diff options
Diffstat (limited to 'arch/x86')
| -rw-r--r-- | arch/x86/hyperv/Makefile | 16 | ||||
| -rw-r--r-- | arch/x86/hyperv/hv_apic.c | 8 | ||||
| -rw-r--r-- | arch/x86/hyperv/hv_crash.c | 642 | ||||
| -rw-r--r-- | arch/x86/hyperv/hv_init.c | 9 | ||||
| -rw-r--r-- | arch/x86/hyperv/hv_trampoline.S | 101 | ||||
| -rw-r--r-- | arch/x86/hyperv/hv_vtl.c | 30 | ||||
| -rw-r--r-- | arch/x86/hyperv/mshv-asm-offsets.c | 37 | ||||
| -rw-r--r-- | arch/x86/hyperv/mshv_vtl_asm.S | 116 | ||||
| -rw-r--r-- | arch/x86/include/asm/mshyperv.h | 45 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mshyperv.c | 88 |
10 files changed, 1071 insertions, 21 deletions
diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile index d55f494f471d..56292102af62 100644 --- a/arch/x86/hyperv/Makefile +++ b/arch/x86/hyperv/Makefile @@ -1,8 +1,22 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y := hv_init.o mmu.o nested.o irqdomain.o ivm.o obj-$(CONFIG_X86_64) += hv_apic.o -obj-$(CONFIG_HYPERV_VTL_MODE) += hv_vtl.o +obj-$(CONFIG_HYPERV_VTL_MODE) += hv_vtl.o mshv_vtl_asm.o + +$(obj)/mshv_vtl_asm.o: $(obj)/mshv-asm-offsets.h + +$(obj)/mshv-asm-offsets.h: $(obj)/mshv-asm-offsets.s FORCE + $(call filechk,offsets,__MSHV_ASM_OFFSETS_H__) ifdef CONFIG_X86_64 obj-$(CONFIG_PARAVIRT_SPINLOCKS) += hv_spinlock.o + + ifdef CONFIG_MSHV_ROOT + CFLAGS_REMOVE_hv_trampoline.o += -pg + CFLAGS_hv_trampoline.o += -fno-stack-protector + obj-$(CONFIG_CRASH_DUMP) += hv_crash.o hv_trampoline.o + endif endif + +targets += mshv-asm-offsets.s +clean-files += mshv-asm-offsets.h diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index bfde0a3498b9..a8de503def37 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -53,6 +53,11 @@ static void hv_apic_icr_write(u32 low, u32 id) wrmsrq(HV_X64_MSR_ICR, reg_val); } +void hv_enable_coco_interrupt(unsigned int cpu, unsigned int vector, bool set) +{ + apic_update_vector(cpu, vector, set); +} + static u32 hv_apic_read(u32 reg) { u32 reg_val, hi; @@ -293,6 +298,9 @@ static void hv_send_ipi_self(int vector) void __init hv_apic_init(void) { + if (cc_platform_has(CC_ATTR_SNP_SECURE_AVIC)) + return; + if (ms_hyperv.hints & HV_X64_CLUSTER_IPI_RECOMMENDED) { pr_info("Hyper-V: Using IPI hypercalls\n"); /* diff --git a/arch/x86/hyperv/hv_crash.c b/arch/x86/hyperv/hv_crash.c new file mode 100644 index 000000000000..c0e22921ace1 --- /dev/null +++ b/arch/x86/hyperv/hv_crash.c @@ -0,0 +1,642 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * X86 specific Hyper-V root partition kdump/crash support module + * + * Copyright (C) 2025, Microsoft, Inc. + * + * This module implements hypervisor RAM collection into vmcore for both + * cases of the hypervisor crash and Linux root crash. Hyper-V implements + * a disable hypercall with a 32bit protected mode ABI callback. This + * mechanism must be used to unlock hypervisor RAM. Since the hypervisor RAM + * is already mapped in Linux, it is automatically collected into Linux vmcore, + * and can be examined by the crash command (raw RAM dump) or windbg. + * + * At a high level: + * + * Hypervisor Crash: + * Upon crash, hypervisor goes into an emergency minimal dispatch loop, a + * restrictive mode with very limited hypercall and MSR support. Each cpu + * then injects NMIs into root vcpus. A shared page is used to check + * by Linux in the NMI handler if the hypervisor has crashed. This shared + * page is setup in hv_root_crash_init during boot. + * + * Linux Crash: + * In case of Linux crash, the callback hv_crash_stop_other_cpus will send + * NMIs to all cpus, then proceed to the crash_nmi_callback where it waits + * for all cpus to be in NMI. + * + * NMI Handler (upon quorum): + * Eventually, in both cases, all cpus will end up in the NMI handler. + * Hyper-V requires the disable hypervisor must be done from the BSP. So + * the BSP NMI handler saves current context, does some fixups and makes + * the hypercall to disable the hypervisor, ie, devirtualize. Hypervisor + * at that point will suspend all vcpus (except the BSP), unlock all its + * RAM, and return to Linux at the 32bit mode entry RIP. + * + * Linux 32bit entry trampoline will then restore long mode and call C + * function here to restore context and continue execution to crash kexec. + */ + +#include <linux/delay.h> +#include <linux/kexec.h> +#include <linux/crash_dump.h> +#include <linux/panic.h> +#include <asm/apic.h> +#include <asm/desc.h> +#include <asm/page.h> +#include <asm/pgalloc.h> +#include <asm/mshyperv.h> +#include <asm/nmi.h> +#include <asm/idtentry.h> +#include <asm/reboot.h> +#include <asm/intel_pt.h> + +bool hv_crash_enabled; +EXPORT_SYMBOL_GPL(hv_crash_enabled); + +struct hv_crash_ctxt { + ulong rsp; + ulong cr0; + ulong cr2; + ulong cr4; + ulong cr8; + + u16 cs; + u16 ss; + u16 ds; + u16 es; + u16 fs; + u16 gs; + + u16 gdt_fill; + struct desc_ptr gdtr; + char idt_fill[6]; + struct desc_ptr idtr; + + u64 gsbase; + u64 efer; + u64 pat; +}; +static