Merge tag 'hyperv-next-signed-20250602' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull hyperv updates from Wei Liu:

 - Support for Virtual Trust Level (VTL) on arm64 (Roman Kisel)

 - Fixes for Hyper-V UIO driver (Long Li)

 - Fixes for Hyper-V PCI driver (Michael Kelley)

 - Select CONFIG_SYSFB for Hyper-V guests (Michael Kelley)

 - Documentation updates for Hyper-V VMBus (Michael Kelley)

 - Enhance logging for hv_kvp_daemon (Shradha Gupta)

* tag 'hyperv-next-signed-20250602' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux: (23 commits)
  Drivers: hv: Always select CONFIG_SYSFB for Hyper-V guests
  Drivers: hv: vmbus: Add comments about races with "channels" sysfs dir
  Documentation: hyperv: Update VMBus doc with new features and info
  PCI: hv: Remove unnecessary flex array in struct pci_packet
  Drivers: hv: Remove hv_alloc/free_* helpers
  Drivers: hv: Use kzalloc for panic page allocation
  uio_hv_generic: Align ring size to system page
  uio_hv_generic: Use correct size for interrupt and monitor pages
  Drivers: hv: Allocate interrupt and monitor pages aligned to system page boundary
  arch/x86: Provide the CPU number in the wakeup AP callback
  x86/hyperv: Fix APIC ID and VP index confusion in hv_snp_boot_ap()
  PCI: hv: Get vPCI MSI IRQ domain from DeviceTree
  ACPI: irq: Introduce acpi_get_gsi_dispatcher()
  Drivers: hv: vmbus: Introduce hv_get_vmbus_root_device()
  Drivers: hv: vmbus: Get the IRQ number from DeviceTree
  dt-bindings: microsoft,vmbus: Add interrupt and DMA coherence properties
  arm64, x86: hyperv: Report the VTL the system boots in
  arm64: hyperv: Initialize the Virtual Trust Level field
  Drivers: hv: Provide arch-neutral implementation of get_vtl()
  Drivers: hv: Enable VTL mode for arm64
  ...

Author: torvalds

Documentation/devicetree/bindings/bus/microsoft,vmbus.yaml

@@ -10,8 +10,8 @@ maintainers:
   - Saurabh Sengar <ssengar@linux.microsoft.com>
 
 description:
-  VMBus is a software bus that implement the protocols for communication
-  between the root or host OS and guest OSs (virtual machines).
+  VMBus is a software bus that implements the protocols for communication
+  between the root or host OS and guest OS'es (virtual machines).
 
 properties:
   compatible:
@@ -25,16 +25,25 @@ properties:
   '#size-cells':
     const: 1
 
+  dma-coherent: true
+
+  interrupts:
+    maxItems: 1
+    description: Interrupt is used to report a message from the host.
+
 required:
   - compatible
   - ranges
+  - interrupts
   - '#address-cells'
   - '#size-cells'
 
 additionalProperties: false
 
 examples:
   - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
     soc {
         #address-cells = <2>;
         #size-cells = <1>;
@@ -49,6 +58,9 @@ examples:
                 #address-cells = <2>;
                 #size-cells = <1>;
                 ranges = <0x0f 0xf0000000 0x0f 0xf0000000 0x10000000>;
+                dma-coherent;
+                interrupt-parent = <&gic>;
+                interrupts = <GIC_PPI 2 IRQ_TYPE_EDGE_RISING>;
             };
         };
     };

Documentation/virt/hyperv/vmbus.rst

@@ -250,10 +250,18 @@ interrupts are not Linux IRQs, there are no entries in /proc/interrupts
 or /proc/irq corresponding to individual VMBus channel interrupts.
 
