diff options
Diffstat (limited to 'tools/testing/selftests/kvm/x86')
77 files changed, 4125 insertions, 1081 deletions
diff --git a/tools/testing/selftests/kvm/x86/amx_test.c b/tools/testing/selftests/kvm/x86/amx_test.c index f4ce5a185a7d..4e63da2b1889 100644 --- a/tools/testing/selftests/kvm/x86/amx_test.c +++ b/tools/testing/selftests/kvm/x86/amx_test.c @@ -69,15 +69,21 @@ static inline void __tileloadd(void *tile) : : "a"(tile), "d"(0)); } +static inline int tileloadd_safe(void *tile) +{ + return kvm_asm_safe(".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 xstate *xstate, uint64_t rfbm) +static inline void __xsavec(struct xstate *xstate, u64 rfbm) { - uint32_t rfbm_lo = rfbm; - uint32_t rfbm_hi = rfbm >> 32; + u32 rfbm_lo = rfbm; + u32 rfbm_hi = rfbm >> 32; asm volatile("xsavec (%%rdi)" : : "D" (xstate), "a" (rfbm_lo), "d" (rfbm_hi) @@ -124,27 +130,52 @@ static void set_tilecfg(struct tile_config *cfg) } } +enum { + /* Retrieve TMM0 from guest, stash it for TEST_RESTORE_TILEDATA */ + TEST_SAVE_TILEDATA = 1, + + /* Check TMM0 against tiledata */ + TEST_COMPARE_TILEDATA = 2, + + /* Restore TMM0 from earlier save */ + TEST_RESTORE_TILEDATA = 4, + + /* Full VM save/restore */ + TEST_SAVE_RESTORE = 8, +}; + static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, struct tile_data *tiledata, struct xstate *xstate) { + int vector; + GUEST_ASSERT(this_cpu_has(X86_FEATURE_XSAVE) && this_cpu_has(X86_FEATURE_OSXSAVE)); check_xtile_info(); - GUEST_SYNC(1); + GUEST_SYNC(TEST_SAVE_RESTORE); /* xfd=0, enable amx */ wrmsr(MSR_IA32_XFD, 0); - GUEST_SYNC(2); + GUEST_SYNC(TEST_SAVE_RESTORE); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == 0); set_tilecfg(amx_cfg); __ldtilecfg(amx_cfg); - GUEST_SYNC(3); + GUEST_SYNC(TEST_SAVE_RESTORE); /* Check save/restore when trap to userspace */ __tileloadd(tiledata); - GUEST_SYNC(4); + GUEST_SYNC(TEST_SAVE_TILEDATA | TEST_COMPARE_TILEDATA | TEST_SAVE_RESTORE); + + /* xfd=0x40000, disable amx tiledata */ + wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILE_DATA); + + /* host tries setting tiledata while guest XFD is set */ + GUEST_SYNC(TEST_RESTORE_TILEDATA); + GUEST_SYNC(TEST_SAVE_RESTORE); + + wrmsr(MSR_IA32_XFD, 0); __tilerelease(); - GUEST_SYNC(5); + GUEST_SYNC(TEST_SAVE_RESTORE); /* * After XSAVEC, XTILEDATA is cleared in the xstate_bv but is set in * the xcomp_bv. @@ -154,6 +185,8 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILE_DATA)); GUEST_ASSERT(xstate->header.xcomp_bv & XFEATURE_MASK_XTILE_DATA); + /* #NM test */ + /* xfd=0x40000, disable amx tiledata */ wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILE_DATA); @@ -166,32 +199,33 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILE_DATA)); GUEST_ASSERT((xstate->header.xcomp_bv & XFEATURE_MASK_XTILE_DATA)); - GUEST_SYNC(6); + GUEST_SYNC(TEST_SAVE_RESTORE); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); set_tilecfg(amx_cfg); __ldtilecfg(amx_cfg); - /* Trigger #NM exception */ - __tileloadd(tiledata); - GUEST_SYNC(10); - GUEST_DONE(); -} + /* Trigger #NM exception */ + vector = tileloadd_safe(tiledata); + __GUEST_ASSERT(vector == NM_VECTOR, + "Wanted #NM on tileloadd with XFD[18]=1, got %s", + ex_str(vector)); -void guest_nm_handler(struct ex_regs *regs) -{ - /* Check if #NM is triggered by XFEATURE_MASK_XTILE_DATA */ - GUEST_SYNC(7); GUEST_ASSERT(!(get_cr0() & X86_CR0_TS)); GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILE_DATA); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); - GUEST_SYNC(8); + GUEST_SYNC(TEST_SAVE_RESTORE); GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILE_DATA); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); /* Clear xfd_err */ wrmsr(MSR_IA32_XFD_ERR, 0); /* xfd=0, enable amx */ wrmsr(MSR_IA32_XFD, 0); - GUEST_SYNC(9); + GUEST_SYNC(TEST_SAVE_RESTORE); + + __tileloadd(tiledata); + GUEST_SYNC(TEST_COMPARE_TILEDATA | TEST_SAVE_RESTORE); + + GUEST_DONE(); } int main(int argc, char *argv[]) @@ -200,10 +234,10 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_x86_state *state; + struct kvm_x86_state *tile_state = NULL; int xsave_restore_size; - vm_vaddr_t amx_cfg, tiledata, xstate; + gva_t amx_cfg, tiledata, xstate; struct ucall uc; - u32 amx_offset; int ret; /* @@ -228,22 +262,20 @@ int main(int argc, char *argv[]) vcpu_regs_get(vcpu, ®s1); - /* Register #NM handler */ - vm_install_exception_handler(vm, NM_VECTOR, guest_nm_handler); - /* amx cfg for guest_code */ - amx_cfg = vm_vaddr_alloc_page(vm); + amx_cfg = vm_alloc_page(vm); memset(addr_gva2hva(vm, amx_cfg), 0x0, getpagesize()); /* amx tiledata for guest_code */ - tiledata = vm_vaddr_alloc_pages(vm, 2); + tiledata = vm_alloc_pages(vm, 2); memset(addr_gva2hva(vm, tiledata), rand() | 1, 2 * getpagesize()); /* XSAVE state for guest_code */ - xstate = vm_vaddr_alloc_pages(vm, DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE)); + xstate = vm_alloc_pages(vm, DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE)); memset(addr_gva2hva(vm, xstate), 0, PAGE_SIZE * DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE)); vcpu_args_set(vcpu, 3, amx_cfg, tiledata, xstate); + int iter = 0; for (;;) { vcpu_run(vcpu); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); @@ -253,37 +285,47 @@ int main(int argc, char *argv[]) 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]); + ++iter; + if (uc.args[1] & TEST_SAVE_TILEDATA) { + fprintf(stderr, "GUEST_SYNC #%d, save tiledata\n", iter); + tile_state = vcpu_save_state(vcpu); + } + if (uc.args[1] & TEST_COMPARE_TILEDATA) { + fprintf(stderr, "GUEST_SYNC #%d, check TMM0 contents\n", iter); /* 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; + u32 amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE; + void *amx_start = (void *)tile_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", ret); + } + if (uc.args[1] & TEST_RESTORE_TILEDATA) { + fprintf(stderr, "GUEST_SYNC #%d, before KVM_SET_XSAVE\n", iter); + vcpu_xsave_set(vcpu, tile_state->xsave); + fprintf(stderr, "GUEST_SYNC #%d, after KVM_SET_XSAVE\n", iter); + } + if (uc.args[1] & TEST_SAVE_RESTORE) { + fprintf(stderr, "GUEST_SYNC #%d, save/restore VM state\n", iter); + 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); kvm_x86_state_cleanup(state); - break; - case 9: - fprintf(stderr, - "GUEST_SYNC(%ld), #NM exception and enable amx\n", uc.args[1]); - break; + + 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); } break; case UCALL_DONE: @@ -293,22 +335,6 @@ int main(int argc, char *argv[]) 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); - 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/aperfmperf_test.c b/tools/testing/selftests/kvm/x86/aperfmperf_test.c new file mode 100644 index 000000000000..c91660103137 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/aperfmperf_test.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test for KVM_X86_DISABLE_EXITS_APERFMPERF + * + * Copyright (C) 2025, Google LLC. + * + * Test the ability to disable VM-exits for rdmsr of IA32_APERF and + * IA32_MPERF. When these VM-exits are disabled, reads of these MSRs + * return the host's values. + * + * Note: Requires read access to /dev/cpu/<lpu>/msr to read host MSRs. + */ + +#include <fcntl.h> +#include <limits.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdint.h> +#include <unistd.h> +#include <asm/msr-index.h> + +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "test_util.h" +#include "vmx.h" + +#define NUM_ITERATIONS 10000 + +static int open_dev_msr(int cpu) +{ + char path[PATH_MAX]; + + snprintf(path, sizeof(path), "/dev/cpu/%d/msr", cpu); + return open_path_or_exit(path, O_RDONLY); +} + +static u64 read_dev_msr(int msr_fd, u32 msr) +{ + u64 data; + ssize_t rc; + + rc = pread(msr_fd, &data, sizeof(data), msr); + TEST_ASSERT(rc == sizeof(data), "Read of MSR 0x%x failed", msr); + + return data; +} + +static void guest_read_aperf_mperf(void) +{ + int i; + + for (i = 0; i < NUM_ITERATIONS; i++) + GUEST_SYNC2(rdmsr(MSR_IA32_APERF), rdmsr(MSR_IA32_MPERF)); +} + +#define L2_GUEST_STACK_SIZE 64 + +static void l2_guest_code(void) +{ + guest_read_aperf_mperf(); + GUEST_DONE(); +} + +static void l1_svm_code(struct svm_test_data *svm) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + + generic_svm_setup(svm, l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + run_guest(vmcb, svm->vmcb_gpa); +} + +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]); + + /* + * Enable MSR bitmaps (the bitmap itself is allocated, zeroed, and set + * in the VMCS by prepare_vmcs()), as MSR exiting mandatory on Intel. + */ + vmwrite(CPU_BASED_VM_EXEC_CONTROL, + vmreadz(CPU_BASED_VM_EXEC_CONTROL) | CPU_BASED_USE_MSR_BITMAPS); + + GUEST_ASSERT(!vmwrite(GUEST_RIP, (u64)l2_guest_code)); + GUEST_ASSERT(!vmlaunch()); +} + +static void guest_code(void *nested_test_data) +{ + guest_read_aperf_mperf(); + + if (this_cpu_has(X86_FEATURE_SVM)) + l1_svm_code(nested_test_data); + else if (this_cpu_has(X86_FEATURE_VMX)) + l1_vmx_code(nested_test_data); + else + GUEST_DONE(); + + TEST_FAIL("L2 should have signaled 'done'"); +} + +static void guest_no_aperfmperf(void) +{ + u64 msr_val; + u8 vector; + + vector = rdmsr_safe(MSR_IA32_APERF, &msr_val); + GUEST_ASSERT(vector == GP_VECTOR); + + vector = rdmsr_safe(MSR_IA32_APERF, &msr_val); + GUEST_ASSERT(vector == GP_VECTOR); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + const bool has_nested = kvm_cpu_has(X86_FEATURE_SVM) || kvm_cpu_has(X86_FEATURE_VMX); + u64 host_aperf_before, host_mperf_before; + gva_t nested_test_data_gva; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + int msr_fd, cpu, i; + + /* Sanity check that APERF/MPERF are unsupported by default. */ + vm = vm_create_with_one_vcpu(&vcpu, guest_no_aperfmperf); + vcpu_run(vcpu); + TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); + kvm_vm_free(vm); + + cpu = pin_self_to_any_cpu(); + + msr_fd = open_dev_msr(cpu); + + /* + * This test requires a non-standard VM initialization, because + * KVM_ENABLE_CAP cannot be used on a VM file descriptor after + * a VCPU has been created. + */ + vm = vm_create(1); + + TEST_REQUIRE(vm_check_cap(vm, KVM_CAP_X86_DISABLE_EXITS) & + KVM_X86_DISABLE_EXITS_APERFMPERF); + + vm_enable_cap(vm, KVM_CAP_X86_DISABLE_EXITS, + KVM_X86_DISABLE_EXITS_APERFMPERF); + + vcpu = vm_vcpu_add(vm, 0, guest_code); + + if (!has_nested) + nested_test_data_gva = NONCANONICAL; + else 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); + + host_aperf_before = read_dev_msr(msr_fd, MSR_IA32_APERF); + host_mperf_before = read_dev_msr(msr_fd, MSR_IA32_MPERF); + + for (i = 0; i <= NUM_ITERATIONS * (1 + has_nested); i++) { + u64 host_aperf_after, host_mperf_after; + u64 guest_aperf, guest_mperf; + struct ucall uc; + + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_DONE: + goto done; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + case UCALL_SYNC: + guest_aperf = uc.args[0]; + guest_mperf = uc.args[1]; + + host_aperf_after = read_dev_msr(msr_fd, MSR_IA32_APERF); + host_mperf_after = read_dev_msr(msr_fd, MSR_IA32_MPERF); + + TEST_ASSERT(host_aperf_before < guest_aperf, + "APERF: host_before (0x%" PRIx64 ") >= guest (0x%" PRIx64 ")", + host_aperf_before, guest_aperf); + TEST_ASSERT(guest_aperf < host_aperf_after, + "APERF: guest (0x%" PRIx64 ") >= host_after (0x%" PRIx64 ")", + guest_aperf, host_aperf_after); + TEST_ASSERT(host_mperf_before < guest_mperf, + "MPERF: host_before (0x%" PRIx64 ") >= guest (0x%" PRIx64 ")", + host_mperf_before, guest_mperf); + TEST_ASSERT(guest_mperf < host_mperf_after, + "MPERF: guest (0x%" PRIx64 ") >= host_after (0x%" PRIx64 ")", + guest_mperf, host_mperf_after); + + host_aperf_before = host_aperf_after; + host_mperf_before = host_mperf_after; + + break; + } + } + TEST_FAIL("Didn't receive UCALL_DONE\n"); +done: + kvm_vm_free(vm); + close(msr_fd); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86/apic_bus_clock_test.c b/tools/testing/selftests/kvm/x86/apic_bus_clock_test.c index f8916bb34405..0c84c27ea584 100644 --- a/tools/testing/selftests/kvm/x86/apic_bus_clock_test.c +++ b/tools/testing/selftests/kvm/x86/apic_bus_clock_test.c @@ -19,8 +19,8 @@ * timer frequency. */ static const struct { - const uint32_t tdcr; - const uint32_t divide_count; + const u32 tdcr; + const u32 divide_count; } tdcrs[] = { {0x0, 2}, {0x1, 4}, @@ -42,12 +42,12 @@ static void apic_enable(void) xapic_enable(); } -static uint32_t apic_read_reg(unsigned int reg) +static u32 apic_read_reg(unsigned int reg) { return is_x2apic ? x2apic_read_reg(reg) : xapic_read_reg(reg); } -static void apic_write_reg(unsigned int reg, uint32_t val) +static void apic_write_reg(unsigned int reg, u32 val) { if (is_x2apic) x2apic_write_reg(reg, val); @@ -55,12 +55,12 @@ static void apic_write_reg(unsigned int reg, uint32_t val) xapic_write_reg(reg, val); } -static void apic_guest_code(uint64_t apic_hz, uint64_t delay_ms) +static void apic_guest_code(u64 apic_hz, u64 delay_ms) { - uint64_t tsc_hz = guest_tsc_khz * 1000; - const uint32_t tmict = ~0u; - uint64_t tsc0, tsc1, freq; - uint32_t tmcct; + u64 tsc_hz = guest_tsc_khz * 1000; + const u32 tmict = ~0u; + u64 tsc0, tsc1, freq; + u32 tmcct; int i; apic_enable(); @@ -121,7 +121,7 @@ static void test_apic_bus_clock(struct kvm_vcpu *vcpu) } } -static void run_apic_bus_clock_test(uint64_t apic_hz, uint64_t delay_ms, +static void run_apic_bus_clock_test(u64 apic_hz, u64 delay_ms, bool x2apic) { struct kvm_vcpu *vcpu; @@ -137,6 +137,10 @@ static void run_apic_bus_clock_test(uint64_t apic_hz, uint64_t delay_ms, vm_enable_cap(vm, KVM_CAP_X86_APIC_BUS_CYCLES_NS, NSEC_PER_SEC / apic_hz); + TEST_ASSERT_EQ(kvm_check_cap(KVM_CAP_X86_APIC_BUS_CYCLES_NS), 1); + TEST_ASSERT_EQ(vm_check_cap(vm, KVM_CAP_X86_APIC_BUS_CYCLES_NS), + NSEC_PER_SEC / apic_hz); + vcpu = vm_vcpu_add(vm, 0, apic_guest_code); vcpu_args_set(vcpu, 2, apic_hz, delay_ms); @@ -168,8 +172,8 @@ int main(int argc, char *argv[]) * Arbitrarilty default to 25MHz for the APIC bus frequency, which is * different enough from the default 1GHz to be interesting. */ - uint64_t apic_hz = 25 * 1000 * 1000; - uint64_t delay_ms = 100; + u64 apic_hz = 25 * 1000 * 1000; + u64 delay_ms = 100; int opt; TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_APIC_BUS_CYCLES_NS)); diff --git a/tools/testing/selftests/kvm/x86/cpuid_test.c b/tools/testing/selftests/kvm/x86/cpuid_test.c index 7b3fda6842bc..ef0ddd240887 100644 --- a/tools/testing/selftests/kvm/x86/cpuid_test.c +++ b/tools/testing/selftests/kvm/x86/cpuid_test.c @@ -140,10 +140,10 @@ static void run_vcpu(struct kvm_vcpu *vcpu, int stage) } } -struct kvm_cpuid2 *vcpu_alloc_cpuid(struct kvm_vm *vm, vm_vaddr_t *p_gva, struct kvm_cpuid2 *cpuid) +struct kvm_cpuid2 *vcpu_alloc_cpuid(struct kvm_vm *vm, gva_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); + gva_t gva = vm_alloc(vm, size, KVM_UTIL_MIN_VADDR); struct kvm_cpuid2 *guest_cpuids = addr_gva2hva(vm, gva); memcpy(guest_cpuids, cpuid, size); @@ -155,6 +155,7 @@ struct kvm_cpuid2 *vcpu_alloc_cpuid(struct kvm_vm *vm, vm_vaddr_t *p_gva, struct static void set_cpuid_after_run(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *ent; + struct kvm_sregs sregs; int rc; u32 eax, ebx, x; @@ -162,6 +163,20 @@ static void set_cpuid_after_run(struct kvm_vcpu *vcpu) rc = __vcpu_set_cpuid(vcpu); TEST_ASSERT(!rc, "Setting unmodified CPUID after KVM_RUN failed: %d", rc); + /* + * Toggle CR4 bits that affect dynamic CPUID feature flags to verify + * setting unmodified CPUID succeeds with runtime CPUID updates. + */ + vcpu_sregs_get(vcpu, &sregs); + if (kvm_cpu_has(X86_FEATURE_XSAVE)) + sregs.cr4 ^= X86_CR4_OSXSAVE; + if (kvm_cpu_has(X86_FEATURE_PKU)) + sregs.cr4 ^= X86_CR4_PKE; + vcpu_sregs_set(vcpu, &sregs); + + 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; @@ -202,7 +217,7 @@ static void test_get_cpuid2(struct kvm_vcpu *vcpu) int main(void) { struct kvm_vcpu *vcpu; - vm_vaddr_t cpuid_gva; + gva_t cpuid_gva; struct kvm_vm *vm; int stage; diff --git a/tools/testing/selftests/kvm/x86/debug_regs.c b/tools/testing/selftests/kvm/x86/debug_regs.c index 2d814c1d1dc4..0dfaf03cd0a0 100644 --- a/tools/testing/selftests/kvm/x86/debug_regs.c +++ b/tools/testing/selftests/kvm/x86/debug_regs.c @@ -16,7 +16,7 @@ #define IRQ_VECTOR 0xAA /* For testing data access debug BP */ -uint32_t guest_value; +u32 guest_value; extern unsigned char sw_bp, hw_bp, write_data, ss_start, bd_start; @@ -86,7 +86,7 @@ int main(void) struct kvm_run *run; struct kvm_vm *vm; struct ucall uc; - uint64_t cmd; + u64 cmd; int i; /* Instruction lengths starting at ss_start */ int ss_size[6] = { diff --git a/tools/testing/selftests/kvm/x86/dirty_log_page_splitting_test.c b/tools/testing/selftests/kvm/x86/dirty_log_page_splitting_test.c index 2929c067c207..388ba4101f97 100644 --- a/tools/testing/selftests/kvm/x86/dirty_log_page_splitting_test.c +++ b/tools/testing/selftests/kvm/x86/dirty_log_page_splitting_test.c @@ -23,7 +23,7 @@ #define SLOTS 2 #define ITERATIONS 2 -static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; +static u64 guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; static enum vm_mem_backing_src_type backing_src = VM_MEM_SRC_ANONYMOUS_HUGETLB; @@ -33,17 +33,17 @@ static int iteration; static int vcpu_last_completed_iteration[KVM_MAX_VCPUS]; struct kvm_page_stats { - uint64_t pages_4k; - uint64_t pages_2m; - uint64_t pages_1g; - uint64_t hugepages; + u64 pages_4k; + u64 pages_2m; + u64 pages_1g; + u64 hugepages; }; static void get_page_stats(struct kvm_vm *vm, struct kvm_page_stats *stats, const char *stage) { - stats->pages_4k = vm_get_stat(vm, "pages_4k"); - stats->pages_2m = vm_get_stat(vm, "pages_2m"); - stats->pages_1g = vm_get_stat(vm, "pages_1g"); + stats->pages_4k = vm_get_stat(vm, pages_4k); + stats->pages_2m = vm_get_stat(vm, pages_2m); + stats->pages_1g = vm_get_stat(vm, pages_1g); stats->hugepages = stats->pages_2m + stats->pages_1g; pr_debug("\nPage stats after %s: 4K: %ld 2M: %ld 1G: %ld huge: %ld\n", @@ -89,9 +89,9 @@ static void run_test(enum vm_guest_mode mode, void *unused) { struct kvm_vm *vm; unsigned long **bitmaps; - uint64_t guest_num_pages; - uint64_t host_num_pages; - uint64_t pages_per_slot; + u64 guest_num_pages; + u64 host_num_pages; + u64 pages_per_slot; int i; struct kvm_page_stats stats_populated; struct kvm_page_stats stats_dirty_logging_enabled; diff --git a/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c b/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c new file mode 100644 index 000000000000..5b3aef109cfc --- /dev/null +++ b/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2026, Red Hat, Inc. + * + * Test that vmx_leave_smm() validates vmcs12 controls before re-entering + * nested guest mode on RSM. + */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "smm.h" +#include "hyperv.h" +#include "vmx.h" + +#define SMRAM_GPA 0x1000000 +#define SMRAM_STAGE 0xfe + +#define SYNC_PORT 0xe + +#define STR(x) #x +#define XSTR(s) STR(s) + +/* + * SMI handler: runs in real-address mode. + * Reports SMRAM_STAGE via port IO, then does RSM. + */ +static u8 smi_handler[] = { + 0xb0, SMRAM_STAGE, /* mov $SMRAM_STAGE, %al */ + 0xe4, SYNC_PORT, /* in $SYNC_PORT, %al */ + 0x0f, 0xaa, /* rsm */ +}; + +static inline void sync_with_host(u64 phase) +{ + asm volatile("in $" XSTR(SYNC_PORT) ", %%al \n" + : "+a" (phase)); +} + +static void l2_guest_code(void) +{ + sync_with_host(1); + + /* After SMI+RSM with invalid controls, we should not reach here. */ + vmcall(); +} + +static void guest_code(struct vmx_pages *vmx_pages, + struct hyperv_test_pages *hv_pages) +{ +#define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + /* Set up Hyper-V enlightenments and eVMCS */ + wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); + enable_vp_assist(hv_pages->vp_assist_gpa, hv_pages->vp_assist); + evmcs_enable(); + + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + GUEST_ASSERT(load_evmcs(hv_pages)); + prepare_vmcs(vmx_pages, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + GUEST_ASSERT(!vmlaunch()); + + /* L2 exits via vmcall if test fails */ + sync_with_host(2); +} + +int main(int argc, char *argv[]) +{ + gva_t vmx_pages_gva = 0, hv_pages_gva = 0; + struct hyperv_test_pages *hv; + struct hv_enlightened_vmcs *evmcs; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct kvm_regs regs; + int stage_reported; + + 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)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_SMM)); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + setup_smram(vm, vcpu, SMRAM_GPA, smi_handler, sizeof(smi_handler)); + + vcpu_set_hv_cpuid(vcpu); + vcpu_enable_evmcs(vcpu); + vcpu_alloc_vmx(vm, &vmx_pages_gva); + hv = vcpu_alloc_hyperv_test_pages(vm, &hv_pages_gva); + vcpu_args_set(vcpu, 2, vmx_pages_gva, hv_pages_gva); + + vcpu_run(vcpu); + + /* L2 is running and syncs with host. */ + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + vcpu_regs_get(vcpu, ®s); + stage_reported = regs.rax & 0xff; + TEST_ASSERT(stage_reported == 1, + "Expected stage 1, got %d", stage_reported); + + /* Inject SMI while L2 is running. */ + inject_smi(vcpu); + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + vcpu_regs_get(vcpu, ®s); + stage_reported = regs.rax & 0xff; + TEST_ASSERT(stage_reported == SMRAM_STAGE, + "Expected SMM handler stage %#x, got %#x", + SMRAM_STAGE, stage_reported); + + /* + * Guest is now paused in the SMI handler, about to execute RSM. + * Hack the eVMCS page to set-up invalid pin-based execution + * control (PIN_BASED_VIRTUAL_NMIS without PIN_BASED_NMI_EXITING). + */ + evmcs = hv->enlightened_vmcs_hva; + evmcs->pin_based_vm_exec_control |= PIN_BASED_VIRTUAL_NMIS; + evmcs->hv_clean_fields = 0; + + /* + * Trigger copy_enlightened_to_vmcs12() via KVM_GET_NESTED_STATE, + * copying the invalid pin_based_vm_exec_control into cached_vmcs12. + */ + union { + struct kvm_nested_state state; + char state_[16384]; + } nested_state_buf; + + memset(&nested_state_buf, 0, sizeof(nested_state_buf)); + nested_state_buf.state.size = sizeof(nested_state_buf); + vcpu_nested_state_get(vcpu, &nested_state_buf.state); + + /* + * Resume the guest. The SMI handler executes RSM, which calls + * vmx_leave_smm(). nested_vmx_check_controls() should detect + * VIRTUAL_NMIS without NMI_EXITING and cause a triple fault. + */ + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_SHUTDOWN); + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86/fastops_test.c b/tools/testing/selftests/kvm/x86/fastops_test.c new file mode 100644 index 000000000000..c0d30ccd8767 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/fastops_test.c @@ -0,0 +1,209 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +/* + * Execute a fastop() instruction, with or without forced emulation. BT bit 0 + * to set RFLAGS.CF based on whether or not the input is even or odd, so that + * instructions like ADC and SBB are deterministic. + */ +#define fastop(__insn) \ + "bt $0, %[bt_val]\n\t" \ + __insn "\n\t" \ + "pushfq\n\t" \ + "pop %[flags]\n\t" + +#define flags_constraint(flags_val) [flags]"=r"(flags_val) +#define bt_constraint(__bt_val) [bt_val]"rm"((u32)__bt_val) + +#define guest_execute_fastop_1(FEP, insn, __val, __flags) \ +({ \ + __asm__ __volatile__(fastop(FEP insn " %[val]") \ + : [val]"+r"(__val), flags_constraint(__flags) \ + : bt_constraint(__val) \ + : "cc", "memory"); \ +}) + +#define guest_test_fastop_1(insn, type_t, __val) \ +({ \ + type_t val = __val, ex_val = __val, input = __val; \ + u64 flags, ex_flags; \ + \ + guest_execute_fastop_1("", insn, ex_val, ex_flags); \ + guest_execute_fastop_1(KVM_FEP, insn, val, flags); \ + \ + __GUEST_ASSERT(val == ex_val, \ + "Wanted 0x%lx for '%s 0x%lx', got 0x%lx", \ + (u64)ex_val, insn, (u64)input, (u64)val); \ + __GUEST_ASSERT(flags == ex_flags, \ + "Wanted flags 0x%lx for '%s 0x%lx', got 0x%lx", \ + ex_flags, insn, (u64)input, flags); \ +}) + +#define guest_execute_fastop_2(FEP, insn, __input, __output, __flags) \ +({ \ + __asm__ __volatile__(fastop(FEP insn " %[input], %[output]") \ + : [output]"+r"(__output), flags_constraint(__flags) \ + : [input]"r"(__input), bt_constraint(__output) \ + : "cc", "memory"); \ +}) + +#define guest_test_fastop_2(insn, type_t, __val1, __val2) \ +({ \ + type_t input = __val1, input2 = __val2, output = __val2, ex_output = __val2; \ + u64 flags, ex_flags; \ + \ + guest_execute_fastop_2("", insn, input, ex_output, ex_flags); \ + guest_execute_fastop_2(KVM_FEP, insn, input, output, flags); \ + \ + __GUEST_ASSERT(output == ex_output, \ + "Wanted 0x%lx for '%s 0x%lx 0x%lx', got 0x%lx", \ + (u64)ex_output, insn, (u64)input, \ + (u64)input2, (u64)output); \ + __GUEST_ASSERT(flags == ex_flags, \ + "Wanted flags 0x%lx for '%s 0x%lx, 0x%lx', got 0x%lx", \ + ex_flags, insn, (u64)input, (u64)input2, flags); \ +}) + +#define guest_execute_fastop_cl(FEP, insn, __shift, __output, __flags) \ +({ \ + __asm__ __volatile__(fastop(FEP insn " %%cl, %[output]") \ + : [output]"+r"(__output), flags_constraint(__flags) \ + : "c"(__shift), bt_constraint(__output) \ + : "cc", "memory"); \ +}) + +#define guest_test_fastop_cl(insn, type_t, __val1, __val2) \ +({ \ + type_t output = __val2, ex_output = __val2, input = __val2; \ + u8 shift = __val1; \ + u64 flags, ex_flags; \ + \ + guest_execute_fastop_cl("", insn, shift, ex_output, ex_flags); \ + guest_execute_fastop_cl(KVM_FEP, insn, shift, output, flags); \ + \ + __GUEST_ASSERT(output == ex_output, \ + "Wanted 0x%lx for '%s 0x%x, 0x%lx', got 0x%lx", \ + (u64)ex_output, insn, shift, (u64)input, \ + (u64)output); \ + __GUEST_ASSERT(flags == ex_flags, \ + "Wanted flags 0x%lx for '%s 0x%x, 0x%lx', got 0x%lx", \ + ex_flags, insn, shift, (u64)input, flags); \ +}) + +#define guest_execute_fastop_div(__KVM_ASM_SAFE, insn, __a, __d, __rm, __flags) \ +({ \ + u64 ign_error_code; \ + u8 vector; \ + \ + __asm__ __volatile__(fastop(__KVM_ASM_SAFE(insn " %[denom]")) \ + : "+a"(__a), "+d"(__d), flags_constraint(__flags), \ + KVM_ASM_SAFE_OUTPUTS(vector, ign_error_code) \ + : [denom]"rm"(__rm), bt_constraint(__rm) \ + : "cc", "memory", KVM_ASM_SAFE_CLOBBERS); \ + vector; \ +}) + +#define guest_test_fastop_div(insn, type_t, __val1, __val2) \ +({ \ + type_t _a = __val1, _d = __val1, rm = __val2; \ + type_t a = _a, d = _d, ex_a = _a, ex_d = _d; \ + u64 flags, ex_flags; \ + u8 v, ex_v; \ + \ + ex_v = guest_execute_fastop_div(KVM_ASM_SAFE, insn, ex_a, ex_d, rm, ex_flags); \ + v = guest_execute_fastop_div(KVM_ASM_SAFE_FEP, insn, a, d, rm, flags); \ + \ + GUEST_ASSERT_EQ(v, ex_v); \ + __GUEST_ASSERT(v == ex_v, \ + "Wanted vector 0x%x for '%s 0x%lx:0x%lx/0x%lx', got 0x%x", \ + ex_v, insn, (u64)_a, (u64)_d, (u64)rm, v); \ + __GUEST_ASSERT(a == ex_a && d == ex_d, \ + "Wanted 0x%lx:0x%lx for '%s 0x%lx:0x%lx/0x%lx', got 0x%lx:0x%lx",\ + (u64)ex_a, (u64)ex_d, insn, (u64)_a, \ + (u64)_d, (u64)rm, (u64)a, (u64)d); \ + __GUEST_ASSERT(v || ex_v || (flags == ex_flags), \ + "Wanted flags 0x%lx for '%s 0x%lx:0x%lx/0x%lx', got 0x%lx", \ + ex_flags, insn, (u64)_a, (u64)_d, (u64)rm, flags);\ +}) + +static const u64 vals[] = { + 0, + 1, + 2, + 4, + 7, + 0x5555555555555555, + 0xaaaaaaaaaaaaaaaa, + 0xfefefefefefefefe, + 0xffffffffffffffff, +}; + +#define guest_test_fastops(type_t, suffix) \ +do { \ + int i, j; \ + \ + for (i = 0; i < ARRAY_SIZE(vals); i++) { \ + guest_test_fastop_1("dec" suffix, type_t, vals[i]); \ + guest_test_fastop_1("inc" suffix, type_t, vals[i]); \ + guest_test_fastop_1("neg" suffix, type_t, vals[i]); \ + guest_test_fastop_1("not" suffix, type_t, vals[i]); \ + \ + for (j = 0; j < ARRAY_SIZE(vals); j++) { \ + guest_test_fastop_2("add" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_2("adc" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_2("and" suffix, type_t, vals[i], vals[j]); \ +if (sizeof(type_t) != 1) { \ + guest_test_fastop_2("bsf" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_2("bsr" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_2("bt" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_2("btc" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_2("btr" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_2("bts" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_2("imul" suffix, type_t, vals[i], vals[j]); \ +} \ + guest_test_fastop_2("cmp" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_2("or" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_2("sbb" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_2("sub" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_2("test" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_2("xor" suffix, type_t, vals[i], vals[j]); \ + \ + guest_test_fastop_cl("rol" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_cl("ror" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_cl("rcl" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_cl("rcr" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_cl("sar" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_cl("shl" suffix, type_t, vals[i], vals[j]); \ + guest_test_fastop_cl("shr" suffix, type_t, vals[i], vals[j]); \ + \ + guest_test_fastop_div("div" suffix, type_t, vals[i], vals[j]); \ + } \ + } \ +} while (0) + +static void guest_code(void) +{ + guest_test_fastops(u8, "b"); + guest_test_fastops(u16, "w"); + guest_test_fastops(u32, "l"); + guest_test_fastops(u64, "q"); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + TEST_REQUIRE(is_forced_emulation_enabled); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + vcpu_run(vcpu); + TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); + + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86/feature_msrs_test.c b/tools/testing/selftests/kvm/x86/feature_msrs_test.c index a72f13ae2edb..158550701771 100644 --- a/tools/testing/selftests/kvm/x86/feature_msrs_test.c +++ b/tools/testing/selftests/kvm/x86/feature_msrs_test.c @@ -12,7 +12,7 @@ #include "kvm_util.h" #include "processor.h" -static bool is_kvm_controlled_msr(uint32_t msr) +static bool is_kvm_controlled_msr(u32 msr) { return msr == MSR_IA32_VMX_CR0_FIXED1 || msr == MSR_IA32_VMX_CR4_FIXED1; } @@ -21,7 +21,7 @@ static bool is_kvm_controlled_msr(uint32_t msr) * For VMX MSRs with a "true" variant, KVM requires userspace to set the "true" * MSR, and doesn't allow setting the hidden version. */ -static bool is_hidden_vmx_msr(uint32_t msr) +static bool is_hidden_vmx_msr(u32 msr) { switch (msr) { case MSR_IA32_VMX_PINBASED_CTLS: @@ -34,15 +34,15 @@ static bool is_hidden_vmx_msr(uint32_t msr) } } -static bool is_quirked_msr(uint32_t msr) +static bool is_quirked_msr(u32 msr) { return msr != MSR_AMD64_DE_CFG; } -static void test_feature_msr(uint32_t msr) +static void test_feature_msr(u32 msr) { - const uint64_t supported_mask = kvm_get_feature_msr(msr); - uint64_t reset_value = is_quirked_msr(msr) ? supported_mask : 0; + const u64 supported_mask = kvm_get_feature_msr(msr); + u64 reset_value = is_quirked_msr(msr) ? supported_mask : 0; struct kvm_vcpu *vcpu; struct kvm_vm *vm; diff --git a/tools/testing/selftests/kvm/x86/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86/fix_hypercall_test.c index 762628f7d4ba..753a0e730ea8 100644 --- a/tools/testing/selftests/kvm/x86/fix_hypercall_test.c +++ b/tools/testing/selftests/kvm/x86/fix_hypercall_test.c @@ -26,18 +26,18 @@ static void guest_ud_handler(struct ex_regs *regs) 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 }; +static const u8 vmx_vmcall[HYPERCALL_INSN_SIZE] = { 0x0f, 0x01, 0xc1 }; +static const u8 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) +extern u8 hypercall_insn[HYPERCALL_INSN_SIZE]; +static u64 do_sched_yield(u8 apic_id) { - uint64_t ret; + u64 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) + : "a"((u64)KVM_HC_SCHED_YIELD), "b"((u64)apic_id) : "memory"); return ret; @@ -45,14 +45,14 @@ static uint64_t do_sched_yield(uint8_t apic_id) static void guest_main(void) { - const uint8_t *native_hypercall_insn; - const uint8_t *other_hypercall_insn; - uint64_t ret; + const u8 *native_hypercall_insn; + const u8 *other_hypercall_insn; + u64 ret; if (host_cpu_is_intel) { native_hypercall_insn = vmx_vmcall; other_hypercall_insn = svm_vmmcall; - } else if (host_cpu_is_amd) { + } else if (host_cpu_is_amd_compatible) { native_hypercall_insn = svm_vmmcall; other_hypercall_insn = vmx_vmcall; } else { @@ -72,7 +72,7 @@ static void guest_main(void) * the "right" hypercall. */ if (quirk_disabled) { - GUEST_ASSERT(ret == (uint64_t)-EFAULT); + GUEST_ASSERT(ret == (u64)-EFAULT); GUEST_ASSERT(!memcmp(other_hypercall_insn, hypercall_insn, HYPERCALL_INSN_SIZE)); } else { diff --git a/tools/testing/selftests/kvm/x86/flds_emulation.h b/tools/testing/selftests/kvm/x86/flds_emulation.h index 37b1a9f52864..fd6b6c67199a 100644 --- a/tools/testing/selftests/kvm/x86/flds_emulation.h +++ b/tools/testing/selftests/kvm/x86/flds_emulation.h @@ -12,7 +12,7 @@ * KVM to emulate the instruction (e.g. by providing an MMIO address) to * exercise emulation failures. */ -static inline void flds(uint64_t address) +static inline void flds(u64 address) { __asm__ __volatile__(FLDS_MEM_EAX :: "a"(address)); } @@ -21,8 +21,8 @@ static inline void handle_flds_emulation_failure_exit(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; struct kvm_regs regs; - uint8_t *insn_bytes; - uint64_t flags; + u8 *insn_bytes; + u64 flags; TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_INTERNAL_ERROR); diff --git a/tools/testing/selftests/kvm/x86/hwcr_msr_test.c b/tools/testing/selftests/kvm/x86/hwcr_msr_test.c index 10b1b0ba374e..8e20a03b3329 100644 --- a/tools/testing/selftests/kvm/x86/hwcr_msr_test.c +++ b/tools/testing/selftests/kvm/x86/hwcr_msr_test.c @@ -10,11 +10,11 @@ void test_hwcr_bit(struct kvm_vcpu *vcpu, unsigned int bit) { - const uint64_t ignored = BIT_ULL(3) | BIT_ULL(6) | BIT_ULL(8); - const uint64_t valid = BIT_ULL(18) | BIT_ULL(24); - const uint64_t legal = ignored | valid; - uint64_t val = BIT_ULL(bit); - uint64_t actual; + const u64 ignored = BIT_ULL(3) | BIT_ULL(6) | BIT_ULL(8); + const u64 valid = BIT_ULL(18) | BIT_ULL(24); + const u64 legal = ignored | valid; + u64 val = BIT_ULL(bit); + u64 actual; int r; r = _vcpu_set_msr(vcpu, MSR_K7_HWCR, val); diff --git a/tools/testing/selftests/kvm/x86/hyperv_clock.c b/tools/testing/selftests/kvm/x86/hyperv_clock.c index e058bc676cd6..c083cea546dc 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_clock.c +++ b/tools/testing/selftests/kvm/x86/hyperv_clock.c @@ -98,7 +98,7 @@ static inline void check_tsc_msr_tsc_page(struct ms_hyperv_tsc_page *tsc_page) GUEST_ASSERT(r2 >= t1 && r2 - t2 < 100000); } -static void guest_main(struct ms_hyperv_tsc_page *tsc_page, vm_paddr_t tsc_page_gpa) +static void guest_main(struct ms_hyperv_tsc_page *tsc_page, gpa_t tsc_page_gpa) { u64 tsc_scale, tsc_offset; @@ -208,7 +208,7 @@ int main(void) struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct ucall uc; - vm_vaddr_t tsc_page_gva; + gva_t tsc_page_gva; int stage; TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_TIME)); @@ -218,7 +218,7 @@ int main(void) vcpu_set_hv_cpuid(vcpu); - tsc_page_gva = vm_vaddr_alloc_page(vm); + tsc_page_gva = vm_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"); diff --git a/tools/testing/selftests/kvm/x86/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86/hyperv_cpuid.c index 4e920705681a..3c21af811d8f 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86/hyperv_cpuid.c @@ -22,25 +22,6 @@ static void guest_code(void) { } -static bool smt_possible(void) -{ - char buf[16]; - FILE *f; - bool res = true; - - f = fopen("/sys/devices/system/cpu/smt/control", "r"); - if (f) { - if (fread(buf, sizeof(*buf), sizeof(buf), f) > 0) { - if (!strncmp(buf, "forceoff", 8) || - !strncmp(buf, "notsupported", 12)) - res = false; - } - fclose(f); - } - - return res; -} - static void test_hv_cpuid(struct kvm_vcpu *vcpu, bool evmcs_expected) { const bool has_irqchip = !vcpu || vcpu->vm->has_irqchip; @@ -64,7 +45,7 @@ static void test_hv_cpuid(struct kvm_vcpu *vcpu, bool evmcs_expected) TEST_ASSERT((entry->function >= 0x40000000) && (entry->function <= 0x40000082), - "function %x is our of supported range", + "function %x is out of supported range", entry->function); TEST_ASSERT(entry->index == 0, @@ -93,7 +74,7 @@ static void test_hv_cpuid(struct kvm_vcpu *vcpu, bool evmcs_expected) case 0x40000004: test_val = entry->eax & (1UL << 18); - TEST_ASSERT(!!test_val == !smt_possible(), + TEST_ASSERT(!!test_val == !is_smt_possible(), "NoNonArchitecturalCoreSharing bit" " doesn't reflect SMT setting"); diff --git a/tools/testing/selftests/kvm/x86/hyperv_evmcs.c b/tools/testing/selftests/kvm/x86/hyperv_evmcs.c index 74cf19661309..c7fa114aee20 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_evmcs.c +++ b/tools/testing/selftests/kvm/x86/hyperv_evmcs.c @@ -30,7 +30,7 @@ static void guest_nmi_handler(struct ex_regs *regs) { } -static inline void rdmsr_from_l2(uint32_t msr) +static inline void rdmsr_from_l2(u32 msr) { /* Currently, L1 doesn't preserve GPRs during vmexits. */ __asm__ __volatile__ ("rdmsr" : : "c"(msr) : @@ -76,7 +76,7 @@ void l2_guest_code(void) } void guest_code(struct vmx_pages *vmx_pages, struct hyperv_test_pages *hv_pages, - vm_vaddr_t hv_hcall_page_gpa) + gpa_t hv_hcall_page_gpa) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; @@ -231,8 +231,8 @@ static struct kvm_vcpu *save_restore_vm(struct kvm_vm *vm, int main(int argc, char *argv[]) { - vm_vaddr_t vmx_pages_gva = 0, hv_pages_gva = 0; - vm_vaddr_t hcall_page; + gva_t vmx_pages_gva = 0, hv_pages_gva = 0; + gva_t hcall_page; struct kvm_vcpu *vcpu; struct kvm_vm *vm; @@ -246,7 +246,7 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu, guest_code); - hcall_page = vm_vaddr_alloc_pages(vm, 1); + hcall_page = vm_alloc_pages(vm, 1); memset(addr_gva2hva(vm, hcall_page), 0x0, getpagesize()); vcpu_set_hv_cpuid(vcpu); diff --git a/tools/testing/selftests/kvm/x86/hyperv_extended_hypercalls.c b/tools/testing/selftests/kvm/x86/hyperv_extended_hypercalls.c index 949e08e98f31..ae047db7b1be 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_extended_hypercalls.c +++ b/tools/testing/selftests/kvm/x86/hyperv_extended_hypercalls.c @@ -15,19 +15,19 @@ /* Any value is fine */ #define EXT_CAPABILITIES 0xbull -static void guest_code(vm_paddr_t in_pg_gpa, vm_paddr_t out_pg_gpa, - vm_vaddr_t out_pg_gva) +static void guest_code(gpa_t in_pg_gpa, gpa_t out_pg_gpa, + gva_t out_pg_gva) { - uint64_t *output_gva; + u64 *output_gva; wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); wrmsr(HV_X64_MSR_HYPERCALL, in_pg_gpa); - output_gva = (uint64_t *)out_pg_gva; + output_gva = (u64 *)out_pg_gva; hyperv_hypercall(HV_EXT_CALL_QUERY_CAPABILITIES, in_pg_gpa, out_pg_gpa); - /* TLFS states output will be a uint64_t value */ + /* TLFS states output will be a u64 value */ GUEST_ASSERT_EQ(*output_gva, EXT_CAPABILITIES); GUEST_DONE(); @@ -35,12 +35,12 @@ static void guest_code(vm_paddr_t in_pg_gpa, vm_paddr_t out_pg_gpa, int main(void) { - vm_vaddr_t hcall_out_page; - vm_vaddr_t hcall_in_page; + gva_t hcall_out_page; + gva_t hcall_in_page; struct kvm_vcpu *vcpu; struct kvm_run *run; struct kvm_vm *vm; - uint64_t *outval; + u64 *outval; struct ucall uc; TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_CPUID)); @@ -57,11 +57,11 @@ int main(void) vcpu_set_hv_cpuid(vcpu); /* Hypercall input */ - hcall_in_page = vm_vaddr_alloc_pages(vm, 1); + hcall_in_page = vm_alloc_pages(vm, 1); memset(addr_gva2hva(vm, hcall_in_page), 0x0, vm->page_size); /* Hypercall output */ - hcall_out_page = vm_vaddr_alloc_pages(vm, 1); + hcall_out_page = vm_alloc_pages(vm, 1); memset(addr_gva2hva(vm, hcall_out_page), 0x0, vm->page_size); vcpu_args_set(vcpu, 3, addr_gva2gpa(vm, hcall_in_page), diff --git a/tools/testing/selftests/kvm/x86/hyperv_features.c b/tools/testing/selftests/kvm/x86/hyperv_features.c index 068e9c69710d..7347f1fe5157 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86/hyperv_features.c @@ -22,27 +22,27 @@ KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EBX, 0) struct msr_data { - uint32_t idx; + u32 idx; bool fault_expected; bool write; u64 write_val; }; struct hcall_data { - uint64_t control; - uint64_t expect; + u64 control; + u64 expect; bool ud_expected; }; -static bool is_write_only_msr(uint32_t msr) +static bool is_write_only_msr(u32 msr) { return msr == HV_X64_MSR_EOI; } static void guest_msr(struct msr_data *msr) { - uint8_t vector = 0; - uint64_t msr_val = 0; + u8 vector = 0; + u64 msr_val = 0; GUEST_ASSERT(msr->idx); @@ -54,12 +54,12 @@ static void guest_msr(struct msr_data *msr) if (msr->fault_expected) __GUEST_ASSERT(vector == GP_VECTOR, - "Expected #GP on %sMSR(0x%x), got vector '0x%x'", - msr->write ? "WR" : "RD", msr->idx, vector); + "Expected #GP on %sMSR(0x%x), got %s", + msr->write ? "WR" : "RD", msr->idx, ex_str(vector)); else __GUEST_ASSERT(!vector, - "Expected success on %sMSR(0x%x), got vector '0x%x'", - msr->write ? "WR" : "RD", msr->idx, vector); + "Expected success on %sMSR(0x%x), got %s", + msr->write ? "WR" : "RD", msr->idx, ex_str(vector)); if (vector || is_write_only_msr(msr->idx)) goto done; @@ -82,10 +82,10 @@ done: GUEST_DONE(); } -static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall) +static void guest_hcall(gpa_t pgs_gpa, struct hcall_data *hcall) { u64 res, input, output; - uint8_t vector; + u8 vector; GUEST_ASSERT_NE(hcall->control, 0); @@ -94,7 +94,7 @@ static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall) if (!(hcall->control & HV_HYPERCALL_FAST_BIT)) { input = pgs_gpa; - output = pgs_gpa + 4096; + output = pgs_gpa + PAGE_SIZE; } else { input = output = 0; } @@ -102,12 +102,12 @@ static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall) vector = __hyperv_hypercall(hcall->control, input, output, &res); if (hcall->ud_expected) { __GUEST_ASSERT(vector == UD_VECTOR, - "Expected #UD for control '%lu', got vector '0x%x'", - hcall->control, vector); + "Expected #UD for control '%lu', got %s", + hcall->control, ex_str(vector)); } else { __GUEST_ASSERT(!vector, - "Expected no exception for control '%lu', got vector '0x%x'", - hcall->control, vector); + "Expected no exception for control '%lu', got %s", + hcall->control, ex_str(vector)); GUEST_ASSERT_EQ(res, hcall->expect); } @@ -134,14 +134,14 @@ static void guest_test_msrs_access(void) struct kvm_vm *vm; struct ucall uc; int stage = 0; - vm_vaddr_t msr_gva; + gva_t msr_gva; struct msr_data *msr; bool has_invtsc = kvm_cpu_has(X86_FEATURE_INVTSC); while (true) { vm = vm_create_with_one_vcpu(&vcpu, guest_msr); - msr_gva = vm_vaddr_alloc_page(vm); + msr_gva = vm_alloc_page(vm); memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize()); msr = addr_gva2hva(vm, msr_gva); @@ -523,17 +523,17 @@ static void guest_test_hcalls_access(void) struct kvm_vm *vm; struct ucall uc; int stage = 0; - vm_vaddr_t hcall_page, hcall_params; + gva_t hcall_page, hcall_params; struct hcall_data *hcall; while (true) { vm = vm_create_with_one_vcpu(&vcpu, guest_hcall); /* Hypercall input/output */ - hcall_page = vm_vaddr_alloc_pages(vm, 2); + hcall_page = vm_alloc_pages(vm, 2); memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); - hcall_params = vm_vaddr_alloc_page(vm); + hcall_params = vm_alloc_page(vm); memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize()); hcall = addr_gva2hva(vm, hcall_params); diff --git a/tools/testing/selftests/kvm/x86/hyperv_ipi.c b/tools/testing/selftests/kvm/x86/hyperv_ipi.c index 22c0c124582f..771535f9aad3 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_ipi.c +++ b/tools/testing/selftests/kvm/x86/hyperv_ipi.c @@ -18,7 +18,7 @@ #define IPI_VECTOR 0xfe -static volatile uint64_t ipis_rcvd[RECEIVER_VCPU_ID_2 + 1]; +static volatile u64 ipis_rcvd[RECEIVER_VCPU_ID_2 + 1]; struct hv_vpset { u64 format; @@ -45,13 +45,13 @@ struct hv_send_ipi_ex { struct hv_vpset vp_set; }; -static inline void hv_init(vm_vaddr_t pgs_gpa) +static inline void hv_init(gpa_t pgs_gpa) { wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa); } -static void receiver_code(void *hcall_page, vm_vaddr_t pgs_gpa) +static void receiver_code(void *hcall_page, gpa_t pgs_gpa) { u32 vcpu_id; @@ -63,8 +63,10 @@ static void receiver_code(void *hcall_page, vm_vaddr_t pgs_gpa) /* Signal sender vCPU we're ready */ ipis_rcvd[vcpu_id] = (u64)-1; - for (;;) - asm volatile("sti; hlt; cli"); + for (;;) { + safe_halt(); + cli(); + } } static void guest_ipi_handler(struct ex_regs *regs) @@ -83,7 +85,7 @@ static inline void nop_loop(void) asm volatile("nop"); } -static void sender_guest_code(void *hcall_page, vm_vaddr_t pgs_gpa) +static void sender_guest_code(void *hcall_page, gpa_t pgs_gpa) { struct hv_send_ipi *ipi = (struct hv_send_ipi *)hcall_page; struct hv_send_ipi_ex *ipi_ex = (struct hv_send_ipi_ex *)hcall_page; @@ -100,7 +102,7 @@ static void sender_guest_code(void *hcall_page, vm_vaddr_t pgs_gpa) /* 'Slow' HvCallSendSyntheticClusterIpi to RECEIVER_VCPU_ID_1 */ ipi->vector = IPI_VECTOR; ipi->cpu_mask = 1 << RECEIVER_VCPU_ID_1; - hyperv_hypercall(HVCALL_SEND_IPI, pgs_gpa, pgs_gpa + 4096); + hyperv_hypercall(HVCALL_SEND_IPI, pgs_gpa, pgs_gpa + PAGE_SIZE); nop_loop(); GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]); GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ipis_expected[1]); @@ -114,13 +116,13 @@ static void sender_guest_code(void *hcall_page, vm_vaddr_t pgs_gpa) GUEST_SYNC(stage++); /* 'Slow' HvCallSendSyntheticClusterIpiEx to RECEIVER_VCPU_ID_1 */ - memset(hcall_page, 0, 4096); + memset(hcall_page, 0, PAGE_SIZE); ipi_ex->vector = IPI_VECTOR; ipi_ex->vp_set.format = HV_GENERIC_SET_SPARSE_4K; ipi_ex->vp_set.valid_bank_mask = 1 << 0; ipi_ex->vp_set.bank_contents[0] = BIT(RECEIVER_VCPU_ID_1); hyperv_hypercall(HVCALL_SEND_IPI_EX | (1 << HV_HYPERCALL_VARHEAD_OFFSET), - pgs_gpa, pgs_gpa + 4096); + pgs_gpa, pgs_gpa + PAGE_SIZE); nop_loop(); GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]); GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ipis_expected[1]); @@ -136,13 +138,13 @@ static void sender_guest_code(void *hcall_page, vm_vaddr_t pgs_gpa) GUEST_SYNC(stage++); /* 'Slow' HvCallSendSyntheticClusterIpiEx to RECEIVER_VCPU_ID_2 */ - memset(hcall_page, 0, 4096); + memset(hcall_page, 0, PAGE_SIZE); ipi_ex->vector = IPI_VECTOR; ipi_ex->vp_set.format = HV_GENERIC_SET_SPARSE_4K; ipi_ex->vp_set.valid_bank_mask = 1 << 1; ipi_ex->vp_set.bank_contents[0] = BIT(RECEIVER_VCPU_ID_2 - 64); hyperv_hypercall(HVCALL_SEND_IPI_EX | (1 << HV_HYPERCALL_VARHEAD_OFFSET), - pgs_gpa, pgs_gpa + 4096); + pgs_gpa, pgs_gpa + PAGE_SIZE); nop_loop(); GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ipis_expected[0]); GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]); @@ -158,14 +160,14 @@ static void sender_guest_code(void *hcall_page, vm_vaddr_t pgs_gpa) GUEST_SYNC(stage++); /* 'Slow' HvCallSendSyntheticClusterIpiEx to both RECEIVER_VCPU_ID_{1,2} */ - memset(hcall_page, 0, 4096); + memset(hcall_page, 0, PAGE_SIZE); ipi_ex->vector = IPI_VECTOR; ipi_ex->vp_set.format = HV_GENERIC_SET_SPARSE_4K; ipi_ex->vp_set.valid_bank_mask = 1 << 1 | 1; ipi_ex->vp_set.bank_contents[0] = BIT(RECEIVER_VCPU_ID_1); ipi_ex->vp_set.bank_contents[1] = BIT(RECEIVER_VCPU_ID_2 - 64); hyperv_hypercall(HVCALL_SEND_IPI_EX | (2 << HV_HYPERCALL_VARHEAD_OFFSET), - pgs_gpa, pgs_gpa + 4096); + pgs_gpa, pgs_gpa + PAGE_SIZE); nop_loop(); GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]); GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]); @@ -181,10 +183,10 @@ static void sender_guest_code(void *hcall_page, vm_vaddr_t pgs_gpa) GUEST_SYNC(stage++); /* 'Slow' HvCallSendSyntheticClusterIpiEx to HV_GENERIC_SET_ALL */ - memset(hcall_page, 0, 4096); + memset(hcall_page, 0, PAGE_SIZE); ipi_ex->vector = IPI_VECTOR; ipi_ex->vp_set.format = HV_GENERIC_SET_ALL; - hyperv_hypercall(HVCALL_SEND_IPI_EX, pgs_gpa, pgs_gpa + 4096); + hyperv_hypercall(HVCALL_SEND_IPI_EX, pgs_gpa, pgs_gpa + PAGE_SIZE); nop_loop(); GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]); GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]); @@ -241,7 +243,7 @@ int main(int argc, char *argv[]) { struct kvm_vm *vm; struct kvm_vcpu *vcpu[3]; - vm_vaddr_t hcall_page; + gva_t hcall_page; pthread_t threads[2]; int stage = 1, r; struct ucall uc; @@ -251,7 +253,7 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu[0], sender_guest_code); /* Hypercall input/output */ - hcall_page = vm_vaddr_alloc_pages(vm, 2); + hcall_page = vm_alloc_pages(vm, 2); memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); diff --git a/tools/testing/selftests/kvm/x86/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86/hyperv_svm_test.c index 0ddb63229bcb..7a62f6a9d606 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_svm_test.c +++ b/tools/testing/selftests/kvm/x86/hyperv_svm_test.c @@ -21,7 +21,7 @@ #define L2_GUEST_STACK_SIZE 256 /* Exit to L1 from L2 with RDMSR instruction */ -static inline void rdmsr_from_l2(uint32_t msr) +static inline void rdmsr_from_l2(u32 msr) { /* Currently, L1 doesn't preserve GPRs during vmexits. */ __asm__ __volatile__ ("rdmsr" : : "c"(msr) : @@ -67,7 +67,7 @@ void l2_guest_code(void) static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm, struct hyperv_test_pages *hv_pages, - vm_vaddr_t pgs_gpa) + gpa_t pgs_gpa) { unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; struct vmcb *vmcb = svm->vmcb; @@ -149,8 +149,8 @@ static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm, int main(int argc, char *argv[]) { - vm_vaddr_t nested_gva = 0, hv_pages_gva = 0; - vm_vaddr_t hcall_page; + gva_t nested_gva = 0, hv_pages_gva = 0; + gva_t hcall_page; struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct ucall uc; @@ -165,7 +165,7 @@ int main(int argc, char *argv[]) vcpu_alloc_svm(vm, &nested_gva); vcpu_alloc_hyperv_test_pages(vm, &hv_pages_gva); - hcall_page = vm_vaddr_alloc_pages(vm, 1); + hcall_page = vm_alloc_pages(vm, 1); memset(addr_gva2hva(vm, hcall_page), 0x0, getpagesize()); vcpu_args_set(vcpu, 3, nested_gva, hv_pages_gva, addr_gva2gpa(vm, hcall_page)); diff --git a/tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c b/tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c index 077cd0ec3040..15ee8b7bfc11 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c +++ b/tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c @@ -61,14 +61,14 @@ struct hv_tlb_flush_ex { * - GVAs of the test pages' PTEs */ struct test_data { - vm_vaddr_t hcall_gva; - vm_paddr_t hcall_gpa; - vm_vaddr_t test_pages; - vm_vaddr_t test_pages_pte[NTEST_PAGES]; + gva_t hcall_gva; + gpa_t hcall_gpa; + gva_t test_pages; + gva_t test_pages_pte[NTEST_PAGES]; }; /* 'Worker' vCPU code checking the contents of the test page */ -static void worker_guest_code(vm_vaddr_t test_data) +static void worker_guest_code(gva_t test_data) { struct test_data *data = (struct test_data *)test_data; u32 vcpu_id = rdmsr(HV_X64_MSR_VP_INDEX); @@ -133,12 +133,12 @@ static void set_expected_val(void *addr, u64 val, int vcpu_id) * Update PTEs swapping two test pages. * TODO: use swap()/xchg() when these are provided. */ -static void swap_two_test_pages(vm_paddr_t pte_gva1, vm_paddr_t pte_gva2) +static void swap_two_test_pages(gpa_t pte_gva1, gpa_t pte_gva2) { - uint64_t tmp = *(uint64_t *)pte_gva1; + u64 tmp = *(u64 *)pte_gva1; - *(uint64_t *)pte_gva1 = *(uint64_t *)pte_gva2; - *(uint64_t *)pte_gva2 = tmp; + *(u64 *)pte_gva1 = *(u64 *)pte_gva2; + *(u64 *)pte_gva2 = tmp; } /* @@ -196,12 +196,12 @@ static inline void post_test(struct test_data *data, u64 exp1, u64 exp2) #define TESTVAL2 0x0202020202020202 /* Main vCPU doing the test */ -static void sender_guest_code(vm_vaddr_t test_data) +static void sender_guest_code(gva_t test_data) { struct test_data *data = (struct test_data *)test_data; struct hv_tlb_flush *flush = (struct hv_tlb_flush *)data->hcall_gva; struct hv_tlb_flush_ex *flush_ex = (struct hv_tlb_flush_ex *)data->hcall_gva; - vm_paddr_t hcall_gpa = data->hcall_gpa; + gpa_t hcall_gpa = data->hcall_gpa; int i, stage = 1; wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); @@ -581,9 +581,9 @@ int main(int argc, char *argv[]) struct kvm_vm *vm; struct kvm_vcpu *vcpu[3]; pthread_t threads[2]; - vm_vaddr_t test_data_page, gva; - vm_paddr_t gpa; - uint64_t *pte; + gva_t test_data_page, gva; + gpa_t gpa; + u64 *pte; struct test_data *data; struct ucall uc; int stage = 1, r, i; @@ -593,11 +593,11 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu[0], sender_guest_code); /* Test data page */ - test_data_page = vm_vaddr_alloc_page(vm); + test_data_page = vm_alloc_page(vm); data = (struct test_data *)addr_gva2hva(vm, test_data_page); /* Hypercall input/output */ - data->hcall_gva = vm_vaddr_alloc_pages(vm, 2); + data->hcall_gva = vm_alloc_pages(vm, 2); data->hcall_gpa = addr_gva2gpa(vm, data->hcall_gva); memset(addr_gva2hva(vm, data->hcall_gva), 0x0, 2 * PAGE_SIZE); @@ -606,7 +606,7 @@ int main(int argc, char *argv[]) * and the test will swap their mappings. The third page keeps the indication * about the current state of mappings. */ - data->test_pages = vm_vaddr_alloc_pages(vm, NTEST_PAGES + 1); + data->test_pages = vm_alloc_pages(vm, NTEST_PAGES + 1); for (i = 0; i < NTEST_PAGES; i++) memset(addr_gva2hva(vm, data->test_pages + PAGE_SIZE * i), (u8)(i + 1), PAGE_SIZE); @@ -617,11 +617,11 @@ int main(int argc, char *argv[]) * Get PTE pointers for test pages and map them inside the guest. * Use separate page for each PTE for simplicity. */ - gva = vm_vaddr_unused_gap(vm, NTEST_PAGES * PAGE_SIZE, KVM_UTIL_MIN_VADDR); + gva = vm_unused_gva_gap(vm, NTEST_PAGES * PAGE_SIZE, KVM_UTIL_MIN_VADDR); for (i = 0; i < NTEST_PAGES; i++) { - pte = vm_get_page_table_entry(vm, data->test_pages + i * PAGE_SIZE); + pte = vm_get_pte(vm, data->test_pages + i * PAGE_SIZE); gpa = addr_hva2gpa(vm, pte); - __virt_pg_map(vm, gva + PAGE_SIZE * i, gpa & PAGE_MASK, PG_LEVEL_4K); + virt_pg_map(vm, gva + PAGE_SIZE * i, gpa & PAGE_MASK); data->test_pages_pte[i] = gva + (gpa & ~PAGE_MASK); } diff --git a/tools/testing/selftests/kvm/x86/kvm_buslock_test.c b/tools/testing/selftests/kvm/x86/kvm_buslock_test.c new file mode 100644 index 000000000000..52014a3210c8 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/kvm_buslock_test.