summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu/mshyperv.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/cpu/mshyperv.c')
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c263
1 files changed, 160 insertions, 103 deletions
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 01fa06dd06b6..c78f860419d6 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -16,11 +16,10 @@
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/kexec.h>
-#include <linux/i8253.h>
#include <linux/random.h>
#include <asm/processor.h>
#include <asm/hypervisor.h>
-#include <asm/hyperv-tlfs.h>
+#include <hyperv/hvhdk.h>
#include <asm/mshyperv.h>
#include <asm/desc.h>
#include <asm/idtentry.h>
@@ -31,11 +30,10 @@
#include <asm/reboot.h>
#include <asm/nmi.h>
#include <clocksource/hyperv_timer.h>
+#include <asm/msr.h>
#include <asm/numa.h>
#include <asm/svm.h>
-/* Is Linux running as the root partition? */
-bool hv_root_partition;
/* Is Linux running on nested Microsoft Hypervisor */
bool hv_nested;
struct ms_hyperv_info ms_hyperv;
@@ -45,71 +43,72 @@ bool hyperv_paravisor_present __ro_after_init;
EXPORT_SYMBOL_GPL(hyperv_paravisor_present);
#if IS_ENABLED(CONFIG_HYPERV)
-static inline unsigned int hv_get_nested_reg(unsigned int reg)
+static inline unsigned int hv_get_nested_msr(unsigned int reg)
{
- if (hv_is_sint_reg(reg))
- return reg - HV_REGISTER_SINT0 + HV_REGISTER_NESTED_SINT0;
+ if (hv_is_sint_msr(reg))
+ return reg - HV_X64_MSR_SINT0 + HV_X64_MSR_NESTED_SINT0;
switch (reg) {
- case HV_REGISTER_SIMP:
- return HV_REGISTER_NESTED_SIMP;
- case HV_REGISTER_SIEFP:
- return HV_REGISTER_NESTED_SIEFP;
- case HV_REGISTER_SVERSION:
- return HV_REGISTER_NESTED_SVERSION;
- case HV_REGISTER_SCONTROL:
- return HV_REGISTER_NESTED_SCONTROL;
- case HV_REGISTER_EOM:
- return HV_REGISTER_NESTED_EOM;
+ case HV_X64_MSR_SIMP:
+ return HV_X64_MSR_NESTED_SIMP;
+ case HV_X64_MSR_SIEFP:
+ return HV_X64_MSR_NESTED_SIEFP;
+ case HV_X64_MSR_SVERSION:
+ return HV_X64_MSR_NESTED_SVERSION;
+ case HV_X64_MSR_SCONTROL:
+ return HV_X64_MSR_NESTED_SCONTROL;
+ case HV_X64_MSR_EOM:
+ return HV_X64_MSR_NESTED_EOM;
default:
return reg;
}
}
-u64 hv_get_non_nested_register(unsigned int reg)
+u64 hv_get_non_nested_msr(unsigned int reg)
{
u64 value;
- if (hv_is_synic_reg(reg) && ms_hyperv.paravisor_present)
+ if (hv_is_synic_msr(reg) && ms_hyperv.paravisor_present)
hv_ivm_msr_read(reg, &value);
else
- rdmsrl(reg, value);
+ rdmsrq(reg, value);
return value;
}
-EXPORT_SYMBOL_GPL(hv_get_non_nested_register);
+EXPORT_SYMBOL_GPL(hv_get_non_nested_msr);
-void hv_set_non_nested_register(unsigned int reg, u64 value)
+void hv_set_non_nested_msr(unsigned int reg, u64 value)
{
- if (hv_is_synic_reg(reg) && ms_hyperv.paravisor_present) {
+ if (hv_is_synic_msr(reg) && ms_hyperv.paravisor_present) {
hv_ivm_msr_write(reg, value);
/* Write proxy bit via wrmsl instruction */
- if (hv_is_sint_reg(reg))
- wrmsrl(reg, value | 1 << 20);
+ if (hv_is_sint_msr(reg))
+ wrmsrq(reg, value | 1 << 20);
} else {
- wrmsrl(reg, value);
+ wrmsrq(reg, value);
}
}
-EXPORT_SYMBOL_GPL(hv_set_non_nested_register);
+EXPORT_SYMBOL_GPL(hv_set_non_nested_msr);
-u64 hv_get_register(unsigned int reg)
