diff options
Diffstat (limited to '')
56 files changed, 5297 insertions, 1900 deletions
diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c new file mode 100644 index 000000000000..dadcbad10a1d --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -0,0 +1,416 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * amx tests + * + * Copyright (C) 2021, Intel, Inc. + * + * Tests for amx #NM exception and save/restore. + */ + +#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 <sys/syscall.h> + +#include "test_util.h" + +#include "kvm_util.h" +#include "processor.h" +#include "vmx.h" + +#ifndef __x86_64__ +# error This test is 64-bit only +#endif + +#define NUM_TILES 8 +#define TILE_SIZE 1024 +#define XSAVE_SIZE ((NUM_TILES * TILE_SIZE) + PAGE_SIZE) + +/* Tile configuration associated: */ +#define MAX_TILES 16 +#define RESERVED_BYTES 14 + +#define XFEATURE_XTILECFG 17 +#define XFEATURE_XTILEDATA 18 +#define XFEATURE_MASK_XTILECFG (1 << XFEATURE_XTILECFG) +#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA) +#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA) + +#define TILE_CPUID 0x1d +#define XSTATE_CPUID 0xd +#define TILE_PALETTE_CPUID_SUBLEAVE 0x1 +#define XSTATE_USER_STATE_SUBLEAVE 0x0 + +#define XSAVE_HDR_OFFSET 512 + +struct xsave_data { + u8 area[XSAVE_SIZE]; +} __aligned(64); + +struct tile_config { + u8 palette_id; + u8 start_row; + u8 reserved[RESERVED_BYTES]; + u16 colsb[MAX_TILES]; + u8 rows[MAX_TILES]; +}; + +struct tile_data { + u8 data[NUM_TILES * TILE_SIZE]; +}; + +struct xtile_info { + u16 bytes_per_tile; + u16 bytes_per_row; + u16 max_names; + u16 max_rows; + u32 xsave_offset; + u32 xsave_size; +}; + +static struct xtile_info xtile; + +static inline u64 __xgetbv(u32 index) +{ + u32 eax, edx; + + asm volatile("xgetbv;" + : "=a" (eax), "=d" (edx) + : "c" (index)); + return eax + ((u64)edx << 32); +} + +static inline void __xsetbv(u32 index, u64 value) +{ + u32 eax = value; + u32 edx = value >> 32; + + asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); +} + +static inline void __ldtilecfg(void *cfg) +{ + asm volatile(".byte 0xc4,0xe2,0x78,0x49,0x00" + : : "a"(cfg)); +} + +static inline void __tileloadd(void *tile) +{ + asm volatile(".byte 0xc4,0xe2,0x7b,0x4b,0x04,0x10" + : : "a"(tile), "d"(0)); +} + +static inline void __tilerelease(void) +{ + asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ::); +} + +static inline void __xsavec(struct xsave_data *data, uint64_t rfbm) +{ + uint32_t rfbm_lo = rfbm; + uint32_t rfbm_hi = rfbm >> 32; + + asm volatile("xsavec (%%rdi)" + : : "D" (data), "a" (rfbm_lo), "d" (rfbm_hi) + : "memory"); +} + +static inline void check_cpuid_xsave(void) +{ + GUEST_ASSERT(this_cpu_has(X86_FEATURE_XSAVE)); + GUEST_ASSERT(this_cpu_has(X86_FEATURE_OSXSAVE)); +} + +static bool check_xsave_supports_xtile(void) +{ + return __xgetbv(0) & XFEATURE_MASK_XTILE; +} + +static bool enum_xtile_config(void) +{ + u32 eax, ebx, ecx, edx; + + __cpuid(TILE_CPUID, TILE_PALETTE_CPUID_SUBLEAVE, &eax, &ebx, &ecx, &edx); + if (!eax || !ebx || !ecx) + return false; + + xtile.max_names = ebx >> 16; + if (xtile.max_names < NUM_TILES) + return false; + + xtile.bytes_per_tile = eax >> 16; + if (xtile.bytes_per_tile < TILE_SIZE) + return false; + + xtile.bytes_per_row = ebx; + xtile.max_rows = ecx; + + return true; +} + +static bool enum_xsave_tile(void) +{ + u32 eax, ebx, ecx, edx; + + __cpuid(XSTATE_CPUID, XFEATURE_XTILEDATA, &eax, &ebx, &ecx, &edx); + if (!eax || !ebx) + return false; + + xtile.xsave_offset = ebx; + xtile.xsave_size = eax; + + return true; +} + +static bool check_xsave_size(void) +{ + u32 eax, ebx, ecx, edx; + bool valid = false; + + __cpuid(XSTATE_CPUID, XSTATE_USER_STATE_SUBLEAVE, &eax, &ebx, &ecx, &edx); + if (ebx && ebx <= XSAVE_SIZE) + valid = true; + + return valid; +} + +static bool check_xtile_info(void) +{ + bool ret = false; + + if (!check_xsave_size()) + return ret; + + if (!enum_xsave_tile()) + return ret; + + if (!enum_xtile_config()) + return ret; + + if (sizeof(struct tile_data) >= xtile.xsave_size) + ret = true; + + return ret; +} + +static void set_tilecfg(struct tile_config *cfg) +{ + int i; + + /* Only palette id 1 */ + cfg->palette_id = 1; + for (i = 0; i < xtile.max_names; i++) { + cfg->colsb[i] = xtile.bytes_per_row; + cfg->rows[i] = xtile.max_rows; + } +} + +static void set_xstatebv(void *data, uint64_t bv) +{ + *(uint64_t *)(data + XSAVE_HDR_OFFSET) = bv; +} + +static u64 get_xstatebv(void *data) +{ + return *(u64 *)(data + XSAVE_HDR_OFFSET); +} + +static void init_regs(void) +{ + uint64_t cr4, xcr0; + + /* turn on CR4.OSXSAVE */ + cr4 = get_cr4(); + cr4 |= X86_CR4_OSXSAVE; + set_cr4(cr4); + + xcr0 = __xgetbv(0); + xcr0 |= XFEATURE_MASK_XTILE; + __xsetbv(0x0, xcr0); +} + +static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, + struct tile_data *tiledata, + struct xsave_data *xsave_data) +{ + init_regs(); + check_cpuid_xsave(); + GUEST_ASSERT(check_xsave_supports_xtile()); + GUEST_ASSERT(check_xtile_info()); + + /* check xtile configs */ + GUEST_ASSERT(xtile.xsave_offset == 2816); + GUEST_ASSERT(xtile.xsave_size == 8192); + GUEST_ASSERT(xtile.max_names == 8); + GUEST_ASSERT(xtile.bytes_per_tile == 1024); + GUEST_ASSERT(xtile.bytes_per_row == 64); + GUEST_ASSERT(xtile.max_rows == 16); + GUEST_SYNC(1); + + /* xfd=0, enable amx */ + wrmsr(MSR_IA32_XFD, 0); + GUEST_SYNC(2); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == 0); + set_tilecfg(amx_cfg); + __ldtilecfg(amx_cfg); + GUEST_SYNC(3); + /* Check save/restore when trap to userspace */ + __tileloadd(tiledata); + GUEST_SYNC(4); + __tilerelease(); + GUEST_SYNC(5); + /* bit 18 not in the XCOMP_BV after xsavec() */ + set_xstatebv(xsave_data, XFEATURE_MASK_XTILEDATA); + __xsavec(xsave_data, XFEATURE_MASK_XTILEDATA); + GUEST_ASSERT((get_xstatebv(xsave_data) & XFEATURE_MASK_XTILEDATA) == 0); + + /* xfd=0x40000, disable amx tiledata */ + wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILEDATA); + GUEST_SYNC(6); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILEDATA); + set_tilecfg(amx_cfg); + __ldtilecfg(amx_cfg); + /* Trigger #NM exception */ + __tileloadd(tiledata); + GUEST_SYNC(10); + + GUEST_DONE(); +} + +void guest_nm_handler(struct ex_regs *regs) +{ + /* Check if #NM is triggered by XFEATURE_MASK_XTILEDATA */ + GUEST_SYNC(7); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA); + GUEST_SYNC(8); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA); + /* Clear xfd_err */ + wrmsr(MSR_IA32_XFD_ERR, 0); + /* xfd=0, enable amx */ + wrmsr(MSR_IA32_XFD, 0); + GUEST_SYNC(9); +} + +int main(int argc, char *argv[]) +{ + struct kvm_regs regs1, regs2; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct kvm_run *run; + struct kvm_x86_state *state; + int xsave_restore_size; + vm_vaddr_t amx_cfg, tiledata, xsavedata; + struct ucall uc; + u32 amx_offset; + int stage, ret; + + vm_xsave_require_permission(XSTATE_XTILE_DATA_BIT); + + /* Create VM */ + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XSAVE)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_AMX_TILE)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XTILECFG)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XTILEDATA)); + + /* Get xsave/restore max size */ + xsave_restore_size = kvm_get_supported_cpuid_entry(0xd)->ecx; + + run = vcpu->run; + vcpu_regs_get(vcpu, ®s1); + + /* Register #NM handler */ + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + vm_install_exception_handler(vm, NM_VECTOR, guest_nm_handler); + + /* amx cfg for guest_code */ + amx_cfg = vm_vaddr_alloc_page(vm); + memset(addr_gva2hva(vm, amx_cfg), 0x0, getpagesize()); + + /* amx tiledata for guest_code */ + tiledata = vm_vaddr_alloc_pages(vm, 2); + memset(addr_gva2hva(vm, tiledata), rand() | 1, 2 * getpagesize()); + + /* xsave data for guest_code */ + xsavedata = vm_vaddr_alloc_pages(vm, 3); + memset(addr_gva2hva(vm, xsavedata), 0, 3 * getpagesize()); + vcpu_args_set(vcpu, 3, amx_cfg, tiledata, xsavedata); + + for (stage = 1; ; stage++) { + vcpu_run(vcpu); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Stage %d: unexpected exit reason: %u (%s),\n", + stage, run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + /* NOT REACHED */ + case UCALL_SYNC: + switch (uc.args[1]) { + case 1: + case 2: + case 3: + case 5: + case 6: + case 7: + case 8: + fprintf(stderr, "GUEST_SYNC(%ld)\n", uc.args[1]); + break; + case 4: + case 10: + fprintf(stderr, + "GUEST_SYNC(%ld), check save/restore status\n", uc.args[1]); + + /* Compacted mode, get amx offset by xsave area + * size subtract 8K amx size. + */ + amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE; + state = vcpu_save_state(vcpu); + void *amx_start = (void *)state->xsave + amx_offset; + void *tiles_data = (void *)addr_gva2hva(vm, tiledata); + /* Only check TMM0 register, 1 tile */ + ret = memcmp(amx_start, tiles_data, TILE_SIZE); + TEST_ASSERT(ret == 0, "memcmp failed, ret=%d\n", ret); + kvm_x86_state_cleanup(state); + break; + case 9: + fprintf(stderr, + "GUEST_SYNC(%ld), #NM exception and enable amx\n", uc.args[1]); + break; + } + break; + case UCALL_DONE: + fprintf(stderr, "UCALL_DONE\n"); + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + + state = vcpu_save_state(vcpu); + memset(®s1, 0, sizeof(regs1)); + vcpu_regs_get(vcpu, ®s1); + + kvm_vm_release(vm); + + /* Restore state in a new VM. */ + vcpu = vm_recreate_with_one_vcpu(vm); + vcpu_load_state(vcpu, state); + run = vcpu->run; + kvm_x86_state_cleanup(state); + + memset(®s2, 0, sizeof(regs2)); + vcpu_regs_get(vcpu, ®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/cpuid_test.c b/tools/testing/selftests/kvm/x86_64/cpuid_test.c new file mode 100644 index 000000000000..a6aeee2e62e4 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/cpuid_test.c @@ -0,0 +1,196 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2021, Red Hat Inc. + * + * Generic tests for KVM CPUID set/get ioctls + */ +#include <asm/kvm_para.h> +#include <linux/kvm_para.h> +#include <stdint.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +/* CPUIDs known to differ */ +struct { + u32 function; + u32 index; +} mangled_cpuids[] = { + /* + * These entries depend on the vCPU's XCR0 register and IA32_XSS MSR, + * which are not controlled for by this test. + */ + {.function = 0xd, .index = 0}, + {.function = 0xd, .index = 1}, +}; + +static void test_guest_cpuids(struct kvm_cpuid2 *guest_cpuid) +{ + int i; + u32 eax, ebx, ecx, edx; + + for (i = 0; i < guest_cpuid->nent; i++) { + __cpuid(guest_cpuid->entries[i].function, + guest_cpuid->entries[i].index, + &eax, &ebx, &ecx, &edx); + + GUEST_ASSERT(eax == guest_cpuid->entries[i].eax && + ebx == guest_cpuid->entries[i].ebx && + ecx == guest_cpuid->entries[i].ecx && + edx == guest_cpuid->entries[i].edx); + } + +} + +static void test_cpuid_40000000(struct kvm_cpuid2 *guest_cpuid) +{ + u32 eax, ebx, ecx, edx; + + cpuid(0x40000000, &eax, &ebx, &ecx, &edx); + + GUEST_ASSERT(eax == 0x40000001); +} + +static void guest_main(struct kvm_cpuid2 *guest_cpuid) +{ + GUEST_SYNC(1); + + test_guest_cpuids(guest_cpuid); + + GUEST_SYNC(2); + + test_cpuid_40000000(guest_cpuid); + + GUEST_DONE(); +} + +static bool is_cpuid_mangled(const struct kvm_cpuid_entry2 *entrie) +{ + int i; + + for (i = 0; i < sizeof(mangled_cpuids); i++) { + if (mangled_cpuids[i].function == entrie->function && + mangled_cpuids[i].index == entrie->index) + return true; + } + + return false; +} + +static void compare_cpuids(const struct kvm_cpuid2 *cpuid1, + const struct kvm_cpuid2 *cpuid2) +{ + const struct kvm_cpuid_entry2 *e1, *e2; + int i; + + TEST_ASSERT(cpuid1->nent == cpuid2->nent, + "CPUID nent mismatch: %d vs. %d", cpuid1->nent, cpuid2->nent); + + for (i = 0; i < cpuid1->nent; i++) { + e1 = &cpuid1->entries[i]; + e2 = &cpuid2->entries[i]; + + TEST_ASSERT(e1->function == e2->function && + e1->index == e2->index && e1->flags == e2->flags, + "CPUID entries[%d] mismtach: 0x%x.%d.%x vs. 0x%x.%d.%x\n", + i, e1->function, e1->index, e1->flags, + e2->function, e2->index, e2->flags); + + if (is_cpuid_mangled(e1)) + continue; + + TEST_ASSERT(e1->eax == e2->eax && e1->ebx == e2->ebx && + e1->ecx == e2->ecx && e1->edx == e2->edx, + "CPUID 0x%x.%x differ: 0x%x:0x%x:0x%x:0x%x vs 0x%x:0x%x:0x%x:0x%x", + e1->function, e1->index, + e1->eax, e1->ebx, e1->ecx, e1->edx, + e2->eax, e2->ebx, e2->ecx, e2->edx); + } +} + +static void run_vcpu(struct kvm_vcpu *vcpu, int stage) +{ + struct ucall uc; + + vcpu_run(vcpu); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && + uc.args[1] == stage + 1, + "Stage %d: Unexpected register values vmexit, got %lx", + stage + 1, (ulong)uc.args[1]); + return; + case UCALL_DONE: + return; + case UCALL_ABORT: + REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx"); + default: + TEST_ASSERT(false, "Unexpected exit: %s", + exit_reason_str(vcpu->run->exit_reason)); + } +} + +struct kvm_cpuid2 *vcpu_alloc_cpuid(struct kvm_vm *vm, vm_vaddr_t *p_gva, struct kvm_cpuid2 *cpuid) +{ + int size = sizeof(*cpuid) + cpuid->nent * sizeof(cpuid->entries[0]); + vm_vaddr_t gva = vm_vaddr_alloc(vm, size, KVM_UTIL_MIN_VADDR); + struct kvm_cpuid2 *guest_cpuids = addr_gva2hva(vm, gva); + + memcpy(guest_cpuids, cpuid, size); + + *p_gva = gva; + return guest_cpuids; +} + +static void set_cpuid_after_run(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *ent; + int rc; + u32 eax, ebx, x; + + /* Setting unmodified CPUID is allowed */ + rc = __vcpu_set_cpuid(vcpu); + TEST_ASSERT(!rc, "Setting unmodified CPUID after KVM_RUN failed: %d", rc); + + /* Changing CPU features is forbidden */ + ent = vcpu_get_cpuid_entry(vcpu, 0x7); + ebx = ent->ebx; + ent->ebx--; + rc = __vcpu_set_cpuid(vcpu); + TEST_ASSERT(rc, "Changing CPU features should fail"); + ent->ebx = ebx; + + /* Changing MAXPHYADDR is forbidden */ + ent = vcpu_get_cpuid_entry(vcpu, 0x80000008); + eax = ent->eax; + x = eax & 0xff; + ent->eax = (eax & ~0xffu) | (x - 1); + rc = __vcpu_set_cpuid(vcpu); + TEST_ASSERT(rc, "Changing MAXPHYADDR should fail"); + ent->eax = eax; +} + +int main(void) +{ + struct kvm_vcpu *vcpu; + vm_vaddr_t cpuid_gva; + struct kvm_vm *vm; + int stage; + + vm = vm_create_with_one_vcpu(&vcpu, guest_main); + + compare_cpuids(kvm_get_supported_cpuid(), vcpu->cpuid); + + vcpu_alloc_cpuid(vm, &cpuid_gva, vcpu->cpuid); + + vcpu_args_set(vcpu, 1, cpuid_gva); + + for (stage = 0; stage < 3; stage++) + run_vcpu(vcpu, stage); + + set_cpuid_after_run(vcpu); + + kvm_vm_free(vm); +} 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 index 6f6fd189dda3..4208487652f8 100644 --- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c +++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c @@ -19,25 +19,11 @@ #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)); + uint64_t cr4 = get_cr4(); - cr4 = get_cr4(); - - return (!!(ecx & X86_FEATURE_OSXSAVE)) == (!!(cr4 & X86_CR4_OSXSAVE)); + return (this_cpu_has(X86_FEATURE_OSXSAVE) == !!(cr4 & X86_CR4_OSXSAVE)); } static void guest_code(void) @@ -63,44 +49,37 @@ static void guest_code(void) int main(int argc, char *argv[]) { + struct kvm_vcpu *vcpu; 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)) { - print_skip("XSAVE feature not supported"); - return 0; - } + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XSAVE)); /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - run = vcpu_state(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + run = vcpu->run; while (1) { - rc = _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); - TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: /* emulate hypervisor clearing CR4.OSXSAVE */ - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); sregs.cr4 &= ~X86_CR4_OSXSAVE; - vcpu_sregs_set(vm, VCPU_ID, &sregs); + vcpu_sregs_set(vcpu, &sregs); break; case UCALL_ABORT: - TEST_FAIL("Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit."); + REPORT_GUEST_ASSERT(uc); break; case UCALL_DONE: goto done; diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c index 5f078db1bcba..7ef99c3359a0 100644 --- a/tools/testing/selftests/kvm/x86_64/debug_regs.c +++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c @@ -10,8 +10,6 @@ #include "processor.h" #include "apic.h" -#define VCPU_ID 0 - #define DR6_BD (1 << 13) #define DR7_GD (1 << 13) @@ -66,21 +64,22 @@ static void guest_code(void) GUEST_DONE(); } -#define CLEAR_DEBUG() memset(&debug, 0, sizeof(debug)) -#define APPLY_DEBUG() vcpu_set_guest_debug(vm, VCPU_ID, &debug) #define CAST_TO_RIP(v) ((unsigned long long)&(v)) -#define SET_RIP(v) do { \ - vcpu_regs_get(vm, VCPU_ID, ®s); \ - regs.rip = (v); \ - vcpu_regs_set(vm, VCPU_ID, ®s); \ - } while (0) -#define MOVE_RIP(v) SET_RIP(regs.rip + (v)); + +static void vcpu_skip_insn(struct kvm_vcpu *vcpu, int insn_len) +{ + struct kvm_regs regs; + + vcpu_regs_get(vcpu, ®s); + regs.rip += insn_len; + vcpu_regs_set(vcpu, ®s); +} int main(void) { struct kvm_guest_debug debug; unsigned long long target_dr6, target_rip; - struct kvm_regs regs; + struct kvm_vcpu *vcpu; struct kvm_run *run; struct kvm_vm *vm; struct ucall uc; @@ -96,35 +95,32 @@ int main(void) 1, /* cli */ }; - if (!kvm_check_cap(KVM_CAP_SET_GUEST_DEBUG)) { - print_skip("KVM_CAP_SET_GUEST_DEBUG not supported"); - return 0; - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_SET_GUEST_DEBUG)); - vm = vm_create_default(VCPU_ID, 0, guest_code); - run = vcpu_state(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + run = vcpu->run; /* Test software BPs - int3 */ - CLEAR_DEBUG(); + memset(&debug, 0, sizeof(debug)); debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP; - APPLY_DEBUG(); - vcpu_run(vm, VCPU_ID); + vcpu_guest_debug_set(vcpu, &debug); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG && run->debug.arch.exception == BP_VECTOR && run->debug.arch.pc == CAST_TO_RIP(sw_bp), "INT3: exit %d exception %d rip 0x%llx (should be 0x%llx)", run->exit_reason, run->debug.arch.exception, run->debug.arch.pc, CAST_TO_RIP(sw_bp)); - MOVE_RIP(1); + vcpu_skip_insn(vcpu, 1); /* Test instruction HW BP over DR[0-3] */ for (i = 0; i < 4; i++) { - CLEAR_DEBUG(); + memset(&debug, 0, sizeof(debug)); debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP; debug.arch.debugreg[i] = CAST_TO_RIP(hw_bp); debug.arch.debugreg[7] = 0x400 | (1UL << (2*i+1)); - APPLY_DEBUG(); - vcpu_run(vm, VCPU_ID); + vcpu_guest_debug_set(vcpu, &debug); + vcpu_run(vcpu); target_dr6 = 0xffff0ff0 | (1UL << i); TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG && run->debug.arch.exception == DB_VECTOR && @@ -137,17 +133,17 @@ int main(void) run->debug.arch.dr6, target_dr6); } /* Skip "nop" */ - MOVE_RIP(1); + vcpu_skip_insn(vcpu, 1); /* Test data access HW BP over DR[0-3] */ for (i = 0; i < 4; i++) { - CLEAR_DEBUG(); + memset(&debug, 0, sizeof(debug)); debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP; debug.arch.debugreg[i] = CAST_TO_RIP(guest_value); debug.arch.debugreg[7] = 0x00000400 | (1UL << (2*i+1)) | (0x000d0000UL << (4*i)); - APPLY_DEBUG(); - vcpu_run(vm, VCPU_ID); + vcpu_guest_debug_set(vcpu, &debug); + vcpu_run(vcpu); target_dr6 = 0xffff0ff0 | (1UL << i); TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG && run->debug.arch.exception == DB_VECTOR && @@ -159,23 +155,22 @@ int main(void) run->debug.arch.pc, CAST_TO_RIP(write_data), run->debug.arch.dr6, target_dr6); /* Rollback the 4-bytes "mov" */ - MOVE_RIP(-7); + vcpu_skip_insn(vcpu, -7); } /* Skip the 4-bytes "mov" */ - MOVE_RIP(7); + vcpu_skip_insn(vcpu, 7); /* Test single step */ target_rip = CAST_TO_RIP(ss_start); target_dr6 = 0xffff4ff0ULL; - vcpu_regs_get(vm, VCPU_ID, ®s); for (i = 0; i < (sizeof(ss_size) / sizeof(ss_size[0])); i++) { target_rip += ss_size[i]; - CLEAR_DEBUG(); + memset(&debug, 0, sizeof(debug)); debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_BLOCKIRQ; debug.arch.debugreg[7] = 0x00000400; - APPLY_DEBUG(); - vcpu_run(vm, VCPU_ID); + vcpu_guest_debug_set(vcpu, &debug); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG && run->debug.arch.exception == DB_VECTOR && run->debug.arch.pc == target_rip && @@ -188,11 +183,11 @@ int main(void) } /* Finally test global disable */ - CLEAR_DEBUG(); + memset(&debug, 0, sizeof(debug)); debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP; debug.arch.debugreg[7] = 0x400 | DR7_GD; - APPLY_DEBUG(); - vcpu_run(vm, VCPU_ID); + vcpu_guest_debug_set(vcpu, &debug); + vcpu_run(vcpu); target_dr6 = 0xffff0ff0 | DR6_BD; TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG && run->debug.arch.exception == DB_VECTOR && @@ -205,12 +200,12 @@ int main(void) target_dr6); /* Disable all debug controls, run to the end */ - CLEAR_DEBUG(); - APPLY_DEBUG(); + memset(&debug, 0, sizeof(debug)); + vcpu_guest_debug_set(vcpu, &debug); - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "KVM_EXIT_IO"); - cmd = get_ucall(vm, VCPU_ID, &uc); + cmd = get_ucall(vcpu, &uc); TEST_ASSERT(cmd == UCALL_DONE, "UCALL_DONE"); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c index f070ff0224fa..236e11755ba6 100644 --- a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c +++ b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c @@ -11,8 +11,6 @@ #include "kvm_util.h" #include "vmx.h" -#define VCPU_ID 1 -#define PAGE_SIZE 4096 #define MAXPHYADDR 36 #define MEM_REGION_GVA 0x0000123456789000 @@ -28,14 +26,6 @@ static void guest_code(void) GUEST_DONE(); } -static void run_guest(struct kvm_vm *vm) -{ - int rc; - - rc = _vcpu_run(vm, VCPU_ID); - TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); -} - /* * Accessors to get R/M, REG, and Mod bits described in the SDM vol 2, * figure 2-2 "Table Interpretation of ModR/M Byte (C8H)". @@ -57,9 +47,9 @@ static bool is_flds(uint8_t *insn_bytes, uint8_t insn_size) GET_RM(insn_bytes[1]) != 0x5; } -static void process_exit_on_emulation_error(struct kvm_vm *vm) +static void process_exit_on_emulation_error(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; struct kvm_regs regs; uint8_t *insn_bytes; uint8_t insn_size; @@ -93,50 +83,48 @@ static void process_exit_on_emulation_error(struct kvm_vm *vm) * contained an flds instruction that is 2-bytes in * length (ie: no prefix, no SIB, no displacement). */ - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); regs.rip += 2; - vcpu_regs_set(vm, VCPU_ID, ®s); + vcpu_regs_set(vcpu, ®s); } } } -static void do_guest_assert(struct kvm_vm *vm, struct ucall *uc) +static void do_guest_assert(struct ucall *uc) { - TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0], __FILE__, - uc->args[1]); + REPORT_GUEST_ASSERT(*uc); } -static void check_for_guest_assert(struct kvm_vm *vm) +static void check_for_guest_assert(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); struct ucall uc; - if (run->exit_reason == KVM_EXIT_IO && - get_ucall(vm, VCPU_ID, &uc) == UCALL_ABORT) { - do_guest_assert(vm, &uc); + if (vcpu->run->exit_reason == KVM_EXIT_IO && + get_ucall(vcpu, &uc) == UCALL_ABORT) { + do_guest_assert(&uc); } } -static void process_ucall_done(struct kvm_vm *vm) +static void process_ucall_done(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; struct ucall uc; - check_for_guest_assert(vm); + check_for_guest_assert(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s)", run->exit_reason, exit_reason_str(run->exit_reason)); - TEST_ASSERT(get_ucall(vm, VCPU_ID, &uc) == UCALL_DONE, + TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_DONE, "Unexpected ucall command: %lu, expected UCALL_DONE (%d)", uc.cmd, UCALL_DONE); } -static uint64_t process_ucall(struct kvm_vm *vm) +static uint64_t process_ucall(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; struct ucall uc; TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, @@ -144,14 +132,14 @@ static uint64_t process_ucall(struct kvm_vm *vm) run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: break; case UCALL_ABORT: - do_guest_assert(vm, &uc); + do_guest_assert(&uc); break; case UCALL_DONE: - process_ucall_done(vm); + process_ucall_done(vcpu); break; default: TEST_ASSERT(false, "Unexpected ucall"); @@ -162,12 +150,7 @@ static uint64_t process_ucall(struct kvm_vm *vm) int main(int argc, char *argv[]) { - struct kvm_enable_cap emul_failure_cap = { - .cap = KVM_CAP_EXIT_ON_EMULATION_FAILURE, - .args[0] = 1, - }; - struct kvm_cpuid_entry2 *entry; - struct kvm_cpuid2 *cpuid; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; uint64_t gpa, pte; uint64_t *hva; @@ -176,24 +159,15 @@ int main(int argc, char *argv[]) /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); - vm = vm_create_default(VCPU_ID, 0, guest_code); - - if (!kvm_check_cap(KVM_CAP_SMALLER_MAXPHYADDR)) { - printf("module parameter 'allow_smaller_maxphyaddr' is not set. Skipping test.\n"); - return 0; - } - - cpuid = kvm_get_supported_cpuid(); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_SMALLER_MAXPHYADDR)); - entry = kvm_get_supported_cpuid_index(0x80000008, 0); - entry->eax = (entry->eax & 0xffffff00) | MAXPHYADDR; - set_cpuid(cpuid, entry); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, cpuid); + vcpu_set_cpuid_maxphyaddr(vcpu, MAXPHYADDR); rc = kvm_check_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE); TEST_ASSERT(rc, "KVM_CAP_EXIT_ON_EMULATION_FAILURE is unavailable"); - vm_enable_cap(vm, &emul_failure_cap); + vm_enable_cap(vm, KVM_CAP_EXIT_ON_EMULATION_FAILURE, 1); vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, MEM_REGION_GPA, MEM_REGION_SLOT, @@ -204,14 +178,14 @@ int main(int argc, char *argv[]) virt_map(vm, MEM_REGION_GVA, MEM_REGION_GPA, 1); hva = addr_gpa2hva(vm, MEM_REGION_GPA); memset(hva, 0, PAGE_SIZE); - pte = vm_get_page_table_entry(vm, VCPU_ID, MEM_REGION_GVA); - vm_set_page_table_entry(vm, VCPU_ID, MEM_REGION_GVA, pte | (1ull << 36)); + pte = vm_get_page_table_entry(vm, vcpu, MEM_REGION_GVA); + vm_set_page_table_entry(vm, vcpu, MEM_REGION_GVA, pte | (1ull << 36)); - run_guest(vm); - process_exit_on_emulation_error(vm); - run_guest(vm); + vcpu_run(vcpu); + process_exit_on_emulation_error(vcpu); + vcpu_run(vcpu); - TEST_ASSERT(process_ucall(vm) == UCALL_DONE, "Expected UCALL_DONE"); + TEST_ASSERT(process_ucall(vcpu) == UCALL_DONE, "Expected UCALL_DONE"); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index 2b46dcca86a8..99bc202243d2 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -10,6 +10,7 @@ #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> +#include <linux/bitmap.h> #include "test_util.h" @@ -17,9 +18,6 @@ #include "vmx.h" -#define VCPU_ID 5 -#define NMI_VECTOR 2 - static int ud_count; static void guest_ud_handler(struct ex_regs *regs) @@ -32,6 +30,22 @@ static void guest_nmi_handler(struct ex_regs *regs) { } +/* Exits to L1 destroy GRPs! */ +static inline void rdmsr_fs_base(void) +{ + __asm__ __volatile__ ("mov $0xc0000100, %%rcx; rdmsr" : : : + "rax", "rbx", "rcx", "rdx", + "rsi", "rdi", "r8", "r9", "r10", "r11", "r12", + "r13", "r14", "r15"); +} +static inline void rdmsr_gs_base(void) +{ + __asm__ __volatile__ ("mov $0xc0000101, %%rcx; rdmsr" : : : + "rax", "rbx", "rcx", "rdx", + "rsi", "rdi", "r8", "r9", "r10", "r11", "r12", + "r13", "r14", "r15"); +} + void l2_guest_code(void) { GUEST_SYNC(7); @@ -41,6 +55,15 @@ void l2_guest_code(void) /* Forced exit to L1 upon restore */ GUEST_SYNC(9); + vmcall(); + + /* MSR-Bitmap tests */ + rdmsr_fs_base(); /* intercepted */ + rdmsr_fs_base(); /* intercepted */ + rdmsr_gs_base(); /* not intercepted */ + vmcall(); + rdmsr_gs_base(); /* intercepted */ + /* Done, exit to L1 and never come back. */ vmcall(); } @@ -76,8 +99,9 @@ void guest_code(struct vmx_pages *vmx_pages) current_evmcs->revision_id = EVMCS_VERSION; GUEST_SYNC(6); - current_evmcs->pin_based_vm_exec_control |= - PIN_BASED_NMI_EXITING; + vmwrite(PIN_BASED_VM_EXEC_CONTROL, vmreadz(PIN_BASED_VM_EXEC_CONTROL) | + PIN_BASED_NMI_EXITING); + GUEST_ASSERT(!vmlaunch()); GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa); @@ -91,6 +115,39 @@ void guest_code(struct vmx_pages *vmx_pages) GUEST_SYNC(10); GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + current_evmcs->guest_rip += 3; /* vmcall */ + + /* Intercept RDMSR 0xc0000100 */ + vmwrite(CPU_BASED_VM_EXEC_CONTROL, vmreadz(CPU_BASED_VM_EXEC_CONTROL) | + CPU_BASED_USE_MSR_BITMAPS); + set_bit(MSR_FS_BASE & 0x1fff, vmx_pages->msr + 0x400); + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_MSR_READ); + current_evmcs->guest_rip += 2; /* rdmsr */ + + /* Enable enlightened MSR bitmap */ + current_evmcs->hv_enlightenments_control.msr_bitmap = 1; + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_MSR_READ); + current_evmcs->guest_rip += 2; /* rdmsr */ + + /* Intercept RDMSR 0xc0000101 without telling KVM about it */ + set_bit(MSR_GS_BASE & 0x1fff, vmx_pages->msr + 0x400); + /* Make sure HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP is set */ + current_evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; + GUEST_ASSERT(!vmresume()); + /* Make sure we don't see EXIT_REASON_MSR_READ here so eMSR bitmap works */ + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + current_evmcs->guest_rip += 3; /* vmcall */ + + /* Now tell KVM we've changed MSR-Bitmap */ + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_MSR_READ); + current_evmcs->guest_rip += 2; /* rdmsr */ + + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); GUEST_SYNC(11); /* Try enlightened vmptrld with an incorrect GPA */ @@ -100,88 +157,86 @@ void guest_code(struct vmx_pages *vmx_pages) GUEST_DONE(); } -void inject_nmi(struct kvm_vm *vm) +void inject_nmi(struct kvm_vcpu *vcpu) { struct kvm_vcpu_events events; - vcpu_events_get(vm, VCPU_ID, &events); + vcpu_events_get(vcpu, &events); events.nmi.pending = 1; events.flags |= KVM_VCPUEVENT_VALID_NMI_PENDING; - vcpu_events_set(vm, VCPU_ID, &events); + vcpu_events_set(vcpu, &events); } -static void save_restore_vm(struct kvm_vm *vm) +static struct kvm_vcpu *save_restore_vm(struct kvm_vm *vm, + struct kvm_vcpu *vcpu) { struct kvm_regs regs1, regs2; struct kvm_x86_state *state; - state = vcpu_save_state(vm, VCPU_ID); + state = vcpu_save_state(vcpu); memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vm, VCPU_ID, ®s1); + vcpu_regs_get(vcpu, ®s1); kvm_vm_release(vm); /* Restore state in a new VM. */ - kvm_vm_restart(vm, O_RDWR); - vm_vcpu_add(vm, VCPU_ID); - vcpu_set_hv_cpuid(vm, VCPU_ID); - vcpu_enable_evmcs(vm, VCPU_ID); - vcpu_load_state(vm, VCPU_ID, state); - free(state); + vcpu = vm_recreate_with_one_vcpu(vm); + vcpu_set_hv_cpuid(vcpu); + vcpu_enable_evmcs(vcpu); + vcpu_load_state(vcpu, state); + kvm_x86_state_cleanup(state); memset(®s2, 0, sizeof(regs2)); - vcpu_regs_get(vm, VCPU_ID, ®s2); + vcpu_regs_get(vcpu, ®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); + return vcpu; } int main(int argc, char *argv[]) { vm_vaddr_t vmx_pages_gva = 0; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; struct ucall uc; int stage; - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); - if (!nested_vmx_supported() || - !kvm_check_cap(KVM_CAP_NESTED_STATE) || - !