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2024 Advanced Micro Devices, Inc. + */ +#include <linux/atomic.h> + +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "vmx.h" +#include "test_util.h" + +#define NR_BUS_LOCKS_PER_LEVEL 100 +#define CACHE_LINE_SIZE 64 + +/* + * To generate a bus lock, carve out a buffer that precisely occupies two cache + * lines and perform an atomic access that splits the two lines. + */ +static u8 buffer[CACHE_LINE_SIZE * 2] __aligned(CACHE_LINE_SIZE); +static atomic_t *val = (void *)&buffer[CACHE_LINE_SIZE - (sizeof(*val) / 2)]; + +static void guest_generate_buslocks(void) +{ + for (int i = 0; i < NR_BUS_LOCKS_PER_LEVEL; i++) + atomic_inc(val); +} + +#define L2_GUEST_STACK_SIZE 64 + +static void l2_guest_code(void) +{ + guest_generate_buslocks(); + GUEST_DONE(); +} + +static void l1_svm_code(struct svm_test_data *svm) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + + generic_svm_setup(svm, l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + run_guest(vmcb, svm->vmcb_gpa); +} + +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(!vmwrite(GUEST_RIP, (u64)l2_guest_code)); + GUEST_ASSERT(!vmlaunch()); +} + +static void guest_code(void *test_data) +{ + guest_generate_buslocks(); + + if (this_cpu_has(X86_FEATURE_SVM)) + l1_svm_code(test_data); + else if (this_cpu_has(X86_FEATURE_VMX)) + l1_vmx_code(test_data); + else + GUEST_DONE(); + + TEST_FAIL("L2 should have signaled 'done'"); +} + +int main(int argc, char *argv[]) +{ + const bool has_nested = kvm_cpu_has(X86_FEATURE_SVM) || kvm_cpu_has(X86_FEATURE_VMX); + gva_t nested_test_data_gva; + struct kvm_vcpu *vcpu; + struct kvm_run *run; + struct kvm_vm *vm; + int i, bus_locks = 0; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_BUS_LOCK_EXIT)); + + vm = vm_create(1); + vm_enable_cap(vm, KVM_CAP_X86_BUS_LOCK_EXIT, KVM_BUS_LOCK_DETECTION_EXIT); + vcpu = vm_vcpu_add(vm, 0, guest_code); + + 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 = vcpu->run; + + for (i = 0; i <= NR_BUS_LOCKS_PER_LEVEL * (1 + has_nested); i++) { + struct ucall uc; + + vcpu_run(vcpu); + + if (run->exit_reason == KVM_EXIT_IO) { + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + goto done; + case UCALL_SYNC: + continue; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd); + } + } + + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_X86_BUS_LOCK); + + /* + * Verify the counter is actually getting incremented, e.g. that + * KVM isn't skipping the instruction. On Intel, the exit is + * trap-like, i.e. the counter should already have been + * incremented. On AMD, it's fault-like, i.e. the counter will + * be incremented when the guest re-executes the instruction. + */ + sync_global_from_guest(vm, *val); + TEST_ASSERT_EQ(atomic_read(val), bus_locks + host_cpu_is_intel); + + bus_locks++; + } + TEST_FAIL("Didn't receive UCALL_DONE, took %u bus lock exits\n", bus_locks); +done: + TEST_ASSERT_EQ(i, bus_locks); + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86/kvm_clock_test.c b/tools/testing/selftests/kvm/x86/kvm_clock_test.c index 5bc12222d87a..5ad4aeb8e373 100644 --- a/tools/testing/selftests/kvm/x86/kvm_clock_test.c +++ b/tools/testing/selftests/kvm/x86/kvm_clock_test.c @@ -17,8 +17,8 @@ #include "processor.h" struct test_case { - uint64_t kvmclock_base; - int64_t realtime_offset; + u64 kvmclock_base; + s64 realtime_offset; }; static struct test_case test_cases[] = { @@ -31,7 +31,7 @@ static struct test_case test_cases[] = { #define GUEST_SYNC_CLOCK(__stage, __val) \ GUEST_SYNC_ARGS(__stage, __val, 0, 0, 0) -static void guest_main(vm_paddr_t pvti_pa, struct pvclock_vcpu_time_info *pvti) +static void guest_main(gpa_t pvti_pa, struct pvclock_vcpu_time_info *pvti) { int i; @@ -52,7 +52,7 @@ static inline void assert_flags(struct kvm_clock_data *data) static void handle_sync(struct ucall *uc, struct kvm_clock_data *start, struct kvm_clock_data *end) { - uint64_t obs, exp_lo, exp_hi; + u64 obs, exp_lo, exp_hi; obs = uc->args[2]; exp_lo = start->clock; @@ -135,8 +135,8 @@ static void enter_guest(struct kvm_vcpu *vcpu) int main(void) { struct kvm_vcpu *vcpu; - vm_vaddr_t pvti_gva; - vm_paddr_t pvti_gpa; + gva_t pvti_gva; + gpa_t pvti_gpa; struct kvm_vm *vm; int flags; @@ -147,7 +147,7 @@ int main(void) vm = vm_create_with_one_vcpu(&vcpu, guest_main); - pvti_gva = vm_vaddr_alloc(vm, getpagesize(), 0x10000); + pvti_gva = vm_alloc(vm, getpagesize(), 0x10000); pvti_gpa = addr_gva2gpa(vm, pvti_gva); vcpu_args_set(vcpu, 2, pvti_gpa, pvti_gva); diff --git a/tools/testing/selftests/kvm/x86/kvm_pv_test.c b/tools/testing/selftests/kvm/x86/kvm_pv_test.c index 1b805cbdb47b..8ed5fa635021 100644 --- a/tools/testing/selftests/kvm/x86/kvm_pv_test.c +++ b/tools/testing/selftests/kvm/x86/kvm_pv_test.c @@ -13,7 +13,7 @@ #include "processor.h" struct msr_data { - uint32_t idx; + u32 idx; const char *name; }; @@ -40,8 +40,8 @@ static struct msr_data msrs_to_test[] = { static void test_msr(struct msr_data *msr) { - uint64_t ignored; - uint8_t vector; + u64 ignored; + u8 vector; PR_MSR(msr); @@ -53,7 +53,7 @@ static void test_msr(struct msr_data *msr) } struct hcall_data { - uint64_t nr; + u64 nr; const char *name; }; @@ -73,7 +73,7 @@ static struct hcall_data hcalls_to_test[] = { static void test_hcall(struct hcall_data *hc) { - uint64_t r; + u64 r; PR_HCALL(hc); r = kvm_hypercall(hc->nr, 0, 0, 0, 0); diff --git a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c index 2b550eff35f1..9c156cf7db0e 100644 --- a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c +++ b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c @@ -7,6 +7,7 @@ #include "kvm_util.h" #include "processor.h" +#include "kselftest.h" #define CPUID_MWAIT (1u << 3) @@ -14,6 +15,8 @@ enum monitor_mwait_testcases { MWAIT_QUIRK_DISABLED = BIT(0), MISC_ENABLES_QUIRK_DISABLED = BIT(1), MWAIT_DISABLED = BIT(2), + CPUID_DISABLED = BIT(3), + TEST_MAX = CPUID_DISABLED * 2 - 1, }; /* @@ -27,19 +30,27 @@ do { \ \ if (fault_wanted) \ __GUEST_ASSERT((vector) == UD_VECTOR, \ - "Expected #UD on " insn " for testcase '0x%x', got '0x%x'", \ - testcase, vector); \ + "Expected #UD on " insn " for testcase '0x%x', got %s", \ + testcase, ex_str(vector)); \ else \ __GUEST_ASSERT(!(vector), \ - "Expected success on " insn " for testcase '0x%x', got '0x%x'", \ - testcase, vector); \ + "Expected success on " insn " for testcase '0x%x', got %s", \ + testcase, ex_str(vector)); \ } while (0) -static void guest_monitor_wait(int testcase) +static void guest_monitor_wait(void *arg) { + int testcase = (int) (long) arg; u8 vector; - GUEST_SYNC(testcase); + u64 val = rdmsr(MSR_IA32_MISC_ENABLE) & ~MSR_IA32_MISC_ENABLE_MWAIT; + if (!(testcase & MWAIT_DISABLED)) + val |= MSR_IA32_MISC_ENABLE_MWAIT; + wrmsr(MSR_IA32_MISC_ENABLE, val); + + __GUEST_ASSERT(this_cpu_has(X86_FEATURE_MWAIT) == !(testcase & MWAIT_DISABLED), + "Expected CPUID.MWAIT %s\n", + (testcase & MWAIT_DISABLED) ? "cleared" : "set"); /* * Arbitrarily MONITOR this function, SVM performs fault checks before @@ -50,80 +61,76 @@ static void guest_monitor_wait(int testcase) vector = kvm_asm_safe("mwait", "a"(guest_monitor_wait), "c"(0), "d"(0)); GUEST_ASSERT_MONITOR_MWAIT("MWAIT", 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; + u64 disabled_quirks; struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct ucall uc; int testcase; + char test[80]; TEST_REQUIRE(this_cpu_has(X86_FEATURE_MWAIT)); 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); + ksft_print_header(); + ksft_set_plan(12); + for (testcase = 0; testcase <= TEST_MAX; testcase++) { + vm = vm_create_with_one_vcpu(&vcpu, guest_monitor_wait); + vcpu_args_set(vcpu, 1, (void *)(long)testcase); + + disabled_quirks = 0; + if (testcase & MWAIT_QUIRK_DISABLED) { + disabled_quirks |= KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS; + strcpy(test, "MWAIT can fault"); + } else { + strcpy(test, "MWAIT never faults"); + } + if (testcase & MISC_ENABLES_QUIRK_DISABLED) { + disabled_quirks |= KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT; + strcat(test, ", MISC_ENABLE updates CPUID"); + } else { + strcat(test, ", no CPUID updates"); + } + + vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, disabled_quirks); + + if (!(testcase & MISC_ENABLES_QUIRK_DISABLED) && + (!!(testcase & CPUID_DISABLED) ^ !!(testcase & MWAIT_DISABLED))) + continue; + + if (testcase & CPUID_DISABLED) { + strcat(test, ", CPUID clear"); + vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_MWAIT); + } else { + strcat(test, ", CPUID set"); + vcpu_set_cpuid_feature(vcpu, X86_FEATURE_MWAIT); + } + + if (testcase & MWAIT_DISABLED) + strcat(test, ", MWAIT disabled"); - while (1) { vcpu_run(vcpu); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { - case UCALL_SYNC: - testcase = uc.args[1]; - break; case UCALL_ABORT: - REPORT_GUEST_ASSERT(uc); - goto done; + /* Detected in vcpu_run */ + break; case UCALL_DONE: - goto done; + ksft_test_result_pass("%s\n", test); + break; 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; + break; } - - vcpu_set_msr(vcpu, MSR_IA32_MISC_ENABLE, - (testcase & MWAIT_DISABLED) ? 0 : MSR_IA32_MISC_ENABLE_MWAIT); + kvm_vm_free(vm); } + ksft_finished(); -done: - kvm_vm_free(vm); return 0; } diff --git a/tools/testing/selftests/kvm/x86/msrs_test.c b/tools/testing/selftests/kvm/x86/msrs_test.c new file mode 100644 index 000000000000..f7e39bf887ad --- /dev/null +++ b/tools/testing/selftests/kvm/x86/msrs_test.c @@ -0,0 +1,489 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <asm/msr-index.h> + +#include <stdint.h> + +#include "kvm_util.h" +#include "processor.h" + +/* Use HYPERVISOR for MSRs that are emulated unconditionally (as is HYPERVISOR). */ +#define X86_FEATURE_NONE X86_FEATURE_HYPERVISOR + +struct kvm_msr { + const struct kvm_x86_cpu_feature feature; + const struct kvm_x86_cpu_feature feature2; + const char *name; + const u64 reset_val; + const u64 write_val; + const u64 rsvd_val; + const u32 index; + const bool is_kvm_defined; +}; + +#define ____MSR_TEST(msr, str, val, rsvd, reset, feat, f2, is_kvm) \ +{ \ + .index = msr, \ + .name = str, \ + .write_val = val, \ + .rsvd_val = rsvd, \ + .reset_val = reset, \ + .feature = X86_FEATURE_ ##feat, \ + .feature2 = X86_FEATURE_ ##f2, \ + .is_kvm_defined = is_kvm, \ +} + +#define __MSR_TEST(msr, str, val, rsvd, reset, feat) \ + ____MSR_TEST(msr, str, val, rsvd, reset, feat, feat, false) + +#define MSR_TEST_NON_ZERO(msr, val, rsvd, reset, feat) \ + __MSR_TEST(msr, #msr, val, rsvd, reset, feat) + +#define MSR_TEST(msr, val, rsvd, feat) \ + __MSR_TEST(msr, #msr, val, rsvd, 0, feat) + +#define MSR_TEST2(msr, val, rsvd, feat, f2) \ + ____MSR_TEST(msr, #msr, val, rsvd, 0, feat, f2, false) + +/* + * Note, use a page aligned value for the canonical value so that the value + * is compatible with MSRs that use bits 11:0 for things other than addresses. + */ +static const u64 canonical_val = 0x123456789000ull; + +/* + * Arbitrary value with bits set in every byte, but not all bits set. This is + * also a non-canonical value, but that's coincidental (any 64-bit value with + * an alternating 0s/1s pattern will be non-canonical). + */ +static const u64 u64_val = 0xaaaa5555aaaa5555ull; + +#define MSR_TEST_CANONICAL(msr, feat) \ + __MSR_TEST(msr, #msr, canonical_val, NONCANONICAL, 0, feat) + +#define MSR_TEST_KVM(msr, val, rsvd, feat) \ + ____MSR_TEST(KVM_REG_ ##msr, #msr, val, rsvd, 0, feat, feat, true) + +/* + * The main struct must be scoped to a function due to the use of structures to + * define features. For the global structure, allocate enough space for the + * foreseeable future without getting too ridiculous, to minimize maintenance + * costs (bumping the array size every time an MSR is added is really annoying). + */ +static struct kvm_msr msrs[128]; +static int idx; + +static bool ignore_unsupported_msrs; + +static u64 fixup_rdmsr_val(u32 msr, u64 want) +{ + /* + * AMD CPUs drop bits 63:32 on some MSRs that Intel CPUs support. KVM + * is supposed to emulate that behavior based on guest vendor model + * (which is the same as the host vendor model for this test). + */ + if (!host_cpu_is_amd_compatible) + return want; + + switch (msr) { + case MSR_IA32_SYSENTER_ESP: + case MSR_IA32_SYSENTER_EIP: + case MSR_TSC_AUX: + return want & GENMASK_ULL(31, 0); + default: + return want; + } +} + +static void __rdmsr(u32 msr, u64 want) +{ + u64 val; + u8 vec; + + vec = rdmsr_safe(msr, &val); + __GUEST_ASSERT(!vec, "Unexpected %s on RDMSR(0x%x)", ex_str(vec), msr); + + __GUEST_ASSERT(val == want, "Wanted 0x%lx from RDMSR(0x%x), got 0x%lx", + want, msr, val); +} + +static void __wrmsr(u32 msr, u64 val) +{ + u8 vec; + + vec = wrmsr_safe(msr, val); + __GUEST_ASSERT(!vec, "Unexpected %s on WRMSR(0x%x, 0x%lx)", + ex_str(vec), msr, val); + __rdmsr(msr, fixup_rdmsr_val(msr, val)); +} + +static void guest_test_supported_msr(const struct kvm_msr *msr) +{ + __rdmsr(msr->index, msr->reset_val); + __wrmsr(msr->index, msr->write_val); + GUEST_SYNC(fixup_rdmsr_val(msr->index, msr->write_val)); + + __rdmsr(msr->index, msr->reset_val); +} + +static void guest_test_unsupported_msr(const struct kvm_msr *msr) +{ + u64 val; + u8 vec; + + /* + * KVM's ABI with respect to ignore_msrs is a mess and largely beyond + * repair, just skip the unsupported MSR tests. + */ + if (ignore_unsupported_msrs) + goto skip_wrmsr_gp; + + /* + * {S,U}_CET exist if IBT or SHSTK is supported, but with bits that are + * writable only if their associated feature is supported. Skip the + * RDMSR #GP test if the secondary feature is supported, but perform + * the WRMSR #GP test as the to-be-written value is tied to the primary + * feature. For all other MSRs, simply do nothing. + */ + if (this_cpu_has(msr->feature2)) { + if (msr->index != MSR_IA32_U_CET && + msr->index != MSR_IA32_S_CET) + goto skip_wrmsr_gp; + + goto skip_rdmsr_gp; + } + + vec = rdmsr_safe(msr->index, &val); + __GUEST_ASSERT(vec == GP_VECTOR, "Wanted #GP on RDMSR(0x%x), got %s", + msr->index, ex_str(vec)); + +skip_rdmsr_gp: + vec = wrmsr_safe(msr->index, msr->write_val); + __GUEST_ASSERT(vec == GP_VECTOR, "Wanted #GP on WRMSR(0x%x, 0x%lx), got %s", + msr->index, msr->write_val, ex_str(vec)); + +skip_wrmsr_gp: + GUEST_SYNC(0); +} + +void guest_test_reserved_val(const struct kvm_msr *msr) +{ + /* Skip reserved value checks as well, ignore_msrs is trully a mess. */ + if (ignore_unsupported_msrs) + return; + + /* + * If the CPU will truncate the written value (e.g. SYSENTER on AMD), + * expect success and a truncated value, not #GP. + */ + if ((!this_cpu_has(msr->feature) && !this_cpu_has(msr->feature2)) || + msr->rsvd_val == fixup_rdmsr_val(msr->index, msr->rsvd_val)) { + u8 vec = wrmsr_safe(msr->index, msr->rsvd_val); + + __GUEST_ASSERT(vec == GP_VECTOR, + "Wanted #GP on WRMSR(0x%x, 0x%lx), got %s", + msr->index, msr->rsvd_val, ex_str(vec)); + } else { + __wrmsr(msr->index, msr->rsvd_val); + __wrmsr(msr->index, msr->reset_val); + } +} + +static void guest_main(void) +{ + for (;;) { + const struct kvm_msr *msr = &msrs[READ_ONCE(idx)]; + + if (this_cpu_has(msr->feature)) + guest_test_supported_msr(msr); + else + guest_test_unsupported_msr(msr); + + if (msr->rsvd_val) + guest_test_reserved_val(msr); + + GUEST_SYNC(msr->reset_val); + } +} + +static bool has_one_reg; +static bool use_one_reg; + +#define KVM_X86_MAX_NR_REGS 1 + +static bool vcpu_has_reg(struct kvm_vcpu *vcpu, u64 reg) +{ + struct { + struct kvm_reg_list list; + u64 regs[KVM_X86_MAX_NR_REGS]; + } regs = {}; + int r, i; + + /* + * If KVM_GET_REG_LIST succeeds with n=0, i.e. there are no supported + * regs, then the vCPU obviously doesn't support the reg. + */ + r = __vcpu_ioctl(vcpu, KVM_GET_REG_LIST, ®s.list); + if (!r) + return false; + + TEST_ASSERT_EQ(errno, E2BIG); + + /* + * KVM x86 is expected to support enumerating a relative small number + * of regs. The majority of registers supported by KVM_{G,S}ET_ONE_REG + * are enumerated via other ioctls, e.g. KVM_GET_MSR_INDEX_LIST. For + * simplicity, hardcode the maximum number of regs and manually update + * the test as necessary. + */ + TEST_ASSERT(regs.list.n <= KVM_X86_MAX_NR_REGS, + "KVM reports %llu regs, test expects at most %u regs, stale test?", + regs.list.n, KVM_X86_MAX_NR_REGS); + + vcpu_ioctl(vcpu, KVM_GET_REG_LIST, ®s.list); + for (i = 0; i < regs.list.n; i++) { + if (regs.regs[i] == reg) + return true; + } + + return false; +} + +static void host_test_kvm_reg(struct kvm_vcpu *vcpu) +{ + bool has_reg = vcpu_cpuid_has(vcpu, msrs[idx].feature); + u64 reset_val = msrs[idx].reset_val; + u64 write_val = msrs[idx].write_val; + u64 rsvd_val = msrs[idx].rsvd_val; + u32 reg = msrs[idx].index; + u64 val; + int r; + + if (!use_one_reg) + return; + + TEST_ASSERT_EQ(vcpu_has_reg(vcpu, KVM_X86_REG_KVM(reg)), has_reg); + + if (!has_reg) { + r = __vcpu_get_reg(vcpu, KVM_X86_REG_KVM(reg), &val); + TEST_ASSERT(r && errno == EINVAL, + "Expected failure on get_reg(0x%x)", reg); + rsvd_val = 0; + goto out; + } + + val = vcpu_get_reg(vcpu, KVM_X86_REG_KVM(reg)); + TEST_ASSERT(val == reset_val, "Wanted 0x%lx from get_reg(0x%x), got 0x%lx", + reset_val, reg, val); + + vcpu_set_reg(vcpu, KVM_X86_REG_KVM(reg), write_val); + val = vcpu_get_reg(vcpu, KVM_X86_REG_KVM(reg)); + TEST_ASSERT(val == write_val, "Wanted 0x%lx from get_reg(0x%x), got 0x%lx", + write_val, reg, val); + +out: + r = __vcpu_set_reg(vcpu, KVM_X86_REG_KVM(reg), rsvd_val); + TEST_ASSERT(r, "Expected failure on set_reg(0x%x, 0x%lx)", reg, rsvd_val); +} + +static void host_test_msr(struct kvm_vcpu *vcpu, u64 guest_val) +{ + u64 reset_val = msrs[idx].reset_val; + u32 msr = msrs[idx].index; + u64 val; + + if (!kvm_cpu_has(msrs[idx].feature)) + return; + + val = vcpu_get_msr(vcpu, msr); + TEST_ASSERT(val == guest_val, "Wanted 0x%lx from get_msr(0x%x), got 0x%lx", + guest_val, msr, val); + + if (use_one_reg) + vcpu_set_reg(vcpu, KVM_X86_REG_MSR(msr), reset_val); + else + vcpu_set_msr(vcpu, msr, reset_val); + + val = vcpu_get_msr(vcpu, msr); + TEST_ASSERT(val == reset_val, "Wanted 0x%lx from get_msr(0x%x), got 0x%lx", + reset_val, msr, val); + + if (!has_one_reg) + return; + + val = vcpu_get_reg(vcpu, KVM_X86_REG_MSR(msr)); + TEST_ASSERT(val == reset_val, "Wanted 0x%lx from get_reg(0x%x), got 0x%lx", + reset_val, msr, val); +} + +static void do_vcpu_run(struct kvm_vcpu *vcpu) +{ + struct ucall uc; + + for (;;) { + vcpu_run(vcpu); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + host_test_msr(vcpu, uc.args[1]); + return; + case UCALL_PRINTF: + pr_info("%s", uc.buffer); + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + case UCALL_DONE: + TEST_FAIL("Unexpected UCALL_DONE"); + default: + TEST_FAIL("Unexpected ucall: %lu", uc.cmd); + } + } +} + +static void vcpus_run(struct kvm_vcpu **vcpus, const int NR_VCPUS) +{ + int i; + + for (i = 0; i < NR_VCPUS; i++) + do_vcpu_run(vcpus[i]); +} + +#define MISC_ENABLES_RESET_VAL (MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL | MSR_IA32_MISC_ENABLE_BTS_UNAVAIL) + +static void test_msrs(void) +{ + const struct kvm_msr __msrs[] = { + MSR_TEST_NON_ZERO(MSR_IA32_MISC_ENABLE, + MISC_ENABLES_RESET_VAL | MSR_IA32_MISC_ENABLE_FAST_STRING, + MSR_IA32_MISC_ENABLE_FAST_STRING, MISC_ENABLES_RESET_VAL, NONE), + MSR_TEST_NON_ZERO(MSR_IA32_CR_PAT, 0x07070707, 0, 0x7040600070406, NONE), + + /* + * TSC_AUX is supported if RDTSCP *or* RDPID is supported. Add + * entries for each features so that TSC_AUX doesn't exists for + * the "unsupported" vCPU, and obviously to test both cases. + */ + MSR_TEST2(MSR_TSC_AUX, 0x12345678, u64_val, RDTSCP, RDPID), + MSR_TEST2(MSR_TSC_AUX, 0x12345678, u64_val, RDPID, RDTSCP), + + MSR_TEST(MSR_IA32_SYSENTER_CS, 0x1234, 0, NONE), + /* + * SYSENTER_{ESP,EIP} are technically non-canonical on Intel, + * but KVM doesn't emulate that behavior on emulated writes, + * i.e. this test will observe different behavior if the MSR + * writes are handed by hardware vs. KVM. KVM's behavior is + * intended (though far from ideal), so don't bother testing + * non-canonical values. + */ + MSR_TEST(MSR_IA32_SYSENTER_ESP, canonical_val, 0, NONE), + MSR_TEST(MSR_IA32_SYSENTER_EIP, canonical_val, 0, NONE), + + MSR_TEST_CANONICAL(MSR_FS_BASE, LM), + MSR_TEST_CANONICAL(MSR_GS_BASE, LM), + MSR_TEST_CANONICAL(MSR_KERNEL_GS_BASE, LM), + MSR_TEST_CANONICAL(MSR_LSTAR, LM), + MSR_TEST_CANONICAL(MSR_CSTAR, LM), + MSR_TEST(MSR_SYSCALL_MASK, 0xffffffff, 0, LM), + + MSR_TEST2(MSR_IA32_S_CET, CET_SHSTK_EN, CET_RESERVED, SHSTK, IBT), + MSR_TEST2(MSR_IA32_S_CET, CET_ENDBR_EN, CET_RESERVED, IBT, SHSTK), + MSR_TEST2(MSR_IA32_U_CET, CET_SHSTK_EN, CET_RESERVED, SHSTK, IBT), + MSR_TEST2(MSR_IA32_U_CET, CET_ENDBR_EN, CET_RESERVED, IBT, SHSTK), + MSR_TEST_CANONICAL(MSR_IA32_PL0_SSP, SHSTK), + MSR_TEST(MSR_IA32_PL0_SSP, canonical_val, canonical_val | 1, SHSTK), + MSR_TEST_CANONICAL(MSR_IA32_PL1_SSP, SHSTK), + MSR_TEST(MSR_IA32_PL1_SSP, canonical_val, canonical_val | 1, SHSTK), + MSR_TEST_CANONICAL(MSR_IA32_PL2_SSP, SHSTK), + MSR_TEST(MSR_IA32_PL2_SSP, canonical_val, canonical_val | 1, SHSTK), + MSR_TEST_CANONICAL(MSR_IA32_PL3_SSP, SHSTK), + MSR_TEST(MSR_IA32_PL3_SSP, canonical_val, canonical_val | 1, SHSTK), + + MSR_TEST_KVM(GUEST_SSP, canonical_val, NONCANONICAL, SHSTK), + }; + + const struct kvm_x86_cpu_feature feat_none = X86_FEATURE_NONE; + const struct kvm_x86_cpu_feature feat_lm = X86_FEATURE_LM; + + /* + * Create three vCPUs, but run them on the same task, to validate KVM's + * context switching of MSR state. Don't pin the task to a pCPU to + * also validate KVM's handling of cross-pCPU migration. Use the full + * set of features for the first two vCPUs, but clear all features in + * third vCPU in order to test both positive and negative paths. + */ + const int NR_VCPUS = 3; + struct kvm_vcpu *vcpus[NR_VCPUS]; + struct kvm_vm *vm; + int i; + + kvm_static_assert(sizeof(__msrs) <= sizeof(msrs)); + kvm_static_assert(ARRAY_SIZE(__msrs) <= ARRAY_SIZE(msrs)); + memcpy(msrs, __msrs, sizeof(__msrs)); + + ignore_unsupported_msrs = kvm_is_ignore_msrs(); + + vm = vm_create_with_vcpus(NR_VCPUS, guest_main, vcpus); + + sync_global_to_guest(vm, msrs); + sync_global_to_guest(vm, ignore_unsupported_msrs); + + /* + * Clear features in the "unsupported features" vCPU. This needs to be + * done before the first vCPU run as KVM's ABI is that guest CPUID is + * immutable once the vCPU has been run. + */ + for (idx = 0; idx < ARRAY_SIZE(__msrs); idx++) { + /* + * Don't clear LM; selftests are 64-bit only, and KVM doesn't + * honor LM=0 for MSRs that are supposed to exist if and only + * if the vCPU is a 64-bit model. Ditto for NONE; clearing a + * fake feature flag will result in false failures. + */ + if (memcmp(&msrs[idx].feature, &feat_lm, sizeof(feat_lm)) && + memcmp(&msrs[idx].feature, &feat_none, sizeof(feat_none))) + vcpu_clear_cpuid_feature(vcpus[2], msrs[idx].feature); + } + + for (idx = 0; idx < ARRAY_SIZE(__msrs); idx++) { + struct kvm_msr *msr = &msrs[idx]; + + if (msr->is_kvm_defined) { + for (i = 0; i < NR_VCPUS; i++) + host_test_kvm_reg(vcpus[i]); + continue; + } + + /* + * Verify KVM_GET_SUPPORTED_CPUID and KVM_GET_MSR_INDEX_LIST + * are consistent with respect to MSRs whose existence is + * enumerated via CPUID. Skip the check for FS/GS.base MSRs, + * as they aren't reported in the save/restore list since their + * state is managed via SREGS. + */ + TEST_ASSERT(msr->index == MSR_FS_BASE || msr->index == MSR_GS_BASE || + kvm_msr_is_in_save_restore_list(msr->index) == + (kvm_cpu_has(msr->feature) || kvm_cpu_has(msr->feature2)), + "%s %s in save/restore list, but %s according to CPUID", msr->name, + kvm_msr_is_in_save_restore_list(msr->index) ? "is" : "isn't", + (kvm_cpu_has(msr->feature) || kvm_cpu_has(msr->feature2)) ? + "supported" : "unsupported"); + + sync_global_to_guest(vm, idx); + + vcpus_run(vcpus, NR_VCPUS); + vcpus_run(vcpus, NR_VCPUS); + } + + kvm_vm_free(vm); +} + +int main(void) +{ + has_one_reg = kvm_has_cap(KVM_CAP_ONE_REG); + + test_msrs(); + + if (has_one_reg) { + use_one_reg = true; + test_msrs(); + } +} diff --git a/tools/testing/selftests/kvm/x86/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86/nested_close_kvm_test.c index dad988351493..761fec293408 100644 --- a/tools/testing/selftests/kvm/x86/vmx_close_while_nested_test.c +++ b/tools/testing/selftests/kvm/x86/nested_close_kvm_test.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * vmx_close_while_nested - * * Copyright (C) 2019, Red Hat, Inc. * * Verify that nothing bad happens if a KVM user exits with open @@ -12,6 +10,7 @@ #include "kvm_util.h" #include "processor.h" #include "vmx.h" +#include "svm_util.h" #include <string.h> #include <sys/ioctl.h> @@ -22,6 +21,8 @@ enum { PORT_L0_EXIT = 0x2000, }; +#define L2_GUEST_STACK_SIZE 64 + static void l2_guest_code(void) { /* Exit to L0 */ @@ -29,9 +30,8 @@ static void l2_guest_code(void) : : [port] "d" (PORT_L0_EXIT) : "rax"); } -static void l1_guest_code(struct vmx_pages *vmx_pages) +static void l1_vmx_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)); @@ -45,19 +45,43 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) GUEST_ASSERT(0); } +static void l1_svm_code(struct svm_test_data *svm) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + /* Prepare the VMCB for L2 execution. */ + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + run_guest(svm->vmcb, svm->vmcb_gpa); + GUEST_ASSERT(0); +} + +static void l1_guest_code(void *data) +{ + if (this_cpu_has(X86_FEATURE_VMX)) + l1_vmx_code(data); + else + l1_svm_code(data); +} + int main(int argc, char *argv[]) { - vm_vaddr_t vmx_pages_gva; + gva_t guest_gva; struct kvm_vcpu *vcpu; struct kvm_vm *vm; - TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX) || + kvm_cpu_has(X86_FEATURE_SVM)); 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); + if (kvm_cpu_has(X86_FEATURE_VMX)) + vcpu_alloc_vmx(vm, &guest_gva); + else + vcpu_alloc_svm(vm, &guest_gva); + + vcpu_args_set(vcpu, 1, guest_gva); for (;;) { volatile struct kvm_run *run = vcpu->run; diff --git a/tools/testing/selftests/kvm/x86/nested_dirty_log_test.c b/tools/testing/selftests/kvm/x86/nested_dirty_log_test.c new file mode 100644 index 000000000000..0e67cce83570 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/nested_dirty_log_test.c @@ -0,0 +1,293 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KVM dirty page logging test + * + * Copyright (C) 2018, Red Hat, Inc. + */ +#include <stdio.h> +#include <stdlib.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "vmx.h" + +/* The memory slot index to track dirty pages */ +#define TEST_MEM_SLOT_INDEX 1 + +/* + * Allocate four pages total. Two pages are used to verify that the KVM marks + * the accessed page/GFN as marked dirty, but not the "other" page. Times two + * so that each "normal" page can be accessed from L2 via an aliased L2 GVA+GPA + * (when TDP is enabled), to verify KVM marks _L1's_ page/GFN as dirty (to + * detect failures, L2 => L1 GPAs can't be identity mapped in the TDP page + * tables, as marking L2's GPA dirty would get a false pass if L1 == L2). + */ +#define TEST_MEM_PAGES 4 + +#define TEST_MEM_BASE 0xc0000000 +#define TEST_MEM_ALIAS_BASE 0xc0002000 + +#define TEST_GUEST_ADDR(base, idx) ((base) + (idx) * PAGE_SIZE) + +#define TEST_GVA(idx) TEST_GUEST_ADDR(TEST_MEM_BASE, idx) +#define TEST_GPA(idx) TEST_GUEST_ADDR(TEST_MEM_BASE, idx) + +#define TEST_ALIAS_GPA(idx) TEST_GUEST_ADDR(TEST_MEM_ALIAS_BASE, idx) + +#define TEST_HVA(vm, idx) addr_gpa2hva(vm, TEST_GPA(idx)) + +#define L2_GUEST_STACK_SIZE 64 + +/* Use the page offset bits to communicate the access+fault type. */ +#define TEST_SYNC_READ_FAULT BIT(0) +#define TEST_SYNC_WRITE_FAULT BIT(1) +#define TEST_SYNC_NO_FAULT BIT(2) + +static void l2_guest_code(gva_t base) +{ + gva_t page0 = TEST_GUEST_ADDR(base, 0); + gva_t page1 = TEST_GUEST_ADDR(base, 1); + + READ_ONCE(*(u64 *)page0); + GUEST_SYNC(page0 | TEST_SYNC_READ_FAULT); + WRITE_ONCE(*(u64 *)page0, 1); + GUEST_SYNC(page0 | TEST_SYNC_WRITE_FAULT); + READ_ONCE(*(u64 *)page0); + GUEST_SYNC(page0 | TEST_SYNC_NO_FAULT); + + WRITE_ONCE(*(u64 *)page1, 1); + GUEST_SYNC(page1 | TEST_SYNC_WRITE_FAULT); + WRITE_ONCE(*(u64 *)page1, 1); + GUEST_SYNC(page1 | TEST_SYNC_WRITE_FAULT); + READ_ONCE(*(u64 *)page1); + GUEST_SYNC(page1 | TEST_SYNC_NO_FAULT); + + /* Exit to L1 and never come back. */ + vmcall(); +} + +static void l2_guest_code_tdp_enabled(void) +{ + /* + * Use the aliased virtual addresses when running with TDP to verify + * that KVM correctly handles the case where a page is dirtied via a + * different GPA than would be used by L1. + */ + l2_guest_code(TEST_MEM_ALIAS_BASE); +} + +static void l2_guest_code_tdp_disabled(void) +{ + /* + * Use the "normal" virtual addresses when running without TDP enabled, + * in which case L2 will use the same page tables as L1, and thus needs + * to use the same virtual addresses that are mapped into L1. + */ + l2_guest_code(TEST_MEM_BASE); +} + +void l1_vmx_code(struct vmx_pages *vmx) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + void *l2_rip; + + GUEST_ASSERT(vmx->vmcs_gpa); + GUEST_ASSERT(prepare_for_vmx_operation(vmx)); + GUEST_ASSERT(load_vmcs(vmx)); + + if (vmx->eptp_gpa) + l2_rip = l2_guest_code_tdp_enabled; + else + l2_rip = l2_guest_code_tdp_disabled; + + prepare_vmcs(vmx, l2_rip, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + GUEST_SYNC(TEST_SYNC_NO_FAULT); + GUEST_ASSERT(!vmlaunch()); + GUEST_SYNC(TEST_SYNC_NO_FAULT); + GUEST_ASSERT_EQ(vmreadz(VM_EXIT_REASON), EXIT_REASON_VMCALL); + GUEST_DONE(); +} + +static void l1_svm_code(struct svm_test_data *svm) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + void *l2_rip; + + if (svm->ncr3_gpa) + l2_rip = l2_guest_code_tdp_enabled; + else + l2_rip = l2_guest_code_tdp_disabled; + + generic_svm_setup(svm, l2_rip, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + GUEST_SYNC(TEST_SYNC_NO_FAULT); + run_guest(svm->vmcb, svm->vmcb_gpa); + GUEST_SYNC(TEST_SYNC_NO_FAULT); + GUEST_ASSERT_EQ(svm->vmcb->control.exit_code, SVM_EXIT_VMMCALL); + GUEST_DONE(); +} + +static void l1_guest_code(void *data) +{ + if (this_cpu_has(X86_FEATURE_VMX)) + l1_vmx_code(data); + else + l1_svm_code(data); +} + +static void test_handle_ucall_sync(struct kvm_vm *vm, u64 arg, + unsigned long *bmap) +{ + gva_t gva = arg & ~(PAGE_SIZE - 1); + int page_nr, i; + + /* + * Extract the page number of underlying physical page, which is also + * the _L1_ page number. The dirty bitmap _must_ be updated based on + * the L1 GPA, not L2 GPA, i.e. whether or not L2 used an aliased GPA + * (i.e. if TDP enabled for L2) is irrelevant with respect to the dirty + * bitmap and which underlying physical page is accessed. + * + * Note, gva will be '0' if there was no access, i.e. if the purpose of + * the sync is to verify all pages are clean. + */ + if (!gva) + page_nr = 0; + else if (gva >= TEST_MEM_ALIAS_BASE) + page_nr = (gva - TEST_MEM_ALIAS_BASE) >> PAGE_SHIFT; + else + page_nr = (gva - TEST_MEM_BASE) >> PAGE_SHIFT; + TEST_ASSERT(page_nr == 0 || page_nr == 1, + "Test bug, unexpected frame number '%u' for arg = %lx", page_nr, arg); + TEST_ASSERT(gva || (arg & TEST_SYNC_NO_FAULT), + "Test bug, gva must be valid if a fault is expected"); + + kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); + + /* + * Check all pages to verify the correct physical page was modified (or + * not), and that all pages are clean/dirty as expected. + * + * If a fault of any kind is expected, the target page should be dirty + * as the Dirty bit is set in the gPTE. KVM should create a writable + * SPTE even on a read fault, *and* KVM must mark the GFN as dirty + * when doing so. + */ + for (i = 0; i < TEST_MEM_PAGES; i++) { + if (i == page_nr && (arg & TEST_SYNC_WRITE_FAULT)) + TEST_ASSERT(*(u64 *)TEST_HVA(vm, i) == 1, + "Page %u incorrectly not written by guest", i); + else + TEST_ASSERT(*(u64 *)TEST_HVA(vm, i) == 0xaaaaaaaaaaaaaaaaULL, + "Page %u incorrectly written by guest", i); + + if (i == page_nr && !