diff options
Diffstat (limited to 'tools/testing/selftests/kvm')
24 files changed, 3852 insertions, 614 deletions
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 63fc1ab9248f..6210ba41c29e 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,3 +1,8 @@ -set_sregs_test -sync_regs_test -vmx_tsc_adjust_test +/x86_64/cr4_cpuid_sync_test +/x86_64/evmcs_test +/x86_64/platform_info_test +/x86_64/set_sregs_test +/x86_64/sync_regs_test +/x86_64/vmx_tsc_adjust_test +/x86_64/state_test +/dirty_log_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index d9d00319b07c..01a219229238 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -1,21 +1,31 @@ all: -top_srcdir = ../../../../ +top_srcdir = ../../../.. UNAME_M := $(shell uname -m) -LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c -LIBKVM_x86_64 = lib/x86.c lib/vmx.c +LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/ucall.c lib/sparsebit.c +LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c +LIBKVM_aarch64 = lib/aarch64/processor.c -TEST_GEN_PROGS_x86_64 = set_sregs_test -TEST_GEN_PROGS_x86_64 += sync_regs_test -TEST_GEN_PROGS_x86_64 += vmx_tsc_adjust_test +TEST_GEN_PROGS_x86_64 = x86_64/platform_info_test +TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test +TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test +TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test +TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test +TEST_GEN_PROGS_x86_64 += x86_64/state_test +TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test +TEST_GEN_PROGS_x86_64 += dirty_log_test + +TEST_GEN_PROGS_aarch64 += dirty_log_test TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M)) LIBKVM += $(LIBKVM_$(UNAME_M)) INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ -CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I.. +LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include +CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I.. +LDFLAGS += -pthread # After inclusion, $(OUTPUT) is defined and # $(TEST_GEN_PROGS) starts with $(OUTPUT)/ @@ -23,7 +33,7 @@ include ../lib.mk STATIC_LIBS := $(OUTPUT)/libkvm.a LIBKVM_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM)) -EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS) +EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS) cscope.* x := $(shell mkdir -p $(sort $(dir $(LIBKVM_OBJ)))) $(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c @@ -32,9 +42,15 @@ $(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ) $(AR) crs $@ $^ -$(LINUX_HDR_PATH): - make -C $(top_srcdir) headers_install - -all: $(STATIC_LIBS) $(LINUX_HDR_PATH) +all: $(STATIC_LIBS) $(TEST_GEN_PROGS): $(STATIC_LIBS) -$(TEST_GEN_PROGS) $(LIBKVM_OBJ): | $(LINUX_HDR_PATH) +$(STATIC_LIBS):| khdr + +cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib .. +cscope: + $(RM) cscope.* + (find $(include_paths) -name '*.h' \ + -exec realpath --relative-base=$(PWD) {} \;; \ + find . -name '*.c' \ + -exec realpath --relative-base=$(PWD) {} \;) | sort -u > cscope.files + cscope -b diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c new file mode 100644 index 000000000000..aeff95a91b15 --- /dev/null +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -0,0 +1,448 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KVM dirty page logging test + * + * Copyright (C) 2018, Red Hat, Inc. + */ + +#define _GNU_SOURCE /* for program_invocation_name */ + +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <time.h> +#include <pthread.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +#define DEBUG printf + +#define VCPU_ID 1 + +/* The memory slot index to track dirty pages */ +#define TEST_MEM_SLOT_INDEX 1 + +/* Default guest test memory offset, 1G */ +#define DEFAULT_GUEST_TEST_MEM 0x40000000 + +/* How many pages to dirty for each guest loop */ +#define TEST_PAGES_PER_LOOP 1024 + +/* How many host loops to run (one KVM_GET_DIRTY_LOG for each loop) */ +#define TEST_HOST_LOOP_N 32UL + +/* Interval for each host loop (ms) */ +#define TEST_HOST_LOOP_INTERVAL 10UL + +/* + * Guest/Host shared variables. Ensure addr_gva2hva() and/or + * sync_global_to/from_guest() are used when accessing from + * the host. READ/WRITE_ONCE() should also be used with anything + * that may change. + */ +static uint64_t host_page_size; +static uint64_t guest_page_size; +static uint64_t guest_num_pages; +static uint64_t random_array[TEST_PAGES_PER_LOOP]; +static uint64_t iteration; + +/* + * GPA offset of the testing memory slot. Must be bigger than + * DEFAULT_GUEST_PHY_PAGES. + */ +static uint64_t guest_test_mem = DEFAULT_GUEST_TEST_MEM; + +/* + * Continuously write to the first 8 bytes of a random pages within + * the testing memory region. + */ +static void guest_code(void) +{ + int i; + + while (true) { + for (i = 0; i < TEST_PAGES_PER_LOOP; i++) { + uint64_t addr = guest_test_mem; + addr += (READ_ONCE(random_array[i]) % guest_num_pages) + * guest_page_size; + addr &= ~(host_page_size - 1); + *(uint64_t *)addr = READ_ONCE(iteration); + } + + /* Tell the host that we need more random numbers */ + GUEST_SYNC(1); + } +} + +/* Host variables */ +static bool host_quit; + +/* Points to the test VM memory region on which we track dirty logs */ +static void *host_test_mem; +static uint64_t host_num_pages; + +/* For statistics only */ +static uint64_t host_dirty_count; +static uint64_t host_clear_count; +static uint64_t host_track_next_count; + +/* + * We use this bitmap to track some pages that should have its dirty + * bit set in the _next_ iteration. For example, if we detected the + * page value changed to current iteration but at the same time the + * page bit is cleared in the latest bitmap, then the system must + * report that write in the next get dirty log call. + */ +static unsigned long *host_bmap_track; + +static void generate_random_array(uint64_t *guest_array, uint64_t size) +{ + uint64_t i; + + for (i = 0; i < size; i++) + guest_array[i] = random(); +} + +static void *vcpu_worker(void *data) +{ + int ret; + struct kvm_vm *vm = data; + uint64_t *guest_array; + uint64_t pages_count = 0; + struct kvm_run *run; + struct ucall uc; + + run = vcpu_state(vm, VCPU_ID); + + guest_array = addr_gva2hva(vm, (vm_vaddr_t)random_array); + generate_random_array(guest_array, TEST_PAGES_PER_LOOP); + + while (!READ_ONCE(host_quit)) { + /* Let the guest dirty the random pages */ + ret = _vcpu_run(vm, VCPU_ID); + if (get_ucall(vm, VCPU_ID, &uc) == UCALL_SYNC) { + pages_count += TEST_PAGES_PER_LOOP; + generate_random_array(guest_array, TEST_PAGES_PER_LOOP); + } else { + TEST_ASSERT(false, + "Invalid guest sync status: " + "exit_reason=%s\n", + exit_reason_str(run->exit_reason)); + } + } + + DEBUG("Dirtied %"PRIu64" pages\n", pages_count); + + return NULL; +} + +static void vm_dirty_log_verify(unsigned long *bmap) +{ + uint64_t page; + uint64_t *value_ptr; + uint64_t step = host_page_size >= guest_page_size ? 1 : + guest_page_size / host_page_size; + + for (page = 0; page < host_num_pages; page += step) { + value_ptr = host_test_mem + page * host_page_size; + + /* If this is a special page that we were tracking... */ + if (test_and_clear_bit(page, host_bmap_track)) { + host_track_next_count++; + TEST_ASSERT(test_bit(page, bmap), + "Page %"PRIu64" should have its dirty bit " + "set in this iteration but it is missing", + page); + } + + if (test_bit(page, bmap)) { + host_dirty_count++; + /* + * If the bit is set, the value written onto + * the corresponding page should be either the + * previous iteration number or the current one. + */ + TEST_ASSERT(*value_ptr == iteration || + *value_ptr == iteration - 1, + "Set page %"PRIu64" value %"PRIu64 + " incorrect (iteration=%"PRIu64")", + page, *value_ptr, iteration); + } else { + host_clear_count++; + /* + * If cleared, the value written can be any + * value smaller or equals to the iteration + * number. Note that the value can be exactly + * (iteration-1) if that write can happen + * like this: + * + * (1) increase loop count to "iteration-1" + * (2) write to page P happens (with value + * "iteration-1") + * (3) get dirty log for "iteration-1"; we'll + * see that page P bit is set (dirtied), + * and not set the bit in host_bmap_track + * (4) increase loop count to "iteration" + * (which is current iteration) + * (5) get dirty log for current iteration, + * we'll see that page P is cleared, with + * value "iteration-1". + */ + TEST_ASSERT(*value_ptr <= iteration, + "Clear page %"PRIu64" value %"PRIu64 + " incorrect (iteration=%"PRIu64")", + page, *value_ptr, iteration); + if (*value_ptr == iteration) { + /* + * This page is _just_ modified; it + * should report its dirtyness in the + * next run + */ + set_bit(page, host_bmap_track); + } + } + } +} + +static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid, + uint64_t extra_mem_pages, void *guest_code) +{ + struct kvm_vm *vm; + uint64_t extra_pg_pages = extra_mem_pages / 512 * 2; + + vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); + kvm_vm_elf_load(vm, program_invocation_name, 0, 0); +#ifdef __x86_64__ + vm_create_irqchip(vm); +#endif + vm_vcpu_add_default(vm, vcpuid, guest_code); + return vm; +} + +static void run_test(enum vm_guest_mode mode, unsigned long iterations, + unsigned long interval, bool top_offset) +{ + unsigned int guest_pa_bits, guest_page_shift; + pthread_t vcpu_thread; + struct kvm_vm *vm; + uint64_t max_gfn; + unsigned long *bmap; + + switch (mode) { + case VM_MODE_P52V48_4K: + guest_pa_bits = 52; + guest_page_shift = 12; + break; + case VM_MODE_P52V48_64K: + guest_pa_bits = 52; + guest_page_shift = 16; + break; + case VM_MODE_P40V48_4K: + guest_pa_bits = 40; + guest_page_shift = 12; + break; + case VM_MODE_P40V48_64K: + guest_pa_bits = 40; + guest_page_shift = 16; + break; + default: + TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", mode); + } + + DEBUG("Testing guest mode: %s\n", vm_guest_mode_string(mode)); + + max_gfn = (1ul << (guest_pa_bits - guest_page_shift)) - 1; + guest_page_size = (1ul << guest_page_shift); + /* 1G of guest page sized pages */ + guest_num_pages = (1ul << (30 - guest_page_shift)); + host_page_size = getpagesize(); + host_num_pages = (guest_num_pages * guest_page_size) / host_page_size + + !!((guest_num_pages * guest_page_size) % host_page_size); + + if (top_offset) { + guest_test_mem = (max_gfn - guest_num_pages) * guest_page_size; + guest_test_mem &= ~(host_page_size - 1); + } + + DEBUG("guest test mem offset: 0x%lx\n", guest_test_mem); + + bmap = bitmap_alloc(host_num_pages); + host_bmap_track = bitmap_alloc(host_num_pages); + + vm = create_vm(mode, VCPU_ID, guest_num_pages, guest_code); + + /* Add an extra memory slot for testing dirty logging */ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + guest_test_mem, + TEST_MEM_SLOT_INDEX, + guest_num_pages, + KVM_MEM_LOG_DIRTY_PAGES); + + /* Do 1:1 mapping for the dirty track memory slot */ + virt_map(vm, guest_test_mem, guest_test_mem, + guest_num_pages * guest_page_size, 0); + + /* Cache the HVA pointer of the region */ + host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_mem); + +#ifdef __x86_64__ + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); +#endif +#ifdef __aarch64__ + ucall_init(vm, UCALL_MMIO, NULL); +#endif + + /* Export the shared variables to the guest */ + sync_global_to_guest(vm, host_page_size); + sync_global_to_guest(vm, guest_page_size); + sync_global_to_guest(vm, guest_test_mem); + sync_global_to_guest(vm, guest_num_pages); + + /* Start the iterations */ + iteration = 1; + sync_global_to_guest(vm, iteration); + host_quit = false; + host_dirty_count = 0; + host_clear_count = 0; + host_track_next_count = 0; + + pthread_create(&vcpu_thread, NULL, vcpu_worker, vm); + + while (iteration < iterations) { + /* Give the vcpu thread some time to dirty some pages */ + usleep(interval * 1000); + kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); + vm_dirty_log_verify(bmap); + iteration++; + sync_global_to_guest(vm, iteration); + } + + /* Tell the vcpu thread to quit */ + host_quit = true; + pthread_join(vcpu_thread, NULL); + + DEBUG("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), " + "track_next (%"PRIu64")\n", host_dirty_count, host_clear_count, + host_track_next_count); + + free(bmap); + free(host_bmap_track); + ucall_uninit(vm); + kvm_vm_free(vm); +} + +static struct vm_guest_modes { + enum vm_guest_mode mode; + bool supported; + bool enabled; +} vm_guest_modes[NUM_VM_MODES] = { +#if defined(__x86_64__) + { VM_MODE_P52V48_4K, 1, 1, }, + { VM_MODE_P52V48_64K, 0, 0, }, + { VM_MODE_P40V48_4K, 0, 0, }, + { VM_MODE_P40V48_64K, 0, 0, }, +#elif defined(__aarch64__) + { VM_MODE_P52V48_4K, 0, 0, }, + { VM_MODE_P52V48_64K, 0, 0, }, + { VM_MODE_P40V48_4K, 1, 1, }, + { VM_MODE_P40V48_64K, 1, 1, }, +#endif +}; + +static void help(char *name) +{ + int i; + + puts(""); + printf("usage: %s [-h] [-i iterations] [-I interval] " + "[-o offset] [-t] [-m mode]\n", name); + puts(""); + printf(" -i: specify iteration counts (default: %"PRIu64")\n", + TEST_HOST_LOOP_N); + printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n", + TEST_HOST_LOOP_INTERVAL); + printf(" -o: guest test memory offset (default: 0x%lx)\n", + DEFAULT_GUEST_TEST_MEM); + printf(" -t: map guest test memory at the top of the allowed " + "physical address range\n"); + printf(" -m: specify the guest mode ID to test " + "(default: test all supported modes)\n" + " This option may be used multiple times.\n" + " Guest mode IDs:\n"); + for (i = 0; i < NUM_VM_MODES; ++i) { + printf(" %d: %s%s\n", + vm_guest_modes[i].mode, + vm_guest_mode_string(vm_guest_modes[i].mode), + vm_guest_modes[i].supported ? " (supported)" : ""); + } + puts(""); + exit(0); +} + +int main(int argc, char *argv[]) +{ + unsigned long iterations = TEST_HOST_LOOP_N; + unsigned long interval = TEST_HOST_LOOP_INTERVAL; + bool mode_selected = false; + bool top_offset = false; + unsigned int mode; + int opt, i; + + while ((opt = getopt(argc, argv, "hi:I:o:tm:")) != -1) { + switch (opt) { + case 'i': + iterations = strtol(optarg, NULL, 10); + break; + case 'I': + interval = strtol(optarg, NULL, 10); + break; + case 'o': + guest_test_mem = strtoull(optarg, NULL, 0); + break; + case 't': + top_offset = true; + break; + case 'm': + if (!mode_selected) { + for (i = 0; i < NUM_VM_MODES; ++i) + vm_guest_modes[i].enabled = 0; + mode_selected = true; + } + mode = strtoul(optarg, NULL, 10); + TEST_ASSERT(mode < NUM_VM_MODES, + "Guest mode ID %d too big", mode); + vm_guest_modes[mode].enabled = 1; + break; + case 'h': + default: + help(argv[0]); + break; + } + } + + TEST_ASSERT(iterations > 2, "Iterations must be greater than two"); + TEST_ASSERT(interval > 0, "Interval must be greater than zero"); + TEST_ASSERT(!top_offset || guest_test_mem == DEFAULT_GUEST_TEST_MEM, + "Cannot use both -o [offset] and -t at the same time"); + + DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n", + iterations, interval); + + srandom(time(0)); + + for (i = 0; i < NUM_VM_MODES; ++i) { + if (!vm_guest_modes[i].enabled) + continue; + TEST_ASSERT(vm_guest_modes[i].supported, + "Guest mode ID %d (%s) not supported.", + vm_guest_modes[i].mode, + vm_guest_mode_string(vm_guest_modes[i].mode)); + run_test(vm_guest_modes[i].mode, iterations, interval, top_offset); + } + + return 0; +} diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h new file mode 100644 index 000000000000..9ef2ab1a0c08 --- /dev/null +++ b/tools/testing/selftests/kvm/include/aarch64/processor.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AArch64 processor specific defines + * + * Copyright (C) 2018, Red Hat, Inc. + */ +#ifndef SELFTEST_KVM_PROCESSOR_H +#define SELFTEST_KVM_PROCESSOR_H + +#include "kvm_util.h" + + +#define ARM64_CORE_REG(x) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ + KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x)) + +#define CPACR_EL1 3, 0, 1, 0, 2 +#define TCR_EL1 3, 0, 2, 0, 2 +#define MAIR_EL1 3, 0, 10, 2, 0 +#define TTBR0_EL1 3, 0, 2, 0, 0 +#define SCTLR_EL1 3, 0, 1, 0, 0 + +/* + * Default MAIR + * index attribute + * DEVICE_nGnRnE 0 0000:0000 + * DEVICE_nGnRE 1 0000:0100 + * DEVICE_GRE 2 0000:1100 + * NORMAL_NC 3 0100:0100 + * NORMAL 4 1111:1111 + * NORMAL_WT 5 1011:1011 + */ +#define DEFAULT_MAIR_EL1 ((0x00ul << (0 * 8)) | \ + (0x04ul << (1 * 8)) | \ + (0x0cul << (2 * 8)) | \ + (0x44ul << (3 * 8)) | \ + (0xfful << (4 * 8)) | \ + (0xbbul << (5 * 8))) + +static inline void get_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint64_t *addr) +{ + struct kvm_one_reg reg; + reg.id = id; + reg.addr = (uint64_t)addr; + vcpu_ioctl(vm, vcpuid, KVM_GET_ONE_REG, ®); +} + +static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint64_t val) +{ + struct kvm_one_reg reg; + reg.id = id; + reg.addr = (uint64_t)&val; + vcpu_ioctl(vm, vcpuid, KVM_SET_ONE_REG, ®); +} + +#endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/evmcs.h new file mode 100644 index 000000000000..4059014d93ea --- /dev/null +++ b/tools/testing/selftests/kvm/include/evmcs.h @@ -0,0 +1,1098 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * tools/testing/selftests/kvm/include/vmx.h + * + * Copyright (C) 2018, Red Hat, Inc. + * + */ + +#ifndef SELFTEST_KVM_EVMCS_H +#define SELFTEST_KVM_EVMCS_H + +#include <stdint.h> +#include "vmx.h" + +#define u16 uint16_t +#define u32 uint32_t +#define u64 uint64_t + +extern bool enable_evmcs; + +struct hv_vp_assist_page { + __u32 apic_assist; + __u32 reserved; + __u64 vtl_control[2]; + __u64 nested_enlightenments_control[2]; + __u32 enlighten_vmentry; + __u64 current_nested_vmcs; +}; + +struct hv_enlightened_vmcs { + u32 revision_id; + u32 abort; + + u16 host_es_selector; + u16 host_cs_selector; + u16 host_ss_selector; + u16 host_ds_selector; + u16 host_fs_selector; + u16 host_gs_selector; + u16 host_tr_selector; + + u64 host_ia32_pat; + u64 host_ia32_efer; + + u64 host_cr0; + u64 host_cr3; + u64 host_cr4; + + u64 host_ia32_sysenter_esp; + u64 host_ia32_sysenter_eip; + u64 host_rip; + u32 host_ia32_sysenter_cs; + + u32 pin_based_vm_exec_control; + u32 vm_exit_controls; + u32 secondary_vm_exec_control; + + u64 io_bitmap_a; + u64 io_bitmap_b; + u64 msr_bitmap; + + u16 guest_es_selector; + u16 guest_cs_selector; + u16 guest_ss_selector; + u16 guest_ds_selector; + u16 guest_fs_selector; + u16 guest_gs_selector; + u16 guest_ldtr_selector; + u16 guest_tr_selector; + + u32 