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { - print_skip("Enlightened VMCS is unsupported"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)); - vcpu_set_hv_cpuid(vm, VCPU_ID); - vcpu_enable_evmcs(vm, VCPU_ID); + vcpu_set_hv_cpuid(vcpu); + vcpu_enable_evmcs(vcpu); vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); + vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); vm_install_exception_handler(vm, NMI_VECTOR, guest_nmi_handler); pr_info("Running L1 which uses EVMCS to run L2\n"); for (stage = 1;; stage++) { - run = vcpu_state(vm, VCPU_ID); - _vcpu_run(vm, VCPU_ID); + run = vcpu->run; + + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Stage %d: unexpected exit reason: %u (%s),\n", stage, run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: break; @@ -196,12 +251,12 @@ int main(int argc, char *argv[]) uc.args[1] == stage, "Stage %d: Unexpected register values vmexit, got %lx", stage, (ulong)uc.args[1]); - save_restore_vm(vm); + vcpu = save_restore_vm(vm, vcpu); /* Force immediate L2->L1 exit before resuming */ if (stage == 8) { pr_info("Injecting NMI into L1 before L2 had a chance to run after restore\n"); - inject_nmi(vm); + inject_nmi(vcpu); } /* @@ -211,7 +266,7 @@ int main(int argc, char *argv[]) */ if (stage == 9) { pr_info("Trying extra KVM_GET_NESTED_STATE/KVM_SET_NESTED_STATE cycle\n"); - save_restore_vm(vm); + vcpu = save_restore_vm(vm, vcpu); } } diff --git a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c new file mode 100644 index 000000000000..32f7e09ef67c --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020, Google LLC. + * + * Tests for KVM paravirtual feature disablement + */ +#include <asm/kvm_para.h> +#include <linux/kvm_para.h> +#include <linux/stringify.h> +#include <stdint.h> + +#include "apic.h" +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +/* VMCALL and VMMCALL are both 3-byte opcodes. */ +#define HYPERCALL_INSN_SIZE 3 + +static bool quirk_disabled; + +static void guest_ud_handler(struct ex_regs *regs) +{ + regs->rax = -EFAULT; + regs->rip += HYPERCALL_INSN_SIZE; +} + +static const uint8_t vmx_vmcall[HYPERCALL_INSN_SIZE] = { 0x0f, 0x01, 0xc1 }; +static const uint8_t svm_vmmcall[HYPERCALL_INSN_SIZE] = { 0x0f, 0x01, 0xd9 }; + +extern uint8_t hypercall_insn[HYPERCALL_INSN_SIZE]; +static uint64_t do_sched_yield(uint8_t apic_id) +{ + uint64_t ret; + + asm volatile("hypercall_insn:\n\t" + ".byte 0xcc,0xcc,0xcc\n\t" + : "=a"(ret) + : "a"((uint64_t)KVM_HC_SCHED_YIELD), "b"((uint64_t)apic_id) + : "memory"); + + return ret; +} + +static void guest_main(void) +{ + const uint8_t *native_hypercall_insn; + const uint8_t *other_hypercall_insn; + uint64_t ret; + + if (is_intel_cpu()) { + native_hypercall_insn = vmx_vmcall; + other_hypercall_insn = svm_vmmcall; + } else if (is_amd_cpu()) { + native_hypercall_insn = svm_vmmcall; + other_hypercall_insn = vmx_vmcall; + } else { + GUEST_ASSERT(0); + /* unreachable */ + return; + } + + memcpy(hypercall_insn, other_hypercall_insn, HYPERCALL_INSN_SIZE); + + ret = do_sched_yield(GET_APIC_ID_FIELD(xapic_read_reg(APIC_ID))); + + /* + * If the quirk is disabled, verify that guest_ud_handler() "returned" + * -EFAULT and that KVM did NOT patch the hypercall. If the quirk is + * enabled, verify that the hypercall succeeded and that KVM patched in + * the "right" hypercall. + */ + if (quirk_disabled) { + GUEST_ASSERT(ret == (uint64_t)-EFAULT); + GUEST_ASSERT(!memcmp(other_hypercall_insn, hypercall_insn, + HYPERCALL_INSN_SIZE)); + } else { + GUEST_ASSERT(!ret); + GUEST_ASSERT(!memcmp(native_hypercall_insn, hypercall_insn, + HYPERCALL_INSN_SIZE)); + } + + GUEST_DONE(); +} + +static void enter_guest(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + struct ucall uc; + + vcpu_run(vcpu); + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + pr_info("%s: %016lx\n", (const char *)uc.args[2], uc.args[3]); + break; + case UCALL_DONE: + return; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + default: + TEST_FAIL("Unhandled ucall: %ld\nexit_reason: %u (%s)", + uc.cmd, run->exit_reason, exit_reason_str(run->exit_reason)); + } +} + +static void test_fix_hypercall(bool disable_quirk) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + vm = vm_create_with_one_vcpu(&vcpu, guest_main); + + vm_init_descriptor_tables(vcpu->vm); + vcpu_init_descriptor_tables(vcpu); + vm_install_exception_handler(vcpu->vm, UD_VECTOR, guest_ud_handler); + + if (disable_quirk) + vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, + KVM_X86_QUIRK_FIX_HYPERCALL_INSN); + + quirk_disabled = disable_quirk; + sync_global_to_guest(vm, quirk_disabled); + + virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); + + enter_guest(vcpu); +} + +int main(void) +{ + TEST_REQUIRE(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & KVM_X86_QUIRK_FIX_HYPERCALL_INSN); + + test_fix_hypercall(false); + test_fix_hypercall(true); +} diff --git a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c deleted file mode 100644 index a711f83749ea..000000000000 --- a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c +++ /dev/null @@ -1,179 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2021, Red Hat Inc. - * - * Generic tests for KVM CPUID set/get ioctls - */ -#include <asm/kvm_para.h> -#include <linux/kvm_para.h> -#include <stdint.h> - -#include "test_util.h" -#include "kvm_util.h" -#include "processor.h" - -#define VCPU_ID 0 - -/* CPUIDs known to differ */ -struct { - u32 function; - u32 index; -} mangled_cpuids[] = { - /* - * These entries depend on the vCPU's XCR0 register and IA32_XSS MSR, - * which are not controlled for by this test. - */ - {.function = 0xd, .index = 0}, - {.function = 0xd, .index = 1}, -}; - -static void test_guest_cpuids(struct kvm_cpuid2 *guest_cpuid) -{ - int i; - u32 eax, ebx, ecx, edx; - - for (i = 0; i < guest_cpuid->nent; i++) { - eax = guest_cpuid->entries[i].function; - ecx = guest_cpuid->entries[i].index; - - cpuid(&eax, &ebx, &ecx, &edx); - - GUEST_ASSERT(eax == guest_cpuid->entries[i].eax && - ebx == guest_cpuid->entries[i].ebx && - ecx == guest_cpuid->entries[i].ecx && - edx == guest_cpuid->entries[i].edx); - } - -} - -static void test_cpuid_40000000(struct kvm_cpuid2 *guest_cpuid) -{ - u32 eax = 0x40000000, ebx, ecx = 0, edx; - - cpuid(&eax, &ebx, &ecx, &edx); - - GUEST_ASSERT(eax == 0x40000001); -} - -static void guest_main(struct kvm_cpuid2 *guest_cpuid) -{ - GUEST_SYNC(1); - - test_guest_cpuids(guest_cpuid); - - GUEST_SYNC(2); - - test_cpuid_40000000(guest_cpuid); - - GUEST_DONE(); -} - -static bool is_cpuid_mangled(struct kvm_cpuid_entry2 *entrie) -{ - int i; - - for (i = 0; i < sizeof(mangled_cpuids); i++) { - if (mangled_cpuids[i].function == entrie->function && - mangled_cpuids[i].index == entrie->index) - return true; - } - - return false; -} - -static void check_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 *entrie) -{ - int i; - - for (i = 0; i < cpuid->nent; i++) { - if (cpuid->entries[i].function == entrie->function && - cpuid->entries[i].index == entrie->index) { - if (is_cpuid_mangled(entrie)) - return; - - TEST_ASSERT(cpuid->entries[i].eax == entrie->eax && - cpuid->entries[i].ebx == entrie->ebx && - cpuid->entries[i].ecx == entrie->ecx && - cpuid->entries[i].edx == entrie->edx, - "CPUID 0x%x.%x differ: 0x%x:0x%x:0x%x:0x%x vs 0x%x:0x%x:0x%x:0x%x", - entrie->function, entrie->index, - cpuid->entries[i].eax, cpuid->entries[i].ebx, - cpuid->entries[i].ecx, cpuid->entries[i].edx, - entrie->eax, entrie->ebx, entrie->ecx, entrie->edx); - return; - } - } - - TEST_ASSERT(false, "CPUID 0x%x.%x not found", entrie->function, entrie->index); -} - -static void compare_cpuids(struct kvm_cpuid2 *cpuid1, struct kvm_cpuid2 *cpuid2) -{ - int i; - - for (i = 0; i < cpuid1->nent; i++) - check_cpuid(cpuid2, &cpuid1->entries[i]); - - for (i = 0; i < cpuid2->nent; i++) - check_cpuid(cpuid1, &cpuid2->entries[i]); -} - -static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid, int stage) -{ - struct ucall uc; - - _vcpu_run(vm, vcpuid); - - switch (get_ucall(vm, vcpuid, &uc)) { - case UCALL_SYNC: - TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && - uc.args[1] == stage + 1, - "Stage %d: Unexpected register values vmexit, got %lx", - stage + 1, (ulong)uc.args[1]); - return; - case UCALL_DONE: - return; - case UCALL_ABORT: - TEST_ASSERT(false, "%s at %s:%ld\n\tvalues: %#lx, %#lx", (const char *)uc.args[0], - __FILE__, uc.args[1], uc.args[2], uc.args[3]); - default: - TEST_ASSERT(false, "Unexpected exit: %s", - exit_reason_str(vcpu_state(vm, vcpuid)->exit_reason)); - } -} - -struct kvm_cpuid2 *vcpu_alloc_cpuid(struct kvm_vm *vm, vm_vaddr_t *p_gva, struct kvm_cpuid2 *cpuid) -{ - int size = sizeof(*cpuid) + cpuid->nent * sizeof(cpuid->entries[0]); - vm_vaddr_t gva = vm_vaddr_alloc(vm, size, KVM_UTIL_MIN_VADDR); - struct kvm_cpuid2 *guest_cpuids = addr_gva2hva(vm, gva); - - memcpy(guest_cpuids, cpuid, size); - - *p_gva = gva; - return guest_cpuids; -} - -int main(void) -{ - struct kvm_cpuid2 *supp_cpuid, *cpuid2; - vm_vaddr_t cpuid_gva; - struct kvm_vm *vm; - int stage; - - vm = vm_create_default(VCPU_ID, 0, guest_main); - - supp_cpuid = kvm_get_supported_cpuid(); - cpuid2 = vcpu_get_cpuid(vm, VCPU_ID); - - compare_cpuids(supp_cpuid, cpuid2); - - vcpu_alloc_cpuid(vm, &cpuid_gva, cpuid2); - - vcpu_args_set(vm, VCPU_ID, 1, cpuid_gva); - - for (stage = 0; stage < 3; stage++) - run_vcpu(vm, VCPU_ID, stage); - - kvm_vm_free(vm); -} diff --git a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c index 8aed0db1331d..d09b3cbcadc6 100644 --- a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c +++ b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c @@ -15,116 +15,21 @@ #include "kvm_util.h" #include "processor.h" -static int kvm_num_index_msrs(int kvm_fd, int nmsrs) -{ - struct kvm_msr_list *list; - int r; - - list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); - list->nmsrs = nmsrs; - r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, list); - TEST_ASSERT(r == -1 && errno == E2BIG, - "Unexpected result from KVM_GET_MSR_INDEX_LIST probe, r: %i", - r); - - r = list->nmsrs; - free(list); - return r; -} - -static void test_get_msr_index(void) -{ - int old_res, res, kvm_fd, r; - struct kvm_msr_list *list; - - kvm_fd = open_kvm_dev_path_or_exit(); - - old_res = kvm_num_index_msrs(kvm_fd, 0); - TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0"); - - if (old_res != 1) { - res = kvm_num_index_msrs(kvm_fd, 1); - TEST_ASSERT(res > 1, "Expecting nmsrs to be > 1"); - TEST_ASSERT(res == old_res, "Expecting nmsrs to be identical"); - } - - list = malloc(sizeof(*list) + old_res * sizeof(list->indices[0])); - list->nmsrs = old_res; - r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, list); - - TEST_ASSERT(r == 0, - "Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST, r: %i", - r); - TEST_ASSERT(list->nmsrs == old_res, "Expecting nmsrs to be identical"); - free(list); - - close(kvm_fd); -} - -static int kvm_num_feature_msrs(int kvm_fd, int nmsrs) -{ - struct kvm_msr_list *list; - int r; - - list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); - list->nmsrs = nmsrs; - r = ioctl(kvm_fd, KVM_GET_MSR_FEATURE_INDEX_LIST, list); - TEST_ASSERT(r == -1 && errno == E2BIG, - "Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST probe, r: %i", - r); - - r = list->nmsrs; - free(list); - return r; -} - -struct kvm_msr_list *kvm_get_msr_feature_list(int kvm_fd, int nmsrs) -{ - struct kvm_msr_list *list; - int r; - - list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); - list->nmsrs = nmsrs; - r = ioctl(kvm_fd, KVM_GET_MSR_FEATURE_INDEX_LIST, list); - - TEST_ASSERT(r == 0, - "Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST, r: %i", - r); - - return list; -} - -static void test_get_msr_feature(void) +int main(int argc, char *argv[]) { - int res, old_res, i, kvm_fd; - struct kvm_msr_list *feature_list; + const struct kvm_msr_list *feature_list; + int i; - kvm_fd = open_kvm_dev_path_or_exit(); + /* + * Skip the entire test if MSR_FEATURES isn't supported, other tests + * will cover the "regular" list of MSRs, the coverage here is purely + * opportunistic and not interesting on its own. + */ + TEST_REQUIRE(kvm_has_cap(KVM_CAP_GET_MSR_FEATURES)); - old_res = kvm_num_feature_msrs(kvm_fd, 0); - TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0"); - - if (old_res != 1) { - res = kvm_num_feature_msrs(kvm_fd, 1); - TEST_ASSERT(res > 1, "Expecting nmsrs to be > 1"); - TEST_ASSERT(res == old_res, "Expecting nmsrs to be identical"); - } - - feature_list = kvm_get_msr_feature_list(kvm_fd, old_res); - TEST_ASSERT(old_res == feature_list->nmsrs, - "Unmatching number of msr indexes"); + (void)kvm_get_msr_index_list(); + feature_list = kvm_get_feature_msr_index_list(); for (i = 0; i < feature_list->nmsrs; i++) kvm_get_feature_msr(feature_list->indices[i]); - - free(feature_list); - close(kvm_fd); -} - -int main(int argc, char *argv[]) -{ - if (kvm_check_cap(KVM_CAP_GET_MSR_FEATURES)) - test_get_msr_feature(); - - test_get_msr_index(); } diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c index e0b2bb1339b1..d576bc8ce823 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c @@ -44,7 +44,7 @@ static inline void nop_loop(void) { int i; - for (i = 0; i < 1000000; i++) + for (i = 0; i < 100000000; i++) asm volatile("nop"); } @@ -56,12 +56,14 @@ static inline void check_tsc_msr_rdtsc(void) tsc_freq = rdmsr(HV_X64_MSR_TSC_FREQUENCY); GUEST_ASSERT(tsc_freq > 0); - /* First, check MSR-based clocksource */ + /* For increased accuracy, take mean rdtsc() before and afrer rdmsr() */ r1 = rdtsc(); t1 = rdmsr(HV_X64_MSR_TIME_REF_COUNT); + r1 = (r1 + rdtsc()) / 2; nop_loop(); r2 = rdtsc(); t2 = rdmsr(HV_X64_MSR_TIME_REF_COUNT); + r2 = (r2 + rdtsc()) / 2; GUEST_ASSERT(r2 > r1 && t2 > t1); @@ -171,22 +173,22 @@ static void guest_main(struct ms_hyperv_tsc_page *tsc_page, vm_paddr_t tsc_page_ GUEST_DONE(); } -#define VCPU_ID 0 - -static void host_check_tsc_msr_rdtsc(struct kvm_vm *vm) +static void host_check_tsc_msr_rdtsc(struct kvm_vcpu *vcpu) { u64 tsc_freq, r1, r2, t1, t2; s64 delta_ns; - tsc_freq = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TSC_FREQUENCY); + tsc_freq = vcpu_get_msr(vcpu, HV_X64_MSR_TSC_FREQUENCY); TEST_ASSERT(tsc_freq > 0, "TSC frequency must be nonzero"); - /* First, check MSR-based clocksource */ + /* For increased accuracy, take mean rdtsc() before and afrer ioctl */ r1 = rdtsc(); - t1 = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TIME_REF_COUNT); + t1 = vcpu_get_msr(vcpu, HV_X64_MSR_TIME_REF_COUNT); + r1 = (r1 + rdtsc()) / 2; nop_loop(); r2 = rdtsc(); - t2 = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TIME_REF_COUNT); + t2 = vcpu_get_msr(vcpu, HV_X64_MSR_TIME_REF_COUNT); + r2 = (r2 + rdtsc()) / 2; TEST_ASSERT(t2 > t1, "Time reference MSR is not monotonic (%ld <= %ld)", t1, t2); @@ -203,36 +205,36 @@ static void host_check_tsc_msr_rdtsc(struct kvm_vm *vm) int main(void) { + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; struct ucall uc; vm_vaddr_t tsc_page_gva; int stage; - vm = vm_create_default(VCPU_ID, 0, guest_main); - run = vcpu_state(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_main); + run = vcpu->run; - vcpu_set_hv_cpuid(vm, VCPU_ID); + vcpu_set_hv_cpuid(vcpu); tsc_page_gva = vm_vaddr_alloc_page(vm); memset(addr_gva2hva(vm, tsc_page_gva), 0x0, getpagesize()); TEST_ASSERT((addr_gva2gpa(vm, tsc_page_gva) & (getpagesize() - 1)) == 0, "TSC page has to be page aligned\n"); - vcpu_args_set(vm, VCPU_ID, 2, tsc_page_gva, addr_gva2gpa(vm, tsc_page_gva)); + vcpu_args_set(vcpu, 2, tsc_page_gva, addr_gva2gpa(vm, tsc_page_gva)); - host_check_tsc_msr_rdtsc(vm); + host_check_tsc_msr_rdtsc(vcpu); for (stage = 1;; stage++) { - _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Stage %d: unexpected exit reason: %u (%s),\n", stage, run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: break; diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c index 7e2d2d17d2ed..e804eb08dff9 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c @@ -20,8 +20,6 @@ #include "processor.h" #include "vmx.h" -#define VCPU_ID 0 - static void guest_code(void) { } @@ -45,32 +43,26 @@ static bool smt_possible(void) return res; } -static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, +static void test_hv_cpuid(const struct kvm_cpuid2 *hv_cpuid_entries, bool evmcs_expected) { int i; - int nent = 9; + int nent_expected = 10; u32 test_val; - if (evmcs_expected) - nent += 1; /* 0x4000000A */ - - TEST_ASSERT(hv_cpuid_entries->nent == nent, + TEST_ASSERT(hv_cpuid_entries->nent == nent_expected, "KVM_GET_SUPPORTED_HV_CPUID should return %d entries" - " with evmcs=%d (returned %d)", - nent, evmcs_expected, hv_cpuid_entries->nent); + " (returned %d)", + nent_expected, hv_cpuid_entries->nent); for (i = 0; i < hv_cpuid_entries->nent; i++) { - struct kvm_cpuid_entry2 *entry = &hv_cpuid_entries->entries[i]; + const struct kvm_cpuid_entry2 *entry = &hv_cpuid_entries->entries[i]; TEST_ASSERT((entry->function >= 0x40000000) && (entry->function <= 0x40000082), "function %x is our of supported range", entry->function); - TEST_ASSERT(evmcs_expected || (entry->function != 0x4000000A), - "0x4000000A leaf should not be reported"); - TEST_ASSERT(entry->index == 0, ".index field should be zero"); @@ -97,8 +89,20 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, "NoNonArchitecturalCoreSharing bit" " doesn't reflect SMT setting"); break; - } + case 0x4000000A: + TEST_ASSERT(entry->eax & (1UL << 19), + "Enlightened MSR-Bitmap should always be supported" + " 0x40000000.EAX: %x", entry->eax); + if (evmcs_expected) + TEST_ASSERT((entry->eax & 0xffff) == 0x101, + "Supported Enlightened VMCS version range is supposed to be 1:1" + " 0x40000000.EAX: %x", entry->eax); + + break; + default: + break; + } /* * If needed for debug: * fprintf(stdout, @@ -107,67 +111,64 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, * entry->edx); */ } - } -void test_hv_cpuid_e2big(struct kvm_vm *vm, bool system) +void test_hv_cpuid_e2big(struct kvm_vm *vm, struct kvm_vcpu *vcpu) { static struct kvm_cpuid2 cpuid = {.nent = 0}; int ret; - if (!system) - ret = _vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, &cpuid); + if (vcpu) + ret = __vcpu_ioctl(vcpu, KVM_GET_SUPPORTED_HV_CPUID, &cpuid); else - ret = _kvm_ioctl(vm, KVM_GET_SUPPORTED_HV_CPUID, &cpuid); + ret = __kvm_ioctl(vm->kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, &cpuid); TEST_ASSERT(ret == -1 && errno == E2BIG, "%s KVM_GET_SUPPORTED_HV_CPUID didn't fail with -E2BIG when" - " it should have: %d %d", system ? "KVM" : "vCPU", ret, errno); + " it should have: %d %d", !vcpu ? "KVM" : "vCPU", ret, errno); } int main(int argc, char *argv[]) { struct kvm_vm *vm; - struct kvm_cpuid2 *hv_cpuid_entries; + const struct kvm_cpuid2 *hv_cpuid_entries; + struct kvm_vcpu *vcpu; /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); - if (!kvm_check_cap(KVM_CAP_HYPERV_CPUID)) { - print_skip("KVM_CAP_HYPERV_CPUID not supported"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_CPUID)); - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); /* Test vCPU ioctl version */ - test_hv_cpuid_e2big(vm, false); + test_hv_cpuid_e2big(vm, vcpu); - hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vm, VCPU_ID); + hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vcpu); test_hv_cpuid(hv_cpuid_entries, false); - free(hv_cpuid_entries); + free((void *)hv_cpuid_entries); - if (!nested_vmx_supported() || - !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { + if (!kvm_cpu_has(X86_FEATURE_VMX) || + !kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { print_skip("Enlightened VMCS is unsupported"); goto do_sys; } - vcpu_enable_evmcs(vm, VCPU_ID); - hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vm, VCPU_ID); + vcpu_enable_evmcs(vcpu); + hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vcpu); test_hv_cpuid(hv_cpuid_entries, true); - free(hv_cpuid_entries); + free((void *)hv_cpuid_entries); do_sys: /* Test system ioctl version */ - if (!kvm_check_cap(KVM_CAP_SYS_HYPERV_CPUID)) { + if (!kvm_has_cap(KVM_CAP_SYS_HYPERV_CPUID)) { print_skip("KVM_CAP_SYS_HYPERV_CPUID not supported"); goto out; } - test_hv_cpuid_e2big(vm, true); + test_hv_cpuid_e2big(vm, NULL); hv_cpuid_entries = kvm_get_supported_hv_cpuid(); - test_hv_cpuid(hv_cpuid_entries, nested_vmx_supported()); + test_hv_cpuid(hv_cpuid_entries, kvm_cpu_has(X86_FEATURE_VMX)); out: kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index 672915ce73d8..05b32e550a80 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -13,78 +13,23 @@ #include "processor.h" #include "hyperv.h" -#define VCPU_ID 0 #define LINUX_OS_ID ((u64)0x8100 << 48) -extern unsigned char rdmsr_start; -extern unsigned char rdmsr_end; - -static u64 do_rdmsr(u32 idx) -{ - u32 lo, hi; - - asm volatile("rdmsr_start: rdmsr;" - "rdmsr_end:" - : "=a"(lo), "=c"(hi) - : "c"(idx)); - - return (((u64) hi) << 32) | lo; -} - -extern unsigned char wrmsr_start; -extern unsigned char wrmsr_end; - -static void do_wrmsr(u32 idx, u64 val) -{ - u32 lo, hi; - - lo = val; - hi = val >> 32; - - asm volatile("wrmsr_start: wrmsr;" - "wrmsr_end:" - : : "a"(lo), "c"(idx), "d"(hi)); -} - -static int nr_gp; -static int nr_ud; - -static inline u64 hypercall(u64 control, vm_vaddr_t input_address, - vm_vaddr_t output_address) -{ - u64 hv_status; - - asm volatile("mov %3, %%r8\n" - "vmcall" - : "=a" (hv_status), - "+c" (control), "+d" (input_address) - : "r" (output_address) - : "cc", "memory", "r8", "r9", "r10", "r11"); - - return hv_status; -} - -static void guest_gp_handler(struct ex_regs *regs) -{ - unsigned char *rip = (unsigned char *)regs->rip; - bool r, w; - - r = rip == &rdmsr_start; - w = rip == &wrmsr_start; - GUEST_ASSERT(r || w); - - nr_gp++; - - if (r) - regs->rip = (uint64_t)&rdmsr_end; - else - regs->rip = (uint64_t)&wrmsr_end; -} - -static void guest_ud_handler(struct ex_regs *regs) +static inline uint8_t hypercall(u64 control, vm_vaddr_t input_address, + vm_vaddr_t output_address, uint64_t *hv_status) { - nr_ud++; - regs->rip += 3; + uint8_t vector; + + /* Note both the hypercall and the "asm safe" clobber r9-r11. */ + asm volatile("mov %[output_address], %%r8\n\t" + KVM_ASM_SAFE("vmcall") + : "=a" (*hv_status), + "+c" (control), "+d" (input_address), + KVM_ASM_SAFE_OUTPUTS(vector) + : [output_address] "r"(output_address), + "a" (-EFAULT) + : "cc", "memory", "r8", KVM_ASM_SAFE_CLOBBERS); + return vector; } struct msr_data { @@ -102,111 +47,105 @@ struct hcall_data { static void guest_msr(struct msr_data *msr) { - int i = 0; - - while (msr->idx) { - WRITE_ONCE(nr_gp, 0); - if (!msr->write) - do_rdmsr(msr->idx); - else - do_wrmsr(msr->idx, msr->write_val); + uint64_t ignored; + uint8_t vector; - if (msr->available) - GUEST_ASSERT(READ_ONCE(nr_gp) == 0); - else - GUEST_ASSERT(READ_ONCE(nr_gp) == 1); + GUEST_ASSERT(msr->idx); - GUEST_SYNC(i++); - } + if (!msr->write) + vector = rdmsr_safe(msr->idx, &ignored); + else + vector = wrmsr_safe(msr->idx, msr->write_val); + if (msr->available) + GUEST_ASSERT_2(!vector, msr->idx, vector); + else + GUEST_ASSERT_2(vector == GP_VECTOR, msr->idx, vector); GUEST_DONE(); } static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall) { - int i = 0; u64 res, input, output; + uint8_t vector; + + GUEST_ASSERT(hcall->control); wrmsr(HV_X64_MSR_GUEST_OS_ID, LINUX_OS_ID); wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa); - while (hcall->control) { - nr_ud = 0; - if (!(hcall->control & HV_HYPERCALL_FAST_BIT)) { - input = pgs_gpa; - output = pgs_gpa + 4096; - } else { - input = output = 0; - } - - res = hypercall(hcall->control, input, output); - if (hcall->ud_expected) - GUEST_ASSERT(nr_ud == 1); - else - GUEST_ASSERT(res == hcall->expect); + if (!(hcall->control & HV_HYPERCALL_FAST_BIT)) { + input = pgs_gpa; + output = pgs_gpa + 4096; + } else { + input = output = 0; + } - GUEST_SYNC(i++); + vector = hypercall(hcall->control, input, output, &res); + if (hcall->ud_expected) { + GUEST_ASSERT_2(vector == UD_VECTOR, hcall->control, vector); + } else { + GUEST_ASSERT_2(!vector, hcall->control, vector); + GUEST_ASSERT_2(res == hcall->expect, hcall->expect, res); } GUEST_DONE(); } -static void hv_set_cpuid(struct kvm_vm *vm, struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 *feat, - struct kvm_cpuid_entry2 *recomm, - struct kvm_cpuid_entry2 *dbg) +static void vcpu_reset_hv_cpuid(struct kvm_vcpu *vcpu) { - TEST_ASSERT(set_cpuid(cpuid, feat), - "failed to set KVM_CPUID_FEATURES leaf"); - TEST_ASSERT(set_cpuid(cpuid, recomm), - "failed to set HYPERV_CPUID_ENLIGHTMENT_INFO leaf"); - TEST_ASSERT(set_cpuid(cpuid, dbg), - "failed to set HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES leaf"); - vcpu_set_cpuid(vm, VCPU_ID, cpuid); + /* + * Enable all supported Hyper-V features, then clear the leafs holding + * the features that will be tested one by one. + */ + vcpu_set_hv_cpuid(vcpu); + + vcpu_clear_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES); + vcpu_clear_cpuid_entry(vcpu, HYPERV_CPUID_ENLIGHTMENT_INFO); + vcpu_clear_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES); } static void guest_test_msrs_access(void) { + struct kvm_cpuid2 *prev_cpuid = NULL; + struct kvm_cpuid_entry2 *feat, *dbg; + struct kvm_vcpu *vcpu; struct kvm_run *run; struct kvm_vm *vm; struct ucall uc; - int stage = 0, r; - struct kvm_cpuid_entry2 feat = { - .function = HYPERV_CPUID_FEATURES - }; - struct kvm_cpuid_entry2 recomm = { - .function = HYPERV_CPUID_ENLIGHTMENT_INFO - }; - struct kvm_cpuid_entry2 dbg = { - .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES - }; - struct kvm_cpuid2 *best; + int stage = 0; vm_vaddr_t msr_gva; - struct kvm_enable_cap cap = { - .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, - .args = {1} - }; struct msr_data *msr; while (true) { - vm = vm_create_default(VCPU_ID, 0, guest_msr); + vm = vm_create_with_one_vcpu(&vcpu, guest_msr); msr_gva = vm_vaddr_alloc_page(vm); memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize()); msr = addr_gva2hva(vm, msr_gva); - vcpu_args_set(vm, VCPU_ID, 1, msr_gva); - vcpu_enable_cap(vm, VCPU_ID, &cap); + vcpu_args_set(vcpu, 1, msr_gva); + vcpu_enable_cap(vcpu, KVM_CAP_HYPERV_ENFORCE_CPUID, 1); - vcpu_set_hv_cpuid(vm, VCPU_ID); + if (!prev_cpuid) { + vcpu_reset_hv_cpuid(vcpu); - best = kvm_get_supported_hv_cpuid(); + prev_cpuid = allocate_kvm_cpuid2(vcpu->cpuid->nent); + } else { + vcpu_init_cpuid(vcpu, prev_cpuid); + } + + feat = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES); + dbg = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); + vcpu_init_descriptor_tables(vcpu); + + run = vcpu->run; - run = vcpu_state(vm, VCPU_ID); + /* TODO: Make this entire test easier to maintain. */ + if (stage >= 21) + vcpu_enable_cap(vcpu, KVM_CAP_HYPERV_SYNIC2, 0); switch (stage) { case 0: @@ -223,7 +162,7 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 2: - feat.eax |= HV_MSR_HYPERCALL_AVAILABLE; + feat->eax |= HV_MSR_HYPERCALL_AVAILABLE; /* * HV_X64_MSR_GUEST_OS_ID has to be written first to make * HV_X64_MSR_HYPERCALL available. @@ -250,12 +189,14 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 6: - feat.eax |= HV_MSR_VP_RUNTIME_AVAILABLE; + feat->eax |= HV_MSR_VP_RUNTIME_AVAILABLE; + msr->idx = HV_X64_MSR_VP_RUNTIME; msr->write = 0; msr->available = 1; break; case 7: /* Read only */ + msr->idx = HV_X64_MSR_VP_RUNTIME; msr->write = 1; msr->write_val = 1; msr->available = 0; @@ -267,12 +208,14 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 9: - feat.eax |= HV_MSR_TIME_REF_COUNT_AVAILABLE; + feat->eax |= HV_MSR_TIME_REF_COUNT_AVAILABLE; + msr->idx = HV_X64_MSR_TIME_REF_COUNT; msr->write = 0; msr->available = 1; break; case 10: /* Read only */ + msr->idx = HV_X64_MSR_TIME_REF_COUNT; msr->write = 1; msr->write_val = 1; msr->available = 0; @@ -284,12 +227,14 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 12: - feat.eax |= HV_MSR_VP_INDEX_AVAILABLE; + feat->eax |= HV_MSR_VP_INDEX_AVAILABLE; + msr->idx = HV_X64_MSR_VP_INDEX; msr->write = 0; msr->available = 1; break; case 13: /* Read only */ + msr->idx = HV_X64_MSR_VP_INDEX; msr->write = 1; msr->write_val = 1; msr->available = 0; @@ -301,11 +246,13 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 15: - feat.eax |= HV_MSR_RESET_AVAILABLE; + feat->eax |= HV_MSR_RESET_AVAILABLE; + msr->idx = HV_X64_MSR_RESET; msr->write = 0; msr->available = 1; break; case 16: + msr->idx = HV_X64_MSR_RESET; msr->write = 1; msr->write_val = 0; msr->available = 1; @@ -317,11 +264,13 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 18: - feat.eax |= HV_MSR_REFERENCE_TSC_AVAILABLE; + feat->eax |= HV_MSR_REFERENCE_TSC_AVAILABLE; + msr->idx = HV_X64_MSR_REFERENCE_TSC; msr->write = 0; msr->available = 1; break; case 19: + msr->idx = HV_X64_MSR_REFERENCE_TSC; msr->write = 1; msr->write_val = 0; msr->available = 1; @@ -337,16 +286,18 @@ static void guest_test_msrs_access(void) * Remains unavailable even with KVM_CAP_HYPERV_SYNIC2 * capability enabled and guest visible CPUID bit unset. */ - cap.cap = KVM_CAP_HYPERV_SYNIC2; - cap.args[0] = 0; - vcpu_enable_cap(vm, VCPU_ID, &cap); + msr->idx = HV_X64_MSR_EOM; + msr->write = 0; + msr->available = 0; break; case 22: - feat.eax |= HV_MSR_SYNIC_AVAILABLE; + feat->eax |= HV_MSR_SYNIC_AVAILABLE; + msr->idx = HV_X64_MSR_EOM; msr->write = 0; msr->available = 1; break; case 23: + msr->idx = HV_X64_MSR_EOM; msr->write = 1; msr->write_val = 0; msr->available = 1; @@ -358,23 +309,29 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 25: - feat.eax |= HV_MSR_SYNTIMER_AVAILABLE; + feat->eax |= HV_MSR_SYNTIMER_AVAILABLE; + msr->idx = HV_X64_MSR_STIMER0_CONFIG; msr->write = 0; msr->available = 1; break; case 26: + msr->idx = HV_X64_MSR_STIMER0_CONFIG; msr->write = 1; msr->write_val = 0; msr->available = 1; break; case 27: /* Direct mode test */ + msr->idx = HV_X64_MSR_STIMER0_CONFIG; msr->write = 1; msr->write_val = 1 << 12; msr->available = 0; break; case 28: - feat.edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; + feat->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; + msr->idx = HV_X64_MSR_STIMER0_CONFIG; + msr->write = 1; + msr->write_val = 1 << 12; msr->available = 1; break; @@ -384,7 +341,8 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 30: - feat.eax |= HV_MSR_APIC_ACCESS_AVAILABLE; + feat->eax |= HV_MSR_APIC_ACCESS_AVAILABLE; + msr->idx = HV_X64_MSR_EOI; msr->write = 1; msr->write_val = 1; msr->available = 1; @@ -396,12 +354,14 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 32: - feat.eax |= HV_ACCESS_FREQUENCY_MSRS; + feat->eax |= HV_ACCESS_FREQUENCY_MSRS; + msr->idx = HV_X64_MSR_TSC_FREQUENCY; msr->write = 0; msr->available = 1; break; case 33: /* Read only */ + msr->idx = HV_X64_MSR_TSC_FREQUENCY; msr->write = 1; msr->write_val = 1; msr->available = 0; @@ -413,11 +373,13 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 35: - feat.eax |= HV_ACCESS_REENLIGHTENMENT; + feat->eax |= HV_ACCESS_REENLIGHTENMENT; + msr->idx = HV_X64_MSR_REENLIGHTENMENT_CONTROL; msr->write = 0; msr->available = 1; break; case 36: + msr->idx = HV_X64_MSR_REENLIGHTENMENT_CONTROL; msr->write = 1; msr->write_val = 1; msr->available = 1; @@ -436,11 +398,13 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 39: - feat.edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; + feat->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; + msr->idx = HV_X64_MSR_CRASH_P0; msr->write = 0; msr->available = 1; break; case 40: + msr->idx = HV_X64_MSR_CRASH_P0; msr->write = 1; msr->write_val = 1; msr->available = 1; @@ -452,48 +416,44 @@ static void guest_test_msrs_access(void) msr->available = 0; break; case 42: - feat.edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE; - dbg.eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + feat->edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE; + dbg->eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + msr->idx = HV_X64_MSR_SYNDBG_STATUS; msr->write = 0; msr->available = 1; break; case 43: + msr->idx = HV_X64_MSR_SYNDBG_STATUS; msr->write = 1; msr->write_val = 0; msr->available = 1; break; case 44: - /* END */ - msr->idx = 0; - break; + kvm_vm_free(vm); + return; } - hv_set_cpuid(vm, best, &feat, &recomm, &dbg); + vcpu_set_cpuid(vcpu); + + memcpy(prev_cpuid, vcpu->cpuid, kvm_cpuid2_size(vcpu->cpuid->nent)); - if (msr->idx) - pr_debug("Stage %d: testing msr: 0x%x for %s\n", stage, - msr->idx, msr->write ? "write" : "read"); - else - pr_debug("Stage %d: finish\n", stage); + pr_debug("Stage %d: testing msr: 0x%x for %s\n", stage, + msr->idx, msr->write ? "write" : "read"); - r = _vcpu_run(vm, VCPU_ID); - TEST_ASSERT(!r, "vcpu_run failed: %d\n", r); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "unexpected exit reason: %u (%s)", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { - case UCALL_SYNC: - TEST_ASSERT(uc.args[1] == 0, - "Unexpected stage: %ld (0 expected)\n", - uc.args[1]); - break; + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT_2(uc, "MSR = %lx, vector = %lx"); return; case UCALL_DONE: + break; + default: + TEST_FAIL("Unhandled ucall: %ld", uc.cmd); return; } @@ -504,55 +464,51 @@ static void guest_test_msrs_access(void) static void guest_test_hcalls_access(void) { + struct kvm_cpuid_entry2 *feat, *recomm, *dbg; + struct kvm_cpuid2 *prev_cpuid = NULL; + struct kvm_vcpu *vcpu; struct kvm_run *run; struct kvm_vm *vm; struct ucall uc; - int stage = 0, r; - struct kvm_cpuid_entry2 feat = { - .function = HYPERV_CPUID_FEATURES, - .eax = HV_MSR_HYPERCALL_AVAILABLE - }; - struct kvm_cpuid_entry2 recomm = { - .function = HYPERV_CPUID_ENLIGHTMENT_INFO - }; - struct kvm_cpuid_entry2 dbg = { - .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES - }; - struct kvm_enable_cap cap = { - .