struct hv_crash_ctxt hv_crash_ctxt; + +/* Shared hypervisor page that contains crash dump area we peek into. + * NB: windbg looks for "hv_cda" symbol so don't change it. + */ +static struct hv_crashdump_area *hv_cda; + +static u32 trampoline_pa, devirt_arg; +static atomic_t crash_cpus_wait; +static void *hv_crash_ptpgs[4]; +static bool hv_has_crashed, lx_has_crashed; + +static void __noreturn hv_panic_timeout_reboot(void) +{ + #define PANIC_TIMER_STEP 100 + + if (panic_timeout > 0) { + int i; + + for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) + mdelay(PANIC_TIMER_STEP); + } + + if (panic_timeout) + native_wrmsrq(HV_X64_MSR_RESET, 1); /* get hyp to reboot */ + + for (;;) + cpu_relax(); +} + +/* This cannot be inlined as it needs stack */ +static noinline __noclone void hv_crash_restore_tss(void) +{ + load_TR_desc(); +} + +/* This cannot be inlined as it needs stack */ +static noinline void hv_crash_clear_kernpt(void) +{ + pgd_t *pgd; + p4d_t *p4d; + + /* Clear entry so it's not confusing to someone looking at the core */ + pgd = pgd_offset_k(trampoline_pa); + p4d = p4d_offset(pgd, trampoline_pa); + native_p4d_clear(p4d); +} + +/* + * This is the C entry point from the asm glue code after the disable hypercall. + * We enter here in IA32-e long mode, ie, full 64bit mode running on kernel + * page tables with our below 4G page identity mapped, but using a temporary + * GDT. ds/fs/gs/es are null. ss is not usable. bp is null. stack is not + * available. We restore kernel GDT, and rest of the context, and continue + * to kexec. + */ +static asmlinkage void __noreturn hv_crash_c_entry(void) +{ + struct hv_crash_ctxt *ctxt = &hv_crash_ctxt; + + /* first thing, restore kernel gdt */ + native_load_gdt(&ctxt->gdtr); + + asm volatile("movw %%ax, %%ss" : : "a"(ctxt->ss)); + asm volatile("movq %0, %%rsp" : : "m"(ctxt->rsp)); + + asm volatile("movw %%ax, %%ds" : : "a"(ctxt->ds)); + asm volatile("movw %%ax, %%es" : : "a"(ctxt->es)); + asm volatile("movw %%ax, %%fs" : : "a"(ctxt->fs)); + asm volatile("movw %%ax, %%gs" : : "a"(ctxt->gs)); + + native_wrmsrq(MSR_IA32_CR_PAT, ctxt->pat); + asm volatile("movq %0, %%cr0" : : "r"(ctxt->cr0)); + + asm volatile("movq %0, %%cr8" : : "r"(ctxt->cr8)); + asm volatile("movq %0, %%cr4" : : "r"(ctxt->cr4)); + asm volatile("movq %0, %%cr2" : : "r"(ctxt->cr4)); + + native_load_idt(&ctxt->idtr); + native_wrmsrq(MSR_GS_BASE, ctxt->gsbase); + native_wrmsrq(MSR_EFER, ctxt->efer); + + /* restore the original kernel CS now via far return */ + asm volatile("movzwq %0, %%rax\n\t" + "pushq %%rax\n\t" + "pushq $1f\n\t" + "lretq\n\t" + "1:nop\n\t" : : "m"(ctxt->cs) : "rax"); + + /* We are in asmlinkage without stack frame, hence make C function + * calls which will buy stack frames. + */ + hv_crash_restore_tss(); + hv_crash_clear_kernpt(); + + /* we are now fully in devirtualized normal kernel mode */ + __crash_kexec(NULL); + + hv_panic_timeout_reboot(); +} +/* Tell gcc we are using lretq long jump in the above function intentionally */ +STACK_FRAME_NON_STANDARD(hv_crash_c_entry); + +static void hv_mark_tss_not_busy(void) +{ + struct desc_struct *desc = get_current_gdt_rw(); + tss_desc tss; + + memcpy(&tss, &desc[GDT_ENTRY_TSS], sizeof(tss_desc)); + tss.type = 0x9; /* available 64-bit TSS. 0xB is busy TSS */ + write_gdt_entry(desc, GDT_ENTRY_TSS, &tss, DESC_TSS); +} + +/* Save essential context */ +static void hv_hvcrash_ctxt_save(void) +{ + struct hv_crash_ctxt *ctxt = &hv_crash_ctxt; + + asm volatile("movq %%rsp,%0" : "=m"(ctxt->rsp)); + + ctxt->cr0 = native_read_cr0(); + ctxt->cr4 = native_read_cr4(); + + asm volatile("movq %%cr2, %0" : "=a"(ctxt->cr2)); + asm volatile("movq %%cr8, %0" : "=a"(ctxt->cr8)); + + asm volatile("movl %%cs, %%eax" : "=a"(ctxt->cs)); + asm volatile("movl %%ss, %%eax" : "=a"(ctxt->ss)); + asm volatile("movl %%ds, %%eax" : "=a"(ctxt->ds)); + asm volatile("movl %%es, %%eax" : "=a"(ctxt->es)); + asm volatile("movl %%fs, %%eax" : "=a"(ctxt->fs)); + asm volatile("movl %%gs, %%eax" : "=a"(ctxt->gs)); + + native_store_gdt(&ctxt->gdtr); + store_idt(&ctxt->idtr); + + ctxt->gsbase = __rdmsr(MSR_GS_BASE); + ctxt->efer = __rdmsr(MSR_EFER); + ctxt->pat = __rdmsr(MSR_IA32_CR_PAT); +} + +/* Add trampoline page to the kernel pagetable for transition to kernel PT */ +static void hv_crash_fixup_kernpt(void) +{ + pgd_t *pgd; + p4d_t *p4d; + + pgd = pgd_offset_k(trampoline_pa); + p4d = p4d_offset(pgd, trampoline_pa); + + /* trampoline_pa is below 4G, so no pre-existing entry to clobber */ + p4d_populate(&init_mm, p4d, (pud_t *)hv_crash_ptpgs[1]); + p4d->p4d = p4d->p4d & ~(_PAGE_NX); /* enable execute */ +} + +/* + * Notify the hyp that Linux has crashed. This will cause the hyp to quiesce + * and suspend all guest VPs. + */ +static void hv_notify_prepare_hyp(void) +{ + u64 status; + struct hv_input_notify_partition_event *input; + struct hv_partition_event_root_crashdump_input *cda; + + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + cda = &input->input.crashdump_input; + memset(input, 0, sizeof(*input)); + input->event = HV_PARTITION_EVENT_ROOT_CRASHDUMP; + + cda->crashdump_action = HV_CRASHDUMP_ENTRY; + status = hv_do_hypercall(HVCALL_NOTIFY_PARTITION_EVENT, input, NULL); + if (!hv_result_success(status)) + return; + + cda->crashdump_action = HV_CRASHDUMP_SUSPEND_ALL_VPS; + hv_do_hypercall(HVCALL_NOTIFY_PARTITION_EVENT, input, NULL); +} + +/* + * Common function for all cpus before devirtualization. + * + * Hypervisor crash: all cpus get here in NMI context. + * Linux crash: the panicing cpu gets here at base level, all others in NMI + * context. Note, panicing cpu may not be the BSP. + * + * The function is not inlined so it will show on the stack. It is named so + * because the crash cmd looks for certain well known function names on the + * stack before looking into the cpu saved note in the elf section, and + * that work is currently incomplete. + * + * Notes: + * Hypervisor crash: + * - the hypervisor is in a very restrictive mode at this point and any + * vmexit it cannot handle would result in reboot. So, no mumbo jumbo, + * just get to kexec as quickly as possible. + * + * Devirtualization is supported from the BSP only at present. + */ +static noinline __noclone void crash_nmi_callback(struct pt_regs *regs) +{ + struct hv_input_disable_hyp_ex *input; + u64 status; + int msecs = 1000, ccpu = smp_processor_id(); + + if (ccpu == 0) { + /* crash_save_cpu() will be done in the kexec path */ + cpu_emergency_stop_pt(); /* disable performance trace */ + atomic_inc(&crash_cpus_wait); + } else { + crash_save_cpu(regs, ccpu); + cpu_emergency_stop_pt(); /* disable performance trace */ + atomic_inc(&crash_cpus_wait); + for (;;) + cpu_relax(); + } + + while (atomic_read(&crash_cpus_wait) < num_online_cpus() && msecs--) + mdelay(1); + + stop_nmi(); + if (!hv_has_crashed) + hv_notify_prepare_hyp(); + + if (crashing_cpu == -1) + crashing_cpu = ccpu; /* crash cmd uses this */ + + hv_hvcrash_ctxt_save(); + hv_mark_tss_not_busy(); + hv_crash_fixup_kernpt(); + + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + memset(input, 0, sizeof(*input)); + input->rip = trampoline_pa; + input->arg = devirt_arg; + + status = hv_do_hypercall(HVCALL_DISABLE_HYP_EX, input, NULL); + + hv_panic_timeout_reboot(); +} + + +static DEFINE_SPINLOCK(hv_crash_reboot_lk); + +/* + * Generic NMI callback handler: could be called without any crash also. + * hv crash: hypervisor injects NMI's into all cpus + * lx crash: panicing cpu sends NMI to all but self via crash_stop_other_cpus + */ +static int hv_crash_nmi_local(unsigned int cmd, struct pt_regs *regs) +{ + if (!hv_has_crashed && hv_cda && hv_cda->cda_valid) + hv_has_crashed = true; + + if (!hv_has_crashed && !lx_has_crashed) + return NMI_DONE; /* ignore the NMI */ + + if (hv_has_crashed && !kexec_crash_loaded()) { + if (spin_trylock(&hv_crash_reboot_lk)) + hv_panic_timeout_reboot(); + else + for (;;) + cpu_relax(); + } + + crash_nmi_callback(regs); + + return NMI_DONE; +} + +/* + * hv_crash_stop_other_cpus() == smp_ops.crash_stop_other_cpus + * + * On normal Linux panic, this is called twice: first from panic and then again + * from native_machine_crash_shutdown. + * + * In case of hyperv, 3 ways to get here: + * 1. hv crash (only BSP will get here): + * BSP : NMI callback -> DisableHv -> hv_crash_asm32 -> hv_crash_c_entry + * -> __crash_kexec -> native_machine_crash_shutdown + * -> crash_smp_send_stop -> smp_ops.crash_stop_other_cpus + * Linux panic: + * 2. panic cpu x: panic() -> crash_smp_send_stop + * -> smp_ops.crash_stop_other_cpus + * 3. BSP: native_machine_crash_shutdown -> crash_smp_send_stop + * + * NB: noclone and non standard stack because of call to crash_setup_regs(). + */ +static void __noclone hv_crash_stop_other_cpus(void) +{ + static bool crash_stop_done; + struct pt_regs lregs; + int ccpu = smp_processor_id(); + + if (hv_has_crashed) + return; /* all cpus already in NMI handler path */ + + if (!kexec_crash_loaded()) { + hv_notify_prepare_hyp(); + hv_panic_timeout_reboot(); /* no return */ + } + + /* If the hv crashes also, we could come here again before cpus_stopped + * is set in crash_smp_send_stop(). So use our own check. + */ + if (crash_stop_done) + return; + crash_stop_done = true; + + /* Linux has crashed: hv is healthy, we can IPI safely */ + lx_has_crashed = true; + wmb(); /* NMI handlers look at lx_has_crashed */ + + apic->send_IPI_allbutself(NMI_VECTOR); + + if (crashing_cpu == -1) + crashing_cpu = ccpu; /* crash cmd uses this */ + + /* crash_setup_regs() happens in kexec also, but for the kexec cpu which + * is the BSP. We could be here on non-BSP cpu, collect regs if so. + */ + if (ccpu) + crash_setup_regs(&lregs, NULL); + + crash_nmi_callback(&lregs); +} +STACK_FRAME_NON_STANDARD(hv_crash_stop_other_cpus); + +/* This GDT is accessed in IA32-e compat mode which uses 32bits addresses */ +struct