if (!ms_hyperv.paravisor_present || !hv_isolation_type_snp()) return 0;
if (!hv_ghcb_pg) return -EINVAL;
/* * GHCB page is allocated by paravisor. The address * returned by MSR_AMD64_SEV_ES_GHCB is above shared * memory boundary and map it here.
*/
rdmsrq(MSR_AMD64_SEV_ES_GHCB, ghcb_gpa);
staticint hv_cpu_init(unsignedint cpu)
{ union hv_vp_assist_msr_contents msr = { 0 }; struct hv_vp_assist_page **hvp; int ret;
ret = hv_common_cpu_init(cpu); if (ret) return ret;
if (!hv_vp_assist_page) return 0;
hvp = &hv_vp_assist_page[cpu]; if (hv_root_partition()) { /* * For root partition we get the hypervisor provided VP assist * page, instead of allocating a new page.
*/
rdmsrq(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
*hvp = memremap(msr.pfn << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT,
PAGE_SIZE, MEMREMAP_WB);
} else { /* * The VP assist page is an "overlay" page (see Hyper-V TLFS's * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed * out to make sure we always write the EOI MSR in * hv_apic_eoi_write() *after* the EOI optimization is disabled * in hv_cpu_die(), otherwise a CPU may not be stopped in the * case of CPU offlining and the VM will hang.
*/ if (!*hvp) {
*hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO);
/* * Hyper-V should never specify a VM that is a Confidential * VM and also running in the root partition. Root partition * is blocked to run in Confidential VM. So only decrypt assist * page in non-root partition here.
*/ if (*hvp && !ms_hyperv.paravisor_present && hv_isolation_type_snp()) {
WARN_ON_ONCE(set_memory_decrypted((unsignedlong)(*hvp), 1));
memset(*hvp, 0, PAGE_SIZE);
}
}
if (*hvp)
msr.pfn = vmalloc_to_pfn(*hvp);
} if (!WARN_ON(!(*hvp))) {
msr.enable = 1;
wrmsrq(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
}
/* Don't issue the callback if TSC accesses are not emulated */ if (hv_reenlightenment_cb && emu_status.inprogress)
hv_reenlightenment_cb();
} static DECLARE_DELAYED_WORK(hv_reenlightenment_work, hv_reenlightenment_notify);
if (hv_ghcb_pg) {
ghcb_va = (void **)this_cpu_ptr(hv_ghcb_pg); if (*ghcb_va)
iounmap(*ghcb_va);
*ghcb_va = NULL;
}
hv_common_cpu_die(cpu);
if (hv_vp_assist_page && hv_vp_assist_page[cpu]) { union hv_vp_assist_msr_contents msr = { 0 }; if (hv_root_partition()) { /* * For root partition the VP assist page is mapped to * hypervisor provided page, and thus we unmap the * page here and nullify it, so that in future we have * correct page address mapped in hv_cpu_init.
*/
memunmap(hv_vp_assist_page[cpu]);
hv_vp_assist_page[cpu] = NULL;
rdmsrq(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
msr.enable = 0;
}
wrmsrq(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
}
if (hv_reenlightenment_cb == NULL) return 0;
rdmsrq(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl)); if (re_ctrl.target_vp == hv_vp_index[cpu]) { /* * Reassign reenlightenment notifications to some other online * CPU or just disable the feature if there are no online CPUs * left (happens on hibernation).
*/
new_cpu = cpumask_any_but(cpu_online_mask, cpu);
/* * A Generation-2 VM doesn't support legacy PCI/PCIe, so both * raw_pci_ops and raw_pci_ext_ops are NULL, and pci_subsys_init() -> * pcibios_init() doesn't call pcibios_resource_survey() -> * e820__reserve_resources_late(); as a result, any emulated persistent * memory of E820_TYPE_PRAM (12) via the kernel parameter * memmap=nn[KMG]!ss is not added into iomem_resource and hence can't be * detected by register_e820_pmem(). Fix this by directly calling * e820__reserve_resources_late() here: e820__reserve_resources_late() * depends on e820__reserve_resources(), which has been called earlier * from setup_arch(). Note: e820__reserve_resources_late() also adds * any memory of E820_TYPE_PMEM (7) into iomem_resource, and * acpi_nfit_register_region() -> acpi_nfit_insert_resource() -> * region_intersects() returns REGION_INTERSECTS, so the memory of * E820_TYPE_PMEM won't get added twice. * * We return 0 here so that pci_arch_init() won't print the warning: * "PCI: Fatal: No config space access function found"
*/ if (gen2vm) {
e820__reserve_resources_late(); return 0;
}
/* For Generation-1 VM, we'll proceed in pci_arch_init(). */ return 1;
}
staticint hv_suspend(void)
{ union hv_x64_msr_hypercall_contents hypercall_msr; int ret;
if (hv_root_partition()) return -EPERM;
/* * Reset the hypercall page as it is going to be invalidated * across hibernation. Setting hv_hypercall_pg to NULL ensures * that any subsequent hypercall operation fails safely instead of * crashing due to an access of an invalid page. The hypercall page * pointer is restored on resume.