guest_es_limit; + u32 guest_cs_limit; + u32 guest_ss_limit; + u32 guest_ds_limit; + u32 guest_fs_limit; + u32 guest_gs_limit; + u32 guest_ldtr_limit; + u32 guest_tr_limit; + u32 guest_gdtr_limit; + u32 guest_idtr_limit; + + u32 guest_es_ar_bytes; + u32 guest_cs_ar_bytes; + u32 guest_ss_ar_bytes; + u32 guest_ds_ar_bytes; + u32 guest_fs_ar_bytes; + u32 guest_gs_ar_bytes; + u32 guest_ldtr_ar_bytes; + u32 guest_tr_ar_bytes; + + u64 guest_es_base; + u64 guest_cs_base; + u64 guest_ss_base; + u64 guest_ds_base; + u64 guest_fs_base; + u64 guest_gs_base; + u64 guest_ldtr_base; + u64 guest_tr_base; + u64 guest_gdtr_base; + u64 guest_idtr_base; + + u64 padding64_1[3]; + + u64 vm_exit_msr_store_addr; + u64 vm_exit_msr_load_addr; + u64 vm_entry_msr_load_addr; + + u64 cr3_target_value0; + u64 cr3_target_value1; + u64 cr3_target_value2; + u64 cr3_target_value3; + + u32 page_fault_error_code_mask; + u32 page_fault_error_code_match; + + u32 cr3_target_count; + u32 vm_exit_msr_store_count; + u32 vm_exit_msr_load_count; + u32 vm_entry_msr_load_count; + + u64 tsc_offset; + u64 virtual_apic_page_addr; + u64 vmcs_link_pointer; + + u64 guest_ia32_debugctl; + u64 guest_ia32_pat; + u64 guest_ia32_efer; + + u64 guest_pdptr0; + u64 guest_pdptr1; + u64 guest_pdptr2; + u64 guest_pdptr3; + + u64 guest_pending_dbg_exceptions; + u64 guest_sysenter_esp; + u64 guest_sysenter_eip; + + u32 guest_activity_state; + u32 guest_sysenter_cs; + + u64 cr0_guest_host_mask; + u64 cr4_guest_host_mask; + u64 cr0_read_shadow; + u64 cr4_read_shadow; + u64 guest_cr0; + u64 guest_cr3; + u64 guest_cr4; + u64 guest_dr7; + + u64 host_fs_base; + u64 host_gs_base; + u64 host_tr_base; + u64 host_gdtr_base; + u64 host_idtr_base; + u64 host_rsp; + + u64 ept_pointer; + + u16 virtual_processor_id; + u16 padding16[3]; + + u64 padding64_2[5]; + u64 guest_physical_address; + + u32 vm_instruction_error; + u32 vm_exit_reason; + u32 vm_exit_intr_info; + u32 vm_exit_intr_error_code; + u32 idt_vectoring_info_field; + u32 idt_vectoring_error_code; + u32 vm_exit_instruction_len; + u32 vmx_instruction_info; + + u64 exit_qualification; + u64 exit_io_instruction_ecx; + u64 exit_io_instruction_esi; + u64 exit_io_instruction_edi; + u64 exit_io_instruction_eip; + + u64 guest_linear_address; + u64 guest_rsp; + u64 guest_rflags; + + u32 guest_interruptibility_info; + u32 cpu_based_vm_exec_control; + u32 exception_bitmap; + u32 vm_entry_controls; + u32 vm_entry_intr_info_field; + u32 vm_entry_exception_error_code; + u32 vm_entry_instruction_len; + u32 tpr_threshold; + + u64 guest_rip; + + u32 hv_clean_fields; + u32 hv_padding_32; + u32 hv_synthetic_controls; + struct { + u32 nested_flush_hypercall:1; + u32 msr_bitmap:1; + u32 reserved:30; + } hv_enlightenments_control; + u32 hv_vp_id; + + u64 hv_vm_id; + u64 partition_assist_page; + u64 padding64_4[4]; + u64 guest_bndcfgs; + u64 padding64_5[7]; + u64 xss_exit_bitmap; + u64 padding64_6[7]; +}; + +#define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073 +#define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001 +#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12 +#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK \ + (~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1)) + +struct hv_enlightened_vmcs *current_evmcs; +struct hv_vp_assist_page *current_vp_assist; + +static inline int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist) +{ + u64 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; + + enable_evmcs = true; + + return 0; +} + +static inline int evmcs_vmptrld(uint64_t vmcs_pa, void *vmcs) +{ + current_vp_assist->current_nested_vmcs = vmcs_pa; + current_vp_assist->enlighten_vmentry = 1; + + current_evmcs = vmcs; + + return 0; +} + +static inline int evmcs_vmptrst(uint64_t *value) +{ + *value = current_vp_assist->current_nested_vmcs & + ~HV_X64_MSR_VP_ASSIST_PAGE_ENABLE; + + return 0; +} + +static inline int evmcs_vmread(uint64_t encoding, uint64_t *value) +{ + switch (encoding) { + case GUEST_RIP: + *value = current_evmcs->guest_rip; + break; + case GUEST_RSP: + *value = current_evmcs->guest_rsp; + break; + case GUEST_RFLAGS: + *value = current_evmcs->guest_rflags; + break; + case HOST_IA32_PAT: + *value = current_evmcs->host_ia32_pat; + break; + case HOST_IA32_EFER: + *value = current_evmcs->host_ia32_efer; + break; + case HOST_CR0: + *value = current_evmcs->host_cr0; + break; + case HOST_CR3: + *value = current_evmcs->host_cr3; + break; + case HOST_CR4: + *value = current_evmcs->host_cr4; + break; + case HOST_IA32_SYSENTER_ESP: + *value = current_evmcs->host_ia32_sysenter_esp; + break; + case HOST_IA32_SYSENTER_EIP: + *value = current_evmcs->host_ia32_sysenter_eip; + break; + case HOST_RIP: + *value = current_evmcs->host_rip; + break; + case IO_BITMAP_A: + *value = current_evmcs->io_bitmap_a; + break; + case IO_BITMAP_B: + *value = current_evmcs->io_bitmap_b; + break; + case MSR_BITMAP: + *value = current_evmcs->msr_bitmap; + break; + case GUEST_ES_BASE: + *value = current_evmcs->guest_es_base; + break; + case GUEST_CS_BASE: + *value = current_evmcs->guest_cs_base; + break; + case GUEST_SS_BASE: + *value = current_evmcs->guest_ss_base; + break; + case GUEST_DS_BASE: + *value = current_evmcs->guest_ds_base; + break; + case GUEST_FS_BASE: + *value = current_evmcs->guest_fs_base; + break; + case GUEST_GS_BASE: + *value = current_evmcs->guest_gs_base; + break; + case GUEST_LDTR_BASE: + *value = current_evmcs->guest_ldtr_base; + break; + case GUEST_TR_BASE: + *value = current_evmcs->guest_tr_base; + break; + case GUEST_GDTR_BASE: + *value = current_evmcs->guest_gdtr_base; + break; + case GUEST_IDTR_BASE: + *value = current_evmcs->guest_idtr_base; + break; + case TSC_OFFSET: + *value = current_evmcs->tsc_offset; + break; + case VIRTUAL_APIC_PAGE_ADDR: + *value = current_evmcs->virtual_apic_page_addr; + break; + case VMCS_LINK_POINTER: + *value = current_evmcs->vmcs_link_pointer; + break; + case GUEST_IA32_DEBUGCTL: + *value = current_evmcs->guest_ia32_debugctl; + break; + case GUEST_IA32_PAT: + *value = current_evmcs->guest_ia32_pat; + break; + case GUEST_IA32_EFER: + *value = current_evmcs->guest_ia32_efer; + break; + case GUEST_PDPTR0: + *value = current_evmcs->guest_pdptr0; + break; + case GUEST_PDPTR1: + *value = current_evmcs->guest_pdptr1; + break; + case GUEST_PDPTR2: + *value = current_evmcs->guest_pdptr2; + break; + case GUEST_PDPTR3: + *value = current_evmcs->guest_pdptr3; + break; + case GUEST_PENDING_DBG_EXCEPTIONS: + *value = current_evmcs->guest_pending_dbg_exceptions; + break; + case GUEST_SYSENTER_ESP: + *value = current_evmcs->guest_sysenter_esp; + break; + case GUEST_SYSENTER_EIP: + *value = current_evmcs->guest_sysenter_eip; + break; + case CR0_GUEST_HOST_MASK: + *value = current_evmcs->cr0_guest_host_mask; + break; + case CR4_GUEST_HOST_MASK: + *value = current_evmcs->cr4_guest_host_mask; + break; + case CR0_READ_SHADOW: + *value = current_evmcs->cr0_read_shadow; + break; + case CR4_READ_SHADOW: + *value = current_evmcs->cr4_read_shadow; + break; + case GUEST_CR0: + *value = current_evmcs->guest_cr0; + break; + case GUEST_CR3: + *value = current_evmcs->guest_cr3; + break; + case GUEST_CR4: + *value = current_evmcs->guest_cr4; + break; + case GUEST_DR7: + *value = current_evmcs->guest_dr7; + break; + case HOST_FS_BASE: + *value = current_evmcs->host_fs_base; + break; + case HOST_GS_BASE: + *value = current_evmcs->host_gs_base; + break; + case HOST_TR_BASE: + *value = current_evmcs->host_tr_base; + break; + case HOST_GDTR_BASE: + *value = current_evmcs->host_gdtr_base; + break; + case HOST_IDTR_BASE: + *value = current_evmcs->host_idtr_base; + break; + case HOST_RSP: + *value = current_evmcs->host_rsp; + break; + case EPT_POINTER: + *value = current_evmcs->ept_pointer; + break; + case GUEST_BNDCFGS: + *value = current_evmcs->guest_bndcfgs; + break; + case XSS_EXIT_BITMAP: + *value = current_evmcs->xss_exit_bitmap; + break; + case GUEST_PHYSICAL_ADDRESS: + *value = current_evmcs->guest_physical_address; + break; + case EXIT_QUALIFICATION: + *value = current_evmcs->exit_qualification; + break; + case GUEST_LINEAR_ADDRESS: + *value = current_evmcs->guest_linear_address; + break; + case VM_EXIT_MSR_STORE_ADDR: + *value = current_evmcs->vm_exit_msr_store_addr; + break; + case VM_EXIT_MSR_LOAD_ADDR: + *value = current_evmcs->vm_exit_msr_load_addr; + break; + case VM_ENTRY_MSR_LOAD_ADDR: + *value = current_evmcs->vm_entry_msr_load_addr; + break; + case CR3_TARGET_VALUE0: + *value = current_evmcs->cr3_target_value0; + break; + case CR3_TARGET_VALUE1: + *value = current_evmcs->cr3_target_value1; + break; + case CR3_TARGET_VALUE2: + *value = current_evmcs->cr3_target_value2; + break; + case CR3_TARGET_VALUE3: + *value = current_evmcs->cr3_target_value3; + break; + case TPR_THRESHOLD: + *value = current_evmcs->tpr_threshold; + break; + case GUEST_INTERRUPTIBILITY_INFO: + *value = current_evmcs->guest_interruptibility_info; + break; + case CPU_BASED_VM_EXEC_CONTROL: + *value = current_evmcs->cpu_based_vm_exec_control; + break; + case EXCEPTION_BITMAP: + *value = current_evmcs->exception_bitmap; + break; + case VM_ENTRY_CONTROLS: + *value = current_evmcs->vm_entry_controls; + break; + case VM_ENTRY_INTR_INFO_FIELD: + *value = current_evmcs->vm_entry_intr_info_field; + break; + case VM_ENTRY_EXCEPTION_ERROR_CODE: + *value = current_evmcs->vm_entry_exception_error_code; + break; + case VM_ENTRY_INSTRUCTION_LEN: + *value = current_evmcs->vm_entry_instruction_len; + break; + case HOST_IA32_SYSENTER_CS: + *value = current_evmcs->host_ia32_sysenter_cs; + break; + case PIN_BASED_VM_EXEC_CONTROL: + *value = current_evmcs->pin_based_vm_exec_control; + break; + case VM_EXIT_CONTROLS: + *value = current_evmcs->vm_exit_controls; + break; + case SECONDARY_VM_EXEC_CONTROL: + *value = current_evmcs->secondary_vm_exec_control; + break; + case GUEST_ES_LIMIT: + *value = current_evmcs->guest_es_limit; + break; + case GUEST_CS_LIMIT: + *value = current_evmcs->guest_cs_limit; + break; + case GUEST_SS_LIMIT: + *value = current_evmcs->guest_ss_limit; + break; + case GUEST_DS_LIMIT: + *value = current_evmcs->guest_ds_limit; + break; + case GUEST_FS_LIMIT: + *value = current_evmcs->guest_fs_limit; + break; + case GUEST_GS_LIMIT: + *value = current_evmcs->guest_gs_limit; + break; + case GUEST_LDTR_LIMIT: + *value = current_evmcs->guest_ldtr_limit; + break; + case GUEST_TR_LIMIT: + *value = current_evmcs->guest_tr_limit; + break; + case GUEST_GDTR_LIMIT: + *value = current_evmcs->guest_gdtr_limit; + break; + case GUEST_IDTR_LIMIT: + *value = current_evmcs->guest_idtr_limit; + break; + case GUEST_ES_AR_BYTES: + *value = current_evmcs->guest_es_ar_bytes; + break; + case GUEST_CS_AR_BYTES: + *value = current_evmcs->guest_cs_ar_bytes; + break; + case GUEST_SS_AR_BYTES: + *value = current_evmcs->guest_ss_ar_bytes; + break; + case GUEST_DS_AR_BYTES: + *value = current_evmcs->guest_ds_ar_bytes; + break; + case GUEST_FS_AR_BYTES: + *value = current_evmcs->guest_fs_ar_bytes; + break; + case GUEST_GS_AR_BYTES: + *value = current_evmcs->guest_gs_ar_bytes; + break; + case GUEST_LDTR_AR_BYTES: + *value = current_evmcs->guest_ldtr_ar_bytes; + break; + case GUEST_TR_AR_BYTES: + *value = current_evmcs->guest_tr_ar_bytes; + break; + case GUEST_ACTIVITY_STATE: + *value = current_evmcs->guest_activity_state; + break; + case GUEST_SYSENTER_CS: + *value = current_evmcs->guest_sysenter_cs; + break; + case VM_INSTRUCTION_ERROR: + *value = current_evmcs->vm_instruction_error; + break; + case VM_EXIT_REASON: + *value = current_evmcs->vm_exit_reason; + break; + case VM_EXIT_INTR_INFO: + *value = current_evmcs->vm_exit_intr_info; + break; + case VM_EXIT_INTR_ERROR_CODE: + *value = current_evmcs->vm_exit_intr_error_code; + break; + case IDT_VECTORING_INFO_FIELD: + *value = current_evmcs->idt_vectoring_info_field; + break; + case IDT_VECTORING_ERROR_CODE: + *value = current_evmcs->idt_vectoring_error_code; + break; + case VM_EXIT_INSTRUCTION_LEN: + *value = current_evmcs->vm_exit_instruction_len; + break; + case VMX_INSTRUCTION_INFO: + *value = current_evmcs->vmx_instruction_info; + break; + case PAGE_FAULT_ERROR_CODE_MASK: + *value = current_evmcs->page_fault_error_code_mask; + break; + case PAGE_FAULT_ERROR_CODE_MATCH: + *value = current_evmcs->page_fault_error_code_match; + break; + case CR3_TARGET_COUNT: + *value = current_evmcs->cr3_target_count; + break; + case VM_EXIT_MSR_STORE_COUNT: + *value = current_evmcs->vm_exit_msr_store_count; + break; + case VM_EXIT_MSR_LOAD_COUNT: + *value = current_evmcs->vm_exit_msr_load_count; + break; + case VM_ENTRY_MSR_LOAD_COUNT: + *value = current_evmcs->vm_entry_msr_load_count; + break; + case HOST_ES_SELECTOR: + *value = current_evmcs->host_es_selector; + break; + case HOST_CS_SELECTOR: + *value = current_evmcs->host_cs_selector; + break; + case HOST_SS_SELECTOR: + *value = current_evmcs->host_ss_selector; + break; + case HOST_DS_SELECTOR: + *value = current_evmcs->host_ds_selector; + break; + case HOST_FS_SELECTOR: + *value = current_evmcs->host_fs_selector; + break; + case HOST_GS_SELECTOR: + *value = current_evmcs->host_gs_selector; + break; + case HOST_TR_SELECTOR: + *value = current_evmcs->host_tr_selector; + break; + case GUEST_ES_SELECTOR: + *value = current_evmcs->guest_es_selector; + break; + case GUEST_CS_SELECTOR: + *value = current_evmcs->guest_cs_selector; + break; + case GUEST_SS_SELECTOR: + *value = current_evmcs->guest_ss_selector; + break; + case GUEST_DS_SELECTOR: + *value = current_evmcs->guest_ds_selector; + break; + case GUEST_FS_SELECTOR: + *value = current_evmcs->guest_fs_selector; + break; + case GUEST_GS_SELECTOR: + *value = current_evmcs->guest_gs_selector; + break; + case GUEST_LDTR_SELECTOR: + *value = current_evmcs->guest_ldtr_selector; + break; + case GUEST_TR_SELECTOR: + *value = current_evmcs->guest_tr_selector; + break; + case VIRTUAL_PROCESSOR_ID: + *value = current_evmcs->virtual_processor_id; + break; + default: return 1; + } + + return 0; +} + +static inline int evmcs_vmwrite(uint64_t encoding, uint64_t value) +{ + switch (encoding) { + case GUEST_RIP: + current_evmcs->guest_rip = value; + break; + case GUEST_RSP: + current_evmcs->guest_rsp = value; + break; + case GUEST_RFLAGS: + current_evmcs->guest_rflags = value; + break; + case HOST_IA32_PAT: + current_evmcs->host_ia32_pat = value; + break; + case HOST_IA32_EFER: + current_evmcs->host_ia32_efer = value; + break; + case HOST_CR0: + current_evmcs->host_cr0 = value; + break; + case HOST_CR3: + current_evmcs->host_cr3 = value; + break; + case HOST_CR4: + current_evmcs->host_cr4 = value; + break; + case HOST_IA32_SYSENTER_ESP: + current_evmcs->host_ia32_sysenter_esp = value; + break; + case HOST_IA32_SYSENTER_EIP: + current_evmcs->host_ia32_sysenter_eip = value; + break; + case HOST_RIP: + current_evmcs->host_rip = value; + break; + case IO_BITMAP_A: + current_evmcs->io_bitmap_a = value; + break; + case IO_BITMAP_B: + current_evmcs->io_bitmap_b = value; + break; + case MSR_BITMAP: + current_evmcs->msr_bitmap = value; + break; + case GUEST_ES_BASE: + current_evmcs->guest_es_base = value; + break; + case GUEST_CS_BASE: + current_evmcs->guest_cs_base = value; + break; + case GUEST_SS_BASE: + current_evmcs->guest_ss_base = value; + break; + case GUEST_DS_BASE: + current_evmcs->guest_ds_base = value; + break; + case GUEST_FS_BASE: + current_evmcs->guest_fs_base = value; + break; + case GUEST_GS_BASE: + current_evmcs->guest_gs_base = value; + break; + case GUEST_LDTR_BASE: + current_evmcs->guest_ldtr_base = value; + break; + case GUEST_TR_BASE: + current_evmcs->guest_tr_base = value; + break; + case GUEST_GDTR_BASE: + current_evmcs->guest_gdtr_base = value; + break; + case GUEST_IDTR_BASE: + current_evmcs->guest_idtr_base = value; + break; + case TSC_OFFSET: + current_evmcs->tsc_offset = value; + break; + case VIRTUAL_APIC_PAGE_ADDR: + current_evmcs->virtual_apic_page_addr = value; + break; + case VMCS_LINK_POINTER: + current_evmcs->vmcs_link_pointer = value; + break; + case GUEST_IA32_DEBUGCTL: + current_evmcs->guest_ia32_debugctl = value; + break; + case GUEST_IA32_PAT: + current_evmcs->guest_ia32_pat = value; + break; + case GUEST_IA32_EFER: + current_evmcs->guest_ia32_efer = value; + break; + case GUEST_PDPTR0: + current_evmcs->guest_pdptr0 = value; + break; + case GUEST_PDPTR1: + current_evmcs->guest_pdptr1 = value; + break; + case GUEST_PDPTR2: + current_evmcs->guest_pdptr2 = value; + break; + case GUEST_PDPTR3: + current_evmcs->guest_pdptr3 = value; + break; + case GUEST_PENDING_DBG_EXCEPTIONS: + current_evmcs->guest_pending_dbg_exceptions = value; + break; + case GUEST_SYSENTER_ESP: + current_evmcs->guest_sysenter_esp = value; + break; + case GUEST_SYSENTER_EIP: + current_evmcs->guest_sysenter_eip = value; + break; + case CR0_GUEST_HOST_MASK: + current_evmcs->cr0_guest_host_mask = value; + break; + case CR4_GUEST_HOST_MASK: + current_evmcs->cr4_guest_host_mask = value; + break; + case CR0_READ_SHADOW: + current_evmcs->cr0_read_shadow = value; + break; + case CR4_READ_SHADOW: + current_evmcs->cr4_read_shadow = value; + break; + case GUEST_CR0: + current_evmcs->guest_cr0 = value; + break; + case GUEST_CR3: + current_evmcs->guest_cr3 = value; + break; + case GUEST_CR4: + current_evmcs->guest_cr4 = value; + break; + case GUEST_DR7: + current_evmcs->guest_dr7 = value; + break; + case HOST_FS_BASE: + current_evmcs->host_fs_base = value; + break; + case HOST_GS_BASE: + current_evmcs->host_gs_base = value; + break; + case HOST_TR_BASE: + current_evmcs->host_tr_base = value; + break; + case HOST_GDTR_BASE: + current_evmcs->host_gdtr_base = value; + break; + case HOST_IDTR_BASE: + current_evmcs->host_idtr_base = value; + break; + case HOST_RSP: + current_evmcs->host_rsp = value; + break; + case EPT_POINTER: + current_evmcs->ept_pointer = value; + break; + case GUEST_BNDCFGS: + current_evmcs->guest_bndcfgs = value; + break; + case XSS_EXIT_BITMAP: + current_evmcs->xss_exit_bitmap = value; + break; + case GUEST_PHYSICAL_ADDRESS: + current_evmcs->guest_physical_address = value; + break; + case EXIT_QUALIFICATION: + current_evmcs->exit_qualification = value; + break; + case GUEST_LINEAR_ADDRESS: + current_evmcs->guest_linear_address = value; + break; + case VM_EXIT_MSR_STORE_ADDR: + current_evmcs->vm_exit_msr_store_addr = value; + break; + case VM_EXIT_MSR_LOAD_ADDR: + current_evmcs->vm_exit_msr_load_addr = value; + break; + case VM_ENTRY_MSR_LOAD_ADDR: + current_evmcs->vm_entry_msr_load_addr = value; + break; + case CR3_TARGET_VALUE0: + current_evmcs->cr3_target_value0 = value; + break; + case CR3_TARGET_VALUE1: + current_evmcs->cr3_target_value1 = value; + break; + case CR3_TARGET_VALUE2: + current_evmcs->cr3_target_value2 = value; + break; + case CR3_TARGET_VALUE3: + current_evmcs->cr3_target_value3 = value; + break; + case TPR_THRESHOLD: + current_evmcs->tpr_threshold = value; + break; + case GUEST_INTERRUPTIBILITY_INFO: + current_evmcs->guest_interruptibility_info = value; + break; + case CPU_BASED_VM_EXEC_CONTROL: + current_evmcs->cpu_based_vm_exec_control = value; + break; + case EXCEPTION_BITMAP: + current_evmcs->exception_bitmap = value; + break; + case VM_ENTRY_CONTROLS: + current_evmcs->vm_entry_controls = value; + break; + case VM_ENTRY_INTR_INFO_FIELD: + current_evmcs->vm_entry_intr_info_field = value; + break; + case VM_ENTRY_EXCEPTION_ERROR_CODE: + current_evmcs->vm_entry_exception_error_code = value; + break; + case VM_ENTRY_INSTRUCTION_LEN: + current_evmcs->vm_entry_instruction_len = value; + break; + case HOST_IA32_SYSENTER_CS: + current_evmcs->host_ia32_sysenter_cs = value; + break; + case PIN_BASED_VM_EXEC_CONTROL: + current_evmcs->pin_based_vm_exec_control = value; + break; + case VM_EXIT_CONTROLS: + current_evmcs->vm_exit_controls = value; + break; + case SECONDARY_VM_EXEC_CONTROL: + current_evmcs->secondary_vm_exec_control = value; + break; + case GUEST_ES_LIMIT: + current_evmcs->guest_es_limit = value; + break; + case GUEST_CS_LIMIT: + current_evmcs->guest_cs_limit = value; + break; + case GUEST_SS_LIMIT: + current_evmcs->guest_ss_limit = value; + break; + case GUEST_DS_LIMIT: + current_evmcs->guest_ds_limit = value; + break; + case GUEST_FS_LIMIT: + current_evmcs->guest_fs_limit = value; + break; + case GUEST_GS_LIMIT: + current_evmcs->guest_gs_limit = value; + break; + case GUEST_LDTR_LIMIT: + current_evmcs->guest_ldtr_limit = value; + break; + case GUEST_TR_LIMIT: + current_evmcs->guest_tr_limit = value; + break; + case GUEST_GDTR_LIMIT: + current_evmcs->guest_gdtr_limit = value; + break; + case GUEST_IDTR_LIMIT: + current_evmcs->guest_idtr_limit = value; + break; + case GUEST_ES_AR_BYTES: + current_evmcs->guest_es_ar_bytes = value; + break; + case GUEST_CS_AR_BYTES: + current_evmcs->guest_cs_ar_bytes = value; + break; + case GUEST_SS_AR_BYTES: + current_evmcs->guest_ss_ar_bytes = value; + break; + case GUEST_DS_AR_BYTES: + current_evmcs->guest_ds_ar_bytes = value; + break; + case GUEST_FS_AR_BYTES: + current_evmcs->guest_fs_ar_bytes = value; + break; + case GUEST_GS_AR_BYTES: + current_evmcs->guest_gs_ar_bytes = value; + break; + case GUEST_LDTR_AR_BYTES: + current_evmcs->guest_ldtr_ar_bytes = value; + break; + case GUEST_TR_AR_BYTES: + current_evmcs->guest_tr_ar_bytes = value; + break; + case GUEST_ACTIVITY_STATE: + current_evmcs->guest_activity_state = value; + break; + case GUEST_SYSENTER_CS: + current_evmcs->guest_sysenter_cs = value; + break; + case VM_INSTRUCTION_ERROR: + current_evmcs->vm_instruction_error = value; + break; + case VM_EXIT_REASON: + current_evmcs->vm_exit_reason = value; + break; + case VM_EXIT_INTR_INFO: + current_evmcs->vm_exit_intr_info = value; + break; + case VM_EXIT_INTR_ERROR_CODE: + current_evmcs->vm_exit_intr_error_code = value; + break; + case IDT_VECTORING_INFO_FIELD: + current_evmcs->idt_vectoring_info_field = value; + break; + case IDT_VECTORING_ERROR_CODE: + current_evmcs->idt_vectoring_error_code = value; + break; + case VM_EXIT_INSTRUCTION_LEN: + current_evmcs->vm_exit_instruction_len = value; + break; + case VMX_INSTRUCTION_INFO: + current_evmcs->vmx_instruction_info = value; + break; + case PAGE_FAULT_ERROR_CODE_MASK: + current_evmcs->page_fault_error_code_mask = value; + break; + case PAGE_FAULT_ERROR_CODE_MATCH: + current_evmcs->page_fault_error_code_match = value; + break; + case CR3_TARGET_COUNT: + current_evmcs->cr3_target_count = value; + break; + case VM_EXIT_MSR_STORE_COUNT: + current_evmcs->vm_exit_msr_store_count = value; + break; + case VM_EXIT_MSR_LOAD_COUNT: + current_evmcs->vm_exit_msr_load_count = value; + break; + case VM_ENTRY_MSR_LOAD_COUNT: + current_evmcs->vm_entry_msr_load_count = value; + break; + case HOST_ES_SELECTOR: + current_evmcs->host_es_selector = value; + break; + case HOST_CS_SELECTOR: + current_evmcs->host_cs_selector = value; + break; + case HOST_SS_SELECTOR: + current_evmcs->host_ss_selector = value; + break; + case HOST_DS_SELECTOR: + current_evmcs->host_ds_selector = value; + break; + case HOST_FS_SELECTOR: + current_evmcs->host_fs_selector = value; + break; + case HOST_GS_SELECTOR: + current_evmcs->host_gs_selector = value; + break; + case HOST_TR_SELECTOR: + current_evmcs->host_tr_selector = value; + break; + case GUEST_ES_SELECTOR: + current_evmcs->guest_es_selector = value; + break; + case GUEST_CS_SELECTOR: + current_evmcs->guest_cs_selector = value; + break; + case GUEST_SS_SELECTOR: + current_evmcs->guest_ss_selector = value; + break; + case GUEST_DS_SELECTOR: + current_evmcs->guest_ds_selector = value; + break; + case GUEST_FS_SELECTOR: + current_evmcs->guest_fs_selector = value; + break; + case GUEST_GS_SELECTOR: + current_evmcs->guest_gs_selector = value; + break; + case GUEST_LDTR_SELECTOR: + current_evmcs->guest_ldtr_selector = value; + break; + case GUEST_TR_SELECTOR: + current_evmcs->guest_tr_selector = value; + break; + case VIRTUAL_PROCESSOR_ID: + current_evmcs->virtual_processor_id = value; + break; + default: return 1; + } + + return 0; +} + +static inline int evmcs_vmlaunch(void) +{ + int ret; + + current_evmcs->hv_clean_fields = 0; + + __asm__ __volatile__("push %%rbp;" + "push %%rcx;" + "push %%rdx;" + "push %%rsi;" + "push %%rdi;" + "push $0;" + "mov %%rsp, (%[host_rsp]);" + "lea 1f(%%rip), %%rax;" + "mov %%rax, (%[host_rip]);" + "vmlaunch;" + "incq (%%rsp);" + "1: pop %%rax;" + "pop %%rdi;" + "pop %%rsi;" + "pop %%rdx;" + "pop %%rcx;" + "pop %%rbp;" + : [ret]"=&a"(ret) + : [host_rsp]"r" + ((uint64_t)¤t_evmcs->host_rsp), + [host_rip]"r" + ((uint64_t)¤t_evmcs->host_rip) + : "memory", "cc", "rbx", "r8", "r9", "r10", + "r11", "r12", "r13", "r14", "r15"); + return ret; +} + +/* + * No guest state (e.g. GPRs) is established by this vmresume. + */ +static inline int evmcs_vmresume(void) +{ + int ret; + + current_evmcs->hv_clean_fields = 0; + + __asm__ __volatile__("push %%rbp;" + "push %%rcx;" + "push %%rdx;" + "push %%rsi;" + "push %%rdi;" + "push $0;" + "mov %%rsp, (%[host_rsp]);" + "lea 1f(%%rip), %%rax;" + "mov %%rax, (%[host_rip]);" + "vmresume;" + "incq (%%rsp);" + "1: pop %%rax;" + "pop %%rdi;" + "pop %%rsi;" + "pop %%rdx;" + "pop %%rcx;" + "pop %%rbp;" + : [ret]"=&a"(ret) + : [host_rsp]"r" + ((uint64_t)¤t_evmcs->host_rsp), + [host_rip]"r" + ((uint64_t)¤t_evmcs->host_rip) + : "memory", "cc", "rbx", "r8", "r9", "r10", + "r11", "r12", "r13", "r14", "r15"); + return ret; +} + +#endif /* !SELFTEST_KVM_EVMCS_H */ diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 637b7017b6ee..a4e59e3b4826 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -7,7 +7,7 @@ * */ #ifndef SELFTEST_KVM_UTIL_H -#define SELFTEST_KVM_UTIL_H 1 +#define SELFTEST_KVM_UTIL_H #include "test_util.h" @@ -17,12 +17,6 @@ #include "sparsebit.h" -/* - * Memslots can't cover the gfn starting at this gpa otherwise vCPUs can't be - * created. Only applies to VMs using EPT. - */ -#define KVM_DEFAULT_IDENTITY_MAP_ADDRESS 0xfffbc000ul - /* Callers of kvm_util only have an incomplete/opaque description of the * structure kvm_util is using to maintain the state of a VM. @@ -33,16 +27,23 @@ typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */ /* Minimum allocated guest virtual and physical addresses */ -#define KVM_UTIL_MIN_VADDR 0x2000 +#define KVM_UTIL_MIN_VADDR 0x2000 #define DEFAULT_GUEST_PHY_PAGES 512 #define DEFAULT_GUEST_STACK_VADDR_MIN 0xab6000 -#define DEFAULT_STACK_PGS 5 +#define DEFAULT_STACK_PGS 5 enum vm_guest_mode { - VM_MODE_FLAT48PG, + VM_MODE_P52V48_4K, + VM_MODE_P52V48_64K, + VM_MODE_P40V48_4K, + VM_MODE_P40V48_64K, + NUM_VM_MODES, }; +#define vm_guest_mode_string(m) vm_guest_mode_string[m] +extern const char * const vm_guest_mode_string[]; + enum vm_mem_backing_src_type { VM_MEM_SRC_ANONYMOUS, VM_MEM_SRC_ANONYMOUS_THP, @@ -50,19 +51,23 @@ enum vm_mem_backing_src_type { }; int kvm_check_cap(long cap); +int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm); void kvm_vm_free(struct kvm_vm *vmp); +void kvm_vm_restart(struct kvm_vm *vmp, int perm); +void kvm_vm_release(struct kvm_vm *vmp); +void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log); -int kvm_memcmp_hva_gva(void *hva, - struct kvm_vm *vm, const vm_vaddr_t gva, size_t len); +int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva, + size_t len); void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename, - uint32_t data_memslot, uint32_t pgd_memslot); + uint32_t data_memslot, uint32_t pgd_memslot); void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); -void vcpu_dump(FILE *stream, struct kvm_vm *vm, - uint32_t vcpuid, uint8_t indent); +void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, + uint8_t indent); void vm_create_irqchip(struct kvm_vm *vm); @@ -71,13 +76,16 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, uint64_t guest_paddr, uint32_t slot, uint64_t npages, uint32_t flags); -void vcpu_ioctl(struct kvm_vm *vm, - uint32_t vcpuid, unsigned long ioctl, void *arg); +void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl, + void *arg); void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); -void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid); +void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, + int gdt_memslot); vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, - uint32_t data_memslot, uint32_t pgd_memslot); + uint32_t data_memslot, uint32_t pgd_memslot); +void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, + size_t size, uint32_t pgd_memslot); void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa); void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); @@ -87,52 +95,35 @@ struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_mp_state *mp_state); -void vcpu_regs_get(struct kvm_vm *vm, - uint32_t vcpuid, struct kvm_regs *regs); -void vcpu_regs_set(struct kvm_vm *vm, - uint32_t vcpuid, struct kvm_regs *regs); + struct kvm_mp_state *mp_state); +void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); +void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...); -void vcpu_sregs_get(struct kvm_vm *vm, - uint32_t vcpuid, struct kvm_sregs *sregs); -void vcpu_sregs_set(struct kvm_vm *vm, - uint32_t vcpuid, struct kvm_sregs *sregs); -int _vcpu_sregs_set(struct kvm_vm *vm, - uint32_t vcpuid, struct kvm_sregs *sregs); +void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_sregs *sregs); +void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_sregs *sregs); +int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_sregs *sregs); void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_vcpu_events *events); + struct kvm_vcpu_events *events); void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_vcpu_events *events); + struct kvm_vcpu_events *events); const char *exit_reason_str(unsigned int exit_reason); void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot); void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, - uint32_t pgd_memslot); -vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, - vm_paddr_t paddr_min, uint32_t memslot); - -struct kvm_cpuid2 *kvm_get_supported_cpuid(void); -void vcpu_set_cpuid( - struct kvm_vm *vm, uint32_t vcpuid, struct kvm_cpuid2 *cpuid); - -struct kvm_cpuid_entry2 * -kvm_get_supported_cpuid_index(uint32_t function, uint32_t index); - -static inline struct kvm_cpuid_entry2 * -kvm_get_supported_cpuid_entry(uint32_t function) -{ - return kvm_get_supported_cpuid_index(function, 0); -} - -struct kvm_vm *vm_create_default(uint32_t vcpuid, void *guest_code); + uint32_t pgd_memslot); +vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, + uint32_t memslot); +vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, + vm_paddr_t paddr_min, uint32_t memslot); + +struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_size, + void *guest_code); void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code); -typedef void (*vmx_guest_code_t)(vm_vaddr_t vmxon_vaddr, - vm_paddr_t vmxon_paddr, - vm_vaddr_t vmcs_vaddr, - vm_paddr_t vmcs_paddr); - struct kvm_userspace_memory_region * kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end); @@ -142,4 +133,49 @@ allocate_kvm_dirty_log(struct kvm_userspace_memory_region *region); int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd); +#define sync_global_to_guest(vm, g) ({ \ + typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + memcpy(_p, &(g), sizeof(g)); \ +}) + +#define sync_global_from_guest(vm, g) ({ \ + typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + memcpy(&(g), _p, sizeof(g)); \ +}) + +/* ucall implementation types */ +typedef enum { + UCALL_PIO, + UCALL_MMIO, +} ucall_type_t; + +/* Common ucalls */ +enum { + UCALL_NONE, + UCALL_SYNC, + UCALL_ABORT, + UCALL_DONE, +}; + +#define UCALL_MAX_ARGS 6 + +struct ucall { + uint64_t cmd; + uint64_t args[UCALL_MAX_ARGS]; +}; + +void ucall_init(struct kvm_vm *vm, ucall_type_t type, void *arg); +void ucall_uninit(struct kvm_vm *vm); +void ucall(uint64_t cmd, int nargs, ...); +uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc); + +#define GUEST_SYNC(stage) ucall(UCALL_SYNC, 2, "hello", stage) +#define GUEST_DONE() ucall(UCALL_DONE, 0) +#define GUEST_ASSERT(_condition) do { \ + if (!(_condition)) \ + ucall(UCALL_ABORT, 2, \ + "Failed guest assert: " \ + #_condition, __LINE__); \ +} while (0) + #endif /* SELFTEST_KVM_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/sparsebit.h b/tools/testing/selftests/kvm/include/sparsebit.h index 54cfeb6568d3..31e030915c1f 100644 --- a/tools/testing/selftests/kvm/include/sparsebit.h +++ b/tools/testing/selftests/kvm/include/sparsebit.h @@ -15,8 +15,8 @@ * even in the case where most bits are set. */ -#ifndef _TEST_SPARSEBIT_H_ -#define _TEST_SPARSEBIT_H_ +#ifndef SELFTEST_KVM_SPARSEBIT_H +#define SELFTEST_KVM_SPARSEBIT_H #include <stdbool.h> #include <stdint.h> @@ -72,4 +72,4 @@ void sparsebit_validate_internal(struct sparsebit *sbit); } #endif -#endif /* _TEST_SPARSEBIT_H_ */ +#endif /* SELFTEST_KVM_SPARSEBIT_H */ diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index ac53730b30aa..c7dafe8bd02c 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -7,8 +7,8 @@ * */ -#ifndef TEST_UTIL_H -#define TEST_UTIL_H 1 +#ifndef SELFTEST_KVM_TEST_UTIL_H +#define SELFTEST_KVM_TEST_UTIL_H #include <stdlib.h> #include <stdarg.h> @@ -28,8 +28,6 @@ int test_seq_read(const char *path, char **bufp, size_t *sizep); void test_assert(bool exp, const char *exp_str, const char *file, unsigned int line, const char *fmt, ...); -#define ARRAY_SIZE(array) (sizeof(array) / sizeof((array)[0])) - #define TEST_ASSERT(e, fmt, ...) \ test_assert((e), #e, __FILE__, __LINE__, fmt, ##__VA_ARGS__) @@ -43,4 +41,4 @@ void test_assert(bool exp, const char *exp_str, #a, #b, #a, (unsigned long) __a, #b, (unsigned long) __b); \ } while (0) -#endif /* TEST_UTIL_H */ +#endif /* SELFTEST_KVM_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/x86.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 4a5b2c4c1a0f..e2884c2b81ff 100644 --- a/tools/testing/selftests/kvm/include/x86.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -1,5 +1,5 @@ /* - * tools/testing/selftests/kvm/include/x86.h + * tools/testing/selftests/kvm/include/x86_64/processor.h * * Copyright (C) 2018, Google LLC. * @@ -7,8 +7,8 @@ * */ -#ifndef SELFTEST_KVM_X86_H -#define SELFTEST_KVM_X86_H +#ifndef SELFTEST_KVM_PROCESSOR_H +#define SELFTEST_KVM_PROCESSOR_H #include <assert.h> #include <stdint.h> @@ -59,8 +59,8 @@ enum x86_register { struct desc64 { uint16_t limit0; uint16_t base0; - unsigned base1:8, type:5, dpl:2, p:1; - unsigned limit1:4, zero0:3, g:1, base2:8; + unsigned base1:8, s:1, type:4, dpl:2, p:1; + unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8; uint32_t base3; uint32_t zero1; } __attribute__((packed)); @@ -303,6 +303,28 @@ static inline unsigned long get_xmm(int n) return 0; } +struct kvm_x86_state; +struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid); +void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_x86_state *state); + +struct kvm_cpuid2 *kvm_get_supported_cpuid(void); +void vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_cpuid2 *cpuid); + +struct kvm_cpuid_entry2 * +kvm_get_supported_cpuid_index(uint32_t function, uint32_t index); + +static inline struct kvm_cpuid_entry2 * +kvm_get_supported_cpuid_entry(uint32_t function) +{ + return kvm_get_supported_cpuid_index(function, 0); +} + +uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index); +void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, + uint64_t msr_value); + /* * Basic CPU control in CR0 */ @@ -1040,4 +1062,4 @@ static inline unsigned long get_xmm(int n) #define MSR_VM_IGNNE 0xc0010115 #define MSR_VM_HSAVE_PA 0xc0010117 -#endif /* !SELFTEST_KVM_X86_H */ +#endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h index 6ed8499807fd..c9bd935b939c 100644 --- a/tools/testing/selftests/kvm/include/vmx.h +++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h @@ -1,5 +1,5 @@ /* - * tools/testing/selftests/kvm/include/vmx.h + * tools/testing/selftests/kvm/include/x86_64/vmx.h * * Copyright (C) 2018, Google LLC. * @@ -11,7 +11,7 @@ #define SELFTEST_KVM_VMX_H #include <stdint.h> -#include "x86.h" +#include "processor.h" #define CPUID_VMX_BIT 5 @@ -339,6 +339,8 @@ struct vmx_msr_entry { uint64_t value; } __attribute__ ((aligned(16))); +#include "evmcs.h" + static inline int vmxon(uint64_t phys) { uint8_t ret; @@ -372,6 +374,9 @@ static inline int vmptrld(uint64_t vmcs_pa) { uint8_t ret; + if (enable_evmcs) + return -1; + __asm__ __volatile__ ("vmptrld %[pa]; setna %[ret]" : [ret]"=rm"(ret) : [pa]"m"(vmcs_pa) @@ -380,6 +385,33 @@ static inline int vmptrld(uint64_t vmcs_pa) return ret; } +static inline int vmptrst(uint64_t *value) +{ + uint64_t tmp; + uint8_t ret; + + if (enable_evmcs) + return evmcs_vmptrst(value); + + __asm__ __volatile__("vmptrst %[value]; setna %[ret]" + : [value]"=m"(tmp), [ret]"=rm"(ret) + : : "cc", "memory"); + + *value = tmp; + return ret; +} + +/* + * A wrapper around vmptrst that ignores errors and returns zero if the + * vmptrst instruction fails. + */ +static inline uint64_t vmptrstz(void) +{ + uint64_t value = 0; + vmptrst(&value); + return value; +} + /* * No guest state (e.g. GPRs) is established by this vmlaunch. */ @@ -387,6 +419,9 @@ static inline int vmlaunch(void) { int ret; + if (enable_evmcs) + return evmcs_vmlaunch(); + __asm__ __volatile__("push %%rbp;" "push %%rcx;" "push %%rdx;" @@ -419,6 +454,9 @@ static inline int vmresume(void) { int ret; + if (enable_evmcs) + return evmcs_vmresume(); + __asm__ __volatile__("push %%rbp;" "push %%rcx;" "push %%rdx;" @@ -444,11 +482,23 @@ static inline int vmresume(void) return ret; } +static inline void vmcall(void) +{ + /* Currently, L1 destroys our GPRs during vmexits. */ + __asm__ __volatile__("push %%rbp; vmcall; pop %%rbp" : : : + "rax", "rbx", "rcx", "rdx", + "rsi", "rdi", "r8", "r9", "r10", "r11", "r12", + "r13", "r14", "r15"); +} + static inline int vmread(uint64_t encoding, uint64_t *value) { uint64_t tmp; uint8_t ret; + if (enable_evmcs) + return evmcs_vmread(encoding, value); + __asm__ __volatile__("vmread %[encoding], %[value]; setna %[ret]" : [value]"=rm"(tmp), [ret]"=rm"(ret) : [encoding]"r"(encoding) @@ -473,6 +523,9 @@ static inline int vmwrite(uint64_t encoding, uint64_t value) { uint8_t ret; + if (enable_evmcs) + return evmcs_vmwrite(encoding, value); + __asm__ __volatile__ ("vmwrite %[value], %[encoding]; setna %[ret]" : [ret]"=rm"(ret) : [value]"rm"(value), [encoding]"r"(encoding) @@ -486,9 +539,43 @@ static inline uint32_t vmcs_revision(void) return rdmsr(MSR_IA32_VMX_BASIC); } -void prepare_for_vmx_operation(void); -void prepare_vmcs(void *guest_rip, void *guest_rsp); -struct kvm_vm *vm_create_default_vmx(uint32_t vcpuid, - vmx_guest_code_t guest_code); +struct vmx_pages { + void *vmxon_hva; + uint64_t vmxon_gpa; + void *vmxon; + + void *vmcs_hva; + uint64_t vmcs_gpa; + void *vmcs; + + void *msr_hva; + uint64_t msr_gpa; + void *msr; + + void *shadow_vmcs_hva; + uint64_t shadow_vmcs_gpa; + void *shadow_vmcs; + + void *vmread_hva; + uint64_t vmread_gpa; + void *vmread; + + void *vmwrite_hva; + uint64_t vmwrite_gpa; + void *vmwrite; + + void *vp_assist_hva; + uint64_t vp_assist_gpa; + void *vp_assist; + + void *enlightened_vmcs_hva; + uint64_t enlightened_vmcs_gpa; + void *enlightened_vmcs; +}; + +struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva); +bool prepare_for_vmx_operation(struct vmx_pages *vmx); +void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp); +bool load_vmcs(struct vmx_pages *vmx); -#endif /* !SELFTEST_KVM_VMX_H */ +#endif /* SELFTEST_KVM_VMX_H */ diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c new file mode 100644 index 000000000000..b6022e2f116e --- /dev/null +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -0,0 +1,311 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * AArch64 code + * + * Copyright (C) 2018, Red Hat, Inc. + */ + +#define _GNU_SOURCE /* for program_invocation_name */ + +#include "kvm_util.h" +#include "../kvm_util_internal.h" +#include "processor.h" + +#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 +#define DEFAULT_ARM64_GUEST_STACK_VADDR_MIN 0xac0000 + +static uint64_t page_align(struct kvm_vm *vm, uint64_t v) +{ + return (v + vm->page_size) & ~(vm->page_size - 1); +} + +static uint64_t pgd_index(struct kvm_vm *vm, vm_vaddr_t gva) +{ + unsigned int shift = (vm->pgtable_levels - 1) * (vm->page_shift - 3) + vm->page_shift; + uint64_t mask = (1UL << (vm->va_bits - shift)) - 1; + + return (gva >> shift) & mask; +} + +static uint64_t pud_index(struct kvm_vm *vm, vm_vaddr_t gva) +{ + unsigned int shift = 2 * (vm->page_shift - 3) + vm->page_shift; + uint64_t mask = (1UL << (vm->page_shift - 3)) - 1; + + TEST_ASSERT(vm->pgtable_levels == 4, + "Mode %d does not have 4 page table levels", vm->mode); + + return (gva >> shift) & mask; +} + +static uint64_t pmd_index(struct kvm_vm *vm, vm_vaddr_t gva) +{ + unsigned int shift = (vm->page_shift - 3) + vm->page_shift; + uint64_t mask = (1UL << (vm->page_shift - 3)) - 1; + + TEST_ASSERT(vm->pgtable_levels >= 3, + "Mode %d does not have >= 3 page table levels", vm->mode); + + return (gva >> shift) & mask; +} + +static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva) +{ + uint64_t mask = (1UL << (vm->page_shift - 3)) - 1; + return (gva >> vm->page_shift) & mask; +} + +static uint64_t pte_addr(struct kvm_vm *vm, uint64_t entry) +{ + uint64_t mask = ((1UL << (vm->va_bits - vm->page_shift)) - 1) << vm->page_shift; + return entry & mask; +} + +static uint64_t ptrs_per_pgd(struct kvm_vm *vm) +{ + unsigned int shift = (vm->pgtable_levels - 1) * (vm->page_shift - 3) + vm->page_shift; + return 1 << (vm->va_bits - shift); +} + +static uint64_t ptrs_per_pte(struct kvm_vm *vm) +{ + return 1 << (vm->page_shift - 3); +} + +void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot) +{ + int rc; + + if (!vm->pgd_created) { + vm_paddr_t paddr = vm_phy_pages_alloc(vm, + page_align(vm, ptrs_per_pgd(vm) * 8) / vm->page_size, + KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot); + vm->pgd = paddr; + vm->pgd_created = true; + } +} + +void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, + uint32_t pgd_memslot, uint64_t flags) +{ + uint8_t attr_idx = flags & 7; + uint64_t *ptep; + + TEST_ASSERT((vaddr % vm->page_size) == 0, + "Virtual address not on page boundary,\n" + " vaddr: 0x%lx vm->page_size: 0x%x", vaddr, vm->page_size); + TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, + (vaddr >> vm->page_shift)), + "Invalid virtual address, vaddr: 0x%lx", vaddr); + TEST_ASSERT((paddr % vm->page_size) == 0, + "Physical address not on page boundary,\n" + " paddr: 0x%lx vm->page_size: 0x%x", paddr, vm->page_size); + TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn, + "Physical address beyond beyond maximum supported,\n" + " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", + paddr, vm->max_gfn, vm->page_size); + + ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, vaddr) * 8; + if (!*ptep) { + *ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot); + *ptep |= 3; + } + + switch (vm->pgtable_levels) { + case 4: + ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, vaddr) * 8; + if (!*ptep) { + *ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot); + *ptep |= 3; + } + /* fall through */ + case 3: + ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, vaddr) * 8; + if (!*ptep) { + *ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot); + *ptep |= 3; + } + /* fall through */ + case 2: + ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, vaddr) * 8; + break; + default: + TEST_ASSERT(false, "Page table levels must be 2, 3, or 4"); + } + + *ptep = paddr | 3; + *ptep |= (attr_idx << 2) | (1 << 10) /* Access Flag */; +} + +void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, + uint32_t pgd_memslot) +{ + uint64_t attr_idx = 4; /* NORMAL (See DEFAULT_MAIR_EL1) */ + + _virt_pg_map(vm, vaddr, paddr, pgd_memslot, attr_idx); +} + +vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +{ + uint64_t *ptep; + + if (!vm->pgd_created) + goto unmapped_gva; + + ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, gva) * 8; + if (!ptep) + goto unmapped_gva; + + switch (vm->pgtable_levels) { + case 4: + ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, gva) * 8; + if (!ptep) + goto unmapped_gva; + /* fall through */ + case 3: + ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, gva) * 8; + if (!ptep) + goto unmapped_gva; + /* fall through */ + case 2: + ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, gva) * 8; + if (!ptep) + goto unmapped_gva; + break; + default: + TEST_ASSERT(false, "Page table levels must be 2, 3, or 4"); + } + + return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1)); + +unmapped_gva: + TEST_ASSERT(false, "No mapping for vm virtual address, " + "gva: 0x%lx", gva); +} + +static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t page, int level) +{ +#ifdef DEBUG_VM + static const char * const type[] = { "", "pud", "pmd", "pte" }; + uint64_t pte, *ptep; + + if (level == 4) + return; + + for (pte = page; pte < page + ptrs_per_pte(vm) * 8; pte += 8) { + ptep = addr_gpa2hva(vm, pte); + if (!*ptep) + continue; + printf("%*s%s: %lx: %lx at %p\n", indent, "", type[level], pte, *ptep, ptep); + pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level + 1); + } +#endif +} + +void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +{ + int level = 4 - (vm->pgtable_levels - 1); + uint64_t pgd, *ptep; + + if (!vm->pgd_created) + return; + + for (pgd = vm->pgd; pgd < vm->pgd + ptrs_per_pgd(vm) * 8; pgd += 8) { + ptep = addr_gpa2hva(vm, pgd); + if (!*ptep) + continue; + printf("%*spgd: %lx: %lx at %p\n", indent, "", pgd, *ptep, ptep); + pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level); + } +} + +struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, + void *guest_code) +{ + uint64_t ptrs_per_4k_pte = 512; + uint64_t extra_pg_pages = (extra_mem_pages / ptrs_per_4k_pte) * 2; + struct kvm_vm *vm; + + vm = vm_create(VM_MODE_P52V48_4K, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); + + kvm_vm_elf_load(vm, program_invocation_name, 0, 0); + vm_vcpu_add_default(vm, vcpuid, guest_code); + + return vm; +} + +void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) +{ + size_t stack_size = vm->page_size == 4096 ? + DEFAULT_STACK_PGS * vm->page_size : + vm->page_size; + uint64_t stack_vaddr = vm_vaddr_alloc(vm, stack_size, + DEFAULT_ARM64_GUEST_STACK_VADDR_MIN, 0, 0); + + vm_vcpu_add(vm, vcpuid, 0, 0); + + set_reg(vm, vcpuid, ARM64_CORE_REG(sp_el1), stack_vaddr + stack_size); + set_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code); +} + +void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot) +{ + struct kvm_vcpu_init init; + uint64_t sctlr_el1, tcr_el1; + + memset(&init, 0, sizeof(init)); + init.target = KVM_ARM_TARGET_GENERIC_V8; + vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_INIT, &init); + + /* + * Enable FP/ASIMD to avoid trapping when accessing Q0-Q15 + * registers, which the variable argument list macros do. + */ + set_reg(vm, vcpuid, ARM64_SYS_REG(CPACR_EL1), 3 << 20); + + get_reg(vm, vcpuid, ARM64_SYS_REG(SCTLR_EL1), &sctlr_el1); + get_reg(vm, vcpuid, ARM64_SYS_REG(TCR_EL1), &tcr_el1); + + switch (vm->mode) { + case VM_MODE_P52V48_4K: + tcr_el1 |= 0ul << 14; /* TG0 = 4KB */ + tcr_el1 |= 6ul << 32; /* IPS = 52 bits */ + break; + case VM_MODE_P52V48_64K: + tcr_el1 |= 1ul << 14; /* TG0 = 64KB */ + tcr_el1 |= 6ul << 32; /* IPS = 52 bits */ + break; + case VM_MODE_P40V48_4K: + tcr_el1 |= 0ul << 14; /* TG0 = 4KB */ + tcr_el1 |= 2ul << 32; /* IPS = 40 bits */ + break; + case VM_MODE_P40V48_64K: + tcr_el1 |= 1ul << 14; /* TG0 = 64KB */ + tcr_el1 |= 2ul << 32; /* IPS = 40 bits */ + break; + default: + TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode); + } + + sctlr_el1 |= (1 << 0) | (1 << 2) | (1 << 12) /* M | C | I */; + /* TCR_EL1 |= IRGN0:WBWA | ORGN0:WBWA | SH0:Inner-Shareable */; + tcr_el1 |= (1 << 8) | (1 << 10) | (3 << 12); + tcr_el1 |= (64 - vm->va_bits) /* T0SZ */; + + set_reg(vm, vcpuid, ARM64_SYS_REG(SCTLR_EL1), sctlr_el1); + set_reg(vm, vcpuid, ARM64_SYS_REG(TCR_EL1), tcr_el1); + set_reg(vm, vcpuid, ARM64_SYS_REG(MAIR_EL1), DEFAULT_MAIR_EL1); + set_reg(vm, vcpuid, ARM64_SYS_REG(TTBR0_EL1), vm->pgd); +} + +void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) +{ + uint64_t pstate, pc; + + get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pstate), &pstate); + get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), &pc); + + fprintf(stream, "%*spstate: 0x%.16llx pc: 0x%.16llx\n", + indent, "", pstate, pc); + +} diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c index cd01144d27c8..6398efe67885 100644 --- a/tools/testing/selftests/kvm/lib/assert.c +++ b/tools/testing/selftests/kvm/lib/assert.c @@ -13,7 +13,7 @@ #include <execinfo.h> #include <sys/syscall.h> -#include "../../kselftest.h" +#include "kselftest.h" /* Dumps the current stack trace to stderr. */ static void __attribute__((noinline)) test_dump_stack(void); diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 37e2a787d2fc..1b41e71283d5 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -14,11 +14,10 @@ #include <sys/mman.h> #include <sys/types.h> #include <sys/stat.h> - -#define KVM_DEV_PATH "/dev/kvm" +#include <linux/kernel.h> #define KVM_UTIL_PGS_PER_HUGEPG 512 -#define KVM_UTIL_MIN_PADDR 0x2000 +#define KVM_UTIL_MIN_PFN 2 /* Aligns x up to the next multiple of size. Size must be a power of 2. */ static void *align(void *x, size_t size) @@ -29,7 +28,8 @@ static void *align(void *x, size_t size) return (void *) (((size_t) x + mask) & ~mask); } -/* Capability +/* + * Capability * * Input Args: * cap - Capability @@ -62,10 +62,52 @@ int kvm_check_cap(long cap) return ret; } -/* VM Create +/* VM Enable Capability + * + * Input Args: + * vm - Virtual Machine + * cap - Capability + * + * Output Args: None + * + * Return: On success, 0. On failure a TEST_ASSERT failure is produced. + * + * Enables a capability (KVM_CAP_*) on the VM. + */ +int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap) +{ + int ret; + + ret = ioctl(vm->fd, KVM_ENABLE_CAP, cap); + TEST_ASSERT(ret == 0, "KVM_ENABLE_CAP IOCTL failed,\n" + " rc: %i errno: %i", ret, errno); + + return ret; +} + +static void vm_open(struct kvm_vm *vm, int perm) +{ + vm->kvm_fd = open(KVM_DEV_PATH, perm); + if (vm->kvm_fd < 0) + exit(KSFT_SKIP); + + vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, NULL); + TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, " + "rc: %i errno: %i", vm->fd, errno); +} + +const char * const vm_guest_mode_string[] = { + "PA-bits:52, VA-bits:48, 4K pages", + "PA-bits:52, VA-bits:48, 64K pages", + "PA-bits:40, VA-bits:48, 4K pages", + "PA-bits:40, VA-bits:48, 64K pages", +}; + +/* + * VM Create * * Input Args: - * mode - VM Mode (e.g. VM_MODE_FLAT48PG) + * mode - VM Mode (e.g. VM_MODE_P52V48_4K) * phy_pages - Physical memory pages * perm - permission * @@ -74,7 +116,7 @@ int kvm_check_cap(long cap) * Return: * Pointer to opaque structure that describes the created VM. * - * Creates a VM with the mode specified by mode (e.g. VM_MODE_FLAT48PG). + * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K). * When phy_pages is non-zero, a memory region of phy_pages physical pages * is created and mapped starting at guest physical address 0. The file * descriptor to control the created VM is created with the permissions @@ -85,44 +127,56 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) struct kvm_vm *vm; int kvm_fd; - /* Allocate memory. */ vm = calloc(1, sizeof(*vm)); - TEST_ASSERT(vm != NULL, "Insufficent Memory"); + TEST_ASSERT(vm != NULL, "Insufficient Memory"); vm->mode = mode; - kvm_fd = open(KVM_DEV_PATH, perm); - if (kvm_fd < 0) - exit(KSFT_SKIP); - - /* Create VM. */ - vm->fd = ioctl(kvm_fd, KVM_CREATE_VM, NULL); - TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, " - "rc: %i errno: %i", vm->fd, errno); - - close(kvm_fd); + vm_open(vm, perm); /* Setup mode specific traits. */ switch (vm->mode) { - case VM_MODE_FLAT48PG: + case VM_MODE_P52V48_4K: + vm->pgtable_levels = 4; vm->page_size = 0x1000; vm->page_shift = 12; - - /* Limit to 48-bit canonical virtual addresses. */ - vm->vpages_valid = sparsebit_alloc(); - sparsebit_set_num(vm->vpages_valid, - 0, (1ULL << (48 - 1)) >> vm->page_shift); - sparsebit_set_num(vm->vpages_valid, - (~((1ULL << (48 - 1)) - 1)) >> vm->page_shift, - (1ULL << (48 - 1)) >> vm->page_shift); - - /* Limit physical addresses to 52-bits. */ - vm->max_gfn = ((1ULL << 52) >> vm->page_shift) - 1; + vm->va_bits = 48; + break; + case VM_MODE_P52V48_64K: + vm->pgtable_levels = 3; + vm->pa_bits = 52; + vm->page_size = 0x10000; + vm->page_shift = 16; + vm->va_bits = 48; + break; + case VM_MODE_P40V48_4K: + vm->pgtable_levels = 4; + vm->pa_bits = 40; + vm->va_bits = 48; + vm->page_size = 0x1000; + vm->page_shift = 12; + break; + case VM_MODE_P40V48_64K: + vm->pgtable_levels = 3; + vm->pa_bits = 40; + vm->va_bits = 48; + vm->page_size = 0x10000; + vm->page_shift = 16; break; - default: TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", mode); } + /* Limit to VA-bit canonical virtual addresses. */ + vm->vpages_valid = sparsebit_alloc(); + sparsebit_set_num(vm->vpages_valid, + 0, (1ULL << (vm->va_bits - 1)) >> vm->page_shift); + sparsebit_set_num(vm->vpages_valid, + (~((1ULL << (vm->va_bits - 1)) - 1)) >> vm->page_shift, + (1ULL << (vm->va_bits - 1)) >> vm->page_shift); + + /* Limit physical addresses to PA-bits. */ + vm->max_gfn = ((1ULL << vm->pa_bits) >> vm->page_shift) - 1; + /* Allocate and setup memory for guest. */ vm->vpages_mapped = sparsebit_alloc(); if (phy_pages != 0) @@ -132,7 +186,53 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) return vm; } -/* Userspace Memory Region Find +/* + * VM Restart + * + * Input Args: + * vm - VM that has been released before + * perm - permission + * + * Output Args: None + * + * Reopens the file descriptors associated to the VM and reinstates the + * global state, such as the irqchip and the memory regions that are mapped + * into the guest. + */ +void kvm_vm_restart(struct kvm_vm *vmp, int perm) +{ + struct userspace_mem_region *region; + + vm_open(vmp, perm); + if (vmp->has_irqchip) + vm_create_irqchip(vmp); + + for (region = vmp->userspace_mem_region_head; region; + region = region->next) { + int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); + TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" + " rc: %i errno: %i\n" + " slot: %u flags: 0x%x\n" + " guest_phys_addr: 0x%lx size: 0x%lx", + ret, errno, region->region.slot, + region->region.flags, + region->region.guest_phys_addr, + region->region.memory_size); + } +} + +void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log) +{ + struct kvm_dirty_log args = { .dirty_bitmap = log, .slot = slot }; + int ret; + + ret = ioctl(vm->fd, KVM_GET_DIRTY_LOG, &args); + TEST_ASSERT(ret == 0, "%s: KVM_GET_DIRTY_LOG failed: %s", + strerror(-ret)); +} + +/* + * Userspace Memory Region Find * * Input Args: * vm - Virtual Machine @@ -150,8 +250,8 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) * of the regions is returned. Null is returned only when no overlapping * region