+u64 hv_get_msr(unsigned int reg)
{
if (hv_nested)
- reg = hv_get_nested_reg(reg);
+ reg = hv_get_nested_msr(reg);
- return hv_get_non_nested_register(reg);
+ return hv_get_non_nested_msr(reg);
}
-EXPORT_SYMBOL_GPL(hv_get_register);
+EXPORT_SYMBOL_GPL(hv_get_msr);
-void hv_set_register(unsigned int reg, u64 value)
+void hv_set_msr(unsigned int reg, u64 value)
{
if (hv_nested)
- reg = hv_get_nested_reg(reg);
+ reg = hv_get_nested_msr(reg);
- hv_set_non_nested_register(reg, value);
+ hv_set_non_nested_msr(reg, value);
}
-EXPORT_SYMBOL_GPL(hv_set_register);
+EXPORT_SYMBOL_GPL(hv_set_msr);
+static void (*mshv_handler)(void);
static void (*vmbus_handler)(void);
static void (*hv_stimer0_handler)(void);
static void (*hv_kexec_handler)(void);
@@ -120,6 +119,9 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback)
struct pt_regs *old_regs = set_irq_regs(regs);
inc_irq_stat(irq_hv_callback_count);
+ if (mshv_handler)
+ mshv_handler();
+
if (vmbus_handler)
vmbus_handler();
@@ -129,6 +131,11 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback)
set_irq_regs(old_regs);
}
+void hv_setup_mshv_handler(void (*handler)(void))
+{
+ mshv_handler = handler;
+}
+
void hv_setup_vmbus_handler(void (*handler)(void))
{
vmbus_handler = handler;
@@ -199,8 +206,8 @@ static void hv_machine_shutdown(void)
* 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);
+ if (kexec_in_progress)
+ cpuhp_remove_state(CPUHP_AP_HYPERV_ONLINE);
/* The function calls stop_other_cpus(). */
native_machine_shutdown();
@@ -209,7 +216,9 @@ static void hv_machine_shutdown(void)
if (kexec_in_progress)
hyperv_cleanup();
}
+#endif /* CONFIG_KEXEC_CORE */
+#ifdef CONFIG_CRASH_DUMP
static void hv_machine_crash_shutdown(struct pt_regs *regs)
{
if (hv_crash_handler)
@@ -221,7 +230,64 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs)
/* Disable the hypercall page when there is only 1 active CPU. */
hyperv_cleanup();
}
-#endif /* CONFIG_KEXEC_CORE */
+#endif /* CONFIG_CRASH_DUMP */
+
+static u64 hv_ref_counter_at_suspend;
+static void (*old_save_sched_clock_state)(void);
+static void (*old_restore_sched_clock_state)(void);
+
+/*
+ * Hyper-V clock counter resets during hibernation. Save and restore clock
+ * offset during suspend/resume, while also considering the time passed
+ * before suspend. This is to make sure that sched_clock using hv tsc page
+ * based clocksource, proceeds from where it left off during suspend and
+ * it shows correct time for the timestamps of kernel messages after resume.
+ */
+static void save_hv_clock_tsc_state(void)
+{
+ hv_ref_counter_at_suspend = hv_read_reference_counter();
+}
+
+static void restore_hv_clock_tsc_state(void)
+{
+ /*
+ * Adjust the offsets used by hv tsc clocksource to
+ * account for the time spent before hibernation.
+ * adjusted value = reference counter (time) at suspend
+ * - reference counter (time) now.
+ */
+ hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter());
+}
+
+/*
+ * Functions to override save_sched_clock_state and restore_sched_clock_state
+ * functions of x86_platform. The Hyper-V clock counter is reset during
+ * suspend-resume and the offset used to measure time needs to be
+ * corrected, post resume.