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, - .args = {1} - }; + int stage = 0; vm_vaddr_t hcall_page, hcall_params; struct hcall_data *hcall; - struct kvm_cpuid2 *best; while (true) { - vm = vm_create_default(VCPU_ID, 0, guest_hcall); + vm = vm_create_with_one_vcpu(&vcpu, guest_hcall); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); + vcpu_init_descriptor_tables(vcpu); /* Hypercall input/output */ hcall_page = vm_vaddr_alloc_pages(vm, 2); - hcall = addr_gva2hva(vm, hcall_page); memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); hcall_params = vm_vaddr_alloc_page(vm); memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize()); + hcall = addr_gva2hva(vm, hcall_params); - vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params); - vcpu_enable_cap(vm, VCPU_ID, &cap); + vcpu_args_set(vcpu, 2, addr_gva2gpa(vm, hcall_page), hcall_params); + vcpu_enable_cap(vcpu, KVM_CAP_HYPERV_ENFORCE_CPUID, 1); - vcpu_set_hv_cpuid(vm, VCPU_ID); + if (!prev_cpuid) { + vcpu_reset_hv_cpuid(vcpu); - best = kvm_get_supported_hv_cpuid(); + prev_cpuid = allocate_kvm_cpuid2(vcpu->cpuid->nent); + } else { + vcpu_init_cpuid(vcpu, prev_cpuid); + } - run = vcpu_state(vm, VCPU_ID); + feat = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES); + recomm = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_ENLIGHTMENT_INFO); + dbg = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES); + + run = vcpu->run; switch (stage) { case 0: - hcall->control = 0xdeadbeef; + feat->eax |= HV_MSR_HYPERCALL_AVAILABLE; + hcall->control = 0xbeef; hcall->expect = HV_STATUS_INVALID_HYPERCALL_CODE; break; @@ -561,7 +517,8 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 2: - feat.ebx |= HV_POST_MESSAGES; + feat->ebx |= HV_POST_MESSAGES; + hcall->control = HVCALL_POST_MESSAGE; hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; break; @@ -570,7 +527,8 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 4: - feat.ebx |= HV_SIGNAL_EVENTS; + feat->ebx |= HV_SIGNAL_EVENTS; + hcall->control = HVCALL_SIGNAL_EVENT; hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; break; @@ -579,11 +537,13 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_INVALID_HYPERCALL_CODE; break; case 6: - dbg.eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + dbg->eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + hcall->control = HVCALL_RESET_DEBUG_SESSION; hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 7: - feat.ebx |= HV_DEBUGGING; + feat->ebx |= HV_DEBUGGING; + hcall->control = HVCALL_RESET_DEBUG_SESSION; hcall->expect = HV_STATUS_OPERATION_DENIED; break; @@ -592,7 +552,8 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 9: - recomm.eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED; + recomm->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED; + hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE; hcall->expect = HV_STATUS_SUCCESS; break; case 10: @@ -600,7 +561,8 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 11: - recomm.eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED; + recomm->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED; + hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX; hcall->expect = HV_STATUS_SUCCESS; break; @@ -609,7 +571,8 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 13: - recomm.eax |= HV_X64_CLUSTER_IPI_RECOMMENDED; + recomm->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED; + hcall->control = HVCALL_SEND_IPI; hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; break; case 14: @@ -623,7 +586,8 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 16: - recomm.ebx = 0xfff; + recomm->ebx = 0xfff; + hcall->control = HVCALL_NOTIFY_LONG_SPIN_WAIT; hcall->expect = HV_STATUS_SUCCESS; break; case 17: @@ -632,42 +596,35 @@ static void guest_test_hcalls_access(void) hcall->ud_expected = true; break; case 18: - feat.edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE; + feat->edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE; + hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | HV_HYPERCALL_FAST_BIT; hcall->ud_expected = false; hcall->expect = HV_STATUS_SUCCESS; break; - case 19: - /* END */ - hcall->control = 0; - break; + kvm_vm_free(vm); + return; } - hv_set_cpuid(vm, best, &feat, &recomm, &dbg); + vcpu_set_cpuid(vcpu); + + memcpy(prev_cpuid, vcpu->cpuid, kvm_cpuid2_size(vcpu->cpuid->nent)); - if (hcall->control) - pr_debug("Stage %d: testing hcall: 0x%lx\n", stage, - hcall->control); - else - pr_debug("Stage %d: finish\n", stage); + pr_debug("Stage %d: testing hcall: 0x%lx\n", stage, hcall->control); - r = _vcpu_run(vm, VCPU_ID); - TEST_ASSERT(!r, "vcpu_run failed: %d\n", r); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "unexpected exit reason: %u (%s)", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { - case UCALL_SYNC: - TEST_ASSERT(uc.args[1] == 0, - "Unexpected stage: %ld (0 expected)\n", - uc.args[1]); - break; + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT_2(uc, "arg1 = %lx, arg2 = %lx"); return; case UCALL_DONE: + break; + default: + TEST_FAIL("Unhandled ucall: %ld", uc.cmd); return; } diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c new file mode 100644 index 000000000000..a380ad7bb9b3 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KVM_GET/SET_* tests + * + * Copyright (C) 2022, Red Hat, Inc. + * + * Tests for Hyper-V extensions to SVM. + */ +#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 <linux/bitmap.h> + +#include "test_util.h" + +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "hyperv.h" + +#define L2_GUEST_STACK_SIZE 256 + +struct hv_enlightenments { + struct __packed hv_enlightenments_control { + u32 nested_flush_hypercall:1; + u32 msr_bitmap:1; + u32 enlightened_npt_tlb: 1; + u32 reserved:29; + } __packed hv_enlightenments_control; + u32 hv_vp_id; + u64 hv_vm_id; + u64 partition_assist_page; + u64 reserved; +} __packed; + +/* + * Hyper-V uses the software reserved clean bit in VMCB + */ +#define VMCB_HV_NESTED_ENLIGHTENMENTS (1U << 31) + +void l2_guest_code(void) +{ + GUEST_SYNC(3); + /* Exit to L1 */ + vmmcall(); + + /* MSR-Bitmap tests */ + rdmsr(MSR_FS_BASE); /* intercepted */ + rdmsr(MSR_FS_BASE); /* intercepted */ + rdmsr(MSR_GS_BASE); /* not intercepted */ + vmmcall(); + rdmsr(MSR_GS_BASE); /* intercepted */ + + GUEST_SYNC(5); + + /* Done, exit to L1 and never come back. */ + vmmcall(); +} + +static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + struct hv_enlightenments *hve = + (struct hv_enlightenments *)vmcb->control.reserved_sw; + + GUEST_SYNC(1); + + wrmsr(HV_X64_MSR_GUEST_OS_ID, (u64)0x8100 << 48); + + GUEST_ASSERT(svm->vmcb_gpa); + /* Prepare for L2 execution. */ + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + GUEST_SYNC(2); + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); + GUEST_SYNC(4); + vmcb->save.rip += 3; + + /* Intercept RDMSR 0xc0000100 */ + vmcb->control.intercept |= 1ULL << INTERCEPT_MSR_PROT; + set_bit(2 * (MSR_FS_BASE & 0x1fff), svm->msr + 0x800); + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_MSR); + vmcb->save.rip += 2; /* rdmsr */ + + /* Enable enlightened MSR bitmap */ + hve->hv_enlightenments_control.msr_bitmap = 1; + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_MSR); + vmcb->save.rip += 2; /* rdmsr */ + + /* Intercept RDMSR 0xc0000101 without telling KVM about it */ + set_bit(2 * (MSR_GS_BASE & 0x1fff), svm->msr + 0x800); + /* Make sure HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP is set */ + vmcb->control.clean |= VMCB_HV_NESTED_ENLIGHTENMENTS; + run_guest(vmcb, svm->vmcb_gpa); + /* Make sure we don't see SVM_EXIT_MSR here so eMSR bitmap works */ + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); + vmcb->save.rip += 3; /* vmcall */ + + /* Now tell KVM we've changed MSR-Bitmap */ + vmcb->control.clean &= ~VMCB_HV_NESTED_ENLIGHTENMENTS; + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_MSR); + vmcb->save.rip += 2; /* rdmsr */ + + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); + GUEST_SYNC(6); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + vm_vaddr_t nested_gva = 0; + + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct kvm_run *run; + struct ucall uc; + int stage; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); + + /* Create VM */ + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + vcpu_set_hv_cpuid(vcpu); + run = vcpu->run; + vcpu_alloc_svm(vm, &nested_gva); + vcpu_args_set(vcpu, 1, nested_gva); + + for (stage = 1;; stage++) { + vcpu_run(vcpu); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Stage %d: unexpected exit reason: %u (%s),\n", + stage, run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + /* NOT REACHED */ + case UCALL_SYNC: + break; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + + /* UCALL_SYNC is handled here. */ + TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && + uc.args[1] == stage, "Stage %d: Unexpected register values vmexit, got %lx", + stage, (ulong)uc.args[1]); + + } + +done: + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c b/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c index 97731454f3f3..813ce282cf56 100644 --- a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c +++ b/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c @@ -16,8 +16,6 @@ #include "kvm_util.h" #include "processor.h" -#define VCPU_ID 0 - struct test_case { uint64_t kvmclock_base; int64_t realtime_offset; @@ -73,8 +71,7 @@ static void handle_sync(struct ucall *uc, struct kvm_clock_data *start, static void handle_abort(struct ucall *uc) { - TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0], - __FILE__, uc->args[1]); + REPORT_GUEST_ASSERT(*uc); } static void setup_clock(struct kvm_vm *vm, struct test_case *test_case) @@ -105,29 +102,27 @@ static void setup_clock(struct kvm_vm *vm, struct test_case *test_case) vm_ioctl(vm, KVM_SET_CLOCK, &data); } -static void enter_guest(struct kvm_vm *vm) +static void enter_guest(struct kvm_vcpu *vcpu) { struct kvm_clock_data start, end; - struct kvm_run *run; + struct kvm_run *run = vcpu->run; + struct kvm_vm *vm = vcpu->vm; struct ucall uc; - int i, r; - - run = vcpu_state(vm, VCPU_ID); + int i; for (i = 0; i < ARRAY_SIZE(test_cases); i++) { setup_clock(vm, &test_cases[i]); vm_ioctl(vm, KVM_GET_CLOCK, &start); - r = _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); vm_ioctl(vm, KVM_GET_CLOCK, &end); - TEST_ASSERT(!r, "vcpu_run failed: %d\n", r); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "unexpected exit reason: %u (%s)", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: handle_sync(&uc, &start, &end); break; @@ -178,26 +173,23 @@ out: int main(void) { + struct kvm_vcpu *vcpu; vm_vaddr_t pvti_gva; vm_paddr_t pvti_gpa; struct kvm_vm *vm; int flags; flags = kvm_check_cap(KVM_CAP_ADJUST_CLOCK); - if (!(flags & KVM_CLOCK_REALTIME)) { - print_skip("KVM_CLOCK_REALTIME not supported; flags: %x", - flags); - exit(KSFT_SKIP); - } + TEST_REQUIRE(flags & KVM_CLOCK_REALTIME); check_clocksource(); - vm = vm_create_default(VCPU_ID, 0, guest_main); + vm = vm_create_with_one_vcpu(&vcpu, guest_main); pvti_gva = vm_vaddr_alloc(vm, getpagesize(), 0x10000); pvti_gpa = addr_gva2gpa(vm, pvti_gva); - vcpu_args_set(vm, VCPU_ID, 2, pvti_gpa, pvti_gva); + vcpu_args_set(vcpu, 2, pvti_gpa, pvti_gva); - enter_guest(vm); + enter_guest(vcpu); kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c index 04ed975662c9..619655c1a1f3 100644 --- a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c +++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c @@ -12,55 +12,6 @@ #include "kvm_util.h" #include "processor.h" -extern unsigned char rdmsr_start; -extern unsigned char rdmsr_end; - -static u64 do_rdmsr(u32 idx) -{ - u32 lo, hi; - - asm volatile("rdmsr_start: rdmsr;" - "rdmsr_end:" - : "=a"(lo), "=c"(hi) - : "c"(idx)); - - return (((u64) hi) << 32) | lo; -} - -extern unsigned char wrmsr_start; -extern unsigned char wrmsr_end; - -static void do_wrmsr(u32 idx, u64 val) -{ - u32 lo, hi; - - lo = val; - hi = val >> 32; - - asm volatile("wrmsr_start: wrmsr;" - "wrmsr_end:" - : : "a"(lo), "c"(idx), "d"(hi)); -} - -static int nr_gp; - -static void guest_gp_handler(struct ex_regs *regs) -{ - unsigned char *rip = (unsigned char *)regs->rip; - bool r, w; - - r = rip == &rdmsr_start; - w = rip == &wrmsr_start; - GUEST_ASSERT(r || w); - - nr_gp++; - - if (r) - regs->rip = (uint64_t)&rdmsr_end; - else - regs->rip = (uint64_t)&wrmsr_end; -} - struct msr_data { uint32_t idx; const char *name; @@ -89,14 +40,16 @@ static struct msr_data msrs_to_test[] = { static void test_msr(struct msr_data *msr) { + uint64_t ignored; + uint8_t vector; + PR_MSR(msr); - do_rdmsr(msr->idx); - GUEST_ASSERT(READ_ONCE(nr_gp) == 1); - nr_gp = 0; - do_wrmsr(msr->idx, 0); - GUEST_ASSERT(READ_ONCE(nr_gp) == 1); - nr_gp = 0; + vector = rdmsr_safe(msr->idx, &ignored); + GUEST_ASSERT_1(vector == GP_VECTOR, vector); + + vector = wrmsr_safe(msr->idx, 0); + GUEST_ASSERT_1(vector == GP_VECTOR, vector); } struct hcall_data { @@ -142,15 +95,6 @@ static void guest_main(void) GUEST_DONE(); } -static void clear_kvm_cpuid_features(struct kvm_cpuid2 *cpuid) -{ - struct kvm_cpuid_entry2 ent = {0}; - - ent.function = KVM_CPUID_FEATURES; - TEST_ASSERT(set_cpuid(cpuid, &ent), - "failed to clear KVM_CPUID_FEATURES leaf"); -} - static void pr_msr(struct ucall *uc) { struct msr_data *msr = (struct msr_data *)uc->args[0]; @@ -165,30 +109,18 @@ static void pr_hcall(struct ucall *uc) pr_info("testing hcall: %s (%lu)\n", hc->name, hc->nr); } -static void handle_abort(struct ucall *uc) +static void enter_guest(struct kvm_vcpu *vcpu) { - TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0], - __FILE__, uc->args[1]); -} - -#define VCPU_ID 0 - -static void enter_guest(struct kvm_vm *vm) -{ - struct kvm_run *run; + struct kvm_run *run = vcpu->run; struct ucall uc; - int r; - - run = vcpu_state(vm, VCPU_ID); while (true) { - r = _vcpu_run(vm, VCPU_ID); - TEST_ASSERT(!r, "vcpu_run failed: %d\n", r); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "unexpected exit reason: %u (%s)", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_PR_MSR: pr_msr(&uc); break; @@ -196,7 +128,7 @@ static void enter_guest(struct kvm_vm *vm) pr_hcall(&uc); break; case UCALL_ABORT: - handle_abort(&uc); + REPORT_GUEST_ASSERT_1(uc, "vector = %lu"); return; case UCALL_DONE: return; @@ -206,29 +138,20 @@ static void enter_guest(struct kvm_vm *vm) int main(void) { - struct kvm_enable_cap cap = {0}; - struct kvm_cpuid2 *best; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; - if (!kvm_check_cap(KVM_CAP_ENFORCE_PV_FEATURE_CPUID)) { - print_skip("KVM_CAP_ENFORCE_PV_FEATURE_CPUID not supported"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_ENFORCE_PV_FEATURE_CPUID)); - vm = vm_create_default(VCPU_ID, 0, guest_main); + vm = vm_create_with_one_vcpu(&vcpu, guest_main); - cap.cap = KVM_CAP_ENFORCE_PV_FEATURE_CPUID; - cap.args[0] = 1; - vcpu_enable_cap(vm, VCPU_ID, &cap); + vcpu_enable_cap(vcpu, KVM_CAP_ENFORCE_PV_FEATURE_CPUID, 1); - best = kvm_get_supported_cpuid(); - clear_kvm_cpuid_features(best); - vcpu_set_cpuid(vm, VCPU_ID, best); + vcpu_clear_cpuid_entry(vcpu, KVM_CPUID_FEATURES); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); + vcpu_init_descriptor_tables(vcpu); - enter_guest(vm); + enter_guest(vcpu); kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/x86_64/max_vcpuid_cap_test.c b/tools/testing/selftests/kvm/x86_64/max_vcpuid_cap_test.c new file mode 100644 index 000000000000..3cc4b86832fe --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/max_vcpuid_cap_test.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * maximum APIC ID capability tests + * + * Copyright (C) 2022, Intel, Inc. + * + * Tests for getting/setting maximum APIC ID capability + */ + +#include "kvm_util.h" + +#define MAX_VCPU_ID 2 + +int main(int argc, char *argv[]) +{ + struct kvm_vm *vm; + int ret; + + vm = vm_create_barebones(); + + /* Get KVM_CAP_MAX_VCPU_ID cap supported in KVM */ + ret = vm_check_cap(vm, KVM_CAP_MAX_VCPU_ID); + + /* Try to set KVM_CAP_MAX_VCPU_ID beyond KVM cap */ + ret = __vm_enable_cap(vm, KVM_CAP_MAX_VCPU_ID, ret + 1); + TEST_ASSERT(ret < 0, + "Setting KVM_CAP_MAX_VCPU_ID beyond KVM cap should fail"); + + /* Set KVM_CAP_MAX_VCPU_ID */ + vm_enable_cap(vm, KVM_CAP_MAX_VCPU_ID, MAX_VCPU_ID); + + + /* Try to set KVM_CAP_MAX_VCPU_ID again */ + ret = __vm_enable_cap(vm, KVM_CAP_MAX_VCPU_ID, MAX_VCPU_ID + 1); + TEST_ASSERT(ret < 0, + "Setting KVM_CAP_MAX_VCPU_ID multiple times should fail"); + + /* Create vCPU with id beyond KVM_CAP_MAX_VCPU_ID cap*/ + ret = __vm_ioctl(vm, KVM_CREATE_VCPU, (void *)MAX_VCPU_ID); + TEST_ASSERT(ret < 0, "Creating vCPU with ID > MAX_VCPU_ID should fail"); + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c index 9f55ccd169a1..fb02581953a3 100644 --- a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c +++ b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c @@ -59,10 +59,10 @@ void test(void) kvm = open("/dev/kvm", O_RDWR); TEST_ASSERT(kvm != -1, "failed to open /dev/kvm"); - kvmvm = ioctl(kvm, KVM_CREATE_VM, 0); - TEST_ASSERT(kvmvm != -1, "KVM_CREATE_VM failed"); + kvmvm = __kvm_ioctl(kvm, KVM_CREATE_VM, NULL); + TEST_ASSERT(kvmvm > 0, KVM_IOCTL_ERROR(KVM_CREATE_VM, kvmvm)); kvmcpu = ioctl(kvmvm, KVM_CREATE_VCPU, 0); - TEST_ASSERT(kvmcpu != -1, "KVM_CREATE_VCPU failed"); + TEST_ASSERT(kvmcpu != -1, KVM_IOCTL_ERROR(KVM_CREATE_VCPU, kvmcpu)); run = (struct kvm_run *)mmap(0, 4096, PROT_READ|PROT_WRITE, MAP_SHARED, kvmcpu, 0); tc.kvmcpu = kvmcpu; @@ -93,15 +93,9 @@ int main(void) { int warnings_before, warnings_after; - if (!is_intel_cpu()) { - print_skip("Must be run on an Intel CPU"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(is_intel_cpu()); - if (vm_is_unrestricted_guest(NULL)) { - print_skip("Unrestricted guest must be disabled"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(!vm_is_unrestricted_guest(NULL)); warnings_before = get_warnings_count(); diff --git a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c deleted file mode 100644 index da2325fcad87..000000000000 --- a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c +++ /dev/null @@ -1,147 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include "kvm_util.h" -#include "processor.h" - -#define VCPU_ID 1 - -#define MMIO_GPA 0x100000000ull - -static void guest_code(void) -{ - (void)READ_ONCE(*((uint64_t *)MMIO_GPA)); - (void)READ_ONCE(*((uint64_t *)MMIO_GPA)); - - GUEST_ASSERT(0); -} - -static void guest_pf_handler(struct ex_regs *regs) -{ - /* PFEC == RSVD | PRESENT (read, kernel). */ - GUEST_ASSERT(regs->error_code == 0x9); - GUEST_DONE(); -} - -static void mmu_role_test(u32 *cpuid_reg, u32 evil_cpuid_val) -{ - u32 good_cpuid_val = *cpuid_reg; - struct kvm_run *run; - struct kvm_vm *vm; - uint64_t cmd; - int r; - - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - run = vcpu_state(vm, VCPU_ID); - - /* Map 1gb page without a backing memlot. */ - __virt_pg_map(vm, MMIO_GPA, MMIO_GPA, X86_PAGE_SIZE_1G); - - r = _vcpu_run(vm, VCPU_ID); - - /* Guest access to the 1gb page should trigger MMIO. */ - TEST_ASSERT(r == 0, "vcpu_run failed: %d\n", r); - TEST_ASSERT(run->exit_reason == KVM_EXIT_MMIO, - "Unexpected exit reason: %u (%s), expected MMIO exit (1gb page w/o memslot)\n", - run->exit_reason, exit_reason_str(run->exit_reason)); - - TEST_ASSERT(run->mmio.len == 8, "Unexpected exit mmio size = %u", run->mmio.len); - - TEST_ASSERT(run->mmio.phys_addr == MMIO_GPA, - "Unexpected exit mmio address = 0x%llx", run->mmio.phys_addr); - - /* - * Effect the CPUID change for the guest and re-enter the guest. Its - * access should now #PF due to the PAGE_SIZE bit being reserved or - * the resulting GPA being invalid. Note, kvm_get_supported_cpuid() - * returns the struct that contains the entry being modified. Eww. - */ - *cpuid_reg = evil_cpuid_val; - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - - /* - * Add a dummy memslot to coerce KVM into bumping the MMIO generation. - * KVM does not "officially" support mucking with CPUID after KVM_RUN, - * and will incorrectly reuse MMIO SPTEs. Don't delete the memslot! - * KVM x86 zaps all shadow pages on memslot deletion. - */ - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, - MMIO_GPA << 1, 10, 1, 0); - - /* Set up a #PF handler to eat the RSVD #PF and signal all done! */ - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_install_exception_handler(vm, PF_VECTOR, guest_pf_handler); - - r = _vcpu_run(vm, VCPU_ID); - TEST_ASSERT(r == 0, "vcpu_run failed: %d\n", r); - - cmd = get_ucall(vm, VCPU_ID, NULL); - TEST_ASSERT(cmd == UCALL_DONE, - "Unexpected guest exit, exit_reason=%s, ucall.cmd = %lu\n", - exit_reason_str(run->exit_reason), cmd); - - /* - * Restore the happy CPUID value for the next test. Yes, changes are - * indeed persistent across VM destruction. - */ - *cpuid_reg = good_cpuid_val; - - kvm_vm_free(vm); -} - -int main(int argc, char *argv[]) -{ - struct kvm_cpuid_entry2 *entry; - int opt; - - /* - * All tests are opt-in because TDP doesn't play nice with reserved #PF - * in the GVA->GPA translation. The hardware page walker doesn't let - * software change GBPAGES or MAXPHYADDR, and KVM doesn't manually walk - * the GVA on fault for performance reasons. - */ - bool do_gbpages = false; - bool do_maxphyaddr = false; - - setbuf(stdout, NULL); - - while ((opt = getopt(argc, argv, "gm")) != -1) { - switch (opt) { - case 'g': - do_gbpages = true; - break; - case 'm': - do_maxphyaddr = true; - break; - case 'h': - default: - printf("usage: %s [-g (GBPAGES)] [-m (MAXPHYADDR)]\n", argv[0]); - break; - } - } - - if (!do_gbpages && !do_maxphyaddr) { - print_skip("No sub-tests selected"); - return 0; - } - - entry = kvm_get_supported_cpuid_entry(0x80000001); - if (!(entry->edx & CPUID_GBPAGES)) { - print_skip("1gb hugepages not supported"); - return 0; - } - - if (do_gbpages) { - pr_info("Test MMIO after toggling CPUID.GBPAGES\n\n"); - mmu_role_test(&entry->edx, entry->edx & ~CPUID_GBPAGES); - } - - if (do_maxphyaddr) { - pr_info("Test MMIO after changing CPUID.MAXPHYADDR\n\n"); - entry = kvm_get_supported_cpuid_entry(0x80000008); - mmu_role_test(&entry->eax, (entry->eax & ~0xff) | 0x20); - } - - return 0; -} diff --git a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c new file mode 100644 index 000000000000..016070cad36e --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "kvm_util.h" +#include "processor.h" + +#define CPUID_MWAIT (1u << 3) + +enum monitor_mwait_testcases { + MWAIT_QUIRK_DISABLED = BIT(0), + MISC_ENABLES_QUIRK_DISABLED = BIT(1), + MWAIT_DISABLED = BIT(2), +}; + +static void guest_monitor_wait(int testcase) +{ + /* + * If both MWAIT and its quirk are disabled, MONITOR/MWAIT should #UD, + * in all other scenarios KVM should emulate them as nops. + */ + bool fault_wanted = (testcase & MWAIT_QUIRK_DISABLED) && + (testcase & MWAIT_DISABLED); + u8 vector; + + GUEST_SYNC(testcase); + + /* + * Arbitrarily MONITOR this function, SVM performs fault checks before + * intercept checks, so the inputs for MONITOR and MWAIT must be valid. + */ + vector = kvm_asm_safe("monitor", "a"(guest_monitor_wait), "c"(0), "d"(0)); + if (fault_wanted) + GUEST_ASSERT_2(vector == UD_VECTOR, testcase, vector); + else + GUEST_ASSERT_2(!vector, testcase, vector); + + vector = kvm_asm_safe("mwait", "a"(guest_monitor_wait), "c"(0), "d"(0)); + if (fault_wanted) + GUEST_ASSERT_2(vector == UD_VECTOR, testcase, vector); + else + GUEST_ASSERT_2(!vector, testcase, vector); +} + +static void guest_code(void) +{ + guest_monitor_wait(MWAIT_DISABLED); + + guest_monitor_wait(MWAIT_QUIRK_DISABLED | MWAIT_DISABLED); + + guest_monitor_wait(MISC_ENABLES_QUIRK_DISABLED | MWAIT_DISABLED); + guest_monitor_wait(MISC_ENABLES_QUIRK_DISABLED); + + guest_monitor_wait(MISC_ENABLES_QUIRK_DISABLED | MWAIT_QUIRK_DISABLED | MWAIT_DISABLED); + guest_monitor_wait(MISC_ENABLES_QUIRK_DISABLED | MWAIT_QUIRK_DISABLED); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + uint64_t disabled_quirks; + struct kvm_vcpu *vcpu; + struct kvm_run *run; + struct kvm_vm *vm; + struct ucall uc; + int testcase; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_DISABLE_QUIRKS2)); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_MWAIT); + + run = vcpu->run; + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + + while (1) { + vcpu_run(vcpu); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + testcase = uc.args[1]; + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT_2(uc, "testcase = %lx, vector = %ld"); + goto done; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + goto done; + } + + disabled_quirks = 0; + if (testcase & MWAIT_QUIRK_DISABLED) + disabled_quirks |= KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS; + if (testcase & MISC_ENABLES_QUIRK_DISABLED) + disabled_quirks |= KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT; + vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, disabled_quirks); + + /* + * If the MISC_ENABLES quirk (KVM neglects to update CPUID to + * enable/disable MWAIT) is disabled, toggle the ENABLE_MWAIT + * bit in MISC_ENABLES accordingly. If the quirk is enabled, + * the only valid configuration is MWAIT disabled, as CPUID + * can't be manually changed after running the vCPU. + */ + if (!(testcase & MISC_ENABLES_QUIRK_DISABLED)) { + TEST_ASSERT(testcase & MWAIT_DISABLED, + "Can't toggle CPUID features after running vCPU"); + continue; + } + + vcpu_set_msr(vcpu, MSR_IA32_MISC_ENABLE, + (testcase & MWAIT_DISABLED) ? 0 : MSR_IA32_MISC_ENABLE_MWAIT); + } + +done: + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c new file mode 100644 index 000000000000..ac33835f78f4 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c @@ -0,0 +1,295 @@ +// SPDX-License-Identifier: GPL-2.0-only +#define _GNU_SOURCE /* for program_invocation_short_name */ + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "vmx.h" +#include "svm_util.h" + +#define L2_GUEST_STACK_SIZE 256 + +/* + * Arbitrary, never shoved into KVM/hardware, just need to avoid conflict with + * the "real" exceptions used, #SS/#GP/#DF (12/13/8). + */ +#define FAKE_TRIPLE_FAULT_VECTOR 0xaa + +/* Arbitrary 32-bit error code injected by this test. */ +#define SS_ERROR_CODE 0xdeadbeef + +/* + * Bit '0' is set on Intel if the exception occurs while delivering a previous + * event/exception. AMD's wording is ambiguous, but presumably the bit is set + * if the exception occurs while delivering an external event, e.g. NMI or INTR, + * but not for exceptions that occur when delivering other exceptions or + * software interrupts. + * + * Note, Intel's name for it, "External event", is misleading and much more + * aligned with AMD's behavior, but the SDM is quite clear on its behavior. + */ +#define ERROR_CODE_EXT_FLAG BIT(0) + +/* + * Bit '1' is set if the fault occurred when looking up a descriptor in the + * IDT, which is the case here as the IDT is empty/NULL. + */ +#define ERROR_CODE_IDT_FLAG BIT(1) + +/* + * The #GP that occurs when vectoring #SS should show the index into the IDT + * for #SS, plus have the "IDT flag" set. + */ +#define GP_ERROR_CODE_AMD ((SS_VECTOR * 8) | ERROR_CODE_IDT_FLAG) +#define GP_ERROR_CODE_INTEL ((SS_VECTOR * 8) | ERROR_CODE_IDT_FLAG | ERROR_CODE_EXT_FLAG) + +/* + * Intel and AMD both shove '0' into the error code on #DF, regardless of what + * led to the double fault. + */ +#define DF_ERROR_CODE 0 + +#define INTERCEPT_SS (BIT_ULL(SS_VECTOR)) +#define INTERCEPT_SS_DF (INTERCEPT_SS | BIT_ULL(DF_VECTOR)) +#define INTERCEPT_SS_GP_DF (INTERCEPT_SS_DF | BIT_ULL(GP_VECTOR)) + +static void l2_ss_pending_test(void) +{ + GUEST_SYNC(SS_VECTOR); +} + +static void l2_ss_injected_gp_test(void) +{ + GUEST_SYNC(GP_VECTOR); +} + +static void l2_ss_injected_df_test(void) +{ + GUEST_SYNC(DF_VECTOR); +} + +static void l2_ss_injected_tf_test(void) +{ + GUEST_SYNC(FAKE_TRIPLE_FAULT_VECTOR); +} + +static void svm_run_l2(struct svm_test_data *svm, void *l2_code, int vector, + uint32_t error_code) +{ + struct vmcb *vmcb = svm->vmcb; + struct vmcb_control_area *ctrl = &vmcb->control; + + vmcb->save.rip = (u64)l2_code; + run_guest(vmcb, svm->vmcb_gpa); + + if (vector == FAKE_TRIPLE_FAULT_VECTOR) + return; + + GUEST_ASSERT_EQ(ctrl->exit_code, (SVM_EXIT_EXCP_BASE + vector)); + GUEST_ASSERT_EQ(ctrl->exit_info_1, error_code); +} + +static void l1_svm_code(struct svm_test_data *svm) +{ + struct vmcb_control_area *ctrl = &svm->vmcb->control; + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + generic_svm_setup(svm, NULL, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + svm->vmcb->save.idtr.limit = 0; + ctrl->intercept |= BIT_ULL(INTERCEPT_SHUTDOWN); + + ctrl->intercept_exceptions = INTERCEPT_SS_GP_DF; + svm_run_l2(svm, l2_ss_pending_test, SS_VECTOR, SS_ERROR_CODE); + svm_run_l2(svm, l2_ss_injected_gp_test, GP_VECTOR, GP_ERROR_CODE_AMD); + + ctrl->intercept_exceptions = INTERCEPT_SS_DF; + svm_run_l2(svm, l2_ss_injected_df_test, DF_VECTOR, DF_ERROR_CODE); + + ctrl->intercept_exceptions = INTERCEPT_SS; + svm_run_l2(svm, l2_ss_injected_tf_test, FAKE_TRIPLE_FAULT_VECTOR, 0); + GUEST_ASSERT_EQ(ctrl->exit_code, SVM_EXIT_SHUTDOWN); + + GUEST_DONE(); +} + +static void vmx_run_l2(void *l2_code, int vector, uint32_t error_code) +{ + GUEST_ASSERT(!vmwrite(GUEST_RIP, (u64)l2_code)); + + GUEST_ASSERT_EQ(vector == SS_VECTOR ? vmlaunch() : vmresume(), 0); + + if (vector == FAKE_TRIPLE_FAULT_VECTOR) + return; + + GUEST_ASSERT_EQ(vmreadz(VM_EXIT_REASON), EXIT_REASON_EXCEPTION_NMI); + GUEST_ASSERT_EQ((vmreadz(VM_EXIT_INTR_INFO) & 0xff), vector); + GUEST_ASSERT_EQ(vmreadz(VM_EXIT_INTR_ERROR_CODE), error_code); +} + +static void l1_vmx_code(struct vmx_pages *vmx) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + GUEST_ASSERT_EQ(prepare_for_vmx_operation(vmx), true); + + GUEST_ASSERT_EQ(load_vmcs(vmx), true); + + prepare_vmcs(vmx, NULL, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + GUEST_ASSERT_EQ(vmwrite(GUEST_IDTR_LIMIT, 0), 0); + + /* + * VMX disallows injecting an exception with error_code[31:16] != 0, + * and hardware will never generate a VM-Exit with bits 31:16 set. + * KVM should likewise truncate the "bad" userspace value. + */ + GUEST_ASSERT_EQ(vmwrite(EXCEPTION_BITMAP, INTERCEPT_SS_GP_DF), 0); + vmx_run_l2(l2_ss_pending_test, SS_VECTOR, (u16)SS_ERROR_CODE); + vmx_run_l2(l2_ss_injected_gp_test, GP_VECTOR, GP_ERROR_CODE_INTEL); + + GUEST_ASSERT_EQ(vmwrite(EXCEPTION_BITMAP, INTERCEPT_SS_DF), 0); + vmx_run_l2(l2_ss_injected_df_test, DF_VECTOR, DF_ERROR_CODE); + + GUEST_ASSERT_EQ(vmwrite(EXCEPTION_BITMAP, INTERCEPT_SS), 0); + vmx_run_l2(l2_ss_injected_tf_test, FAKE_TRIPLE_FAULT_VECTOR, 0); + GUEST_ASSERT_EQ(vmreadz(VM_EXIT_REASON), EXIT_REASON_TRIPLE_FAULT); + + GUEST_DONE(); +} + +static void __attribute__((__flatten__)) l1_guest_code(void *test_data) +{ + if (this_cpu_has(X86_FEATURE_SVM)) + l1_svm_code(test_data); + else + l1_vmx_code(test_data); +} + +static void assert_ucall_vector(struct kvm_vcpu *vcpu, int vector) +{ + struct kvm_run *run = vcpu->run; + struct ucall uc; + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + TEST_ASSERT(vector == uc.args[1], + "Expected L2 to ask for %d, got %ld", vector, uc.args[1]); + break; + case UCALL_DONE: + TEST_ASSERT(vector == -1, + "Expected L2 to ask for %d, L2 says it's done", vector); + break; + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld (0x%lx != 0x%lx)", + (const char *)uc.args[0], __FILE__, uc.args[1], + uc.args[2], uc.args[3]); + break; + default: + TEST_FAIL("Expected L2 to ask for %d, got unexpected ucall %lu", vector, uc.cmd); + } +} + +static void queue_ss_exception(struct kvm_vcpu *vcpu, bool inject) +{ + struct kvm_vcpu_events events; + + vcpu_events_get(vcpu, &events); + + TEST_ASSERT(!events.exception.pending, + "Vector %d unexpectedlt pending", events.exception.nr); + TEST_ASSERT(!events.exception.injected, + "Vector %d unexpectedly injected", events.exception.nr); + + events.flags = KVM_VCPUEVENT_VALID_PAYLOAD; + events.exception.pending = !inject; + events.exception.injected = inject; + events.exception.nr = SS_VECTOR; + events.exception.has_error_code = true; + events.exception.error_code = SS_ERROR_CODE; + vcpu_events_set(vcpu, &events); +} + +/* + * Verify KVM_{G,S}ET_EVENTS play nice with pending vs. injected exceptions + * when an exception is being queued for L2. Specifically, verify that KVM + * honors L1 exception intercept controls when a #SS is pending/injected, + * triggers a #GP on vectoring the #SS, morphs to #DF if #GP isn't intercepted + * by L1, and finally causes (nested) SHUTDOWN if #DF isn't intercepted by L1. + */ +int main(int argc, char *argv[]) +{ + vm_vaddr_t nested_test_data_gva; + struct kvm_vcpu_events events; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_EXCEPTION_PAYLOAD)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM) || kvm_cpu_has(X86_FEATURE_VMX)); + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + vm_enable_cap(vm, KVM_CAP_EXCEPTION_PAYLOAD, -2ul); + + if (kvm_cpu_has(X86_FEATURE_SVM)) + vcpu_alloc_svm(vm, &nested_test_data_gva); + else + vcpu_alloc_vmx(vm, &nested_test_data_gva); + + vcpu_args_set(vcpu, 1, nested_test_data_gva); + + /* Run L1 => L2. L2 should sync and request #SS. */ + vcpu_run(vcpu); + assert_ucall_vector(vcpu, SS_VECTOR); + + /* Pend #SS and request immediate exit. #SS should still be pending. */ + queue_ss_exception(vcpu, false); + vcpu->run->immediate_exit = true; + vcpu_run_complete_io(vcpu); + + /* Verify the pending events comes back out the same as it went in. */ + vcpu_events_get(vcpu, &events); + ASSERT_EQ(events.flags & KVM_VCPUEVENT_VALID_PAYLOAD, + KVM_VCPUEVENT_VALID_PAYLOAD); + ASSERT_EQ(events.exception.pending, true); + ASSERT_EQ(events.exception.nr, SS_VECTOR); + ASSERT_EQ(events.exception.has_error_code, true); + ASSERT_EQ(events.exception.error_code, SS_ERROR_CODE); + + /* + * Run for real with the pending #SS, L1 should get a VM-Exit due to + * #SS interception and re-enter L2 to request #GP (via injected #SS). + */ + vcpu->run->immediate_exit = false; + vcpu_run(vcpu); + assert_ucall_vector(vcpu, GP_VECTOR); + + /* + * Inject #SS, the #SS should bypass interception and cause #GP, which + * L1 should intercept before KVM morphs it to #DF. L1 should then + * disable #GP interception and run L2 to request #DF (via #SS => #GP). + */ + queue_ss_exception(vcpu, true); + vcpu_run(vcpu); + assert_ucall_vector(vcpu, DF_VECTOR); + + /* + * Inject #SS, the #SS should bypass interception and cause #GP, which + * L1 is no longer interception, and so should see a #DF VM-Exit. L1 + * should then signal that is done. + */ + queue_ss_exception(vcpu, true); + vcpu_run(vcpu); + assert_ucall_vector(vcpu, FAKE_TRIPLE_FAULT_VECTOR); + + /* + * Inject #SS yet again. L1 is not intercepting #GP or #DF, and so + * should see nested TRIPLE_FAULT / SHUTDOWN. + */ + queue_ss_exception(vcpu, true); + vcpu_run(vcpu); + assert_ucall_vector(vcpu, -1); + + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c new file mode 100644 index 000000000000..59ffe7fd354f --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c @@ -0,0 +1,272 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * tools/testing/selftests/kvm/nx_huge_page_test.c + * + * Usage: to be run via nx_huge_page_test.sh, which does the necessary + * environment setup and teardown + * + * Copyright (C) 2022, Google LLC. + */ + +#define _GNU_SOURCE + +#include <fcntl.h> +#include <stdint.h> +#include <time.h> + +#include <test_util.h> +#include "kvm_util.h" +#include "processor.h" + +#define HPAGE_SLOT 10 +#define HPAGE_GPA (4UL << 30) /* 4G prevents collision w/ slot 0 */ +#define HPAGE_GVA HPAGE_GPA /* GVA is arbitrary, so use GPA. */ +#define PAGES_PER_2MB_HUGE_PAGE 512 +#define HPAGE_SLOT_NPAGES (3 * PAGES_PER_2MB_HUGE_PAGE) + +/* + * Passed by nx_huge_pages_test.sh to provide an easy warning if this test is + * being run without it. + */ +#define MAGIC_TOKEN 887563923 + +/* + * x86 opcode for the return instruction. Used to call into, and then + * immediately return from, memory backed with hugepages. + */ +#define RETURN_OPCODE 0xC3 + +/* Call the specified memory address. */ +static void guest_do_CALL(uint64_t target) +{ + ((void (*)(void)) target)(); +} + +/* + * Exit the VM after each memory access so that the userspace component of the + * test can make assertions about the pages backing the VM. + * + * See the below for an explanation of how each access should affect the + * backing mappings. + */ +void guest_code(void) +{ + uint64_t hpage_1 = HPAGE_GVA; + uint64_t hpage_2 = hpage_1 + (PAGE_SIZE * 512); + uint64_t hpage_3 = hpage_2 + (PAGE_SIZE * 512); + + READ_ONCE(*(uint64_t *)hpage_1); + GUEST_SYNC(1); + + READ_ONCE(*(uint64_t *)hpage_2); + GUEST_SYNC(2); + + guest_do_CALL(hpage_1); + GUEST_SYNC(3); + + guest_do_CALL(hpage_3); + GUEST_SYNC(4); + + READ_ONCE(*(uint64_t *)hpage_1); + GUEST_SYNC(5); + + READ_ONCE(*(uint64_t *)hpage_3); + GUEST_SYNC(6); +} + +static void check_2m_page_count(struct kvm_vm *vm, int expected_pages_2m) +{ + int actual_pages_2m; + + actual_pages_2m = vm_get_stat(vm, "pages_2m"); + + TEST_ASSERT(actual_pages_2m == expected_pages_2m, + "Unexpected 2m page count. Expected %d, got %d", + expected_pages_2m, actual_pages_2m); +} + +static void check_split_count(struct kvm_vm *vm, int expected_splits) +{ + int actual_splits; + + actual_splits = vm_get_stat(vm, "nx_lpage_splits"); + + TEST_ASSERT(actual_splits == expected_splits, + "Unexpected NX huge page split count. Expected %d, got %d", + expected_splits, actual_splits); +} + +static void wait_for_reclaim(int reclaim_period_ms) +{ + long reclaim_wait_ms; + struct timespec ts; + + reclaim_wait_ms = reclaim_period_ms * 5; + ts.tv_sec = reclaim_wait_ms / 1000; + ts.tv_nsec = (reclaim_wait_ms - (ts.tv_sec * 1000)) * 1000000; + nanosleep(&ts, NULL); +} + +void run_test(int reclaim_period_ms, bool disable_nx_huge_pages, + bool reboot_permissions) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + uint64_t nr_bytes; + void *hva; + int r; + + vm = vm_create(1); + + if (disable_nx_huge_pages) { + r = __vm_disable_nx_huge_pages(vm); + if (reboot_permissions) { + TEST_ASSERT(!r, "Disabling NX huge pages should succeed if process has reboot permissions"); + } else { + TEST_ASSERT(r == -1 && errno == EPERM, + "This process should not have permission to disable NX huge pages"); + return; + } + } + + vcpu = vm_vcpu_add(vm, 0, guest_code); + + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS_HUGETLB, + HPAGE_GPA, HPAGE_SLOT, + HPAGE_SLOT_NPAGES, 0); + + nr_bytes = HPAGE_SLOT_NPAGES * vm->page_size; + + /* + * Ensure that KVM can map HPAGE_SLOT with huge pages by mapping the + * region into the guest with 2MiB pages whenever TDP is disabled (i.e. + * whenever KVM is shadowing the guest page tables). + * + * When TDP is enabled, KVM should be able to map HPAGE_SLOT with huge + * pages irrespective of the guest page size, so map with 4KiB pages + * to test that that is the case. + */ + if (kvm_is_tdp_enabled()) + virt_map_level(vm, HPAGE_GVA, HPAGE_GPA, nr_bytes, PG_LEVEL_4K); + else + virt_map_level(vm, HPAGE_GVA, HPAGE_GPA, nr_bytes, PG_LEVEL_2M); + + hva = addr_gpa2hva(vm, HPAGE_GPA); + memset(hva, RETURN_OPCODE, nr_bytes); + + check_2m_page_count(vm, 0); + check_split_count(vm, 0); + + /* + * The guest code will first read from the first hugepage, resulting + * in a huge page mapping being created. + */ + vcpu_run(vcpu); + check_2m_page_count(vm, 1); + check_split_count(vm, 0); + + /* + * Then the guest code will read from the second hugepage, resulting + * in another huge page mapping being created. + */ + vcpu_run(vcpu); + check_2m_page_count(vm, 2); + check_split_count(vm, 0); + + /* + * Next, the guest will execute from the first huge page, causing it + * to be remapped at 4k. + * + * If NX huge pages are disabled, this should have no effect. + */ + vcpu_run(vcpu); + check_2m_page_count(vm, disable_nx_huge_pages ? 