diff options
Diffstat (limited to 'tools/testing/selftests/kvm/lib/x86_64')
| -rw-r--r-- | tools/testing/selftests/kvm/lib/x86_64/hyperv.c | 46 | ||||
| -rw-r--r-- | tools/testing/selftests/kvm/lib/x86_64/memstress.c (renamed from tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c) | 37 | ||||
| -rw-r--r-- | tools/testing/selftests/kvm/lib/x86_64/processor.c | 314 | ||||
| -rw-r--r-- | tools/testing/selftests/kvm/lib/x86_64/ucall.c | 39 | ||||
| -rw-r--r-- | tools/testing/selftests/kvm/lib/x86_64/vmx.c | 56 |
5 files changed, 225 insertions, 267 deletions
diff --git a/tools/testing/selftests/kvm/lib/x86_64/hyperv.c b/tools/testing/selftests/kvm/lib/x86_64/hyperv.c new file mode 100644 index 000000000000..efb7e7a1354d --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/hyperv.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Hyper-V specific functions. + * + * Copyright (C) 2021, Red Hat Inc. + */ +#include <stdint.h> +#include "processor.h" +#include "hyperv.h" + +struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm, + vm_vaddr_t *p_hv_pages_gva) +{ + vm_vaddr_t hv_pages_gva = vm_vaddr_alloc_page(vm); + struct hyperv_test_pages *hv = addr_gva2hva(vm, hv_pages_gva); + + /* Setup of a region of guest memory for the VP Assist page. */ + hv->vp_assist = (void *)vm_vaddr_alloc_page(vm); + hv->vp_assist_hva = addr_gva2hva(vm, (uintptr_t)hv->vp_assist); + hv->vp_assist_gpa = addr_gva2gpa(vm, (uintptr_t)hv->vp_assist); + + /* Setup of a region of guest memory for the partition assist page. */ + hv->partition_assist = (void *)vm_vaddr_alloc_page(vm); + hv->partition_assist_hva = addr_gva2hva(vm, (uintptr_t)hv->partition_assist); + hv->partition_assist_gpa = addr_gva2gpa(vm, (uintptr_t)hv->partition_assist); + + /* Setup of a region of guest memory for the enlightened VMCS. */ + hv->enlightened_vmcs = (void *)vm_vaddr_alloc_page(vm); + hv->enlightened_vmcs_hva = addr_gva2hva(vm, (uintptr_t)hv->enlightened_vmcs); + hv->enlightened_vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)hv->enlightened_vmcs); + + *p_hv_pages_gva = hv_pages_gva; + return hv; +} + +int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist) +{ + uint64_t val = (vp_assist_pa & HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK) | + HV_X64_MSR_VP_ASSIST_PAGE_ENABLE; + + wrmsr(HV_X64_MSR_VP_ASSIST_PAGE, val); + + current_vp_assist = vp_assist; + + return 0; +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c b/tools/testing/selftests/kvm/lib/x86_64/memstress.c index 0f344a7c89c4..d61e623afc8c 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c +++ b/tools/testing/selftests/kvm/lib/x86_64/memstress.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * x86_64-specific extensions to perf_test_util.c. + * x86_64-specific extensions to memstress.c. * * Copyright (C) 2022, Google, Inc. */ @@ -11,25 +11,25 @@ #include "test_util.h" #include "kvm_util.h" -#include "perf_test_util.h" +#include "memstress.h" #include "processor.h" #include "vmx.h" -void perf_test_l2_guest_code(uint64_t vcpu_id) +void memstress_l2_guest_code(uint64_t vcpu_id) { - perf_test_guest_code(vcpu_id); + memstress_guest_code(vcpu_id); vmcall(); } -extern char perf_test_l2_guest_entry[]; +extern char memstress_l2_guest_entry[]; __asm__( -"perf_test_l2_guest_entry:" +"memstress_l2_guest_entry:" " mov (%rsp), %rdi;" -" call