(arg & TEST_SYNC_NO_FAULT)) + TEST_ASSERT(test_bit(i, bmap), + "Page %u incorrectly reported clean on %s fault", + i, arg & TEST_SYNC_READ_FAULT ? "read" : "write"); + else + TEST_ASSERT(!test_bit(i, bmap), + "Page %u incorrectly reported dirty", i); + } +} + +static void test_dirty_log(bool nested_tdp) +{ + gva_t nested_gva = 0; + unsigned long *bmap; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct ucall uc; + bool done = false; + + pr_info("Nested TDP: %s\n", nested_tdp ? "enabled" : "disabled"); + + /* Create VM */ + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + if (nested_tdp) + vm_enable_tdp(vm); + + if (kvm_cpu_has(X86_FEATURE_VMX)) + vcpu_alloc_vmx(vm, &nested_gva); + else + vcpu_alloc_svm(vm, &nested_gva); + + vcpu_args_set(vcpu, 1, nested_gva); + + /* Add an extra memory slot for testing dirty logging */ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + TEST_MEM_BASE, + TEST_MEM_SLOT_INDEX, + TEST_MEM_PAGES, + KVM_MEM_LOG_DIRTY_PAGES); + + /* + * Add an identity map for GVA range [0xc0000000, 0xc0004000). This + * affects both L1 and L2. However... + */ + virt_map(vm, TEST_MEM_BASE, TEST_MEM_BASE, TEST_MEM_PAGES); + + /* + * ... pages in the L2 GPA address range [0xc0002000, 0xc0004000) will + * map to [0xc0000000, 0xc0002000) when TDP is enabled (for L2). + * + * When TDP is disabled, the L2 guest code will still access the same L1 + * GPAs as the TDP enabled case. + * + * Set the Dirty bit in the PTEs used by L2 so that KVM will create + * writable SPTEs when handling read faults (if the Dirty bit isn't + * set, KVM must intercept the next write to emulate the Dirty bit + * update). + */ + if (nested_tdp) { + tdp_identity_map_default_memslots(vm); + tdp_map(vm, TEST_ALIAS_GPA(0), TEST_GPA(0), PAGE_SIZE); + tdp_map(vm, TEST_ALIAS_GPA(1), TEST_GPA(1), PAGE_SIZE); + + *tdp_get_pte(vm, TEST_ALIAS_GPA(0)) |= PTE_DIRTY_MASK(&vm->stage2_mmu); + *tdp_get_pte(vm, TEST_ALIAS_GPA(1)) |= PTE_DIRTY_MASK(&vm->stage2_mmu); + } else { + *vm_get_pte(vm, TEST_GVA(0)) |= PTE_DIRTY_MASK(&vm->mmu); + *vm_get_pte(vm, TEST_GVA(1)) |= PTE_DIRTY_MASK(&vm->mmu); + } + + bmap = bitmap_zalloc(TEST_MEM_PAGES); + + while (!done) { + memset(TEST_HVA(vm, 0), 0xaa, TEST_MEM_PAGES * PAGE_SIZE); + + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + /* NOT REACHED */ + case UCALL_SYNC: + test_handle_ucall_sync(vm, uc.args[1], bmap); + break; + case UCALL_DONE: + done = true; + break; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + } +} + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX) || kvm_cpu_has(X86_FEATURE_SVM)); + + test_dirty_log(/*nested_tdp=*/false); + + if (kvm_cpu_has_tdp()) + test_dirty_log(/*nested_tdp=*/true); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86/nested_emulation_test.c b/tools/testing/selftests/kvm/x86/nested_emulation_test.c new file mode 100644 index 000000000000..fb7dcbe53ac7 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/nested_emulation_test.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "vmx.h" +#include "svm_util.h" + +enum { + SVM_F, + VMX_F, + NR_VIRTUALIZATION_FLAVORS, +}; + +struct emulated_instruction { + const char name[32]; + u8 opcode[15]; + u32 exit_reason[NR_VIRTUALIZATION_FLAVORS]; +}; + +static struct emulated_instruction instructions[] = { + { + .name = "pause", + .opcode = { 0xf3, 0x90 }, + .exit_reason = { SVM_EXIT_PAUSE, + EXIT_REASON_PAUSE_INSTRUCTION, } + }, + { + .name = "hlt", + .opcode = { 0xf4 }, + .exit_reason = { SVM_EXIT_HLT, + EXIT_REASON_HLT, } + }, +}; + +static u8 kvm_fep[] = { 0x0f, 0x0b, 0x6b, 0x76, 0x6d }; /* ud2 ; .ascii "kvm" */ +static u8 l2_guest_code[sizeof(kvm_fep) + 15]; +static u8 *l2_instruction = &l2_guest_code[sizeof(kvm_fep)]; + +static u32 get_instruction_length(struct emulated_instruction *insn) +{ + u32 i; + + for (i = 0; i < ARRAY_SIZE(insn->opcode) && insn->opcode[i]; i++) + ; + + return i; +} + +static void guest_code(void *test_data) +{ + int f = this_cpu_has(X86_FEATURE_SVM) ? SVM_F : VMX_F; + int i; + + memcpy(l2_guest_code, kvm_fep, sizeof(kvm_fep)); + + if (f == SVM_F) { + struct svm_test_data *svm = test_data; + struct vmcb *vmcb = svm->vmcb; + + generic_svm_setup(svm, NULL, NULL); + vmcb->save.idtr.limit = 0; + vmcb->save.rip = (u64)l2_guest_code; + + vmcb->control.intercept |= BIT_ULL(INTERCEPT_SHUTDOWN) | + BIT_ULL(INTERCEPT_PAUSE) | + BIT_ULL(INTERCEPT_HLT); + vmcb->control.intercept_exceptions = 0; + } else { + GUEST_ASSERT(prepare_for_vmx_operation(test_data)); + GUEST_ASSERT(load_vmcs(test_data)); + + prepare_vmcs(test_data, NULL, NULL); + GUEST_ASSERT(!vmwrite(GUEST_IDTR_LIMIT, 0)); + GUEST_ASSERT(!vmwrite(GUEST_RIP, (u64)l2_guest_code)); + GUEST_ASSERT(!vmwrite(EXCEPTION_BITMAP, 0)); + + vmwrite(CPU_BASED_VM_EXEC_CONTROL, vmreadz(CPU_BASED_VM_EXEC_CONTROL) | + CPU_BASED_PAUSE_EXITING | + CPU_BASED_HLT_EXITING); + } + + for (i = 0; i < ARRAY_SIZE(instructions); i++) { + struct emulated_instruction *insn = &instructions[i]; + u32 insn_len = get_instruction_length(insn); + u32 exit_insn_len; + u32 exit_reason; + + /* + * Copy the target instruction to the L2 code stream, and fill + * the remaining bytes with INT3s so that a missed intercept + * results in a consistent failure mode (SHUTDOWN). + */ + memcpy(l2_instruction, insn->opcode, insn_len); + memset(l2_instruction + insn_len, 0xcc, sizeof(insn->opcode) - insn_len); + + if (f == SVM_F) { + struct svm_test_data *svm = test_data; + struct vmcb *vmcb = svm->vmcb; + + run_guest(vmcb, svm->vmcb_gpa); + exit_reason = vmcb->control.exit_code; + exit_insn_len = vmcb->control.next_rip - vmcb->save.rip; + GUEST_ASSERT_EQ(vmcb->save.rip, (u64)l2_instruction); + } else { + GUEST_ASSERT_EQ(i ? vmresume() : vmlaunch(), 0); + exit_reason = vmreadz(VM_EXIT_REASON); + exit_insn_len = vmreadz(VM_EXIT_INSTRUCTION_LEN); + GUEST_ASSERT_EQ(vmreadz(GUEST_RIP), (u64)l2_instruction); + } + + __GUEST_ASSERT(exit_reason == insn->exit_reason[f], + "Wanted exit_reason '0x%x' for '%s', got '0x%x'", + insn->exit_reason[f], insn->name, exit_reason); + + __GUEST_ASSERT(exit_insn_len == insn_len, + "Wanted insn_len '%u' for '%s', got '%u'", + insn_len, insn->name, exit_insn_len); + } + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + gva_t nested_test_data_gva; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + TEST_REQUIRE(is_forced_emulation_enabled); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM) || kvm_cpu_has(X86_FEATURE_VMX)); + + vm = vm_create_with_one_vcpu(&vcpu, 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); + + vcpu_run(vcpu); + TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); + + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86/nested_exceptions_test.c b/tools/testing/selftests/kvm/x86/nested_exceptions_test.c index 3641a42934ac..186e980aa8ee 100644 --- a/tools/testing/selftests/kvm/x86/nested_exceptions_test.c +++ b/tools/testing/selftests/kvm/x86/nested_exceptions_test.c @@ -72,7 +72,7 @@ static void l2_ss_injected_tf_test(void) } static void svm_run_l2(struct svm_test_data *svm, void *l2_code, int vector, - uint32_t error_code) + u32 error_code) { struct vmcb *vmcb = svm->vmcb; struct vmcb_control_area *ctrl = &vmcb->control; @@ -111,7 +111,7 @@ static void l1_svm_code(struct svm_test_data *svm) GUEST_DONE(); } -static void vmx_run_l2(void *l2_code, int vector, uint32_t error_code) +static void vmx_run_l2(void *l2_code, int vector, u32 error_code) { GUEST_ASSERT(!vmwrite(GUEST_RIP, (u64)l2_code)); @@ -216,7 +216,7 @@ static void queue_ss_exception(struct kvm_vcpu *vcpu, bool inject) */ int main(int argc, char *argv[]) { - vm_vaddr_t nested_test_data_gva; + gva_t nested_test_data_gva; struct kvm_vcpu_events events; struct kvm_vcpu *vcpu; struct kvm_vm *vm; diff --git a/tools/testing/selftests/kvm/x86/nested_invalid_cr3_test.c b/tools/testing/selftests/kvm/x86/nested_invalid_cr3_test.c new file mode 100644 index 000000000000..11fd2467d823 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/nested_invalid_cr3_test.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2025, Google LLC. + * + * This test verifies that L1 fails to enter L2 with an invalid CR3, and + * succeeds otherwise. + */ +#include "kvm_util.h" +#include "vmx.h" +#include "svm_util.h" +#include "kselftest.h" + + +#define L2_GUEST_STACK_SIZE 64 + +static void l2_guest_code(void) +{ + vmcall(); +} + +static void l1_svm_code(struct svm_test_data *svm) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + uintptr_t save_cr3; + + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* Try to run L2 with invalid CR3 and make sure it fails */ + save_cr3 = svm->vmcb->save.cr3; + svm->vmcb->save.cr3 = -1ull; + run_guest(svm->vmcb, svm->vmcb_gpa); + GUEST_ASSERT(svm->vmcb->control.exit_code == SVM_EXIT_ERR); + + /* Now restore CR3 and make sure L2 runs successfully */ + svm->vmcb->save.cr3 = save_cr3; + run_guest(svm->vmcb, svm->vmcb_gpa); + GUEST_ASSERT(svm->vmcb->control.exit_code == SVM_EXIT_VMMCALL); + + GUEST_DONE(); +} + +static void l1_vmx_code(struct vmx_pages *vmx_pages) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + uintptr_t save_cr3; + + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + GUEST_ASSERT(load_vmcs(vmx_pages)); + + prepare_vmcs(vmx_pages, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* Try to run L2 with invalid CR3 and make sure it fails */ + save_cr3 = vmreadz(GUEST_CR3); + vmwrite(GUEST_CR3, -1ull); + GUEST_ASSERT(!vmlaunch()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == + (EXIT_REASON_FAILED_VMENTRY | EXIT_REASON_INVALID_STATE)); + + /* Now restore CR3 and make sure L2 runs successfully */ + vmwrite(GUEST_CR3, save_cr3); + GUEST_ASSERT(!vmlaunch()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + + GUEST_DONE(); +} + +static void l1_guest_code(void *data) +{ + if (this_cpu_has(X86_FEATURE_VMX)) + l1_vmx_code(data); + else + l1_svm_code(data); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + gva_t guest_gva = 0; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX) || + kvm_cpu_has(X86_FEATURE_SVM)); + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + + if (kvm_cpu_has(X86_FEATURE_VMX)) + vcpu_alloc_vmx(vm, &guest_gva); + else + vcpu_alloc_svm(vm, &guest_gva); + + vcpu_args_set(vcpu, 1, guest_gva); + + for (;;) { + struct ucall uc; + + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + case UCALL_SYNC: + break; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + } + +done: + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86/nested_set_state_test.c index 67a62a5a8895..831380732671 100644 --- a/tools/testing/selftests/kvm/x86/vmx_set_nested_state_test.c +++ b/tools/testing/selftests/kvm/x86/nested_set_state_test.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * vmx_set_nested_state_test - * * Copyright (C) 2019, Google LLC. * * This test verifies the integrity of calling the ioctl KVM_SET_NESTED_STATE. @@ -11,6 +9,7 @@ #include "kvm_util.h" #include "processor.h" #include "vmx.h" +#include "svm_util.h" #include <errno.h> #include <linux/kvm.h> @@ -241,8 +240,108 @@ void test_vmx_nested_state(struct kvm_vcpu *vcpu) 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); - TEST_ASSERT(state->hdr.vmx.vmxon_pa == -1ull, "vmxon_pa must be -1ull."); - TEST_ASSERT(state->hdr.vmx.vmcs12_pa == -1ull, "vmcs_pa must be -1ull."); + + TEST_ASSERT_EQ(state->hdr.vmx.vmxon_pa, -1ull); + TEST_ASSERT_EQ(state->hdr.vmx.vmcs12_pa, -1ull); + TEST_ASSERT_EQ(state->flags, 0); + + free(state); +} + +static void vcpu_efer_enable_svm(struct kvm_vcpu *vcpu) +{ + u64 old_efer = vcpu_get_msr(vcpu, MSR_EFER); + + vcpu_set_msr(vcpu, MSR_EFER, old_efer | EFER_SVME); +} + +static void vcpu_efer_disable_svm(struct kvm_vcpu *vcpu) +{ + u64 old_efer = vcpu_get_msr(vcpu, MSR_EFER); + + vcpu_set_msr(vcpu, MSR_EFER, old_efer & ~EFER_SVME); +} + +void set_default_svm_state(struct kvm_nested_state *state, int size) +{ + memset(state, 0, size); + state->format = 1; + state->size = size; + state->hdr.svm.vmcb_pa = 0x3000; +} + +void test_svm_nested_state(struct kvm_vcpu *vcpu) +{ + /* Add a page for VMCB. */ + const int state_sz = sizeof(struct kvm_nested_state) + getpagesize(); + struct kvm_nested_state *state = + (struct kvm_nested_state *)malloc(state_sz); + + vcpu_set_cpuid_feature(vcpu, X86_FEATURE_SVM); + + /* The format must be set to 1. 0 for VMX, 1 for SVM. */ + set_default_svm_state(state, state_sz); + state->format = 0; + test_nested_state_expect_einval(vcpu, state); + + /* Invalid flags are rejected, KVM_STATE_NESTED_EVMCS is VMX-only */ + set_default_svm_state(state, state_sz); + state->flags = KVM_STATE_NESTED_EVMCS; + test_nested_state_expect_einval(vcpu, state); + + /* + * If EFER.SVME is clear, guest mode is disallowed and GIF can be set or + * cleared. + */ + vcpu_efer_disable_svm(vcpu); + + set_default_svm_state(state, state_sz); + state->flags = KVM_STATE_NESTED_GUEST_MODE; + test_nested_state_expect_einval(vcpu, state); + + state->flags = 0; + test_nested_state(vcpu, state); + + state->flags = KVM_STATE_NESTED_GIF_SET; + test_nested_state(vcpu, state); + + /* Enable SVM in the guest EFER. */ + vcpu_efer_enable_svm(vcpu); + + /* Setting vmcb_pa to a non-aligned address is only fine when not entering guest mode */ + set_default_svm_state(state, state_sz); + state->hdr.svm.vmcb_pa = -1ull; + state->flags = 0; + test_nested_state(vcpu, state); + state->flags = KVM_STATE_NESTED_GUEST_MODE; + test_nested_state_expect_einval(vcpu, state); + + /* + * Size must be large enough to fit kvm_nested_state and VMCB + * only when entering guest mode. + */ + set_default_svm_state(state, state_sz/2); + state->flags = 0; + test_nested_state(vcpu, state); + state->flags = KVM_STATE_NESTED_GUEST_MODE; + test_nested_state_expect_einval(vcpu, state); + + /* + * Test that if we leave nesting the state reflects that when we get it + * again, except for vmcb_pa, which is always returned as 0 when not in + * guest mode. + */ + set_default_svm_state(state, state_sz); + state->hdr.svm.vmcb_pa = -1ull; + state->flags = KVM_STATE_NESTED_GIF_SET; + 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); + + TEST_ASSERT_EQ(state->hdr.svm.vmcb_pa, 0); + TEST_ASSERT_EQ(state->flags, KVM_STATE_NESTED_GIF_SET); free(state); } @@ -255,20 +354,20 @@ int main(int argc, char *argv[]) have_evmcs = kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX) || + kvm_cpu_has(X86_FEATURE_SVM)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE)); - /* - * AMD currently does not implement set_nested_state, so for now we - * just early out. - */ - TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); - vm = vm_create_with_one_vcpu(&vcpu, NULL); /* - * First run tests with VMX disabled to check error handling. + * First run tests with VMX/SVM disabled to check error handling. + * test_{vmx/svm}_nested_state() will re-enable as needed. */ - vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_VMX); + if (kvm_cpu_has(X86_FEATURE_VMX)) + vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_VMX); + else + vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_SVM); /* Passing a NULL kvm_nested_state causes a EFAULT. */ test_nested_state_expect_efault(vcpu, NULL); @@ -297,7 +396,10 @@ int main(int argc, char *argv[]) state.flags = KVM_STATE_NESTED_RUN_PENDING; test_nested_state_expect_einval(vcpu, &state); - test_vmx_nested_state(vcpu); + if (kvm_cpu_has(X86_FEATURE_VMX)) + test_vmx_nested_state(vcpu); + else + test_svm_nested_state(vcpu); kvm_vm_free(vm); return 0; diff --git a/tools/testing/selftests/kvm/x86/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86/nested_tsc_adjust_test.c index 2ceb5c78c442..f0e4adac4751 100644 --- a/tools/testing/selftests/kvm/x86/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86/nested_tsc_adjust_test.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * vmx_tsc_adjust_test - * * Copyright (C) 2018, Google LLC. * * IA32_TSC_ADJUST test @@ -22,6 +20,7 @@ #include "kvm_util.h" #include "processor.h" #include "vmx.h" +#include "svm_util.h" #include <string.h> #include <sys/ioctl.h> @@ -35,6 +34,8 @@ #define TSC_ADJUST_VALUE (1ll << 32) #define TSC_OFFSET_VALUE -(1ll << 48) +#define L2_GUEST_STACK_SIZE 64 + enum { PORT_ABORT = 0x1000, PORT_REPORT, @@ -52,9 +53,9 @@ enum { /* The virtual machine object. */ static struct kvm_vm *vm; -static void check_ia32_tsc_adjust(int64_t max) +static void check_ia32_tsc_adjust(s64 max) { - int64_t adjust; + s64 adjust; adjust = rdmsr(MSR_IA32_TSC_ADJUST); GUEST_SYNC(adjust); @@ -63,7 +64,7 @@ static void check_ia32_tsc_adjust(int64_t max) static void l2_guest_code(void) { - uint64_t l1_tsc = rdtsc() - TSC_OFFSET_VALUE; + u64 l1_tsc = rdtsc() - TSC_OFFSET_VALUE; wrmsr(MSR_IA32_TSC, l1_tsc - TSC_ADJUST_VALUE); check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE); @@ -72,46 +73,51 @@ static void l2_guest_code(void) __asm__ __volatile__("vmcall"); } -static void l1_guest_code(struct vmx_pages *vmx_pages) +static void l1_guest_code(void *data) { -#define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; - uint32_t control; - uintptr_t save_cr3; + /* Set TSC from L1 and make sure TSC_ADJUST is updated correctly */ GUEST_ASSERT(rdtsc() < TSC_ADJUST_VALUE); wrmsr(MSR_IA32_TSC, rdtsc() - TSC_ADJUST_VALUE); check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE); - 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]); - control = vmreadz(CPU_BASED_VM_EXEC_CONTROL); - control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETTING; - vmwrite(CPU_BASED_VM_EXEC_CONTROL, control); - vmwrite(TSC_OFFSET, TSC_OFFSET_VALUE); - - /* Jump into L2. First, test failure to load guest CR3. */ - save_cr3 = vmreadz(GUEST_CR3); - vmwrite(GUEST_CR3, -1ull); - GUEST_ASSERT(!vmlaunch()); - GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == - (EXIT_REASON_FAILED_VMENTRY | EXIT_REASON_INVALID_STATE)); - check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE); - vmwrite(GUEST_CR3, save_cr3); - - GUEST_ASSERT(!vmlaunch()); - GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + /* + * Run L2 with TSC_OFFSET. L2 will write to TSC, and L1 is not + * intercepting the write so it should update L1's TSC_ADJUST. + */ + if (this_cpu_has(X86_FEATURE_VMX)) { + struct vmx_pages *vmx_pages = data; + u32 control; + + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + GUEST_ASSERT(load_vmcs(vmx_pages)); + + prepare_vmcs(vmx_pages, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + control = vmreadz(CPU_BASED_VM_EXEC_CONTROL); + control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETTING; + vmwrite(CPU_BASED_VM_EXEC_CONTROL, control); + vmwrite(TSC_OFFSET, TSC_OFFSET_VALUE); + + GUEST_ASSERT(!vmlaunch()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + } else { + struct svm_test_data *svm = data; + + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + svm->vmcb->control.tsc_offset = TSC_OFFSET_VALUE; + run_guest(svm->vmcb, svm->vmcb_gpa); + GUEST_ASSERT(svm->vmcb->control.exit_code == SVM_EXIT_VMMCALL); + } check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE); - GUEST_DONE(); } -static void report(int64_t val) +static void report(s64 val) { pr_info("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n", val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE); @@ -119,16 +125,19 @@ static void report(int64_t val) int main(int argc, char *argv[]) { - vm_vaddr_t vmx_pages_gva; + gva_t nested_gva; struct kvm_vcpu *vcpu; - TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX) || + kvm_cpu_has(X86_FEATURE_SVM)); - vm = vm_create_with_one_vcpu(&vcpu, (void *) l1_guest_code); + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + if (kvm_cpu_has(X86_FEATURE_VMX)) + vcpu_alloc_vmx(vm, &nested_gva); + else + vcpu_alloc_svm(vm, &nested_gva); - /* Allocate VMX pages and shared descriptors (vmx_pages). */ - vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vcpu, 1, vmx_pages_gva); + vcpu_args_set(vcpu, 1, nested_gva); for (;;) { struct ucall uc; diff --git a/tools/testing/selftests/kvm/x86/vmx_nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86/nested_tsc_scaling_test.c index 1759fa5cb3f2..190e93af20a1 100644 --- a/tools/testing/selftests/kvm/x86/vmx_nested_tsc_scaling_test.c +++ b/tools/testing/selftests/kvm/x86/nested_tsc_scaling_test.c @@ -13,12 +13,13 @@ #include "kvm_util.h" #include "vmx.h" +#include "svm_util.h" #include "kselftest.h" /* L2 is scaled up (from L1's perspective) by this factor */ #define L2_SCALE_FACTOR 4ULL -#define TSC_OFFSET_L2 ((uint64_t) -33125236320908) +#define TSC_OFFSET_L2 ((u64)-33125236320908) #define TSC_MULTIPLIER_L2 (L2_SCALE_FACTOR << 48) #define L2_GUEST_STACK_SIZE 64 @@ -34,9 +35,9 @@ enum { USLEEP, UCHECK_L1, UCHECK_L2 }; * measurements, a difference of 1% between the actual and the expected value * is tolerated. */ -static void compare_tsc_freq(uint64_t actual, uint64_t expected) +static void compare_tsc_freq(u64 actual, u64 expected) { - uint64_t tolerance, thresh_low, thresh_high; + u64 tolerance, thresh_low, thresh_high; tolerance = expected / 100; thresh_low = expected - tolerance; @@ -54,7 +55,7 @@ static void compare_tsc_freq(uint64_t actual, uint64_t expected) static void check_tsc_freq(int level) { - uint64_t tsc_start, tsc_end, tsc_freq; + u64 tsc_start, tsc_end, tsc_freq; /* * Reading the TSC twice with about a second's difference should give @@ -79,10 +80,33 @@ static void l2_guest_code(void) __asm__ __volatile__("vmcall"); } -static void l1_guest_code(struct vmx_pages *vmx_pages) +static void l1_svm_code(struct svm_test_data *svm) { unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; - uint32_t control; + + /* check that L1's frequency looks alright before launching L2 */ + check_tsc_freq(UCHECK_L1); + + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* enable TSC scaling for L2 */ + wrmsr(MSR_AMD64_TSC_RATIO, L2_SCALE_FACTOR << 32); + + /* launch L2 */ + run_guest(svm->vmcb, svm->vmcb_gpa); + GUEST_ASSERT(svm->vmcb->control.exit_code == SVM_EXIT_VMMCALL); + + /* check that L1's frequency still looks good */ + check_tsc_freq(UCHECK_L1); + + GUEST_DONE(); +} + +static void l1_vmx_code(struct vmx_pages *vmx_pages) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + u32 control; /* check that L1's frequency looks alright before launching L2 */ check_tsc_freq(UCHECK_L1); @@ -116,20 +140,29 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) GUEST_DONE(); } +static void l1_guest_code(void *data) +{ + if (this_cpu_has(X86_FEATURE_VMX)) + l1_vmx_code(data); + else + l1_svm_code(data); +} + int main(int argc, char *argv[]) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; - vm_vaddr_t vmx_pages_gva; + gva_t guest_gva = 0; - uint64_t tsc_start, tsc_end; - uint64_t tsc_khz; - uint64_t l1_scale_factor; - uint64_t l0_tsc_freq = 0; - uint64_t l1_tsc_freq = 0; - uint64_t l2_tsc_freq = 0; + u64 tsc_start, tsc_end; + u64 tsc_khz; + u64 l1_scale_factor; + u64 l0_tsc_freq = 0; + u64 l1_tsc_freq = 0; + u64 l2_tsc_freq = 0; - TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX) || + kvm_cpu_has(X86_FEATURE_SVM)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_TSC_CONTROL)); TEST_REQUIRE(sys_clocksource_is_based_on_tsc()); @@ -152,8 +185,13 @@ int main(int argc, char *argv[]) printf("real TSC frequency is around: %"PRIu64"\n", l0_tsc_freq); vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); - vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vcpu, 1, vmx_pages_gva); + + if (kvm_cpu_has(X86_FEATURE_VMX)) + vcpu_alloc_vmx(vm, &guest_gva); + else + vcpu_alloc_svm(vm, &guest_gva); + + vcpu_args_set(vcpu, 1, guest_gva); tsc_khz = __vcpu_ioctl(vcpu, KVM_GET_TSC_KHZ, NULL); TEST_ASSERT(tsc_khz != -1, "vcpu ioctl KVM_GET_TSC_KHZ failed"); diff --git a/tools/testing/selftests/kvm/x86/nested_vmsave_vmload_test.c b/tools/testing/selftests/kvm/x86/nested_vmsave_vmload_test.c new file mode 100644 index 000000000000..85d3f4cc76f3 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/nested_vmsave_vmload_test.c @@ -0,0 +1,197 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2026, Google LLC. + */ +#include "kvm_util.h" +#include "vmx.h" +#include "svm_util.h" +#include "kselftest.h" + +/* + * Allocate two VMCB pages for testing. Both pages have different GVAs (shared + * by both L1 and L2) and L1 GPAs. A single L2 GPA is used such that: + * - L2 GPA == L1 GPA for VMCB0. + * - L2 GPA is mapped to L1 GPA for VMCB1 using NPT in L1. + * + * This allows testing whether the GPA used by VMSAVE/VMLOAD in L2 is + * interpreted as a direct L1 GPA or translated using NPT as an L2 GPA, depends + * on which VMCB is accessed. + */ +#define TEST_MEM_SLOT_INDEX 1 +#define TEST_MEM_PAGES 2 +#define TEST_MEM_BASE 0xc0000000 + +#define TEST_GUEST_ADDR(idx) (TEST_MEM_BASE + (idx) * PAGE_SIZE) + +#define TEST_VMCB_L1_GPA(idx) TEST_GUEST_ADDR(idx) +#define TEST_VMCB_GVA(idx) TEST_GUEST_ADDR(idx) + +#define TEST_VMCB_L2_GPA TEST_VMCB_L1_GPA(0) + +#define L2_GUEST_STACK_SIZE 64 + +static void l2_guest_code_vmsave(void) +{ + asm volatile("vmsave %0" : : "a"(TEST_VMCB_L2_GPA) : "memory"); +} + +static void l2_guest_code_vmload(void) +{ + asm volatile("vmload %0" : : "a"(TEST_VMCB_L2_GPA) : "memory"); +} + +static void l2_guest_code_vmcb(int vmcb_idx) +{ + wrmsr(MSR_KERNEL_GS_BASE, 0xaaaa); + l2_guest_code_vmsave(); + + /* Verify the VMCB used by VMSAVE and update KERNEL_GS_BASE to 0xbbbb */ + GUEST_SYNC(vmcb_idx); + + l2_guest_code_vmload(); + GUEST_ASSERT_EQ(rdmsr(MSR_KERNEL_GS_BASE), 0xbbbb); + + /* Reset MSR_KERNEL_GS_BASE */ + wrmsr(MSR_KERNEL_GS_BASE, 0); + l2_guest_code_vmsave(); + + vmmcall(); +} + +static void l2_guest_code_vmcb0(void) +{ + l2_guest_code_vmcb(0); +} + +static void l2_guest_code_vmcb1(void) +{ + l2_guest_code_vmcb(1); +} + +static void l1_guest_code(struct svm_test_data *svm) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + /* Each test case initializes the guest RIP below */ + generic_svm_setup(svm, NULL, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* Set VMSAVE/VMLOAD intercepts and make sure they work with.. */ + svm->vmcb->control.intercept |= (BIT_ULL(INTERCEPT_VMSAVE) | + BIT_ULL(INTERCEPT_VMLOAD)); + + /* ..SVM_MISC2_ENABLE_V_VMLOAD_VMSAVE cleared.. */ + svm->vmcb->control.misc_ctl2 &= ~SVM_MISC2_ENABLE_V_VMLOAD_VMSAVE; + + svm->vmcb->save.rip = (u64)l2_guest_code_vmsave; + run_guest(svm->vmcb, svm->vmcb_gpa); + GUEST_ASSERT_EQ(svm->vmcb->control.exit_code, SVM_EXIT_VMSAVE); + + svm->vmcb->save.rip = (u64)l2_guest_code_vmload; + run_guest(svm->vmcb, svm->vmcb_gpa); + GUEST_ASSERT_EQ(svm->vmcb->control.exit_code, SVM_EXIT_VMLOAD); + + /* ..and SVM_MISC2_ENABLE_V_VMLOAD_VMSAVE set */ + svm->vmcb->control.misc_ctl2 |= SVM_MISC2_ENABLE_V_VMLOAD_VMSAVE; + + svm->vmcb->save.rip = (u64)l2_guest_code_vmsave; + run_guest(svm->vmcb, svm->vmcb_gpa); + GUEST_ASSERT_EQ(svm->vmcb->control.exit_code, SVM_EXIT_VMSAVE); + + svm->vmcb->save.rip = (u64)l2_guest_code_vmload; + run_guest(svm->vmcb, svm->vmcb_gpa); + GUEST_ASSERT_EQ(svm->vmcb->control.exit_code, SVM_EXIT_VMLOAD); + + /* Now clear the intercepts to test VMSAVE/VMLOAD behavior */ + svm->vmcb->control.intercept &= ~(BIT_ULL(INTERCEPT_VMSAVE) | + BIT_ULL(INTERCEPT_VMLOAD)); + + /* + * Without SVM_MISC2_ENABLE_V_VMLOAD_VMSAVE, the GPA will be + * interpreted as an L1 GPA, so VMCB0 should be used. + */ + svm->vmcb->save.rip = (u64)l2_guest_code_vmcb0; + svm->vmcb->control.misc_ctl2 &= ~SVM_MISC2_ENABLE_V_VMLOAD_VMSAVE; + run_guest(svm->vmcb, svm->vmcb_gpa); + GUEST_ASSERT_EQ(svm->vmcb->control.exit_code, SVM_EXIT_VMMCALL); + + /* + * With SVM_MISC2_ENABLE_V_VMLOAD_VMSAVE, the GPA will be interpeted as + * an L2 GPA, and translated through the NPT to VMCB1. + */ + svm->vmcb->save.rip = (u64)l2_guest_code_vmcb1; + svm->vmcb->control.misc_ctl2 |= SVM_MISC2_ENABLE_V_VMLOAD_VMSAVE; + run_guest(svm->vmcb, svm->vmcb_gpa); + GUEST_ASSERT_EQ(svm->vmcb->control.exit_code, SVM_EXIT_VMMCALL); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + gva_t nested_gva = 0; + struct vmcb *test_vmcb[2]; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + int i; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_NPT)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_V_VMSAVE_VMLOAD)); + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + vm_enable_tdp(vm); + + vcpu_alloc_svm(vm, &nested_gva); + vcpu_args_set(vcpu, 1, nested_gva); + + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + TEST_MEM_BASE, TEST_MEM_SLOT_INDEX, + TEST_MEM_PAGES, 0); + + for (i = 0; i <= 1; i++) { + virt_map(vm, TEST_VMCB_GVA(i), TEST_VMCB_L1_GPA(i), 1); + test_vmcb[i] = (struct vmcb *)addr_gva2hva(vm, TEST_VMCB_GVA(i)); + } + + tdp_identity_map_default_memslots(vm); + + /* + * L2 GPA == L1_GPA(0), but map it to L1_GPA(1), to allow testing + * whether the L2 GPA is interpreted as an L1 GPA or translated through + * the NPT. + */ + TEST_ASSERT_EQ(TEST_VMCB_L2_GPA, TEST_VMCB_L1_GPA(0)); + tdp_map(vm, TEST_VMCB_L2_GPA, TEST_VMCB_L1_GPA(1), PAGE_SIZE); + + for (;;) { + struct ucall uc; + + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + case UCALL_SYNC: + i = uc.args[1]; + TEST_ASSERT(i == 0 || i == 1, "Unexpected VMCB idx: %d", i); + + /* + * Check that only the expected VMCB has KERNEL_GS_BASE + * set to 0xaaaa, and update it to 0xbbbb. + */ + TEST_ASSERT_EQ(test_vmcb[i]->save.kernel_gs_base, 0xaaaa); + TEST_ASSERT_EQ(test_vmcb[1-i]->save.kernel_gs_base, 0); + test_vmcb[i]->save.kernel_gs_base = 0xbbbb; + break; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + } + +done: + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86/nx_huge_pages_test.c index e7efb2b35f8b..70950067b989 100644 --- a/tools/testing/selftests/kvm/x86/nx_huge_pages_test.c +++ b/tools/testing/selftests/kvm/x86/nx_huge_pages_test.c @@ -32,7 +32,7 @@ #define RETURN_OPCODE 0xC3 /* Call the specified memory address. */ -static void guest_do_CALL(uint64_t target) +static void guest_do_CALL(u64 target) { ((void (*)(void)) target)(); } @@ -46,14 +46,14 @@ static void guest_do_CALL(uint64_t target) */ 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); + u64 hpage_1 = HPAGE_GVA; + u64 hpage_2 = hpage_1 + (PAGE_SIZE * 512); + u64 hpage_3 = hpage_2 + (PAGE_SIZE * 512); - READ_ONCE(*(uint64_t *)hpage_1); + READ_ONCE(*(u64 *)hpage_1); GUEST_SYNC(1); - READ_ONCE(*(uint64_t *)hpage_2); + READ_ONCE(*(u64 *)hpage_2); GUEST_SYNC(2); guest_do_CALL(hpage_1); @@ -62,10 +62,10 @@ void guest_code(void) guest_do_CALL(hpage_3); GUEST_SYNC(4); - READ_ONCE(*(uint64_t *)hpage_1); + READ_ONCE(*(u64 *)hpage_1); GUEST_SYNC(5); - READ_ONCE(*(uint64_t *)hpage_3); + READ_ONCE(*(u64 *)hpage_3); GUEST_SYNC(6); } @@ -73,7 +73,7 @@ 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"); + 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", @@ -84,7 +84,7 @@ static void check_split_count(struct kvm_vm *vm, int expected_splits) { int actual_splits; - actual_splits = vm_get_stat(vm, "nx_lpage_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", @@ -107,7 +107,7 @@ void run_test(int reclaim_period_ms, bool disable_nx_huge_pages, { struct kvm_vcpu *vcpu; struct kvm_vm *vm; - uint64_t nr_bytes; + u64 nr_bytes; void *hva; int r; diff --git a/tools/testing/selftests/kvm/x86/platform_info_test.c b/tools/testing/selftests/kvm/x86/platform_info_test.c index 9cbf283ebc55..80bb07e6531c 100644 --- a/tools/testing/selftests/kvm/x86/platform_info_test.c +++ b/tools/testing/selftests/kvm/x86/platform_info_test.c @@ -23,8 +23,8 @@ static void guest_code(void) { - uint64_t msr_platform_info; - uint8_t vector; + u64 msr_platform_info; + u8 vector; GUEST_SYNC(true); msr_platform_info = rdmsr(MSR_PLATFORM_INFO); @@ -42,7 +42,7 @@ int main(int argc, char *argv[]) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; - uint64_t msr_platform_info; + u64 msr_platform_info; struct ucall uc; TEST_REQUIRE(kvm_has_cap(KVM_CAP_MSR_PLATFORM_INFO)); diff --git a/tools/testing/selftests/kvm/x86/pmu_counters_test.c b/tools/testing/selftests/kvm/x86/pmu_counters_test.c index 698cb36989db..dc6afac3aa91 100644 --- a/tools/testing/selftests/kvm/x86/pmu_counters_test.c +++ b/tools/testing/selftests/kvm/x86/pmu_counters_test.c @@ -14,10 +14,10 @@ #define NUM_BRANCH_INSNS_RETIRED (NUM_LOOPS) /* - * Number of instructions in each loop. 1 CLFLUSH/CLFLUSHOPT/NOP, 1 MFENCE, - * 1 LOOP. + * Number of instructions in each loop. 1 ENTER, 1 CLFLUSH/CLFLUSHOPT/NOP, + * 1 MFENCE, 1 MOV, 1 LEAVE, 1 LOOP. */ -#define NUM_INSNS_PER_LOOP 3 +#define NUM_INSNS_PER_LOOP 6 /* * Number of "extra" instructions that will be counted, i.e. the number of @@ -29,19 +29,74 @@ /* Total number of instructions retired within the measured section. */ #define NUM_INSNS_RETIRED (NUM_LOOPS * NUM_INSNS_PER_LOOP + NUM_EXTRA_INSNS) +/* Track which architectural events are supported by hardware. */ +static u32 hardware_pmu_arch_events; -static uint8_t kvm_pmu_version; +static u8 kvm_pmu_version; static bool kvm_has_perf_caps; +#define X86_PMU_FEATURE_NULL \ +({ \ + struct kvm_x86_pmu_feature feature = {}; \ + \ + feature; \ +}) + +static bool pmu_is_null_feature(struct kvm_x86_pmu_feature event) +{ + return !(*(u64 *)&event); +} + +struct kvm_intel_pmu_event { + struct kvm_x86_pmu_feature gp_event; + struct kvm_x86_pmu_feature fixed_event; +}; + +/* + * Wrap the array to appease the compiler, as the macros used to construct each + * kvm_x86_pmu_feature use syntax that's only valid in function scope, and the + * compiler often thinks the feature definitions aren't compile-time constants. + */ +static struct kvm_intel_pmu_event intel_event_to_feature(u8 idx) +{ + const struct kvm_intel_pmu_event __intel_event_to_feature[] = { + [INTEL_ARCH_CPU_CYCLES_INDEX] = { X86_PMU_FEATURE_CPU_CYCLES, X86_PMU_FEATURE_CPU_CYCLES_FIXED }, + [INTEL_ARCH_INSTRUCTIONS_RETIRED_INDEX] = { X86_PMU_FEATURE_INSNS_RETIRED, X86_PMU_FEATURE_INSNS_RETIRED_FIXED }, + /* + * Note, the fixed counter for reference cycles is NOT the same as the + * general purpose architectural event. The fixed counter explicitly + * counts at the same frequency as the TSC, whereas the GP event counts + * at a fixed, but uarch specific, frequency. Bundle them here for + * simplicity. + */ + [INTEL_ARCH_REFERENCE_CYCLES_INDEX] = { X86_PMU_FEATURE_REFERENCE_CYCLES, X86_PMU_FEATURE_REFERENCE_TSC_CYCLES_FIXED }, + [INTEL_ARCH_LLC_REFERENCES_INDEX] = { X86_PMU_FEATURE_LLC_REFERENCES, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_LLC_MISSES_INDEX] = { X86_PMU_FEATURE_LLC_MISSES, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_BRANCHES_RETIRED_INDEX] = { X86_PMU_FEATURE_BRANCH_INSNS_RETIRED, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_BRANCHES_MISPREDICTED_INDEX] = { X86_PMU_FEATURE_BRANCHES_MISPREDICTED, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_TOPDOWN_SLOTS_INDEX] = { X86_PMU_FEATURE_TOPDOWN_SLOTS, X86_PMU_FEATURE_TOPDOWN_SLOTS_FIXED }, + [INTEL_ARCH_TOPDOWN_BE_BOUND_INDEX] = { X86_PMU_FEATURE_TOPDOWN_BE_BOUND, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_TOPDOWN_BAD_SPEC_INDEX] = { X86_PMU_FEATURE_TOPDOWN_BAD_SPEC, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_TOPDOWN_FE_BOUND_INDEX] = { X86_PMU_FEATURE_TOPDOWN_FE_BOUND, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_TOPDOWN_RETIRING_INDEX] = { X86_PMU_FEATURE_TOPDOWN_RETIRING, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_LBR_INSERTS_INDEX] = { X86_PMU_FEATURE_LBR_INSERTS, X86_PMU_FEATURE_NULL }, + }; + + kvm_static_assert(ARRAY_SIZE(__intel_event_to_feature) == NR_INTEL_ARCH_EVENTS); + + return __intel_event_to_feature[idx]; +} + static struct kvm_vm *pmu_vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, void *guest_code, - uint8_t pmu_version, - uint64_t perf_capabilities) + u8 pmu_version, + u64 perf_capabilities) { struct kvm_vm *vm; vm = vm_create_with_one_vcpu(vcpu, guest_code); sync_global_to_guest(vm, kvm_pmu_version); + sync_global_to_guest(vm, hardware_pmu_arch_events); /* * Set PERF_CAPABILITIES before PMU version as KVM disallows enabling @@ -77,7 +132,7 @@ static void run_vcpu(struct kvm_vcpu *vcpu) } while (uc.cmd != UCALL_DONE); } -static uint8_t guest_get_pmu_version(void) +static u8 guest_get_pmu_version(void) { /* * Return the effective PMU version, i.e. the minimum between what KVM @@ -86,7 +141,7 @@ static uint8_t guest_get_pmu_version(void) * supported by KVM to verify KVM doesn't freak out and do something * bizarre with an architecturally valid, but unsupported, version. */ - return min_t(uint8_t, kvm_pmu_version, this_cpu_property(X86_PROPERTY_PMU_VERSION)); + return min_t(u8, kvm_pmu_version, this_cpu_property(X86_PROPERTY_PMU_VERSION)); } /* @@ -98,22 +153,28 @@ static uint8_t guest_get_pmu_version(void) * Sanity check that in all cases, the event doesn't count when it's disabled, * and that KVM correctly emulates the write of an arbitrary value. */ -static void guest_assert_event_count(uint8_t idx, - struct kvm_x86_pmu_feature event, - uint32_t pmc, uint32_t pmc_msr) +static void guest_assert_event_count(u8 idx, u32 pmc, u32 pmc_msr) { - uint64_t count; + u64 count; count = _rdpmc(pmc); - if (!this_pmu_has(event)) + if (!(hardware_pmu_arch_events & BIT(idx))) goto sanity_checks; switch (idx) { case INTEL_ARCH_INSTRUCTIONS_RETIRED_INDEX: - GUEST_ASSERT_EQ(count, NUM_INSNS_RETIRED); + /* Relax precise count check due to VM-EXIT/VM-ENTRY overcount issue */ + if (this_pmu_has_errata(INSTRUCTIONS_RETIRED_OVERCOUNT)) + GUEST_ASSERT(count >= NUM_INSNS_RETIRED); + else + GUEST_ASSERT_EQ(count, NUM_INSNS_RETIRED); break; case INTEL_ARCH_BRANCHES_RETIRED_INDEX: - GUEST_ASSERT_EQ(count, NUM_BRANCH_INSNS_RETIRED); + /* Relax precise count check due to VM-EXIT/VM-ENTRY overcount issue */ + if (this_pmu_has_errata(BRANCHES_RETIRED_OVERCOUNT)) + GUEST_ASSERT(count >= NUM_BRANCH_INSNS_RETIRED); + else + GUEST_ASSERT_EQ(count, NUM_BRANCH_INSNS_RETIRED); break; case INTEL_ARCH_LLC_REFERENCES_INDEX: case INTEL_ARCH_LLC_MISSES_INDEX: @@ -123,10 +184,15 @@ static void guest_assert_event_count(uint8_t idx, fallthrough; case INTEL_ARCH_CPU_CYCLES_INDEX: case INTEL_ARCH_REFERENCE_CYCLES_INDEX: + case INTEL_ARCH_TOPDOWN_BE_BOUND_INDEX: + case INTEL_ARCH_TOPDOWN_FE_BOUND_INDEX: GUEST_ASSERT_NE(count, 0); break; case INTEL_ARCH_TOPDOWN_SLOTS_INDEX: - GUEST_ASSERT(count >= NUM_INSNS_RETIRED); + case INTEL_ARCH_TOPDOWN_RETIRING_INDEX: + __GUEST_ASSERT(count >= NUM_INSNS_RETIRED, + "Expected top-down slots >= %u, got count = %lu", + NUM_INSNS_RETIRED, count); break; default: break; @@ -160,83 +226,52 @@ do { \ __asm__ __volatile__("wrmsr\n\t" \ " mov $" __stringify(NUM_LOOPS) ", %%ecx\n\t" \ "1:\n\t" \ + FEP "enter $0, $0\n\t" \ clflush "\n\t" \ "mfence\n\t" \ + "mov %[m], %%eax\n\t" \ + FEP "leave\n\t" \ FEP "loop 1b\n\t" \ FEP "mov %%edi, %%ecx\n\t" \ FEP "xor %%eax, %%eax\n\t" \ FEP "xor %%edx, %%edx\n\t" \ "wrmsr\n\t" \ - :: "a"((uint32_t)_value), "d"(_value >> 32), \ - "c"(_msr), "D"(_msr) \ + :: "a"((u32)_value), "d"(_value >> 32), \ + "c"(_msr), "D"(_msr), [m]"m"(kvm_pmu_version) \ ); \ } while (0) -#define GUEST_TEST_EVENT(_idx, _event, _pmc, _pmc_msr, _ctrl_msr, _value, FEP) \ +#define GUEST_TEST_EVENT(_idx, _pmc, _pmc_msr, _ctrl_msr, _value, FEP) \ do { \ - wrmsr(pmc_msr, 0); \ + wrmsr(_pmc_msr, 0); \ \ if (this_cpu_has(X86_FEATURE_CLFLUSHOPT)) \ - GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflushopt .", FEP); \ + GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflushopt %[m]", FEP); \ else if (this_cpu_has(X86_FEATURE_CLFLUSH)) \ - GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflush .", FEP); \ + GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflush %[m]", FEP); \ else \ GUEST_MEASURE_EVENT(_ctrl_msr, _value, "nop", FEP); \ \ - guest_assert_event_count(_idx, _event, _pmc, _pmc_msr); \ + guest_assert_event_count(_idx, _pmc, _pmc_msr); \ } while (0) -static void __guest_test_arch_event(uint8_t idx, struct kvm_x86_pmu_feature event, - uint32_t pmc, uint32_t pmc_msr, - uint32_t ctrl_msr, uint64_t ctrl_msr_value) +static void __guest_test_arch_event(u8 idx, u32 pmc, u32 pmc_msr, + u32 ctrl_msr, u64 ctrl_msr_value) { - GUEST_TEST_EVENT(idx, event, pmc, pmc_msr, ctrl_msr, ctrl_msr_value, ""); + GUEST_TEST_EVENT(idx, pmc, pmc_msr, ctrl_msr, ctrl_msr_value, ""); if (is_forced_emulation_enabled) - GUEST_TEST_EVENT(idx, event, pmc, pmc_msr, ctrl_msr, ctrl_msr_value, KVM_FEP); -} - -#define X86_PMU_FEATURE_NULL \ -({ \ - struct kvm_x86_pmu_feature feature = {}; \ - \ - feature; \ -}) - -static bool pmu_is_null_feature(struct kvm_x86_pmu_feature event) -{ - return !(*(u64 *)&event); + GUEST_TEST_EVENT(idx, pmc, pmc_msr, ctrl_msr, ctrl_msr_value, KVM_FEP); } -static void guest_test_arch_event(uint8_t idx) +static void guest_test_arch_event(u8 idx) { - const struct { - struct kvm_x86_pmu_feature gp_event; - struct kvm_x86_pmu_feature fixed_event; - } intel_event_to_feature[] = { - [INTEL_ARCH_CPU_CYCLES_INDEX] = { X86_PMU_FEATURE_CPU_CYCLES, X86_PMU_FEATURE_CPU_CYCLES_FIXED }, - [INTEL_ARCH_INSTRUCTIONS_RETIRED_INDEX] = { X86_PMU_FEATURE_INSNS_RETIRED, X86_PMU_FEATURE_INSNS_RETIRED_FIXED }, - /* - * Note, the fixed counter for reference cycles is NOT the same - * as the general purpose architectural event. The fixed counter - * explicitly counts at the same frequency as the TSC, whereas - * the GP event counts at a fixed, but uarch specific, frequency. - * Bundle them here for simplicity. - */ - [INTEL_ARCH_REFERENCE_CYCLES_INDEX] = { X86_PMU_FEATURE_REFERENCE_CYCLES, X86_PMU_FEATURE_REFERENCE_TSC_CYCLES_FIXED }, - [INTEL_ARCH_LLC_REFERENCES_INDEX] = { X86_PMU_FEATURE_LLC_REFERENCES, X86_PMU_FEATURE_NULL }, - [INTEL_ARCH_LLC_MISSES_INDEX] = { X86_PMU_FEATURE_LLC_MISSES, X86_PMU_FEATURE_NULL }, - [INTEL_ARCH_BRANCHES_RETIRED_INDEX] = { X86_PMU_FEATURE_BRANCH_INSNS_RETIRED, X86_PMU_FEATURE_NULL }, - [INTEL_ARCH_BRANCHES_MISPREDICTED_INDEX] = { X86_PMU_FEATURE_BRANCHES_MISPREDICTED, X86_PMU_FEATURE_NULL }, - [INTEL_ARCH_TOPDOWN_SLOTS_INDEX] = { X86_PMU_FEATURE_TOPDOWN_SLOTS, X86_PMU_FEATURE_TOPDOWN_SLOTS_FIXED }, - }; - - uint32_t nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); - uint32_t pmu_version = guest_get_pmu_version(); + u32 nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); + u32 pmu_version = guest_get_pmu_version(); /* PERF_GLOBAL_CTRL exists only for Architectural PMU Version 2+. */ bool guest_has_perf_global_ctrl = pmu_version >= 2; struct kvm_x86_pmu_feature gp_event, fixed_event; - uint32_t base_pmc_msr; + u32 base_pmc_msr; unsigned int i; /* The host side shouldn't invoke this without a guest PMU. */ @@ -248,13 +283,13 @@ static void guest_test_arch_event(uint8_t idx) else base_pmc_msr = MSR_IA32_PERFCTR0; - gp_event = intel_event_to_feature[idx].gp_event; + gp_event = intel_event_to_feature(idx).gp_event; GUEST_ASSERT_EQ(idx, gp_event.f.bit); GUEST_ASSERT(nr_gp_counters); for (i = 0; i < nr_gp_counters; i++) { - uint64_t eventsel = ARCH_PERFMON_EVENTSEL_OS | + u64 eventsel = ARCH_PERFMON_EVENTSEL_OS | ARCH_PERFMON_EVENTSEL_ENABLE | intel_pmu_arch_events[idx]; @@ -262,14 +297,14 @@ static void guest_test_arch_event(uint8_t idx) if (guest_has_perf_global_ctrl) wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, BIT_ULL(i)); - __guest_test_arch_event(idx, gp_event, i, base_pmc_msr + i, + __guest_test_arch_event(idx, i, base_pmc_msr + i, MSR_P6_EVNTSEL0 + i, eventsel); } if (!guest_has_perf_global_ctrl) return; - fixed_event = intel_event_to_feature[idx].fixed_event; + fixed_event = intel_event_to_feature(idx).fixed_event; if (pmu_is_null_feature(fixed_event) || !this_pmu_has(fixed_event)) return; @@ -277,7 +312,7 @@ static void guest_test_arch_event(uint8_t idx) wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, FIXED_PMC_CTRL(i, FIXED_PMC_KERNEL)); - __guest_test_arch_event(idx, fixed_event, i | INTEL_RDPMC_FIXED, + __guest_test_arch_event(idx, i | INTEL_RDPMC_FIXED, MSR_CORE_PERF_FIXED_CTR0 + i, MSR_CORE_PERF_GLOBAL_CTRL, FIXED_PMC_GLOBAL_CTRL_ENABLE(i)); @@ -285,7 +320,7 @@ static void guest_test_arch_event(uint8_t idx) static void guest_test_arch_events(void) { - uint8_t i; + u8 i; for (i = 0; i < NR_INTEL_ARCH_EVENTS; i++) guest_test_arch_event(i); @@ -293,8 +328,8 @@ static void guest_test_arch_events(void) GUEST_DONE(); } -static void test_arch_events(uint8_t pmu_version, uint64_t perf_capabilities, - uint8_t length, uint8_t unavailable_mask) +static void test_arch_events(u8 pmu_version, u64 perf_capabilities, + u8 length, u32 unavailable_mask) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; @@ -303,6 +338,9 @@ static void test_arch_events(uint8_t pmu_version, uint64_t perf_capabilities, if (!pmu_version) return; + unavailable_mask &= GENMASK(X86_PROPERTY_PMU_EVENTS_MASK.hi_bit, + X86_PROPERTY_PMU_EVENTS_MASK.lo_bit); + vm = pmu_vm_create_with_one_vcpu(&vcpu, guest_test_arch_events, pmu_version, perf_capabilities); @@ -327,19 +365,19 @@ static void test_arch_events(uint8_t pmu_version, uint64_t perf_capabilities, #define GUEST_ASSERT_PMC_MSR_ACCESS(insn, msr, expect_gp, vector) \ __GUEST_ASSERT(expect_gp ? vector == GP_VECTOR : !vector, \ - "Expected %s on " #insn "(0x%x), got vector %u", \ - expect_gp ? "#GP" : "no fault", msr, vector) \ + "Expected %s on " #insn "(0x%x), got %s", \ + expect_gp ? "#GP" : "no fault", msr, ex_str(vector)) \ #define GUEST_ASSERT_PMC_VALUE(insn, msr, val, expected) \ - __GUEST_ASSERT(val == expected_val, \ + __GUEST_ASSERT(val == expected, \ "Expected " #insn "(0x%x) to yield 0x%lx, got 0x%lx", \ - msr, expected_val, val); + msr, expected, val); -static void guest_test_rdpmc(uint32_t rdpmc_idx, bool expect_success, - uint64_t expected_val) +static void guest_test_rdpmc(u32 rdpmc_idx, bool expect_success, + u64 expected_val) { - uint8_t vector; - uint64_t val; + u8 vector; + u64 val; vector = rdpmc_safe(rdpmc_idx, &val); GUEST_ASSERT_PMC_MSR_ACCESS(RDPMC, rdpmc_idx, !expect_success, vector); @@ -355,19 +393,19 @@ static void guest_test_rdpmc(uint32_t rdpmc_idx, bool expect_success, GUEST_ASSERT_PMC_VALUE(RDPMC, rdpmc_idx, val, expected_val); } -static void guest_rd_wr_counters(uint32_t base_msr, uint8_t nr_possible_counters, - uint8_t nr_counters, uint32_t or_mask) +static void guest_rd_wr_counters(u32 base_msr, u8 nr_possible_counters, + u8 nr_counters, u32 or_mask) { const bool pmu_has_fast_mode = !guest_get_pmu_version(); - uint8_t i; + u8 i; for (i = 0; i < nr_possible_counters; i++) { /* * TODO: Test a value that validates full-width writes and the * width of the counters. */ - const uint64_t test_val = 0xffff; - const uint32_t msr = base_msr + i; + const u64 test_val = 0xffff; + const u32 msr = base_msr + i; /* * Fixed counters are supported if the counter is less than the @@ -380,12 +418,12 @@ static void guest_rd_wr_counters(uint32_t base_msr, uint8_t nr_possible_counters * KVM drops writes to MSR_P6_PERFCTR[0|1] if the counters are * unsupported, i.e. doesn't #GP and reads back '0'. */ - const uint64_t expected_val = expect_success ? test_val : 0; + const u64 expected_val = expect_success ? test_val : 0; const bool expect_gp = !expect_success && msr != MSR_P6_PERFCTR0 && msr != MSR_P6_PERFCTR1; - uint32_t rdpmc_idx; - uint8_t vector; - uint64_t val; + u32 rdpmc_idx; + u8 vector; + u64 val; vector = wrmsr_safe(msr, test_val); GUEST_ASSERT_PMC_MSR_ACCESS(WRMSR, msr, expect_gp, vector); @@ -423,9 +461,9 @@ static void guest_rd_wr_counters(uint32_t base_msr, uint8_t nr_possible_counters static void guest_test_gp_counters(void) { - uint8_t pmu_version = guest_get_pmu_version(); - uint8_t nr_gp_counters = 0; - uint32_t base_msr; + u8 pmu_version = guest_get_pmu_version(); + u8 nr_gp_counters = 0; + u32 base_msr; if (pmu_version) nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); @@ -439,7 +477,7 @@ static void guest_test_gp_counters(void) * counters, of which there are none. */ if (pmu_version > 1) { - uint64_t global_ctrl = rdmsr(MSR_CORE_PERF_GLOBAL_CTRL); + u64 global_ctrl = rdmsr(MSR_CORE_PERF_GLOBAL_CTRL); if (nr_gp_counters) GUEST_ASSERT_EQ(global_ctrl, GENMASK_ULL(nr_gp_counters - 1, 0)); @@ -457,8 +495,8 @@ static void guest_test_gp_counters(void) GUEST_DONE(); } -static void test_gp_counters(uint8_t pmu_version, uint64_t perf_capabilities, - uint8_t nr_gp_counters) +static void test_gp_counters(u8 pmu_version, u64 perf_capabilities, + u8 nr_gp_counters) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; @@ -476,9 +514,9 @@ static void test_gp_counters(uint8_t pmu_version, uint64_t perf_capabilities, static void guest_test_fixed_counters(void) { - uint64_t supported_bitmask = 0; - uint8_t nr_fixed_counters = 0; - uint8_t i; + u64 supported_bitmask = 0; + u8 nr_fixed_counters = 0; + u8 i; /* Fixed counters require Architectural vPMU Version 2+. */ if (guest_get_pmu_version() >= 2) @@ -495,8 +533,8 @@ static void guest_test_fixed_counters(void) nr_fixed_counters, supported_bitmask); for (i = 0; i < MAX_NR_FIXED_COUNTERS; i++) { - uint8_t vector; - uint64_t val; + u8 vector; + u64 val; if (i >= nr_fixed_counters && !