1 files changed, 184 insertions, 54 deletions

diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index caa032ce3fe3..831613959a92 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -18,11 +18,13 @@
 #include <linux/kexec.h>
 #include <linux/i8253.h>
 #include <linux/random.h>
+#include <linux/swiotlb.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
 #include <asm/desc.h>
+#include <asm/idtentry.h>
 #include <asm/irq_regs.h>
 #include <asm/i8259.h>
 #include <asm/apic.h>
@@ -30,9 +32,12 @@
 #include <asm/reboot.h>
 #include <asm/nmi.h>
 #include <clocksource/hyperv_timer.h>
+#include <asm/numa.h>
+#include <asm/coco.h>
 
+/* Is Linux running as the root partition? */
+bool hv_root_partition;
 struct ms_hyperv_info ms_hyperv;
-EXPORT_SYMBOL_GPL(ms_hyperv);
 
 #if IS_ENABLED(CONFIG_HYPERV)
 static void (*vmbus_handler)(void);
@@ -40,11 +45,10 @@ static void (*hv_stimer0_handler)(void);
 static void (*hv_kexec_handler)(void);
 static void (*hv_crash_handler)(struct pt_regs *regs);
 
-__visible void __irq_entry hyperv_vector_handler(struct pt_regs *regs)
+DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	entering_irq();
 	inc_irq_stat(irq_hv_callback_count);
 	if (vmbus_handler)
 		vmbus_handler();
@@ -52,96 +56,100 @@ __visible void __irq_entry hyperv_vector_handler(struct pt_regs *regs)
 	if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED)
 		ack_APIC_irq();
 
-	exiting_irq();
 	set_irq_regs(old_regs);
 }
 
-void hv_setup_vmbus_irq(void (*handler)(void))
+void hv_setup_vmbus_handler(void (*handler)(void))
 {
 	vmbus_handler = handler;
 }
 
-void hv_remove_vmbus_irq(void)
+void hv_remove_vmbus_handler(void)
 {
 	/* We have no way to deallocate the interrupt gate */
 	vmbus_handler = NULL;
 }
-EXPORT_SYMBOL_GPL(hv_setup_vmbus_irq);
-EXPORT_SYMBOL_GPL(hv_remove_vmbus_irq);
 
 /*
  * Routines to do per-architecture handling of stimer0
  * interrupts when in Direct Mode
  */
-
-__visible void __irq_entry hv_stimer0_vector_handler(struct pt_regs *regs)
+DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_stimer0)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	entering_irq();
 	inc_irq_stat(hyperv_stimer0_count);
 	if (hv_stimer0_handler)
 		hv_stimer0_handler();
-	add_interrupt_randomness(HYPERV_STIMER0_VECTOR, 0);
+	add_interrupt_randomness(HYPERV_STIMER0_VECTOR);
 	ack_APIC_irq();
 
-	exiting_irq();
 	set_irq_regs(old_regs);
 }
 
-int hv_setup_stimer0_irq(int *irq, int *vector, void (*handler)(void))
+/* For x86/x64, override weak placeholders in hyperv_timer.c */
+void hv_setup_stimer0_handler(void (*handler)(void))
 {
-	*vector = HYPERV_STIMER0_VECTOR;
-	*irq = -1;   /* Unused on x86/x64 */
 	hv_stimer0_handler = handler;
-	return 0;
 }
-EXPORT_SYMBOL_GPL(hv_setup_stimer0_irq);
 
-void hv_remove_stimer0_irq(int irq)
+void hv_remove_stimer0_handler(void)
 {
 	/* We have no way to deallocate the interrupt gate */
 	hv_stimer0_handler = NULL;
 }
-EXPORT_SYMBOL_GPL(hv_remove_stimer0_irq);
 
 void hv_setup_kexec_handler(void (*handler)(void))
 {
 	hv_kexec_handler = handler;
 }
-EXPORT_SYMBOL_GPL(hv_setup_kexec_handler);
 
 void hv_remove_kexec_handler(void)
 {
 	hv_kexec_handler = NULL;
 }
-EXPORT_SYMBOL_GPL(hv_remove_kexec_handler);
 
 void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs))
 {
 	hv_crash_handler = handler;
 }
-EXPORT_SYMBOL_GPL(hv_setup_crash_handler);
 
 void hv_remove_crash_handler(void)
 {
 	hv_crash_handler = NULL;
 }
-EXPORT_SYMBOL_GPL(hv_remove_crash_handler);
 