perf_test_l2_guest_code;" +" call memstress_l2_guest_code;" " ud2;" ); -static void perf_test_l1_guest_code(struct vmx_pages *vmx, uint64_t vcpu_id) +static void memstress_l1_guest_code(struct vmx_pages *vmx, uint64_t vcpu_id) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; @@ -42,14 +42,14 @@ static void perf_test_l1_guest_code(struct vmx_pages *vmx, uint64_t vcpu_id) rsp = &l2_guest_stack[L2_GUEST_STACK_SIZE - 1]; *rsp = vcpu_id; - prepare_vmcs(vmx, perf_test_l2_guest_entry, rsp); + prepare_vmcs(vmx, memstress_l2_guest_entry, rsp); GUEST_ASSERT(!vmlaunch()); GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); GUEST_DONE(); } -uint64_t perf_test_nested_pages(int nr_vcpus) +uint64_t memstress_nested_pages(int nr_vcpus) { /* * 513 page tables is enough to identity-map 256 TiB of L2 with 1G @@ -59,7 +59,7 @@ uint64_t perf_test_nested_pages(int nr_vcpus) return 513 + 10 * nr_vcpus; } -void perf_test_setup_ept(struct vmx_pages *vmx, struct kvm_vm *vm) +void memstress_setup_ept(struct vmx_pages *vmx, struct kvm_vm *vm) { uint64_t start, end; @@ -72,12 +72,12 @@ void perf_test_setup_ept(struct vmx_pages *vmx, struct kvm_vm *vm) */ nested_identity_map_1g(vmx, vm, 0, 0x100000000ULL); - start = align_down(perf_test_args.gpa, PG_SIZE_1G); - end = align_up(perf_test_args.gpa + perf_test_args.size, PG_SIZE_1G); + start = align_down(memstress_args.gpa, PG_SIZE_1G); + end = align_up(memstress_args.gpa + memstress_args.size, PG_SIZE_1G); nested_identity_map_1g(vmx, vm, start, end - start); } -void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[]) +void memstress_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[]) { struct vmx_pages *vmx, *vmx0 = NULL; struct kvm_regs regs; @@ -85,12 +85,13 @@ void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vc int vcpu_id; TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + TEST_REQUIRE(kvm_cpu_has_ept()); for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { vmx = vcpu_alloc_vmx(vm, &vmx_gva); if (vcpu_id == 0) { - perf_test_setup_ept(vmx, vm); + memstress_setup_ept(vmx, vm); vmx0 = vmx; } else { /* Share the same EPT table across all vCPUs. */ @@ -100,11 +101,11 @@ void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vc } /* - * Override the vCPU to run perf_test_l1_guest_code() which will - * bounce it into L2 before calling perf_test_guest_code(). + * Override the vCPU to run memstress_l1_guest_code() which will + * bounce it into L2 before calling memstress_guest_code(). */ vcpu_regs_get(vcpus[vcpu_id], ®s); - regs.rip = (unsigned long) perf_test_l1_guest_code; + regs.rip = (unsigned long) memstress_l1_guest_code; vcpu_regs_set(vcpus[vcpu_id], ®s); vcpu_args_set(vcpus[vcpu_id], 2, vmx_gva, vcpu_id); } diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 41c1c73c464d..c4d368d56cfe 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -131,23 +131,28 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm) } } -static void *virt_get_pte(struct kvm_vm *vm, uint64_t pt_pfn, uint64_t vaddr, - int level) +static void *virt_get_pte(struct kvm_vm *vm, uint64_t *parent_pte, + uint64_t vaddr, int level) { - uint64_t *page_table = addr_gpa2hva(vm, pt_pfn << vm->page_shift); + uint64_t pt_gpa = PTE_GET_PA(*parent_pte); + uint64_t *page_table = addr_gpa2hva(vm, pt_gpa); int index = (vaddr >> PG_LEVEL_SHIFT(level)) & 