(supported_bitmask & BIT_ULL(i))) { vector = wrmsr_safe(MSR_CORE_PERF_FIXED_CTR_CTRL, @@ -523,9 +561,8 @@ static void guest_test_fixed_counters(void) GUEST_DONE(); } -static void test_fixed_counters(uint8_t pmu_version, uint64_t perf_capabilities, - uint8_t nr_fixed_counters, - uint32_t supported_bitmask) +static void test_fixed_counters(u8 pmu_version, u64 perf_capabilities, + u8 nr_fixed_counters, u32 supported_bitmask) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; @@ -545,40 +582,67 @@ static void test_fixed_counters(uint8_t pmu_version, uint64_t perf_capabilities, static void test_intel_counters(void) { - uint8_t nr_arch_events = kvm_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); - uint8_t nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); - uint8_t nr_gp_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); - uint8_t pmu_version = kvm_cpu_property(X86_PROPERTY_PMU_VERSION); + u8 nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); + u8 nr_gp_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); + u8 pmu_version = kvm_cpu_property(X86_PROPERTY_PMU_VERSION); unsigned int i; - uint8_t v, j; - uint32_t k; + u8 v, j; + u32 k; - const uint64_t perf_caps[] = { + const u64 perf_caps[] = { 0, PMU_CAP_FW_WRITES, }; /* + * To keep the total runtime reasonable, test only a handful of select, + * semi-arbitrary values for the mask of unavailable PMU events. Test + * 0 (all events available) and all ones (no events available) as well + * as alternating bit sequencues, e.g. to detect if KVM is checking the + * wrong bit(s). + */ + const u32 unavailable_masks[] = { + 0x0, + 0xffffffffu, + 0xaaaaaaaau, + 0x55555555u, + 0xf0f0f0f0u, + 0x0f0f0f0fu, + 0xa0a0a0a0u, + 0x0a0a0a0au, + 0x50505050u, + 0x05050505u, + }; + + /* * Test up to PMU v5, which is the current maximum version defined by * Intel, i.e. is the last version that is guaranteed to be backwards * compatible with KVM's existing behavior. */ - uint8_t max_pmu_version = max_t(typeof(pmu_version), pmu_version, 5); + u8 max_pmu_version = max_t(typeof(pmu_version), pmu_version, 5); /* * Detect the existence of events that aren't supported by selftests. - * This will (obviously) fail any time the kernel adds support for a - * new event, but it's worth paying that price to keep the test fresh. + * This will (obviously) fail any time hardware adds support for a new + * event, but it's worth paying that price to keep the test fresh. */ - TEST_ASSERT(nr_arch_events <= NR_INTEL_ARCH_EVENTS, + TEST_ASSERT(this_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH) <= NR_INTEL_ARCH_EVENTS, "New architectural event(s) detected; please update this test (length = %u, mask = %x)", - nr_arch_events, kvm_cpu_property(X86_PROPERTY_PMU_EVENTS_MASK)); + this_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH), + this_cpu_property(X86_PROPERTY_PMU_EVENTS_MASK)); /* - * Force iterating over known arch events regardless of whether or not - * KVM/hardware supports a given event. + * Iterate over known arch events irrespective of KVM/hardware support + * to verify that KVM doesn't reject programming of events just because + * the *architectural* encoding is unsupported. Track which events are + * supported in hardware; the guest side will validate supported events + * count correctly, even if *enumeration* of the event is unsupported + * by KVM and/or isn't exposed to the guest. */ - nr_arch_events = max_t(typeof(nr_arch_events), nr_arch_events, NR_INTEL_ARCH_EVENTS); + for (i = 0; i < NR_INTEL_ARCH_EVENTS; i++) { + if (this_pmu_has(intel_event_to_feature(i).gp_event)) + hardware_pmu_arch_events |= BIT(i); + } for (v = 0; v <= max_pmu_version; v++) { for (i = 0; i < ARRAY_SIZE(perf_caps); i++) { @@ -587,16 +651,7 @@ static void test_intel_counters(void) pr_info("Testing arch events, PMU version %u, perf_caps = %lx\n", v, perf_caps[i]); - /* - * To keep the total runtime reasonable, test every - * possible non-zero, non-reserved bitmap combination - * only with the native PMU version and the full bit - * vector length. - */ - if (v == pmu_version) { - for (k = 1; k < (BIT(nr_arch_events) - 1); k++) - test_arch_events(v, perf_caps[i], nr_arch_events, k); - } + /* * Test single bits for all PMU version and lengths up * the number of events +1 (to verify KVM doesn't do @@ -604,12 +659,9 @@ static void test_intel_counters(void) * host length). Explicitly test a mask of '0' and all * ones i.e. all events being available and unavailable. */ - for (j = 0; j <= nr_arch_events + 1; j++) { - test_arch_events(v, perf_caps[i], j, 0); - test_arch_events(v, perf_caps[i], j, 0xff); - - for (k = 0; k < nr_arch_events; k++) - test_arch_events(v, perf_caps[i], j, BIT(k)); + for (j = 0; j <= NR_INTEL_ARCH_EVENTS + 1; j++) { + for (k = 1; k < ARRAY_SIZE(unavailable_masks); k++) + test_arch_events(v, perf_caps[i], j, unavailable_masks[k]); } pr_info("Testing GP counters, PMU version %u, perf_caps = %lx\n", diff --git a/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c index c15513cd74d1..c1232344fda8 100644 --- a/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c @@ -53,11 +53,11 @@ static const struct __kvm_pmu_event_filter base_event_filter = { }; struct { - uint64_t loads; - uint64_t stores; - uint64_t loads_stores; - uint64_t branches_retired; - uint64_t instructions_retired; + u64 loads; + u64 stores; + u64 loads_stores; + u64 branches_retired; + u64 instructions_retired; } pmc_results; /* @@ -75,9 +75,9 @@ static void guest_gp_handler(struct ex_regs *regs) * * Return on success. GUEST_SYNC(0) on error. */ -static void check_msr(uint32_t msr, uint64_t bits_to_flip) +static void check_msr(u32 msr, u64 bits_to_flip) { - uint64_t v = rdmsr(msr) ^ bits_to_flip; + u64 v = rdmsr(msr) ^ bits_to_flip; wrmsr(msr, v); if (rdmsr(msr) != v) @@ -89,10 +89,10 @@ static void check_msr(uint32_t msr, uint64_t bits_to_flip) GUEST_SYNC(-EIO); } -static void run_and_measure_loop(uint32_t msr_base) +static void run_and_measure_loop(u32 msr_base) { - const uint64_t branches_retired = rdmsr(msr_base + 0); - const uint64_t insn_retired = rdmsr(msr_base + 1); + const u64 branches_retired = rdmsr(msr_base + 0); + const u64 insn_retired = rdmsr(msr_base + 1); __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); @@ -147,7 +147,7 @@ static void amd_guest_code(void) * 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) +static u64 run_vcpu_to_sync(struct kvm_vcpu *vcpu) { struct ucall uc; @@ -161,7 +161,7 @@ static uint64_t run_vcpu_to_sync(struct kvm_vcpu *vcpu) static void run_vcpu_and_sync_pmc_results(struct kvm_vcpu *vcpu) { - uint64_t r; + u64 r; memset(&pmc_results, 0, sizeof(pmc_results)); sync_global_to_guest(vcpu->vm, pmc_results); @@ -182,7 +182,7 @@ static void run_vcpu_and_sync_pmc_results(struct kvm_vcpu *vcpu) */ static bool sanity_check_pmu(struct kvm_vcpu *vcpu) { - uint64_t r; + u64 r; vm_install_exception_handler(vcpu->vm, GP_VECTOR, guest_gp_handler); r = run_vcpu_to_sync(vcpu); @@ -195,7 +195,7 @@ static bool sanity_check_pmu(struct kvm_vcpu *vcpu) * Remove the first occurrence of 'event' (if any) from the filter's * event list. */ -static void remove_event(struct __kvm_pmu_event_filter *f, uint64_t event) +static void remove_event(struct __kvm_pmu_event_filter *f, u64 event) { bool found = false; int i; @@ -212,10 +212,12 @@ static void remove_event(struct __kvm_pmu_event_filter *f, uint64_t event) #define ASSERT_PMC_COUNTING_INSTRUCTIONS() \ do { \ - uint64_t br = pmc_results.branches_retired; \ - uint64_t ir = pmc_results.instructions_retired; \ + u64 br = pmc_results.branches_retired; \ + u64 ir = pmc_results.instructions_retired; \ + bool br_matched = this_pmu_has_errata(BRANCHES_RETIRED_OVERCOUNT) ? \ + br >= NUM_BRANCHES : br == NUM_BRANCHES; \ \ - if (br && br != NUM_BRANCHES) \ + if (br && !br_matched) \ pr_info("%s: Branch instructions retired = %lu (expected %u)\n", \ __func__, br, NUM_BRANCHES); \ TEST_ASSERT(br, "%s: Branch instructions retired = %lu (expected > 0)", \ @@ -226,8 +228,8 @@ do { \ #define ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS() \ do { \ - uint64_t br = pmc_results.branches_retired; \ - uint64_t ir = pmc_results.instructions_retired; \ + u64 br = pmc_results.branches_retired; \ + u64 ir = pmc_results.instructions_retired; \ \ TEST_ASSERT(!br, "%s: Branch instructions retired = %lu (expected 0)", \ __func__, br); \ @@ -359,7 +361,8 @@ static bool use_intel_pmu(void) */ static bool use_amd_pmu(void) { - return host_cpu_is_amd && kvm_cpu_family() >= 0x17; + return (host_cpu_is_amd && kvm_cpu_family() >= 0x17) || + host_cpu_is_hygon; } /* @@ -375,7 +378,7 @@ static bool use_amd_pmu(void) static bool supports_event_mem_inst_retired(void) { - uint32_t eax, ebx, ecx, edx; + u32 eax, ebx, ecx, edx; cpuid(1, &eax, &ebx, &ecx, &edx); if (x86_family(eax) == 0x6) { @@ -412,15 +415,15 @@ static bool supports_event_mem_inst_retired(void) #define EXCLUDE_MASKED_ENTRY(event_select, mask, match) \ KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, true) -static void masked_events_guest_test(uint32_t msr_base) +static void masked_events_guest_test(u32 msr_base) { /* * The actual value of the counters don't determine the outcome of * the test. Only that they are zero or non-zero. */ - const uint64_t loads = rdmsr(msr_base + 0); - const uint64_t stores = rdmsr(msr_base + 1); - const uint64_t loads_stores = rdmsr(msr_base + 2); + const u64 loads = rdmsr(msr_base + 0); + const u64 stores = rdmsr(msr_base + 1); + const u64 loads_stores = rdmsr(msr_base + 2); int val; @@ -473,7 +476,7 @@ static void amd_masked_events_guest_code(void) } static void run_masked_events_test(struct kvm_vcpu *vcpu, - const uint64_t masked_events[], + const u64 masked_events[], const int nmasked_events) { struct __kvm_pmu_event_filter f = { @@ -482,7 +485,7 @@ static void run_masked_events_test(struct kvm_vcpu *vcpu, .flags = KVM_PMU_EVENT_FLAG_MASKED_EVENTS, }; - memcpy(f.events, masked_events, sizeof(uint64_t) * nmasked_events); + memcpy(f.events, masked_events, sizeof(u64) * nmasked_events); test_with_filter(vcpu, &f); } @@ -491,12 +494,12 @@ static void run_masked_events_test(struct kvm_vcpu *vcpu, #define ALLOW_LOADS_STORES BIT(2) struct masked_events_test { - uint64_t intel_events[MAX_TEST_EVENTS]; - uint64_t intel_event_end; - uint64_t amd_events[MAX_TEST_EVENTS]; - uint64_t amd_event_end; + u64 intel_events[MAX_TEST_EVENTS]; + u64 intel_event_end; + u64 amd_events[MAX_TEST_EVENTS]; + u64 amd_event_end; const char *msg; - uint32_t flags; + u32 flags; }; /* @@ -579,9 +582,9 @@ const struct masked_events_test test_cases[] = { }; static int append_test_events(const struct masked_events_test *test, - uint64_t *events, int nevents) + u64 *events, int nevents) { - const uint64_t *evts; + const u64 *evts; int i; evts = use_intel_pmu() ? test->intel_events : test->amd_events; @@ -600,7 +603,7 @@ static bool bool_eq(bool a, bool b) return a == b; } -static void run_masked_events_tests(struct kvm_vcpu *vcpu, uint64_t *events, +static void run_masked_events_tests(struct kvm_vcpu *vcpu, u64 *events, int nevents) { int ntests = ARRAY_SIZE(test_cases); @@ -627,7 +630,7 @@ static void run_masked_events_tests(struct kvm_vcpu *vcpu, uint64_t *events, } } -static void add_dummy_events(uint64_t *events, int nevents) +static void add_dummy_events(u64 *events, int nevents) { int i; @@ -647,7 +650,7 @@ static void add_dummy_events(uint64_t *events, int nevents) static void test_masked_events(struct kvm_vcpu *vcpu) { int nevents = KVM_PMU_EVENT_FILTER_MAX_EVENTS - MAX_TEST_EVENTS; - uint64_t events[KVM_PMU_EVENT_FILTER_MAX_EVENTS]; + u64 events[KVM_PMU_EVENT_FILTER_MAX_EVENTS]; /* Run the test cases against a sparse PMU event filter. */ run_masked_events_tests(vcpu, events, 0); @@ -665,8 +668,8 @@ static int set_pmu_event_filter(struct kvm_vcpu *vcpu, return __vm_ioctl(vcpu->vm, KVM_SET_PMU_EVENT_FILTER, f); } -static int set_pmu_single_event_filter(struct kvm_vcpu *vcpu, uint64_t event, - uint32_t flags, uint32_t action) +static int set_pmu_single_event_filter(struct kvm_vcpu *vcpu, u64 event, + u32 flags, u32 action) { struct __kvm_pmu_event_filter f = { .nevents = 1, @@ -682,9 +685,9 @@ static int set_pmu_single_event_filter(struct kvm_vcpu *vcpu, uint64_t event, static void test_filter_ioctl(struct kvm_vcpu *vcpu) { - uint8_t nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); + u8 nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); struct __kvm_pmu_event_filter f; - uint64_t e = ~0ul; + u64 e = ~0ul; int r; /* @@ -726,7 +729,7 @@ static void test_filter_ioctl(struct kvm_vcpu *vcpu) TEST_ASSERT(!r, "Masking non-existent fixed counters should be allowed"); } -static void intel_run_fixed_counter_guest_code(uint8_t idx) +static void intel_run_fixed_counter_guest_code(u8 idx) { for (;;) { wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); @@ -742,8 +745,8 @@ static void intel_run_fixed_counter_guest_code(uint8_t idx) } } -static uint64_t test_with_fixed_counter_filter(struct kvm_vcpu *vcpu, - uint32_t action, uint32_t bitmap) +static u64 test_with_fixed_counter_filter(struct kvm_vcpu *vcpu, + u32 action, u32 bitmap) { struct __kvm_pmu_event_filter f = { .action = action, @@ -754,9 +757,9 @@ static uint64_t test_with_fixed_counter_filter(struct kvm_vcpu *vcpu, return run_vcpu_to_sync(vcpu); } -static uint64_t test_set_gp_and_fixed_event_filter(struct kvm_vcpu *vcpu, - uint32_t action, - uint32_t bitmap) +static u64 test_set_gp_and_fixed_event_filter(struct kvm_vcpu *vcpu, + u32 action, + u32 bitmap) { struct __kvm_pmu_event_filter f = base_event_filter; @@ -767,12 +770,12 @@ static uint64_t test_set_gp_and_fixed_event_filter(struct kvm_vcpu *vcpu, return run_vcpu_to_sync(vcpu); } -static void __test_fixed_counter_bitmap(struct kvm_vcpu *vcpu, uint8_t idx, - uint8_t nr_fixed_counters) +static void __test_fixed_counter_bitmap(struct kvm_vcpu *vcpu, u8 idx, + u8 nr_fixed_counters) { unsigned int i; - uint32_t bitmap; - uint64_t count; + u32 bitmap; + u64 count; TEST_ASSERT(nr_fixed_counters < sizeof(bitmap) * 8, "Invalid nr_fixed_counters"); @@ -812,10 +815,10 @@ static void __test_fixed_counter_bitmap(struct kvm_vcpu *vcpu, uint8_t idx, static void test_fixed_counter_bitmap(void) { - uint8_t nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); + u8 nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); struct kvm_vm *vm; struct kvm_vcpu *vcpu; - uint8_t idx; + u8 idx; /* * Check that pmu_event_filter works as expected when it's applied to diff --git a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c index 82a8d88b5338..1d2f5d4fd45d 100644 --- a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c +++ b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c @@ -23,13 +23,13 @@ #include <processor.h> #define BASE_DATA_SLOT 10 -#define BASE_DATA_GPA ((uint64_t)(1ull << 32)) -#define PER_CPU_DATA_SIZE ((uint64_t)(SZ_2M + PAGE_SIZE)) +#define BASE_DATA_GPA ((u64)(1ull << 32)) +#define PER_CPU_DATA_SIZE ((u64)(SZ_2M + PAGE_SIZE)) /* Horrific macro so that the line info is captured accurately :-( */ #define memcmp_g(gpa, pattern, size) \ do { \ - uint8_t *mem = (uint8_t *)gpa; \ + u8 *mem = (u8 *)gpa; \ size_t i; \ \ for (i = 0; i < size; i++) \ @@ -38,7 +38,7 @@ do { \ pattern, i, gpa + i, mem[i]); \ } while (0) -static void memcmp_h(uint8_t *mem, uint64_t gpa, uint8_t pattern, size_t size) +static void memcmp_h(u8 *mem, gpa_t gpa, u8 pattern, size_t size) { size_t i; @@ -70,13 +70,13 @@ enum ucall_syncs { SYNC_PRIVATE, }; -static void guest_sync_shared(uint64_t gpa, uint64_t size, - uint8_t current_pattern, uint8_t new_pattern) +static void guest_sync_shared(gpa_t gpa, u64 size, + u8 current_pattern, u8 new_pattern) { GUEST_SYNC5(SYNC_SHARED, gpa, size, current_pattern, new_pattern); } -static void guest_sync_private(uint64_t gpa, uint64_t size, uint8_t pattern) +static void guest_sync_private(gpa_t gpa, u64 size, u8 pattern) { GUEST_SYNC4(SYNC_PRIVATE, gpa, size, pattern); } @@ -86,10 +86,10 @@ static void guest_sync_private(uint64_t gpa, uint64_t size, uint8_t pattern) #define MAP_GPA_SHARED BIT(1) #define MAP_GPA_DO_FALLOCATE BIT(2) -static void guest_map_mem(uint64_t gpa, uint64_t size, bool map_shared, +static void guest_map_mem(gpa_t gpa, u64 size, bool map_shared, bool do_fallocate) { - uint64_t flags = MAP_GPA_SET_ATTRIBUTES; + u64 flags = MAP_GPA_SET_ATTRIBUTES; if (map_shared) flags |= MAP_GPA_SHARED; @@ -98,19 +98,19 @@ static void guest_map_mem(uint64_t gpa, uint64_t size, bool map_shared, kvm_hypercall_map_gpa_range(gpa, size, flags); } -static void guest_map_shared(uint64_t gpa, uint64_t size, bool do_fallocate) +static void guest_map_shared(gpa_t gpa, u64 size, bool do_fallocate) { guest_map_mem(gpa, size, true, do_fallocate); } -static void guest_map_private(uint64_t gpa, uint64_t size, bool do_fallocate) +static void guest_map_private(gpa_t gpa, u64 size, bool do_fallocate) { guest_map_mem(gpa, size, false, do_fallocate); } struct { - uint64_t offset; - uint64_t size; + u64 offset; + u64 size; } static const test_ranges[] = { GUEST_STAGE(0, PAGE_SIZE), GUEST_STAGE(0, SZ_2M), @@ -119,11 +119,11 @@ struct { GUEST_STAGE(SZ_2M, PAGE_SIZE), }; -static void guest_test_explicit_conversion(uint64_t base_gpa, bool do_fallocate) +static void guest_test_explicit_conversion(u64 base_gpa, bool do_fallocate) { - const uint8_t def_p = 0xaa; - const uint8_t init_p = 0xcc; - uint64_t j; + const u8 def_p = 0xaa; + const u8 init_p = 0xcc; + u64 j; int i; /* Memory should be shared by default. */ @@ -134,12 +134,12 @@ static void guest_test_explicit_conversion(uint64_t base_gpa, bool do_fallocate) memcmp_g(base_gpa, init_p, PER_CPU_DATA_SIZE); for (i = 0; i < ARRAY_SIZE(test_ranges); i++) { - uint64_t gpa = base_gpa + test_ranges[i].offset; - uint64_t size = test_ranges[i].size; - uint8_t p1 = 0x11; - uint8_t p2 = 0x22; - uint8_t p3 = 0x33; - uint8_t p4 = 0x44; + gpa_t gpa = base_gpa + test_ranges[i].offset; + u64 size = test_ranges[i].size; + u8 p1 = 0x11; + u8 p2 = 0x22; + u8 p3 = 0x33; + u8 p4 = 0x44; /* * Set the test region to pattern one to differentiate it from @@ -214,10 +214,10 @@ skip: } } -static void guest_punch_hole(uint64_t gpa, uint64_t size) +static void guest_punch_hole(gpa_t gpa, u64 size) { /* "Mapping" memory shared via fallocate() is done via PUNCH_HOLE. */ - uint64_t flags = MAP_GPA_SHARED | MAP_GPA_DO_FALLOCATE; + u64 flags = MAP_GPA_SHARED | MAP_GPA_DO_FALLOCATE; kvm_hypercall_map_gpa_range(gpa, size, flags); } @@ -227,9 +227,9 @@ static void guest_punch_hole(uint64_t gpa, uint64_t size) * proper conversion. Freeing (PUNCH_HOLE) should zap SPTEs, and reallocating * (subsequent fault) should zero memory. */ -static void guest_test_punch_hole(uint64_t base_gpa, bool precise) +static void guest_test_punch_hole(u64 base_gpa, bool precise) { - const uint8_t init_p = 0xcc; + const u8 init_p = 0xcc; int i; /* @@ -239,8 +239,8 @@ static void guest_test_punch_hole(uint64_t base_gpa, bool precise) guest_map_private(base_gpa, PER_CPU_DATA_SIZE, false); for (i = 0; i < ARRAY_SIZE(test_ranges); i++) { - uint64_t gpa = base_gpa + test_ranges[i].offset; - uint64_t size = test_ranges[i].size; + gpa_t gpa = base_gpa + test_ranges[i].offset; + u64 size = test_ranges[i].size; /* * Free all memory before each iteration, even for the !precise @@ -268,7 +268,7 @@ static void guest_test_punch_hole(uint64_t base_gpa, bool precise) } } -static void guest_code(uint64_t base_gpa) +static void guest_code(u64 base_gpa) { /* * Run the conversion test twice, with and without doing fallocate() on @@ -289,8 +289,8 @@ static void guest_code(uint64_t base_gpa) static void handle_exit_hypercall(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; - uint64_t gpa = run->hypercall.args[0]; - uint64_t size = run->hypercall.args[1] * PAGE_SIZE; + gpa_t gpa = run->hypercall.args[0]; + u64 size = run->hypercall.args[1] * PAGE_SIZE; bool set_attributes = run->hypercall.args[2] & MAP_GPA_SET_ATTRIBUTES; bool map_shared = run->hypercall.args[2] & MAP_GPA_SHARED; bool do_fallocate = run->hypercall.args[2] & MAP_GPA_DO_FALLOCATE; @@ -337,7 +337,7 @@ static void *__test_mem_conversions(void *__vcpu) case UCALL_ABORT: REPORT_GUEST_ASSERT(uc); case UCALL_SYNC: { - uint64_t gpa = uc.args[1]; + gpa_t gpa = uc.args[1]; size_t size = uc.args[2]; size_t i; @@ -347,7 +347,7 @@ static void *__test_mem_conversions(void *__vcpu) for (i = 0; i < size; i += vm->page_size) { size_t nr_bytes = min_t(size_t, vm->page_size, size - i); - uint8_t *hva = addr_gpa2hva(vm, gpa + i); + u8 *hva = addr_gpa2hva(vm, gpa + i); /* In all cases, the host should observe the shared data. */ memcmp_h(hva, gpa + i, uc.args[3], nr_bytes); @@ -366,8 +366,8 @@ static void *__test_mem_conversions(void *__vcpu) } } -static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t nr_vcpus, - uint32_t nr_memslots) +static void test_mem_conversions(enum vm_mem_backing_src_type src_type, u32 nr_vcpus, + u32 nr_memslots) { /* * Allocate enough memory so that each vCPU's chunk of memory can be @@ -380,7 +380,7 @@ static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; pthread_t threads[KVM_MAX_VCPUS]; struct kvm_vm *vm; - int memfd, i, r; + int memfd, i; const struct vm_shape shape = { .mode = VM_MODE_DEFAULT, @@ -402,7 +402,7 @@ static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t KVM_MEM_GUEST_MEMFD, memfd, slot_size * i); for (i = 0; i < nr_vcpus; i++) { - uint64_t gpa = BASE_DATA_GPA + i * per_cpu_size; + gpa_t gpa = BASE_DATA_GPA + i * per_cpu_size; vcpu_args_set(vcpus[i], 1, gpa); @@ -428,11 +428,8 @@ static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t * should prevent the VM from being fully destroyed until the last * reference to the guest_memfd is also put. */ - r = fallocate(memfd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, memfd_size); - TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r)); - - r = fallocate(memfd, FALLOC_FL_KEEP_SIZE, 0, memfd_size); - TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r)); + kvm_fallocate(memfd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, memfd_size); + kvm_fallocate(memfd, FALLOC_FL_KEEP_SIZE, 0, memfd_size); close(memfd); } @@ -453,8 +450,8 @@ static void usage(const char *cmd) int main(int argc, char *argv[]) { enum vm_mem_backing_src_type src_type = DEFAULT_VM_MEM_SRC; - uint32_t nr_memslots = 1; - uint32_t nr_vcpus = 1; + u32 nr_memslots = 1; + u32 nr_vcpus = 1; int opt; TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)); diff --git a/tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c b/tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c index 13e72fcec8dd..10db9fe6d906 100644 --- a/tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c +++ b/tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c @@ -17,17 +17,17 @@ #define EXITS_TEST_SIZE (EXITS_TEST_NPAGES * PAGE_SIZE) #define EXITS_TEST_SLOT 10 -static uint64_t guest_repeatedly_read(void) +static u64 guest_repeatedly_read(void) { - volatile uint64_t value; + volatile u64 value; while (true) - value = *((uint64_t *) EXITS_TEST_GVA); + value = *((u64 *)EXITS_TEST_GVA); return value; } -static uint32_t run_vcpu_get_exit_reason(struct kvm_vcpu *vcpu) +static u32 run_vcpu_get_exit_reason(struct kvm_vcpu *vcpu) { int r; @@ -50,7 +50,7 @@ static void test_private_access_memslot_deleted(void) struct kvm_vcpu *vcpu; pthread_t vm_thread; void *thread_return; - uint32_t exit_reason; + u32 exit_reason; vm = vm_create_shape_with_one_vcpu(protected_vm_shape, &vcpu, guest_repeatedly_read); @@ -72,7 +72,7 @@ static void test_private_access_memslot_deleted(void) vm_mem_region_delete(vm, EXITS_TEST_SLOT); pthread_join(vm_thread, &thread_return); - exit_reason = (uint32_t)(uint64_t)thread_return; + exit_reason = (u32)(u64)thread_return; TEST_ASSERT_EQ(exit_reason, KVM_EXIT_MEMORY_FAULT); TEST_ASSERT_EQ(vcpu->run->memory_fault.flags, KVM_MEMORY_EXIT_FLAG_PRIVATE); @@ -86,7 +86,7 @@ static void test_private_access_memslot_not_private(void) { struct kvm_vm *vm; struct kvm_vcpu *vcpu; - uint32_t exit_reason; + u32 exit_reason; vm = vm_create_shape_with_one_vcpu(protected_vm_shape, &vcpu, guest_repeatedly_read); diff --git a/tools/testing/selftests/kvm/x86/set_boot_cpu_id.c b/tools/testing/selftests/kvm/x86/set_boot_cpu_id.c index 49913784bc82..8e3898646c69 100644 --- a/tools/testing/selftests/kvm/x86/set_boot_cpu_id.c +++ b/tools/testing/selftests/kvm/x86/set_boot_cpu_id.c @@ -86,11 +86,11 @@ static void run_vcpu(struct kvm_vcpu *vcpu) } } -static struct kvm_vm *create_vm(uint32_t nr_vcpus, uint32_t bsp_vcpu_id, +static struct kvm_vm *create_vm(u32 nr_vcpus, u32 bsp_vcpu_id, struct kvm_vcpu *vcpus[]) { struct kvm_vm *vm; - uint32_t i; + u32 i; vm = vm_create(nr_vcpus); @@ -104,7 +104,7 @@ static struct kvm_vm *create_vm(uint32_t nr_vcpus, uint32_t bsp_vcpu_id, return vm; } -static void run_vm_bsp(uint32_t bsp_vcpu_id) +static void run_vm_bsp(u32 bsp_vcpu_id) { struct kvm_vcpu *vcpus[2]; struct kvm_vm *vm; diff --git a/tools/testing/selftests/kvm/x86/set_sregs_test.c b/tools/testing/selftests/kvm/x86/set_sregs_test.c index f4095a3d1278..8e654cc9ab16 100644 --- a/tools/testing/selftests/kvm/x86/set_sregs_test.c +++ b/tools/testing/selftests/kvm/x86/set_sregs_test.c @@ -46,9 +46,9 @@ do { \ X86_CR4_MCE | X86_CR4_PGE | X86_CR4_PCE | \ X86_CR4_OSFXSR | X86_CR4_OSXMMEXCPT) -static uint64_t calc_supported_cr4_feature_bits(void) +static u64 calc_supported_cr4_feature_bits(void) { - uint64_t cr4 = KVM_ALWAYS_ALLOWED_CR4; + u64 cr4 = KVM_ALWAYS_ALLOWED_CR4; if (kvm_cpu_has(X86_FEATURE_UMIP)) cr4 |= X86_CR4_UMIP; @@ -74,7 +74,7 @@ static uint64_t calc_supported_cr4_feature_bits(void) return cr4; } -static void test_cr_bits(struct kvm_vcpu *vcpu, uint64_t cr4) +static void test_cr_bits(struct kvm_vcpu *vcpu, u64 cr4) { struct kvm_sregs sregs; int rc, i; diff --git a/tools/testing/selftests/kvm/x86/sev_init2_tests.c b/tools/testing/selftests/kvm/x86/sev_init2_tests.c index 3fb967f40c6a..8eeba2327c7c 100644 --- a/tools/testing/selftests/kvm/x86/sev_init2_tests.c +++ b/tools/testing/selftests/kvm/x86/sev_init2_tests.c @@ -28,12 +28,13 @@ int kvm_fd; u64 supported_vmsa_features; bool have_sev_es; +bool have_snp; static int __sev_ioctl(int vm_fd, int cmd_id, void *data) { struct kvm_sev_cmd cmd = { .id = cmd_id, - .data = (uint64_t)data, + .data = (u64)data, .sev_fd = open_sev_dev_path_or_exit(), }; int ret; @@ -83,6 +84,9 @@ void test_vm_types(void) if (have_sev_es) test_init2(KVM_X86_SEV_ES_VM, &(struct kvm_sev_init){}); + if (have_snp) + test_init2(KVM_X86_SNP_VM, &(struct kvm_sev_init){}); + test_init2_invalid(0, &(struct kvm_sev_init){}, "VM type is KVM_X86_DEFAULT_VM"); if (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)) @@ -90,7 +94,7 @@ void test_vm_types(void) "VM type is KVM_X86_SW_PROTECTED_VM"); } -void test_flags(uint32_t vm_type) +void test_flags(u32 vm_type) { int i; @@ -100,7 +104,7 @@ void test_flags(uint32_t vm_type) "invalid flag"); } -void test_features(uint32_t vm_type, uint64_t supported_features) +void test_features(u32 vm_type, u64 supported_features) { int i; @@ -138,15 +142,24 @@ int main(int argc, char *argv[]) "sev-es: KVM_CAP_VM_TYPES (%x) does not match cpuid (checking %x)", kvm_check_cap(KVM_CAP_VM_TYPES), 1 << KVM_X86_SEV_ES_VM); + have_snp = kvm_cpu_has(X86_FEATURE_SEV_SNP); + TEST_ASSERT(have_snp == !!(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SNP_VM)), + "sev-snp: KVM_CAP_VM_TYPES (%x) indicates SNP support (bit %d), but CPUID does not", + kvm_check_cap(KVM_CAP_VM_TYPES), KVM_X86_SNP_VM); + test_vm_types(); test_flags(KVM_X86_SEV_VM); if (have_sev_es) test_flags(KVM_X86_SEV_ES_VM); + if (have_snp) + test_flags(KVM_X86_SNP_VM); test_features(KVM_X86_SEV_VM, 0); if (have_sev_es) test_features(KVM_X86_SEV_ES_VM, supported_vmsa_features); + if (have_snp) + test_features(KVM_X86_SNP_VM, supported_vmsa_features); return 0; } diff --git a/tools/testing/selftests/kvm/x86/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86/sev_migrate_tests.c index 0a6dfba3905b..6b0928e69051 100644 --- a/tools/testing/selftests/kvm/x86/sev_migrate_tests.c +++ b/tools/testing/selftests/kvm/x86/sev_migrate_tests.c @@ -36,8 +36,6 @@ static struct kvm_vm *sev_vm_create(bool es) sev_vm_launch(vm, es ? SEV_POLICY_ES : 0); - if (es) - vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL); return vm; } diff --git a/tools/testing/selftests/kvm/x86/sev_smoke_test.c b/tools/testing/selftests/kvm/x86/sev_smoke_test.c index d97816dc476a..1a49ee391586 100644 --- a/tools/testing/selftests/kvm/x86/sev_smoke_test.c +++ b/tools/testing/selftests/kvm/x86/sev_smoke_test.c @@ -13,21 +13,61 @@ #include "linux/psp-sev.h" #include "sev.h" +static void guest_sev_test_msr(u32 msr) +{ + u64 val = rdmsr(msr); + + wrmsr(msr, val); + GUEST_ASSERT(val == rdmsr(msr)); +} + +#define guest_sev_test_reg(reg) \ +do { \ + u64 val = get_##reg(); \ + \ + set_##reg(val); \ + GUEST_ASSERT(val == get_##reg()); \ +} while (0) + +static void guest_sev_test_regs(void) +{ + guest_sev_test_msr(MSR_EFER); + guest_sev_test_reg(cr0); + guest_sev_test_reg(cr3); + guest_sev_test_reg(cr4); + guest_sev_test_reg(cr8); +} #define XFEATURE_MASK_X87_AVX (XFEATURE_MASK_FP | XFEATURE_MASK_SSE | XFEATURE_MASK_YMM) +static void guest_snp_code(void) +{ + u64 sev_msr = rdmsr(MSR_AMD64_SEV); + + GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_ENABLED); + GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_ES_ENABLED); + GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_SNP_ENABLED); + + guest_sev_test_regs(); + + wrmsr(MSR_AMD64_SEV_ES_GHCB, GHCB_MSR_TERM_REQ); + vmgexit(); +} + static void guest_sev_es_code(void) { /* TODO: Check CPUID after GHCB-based hypercall support is added. */ GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED); GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ES_ENABLED); + guest_sev_test_regs(); + /* * TODO: Add GHCB and ucall support for SEV-ES guests. For now, simply * force "termination" to signal "done" via the GHCB MSR protocol. */ wrmsr(MSR_AMD64_SEV_ES_GHCB, GHCB_MSR_TERM_REQ); - __asm__ __volatile__("rep; vmmcall"); + vmgexit(); } static void guest_sev_code(void) @@ -35,6 +75,8 @@ static void guest_sev_code(void) GUEST_ASSERT(this_cpu_has(X86_FEATURE_SEV)); GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED); + guest_sev_test_regs(); + GUEST_DONE(); } @@ -62,19 +104,19 @@ static void compare_xsave(u8 *from_host, u8 *from_guest) abort(); } -static void test_sync_vmsa(uint32_t policy) +static void test_sync_vmsa(u32 type, u64 policy) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; - vm_vaddr_t gva; + gva_t gva; void *hva; double x87val = M_PI; struct kvm_xsave __attribute__((aligned(64))) xsave = { 0 }; - vm = vm_sev_create_with_one_vcpu(KVM_X86_SEV_ES_VM, guest_code_xsave, &vcpu); - gva = vm_vaddr_alloc_shared(vm, PAGE_SIZE, KVM_UTIL_MIN_VADDR, - MEM_REGION_TEST_DATA); + vm = vm_sev_create_with_one_vcpu(type, guest_code_xsave, &vcpu); + gva = vm_alloc_shared(vm, PAGE_SIZE, KVM_UTIL_MIN_VADDR, + MEM_REGION_TEST_DATA); hva = addr_gva2hva(vm, gva); vcpu_args_set(vcpu, 1, gva); @@ -89,10 +131,10 @@ static void test_sync_vmsa(uint32_t policy) : "ymm4", "st", "st(1)", "st(2)", "st(3)", "st(4)", "st(5)", "st(6)", "st(7)"); vcpu_xsave_set(vcpu, &xsave); - vm_sev_launch(vm, SEV_POLICY_ES | policy, NULL); + vm_sev_launch(vm, policy, NULL); /* This page is shared, so make it decrypted. */ - memset(hva, 0, 4096); + memset(hva, 0, PAGE_SIZE); vcpu_run(vcpu); @@ -108,14 +150,12 @@ static void test_sync_vmsa(uint32_t policy) kvm_vm_free(vm); } -static void test_sev(void *guest_code, uint64_t policy) +static void test_sev(void *guest_code, u32 type, u64 policy) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct ucall uc; - uint32_t type = policy & SEV_POLICY_ES ? KVM_X86_SEV_ES_VM : KVM_X86_SEV_VM; - vm = vm_sev_create_with_one_vcpu(type, guest_code, &vcpu); /* TODO: Validate the measurement is as expected. */ @@ -124,7 +164,7 @@ static void test_sev(void *guest_code, uint64_t policy) for (;;) { vcpu_run(vcpu); - if (policy & SEV_POLICY_ES) { + if (is_sev_es_vm(vm)) { TEST_ASSERT(vcpu->run->exit_reason == KVM_EXIT_SYSTEM_EVENT, "Wanted SYSTEM_EVENT, got %s", exit_reason_str(vcpu->run->exit_reason)); @@ -161,16 +201,14 @@ static void guest_shutdown_code(void) __asm__ __volatile__("ud2"); } -static void test_sev_es_shutdown(void) +static void test_sev_shutdown(u32 type, u64 policy) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; - uint32_t type = KVM_X86_SEV_ES_VM; - vm = vm_sev_create_with_one_vcpu(type, guest_shutdown_code, &vcpu); - vm_sev_launch(vm, SEV_POLICY_ES, NULL); + vm_sev_launch(vm, policy, NULL); vcpu_run(vcpu); TEST_ASSERT(vcpu->run->exit_reason == KVM_EXIT_SHUTDOWN, @@ -180,27 +218,42 @@ static void test_sev_es_shutdown(void) kvm_vm_free(vm); } -int main(int argc, char *argv[]) +static void test_sev_smoke(void *guest, u32 type, u64 policy) { const u64 xf_mask = XFEATURE_MASK_X87_AVX; - TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV)); - - test_sev(guest_sev_code, SEV_POLICY_NO_DBG); - test_sev(guest_sev_code, 0); + if (type == KVM_X86_SNP_VM) + test_sev(guest, type, policy | SNP_POLICY_DBG); + else + test_sev(guest, type, policy | SEV_POLICY_NO_DBG); + test_sev(guest, type, policy); - if (kvm_cpu_has(X86_FEATURE_SEV_ES)) { - test_sev(guest_sev_es_code, SEV_POLICY_ES | SEV_POLICY_NO_DBG); - test_sev(guest_sev_es_code, SEV_POLICY_ES); + if (type == KVM_X86_SEV_VM) + return; - test_sev_es_shutdown(); + test_sev_shutdown(type, policy); - if (kvm_has_cap(KVM_CAP_XCRS) && - (xgetbv(0) & kvm_cpu_supported_xcr0() & xf_mask) == xf_mask) { - test_sync_vmsa(0); - test_sync_vmsa(SEV_POLICY_NO_DBG); - } + if (kvm_has_cap(KVM_CAP_XCRS) && + (xgetbv(0) & kvm_cpu_supported_xcr0() & xf_mask) == xf_mask) { + test_sync_vmsa(type, policy); + if (type == KVM_X86_SNP_VM) + test_sync_vmsa(type, policy | SNP_POLICY_DBG); + else + test_sync_vmsa(type, policy | SEV_POLICY_NO_DBG); } +} + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV)); + + test_sev_smoke(guest_sev_code, KVM_X86_SEV_VM, 0); + + if (kvm_cpu_has(X86_FEATURE_SEV_ES)) + test_sev_smoke(guest_sev_es_code, KVM_X86_SEV_ES_VM, SEV_POLICY_ES); + + if (kvm_cpu_has(X86_FEATURE_SEV_SNP)) + test_sev_smoke(guest_snp_code, KVM_X86_SNP_VM, snp_default_policy()); return 0; } diff --git a/tools/testing/selftests/kvm/x86/smaller_maxphyaddr_emulation_test.c b/tools/testing/selftests/kvm/x86/smaller_maxphyaddr_emulation_test.c index fabeeaddfb3a..3dca85e95478 100644 --- a/tools/testing/selftests/kvm/x86/smaller_maxphyaddr_emulation_test.c +++ b/tools/testing/selftests/kvm/x86/smaller_maxphyaddr_emulation_test.c @@ -20,8 +20,8 @@ static void guest_code(bool tdp_enabled) { - uint64_t error_code; - uint64_t vector; + u64 error_code; + u64 vector; vector = kvm_asm_safe_ec(FLDS_MEM_EAX, error_code, "a"(MEM_REGION_GVA)); @@ -47,9 +47,8 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct ucall uc; - uint64_t *pte; - uint64_t *hva; - uint64_t gpa; + u64 *hva; + gpa_t gpa; int rc; TEST_REQUIRE(kvm_has_cap(KVM_CAP_SMALLER_MAXPHYADDR)); @@ -73,8 +72,7 @@ int main(int argc, char *argv[]) hva = addr_gpa2hva(vm, MEM_REGION_GPA); memset(hva, 0, PAGE_SIZE); - pte = vm_get_page_table_entry(vm, MEM_REGION_GVA); - *pte |= BIT_ULL(MAXPHYADDR); + *vm_get_pte(vm, MEM_REGION_GVA) |= BIT_ULL(MAXPHYADDR); vcpu_run(vcpu); diff --git a/tools/testing/selftests/kvm/x86/smm_test.c b/tools/testing/selftests/kvm/x86/smm_test.c index 55c88d664a94..740051167dbd 100644 --- a/tools/testing/selftests/kvm/x86/smm_test.c +++ b/tools/testing/selftests/kvm/x86/smm_test.c @@ -14,13 +14,11 @@ #include "test_util.h" #include "kvm_util.h" +#include "smm.h" #include "vmx.h" #include "svm_util.h" -#define SMRAM_SIZE 65536 -#define SMRAM_MEMSLOT ((1 << 16) | 1) -#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) #define SMRAM_GPA 0x1000000 #define SMRAM_STAGE 0xfe @@ -36,13 +34,13 @@ * independent subset of asm here. * SMI handler always report back fixed stage SMRAM_STAGE. */ -uint8_t smi_handler[] = { +u8 smi_handler[] = { 0xb0, SMRAM_STAGE, /* mov $SMRAM_STAGE, %al */ 0xe4, SYNC_PORT, /* in $SYNC_PORT, %al */ 0x0f, 0xaa, /* rsm */ }; -static inline void sync_with_host(uint64_t phase) +static inline void sync_with_host(u64 phase) { asm volatile("in $" XSTR(SYNC_PORT)", %%al \n" : "+a" (phase)); @@ -67,7 +65,7 @@ static void guest_code(void *arg) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; - uint64_t apicbase = rdmsr(MSR_IA32_APICBASE); + u64 apicbase = rdmsr(MSR_IA32_APICBASE); struct svm_test_data *svm = arg; struct vmx_pages *vmx_pages = arg; @@ -113,21 +111,9 @@ static void guest_code(void *arg) sync_with_host(DONE); } -void inject_smi(struct kvm_vcpu *vcpu) -{ - struct kvm_vcpu_events events; - - vcpu_events_get(vcpu, &events); - - events.smi.pending = 1; - events.flags |= KVM_VCPUEVENT_VALID_SMM; - - vcpu_events_set(vcpu, &events); -} - int main(int argc, char *argv[]) { - vm_vaddr_t nested_gva = 0; + gva_t nested_gva = 0; struct kvm_vcpu *vcpu; struct kvm_regs regs; @@ -140,16 +126,7 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA, - SMRAM_MEMSLOT, SMRAM_PAGES, 0); - TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, SMRAM_GPA, SMRAM_MEMSLOT) - == SMRAM_GPA, "could not allocate guest physical addresses?"); - - memset(addr_gpa2hva(vm, SMRAM_GPA), 0x0, SMRAM_SIZE); - memcpy(addr_gpa2hva(vm, SMRAM_GPA) + 0x8000, smi_handler, - sizeof(smi_handler)); - - vcpu_set_msr(vcpu, MSR_IA32_SMBASE, SMRAM_GPA); + setup_smram(vm, vcpu, SMRAM_GPA, smi_handler, sizeof(smi_handler)); if (kvm_has_cap(KVM_CAP_NESTED_STATE)) { if (kvm_cpu_has(X86_FEATURE_SVM)) diff --git a/tools/testing/selftests/kvm/x86/state_test.c b/tools/testing/selftests/kvm/x86/state_test.c index 141b7fc0c965..409c6cc9f921 100644 --- a/tools/testing/selftests/kvm/x86/state_test.c +++ b/tools/testing/selftests/kvm/x86/state_test.c @@ -26,7 +26,9 @@ void svm_l2_guest_code(void) GUEST_SYNC(4); /* Exit to L1 */ vmcall(); + clgi(); GUEST_SYNC(6); + stgi(); /* Done, exit to L1 and never come back. */ vmcall(); } @@ -41,6 +43,8 @@ static void svm_l1_guest_code(struct svm_test_data *svm) generic_svm_setup(svm, svm_l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + vmcb->control.int_ctl |= (V_GIF_ENABLE_MASK | V_GIF_MASK); + GUEST_SYNC(3); run_guest(vmcb, svm->vmcb_gpa); GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); @@ -140,8 +144,8 @@ static void __attribute__((__flatten__)) guest_code(void *arg) GUEST_SYNC(1); if (this_cpu_has(X86_FEATURE_XSAVE)) { - uint64_t supported_xcr0 = this_cpu_supported_xcr0(); - uint8_t buffer[4096]; + u64 supported_xcr0 = this_cpu_supported_xcr0(); + u8 buffer[PAGE_SIZE]; memset(buffer, 0xcc, sizeof(buffer)); @@ -168,8 +172,8 @@ static void __attribute__((__flatten__)) guest_code(void *arg) } if (this_cpu_has(X86_FEATURE_MPX)) { - uint64_t bounds[2] = { 10, 0xffffffffull }; - uint64_t output[2] = { }; + u64 bounds[2] = { 10, 0xffffffffull }; + u64 output[2] = { }; GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_BNDREGS); GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_BNDCSR); @@ -222,10 +226,39 @@ static void __attribute__((__flatten__)) guest_code(void *arg) GUEST_DONE(); } +void svm_check_nested_state(int stage, struct kvm_x86_state *state) +{ + struct vmcb *vmcb = (struct vmcb *)state->nested.data.svm; + + if (kvm_cpu_has(X86_FEATURE_VGIF)) { + if (stage == 4) + TEST_ASSERT_EQ(!!(vmcb->control.int_ctl & V_GIF_MASK), 1); + if (stage == 6) + TEST_ASSERT_EQ(!!(vmcb->control.int_ctl & V_GIF_MASK), 0); + } + + if (kvm_cpu_has(X86_FEATURE_NRIPS)) { + /* + * GUEST_SYNC() causes IO emulation in KVM, in which case the + * RIP is advanced before exiting to userspace. Hence, the RIP + * in the saved state should be the same as nRIP saved by the + * CPU in the VMCB. + */ + if (stage == 6) + TEST_ASSERT_EQ(vmcb->control.next_rip, state->regs.rip); + } +} + +void check_nested_state(int stage, struct kvm_x86_state *state) +{ + if (kvm_has_cap(KVM_CAP_NESTED_STATE) && kvm_cpu_has(X86_FEATURE_SVM)) + svm_check_nested_state(stage, state); +} + int main(int argc, char *argv[]) { - uint64_t *xstate_bv, saved_xstate_bv; - vm_vaddr_t nested_gva = 0; + u64 *xstate_bv, saved_xstate_bv; + gva_t nested_gva = 0; struct kvm_cpuid2 empty_cpuid = {}; struct kvm_regs regs1, regs2; struct kvm_vcpu *vcpu, *vcpuN; @@ -278,6 +311,8 @@ int main(int argc, char *argv[]) kvm_vm_release(vm); + check_nested_state(stage, state); + /* Restore state in a new VM. */ vcpu = vm_recreate_with_one_vcpu(vm); vcpu_load_state(vcpu, state); @@ -296,7 +331,7 @@ int main(int argc, char *argv[]) * supported features, even if something goes awry in saving * the original snapshot. */ - xstate_bv = (void *)&((uint8_t *)state->xsave->region)[512]; + xstate_bv = (void *)&((u8 *)state->xsave->region)[512]; saved_xstate_bv = *xstate_bv; vcpuN = __vm_vcpu_add(vm, vcpu->id + 1); diff --git a/tools/testing/selftests/kvm/x86/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86/svm_int_ctl_test.c index 916e04248fbb..d3cc5e4f7883 100644 --- a/tools/testing/selftests/kvm/x86/svm_int_ctl_test.c +++ b/tools/testing/selftests/kvm/x86/svm_int_ctl_test.c @@ -42,10 +42,7 @@ static void l2_guest_code(struct svm_test_data *svm) x2apic_write_reg(APIC_ICR, APIC_DEST_SELF | APIC_INT_ASSERT | INTR_IRQ_NUMBER); - __asm__ __volatile__( - "sti\n" - "nop\n" - ); + sti_nop(); GUEST_ASSERT(vintr_irq_called); GUEST_ASSERT(intr_irq_called); @@ -85,7 +82,7 @@ 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; + gva_t svm_gva; struct kvm_vm *vm; struct ucall uc; diff --git a/tools/testing/selftests/kvm/x86/svm_lbr_nested_state.c b/tools/testing/selftests/kvm/x86/svm_lbr_nested_state.c new file mode 100644 index 000000000000..7fbfaa054c95 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/svm_lbr_nested_state.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2026, Google, Inc. + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" + + +#define L2_GUEST_STACK_SIZE 64 + +#define DO_BRANCH() do { asm volatile("jmp 1f\n 1: nop"); } while (0) + +struct lbr_branch { + u64 from, to; +}; + +volatile struct lbr_branch l2_branch; + +#define RECORD_AND_CHECK_BRANCH(b) \ +do { \ + wrmsr(MSR_IA32_DEBUGCTLMSR, DEBUGCTLMSR_LBR); \ + DO_BRANCH(); \ + (b)->from = rdmsr(MSR_IA32_LASTBRANCHFROMIP); \ + (b)->to = rdmsr(MSR_IA32_LASTBRANCHTOIP); \ + /* Disable LBR right after to avoid overriding the IPs */ \ + wrmsr(MSR_IA32_DEBUGCTLMSR, 0); \ + \ + GUEST_ASSERT_NE((b)->from, 0); \ + GUEST_ASSERT_NE((b)->to, 0); \ +} while (0) + +#define CHECK_BRANCH_MSRS(b) \ +do { \ + GUEST_ASSERT_EQ((b)->from, rdmsr(MSR_IA32_LASTBRANCHFROMIP)); \ + GUEST_ASSERT_EQ((b)->to, rdmsr(MSR_IA32_LASTBRANCHTOIP)); \ +} while (0) + +#define CHECK_BRANCH_VMCB(b, vmcb) \ +do { \ + GUEST_ASSERT_EQ((b)->from, vmcb->save.br_from); \ + GUEST_ASSERT_EQ((b)->to, vmcb->save.br_to); \ +} while (0) + +static void l2_guest_code(struct svm_test_data *svm) +{ + /* Record a branch, trigger save/restore, and make sure LBRs are intact */ + RECORD_AND_CHECK_BRANCH(&l2_branch); + GUEST_SYNC(true); + CHECK_BRANCH_MSRS(&l2_branch); + vmmcall(); +} + +static void l1_guest_code(struct svm_test_data *svm, bool nested_lbrv) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + struct lbr_branch l1_branch; + + /* Record a branch, trigger save/restore, and make sure LBRs are intact */ + RECORD_AND_CHECK_BRANCH(&l1_branch); + GUEST_SYNC(true); + CHECK_BRANCH_MSRS(&l1_branch); + + /* Run L2, which will also do the same */ + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + if (nested_lbrv) + vmcb->control.misc_ctl2 = SVM_MISC2_ENABLE_V_LBR; + else + vmcb->control.misc_ctl2 &= ~SVM_MISC2_ENABLE_V_LBR; + + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(svm->vmcb->control.exit_code == SVM_EXIT_VMMCALL); + + /* Trigger save/restore one more time before checking, just for kicks */ + GUEST_SYNC(true); + + /* + * If LBR_CTL_ENABLE is set, L1 and L2 should have separate LBR MSRs, so + * expect L1's LBRs to remain intact and L2 LBRs to be in the VMCB. + * Otherwise, the MSRs are shared between L1 & L2 so expect L2's LBRs. + */ + if (nested_lbrv) { + CHECK_BRANCH_MSRS(&l1_branch); + CHECK_BRANCH_VMCB(&l2_branch, vmcb); + } else { + CHECK_BRANCH_MSRS(&l2_branch); + } + GUEST_DONE(); +} + +void test_lbrv_nested_state(bool nested_lbrv) +{ + struct kvm_x86_state *state = NULL; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct ucall uc; + gva_t svm_gva; + + pr_info("Testing with nested LBRV %s\n", nested_lbrv ? "enabled" : "disabled"); + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + vcpu_alloc_svm(vm, &svm_gva); + vcpu_args_set(vcpu, 2, svm_gva, nested_lbrv); + + for (;;) { + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + /* Save the vCPU state and restore it in a new VM on sync */ + pr_info("Guest triggered save/restore.\n"); + state = vcpu_save_state(vcpu); + kvm_vm_release(vm); + vcpu = vm_recreate_with_one_vcpu(vm); + vcpu_load_state(vcpu, state); + kvm_x86_state_cleanup(state); + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + /* NOT REACHED */ + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + } +done: + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); + TEST_REQUIRE(kvm_is_lbrv_enabled()); + + test_lbrv_nested_state(/*nested_lbrv=*/false); + test_lbrv_nested_state(/*nested_lbrv=*/true); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86/svm_nested_clear_efer_svme.c b/tools/testing/selftests/kvm/x86/svm_nested_clear_efer_svme.c new file mode 100644 index 000000000000..6a89eaffc657 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/svm_nested_clear_efer_svme.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2026, Google LLC. + */ +#include "kvm_util.h" +#include "vmx.h" +#include "svm_util.h" +#include "kselftest.h" + + +#define L2_GUEST_STACK_SIZE 64 + +static void l2_guest_code(void) +{ + unsigned long efer = rdmsr(MSR_EFER); + + /* generic_svm_setup() initializes EFER_SVME set for L2 */ + GUEST_ASSERT(efer & EFER_SVME); + wrmsr(MSR_EFER, efer & ~EFER_SVME); + + /* Unreachable, L1 should be shutdown */ + GUEST_ASSERT(0); +} + +static void l1_guest_code(struct svm_test_data *svm) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + run_guest(svm->vmcb, svm->vmcb_gpa); + + /* Unreachable, L1 should be shutdown */ + GUEST_ASSERT(0); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + gva_t nested_gva = 0; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + + vcpu_alloc_svm(vm, &nested_gva); + vcpu_args_set(vcpu, 1, nested_gva); + + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_SHUTDOWN); + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86/svm_nested_shutdown_test.c b/tools/testing/selftests/kvm/x86/svm_nested_shutdown_test.c index 00135cbba35e..c6ea3d609a62 100644 --- a/tools/testing/selftests/kvm/x86/svm_nested_shutdown_test.c +++ b/tools/testing/selftests/kvm/x86/svm_nested_shutdown_test.c @@ -42,7 +42,7 @@ static void l1_guest_code(struct svm_test_data *svm, struct idt_entry *idt) int main(int argc, char *argv[]) { struct kvm_vcpu *vcpu; - vm_vaddr_t svm_gva; + gva_t svm_gva; struct kvm_vm *vm; TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); diff --git a/tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c index 7b6481d6c0d3..f72f11d4c4f8 100644 --- a/tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c +++ b/tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c @@ -76,7 +76,7 @@ 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) +static void l1_guest_code(struct svm_test_data *svm, u64 is_nmi, u64 idt_alt) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; @@ -103,7 +103,7 @@ static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t i run_guest(vmcb, svm->vmcb_gpa); __GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL, - "Expected VMMCAL #VMEXIT, got '0x%x', info1 = '0x%lx, info2 = '0x%lx'", + "Expected VMMCAL #VMEXIT, got '0x%lx', info1 = '0x%lx, info2 = '0x%lx'", vmcb->control.exit_code, vmcb->control.exit_info_1, vmcb->control.exit_info_2); @@ -133,7 +133,7 @@ static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t i run_guest(vmcb, svm->vmcb_gpa); __GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_HLT, - "Expected HLT #VMEXIT, got '0x%x', info1 = '0x%lx, info2 = '0x%lx'", + "Expected HLT #VMEXIT, got '0x%lx', info1 = '0x%lx, info2 = '0x%lx'", vmcb->control.exit_code, vmcb->control.exit_info_1, vmcb->control.exit_info_2); @@ -144,8 +144,8 @@ 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; + gva_t svm_gva; + gva_t idt_alt_vm; struct kvm_guest_debug debug; pr_info("Running %s test\n", is_nmi ? "NMI" : "soft int"); @@ -161,14 +161,14 @@ static void run_test(bool is_nmi) if (!is_nmi) { void *idt, *idt_alt; - idt_alt_vm = vm_vaddr_alloc_page(vm); + idt_alt_vm = vm_alloc_page(vm); idt_alt = addr_gva2hva(vm, idt_alt_vm); idt = addr_gva2hva(vm, vm->arch.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); + vcpu_args_set(vcpu, 3, svm_gva, (u64)is_nmi, (u64)idt_alt_vm); memset(&debug, 0, sizeof(debug)); vcpu_guest_debug_set(vcpu, &debug); diff --git a/tools/testing/selftests/kvm/x86/svm_nested_vmcb12_gpa.c b/tools/testing/selftests/kvm/x86/svm_nested_vmcb12_gpa.c new file mode 100644 index 000000000000..a4935ce2fb99 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/svm_nested_vmcb12_gpa.c @@ -0,0 +1,176 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2026, Google LLC. + */ +#include "kvm_util.h" +#include "vmx.h" +#include "svm_util.h" +#include "kselftest.h" +#include "kvm_test_harness.h" +#include "test_util.h" + + +#define L2_GUEST_STACK_SIZE 64 + +#define SYNC_GP 101 +#define SYNC_L2_STARTED 102 + +static unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + +static void guest_gp_handler(struct ex_regs *regs) +{ + GUEST_SYNC(SYNC_GP); +} + +static void l2_code(void) +{ + GUEST_SYNC(SYNC_L2_STARTED); + vmcall(); +} + +static void l1_vmrun(struct svm_test_data *svm, gpa_t gpa) +{ + generic_svm_setup(svm, l2_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + asm volatile ("vmrun %[gpa]" : : [gpa] "a" (gpa) : "memory"); +} + +static void l1_vmload(struct svm_test_data *svm, gpa_t gpa) +{ + generic_svm_setup(svm, l2_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + asm volatile ("vmload %[gpa]" : : [gpa] "a" (gpa) : "memory"); +} + +static void l1_vmsave(struct svm_test_data *svm, gpa_t gpa) +{ + generic_svm_setup(svm, l2_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + asm volatile ("vmsave %[gpa]" : : [gpa] "a" (gpa) : "memory"); +} + +static void l1_vmexit(struct svm_test_data *svm, gpa_t gpa) +{ + generic_svm_setup(svm, l2_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + run_guest(svm->vmcb, svm->vmcb_gpa); + GUEST_ASSERT(svm->vmcb->control.exit_code == SVM_EXIT_VMMCALL); + GUEST_DONE(); +} + +static u64 unmappable_gpa(struct kvm_vcpu *vcpu) +{ + struct userspace_mem_region *region; + u64 region_gpa_end, vm_gpa_end = 0; + int i; + + hash_for_each(vcpu->vm->regions.slot_hash, i, region, slot_node) { + region_gpa_end = region->region.guest_phys_addr + region->region.memory_size; + vm_gpa_end = max(vm_gpa_end, region_gpa_end); + } + + return vm_gpa_end; +} + +static void test_invalid_vmcb12(struct kvm_vcpu *vcpu) +{ + gva_t nested_gva = 0; + struct ucall uc; + + + vm_install_exception_handler(vcpu->vm, GP_VECTOR, guest_gp_handler); + vcpu_alloc_svm(vcpu->vm, &nested_gva); + vcpu_args_set(vcpu, 2, nested_gva, -1ULL); + vcpu_run(vcpu); + + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + TEST_ASSERT_EQ(get_ucall(vcpu, &uc), UCALL_SYNC); + TEST_ASSERT_EQ(uc.args[1], SYNC_GP); +} + +static void test_unmappable_vmcb12(struct kvm_vcpu *vcpu) +{ + gva_t nested_gva = 0; + + vcpu_alloc_svm(vcpu->vm, &nested_gva); + vcpu_args_set(vcpu, 2, nested_gva, unmappable_gpa(vcpu)); + vcpu_run(vcpu); + + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_INTERNAL_ERROR); + TEST_ASSERT_EQ(vcpu->run->emulation_failure.suberror, KVM_INTERNAL_ERROR_EMULATION); +} + +static void test_unmappable_vmcb12_vmexit(struct kvm_vcpu *vcpu) +{ + struct kvm_x86_state *state; + gva_t nested_gva = 0; + struct ucall uc; + + /* + * Enter L2 (with a legit vmcb12 GPA), then overwrite vmcb12 GPA with an + * unmappable GPA. KVM will fail to map vmcb12 on nested VM-Exit and + * cause a shutdown. + */ + vcpu_alloc_svm(vcpu->vm, &nested_gva); + vcpu_args_set(vcpu, 2, nested_gva, unmappable_gpa(vcpu)); + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + TEST_ASSERT_EQ(get_ucall(vcpu, &uc), UCALL_SYNC); + TEST_ASSERT_EQ(uc.args[1], SYNC_L2_STARTED); + + state = vcpu_save_state(vcpu); + state->nested.hdr.svm.vmcb_pa = unmappable_gpa(vcpu); + vcpu_load_state(vcpu, state); + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_SHUTDOWN); + + kvm_x86_state_cleanup(state); +} + +KVM_ONE_VCPU_TEST_SUITE(vmcb12_gpa); + +KVM_ONE_VCPU_TEST(vmcb12_gpa, vmrun_invalid, l1_vmrun) +{ + test_invalid_vmcb12(vcpu); +} + +KVM_ONE_VCPU_TEST(vmcb12_gpa, vmload_invalid, l1_vmload) +{ + test_invalid_vmcb12(vcpu); +} + +KVM_ONE_VCPU_TEST(vmcb12_gpa, vmsave_invalid, l1_vmsave) +{ + test_invalid_vmcb12(vcpu); +} + +KVM_ONE_VCPU_TEST(vmcb12_gpa, vmrun_unmappable, l1_vmrun) +{ + test_unmappable_vmcb12(vcpu); +} + +KVM_ONE_VCPU_TEST(vmcb12_gpa, vmload_unmappable, l1_vmload) +{ + test_unmappable_vmcb12(vcpu); +} + +KVM_ONE_VCPU_TEST(vmcb12_gpa, vmsave_unmappable, l1_vmsave) +{ + test_unmappable_vmcb12(vcpu); +} + +/* + * Invalid vmcb12_gpa cannot be test for #VMEXIT as KVM_SET_NESTED_STATE will + * reject it. + */ +KVM_ONE_VCPU_TEST(vmcb12_gpa, vmexit_unmappable, l1_vmexit) +{ + test_unmappable_vmcb12_vmexit(vcpu); +} + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); + + return test_harness_run(argc, argv); +} diff --git a/tools/testing/selftests/kvm/x86/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86/svm_vmcall_test.c index 8a62cca28cfb..b1887242f3b8 100644 --- a/tools/testing/selftests/kvm/x86/svm_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86/svm_vmcall_test.c @@ -36,7 +36,7 @@ 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; + gva_t svm_gva; struct kvm_vm *vm; TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); diff --git a/tools/testing/selftests/kvm/x86/sync_regs_test.c b/tools/testing/selftests/kvm/x86/sync_regs_test.c index 8fa3948b0170..e0c52321f87c 100644 --- a/tools/testing/selftests/kvm/x86/sync_regs_test.c +++ b/tools/testing/selftests/kvm/x86/sync_regs_test.c @@ -20,7 +20,7 @@ #include "kvm_util.h" #include "processor.h" -#define UCALL_PIO_PORT ((uint16_t)0x1000) +#define UCALL_PIO_PORT ((u16)0x1000) struct ucall uc_none = { .cmd = UCALL_NONE, diff --git a/tools/testing/selftests/kvm/x86/triple_fault_event_test.c b/tools/testing/selftests/kvm/x86/triple_fault_event_test.c index 56306a19144a..f1c488e0d497 100644 --- a/tools/testing/selftests/kvm/x86/triple_fault_event_test.c +++ b/tools/testing/selftests/kvm/x86/triple_fault_event_test.c @@ -72,13 +72,13 @@ int main(void) if (has_vmx) { - vm_vaddr_t vmx_pages_gva; + gva_t vmx_pages_gva; vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code_vmx); vcpu_alloc_vmx(vm, &vmx_pages_gva); vcpu_args_set(vcpu, 1, vmx_pages_gva); } else { - vm_vaddr_t svm_gva; + gva_t svm_gva; vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code_svm); vcpu_alloc_svm(vm, &svm_gva); diff --git a/tools/testing/selftests/kvm/x86/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86/tsc_msrs_test.c index 12b0964f4f13..91583969a14f 100644 --- a/tools/testing/selftests/kvm/x86/tsc_msrs_test.c +++ b/tools/testing/selftests/kvm/x86/tsc_msrs_test.c @@ -95,7 +95,7 @@ int main(void) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; - uint64_t val; + u64 val; ksft_print_header(); ksft_set_plan(5); diff --git a/tools/testing/selftests/kvm/x86/tsc_scaling_sync.c b/tools/testing/selftests/kvm/x86/tsc_scaling_sync.c index 59c7304f805e..59da8d4da607 100644 --- a/tools/testing/selftests/kvm/x86/tsc_scaling_sync.c +++ b/tools/testing/selftests/kvm/x86/tsc_scaling_sync.c @@ -21,10 +21,10 @@ pthread_spinlock_t create_lock; #define TEST_TSC_KHZ 2345678UL #define TEST_TSC_OFFSET 200000000 -uint64_t tsc_sync; +u64 tsc_sync; static void guest_code(void) { - uint64_t start_tsc, local_tsc, tmp; + u64 start_tsc, local_tsc, tmp; start_tsc = rdtsc(); do { diff --git a/tools/testing/selftests/kvm/x86/ucna_injection_test.c b/tools/testing/selftests/kvm/x86/ucna_injection_test.c index 57f157c06b39..df1ec8209c76 100644 --- a/tools/testing/selftests/kvm/x86/ucna_injection_test.c +++ b/tools/testing/selftests/kvm/x86/ucna_injection_test.c @@ -45,7 +45,7 @@ #define MCI_CTL2_RESERVED_BIT BIT_ULL(29) -static uint64_t supported_mcg_caps; +static u64 supported_mcg_caps; /* * Record states about the injected UCNA. @@ -53,30 +53,30 @@ static uint64_t supported_mcg_caps; * 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; +static volatile u64 i_ucna_rcvd; +static volatile u64 i_ucna_addr; +static volatile u64 ucna_addr; +static volatile u64 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; + u64 *p_i_ucna_rcvd; + u64 *p_i_ucna_addr; + u64 *p_ucna_addr; + u64 *p_ucna_addr2; }; static void verify_apic_base_addr(void) { - uint64_t msr = rdmsr(MSR_IA32_APICBASE); - uint64_t base = GET_APIC_BASE(msr); + u64 msr = rdmsr(MSR_IA32_APICBASE); + u64 base = GET_APIC_BASE(msr); GUEST_ASSERT(base == APIC_DEFAULT_GPA); } static void ucna_injection_guest_code(void) { - uint64_t ctl2; + u64 ctl2; verify_apic_base_addr(); xapic_enable(); @@ -86,7 +86,7 @@ static void ucna_injection_guest_code(void) wrmsr(MSR_IA32_MCx_CTL2(UCNA_BANK), ctl2 | MCI_CTL2_CMCI_EN); /* Enables interrupt in guest. */ - asm volatile("sti"); + sti(); /* Let user space inject the first UCNA */ GUEST_SYNC(SYNC_FIRST_UCNA); @@ -106,7 +106,7 @@ static void ucna_injection_guest_code(void) static void cmci_disabled_guest_code(void) { - uint64_t ctl2 = rdmsr(MSR_IA32_MCx_CTL2(UCNA_BANK)); + u64 ctl2 = rdmsr(MSR_IA32_MCx_CTL2(UCNA_BANK)); wrmsr(MSR_IA32_MCx_CTL2(UCNA_BANK), ctl2 | MCI_CTL2_CMCI_EN); GUEST_DONE(); @@ -114,7 +114,7 @@ static void cmci_disabled_guest_code(void) static void cmci_enabled_guest_code(void) { - uint64_t ctl2 = rdmsr(MSR_IA32_MCx_CTL2(UCNA_BANK)); + u64 ctl2 = rdmsr(MSR_IA32_MCx_CTL2(UCNA_BANK)); wrmsr(MSR_IA32_MCx_CTL2(UCNA_BANK), ctl2 | MCI_CTL2_RESERVED_BIT); GUEST_DONE(); @@ -145,14 +145,15 @@ static void run_vcpu_expect_gp(struct kvm_vcpu *vcpu) printf("vCPU received GP in guest.