+ */
+static void hv_save_sched_clock_state(void)
+{
+ old_save_sched_clock_state();
+ save_hv_clock_tsc_state();
+}
+
+static void hv_restore_sched_clock_state(void)
+{
+ restore_hv_clock_tsc_state();
+ old_restore_sched_clock_state();
+}
+
+static void __init x86_setup_ops_for_tsc_pg_clock(void)
+{
+ if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
+ return;
+
+ old_save_sched_clock_state = x86_platform.save_sched_clock_state;
+ x86_platform.save_sched_clock_state = hv_save_sched_clock_state;
+
+ old_restore_sched_clock_state = x86_platform.restore_sched_clock_state;
+ x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state;
+}
#endif /* CONFIG_HYPERV */
static uint32_t __init ms_hyperv_platform(void)
@@ -280,7 +346,7 @@ static unsigned long hv_get_tsc_khz(void)
{
unsigned long freq;
- rdmsrl(HV_X64_MSR_TSC_FREQUENCY, freq);
+ rdmsrq(HV_X64_MSR_TSC_FREQUENCY, freq);
return freq / 1000;
}
@@ -350,13 +416,25 @@ static void __init reduced_hw_init(void)
x86_init.irqs.pre_vector_init = x86_init_noop;
}
+int hv_get_hypervisor_version(union hv_hypervisor_version_info *info)
+{
+ unsigned int hv_max_functions;
+
+ hv_max_functions = cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS);
+ if (hv_max_functions < HYPERV_CPUID_VERSION) {
+ pr_err("%s: Could not detect Hyper-V version\n", __func__);
+ return -ENODEV;
+ }
+
+ cpuid(HYPERV_CPUID_VERSION, &info->eax, &info->ebx, &info->ecx, &info->edx);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(hv_get_hypervisor_version);
+
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;
- int hv_host_info_edx;
#ifdef CONFIG_PARAVIRT
pv_info.name = "Hyper-V";
@@ -367,13 +445,15 @@ static void __init ms_hyperv_init_platform(void)
*/
ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES);
ms_hyperv.priv_high = cpuid_ebx(HYPERV_CPUID_FEATURES);
+ ms_hyperv.ext_features = cpuid_ecx(HYPERV_CPUID_FEATURES);
ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
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,
+ pr_info("Hyper-V: privilege flags low %#x, high %#x, ext %#x, hints %#x, misc %#x\n",
+ ms_hyperv.features, ms_hyperv.priv_high,
+ ms_hyperv.ext_features, ms_hyperv.hints,
ms_hyperv.misc_features);
ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS);
@@ -382,50 +462,18 @@ static void __init ms_hyperv_init_platform(void)
pr_debug("Hyper-V: max %u virtual processors, %u logical processors\n",
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.
- *
- * Hyper-V should never specify running as root and as a Confidential
- * VM. But to protect against a compromised/malicious Hyper-V trying
- * to exploit root behavior to expose Confidential VM memory, ignore
- * the root partition setting if also a Confidential VM.
- */
- if ((ms_hyperv.priv_high & HV_CPU_MANAGEMENT) &&
- !(ms_hyperv.priv_high & HV_ISOLATION)) {
- hv_root_partition = true;
- pr_info("Hyper-V: running as root partition\n");
- }
+ hv_identify_partition_type();
if (ms_hyperv.hints & HV_X64_HYPERV_NESTED) {
hv_nested = true;
pr_info("Hyper-V: running on a nested hypervisor\n");
}
- /*
- * Extract host information.
- */
- 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_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_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;
+ setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
}
if (ms_hyperv.priv_high & HV_ISOLATION) {
@@ -451,10 +499,24 @@ static void __init ms_hyperv_init_platform(void)
ms_hyperv.hints &= ~HV_X64_APIC_ACCESS_RECOMMENDED;
if (!ms_hyperv.paravisor_present) {
- /* To be supported: more work is required. */
+ /*
+ * Mark the Hyper-V TSC page feature as disabled
+ * in a TDX VM without paravisor so that the
+ * Invariant TSC, which is a better clocksource
+ * anyway, is used instead.
+ */
ms_hyperv.features &= ~HV_MSR_REFERENCE_TSC_AVAILABLE;
- /* HV_REGISTER_CRASH_CTL is unsupported. */
+ /*
+ * The Invariant TSC is expected to be available
+ * in a TDX VM without paravisor, but if not,
+ * print a warning message. The slower Hyper-V MSR-based
+ * Ref Counter should end up being the clocksource.