 An online CPU in a Linux guest may not be taken offline if it has
-VMBus channel interrupts assigned to it.  Any such channel
-interrupts must first be manually reassigned to another CPU as
-described above.  When no channel interrupts are assigned to the
-CPU, it can be taken offline.
+VMBus channel interrupts assigned to it. Starting in kernel v6.15,
+any such interrupts are automatically reassigned to some other CPU
+at the time of offlining. The "other" CPU is chosen by the
+implementation and is not load balanced or otherwise intelligently
+determined. If the CPU is onlined again, channel interrupts previously
+assigned to it are not moved back. As a result, after multiple CPUs
+have been offlined, and perhaps onlined again, the interrupt-to-CPU
+mapping may be scrambled and non-optimal. In such a case, optimal
+assignments must be re-established manually. For kernels v6.14 and
+earlier, any conflicting channel interrupts must first be manually
+reassigned to another CPU as described above. Then when no channel
+interrupts are assigned to the CPU, it can be taken offline.
 
 The VMBus channel interrupt handling code is designed to work
 correctly even if an interrupt is received on a CPU other than the
@@ -324,3 +332,15 @@ rescinded, neither Hyper-V nor Linux retains any state about
 its previous existence. Such a device might be re-added later,
 in which case it is treated as an entirely new device. See
 vmbus_onoffer_rescind().
+
+For some devices, such as the KVP device, Hyper-V automatically
+sends a rescind message when the primary channel is closed,
+likely as a result of unbinding the device from its driver.
+The rescind causes Linux to remove the device. But then Hyper-V
+immediately reoffers the device to the guest, causing a new
+instance of the device to be created in Linux. For other
+devices, such as the synthetic SCSI and NIC devices, closing the
+primary channel does *not* result in Hyper-V sending a rescind
+message. The device continues to exist in Linux on the VMBus,
+but with no driver bound to it. The same driver or a new driver
+can subsequently be bound to the existing instance of the device.

arch/arm64/hyperv/mshyperv.c

@@ -28,6 +28,48 @@ int hv_get_hypervisor_version(union hv_hypervisor_version_info *info)
 }
 EXPORT_SYMBOL_GPL(hv_get_hypervisor_version);
 
+#ifdef CONFIG_ACPI
+
+static bool __init hyperv_detect_via_acpi(void)
+{
+	if (acpi_disabled)
+		return false;
+	/*
+	 * Hypervisor ID is only available in ACPI v6+, and the
+	 * structure layout was extended in v6 to accommodate that
+	 * new field.
+	 *
+	 * At the very minimum, this check makes sure not to read
+	 * past the FADT structure.
+	 *
+	 * It is also needed to catch running in some unknown
+	 * non-Hyper-V environment that has ACPI 5.x or less.
+	 * In such a case, it can't be Hyper-V.
+	 */
+	if (acpi_gbl_FADT.header.revision < 6)
+		return false;
+	return strncmp((char *)&acpi_gbl_FADT.hypervisor_id, "MsHyperV", 8) == 0;
+}
+
+#else
+
+static bool __init hyperv_detect_via_acpi(void)
+{
+	return false;
+}
+
+#endif
+
+static bool __init hyperv_detect_via_smccc(void)
+{
+	uuid_t hyperv_uuid = UUID_INIT(
+		0x58ba324d, 0x6447, 0x24cd,
+		0x75, 0x6c, 0xef, 0x8e,
+		0x24, 0x70, 0x59, 0x16);
+
+	return arm_smccc_hypervisor_has_uuid(&hyperv_uuid);
+}
+
 static int __init hyperv_init(void)
 {
 	struct hv_get_vp_registers_output	result;
@@ -36,13 +78,11 @@ static int __init hyperv_init(void)
 
 	/*
 	 * Allow for a kernel built with CONFIG_HYPERV to be running in
-	 * a non-Hyper-V environment, including on DT instead of ACPI.
+	 * a non-Hyper-V environment.
+	 *
 	 * In such cases, do nothing and return success.
 	 */
-	if (acpi_disabled)
-		return 0;
-
-	if (strncmp((char *)&acpi_gbl_FADT.hypervisor_id, "MsHyperV", 8))
+	if (!hyperv_detect_via_acpi() && !hyperv_detect_via_smccc())
 		return 0;
 