0x1ffu; + TEST_ASSERT((*parent_pte & PTE_PRESENT_MASK) || parent_pte == &vm->pgd, + "Parent PTE (level %d) not PRESENT for gva: 0x%08lx", + level + 1, vaddr); + return &page_table[index]; } static uint64_t *virt_create_upper_pte(struct kvm_vm *vm, - uint64_t pt_pfn, + uint64_t *parent_pte, uint64_t vaddr, uint64_t paddr, int current_level, int target_level) { - uint64_t *pte = virt_get_pte(vm, pt_pfn, vaddr, current_level); + uint64_t *pte = virt_get_pte(vm, parent_pte, vaddr, current_level); if (!(*pte & PTE_PRESENT_MASK)) { *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK; @@ -197,21 +202,20 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level) * Allocate upper level page tables, if not already present. Return * early if a hugepage was created. */ - pml4e = virt_create_upper_pte(vm, vm->pgd >> vm->page_shift, - vaddr, paddr, PG_LEVEL_512G, level); + pml4e = virt_create_upper_pte(vm, &vm->pgd, vaddr, paddr, PG_LEVEL_512G, level); if (*pml4e & PTE_LARGE_MASK) return; - pdpe = virt_create_upper_pte(vm, PTE_GET_PFN(*pml4e), vaddr, paddr, PG_LEVEL_1G, level); + pdpe = virt_create_upper_pte(vm, pml4e, vaddr, paddr, PG_LEVEL_1G, level); if (*pdpe & PTE_LARGE_MASK) return; - pde = virt_create_upper_pte(vm, PTE_GET_PFN(*pdpe), vaddr, paddr, PG_LEVEL_2M, level); + pde = virt_create_upper_pte(vm, pdpe, vaddr, paddr, PG_LEVEL_2M, level); if (*pde & PTE_LARGE_MASK) return; /* Fill in page table entry. */ - pte = virt_get_pte(vm, PTE_GET_PFN(*pde), vaddr, PG_LEVEL_4K); + pte = virt_get_pte(vm, pde, vaddr, PG_LEVEL_4K); TEST_ASSERT(!(*pte & PTE_PRESENT_MASK), "PTE already present for 4k page at vaddr: 0x%lx\n", vaddr); *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK); @@ -241,30 +245,25 @@ void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, } } -static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm, - struct kvm_vcpu *vcpu, - uint64_t vaddr) +static bool vm_is_target_pte(uint64_t *pte, int *level, int current_level) { - uint16_t index[4]; - uint64_t *pml4e, *pdpe, *pde; - uint64_t *pte; - struct kvm_sregs sregs; - uint64_t rsvd_mask = 0; + if (*pte & PTE_LARGE_MASK) { + TEST_ASSERT(*level == PG_LEVEL_NONE || + *level == current_level, + "Unexpected hugepage at level %d\n", current_level); + *level = current_level; + } - /* Set the high bits in the reserved mask. */ - if (vm->pa_bits < 52) - rsvd_mask = GENMASK_ULL(51, vm->pa_bits); + return *level == current_level; +} - /* - * SDM vol 3, fig 4-11 "Formats of CR3 and Paging-Structure Entries - * with 4-Level Paging and 5-Level Paging". - * If IA32_EFER.NXE = 0 and the P flag of a paging-structure entry is 1, - * the XD flag (bit 63) is reserved. - */ - vcpu_sregs_get(vcpu, &sregs); - if ((sregs.efer & EFER_NX) == 0) { - rsvd_mask |= PTE_NX_MASK; - } +uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr, + int *level) +{ + uint64_t *pml4e, *pdpe, *pde; + + TEST_ASSERT(*level >= PG_LEVEL_NONE && *level < PG_LEVEL_NUM, + "Invalid PG_LEVEL_* '%d'", *level); TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " "unknown or unsupported guest mode, mode: 0x%x", vm->mode); @@ -279,54 +278,26 @@ static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm, TEST_ASSERT(vaddr == (((int64_t)vaddr << 16) >> 16), "Canonical check failed. The virtual address is invalid."); - index[0] = (vaddr >> 12) & 