exists. */ -static struct userspace_mem_region *userspace_mem_region_find( - struct kvm_vm *vm, uint64_t start, uint64_t end) +static struct userspace_mem_region * +userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end) { struct userspace_mem_region *region; @@ -167,7 +267,8 @@ static struct userspace_mem_region *userspace_mem_region_find( return NULL; } -/* KVM Userspace Memory Region Find +/* + * KVM Userspace Memory Region Find * * Input Args: * vm - Virtual Machine @@ -195,7 +296,8 @@ kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start, return ®ion->region; } -/* VCPU Find +/* + * VCPU Find * * Input Args: * vm - Virtual Machine @@ -210,8 +312,7 @@ kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start, * returns a pointer to it. Returns NULL if the VM doesn't contain a VCPU * for the specified vcpuid. */ -struct vcpu *vcpu_find(struct kvm_vm *vm, - uint32_t vcpuid) +struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid) { struct vcpu *vcpup; @@ -223,7 +324,8 @@ struct vcpu *vcpu_find(struct kvm_vm *vm, return NULL; } -/* VM VCPU Remove +/* + * VM VCPU Remove * * Input Args: * vm - Virtual Machine @@ -238,8 +340,12 @@ struct vcpu *vcpu_find(struct kvm_vm *vm, static void vm_vcpu_rm(struct kvm_vm *vm, uint32_t vcpuid) { struct vcpu *vcpu = vcpu_find(vm, vcpuid); + int ret; - int ret = close(vcpu->fd); + ret = munmap(vcpu->state, sizeof(*vcpu->state)); + TEST_ASSERT(ret == 0, "munmap of VCPU fd failed, rc: %i " + "errno: %i", ret, errno); + close(vcpu->fd); TEST_ASSERT(ret == 0, "Close of VCPU fd failed, rc: %i " "errno: %i", ret, errno); @@ -252,8 +358,24 @@ static void vm_vcpu_rm(struct kvm_vm *vm, uint32_t vcpuid) free(vcpu); } +void kvm_vm_release(struct kvm_vm *vmp) +{ + int ret; + + while (vmp->vcpu_head) + vm_vcpu_rm(vmp, vmp->vcpu_head->id); + + ret = close(vmp->fd); + TEST_ASSERT(ret == 0, "Close of vm fd failed,\n" + " vmp->fd: %i rc: %i errno: %i", vmp->fd, ret, errno); -/* Destroys and frees the VM pointed to by vmp. + close(vmp->kvm_fd); + TEST_ASSERT(ret == 0, "Close of /dev/kvm fd failed,\n" + " vmp->kvm_fd: %i rc: %i errno: %i", vmp->kvm_fd, ret, errno); +} + +/* + * Destroys and frees the VM pointed to by vmp. */ void kvm_vm_free(struct kvm_vm *vmp) { @@ -282,24 +404,18 @@ void kvm_vm_free(struct kvm_vm *vmp) free(region); } - /* Free VCPUs. */ - while (vmp->vcpu_head) - vm_vcpu_rm(vmp, vmp->vcpu_head->id); - /* Free sparsebit arrays. */ sparsebit_free(&vmp->vpages_valid); sparsebit_free(&vmp->vpages_mapped); - /* Close file descriptor for the VM. */ - ret = close(vmp->fd); - TEST_ASSERT(ret == 0, "Close of vm fd failed,\n" - " vmp->fd: %i rc: %i errno: %i", vmp->fd, ret, errno); + kvm_vm_release(vmp); /* Free the structure describing the VM. */ free(vmp); } -/* Memory Compare, host virtual to guest virtual +/* + * Memory Compare, host virtual to guest virtual * * Input Args: * hva - Starting host virtual address @@ -321,23 +437,25 @@ void kvm_vm_free(struct kvm_vm *vmp) * a length of len, to the guest bytes starting at the guest virtual * address given by gva. */ -int kvm_memcmp_hva_gva(void *hva, - struct kvm_vm *vm, vm_vaddr_t gva, size_t len) +int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len) { size_t amt; - /* Compare a batch of bytes until either a match is found + /* + * Compare a batch of bytes until either a match is found * or all the bytes have been compared. */ for (uintptr_t offset = 0; offset < len; offset += amt) { uintptr_t ptr1 = (uintptr_t)hva + offset; - /* Determine host address for guest virtual address + /* + * Determine host address for guest virtual address * at offset. */ uintptr_t ptr2 = (uintptr_t)addr_gva2hva(vm, gva + offset); - /* Determine amount to compare on this pass. + /* + * Determine amount to compare on this pass. * Don't allow the comparsion to cross a page boundary. */ amt = len - offset; @@ -349,7 +467,8 @@ int kvm_memcmp_hva_gva(void *hva, assert((ptr1 >> vm->page_shift) == ((ptr1 + amt - 1) >> vm->page_shift)); assert((ptr2 >> vm->page_shift) == ((ptr2 + amt - 1) >> vm->page_shift)); - /* Perform the comparison. If there is a difference + /* + * Perform the comparison. If there is a difference * return that result to the caller, otherwise need * to continue on looking for a mismatch. */ @@ -358,109 +477,15 @@ int kvm_memcmp_hva_gva(void *hva, return ret; } - /* No mismatch found. Let the caller know the two memory + /* + * No mismatch found. Let the caller know the two memory * areas are equal. */ return 0; } -/* Allocate an instance of struct kvm_cpuid2 - * - * Input Args: None - * - * Output Args: None - * - * Return: A pointer to the allocated struct. The caller is responsible - * for freeing this struct. - * - * Since kvm_cpuid2 uses a 0-length array to allow a the size of the - * array to be decided at allocation time, allocation is slightly - * complicated. This function uses a reasonable default length for - * the array and performs the appropriate allocation. - */ -static struct kvm_cpuid2 *allocate_kvm_cpuid2(void) -{ - struct kvm_cpuid2 *cpuid; - int nent = 100; - size_t size; - - size = sizeof(*cpuid); - size += nent * sizeof(struct kvm_cpuid_entry2); - cpuid = malloc(size); - if (!cpuid) { - perror("malloc"); - abort(); - } - - cpuid->nent = nent; - - return cpuid; -} - -/* KVM Supported CPUID Get - * - * Input Args: None - * - * Output Args: - * - * Return: The supported KVM CPUID - * - * Get the guest CPUID supported by KVM. - */ -struct kvm_cpuid2 *kvm_get_supported_cpuid(void) -{ - static struct kvm_cpuid2 *cpuid; - int ret; - int kvm_fd; - - if (cpuid) - return cpuid; - - cpuid = allocate_kvm_cpuid2(); - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); - - ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid); - TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n", - ret, errno); - - close(kvm_fd); - return cpuid; -} - -/* Locate a cpuid entry. - * - * Input Args: - * cpuid: The cpuid. - * function: The function of the cpuid entry to find. - * - * Output Args: None - * - * Return: A pointer to the cpuid entry. Never returns NULL. - */ -struct kvm_cpuid_entry2 * -kvm_get_supported_cpuid_index(uint32_t function, uint32_t index) -{ - struct kvm_cpuid2 *cpuid; - struct kvm_cpuid_entry2 *entry = NULL; - int i; - - cpuid = kvm_get_supported_cpuid(); - for (i = 0; i < cpuid->nent; i++) { - if (cpuid->entries[i].function == function && - cpuid->entries[i].index == index) { - entry = &cpuid->entries[i]; - break; - } - } - - TEST_ASSERT(entry, "Guest CPUID entry not found: (EAX=%x, ECX=%x).", - function, index); - return entry; -} - -/* VM Userspace Memory Region Add +/* + * VM Userspace Memory Region Add * * Input Args: * vm - Virtual Machine @@ -502,7 +527,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, " vm->max_gfn: 0x%lx vm->page_size: 0x%x", guest_paddr, npages, vm->max_gfn, vm->page_size); - /* Confirm a mem region with an overlapping address doesn't + /* + * Confirm a mem region with an overlapping address doesn't * already exist. */ region = (struct userspace_mem_region *) userspace_mem_region_find( @@ -593,7 +619,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, vm->userspace_mem_region_head = region; } -/* Memslot to region +/* + * Memslot to region * * Input Args: * vm - Virtual Machine @@ -607,8 +634,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, * on error (e.g. currently no memory region using memslot as a KVM * memory slot ID). */ -static struct userspace_mem_region *memslot2region(struct kvm_vm *vm, - uint32_t memslot) +static struct userspace_mem_region * +memslot2region(struct kvm_vm *vm, uint32_t memslot) { struct userspace_mem_region *region; @@ -628,7 +655,8 @@ static struct userspace_mem_region *memslot2region(struct kvm_vm *vm, return region; } -/* VM Memory Region Flags Set +/* + * VM Memory Region Flags Set * * Input Args: * vm - Virtual Machine @@ -646,7 +674,6 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags) int ret; struct userspace_mem_region *region; - /* Locate memory region. */ region = memslot2region(vm, slot); region->region.flags = flags; @@ -658,7 +685,8 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags) ret, errno, slot, flags); } -/* VCPU mmap Size +/* + * VCPU mmap Size * * Input Args: None * @@ -688,7 +716,8 @@ static int vcpu_mmap_sz(void) return ret; } -/* VM VCPU Add +/* + * VM VCPU Add * * Input Args: * vm - Virtual Machine @@ -701,7 +730,8 @@ static int vcpu_mmap_sz(void) * Creates and adds to the VM specified by vm and virtual CPU with * the ID given by vcpuid. */ -void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid) +void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, + int gdt_memslot) { struct vcpu *vcpu; @@ -736,10 +766,11 @@ void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid) vcpu->next = vm->vcpu_head; vm->vcpu_head = vcpu; - vcpu_setup(vm, vcpuid); + vcpu_setup(vm, vcpuid, pgd_memslot, gdt_memslot); } -/* VM Virtual Address Unused Gap +/* + * VM Virtual Address Unused Gap * * Input Args: * vm - Virtual Machine @@ -759,14 +790,14 @@ void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid) * sz unallocated bytes >= vaddr_min is available. */ static vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, - vm_vaddr_t vaddr_min) + vm_vaddr_t vaddr_min) { uint64_t pages = (sz + vm->page_size - 1) >> vm->page_shift; /* Determine lowest permitted virtual page index. */ uint64_t pgidx_start = (vaddr_min + vm->page_size - 1) >> vm->page_shift; if ((pgidx_start * vm->page_size) < vaddr_min) - goto no_va_found; + goto no_va_found; /* Loop over section with enough valid virtual page indexes. */ if (!sparsebit_is_set_num(vm->vpages_valid, @@ -825,7 +856,8 @@ va_found: return pgidx_start * vm->page_size; } -/* VM Virtual Address Allocate +/* + * VM Virtual Address Allocate * * Input Args: * vm - Virtual Machine @@ -846,13 +878,14 @@ va_found: * a page. */ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, - uint32_t data_memslot, uint32_t pgd_memslot) + uint32_t data_memslot, uint32_t pgd_memslot) { uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0); virt_pgd_alloc(vm, pgd_memslot); - /* Find an unused range of virtual page addresses of at least + /* + * Find an unused range of virtual page addresses of at least * pages in length. */ vm_vaddr_t vaddr_start = vm_vaddr_unused_gap(vm, sz, vaddr_min); @@ -862,7 +895,8 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, pages--, vaddr += vm->page_size) { vm_paddr_t paddr; - paddr = vm_phy_page_alloc(vm, KVM_UTIL_MIN_PADDR, data_memslot); + paddr = vm_phy_page_alloc(vm, + KVM_UTIL_MIN_PFN * vm->page_size, data_memslot); virt_pg_map(vm, vaddr, paddr, pgd_memslot); @@ -873,7 +907,41 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, return vaddr_start; } -/* Address VM Physical to Host Virtual +/* + * Map a range of VM virtual address to the VM's physical address + * + * Input Args: + * vm - Virtual Machine + * vaddr - Virtuall address to map + * paddr - VM Physical Address + * size - The size of the range to map + * pgd_memslot - Memory region slot for new virtual translation tables + * + * Output Args: None + * + * Return: None + * + * Within the VM given by vm, creates a virtual translation for the + * page range starting at vaddr to the page range starting at paddr. + */ +void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, + size_t size, uint32_t pgd_memslot) +{ + size_t page_size = vm->page_size; + size_t npages = size / page_size; + + TEST_ASSERT(vaddr + size > vaddr, "Vaddr overflow"); + TEST_ASSERT(paddr + size > paddr, "Paddr overflow"); + + while (npages--) { + virt_pg_map(vm, vaddr, paddr, pgd_memslot); + vaddr += page_size; + paddr += page_size; + } +} + +/* + * Address VM Physical to Host Virtual * * Input Args: * vm - Virtual Machine @@ -905,7 +973,8 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) return NULL; } -/* Address Host Virtual to VM Physical +/* + * Address Host Virtual to VM Physical * * Input Args: * vm - Virtual Machine @@ -939,7 +1008,8 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) return -1; } -/* VM Create IRQ Chip +/* + * VM Create IRQ Chip * * Input Args: * vm - Virtual Machine @@ -957,9 +1027,12 @@ void vm_create_irqchip(struct kvm_vm *vm) ret = ioctl(vm->fd, KVM_CREATE_IRQCHIP, 0); TEST_ASSERT(ret == 0, "KVM_CREATE_IRQCHIP IOCTL failed, " "rc: %i errno: %i", ret, errno); + + vm->has_irqchip = true; } -/* VM VCPU State +/* + * VM VCPU State * * Input Args: * vm - Virtual Machine @@ -981,7 +1054,8 @@ struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid) return vcpu->state; } -/* VM VCPU Run +/* + * VM VCPU Run * * Input Args: * vm - Virtual Machine @@ -1007,13 +1081,14 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid) int rc; TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - do { + do { rc = ioctl(vcpu->fd, KVM_RUN, NULL); } while (rc == -1 && errno == EINTR); return rc; } -/* VM VCPU Set MP State +/* + * VM VCPU Set MP State * * Input Args: * vm - Virtual Machine @@ -1028,7 +1103,7 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid) * by mp_state. */ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_mp_state *mp_state) + struct kvm_mp_state *mp_state) { struct vcpu *vcpu = vcpu_find(vm, vcpuid); int ret; @@ -1040,7 +1115,8 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, "rc: %i errno: %i", ret, errno); } -/* VM VCPU Regs Get +/* + * VM VCPU Regs Get * * Input Args: * vm - Virtual Machine @@ -1054,21 +1130,20 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, * Obtains the current register state for the VCPU specified by vcpuid * and stores it at the location given by regs. */ -void vcpu_regs_get(struct kvm_vm *vm, - uint32_t vcpuid, struct kvm_regs *regs) +void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs) { struct vcpu *vcpu = vcpu_find(vm, vcpuid); int ret; TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - /* Get the regs. */ ret = ioctl(vcpu->fd, KVM_GET_REGS, regs); TEST_ASSERT(ret == 0, "KVM_GET_REGS failed, rc: %i errno: %i", ret, errno); } -/* VM VCPU Regs Set +/* + * VM VCPU Regs Set * * Input Args: * vm - Virtual Machine @@ -1082,99 +1157,46 @@ void vcpu_regs_get(struct kvm_vm *vm, * Sets the regs of the VCPU specified by vcpuid to the values * given by regs. */ -void vcpu_regs_set(struct kvm_vm *vm, - uint32_t vcpuid, struct kvm_regs *regs) +void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs) { struct vcpu *vcpu = vcpu_find(vm, vcpuid); int ret; TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - /* Set the regs. */ ret = ioctl(vcpu->fd, KVM_SET_REGS, regs); TEST_ASSERT(ret == 0, "KVM_SET_REGS failed, rc: %i errno: %i", ret, errno); } void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_vcpu_events *events) + struct kvm_vcpu_events *events) { struct vcpu *vcpu = vcpu_find(vm, vcpuid); int ret; TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - /* Get the regs. */ ret = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, events); TEST_ASSERT(ret == 0, "KVM_GET_VCPU_EVENTS, failed, rc: %i errno: %i", ret, errno); } void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_vcpu_events *events) + struct kvm_vcpu_events *events) { struct vcpu *vcpu = vcpu_find(vm, vcpuid); int ret; TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - /* Set the regs. */ ret = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, events); TEST_ASSERT(ret == 0, "KVM_SET_VCPU_EVENTS, failed, rc: %i errno: %i", ret, errno); } -/* VM VCPU Args Set - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * num - number of arguments - * ... - arguments, each of type uint64_t - * - * Output Args: None - * - * Return: None - * - * Sets the first num function input arguments to the values - * given as variable args. Each of the variable args is expected to - * be of type uint64_t. - */ -void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) -{ - va_list ap; - struct kvm_regs regs; - - TEST_ASSERT(num >= 1 && num <= 6, "Unsupported number of args,\n" - " num: %u\n", - num); - - va_start(ap, num); - vcpu_regs_get(vm, vcpuid, ®s); - - if (num >= 1) - regs.rdi = va_arg(ap, uint64_t); - - if (num >= 2) - regs.rsi = va_arg(ap, uint64_t); - - if (num >= 3) - regs.rdx = va_arg(ap, uint64_t); - - if (num >= 4) - regs.rcx = va_arg(ap, uint64_t); - - if (num >= 5) - regs.r8 = va_arg(ap, uint64_t); - - if (num >= 6) - regs.r9 = va_arg(ap, uint64_t); - - vcpu_regs_set(vm, vcpuid, ®s); - va_end(ap); -} - -/* VM VCPU System Regs Get +/* + * VM VCPU System Regs Get * * Input Args: * vm - Virtual Machine @@ -1188,22 +1210,20 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) * Obtains the current system register state for the VCPU specified by * vcpuid and stores it at the location given by sregs. */ -void vcpu_sregs_get(struct kvm_vm *vm, - uint32_t vcpuid, struct kvm_sregs *sregs) +void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs) { struct vcpu *vcpu = vcpu_find(vm, vcpuid); int ret; TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - /* Get the regs. */ - /* Get the regs. */ ret = ioctl(vcpu->fd, KVM_GET_SREGS, sregs); TEST_ASSERT(ret == 0, "KVM_GET_SREGS failed, rc: %i errno: %i", ret, errno); } -/* VM VCPU System Regs Set +/* + * VM VCPU System Regs Set * * Input Args: * vm - Virtual Machine @@ -1217,27 +1237,25 @@ void vcpu_sregs_get(struct kvm_vm *vm, * Sets the system regs of the VCPU specified by vcpuid to the values * given by sregs. */ -void vcpu_sregs_set(struct kvm_vm *vm, - uint32_t vcpuid, struct kvm_sregs *sregs) +void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs) { int ret = _vcpu_sregs_set(vm, vcpuid, sregs); TEST_ASSERT(ret == 0, "KVM_RUN IOCTL failed, " "rc: %i errno: %i", ret, errno); } -int _vcpu_sregs_set(struct kvm_vm *vm, - uint32_t vcpuid, struct kvm_sregs *sregs) +int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs) { struct vcpu *vcpu = vcpu_find(vm, vcpuid); int ret; TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - /* Get the regs. */ return ioctl(vcpu->fd, KVM_SET_SREGS, sregs); } -/* VCPU Ioctl +/* + * VCPU Ioctl * * Input Args: * vm - Virtual Machine @@ -1249,8 +1267,8 @@ int _vcpu_sregs_set(struct kvm_vm *vm, * * Issues an arbitrary ioctl on a VCPU fd. */ -void vcpu_ioctl(struct kvm_vm *vm, - uint32_t vcpuid, unsigned long cmd, void *arg) +void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, + unsigned long cmd, void *arg) { struct