Merge tag 'hyperv-next-signed-20250324' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull hyperv updates from Wei Liu:

 - Add support for running as the root partition in Hyper-V (Microsoft
   Hypervisor) by exposing /dev/mshv (Nuno and various people)

 - Add support for CPU offlining in Hyper-V (Hamza Mahfooz)

 - Misc fixes and cleanups (Roman Kisel, Tianyu Lan, Wei Liu, Michael
   Kelley, Thorsten Blum)

* tag 'hyperv-next-signed-20250324' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux: (24 commits)
  x86/hyperv: fix an indentation issue in mshyperv.h
  x86/hyperv: Add comments about hv_vpset and var size hypercall input args
  Drivers: hv: Introduce mshv_root module to expose /dev/mshv to VMMs
  hyperv: Add definitions for root partition driver to hv headers
  x86: hyperv: Add mshv_handler() irq handler and setup function
  Drivers: hv: Introduce per-cpu event ring tail
  Drivers: hv: Export some functions for use by root partition module
  acpi: numa: Export node_to_pxm()
  hyperv: Introduce hv_recommend_using_aeoi()
  arm64/hyperv: Add some missing functions to arm64
  x86/mshyperv: Add support for extended Hyper-V features
  hyperv: Log hypercall status codes as strings
  x86/hyperv: Fix check of return value from snp_set_vmsa()
  x86/hyperv: Add VTL mode callback for restarting the system
  x86/hyperv: Add VTL mode emergency restart callback
  hyperv: Remove unused union and structs
  hyperv: Add CONFIG_MSHV_ROOT to gate root partition support
  hyperv: Change hv_root_partition into a function
  hyperv: Convert hypercall statuses to linux error codes
  drivers/hv: add CPU offlining support
  ...

Author: torvalds

Documentation/userspace-api/ioctl/ioctl-number.rst

@@ -370,6 +370,8 @@ Code  Seq#    Include File                                           Comments
 0xB7  all    uapi/linux/remoteproc_cdev.h                            <mailto:linux-remoteproc@vger.kernel.org>
 0xB7  all    uapi/linux/nsfs.h                                       <mailto:Andrei Vagin <avagin@openvz.org>>
 0xB8  01-02  uapi/misc/mrvl_cn10k_dpi.h                              Marvell CN10K DPI driver
+0xB8  all    uapi/linux/mshv.h                                       Microsoft Hyper-V /dev/mshv driver
+                                                                     <mailto:linux-hyperv@vger.kernel.org>
 0xC0  00-0F  linux/usb/iowarrior.h
 0xCA  00-0F  uapi/misc/cxl.h
 0xCA  10-2F  uapi/misc/ocxl.h

arch/arm64/hyperv/hv_core.c

@@ -53,6 +53,23 @@ u64 hv_do_fast_hypercall8(u16 code, u64 input)
 }
 EXPORT_SYMBOL_GPL(hv_do_fast_hypercall8);
 
+/*
+ * hv_do_fast_hypercall16 -- Invoke the specified hypercall
+ * with arguments in registers instead of physical memory.
+ * Avoids the overhead of virt_to_phys for simple hypercalls.
+ */
+u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
+{
+	struct arm_smccc_res	res;
+	u64			control;
+
+	control = (u64)code | HV_HYPERCALL_FAST_BIT;
+
+	arm_smccc_1_1_hvc(HV_FUNC_ID, control, input1, input2, &res);
+	return res.a0;
+}
+EXPORT_SYMBOL_GPL(hv_do_fast_hypercall16);
+
 /*
  * Set a single VP register to a 64-bit value.
  */

arch/arm64/hyperv/mshyperv.c

@@ -26,6 +26,7 @@ int hv_get_hypervisor_version(union hv_hypervisor_version_info *info)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(hv_get_hypervisor_version);
 
 static int __init hyperv_init(void)
 {
@@ -61,6 +62,8 @@ static int __init hyperv_init(void)
 		ms_hyperv.features, ms_hyperv.priv_high, ms_hyperv.hints,
 		ms_hyperv.misc_features);
 
+	hv_identify_partition_type();
+
 	ret = hv_common_init();
 	if (ret)
 		return ret;
@@ -72,6 +75,9 @@ static int __init hyperv_init(void)
 		return ret;
 	}
 