+ */
+ if (!(ms_hyperv.features & HV_ACCESS_TSC_INVARIANT))
+ pr_warn("Hyper-V: Invariant TSC is unavailable\n");
+
+ /* HV_MSR_CRASH_CTL is unsupported. */
ms_hyperv.misc_features &= ~HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE;
/* Don't trust Hyper-V's TLB-flushing hypercalls. */
@@ -480,7 +542,7 @@ static void __init ms_hyperv_init_platform(void)
*/
u64 hv_lapic_frequency;
- rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency);
+ rdmsrq(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency);
hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ);
lapic_timer_period = hv_lapic_frequency;
pr_info("Hyper-V: LAPIC Timer Frequency: %#x\n",
@@ -495,10 +557,14 @@ static void __init ms_hyperv_init_platform(void)
no_timer_check = 1;
#endif
-#if IS_ENABLED(CONFIG_HYPERV) && defined(CONFIG_KEXEC_CORE)
+#if IS_ENABLED(CONFIG_HYPERV)
+#if defined(CONFIG_KEXEC_CORE)
machine_ops.shutdown = hv_machine_shutdown;
+#endif
+#if defined(CONFIG_CRASH_DUMP)
machine_ops.crash_shutdown = hv_machine_crash_shutdown;
#endif
+#endif
if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) {
/*
* Writing to synthetic MSR 0x40000118 updates/changes the
@@ -509,7 +575,7 @@ static void __init ms_hyperv_init_platform(void)
* setting of this MSR bit should happen before init_intel()
* is called.
*/
- wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, HV_EXPOSE_INVARIANT_TSC);
+ wrmsrq(HV_X64_MSR_TSC_INVARIANT_CONTROL, HV_EXPOSE_INVARIANT_TSC);
setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
}
@@ -520,16 +586,6 @@ static void __init ms_hyperv_init_platform(void)
if (efi_enabled(EFI_BOOT))
x86_platform.get_nmi_reason = hv_get_nmi_reason;
- /*
- * Hyper-V VMs have a PIT emulation quirk such that zeroing the
- * counter register during PIT shutdown restarts the PIT. So it
- * continues to interrupt @18.2 HZ. Setting i8253_clear_counter
- * to false tells pit_shutdown() not to zero the counter so that
- * the PIT really is shutdown. Generation 2 VMs don't have a PIT,
- * and setting this value has no effect.
- */
- i8253_clear_counter_on_shutdown = false;
-
#if IS_ENABLED(CONFIG_HYPERV)
if ((hv_get_isolation_type() == HV_ISOLATION_TYPE_VBS) ||
ms_hyperv.paravisor_present)
@@ -539,24 +595,23 @@ 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, asm_sysvec_hyperv_callback);
- /* Setup the IDT for reenlightenment notifications */
+ /* Install system interrupt handler for hypervisor callback */
+ sysvec_install(HYPERVISOR_CALLBACK_VECTOR, sysvec_hyperv_callback);
+
+ /* Install system interrupt handler for reenlightenment notifications */
if (ms_hyperv.features & HV_ACCESS_REENLIGHTENMENT) {
- alloc_intr_gate(HYPERV_REENLIGHTENMENT_VECTOR,
- asm_sysvec_hyperv_reenlightenment);
+ sysvec_install(HYPERV_REENLIGHTENMENT_VECTOR, sysvec_hyperv_reenlightenment);
}
- /* Setup the IDT for stimer0 */
+ /* Install system interrupt handler for stimer0 */
if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE) {
- alloc_intr_gate(HYPERV_STIMER0_VECTOR,
- asm_sysvec_hyperv_stimer0);
+ sysvec_install(HYPERV_STIMER0_VECTOR, sysvec_hyperv_stimer0);
}
# ifdef CONFIG_SMP
smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu;
- if (hv_root_partition ||
+ if (hv_root_partition() ||
(!ms_hyperv.paravisor_present && hv_isolation_type_snp()))
smp_ops.smp_prepare_cpus = hv_smp_prepare_cpus;
# endif
@@ -574,6 +629,7 @@ static void __init ms_hyperv_init_platform(void)
/* Register Hyper-V specific clocksource */
hv_init_clocksource();
+ x86_setup_ops_for_tsc_pg_clock();
hv_vtl_init_platform();
#endif
/*
@@ -643,6 +699,7 @@ const __initconst struct hypervisor_x86 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,
+ .init.guest_late_init = ms_hyperv_late_init,
#ifdef CONFIG_AMD_MEM_ENCRYPT
.runtime.sev_es_hcall_prepare = hv_sev_es_hcall_prepare,
.runtime.sev_es_hcall_finish = hv_sev_es_hcall_finish,
generated by cgit (git 2.34.1) at 2025-08-01 06:09:54 +0000