_irqs_common(domain, virq, nr_irqs);
+		return -ENOMEM;
+	}
+
+	irq_data = irq_domain_get_irq_data(domain, virq);
+	if (!irq_data) {
+		kfree(data);
+		irq_domain_free_irqs_common(domain, virq, nr_irqs);
+		return -EINVAL;
+	}
+
+	data->ioapic_id = info->devid;
+	data->is_level = info->ioapic.is_level;
+
+	irq_data->chip = &hyperv_root_ir_chip;
+	irq_data->chip_data = data;
+
+	return 0;
+}
+
+static void hyperv_root_irq_remapping_free(struct irq_domain *domain,
+				 unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *irq_data;
+	struct hyperv_root_ir_data *data;
+	struct hv_interrupt_entry *e;
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+
+		if (irq_data && irq_data->chip_data) {
+			data = irq_data->chip_data;
+			e = &data->entry;
+
+			if (e->source == HV_DEVICE_TYPE_IOAPIC
+			      && e->ioapic_rte.as_uint64)
+				hv_unmap_ioapic_interrupt(data->ioapic_id,
+							&data->entry);
+
+			kfree(data);
+		}
+	}
+
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
+
+static const struct irq_domain_ops hyperv_root_ir_domain_ops = {
+	.select = hyperv_irq_remapping_select,
+	.alloc = hyperv_root_irq_remapping_alloc,
+	.free = hyperv_root_irq_remapping_free,
+};
+
 #endif