 	/* Setup the guest ID */
@@ -77,6 +117,9 @@ static int __init hyperv_init(void)
 
 	if (ms_hyperv.priv_high & HV_ACCESS_PARTITION_ID)
 		hv_get_partition_id();
+	ms_hyperv.vtl = get_vtl();
+	if (ms_hyperv.vtl > 0) /* non default VTL */
+		pr_info("Linux runs in Hyper-V Virtual Trust Level %d\n", ms_hyperv.vtl);
 
 	ms_hyperv_late_init();
 

arch/arm64/kvm/hypercalls.c

@@ -270,6 +270,7 @@ int kvm_smccc_call_handler(struct kvm_vcpu *vcpu)
 	u32 feature;
 	u8 action;
 	gpa_t gpa;
+	uuid_t uuid;
 
 	action = kvm_smccc_get_action(vcpu, func_id);
 	switch (action) {
@@ -355,10 +356,11 @@ int kvm_smccc_call_handler(struct kvm_vcpu *vcpu)
 			val[0] = gpa;
 		break;
 	case ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID:
-		val[0] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0;
-		val[1] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1;
-		val[2] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2;
-		val[3] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3;
+		uuid = ARM_SMCCC_VENDOR_HYP_UID_KVM;
+		val[0] = smccc_uuid_to_reg(&uuid, 0);
+		val[1] = smccc_uuid_to_reg(&uuid, 1);
+		val[2] = smccc_uuid_to_reg(&uuid, 2);
+		val[3] = smccc_uuid_to_reg(&uuid, 3);
 		break;
 	case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID:
 		val[0] = smccc_feat->vendor_hyp_bmap;

arch/x86/coco/sev/core.c

@@ -869,12 +869,12 @@ static void *snp_alloc_vmsa_page(int cpu)
 	return page_address(p + 1);
 }
 
-static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
+static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip, unsigned int cpu)
 {
 	struct sev_es_save_area *cur_vmsa, *vmsa;
 	struct svsm_ca *caa;
 	u8 sipi_vector;
-	int cpu, ret;
+	int ret;
 	u64 cr4;
 
 	/*
@@ -895,15 +895,6 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
 
 	/* Override start_ip with known protected guest start IP */
 	start_ip = real_mode_header->sev_es_trampoline_start;
-
-	/* Find the logical CPU for the APIC ID */
-	for_each_present_cpu(cpu) {
-		if (arch_match_cpu_phys_id(cpu, apic_id))
-			break;
-	}
-	if (cpu >= nr_cpu_ids)
-		return -EINVAL;
-
 	cur_vmsa = per_cpu(sev_vmsa, cpu);
 
 	/*

arch/x86/hyperv/hv_init.c

@@ -391,40 +391,6 @@ static void __init hv_stimer_setup_percpu_clockev(void)
 		old_setup_percpu_clockev();
 }
 
-#if IS_ENABLED(CONFIG_HYPERV_VTL_MODE)
-static u8 __init get_vtl(void)
-{
-	u64 control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_REGISTERS;
-	struct hv_input_get_vp_registers *input;
-	struct hv_output_get_vp_registers *output;
-	unsigned long flags;
-	u64 ret;
-
-	local_irq_save(flags);
-	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
-	output = *this_cpu_ptr(hyperv_pcpu_output_arg);
-
-	memset(input, 0, struct_size(input, names, 1));
-	input->partition_id = HV_PARTITION_ID_SELF;
-	input->vp_index = HV_VP_INDEX_SELF;
-	input->input_vtl.as_uint8 = 0;
-	input->names[0] = HV_REGISTER_VSM_VP_STATUS;
-
-	ret = hv_do_hypercall(control, input, output);
-	if (hv_result_success(ret)) {
-		ret = output->values[0].reg8 & HV_X64_VTL_MASK;
-	} else {
-		pr_err("Failed to get VTL(error: %lld) exiting...\n", ret);
-		BUG();
-	}
-
-	local_irq_restore(flags);
-	return ret;
-}
-#else
-static inline u8 get_vtl(void) { return 0; }
-#endif
-
 /*
  * This function is to be invoked early in the boot sequence after the
  * hypervisor has been detected.
@@ -707,3 +673,36 @@ bool hv_is_hyperv_initialized(void)
 	return hypercall_msr.enable;
 }
 EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized);
+
+int hv_apicid_to_vp_index(u32 apic_id)
+{
+	u64 control;
+	u64 status;
+	unsigned long irq_flags;
+	struct hv_get_vp_from_apic_id_in *input;
+	u32 *output, ret;
+
+	local_irq_save(irq_flags);
+
+	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+	memset(input, 0, sizeof(*input));
+	input->partition_id = HV_PARTITION_ID_SELF;
+	input->apic_ids[0] = apic_id;
+
+	output = *this_cpu_ptr(hyperv_pcpu_output_arg);
+
+	control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_INDEX_FROM_APIC_ID;
+	status = hv_do_hypercall(control, input, output);
+	ret = output[0];
+
+	local_irq_restore(irq_flags);
+
+	if (!hv_result_success(status)) {
+		pr_err("failed to get vp index from apic id %d, status %#llx\n",
+		       apic_id, status);
+		return -EINVAL;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hv_apicid_to_vp_index);