2 : 1); + check_split_count(vm, disable_nx_huge_pages ? 0 : 1); + + /* + * Executing from the third huge page (previously unaccessed) will + * cause part to be mapped at 4k. + * + * If NX huge pages are disabled, it should be mapped at 2M. + */ + vcpu_run(vcpu); + check_2m_page_count(vm, disable_nx_huge_pages ? 3 : 1); + check_split_count(vm, disable_nx_huge_pages ? 0 : 2); + + /* Reading from the first huge page again should have no effect. */ + vcpu_run(vcpu); + check_2m_page_count(vm, disable_nx_huge_pages ? 3 : 1); + check_split_count(vm, disable_nx_huge_pages ? 0 : 2); + + /* Give recovery thread time to run. */ + wait_for_reclaim(reclaim_period_ms); + + /* + * Now that the reclaimer has run, all the split pages should be gone. + * + * If NX huge pages are disabled, the relaimer will not run, so + * nothing should change from here on. + */ + check_2m_page_count(vm, disable_nx_huge_pages ? 3 : 1); + check_split_count(vm, 0); + + /* + * The 4k mapping on hpage 3 should have been removed, so check that + * reading from it causes a huge page mapping to be installed. + */ + vcpu_run(vcpu); + check_2m_page_count(vm, disable_nx_huge_pages ? 3 : 2); + check_split_count(vm, 0); + + kvm_vm_free(vm); +} + +static void help(char *name) +{ + puts(""); + printf("usage: %s [-h] [-p period_ms] [-t token]\n", name); + puts(""); + printf(" -p: The NX reclaim period in miliseconds.\n"); + printf(" -t: The magic token to indicate environment setup is done.\n"); + printf(" -r: The test has reboot permissions and can disable NX huge pages.\n"); + puts(""); + exit(0); +} + +int main(int argc, char **argv) +{ + int reclaim_period_ms = 0, token = 0, opt; + bool reboot_permissions = false; + + while ((opt = getopt(argc, argv, "hp:t:r")) != -1) { + switch (opt) { + case 'p': + reclaim_period_ms = atoi(optarg); + break; + case 't': + token = atoi(optarg); + break; + case 'r': + reboot_permissions = true; + break; + case 'h': + default: + help(argv[0]); + break; + } + } + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_VM_DISABLE_NX_HUGE_PAGES)); + TEST_REQUIRE(reclaim_period_ms > 0); + + __TEST_REQUIRE(token == MAGIC_TOKEN, + "This test must be run with the magic token %d.\n" + "This is done by nx_huge_pages_test.sh, which\n" + "also handles environment setup for the test."); + + run_test(reclaim_period_ms, false, reboot_permissions); + run_test(reclaim_period_ms, true, reboot_permissions); + + return 0; +} + diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh new file mode 100755 index 000000000000..0560149e66ed --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh @@ -0,0 +1,59 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-only */ +# +# Wrapper script which performs setup and cleanup for nx_huge_pages_test. +# Makes use of root privileges to set up huge pages and KVM module parameters. +# +# tools/testing/selftests/kvm/nx_huge_page_test.sh +# Copyright (C) 2022, Google LLC. + +set -e + +NX_HUGE_PAGES=$(cat /sys/module/kvm/parameters/nx_huge_pages) +NX_HUGE_PAGES_RECOVERY_RATIO=$(cat /sys/module/kvm/parameters/nx_huge_pages_recovery_ratio) +NX_HUGE_PAGES_RECOVERY_PERIOD=$(cat /sys/module/kvm/parameters/nx_huge_pages_recovery_period_ms) +HUGE_PAGES=$(cat /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages) + +set +e + +function sudo_echo () { + echo "$1" | sudo tee -a "$2" > /dev/null +} + +NXECUTABLE="$(dirname $0)/nx_huge_pages_test" + +sudo_echo test /dev/null || exit 4 # KSFT_SKIP=4 + +( + set -e + + sudo_echo 1 /sys/module/kvm/parameters/nx_huge_pages + sudo_echo 1 /sys/module/kvm/parameters/nx_huge_pages_recovery_ratio + sudo_echo 100 /sys/module/kvm/parameters/nx_huge_pages_recovery_period_ms + sudo_echo "$(( $HUGE_PAGES + 3 ))" /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages + + # Test with reboot permissions + if [ $(whoami) == "root" ] || sudo setcap cap_sys_boot+ep $NXECUTABLE 2> /dev/null; then + echo Running test with CAP_SYS_BOOT enabled + $NXECUTABLE -t 887563923 -p 100 -r + test $(whoami) == "root" || sudo setcap cap_sys_boot-ep $NXECUTABLE + else + echo setcap failed, skipping nx_huge_pages_test with CAP_SYS_BOOT enabled + fi + + # Test without reboot permissions + if [ $(whoami) != "root" ] ; then + echo Running test with CAP_SYS_BOOT disabled + $NXECUTABLE -t 887563923 -p 100 + else + echo Running as root, skipping nx_huge_pages_test with CAP_SYS_BOOT disabled + fi +) +RET=$? + +sudo_echo "$NX_HUGE_PAGES" /sys/module/kvm/parameters/nx_huge_pages +sudo_echo "$NX_HUGE_PAGES_RECOVERY_RATIO" /sys/module/kvm/parameters/nx_huge_pages_recovery_ratio +sudo_echo "$NX_HUGE_PAGES_RECOVERY_PERIOD" /sys/module/kvm/parameters/nx_huge_pages_recovery_period_ms +sudo_echo "$HUGE_PAGES" /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages + +exit $RET diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c index 1e89688cbbbf..76417c7d687b 100644 --- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c +++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c @@ -21,7 +21,6 @@ #include "kvm_util.h" #include "processor.h" -#define VCPU_ID 0 #define MSR_PLATFORM_INFO_MAX_TURBO_RATIO 0xff00 static void guest_code(void) @@ -35,28 +34,18 @@ static void guest_code(void) } } -static void set_msr_platform_info_enabled(struct kvm_vm *vm, bool enable) +static void test_msr_platform_info_enabled(struct kvm_vcpu *vcpu) { - 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 kvm_run *run = vcpu->run; struct ucall uc; - set_msr_platform_info_enabled(vm, true); - vcpu_run(vm, VCPU_ID); + vm_enable_cap(vcpu->vm, KVM_CAP_MSR_PLATFORM_INFO, true); + vcpu_run(vcpu); 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); + get_ucall(vcpu, &uc); TEST_ASSERT(uc.cmd == UCALL_SYNC, "Received ucall other than UCALL_SYNC: %lu\n", uc.cmd); TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) == @@ -65,12 +54,12 @@ static void test_msr_platform_info_enabled(struct kvm_vm *vm) MSR_PLATFORM_INFO_MAX_TURBO_RATIO); } -static void test_msr_platform_info_disabled(struct kvm_vm *vm) +static void test_msr_platform_info_disabled(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; - set_msr_platform_info_enabled(vm, false); - vcpu_run(vm, VCPU_ID); + vm_enable_cap(vcpu->vm, KVM_CAP_MSR_PLATFORM_INFO, false); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, "Exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n", run->exit_reason, @@ -79,27 +68,23 @@ static void test_msr_platform_info_disabled(struct kvm_vm *vm) int main(int argc, char *argv[]) { + struct kvm_vcpu *vcpu; struct kvm_vm *vm; - 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) { - print_skip("KVM_CAP_MSR_PLATFORM_INFO not supported"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_MSR_PLATFORM_INFO)); - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(&vcpu, 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_enabled(vm); - test_msr_platform_info_disabled(vm); - vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, msr_platform_info); + msr_platform_info = vcpu_get_msr(vcpu, MSR_PLATFORM_INFO); + vcpu_set_msr(vcpu, MSR_PLATFORM_INFO, + msr_platform_info | MSR_PLATFORM_INFO_MAX_TURBO_RATIO); + test_msr_platform_info_enabled(vcpu); + test_msr_platform_info_disabled(vcpu); + vcpu_set_msr(vcpu, MSR_PLATFORM_INFO, msr_platform_info); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c new file mode 100644 index 000000000000..ea4e259a1e2e --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -0,0 +1,479 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test for x86 KVM_SET_PMU_EVENT_FILTER. + * + * Copyright (C) 2022, Google LLC. + * + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Verifies the expected behavior of allow lists and deny lists for + * virtual PMU events. + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +/* + * In lieu of copying perf_event.h into tools... + */ +#define ARCH_PERFMON_EVENTSEL_OS (1ULL << 17) +#define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22) + +union cpuid10_eax { + struct { + unsigned int version_id:8; + unsigned int num_counters:8; + unsigned int bit_width:8; + unsigned int mask_length:8; + } split; + unsigned int full; +}; + +union cpuid10_ebx { + struct { + unsigned int no_unhalted_core_cycles:1; + unsigned int no_instructions_retired:1; + unsigned int no_unhalted_reference_cycles:1; + unsigned int no_llc_reference:1; + unsigned int no_llc_misses:1; + unsigned int no_branch_instruction_retired:1; + unsigned int no_branch_misses_retired:1; + } split; + unsigned int full; +}; + +/* End of stuff taken from perf_event.h. */ + +/* Oddly, this isn't in perf_event.h. */ +#define ARCH_PERFMON_BRANCHES_RETIRED 5 + +#define NUM_BRANCHES 42 + +/* + * This is how the event selector and unit mask are stored in an AMD + * core performance event-select register. Intel's format is similar, + * but the event selector is only 8 bits. + */ +#define EVENT(select, umask) ((select & 0xf00UL) << 24 | (select & 0xff) | \ + (umask & 0xff) << 8) + +/* + * "Branch instructions retired", from the Intel SDM, volume 3, + * "Pre-defined Architectural Performance Events." + */ + +#define INTEL_BR_RETIRED EVENT(0xc4, 0) + +/* + * "Retired branch instructions", from Processor Programming Reference + * (PPR) for AMD Family 17h Model 01h, Revision B1 Processors, + * Preliminary Processor Programming Reference (PPR) for AMD Family + * 17h Model 31h, Revision B0 Processors, and Preliminary Processor + * Programming Reference (PPR) for AMD Family 19h Model 01h, Revision + * B1 Processors Volume 1 of 2. + */ + +#define AMD_ZEN_BR_RETIRED EVENT(0xc2, 0) + +/* + * This event list comprises Intel's eight architectural events plus + * AMD's "retired branch instructions" for Zen[123] (and possibly + * other AMD CPUs). + */ +static const uint64_t event_list[] = { + EVENT(0x3c, 0), + EVENT(0xc0, 0), + EVENT(0x3c, 1), + EVENT(0x2e, 0x4f), + EVENT(0x2e, 0x41), + EVENT(0xc4, 0), + EVENT(0xc5, 0), + EVENT(0xa4, 1), + AMD_ZEN_BR_RETIRED, +}; + +/* + * If we encounter a #GP during the guest PMU sanity check, then the guest + * PMU is not functional. Inform the hypervisor via GUEST_SYNC(0). + */ +static void guest_gp_handler(struct ex_regs *regs) +{ + GUEST_SYNC(0); +} + +/* + * Check that we can write a new value to the given MSR and read it back. + * The caller should provide a non-empty set of bits that are safe to flip. + * + * Return on success. GUEST_SYNC(0) on error. + */ +static void check_msr(uint32_t msr, uint64_t bits_to_flip) +{ + uint64_t v = rdmsr(msr) ^ bits_to_flip; + + wrmsr(msr, v); + if (rdmsr(msr) != v) + GUEST_SYNC(0); + + v ^= bits_to_flip; + wrmsr(msr, v); + if (rdmsr(msr) != v) + GUEST_SYNC(0); +} + +static void intel_guest_code(void) +{ + check_msr(MSR_CORE_PERF_GLOBAL_CTRL, 1); + check_msr(MSR_P6_EVNTSEL0, 0xffff); + check_msr(MSR_IA32_PMC0, 0xffff); + GUEST_SYNC(1); + + for (;;) { + uint64_t br0, br1; + + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); + wrmsr(MSR_P6_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | INTEL_BR_RETIRED); + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 1); + br0 = rdmsr(MSR_IA32_PMC0); + __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); + br1 = rdmsr(MSR_IA32_PMC0); + GUEST_SYNC(br1 - br0); + } +} + +/* + * To avoid needing a check for CPUID.80000001:ECX.PerfCtrExtCore[bit 23], + * this code uses the always-available, legacy K7 PMU MSRs, which alias to + * the first four of the six extended core PMU MSRs. + */ +static void amd_guest_code(void) +{ + check_msr(MSR_K7_EVNTSEL0, 0xffff); + check_msr(MSR_K7_PERFCTR0, 0xffff); + GUEST_SYNC(1); + + for (;;) { + uint64_t br0, br1; + + wrmsr(MSR_K7_EVNTSEL0, 0); + wrmsr(MSR_K7_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_BR_RETIRED); + br0 = rdmsr(MSR_K7_PERFCTR0); + __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); + br1 = rdmsr(MSR_K7_PERFCTR0); + GUEST_SYNC(br1 - br0); + } +} + +/* + * Run the VM to the next GUEST_SYNC(value), and return the value passed + * to the sync. Any other exit from the guest is fatal. + */ +static uint64_t run_vcpu_to_sync(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + struct ucall uc; + + vcpu_run(vcpu); + 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(vcpu, &uc); + TEST_ASSERT(uc.cmd == UCALL_SYNC, + "Received ucall other than UCALL_SYNC: %lu", uc.cmd); + return uc.args[1]; +} + +/* + * In a nested environment or if the vPMU is disabled, the guest PMU + * might not work as architected (accessing the PMU MSRs may raise + * #GP, or writes could simply be discarded). In those situations, + * there is no point in running these tests. The guest code will perform + * a sanity check and then GUEST_SYNC(success). In the case of failure, + * the behavior of the guest on resumption is undefined. + */ +static bool sanity_check_pmu(struct kvm_vcpu *vcpu) +{ + bool success; + + vm_install_exception_handler(vcpu->vm, GP_VECTOR, guest_gp_handler); + success = run_vcpu_to_sync(vcpu); + vm_install_exception_handler(vcpu->vm, GP_VECTOR, NULL); + + return success; +} + +static struct kvm_pmu_event_filter *alloc_pmu_event_filter(uint32_t nevents) +{ + struct kvm_pmu_event_filter *f; + int size = sizeof(*f) + nevents * sizeof(f->events[0]); + + f = malloc(size); + TEST_ASSERT(f, "Out of memory"); + memset(f, 0, size); + f->nevents = nevents; + return f; +} + + +static struct kvm_pmu_event_filter * +create_pmu_event_filter(const uint64_t event_list[], + int nevents, uint32_t action) +{ + struct kvm_pmu_event_filter *f; + int i; + + f = alloc_pmu_event_filter(nevents); + f->action = action; + for (i = 0; i < nevents; i++) + f->events[i] = event_list[i]; + + return f; +} + +static struct kvm_pmu_event_filter *event_filter(uint32_t action) +{ + return create_pmu_event_filter(event_list, + ARRAY_SIZE(event_list), + action); +} + +/* + * Remove the first occurrence of 'event' (if any) from the filter's + * event list. + */ +static struct kvm_pmu_event_filter *remove_event(struct kvm_pmu_event_filter *f, + uint64_t event) +{ + bool found = false; + int i; + + for (i = 0; i < f->nevents; i++) { + if (found) + f->events[i - 1] = f->events[i]; + else + found = f->events[i] == event; + } + if (found) + f->nevents--; + return f; +} + +static void test_without_filter(struct kvm_vcpu *vcpu) +{ + uint64_t count = run_vcpu_to_sync(vcpu); + + if (count != NUM_BRANCHES) + pr_info("%s: Branch instructions retired = %lu (expected %u)\n", + __func__, count, NUM_BRANCHES); + TEST_ASSERT(count, "Allowed PMU event is not counting"); +} + +static uint64_t test_with_filter(struct kvm_vcpu *vcpu, + struct kvm_pmu_event_filter *f) +{ + vm_ioctl(vcpu->vm, KVM_SET_PMU_EVENT_FILTER, f); + return run_vcpu_to_sync(vcpu); +} + +static void test_amd_deny_list(struct kvm_vcpu *vcpu) +{ + uint64_t event = EVENT(0x1C2, 0); + struct kvm_pmu_event_filter *f; + uint64_t count; + + f = create_pmu_event_filter(&event, 1, KVM_PMU_EVENT_DENY); + count = test_with_filter(vcpu, f); + + free(f); + if (count != NUM_BRANCHES) + pr_info("%s: Branch instructions retired = %lu (expected %u)\n", + __func__, count, NUM_BRANCHES); + TEST_ASSERT(count, "Allowed PMU event is not counting"); +} + +static void test_member_deny_list(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY); + uint64_t count = test_with_filter(vcpu, f); + + free(f); + if (count) + pr_info("%s: Branch instructions retired = %lu (expected 0)\n", + __func__, count); + TEST_ASSERT(!count, "Disallowed PMU Event is counting"); +} + +static void test_member_allow_list(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW); + uint64_t count = test_with_filter(vcpu, f); + + free(f); + if (count != NUM_BRANCHES) + pr_info("%s: Branch instructions retired = %lu (expected %u)\n", + __func__, count, NUM_BRANCHES); + TEST_ASSERT(count, "Allowed PMU event is not counting"); +} + +static void test_not_member_deny_list(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY); + uint64_t count; + + remove_event(f, INTEL_BR_RETIRED); + remove_event(f, AMD_ZEN_BR_RETIRED); + count = test_with_filter(vcpu, f); + free(f); + if (count != NUM_BRANCHES) + pr_info("%s: Branch instructions retired = %lu (expected %u)\n", + __func__, count, NUM_BRANCHES); + TEST_ASSERT(count, "Allowed PMU event is not counting"); +} + +static void test_not_member_allow_list(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW); + uint64_t count; + + remove_event(f, INTEL_BR_RETIRED); + remove_event(f, AMD_ZEN_BR_RETIRED); + count = test_with_filter(vcpu, f); + free(f); + if (count) + pr_info("%s: Branch instructions retired = %lu (expected 0)\n", + __func__, count); + TEST_ASSERT(!count, "Disallowed PMU Event is counting"); +} + +/* + * Verify that setting KVM_PMU_CAP_DISABLE prevents the use of the PMU. + * + * Note that KVM_CAP_PMU_CAPABILITY must be invoked prior to creating VCPUs. + */ +static void test_pmu_config_disable(void (*guest_code)(void)) +{ + struct kvm_vcpu *vcpu; + int r; + struct kvm_vm *vm; + + r = kvm_check_cap(KVM_CAP_PMU_CAPABILITY); + if (!(r & KVM_PMU_CAP_DISABLE)) + return; + + vm = vm_create(1); + + vm_enable_cap(vm, KVM_CAP_PMU_CAPABILITY, KVM_PMU_CAP_DISABLE); + + vcpu = vm_vcpu_add(vm, 0, guest_code); + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + + TEST_ASSERT(!sanity_check_pmu(vcpu), + "Guest should not be able to use disabled PMU."); + + kvm_vm_free(vm); +} + +/* + * Check for a non-zero PMU version, at least one general-purpose + * counter per logical processor, an EBX bit vector of length greater + * than 5, and EBX[5] clear. + */ +static bool check_intel_pmu_leaf(const struct kvm_cpuid_entry2 *entry) +{ + union cpuid10_eax eax = { .full = entry->eax }; + union cpuid10_ebx ebx = { .full = entry->ebx }; + + return eax.split.version_id && eax.split.num_counters > 0 && + eax.split.mask_length > ARCH_PERFMON_BRANCHES_RETIRED && + !ebx.split.no_branch_instruction_retired; +} + +/* + * Note that CPUID leaf 0xa is Intel-specific. This leaf should be + * clear on AMD hardware. + */ +static bool use_intel_pmu(void) +{ + const struct kvm_cpuid_entry2 *entry; + + entry = kvm_get_supported_cpuid_entry(0xa); + return is_intel_cpu() && check_intel_pmu_leaf(entry); +} + +static bool is_zen1(uint32_t eax) +{ + return x86_family(eax) == 0x17 && x86_model(eax) <= 0x0f; +} + +static bool is_zen2(uint32_t eax) +{ + return x86_family(eax) == 0x17 && + x86_model(eax) >= 0x30 && x86_model(eax) <= 0x3f; +} + +static bool is_zen3(uint32_t eax) +{ + return x86_family(eax) == 0x19 && x86_model(eax) <= 0x0f; +} + +/* + * Determining AMD support for a PMU event requires consulting the AMD + * PPR for the CPU or reference material derived therefrom. The AMD + * test code herein has been verified to work on Zen1, Zen2, and Zen3. + * + * Feel free to add more AMD CPUs that are documented to support event + * select 0xc2 umask 0 as "retired branch instructions." + */ +static bool use_amd_pmu(void) +{ + const struct kvm_cpuid_entry2 *entry; + + entry = kvm_get_supported_cpuid_entry(1); + return is_amd_cpu() && + (is_zen1(entry->eax) || + is_zen2(entry->eax) || + is_zen3(entry->eax)); +} + +int main(int argc, char *argv[]) +{ + void (*guest_code)(void); + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_FILTER)); + + TEST_REQUIRE(use_intel_pmu() || use_amd_pmu()); + guest_code = use_intel_pmu() ? intel_guest_code : amd_guest_code; + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + + TEST_REQUIRE(sanity_check_pmu(vcpu)); + + if (use_amd_pmu()) + test_amd_deny_list(vcpu); + + test_without_filter(vcpu); + test_member_deny_list(vcpu); + test_member_allow_list(vcpu); + test_not_member_deny_list(vcpu); + test_not_member_allow_list(vcpu); + + kvm_vm_free(vm); + + test_pmu_config_disable(guest_code); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c index ae76436af0cc..b25d7556b638 100644 --- a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c +++ b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c @@ -16,10 +16,6 @@ #include "processor.h" #include "apic.h" -#define N_VCPU 2 -#define VCPU_ID0 0 -#define VCPU_ID1 1 - static void guest_bsp_vcpu(void *arg) { GUEST_SYNC(1); @@ -38,31 +34,30 @@ static void guest_not_bsp_vcpu(void *arg) GUEST_DONE(); } -static void test_set_boot_busy(struct kvm_vm *vm) +static void test_set_bsp_busy(struct kvm_vcpu *vcpu, const char *msg) { - int res; + int r = __vm_ioctl(vcpu->vm, KVM_SET_BOOT_CPU_ID, + (void *)(unsigned long)vcpu->id); - res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID0); - TEST_ASSERT(res == -1 && errno == EBUSY, - "KVM_SET_BOOT_CPU_ID set while running vm"); + TEST_ASSERT(r == -1 && errno == EBUSY, "KVM_SET_BOOT_CPU_ID set %s", msg); } -static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid) +static void run_vcpu(struct kvm_vcpu *vcpu) { struct ucall uc; int stage; for (stage = 0; stage < 2; stage++) { - vcpu_run(vm, vcpuid); + vcpu_run(vcpu); - switch (get_ucall(vm, vcpuid, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && uc.args[1] == stage + 1, "Stage %d: Unexpected register values vmexit, got %lx", stage + 1, (ulong)uc.args[1]); - test_set_boot_busy(vm); + test_set_bsp_busy(vcpu, "while running vm"); break; case UCALL_DONE: TEST_ASSERT(stage == 1, @@ -70,91 +65,67 @@ static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid) stage); break; case UCALL_ABORT: - TEST_ASSERT(false, "%s at %s:%ld\n\tvalues: %#lx, %#lx", - (const char *)uc.args[0], __FILE__, - uc.args[1], uc.args[2], uc.args[3]); + REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx"); default: TEST_ASSERT(false, "Unexpected exit: %s", - exit_reason_str(vcpu_state(vm, vcpuid)->exit_reason)); + exit_reason_str(vcpu->run->exit_reason)); } } } -static struct kvm_vm *create_vm(void) +static struct kvm_vm *create_vm(uint32_t nr_vcpus, uint32_t bsp_vcpu_id, + struct kvm_vcpu *vcpus[]) { struct kvm_vm *vm; - uint64_t vcpu_pages = (DEFAULT_STACK_PGS) * 2; - uint64_t extra_pg_pages = vcpu_pages / PTES_PER_MIN_PAGE * N_VCPU; - uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages; + uint32_t i; - pages = vm_adjust_num_guest_pages(VM_MODE_DEFAULT, pages); - vm = vm_create(VM_MODE_DEFAULT, pages, O_RDWR); + vm = vm_create(nr_vcpus); - kvm_vm_elf_load(vm, program_invocation_name); - vm_create_irqchip(vm); + vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *)(unsigned long)bsp_vcpu_id); + for (i = 0; i < nr_vcpus; i++) + vcpus[i] = vm_vcpu_add(vm, i, i == bsp_vcpu_id ? guest_bsp_vcpu : + guest_not_bsp_vcpu); return vm; } -static void add_x86_vcpu(struct kvm_vm *vm, uint32_t vcpuid, bool bsp_code) -{ - if (bsp_code) - vm_vcpu_add_default(vm, vcpuid, guest_bsp_vcpu); - else - vm_vcpu_add_default(vm, vcpuid, guest_not_bsp_vcpu); -} - -static void run_vm_bsp(uint32_t bsp_vcpu) +static void run_vm_bsp(uint32_t bsp_vcpu_id) { + struct kvm_vcpu *vcpus[2]; struct kvm_vm *vm; - bool is_bsp_vcpu1 = bsp_vcpu == VCPU_ID1; - vm = create_vm(); + vm = create_vm(ARRAY_SIZE(vcpus), bsp_vcpu_id, vcpus); - if (is_bsp_vcpu1) - vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1); - - add_x86_vcpu(vm, VCPU_ID0, !is_bsp_vcpu1); - add_x86_vcpu(vm, VCPU_ID1, is_bsp_vcpu1); - - run_vcpu(vm, VCPU_ID0); - run_vcpu(vm, VCPU_ID1); + run_vcpu(vcpus[0]); + run_vcpu(vcpus[1]); kvm_vm_free(vm); } static void check_set_bsp_busy(void) { + struct kvm_vcpu *vcpus[2]; struct kvm_vm *vm; - int res; - vm = create_vm(); + vm = create_vm(ARRAY_SIZE(vcpus), 0, vcpus); - add_x86_vcpu(vm, VCPU_ID0, true); - add_x86_vcpu(vm, VCPU_ID1, false); + test_set_bsp_busy(vcpus[1], "after adding vcpu"); - res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1); - TEST_ASSERT(res == -1 && errno == EBUSY, "KVM_SET_BOOT_CPU_ID set after adding vcpu"); + run_vcpu(vcpus[0]); + run_vcpu(vcpus[1]); - run_vcpu(vm, VCPU_ID0); - run_vcpu(vm, VCPU_ID1); - - res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1); - TEST_ASSERT(res == -1 && errno == EBUSY, "KVM_SET_BOOT_CPU_ID set to a terminated vcpu"); + test_set_bsp_busy(vcpus[1], "to a terminated vcpu"); kvm_vm_free(vm); } int main(int argc, char *argv[]) { - if (!kvm_check_cap(KVM_CAP_SET_BOOT_CPU_ID)) { - print_skip("set_boot_cpu_id not available"); - return 0; - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_SET_BOOT_CPU_ID)); - run_vm_bsp(VCPU_ID0); - run_vm_bsp(VCPU_ID1); - run_vm_bsp(VCPU_ID0); + run_vm_bsp(0); + run_vm_bsp(1); + run_vm_bsp(0); check_set_bsp_busy(); } diff --git a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c index 318be0bf77ab..2bb08bf2125d 100644 --- a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c +++ b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c @@ -22,9 +22,7 @@ #include "kvm_util.h" #include "processor.h" -#define VCPU_ID 5 - -static void test_cr4_feature_bit(struct kvm_vm *vm, struct kvm_sregs *orig, +static void test_cr4_feature_bit(struct kvm_vcpu *vcpu, struct kvm_sregs *orig, uint64_t feature_bit) { struct kvm_sregs sregs; @@ -37,44 +35,40 @@ static void test_cr4_feature_bit(struct kvm_vm *vm, struct kvm_sregs *orig, memcpy(&sregs, orig, sizeof(sregs)); sregs.cr4 |= feature_bit; - rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs); + rc = _vcpu_sregs_set(vcpu, &sregs); TEST_ASSERT(rc, "KVM allowed unsupported CR4 bit (0x%lx)", feature_bit); /* Sanity check that KVM didn't change anything. */ - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); TEST_ASSERT(!memcmp(&sregs, orig, sizeof(sregs)), "KVM modified sregs"); } -static uint64_t calc_cr4_feature_bits(struct kvm_vm *vm) +static uint64_t calc_supported_cr4_feature_bits(void) { - struct kvm_cpuid_entry2 *cpuid_1, *cpuid_7; uint64_t cr4; - cpuid_1 = kvm_get_supported_cpuid_entry(1); - cpuid_7 = kvm_get_supported_cpuid_entry(7); - cr4 = X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_OSXMMEXCPT; - if (cpuid_7->ecx & CPUID_UMIP) + if (kvm_cpu_has(X86_FEATURE_UMIP)) cr4 |= X86_CR4_UMIP; - if (cpuid_7->ecx & CPUID_LA57) + if (kvm_cpu_has(X86_FEATURE_LA57)) cr4 |= X86_CR4_LA57; - if (cpuid_1->ecx & CPUID_VMX) + if (kvm_cpu_has(X86_FEATURE_VMX)) cr4 |= X86_CR4_VMXE; - if (cpuid_1->ecx & CPUID_SMX) + if (kvm_cpu_has(X86_FEATURE_SMX)) cr4 |= X86_CR4_SMXE; - if (cpuid_7->ebx & CPUID_FSGSBASE) + if (kvm_cpu_has(X86_FEATURE_FSGSBASE)) cr4 |= X86_CR4_FSGSBASE; - if (cpuid_1->ecx & CPUID_PCID) + if (kvm_cpu_has(X86_FEATURE_PCID)) cr4 |= X86_CR4_PCIDE; - if (cpuid_1->ecx & CPUID_XSAVE) + if (kvm_cpu_has(X86_FEATURE_XSAVE)) cr4 |= X86_CR4_OSXSAVE; - if (cpuid_7->ebx & CPUID_SMEP) + if (kvm_cpu_has(X86_FEATURE_SMEP)) cr4 |= X86_CR4_SMEP; - if (cpuid_7->ebx & CPUID_SMAP) + if (kvm_cpu_has(X86_FEATURE_SMAP)) cr4 |= X86_CR4_SMAP; - if (cpuid_7->ecx & CPUID_PKU) + if (kvm_cpu_has(X86_FEATURE_PKU)) cr4 |= X86_CR4_PKE; return cr4; @@ -83,6 +77,7 @@ static uint64_t calc_cr4_feature_bits(struct kvm_vm *vm) int main(int argc, char *argv[]) { struct kvm_sregs sregs; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; uint64_t cr4; int rc; @@ -95,44 +90,44 @@ int main(int argc, char *argv[]) * use it to verify all supported CR4 bits can be set prior to defining * the vCPU model, i.e. without doing KVM_SET_CPUID2. */ - vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); - vm_vcpu_add(vm, VCPU_ID); + vm = vm_create_barebones(); + vcpu = __vm_vcpu_add(vm, 0); - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); - sregs.cr4 |= calc_cr4_feature_bits(vm); + sregs.cr4 |= calc_supported_cr4_feature_bits(); cr4 = sregs.cr4; - rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs); + rc = _vcpu_sregs_set(vcpu, &sregs); TEST_ASSERT(!rc, "Failed to set supported CR4 bits (0x%lx)", cr4); - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); TEST_ASSERT(sregs.cr4 == cr4, "sregs.CR4 (0x%llx) != CR4 (0x%lx)", sregs.cr4, cr4); /* Verify all unsupported features are rejected by KVM. */ - test_cr4_feature_bit(vm, &sregs, X86_CR4_UMIP); - test_cr4_feature_bit(vm, &sregs, X86_CR4_LA57); - test_cr4_feature_bit(vm, &sregs, X86_CR4_VMXE); - test_cr4_feature_bit(vm, &sregs, X86_CR4_SMXE); - test_cr4_feature_bit(vm, &sregs, X86_CR4_FSGSBASE); - test_cr4_feature_bit(vm, &sregs, X86_CR4_PCIDE); - test_cr4_feature_bit(vm, &sregs, X86_CR4_OSXSAVE); - test_cr4_feature_bit(vm, &sregs, X86_CR4_SMEP); - test_cr4_feature_bit(vm, &sregs, X86_CR4_SMAP); - test_cr4_feature_bit(vm, &sregs, X86_CR4_PKE); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_UMIP); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_LA57); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_VMXE); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_SMXE); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_FSGSBASE); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_PCIDE); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_OSXSAVE); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_SMEP); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_SMAP); + test_cr4_feature_bit(vcpu, &sregs, X86_CR4_PKE); kvm_vm_free(vm); /* Create a "real" VM and verify APIC_BASE can be set. */ - vm = vm_create_default(VCPU_ID, 0, NULL); + vm = vm_create_with_one_vcpu(&vcpu, NULL); - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); sregs.apic_base = 1 << 10; - rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs); + rc = _vcpu_sregs_set(vcpu, &sregs); TEST_ASSERT(rc, "Set IA32_APIC_BASE to %llx (invalid)", sregs.apic_base); sregs.apic_base = 1 << 11; - rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs); + rc = _vcpu_sregs_set(vcpu, &sregs); TEST_ASSERT(!rc, "Couldn't set IA32_APIC_BASE to %llx (valid)", sregs.apic_base); diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c index 29b18d565cf4..c7ef97561038 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c +++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c @@ -12,7 +12,6 @@ #include "processor.h" #include "svm_util.h" #include "kselftest.h" -#include "../lib/kvm_util_internal.h" #define SEV_POLICY_ES 0b100 @@ -21,7 +20,9 @@ #define NR_LOCK_TESTING_THREADS 3 #define NR_LOCK_TESTING_ITERATIONS 10000 -static void sev_ioctl(int vm_fd, int cmd_id, void *data) +bool have_sev_es; + +static int __sev_ioctl(int vm_fd, int cmd_id, void *data, __u32 *fw_error) { struct kvm_sev_cmd cmd = { .id = cmd_id, @@ -31,9 +32,19 @@ static void sev_ioctl(int vm_fd, int cmd_id, void *data) int ret; ret = ioctl(vm_fd, KVM_MEMORY_ENCRYPT_OP, &cmd); - TEST_ASSERT((ret == 0 || cmd.error == SEV_RET_SUCCESS), + *fw_error = cmd.error; + return ret; +} + +static void sev_ioctl(int vm_fd, int cmd_id, void *data) +{ + int ret; + __u32 fw_error; + + ret = __sev_ioctl(vm_fd, cmd_id, data, &fw_error); + TEST_ASSERT(ret == 0 && fw_error == SEV_RET_SUCCESS, "%d failed: return code: %d, errno: %d, fw error: %d", - cmd_id, ret, errno, cmd.error); + cmd_id, ret, errno, fw_error); } static struct kvm_vm *sev_vm_create(bool es) @@ -42,10 +53,10 @@ static struct kvm_vm *sev_vm_create(bool es) struct kvm_sev_launch_start start = { 0 }; int i; - vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + vm = vm_create_barebones(); sev_ioctl(vm->fd, es ? KVM_SEV_ES_INIT : KVM_SEV_INIT, NULL); for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i) - vm_vcpu_add(vm, i); + __vm_vcpu_add(vm, i); if (es) start.policy |= SEV_POLICY_ES; sev_ioctl(vm->fd, KVM_SEV_LAUNCH_START, &start); @@ -59,32 +70,27 @@ static struct kvm_vm *aux_vm_create(bool with_vcpus) struct kvm_vm *vm; int i; - vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + vm = vm_create_barebones(); if (!with_vcpus) return