0x1ffu; - index[1] = (vaddr >> 21) & 0x1ffu; - index[2] = (vaddr >> 30) & 0x1ffu; - index[3] = (vaddr >> 39) & 0x1ffu; - - pml4e = addr_gpa2hva(vm, vm->pgd); - TEST_ASSERT(pml4e[index[3]] & PTE_PRESENT_MASK, - "Expected pml4e to be present for gva: 0x%08lx", vaddr); - TEST_ASSERT((pml4e[index[3]] & (rsvd_mask | PTE_LARGE_MASK)) == 0, - "Unexpected reserved bits set."); - - pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size); - TEST_ASSERT(pdpe[index[2]] & PTE_PRESENT_MASK, - "Expected pdpe to be present for gva: 0x%08lx", vaddr); - TEST_ASSERT(!(pdpe[index[2]] & PTE_LARGE_MASK), - "Expected pdpe to map a pde not a 1-GByte page."); - TEST_ASSERT((pdpe[index[2]] & rsvd_mask) == 0, - "Unexpected reserved bits set."); + pml4e = virt_get_pte(vm, &vm->pgd, vaddr, PG_LEVEL_512G); + if (vm_is_target_pte(pml4e, level, PG_LEVEL_512G)) + return pml4e; - pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size); - TEST_ASSERT(pde[index[1]] & PTE_PRESENT_MASK, - "Expected pde to be present for gva: 0x%08lx", vaddr); - TEST_ASSERT(!(pde[index[1]] & PTE_LARGE_MASK), - "Expected pde to map a pte not a 2-MByte page."); - TEST_ASSERT((pde[index[1]] & rsvd_mask) == 0, - "Unexpected reserved bits set."); + pdpe = virt_get_pte(vm, pml4e, vaddr, PG_LEVEL_1G); + if (vm_is_target_pte(pdpe, level, PG_LEVEL_1G)) + return pdpe; - pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size); - TEST_ASSERT(pte[index[0]] & PTE_PRESENT_MASK, - "Expected pte to be present for gva: 0x%08lx", vaddr); + pde = virt_get_pte(vm, pdpe, vaddr, PG_LEVEL_2M); + if (vm_is_target_pte(pde, level, PG_LEVEL_2M)) + return pde; - return &pte[index[0]]; + return virt_get_pte(vm, pde, vaddr, PG_LEVEL_4K); } -uint64_t vm_get_page_table_entry(struct kvm_vm *vm, struct kvm_vcpu *vcpu, - uint64_t vaddr) +uint64_t *vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr) { - uint64_t *pte = _vm_get_page_table_entry(vm, vcpu, vaddr); + int level = PG_LEVEL_4K; - return *(uint64_t *)pte; -} - -void vm_set_page_table_entry(struct kvm_vm *vm, struct kvm_vcpu *vcpu, - uint64_t vaddr, uint64_t pte) -{ - uint64_t *new_pte = _vm_get_page_table_entry(vm, vcpu, vaddr); - - *(uint64_t *)new_pte = pte; + return __vm_get_page_table_entry(vm, vaddr, &level); } void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) @@ -512,47 +483,23 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector, vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) { - uint16_t index[4]; - uint64_t *pml4e, *pdpe, *pde; - uint64_t *pte; - - TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " - "unknown or unsupported guest mode, mode: 0x%x", vm->mode); - - index[0] = (gva >> 12) & 0x1ffu; - index[1] = (gva >> 21) & 0x1ffu; - index[2] = (gva >> 30) & 0x1ffu; - index[3] = (gva >> 39) & 0x1ffu; - - if (!vm->pgd_created) - goto unmapped_gva; - pml4e = addr_gpa2hva(vm, vm->pgd); - if (!(pml4e[index[3]] & PTE_PRESENT_MASK)) - goto unmapped_gva; - - pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size); - if (!(pdpe[index[2]] & PTE_PRESENT_MASK)) - goto unmapped_gva; - - pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size); - if (!(pde[index[1]] & PTE_PRESENT_MASK)) - goto unmapped_gva; + int level = PG_LEVEL_NONE; + uint64_t *pte = __vm_get_page_table_entry(vm, gva, &level); - pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size); - if (!