 #ifdef CONFIG_KEXEC_CORE
 static void hv_machine_shutdown(void)
 {
 	if (kexec_in_progress && hv_kexec_handler)
 		hv_kexec_handler();
+
+	/*
+	 * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor
+	 * corrupts the old VP Assist Pages and can crash the kexec kernel.
+	 */
+	if (kexec_in_progress && hyperv_init_cpuhp > 0)
+		cpuhp_remove_state(hyperv_init_cpuhp);
+
+	/* The function calls stop_other_cpus(). */
 	native_machine_shutdown();
+
+	/* Disable the hypercall page when there is only 1 active CPU. */
+	if (kexec_in_progress)
+		hyperv_cleanup();
 }
 
 static void hv_machine_crash_shutdown(struct pt_regs *regs)
 {
 	if (hv_crash_handler)
 		hv_crash_handler(regs);
+
+	/* The function calls crash_smp_send_stop(). */
 	native_machine_crash_shutdown(regs);
+
+	/* Disable the hypercall page when there is only 1 active CPU. */
+	hyperv_cleanup();
 }
 #endif /* CONFIG_KEXEC_CORE */
 #endif /* CONFIG_HYPERV */
@@ -157,12 +165,22 @@ static uint32_t  __init ms_hyperv_platform(void)
 	cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS,
 	      &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]);
 
-	if (eax >= HYPERV_CPUID_MIN &&
-	    eax <= HYPERV_CPUID_MAX &&
-	    !memcmp("Microsoft Hv", hyp_signature, 12))
-		return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS;
+	if (eax < HYPERV_CPUID_MIN || eax > HYPERV_CPUID_MAX ||
+	    memcmp("Microsoft Hv", hyp_signature, 12))
+		return 0;
 
-	return 0;
+	/* HYPERCALL and VP_INDEX MSRs are mandatory for all features. */
+	eax = cpuid_eax(HYPERV_CPUID_FEATURES);
+	if (!(eax & HV_MSR_HYPERCALL_AVAILABLE)) {
+		pr_warn("x86/hyperv: HYPERCALL MSR not available.\n");
+		return 0;
+	}
+	if (!(eax & HV_MSR_VP_INDEX_AVAILABLE)) {
+		pr_warn("x86/hyperv: VP_INDEX MSR not available.\n");
+		return 0;
+	}
+
+	return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS;
 }
 
 static unsigned char hv_get_nmi_reason(void)
@@ -173,7 +191,7 @@ static unsigned char hv_get_nmi_reason(void)
 #ifdef CONFIG_X86_LOCAL_APIC
 /*
  * Prior to WS2016 Debug-VM sends NMIs to all CPUs which makes
- * it dificult to process CHANNELMSG_UNLOAD in case of crash. Handle
+ * it difficult to process CHANNELMSG_UNLOAD in case of crash. Handle
  * unknown NMI on the first CPU which gets it.
  */
 static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs)
@@ -207,10 +225,37 @@ static void __init hv_smp_prepare_boot_cpu(void)
 	hv_init_spinlocks();
 #endif
 }
+
+static void __init hv_smp_prepare_cpus(unsigned int max_cpus)
+{
+#ifdef CONFIG_X86_64
+	int i;
+	int ret;
+#endif
+
+	native_smp_prepare_cpus(max_cpus);
+
+#ifdef CONFIG_X86_64
+	for_each_present_cpu(i) {
+		if (i == 0)
+			continue;
+		ret = hv_call_add_logical_proc(numa_cpu_node(i), i, cpu_physical_id(i));
+		BUG_ON(ret);
+	}
+
+	for_each_present_cpu(i) {
+		if (i == 0)
+			continue;
+		ret = hv_call_create_vp(numa_cpu_node(i), hv_current_partition_id, i, i);
+		BUG_ON(ret);
+	}
+#endif
+}
 #endif
 
 static void __init ms_hyperv_init_platform(void)
 {
+	int hv_max_functions_eax;
 	int hv_host_info_eax;
 	int hv_host_info_ebx;
 	int hv_host_info_ecx;
@@ -224,11 +269,15 @@ static void __init ms_hyperv_init_platform(void)
 	 * Extract the features and hints
 	 */
 	ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES);
+	ms_hyperv.priv_high = cpuid_ebx(HYPERV_CPUID_FEATURES);
 	ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
 	ms_hyperv.hints    = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
 