vcpu *vcpu = vcpu_find(vm, vcpuid); int ret; @@ -1262,7 +1280,8 @@ void vcpu_ioctl(struct kvm_vm *vm, cmd, ret, errno, strerror(errno)); } -/* VM Ioctl +/* + * VM Ioctl * * Input Args: * vm - Virtual Machine @@ -1282,7 +1301,8 @@ void vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg) cmd, ret, errno, strerror(errno)); } -/* VM Dump +/* + * VM Dump * * Input Args: * vm - Virtual Machine @@ -1329,38 +1349,6 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) vcpu_dump(stream, vm, vcpu->id, indent + 2); } -/* VM VCPU Dump - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * indent - Left margin indent amount - * - * Output Args: - * stream - Output FILE stream - * - * Return: None - * - * Dumps the current state of the VCPU specified by vcpuid, within the VM - * given by vm, to the FILE stream given by stream. - */ -void vcpu_dump(FILE *stream, struct kvm_vm *vm, - uint32_t vcpuid, uint8_t indent) -{ - struct kvm_regs regs; - struct kvm_sregs sregs; - - fprintf(stream, "%*scpuid: %u\n", indent, "", vcpuid); - - fprintf(stream, "%*sregs:\n", indent + 2, ""); - vcpu_regs_get(vm, vcpuid, ®s); - regs_dump(stream, ®s, indent + 4); - - fprintf(stream, "%*ssregs:\n", indent + 2, ""); - vcpu_sregs_get(vm, vcpuid, &sregs); - sregs_dump(stream, &sregs, indent + 4); -} - /* Known KVM exit reasons */ static struct exit_reason { unsigned int reason; @@ -1391,7 +1379,8 @@ static struct exit_reason { #endif }; -/* Exit Reason String +/* + * Exit Reason String * * Input Args: * exit_reason - Exit reason @@ -1417,10 +1406,12 @@ const char *exit_reason_str(unsigned int exit_reason) return "Unknown"; } -/* Physical Page Allocate +/* + * Physical Contiguous Page Allocator * * Input Args: * vm - Virtual Machine + * num - number of pages * paddr_min - Physical address minimum * memslot - Memory region to allocate page from * @@ -1429,47 +1420,59 @@ const char *exit_reason_str(unsigned int exit_reason) * Return: * Starting physical address * - * Within the VM specified by vm, locates an available physical page - * at or above paddr_min. If found, the page is marked as in use - * and its address is returned. A TEST_ASSERT failure occurs if no - * page is available at or above paddr_min. + * Within the VM specified by vm, locates a range of available physical + * pages at or above paddr_min. If found, the pages are marked as in use + * and thier base address is returned. A TEST_ASSERT failure occurs if + * not enough pages are available at or above paddr_min. */ -vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, - vm_paddr_t paddr_min, uint32_t memslot) +vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, + vm_paddr_t paddr_min, uint32_t memslot) { struct userspace_mem_region *region; - sparsebit_idx_t pg; + sparsebit_idx_t pg, base; + + TEST_ASSERT(num > 0, "Must allocate at least one page"); TEST_ASSERT((paddr_min % vm->page_size) == 0, "Min physical address " "not divisible by page size.\n" " paddr_min: 0x%lx page_size: 0x%x", paddr_min, vm->page_size); - /* Locate memory region. */ region = memslot2region(vm, memslot); + base = pg = paddr_min >> vm->page_shift; - /* Locate next available physical page at or above paddr_min. */ - pg = paddr_min >> vm->page_shift; - - if (!sparsebit_is_set(region->unused_phy_pages, pg)) { - pg = sparsebit_next_set(region->unused_phy_pages, pg); - if (pg == 0) { - fprintf(stderr, "No guest physical page available, " - "paddr_min: 0x%lx page_size: 0x%x memslot: %u", - paddr_min, vm->page_size, memslot); - fputs("---- vm dump ----\n", stderr); - vm_dump(stderr, vm, 2); - abort(); + do { + for (; pg < base + num; ++pg) { + if (!sparsebit_is_set(region->unused_phy_pages, pg)) { + base = pg = sparsebit_next_set(region->unused_phy_pages, pg); + break; + } } + } while (pg && pg != base + num); + + if (pg == 0) { + fprintf(stderr, "No guest physical page available, " + "paddr_min: 0x%lx page_size: 0x%x memslot: %u\n", + paddr_min, vm->page_size, memslot); + fputs("---- vm dump ----\n", stderr); + vm_dump(stderr, vm, 2); + abort(); } - /* Specify page as in use and return its address. */ - sparsebit_clear(region->unused_phy_pages, pg); + for (pg = base; pg < base + num; ++pg) + sparsebit_clear(region->unused_phy_pages, pg); - return pg * vm->page_size; + return base * vm->page_size; } -/* Address Guest Virtual to Host Virtual +vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, + uint32_t memslot) +{ + return vm_phy_pages_alloc(vm, 1, paddr_min, memslot); +} + +/* + * Address Guest Virtual to Host Virtual * * Input Args: * vm - Virtual Machine diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index a0bd1980c81c..52701db0f253 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -1,28 +1,29 @@ /* - * tools/testing/selftests/kvm/lib/kvm_util.c + * tools/testing/selftests/kvm/lib/kvm_util_internal.h * * Copyright (C) 2018, Google LLC. * * This work is licensed under the terms of the GNU GPL, version 2. */ -#ifndef KVM_UTIL_INTERNAL_H -#define KVM_UTIL_INTERNAL_H 1 +#ifndef SELFTEST_KVM_UTIL_INTERNAL_H +#define SELFTEST_KVM_UTIL_INTERNAL_H #include "sparsebit.h" +#define KVM_DEV_PATH "/dev/kvm" + #ifndef BITS_PER_BYTE -#define BITS_PER_BYTE 8 +#define BITS_PER_BYTE 8 #endif #ifndef BITS_PER_LONG -#define BITS_PER_LONG (BITS_PER_BYTE * sizeof(long)) +#define BITS_PER_LONG (BITS_PER_BYTE * sizeof(long)) #endif #define DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) -#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_LONG) +#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_LONG) -/* Concrete definition of struct kvm_vm. */ struct userspace_mem_region { struct userspace_mem_region *next, *prev; struct kvm_userspace_memory_region region; @@ -43,25 +44,30 @@ struct vcpu { struct kvm_vm { int mode; + int kvm_fd; int fd; + unsigned int pgtable_levels; unsigned int page_size; unsigned int page_shift; + unsigned int pa_bits; + unsigned int va_bits; uint64_t max_gfn; struct vcpu *vcpu_head; struct userspace_mem_region *userspace_mem_region_head; struct sparsebit *vpages_valid; struct sparsebit *vpages_mapped; + bool has_irqchip; bool pgd_created; vm_paddr_t pgd; + vm_vaddr_t gdt; + vm_vaddr_t tss; }; -struct vcpu *vcpu_find(struct kvm_vm *vm, - uint32_t vcpuid); -void vcpu_setup(struct kvm_vm *vm, int vcpuid); +struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid); +void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, + int gdt_memslot); void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); -void regs_dump(FILE *stream, struct kvm_regs *regs, - uint8_t indent); -void sregs_dump(FILE *stream, struct kvm_sregs *sregs, - uint8_t indent); +void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent); +void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent); -#endif +#endif /* SELFTEST_KVM_UTIL_INTERNAL_H */ diff --git a/tools/testing/selftests/kvm/lib/ucall.c b/tools/testing/selftests/kvm/lib/ucall.c new file mode 100644 index 000000000000..4777f9bb5194 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/ucall.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ucall support. A ucall is a "hypercall to userspace". + * + * Copyright (C) 2018, Red Hat, Inc. + */ +#include "kvm_util.h" +#include "kvm_util_internal.h" + +#define UCALL_PIO_PORT ((uint16_t)0x1000) + +static ucall_type_t ucall_type; +static vm_vaddr_t *ucall_exit_mmio_addr; + +static bool ucall_mmio_init(struct kvm_vm *vm, vm_paddr_t gpa) +{ + if (kvm_userspace_memory_region_find(vm, gpa, gpa + 1)) + return false; + + virt_pg_map(vm, gpa, gpa, 0); + + ucall_exit_mmio_addr = (vm_vaddr_t *)gpa; + sync_global_to_guest(vm, ucall_exit_mmio_addr); + + return true; +} + +void ucall_init(struct kvm_vm *vm, ucall_type_t type, void *arg) +{ + ucall_type = type; + sync_global_to_guest(vm, ucall_type); + + if (type == UCALL_PIO) + return; + + if (type == UCALL_MMIO) { + vm_paddr_t gpa, start, end, step; + bool ret; + + if (arg) { + gpa = (vm_paddr_t)arg; + ret = ucall_mmio_init(vm, gpa); + TEST_ASSERT(ret, "Can't set ucall mmio address to %lx", gpa); + return; + } + + /* + * Find an address within the allowed virtual address space, + * that does _not_ have a KVM memory region associated with it. + * Identity mapping an address like this allows the guest to + * access it, but as KVM doesn't know what to do with it, it + * will assume it's something userspace handles and exit with + * KVM_EXIT_MMIO. Well, at least that's how it works for AArch64. + * Here we start with a guess that the addresses around two + * thirds of the VA space are unmapped and then work both down + * and up from there in 1/6 VA space sized steps. + */ + start = 1ul << (vm->va_bits * 2 / 3); + end = 1ul << vm->va_bits; + step = 1ul << (vm->va_bits / 6); + for (gpa = start; gpa >= 0; gpa -= step) { + if (ucall_mmio_init(vm, gpa & ~(vm->page_size - 1))) + return; + } + for (gpa = start + step; gpa < end; gpa += step) { + if (ucall_mmio_init(vm, gpa & ~(vm->page_size - 1))) + return; + } + TEST_ASSERT(false, "Can't find a ucall mmio address"); + } +} + +void ucall_uninit(struct kvm_vm *vm) +{ + ucall_type = 0; + sync_global_to_guest(vm, ucall_type); + ucall_exit_mmio_addr = 0; + sync_global_to_guest(vm, ucall_exit_mmio_addr); +} + +static void ucall_pio_exit(struct ucall *uc) +{ +#ifdef __x86_64__ + asm volatile("in %[port], %%al" + : : [port] "d" (UCALL_PIO_PORT), "D" (uc) : "rax"); +#endif +} + +static void ucall_mmio_exit(struct ucall *uc) +{ + *ucall_exit_mmio_addr = (vm_vaddr_t)uc; +} + +void ucall(uint64_t cmd, int nargs, ...) +{ + struct ucall uc = { + .cmd = cmd, + }; + va_list va; + int i; + + nargs = nargs <= UCALL_MAX_ARGS ? 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); + + switch (ucall_type) { + case UCALL_PIO: + ucall_pio_exit(&uc); + break; + case UCALL_MMIO: + ucall_mmio_exit(&uc); + break; + }; +} + +uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) +{ + struct kvm_run *run = vcpu_state(vm, vcpu_id); + + memset(uc, 0, sizeof(*uc)); + +#ifdef __x86_64__ + if (ucall_type == UCALL_PIO && run->exit_reason == KVM_EXIT_IO && + run->io.port == UCALL_PIO_PORT) { + struct kvm_regs regs; + vcpu_regs_get(vm, vcpu_id, ®s); + memcpy(uc, addr_gva2hva(vm, (vm_vaddr_t)regs.rdi), sizeof(*uc)); + return uc->cmd; + } +#endif + if (ucall_type == UCALL_MMIO && run->exit_reason == KVM_EXIT_MMIO && + run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) { + vm_vaddr_t gva; + TEST_ASSERT(run->mmio.is_write && run->mmio.len == 8, + "Unexpected ucall exit mmio address access"); + gva = *(vm_vaddr_t *)run->mmio.data; + memcpy(uc, addr_gva2hva(vm, gva), sizeof(*uc)); + } + + return uc->cmd; +} diff --git a/tools/testing/selftests/kvm/lib/x86.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 2f17675f4275..f28127f4a3af 100644 --- a/tools/testing/selftests/kvm/lib/x86.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1,5 +1,5 @@ /* - * tools/testing/selftests/kvm/lib/x86.c + * tools/testing/selftests/kvm/lib/x86_64/processor.c * * Copyright (C) 2018, Google LLC. * @@ -10,8 +10,8 @@ #include "test_util.h" #include "kvm_util.h" -#include "kvm_util_internal.h" -#include "x86.h" +#include "../kvm_util_internal.h" +#include "processor.h" /* Minimum physical address used for virtual translation tables. */ #define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 @@ -231,7 +231,7 @@ void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot) { int rc; - TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use " + TEST_ASSERT(vm->mode == VM_MODE_P52V48_4K, "Attempt to use " "unknown or unsupported guest mode, mode: 0x%x", vm->mode); /* If needed, create page map l4 table. */ @@ -239,25 +239,6 @@ void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot) vm_paddr_t paddr = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot); vm->pgd = paddr; - - /* Set pointer to pgd tables in all the VCPUs that - * have already been created. Future VCPUs will have - * the value set as each one is created. - */ - for (struct vcpu *vcpu = vm->vcpu_head; vcpu; - vcpu = vcpu->next) { - struct kvm_sregs sregs; - - /* Obtain the current system register settings */ - vcpu_sregs_get(vm, vcpu->id, &sregs); - - /* Set and store the pointer to the start of the - * pgd tables. - */ - sregs.cr3 = vm->pgd; - vcpu_sregs_set(vm, vcpu->id, &sregs); - } - vm->pgd_created = true; } } @@ -283,7 +264,7 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, uint16_t index[4]; struct pageMapL4Entry *pml4e; - TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use " + TEST_ASSERT(vm->mode == VM_MODE_P52V48_4K, "Attempt to use " "unknown or unsupported guest mode, mode: 0x%x", vm->mode); TEST_ASSERT((vaddr % vm->page_size) == 0, @@ -460,9 +441,32 @@ static void kvm_seg_set_unusable(struct kvm_segment *segp) segp->unusable = true; } +static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp) +{ + void *gdt = addr_gva2hva(vm, vm->gdt); + struct desc64 *desc = gdt + (segp->selector >> 3) * 8; + + desc->limit0 = segp->limit & 0xFFFF; + desc->base0 = segp->base & 0xFFFF; + desc->base1 = segp->base >> 16; + desc->s = segp->s; + desc->type = segp->type; + desc->dpl = segp->dpl; + desc->p = segp->present; + desc->limit1 = segp->limit >> 16; + desc->l = segp->l; + desc->db = segp->db; + desc->g = segp->g; + desc->base2 = segp->base >> 24; + if (!segp->s) + desc->base3 = segp->base >> 32; +} + + /* Set Long Mode Flat Kernel Code Segment * * Input Args: + * vm - VM whose GDT is being filled, or NULL to only write segp * selector - selector value * * Output Args: @@ -473,7 +477,7 @@ static void kvm_seg_set_unusable(struct kvm_segment *segp) * Sets up the KVM segment pointed to by segp, to be a code segment * with the selector value given by selector. */ -static void kvm_seg_set_kernel_code_64bit(uint16_t selector, +static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector, struct kvm_segment *segp) { memset(segp, 0, sizeof(*segp)); @@ -486,11 +490,14 @@ static void kvm_seg_set_kernel_code_64bit(uint16_t selector, segp->g = true; segp->l = true; segp->present = 1; + if (vm) + kvm_seg_fill_gdt_64bit(vm, segp); } /* Set Long Mode Flat Kernel Data Segment * * Input Args: + * vm - VM whose GDT is being filled, or NULL to only write segp * selector - selector value * * Output Args: @@ -501,7 +508,7 @@ static void kvm_seg_set_kernel_code_64bit(uint16_t selector, * Sets up the KVM segment pointed to by segp, to be a data segment * with the selector value given by selector. */ -static void kvm_seg_set_kernel_data_64bit(uint16_t selector, +static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector, struct kvm_segment *segp) { memset(segp, 0, sizeof(*segp)); @@ -513,6 +520,8 @@ static void kvm_seg_set_kernel_data_64bit(uint16_t selector, */ segp->g = true; segp->present = true; + if (vm) + kvm_seg_fill_gdt_64bit(vm, segp); } /* Address Guest Virtual to Guest Physical @@ -542,7 +551,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) struct pageTableEntry *pte; void *hva; - TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use " + TEST_ASSERT(vm->mode == VM_MODE_P52V48_4K, "Attempt to use " "unknown or unsupported guest mode, mode: 0x%x", vm->mode); index[0] = (gva >> 12) & 0x1ffu; @@ -575,44 +584,64 @@ unmapped_gva: "gva: 0x%lx", gva); } -void vcpu_setup(struct kvm_vm *vm, int vcpuid) +static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt, int gdt_memslot, + int pgd_memslot) +{ + if (!vm->gdt) + vm->gdt = vm_vaddr_alloc(vm, getpagesize(), + KVM_UTIL_MIN_VADDR, gdt_memslot, pgd_memslot); + + dt->base = vm->gdt; + dt->limit = getpagesize(); +} + +static void kvm_setup_tss_64bit(struct kvm_vm *vm, struct kvm_segment *segp, + int selector, int gdt_memslot, + int pgd_memslot) +{ + if (!vm->tss) + vm->tss = vm_vaddr_alloc(vm, getpagesize(), + KVM_UTIL_MIN_VADDR, gdt_memslot, pgd_memslot); + + memset(segp, 0, sizeof(*segp)); + segp->base = vm->tss; + segp->limit = 0x67; + segp->selector = selector; + segp->type = 0xb; + segp->present = 1; + kvm_seg_fill_gdt_64bit(vm, segp); +} + +void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot) { struct kvm_sregs sregs; /* Set mode specific system register values. */ vcpu_sregs_get(vm, vcpuid, &sregs); + sregs.idt.limit = 0; + + kvm_setup_gdt(vm, &sregs.gdt, gdt_memslot, pgd_memslot); + switch (vm->mode) { - case VM_MODE_FLAT48PG: + case VM_MODE_P52V48_4K: sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG; - sregs.cr4 |= X86_CR4_PAE; + sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR; sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX); kvm_seg_set_unusable(&sregs.ldt); - kvm_seg_set_kernel_code_64bit(0x8, &sregs.cs); - kvm_seg_set_kernel_data_64bit(0x10, &sregs.ds); - kvm_seg_set_kernel_data_64bit(0x10, &sregs.es); + kvm_seg_set_kernel_code_64bit(vm, 0x8, &sregs.cs); + kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.ds); + kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.es); + kvm_setup_tss_64bit(vm, &sregs.tr, 0x18, gdt_memslot, pgd_memslot); break; default: TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode); } - vcpu_sregs_set(vm, vcpuid, &sregs); - /* If virtual translation table have been setup, set system register - * to point to the tables. It's okay if they haven't been setup yet, - * in that the code that sets up the virtual translation tables, will - * go back through any VCPUs that have already been created and set - * their values. - */ - if (vm->pgd_created) { - struct kvm_sregs sregs; - - vcpu_sregs_get(vm, vcpuid, &sregs); - - sregs.cr3 = vm->pgd; - vcpu_sregs_set(vm, vcpuid, &sregs); - } + sregs.cr3 = vm->pgd; + vcpu_sregs_set(vm, vcpuid, &sregs); } /* Adds a vCPU with reasonable defaults (i.e., a stack) * @@ -629,7 +658,7 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) DEFAULT_GUEST_STACK_VADDR_MIN, 0, 0); /* Create VCPU */ - vm_vcpu_add(vm, vcpuid); + vm_vcpu_add(vm, vcpuid, 0, 0); /* Setup guest general purpose registers */ vcpu_regs_get(vm, vcpuid, ®s); @@ -643,6 +672,102 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) vcpu_set_mp_state(vm, vcpuid, &mp_state); } +/* Allocate an instance of struct kvm_cpuid2 + * + * Input Args: None + * + * Output Args: None + * + * Return: A pointer to the allocated struct. The caller is responsible + * for freeing this struct. + * + * Since kvm_cpuid2 uses a 0-length array to allow a the size of the + * array to be decided at allocation time, allocation is slightly + * complicated. This