hv_gdtreg_32 { + u16 fill; + u16 limit; + u32 address; +} __packed; + +/* We need a CS with L bit to goto IA32-e long mode from 32bit compat mode */ +struct hv_crash_tramp_gdt { + u64 null; /* index 0, selector 0, null selector */ + u64 cs64; /* index 1, selector 8, cs64 selector */ +} __packed; + +/* No stack, so jump via far ptr in memory to load the 64bit CS */ +struct hv_cs_jmptgt { + u32 address; + u16 csval; + u16 fill; +} __packed; + +/* Linux use only, hypervisor doesn't look at this struct */ +struct hv_crash_tramp_data { + u64 tramp32_cr3; + u64 kernel_cr3; + struct hv_gdtreg_32 gdtr32; + struct hv_crash_tramp_gdt tramp_gdt; + struct hv_cs_jmptgt cs_jmptgt; + u64 c_entry_addr; +} __packed; + +/* + * Setup a temporary gdt to allow the asm code to switch to the long mode. + * Since the asm code is relocated/copied to a below 4G page, it cannot use rip + * relative addressing, hence we must use trampoline_pa here. Also, save other + * info like jmp and C entry targets for same reasons. + * + * Returns: 0 on success, -1 on error + */ +static int hv_crash_setup_trampdata(u64 trampoline_va) +{ + int size, offs; + void *dest; + struct hv_crash_tramp_data *tramp; + + /* These must match exactly the ones in the corresponding asm file */ + BUILD_BUG_ON(offsetof(struct hv_crash_tramp_data, tramp32_cr3) != 0); + BUILD_BUG_ON(offsetof(struct hv_crash_tramp_data, kernel_cr3) != 8); + BUILD_BUG_ON(offsetof(struct hv_crash_tramp_data, gdtr32.limit) != 18); + BUILD_BUG_ON(offsetof(struct hv_crash_tramp_data, + cs_jmptgt.address) != 40); + BUILD_BUG_ON(offsetof(struct hv_crash_tramp_data, c_entry_addr) != 48); + + /* hv_crash_asm_end is beyond last byte by 1 */ + size = &hv_crash_asm_end - &hv_crash_asm32; + if (size + sizeof(struct hv_crash_tramp_data) > PAGE_SIZE) { + pr_err("%s: trampoline page overflow\n", __func__); + return -1; + } + + dest = (void *)trampoline_va; + memcpy(dest, &hv_crash_asm32, size); + + dest += size; + dest = (void *)round_up((ulong)dest, 16); + tramp = (struct hv_crash_tramp_data *)dest; + + /* see MAX_ASID_AVAILABLE in tlb.c: "PCID 0 is reserved for use by + * non-PCID-aware users". Build cr3 with pcid 0 + */ + tramp->tramp32_cr3 = __sme_pa(hv_crash_ptpgs[0]); + + /* Note, when restoring X86_CR4_PCIDE, cr3[11:0] must be zero */ + tramp->kernel_cr3 = __sme_pa(init_mm.pgd); + + tramp->gdtr32.limit = sizeof(struct hv_crash_tramp_gdt); + tramp->gdtr32.address = trampoline_pa + + (ulong)&tramp->tramp_gdt - trampoline_va; + + /* base:0 limit:0xfffff type:b dpl:0 P:1 L:1 D:0 avl:0 G:1 */ + tramp->tramp_gdt.cs64 = 0x00af9a000000ffff; + + tramp->cs_jmptgt.csval = 0x8; + offs = (ulong)&hv_crash_asm64 - (ulong)&hv_crash_asm32; + tramp->cs_jmptgt.address = trampoline_pa + offs; + + tramp->c_entry_addr = (u64)&hv_crash_c_entry; + + devirt_arg = trampoline_pa + (ulong)dest - trampoline_va; + + return 0; +} + +/* + * Build 32bit trampoline page table for transition from protected mode + * non-paging to long-mode paging. This transition needs pagetables below 4G. + */ +static void hv_crash_build_tramp_pt(void) +{ + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + u64 pa, addr = trampoline_pa; + + p4d = hv_crash_ptpgs[0] + pgd_index(addr) * sizeof(p4d); + pa = virt_to_phys(hv_crash_ptpgs[1]); + set_p4d(p4d, __p4d(_PAGE_TABLE | pa)); + p4d->p4d &= ~(_PAGE_NX); /* enable execute */ + + pud = hv_crash_ptpgs[1] + pud_index(addr) * sizeof(pud); + pa = virt_to_phys(hv_crash_ptpgs[2]); + set_pud(pud, __pud(_PAGE_TABLE | pa)); + + pmd = hv_crash_ptpgs[2] + pmd_index(addr) * sizeof(pmd); + pa = virt_to_phys(hv_crash_ptpgs[3]); + set_pmd(pmd, __pmd(_PAGE_TABLE | pa)); + + pte = hv_crash_ptpgs[3] + pte_index(addr) * sizeof(pte); + set_pte(pte, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_EXEC)); +} + +/* + * Setup trampoline for devirtualization: + * - a page below 4G, ie 32bit addr containing asm glue code that hyp jmps to + * in protected mode. + * - 4 pages for a temporary page table that asm code uses to turn paging on + * - a temporary gdt to use in the compat mode. + * + * Returns: 0 on success + */ +static int hv_crash_trampoline_setup(void) +{ + int i, rc, order; + struct page *page; + u64 trampoline_va; + gfp_t flags32 = GFP_KERNEL | GFP_DMA32 | __GFP_ZERO; + + /* page for 32bit trampoline assembly code + hv_crash_tramp_data */ + page = alloc_page(flags32); + if (page == NULL) { + pr_err("%s: failed to alloc asm stub page\n", __func__); + return -1; + } + + trampoline_va = (u64)page_to_virt(page); + trampoline_pa = (u32)page_to_phys(page); + + order = 2; /* alloc 2^2 pages */ + page = alloc_pages(flags32, order); + if (page == NULL) { + pr_err("%s: failed to alloc pt pages\n", __func__); + free_page(trampoline_va); + return -1; + } + + for (i = 0; i < 4; i++, page++) + hv_crash_ptpgs[i] = page_to_virt(page); + + hv_crash_build_tramp_pt(); + + rc = hv_crash_setup_trampdata(trampoline_va); + if (rc) + goto errout; + + return 0; + +errout: + free_page(trampoline_va); + free_pages((ulong)hv_crash_ptpgs[0], order); + + return rc; +} + +/* Setup for kdump kexec to collect hypervisor RAM when running as root */ +void hv_root_crash_init(void) +{ + int rc; + struct hv_input_get_system_property *input; + struct hv_output_get_system_property *output; + unsigned long flags; + u64 status; + union hv_pfn_range cda_info; + + if (pgtable_l5_enabled()) { + pr_err("Hyper-V: crash dump not yet supported on 5level PTs\n"); + return; + } + + rc = register_nmi_handler(NMI_LOCAL, hv_crash_nmi_local, NMI_FLAG_FIRST, + "hv_crash_nmi"); + if (rc) { + pr_err("Hyper-V: failed to register crash nmi handler\n"); + return; + } + + local_irq_save(flags); + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + output = *this_cpu_ptr(hyperv_pcpu_output_arg); + + memset(input, 0, sizeof(*input)); + input->property_id = HV_SYSTEM_PROPERTY_CRASHDUMPAREA; + + status = hv_do_hypercall(HVCALL_GET_SYSTEM_PROPERTY, input, output); + cda_info.as_uint64 = output->hv_cda_info.as_uint64; + local_irq_restore(flags); + + if (!hv_result_success(status)) { + pr_err("Hyper-V: %s: property:%d %s\n", __func__, + input->property_id, hv_result_to_string(status)); + goto err_out; + } + + if (cda_info.base_pfn == 0) { + pr_err("Hyper-V: hypervisor crash dump area pfn is 0\n"); + goto err_out; + } + + hv_cda = phys_to_virt(cda_info.base_pfn << HV_HYP_PAGE_SHIFT); + + rc = hv_crash_trampoline_setup(); + if (rc) + goto err_out; + + smp_ops.crash_stop_other_cpus = hv_crash_stop_other_cpus; + + crash_kexec_post_notifiers = true; + hv_crash_enabled = true; + pr_info("Hyper-V: both linux and hypervisor kdump support enabled\n"); + + return; + +err_out: + unregister_nmi_handler(NMI_LOCAL, "hv_crash_nmi"); + pr_err("Hyper-V: only linux root kdump support enabled\n"); +} diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 085ef4f2e73a..14de43f4bc6c 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -170,6 +170,10 @@ static int hv_cpu_init(unsigned int cpu) wrmsrq(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); } + /* Allow Hyper-V stimer vector to be injected from Hypervisor. */ + if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE) + apic_update_vector(cpu, HYPERV_STIMER0_VECTOR, true); + return hyperv_init_ghcb(); } @@ -277,6 +281,9 @@ static int hv_cpu_die(unsigned int cpu) *ghcb_va = NULL; } + if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE) + apic_update_vector(cpu, HYPERV_STIMER0_VECTOR, false); + hv_common_cpu_die(cpu); if (hv_vp_assist_page && hv_vp_assist_page[cpu]) { @@ -551,6 +558,8 @@ void __init hyperv_init(void) memunmap(src); hv_remap_tsc_clocksource(); + hv_root_crash_init(); + hv_sleep_notifiers_register(); } else { hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg); wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); diff --git a/arch/x86/hyperv/hv_trampoline.S b/arch/x86/hyperv/hv_trampoline.S new file mode 100644 index 000000000000..25f02ff12286 --- /dev/null +++ b/arch/x86/hyperv/hv_trampoline.S @@ -0,0 +1,101 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * X86 specific Hyper-V kdump/crash related code. + * + * Copyright (C) 2025, Microsoft, Inc. + * + */ +#include <linux/linkage.h> +#include <asm/alternative.h> +#include <asm/msr.h> +#include <asm/processor-flags.h> +#include <asm/nospec-branch.h> + +/* + * void noreturn hv_crash_asm32(arg1) + * arg1 == edi == 32bit PA of struct hv_crash_tramp_data + * + * The hypervisor jumps here upon devirtualization in protected mode. This + * code gets copied to a page in the low 4G ie, 32bit space so it can run + * in the protected mode. Hence we cannot use any compile/link time offsets or + * addresses. It restores long mode via temporary gdt and page tables and + * eventually jumps to kernel code entry at HV_CRASHDATA_OFFS_C_entry. + * + * PreCondition (ie, Hypervisor call back ABI): + * o CR0 is set to 0x0021: PE(prot mode) and NE are set, paging is disabled + * o CR4 is set to 0x0 + * o IA32_EFER is set to 0x901 (SCE and NXE are set) + * o EDI is set to the Arg passed to HVCALL_DISABLE_HYP_EX. + * o CS, DS, ES, FS, GS are all initialized with a base of 0 and limit 0xFFFF + * o IDTR, TR and GDTR are initialized with a base of 0 and limit of 0xFFFF + * o LDTR is initialized as invalid (limit of 0) + * o MSR PAT is power on default. + * o Other state/registers are cleared. All TLBs flushed. + */ + +#define HV_CRASHDATA_OFFS_TRAMPCR3 0x0 /* 0 */ +#define HV_CRASHDATA_OFFS_KERNCR3 0x8 /* 8 */ +#define HV_CRASHDATA_OFFS_GDTRLIMIT 0x12 /* 18 */ +#define HV_CRASHDATA_OFFS_CS_JMPTGT 0x28 /* 40 */ +#define HV_CRASHDATA_OFFS_C_entry 0x30 /* 48 */ + + .text + .code32 + +SYM_CODE_START(hv_crash_asm32) + UNWIND_HINT_UNDEFINED + ENDBR + movl $X86_CR4_PAE, %ecx + movl %ecx, %cr4 + + movl %edi, %ebx + add $HV_CRASHDATA_OFFS_TRAMPCR3, %ebx + movl %cs:(%ebx), %eax + movl %eax, %cr3 + + /* Setup EFER for long mode now */ + movl $MSR_EFER, %ecx + rdmsr + btsl $_EFER_LME, %eax + wrmsr + + /* Turn paging on using the temp 32bit trampoline page table */ + movl %cr0, %eax + orl $(X86_CR0_PG), %eax + movl %eax, %cr0 + + /* since kernel cr3 could be above 4G, we need to be in the long mode + * before we can load 64bits of the kernel cr3. We use a temp gdt for + * that with CS.L=1 and CS.D=0 */ + mov %edi, %eax + add $HV_CRASHDATA_OFFS_GDTRLIMIT, %eax + lgdtl %cs:(%eax) + + /* not done yet, restore CS now to switch to CS.L=1 */ + mov %edi, %eax + add $HV_CRASHDATA_OFFS_CS_JMPTGT, %eax + ljmp %cs:*(%eax) +SYM_CODE_END(hv_crash_asm32) + + /* we now run in full 64bit IA32-e long mode, CS.L=1 and CS.D=0 */ + .code64 + .balign 8 +SYM_CODE_START(hv_crash_asm64) + UNWIND_HINT_UNDEFINED + ENDBR + /* restore kernel page tables so we can jump to kernel code */ + mov %edi, %eax + add $HV_CRASHDATA_OFFS_KERNCR3, %eax + movq %cs:(%eax), %rbx + movq %rbx, %cr3 + + mov %edi, %eax + add $HV_CRASHDATA_OFFS_C_entry, %eax + movq %cs:(%eax), %rbx + ANNOTATE_RETPOLINE_SAFE + jmp *%rbx + + int $3 + +SYM_INNER_LABEL(hv_crash_asm_end, SYM_L_GLOBAL) +SYM_CODE_END(hv_crash_asm64) diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index 042e8712d8de..c0edaed0efb3 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -9,12 +9,17 @@ #include <asm/apic.h> #include <asm/boot.h> #include <asm/desc.h> +#include <asm/fpu/api.h> +#include <asm/fpu/types.h> #include <asm/i8259.h> #include <asm/mshyperv.h> #include <asm/msr.h> #include <asm/realmode.h> #include <asm/reboot.h> +#include <asm/smap.h> +#include <linux/export.h> #include <../kernel/smpboot.h> +#include "../../kernel/fpu/legacy.h" extern struct boot_params boot_params; static struct real_mode_header hv_vtl_real_mode_header; @@ -249,3 +254,28 @@ int __init hv_vtl_early_init(void) return 0; } + +DEFINE_STATIC_CALL_NULL(__mshv_vtl_return_hypercall, void (*)(void)); + +void mshv_vtl_return_call_init(u64 vtl_return_offset) +{ + static_call_update(__mshv_vtl_return_hypercall, + (void *)((u8 *)hv_hypercall_pg + vtl_return_offset)); +} +EXPORT_SYMBOL(mshv_vtl_return_call_init); + +void mshv_vtl_return_call(struct mshv_vtl_cpu_context *vtl0) +{ + struct hv_vp_assist_page *hvp; + + hvp = hv_vp_assist_page[smp_processor_id()]; + hvp->vtl_ret_x64rax = vtl0->rax; + hvp->vtl_ret_x64rcx = vtl0->rcx; + + kernel_fpu_begin_mask(0); + fxrstor(&vtl0->fx_state); + __mshv_vtl_return_call(vtl0); + fxsave(&vtl0->fx_state); + kernel_fpu_end(); +} +EXPORT_SYMBOL(mshv_vtl_return_call); diff --git a/arch/x86/hyperv/mshv-asm-offsets.c b/arch/x86/hyperv/mshv-asm-offsets.c new file mode 100644 index 000000000000..882c1db6df16 --- /dev/null +++ b/arch/x86/hyperv/mshv-asm-offsets.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Generate definitions needed by assembly language modules. + * This code generates raw asm output which is post-processed to extract + * and format the required data. + * + * Copyright (c) 2025, Microsoft Corporation. + * + * Author: + * Naman Jain <namjain@microsoft.com> + */ +#define COMPILE_OFFSETS + +#include <linux/kbuild.h> +#include <asm/mshyperv.h> + +static void __used common(void) +{ + if (IS_ENABLED(CONFIG_HYPERV_VTL_MODE)) { + OFFSET(MSHV_VTL_CPU_CONTEXT_rax, mshv_vtl_cpu_context, rax); + OFFSET(MSHV_VTL_CPU_CONTEXT_rcx, mshv_vtl_cpu_context, rcx); + OFFSET(MSHV_VTL_CPU_CONTEXT_rdx, mshv_vtl_cpu_context, rdx); + OFFSET(MSHV_VTL_CPU_CONTEXT_rbx, mshv_vtl_cpu_context, rbx); + OFFSET(MSHV_VTL_CPU_CONTEXT_rbp, mshv_vtl_cpu_context, rbp); + OFFSET(MSHV_VTL_CPU_CONTEXT_rsi, mshv_vtl_cpu_context, rsi); + OFFSET(MSHV_VTL_CPU_CONTEXT_rdi, mshv_vtl_cpu_context, rdi); + OFFSET(MSHV_VTL_CPU_CONTEXT_r8, mshv_vtl_cpu_context, r8); + OFFSET(MSHV_VTL_CPU_CONTEXT_r9, mshv_vtl_cpu_context, r9); + OFFSET(MSHV_VTL_CPU_CONTEXT_r10, mshv_vtl_cpu_context, r10); + OFFSET(MSHV_VTL_CPU_CONTEXT_r11, mshv_vtl_cpu_context, r11); + OFFSET(MSHV_VTL_CPU_CONTEXT_r12, mshv_vtl_cpu_context, r12); + OFFSET(MSHV_VTL_CPU_CONTEXT_r13, mshv_vtl_cpu_context, r13); + OFFSET(MSHV_VTL_CPU_CONTEXT_r14, mshv_vtl_cpu_context, r14); + OFFSET(MSHV_VTL_CPU_CONTEXT_r15, mshv_vtl_cpu_context, r15); + OFFSET(MSHV_VTL_CPU_CONTEXT_cr2, mshv_vtl_cpu_context, cr2); + } +} diff --git a/arch/x86/hyperv/mshv_vtl_asm.S b/arch/x86/hyperv/mshv_vtl_asm.S new file mode 100644 index 000000000000..f595eefad9ab --- /dev/null +++ b/arch/x86/hyperv/mshv_vtl_asm.S @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Assembly level code for mshv_vtl VTL transition + * + * Copyright (c) 2025, Microsoft Corporation. + * + * Author: + * Naman Jain <namjain@microsoft.com> + */ + +#include <linux/linkage.h> +#include <linux/static_call_types.h> +#include <asm/asm.h> +#include <asm/asm-offsets.h> +#include <asm/frame.h> +#include "mshv-asm-offsets.h" + + .text + .section .noinstr.text, "ax" +/* + * void __mshv_vtl_return_call(struct mshv_vtl_cpu_context *vtl0) + * + * This function is used to context switch between different Virtual Trust