vm; for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i) - vm_vcpu_add(vm, i); + __vm_vcpu_add(vm, i); return vm; } -static int __sev_migrate_from(int dst_fd, int src_fd) +static int __sev_migrate_from(struct kvm_vm *dst, struct kvm_vm *src) { - struct kvm_enable_cap cap = { - .cap = KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM, - .args = { src_fd } - }; - - return ioctl(dst_fd, KVM_ENABLE_CAP, &cap); + return __vm_enable_cap(dst, KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM, src->fd); } -static void sev_migrate_from(int dst_fd, int src_fd) +static void sev_migrate_from(struct kvm_vm *dst, struct kvm_vm *src) { int ret; - ret = __sev_migrate_from(dst_fd, src_fd); + ret = __sev_migrate_from(dst, src); TEST_ASSERT(!ret, "Migration failed, ret: %d, errno: %d\n", ret, errno); } @@ -99,13 +105,13 @@ static void test_sev_migrate_from(bool es) dst_vms[i] = aux_vm_create(true); /* Initial migration from the src to the first dst. */ - sev_migrate_from(dst_vms[0]->fd, src_vm->fd); + sev_migrate_from(dst_vms[0], src_vm); for (i = 1; i < NR_MIGRATE_TEST_VMS; i++) - sev_migrate_from(dst_vms[i]->fd, dst_vms[i - 1]->fd); + sev_migrate_from(dst_vms[i], dst_vms[i - 1]); /* Migrate the guest back to the original VM. */ - ret = __sev_migrate_from(src_vm->fd, dst_vms[NR_MIGRATE_TEST_VMS - 1]->fd); + ret = __sev_migrate_from(src_vm, dst_vms[NR_MIGRATE_TEST_VMS - 1]); TEST_ASSERT(ret == -1 && errno == EIO, "VM that was migrated from should be dead. ret %d, errno: %d\n", ret, errno); @@ -117,7 +123,7 @@ static void test_sev_migrate_from(bool es) struct locking_thread_input { struct kvm_vm *vm; - int source_fds[NR_LOCK_TESTING_THREADS]; + struct kvm_vm *source_vms[NR_LOCK_TESTING_THREADS]; }; static void *locking_test_thread(void *arg) @@ -127,7 +133,7 @@ static void *locking_test_thread(void *arg) for (i = 0; i < NR_LOCK_TESTING_ITERATIONS; ++i) { j = i % NR_LOCK_TESTING_THREADS; - __sev_migrate_from(input->vm->fd, input->source_fds[j]); + __sev_migrate_from(input->vm, input->source_vms[j]); } return NULL; @@ -141,11 +147,11 @@ static void test_sev_migrate_locking(void) for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i) { input[i].vm = sev_vm_create(/* es= */ false); - input[0].source_fds[i] = input[i].vm->fd; + input[0].source_vms[i] = input[i].vm; } for (i = 1; i < NR_LOCK_TESTING_THREADS; ++i) - memcpy(input[i].source_fds, input[0].source_fds, - sizeof(input[i].source_fds)); + memcpy(input[i].source_vms, input[0].source_vms, + sizeof(input[i].source_vms)); for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i) pthread_create(&pt[i], NULL, locking_test_thread, &input[i]); @@ -162,89 +168,123 @@ static void test_sev_migrate_parameters(void) *sev_es_vm_no_vmsa; int ret; + vm_no_vcpu = vm_create_barebones(); + vm_no_sev = aux_vm_create(true); + ret = __sev_migrate_from(vm_no_vcpu, vm_no_sev); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "Migrations require SEV enabled. ret %d, errno: %d\n", ret, + errno); + + if (!have_sev_es) + goto out; + sev_vm = sev_vm_create(/* es= */ false); sev_es_vm = sev_vm_create(/* es= */ true); - vm_no_vcpu = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); - vm_no_sev = aux_vm_create(true); - sev_es_vm_no_vmsa = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + sev_es_vm_no_vmsa = vm_create_barebones(); sev_ioctl(sev_es_vm_no_vmsa->fd, KVM_SEV_ES_INIT, NULL); - vm_vcpu_add(sev_es_vm_no_vmsa, 1); + __vm_vcpu_add(sev_es_vm_no_vmsa, 1); - ret = __sev_migrate_from(sev_vm->fd, sev_es_vm->fd); + ret = __sev_migrate_from(sev_vm, sev_es_vm); TEST_ASSERT( ret == -1 && errno == EINVAL, "Should not be able migrate to SEV enabled VM. ret: %d, errno: %d\n", ret, errno); - ret = __sev_migrate_from(sev_es_vm->fd, sev_vm->fd); + ret = __sev_migrate_from(sev_es_vm, sev_vm); TEST_ASSERT( ret == -1 && errno == EINVAL, "Should not be able migrate to SEV-ES enabled VM. ret: %d, errno: %d\n", ret, errno); - ret = __sev_migrate_from(vm_no_vcpu->fd, sev_es_vm->fd); + ret = __sev_migrate_from(vm_no_vcpu, sev_es_vm); TEST_ASSERT( ret == -1 && errno == EINVAL, "SEV-ES migrations require same number of vCPUS. ret: %d, errno: %d\n", ret, errno); - ret = __sev_migrate_from(vm_no_vcpu->fd, sev_es_vm_no_vmsa->fd); + ret = __sev_migrate_from(vm_no_vcpu, sev_es_vm_no_vmsa); TEST_ASSERT( ret == -1 && errno == EINVAL, "SEV-ES migrations require UPDATE_VMSA. ret %d, errno: %d\n", ret, errno); - ret = __sev_migrate_from(vm_no_vcpu->fd, vm_no_sev->fd); - TEST_ASSERT(ret == -1 && errno == EINVAL, - "Migrations require SEV enabled. ret %d, errno: %d\n", ret, - errno); - kvm_vm_free(sev_vm); kvm_vm_free(sev_es_vm); kvm_vm_free(sev_es_vm_no_vmsa); +out: kvm_vm_free(vm_no_vcpu); kvm_vm_free(vm_no_sev); } -static int __sev_mirror_create(int dst_fd, int src_fd) +static int __sev_mirror_create(struct kvm_vm *dst, struct kvm_vm *src) { - struct kvm_enable_cap cap = { - .cap = KVM_CAP_VM_COPY_ENC_CONTEXT_FROM, - .args = { src_fd } - }; - - return ioctl(dst_fd, KVM_ENABLE_CAP, &cap); + return __vm_enable_cap(dst, KVM_CAP_VM_COPY_ENC_CONTEXT_FROM, src->fd); } -static void sev_mirror_create(int dst_fd, int src_fd) +static void sev_mirror_create(struct kvm_vm *dst, struct kvm_vm *src) { int ret; - ret = __sev_mirror_create(dst_fd, src_fd); + ret = __sev_mirror_create(dst, src); TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d\n", ret, errno); } +static void verify_mirror_allowed_cmds(int vm_fd) +{ + struct kvm_sev_guest_status status; + + for (int cmd_id = KVM_SEV_INIT; cmd_id < KVM_SEV_NR_MAX; ++cmd_id) { + int ret; + __u32 fw_error; + + /* + * These commands are allowed for mirror VMs, all others are + * not. + */ + switch (cmd_id) { + case KVM_SEV_LAUNCH_UPDATE_VMSA: + case KVM_SEV_GUEST_STATUS: + case KVM_SEV_DBG_DECRYPT: + case KVM_SEV_DBG_ENCRYPT: + continue; + default: + break; + } + + /* + * These commands should be disallowed before the data + * parameter is examined so NULL is OK here. + */ + ret = __sev_ioctl(vm_fd, cmd_id, NULL, &fw_error); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "Should not be able call command: %d. ret: %d, errno: %d\n", + cmd_id, ret, errno); + } + + sev_ioctl(vm_fd, KVM_SEV_GUEST_STATUS, &status); +} + static void test_sev_mirror(bool es) { struct kvm_vm *src_vm, *dst_vm; - struct kvm_sev_launch_start start = { - .policy = es ? SEV_POLICY_ES : 0 - }; int i; src_vm = sev_vm_create(es); dst_vm = aux_vm_create(false); - sev_mirror_create(dst_vm->fd, src_vm->fd); + sev_mirror_create(dst_vm, src_vm); /* Check that we can complete creation of the mirror VM. */ for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i) - vm_vcpu_add(dst_vm, i); - sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_START, &start); + __vm_vcpu_add(dst_vm, i); + if (es) sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL); + verify_mirror_allowed_cmds(dst_vm->fd); + kvm_vm_free(src_vm); kvm_vm_free(dst_vm); } @@ -255,93 +295,126 @@ static void test_sev_mirror_parameters(void) int ret; sev_vm = sev_vm_create(/* es= */ false); - sev_es_vm = sev_vm_create(/* es= */ true); vm_with_vcpu = aux_vm_create(true); vm_no_vcpu = aux_vm_create(false); - ret = __sev_mirror_create(sev_vm->fd, sev_vm->fd); + ret = __sev_mirror_create(sev_vm, sev_vm); TEST_ASSERT( ret == -1 && errno == EINVAL, "Should not be able copy context to self. ret: %d, errno: %d\n", ret, errno); - ret = __sev_mirror_create(sev_vm->fd, sev_es_vm->fd); + ret = __sev_mirror_create(vm_no_vcpu, vm_with_vcpu); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "Copy context requires SEV enabled. ret %d, errno: %d\n", ret, + errno); + + ret = __sev_mirror_create(vm_with_vcpu, sev_vm); TEST_ASSERT( ret == -1 && errno == EINVAL, - "Should not be able copy context to SEV enabled VM. ret: %d, errno: %d\n", + "SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d\n", ret, errno); - ret = __sev_mirror_create(sev_es_vm->fd, sev_vm->fd); + if (!have_sev_es) + goto out; + + sev_es_vm = sev_vm_create(/* es= */ true); + ret = __sev_mirror_create(sev_vm, sev_es_vm); TEST_ASSERT( ret == -1 && errno == EINVAL, - "Should not be able copy context to SEV-ES enabled VM. ret: %d, errno: %d\n", + "Should not be able copy context to SEV enabled VM. ret: %d, errno: %d\n", ret, errno); - ret = __sev_mirror_create(vm_no_vcpu->fd, vm_with_vcpu->fd); - TEST_ASSERT(ret == -1 && errno == EINVAL, - "Copy context requires SEV enabled. ret %d, errno: %d\n", ret, - errno); - - ret = __sev_mirror_create(vm_with_vcpu->fd, sev_vm->fd); + ret = __sev_mirror_create(sev_es_vm, sev_vm); TEST_ASSERT( ret == -1 && errno == EINVAL, - "SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d\n", + "Should not be able copy context to SEV-ES enabled VM. ret: %d, errno: %d\n", ret, errno); - kvm_vm_free(sev_vm); kvm_vm_free(sev_es_vm); + +out: + kvm_vm_free(sev_vm); kvm_vm_free(vm_with_vcpu); kvm_vm_free(vm_no_vcpu); } static void test_sev_move_copy(void) { - struct kvm_vm *dst_vm, *sev_vm, *mirror_vm, *dst_mirror_vm; - int ret; + struct kvm_vm *dst_vm, *dst2_vm, *dst3_vm, *sev_vm, *mirror_vm, + *dst_mirror_vm, *dst2_mirror_vm, *dst3_mirror_vm; sev_vm = sev_vm_create(/* es= */ false); dst_vm = aux_vm_create(true); + dst2_vm = aux_vm_create(true); + dst3_vm = aux_vm_create(true); mirror_vm = aux_vm_create(false); dst_mirror_vm = aux_vm_create(false); + dst2_mirror_vm = aux_vm_create(false); + dst3_mirror_vm = aux_vm_create(false); - sev_mirror_create(mirror_vm->fd, sev_vm->fd); - ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd); - TEST_ASSERT(ret == -1 && errno == EBUSY, - "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret, - errno); + sev_mirror_create(mirror_vm, sev_vm); - /* The mirror itself can be migrated. */ - sev_migrate_from(dst_mirror_vm->fd, mirror_vm->fd); - ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd); - TEST_ASSERT(ret == -1 && errno == EBUSY, - "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret, - errno); + sev_migrate_from(dst_mirror_vm, mirror_vm); + sev_migrate_from(dst_vm, sev_vm); + + sev_migrate_from(dst2_vm, dst_vm); + sev_migrate_from(dst2_mirror_vm, dst_mirror_vm); + + sev_migrate_from(dst3_mirror_vm, dst2_mirror_vm); + sev_migrate_from(dst3_vm, dst2_vm); + + kvm_vm_free(dst_vm); + kvm_vm_free(sev_vm); + kvm_vm_free(dst2_vm); + kvm_vm_free(dst3_vm); + kvm_vm_free(mirror_vm); + kvm_vm_free(dst_mirror_vm); + kvm_vm_free(dst2_mirror_vm); + kvm_vm_free(dst3_mirror_vm); /* - * mirror_vm is not a mirror anymore, dst_mirror_vm is. Thus, - * the owner can be copied as soon as dst_mirror_vm is gone. + * Run similar test be destroy mirrors before mirrored VMs to ensure + * destruction is done safely. */ - kvm_vm_free(dst_mirror_vm); - sev_migrate_from(dst_vm->fd, sev_vm->fd); + sev_vm = sev_vm_create(/* es= */ false); + dst_vm = aux_vm_create(true); + mirror_vm = aux_vm_create(false); + dst_mirror_vm = aux_vm_create(false); + + sev_mirror_create(mirror_vm, sev_vm); + + sev_migrate_from(dst_mirror_vm, mirror_vm); + sev_migrate_from(dst_vm, sev_vm); kvm_vm_free(mirror_vm); + kvm_vm_free(dst_mirror_vm); kvm_vm_free(dst_vm); kvm_vm_free(sev_vm); } int main(int argc, char *argv[]) { - if (kvm_check_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM)) { + TEST_REQUIRE(kvm_has_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)); + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV)); + + have_sev_es = kvm_cpu_has(X86_FEATURE_SEV_ES); + + if (kvm_has_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM)) { test_sev_migrate_from(/* es= */ false); - test_sev_migrate_from(/* es= */ true); + if (have_sev_es) + test_sev_migrate_from(/* es= */ true); test_sev_migrate_locking(); test_sev_migrate_parameters(); - if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) + if (kvm_has_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) test_sev_move_copy(); } - if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) { + if (kvm_has_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) { test_sev_mirror(/* es= */ false); - test_sev_mirror(/* es= */ true); + if (have_sev_es) + test_sev_mirror(/* es= */ true); test_sev_mirror_parameters(); } return 0; diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index d0fe2fdce58c..1f136a81858e 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -19,10 +19,6 @@ #include "vmx.h" #include "svm_util.h" -#define VCPU_ID 1 - -#define PAGE_SIZE 4096 - #define SMRAM_SIZE 65536 #define SMRAM_MEMSLOT ((1 << 16) | 1) #define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) @@ -87,7 +83,7 @@ static void guest_code(void *arg) sync_with_host(4); if (arg) { - if (cpu_has_svm()) { + if (this_cpu_has(X86_FEATURE_SVM)) { generic_svm_setup(svm, l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); } else { @@ -103,9 +99,8 @@ static void guest_code(void *arg) sync_with_host(7); - if (cpu_has_svm()) { + if (this_cpu_has(X86_FEATURE_SVM)) { run_guest(svm->vmcb, svm->vmcb_gpa); - svm->vmcb->save.rip += 3; run_guest(svm->vmcb, svm->vmcb_gpa); } else { vmlaunch(); @@ -119,22 +114,23 @@ static void guest_code(void *arg) sync_with_host(DONE); } -void inject_smi(struct kvm_vm *vm) +void inject_smi(struct kvm_vcpu *vcpu) { struct kvm_vcpu_events events; - vcpu_events_get(vm, VCPU_ID, &events); + vcpu_events_get(vcpu, &events); events.smi.pending = 1; events.flags |= KVM_VCPUEVENT_VALID_SMM; - vcpu_events_set(vm, VCPU_ID, &events); + vcpu_events_set(vcpu, &events); } int main(int argc, char *argv[]) { vm_vaddr_t nested_gva = 0; + struct kvm_vcpu *vcpu; struct kvm_regs regs; struct kvm_vm *vm; struct kvm_run *run; @@ -142,9 +138,9 @@ int main(int argc, char *argv[]) int stage, stage_reported; /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); - run = vcpu_state(vm, VCPU_ID); + run = vcpu->run; vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA, SMRAM_MEMSLOT, SMRAM_PAGES, 0); @@ -155,29 +151,29 @@ int main(int argc, char *argv[]) memcpy(addr_gpa2hva(vm, SMRAM_GPA) + 0x8000, smi_handler, sizeof(smi_handler)); - vcpu_set_msr(vm, VCPU_ID, MSR_IA32_SMBASE, SMRAM_GPA); + vcpu_set_msr(vcpu, MSR_IA32_SMBASE, SMRAM_GPA); - if (kvm_check_cap(KVM_CAP_NESTED_STATE)) { - if (nested_svm_supported()) + if (kvm_has_cap(KVM_CAP_NESTED_STATE)) { + if (kvm_cpu_has(X86_FEATURE_SVM)) vcpu_alloc_svm(vm, &nested_gva); - else if (nested_vmx_supported()) + else if (kvm_cpu_has(X86_FEATURE_VMX)) vcpu_alloc_vmx(vm, &nested_gva); } if (!nested_gva) pr_info("will skip SMM test with VMX enabled\n"); - vcpu_args_set(vm, VCPU_ID, 1, nested_gva); + vcpu_args_set(vcpu, 1, nested_gva); for (stage = 1;; stage++) { - _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Stage %d: unexpected exit reason: %u (%s),\n", stage, run->exit_reason, exit_reason_str(run->exit_reason)); memset(®s, 0, sizeof(regs)); - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); stage_reported = regs.rax & 0xff; @@ -194,7 +190,7 @@ int main(int argc, char *argv[]) * return from it. Do not perform save/restore while in SMM yet. */ if (stage == 8) { - inject_smi(vm); + inject_smi(vcpu); continue; } @@ -203,16 +199,15 @@ int main(int argc, char *argv[]) * during L2 execution. */ if (stage == 10) - inject_smi(vm); + inject_smi(vcpu); - state = vcpu_save_state(vm, VCPU_ID); + state = vcpu_save_state(vcpu); kvm_vm_release(vm); - kvm_vm_restart(vm, O_RDWR); - vm_vcpu_add(vm, VCPU_ID); - 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); + + vcpu = vm_recreate_with_one_vcpu(vm); + vcpu_load_state(vcpu, state); + run = vcpu->run; + kvm_x86_state_cleanup(state); } done: diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c index 32854c1462ad..ea578971fb9f 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -20,7 +20,6 @@ #include "vmx.h" #include "svm_util.h" -#define VCPU_ID 5 #define L2_GUEST_STACK_SIZE 256 void svm_l2_guest_code(void) @@ -143,7 +142,7 @@ static void __attribute__((__flatten__)) guest_code(void *arg) GUEST_SYNC(2); if (arg) { - if (cpu_has_svm()) + if (this_cpu_has(X86_FEATURE_SVM)) svm_l1_guest_code(arg); else vmx_l1_guest_code(arg); @@ -157,6 +156,7 @@ int main(int argc, char *argv[]) vm_vaddr_t nested_gva = 0; struct kvm_regs regs1, regs2; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; struct kvm_x86_state *state; @@ -164,34 +164,33 @@ int main(int argc, char *argv[]) int stage; /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - run = vcpu_state(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + run = vcpu->run; - vcpu_regs_get(vm, VCPU_ID, ®s1); + vcpu_regs_get(vcpu, ®s1); - if (kvm_check_cap(KVM_CAP_NESTED_STATE)) { - if (nested_svm_supported()) + if (kvm_has_cap(KVM_CAP_NESTED_STATE)) { + if (kvm_cpu_has(X86_FEATURE_SVM)) vcpu_alloc_svm(vm, &nested_gva); - else if (nested_vmx_supported()) + else if (kvm_cpu_has(X86_FEATURE_VMX)) vcpu_alloc_vmx(vm, &nested_gva); } if (!nested_gva) pr_info("will skip nested state checks\n"); - vcpu_args_set(vm, VCPU_ID, 1, nested_gva); + vcpu_args_set(vcpu, 1, nested_gva); for (stage = 1;; stage++) { - _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Stage %d: unexpected exit reason: %u (%s),\n", stage, run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: break; @@ -206,22 +205,20 @@ int main(int argc, char *argv[]) uc.args[1] == stage, "Stage %d: Unexpected register values vmexit, got %lx", stage, (ulong)uc.args[1]); - state = vcpu_save_state(vm, VCPU_ID); + state = vcpu_save_state(vcpu); memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vm, VCPU_ID, ®s1); + vcpu_regs_get(vcpu, ®s1); kvm_vm_release(vm); /* Restore state in a new VM. */ - kvm_vm_restart(vm, O_RDWR); - vm_vcpu_add(vm, VCPU_ID); - 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); + vcpu = vm_recreate_with_one_vcpu(vm); + vcpu_load_state(vcpu, state); + run = vcpu->run; + kvm_x86_state_cleanup(state); memset(®s2, 0, sizeof(regs2)); - vcpu_regs_get(vm, VCPU_ID, ®s2); + vcpu_regs_get(vcpu, ®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); diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c index 30a81038df46..4a07ba227b99 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c @@ -13,10 +13,6 @@ #include "svm_util.h" #include "apic.h" -#define VCPU_ID 0 - -static struct kvm_vm *vm; - bool vintr_irq_called; bool intr_irq_called; @@ -88,33 +84,36 @@ static void l1_guest_code(struct svm_test_data *svm) int main(int argc, char *argv[]) { + struct kvm_vcpu *vcpu; + struct kvm_run *run; vm_vaddr_t svm_gva; + struct kvm_vm *vm; + struct ucall uc; - nested_svm_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); - vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); + vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vm, VINTR_IRQ_NUMBER, vintr_irq_handler); vm_install_exception_handler(vm, INTR_IRQ_NUMBER, intr_irq_handler); vcpu_alloc_svm(vm, &svm_gva); - vcpu_args_set(vm, VCPU_ID, 1, svm_gva); + vcpu_args_set(vcpu, 1, svm_gva); - struct kvm_run *run = vcpu_state(vm, VCPU_ID); - struct ucall uc; + run = vcpu->run; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s", (const char *)uc.args[0]); + REPORT_GUEST_ASSERT(uc); break; /* NOT REACHED */ case UCALL_DONE: diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c new file mode 100644 index 000000000000..e637d7736012 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c @@ -0,0 +1,211 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2022 Oracle and/or its affiliates. + * + * Based on: + * svm_int_ctl_test + * + * Copyright (C) 2021, Red Hat, Inc. + * + */ + +#include <stdatomic.h> +#include <stdio.h> +#include <unistd.h> +#include "apic.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "test_util.h" + +#define INT_NR 0x20 + +static_assert(ATOMIC_INT_LOCK_FREE == 2, "atomic int is not lockless"); + +static unsigned int bp_fired; +static void guest_bp_handler(struct ex_regs *regs) +{ + bp_fired++; +} + +static unsigned int int_fired; +static void l2_guest_code_int(void); + +static void guest_int_handler(struct ex_regs *regs) +{ + int_fired++; + GUEST_ASSERT_2(regs->rip == (unsigned long)l2_guest_code_int, + regs->rip, (unsigned long)l2_guest_code_int); +} + +static void l2_guest_code_int(void) +{ + GUEST_ASSERT_1(int_fired == 1, int_fired); + vmmcall(); + ud2(); + + GUEST_ASSERT_1(bp_fired == 1, bp_fired); + hlt(); +} + +static atomic_int nmi_stage; +#define nmi_stage_get() atomic_load_explicit(&nmi_stage, memory_order_acquire) +#define nmi_stage_inc() atomic_fetch_add_explicit(&nmi_stage, 1, memory_order_acq_rel) +static void guest_nmi_handler(struct ex_regs *regs) +{ + nmi_stage_inc(); + + if (nmi_stage_get() == 1) { + vmmcall(); + GUEST_ASSERT(false); + } else { + GUEST_ASSERT_1(nmi_stage_get() == 3, nmi_stage_get()); + GUEST_DONE(); + } +} + +static void l2_guest_code_nmi(void) +{ + ud2(); +} + +static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t idt_alt) +{ + #define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + + if (is_nmi) + x2apic_enable(); + + /* Prepare for L2 execution. */ + generic_svm_setup(svm, + is_nmi ? l2_guest_code_nmi : l2_guest_code_int, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + vmcb->control.intercept_exceptions |= BIT(PF_VECTOR) | BIT(UD_VECTOR); + vmcb->control.intercept |= BIT(INTERCEPT_NMI) | BIT(INTERCEPT_HLT); + + if (is_nmi) { + vmcb->control.event_inj = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI; + } else { + vmcb->control.event_inj = INT_NR | SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_SOFT; + /* The return address pushed on stack */ + vmcb->control.next_rip = vmcb->save.rip; + } + + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT_3(vmcb->control.exit_code == SVM_EXIT_VMMCALL, + vmcb->control.exit_code, + vmcb->control.exit_info_1, vmcb->control.exit_info_2); + + if (is_nmi) { + clgi(); + x2apic_write_reg(APIC_ICR, APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_NMI); + + GUEST_ASSERT_1(nmi_stage_get() == 1, nmi_stage_get()); + nmi_stage_inc(); + + stgi(); + /* self-NMI happens here */ + while (true) + cpu_relax(); + } + + /* Skip over VMMCALL */ + vmcb->save.rip += 3; + + /* Switch to alternate IDT to cause intervening NPF again */ + vmcb->save.idtr.base = idt_alt; + vmcb->control.clean = 0; /* &= ~BIT(VMCB_DT) would be enough */ + + vmcb->control.event_inj = BP_VECTOR | SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_EXEPT; + /* The return address pushed on stack, skip over UD2 */ + vmcb->control.next_rip = vmcb->save.rip + 2; + + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT_3(vmcb->control.exit_code == SVM_EXIT_HLT, + vmcb->control.exit_code, + vmcb->control.exit_info_1, vmcb->control.exit_info_2); + + GUEST_DONE(); +} + +static void run_test(bool is_nmi) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + vm_vaddr_t svm_gva; + vm_vaddr_t idt_alt_vm; + struct kvm_guest_debug debug; + + pr_info("Running %s test\n", is_nmi ? "NMI" : "soft int"); + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + + vm_install_exception_handler(vm, NMI_VECTOR, guest_nmi_handler); + vm_install_exception_handler(vm, BP_VECTOR, guest_bp_handler); + vm_install_exception_handler(vm, INT_NR, guest_int_handler); + + vcpu_alloc_svm(vm, &svm_gva); + + if (!is_nmi) { + void *idt, *idt_alt; + + idt_alt_vm = vm_vaddr_alloc_page(vm); + idt_alt = addr_gva2hva(vm, idt_alt_vm); + idt = addr_gva2hva(vm, vm->idt); + memcpy(idt_alt, idt, getpagesize()); + } else { + idt_alt_vm = 0; + } + vcpu_args_set(vcpu, 3, svm_gva, (uint64_t)is_nmi, (uint64_t)idt_alt_vm); + + memset(&debug, 0, sizeof(debug)); + vcpu_guest_debug_set(vcpu, &debug); + + struct kvm_run *run = vcpu->run; + struct ucall uc; + + alarm(2); + vcpu_run(vcpu); + alarm(0); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT_3(uc, "vals = 0x%lx 0x%lx 0x%lx"); + break; + /* NOT REACHED */ + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd); + } +done: + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); + + TEST_ASSERT(kvm_cpu_has(X86_FEATURE_NRIPS), + "KVM with nSVM is supposed to unconditionally advertise nRIP Save"); + + atomic_init(&nmi_stage, 0); + + run_test(false); + run_test(true); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c index be2ca157485b..c3ac45df7483 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c @@ -12,10 +12,6 @@ #include "processor.h" #include "svm_util.h" -#define VCPU_ID 5 - -static struct kvm_vm *vm; - static void l2_guest_code(struct svm_test_data *svm) { __asm__ __volatile__("vmcall"); @@ -39,28 +35,30 @@ static void l1_guest_code(struct svm_test_data *svm) int main(int argc, char *argv[]) { + struct kvm_vcpu *vcpu; vm_vaddr_t svm_gva; + struct kvm_vm *vm; - nested_svm_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); - vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); vcpu_alloc_svm(vm, &svm_gva); - vcpu_args_set(vm, VCPU_ID, 1, svm_gva); + vcpu_args_set(vcpu, 1, svm_gva); for (;;) { - volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + volatile struct kvm_run *run = vcpu->run; struct ucall uc; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s", (const char *)uc.args[0]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: break; diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c index fc03a150278d..9b6db0b0b13e 100644 --- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c +++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c @@ -20,8 +20,6 @@ #include "kvm_util.h" #include "processor.h" -#define VCPU_ID 5 - #define UCALL_PIO_PORT ((uint16_t)0x1000) struct ucall uc_none = { @@ -84,6 +82,7 @@ static void compare_vcpu_events(struct kvm_vcpu_events *left, int main(int argc, char *argv[]) { + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; struct kvm_regs regs; @@ -95,66 +94,59 @@ int main(int argc, char *argv[]) setbuf(stdout, NULL); cap = kvm_check_cap(KVM_CAP_SYNC_REGS); - if ((cap & TEST_SYNC_FIELDS) != TEST_SYNC_FIELDS) { - print_skip("KVM_CAP_SYNC_REGS not supported"); - exit(KSFT_SKIP); - } - if ((cap & INVALID_SYNC_FIELD) != 0) { - print_skip("The \"invalid\" field is not invalid"); - exit(KSFT_SKIP); - } + TEST_REQUIRE((cap & TEST_SYNC_FIELDS) == TEST_SYNC_FIELDS); + TEST_REQUIRE(!(cap & INVALID_SYNC_FIELD)); - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); - run = vcpu_state(vm, VCPU_ID); + run = vcpu->run; /* Request reading invalid register set from VCPU. */ run->kvm_valid_regs = INVALID_SYNC_FIELD; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(rv < 0 && errno == EINVAL, "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n", rv); - vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0; + run->kvm_valid_regs = 0; run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(rv < 0 && errno == EINVAL, "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n", rv); - vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0; + run->kvm_valid_regs = 0; /* Request setting invalid register set into VCPU. */ run->kvm_dirty_regs = INVALID_SYNC_FIELD; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(rv < 0 && errno == EINVAL, "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n", rv); - vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0; + run->kvm_dirty_regs = 0; run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(rv < 0 && errno == EINVAL, "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n", rv); - vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0; + run->kvm_dirty_regs = 0; /* Request and verify all valid register sets. */ /* TODO: BUILD TIME CHECK: TEST_ASSERT(KVM_SYNC_X86_NUM_FIELDS != 3); */ run->kvm_valid_regs = TEST_SYNC_FIELDS; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", run->exit_reason, exit_reason_str(run->exit_reason)); - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); compare_regs(®s, &run->s.regs.regs); - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); compare_sregs(&sregs, &run->s.regs.sregs); - vcpu_events_get(vm, VCPU_ID, &events); + vcpu_events_get(vcpu, &events); compare_vcpu_events(&events, &run->s.regs.events); /* Set and verify various register values. */ @@ -164,7 +156,7 @@ int main(int argc, char *argv[]) run->kvm_valid_regs = TEST_SYNC_FIELDS; run->kvm_dirty_regs = KVM_SYNC_X86_REGS | KVM_SYNC_X86_SREGS; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", run->exit_reason, @@ -176,13 +168,13 @@ int main(int argc, char *argv[]) "apic_base sync regs value incorrect 0x%llx.", run->s.regs.sregs.apic_base); - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); compare_regs(®s, &run->s.regs.regs); - vcpu_sregs_get(vm, VCPU_ID, &sregs); + vcpu_sregs_get(vcpu, &sregs); compare_sregs(&sregs, &run->s.regs.sregs); - vcpu_events_get(vm, VCPU_ID, &events); + vcpu_events_get(vcpu, &events); compare_vcpu_events(&events, &run->s.regs.events); /* Clear kvm_dirty_regs bits, verify new s.regs values are @@ -191,7 +183,7 @@ int main(int argc, char *argv[]) run->kvm_valid_regs = TEST_SYNC_FIELDS; run->kvm_dirty_regs = 0; run->s.regs.regs.rbx = 0xDEADBEEF; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", run->exit_reason, @@ -208,8 +200,8 @@ int main(int argc, char *argv[]) run->kvm_dirty_regs = 0; run->s.regs.regs.rbx = 0xAAAA; regs.rbx = 0xBAC0; - vcpu_regs_set(vm, VCPU_ID, ®s); - rv = _vcpu_run(vm, VCPU_ID); + vcpu_regs_set(vcpu, ®s); + rv = _vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", run->exit_reason, @@ -217,7 +209,7 @@ int main(int argc, char *argv[]) TEST_ASSERT(run->s.regs.regs.rbx == 0xAAAA, "rbx sync regs value incorrect 0x%llx.", run->s.regs.regs.rbx); - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); TEST_ASSERT(regs.rbx == 0xBAC0 + 1, "rbx guest value incorrect 0x%llx.", regs.rbx); @@ -229,7 +221,7 @@ int main(int argc, char *argv[]) run->kvm_valid_regs = 0; run->kvm_dirty_regs = TEST_SYNC_FIELDS; run->s.regs.regs.rbx = 0xBBBB; - rv = _vcpu_run(vm, VCPU_ID); + rv = _vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", run->exit_reason, @@ -237,7 +229,7 @@ int main(int argc, char *argv[]) TEST_ASSERT(run->s.regs.regs.rbx == 0xBBBB, "rbx sync regs value incorrect 0x%llx.", run->s.regs.regs.rbx); - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); TEST_ASSERT(regs.rbx == 0xBBBB + 1, "rbx guest value incorrect 0x%llx.", regs.rbx); diff --git a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c b/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c new file mode 100644 index 000000000000..70b44f0b52fe --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c @@ -0,0 +1,90 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "vmx.h" + +#include <string.h> +#include <sys/ioctl.h> + +#include "kselftest.h" + +#define ARBITRARY_IO_PORT 0x2000 + +/* The virtual machine object. */ +static struct kvm_vm *vm; + +static void l2_guest_code(void) +{ + asm volatile("inb %%dx, %%al" + : : [port] "d" (ARBITRARY_IO_PORT) : "rax"); +} + +void l1_guest_code(struct vmx_pages *vmx) +{ +#define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + GUEST_ASSERT(vmx->vmcs_gpa); + GUEST_ASSERT(prepare_for_vmx_operation(vmx)); + GUEST_ASSERT(load_vmcs(vmx)); + + prepare_vmcs(vmx, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + GUEST_ASSERT(!vmlaunch()); + /* L2 should triple fault after a triple fault event injected. */ + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_TRIPLE_FAULT); + GUEST_DONE(); +} + +int main(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_run *run; + struct kvm_vcpu_events events; + vm_vaddr_t vmx_pages_gva; + struct ucall uc; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_TRIPLE_FAULT_EVENT)); + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + vm_enable_cap(vm, KVM_CAP_X86_TRIPLE_FAULT_EVENT, 1); + + run = vcpu->run; + vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); + vcpu_run(vcpu); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Expected KVM_EXIT_IO, got: %u (%s)\n", + run->exit_reason, exit_reason_str(run->exit_reason)); + TEST_ASSERT(run->io.port == ARBITRARY_IO_PORT, + "Expected IN from port %d from L2, got port %d", + ARBITRARY_IO_PORT, run->io.port); + vcpu_events_get(vcpu, &events); + events.flags |= KVM_VCPUEVENT_VALID_TRIPLE_FAULT; + events.triple_fault.pending = true; + vcpu_events_set(vcpu, &events); + run->immediate_exit = true; + vcpu_run_complete_io(vcpu); + + vcpu_events_get(vcpu, &events); + TEST_ASSERT(events.flags & KVM_VCPUEVENT_VALID_TRIPLE_FAULT, + "Triple fault event invalid"); + TEST_ASSERT(events.triple_fault.pending, + "No triple fault pending"); + vcpu_run(vcpu); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_DONE: + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + default: + TEST_FAIL("Unexpected ucall: %lu", uc.cmd); + } + +} diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c index 5a6a662f2e59..22d366c697f7 100644 --- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c +++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c @@ -9,14 +9,12 @@ #include "kvm_util.h" #include "processor.h" -#define VCPU_ID 0 - #define UNITY (1ull << 30) #define HOST_ADJUST (UNITY * 64) #define GUEST_STEP (UNITY * 4) #define ROUND(x) ((x + UNITY / 2) & -UNITY) #define rounded_rdmsr(x) ROUND(rdmsr(x)) -#define rounded_host_rdmsr(x) ROUND(vcpu_get_msr(vm, 0, x)) +#define rounded_host_rdmsr(x) ROUND(vcpu_get_msr(vcpu, x)) static void guest_code(void) { @@ -66,51 +64,48 @@ static void guest_code(void) GUEST_DONE(); } -static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid, int stage) +static void run_vcpu(struct kvm_vcpu *vcpu, int stage) { struct ucall uc; - vcpu_args_set(vm, vcpuid, 1, vcpuid); - - vcpu_ioctl(vm, vcpuid, KVM_RUN, NULL); + vcpu_run(vcpu); - switch (get_ucall(vm, vcpuid, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && - uc.args[1] == stage + 1, "Stage %d: Unexpected register values vmexit, got %lx", - stage + 1, (ulong)uc.args[1]); + uc.args[1] == stage + 1, "Stage %d: Unexpected register values vmexit, got %lx", + stage + 1, (ulong)uc.args[1]); return; case UCALL_DONE: return; case UCALL_ABORT: - TEST_ASSERT(false, "%s at %s:%ld\n" \ - "\tvalues: %#lx, %#lx", (const char *)uc.args[0], - __FILE__, uc.args[1], uc.args[2], uc.args[3]); + REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx"); default: TEST_ASSERT(false, "Unexpected exit: %s", - exit_reason_str(vcpu_state(vm, vcpuid)->exit_reason)); + exit_reason_str(vcpu->run->exit_reason)); } } int main(void) { + struct kvm_vcpu *vcpu; struct kvm_vm *vm; uint64_t val; - vm = vm_create_default(VCPU_ID, 0, guest_code); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); val = 0; ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); /* Guest: writes to MSR_IA32_TSC affect both MSRs. */ - run_vcpu(vm, VCPU_ID, 1); + run_vcpu(vcpu, 1); val = 1ull * GUEST_STEP; ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); /* Guest: writes to MSR_IA32_TSC_ADJUST affect both MSRs. */ - run_vcpu(vm, VCPU_ID, 2); + run_vcpu(vcpu, 2); val = 2ull * GUEST_STEP; ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); @@ -119,18 +114,18 @@ int main(void) * Host: writes to MSR_IA32_TSC set the host-side offset * and therefore do not change MSR_IA32_TSC_ADJUST. */ - vcpu_set_msr(vm, 0, MSR_IA32_TSC, HOST_ADJUST + val); + vcpu_set_msr(vcpu, MSR_IA32_TSC, HOST_ADJUST + val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); - run_vcpu(vm, VCPU_ID, 3); + run_vcpu(vcpu, 3); /* Host: writes to MSR_IA32_TSC_ADJUST do not modify the TSC. */ - vcpu_set_msr(vm, 0, MSR_IA32_TSC_ADJUST, UNITY * 123456); + vcpu_set_msr(vcpu, MSR_IA32_TSC_ADJUST, UNITY * 123456); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val); - ASSERT_EQ(vcpu_get_msr(vm, 0, MSR_IA32_TSC_ADJUST), UNITY * 123456); + ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_TSC_ADJUST), UNITY * 123456); /* Restore previous value. */ - vcpu_set_msr(vm, 0, MSR_IA32_TSC_ADJUST, val); + vcpu_set_msr(vcpu, MSR_IA32_TSC_ADJUST, val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); @@ -138,7 +133,7 @@ int main(void) * Guest: writes to MSR_IA32_TSC_ADJUST do not destroy the * host-side offset and affect both MSRs. */ - run_vcpu(vm, VCPU_ID, 4); + run_vcpu(vcpu, 4); val = 3ull * GUEST_STEP; ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); @@ -147,7 +142,7 @@ int main(void) * Guest: writes to MSR_IA32_TSC affect both MSRs, so the host-side * offset is now visible in MSR_IA32_TSC_ADJUST. */ - run_vcpu(vm, VCPU_ID, 5); + run_vcpu(vcpu, 5); val = 4ull * GUEST_STEP; ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val - HOST_ADJUST); diff --git a/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c b/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c new file mode 100644 index 000000000000..47139aab7408 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * svm_vmcall_test + * + * Copyright © 2021 Amazon.com, Inc. or its affiliates. + * + * Xen shared_info / pvclock testing + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +#include <stdint.h> +#include <time.h> +#include <sched.h> +#include <signal.h> +#include <pthread.h> + +#define NR_TEST_VCPUS 20 + +static struct kvm_vm *vm; +pthread_spinlock_t create_lock; + +#define TEST_TSC_KHZ 2345678UL +#define TEST_TSC_OFFSET 200000000 + +uint64_t tsc_sync; +static void guest_code(void) +{ + uint64_t start_tsc, local_tsc, tmp; + + start_tsc = rdtsc(); + do { + tmp = READ_ONCE(tsc_sync); + local_tsc = rdtsc(); + WRITE_ONCE(tsc_sync, local_tsc); + if (unlikely(local_tsc < tmp)) + GUEST_SYNC_ARGS(0, local_tsc, tmp, 0, 0); + + } while (local_tsc - start_tsc < 5000 * TEST_TSC_KHZ); + + GUEST_DONE(); +} + + +static void *run_vcpu(void *_cpu_nr) +{ + unsigned long vcpu_id = (unsigned long)_cpu_nr; + unsigned long failures = 0; + static bool first_cpu_done; + struct kvm_vcpu *vcpu; + + /* The kernel is fine, but vm_vcpu_add() needs locking */ + pthread_spin_lock(&create_lock); + + vcpu = vm_vcpu_add(vm, vcpu_id, guest_code); + + if (!first_cpu_done) { + first_cpu_done = true; + vcpu_set_msr(vcpu, MSR_IA32_TSC, TEST_TSC_OFFSET); + } + + pthread_spin_unlock(&create_lock); + + for (;;) { + volatile struct kvm_run *run = vcpu->run; + struct ucall uc; + + vcpu_run(vcpu); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_DONE: + goto out; + + case UCALL_SYNC: + printf("Guest %d sync %lx %lx %ld\n", vcpu->id, + uc.args[2], uc.args[3], uc.args[2] - uc.args[3]); + failures++; + break; + + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + } + out: + return (void *)failures; +} + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_has_cap(KVM_CAP_VM_TSC_CONTROL)); + + vm = vm_create(NR_TEST_VCPUS); + vm_ioctl(vm, KVM_SET_TSC_KHZ, (void *) TEST_TSC_KHZ); + + pthread_spin_init(&create_lock, PTHREAD_PROCESS_PRIVATE); + pthread_t cpu_threads[NR_TEST_VCPUS]; + unsigned long cpu; + for (cpu = 0; cpu < NR_TEST_VCPUS; cpu++) + pthread_create(&cpu_threads[cpu], NULL, run_vcpu, (void *)cpu); + + unsigned long failures = 0; + for (cpu = 0; cpu < NR_TEST_VCPUS; cpu++) { + void *this_cpu_failures; + pthread_join(cpu_threads[cpu], &this_cpu_failures); + failures += (unsigned long)this_cpu_failures; + } + + TEST_ASSERT(!failures, "TSC sync failed"); + pthread_spin_destroy(&create_lock); + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c new file mode 100644 index 000000000000..a897c7fd8abe --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c @@ -0,0 +1,316 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ucna_injection_test + * + * Copyright (C) 2022, Google LLC. + * + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Test that user space can inject UnCorrectable No Action required (UCNA) + * memory errors to the guest. + * + * The test starts one vCPU with the MCG_CMCI_P enabled. It verifies that + * proper UCNA errors can be injected to a vCPU with MCG_CMCI_P and + * corresponding per-bank control register (MCI_CTL2) bit enabled. + * The test also checks that the UCNA errors get recorded in the + * Machine Check bank registers no matter the error signal interrupts get + * delivered into the guest or not. + * + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <pthread.h> +#include <inttypes.h> +#include <string.h> +#include <time.h> + +#include "kvm_util_base.h" +#include "kvm_util.h" +#include "mce.h" +#include "processor.h" +#include "test_util.h" +#include "apic.h" + +#define SYNC_FIRST_UCNA 9 +#define SYNC_SECOND_UCNA 10 +#define SYNC_GP 11 +#define FIRST_UCNA_ADDR 0xdeadbeef +#define SECOND_UCNA_ADDR 0xcafeb0ba + +/* + * Vector for the CMCI interrupt. + * Value is arbitrary. Any value in 0x20-0xFF should work: + * https://wiki.osdev.org/Interrupt_Vector_Table + */ +#define CMCI_VECTOR 0xa9 + +#define UCNA_BANK 0x7 // IMC0 bank + +#define MCI_CTL2_RESERVED_BIT BIT_ULL(29) + +static uint64_t supported_mcg_caps; + +/* + * Record states about the injected UCNA. + * The variables started with the 'i_' prefixes are recorded in interrupt + * handler. Variables without the 'i_' prefixes are recorded in guest main + * execution thread. + */ +static volatile uint64_t i_ucna_rcvd; +static volatile uint64_t i_ucna_addr; +static volatile uint64_t ucna_addr; +static volatile uint64_t ucna_addr2; + +struct thread_params { + struct kvm_vcpu *vcpu; + uint64_t *p_i_ucna_rcvd; + uint64_t *p_i_ucna_addr; + uint64_t *p_ucna_addr; + uint64_t *p_ucna_addr2; +}; + +static void verify_apic_base_addr(void) +{ + uint64_t msr = rdmsr(MSR_IA32_APICBASE); + uint64_t base = GET_APIC_BASE(msr); + + GUEST_ASSERT(base == APIC_DEFAULT_GPA); +} + +static void ucna_injection_guest_code(void) +{ + uint64_t ctl2; + verify_apic_base_addr(); + xapic_enable(); + + /* Sets up the interrupt vector and enables per-bank CMCI sigaling. */ + xapic_write_reg(APIC_LVTCMCI, CMCI_VECTOR | APIC_DM_FIXED); + ctl2 = rdmsr(MSR_IA32_MCx_CTL2(UCNA_BANK)); + wrmsr(MSR_IA32_MCx_CTL2(UCNA_BANK), ctl2 | MCI_CTL2_CMCI_EN); + + /* Enables interrupt in guest. */ + asm volatile("sti"); + + /* Let user space inject the first UCNA */ + GUEST_SYNC(SYNC_FIRST_UCNA); + + ucna_addr = rdmsr(MSR_IA32_MCx_ADDR(UCNA_BANK)); + + /* Disables the per-bank CMCI signaling. */ + ctl2 = rdmsr(MSR_IA32_MCx_CTL2(UCNA_BANK)); + wrmsr(MSR_IA32_MCx_CTL2(UCNA_BANK), ctl2 & ~MCI_CTL2_CMCI_EN); + + /* Let the user space inject the second UCNA */ + GUEST_SYNC(SYNC_SECOND_UCNA); + + ucna_addr2 = rdmsr(MSR_IA32_MCx_ADDR(UCNA_BANK)); + GUEST_DONE(); +} + +static void cmci_disabled_guest_code(void) +{ + uint64_t ctl2 = rdmsr(MSR_IA32_MCx_CTL2(UCNA_BANK)); + wrmsr(MSR_IA32_MCx_CTL2(UCNA_BANK), ctl2 | MCI_CTL2_CMCI_EN); + + GUEST_DONE(); +} + +static void cmci_enabled_guest_code(void) +{ + uint64_t ctl2 = rdmsr(MSR_IA32_MCx_CTL2(UCNA_BANK)); + wrmsr(MSR_IA32_MCx_CTL2(UCNA_BANK), ctl2 | MCI_CTL2_RESERVED_BIT); + + GUEST_DONE(); +} + +static void guest_cmci_handler(struct ex_regs *regs) +{ + i_ucna_rcvd++; + i_ucna_addr = rdmsr(MSR_IA32_MCx_ADDR(UCNA_BANK)); + xapic_write_reg(APIC_EOI, 0); +} + +static void guest_gp_handler(struct ex_regs *regs) +{ + GUEST_SYNC(SYNC_GP); +} + +static void run_vcpu_expect_gp(struct kvm_vcpu *vcpu) +{ + unsigned int exit_reason; + struct ucall uc; + + vcpu_run(vcpu); + + exit_reason = vcpu->run->exit_reason; + TEST_ASSERT(exit_reason == KVM_EXIT_IO, + "exited with unexpected exit reason %u-%s, expected KVM_EXIT_IO", + exit_reason, exit_reason_str(exit_reason)); + TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_SYNC, + "Expect UCALL_SYNC\n"); + TEST_ASSERT(uc.args[1] == SYNC_GP, "#GP is expected."); + printf("vCPU received GP in guest.\n"); +} + +static void inject_ucna(struct kvm_vcpu *vcpu, uint64_t addr) { + /* + * A UCNA error is indicated with VAL=1, UC=1, PCC=0, S=0 and AR=0 in + * the IA32_MCi_STATUS register. + * MSCOD=1 (BIT[16] - MscodDataRdErr). + * MCACOD=0x0090 (Memory controller error format, channel 0) + */ + uint64_t status = MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN | + MCI_STATUS_MISCV | MCI_STATUS_ADDRV | 0x10090; + struct kvm_x86_mce mce = {}; + mce.status = status; + mce.mcg_status = 0; + /* + * MCM_ADDR_PHYS indicates the reported address is a physical address. + * Lowest 6 bits is the recoverable address LSB, i.e., the injected MCE + * is at 4KB granularity. + */ + mce.misc = (MCM_ADDR_PHYS << 6) | 0xc; + mce.addr = addr; + mce.bank = UCNA_BANK; + + vcpu_ioctl(vcpu, KVM_X86_SET_MCE, &mce); +} + +static void *run_ucna_injection(void *arg) +{ + struct thread_params *params = (struct thread_params *)arg; + struct ucall uc; + int old; + int r; + unsigned int exit_reason; + + r = pthread_setcanceltype(PTHREAD_CANCEL_ASYNCHRONOUS, &old); + TEST_ASSERT(r == 0, + "pthread_setcanceltype failed with errno=%d", + r); + + vcpu_run(params->vcpu); + + exit_reason = params->vcpu->run->exit_reason; + TEST_ASSERT(exit_reason == KVM_EXIT_IO, + "unexpected exit reason %u-%s, expected KVM_EXIT_IO", + exit_reason, exit_reason_str(exit_reason)); + TEST_ASSERT(get_ucall(params->vcpu, &uc) == UCALL_SYNC, + "Expect UCALL_SYNC\n"); + TEST_ASSERT(uc.args[1] == SYNC_FIRST_UCNA, "Injecting first UCNA."); + + printf("Injecting first UCNA at %#x.\n", FIRST_UCNA_ADDR); + + inject_ucna(params->vcpu, FIRST_UCNA_ADDR); + vcpu_run(params->vcpu); + + exit_reason = params->vcpu->run->exit_reason; + TEST_ASSERT(exit_reason == KVM_EXIT_IO, + "unexpected exit reason %u-%s, expected KVM_EXIT_IO", + exit_reason, exit_reason_str(exit_reason)); + TEST_ASSERT(get_ucall(params->vcpu, &uc) == UCALL_SYNC, + "Expect UCALL_SYNC\n"); + TEST_ASSERT(uc.args[1] == SYNC_SECOND_UCNA, "Injecting second UCNA."); + + printf("Injecting second UCNA at %#x.\n", SECOND_UCNA_ADDR); + + inject_ucna(params->vcpu, SECOND_UCNA_ADDR); + vcpu_run(params->vcpu); + + exit_reason = params->vcpu->run->exit_reason; + TEST_ASSERT(exit_reason == KVM_EXIT_IO, + "unexpected exit reason %u-%s, expected KVM_EXIT_IO", + exit_reason, exit_reason_str(exit_reason)); + if (get_ucall(params->vcpu, &uc) == UCALL_ABORT) { + TEST_ASSERT(false, "vCPU assertion failure: %s.\n", + (const char *)uc.args[0]); + } + + return NULL; +} + +static void test_ucna_injection(struct kvm_vcpu *vcpu, struct thread_params *params) +{ + struct kvm_vm *vm = vcpu->vm; + params->vcpu = vcpu; + params->p_i_ucna_rcvd = (uint64_t *)addr_gva2hva(vm, (uint64_t)&i_ucna_rcvd); + params->p_i_ucna_addr = (uint64_t *)addr_gva2hva(vm, (uint64_t)&i_ucna_addr); + params->p_ucna_addr = (uint64_t *)addr_gva2hva(vm, (uint64_t)&ucna_addr); + params->p_ucna_addr2 = (uint64_t *)addr_gva2hva(vm, (uint64_t)&ucna_addr2); + + run_ucna_injection(params); + + TEST_ASSERT(*params->p_i_ucna_rcvd == 1, "Only first UCNA get signaled."); + TEST_ASSERT(*params->p_i_ucna_addr == FIRST_UCNA_ADDR, + "Only first UCNA reported addr get recorded via interrupt."); + TEST_ASSERT(*params->p_ucna_addr == FIRST_UCNA_ADDR, + "First injected UCNAs should get exposed via registers."); + TEST_ASSERT(*params->p_ucna_addr2 == SECOND_UCNA_ADDR, + "Second injected UCNAs should get exposed via registers."); + + printf("Test successful.\n" + "UCNA CMCI interrupts received: %ld\n" + "Last UCNA address received via CMCI: %lx\n" + "First UCNA address in vCPU thread: %lx\n" + "Second UCNA address in vCPU thread: %lx\n", + *params->p_i_ucna_rcvd, *params->p_i_ucna_addr, + *params->p_ucna_addr, *params->p_ucna_addr2); +} + +static void setup_mce_cap(struct kvm_vcpu *vcpu, bool enable_cmci_p) +{ + uint64_t mcg_caps = MCG_CTL_P | MCG_SER_P | MCG_LMCE_P | KVM_MAX_MCE_BANKS; + if (enable_cmci_p) + mcg_caps |= MCG_CMCI_P; + + mcg_caps &= supported_mcg_caps | MCG_CAP_BANKS_MASK; + vcpu_ioctl(vcpu, KVM_X86_SETUP_MCE, &mcg_caps); +} + +static struct kvm_vcpu *create_vcpu_with_mce_cap(struct kvm_vm *vm, uint32_t vcpuid, + bool enable_cmci_p, void *guest_code) +{ + struct kvm_vcpu *vcpu = vm_vcpu_add(vm, vcpuid, guest_code); + setup_mce_cap(vcpu, enable_cmci_p); + return vcpu; +} + +int main(int argc, char *argv[]) +{ + struct thread_params params; + struct kvm_vm *vm; + struct kvm_vcpu *ucna_vcpu; + struct kvm_vcpu *cmcidis_vcpu; + struct kvm_vcpu *cmci_vcpu; + + kvm_check_cap(KVM_CAP_MCE); + + vm = __vm_create(VM_MODE_DEFAULT, 3, 0); + + kvm_ioctl(vm->kvm_fd, KVM_X86_GET_MCE_CAP_SUPPORTED, + &supported_mcg_caps); + + if (!(supported_mcg_caps & MCG_CMCI_P)) { + print_skip("MCG_CMCI_P is not supported"); + exit(KSFT_SKIP); + } + + ucna_vcpu = create_vcpu_with_mce_cap(vm, 0, true, ucna_injection_guest_code); + cmcidis_vcpu = create_vcpu_with_mce_cap(vm, 1, false, cmci_disabled_guest_code); + cmci_vcpu = create_vcpu_with_mce_cap(vm, 2, true, cmci_enabled_guest_code); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(ucna_vcpu); + vcpu_init_descriptor_tables(cmcidis_vcpu); + vcpu_init_descriptor_tables(cmci_vcpu); + vm_install_exception_handler(vm, CMCI_VECTOR, guest_cmci_handler); + vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); + + virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); + + test_ucna_injection(ucna_vcpu, ¶ms); + run_vcpu_expect_gp(cmcidis_vcpu); + run_vcpu_expect_gp(cmci_vcpu); + + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c index e4bef2e05686..7316521428f8 100644 --- a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c +++ b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c @@ -10,8 +10,6 @@ #include "kvm_util.h" #include "processor.h" -#define VCPU_ID 1 - static void guest_ins_port80(uint8_t *buffer, unsigned int count) { unsigned long end; @@ -52,31 +50,29 @@ static void guest_code(void) int main(int argc, char *argv[]) { + struct kvm_vcpu *vcpu; struct kvm_regs regs; struct kvm_run *run; struct kvm_vm *vm; struct ucall uc; - int rc; /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - run = vcpu_state(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + run = vcpu->run; memset(®s, 0, sizeof(regs)); while (1) { - rc = _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); - TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", run->exit_reason, exit_reason_str(run->exit_reason)); - if (get_ucall(vm, VCPU_ID, &uc)) + if (get_ucall(vcpu, &uc)) break; TEST_ASSERT(run->io.port == 0x80, @@ -89,22 +85,20 @@ int main(int argc, char *argv[]) * scope from a testing perspective as it's not ABI in any way, * i.e. it really is abusing internal KVM knowledge. */ - vcpu_regs_get(vm, VCPU_ID, ®s); + vcpu_regs_get(vcpu, ®s); if (regs.rcx == 2) regs.rcx = 1; if (regs.rcx == 3) regs.rcx = 8192; memset((void *)run + run->io.data_offset, 0xaa, 4096); - vcpu_regs_set(vm, VCPU_ID, ®s); + vcpu_regs_set(vcpu, ®s); } switch (uc.cmd) { case UCALL_DONE: break; case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld : argN+1 = 0x%lx, argN+2 = 0x%lx", - (const char *)uc.args[0], __FILE__, uc.args[1], - uc.args[2], uc.args[3]); + REPORT_GUEST_ASSERT_2(uc, "argN+1 = 0x%lx, argN+2 = 0x%lx"); default: TEST_FAIL("Unknown ucall %lu", uc.cmd); } diff --git a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c index e3e20e8848d0..a4f06370a245 100644 --- a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c +++ b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c @@ -17,7 +17,6 @@ #define KVM_FEP_LENGTH 5 static int fep_available = 1; -#define VCPU_ID 1 #define MSR_NON_EXISTENT 0x474f4f00 static u64 deny_bits = 0; @@ -395,31 +394,21 @@ static void guest_ud_handler(struct ex_regs *regs) regs->rip += KVM_FEP_LENGTH; } -static void run_guest(struct kvm_vm *vm) +static void check_for_guest_assert(struct kvm_vcpu *vcpu) { - int rc; - - rc = _vcpu_run(vm, VCPU_ID); - TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); -} - -static void check_for_guest_assert(struct kvm_vm *vm) -{ - struct kvm_run *run = vcpu_state(vm, VCPU_ID); struct ucall uc; - if (run->exit_reason == KVM_EXIT_IO && - get_ucall(vm, VCPU_ID, &uc) == UCALL_ABORT) { - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + if (vcpu->run->exit_reason == KVM_EXIT_IO && + get_ucall(vcpu, &uc) == UCALL_ABORT) { + REPORT_GUEST_ASSERT(uc); } } -static void process_rdmsr(struct kvm_vm *vm, uint32_t msr_index) +static void process_rdmsr(struct kvm_vcpu *vcpu, uint32_t msr_index) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; - check_for_guest_assert(vm); + check_for_guest_assert(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_X86_RDMSR, "Unexpected exit reason: %u (%s),\n", @@ -450,11 +439,11 @@ static void process_rdmsr(struct kvm_vm *vm, uint32_t msr_index) } } -static void process_wrmsr(struct kvm_vm *vm, uint32_t msr_index) +static void process_wrmsr(struct kvm_vcpu *vcpu, uint32_t msr_index) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; - check_for_guest_assert(vm); + check_for_guest_assert(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_X86_WRMSR, "Unexpected exit reason: %u (%s),\n", @@ -481,43 +470,43 @@ static void process_wrmsr(struct kvm_vm *vm, uint32_t msr_index) } } -static void process_ucall_done(struct kvm_vm *vm) +static void process_ucall_done(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; struct ucall uc; - check_for_guest_assert(vm); + check_for_guest_assert(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s)", run->exit_reason, exit_reason_str(run->exit_reason)); - TEST_ASSERT(get_ucall(vm, VCPU_ID, &uc) == UCALL_DONE, + TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_DONE, "Unexpected ucall command: %lu, expected UCALL_DONE (%d)", uc.cmd, UCALL_DONE); } -static uint64_t process_ucall(struct kvm_vm *vm) +static uint64_t process_ucall(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_run *run = vcpu->run; struct ucall uc = {}; - check_for_guest_assert(vm); + check_for_guest_assert(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s)", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: break; case UCALL_ABORT: - check_for_guest_assert(vm); + check_for_guest_assert(vcpu); break; case UCALL_DONE: - process_ucall_done(vm); + process_ucall_done(vcpu); break; default: TEST_ASSERT(false, "Unexpected ucall"); @@ -526,45 +515,43 @@ static uint64_t process_ucall(struct kvm_vm *vm) return uc.cmd; } -static void run_guest_then_process_rdmsr(struct kvm_vm *vm, uint32_t msr_index) +static void run_guest_then_process_rdmsr(struct kvm_vcpu *vcpu, + uint32_t msr_index) { - run_guest(vm); - process_rdmsr(vm, msr_index); + vcpu_run(vcpu); + process_rdmsr(vcpu, msr_index); } -static void run_guest_then_process_wrmsr(struct kvm_vm *vm, uint32_t msr_index) +static void run_guest_then_process_wrmsr(struct kvm_vcpu *vcpu, + uint32_t msr_index) { - run_guest(vm); - process_wrmsr(vm, msr_index); + vcpu_run(vcpu); + process_wrmsr(vcpu, msr_index); } -static uint64_t run_guest_then_process_ucall(struct kvm_vm *vm) +static uint64_t run_guest_then_process_ucall(struct kvm_vcpu *vcpu) { - run_guest(vm); - return process_ucall(vm); + vcpu_run(vcpu); + return process_ucall(vcpu); } -static void run_guest_then_process_ucall_done(struct kvm_vm *vm) +static void run_guest_then_process_ucall_done(struct kvm_vcpu *vcpu) { - run_guest(vm); - process_ucall_done(vm); + vcpu_run(vcpu); + process_ucall_done(vcpu); } -static void test_msr_filter_allow(void) { - struct kvm_enable_cap cap = { - .cap = KVM_CAP_X86_USER_SPACE_MSR, - .args[0] = KVM_MSR_EXIT_REASON_FILTER, - }; +static void test_msr_filter_allow(void) +{ + struct kvm_vcpu *vcpu; struct kvm_vm *vm; int rc; - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code_filter_allow); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + vm = vm_create_with_one_vcpu(&vcpu, guest_code_filter_allow); rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); - vm_enable_cap(vm, &cap); + vm_enable_cap(vm, KVM_CAP_X86_USER_SPACE_MSR, KVM_MSR_EXIT_REASON_FILTER); rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER); TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available"); @@ -572,43 +559,43 @@ static void test_msr_filter_allow(void) { vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_allow); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); + vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); /* Process guest code userspace exits. */ - run_guest_then_process_rdmsr(vm, MSR_IA32_XSS); - run_guest_then_process_wrmsr(vm, MSR_IA32_XSS); - run_guest_then_process_wrmsr(vm, MSR_IA32_XSS); + run_guest_then_process_rdmsr(vcpu, MSR_IA32_XSS); + run_guest_then_process_wrmsr(vcpu, MSR_IA32_XSS); + run_guest_then_process_wrmsr(vcpu, MSR_IA32_XSS); - run_guest_then_process_rdmsr(vm, MSR_IA32_FLUSH_CMD); - run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD); - run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD); + run_guest_then_process_rdmsr(vcpu, MSR_IA32_FLUSH_CMD); + run_guest_then_process_wrmsr(vcpu, MSR_IA32_FLUSH_CMD); + run_guest_then_process_wrmsr(vcpu, MSR_IA32_FLUSH_CMD); - run_guest_then_process_wrmsr(vm, MSR_NON_EXISTENT); - run_guest_then_process_rdmsr(vm, MSR_NON_EXISTENT); + run_guest_then_process_wrmsr(vcpu, MSR_NON_EXISTENT); + run_guest_then_process_rdmsr(vcpu, MSR_NON_EXISTENT); vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); - run_guest(vm); + vcpu_run(vcpu); vm_install_exception_handler(vm, UD_VECTOR, NULL); - if (process_ucall(vm) != UCALL_DONE) { + if (process_ucall(vcpu) != UCALL_DONE) { vm_install_exception_handler(vm, GP_VECTOR, guest_fep_gp_handler); /* Process emulated rdmsr and wrmsr instructions. */ - run_guest_then_process_rdmsr(vm, MSR_IA32_XSS); - run_guest_then_process_wrmsr(vm, MSR_IA32_XSS); - run_guest_then_process_wrmsr(vm, MSR_IA32_XSS); + run_guest_then_process_rdmsr(vcpu, MSR_IA32_XSS); + run_guest_then_process_wrmsr(vcpu, MSR_IA32_XSS); + run_guest_then_process_wrmsr(vcpu, MSR_IA32_XSS); - run_guest_then_process_rdmsr(vm, MSR_IA32_FLUSH_CMD); - run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD); - run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD); + run_guest_then_process_rdmsr(vcpu, MSR_IA32_FLUSH_CMD); + run_guest_then_process_wrmsr(vcpu, MSR_IA32_FLUSH_CMD); + run_guest_then_process_wrmsr(vcpu, MSR_IA32_FLUSH_CMD); - run_guest_then_process_wrmsr(vm, MSR_NON_EXISTENT); - run_guest_then_process_rdmsr(vm, MSR_NON_EXISTENT); + run_guest_then_process_wrmsr(vcpu, MSR_NON_EXISTENT); + run_guest_then_process_rdmsr(vcpu, MSR_NON_EXISTENT); /* Confirm the guest completed without issues. */ - run_guest_then_process_ucall_done(vm); + run_guest_then_process_ucall_done(vcpu); } else { printf("To run the instruction emulated tests set the module parameter 'kvm.force_emulation_prefix=1'\n"); } @@ -616,16 +603,16 @@ static void test_msr_filter_allow(void) { kvm_vm_free(vm); } -static int handle_ucall(struct kvm_vm *vm) +static int handle_ucall(struct kvm_vcpu *vcpu) { struct ucall uc; - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("Guest assertion not met"); + REPORT_GUEST_ASSERT(uc); break; case UCALL_SYNC: - vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &no_filter_deny); + vm_ioctl(vcpu->vm, KVM_X86_SET_MSR_FILTER, &no_filter_deny); break; case UCALL_DONE: return 1; @@ -673,25 +660,21 @@ static void handle_wrmsr(struct kvm_run *run) } } -static void test_msr_filter_deny(void) { - struct kvm_enable_cap cap = { - .cap = KVM_CAP_X86_USER_SPACE_MSR, - .args[0] = KVM_MSR_EXIT_REASON_INVAL | - KVM_MSR_EXIT_REASON_UNKNOWN | - KVM_MSR_EXIT_REASON_FILTER, - }; +static void test_msr_filter_deny(void) +{ + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; int rc; - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code_filter_deny); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - run = vcpu_state(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_code_filter_deny); + run = vcpu->run; rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); - vm_enable_cap(vm, &cap); + vm_enable_cap(vm, KVM_CAP_X86_USER_SPACE_MSR, KVM_MSR_EXIT_REASON_INVAL | + KVM_MSR_EXIT_REASON_UNKNOWN | + KVM_MSR_EXIT_REASON_FILTER); rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER); TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available"); @@ -700,9 +683,7 @@ static void test_msr_filter_deny(void) { vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_deny); while (1) { - rc = _vcpu_run(vm, VCPU_ID); - - TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); + vcpu_run(vcpu); switch (run->exit_reason) { case KVM_EXIT_X86_RDMSR: @@ -712,7 +693,7 @@ static void test_msr_filter_deny(void) { handle_wrmsr(run); break; case KVM_EXIT_IO: - if (handle_ucall(vm)) + if (handle_ucall(vcpu)) goto done; break; } @@ -726,31 +707,28 @@ done: kvm_vm_free(vm); } -static void test_msr_permission_bitmap(void) { - struct kvm_enable_cap cap = { - .cap = KVM_CAP_X86_USER_SPACE_MSR, - .args[0] = KVM_MSR_EXIT_REASON_FILTER, - }; +static void test_msr_permission_bitmap(void) +{ + struct kvm_vcpu *vcpu; struct kvm_vm *vm; int rc; - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code_permission_bitmap); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + vm = vm_create_with_one_vcpu(&vcpu, guest_code_permission_bitmap); rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); - vm_enable_cap(vm, &cap); + vm_enable_cap(vm, KVM_CAP_X86_USER_SPACE_MSR, KVM_MSR_EXIT_REASON_FILTER); rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER); TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available"); vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_fs); - run_guest_then_process_rdmsr(vm, MSR_FS_BASE); - TEST_ASSERT(run_guest_then_process_ucall(vm) == UCALL_SYNC, "Expected ucall state to be UCALL_SYNC."); + run_guest_then_process_rdmsr(vcpu, MSR_FS_BASE); + TEST_ASSERT(run_guest_then_process_ucall(vcpu) == UCALL_SYNC, + "Expected ucall state to be UCALL_SYNC."); vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_gs); - run_guest_then_process_rdmsr(vm, MSR_GS_BASE); - run_guest_then_process_ucall_done(vm); + run_guest_then_process_rdmsr(vcpu, MSR_GS_BASE); + run_guest_then_process_ucall_done(vcpu); kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c index d438c4d3228a..5abecf06329e 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c @@ -28,11 +28,6 @@ #include "kselftest.h" -#define VCPU_ID 0 - -/* The virtual machine object. */ -static struct kvm_vm *vm; - static void l2_guest_code(void) { /* Exit to L1 */ @@ -77,33 +72,29 @@ static void l1_guest_code(struct vmx_pages *vmx_pages, unsigned long high_gpa) int main(int argc, char *argv[]) { unsigned long apic_access_addr = ~0ul; - unsigned int paddr_width; - unsigned int vaddr_width; vm_vaddr_t vmx_pages_gva; unsigned long high_gpa; struct vmx_pages *vmx; bool done = false; - nested_vmx_check_supported(); + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; - vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); - kvm_get_cpu_address_width(&paddr_width, &vaddr_width); - high_gpa = (1ul << paddr_width) - getpagesize(); - if ((unsigned long)DEFAULT_GUEST_PHY_PAGES * getpagesize() > high_gpa) { - print_skip("No unbacked physical page available"); - exit(KSFT_SKIP); - } + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + + high_gpa = (vm->max_gfn - 1) << vm->page_shift; vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva); prepare_virtualize_apic_accesses(vmx, vm); - vcpu_args_set(vm, VCPU_ID, 2, vmx_pages_gva, high_gpa); + vcpu_args_set(vcpu, 2, vmx_pages_gva, high_gpa); while (!done) { - volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + volatile struct kvm_run *run = vcpu->run; struct ucall uc; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); if (apic_access_addr == high_gpa) { TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR, @@ -121,10 +112,9 @@ int main(int argc, char *argv[]) run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: apic_access_addr = uc.args[1]; diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c index 2835a17f1b7a..d79651b02740 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c @@ -18,20 +18,15 @@ #include "kselftest.h" -#define VCPU_ID 5 - enum { PORT_L0_EXIT = 0x2000, }; -/* The virtual machine object. */ -static struct kvm_vm *vm; - static void l2_guest_code(void) { /* Exit to L0 */ - asm volatile("inb %%dx, %%al" - : : [port] "d" (PORT_L0_EXIT) : "rax"); + asm volatile("inb %%dx, %%al" + : : [port] "d" (PORT_L0_EXIT) : "rax"); } static void l1_guest_code(struct vmx_pages *vmx_pages) @@ -53,20 +48,22 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) int main(int argc, char *argv[]) { vm_vaddr_t vmx_pages_gva; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; - nested_vmx_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); - vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); /* Allocate VMX pages and shared descriptors (vmx_pages). */ vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); for (;;) { - volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + volatile struct kvm_run *run = vcpu->run; struct ucall uc; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", run->exit_reason, @@ -75,9 +72,9 @@ int main(int argc, char *argv[]) if (run->io.port == PORT_L0_EXIT) break; - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s", (const char *)uc.args[0]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ default: TEST_FAIL("Unknown ucall %lu", uc.cmd); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c index 68f26a8b4f42..2d8c23d639f7 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c @@ -17,8 +17,6 @@ #include "processor.h" #include "vmx.h" -#define VCPU_ID 1 - /* The memory slot index to track dirty pages */ #define TEST_MEM_SLOT_INDEX 1 #define TEST_MEM_PAGES 3 @@ -73,18 +71,19 @@ int main(int argc, char *argv[]) unsigned long *bmap; uint64_t *host_test_mem; + struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; struct ucall uc; bool done = false; - nested_vmx_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, l1_guest_code); + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); - run = vcpu_state(vm, VCPU_ID); + vcpu_args_set(vcpu, 1, vmx_pages_gva); + run = vcpu->run; /* Add an extra memory slot for testing dirty logging */ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, @@ -116,16 +115,15 @@ int main(int argc, char *argv[]) while (!done) { memset(host_test_mem, 0xaa, TEST_MEM_PAGES * 4096); - _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: /* diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c new file mode 100644 index 000000000000..2641b286b4ed --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c @@ -0,0 +1,147 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +#include <signal.