+	if (ms_hyperv.priv_high & HV_ACCESS_PARTITION_ID)
+		hv_get_partition_id();
+
 	ms_hyperv_late_init();
 
 	hyperv_initialized = true;

arch/arm64/include/asm/mshyperv.h

@@ -40,6 +40,19 @@ static inline u64 hv_get_msr(unsigned int reg)
 	return hv_get_vpreg(reg);
 }
 
+/*
+ * Nested is not supported on arm64
+ */
+static inline void hv_set_non_nested_msr(unsigned int reg, u64 value)
+{
+	hv_set_msr(reg, value);
+}
+
+static inline u64 hv_get_non_nested_msr(unsigned int reg)
+{
+	return hv_get_msr(reg);
+}
+
 /* SMCCC hypercall parameters */
 #define HV_SMCCC_FUNC_NUMBER	1
 #define HV_FUNC_ID	ARM_SMCCC_CALL_VAL(			\

arch/x86/hyperv/Makefile

@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y			:= hv_init.o mmu.o nested.o irqdomain.o ivm.o
-obj-$(CONFIG_X86_64)	+= hv_apic.o hv_proc.o
+obj-$(CONFIG_X86_64)	+= hv_apic.o
 obj-$(CONFIG_HYPERV_VTL_MODE)	+= hv_vtl.o
 
 ifdef CONFIG_X86_64

arch/x86/hyperv/hv_apic.c

@@ -145,6 +145,11 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector,
 		ipi_arg->vp_set.format = HV_GENERIC_SET_ALL;
 	}
 
+	/*
+	 * For this hypercall, Hyper-V treats the valid_bank_mask field
+	 * of ipi_arg->vp_set as part of the fixed size input header.
+	 * So the variable input header size is equal to nr_bank.
+	 */
 	status = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank,
 				     ipi_arg, NULL);
 

arch/x86/hyperv/hv_init.c

@@ -34,9 +34,6 @@
 #include <clocksource/hyperv_timer.h>
 #include <linux/highmem.h>
 
-u64 hv_current_partition_id = ~0ull;
-EXPORT_SYMBOL_GPL(hv_current_partition_id);
-
 void *hv_hypercall_pg;
 EXPORT_SYMBOL_GPL(hv_hypercall_pg);
 
@@ -93,7 +90,7 @@ static int hv_cpu_init(unsigned int cpu)
 		return 0;
 
 	hvp = &hv_vp_assist_page[cpu];
-	if (hv_root_partition) {
+	if (hv_root_partition()) {
 		/*
 		 * For root partition we get the hypervisor provided VP assist
 		 * page, instead of allocating a new page.
@@ -245,7 +242,7 @@ static int hv_cpu_die(unsigned int cpu)
 
 	if (hv_vp_assist_page && hv_vp_assist_page[cpu]) {
 		union hv_vp_assist_msr_contents msr = { 0 };
-		if (hv_root_partition) {
+		if (hv_root_partition()) {
 			/*
 			 * For root partition the VP assist page is mapped to
 			 * hypervisor provided page, and thus we unmap the
@@ -320,7 +317,7 @@ static int hv_suspend(void)
 	union hv_x64_msr_hypercall_contents hypercall_msr;
 	int ret;
 
-	if (hv_root_partition)
+	if (hv_root_partition())
 		return -EPERM;
 
 	/*
@@ -393,24 +390,6 @@ static void __init hv_stimer_setup_percpu_clockev(void)
 		old_setup_percpu_clockev();
 }
 
-static void __init hv_get_partition_id(void)
-{
-	struct hv_get_partition_id *output_page;
-	u64 status;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	output_page = *this_cpu_ptr(hyperv_pcpu_output_arg);
-	status = hv_do_hypercall(HVCALL_GET_PARTITION_ID, NULL, output_page);
-	if (!hv_result_success(status)) {
-		/* No point in proceeding if this failed */
-		pr_err("Failed to get partition ID: %lld\n", status);
-		BUG();
-	}
-	hv_current_partition_id = output_page->partition_id;
-	local_irq_restore(flags);
-}
-
 #if IS_ENABLED(CONFIG_HYPERV_VTL_MODE)
 static u8 __init get_vtl(void)
 {
@@ -539,7 +518,7 @@ void __init hyperv_init(void)
 	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 	hypercall_msr.enable = 1;
 
-	if (hv_root_partition) {
+	if (hv_root_partition()) {
 		struct page *pg;
 		void *src;
 