Levels. + * It is marked as 'noinstr' to prevent against instrumentation and debugging facilities. + * NMIs aren't a problem because the NMI handler saves/restores CR2 specifically to guard + * against #PFs in NMI context clobbering the guest state. + */ +SYM_FUNC_START(__mshv_vtl_return_call) + /* Push callee save registers */ + pushq %rbp + mov %rsp, %rbp + pushq %r12 + pushq %r13 + pushq %r14 + pushq %r15 + pushq %rbx + + /* register switch to VTL0 clobbers all registers except rax/rcx */ + mov %_ASM_ARG1, %rax + + /* grab rbx/rbp/rsi/rdi/r8-r15 */ + mov MSHV_VTL_CPU_CONTEXT_rbx(%rax), %rbx + mov MSHV_VTL_CPU_CONTEXT_rbp(%rax), %rbp + mov MSHV_VTL_CPU_CONTEXT_rsi(%rax), %rsi + mov MSHV_VTL_CPU_CONTEXT_rdi(%rax), %rdi + mov MSHV_VTL_CPU_CONTEXT_r8(%rax), %r8 + mov MSHV_VTL_CPU_CONTEXT_r9(%rax), %r9 + mov MSHV_VTL_CPU_CONTEXT_r10(%rax), %r10 + mov MSHV_VTL_CPU_CONTEXT_r11(%rax), %r11 + mov MSHV_VTL_CPU_CONTEXT_r12(%rax), %r12 + mov MSHV_VTL_CPU_CONTEXT_r13(%rax), %r13 + mov MSHV_VTL_CPU_CONTEXT_r14(%rax), %r14 + mov MSHV_VTL_CPU_CONTEXT_r15(%rax), %r15 + + mov MSHV_VTL_CPU_CONTEXT_cr2(%rax), %rdx + mov %rdx, %cr2 + mov MSHV_VTL_CPU_CONTEXT_rdx(%rax), %rdx + + /* stash host registers on stack */ + pushq %rax + pushq %rcx + + xor %ecx, %ecx + + /* make a hypercall to switch VTL */ + call STATIC_CALL_TRAMP_STR(__mshv_vtl_return_hypercall) + + /* stash guest registers on stack, restore saved host copies */ + pushq %rax + pushq %rcx + mov 16(%rsp), %rcx + mov 24(%rsp), %rax + + mov %rdx, MSHV_VTL_CPU_CONTEXT_rdx(%rax) + mov %cr2, %rdx + mov %rdx, MSHV_VTL_CPU_CONTEXT_cr2(%rax) + pop MSHV_VTL_CPU_CONTEXT_rcx(%rax) + pop MSHV_VTL_CPU_CONTEXT_rax(%rax) + add $16, %rsp + + /* save rbx/rbp/rsi/rdi/r8-r15 */ + mov %rbx, MSHV_VTL_CPU_CONTEXT_rbx(%rax) + mov %rbp, MSHV_VTL_CPU_CONTEXT_rbp(%rax) + mov %rsi, MSHV_VTL_CPU_CONTEXT_rsi(%rax) + mov %rdi, MSHV_VTL_CPU_CONTEXT_rdi(%rax) + mov %r8, MSHV_VTL_CPU_CONTEXT_r8(%rax) + mov %r9, MSHV_VTL_CPU_CONTEXT_r9(%rax) + mov %r10, MSHV_VTL_CPU_CONTEXT_r10(%rax) + mov %r11, MSHV_VTL_CPU_CONTEXT_r11(%rax) + mov %r12, MSHV_VTL_CPU_CONTEXT_r12(%rax) + mov %r13, MSHV_VTL_CPU_CONTEXT_r13(%rax) + mov %r14, MSHV_VTL_CPU_CONTEXT_r14(%rax) + mov %r15, MSHV_VTL_CPU_CONTEXT_r15(%rax) + + /* pop callee-save registers r12-r15, rbx */ + pop %rbx + pop %r15 + pop %r14 + pop %r13 + pop %r12 + + pop %rbp + RET +SYM_FUNC_END(__mshv_vtl_return_call) +/* + * Make sure that static_call_key symbol: __SCK____mshv_vtl_return_hypercall is accessible here. + * Below code is inspired from __ADDRESSABLE(sym) macro. Symbol name is kept simple, to avoid + * naming it something like "__UNIQUE_ID_addressable___SCK____mshv_vtl_return_hypercall_662.0" + * which would otherwise have been generated by the macro. + */ + .section .discard.addressable,"aw" + .align 8 + .type mshv_vtl_return_sym, @object + .size mshv_vtl_return_sym, 8 +mshv_vtl_return_sym: + .quad __SCK____mshv_vtl_return_hypercall diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 605abd02158d..eef4c3a5ba28 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -11,6 +11,7 @@ #include <asm/paravirt.h> #include <asm/msr.h> #include <hyperv/hvhdk.h> +#include <asm/fpu/types.h> /* * Hyper-V always provides a single IO-APIC at this MMIO address. @@ -176,6 +177,8 @@ int hyperv_flush_guest_mapping_range(u64 as, int hyperv_fill_flush_guest_mapping_list( struct hv_guest_mapping_flush_list *flush, u64 start_gfn, u64 end_gfn); +void hv_sleep_notifiers_register(void); +void hv_machine_power_off(void); #ifdef CONFIG_X86_64 void hv_apic_init(void); @@ -237,6 +240,15 @@ static __always_inline u64 hv_raw_get_msr(unsigned int reg) } int hv_apicid_to_vp_index(u32 apic_id); +#if IS_ENABLED(CONFIG_MSHV_ROOT) && IS_ENABLED(CONFIG_CRASH_DUMP) +void hv_root_crash_init(void); +void hv_crash_asm32(void); +void hv_crash_asm64(void); +void hv_crash_asm_end(void); +#else /* CONFIG_MSHV_ROOT && CONFIG_CRASH_DUMP */ +static inline void hv_root_crash_init(void) {} +#endif /* CONFIG_MSHV_ROOT && CONFIG_CRASH_DUMP */ + #else /* CONFIG_HYPERV */ static inline void hyperv_init(void) {} static inline void hyperv_setup_mmu_ops(void) {} @@ -260,13 +272,46 @@ static inline u64 hv_get_non_nested_msr(unsigned int reg) { return 0; } static inline int hv_apicid_to_vp_index(u32 apic_id) { return -EINVAL; } #endif /* CONFIG_HYPERV */ +struct mshv_vtl_cpu_context { + union { + struct { + u64 rax; + u64 rcx; + u64 rdx; + u64 rbx; + u64 cr2; + u64 rbp; + u64 rsi; + u64 rdi; + u64 r8; + u64 r9; + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; + }; + u64 gp_regs[16]; + }; + + struct fxregs_state fx_state; +}; #ifdef CONFIG_HYPERV_VTL_MODE void __init hv_vtl_init_platform(void); int __init hv_vtl_early_init(void); +void mshv_vtl_return_call(struct mshv_vtl_cpu_context *vtl0); +void mshv_vtl_return_call_init(u64 vtl_return_offset); +void mshv_vtl_return_hypercall(void); +void __mshv_vtl_return_call(struct mshv_vtl_cpu_context *vtl0); #else