arch/x86/hyperv/hv_vtl.c

@@ -56,7 +56,12 @@ static void  __noreturn hv_vtl_restart(char __maybe_unused *cmd)
 
 void __init hv_vtl_init_platform(void)
 {
-	pr_info("Linux runs in Hyper-V Virtual Trust Level\n");
+	/*
+	 * This function is a no-op if the VTL mode is not enabled.
+	 * If it is, this function runs if and only the kernel boots in
+	 * VTL2 which the x86 hv initialization path makes sure of.
+	 */
+	pr_info("Linux runs in Hyper-V Virtual Trust Level %d\n", ms_hyperv.vtl);
 
 	x86_platform.realmode_reserve = x86_init_noop;
 	x86_platform.realmode_init = x86_init_noop;
@@ -207,63 +212,23 @@ static int hv_vtl_bringup_vcpu(u32 target_vp_index, int cpu, u64 eip_ignored)
 	return ret;
 }
 
-static int hv_vtl_apicid_to_vp_id(u32 apic_id)
-{
-	u64 control;
-	u64 status;
-	unsigned long irq_flags;
-	struct hv_get_vp_from_apic_id_in *input;
-	u32 *output, ret;
-
-	local_irq_save(irq_flags);
-
-	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
-	memset(input, 0, sizeof(*input));
-	input->partition_id = HV_PARTITION_ID_SELF;
-	input->apic_ids[0] = apic_id;
-
-	output = *this_cpu_ptr(hyperv_pcpu_output_arg);
-
-	control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_ID_FROM_APIC_ID;
-	status = hv_do_hypercall(control, input, output);
-	ret = output[0];
-
-	local_irq_restore(irq_flags);
-
-	if (!hv_result_success(status)) {
-		pr_err("failed to get vp id from apic id %d, status %#llx\n",
-		       apic_id, status);
-		return -EINVAL;
-	}
-
-	return ret;
-}
-
-static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip)
+static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip, unsigned int cpu)
 {
-	int vp_id, cpu;
-
-	/* Find the logical CPU for the APIC ID */
-	for_each_present_cpu(cpu) {
-		if (arch_match_cpu_phys_id(cpu, apicid))
-			break;
-	}
-	if (cpu >= nr_cpu_ids)
-		return -EINVAL;
+	int vp_index;
 
 	pr_debug("Bringing up CPU with APIC ID %d in VTL2...\n", apicid);
-	vp_id = hv_vtl_apicid_to_vp_id(apicid);
+	vp_index = hv_apicid_to_vp_index(apicid);
 
-	if (vp_id < 0) {
+	if (vp_index < 0) {
 		pr_err("Couldn't find CPU with APIC ID %d\n", apicid);
 		return -EINVAL;
 	}
-	if (vp_id > ms_hyperv.max_vp_index) {
-		pr_err("Invalid CPU id %d for APIC ID %d\n", vp_id, apicid);
+	if (vp_index > ms_hyperv.max_vp_index) {
+		pr_err("Invalid CPU id %d for APIC ID %d\n", vp_index, apicid);
 		return -EINVAL;
 	}
 
-	return hv_vtl_bringup_vcpu(vp_id, cpu, start_eip);
+	return hv_vtl_bringup_vcpu(vp_index, cpu, start_eip);
 }
 
 int __init hv_vtl_early_init(void)