-	pr_info("Hyper-V: features 0x%x, hints 0x%x\n",
-		ms_hyperv.features, ms_hyperv.hints);
+	hv_max_functions_eax = cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS);
+
+	pr_info("Hyper-V: privilege flags low 0x%x, high 0x%x, hints 0x%x, misc 0x%x\n",
+		ms_hyperv.features, ms_hyperv.priv_high, ms_hyperv.hints,
+		ms_hyperv.misc_features);
 
 	ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS);
 	ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS);
@@ -237,34 +286,73 @@ static void __init ms_hyperv_init_platform(void)
 		 ms_hyperv.max_vp_index, ms_hyperv.max_lp_index);
 
 	/*
+	 * Check CPU management privilege.
+	 *
+	 * To mirror what Windows does we should extract CPU management
+	 * features and use the ReservedIdentityBit to detect if Linux is the
+	 * root partition. But that requires negotiating CPU management
+	 * interface (a process to be finalized).
+	 *
+	 * For now, use the privilege flag as the indicator for running as
+	 * root.
+	 */
+	if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_CPU_MANAGEMENT) {
+		hv_root_partition = true;
+		pr_info("Hyper-V: running as root partition\n");
+	}
+
+	/*
 	 * Extract host information.
 	 */
-	if (cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS) >=
-	    HYPERV_CPUID_VERSION) {
+	if (hv_max_functions_eax >= HYPERV_CPUID_VERSION) {
 		hv_host_info_eax = cpuid_eax(HYPERV_CPUID_VERSION);
 		hv_host_info_ebx = cpuid_ebx(HYPERV_CPUID_VERSION);
 		hv_host_info_ecx = cpuid_ecx(HYPERV_CPUID_VERSION);
 		hv_host_info_edx = cpuid_edx(HYPERV_CPUID_VERSION);
 
-		pr_info("Hyper-V Host Build:%d-%d.%d-%d-%d.%d\n",
-			hv_host_info_eax, hv_host_info_ebx >> 16,
-			hv_host_info_ebx & 0xFFFF, hv_host_info_ecx,
-			hv_host_info_edx >> 24, hv_host_info_edx & 0xFFFFFF);
+		pr_info("Hyper-V: Host Build %d.%d.%d.%d-%d-%d\n",
+			hv_host_info_ebx >> 16, hv_host_info_ebx & 0xFFFF,
+			hv_host_info_eax, hv_host_info_edx & 0xFFFFFF,
+			hv_host_info_ecx, hv_host_info_edx >> 24);
 	}
 
-	if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS &&
+	if (ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS &&
 	    ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
 		x86_platform.calibrate_tsc = hv_get_tsc_khz;
 		x86_platform.calibrate_cpu = hv_get_tsc_khz;
 	}
 
-	if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED) {
+	if (ms_hyperv.priv_high & HV_ISOLATION) {
+		ms_hyperv.isolation_config_a = cpuid_eax(HYPERV_CPUID_ISOLATION_CONFIG);
+		ms_hyperv.isolation_config_b = cpuid_ebx(HYPERV_CPUID_ISOLATION_CONFIG);
+		ms_hyperv.shared_gpa_boundary =
+			BIT_ULL(ms_hyperv.shared_gpa_boundary_bits);
+
+		pr_info("Hyper-V: Isolation Config: Group A 0x%x, Group B 0x%x\n",
+			ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b);
+
+		if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP) {
+			static_branch_enable(&isolation_type_snp);
+#ifdef CONFIG_SWIOTLB
+			swiotlb_unencrypted_base = ms_hyperv.shared_gpa_boundary;
+#endif
+		}
+		/* Isolation VMs are unenlightened SEV-based VMs, thus this check: */
+		if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
+			if (hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE)
+				cc_set_vendor(CC_VENDOR_HYPERV);
+		}
+	}
+
+	if (hv_max_functions_eax >= HYPERV_CPUID_NESTED_FEATURES) {
 		ms_hyperv.nested_features =
 			cpuid_eax(HYPERV_CPUID_NESTED_FEATURES);
+		pr_info("Hyper-V: Nested features: 0x%x\n",
+			ms_hyperv.nested_features);
 	}
 
 #ifdef CONFIG_X86_LOCAL_APIC
-	if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS &&
+	if (ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS &&
 	    ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
 		/*
 		 * Get the APIC frequency.
@@ -290,11 +378,18 @@ static void __init ms_hyperv_init_platform(void)
 	machine_ops.shutdown = hv_machine_shutdown;
 	machine_ops.crash_shutdown = hv_machine_crash_shutdown;
 #endif
-	if (ms_hyperv.features & HV_X64_ACCESS_TSC_INVARIANT) {
+	if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) {
+		/*
+		 * Writing to synthetic MSR 0x40000118 updates/changes the
+		 * guest visible CPUIDs. Setting bit 0 of this MSR  enables
+		 * guests to report invariant TSC feature through CPUID
+		 * instruction, CPUID 0x800000007/EDX, bit 8. See code in
+		 * early_init_intel() where this bit is examined. The
+		 * setting of this MSR bit should happen before init_intel()
+		 * is called.
+		 */
 		wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, 0x1);
 		setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
-	} else {
-		mark_tsc_unstable("running on Hyper-V");
 	}
 