@@ -605,17 +584,15 @@ void __init hyperv_init(void)
 
 	register_syscore_ops(&hv_syscore_ops);
 
-	if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_ACCESS_PARTITION_ID)
+	if (ms_hyperv.priv_high & HV_ACCESS_PARTITION_ID)
 		hv_get_partition_id();
 
-	BUG_ON(hv_root_partition && hv_current_partition_id == ~0ull);
-
 #ifdef CONFIG_PCI_MSI
 	/*
 	 * If we're running as root, we want to create our own PCI MSI domain.
 	 * We can't set this in hv_pci_init because that would be too late.
 	 */
-	if (hv_root_partition)
+	if (hv_root_partition())
 		x86_init.irqs.create_pci_msi_domain = hv_create_pci_msi_domain;
 #endif
 

arch/x86/hyperv/hv_vtl.c

@@ -12,6 +12,7 @@
 #include <asm/i8259.h>
 #include <asm/mshyperv.h>
 #include <asm/realmode.h>
+#include <asm/reboot.h>
 #include <../kernel/smpboot.h>
 
 extern struct boot_params boot_params;
@@ -22,6 +23,36 @@ static bool __init hv_vtl_msi_ext_dest_id(void)
 	return true;
 }
 
+/*
+ * The `native_machine_emergency_restart` function from `reboot.c` writes
+ * to the physical address 0x472 to indicate the type of reboot for the
+ * firmware. We cannot have that in VSM as the memory composition might
+ * be more generic, and such write effectively corrupts the memory thus
+ * making diagnostics harder at the very least.
+ */
+static void  __noreturn hv_vtl_emergency_restart(void)
+{
+	/*
+	 * Cause a triple fault and the immediate reset. Here the code does not run
+	 * on the top of any firmware, whereby cannot reach out to its services.
+	 * The inifinite loop is for the improbable case that the triple fault does
+	 * not work and have to preserve the state intact for debugging.
+	 */
+	for (;;) {
+		idt_invalidate();
+		__asm__ __volatile__("int3");
+	}
+}
+
+/*
+ * The only way to restart in the VTL mode is to triple fault as the kernel runs
+ * as firmware.
+ */
+static void  __noreturn hv_vtl_restart(char __maybe_unused *cmd)
+{
+	hv_vtl_emergency_restart();
+}
+
 void __init hv_vtl_init_platform(void)
 {
 	pr_info("Linux runs in Hyper-V Virtual Trust Level\n");
@@ -236,6 +267,9 @@ static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip)
 
 int __init hv_vtl_early_init(void)
 {
+	machine_ops.emergency_restart = hv_vtl_emergency_restart;
+	machine_ops.restart = hv_vtl_restart;
+
 	/*
 	 * `boot_cpu_has` returns the runtime feature support,
 	 * and here is the earliest it can be used.

arch/x86/hyperv/irqdomain.c

@@ -64,7 +64,7 @@ static int hv_map_interrupt(union hv_device_id device_id, bool level,
 	local_irq_restore(flags);
 
 	if (!hv_result_success(status))
-		pr_err("%s: hypercall failed, status %lld\n", __func__, status);
+		hv_status_err(status, "\n");
 
 	return hv_result(status);
 }
@@ -224,7 +224,7 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		kfree(stored_entry);
 
 		if (status != HV_STATUS_SUCCESS) {
-			pr_debug("%s: failed to unmap, status %lld", __func__, status);
+			hv_status_debug(status, "failed to unmap\n");
 			return;
 		}
 	}
@@ -273,7 +273,7 @@ static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd)
 	status = hv_unmap_msi_interrupt(dev, &old_entry);
 
 	if (status != HV_STATUS_SUCCESS)
-		pr_err("%s: hypercall failed, status %lld\n", __func__, status);
+		hv_status_err(status, "\n");
 }
 
 static void hv_msi_free_irq(struct irq_domain *domain,

arch/x86/hyperv/ivm.c

@@ -338,7 +338,7 @@ int hv_snp_boot_ap(u32 cpu, unsigned long start_ip)
 	vmsa->sev_features = sev_status >> 2;
 
 	ret = snp_set_vmsa(vmsa, true);
-	if (!ret) {
+	if (ret) {
 		pr_err("RMPADJUST(%llx) failed: %llx\n", (u64)vmsa, ret);
 		free_page((u64)vmsa);
 		return ret;