Group the code this way so that we can avoid too many ifdef's: Data only used in an SNP VM with the paravisor; Functions only used in an SNP VM with the paravisor; Data only used in an SNP VM without the paravisor; Functions only used in an SNP VM without the paravisor; Functions only used in a TDX VM, with and without the paravisor; Functions used in an SNP or TDX VM, when the paravisor is present; Functions always used, even in a regular non-CoCo VM. No functional change. Signed-off-by: Dexuan Cui <decui@xxxxxxxxxxxxx> --- This patch appears the first time in v3. arch/x86/hyperv/ivm.c | 309 ++++++++++++++++++++---------------------- 1 file changed, 150 insertions(+), 159 deletions(-) diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 3d48f823582c..8fb3b28670e9 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -30,9 +30,6 @@ #define GHCB_USAGE_HYPERV_CALL 1 -static u8 ap_start_input_arg[PAGE_SIZE] __bss_decrypted __aligned(PAGE_SIZE); -static u8 ap_start_stack[PAGE_SIZE] __aligned(PAGE_SIZE); - union hv_ghcb { struct ghcb ghcb; struct { @@ -66,10 +63,10 @@ union hv_ghcb { } hypercall; } __packed __aligned(HV_HYP_PAGE_SIZE); -static DEFINE_PER_CPU(struct sev_es_save_area *, hv_sev_vmsa); - +/* Only used in an SNP VM with the paravisor */ static u16 hv_ghcb_version __ro_after_init; +/* Functions only used in an SNP VM with the paravisor go here. */ u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size) { union hv_ghcb *hv_ghcb; @@ -247,6 +244,140 @@ static void hv_ghcb_msr_read(u64 msr, u64 *value) local_irq_restore(flags); } +/* Only used in a fully enlightened SNP VM, i.e. without the paravisor */ +static u8 ap_start_input_arg[PAGE_SIZE] __bss_decrypted __aligned(PAGE_SIZE); +static u8 ap_start_stack[PAGE_SIZE] __aligned(PAGE_SIZE); +static DEFINE_PER_CPU(struct sev_es_save_area *, hv_sev_vmsa); + +/* Functions only used in an SNP VM without the paravisor go here. */ + +#define hv_populate_vmcb_seg(seg, gdtr_base) \ +do { \ + if (seg.selector) { \ + seg.base = 0; \ + seg.limit = HV_AP_SEGMENT_LIMIT; \ + seg.attrib = *(u16 *)(gdtr_base + seg.selector + 5); \ + seg.attrib = (seg.attrib & 0xFF) | ((seg.attrib >> 4) & 0xF00); \ + } \ +} while (0) \ + +static int snp_set_vmsa(void *va, bool vmsa) +{ + u64 attrs; + + /* + * Running at VMPL0 allows the kernel to change the VMSA bit for a page + * using the RMPADJUST instruction. However, for the instruction to + * succeed it must target the permissions of a lesser privileged + * (higher numbered) VMPL level, so use VMPL1 (refer to the RMPADJUST + * instruction in the AMD64 APM Volume 3). + */ + attrs = 1; + if (vmsa) + attrs |= RMPADJUST_VMSA_PAGE_BIT; + + return rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs); +} + +static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa) +{ + int err; + + err = snp_set_vmsa(vmsa, false); + if (err) + pr_err("clear VMSA page failed (%u), leaking page\n", err); + else + free_page((unsigned long)vmsa); +} + +int hv_snp_boot_ap(int cpu, unsigned long start_ip) +{ + struct sev_es_save_area *vmsa = (struct sev_es_save_area *) + __get_free_page(GFP_KERNEL | __GFP_ZERO); + struct sev_es_save_area *cur_vmsa; + struct desc_ptr gdtr; + u64 ret, retry = 5; + struct hv_enable_vp_vtl *start_vp_input; + unsigned long flags; + + if (!vmsa) + return -ENOMEM; + + native_store_gdt(&gdtr); + + vmsa->gdtr.base = gdtr.address; + vmsa->gdtr.limit = gdtr.size; + + asm volatile("movl %%es, %%eax;" : "=a" (vmsa->es.selector)); + hv_populate_vmcb_seg(vmsa->es, vmsa->gdtr.base); + + asm volatile("movl %%cs, %%eax;" : "=a" (vmsa->cs.selector)); + hv_populate_vmcb_seg(vmsa->cs, vmsa->gdtr.base); + + asm volatile("movl %%ss, %%eax;" : "=a" (vmsa->ss.selector)); + hv_populate_vmcb_seg(vmsa->ss, vmsa->gdtr.base); + + asm volatile("movl %%ds, %%eax;" : "=a" (vmsa->ds.selector)); + hv_populate_vmcb_seg(vmsa->ds, vmsa->gdtr.base); + + vmsa->efer = native_read_msr(MSR_EFER); + + asm volatile("movq %%cr4, %%rax;" : "=a" (vmsa->cr4)); + asm volatile("movq %%cr3, %%rax;" : "=a" (vmsa->cr3)); + asm volatile("movq %%cr0, %%rax;" : "=a" (vmsa->cr0)); + + vmsa->xcr0 = 1; + vmsa->g_pat = HV_AP_INIT_GPAT_DEFAULT; + vmsa->rip = (u64)secondary_startup_64_no_verify; + vmsa->rsp = (u64)&ap_start_stack[PAGE_SIZE]; + + /* + * Set the SNP-specific fields for this VMSA: + * VMPL level + * SEV_FEATURES (matches the SEV STATUS MSR right shifted 2 bits) + */ + vmsa->vmpl = 0; + vmsa->sev_features = sev_status >> 2; + + ret = snp_set_vmsa(vmsa, true); + if (!ret) { + pr_err("RMPADJUST(%llx) failed: %llx\n", (u64)vmsa, ret); + free_page((u64)vmsa); + return ret; + } + + local_irq_save(flags); + start_vp_input = (struct hv_enable_vp_vtl *)ap_start_input_arg; + memset(start_vp_input, 0, sizeof(*start_vp_input)); + start_vp_input->partition_id = -1; + start_vp_input->vp_index = cpu; + start_vp_input->target_vtl.target_vtl = ms_hyperv.vtl; + *(u64 *)&start_vp_input->vp_context = __pa(vmsa) | 1; + + do { + ret = hv_do_hypercall(HVCALL_START_VP, + start_vp_input, NULL); + } while (hv_result(ret) == HV_STATUS_TIME_OUT && retry--); + + local_irq_restore(flags); + + if (!hv_result_success(ret)) { + pr_err("HvCallStartVirtualProcessor failed: %llx\n", ret); + snp_cleanup_vmsa(vmsa); + vmsa = NULL; + } + + cur_vmsa = per_cpu(hv_sev_vmsa, cpu); + /* Free up any previous VMSA page */ + if (cur_vmsa) + snp_cleanup_vmsa(cur_vmsa); + + /* Record the current VMSA page */ + per_cpu(hv_sev_vmsa, cpu) = vmsa; + + return ret; +} + #else static inline void hv_ghcb_msr_write(u64 msr, u64 value) {} static inline void hv_ghcb_msr_read(u64 msr, u64 *value) {} @@ -282,6 +413,20 @@ static void hv_tdx_msr_read(u64 msr, u64 *val) else *val = args.r11; } + +u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2) +{ + struct tdx_hypercall_args args = { }; + + args.r10 = control; + args.rdx = param1; + args.r8 = param2; + + (void)__tdx_hypercall_ret(&args); + + return args.r11; +} + #else static inline void hv_tdx_msr_write(u64 msr, u64 value) {} static inline void hv_tdx_msr_read(u64 msr, u64 *value) {} @@ -309,9 +454,7 @@ void hv_ivm_msr_read(u64 msr, u64 *value) else if (hv_isolation_type_snp()) hv_ghcb_msr_read(msr, value); } -#endif -#if defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST) /* * hv_mark_gpa_visibility - Set pages visible to host via hvcall. * @@ -432,141 +575,6 @@ static bool hv_is_private_mmio(u64 addr) return false; } -#endif /* defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST) */ - -#ifdef CONFIG_AMD_MEM_ENCRYPT - -#define hv_populate_vmcb_seg(seg, gdtr_base) \ -do { \ - if (seg.selector) { \ - seg.base = 0; \ - seg.limit = HV_AP_SEGMENT_LIMIT; \ - seg.attrib = *(u16 *)(gdtr_base + seg.selector + 5); \ - seg.attrib = (seg.attrib & 0xFF) | ((seg.attrib >> 4) & 0xF00); \ - } \ -} while (0) \ - -static int snp_set_vmsa(void *va, bool vmsa) -{ - u64 attrs; - - /* - * Running at VMPL0 allows the kernel to change the VMSA bit for a page - * using the RMPADJUST instruction. However, for the instruction to - * succeed it must target the permissions of a lesser privileged - * (higher numbered) VMPL