function uses a reasonable default length for + * the array and performs the appropriate allocation. + */ +static struct kvm_cpuid2 *allocate_kvm_cpuid2(void) +{ + struct kvm_cpuid2 *cpuid; + int nent = 100; + size_t size; + + size = sizeof(*cpuid); + size += nent * sizeof(struct kvm_cpuid_entry2); + cpuid = malloc(size); + if (!cpuid) { + perror("malloc"); + abort(); + } + + cpuid->nent = nent; + + return cpuid; +} + +/* KVM Supported CPUID Get + * + * Input Args: None + * + * Output Args: + * + * Return: The supported KVM CPUID + * + * Get the guest CPUID supported by KVM. + */ +struct kvm_cpuid2 *kvm_get_supported_cpuid(void) +{ + static struct kvm_cpuid2 *cpuid; + int ret; + int kvm_fd; + + if (cpuid) + return cpuid; + + cpuid = allocate_kvm_cpuid2(); + kvm_fd = open(KVM_DEV_PATH, O_RDONLY); + if (kvm_fd < 0) + exit(KSFT_SKIP); + + ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid); + TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n", + ret, errno); + + close(kvm_fd); + return cpuid; +} + +/* Locate a cpuid entry. + * + * Input Args: + * cpuid: The cpuid. + * function: The function of the cpuid entry to find. + * + * Output Args: None + * + * Return: A pointer to the cpuid entry. Never returns NULL. + */ +struct kvm_cpuid_entry2 * +kvm_get_supported_cpuid_index(uint32_t function, uint32_t index) +{ + struct kvm_cpuid2 *cpuid; + struct kvm_cpuid_entry2 *entry = NULL; + int i; + + cpuid = kvm_get_supported_cpuid(); + for (i = 0; i < cpuid->nent; i++) { + if (cpuid->entries[i].function == function && + cpuid->entries[i].index == index) { + entry = &cpuid->entries[i]; + break; + } + } + + TEST_ASSERT(entry, "Guest CPUID entry not found: (EAX=%x, ECX=%x).", + function, index); + return entry; +} + /* VM VCPU CPUID Set * * Input Args: @@ -669,10 +794,14 @@ void vcpu_set_cpuid(struct kvm_vm *vm, rc, errno); } + /* Create a VM with reasonable defaults * * Input Args: * vcpuid - The id of the single VCPU to add to the VM. + * extra_mem_pages - The size of extra memories to add (this will + * decide how much extra space we will need to + * setup the page tables using mem slot 0) * guest_code - The vCPU's entry point * * Output Args: None @@ -680,12 +809,23 @@ void vcpu_set_cpuid(struct kvm_vm *vm, * Return: * Pointer to opaque structure that describes the created VM. */ -struct kvm_vm *vm_create_default(uint32_t vcpuid, void *guest_code) +struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, + void *guest_code) { struct kvm_vm *vm; + /* + * For x86 the maximum page table size for a memory region + * will be when only 4K pages are used. In that case the + * total extra size for page tables (for extra N pages) will + * be: N/512+N/512^2+N/512^3+... which is definitely smaller + * than N/512*2. + */ + uint64_t extra_pg_pages = extra_mem_pages / 512 * 2; /* Create VM */ - vm = vm_create(VM_MODE_FLAT48PG, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + vm = vm_create(VM_MODE_P52V48_4K, + DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, + O_RDWR); /* Setup guest code */ kvm_vm_elf_load(vm, program_invocation_name, 0, 0); @@ -698,3 +838,296 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, void *guest_code) return vm; } + +/* VCPU Get MSR + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * msr_index - Index of MSR + * + * Output Args: None + * + * Return: On success, value of the MSR. On failure a TEST_ASSERT is produced. + * + * Get value of MSR for VCPU. + */ +uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + struct { + struct kvm_msrs header; + struct kvm_msr_entry entry; + } buffer = {}; + int r; + + TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); + buffer.header.nmsrs = 1; + buffer.entry.index = msr_index; + r = ioctl(vcpu->fd, KVM_GET_MSRS, &buffer.header); + TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n" + " rc: %i errno: %i", r, errno); + + return buffer.entry.data; +} + +/* VCPU Set MSR + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * msr_index - Index of MSR + * msr_value - New value of MSR + * + * Output Args: None + * + * Return: On success, nothing. On failure a TEST_ASSERT is produced. + * + * Set value of MSR for VCPU. + */ +void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, + uint64_t msr_value) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + struct { + struct kvm_msrs header; + struct kvm_msr_entry entry; + } buffer = {}; + int r; + + TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); + memset(&buffer, 0, sizeof(buffer)); + buffer.header.nmsrs = 1; + buffer.entry.index = msr_index; + buffer.entry.data = msr_value; + r = ioctl(vcpu->fd, KVM_SET_MSRS, &buffer.header); + TEST_ASSERT(r == 1, "KVM_SET_MSRS IOCTL failed,\n" + " rc: %i errno: %i", r, errno); +} + +/* VM VCPU Args Set + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * num - number of arguments + * ... - arguments, each of type uint64_t + * + * Output Args: None + * + * Return: None + * + * Sets the first num function input arguments to the values + * given as variable args. Each of the variable args is expected to + * be of type uint64_t. + */ +void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) +{ + va_list ap; + struct kvm_regs regs; + + TEST_ASSERT(num >= 1 && num <= 6, "Unsupported number of args,\n" + " num: %u\n", + num); + + va_start(ap, num); + vcpu_regs_get(vm, vcpuid, ®s); + + if (num >= 1) + regs.rdi = va_arg(ap, uint64_t); + + if (num >= 2) + regs.rsi = va_arg(ap, uint64_t); + + if (num >= 3) + regs.rdx = va_arg(ap, uint64_t); + + if (num >= 4) + regs.rcx = va_arg(ap, uint64_t); + + if (num >= 5) + regs.r8 = va_arg(ap, uint64_t); + + if (num >= 6) + regs.r9 = va_arg(ap, uint64_t); + + vcpu_regs_set(vm, vcpuid, ®s); + va_end(ap); +} + +/* + * VM VCPU Dump + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * indent - Left margin indent amount + * + * Output Args: + * stream - Output FILE stream + * + * Return: None + * + * Dumps the current state of the VCPU specified by vcpuid, within the VM + * given by vm, to the FILE stream given by stream. + */ +void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) +{ + struct kvm_regs regs; + struct kvm_sregs sregs; + + fprintf(stream, "%*scpuid: %u\n", indent, "", vcpuid); + + fprintf(stream, "%*sregs:\n", indent + 2, ""); + vcpu_regs_get(vm, vcpuid, ®s); + regs_dump(stream, ®s, indent + 4); + + fprintf(stream, "%*ssregs:\n", indent + 2, ""); + vcpu_sregs_get(vm, vcpuid, &sregs); + sregs_dump(stream, &sregs, indent + 4); +} + +struct kvm_x86_state { + struct kvm_vcpu_events events; + struct kvm_mp_state mp_state; + struct kvm_regs regs; + struct kvm_xsave xsave; + struct kvm_xcrs xcrs; + struct kvm_sregs sregs; + struct kvm_debugregs debugregs; + union { + struct kvm_nested_state nested; + char nested_[16384]; + }; + struct kvm_msrs msrs; +}; + +static int kvm_get_num_msrs(struct kvm_vm *vm) +{ + struct kvm_msr_list nmsrs; + int r; + + nmsrs.nmsrs = 0; + r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, &nmsrs); + TEST_ASSERT(r == -1 && errno == E2BIG, "Unexpected result from KVM_GET_MSR_INDEX_LIST probe, r: %i", + r); + + return nmsrs.nmsrs; +} + +struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + struct kvm_msr_list *list; + struct kvm_x86_state *state; + int nmsrs, r, i; + static int nested_size = -1; + + if (nested_size == -1) { + nested_size = kvm_check_cap(KVM_CAP_NESTED_STATE); + TEST_ASSERT(nested_size <= sizeof(state->nested_), + "Nested state size too big, %i > %zi", + nested_size, sizeof(state->nested_)); + } + + nmsrs = kvm_get_num_msrs(vm); + list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); + list->nmsrs = nmsrs; + r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, list); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i", + r); + + state = malloc(sizeof(*state) + nmsrs * sizeof(state->msrs.entries[0])); + r = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, &state->events); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_VCPU_EVENTS, r: %i", + r); + + r = ioctl(vcpu->fd, KVM_GET_MP_STATE, &state->mp_state); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MP_STATE, r: %i", + r); + + r = ioctl(vcpu->fd, KVM_GET_REGS, &state->regs); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_REGS, r: %i", + r); + + r = ioctl(vcpu->fd, KVM_GET_XSAVE, &state->xsave); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i", + r); + + r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XCRS, r: %i", + r); + + r = ioctl(vcpu->fd, KVM_GET_SREGS, &state->sregs); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i", + r); + + if (nested_size) { + state->nested.size = sizeof(state->nested_); + r = ioctl(vcpu->fd, KVM_GET_NESTED_STATE, &state->nested); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_NESTED_STATE, r: %i", + r); + TEST_ASSERT(state->nested.size <= nested_size, + "Nested state size too big, %i (KVM_CHECK_CAP gave %i)", + state->nested.size, nested_size); + } else + state->nested.size = 0; + + state->msrs.nmsrs = nmsrs; + for (i = 0; i < nmsrs; i++) + state->msrs.entries[i].index = list->indices[i]; + r = ioctl(vcpu->fd, KVM_GET_MSRS, &state->msrs); + TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed at %x)", + r, r == nmsrs ? -1 : list->indices[r]); + + r = ioctl(vcpu->fd, KVM_GET_DEBUGREGS, &state->debugregs); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_DEBUGREGS, r: %i", + r); + + free(list); + return state; +} + +void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *state) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + int r; + + if (state->nested.size) { + r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i", + r); + } + + r = ioctl(vcpu->fd, KVM_SET_XSAVE, &state->xsave); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i", + r); + + r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XCRS, r: %i", + r); + + r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i", + r); + + r = ioctl(vcpu->fd, KVM_SET_MSRS, &state->msrs); + TEST_ASSERT(r == state->msrs.nmsrs, "Unexpected result from KVM_SET_MSRS, r: %i (failed at %x)", + r, r == state->msrs.nmsrs ? -1 : state->msrs.entries[r].index); + + r = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, &state->events); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_VCPU_EVENTS, r: %i", + r); + + r = ioctl(vcpu->fd, KVM_SET_MP_STATE, &state->mp_state); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_MP_STATE, r: %i", + r); + + r = ioctl(vcpu->fd, KVM_SET_DEBUGREGS, &state->debugregs); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_DEBUGREGS, r: %i", + r); + + r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i", + r); +} diff --git a/tools/testing/selftests/kvm/lib/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index 0231bc0aae7b..771ba6bf751c 100644 --- a/tools/testing/selftests/kvm/lib/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -1,5 +1,5 @@ /* - * tools/testing/selftests/kvm/lib/x86.c + * tools/testing/selftests/kvm/lib/x86_64/vmx.c * * Copyright (C) 2018, Google LLC. * @@ -10,50 +10,79 @@ #include "test_util.h" #include "kvm_util.h" -#include "x86.h" +#include "processor.h" #include "vmx.h" -/* Create a default VM for VMX tests. +bool enable_evmcs; + +/* Allocate memory regions for nested VMX tests. * * Input Args: - * vcpuid - The id of the single VCPU to add to the VM. - * guest_code - The vCPU's entry point + * vm - The VM to allocate guest-virtual addresses in. * - * Output Args: None + * Output Args: + * p_vmx_gva - The guest virtual address for the struct vmx_pages. * * Return: - * Pointer to opaque structure that describes the created VM. + * Pointer to structure with the addresses of the VMX areas. */ -struct kvm_vm * -vm_create_default_vmx(uint32_t vcpuid, vmx_guest_code_t guest_code) +struct vmx_pages * +vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva) { - struct kvm_cpuid2 *cpuid; - struct kvm_vm *vm; - vm_vaddr_t vmxon_vaddr; - vm_paddr_t vmxon_paddr; - vm_vaddr_t vmcs_vaddr; - vm_paddr_t vmcs_paddr; - - vm = vm_create_default(vcpuid, (void *) guest_code); - - /* Enable nesting in CPUID */ - vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid()); + vm_vaddr_t vmx_gva = vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + struct vmx_pages *vmx = addr_gva2hva(vm, vmx_gva); /* Setup of a region of guest memory for the vmxon region. */ - vmxon_vaddr = vm_vaddr_alloc(vm, getpagesize(), 0, 0, 0); - vmxon_paddr = addr_gva2gpa(vm, vmxon_vaddr); + vmx->vmxon = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + vmx->vmxon_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmxon); + vmx->vmxon_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmxon); /* Setup of a region of guest memory for a vmcs. */ - vmcs_vaddr = vm_vaddr_alloc(vm, getpagesize(), 0, 0, 0); - vmcs_paddr = addr_gva2gpa(vm, vmcs_vaddr); + vmx->vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + vmx->vmcs_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmcs); + vmx->vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmcs); + + /* Setup of a region of guest memory for the MSR bitmap. */ + vmx->msr = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + vmx->msr_hva = addr_gva2hva(vm, (uintptr_t)vmx->msr); + vmx->msr_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->msr); + memset(vmx->msr_hva, 0, getpagesize()); + + /* Setup of a region of guest memory for the shadow VMCS. */ + vmx->shadow_vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + vmx->shadow_vmcs_hva = addr_gva2hva(vm, (uintptr_t)vmx->shadow_vmcs); + vmx->shadow_vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->shadow_vmcs); - vcpu_args_set(vm, vcpuid, 4, vmxon_vaddr, vmxon_paddr, vmcs_vaddr, - vmcs_paddr); + /* Setup of a region of guest memory for the VMREAD and VMWRITE bitmaps. */ + vmx->vmread = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + vmx->vmread_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmread); + vmx->vmread_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmread); + memset(vmx->vmread_hva, 0, getpagesize()); - return vm; + vmx->vmwrite = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + vmx->vmwrite_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmwrite); + 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(vm, getpagesize(), + 0x10000, 0, 0); + 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(vm, getpagesize(), + 0x10000, 0, 0); + 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; } -void prepare_for_vmx_operation(void) +bool prepare_for_vmx_operation(struct vmx_pages *vmx) { uint64_t feature_control; uint64_t required; @@ -88,18 +117,55 @@ void prepare_for_vmx_operation(void) feature_control = rdmsr(MSR_IA32_FEATURE_CONTROL); if ((feature_control & required) != required) wrmsr(MSR_IA32_FEATURE_CONTROL, feature_control | required); + + /* Enter VMX root operation. */ + *(uint32_t *)(vmx->vmxon) = vmcs_revision(); + if (vmxon(vmx->vmxon_gpa)) + return false; + + return true; +} + +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 = vmcs_revision(); + } + + return true; } /* * Initialize the control fields to the most basic settings possible. */ -static inline void init_vmcs_control_fields(void) +static inline void init_vmcs_control_fields(struct vmx_pages *vmx) { vmwrite(VIRTUAL_PROCESSOR_ID, 0); vmwrite(POSTED_INTR_NV, 0); - vmwrite(PIN_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_PINBASED_CTLS)); - vmwrite(CPU_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_PROCBASED_CTLS)); + vmwrite(PIN_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PINBASED_CTLS)); + if (!vmwrite(SECONDARY_VM_EXEC_CONTROL, 0)) + vmwrite(CPU_BASED_VM_EXEC_CONTROL, + rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS) | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS); + else + vmwrite(CPU_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS)); vmwrite(EXCEPTION_BITMAP, 0); vmwrite(PAGE_FAULT_ERROR_CODE_MASK, 0); vmwrite(PAGE_FAULT_ERROR_CODE_MATCH, -1); /* Never match */ @@ -113,12 +179,15 @@ static inline void init_vmcs_control_fields(void) vmwrite(VM_ENTRY_MSR_LOAD_COUNT, 0); vmwrite(VM_ENTRY_INTR_INFO_FIELD, 0); vmwrite(TPR_THRESHOLD, 0); - vmwrite(SECONDARY_VM_EXEC_CONTROL, 0); vmwrite(CR0_GUEST_HOST_MASK, 0); vmwrite(CR4_GUEST_HOST_MASK, 0); vmwrite(CR0_READ_SHADOW, get_cr0()); vmwrite(CR4_READ_SHADOW, get_cr4()); + + vmwrite(MSR_BITMAP, vmx->msr_gpa); + vmwrite(VMREAD_BITMAP, vmx->vmread_gpa); + vmwrite(VMWRITE_BITMAP, vmx->vmwrite_gpa); } /* @@ -235,9 +304,9 @@ static inline void init_vmcs_guest_state(void *rip, void *rsp) vmwrite(GUEST_SYSENTER_EIP, vmreadz(HOST_IA32_SYSENTER_EIP)); } -void prepare_vmcs(void *guest_rip, void *guest_rsp) +void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp) { - init_vmcs_control_fields(); + init_vmcs_control_fields(vmx); init_vmcs_host_state(); init_vmcs_guest_state(guest_rip, guest_rsp); } diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c new file mode 100644 index 000000000000..d503a51fad30 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c @@ -0,0 +1,113 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * CR4 and CPUID sync test + * + * Copyright 2018, Red Hat, Inc. and/or its affiliates. + * + * Author: + * Wei Huang <wei@redhat.com> + */ + +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" + +#include "kvm_util.h" +#include "processor.h" + +#define X86_FEATURE_XSAVE (1<<26) +#define X86_FEATURE_OSXSAVE (1<<27) +#define VCPU_ID 1 + +static inline bool cr4_cpuid_is_sync(void) +{ + int func, subfunc; + uint32_t eax, ebx, ecx, edx; + uint64_t cr4; + + func = 0x1; + subfunc = 0x0; + __asm__ __volatile__("cpuid" + : "=a"(eax), "=b"(ebx), "=c"(ecx), "=d"(edx) + : "a"(func), "c"(subfunc)); + + cr4 = get_cr4(); + + return (!!(ecx & X86_FEATURE_OSXSAVE)) == (!!(cr4 & X86_CR4_OSXSAVE)); +} + +static void guest_code(void) +{ + uint64_t cr4; + + /* turn on CR4.OSXSAVE */ + cr4 = get_cr4(); + cr4 |= X86_CR4_OSXSAVE; + set_cr4(cr4); + + /* verify CR4.OSXSAVE == CPUID.OSXSAVE */ + GUEST_ASSERT(cr4_cpuid_is_sync()); + + /* notify hypervisor to change CR4 */ + GUEST_SYNC(0); + + /* check again */ + GUEST_ASSERT(cr4_cpuid_is_sync()); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + struct kvm_run *run; + struct kvm_vm *vm; + struct kvm_sregs sregs; + struct kvm_cpuid_entry2 *entry; + struct ucall uc; + int rc; + + entry = kvm_get_supported_cpuid_entry(1); + if (!