*/
hv_hypercall_pg_saved = hv_hypercall_pg;
hv_hypercall_pg = NULL;
/* Disable the hypercall page in the hypervisor */
rdmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
hypercall_msr.enable = 0;
wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
ret = hv_cpu_die(0); return ret;
}
staticvoid hv_resume(void)
{ union hv_x64_msr_hypercall_contents hypercall_msr; int ret;
/* * Reenlightenment notifications are disabled by hv_cpu_die(0), * reenable them here if hv_reenlightenment_cb was previously set.
*/ if (hv_reenlightenment_cb)
set_hv_tscchange_cb(hv_reenlightenment_cb);
}
/* Note: when the ops are called, only CPU0 is online and IRQs are disabled. */ staticstruct syscore_ops hv_syscore_ops = {
.suspend = hv_suspend,
.resume = hv_resume,
};
staticvoid __init hv_stimer_setup_percpu_clockev(void)
{ /* * Ignore any errors in setting up stimer clockevents * as we can run with the LAPIC timer as a fallback.
*/
(void)hv_stimer_alloc(false);
/* * Still register the LAPIC timer, because the direct-mode STIMER is * not supported by old versions of Hyper-V. This also allows users * to switch to LAPIC timer via /sys, if they want to.
*/ if (old_setup_percpu_clockev)
old_setup_percpu_clockev();
}
/* * This function is to be invoked early in the boot sequence after the * hypervisor has been detected. * * 1. Setup the hypercall page. * 2. Register Hyper-V specific clocksource. * 3. Setup Hyper-V specific APIC entry points.
*/ void __init hyperv_init(void)
{
u64 guest_id; union hv_x64_msr_hypercall_contents hypercall_msr; int cpuhp;
if (x86_hyper_type != X86_HYPER_MS_HYPERV) return;
if (hv_common_init()) return;
/* * The VP assist page is useless to a TDX guest: the only use we * would have for it is lazy EOI, which can not be used with TDX.
*/ if (hv_isolation_type_tdx())
hv_vp_assist_page = NULL; else
hv_vp_assist_page = kcalloc(nr_cpu_ids, sizeof(*hv_vp_assist_page),
GFP_KERNEL); if (!hv_vp_assist_page) {
ms_hyperv.hints &= ~HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
if (!hv_isolation_type_tdx()) goto common_free;
}
if (ms_hyperv.paravisor_present && hv_isolation_type_snp()) { /* Negotiate GHCB Version. */ if (!hv_ghcb_negotiate_protocol())
hv_ghcb_terminate(SEV_TERM_SET_GEN,
GHCB_SEV_ES_PROT_UNSUPPORTED);
hv_ghcb_pg = alloc_percpu(union hv_ghcb *); if (!hv_ghcb_pg) goto free_vp_assist_page;
}
/* * Setup the hypercall page and enable hypercalls. * 1. Register the guest ID * 2. Enable the hypercall and register the hypercall page * * A TDX VM with no paravisor only uses TDX GHCI rather than hv_hypercall_pg: * when the hypercall input is a page, such a VM must pass a decrypted * page to Hyper-V, e.g. hv_post_message() uses the per-CPU page * hyperv_pcpu_input_arg, which is decrypted if no paravisor is present. * * A TDX VM with the paravisor uses hv_hypercall_pg for most hypercalls, * which are handled by the paravisor and the VM must use an encrypted * input page: in such a VM, the hyperv_pcpu_input_arg is encrypted and * used in the hypercalls, e.g. see hv_mark_gpa_visibility() and * hv_arch_irq_unmask(). Such a VM uses TDX GHCI for two hypercalls: * 1. HVCALL_SIGNAL_EVENT: see vmbus_set_event() and _hv_do_fast_hypercall8(). * 2. HVCALL_POST_MESSAGE: the input page must be a decrypted page, i.e. * hv_post_message() in such a VM can't use the encrypted hyperv_pcpu_input_arg; * instead, hv_post_message() uses the post_msg_page, which is decrypted * in such a VM and is only used in such a VM.