level, so use VMPL1 (refer to the RMPADJUST - * instruction in the AMD64 APM Volume 3). - */ - attrs = 1; - if (vmsa) - attrs |= RMPADJUST_VMSA_PAGE_BIT; - - return rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs); -} - -static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa) -{ - int err; - - err = snp_set_vmsa(vmsa, false); - if (err) - pr_err("clear VMSA page failed (%u), leaking page\n", err); - else - free_page((unsigned long)vmsa); -} - -int hv_snp_boot_ap(int cpu, unsigned long start_ip) -{ - struct sev_es_save_area *vmsa = (struct sev_es_save_area *) - __get_free_page(GFP_KERNEL | __GFP_ZERO); - struct sev_es_save_area *cur_vmsa; - struct desc_ptr gdtr; - u64 ret, retry = 5; - struct hv_enable_vp_vtl *start_vp_input; - unsigned long flags; - - if (!vmsa) - return -ENOMEM; - - native_store_gdt(&gdtr); - - vmsa->gdtr.base = gdtr.address; - vmsa->gdtr.limit = gdtr.size; - - asm volatile("movl %%es, %%eax;" : "=a" (vmsa->es.selector)); - hv_populate_vmcb_seg(vmsa->es, vmsa->gdtr.base); - - asm volatile("movl %%cs, %%eax;" : "=a" (vmsa->cs.selector)); - hv_populate_vmcb_seg(vmsa->cs, vmsa->gdtr.base); - - asm volatile("movl %%ss, %%eax;" : "=a" (vmsa->ss.selector)); - hv_populate_vmcb_seg(vmsa->ss, vmsa->gdtr.base); - - asm volatile("movl %%ds, %%eax;" : "=a" (vmsa->ds.selector)); - hv_populate_vmcb_seg(vmsa->ds, vmsa->gdtr.base); - - vmsa->efer = native_read_msr(MSR_EFER); - - asm volatile("movq %%cr4, %%rax;" : "=a" (vmsa->cr4)); - asm volatile("movq %%cr3, %%rax;" : "=a" (vmsa->cr3)); - asm volatile("movq %%cr0, %%rax;" : "=a" (vmsa->cr0)); - - vmsa->xcr0 = 1; - vmsa->g_pat = HV_AP_INIT_GPAT_DEFAULT; - vmsa->rip = (u64)secondary_startup_64_no_verify; - vmsa->rsp = (u64)&ap_start_stack[PAGE_SIZE]; - - /* - * Set the SNP-specific fields for this VMSA: - * VMPL level - * SEV_FEATURES (matches the SEV STATUS MSR right shifted 2 bits) - */ - vmsa->vmpl = 0; - vmsa->sev_features = sev_status >> 2; - - ret = snp_set_vmsa(vmsa, true); - if (!ret) { - pr_err("RMPADJUST(%llx) failed: %llx\n", (u64)vmsa, ret); - free_page((u64)vmsa); - return ret; - } - - local_irq_save(flags); - start_vp_input = (struct hv_enable_vp_vtl *)ap_start_input_arg; - memset(start_vp_input, 0, sizeof(*start_vp_input)); - start_vp_input->partition_id = -1; - start_vp_input->vp_index = cpu; - start_vp_input->target_vtl.target_vtl = ms_hyperv.vtl; - *(u64 *)&start_vp_input->vp_context = __pa(vmsa) | 1; - - do { - ret = hv_do_hypercall(HVCALL_START_VP, - start_vp_input, NULL); - } while (hv_result(ret) == HV_STATUS_TIME_OUT && retry--); - - local_irq_restore(flags); - - if (!hv_result_success(ret)) { - pr_err("HvCallStartVirtualProcessor failed: %llx\n", ret); - snp_cleanup_vmsa(vmsa); - vmsa = NULL; - } - - cur_vmsa = per_cpu(hv_sev_vmsa, cpu); - /* Free up any previous VMSA page */ - if (cur_vmsa) - snp_cleanup_vmsa(cur_vmsa); - - /* Record the current VMSA page */ - per_cpu(hv_sev_vmsa, cpu) = vmsa; - - return ret; -} - -#endif /* CONFIG_AMD_MEM_ENCRYPT */ - -#if defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST) - void __init hv_vtom_init(void) { enum hv_isolation_type type = hv_get_isolation_type(); @@ -654,20 +662,3 @@ bool hv_isolation_type_tdx(void) { return static_branch_unlikely(&isolation_type_tdx); } - -#ifdef CONFIG_INTEL_TDX_GUEST - -u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2) -{ - struct tdx_hypercall_args args = { }; - - args.r10 = control; - args.rdx = param1; - args.r8 = param2; - - (void)__tdx_hypercall_ret(&args); - - return args.r11; -} - -#endif -- 2.25.1