(pte[index[0]] & PTE_PRESENT_MASK)) - goto unmapped_gva; + TEST_ASSERT(*pte & PTE_PRESENT_MASK, + "Leaf PTE not PRESENT for gva: 0x%08lx", gva); - return (PTE_GET_PFN(pte[index[0]]) * vm->page_size) + (gva & ~PAGE_MASK); - -unmapped_gva: - TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva); - exit(EXIT_FAILURE); + /* + * No need for a hugepage mask on the PTE, x86-64 requires the "unused" + * address bits to be zero. + */ + return PTE_GET_PA(*pte) | (gva & ~HUGEPAGE_MASK(level)); } static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt) { if (!vm->gdt) - vm->gdt = vm_vaddr_alloc_page(vm); + vm->gdt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); dt->base = vm->gdt; dt->limit = getpagesize(); @@ -562,7 +509,7 @@ static void kvm_setup_tss_64bit(struct kvm_vm *vm, struct kvm_segment *segp, int selector) { if (!vm->tss) - vm->tss = vm_vaddr_alloc_page(vm); + vm->tss = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); memset(segp, 0, sizeof(*segp)); segp->base = vm->tss; @@ -605,38 +552,9 @@ static void vcpu_setup(struct kvm_vm *vm, struct kvm_vcpu *vcpu) vcpu_sregs_set(vcpu, &sregs); } -void __vm_xsave_require_permission(int bit, const char *name) +void kvm_arch_vm_post_create(struct kvm_vm *vm) { - int kvm_fd; - u64 bitmask; - long rc; - struct kvm_device_attr attr = { - .group = 0, - .attr = KVM_X86_XCOMP_GUEST_SUPP, - .addr = (unsigned long) &bitmask - }; - - TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XFD)); - - kvm_fd = open_kvm_dev_path_or_exit(); - rc = __kvm_ioctl(kvm_fd, KVM_GET_DEVICE_ATTR, &attr); - close(kvm_fd); - - if (rc == -1 && (errno == ENXIO || errno == EINVAL)) - __TEST_REQUIRE(0, "KVM_X86_XCOMP_GUEST_SUPP not supported"); - - TEST_ASSERT(rc == 0, "KVM_GET_DEVICE_ATTR(0, KVM_X86_XCOMP_GUEST_SUPP) error: %ld", rc); - - __TEST_REQUIRE(bitmask & (1ULL << bit), - "Required XSAVE feature '%s' not supported", name); - - TEST_REQUIRE(!syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, bit)); - - rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_GUEST_PERM, &bitmask); - TEST_ASSERT(rc == 0, "prctl(ARCH_GET_XCOMP_GUEST_PERM) error: %ld", rc); - TEST_ASSERT(bitmask & (1ULL << bit), - "prctl(ARCH_REQ_XCOMP_GUEST_PERM) failure bitmask=0x%lx", - bitmask); + vm_create_irqchip(vm); } struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, @@ -647,8 +565,9 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, vm_vaddr_t stack_vaddr; struct kvm_vcpu *vcpu; - stack_vaddr = vm_vaddr_alloc(vm, DEFAULT_STACK_PGS * getpagesize(), - DEFAULT_GUEST_STACK_VADDR_MIN); + stack_vaddr = __vm_vaddr_alloc(vm, DEFAULT_STACK_PGS * getpagesize(), + DEFAULT_GUEST_STACK_VADDR_MIN, + MEM_REGION_DATA); vcpu = __vm_vcpu_add(vm, vcpu_id); vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid()); @@ -683,25 +602,29 @@ void vcpu_arch_free(struct kvm_vcpu *vcpu) free(vcpu->cpuid); } +/* Do not use kvm_supported_cpuid directly except for validity checks. */ +static void *kvm_supported_cpuid; + const struct kvm_cpuid2 *kvm_get_supported_cpuid(void) { - static struct kvm_cpuid2 *cpuid; int kvm_fd; - if (cpuid) - return cpuid; + if (kvm_supported_cpuid) + return kvm_supported_cpuid; - cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES); + kvm_supported_cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES); kvm_fd = open_kvm_dev_path_or_exit(); - kvm_ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid); + kvm_ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, + (struct kvm_cpuid2 *)kvm_supported_cpuid); close(kvm_fd); - return cpuid; + return kvm_supported_cpuid; } -bool kvm_cpuid_has(const struct kvm_cpuid2 *cpuid, - struct kvm_x86_cpu_feature feature) +static uint32_t __kvm_cpu_has(const struct kvm_cpuid2 *cpuid, + uint32_t function, uint32_t index, + uint8_t reg, uint8_t lo, uint8_t hi) { const struct kvm_cpuid_entry2 *entry; int i; @@ -714,12 +637,25 @@ bool kvm_cpuid_has(const struct kvm_cpuid2 *cpuid, * order, but kvm_x86_cpu_feature matches that mess, so yay * pointer shenanigans! */ - if (entry->function == feature.function && - entry->index == feature.index) - return (&entry->eax)[feature.reg] & BIT(feature.bit); + if (entry->function == function && entry->index == index) + return ((&entry->eax)[reg] & GENMASK(hi, lo)) >> lo; } - return false; + return 0; +} + +bool kvm_cpuid_has(const struct kvm_cpuid2 *cpuid, + struct kvm_x86_cpu_feature feature) +{ + return __kvm_cpu_has(cpuid, feature.function, feature.index, + feature.reg, feature.bit, feature.bit); +} + +uint32_t kvm_cpuid_property(const struct kvm_cpuid2 *cpuid, + struct kvm_x86_cpu_property property) +{ + return __kvm_cpu_has(cpuid, property.function, property.index, + property.reg, property.lo_bit, property.hi_bit); } uint64_t kvm_get_feature_msr(uint64_t msr_index) @@ -741,6 +677,41 @@ uint64_t kvm_get_feature_msr(uint64_t msr_index) return buffer.entry.data; } +void __vm_xsave_require_permission(int bit, const char *name) +{ + int kvm_fd; + u64 bitmask; + long rc; + struct kvm_device_attr attr = { + .group = 0, + .attr = KVM_X86_XCOMP_GUEST_SUPP, + .addr = (unsigned long) &bitmask + }; + + TEST_ASSERT(!kvm_supported_cpuid, + "kvm_get_supported_cpuid() cannot be used before ARCH_REQ_XCOMP_GUEST_PERM"); + + kvm_fd = open_kvm_dev_path_or_exit(); + rc = __kvm_ioctl(kvm_fd, KVM_GET_DEVICE_ATTR, &attr); + close(kvm_fd); + + if (rc == -1 && (errno == ENXIO || errno == EINVAL)) + __TEST_REQUIRE(0, "KVM_X86_XCOMP_GUEST_SUPP not supported"); + + TEST_ASSERT(rc == 0, "KVM_GET_DEVICE_ATTR(0, KVM_X86_XCOMP_GUEST_SUPP) error: %ld", rc); + + __TEST_REQUIRE(bitmask & (1ULL << bit), + "Required XSAVE feature '%s' not supported", name); + + TEST_REQUIRE(!syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, bit)); + + rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_GUEST_PERM, &bitmask); + TEST_ASSERT(rc == 0, "prctl(ARCH_GET_XCOMP_GUEST_PERM) error: %ld", rc); + TEST_ASSERT(bitmask & (1ULL << bit), + "prctl(ARCH_REQ_XCOMP_GUEST_PERM) failure bitmask=0x%lx", + bitmask); +} + void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid) { TEST_ASSERT(cpuid != vcpu->cpuid, "@cpuid can't be the vCPU's CPUID"); @@ -1059,18 +1030,12 @@ bool is_amd_cpu(void) void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) { - const struct kvm_cpuid_entry2 *entry; - bool pae; - - /* SDM 4.1.4 */ - if (kvm_get_cpuid_max_extended() < 0x80000008) { - pae = kvm_get_supported_cpuid_entry(1)->edx & (1 << 6); - *pa_bits = pae ? 36 : 32; + if (!kvm_cpu_has_p(X86_PROPERTY_MAX_PHY_ADDR)) { + *pa_bits == kvm_cpu_has(X86_FEATURE_PAE) ? 