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/time.h> + +#include "kselftest.h" + +static void guest_ud_handler(struct ex_regs *regs) +{ + /* Loop on the ud2 until guest state is made invalid. */ +} + +static void guest_code(void) +{ + asm volatile("ud2"); +} + +static void __run_vcpu_with_invalid_state(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + + vcpu_run(vcpu); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR, + "Expected KVM_EXIT_INTERNAL_ERROR, got %d (%s)\n", + run->exit_reason, exit_reason_str(run->exit_reason)); + TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION, + "Expected emulation failure, got %d\n", + run->emulation_failure.suberror); +} + +static void run_vcpu_with_invalid_state(struct kvm_vcpu *vcpu) +{ + /* + * Always run twice to verify KVM handles the case where _KVM_ queues + * an exception with invalid state and then exits to userspace, i.e. + * that KVM doesn't explode if userspace ignores the initial error. + */ + __run_vcpu_with_invalid_state(vcpu); + __run_vcpu_with_invalid_state(vcpu); +} + +static void set_timer(void) +{ + struct itimerval timer; + + timer.it_value.tv_sec = 0; + timer.it_value.tv_usec = 200; + timer.it_interval = timer.it_value; + ASSERT_EQ(setitimer(ITIMER_REAL, &timer, NULL), 0); +} + +static void set_or_clear_invalid_guest_state(struct kvm_vcpu *vcpu, bool set) +{ + static struct kvm_sregs sregs; + + if (!sregs.cr0) + vcpu_sregs_get(vcpu, &sregs); + sregs.tr.unusable = !!set; + vcpu_sregs_set(vcpu, &sregs); +} + +static void set_invalid_guest_state(struct kvm_vcpu *vcpu) +{ + set_or_clear_invalid_guest_state(vcpu, true); +} + +static void clear_invalid_guest_state(struct kvm_vcpu *vcpu) +{ + set_or_clear_invalid_guest_state(vcpu, false); +} + +static struct kvm_vcpu *get_set_sigalrm_vcpu(struct kvm_vcpu *__vcpu) +{ + static struct kvm_vcpu *vcpu = NULL; + + if (__vcpu) + vcpu = __vcpu; + return vcpu; +} + +static void sigalrm_handler(int sig) +{ + struct kvm_vcpu *vcpu = get_set_sigalrm_vcpu(NULL); + struct kvm_vcpu_events events; + + TEST_ASSERT(sig == SIGALRM, "Unexpected signal = %d", sig); + + vcpu_events_get(vcpu, &events); + + /* + * If an exception is pending, attempt KVM_RUN with invalid guest, + * otherwise rearm the timer and keep doing so until the timer fires + * between KVM queueing an exception and re-entering the guest. + */ + if (events.exception.pending) { + set_invalid_guest_state(vcpu); + run_vcpu_with_invalid_state(vcpu); + } else { + set_timer(); + } +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + TEST_REQUIRE(is_intel_cpu()); + TEST_REQUIRE(!vm_is_unrestricted_guest(NULL)); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + get_set_sigalrm_vcpu(vcpu); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + + vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); + + /* + * Stuff invalid guest state for L2 by making TR unusuable. The next + * KVM_RUN should induce a TRIPLE_FAULT in L2 as KVM doesn't support + * emulating invalid guest state for L2. + */ + set_invalid_guest_state(vcpu); + run_vcpu_with_invalid_state(vcpu); + + /* + * Verify KVM also handles the case where userspace gains control while + * an exception is pending and stuffs invalid state. Run with valid + * guest state and a timer firing every 200us, and attempt to enter the + * guest with invalid state when the handler interrupts KVM with an + * exception pending. + */ + clear_invalid_guest_state(vcpu); + TEST_ASSERT(signal(SIGALRM, sigalrm_handler) != SIG_ERR, + "Failed to register SIGALRM handler, errno = %d (%s)", + errno, strerror(errno)); + + set_timer(); + run_vcpu_with_invalid_state(vcpu); +} diff --git a/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c new file mode 100644 index 000000000000..6bfb4bb471ca --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "vmx.h" + +#include <string.h> +#include <sys/ioctl.h> + +#include "kselftest.h" + +#define ARBITRARY_IO_PORT 0x2000 + +static struct kvm_vm *vm; + +static void l2_guest_code(void) +{ + /* + * Generate an exit to L0 userspace, i.e. main(), via I/O to an + * arbitrary port. + */ + asm volatile("inb %%dx, %%al" + : : [port] "d" (ARBITRARY_IO_PORT) : "rax"); +} + +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]; + + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + GUEST_ASSERT(load_vmcs(vmx_pages)); + + /* Prepare the VMCS for L2 execution. */ + prepare_vmcs(vmx_pages, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* + * L2 must be run without unrestricted guest, verify that the selftests + * library hasn't enabled it. Because KVM selftests jump directly to + * 64-bit mode, unrestricted guest support isn't required. + */ + GUEST_ASSERT(!(vmreadz(CPU_BASED_VM_EXEC_CONTROL) & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) || + !(vmreadz(SECONDARY_VM_EXEC_CONTROL) & SECONDARY_EXEC_UNRESTRICTED_GUEST)); + + GUEST_ASSERT(!vmlaunch()); + + /* L2 should triple fault after main() stuffs invalid guest state. */ + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_TRIPLE_FAULT); + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + vm_vaddr_t vmx_pages_gva; + struct kvm_sregs sregs; + struct kvm_vcpu *vcpu; + struct kvm_run *run; + struct ucall uc; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + + /* Allocate VMX pages and shared descriptors (vmx_pages). */ + vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); + + vcpu_run(vcpu); + + run = vcpu->run; + + /* + * The first exit to L0 userspace should be an I/O access from L2. + * Running L1 should launch L2 without triggering an exit to userspace. + */ + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Expected KVM_EXIT_IO, got: %u (%s)\n", + run->exit_reason, exit_reason_str(run->exit_reason)); + + TEST_ASSERT(run->io.port == ARBITRARY_IO_PORT, + "Expected IN from port %d from L2, got port %d", + ARBITRARY_IO_PORT, run->io.port); + + /* + * Stuff invalid guest state for L2 by making TR unusuable. The next + * KVM_RUN should induce a TRIPLE_FAULT in L2 as KVM doesn't support + * emulating invalid guest state for L2. + */ + memset(&sregs, 0, sizeof(sregs)); + vcpu_sregs_get(vcpu, &sregs); + sregs.tr.unusable = 1; + vcpu_sregs_set(vcpu, &sregs); + + vcpu_run(vcpu); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_DONE: + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + default: + TEST_FAIL("Unexpected ucall: %lu", uc.cmd); + } +} diff --git a/tools/testing/selftests/kvm/x86_64/vmx_msrs_test.c b/tools/testing/selftests/kvm/x86_64/vmx_msrs_test.c new file mode 100644 index 000000000000..322d561b4260 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/vmx_msrs_test.c @@ -0,0 +1,84 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * VMX control MSR test + * + * Copyright (C) 2022 Google LLC. + * + * Tests for KVM ownership of bits in the VMX entry/exit control MSRs. Checks + * that KVM will set owned bits where appropriate, and will not if + * KVM_X86_QUIRK_TWEAK_VMX_CTRL_MSRS is disabled. + */ +#include <linux/bitmap.h> +#include "kvm_util.h" +#include "vmx.h" + +static void vmx_fixed1_msr_test(struct kvm_vcpu *vcpu, uint32_t msr_index, + uint64_t mask) +{ + uint64_t val = vcpu_get_msr(vcpu, msr_index); + uint64_t bit; + + mask &= val; + + for_each_set_bit(bit, &mask, 64) { + vcpu_set_msr(vcpu, msr_index, val & ~BIT_ULL(bit)); + vcpu_set_msr(vcpu, msr_index, val); + } +} + +static void vmx_fixed0_msr_test(struct kvm_vcpu *vcpu, uint32_t msr_index, + uint64_t mask) +{ + uint64_t val = vcpu_get_msr(vcpu, msr_index); + uint64_t bit; + + mask = ~mask | val; + + for_each_clear_bit(bit, &mask, 64) { + vcpu_set_msr(vcpu, msr_index, val | BIT_ULL(bit)); + vcpu_set_msr(vcpu, msr_index, val); + } +} + +static void vmx_fixed0and1_msr_test(struct kvm_vcpu *vcpu, uint32_t msr_index) +{ + vmx_fixed0_msr_test(vcpu, msr_index, GENMASK_ULL(31, 0)); + vmx_fixed1_msr_test(vcpu, msr_index, GENMASK_ULL(63, 32)); +} + +static void vmx_save_restore_msrs_test(struct kvm_vcpu *vcpu) +{ + vcpu_set_msr(vcpu, MSR_IA32_VMX_VMCS_ENUM, 0); + vcpu_set_msr(vcpu, MSR_IA32_VMX_VMCS_ENUM, -1ull); + + vmx_fixed1_msr_test(vcpu, MSR_IA32_VMX_BASIC, + BIT_ULL(49) | BIT_ULL(54) | BIT_ULL(55)); + + vmx_fixed1_msr_test(vcpu, MSR_IA32_VMX_MISC, + BIT_ULL(5) | GENMASK_ULL(8, 6) | BIT_ULL(14) | + BIT_ULL(15) | BIT_ULL(28) | BIT_ULL(29) | BIT_ULL(30)); + + vmx_fixed0and1_msr_test(vcpu, MSR_IA32_VMX_PROCBASED_CTLS2); + vmx_fixed1_msr_test(vcpu, MSR_IA32_VMX_EPT_VPID_CAP, -1ull); + vmx_fixed0and1_msr_test(vcpu, MSR_IA32_VMX_TRUE_PINBASED_CTLS); + vmx_fixed0and1_msr_test(vcpu, MSR_IA32_VMX_TRUE_PROCBASED_CTLS); + vmx_fixed0and1_msr_test(vcpu, MSR_IA32_VMX_TRUE_EXIT_CTLS); + vmx_fixed0and1_msr_test(vcpu, MSR_IA32_VMX_TRUE_ENTRY_CTLS); + vmx_fixed1_msr_test(vcpu, MSR_IA32_VMX_VMFUNC, -1ull); +} + +int main(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_DISABLE_QUIRKS2)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + + /* No need to actually do KVM_RUN, thus no guest code. */ + vm = vm_create_with_one_vcpu(&vcpu, NULL); + + vmx_save_restore_msrs_test(vcpu); + + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c index 280c01fd2412..465a9434d61c 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c @@ -15,9 +15,6 @@ #include "vmx.h" #include "kselftest.h" - -#define VCPU_ID 0 - /* L2 is scaled up (from L1's perspective) by this factor */ #define L2_SCALE_FACTOR 4ULL @@ -119,14 +116,6 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) GUEST_DONE(); } -static void tsc_scaling_check_supported(void) -{ - if (!kvm_check_cap(KVM_CAP_TSC_CONTROL)) { - print_skip("TSC scaling not supported by the HW"); - exit(KSFT_SKIP); - } -} - static void stable_tsc_check_supported(void) { FILE *fp; @@ -150,6 +139,7 @@ skip_test: int main(int argc, char *argv[]) { + struct kvm_vcpu *vcpu; struct kvm_vm *vm; vm_vaddr_t vmx_pages_gva; @@ -160,8 +150,8 @@ int main(int argc, char *argv[]) uint64_t l1_tsc_freq = 0; uint64_t l2_tsc_freq = 0; - nested_vmx_check_supported(); - tsc_scaling_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_TSC_CONTROL)); stable_tsc_check_supported(); /* @@ -182,30 +172,29 @@ int main(int argc, char *argv[]) l0_tsc_freq = tsc_end - tsc_start; printf("real TSC frequency is around: %"PRIu64"\n", l0_tsc_freq); - vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); - tsc_khz = _vcpu_ioctl(vm, VCPU_ID, KVM_GET_TSC_KHZ, NULL); + tsc_khz = __vcpu_ioctl(vcpu, KVM_GET_TSC_KHZ, NULL); TEST_ASSERT(tsc_khz != -1, "vcpu ioctl KVM_GET_TSC_KHZ failed"); /* scale down L1's TSC frequency */ - vcpu_ioctl(vm, VCPU_ID, KVM_SET_TSC_KHZ, - (void *) (tsc_khz / l1_scale_factor)); + vcpu_ioctl(vcpu, KVM_SET_TSC_KHZ, (void *) (tsc_khz / l1_scale_factor)); for (;;) { - volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + volatile struct kvm_run *run = vcpu->run; struct ucall uc; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s", (const char *) uc.args[0]); + REPORT_GUEST_ASSERT(uc); case UCALL_SYNC: switch (uc.args[0]) { case USLEEP: diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c new file mode 100644 index 000000000000..069589c52f41 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test for VMX-pmu perf capability msr + * + * Copyright (C) 2021 Intel Corporation + * + * Test to check the effect of various CPUID settings on + * MSR_IA32_PERF_CAPABILITIES MSR, and check that what + * we write with KVM_SET_MSR is _not_ modified by the guest + * and check it can be retrieved with KVM_GET_MSR, also test + * the invalid LBR formats are rejected. + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <sys/ioctl.h> + +#include "kvm_util.h" +#include "vmx.h" + +#define PMU_CAP_FW_WRITES (1ULL << 13) +#define PMU_CAP_LBR_FMT 0x3f + +union cpuid10_eax { + struct { + unsigned int version_id:8; + unsigned int num_counters:8; + unsigned int bit_width:8; + unsigned int mask_length:8; + } split; + unsigned int full; +}; + +union perf_capabilities { + struct { + u64 lbr_format:6; + u64 pebs_trap:1; + u64 pebs_arch_reg:1; + u64 pebs_format:4; + u64 smm_freeze:1; + u64 full_width_write:1; + u64 pebs_baseline:1; + u64 perf_metrics:1; + u64 pebs_output_pt_available:1; + u64 anythread_deprecated:1; + }; + u64 capabilities; +}; + +static void guest_code(void) +{ + wrmsr(MSR_IA32_PERF_CAPABILITIES, PMU_CAP_LBR_FMT); +} + +int main(int argc, char *argv[]) +{ + const struct kvm_cpuid_entry2 *entry_a_0; + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + int ret; + union cpuid10_eax eax; + union perf_capabilities host_cap; + uint64_t val; + + host_cap.capabilities = kvm_get_feature_msr(MSR_IA32_PERF_CAPABILITIES); + host_cap.capabilities &= (PMU_CAP_FW_WRITES | PMU_CAP_LBR_FMT); + + /* Create VM */ + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_PDCM)); + + TEST_REQUIRE(kvm_get_cpuid_max_basic() >= 0xa); + entry_a_0 = kvm_get_supported_cpuid_entry(0xa); + + eax.full = entry_a_0->eax; + __TEST_REQUIRE(eax.split.version_id, "PMU is not supported by the vCPU"); + + /* testcase 1, set capabilities when we have PDCM bit */ + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_FW_WRITES); + + /* check capabilities can be retrieved with KVM_GET_MSR */ + ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), PMU_CAP_FW_WRITES); + + /* check whatever we write with KVM_SET_MSR is _not_ modified */ + vcpu_run(vcpu); + ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), PMU_CAP_FW_WRITES); + + /* testcase 2, check valid LBR formats are accepted */ + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, 0); + ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), 0); + + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.lbr_format); + ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), (u64)host_cap.lbr_format); + + /* + * Testcase 3, check that an "invalid" LBR format is rejected. Only an + * exact match of the host's format (and 0/disabled) is allowed. + */ + for (val = 1; val <= PMU_CAP_LBR_FMT; val++) { + if (val == (host_cap.capabilities & PMU_CAP_LBR_FMT)) + continue; + + ret = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, val); + TEST_ASSERT(!ret, "Bad LBR FMT = 0x%lx didn't fail", val); + } + + printf("Completed perf capability tests.\n"); + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c deleted file mode 100644 index 23051d84b907..000000000000 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c +++ /dev/null @@ -1,131 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * VMX-pmu related msrs test - * - * Copyright (C) 2021 Intel Corporation - * - * Test to check the effect of various CPUID settings - * on the MSR_IA32_PERF_CAPABILITIES MSR, and check that - * whatever we write with KVM_SET_MSR is _not_ modified - * in the guest and test it can be retrieved with KVM_GET_MSR. - * - * Test to check that invalid LBR formats are rejected. - */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ -#include <sys/ioctl.h> - -#include "kvm_util.h" -#include "vmx.h" - -#define VCPU_ID 0 - -#define X86_FEATURE_PDCM (1<<15) -#define PMU_CAP_FW_WRITES (1ULL << 13) -#define PMU_CAP_LBR_FMT 0x3f - -union cpuid10_eax { - struct { - unsigned int version_id:8; - unsigned int num_counters:8; - unsigned int bit_width:8; - unsigned int mask_length:8; - } split; - unsigned int full; -}; - -union perf_capabilities { - struct { - u64 lbr_format:6; - u64 pebs_trap:1; - u64 pebs_arch_reg:1; - u64 pebs_format:4; - u64 smm_freeze:1; - u64 full_width_write:1; - u64 pebs_baseline:1; - u64 perf_metrics:1; - u64 pebs_output_pt_available:1; - u64 anythread_deprecated:1; - }; - u64 capabilities; -}; - -static void guest_code(void) -{ - wrmsr(MSR_IA32_PERF_CAPABILITIES, PMU_CAP_LBR_FMT); -} - -int main(int argc, char *argv[]) -{ - struct kvm_cpuid2 *cpuid; - struct kvm_cpuid_entry2 *entry_1_0; - struct kvm_cpuid_entry2 *entry_a_0; - bool pdcm_supported = false; - struct kvm_vm *vm; - int ret; - union cpuid10_eax eax; - union perf_capabilities host_cap; - - host_cap.capabilities = kvm_get_feature_msr(MSR_IA32_PERF_CAPABILITIES); - host_cap.capabilities &= (PMU_CAP_FW_WRITES | PMU_CAP_LBR_FMT); - - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - cpuid = kvm_get_supported_cpuid(); - - if (kvm_get_cpuid_max_basic() >= 0xa) { - entry_1_0 = kvm_get_supported_cpuid_index(1, 0); - entry_a_0 = kvm_get_supported_cpuid_index(0xa, 0); - pdcm_supported = entry_1_0 && !!(entry_1_0->ecx & X86_FEATURE_PDCM); - eax.full = entry_a_0->eax; - } - if (!pdcm_supported) { - print_skip("MSR_IA32_PERF_CAPABILITIES is not supported by the vCPU"); - exit(KSFT_SKIP); - } - if (!eax.split.version_id) { - print_skip("PMU is not supported by the vCPU"); - exit(KSFT_SKIP); - } - - /* testcase 1, set capabilities when we have PDCM bit */ - vcpu_set_cpuid(vm, VCPU_ID, cpuid); - vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_FW_WRITES); - - /* check capabilities can be retrieved with KVM_GET_MSR */ - ASSERT_EQ(vcpu_get_msr(vm, VCPU_ID, MSR_IA32_PERF_CAPABILITIES), PMU_CAP_FW_WRITES); - - /* check whatever we write with KVM_SET_MSR is _not_ modified */ - vcpu_run(vm, VCPU_ID); - ASSERT_EQ(vcpu_get_msr(vm, VCPU_ID, MSR_IA32_PERF_CAPABILITIES), PMU_CAP_FW_WRITES); - - /* testcase 2, check valid LBR formats are accepted */ - vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, 0); - ASSERT_EQ(vcpu_get_msr(vm, VCPU_ID, MSR_IA32_PERF_CAPABILITIES), 0); - - vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, host_cap.lbr_format); - ASSERT_EQ(vcpu_get_msr(vm, VCPU_ID, MSR_IA32_PERF_CAPABILITIES), (u64)host_cap.lbr_format); - - /* testcase 3, check invalid LBR format is rejected */ - ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_LBR_FMT); - TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail."); - - /* testcase 4, set capabilities when we don't have PDCM bit */ - entry_1_0->ecx &= ~X86_FEATURE_PDCM; - vcpu_set_cpuid(vm, VCPU_ID, cpuid); - ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); - TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail."); - - /* testcase 5, set capabilities when we don't have PMU version bits */ - entry_1_0->ecx |= X86_FEATURE_PDCM; - eax.split.version_id = 0; - entry_1_0->ecx = eax.full; - vcpu_set_cpuid(vm, VCPU_ID, cpuid); - ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_FW_WRITES); - TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail."); - - vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, 0); - ASSERT_EQ(vcpu_get_msr(vm, VCPU_ID, MSR_IA32_PERF_CAPABILITIES), 0); - - kvm_vm_free(vm); -} diff --git a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c index a07480aed397..0efdc05969a5 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c @@ -22,7 +22,6 @@ #include "processor.h" #include "vmx.h" -#define VCPU_ID 5 #define PREEMPTION_TIMER_VALUE 100000000ull #define PREEMPTION_TIMER_VALUE_THRESHOLD1 80000000ull @@ -159,6 +158,7 @@ int main(int argc, char *argv[]) struct kvm_regs regs1, regs2; struct kvm_vm *vm; struct kvm_run *run; + struct kvm_vcpu *vcpu; struct kvm_x86_state *state; struct ucall uc; int stage; @@ -167,33 +167,29 @@ int main(int argc, char *argv[]) * AMD currently does not implement any VMX features, so for now we * just early out. */ - nested_vmx_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); - if (!kvm_check_cap(KVM_CAP_NESTED_STATE)) { - print_skip("KVM_CAP_NESTED_STATE not supported"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE)); /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - run = vcpu_state(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + run = vcpu->run; - vcpu_regs_get(vm, VCPU_ID, ®s1); + vcpu_regs_get(vcpu, ®s1); vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); for (stage = 1;; stage++) { - _vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Stage %d: unexpected exit reason: %u (%s),\n", stage, run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], - __FILE__, uc.args[1]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: break; @@ -232,22 +228,20 @@ int main(int argc, char *argv[]) stage, uc.args[4], uc.args[5]); } - state = vcpu_save_state(vm, VCPU_ID); + state = vcpu_save_state(vcpu); memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vm, VCPU_ID, ®s1); + vcpu_regs_get(vcpu, ®s1); kvm_vm_release(vm); /* Restore state in a new VM. */ - kvm_vm_restart(vm, O_RDWR); - vm_vcpu_add(vm, VCPU_ID); - 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); + vcpu = vm_recreate_with_one_vcpu(vm); + vcpu_load_state(vcpu, state); + run = vcpu->run; + kvm_x86_state_cleanup(state); memset(®s2, 0, sizeof(regs2)); - vcpu_regs_get(vm, VCPU_ID, ®s2); + vcpu_regs_get(vcpu, ®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); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c index 5827b9bae468..41ea7028a1f8 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c @@ -23,38 +23,37 @@ * changes this should be updated. */ #define VMCS12_REVISION 0x11e57ed0 -#define VCPU_ID 5 bool have_evmcs; -void test_nested_state(struct kvm_vm *vm, struct kvm_nested_state *state) +void test_nested_state(struct kvm_vcpu *vcpu, struct kvm_nested_state *state) { - vcpu_nested_state_set(vm, VCPU_ID, state, false); + vcpu_nested_state_set(vcpu, state); } -void test_nested_state_expect_errno(struct kvm_vm *vm, +void test_nested_state_expect_errno(struct kvm_vcpu *vcpu, struct kvm_nested_state *state, int expected_errno) { int rv; - rv = vcpu_nested_state_set(vm, VCPU_ID, state, true); + rv = __vcpu_nested_state_set(vcpu, state); TEST_ASSERT(rv == -1 && errno == expected_errno, "Expected %s (%d) from vcpu_nested_state_set but got rv: %i errno: %s (%d)", strerror(expected_errno), expected_errno, rv, strerror(errno), errno); } -void test_nested_state_expect_einval(struct kvm_vm *vm, +void test_nested_state_expect_einval(struct kvm_vcpu *vcpu, struct kvm_nested_state *state) { - test_nested_state_expect_errno(vm, state, EINVAL); + test_nested_state_expect_errno(vcpu, state, EINVAL); } -void test_nested_state_expect_efault(struct kvm_vm *vm, +void test_nested_state_expect_efault(struct kvm_vcpu *vcpu, struct kvm_nested_state *state) { - test_nested_state_expect_errno(vm, state, EFAULT); + test_nested_state_expect_errno(vcpu, state, EFAULT); } void set_revision_id_for_vmcs12(struct kvm_nested_state *state, @@ -86,7 +85,7 @@ void set_default_vmx_state(struct kvm_nested_state *state, int size) set_revision_id_for_vmcs12(state, VMCS12_REVISION); } -void test_vmx_nested_state(struct kvm_vm *vm) +void test_vmx_nested_state(struct kvm_vcpu *vcpu) { /* Add a page for VMCS12. */ const int state_sz = sizeof(struct kvm_nested_state) + getpagesize(); @@ -96,14 +95,14 @@ void test_vmx_nested_state(struct kvm_vm *vm) /* The format must be set to 0. 0 for VMX, 1 for SVM. */ set_default_vmx_state(state, state_sz); state->format = 1; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* * We cannot virtualize anything if the guest does not have VMX * enabled. */ set_default_vmx_state(state, state_sz); - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* * We cannot virtualize anything if the guest does not have VMX @@ -112,17 +111,17 @@ void test_vmx_nested_state(struct kvm_vm *vm) */ set_default_vmx_state(state, state_sz); state->hdr.vmx.vmxon_pa = -1ull; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); state->hdr.vmx.vmcs12_pa = -1ull; state->flags = KVM_STATE_NESTED_EVMCS; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); state->flags = 0; - test_nested_state(vm, state); + test_nested_state(vcpu, state); /* Enable VMX in the guest CPUID. */ - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + vcpu_set_cpuid_feature(vcpu, X86_FEATURE_VMX); /* * Setting vmxon_pa == -1ull and vmcs_pa == -1ull exits early without @@ -133,34 +132,34 @@ void test_vmx_nested_state(struct kvm_vm *vm) set_default_vmx_state(state, state_sz); state->hdr.vmx.vmxon_pa = -1ull; state->hdr.vmx.vmcs12_pa = -1ull; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); state->flags &= KVM_STATE_NESTED_EVMCS; if (have_evmcs) { - test_nested_state_expect_einval(vm, state); - vcpu_enable_evmcs(vm, VCPU_ID); + test_nested_state_expect_einval(vcpu, state); + vcpu_enable_evmcs(vcpu); } - test_nested_state(vm, state); + test_nested_state(vcpu, state); /* It is invalid to have vmxon_pa == -1ull and SMM flags non-zero. */ state->hdr.vmx.smm.flags = 1; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* Invalid flags are rejected. */ set_default_vmx_state(state, state_sz); state->hdr.vmx.flags = ~0; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* It is invalid to have vmxon_pa == -1ull and vmcs_pa != -1ull. */ set_default_vmx_state(state, state_sz); state->hdr.vmx.vmxon_pa = -1ull; state->flags = 0; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* It is invalid to have vmxon_pa set to a non-page aligned address. */ set_default_vmx_state(state, state_sz); state->hdr.vmx.vmxon_pa = 1; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* * It is invalid to have KVM_STATE_NESTED_SMM_GUEST_MODE and @@ -170,7 +169,7 @@ void test_vmx_nested_state(struct kvm_vm *vm) state->flags = KVM_STATE_NESTED_GUEST_MODE | KVM_STATE_NESTED_RUN_PENDING; state->hdr.vmx.smm.flags = KVM_STATE_NESTED_SMM_GUEST_MODE; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* * It is invalid to have any of the SMM flags set besides: @@ -180,13 +179,13 @@ void test_vmx_nested_state(struct kvm_vm *vm) set_default_vmx_state(state, state_sz); state->hdr.vmx.smm.flags = ~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON); - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* Outside SMM, SMM flags must be zero. */ set_default_vmx_state(state, state_sz); state->flags = 0; state->hdr.vmx.smm.flags = KVM_STATE_NESTED_SMM_GUEST_MODE; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* * Size must be large enough to fit kvm_nested_state and vmcs12 @@ -195,13 +194,13 @@ void test_vmx_nested_state(struct kvm_vm *vm) set_default_vmx_state(state, state_sz); state->size = sizeof(*state); state->flags = 0; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); set_default_vmx_state(state, state_sz); state->size = sizeof(*state); state->flags = 0; state->hdr.vmx.vmcs12_pa = -1; - test_nested_state(vm, state); + test_nested_state(vcpu, state); /* * KVM_SET_NESTED_STATE succeeds with invalid VMCS @@ -209,7 +208,7 @@ void test_vmx_nested_state(struct kvm_vm *vm) */ set_default_vmx_state(state, state_sz); state->flags = 0; - test_nested_state(vm, state); + test_nested_state(vcpu, state); /* Invalid flags are rejected, even if no VMCS loaded. */ set_default_vmx_state(state, state_sz); @@ -217,13 +216,13 @@ void test_vmx_nested_state(struct kvm_vm *vm) state->flags = 0; state->hdr.vmx.vmcs12_pa = -1; state->hdr.vmx.flags = ~0; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* vmxon_pa cannot be the same address as vmcs_pa. */ set_default_vmx_state(state, state_sz); state->hdr.vmx.vmxon_pa = 0; state->hdr.vmx.vmcs12_pa = 0; - test_nested_state_expect_einval(vm, state); + test_nested_state_expect_einval(vcpu, state); /* * Test that if we leave nesting the state reflects that when we get @@ -233,8 +232,8 @@ void test_vmx_nested_state(struct kvm_vm *vm) state->hdr.vmx.vmxon_pa = -1ull; state->hdr.vmx.vmcs12_pa = -1ull; state->flags = 0; - test_nested_state(vm, state); - vcpu_nested_state_get(vm, VCPU_ID, state); + test_nested_state(vcpu, state); + vcpu_nested_state_get(vcpu, state); TEST_ASSERT(state->size >= sizeof(*state) && state->size <= state_sz, "Size must be between %ld and %d. The size returned was %d.", sizeof(*state), state_sz, state->size); @@ -244,54 +243,36 @@ void test_vmx_nested_state(struct kvm_vm *vm) free(state); } -void disable_vmx(struct kvm_vm *vm) -{ - struct kvm_cpuid2 *cpuid = kvm_get_supported_cpuid(); - int i; - - for (i = 0; i < cpuid->nent; ++i) - if (cpuid->entries[i].function == 1 && - cpuid->entries[i].index == 0) - break; - TEST_ASSERT(i != cpuid->nent, "CPUID function 1 not found"); - - cpuid->entries[i].ecx &= ~CPUID_VMX; - vcpu_set_cpuid(vm, VCPU_ID, cpuid); - cpuid->entries[i].ecx |= CPUID_VMX; -} - int main(int argc, char *argv[]) { struct kvm_vm *vm; struct kvm_nested_state state; + struct kvm_vcpu *vcpu; have_evmcs = kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS); - if (!kvm_check_cap(KVM_CAP_NESTED_STATE)) { - print_skip("KVM_CAP_NESTED_STATE not available"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE)); /* * AMD currently does not implement set_nested_state, so for now we * just early out. */ - nested_vmx_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); - vm = vm_create_default(VCPU_ID, 0, 0); + vm = vm_create_with_one_vcpu(&vcpu, NULL); /* * First run tests with VMX disabled to check error handling. */ - disable_vmx(vm); + vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_VMX); /* Passing a NULL kvm_nested_state causes a EFAULT. */ - test_nested_state_expect_efault(vm, NULL); + test_nested_state_expect_efault(vcpu, NULL); /* 'size' cannot be smaller than sizeof(kvm_nested_state). */ set_default_state(&state); state.size = 0; - test_nested_state_expect_einval(vm, &state); + test_nested_state_expect_einval(vcpu, &state); /* * Setting the flags 0xf fails the flags check. The only flags that @@ -302,7 +283,7 @@ int main(int argc, char *argv[]) */ set_default_state(&state); state.flags = 0xf; - test_nested_state_expect_einval(vm, &state); + test_nested_state_expect_einval(vcpu, &state); /* * If KVM_STATE_NESTED_RUN_PENDING is set then @@ -310,9 +291,9 @@ int main(int argc, char *argv[]) */ set_default_state(&state); state.flags = KVM_STATE_NESTED_RUN_PENDING; - test_nested_state_expect_einval(vm, &state); + test_nested_state_expect_einval(vcpu, &state); - test_vmx_nested_state(vm); + test_vmx_nested_state(vcpu); kvm_vm_free(vm); return 0; diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c index e683d0ac3e45..5943187e8594 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c @@ -32,9 +32,6 @@ #define MSR_IA32_TSC_ADJUST 0x3b #endif -#define PAGE_SIZE 4096 -#define VCPU_ID 5 - #define TSC_ADJUST_VALUE (1ll << 32) #define TSC_OFFSET_VALUE -(1ll << 48) @@ -128,28 +125,29 @@ static void report(int64_t val) int main(int argc, char *argv[]) { vm_vaddr_t vmx_pages_gva; + struct kvm_vcpu *vcpu; - nested_vmx_check_supported(); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); - vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vm = vm_create_with_one_vcpu(&vcpu, (void *) l1_guest_code); /* Allocate VMX pages and shared descriptors (vmx_pages). */ vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); for (;;) { - volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + volatile struct kvm_run *run = vcpu->run; struct ucall uc; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s", (const char *)uc.args[0]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: report(uc.args[1]); diff --git a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c index afbbc40df884..3d272d7f961e 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c @@ -39,9 +39,6 @@ /* Default delay between migrate_pages calls (microseconds) */ #define DEFAULT_DELAY_USECS 500000 -#define HALTER_VCPU_ID 0 -#define SENDER_VCPU_ID 1 - /* * Vector for IPI from sender vCPU to halting vCPU. * Value is arbitrary and was chosen for the alternating bit pattern. Any @@ -79,8 +76,7 @@ struct test_data_page { struct thread_params { struct test_data_page *data; - struct kvm_vm *vm; - uint32_t vcpu_id; + struct kvm_vcpu *vcpu; uint64_t *pipis_rcvd; /* host address of ipis_rcvd global */ }; @@ -198,6 +194,7 @@ static void sender_guest_code(struct test_data_page *data) static void *vcpu_thread(void *arg) { struct thread_params *params = (struct thread_params *)arg; + struct kvm_vcpu *vcpu = params->vcpu; struct ucall uc; int old; int r; @@ -206,17 +203,17 @@ static void *vcpu_thread(void *arg) r = pthread_setcanceltype(PTHREAD_CANCEL_ASYNCHRONOUS, &old); TEST_ASSERT(r == 0, "pthread_setcanceltype failed on vcpu_id=%u with errno=%d", - params->vcpu_id, r); + vcpu->id, r); - fprintf(stderr, "vCPU thread running vCPU %u\n", params->vcpu_id); - vcpu_run(params->vm, params->vcpu_id); - exit_reason = vcpu_state(params->vm, params->vcpu_id)->exit_reason; + fprintf(stderr, "vCPU thread running vCPU %u\n", vcpu->id); + vcpu_run(vcpu); + exit_reason = vcpu->run->exit_reason; TEST_ASSERT(exit_reason == KVM_EXIT_IO, "vCPU %u exited with unexpected exit reason %u-%s, expected KVM_EXIT_IO", - params->vcpu_id, exit_reason, exit_reason_str(exit_reason)); + vcpu->id, exit_reason, exit_reason_str(exit_reason)); - if (get_ucall(params->vm, params->vcpu_id, &uc) == UCALL_ABORT) { + if (get_ucall(vcpu, &uc) == UCALL_ABORT) { TEST_ASSERT(false, "vCPU %u exited with error: %s.\n" "Sending vCPU sent %lu IPIs to halting vCPU\n" @@ -224,7 +221,7 @@ static void *vcpu_thread(void *arg) "Halter TPR=%#x PPR=%#x LVR=%#x\n" "Migrations attempted: %lu\n" "Migrations completed: %lu\n", - params->vcpu_id, (const char *)uc.args[0], + vcpu->id, (const char *)uc.args[0], params->data->ipis_sent, params->data->hlt_count, params->data->wake_count, *params->pipis_rcvd, params->data->halter_tpr, @@ -236,7 +233,7 @@ static void *vcpu_thread(void *arg) return NULL; } -static void cancel_join_vcpu_thread(pthread_t thread, uint32_t vcpu_id) +static void cancel_join_vcpu_thread(pthread_t thread, struct kvm_vcpu *vcpu) { void *retval; int r; @@ -244,12 +241,12 @@ static void cancel_join_vcpu_thread(pthread_t thread, uint32_t vcpu_id) r = pthread_cancel(thread); TEST_ASSERT(r == 0, "pthread_cancel on vcpu_id=%d failed with errno=%d", - vcpu_id, r); + vcpu->id, r); r = pthread_join(thread, &retval); TEST_ASSERT(r == 0, "pthread_join on vcpu_id=%d failed with errno=%d", - vcpu_id, r); + vcpu->id, r); TEST_ASSERT(retval == PTHREAD_CANCELED, "expected retval=%p, got %p", PTHREAD_CANCELED, retval); @@ -415,34 +412,30 @@ int main(int argc, char *argv[]) if (delay_usecs <= 0) delay_usecs = DEFAULT_DELAY_USECS; - vm = vm_create_default(HALTER_VCPU_ID, 0, halter_guest_code); - params[0].vm = vm; - params[1].vm = vm; + vm = vm_create_with_one_vcpu(¶ms[0].vcpu, halter_guest_code); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, HALTER_VCPU_ID); + vcpu_init_descriptor_tables(params[0].vcpu); vm_install_exception_handler(vm, IPI_VECTOR, guest_ipi_handler); virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); - vm_vcpu_add_default(vm, SENDER_VCPU_ID, sender_guest_code); + params[1].vcpu = vm_vcpu_add(vm, 1, sender_guest_code); test_data_page_vaddr = vm_vaddr_alloc_page(vm); - data = - (struct test_data_page *)addr_gva2hva(vm, test_data_page_vaddr); + data = addr_gva2hva(vm, test_data_page_vaddr); memset(data, 0, sizeof(*data)); params[0].data = data; params[1].data = data; - vcpu_args_set(vm, HALTER_VCPU_ID, 1, test_data_page_vaddr); - vcpu_args_set(vm, SENDER_VCPU_ID, 1, test_data_page_vaddr); + vcpu_args_set(params[0].vcpu, 1, test_data_page_vaddr); + vcpu_args_set(params[1].vcpu, 1, test_data_page_vaddr); pipis_rcvd = (uint64_t *)addr_gva2hva(vm, (uint64_t)&ipis_rcvd); params[0].pipis_rcvd = pipis_rcvd; params[1].pipis_rcvd = pipis_rcvd; /* Start halter vCPU thread and wait for it to execute first HLT. */ - params[0].vcpu_id = HALTER_VCPU_ID; r = pthread_create(&threads[0], NULL, vcpu_thread, ¶ms[0]); TEST_ASSERT(r == 0, "pthread_create halter failed errno=%d", errno); @@ -462,7 +455,6 @@ int main(int argc, char *argv[]) "Halter vCPU thread reported its APIC ID: %u after %d seconds.\n", data->halter_apic_id, wait_secs); - params[1].vcpu_id = SENDER_VCPU_ID; r = pthread_create(&threads[1], NULL, vcpu_thread, ¶ms[1]); TEST_ASSERT(r == 0, "pthread_create sender failed errno=%d", errno); @@ -478,8 +470,8 @@ int main(int argc, char *argv[]) /* * Cancel threads and wait for them to stop. */ - cancel_join_vcpu_thread(threads[0], HALTER_VCPU_ID); - cancel_join_vcpu_thread(threads[1], SENDER_VCPU_ID); + cancel_join_vcpu_thread(threads[0], params[0].vcpu); + cancel_join_vcpu_thread(threads[1], params[1].vcpu); fprintf(stderr, "Test successful after running for %d seconds.