*/
guest_id = hv_generate_guest_id(LINUX_VERSION_CODE);
wrmsrq(HV_X64_MSR_GUEST_OS_ID, guest_id);
/* With the paravisor, the VM must also write the ID via GHCB/GHCI */
hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, guest_id);
/* A TDX VM with no paravisor only uses TDX GHCI rather than hv_hypercall_pg */ if (hv_isolation_type_tdx() && !ms_hyperv.paravisor_present) goto skip_hypercall_pg_init;
if (hv_root_partition()) { struct page *pg; void *src;
/* * For the root partition, the hypervisor will set up its * hypercall page. The hypervisor guarantees it will not show * up in the root's address space. The root can't change the * location of the hypercall page. * * Order is important here. We must enable the hypercall page * so it is populated with code, then copy the code to an * executable page.
*/
wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
skip_hypercall_pg_init: /* * Some versions of Hyper-V that provide IBT in guest VMs have a bug * in that there's no ENDBR64 instruction at the entry to the * hypercall page. Because hypercalls are invoked via an indirect call * to the hypercall page, all hypercall attempts fail when IBT is * enabled, and Linux panics. For such buggy versions, disable IBT. * * Fixed versions of Hyper-V always provide ENDBR64 on the hypercall * page, so if future Linux kernel versions enable IBT for 32-bit * builds, additional hypercall page hackery will be required here * to provide an ENDBR32.
*/ #ifdef CONFIG_X86_KERNEL_IBT if (cpu_feature_enabled(X86_FEATURE_IBT) &&
*(u32 *)hv_hypercall_pg != gen_endbr()) {
setup_clear_cpu_cap(X86_FEATURE_IBT);
pr_warn("Disabling IBT because of Hyper-V bug\n");
} #endif
/* * hyperv_init() is called before LAPIC is initialized: see * apic_intr_mode_init() -> x86_platform.apic_post_init() and * apic_bsp_setup() -> setup_local_APIC(). The direct-mode STIMER * depends on LAPIC, so hv_stimer_alloc() should be called from * x86_init.timers.setup_percpu_clockev.
*/
old_setup_percpu_clockev = x86_init.timers.setup_percpu_clockev;
x86_init.timers.setup_percpu_clockev = hv_stimer_setup_percpu_clockev;
hv_apic_init();
x86_init.pci.arch_init = hv_pci_init;
register_syscore_ops(&hv_syscore_ops);
if (ms_hyperv.priv_high & HV_ACCESS_PARTITION_ID)
hv_get_partition_id();
#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())
x86_init.irqs.create_pci_msi_domain = hv_create_pci_msi_domain; #endif
/* Query the VMs extended capability once, so that it can be cached. */
hv_query_ext_cap(0);
/* Find the VTL */
ms_hyperv.vtl = get_vtl();
if (ms_hyperv.vtl > 0) /* non default VTL */
hv_vtl_early_init();
/* * This routine is called before kexec/kdump, it does the required cleanup.
*/ void hyperv_cleanup(void)
{ union hv_x64_msr_hypercall_contents hypercall_msr; union hv_reference_tsc_msr tsc_msr;
/* Reset our OS id */
wrmsrq(HV_X64_MSR_GUEST_OS_ID, 0);
hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
/* * Reset hypercall page reference before reset the page, * let hypercall operations fail safely rather than * panic the kernel for using invalid hypercall page
*/
hv_hypercall_pg = NULL;
/* * We prefer to report panic on 'die' chain as we have proper * registers to report, but if we miss it (e.g. on BUG()) we need * to report it on 'panic'.
*/ if (panic_reported) return;
panic_reported = true;
/* * Let Hyper-V know there is crash data available
*/
wrmsrq(HV_X64_MSR_CRASH_CTL, HV_CRASH_CTL_CRASH_NOTIFY);
}
EXPORT_SYMBOL_GPL(hyperv_report_panic);
bool hv_is_hyperv_initialized(void)
{ union hv_x64_msr_hypercall_contents hypercall_msr;
/* * Ensure that we're really on Hyper-V, and not a KVM or Xen * emulation of Hyper-V
*/ if (x86_hyper_type != X86_HYPER_MS_HYPERV) returnfalse;
/* A TDX VM with no paravisor uses TDX GHCI call rather than hv_hypercall_pg */ if (hv_isolation_type_tdx() && !ms_hyperv.paravisor_present) returntrue; /* * Verify that earlier initialization succeeded by checking * that the hypercall page is setup
*/
hypercall_msr.as_uint64 = 0;
rdmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.