36 : 32; *va_bits = 32; } else { - entry = kvm_get_supported_cpuid_entry(0x80000008); - *pa_bits = entry->eax & 0xff; - *va_bits = (entry->eax >> 8) & 0xff; + *pa_bits = kvm_cpu_property(X86_PROPERTY_MAX_PHY_ADDR); + *va_bits = kvm_cpu_property(X86_PROPERTY_MAX_VIRT_ADDR); } } @@ -1103,6 +1068,7 @@ static bool kvm_fixup_exception(struct ex_regs *regs) regs->rip = regs->r11; regs->r9 = regs->vector; + regs->r10 = regs->error_code; return true; } @@ -1132,8 +1098,8 @@ void vm_init_descriptor_tables(struct kvm_vm *vm) extern void *idt_handlers; int i; - vm->idt = vm_vaddr_alloc_page(vm); - vm->handlers = vm_vaddr_alloc_page(vm); + vm->idt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); + vm->handlers = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); /* Handlers have the same address in both address spaces.*/ for (i = 0; i < NUM_INTERRUPTS; i++) set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0, @@ -1265,7 +1231,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) { const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */ unsigned long ht_gfn, max_gfn, max_pfn; - uint32_t eax, ebx, ecx, edx, max_ext_leaf; + uint8_t maxphyaddr; max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1; @@ -1279,8 +1245,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) /* Before family 17h, the HyperTransport area is just below 1T. */ ht_gfn = (1 << 28) - num_ht_pages; - cpuid(1, &eax, &ebx, &ecx, &edx); - if (x86_family(eax) < 0x17) + if (this_cpu_family() < 0x17) goto done; /* @@ -1288,17 +1253,14 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) * reduced due to SME by bits 11:6 of CPUID[0x8000001f].EBX. Use * the old conservative value if MAXPHYADDR is not enumerated. */ - cpuid(0x80000000, &eax, &ebx, &ecx, &edx); - max_ext_leaf = eax; - if (max_ext_leaf < 0x80000008) + if (!this_cpu_has_p(X86_PROPERTY_MAX_PHY_ADDR)) goto done; - cpuid(0x80000008, &eax, &ebx, &ecx, &edx); - max_pfn = (1ULL << ((eax & 0xff) - vm->page_shift)) - 1; - if (max_ext_leaf >= 0x8000001f) { - cpuid(0x8000001f, &eax, &ebx, &ecx, &edx); - max_pfn >>= (ebx >> 6) & 0x3f; - } + maxphyaddr = this_cpu_property(X86_PROPERTY_MAX_PHY_ADDR); + max_pfn = (1ULL << (maxphyaddr - vm->page_shift)) - 1; + + if (this_cpu_has_p(X86_PROPERTY_PHYS_ADDR_REDUCTION)) + max_pfn >>= this_cpu_property(X86_PROPERTY_PHYS_ADDR_REDUCTION); ht_gfn = max_pfn - num_ht_pages; done: diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86_64/ucall.c index e5f0f9e0d3ee..4d41dc63cc9e 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/ucall.c +++ b/tools/testing/selftests/kvm/lib/x86_64/ucall.c @@ -8,52 +8,25 @@ #define UCALL_PIO_PORT ((uint16_t)0x1000) -void ucall_init(struct kvm_vm *vm, void *arg) +void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) { } -void ucall_uninit(struct kvm_vm *vm) +void ucall_arch_do_ucall(vm_vaddr_t uc) { -} - -void ucall(uint64_t cmd, int nargs, ...) -{ - struct ucall uc = { - .cmd = cmd, - }; - va_list va; - int i; - - nargs = min(nargs, UCALL_MAX_ARGS); - - va_start(va, nargs); - for (i = 0; i < nargs; ++i) - uc.args[i] = va_arg(va, uint64_t); - va_end(va); - asm volatile("in %[port], %%al" - : : [port] "d" (UCALL_PIO_PORT), "D" (&uc) : "rax", "memory"); + : : [port] "d" (UCALL_PIO_PORT), "D" (uc) : "rax", "memory"); } -uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc) +void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; - struct ucall ucall = {}; - - if (uc) - memset(uc, 0, sizeof(*uc)); if (run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) { struct kvm_regs regs; vcpu_regs_get(vcpu, ®s); - memcpy(&ucall, addr_gva2hva(vcpu->vm, (vm_vaddr_t)regs.rdi), - sizeof(ucall)); - - vcpu_run_complete_io(vcpu); - if (uc) - memcpy(uc, &ucall, sizeof(ucall)); + return (void *)regs.rdi; } - - return ucall.cmd; + return NULL; } diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index d21049c38fc5..59d97531c9b1 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -109,18 +109,6 @@ vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva) vmx->vmwrite_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmwrite); memset(vmx->vmwrite_hva, 0, getpagesize()); - /* Setup of a region of guest memory for the VP Assist page. */ - vmx->vp_assist = (void *)vm_vaddr_alloc_page(vm); - vmx->vp_assist_hva = addr_gva2hva(vm, (uintptr_t)vmx->vp_assist); - vmx->vp_assist_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vp_assist); - - /* Setup of a region of guest memory for the enlightened VMCS. */ - vmx->enlightened_vmcs = (void *)vm_vaddr_alloc_page(vm); - vmx->enlightened_vmcs_hva = - addr_gva2hva(vm, (uintptr_t)vmx->enlightened_vmcs); - vmx->enlightened_vmcs_gpa = - addr_gva2gpa(vm, (uintptr_t)vmx->enlightened_vmcs); - *p_vmx_gva = vmx_gva; return vmx; } @@ -171,26 +159,18 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx) bool load_vmcs(struct vmx_pages *vmx) { - if (!enable_evmcs) { - /* Load a VMCS. */ - *(uint32_t *)(vmx->vmcs) = vmcs_revision(); - if (vmclear(vmx->vmcs_gpa)) - return false; - - if (vmptrld(vmx->vmcs_gpa)) - return false; - - /* Setup shadow VMCS, do not load it yet. */ - *(uint32_t *)(vmx->shadow_vmcs) = - vmcs_revision() | 0x80000000ul; - if (vmclear(vmx->shadow_vmcs_gpa)) - return false; - } else { - if (evmcs_vmptrld(vmx->enlightened_vmcs_gpa, - vmx->enlightened_vmcs)) - return false; - current_evmcs->revision_id = EVMCS_VERSION; - } + /* Load a VMCS. */ + *(uint32_t *)(vmx->vmcs) = vmcs_revision(); + if (vmclear(vmx->vmcs_gpa)) + return false; + + if (vmptrld(vmx->vmcs_gpa)) + return false; + + /* Setup shadow VMCS, do not load it yet. */ + *(uint32_t *)(vmx->shadow_vmcs) = vmcs_revision() | 0x80000000ul; + if (vmclear(vmx->shadow_vmcs_gpa)) + return false; return true; } @@ -544,26 +524,22 @@ void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm, __nested_map(vmx, vm, addr, addr, size, PG_LEVEL_1G); } -bool kvm_vm_has_ept(struct kvm_vm *vm) +bool kvm_cpu_has_ept(void) { - struct kvm_vcpu *vcpu; uint64_t ctrl; - vcpu = list_first_entry(&vm->vcpus, struct kvm_vcpu, list); - TEST_ASSERT(vcpu, "Cannot determine EPT support without vCPUs.\n"); - - ctrl = vcpu_get_msr(vcpu, MSR_IA32_VMX_TRUE_PROCBASED_CTLS) >> 32; + ctrl = kvm_get_feature_msr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS) >> 32; if (!(ctrl & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) return false; - ctrl = vcpu_get_msr(vcpu, MSR_IA32_VMX_PROCBASED_CTLS2) >> 32; + ctrl = kvm_get_feature_msr(MSR_IA32_VMX_PROCBASED_CTLS2) >> 32; return ctrl & SECONDARY_EXEC_ENABLE_EPT; } void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm, uint32_t eptp_memslot) { - TEST_REQUIRE(kvm_vm_has_ept(vm)); + TEST_ASSERT(kvm_cpu_has_ept(), "KVM doesn't support nested EPT"); vmx->eptp = (void *)vm_vaddr_alloc_page(vm); vmx->eptp_hva = addr_gva2hva(vm, (uintptr_t)vmx->eptp); |