\n" diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c new file mode 100644 index 000000000000..6f7a5ef66718 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0-only +#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 "apic.h" +#include "kvm_util.h" +#include "processor.h" +#include "test_util.h" + +struct xapic_vcpu { + struct kvm_vcpu *vcpu; + bool is_x2apic; +}; + +static void xapic_guest_code(void) +{ + asm volatile("cli"); + + xapic_enable(); + + while (1) { + uint64_t val = (u64)xapic_read_reg(APIC_IRR) | + (u64)xapic_read_reg(APIC_IRR + 0x10) << 32; + + xapic_write_reg(APIC_ICR2, val >> 32); + xapic_write_reg(APIC_ICR, val); + GUEST_SYNC(val); + } +} + +static void x2apic_guest_code(void) +{ + asm volatile("cli"); + + x2apic_enable(); + + do { + uint64_t val = x2apic_read_reg(APIC_IRR) | + x2apic_read_reg(APIC_IRR + 0x10) << 32; + + x2apic_write_reg(APIC_ICR, val); + GUEST_SYNC(val); + } while (1); +} + +static void ____test_icr(struct xapic_vcpu *x, uint64_t val) +{ + struct kvm_vcpu *vcpu = x->vcpu; + struct kvm_lapic_state xapic; + struct ucall uc; + uint64_t icr; + + /* + * Tell the guest what ICR value to write. Use the IRR to pass info, + * all bits are valid and should not be modified by KVM (ignoring the + * fact that vectors 0-15 are technically illegal). + */ + vcpu_ioctl(vcpu, KVM_GET_LAPIC, &xapic); + *((u32 *)&xapic.regs[APIC_IRR]) = val; + *((u32 *)&xapic.regs[APIC_IRR + 0x10]) = val >> 32; + vcpu_ioctl(vcpu, KVM_SET_LAPIC, &xapic); + + vcpu_run(vcpu); + ASSERT_EQ(get_ucall(vcpu, &uc), UCALL_SYNC); + ASSERT_EQ(uc.args[1], val); + + vcpu_ioctl(vcpu, KVM_GET_LAPIC, &xapic); + icr = (u64)(*((u32 *)&xapic.regs[APIC_ICR])) | + (u64)(*((u32 *)&xapic.regs[APIC_ICR2])) << 32; + if (!x->is_x2apic) { + val &= (-1u | (0xffull << (32 + 24))); + ASSERT_EQ(icr, val & ~APIC_ICR_BUSY); + } else { + ASSERT_EQ(icr & ~APIC_ICR_BUSY, val & ~APIC_ICR_BUSY); + } +} + +#define X2APIC_RSVED_BITS_MASK (GENMASK_ULL(31,20) | \ + GENMASK_ULL(17,16) | \ + GENMASK_ULL(13,13)) + +static void __test_icr(struct xapic_vcpu *x, uint64_t val) +{ + if (x->is_x2apic) { + /* Hardware writing vICR register requires reserved bits 31:20, + * 17:16 and 13 kept as zero to avoid #GP exception. Data value + * written to vICR should mask out those bits above. + */ + val &= ~X2APIC_RSVED_BITS_MASK; + } + ____test_icr(x, val | APIC_ICR_BUSY); + ____test_icr(x, val & ~(u64)APIC_ICR_BUSY); +} + +static void test_icr(struct xapic_vcpu *x) +{ + struct kvm_vcpu *vcpu = x->vcpu; + uint64_t icr, i, j; + + icr = APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_FIXED; + for (i = 0; i <= 0xff; i++) + __test_icr(x, icr | i); + + icr = APIC_INT_ASSERT | APIC_DM_FIXED; + for (i = 0; i <= 0xff; i++) + __test_icr(x, icr | i); + + /* + * Send all flavors of IPIs to non-existent vCPUs. TODO: use number of + * vCPUs, not vcpu.id + 1. Arbitrarily use vector 0xff. + */ + icr = APIC_INT_ASSERT | 0xff; + for (i = vcpu->id + 1; i < 0xff; i++) { + for (j = 0; j < 8; j++) + __test_icr(x, i << (32 + 24) | icr | (j << 8)); + } + + /* And again with a shorthand destination for all types of IPIs. */ + icr = APIC_DEST_ALLBUT | APIC_INT_ASSERT; + for (i = 0; i < 8; i++) + __test_icr(x, icr | (i << 8)); + + /* And a few garbage value, just make sure it's an IRQ (blocked). */ + __test_icr(x, 0xa5a5a5a5a5a5a5a5 & ~APIC_DM_FIXED_MASK); + __test_icr(x, 0x5a5a5a5a5a5a5a5a & ~APIC_DM_FIXED_MASK); + __test_icr(x, -1ull & ~APIC_DM_FIXED_MASK); +} + +int main(int argc, char *argv[]) +{ + struct xapic_vcpu x = { + .vcpu = NULL, + .is_x2apic = true, + }; + struct kvm_vm *vm; + + vm = vm_create_with_one_vcpu(&x.vcpu, x2apic_guest_code); + test_icr(&x); + kvm_vm_free(vm); + + /* + * Use a second VM for the xAPIC test so that x2APIC can be hidden from + * the guest in order to test AVIC. KVM disallows changing CPUID after + * KVM_RUN and AVIC is disabled if _any_ vCPU is allowed to use x2APIC. + */ + vm = vm_create_with_one_vcpu(&x.vcpu, xapic_guest_code); + x.is_x2apic = false; + + vcpu_clear_cpuid_feature(x.vcpu, X86_FEATURE_X2APIC); + + virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); + test_icr(&x); + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index a0699f00b3d6..2a5727188c8d 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -14,44 +14,77 @@ #include <stdint.h> #include <time.h> #include <sched.h> +#include <signal.h> +#include <pthread.h> -#define VCPU_ID 5 +#include <sys/eventfd.h> + +/* Defined in include/linux/kvm_types.h */ +#define GPA_INVALID (~(ulong)0) #define SHINFO_REGION_GVA 0xc0000000ULL #define SHINFO_REGION_GPA 0xc0000000ULL #define SHINFO_REGION_SLOT 10 -#define PAGE_SIZE 4096 +#define DUMMY_REGION_GPA (SHINFO_REGION_GPA + (2 * PAGE_SIZE)) +#define DUMMY_REGION_SLOT 11 + +#define SHINFO_ADDR (SHINFO_REGION_GPA) #define PVTIME_ADDR (SHINFO_REGION_GPA + PAGE_SIZE) #define RUNSTATE_ADDR (SHINFO_REGION_GPA + PAGE_SIZE + 0x20) #define VCPU_INFO_ADDR (SHINFO_REGION_GPA + 0x40) +#define SHINFO_VADDR (SHINFO_REGION_GVA) #define RUNSTATE_VADDR (SHINFO_REGION_GVA + PAGE_SIZE + 0x20) #define VCPU_INFO_VADDR (SHINFO_REGION_GVA + 0x40) #define EVTCHN_VECTOR 0x10 -static struct kvm_vm *vm; +#define EVTCHN_TEST1 15 +#define EVTCHN_TEST2 66 +#define EVTCHN_TIMER 13 #define XEN_HYPERCALL_MSR 0x40000000 #define MIN_STEAL_TIME 50000 +#define SHINFO_RACE_TIMEOUT 2 /* seconds */ + +#define __HYPERVISOR_set_timer_op 15 +#define __HYPERVISOR_sched_op 29 +#define __HYPERVISOR_event_channel_op 32 + +#define SCHEDOP_poll 3 + +#define EVTCHNOP_send 4 + +#define EVTCHNSTAT_interdomain 2 + +struct evtchn_send { + u32 port; +}; + +struct sched_poll { + u32 *ports; + unsigned int nr_ports; + u64 timeout; +}; + struct pvclock_vcpu_time_info { - u32 version; - u32 pad0; - u64 tsc_timestamp; - u64 system_time; - u32 tsc_to_system_mul; - s8 tsc_shift; - u8 flags; - u8 pad[2]; + u32 version; + u32 pad0; + u64 tsc_timestamp; + u64 system_time; + u32 tsc_to_system_mul; + s8 tsc_shift; + u8 flags; + u8 pad[2]; } __attribute__((__packed__)); /* 32 bytes */ struct pvclock_wall_clock { - u32 version; - u32 sec; - u32 nsec; + u32 version; + u32 sec; + u32 nsec; } __attribute__((__packed__)); struct vcpu_runstate_info { @@ -66,29 +99,62 @@ struct arch_vcpu_info { }; struct vcpu_info { - uint8_t evtchn_upcall_pending; - uint8_t evtchn_upcall_mask; - unsigned long evtchn_pending_sel; - struct arch_vcpu_info arch; - struct pvclock_vcpu_time_info time; + uint8_t evtchn_upcall_pending; + uint8_t evtchn_upcall_mask; + unsigned long evtchn_pending_sel; + struct arch_vcpu_info arch; + struct pvclock_vcpu_time_info time; }; /* 64 bytes (x86) */ +struct shared_info { + struct vcpu_info vcpu_info[32]; + unsigned long evtchn_pending[64]; + unsigned long evtchn_mask[64]; + struct pvclock_wall_clock wc; + uint32_t wc_sec_hi; + /* arch_shared_info here */ +}; + #define RUNSTATE_running 0 #define RUNSTATE_runnable 1 #define RUNSTATE_blocked 2 #define RUNSTATE_offline 3 +static const char *runstate_names[] = { + "running", + "runnable", + "blocked", + "offline" +}; + +struct { + struct kvm_irq_routing info; + struct kvm_irq_routing_entry entries[2]; +} irq_routes; + +static volatile bool guest_saw_irq; + static void evtchn_handler(struct ex_regs *regs) { struct vcpu_info *vi = (void *)VCPU_INFO_VADDR; vi->evtchn_upcall_pending = 0; + vi->evtchn_pending_sel = 0; + guest_saw_irq = true; GUEST_SYNC(0x20); } +static void guest_wait_for_irq(void) +{ + while (!guest_saw_irq) + __asm__ __volatile__ ("rep nop" : : : "memory"); + guest_saw_irq = false; +} + static void guest_code(void) { struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR; + int i; __asm__ __volatile__( "sti\n" @@ -98,6 +164,8 @@ static void guest_code(void) /* Trigger an interrupt injection */ GUEST_SYNC(0); + guest_wait_for_irq(); + /* Test having the host set runstates manually */ GUEST_SYNC(RUNSTATE_runnable); GUEST_ASSERT(rs->time[RUNSTATE_runnable] != 0); @@ -127,7 +195,186 @@ static void guest_code(void) GUEST_SYNC(6); GUEST_ASSERT(rs->time[RUNSTATE_runnable] >= MIN_STEAL_TIME); - GUEST_DONE(); + /* Attempt to deliver a *masked* interrupt */ + GUEST_SYNC(7); + + /* Wait until we see the bit set */ + struct shared_info *si = (void *)SHINFO_VADDR; + while (!si->evtchn_pending[0]) + __asm__ __volatile__ ("rep nop" : : : "memory"); + + /* Now deliver an *unmasked* interrupt */ + GUEST_SYNC(8); + + guest_wait_for_irq(); + + /* Change memslots and deliver an interrupt */ + GUEST_SYNC(9); + + guest_wait_for_irq(); + + /* Deliver event channel with KVM_XEN_HVM_EVTCHN_SEND */ + GUEST_SYNC(10); + + guest_wait_for_irq(); + + GUEST_SYNC(11); + + /* Our turn. Deliver event channel (to ourselves) with + * EVTCHNOP_send hypercall. */ + unsigned long rax; + struct evtchn_send s = { .port = 127 }; + __asm__ __volatile__ ("vmcall" : + "=a" (rax) : + "a" (__HYPERVISOR_event_channel_op), + "D" (EVTCHNOP_send), + "S" (&s)); + + GUEST_ASSERT(rax == 0); + + guest_wait_for_irq(); + + GUEST_SYNC(12); + + /* Deliver "outbound" event channel to an eventfd which + * happens to be one of our own irqfds. */ + s.port = 197; + __asm__ __volatile__ ("vmcall" : + "=a" (rax) : + "a" (__HYPERVISOR_event_channel_op), + "D" (EVTCHNOP_send), + "S" (&s)); + + GUEST_ASSERT(rax == 0); + + guest_wait_for_irq(); + + GUEST_SYNC(13); + + /* Set a timer 100ms in the future. */ + __asm__ __volatile__ ("vmcall" : + "=a" (rax) : + "a" (__HYPERVISOR_set_timer_op), + "D" (rs->state_entry_time + 100000000)); + GUEST_ASSERT(rax == 0); + + GUEST_SYNC(14); + + /* Now wait for the timer */ + guest_wait_for_irq(); + + GUEST_SYNC(15); + + /* The host has 'restored' the timer. Just wait for it. */ + guest_wait_for_irq(); + + GUEST_SYNC(16); + + /* Poll for an event channel port which is already set */ + u32 ports[1] = { EVTCHN_TIMER }; + struct sched_poll p = { + .ports = ports, + .nr_ports = 1, + .timeout = 0, + }; + + __asm__ __volatile__ ("vmcall" : + "=a" (rax) : + "a" (__HYPERVISOR_sched_op), + "D" (SCHEDOP_poll), + "S" (&p)); + + GUEST_ASSERT(rax == 0); + + GUEST_SYNC(17); + + /* Poll for an unset port and wait for the timeout. */ + p.timeout = 100000000; + __asm__ __volatile__ ("vmcall" : + "=a" (rax) : + "a" (__HYPERVISOR_sched_op), + "D" (SCHEDOP_poll), + "S" (&p)); + + GUEST_ASSERT(rax == 0); + + GUEST_SYNC(18); + + /* A timer will wake the masked port we're waiting on, while we poll */ + p.timeout = 0; + __asm__ __volatile__ ("vmcall" : + "=a" (rax) : + "a" (__HYPERVISOR_sched_op), + "D" (SCHEDOP_poll), + "S" (&p)); + + GUEST_ASSERT(rax == 0); + + GUEST_SYNC(19); + + /* A timer wake an *unmasked* port which should wake us with an + * actual interrupt, while we're polling on a different port. */ + ports[0]++; + p.timeout = 0; + __asm__ __volatile__ ("vmcall" : + "=a" (rax) : + "a" (__HYPERVISOR_sched_op), + "D" (SCHEDOP_poll), + "S" (&p)); + + GUEST_ASSERT(rax == 0); + + guest_wait_for_irq(); + + GUEST_SYNC(20); + + /* Timer should have fired already */ + guest_wait_for_irq(); + + GUEST_SYNC(21); + /* Racing host ioctls */ + + guest_wait_for_irq(); + + GUEST_SYNC(22); + /* Racing vmcall against host ioctl */ + + ports[0] = 0; + + p = (struct sched_poll) { + .ports = ports, + .nr_ports = 1, + .timeout = 0 + }; + +wait_for_timer: + /* + * Poll for a timer wake event while the worker thread is mucking with + * the shared info. KVM XEN drops timer IRQs if the shared info is + * invalid when the timer expires. Arbitrarily poll 100 times before + * giving up and asking the VMM to re-arm the timer. 100 polls should + * consume enough time to beat on KVM without taking too long if the + * timer IRQ is dropped due to an invalid event channel. + */ + for (i = 0; i < 100 && !guest_saw_irq; i++) + asm volatile("vmcall" + : "=a" (rax) + : "a" (__HYPERVISOR_sched_op), + "D" (SCHEDOP_poll), + "S" (&p) + : "memory"); + + /* + * Re-send the timer IRQ if it was (likely) dropped due to the timer + * expiring while the event channel was invalid. + */ + if (!guest_saw_irq) { + GUEST_SYNC(23); + goto wait_for_timer; + } + guest_saw_irq = false; + + GUEST_SYNC(24); } static int cmp_timespec(struct timespec *a, struct timespec *b) @@ -144,32 +391,82 @@ static int cmp_timespec(struct timespec *a, struct timespec *b) return 0; } +static struct vcpu_info *vinfo; +static struct kvm_vcpu *vcpu; + +static void handle_alrm(int sig) +{ + if (vinfo) + printf("evtchn_upcall_pending 0x%x\n", vinfo->evtchn_upcall_pending); + vcpu_dump(stdout, vcpu, 0); + TEST_FAIL("IRQ delivery timed out"); +} + +static void *juggle_shinfo_state(void *arg) +{ + struct kvm_vm *vm = (struct kvm_vm *)arg; + + struct kvm_xen_hvm_attr cache_init = { + .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, + .u.shared_info.gfn = SHINFO_REGION_GPA / PAGE_SIZE + }; + + struct kvm_xen_hvm_attr cache_destroy = { + .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, + .u.shared_info.gfn = GPA_INVALID + }; + + for (;;) { + __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_init); + __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_destroy); + pthread_testcancel(); + }; + + return NULL; +} + int main(int argc, char *argv[]) { struct timespec min_ts, max_ts, vm_ts; + struct kvm_vm *vm; + pthread_t thread; + bool verbose; + int ret; + + verbose = argc > 1 && (!strncmp(argv[1], "-v", 3) || + !strncmp(argv[1], "--verbose", 10)); int xen_caps = kvm_check_cap(KVM_CAP_XEN_HVM); - if (!(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO) ) { - print_skip("KVM_XEN_HVM_CONFIG_SHARED_INFO not available"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO); bool do_runstate_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE); + bool do_eventfd_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL); + bool do_evtchn_tests = do_eventfd_tests && !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_SEND); clock_gettime(CLOCK_REALTIME, &min_ts); - vm = vm_create_default(VCPU_ID, 0, (void *) guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); /* Map a region for the shared_info page */ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SHINFO_REGION_GPA, SHINFO_REGION_SLOT, 2, 0); virt_map(vm, SHINFO_REGION_GVA, SHINFO_REGION_GPA, 2); + struct shared_info *shinfo = addr_gpa2hva(vm, SHINFO_VADDR); + + int zero_fd = open("/dev/zero", O_RDONLY); + TEST_ASSERT(zero_fd != -1, "Failed to open /dev/zero"); + struct kvm_xen_hvm_config hvmc = { .flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL, .msr = XEN_HYPERCALL_MSR, }; + + /* Let the kernel know that we *will* use it for sending all + * event channels, which lets it intercept SCHEDOP_poll */ + if (do_evtchn_tests) + hvmc.flags |= KVM_XEN_HVM_CONFIG_EVTCHN_SEND; + vm_ioctl(vm, KVM_XEN_HVM_CONFIG, &hvmc); struct kvm_xen_hvm_attr lm = { @@ -184,17 +481,27 @@ int main(int argc, char *argv[]) }; vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &ha); + /* + * Test what happens when the HVA of the shinfo page is remapped after + * the kernel has a reference to it. But make sure we copy the clock + * info over since that's only set at setup time, and we test it later. + */ + struct pvclock_wall_clock wc_copy = shinfo->wc; + void *m = mmap(shinfo, PAGE_SIZE, PROT_READ|PROT_WRITE, MAP_FIXED|MAP_PRIVATE, zero_fd, 0); + TEST_ASSERT(m == shinfo, "Failed to map /dev/zero over shared info"); + shinfo->wc = wc_copy; + struct kvm_xen_vcpu_attr vi = { .type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO, .u.gpa = VCPU_INFO_ADDR, }; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &vi); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &vi); struct kvm_xen_vcpu_attr pvclock = { .type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO, .u.gpa = PVTIME_ADDR, }; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &pvclock); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &pvclock); struct kvm_xen_hvm_attr vec = { .type = KVM_XEN_ATTR_TYPE_UPCALL_VECTOR, @@ -203,7 +510,7 @@ int main(int argc, char *argv[]) vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &vec); vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); + vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vm, EVTCHN_VECTOR, evtchn_handler); if (do_runstate_tests) { @@ -211,10 +518,85 @@ int main(int argc, char *argv[]) .type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR, .u.gpa = RUNSTATE_ADDR, }; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &st); } - struct vcpu_info *vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR); + int irq_fd[2] = { -1, -1 }; + + if (do_eventfd_tests) { + irq_fd[0] = eventfd(0, 0); + irq_fd[1] = eventfd(0, 0); + + /* Unexpected, but not a KVM failure */ + if (irq_fd[0] == -1 || irq_fd[1] == -1) + do_evtchn_tests = do_eventfd_tests = false; + } + + if (do_eventfd_tests) { + irq_routes.info.nr = 2; + + irq_routes.entries[0].gsi = 32; + irq_routes.entries[0].type = KVM_IRQ_ROUTING_XEN_EVTCHN; + irq_routes.entries[0].u.xen_evtchn.port = EVTCHN_TEST1; + irq_routes.entries[0].u.xen_evtchn.vcpu = vcpu->id; + irq_routes.entries[0].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; + + irq_routes.entries[1].gsi = 33; + irq_routes.entries[1].type = KVM_IRQ_ROUTING_XEN_EVTCHN; + irq_routes.entries[1].u.xen_evtchn.port = EVTCHN_TEST2; + irq_routes.entries[1].u.xen_evtchn.vcpu = vcpu->id; + irq_routes.entries[1].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; + + vm_ioctl(vm, KVM_SET_GSI_ROUTING, &irq_routes.info); + + struct kvm_irqfd ifd = { }; + + ifd.fd = irq_fd[0]; + ifd.gsi = 32; + vm_ioctl(vm, KVM_IRQFD, &ifd); + + ifd.fd = irq_fd[1]; + ifd.gsi = 33; + vm_ioctl(vm, KVM_IRQFD, &ifd); + + struct sigaction sa = { }; + sa.sa_handler = handle_alrm; + sigaction(SIGALRM, &sa, NULL); + } + + struct kvm_xen_vcpu_attr tmr = { + .type = KVM_XEN_VCPU_ATTR_TYPE_TIMER, + .u.timer.port = EVTCHN_TIMER, + .u.timer.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL, + .u.timer.expires_ns = 0 + }; + + if (do_evtchn_tests) { + struct kvm_xen_hvm_attr inj = { + .type = KVM_XEN_ATTR_TYPE_EVTCHN, + .u.evtchn.send_port = 127, + .u.evtchn.type = EVTCHNSTAT_interdomain, + .u.evtchn.flags = 0, + .u.evtchn.deliver.port.port = EVTCHN_TEST1, + .u.evtchn.deliver.port.vcpu = vcpu->id + 1, + .u.evtchn.deliver.port.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL, + }; + vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &inj); + + /* Test migration to a different vCPU */ + inj.u.evtchn.flags = KVM_XEN_EVTCHN_UPDATE; + inj.u.evtchn.deliver.port.vcpu = vcpu->id; + vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &inj); + + inj.u.evtchn.send_port = 197; + inj.u.evtchn.deliver.eventfd.port = 0; + inj.u.evtchn.deliver.eventfd.fd = irq_fd[1]; + inj.u.evtchn.flags = 0; + vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &inj); + + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); + } + vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR); vinfo->evtchn_upcall_pending = 0; struct vcpu_runstate_info *rs = addr_gpa2hva(vm, RUNSTATE_ADDR); @@ -223,19 +605,19 @@ int main(int argc, char *argv[]) bool evtchn_irq_expected = false; for (;;) { - volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + volatile struct kvm_run *run = vcpu->run; struct ucall uc; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s", (const char *)uc.args[0]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: { struct kvm_xen_vcpu_attr rst; @@ -248,6 +630,8 @@ int main(int argc, char *argv[]) switch (uc.args[1]) { case 0: + if (verbose) + printf("Delivering evtchn upcall\n"); evtchn_irq_expected = true; vinfo->evtchn_upcall_pending = 1; break; @@ -256,11 +640,16 @@ int main(int argc, char *argv[]) TEST_ASSERT(!evtchn_irq_expected, "Event channel IRQ not seen"); if (!do_runstate_tests) goto done; + if (verbose) + printf("Testing runstate %s\n", runstate_names[uc.args[1]]); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT; rst.u.runstate.state = uc.args[1]; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &rst); break; + case 4: + if (verbose) + printf("Testing RUNSTATE_ADJUST\n"); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST; memset(&rst.u, 0, sizeof(rst.u)); rst.u.runstate.state = (uint64_t)-1; @@ -270,25 +659,274 @@ int main(int argc, char *argv[]) 0x6b6b - rs->time[RUNSTATE_offline]; rst.u.runstate.time_runnable = -rst.u.runstate.time_blocked - rst.u.runstate.time_offline; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &rst); break; case 5: + if (verbose) + printf("Testing RUNSTATE_DATA\n"); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA; memset(&rst.u, 0, sizeof(rst.u)); rst.u.runstate.state = RUNSTATE_running; rst.u.runstate.state_entry_time = 0x6b6b + 0x5a; rst.u.runstate.time_blocked = 0x6b6b; rst.u.runstate.time_offline = 0x5a; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &rst); break; + case 6: + if (verbose) + printf("Testing steal time\n"); /* Yield until scheduler delay exceeds target */ rundelay = get_run_delay() + MIN_STEAL_TIME; do { sched_yield(); } while (get_run_delay() < rundelay); break; + + case 7: + if (!do_eventfd_tests) + goto done; + if (verbose) + printf("Testing masked event channel\n"); + shinfo->evtchn_mask[0] = 1UL << EVTCHN_TEST1; + eventfd_write(irq_fd[0], 1UL); + alarm(1); + break; + + case 8: + if (verbose) + printf("Testing unmasked event channel\n"); + /* Unmask that, but deliver the other one */ + shinfo->evtchn_pending[0] = 0; + shinfo->evtchn_mask[0] = 0; + eventfd_write(irq_fd[1], 1UL); + evtchn_irq_expected = true; + alarm(1); + break; + + case 9: + TEST_ASSERT(!evtchn_irq_expected, + "Expected event channel IRQ but it didn't happen"); + shinfo->evtchn_pending[1] = 0; + if (verbose) + printf("Testing event channel after memslot change\n"); + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + DUMMY_REGION_GPA, DUMMY_REGION_SLOT, 1, 0); + eventfd_write(irq_fd[0], 1UL); + evtchn_irq_expected = true; + alarm(1); + break; + + case 10: + TEST_ASSERT(!evtchn_irq_expected, + "Expected event channel IRQ but it didn't happen"); + if (!do_evtchn_tests) + goto done; + + shinfo->evtchn_pending[0] = 0; + if (verbose) + printf("Testing injection with KVM_XEN_HVM_EVTCHN_SEND\n"); + + struct kvm_irq_routing_xen_evtchn e; + e.port = EVTCHN_TEST2; + e.vcpu = vcpu->id; + e.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; + + vm_ioctl(vm, KVM_XEN_HVM_EVTCHN_SEND, &e); + evtchn_irq_expected = true; + alarm(1); + break; + + case 11: + TEST_ASSERT(!evtchn_irq_expected, + "Expected event channel IRQ but it didn't happen"); + shinfo->evtchn_pending[1] = 0; + + if (verbose) + printf("Testing guest EVTCHNOP_send direct to evtchn\n"); + evtchn_irq_expected = true; + alarm(1); + break; + + case 12: + TEST_ASSERT(!evtchn_irq_expected, + "Expected event channel IRQ but it didn't happen"); + shinfo->evtchn_pending[0] = 0; + + if (verbose) + printf("Testing guest EVTCHNOP_send to eventfd\n"); + evtchn_irq_expected = true; + alarm(1); + break; + + case 13: + TEST_ASSERT(!evtchn_irq_expected, + "Expected event channel IRQ but it didn't happen"); + shinfo->evtchn_pending[1] = 0; + + if (verbose) + printf("Testing guest oneshot timer\n"); + break; + + case 14: + memset(&tmr, 0, sizeof(tmr)); + tmr.type = KVM_XEN_VCPU_ATTR_TYPE_TIMER; + vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &tmr); + TEST_ASSERT(tmr.u.timer.port == EVTCHN_TIMER, + "Timer port not returned"); + TEST_ASSERT(tmr.u.timer.priority == KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL, + "Timer priority not returned"); + TEST_ASSERT(tmr.u.timer.expires_ns > rs->state_entry_time, + "Timer expiry not returned"); + evtchn_irq_expected = true; + alarm(1); + break; + + case 15: + TEST_ASSERT(!evtchn_irq_expected, + "Expected event channel IRQ but it didn't happen"); + shinfo->evtchn_pending[0] = 0; + + if (verbose) + printf("Testing restored oneshot timer\n"); + + tmr.u.timer.expires_ns = rs->state_entry_time + 100000000; + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); + evtchn_irq_expected = true; + alarm(1); + break; + + case 16: + TEST_ASSERT(!evtchn_irq_expected, + "Expected event channel IRQ but it didn't happen"); + + if (verbose) + printf("Testing SCHEDOP_poll with already pending event\n"); + shinfo->evtchn_pending[0] = shinfo->evtchn_mask[0] = 1UL << EVTCHN_TIMER; + alarm(1); + break; + + case 17: + if (verbose) + printf("Testing SCHEDOP_poll timeout\n"); + shinfo->evtchn_pending[0] = 0; + alarm(1); + break; + + case 18: + if (verbose) + printf("Testing SCHEDOP_poll wake on masked event\n"); + + tmr.u.timer.expires_ns = rs->state_entry_time + 100000000; + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); + alarm(1); + break; + + case 19: + shinfo->evtchn_pending[0] = shinfo->evtchn_mask[0] = 0; + if (verbose) + printf("Testing SCHEDOP_poll wake on unmasked event\n"); + + evtchn_irq_expected = true; + tmr.u.timer.expires_ns = rs->state_entry_time + 100000000; + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); + + /* Read it back and check the pending time is reported correctly */ + tmr.u.timer.expires_ns = 0; + vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &tmr); + TEST_ASSERT(tmr.u.timer.expires_ns == rs->state_entry_time + 100000000, + "Timer not reported pending"); + alarm(1); + break; + + case 20: + TEST_ASSERT(!evtchn_irq_expected, + "Expected event channel IRQ but it didn't happen"); + /* Read timer and check it is no longer pending */ + vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &tmr); + TEST_ASSERT(!tmr.u.timer.expires_ns, "Timer still reported pending"); + + shinfo->evtchn_pending[0] = 0; + if (verbose) + printf("Testing timer in the past\n"); + + evtchn_irq_expected = true; + tmr.u.timer.expires_ns = rs->state_entry_time - 100000000ULL; + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); + alarm(1); + break; + + case 21: + TEST_ASSERT(!evtchn_irq_expected, + "Expected event channel IRQ but it didn't happen"); + alarm(0); + + if (verbose) + printf("Testing shinfo lock corruption (KVM_XEN_HVM_EVTCHN_SEND)\n"); + + ret = pthread_create(&thread, NULL, &juggle_shinfo_state, (void *)vm); + TEST_ASSERT(ret == 0, "pthread_create() failed: %s", strerror(ret)); + + struct kvm_irq_routing_xen_evtchn uxe = { + .port = 1, + .vcpu = vcpu->id, + .priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL + }; + + evtchn_irq_expected = true; + for (time_t t = time(NULL) + SHINFO_RACE_TIMEOUT; time(NULL) < t;) + __vm_ioctl(vm, KVM_XEN_HVM_EVTCHN_SEND, &uxe); + break; + + case 22: + TEST_ASSERT(!evtchn_irq_expected, + "Expected event channel IRQ but it didn't happen"); + + if (verbose) + printf("Testing shinfo lock corruption (SCHEDOP_poll)\n"); + + shinfo->evtchn_pending[0] = 1; + + evtchn_irq_expected = true; + tmr.u.timer.expires_ns = rs->state_entry_time + + SHINFO_RACE_TIMEOUT * 1000000000ULL; + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); + break; + + case 23: + /* + * Optional and possibly repeated sync point. + * Injecting the timer IRQ may fail if the + * shinfo is invalid when the timer expires. + * If the timer has expired but the IRQ hasn't + * been delivered, rearm the timer and retry. + */ + vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &tmr); + + /* Resume the guest if the timer is still pending. */ + if (tmr.u.timer.expires_ns) + break; + + /* All done if the IRQ was delivered. */ + if (!evtchn_irq_expected) + break; + + tmr.u.timer.expires_ns = rs->state_entry_time + + SHINFO_RACE_TIMEOUT * 1000000000ULL; + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); + break; + case 24: + TEST_ASSERT(!evtchn_irq_expected, + "Expected event channel IRQ but it didn't happen"); + + ret = pthread_cancel(thread); + TEST_ASSERT(ret == 0, "pthread_cancel() failed: %s", strerror(ret)); + + ret = pthread_join(thread, 0); + TEST_ASSERT(ret == 0, "pthread_join() failed: %s", strerror(ret)); + goto done; + case 0x20: TEST_ASSERT(evtchn_irq_expected, "Unexpected event channel IRQ"); evtchn_irq_expected = false; @@ -304,6 +942,7 @@ int main(int argc, char *argv[]) } done: + alarm(0); clock_gettime(CLOCK_REALTIME, &max_ts); /* @@ -318,9 +957,19 @@ int main(int argc, char *argv[]) ti = addr_gpa2hva(vm, SHINFO_REGION_GPA + 0x40 + 0x20); ti2 = addr_gpa2hva(vm, PVTIME_ADDR); + if (verbose) { + printf("Wall clock (v %d) %d.%09d\n", wc->version, wc->sec, wc->nsec); + printf("Time info 1: v %u tsc %" PRIu64 " time %" PRIu64 " mul %u shift %u flags %x\n", + ti->version, ti->tsc_timestamp, ti->system_time, ti->tsc_to_system_mul, + ti->tsc_shift, ti->flags); + printf("Time info 2: v %u tsc %" PRIu64 " time %" PRIu64 " mul %u shift %u flags %x\n", + ti2->version, ti2->tsc_timestamp, ti2->system_time, ti2->tsc_to_system_mul, + ti2->tsc_shift, ti2->flags); + } + vm_ts.tv_sec = wc->sec; vm_ts.tv_nsec = wc->nsec; - TEST_ASSERT(wc->version && !(wc->version & 1), + TEST_ASSERT(wc->version && !(wc->version & 1), "Bad wallclock version %x", wc->version); TEST_ASSERT(cmp_timespec(&min_ts, &vm_ts) <= 0, "VM time too old"); TEST_ASSERT(cmp_timespec(&max_ts, &vm_ts) >= 0, "VM time too new"); @@ -339,8 +988,17 @@ int main(int argc, char *argv[]) struct kvm_xen_vcpu_attr rst = { .type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA, }; - vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &rst); - + vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &rst); + + if (verbose) { + printf("Runstate: %s(%d), entry %" PRIu64 " ns\n", + rs->state <= RUNSTATE_offline ? runstate_names[rs->state] : "unknown", + rs->state, rs->state_entry_time); + for (int i = RUNSTATE_running; i <= RUNSTATE_offline; i++) { + printf("State %s: %" PRIu64 " ns\n", + runstate_names[i], rs->time[i]); + } + } TEST_ASSERT(rs->state == rst.u.runstate.state, "Runstate mismatch"); TEST_ASSERT(rs->state_entry_time == rst.u.runstate.state_entry_time, "State entry time mismatch"); diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c index adc94452b57c..88914d48c65e 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c @@ -11,13 +11,8 @@ #include "kvm_util.h" #include "processor.h" -#define VCPU_ID 5 - #define HCALL_REGION_GPA 0xc0000000ULL #define HCALL_REGION_SLOT 10 -#define PAGE_SIZE 4096 - -static struct kvm_vm *vm; #define INPUTVALUE 17 #define ARGVALUE(x) (0xdeadbeef5a5a0000UL + x) @@ -85,14 +80,15 @@ static void guest_code(void) int main(int argc, char *argv[]) { - if (!(kvm_check_cap(KVM_CAP_XEN_HVM) & - KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL) ) { - print_skip("KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL not available"); - exit(KSFT_SKIP); - } + unsigned int xen_caps; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + xen_caps = kvm_check_cap(KVM_CAP_XEN_HVM); + TEST_REQUIRE(xen_caps & KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL); - vm = vm_create_default(VCPU_ID, 0, (void *) guest_code); - vcpu_set_hv_cpuid(vm, VCPU_ID); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + vcpu_set_hv_cpuid(vcpu); struct kvm_xen_hvm_config hvmc = { .flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL, @@ -106,10 +102,10 @@ int main(int argc, char *argv[]) virt_map(vm, HCALL_REGION_GPA, HCALL_REGION_GPA, 2); for (;;) { - volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + volatile struct kvm_run *run = vcpu->run; struct ucall uc; - vcpu_run(vm, VCPU_ID); + vcpu_run(vcpu); if (run->exit_reason == KVM_EXIT_XEN) { ASSERT_EQ(run->xen.type, KVM_EXIT_XEN_HCALL); @@ -131,9 +127,9 @@ int main(int argc, char *argv[]) run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vm, VCPU_ID, &uc)) { + switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - TEST_FAIL("%s", (const char *)uc.args[0]); + REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: break; diff --git a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c index 3529376747c2..e0ddf47362e7 100644 --- a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c +++ b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c @@ -12,64 +12,44 @@ #include "kvm_util.h" #include "vmx.h" -#define VCPU_ID 1 #define MSR_BITS 64 -#define X86_FEATURE_XSAVES (1<<3) - -bool is_supported_msr(u32 msr_index) -{ - struct kvm_msr_list *list; - bool found = false; - int i; - - list = kvm_get_msr_index_list(); - for (i = 0; i < list->nmsrs; ++i) { - if (list->indices[i] == msr_index) { - found = true; - break; - } - } - - free(list); - return found; -} - int main(int argc, char *argv[]) { - struct kvm_cpuid_entry2 *entry; - bool xss_supported = false; + bool xss_in_msr_list; struct kvm_vm *vm; + struct kvm_vcpu *vcpu; uint64_t xss_val; int i, r; /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, 0); + vm = vm_create_with_one_vcpu(&vcpu, NULL); - if (kvm_get_cpuid_max_basic() >= 0xd) { - entry = kvm_get_supported_cpuid_index(0xd, 1); - xss_supported = entry && !!(entry->eax & X86_FEATURE_XSAVES); - } - if (!xss_supported) { - print_skip("IA32_XSS is not supported by the vCPU"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XSAVES)); - xss_val = vcpu_get_msr(vm, VCPU_ID, MSR_IA32_XSS); + xss_val = vcpu_get_msr(vcpu, MSR_IA32_XSS); TEST_ASSERT(xss_val == 0, "MSR_IA32_XSS should be initialized to zero\n"); - vcpu_set_msr(vm, VCPU_ID, MSR_IA32_XSS, xss_val); + vcpu_set_msr(vcpu, MSR_IA32_XSS, xss_val); + /* * At present, KVM only supports a guest IA32_XSS value of 0. Verify * that trying to set the guest IA32_XSS to an unsupported value fails. * Also, in the future when a non-zero value succeeds check that - * IA32_XSS is in the KVM_GET_MSR_INDEX_LIST. + * IA32_XSS is in the list of MSRs to save/restore. */ + xss_in_msr_list = kvm_msr_is_in_save_restore_list(MSR_IA32_XSS); for (i = 0; i < MSR_BITS; ++i) { - r = _vcpu_set_msr(vm, VCPU_ID, MSR_IA32_XSS, 1ull << i); - TEST_ASSERT(r == 0 || is_supported_msr(MSR_IA32_XSS), - "IA32_XSS was able to be set, but was not found in KVM_GET_MSR_INDEX_LIST.\n"); + r = _vcpu_set_msr(vcpu, MSR_IA32_XSS, 1ull << i); + + /* + * Setting a list of MSRs returns the entry that "faulted", or + * the last entry +1 if all MSRs were successfully written. + */ + TEST_ASSERT(!r || r == 1, KVM_IOCTL_ERROR(KVM_SET_MSRS, r)); + TEST_ASSERT(r != 1 || xss_in_msr_list, + "IA32_XSS was able to be set, but was not in save/restore list"); } kvm_vm_free(vm); |