static inline void __init hv_vtl_init_platform(void) {} static inline int __init hv_vtl_early_init(void) { return 0; } +static inline void mshv_vtl_return_call(struct mshv_vtl_cpu_context *vtl0) {} +static inline void mshv_vtl_return_call_init(u64 vtl_return_offset) {} +static inline void mshv_vtl_return_hypercall(void) {} +static inline void __mshv_vtl_return_call(struct mshv_vtl_cpu_context *vtl0) {} #endif #include <asm-generic/mshyperv.h> diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index c4febdbcfe4d..579fb2c64cfd 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -28,9 +28,9 @@ #include <asm/apic.h> #include <asm/timer.h> #include <asm/reboot.h> +#include <asm/msr.h> #include <asm/nmi.h> #include <clocksource/hyperv_timer.h> -#include <asm/msr.h> #include <asm/numa.h> #include <asm/svm.h> @@ -39,6 +39,12 @@ bool hv_nested; struct ms_hyperv_info ms_hyperv; #if IS_ENABLED(CONFIG_HYPERV) +/* + * When running with the paravisor, controls proxying the synthetic interrupts + * from the host + */ +static bool hv_para_sint_proxy; + static inline unsigned int hv_get_nested_msr(unsigned int reg) { if (hv_is_sint_msr(reg)) @@ -75,17 +81,51 @@ EXPORT_SYMBOL_GPL(hv_get_non_nested_msr); void hv_set_non_nested_msr(unsigned int reg, u64 value) { if (hv_is_synic_msr(reg) && ms_hyperv.paravisor_present) { + /* The hypervisor will get the intercept. */ hv_ivm_msr_write(reg, value); - /* Write proxy bit via wrmsl instruction */ - if (hv_is_sint_msr(reg)) - wrmsrq(reg, value | 1 << 20); + /* Using wrmsrq so the following goes to the paravisor. */ + if (hv_is_sint_msr(reg)) { + union hv_synic_sint sint = { .as_uint64 = value }; + + sint.proxy = hv_para_sint_proxy; + native_wrmsrq(reg, sint.as_uint64); + } } else { - wrmsrq(reg, value); + native_wrmsrq(reg, value); } } EXPORT_SYMBOL_GPL(hv_set_non_nested_msr); +/* + * Enable or disable proxying synthetic interrupts + * to the paravisor. + */ +void hv_para_set_sint_proxy(bool enable) +{ + hv_para_sint_proxy = enable; +} + +/* + * Get the SynIC register value from the paravisor. + */ +u64 hv_para_get_synic_register(unsigned int reg) +{ + if (WARN_ON(!ms_hyperv.paravisor_present || !hv_is_synic_msr(reg))) + return ~0ULL; + return native_read_msr(reg); +} + +/* + * Set the SynIC register value with the paravisor. + */ +void hv_para_set_synic_register(unsigned int reg, u64 val) +{ + if (WARN_ON(!ms_hyperv.paravisor_present || !hv_is_synic_msr(reg))) + return; + native_write_msr(reg, val); +} + u64 hv_get_msr(unsigned int reg) { if (hv_nested) @@ -215,7 +255,7 @@ static void hv_machine_shutdown(void) #endif /* CONFIG_KEXEC_CORE */ #ifdef CONFIG_CRASH_DUMP -static void hv_machine_crash_shutdown(struct pt_regs *regs) +static void hv_guest_crash_shutdown(struct pt_regs *regs) { if (hv_crash_handler) hv_crash_handler(regs); @@ -440,7 +480,7 @@ EXPORT_SYMBOL_GPL(hv_get_hypervisor_version); static void __init ms_hyperv_init_platform(void) { - int hv_max_functions_eax; + int hv_max_functions_eax, eax; #ifdef CONFIG_PARAVIRT pv_info.name = "Hyper-V"; @@ -470,11 +510,27 @@ static void __init ms_hyperv_init_platform(void) hv_identify_partition_type(); + if (cc_platform_has(CC_ATTR_SNP_SECURE_AVIC)) + ms_hyperv.hints |= HV_DEPRECATING_AEOI_RECOMMENDED; + if (ms_hyperv.hints & HV_X64_HYPERV_NESTED) { hv_nested = true; pr_info("Hyper-V: running on a nested hypervisor\n"); } + /* + * There is no check against the max function for HYPERV_CPUID_VIRT_STACK_* CPUID + * leaves as the hypervisor doesn't handle them. Even a nested root partition (L2 + * root) will not get them because the nested (L1) hypervisor filters them out. + * These are handled through intercept processing by the Windows Hyper-V stack + * or the paravisor. + */ + eax = cpuid_eax(HYPERV_CPUID_VIRT_STACK_PROPERTIES); + ms_hyperv.confidential_vmbus_available = + eax & HYPERV_VS_PROPERTIES_EAX_CONFIDENTIAL_VMBUS_AVAILABLE; + ms_hyperv.msi_ext_dest_id = + eax & HYPERV_VS_PROPERTIES_EAX_EXTENDED_IOAPIC_RTE; + 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; @@ -565,11 +621,14 @@ static void __init ms_hyperv_init_platform(void) #endif #if IS_ENABLED(CONFIG_HYPERV) + if (hv_root_partition()) + machine_ops.power_off = hv_machine_power_off; #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; + if (!hv_root_partition()) + machine_ops.crash_shutdown = hv_guest_crash_shutdown; #endif #endif /* @@ -675,21 +734,10 @@ static bool __init ms_hyperv_x2apic_available(void) * pci-hyperv host bridge. * * Note: for a Hyper-V root partition, this will always return false. - * The hypervisor doesn't expose these HYPERV_CPUID_VIRT_STACK_* cpuids by - * default, they are implemented as intercepts by the Windows Hyper-V stack. - * Even a nested root partition (L2 root) will not get them because the - * nested (L1) hypervisor filters them out. */ 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; + return ms_hyperv.msi_ext_dest_id; } #ifdef CONFIG_AMD_MEM_ENCRYPT |