 	/*
@@ -321,25 +416,29 @@ static void __init ms_hyperv_init_platform(void)
 	x86_platform.apic_post_init = hyperv_init;
 	hyperv_setup_mmu_ops();
 	/* Setup the IDT for hypervisor callback */
-	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
+	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_hyperv_callback);
 
 	/* Setup the IDT for reenlightenment notifications */
-	if (ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT)
+	if (ms_hyperv.features & HV_ACCESS_REENLIGHTENMENT) {
 		alloc_intr_gate(HYPERV_REENLIGHTENMENT_VECTOR,
-				hyperv_reenlightenment_vector);
+				asm_sysvec_hyperv_reenlightenment);
+	}
 
 	/* Setup the IDT for stimer0 */
-	if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE)
+	if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE) {
 		alloc_intr_gate(HYPERV_STIMER0_VECTOR,
-				hv_stimer0_callback_vector);
+				asm_sysvec_hyperv_stimer0);
+	}
 
 # ifdef CONFIG_SMP
 	smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu;
+	if (hv_root_partition)
+		smp_ops.smp_prepare_cpus = hv_smp_prepare_cpus;
 # endif
 
 	/*
 	 * Hyper-V doesn't provide irq remapping for IO-APIC. To enable x2apic,
-	 * set x2apic destination mode to physcial mode when x2apic is available
+	 * set x2apic destination mode to physical mode when x2apic is available
 	 * and Hyper-V IOMMU driver makes sure cpus assigned with IO-APIC irqs
 	 * have 8-bit APIC id.
 	 */
@@ -351,18 +450,49 @@ static void __init ms_hyperv_init_platform(void)
 	/* Register Hyper-V specific clocksource */
 	hv_init_clocksource();
 #endif
+	/*
+	 * TSC should be marked as unstable only after Hyper-V
+	 * clocksource has been initialized. This ensures that the
+	 * stability of the sched_clock is not altered.
+	 */
+	if (!(ms_hyperv.features & HV_ACCESS_TSC_INVARIANT))
+		mark_tsc_unstable("running on Hyper-V");
+
+	hardlockup_detector_disable();
 }
 
-void hv_setup_sched_clock(void *sched_clock)
+static bool __init ms_hyperv_x2apic_available(void)
 {
-#ifdef CONFIG_PARAVIRT
-	pv_ops.time.sched_clock = sched_clock;
-#endif
+	return x2apic_supported();
+}
+
+/*
+ * If ms_hyperv_msi_ext_dest_id() returns true, hyperv_prepare_irq_remapping()
+ * returns -ENODEV and the Hyper-V IOMMU driver is not used; instead, the
+ * generic support of the 15-bit APIC ID is used: see __irq_msi_compose_msg().
+ *
+ * Note: for a VM on Hyper-V, the I/O-APIC is the only device which
+ * (logically) generates MSIs directly to the system APIC irq domain.
+ * There is no HPET, and PCI MSI/MSI-X interrupts are remapped by the
+ * pci-hyperv host bridge.
+ */
+static bool __init ms_hyperv_msi_ext_dest_id(void)
+{
+	u32 eax;
+
+	eax = cpuid_eax(HYPERV_CPUID_VIRT_STACK_INTERFACE);
+	if (eax != HYPERV_VS_INTERFACE_EAX_SIGNATURE)
+		return false;
+
+	eax = cpuid_eax(HYPERV_CPUID_VIRT_STACK_PROPERTIES);
+	return eax & HYPERV_VS_PROPERTIES_EAX_EXTENDED_IOAPIC_RTE;
 }
 
 const __initconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
 	.name			= "Microsoft Hyper-V",
 	.detect			= ms_hyperv_platform,
 	.type			= X86_HYPER_MS_HYPERV,
+	.init.x2apic_available	= ms_hyperv_x2apic_available,
+	.init.msi_ext_dest_id	= ms_hyperv_msi_ext_dest_id,
 	.init.init_platform	= ms_hyperv_init_platform,
 };