(entry->ecx & X86_FEATURE_XSAVE)) { + printf("XSAVE feature not supported, skipping test\n"); + return 0; + } + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + run = vcpu_state(vm, VCPU_ID); + + while (1) { + rc = _vcpu_run(vm, VCPU_ID); + + if (run->exit_reason == KVM_EXIT_IO) { + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_SYNC: + /* emulate hypervisor clearing CR4.OSXSAVE */ + vcpu_sregs_get(vm, VCPU_ID, &sregs); + sregs.cr4 &= ~X86_CR4_OSXSAVE; + vcpu_sregs_set(vm, VCPU_ID, &sregs); + break; + case UCALL_ABORT: + TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit."); + break; + case UCALL_DONE: + goto done; + default: + TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); + } + } + } + + kvm_vm_free(vm); + +done: + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c new file mode 100644 index 000000000000..92c2cfd1b182 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2018, Red Hat, Inc. + * + * Tests for Enlightened VMCS, including nested guest state. + */ +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" + +#include "kvm_util.h" + +#include "vmx.h" + +#define VCPU_ID 5 + +static bool have_nested_state; + +void l2_guest_code(void) +{ + GUEST_SYNC(6); + + GUEST_SYNC(7); + + /* Done, exit to L1 and never come back. */ + vmcall(); +} + +void l1_guest_code(struct vmx_pages *vmx_pages) +{ +#define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + enable_vp_assist(vmx_pages->vp_assist_gpa, vmx_pages->vp_assist); + + GUEST_ASSERT(vmx_pages->vmcs_gpa); + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + GUEST_SYNC(3); + GUEST_ASSERT(load_vmcs(vmx_pages)); + GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa); + + GUEST_SYNC(4); + GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa); + + prepare_vmcs(vmx_pages, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + GUEST_SYNC(5); + GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa); + GUEST_ASSERT(!vmlaunch()); + GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa); + GUEST_SYNC(8); + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + GUEST_SYNC(9); +} + +void guest_code(struct vmx_pages *vmx_pages) +{ + GUEST_SYNC(1); + GUEST_SYNC(2); + + if (vmx_pages) + l1_guest_code(vmx_pages); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + struct vmx_pages *vmx_pages = NULL; + vm_vaddr_t vmx_pages_gva = 0; + + struct kvm_regs regs1, regs2; + struct kvm_vm *vm; + struct kvm_run *run; + struct kvm_x86_state *state; + struct ucall uc; + int stage; + uint16_t evmcs_ver; + struct kvm_enable_cap enable_evmcs_cap = { + .cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS, + .args[0] = (unsigned long)&evmcs_ver + }; + + struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + + if (!kvm_check_cap(KVM_CAP_NESTED_STATE) || + !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { + printf("capabilities not available, skipping test\n"); + exit(KSFT_SKIP); + } + + vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap); + + run = vcpu_state(vm, VCPU_ID); + + vcpu_regs_get(vm, VCPU_ID, ®s1); + + vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + + for (stage = 1;; stage++) { + _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + memset(®s1, 0, sizeof(regs1)); + vcpu_regs_get(vm, VCPU_ID, ®s1); + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0], + __FILE__, uc.args[1]); + /* NOT REACHED */ + case UCALL_SYNC: + break; + case UCALL_DONE: + goto done; + default: + TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); + } + + /* UCALL_SYNC is handled here. */ + TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && + uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx", + stage, (ulong)uc.args[1]); + + state = vcpu_save_state(vm, VCPU_ID); + kvm_vm_release(vm); + + /* Restore state in a new VM. */ + kvm_vm_restart(vm, O_RDWR); + vm_vcpu_add(vm, VCPU_ID, 0, 0); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + vcpu_load_state(vm, VCPU_ID, state); + run = vcpu_state(vm, VCPU_ID); + free(state); + + memset(®s2, 0, sizeof(regs2)); + vcpu_regs_get(vm, VCPU_ID, ®s2); + TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), + "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", + (ulong) regs2.rdi, (ulong) regs2.rsi); + } + +done: + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c new file mode 100644 index 000000000000..eb3e7a838cb4 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test for x86 KVM_CAP_MSR_PLATFORM_INFO + * + * Copyright (C) 2018, Google LLC. + * + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Verifies expected behavior of controlling guest access to + * MSR_PLATFORM_INFO. + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +#define VCPU_ID 0 +#define MSR_PLATFORM_INFO_MAX_TURBO_RATIO 0xff00 + +static void guest_code(void) +{ + uint64_t msr_platform_info; + + for (;;) { + msr_platform_info = rdmsr(MSR_PLATFORM_INFO); + GUEST_SYNC(msr_platform_info); + asm volatile ("inc %r11"); + } +} + +static void set_msr_platform_info_enabled(struct kvm_vm *vm, bool enable) +{ + struct kvm_enable_cap cap = {}; + + cap.cap = KVM_CAP_MSR_PLATFORM_INFO; + cap.flags = 0; + cap.args[0] = (int)enable; + vm_enable_cap(vm, &cap); +} + +static void test_msr_platform_info_enabled(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + set_msr_platform_info_enabled(vm, true); + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Exit_reason other than KVM_EXIT_IO: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + get_ucall(vm, VCPU_ID, &uc); + TEST_ASSERT(uc.cmd == UCALL_SYNC, + "Received ucall other than UCALL_SYNC: %u\n", + ucall); + TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) == + MSR_PLATFORM_INFO_MAX_TURBO_RATIO, + "Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.", + MSR_PLATFORM_INFO_MAX_TURBO_RATIO); +} + +static void test_msr_platform_info_disabled(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + + set_msr_platform_info_enabled(vm, false); + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, + "Exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vm *vm; + struct kvm_run *state; + int rv; + uint64_t msr_platform_info; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + rv = kvm_check_cap(KVM_CAP_MSR_PLATFORM_INFO); + if (!rv) { + fprintf(stderr, + "KVM_CAP_MSR_PLATFORM_INFO not supported, skip test\n"); + exit(KSFT_SKIP); + } + + vm = vm_create_default(VCPU_ID, 0, guest_code); + + msr_platform_info = vcpu_get_msr(vm, VCPU_ID, MSR_PLATFORM_INFO); + vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, + msr_platform_info | MSR_PLATFORM_INFO_MAX_TURBO_RATIO); + test_msr_platform_info_disabled(vm); + test_msr_platform_info_enabled(vm); + vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, msr_platform_info); + + kvm_vm_free(vm); + + return 0; +} diff --git a/tools/testing/selftests/kvm/set_sregs_test.c b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c index 090fd3f19352..35640e8e95bc 100644 --- a/tools/testing/selftests/kvm/set_sregs_test.c +++ b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c @@ -22,7 +22,7 @@ #include "test_util.h" #include "kvm_util.h" -#include "x86.h" +#include "processor.h" #define VCPU_ID 5 @@ -36,7 +36,7 @@ int main(int argc, char *argv[]) setbuf(stdout, NULL); /* Create VM */ - vm = vm_create_default(VCPU_ID, NULL); + vm = vm_create_default(VCPU_ID, 0, NULL); vcpu_sregs_get(vm, VCPU_ID, &sregs); sregs.apic_base = 1 << 10; diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c new file mode 100644 index 000000000000..03da41f0f736 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -0,0 +1,199 @@ +/* + * KVM_GET/SET_* tests + * + * Copyright (C) 2018, Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Tests for vCPU state save/restore, including nested guest state. + */ +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" + +#include "kvm_util.h" +#include "processor.h" +#include "vmx.h" + +#define VCPU_ID 5 + +static bool have_nested_state; + +void l2_guest_code(void) +{ + GUEST_SYNC(6); + + /* Exit to L1 */ + vmcall(); + + /* L1 has now set up a shadow VMCS for us. */ + GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee); + GUEST_SYNC(10); + GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee); + GUEST_ASSERT(!vmwrite(GUEST_RIP, 0xc0fffee)); + GUEST_SYNC(11); + GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0fffee); + GUEST_ASSERT(!vmwrite(GUEST_RIP, 0xc0ffffee)); + GUEST_SYNC(12); + + /* Done, exit to L1 and never come back. */ + vmcall(); +} + +void l1_guest_code(struct vmx_pages *vmx_pages) +{ +#define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + GUEST_ASSERT(vmx_pages->vmcs_gpa); + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + GUEST_SYNC(3); + GUEST_ASSERT(load_vmcs(vmx_pages)); + GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa); + + GUEST_SYNC(4); + GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa); + + prepare_vmcs(vmx_pages, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + GUEST_SYNC(5); + GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa); + GUEST_ASSERT(!vmlaunch()); + GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + + /* Check that the launched state is preserved. */ + GUEST_ASSERT(vmlaunch()); + + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + + GUEST_SYNC(7); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + + vmwrite(GUEST_RIP, vmreadz(GUEST_RIP) + 3); + + vmwrite(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS); + vmwrite(VMCS_LINK_POINTER, vmx_pages->shadow_vmcs_gpa); + + GUEST_ASSERT(!vmptrld(vmx_pages->shadow_vmcs_gpa)); + GUEST_ASSERT(vmlaunch()); + GUEST_SYNC(8); + GUEST_ASSERT(vmlaunch()); + GUEST_ASSERT(vmresume()); + + vmwrite(GUEST_RIP, 0xc0ffee); + GUEST_SYNC(9); + GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee); + + GUEST_ASSERT(!vmptrld(vmx_pages->vmcs_gpa)); + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + + GUEST_ASSERT(!vmptrld(vmx_pages->shadow_vmcs_gpa)); + GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffffee); + GUEST_ASSERT(vmlaunch()); + GUEST_ASSERT(vmresume()); + GUEST_SYNC(13); + GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffffee); + GUEST_ASSERT(vmlaunch()); + GUEST_ASSERT(vmresume()); +} + +void guest_code(struct vmx_pages *vmx_pages) +{ + GUEST_SYNC(1); + GUEST_SYNC(2); + + if (vmx_pages) + l1_guest_code(vmx_pages); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + struct vmx_pages *vmx_pages = NULL; + vm_vaddr_t vmx_pages_gva = 0; + + struct kvm_regs regs1, regs2; + struct kvm_vm *vm; + struct kvm_run *run; + struct kvm_x86_state *state; + struct ucall uc; + int stage; + + struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + run = vcpu_state(vm, VCPU_ID); + + vcpu_regs_get(vm, VCPU_ID, ®s1); + + if (kvm_check_cap(KVM_CAP_NESTED_STATE)) { + vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + } else { + printf("will skip nested state checks\n"); + vcpu_args_set(vm, VCPU_ID, 1, 0); + } + + for (stage = 1;; stage++) { + _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + memset(®s1, 0, sizeof(regs1)); + vcpu_regs_get(vm, VCPU_ID, ®s1); + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0], + __FILE__, uc.args[1]); + /* NOT REACHED */ + case UCALL_SYNC: + break; + case UCALL_DONE: + goto done; + default: + TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); + } + + /* UCALL_SYNC is handled here. */ + TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && + uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx", + stage, (ulong)uc.args[1]); + + state = vcpu_save_state(vm, VCPU_ID); + kvm_vm_release(vm); + + /* Restore state in a new VM. */ + kvm_vm_restart(vm, O_RDWR); + vm_vcpu_add(vm, VCPU_ID, 0, 0); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + vcpu_load_state(vm, VCPU_ID, state); + run = vcpu_state(vm, VCPU_ID); + free(state); + + memset(®s2, 0, sizeof(regs2)); + vcpu_regs_get(vm, VCPU_ID, ®s2); + TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), + "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", + (ulong) regs2.rdi, (ulong) regs2.rsi); + } + +done: + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c index eae1ece3c31b..c8478ce9ea77 100644 --- a/tools/testing/selftests/kvm/sync_regs_test.c +++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c @@ -19,31 +19,14 @@ #include "test_util.h" #include "kvm_util.h" -#include "x86.h" +#include "processor.h" #define VCPU_ID 5 -#define PORT_HOST_SYNC 0x1000 - -static void __exit_to_l0(uint16_t port, uint64_t arg0, uint64_t arg1) -{ - __asm__ __volatile__("in %[port], %%al" - : - : [port]"d"(port), "D"(arg0), "S"(arg1) - : "rax"); -} - -#define exit_to_l0(_port, _arg0, _arg1) \ - __exit_to_l0(_port, (uint64_t) (_arg0), (uint64_t) (_arg1)) - -#define GUEST_ASSERT(_condition) do { \ - if (!(_condition)) \ - exit_to_l0(PORT_ABORT, "Failed guest assert: " #_condition, 0);\ -} while (0) void guest_code(void) { for (;;) { - exit_to_l0(PORT_HOST_SYNC, "hello", 0); + GUEST_SYNC(0); asm volatile ("inc %r11"); } } @@ -111,7 +94,7 @@ int main(int argc, char *argv[]) } /* Create VM */ - vm = vm_create_default(VCPU_ID, guest_code); + vm = vm_create_default(VCPU_ID, 0, guest_code); run = vcpu_state(vm, VCPU_ID); diff --git a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c index d7cb7944a42e..18fa64db0d7a 100644 --- a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c @@ -1,5 +1,5 @@ /* - * gtests/tests/vmx_tsc_adjust_test.c + * vmx_tsc_adjust_test * * Copyright (C) 2018, Google LLC. * @@ -22,13 +22,13 @@ #include "test_util.h" #include "kvm_util.h" -#include "x86.h" +#include "processor.h" #include "vmx.h" #include <string.h> #include <sys/ioctl.h> -#include "../kselftest.h" +#include "kselftest.h" #ifndef MSR_IA32_TSC_ADJUST #define MSR_IA32_TSC_ADJUST 0x3b @@ -46,11 +46,6 @@ enum { PORT_DONE, }; -struct vmx_page { - vm_vaddr_t virt; - vm_paddr_t phys; -}; - enum { VMXON_PAGE = 0, VMCS_PAGE, @@ -67,30 +62,12 @@ struct kvm_single_msr { /* The virtual machine object. */ static struct kvm_vm *vm; -/* Array of vmx_page descriptors that is shared with the guest. */ -struct vmx_page *vmx_pages; - -#define exit_to_l0(_port, _arg) do_exit_to_l0(_port, (unsigned long) (_arg)) -static void do_exit_to_l0(uint16_t port, unsigned long arg) -{ - __asm__ __volatile__("in %[port], %%al" - : - : [port]"d"(port), "D"(arg) - : "rax"); -} - - -#define GUEST_ASSERT(_condition) do { \ - if (!(_condition)) \ - exit_to_l0(PORT_ABORT, "Failed guest assert: " #_condition); \ -} while (0) - static void check_ia32_tsc_adjust(int64_t max) { int64_t adjust; adjust = rdmsr(MSR_IA32_TSC_ADJUST); - exit_to_l0(PORT_REPORT, adjust); + GUEST_SYNC(adjust); GUEST_ASSERT(adjust <= max); } @@ -105,7 +82,7 @@ static void l2_guest_code(void) __asm__ __volatile__("vmcall"); } -static void l1_guest_code(struct vmx_page *vmx_pages) +static void l1_guest_code(struct vmx_pages *vmx_pages) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; @@ -116,23 +93,15 @@ static void l1_guest_code(struct vmx_page *vmx_pages) wrmsr(MSR_IA32_TSC, rdtsc() - TSC_ADJUST_VALUE); check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE); - prepare_for_vmx_operation(); - - /* Enter VMX root operation. */ - *(uint32_t *)vmx_pages[VMXON_PAGE].virt = vmcs_revision(); - GUEST_ASSERT(!vmxon(vmx_pages[VMXON_PAGE].phys)); - - /* Load a VMCS. */ - *(uint32_t *)vmx_pages[VMCS_PAGE].virt = vmcs_revision(); - GUEST_ASSERT(!vmclear(vmx_pages[VMCS_PAGE].phys)); - GUEST_ASSERT(!vmptrld(vmx_pages[VMCS_PAGE].phys)); + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + GUEST_ASSERT(load_vmcs(vmx_pages)); /* Prepare the VMCS for L2 execution. */ - prepare_vmcs(l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + prepare_vmcs(vmx_pages, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); control = vmreadz(CPU_BASED_VM_EXEC_CONTROL); control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETING; vmwrite(CPU_BASED_VM_EXEC_CONTROL, control); - vmwrite(MSR_BITMAP, vmx_pages[MSR_BITMAP_PAGE].phys); vmwrite(TSC_OFFSET, TSC_OFFSET_VALUE); /* Jump into L2. First, test failure to load guest CR3. */ @@ -149,34 +118,7 @@ static void l1_guest_code(struct vmx_page *vmx_pages) check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE); - exit_to_l0(PORT_DONE, 0); -} - -static void allocate_vmx_page(struct vmx_page *page) -{ - vm_vaddr_t virt; - - virt = vm_vaddr_alloc(vm, PAGE_SIZE, 0, 0, 0); - memset(addr_gva2hva(vm, virt), 0, PAGE_SIZE); - - page->virt = virt; - page->phys = addr_gva2gpa(vm, virt); -} - -static vm_vaddr_t allocate_vmx_pages(void) -{ - vm_vaddr_t vmx_pages_vaddr; - int i; - - vmx_pages_vaddr = vm_vaddr_alloc( - vm, sizeof(struct vmx_page) * NUM_VMX_PAGES, 0, 0, 0); - - vmx_pages = (void *) addr_gva2hva(vm, vmx_pages_vaddr); - - for (i = 0; i < NUM_VMX_PAGES; i++) - allocate_vmx_page(&vmx_pages[i]); - - return vmx_pages_vaddr; + GUEST_DONE(); } void report(int64_t val) @@ -187,7 +129,8 @@ void report(int64_t val) int main(int argc, char *argv[]) { - vm_vaddr_t vmx_pages_vaddr; + struct vmx_pages *vmx_pages; + vm_vaddr_t vmx_pages_gva; struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); if (!(entry->ecx & CPUID_VMX)) { @@ -195,35 +138,34 @@ int main(int argc, char *argv[]) exit(KSFT_SKIP); } - vm = vm_create_default_vmx(VCPU_ID, (void *) l1_guest_code); + vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); /* Allocate VMX pages and shared descriptors (vmx_pages). */ - vmx_pages_vaddr = allocate_vmx_pages(); - vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_vaddr); + vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); for (;;) { volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); - struct kvm_regs regs; + struct ucall uc; vcpu_run(vm, VCPU_ID); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Got exit_reason other than KVM_EXIT_IO: %u (%s),\n", + "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", run->exit_reason, exit_reason_str(run->exit_reason)); - vcpu_regs_get(vm, VCPU_ID, ®s); - - switch (run->io.port) { - case PORT_ABORT: - TEST_ASSERT(false, "%s", (const char *) regs.rdi); + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_ASSERT(false, "%s", (const char *)uc.args[0]); /* NOT REACHED */ - case PORT_REPORT: - report(regs.rdi); + case UCALL_SYNC: + report(uc.args[1]); break; - case PORT_DONE: + case UCALL_DONE: goto done; default: - TEST_ASSERT(false, "Unknown port 0x%x.", run->io.port); + TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); } } |