\n"); } -static void inject_ucna(struct kvm_vcpu *vcpu, uint64_t addr) { +static void inject_ucna(struct kvm_vcpu *vcpu, u64 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 | + u64 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; @@ -216,10 +217,10 @@ static void test_ucna_injection(struct kvm_vcpu *vcpu, struct thread_params *par { 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); + params->p_i_ucna_rcvd = (u64 *)addr_gva2hva(vm, (u64)&i_ucna_rcvd); + params->p_i_ucna_addr = (u64 *)addr_gva2hva(vm, (u64)&i_ucna_addr); + params->p_ucna_addr = (u64 *)addr_gva2hva(vm, (u64)&ucna_addr); + params->p_ucna_addr2 = (u64 *)addr_gva2hva(vm, (u64)&ucna_addr2); run_ucna_injection(params); @@ -242,7 +243,7 @@ static void test_ucna_injection(struct kvm_vcpu *vcpu, struct thread_params *par 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; + u64 mcg_caps = MCG_CTL_P | MCG_SER_P | MCG_LMCE_P | KVM_MAX_MCE_BANKS; if (enable_cmci_p) mcg_caps |= MCG_CMCI_P; @@ -250,7 +251,7 @@ static void setup_mce_cap(struct kvm_vcpu *vcpu, bool enable_cmci_p) 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, +static struct kvm_vcpu *create_vcpu_with_mce_cap(struct kvm_vm *vm, u32 vcpuid, bool enable_cmci_p, void *guest_code) { struct kvm_vcpu *vcpu = vm_vcpu_add(vm, vcpuid, guest_code); diff --git a/tools/testing/selftests/kvm/x86/userspace_io_test.c b/tools/testing/selftests/kvm/x86/userspace_io_test.c index 9481cbcf284f..9c5a87576c2e 100644 --- a/tools/testing/selftests/kvm/x86/userspace_io_test.c +++ b/tools/testing/selftests/kvm/x86/userspace_io_test.c @@ -10,7 +10,7 @@ #include "kvm_util.h" #include "processor.h" -static void guest_ins_port80(uint8_t *buffer, unsigned int count) +static void guest_ins_port80(u8 *buffer, unsigned int count) { unsigned long end; @@ -26,7 +26,7 @@ static void guest_ins_port80(uint8_t *buffer, unsigned int count) static void guest_code(void) { - uint8_t buffer[8192]; + u8 buffer[8192]; int i; /* @@ -85,7 +85,7 @@ int main(int argc, char *argv[]) regs.rcx = 1; if (regs.rcx == 3) regs.rcx = 8192; - memset((void *)run + run->io.data_offset, 0xaa, 4096); + memset((void *)run + run->io.data_offset, 0xaa, PAGE_SIZE); vcpu_regs_set(vcpu, ®s); } diff --git a/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c index 32b2794b78fe..2808ce727e5f 100644 --- a/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c +++ b/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c @@ -23,21 +23,21 @@ struct kvm_msr_filter filter_allow = { .nmsrs = 1, /* Test an MSR the kernel knows about. */ .base = MSR_IA32_XSS, - .bitmap = (uint8_t*)&deny_bits, + .bitmap = (u8 *)&deny_bits, }, { .flags = KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE, .nmsrs = 1, /* Test an MSR the kernel doesn't know about. */ .base = MSR_IA32_FLUSH_CMD, - .bitmap = (uint8_t*)&deny_bits, + .bitmap = (u8 *)&deny_bits, }, { .flags = KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE, .nmsrs = 1, /* Test a fabricated MSR that no one knows about. */ .base = MSR_NON_EXISTENT, - .bitmap = (uint8_t*)&deny_bits, + .bitmap = (u8 *)&deny_bits, }, }, }; @@ -49,7 +49,7 @@ struct kvm_msr_filter filter_fs = { .flags = KVM_MSR_FILTER_READ, .nmsrs = 1, .base = MSR_FS_BASE, - .bitmap = (uint8_t*)&deny_bits, + .bitmap = (u8 *)&deny_bits, }, }, }; @@ -61,12 +61,12 @@ struct kvm_msr_filter filter_gs = { .flags = KVM_MSR_FILTER_READ, .nmsrs = 1, .base = MSR_GS_BASE, - .bitmap = (uint8_t*)&deny_bits, + .bitmap = (u8 *)&deny_bits, }, }, }; -static uint64_t msr_non_existent_data; +static u64 msr_non_existent_data; static int guest_exception_count; static u32 msr_reads, msr_writes; @@ -77,7 +77,7 @@ static u8 bitmap_c0000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; static u8 bitmap_c0000000_read[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; static u8 bitmap_deadbeef[1] = { 0x1 }; -static void deny_msr(uint8_t *bitmap, u32 msr) +static void deny_msr(u8 *bitmap, u32 msr) { u32 idx = msr & (KVM_MSR_FILTER_MAX_BITMAP_SIZE - 1); @@ -142,26 +142,26 @@ struct kvm_msr_filter no_filter_deny = { * Note: Force test_rdmsr() to not be inlined to prevent the labels, * rdmsr_start and rdmsr_end, from being defined multiple times. */ -static noinline uint64_t test_rdmsr(uint32_t msr) +static noinline u64 test_rdmsr(u32 msr) { - uint32_t a, d; + u32 a, d; guest_exception_count = 0; __asm__ __volatile__("rdmsr_start: rdmsr; rdmsr_end:" : "=a"(a), "=d"(d) : "c"(msr) : "memory"); - return a | ((uint64_t) d << 32); + return a | ((u64)d << 32); } /* * Note: Force test_wrmsr() to not be inlined to prevent the labels, * wrmsr_start and wrmsr_end, from being defined multiple times. */ -static noinline void test_wrmsr(uint32_t msr, uint64_t value) +static noinline void test_wrmsr(u32 msr, u64 value) { - uint32_t a = value; - uint32_t d = value >> 32; + u32 a = value; + u32 d = value >> 32; guest_exception_count = 0; @@ -176,26 +176,26 @@ extern char wrmsr_start, wrmsr_end; * Note: Force test_em_rdmsr() to not be inlined to prevent the labels, * rdmsr_start and rdmsr_end, from being defined multiple times. */ -static noinline uint64_t test_em_rdmsr(uint32_t msr) +static noinline u64 test_em_rdmsr(u32 msr) { - uint32_t a, d; + u32 a, d; guest_exception_count = 0; __asm__ __volatile__(KVM_FEP "em_rdmsr_start: rdmsr; em_rdmsr_end:" : "=a"(a), "=d"(d) : "c"(msr) : "memory"); - return a | ((uint64_t) d << 32); + return a | ((u64)d << 32); } /* * Note: Force test_em_wrmsr() to not be inlined to prevent the labels, * wrmsr_start and wrmsr_end, from being defined multiple times. */ -static noinline void test_em_wrmsr(uint32_t msr, uint64_t value) +static noinline void test_em_wrmsr(u32 msr, u64 value) { - uint32_t a = value; - uint32_t d = value >> 32; + u32 a = value; + u32 d = value >> 32; guest_exception_count = 0; @@ -208,7 +208,7 @@ extern char em_wrmsr_start, em_wrmsr_end; static void guest_code_filter_allow(void) { - uint64_t data; + u64 data; /* * Test userspace intercepting rdmsr / wrmsr for MSR_IA32_XSS. @@ -328,7 +328,7 @@ static void guest_code_filter_deny(void) static void guest_code_permission_bitmap(void) { - uint64_t data; + u64 data; data = test_rdmsr(MSR_FS_BASE); GUEST_ASSERT(data == MSR_FS_BASE); @@ -343,6 +343,12 @@ static void guest_code_permission_bitmap(void) data = test_rdmsr(MSR_GS_BASE); GUEST_ASSERT(data == MSR_GS_BASE); + /* Access the MSRs again to ensure KVM has disabled interception.*/ + data = test_rdmsr(MSR_FS_BASE); + GUEST_ASSERT(data != MSR_FS_BASE); + data = test_rdmsr(MSR_GS_BASE); + GUEST_ASSERT(data != MSR_GS_BASE); + GUEST_DONE(); } @@ -385,7 +391,7 @@ static void check_for_guest_assert(struct kvm_vcpu *vcpu) } } -static void process_rdmsr(struct kvm_vcpu *vcpu, uint32_t msr_index) +static void process_rdmsr(struct kvm_vcpu *vcpu, u32 msr_index) { struct kvm_run *run = vcpu->run; @@ -417,7 +423,7 @@ static void process_rdmsr(struct kvm_vcpu *vcpu, uint32_t msr_index) } } -static void process_wrmsr(struct kvm_vcpu *vcpu, uint32_t msr_index) +static void process_wrmsr(struct kvm_vcpu *vcpu, u32 msr_index) { struct kvm_run *run = vcpu->run; @@ -458,7 +464,7 @@ static void process_ucall_done(struct kvm_vcpu *vcpu) uc.cmd, UCALL_DONE); } -static uint64_t process_ucall(struct kvm_vcpu *vcpu) +static u64 process_ucall(struct kvm_vcpu *vcpu) { struct ucall uc = {}; @@ -483,20 +489,20 @@ static uint64_t process_ucall(struct kvm_vcpu *vcpu) } static void run_guest_then_process_rdmsr(struct kvm_vcpu *vcpu, - uint32_t msr_index) + u32 msr_index) { vcpu_run(vcpu); process_rdmsr(vcpu, msr_index); } static void run_guest_then_process_wrmsr(struct kvm_vcpu *vcpu, - uint32_t msr_index) + u32 msr_index) { vcpu_run(vcpu); process_wrmsr(vcpu, msr_index); } -static uint64_t run_guest_then_process_ucall(struct kvm_vcpu *vcpu) +static u64 run_guest_then_process_ucall(struct kvm_vcpu *vcpu) { vcpu_run(vcpu); return process_ucall(vcpu); @@ -513,7 +519,7 @@ KVM_ONE_VCPU_TEST_SUITE(user_msr); KVM_ONE_VCPU_TEST(user_msr, msr_filter_allow, guest_code_filter_allow) { struct kvm_vm *vm = vcpu->vm; - uint64_t cmd; + u64 cmd; int rc; rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); @@ -682,6 +688,8 @@ KVM_ONE_VCPU_TEST(user_msr, msr_permission_bitmap, guest_code_permission_bitmap) "Expected ucall state to be UCALL_SYNC."); vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_gs); run_guest_then_process_rdmsr(vcpu, MSR_GS_BASE); + + vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_allow); run_guest_then_process_ucall_done(vcpu); } @@ -724,7 +732,7 @@ static void run_msr_filter_flag_test(struct kvm_vm *vm) .flags = KVM_MSR_FILTER_READ, .nmsrs = 1, .base = 0, - .bitmap = (uint8_t *)&deny_bits, + .bitmap = (u8 *)&deny_bits, }, }, }; diff --git a/tools/testing/selftests/kvm/x86/vmx_apic_access_test.c b/tools/testing/selftests/kvm/x86/vmx_apic_access_test.c index a81a24761aac..1720113eae79 100644 --- a/tools/testing/selftests/kvm/x86/vmx_apic_access_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_apic_access_test.c @@ -38,7 +38,7 @@ static void l1_guest_code(struct vmx_pages *vmx_pages, unsigned long high_gpa) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; - uint32_t control; + u32 control; GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); GUEST_ASSERT(load_vmcs(vmx_pages)); @@ -72,7 +72,7 @@ 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; - vm_vaddr_t vmx_pages_gva; + gva_t vmx_pages_gva; unsigned long high_gpa; struct vmx_pages *vmx; bool done = false; diff --git a/tools/testing/selftests/kvm/x86/vmx_apicv_updates_test.c b/tools/testing/selftests/kvm/x86/vmx_apicv_updates_test.c new file mode 100644 index 000000000000..80a4fd1e5bbb --- /dev/null +++ b/tools/testing/selftests/kvm/x86/vmx_apicv_updates_test.c @@ -0,0 +1,155 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "vmx.h" + +#define GOOD_IPI_VECTOR 0xe0 +#define BAD_IPI_VECTOR 0xf0 + +static volatile int good_ipis_received; + +static void good_ipi_handler(struct ex_regs *regs) +{ + good_ipis_received++; +} + +static void bad_ipi_handler(struct ex_regs *regs) +{ + GUEST_FAIL("Received \"bad\" IPI; ICR MMIO write should have been ignored"); +} + +static void l2_guest_code(void) +{ + x2apic_enable(); + vmcall(); + + xapic_enable(); + xapic_write_reg(APIC_ID, 1 << 24); + vmcall(); +} + +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]; + u32 control; + + 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]); + control = vmreadz(CPU_BASED_VM_EXEC_CONTROL); + control |= CPU_BASED_USE_MSR_BITMAPS; + vmwrite(CPU_BASED_VM_EXEC_CONTROL, control); + + /* Modify APIC ID to coerce KVM into inhibiting APICv. */ + xapic_enable(); + xapic_write_reg(APIC_ID, 1 << 24); + + /* + * Generate+receive an IRQ without doing EOI to get an IRQ set in vISR + * but not SVI. APICv should be inhibited due to running with a + * modified APIC ID. + */ + xapic_write_reg(APIC_ICR, APIC_DEST_SELF | APIC_DM_FIXED | GOOD_IPI_VECTOR); + GUEST_ASSERT_EQ(xapic_read_reg(APIC_ID), 1 << 24); + + /* Enable IRQs and verify the IRQ was received. */ + sti_nop(); + GUEST_ASSERT_EQ(good_ipis_received, 1); + + /* + * Run L2 to switch to x2APIC mode, which in turn will uninhibit APICv, + * as KVM should force the APIC ID back to its default. + */ + GUEST_ASSERT(!vmlaunch()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + vmwrite(GUEST_RIP, vmreadz(GUEST_RIP) + vmreadz(VM_EXIT_INSTRUCTION_LEN)); + GUEST_ASSERT(rdmsr(MSR_IA32_APICBASE) & MSR_IA32_APICBASE_EXTD); + + /* + * Scribble the APIC access page to verify KVM disabled xAPIC + * virtualization in vmcs01, and to verify that KVM flushes L1's TLB + * when L2 switches back to accelerated xAPIC mode. + */ + xapic_write_reg(APIC_ICR2, 0xdeadbeefu); + xapic_write_reg(APIC_ICR, APIC_DEST_SELF | APIC_DM_FIXED | BAD_IPI_VECTOR); + + /* + * Verify the IRQ is still in-service and emit an EOI to verify KVM + * propagates the highest vISR vector to SVI when APICv is activated + * (and does so even if APICv was uninhibited while L2 was active). + */ + GUEST_ASSERT_EQ(x2apic_read_reg(APIC_ISR + APIC_VECTOR_TO_REG_OFFSET(GOOD_IPI_VECTOR)), + BIT(APIC_VECTOR_TO_BIT_NUMBER(GOOD_IPI_VECTOR))); + x2apic_write_reg(APIC_EOI, 0); + GUEST_ASSERT_EQ(x2apic_read_reg(APIC_ISR + APIC_VECTOR_TO_REG_OFFSET(GOOD_IPI_VECTOR)), 0); + + /* + * Run L2 one more time to switch back to xAPIC mode to verify that KVM + * handles the x2APIC => xAPIC transition and inhibits APICv while L2 + * is active. + */ + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + GUEST_ASSERT(!(rdmsr(MSR_IA32_APICBASE) & MSR_IA32_APICBASE_EXTD)); + + xapic_write_reg(APIC_ICR, APIC_DEST_SELF | APIC_DM_FIXED | GOOD_IPI_VECTOR); + /* Re-enable IRQs, as VM-Exit clears RFLAGS.IF. */ + sti_nop(); + GUEST_ASSERT_EQ(good_ipis_received, 2); + + GUEST_ASSERT_EQ(xapic_read_reg(APIC_ISR + APIC_VECTOR_TO_REG_OFFSET(GOOD_IPI_VECTOR)), + BIT(APIC_VECTOR_TO_BIT_NUMBER(GOOD_IPI_VECTOR))); + xapic_write_reg(APIC_EOI, 0); + GUEST_ASSERT_EQ(xapic_read_reg(APIC_ISR + APIC_VECTOR_TO_REG_OFFSET(GOOD_IPI_VECTOR)), 0); + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + gva_t vmx_pages_gva; + struct vmx_pages *vmx; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct ucall uc; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + + vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva); + prepare_virtualize_apic_accesses(vmx, vm); + vcpu_args_set(vcpu, 1, vmx_pages_gva); + + virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); + vm_install_exception_handler(vm, BAD_IPI_VECTOR, bad_ipi_handler); + vm_install_exception_handler(vm, GOOD_IPI_VECTOR, good_ipi_handler); + + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + /* NOT REACHED */ + case UCALL_DONE: + break; + default: + TEST_FAIL("Unexpected ucall %lu", uc.cmd); + } + + /* + * Verify at least two IRQs were injected. Unfortunately, KVM counts + * re-injected IRQs (e.g. if delivering the IRQ hits an EPT violation), + * so being more precise isn't possible given the current stats. + */ + TEST_ASSERT(vcpu_get_stat(vcpu, irq_injections) >= 2, + "Wanted at least 2 IRQ injections, got %lu\n", + vcpu_get_stat(vcpu, irq_injections)); + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c deleted file mode 100644 index fa512d033205..000000000000 --- a/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c +++ /dev/null @@ -1,179 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * KVM dirty page logging test - * - * Copyright (C) 2018, Red Hat, Inc. - */ -#include <stdio.h> -#include <stdlib.h> -#include <linux/bitmap.h> -#include <linux/bitops.h> - -#include "test_util.h" -#include "kvm_util.h" -#include "processor.h" -#include "vmx.h" - -/* The memory slot index to track dirty pages */ -#define TEST_MEM_SLOT_INDEX 1 -#define TEST_MEM_PAGES 3 - -/* L1 guest test virtual memory offset */ -#define GUEST_TEST_MEM 0xc0000000 - -/* L2 guest test virtual memory offset */ -#define NESTED_TEST_MEM1 0xc0001000 -#define NESTED_TEST_MEM2 0xc0002000 - -static void l2_guest_code(u64 *a, u64 *b) -{ - READ_ONCE(*a); - WRITE_ONCE(*a, 1); - GUEST_SYNC(true); - GUEST_SYNC(false); - - WRITE_ONCE(*b, 1); - GUEST_SYNC(true); - WRITE_ONCE(*b, 1); - GUEST_SYNC(true); - GUEST_SYNC(false); - - /* Exit to L1 and never come back. */ - vmcall(); -} - -static void l2_guest_code_ept_enabled(void) -{ - l2_guest_code((u64 *)NESTED_TEST_MEM1, (u64 *)NESTED_TEST_MEM2); -} - -static void l2_guest_code_ept_disabled(void) -{ - /* Access the same L1 GPAs as l2_guest_code_ept_enabled() */ - l2_guest_code((u64 *)GUEST_TEST_MEM, (u64 *)GUEST_TEST_MEM); -} - -void l1_guest_code(struct vmx_pages *vmx) -{ -#define L2_GUEST_STACK_SIZE 64 - unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; - void *l2_rip; - - GUEST_ASSERT(vmx->vmcs_gpa); - GUEST_ASSERT(prepare_for_vmx_operation(vmx)); - GUEST_ASSERT(load_vmcs(vmx)); - - if (vmx->eptp_gpa) - l2_rip = l2_guest_code_ept_enabled; - else - l2_rip = l2_guest_code_ept_disabled; - - prepare_vmcs(vmx, l2_rip, &l2_guest_stack[L2_GUEST_STACK_SIZE]); - - GUEST_SYNC(false); - GUEST_ASSERT(!vmlaunch()); - GUEST_SYNC(false); - GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); - GUEST_DONE(); -} - -static void test_vmx_dirty_log(bool enable_ept) -{ - vm_vaddr_t vmx_pages_gva = 0; - struct vmx_pages *vmx; - unsigned long *bmap; - uint64_t *host_test_mem; - - struct kvm_vcpu *vcpu; - struct kvm_vm *vm; - struct ucall uc; - bool done = false; - - pr_info("Nested EPT: %s\n", enable_ept ? "enabled" : "disabled"); - - /* Create VM */ - vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); - vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vcpu, 1, vmx_pages_gva); - - /* Add an extra memory slot for testing dirty logging */ - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, - GUEST_TEST_MEM, - TEST_MEM_SLOT_INDEX, - TEST_MEM_PAGES, - KVM_MEM_LOG_DIRTY_PAGES); - - /* - * Add an identity map for GVA range [0xc0000000, 0xc0002000). This - * affects both L1 and L2. However... - */ - virt_map(vm, GUEST_TEST_MEM, GUEST_TEST_MEM, TEST_MEM_PAGES); - - /* - * ... pages in the L2 GPA range [0xc0001000, 0xc0003000) will map to - * 0xc0000000. - * - * Note that prepare_eptp should be called only L1's GPA map is done, - * meaning after the last call to virt_map. - * - * When EPT is disabled, the L2 guest code will still access the same L1 - * GPAs as the EPT enabled case. - */ - if (enable_ept) { - prepare_eptp(vmx, vm, 0); - nested_map_memslot(vmx, vm, 0); - nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096); - nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096); - } - - bmap = bitmap_zalloc(TEST_MEM_PAGES); - host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM); - - while (!done) { - memset(host_test_mem, 0xaa, TEST_MEM_PAGES * 4096); - vcpu_run(vcpu); - TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); - - switch (get_ucall(vcpu, &uc)) { - case UCALL_ABORT: - REPORT_GUEST_ASSERT(uc); - /* NOT REACHED */ - case UCALL_SYNC: - /* - * The nested guest wrote at offset 0x1000 in the memslot, but the - * dirty bitmap must be filled in according to L1 GPA, not L2. - */ - kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); - if (uc.args[1]) { - TEST_ASSERT(test_bit(0, bmap), "Page 0 incorrectly reported clean"); - TEST_ASSERT(host_test_mem[0] == 1, "Page 0 not written by guest"); - } else { - TEST_ASSERT(!test_bit(0, bmap), "Page 0 incorrectly reported dirty"); - TEST_ASSERT(host_test_mem[0] == 0xaaaaaaaaaaaaaaaaULL, "Page 0 written by guest"); - } - - TEST_ASSERT(!test_bit(1, bmap), "Page 1 incorrectly reported dirty"); - TEST_ASSERT(host_test_mem[4096 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 1 written by guest"); - TEST_ASSERT(!test_bit(2, bmap), "Page 2 incorrectly reported dirty"); - TEST_ASSERT(host_test_mem[8192 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 2 written by guest"); - break; - case UCALL_DONE: - done = true; - break; - default: - TEST_FAIL("Unknown ucall %lu", uc.cmd); - } - } -} - -int main(int argc, char *argv[]) -{ - TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); - - test_vmx_dirty_log(/*enable_ept=*/false); - - if (kvm_cpu_has_ept()) - test_vmx_dirty_log(/*enable_ept=*/true); - - return 0; -} diff --git a/tools/testing/selftests/kvm/x86/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86/vmx_exception_with_invalid_guest_state.c index 3fd6eceab46f..2cae86d9d5e2 100644 --- a/tools/testing/selftests/kvm/x86/vmx_exception_with_invalid_guest_state.c +++ b/tools/testing/selftests/kvm/x86/vmx_exception_with_invalid_guest_state.c @@ -110,7 +110,7 @@ int main(int argc, char *argv[]) struct kvm_vm *vm; TEST_REQUIRE(host_cpu_is_intel); - TEST_REQUIRE(!vm_is_unrestricted_guest(NULL)); + TEST_REQUIRE(!kvm_is_unrestricted_guest_enabled()); vm = vm_create_with_one_vcpu(&vcpu, guest_code); get_set_sigalrm_vcpu(vcpu); diff --git a/tools/testing/selftests/kvm/x86/vmx_invalid_nested_guest_state.c b/tools/testing/selftests/kvm/x86/vmx_invalid_nested_guest_state.c index a100ee5f0009..a2eaceed9ad5 100644 --- a/tools/testing/selftests/kvm/x86/vmx_invalid_nested_guest_state.c +++ b/tools/testing/selftests/kvm/x86/vmx_invalid_nested_guest_state.c @@ -52,7 +52,7 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) int main(int argc, char *argv[]) { - vm_vaddr_t vmx_pages_gva; + gva_t vmx_pages_gva; struct kvm_sregs sregs; struct kvm_vcpu *vcpu; struct kvm_run *run; diff --git a/tools/testing/selftests/kvm/x86/vmx_msrs_test.c b/tools/testing/selftests/kvm/x86/vmx_msrs_test.c index 90720b6205f4..c1e8632a1bb6 100644 --- a/tools/testing/selftests/kvm/x86/vmx_msrs_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_msrs_test.c @@ -12,11 +12,10 @@ #include "kvm_util.h" #include "vmx.h" -static void vmx_fixed1_msr_test(struct kvm_vcpu *vcpu, uint32_t msr_index, - uint64_t mask) +static void vmx_fixed1_msr_test(struct kvm_vcpu *vcpu, u32 msr_index, u64 mask) { - uint64_t val = vcpu_get_msr(vcpu, msr_index); - uint64_t bit; + u64 val = vcpu_get_msr(vcpu, msr_index); + u64 bit; mask &= val; @@ -26,11 +25,10 @@ static void vmx_fixed1_msr_test(struct kvm_vcpu *vcpu, uint32_t msr_index, } } -static void vmx_fixed0_msr_test(struct kvm_vcpu *vcpu, uint32_t msr_index, - uint64_t mask) +static void vmx_fixed0_msr_test(struct kvm_vcpu *vcpu, u32 msr_index, u64 mask) { - uint64_t val = vcpu_get_msr(vcpu, msr_index); - uint64_t bit; + u64 val = vcpu_get_msr(vcpu, msr_index); + u64 bit; mask = ~mask | val; @@ -40,7 +38,7 @@ static void vmx_fixed0_msr_test(struct kvm_vcpu *vcpu, uint32_t msr_index, } } -static void vmx_fixed0and1_msr_test(struct kvm_vcpu *vcpu, uint32_t msr_index) +static void vmx_fixed0and1_msr_test(struct kvm_vcpu *vcpu, u32 msr_index) { vmx_fixed0_msr_test(vcpu, msr_index, GENMASK_ULL(31, 0)); vmx_fixed1_msr_test(vcpu, msr_index, GENMASK_ULL(63, 32)); @@ -68,10 +66,10 @@ static void vmx_save_restore_msrs_test(struct kvm_vcpu *vcpu) } static void __ia32_feature_control_msr_test(struct kvm_vcpu *vcpu, - uint64_t msr_bit, + u64 msr_bit, struct kvm_x86_cpu_feature feature) { - uint64_t val; + u64 val; vcpu_clear_cpuid_feature(vcpu, feature); @@ -90,7 +88,7 @@ static void __ia32_feature_control_msr_test(struct kvm_vcpu *vcpu, static void ia32_feature_control_msr_test(struct kvm_vcpu *vcpu) { - uint64_t supported_bits = FEAT_CTL_LOCKED | + u64 supported_bits = FEAT_CTL_LOCKED | FEAT_CTL_VMX_ENABLED_INSIDE_SMX | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX | FEAT_CTL_SGX_LC_ENABLED | diff --git a/tools/testing/selftests/kvm/x86/vmx_nested_la57_state_test.c b/tools/testing/selftests/kvm/x86/vmx_nested_la57_state_test.c new file mode 100644 index 000000000000..f13dee317383 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/vmx_nested_la57_state_test.c @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2025, Google LLC. + * + * Test KVM's ability to save and restore nested state when the L1 guest + * is using 5-level paging and the L2 guest is using 4-level paging. + * + * This test would have failed prior to commit 9245fd6b8531 ("KVM: x86: + * model canonical checks more precisely"). + */ +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "vmx.h" + +#define LA57_GS_BASE 0xff2bc0311fb00000ull + +static void l2_guest_code(void) +{ + /* + * Sync with L0 to trigger save/restore. After + * resuming, execute VMCALL to exit back to L1. + */ + GUEST_SYNC(1); + vmcall(); +} + +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]; + u64 guest_cr4; + gpa_t pml5_pa, pml4_pa; + u64 *pml5; + u64 exit_reason; + + /* Set GS_BASE to a value that is only canonical with LA57. */ + wrmsr(MSR_GS_BASE, LA57_GS_BASE); + GUEST_ASSERT(rdmsr(MSR_GS_BASE) == LA57_GS_BASE); + + GUEST_ASSERT(vmx_pages->vmcs_gpa); + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + GUEST_ASSERT(load_vmcs(vmx_pages)); + + prepare_vmcs(vmx_pages, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* + * Set up L2 with a 4-level page table by pointing its CR3 to + * L1's first PML4 table and clearing CR4.LA57. This creates + * the CR4.LA57 mismatch that exercises the bug. + */ + pml5_pa = get_cr3() & PHYSICAL_PAGE_MASK; + pml5 = (u64 *)pml5_pa; + pml4_pa = pml5[0] & PHYSICAL_PAGE_MASK; + vmwrite(GUEST_CR3, pml4_pa); + + guest_cr4 = vmreadz(GUEST_CR4); + guest_cr4 &= ~X86_CR4_LA57; + vmwrite(GUEST_CR4, guest_cr4); + + GUEST_ASSERT(!vmlaunch()); + + exit_reason = vmreadz(VM_EXIT_REASON); + GUEST_ASSERT(exit_reason == EXIT_REASON_VMCALL); +} + +void guest_code(struct vmx_pages *vmx_pages) +{ + l1_guest_code(vmx_pages); + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + gva_t vmx_pages_gva = 0; + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + struct kvm_x86_state *state; + struct ucall uc; + int stage; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_LA57)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE)); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + /* + * L1 needs to read its own PML5 table to set up L2. Identity map + * the PML5 table to facilitate this. + */ + virt_map(vm, vm->mmu.pgd, vm->mmu.pgd, 1); + + vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); + + for (stage = 1;; stage++) { + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + + 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); + } + + TEST_ASSERT(uc.args[1] == stage, + "Expected stage %d, got stage %lu", stage, (ulong)uc.args[1]); + if (stage == 1) { + pr_info("L2 is active; performing save/restore.\n"); + state = vcpu_save_state(vcpu); + + kvm_vm_release(vm); + + /* Restore state in a new VM. */ + vcpu = vm_recreate_with_one_vcpu(vm); + vcpu_load_state(vcpu, state); + kvm_x86_state_cleanup(state); + } + } + +done: + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c index a1f5ff45d518..d004108dbdc6 100644 --- a/tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c @@ -29,7 +29,7 @@ static union perf_capabilities { u64 pebs_baseline:1; u64 perf_metrics:1; u64 pebs_output_pt_available:1; - u64 anythread_deprecated:1; + u64 pebs_timing_info:1; }; u64 capabilities; } host_cap; @@ -44,6 +44,7 @@ static const union perf_capabilities immutable_caps = { .pebs_arch_reg = 1, .pebs_format = -1, .pebs_baseline = 1, + .pebs_timing_info = 1, }; static const union perf_capabilities format_caps = { @@ -51,16 +52,16 @@ static const union perf_capabilities format_caps = { .pebs_format = -1, }; -static void guest_test_perf_capabilities_gp(uint64_t val) +static void guest_test_perf_capabilities_gp(u64 val) { - uint8_t vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, val); + u8 vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, val); __GUEST_ASSERT(vector == GP_VECTOR, - "Expected #GP for value '0x%lx', got vector '0x%x'", - val, vector); + "Expected #GP for value '0x%lx', got %s", + val, ex_str(vector)); } -static void guest_code(uint64_t current_val) +static void guest_code(u64 current_val) { int i; @@ -128,7 +129,7 @@ KVM_ONE_VCPU_TEST(vmx_pmu_caps, basic_perf_capabilities, guest_code) KVM_ONE_VCPU_TEST(vmx_pmu_caps, fungible_perf_capabilities, guest_code) { - const uint64_t fungible_caps = host_cap.capabilities & ~immutable_caps.capabilities; + const u64 fungible_caps = host_cap.capabilities & ~immutable_caps.capabilities; int bit; for_each_set_bit(bit, &fungible_caps, 64) { @@ -147,7 +148,7 @@ KVM_ONE_VCPU_TEST(vmx_pmu_caps, fungible_perf_capabilities, guest_code) */ KVM_ONE_VCPU_TEST(vmx_pmu_caps, immutable_perf_capabilities, guest_code) { - const uint64_t reserved_caps = (~host_cap.capabilities | + const u64 reserved_caps = (~host_cap.capabilities | immutable_caps.capabilities) & ~format_caps.capabilities; union perf_capabilities val = host_cap; @@ -209,7 +210,7 @@ KVM_ONE_VCPU_TEST(vmx_pmu_caps, lbr_perf_capabilities, guest_code) KVM_ONE_VCPU_TEST(vmx_pmu_caps, perf_capabilities_unsupported, guest_code) { - uint64_t val; + u64 val; int i, r; vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); diff --git a/tools/testing/selftests/kvm/x86/vmx_preemption_timer_test.c b/tools/testing/selftests/kvm/x86/vmx_preemption_timer_test.c index 00dd2ac07a61..1b7b6ba23de7 100644 --- a/tools/testing/selftests/kvm/x86/vmx_preemption_timer_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_preemption_timer_test.c @@ -152,7 +152,7 @@ void guest_code(struct vmx_pages *vmx_pages) int main(int argc, char *argv[]) { - vm_vaddr_t vmx_pages_gva = 0; + gva_t vmx_pages_gva = 0; struct kvm_regs regs1, regs2; struct kvm_vm *vm; diff --git a/tools/testing/selftests/kvm/x86/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86/xapic_ipi_test.c index a76078a08ff8..39ce9a9369f5 100644 --- a/tools/testing/selftests/kvm/x86/xapic_ipi_test.c +++ b/tools/testing/selftests/kvm/x86/xapic_ipi_test.c @@ -48,20 +48,20 @@ * Incremented in the IPI handler. Provides evidence to the sender that the IPI * arrived at the destination */ -static volatile uint64_t ipis_rcvd; +static volatile u64 ipis_rcvd; /* Data struct shared between host main thread and vCPUs */ struct test_data_page { - uint32_t halter_apic_id; - volatile uint64_t hlt_count; - volatile uint64_t wake_count; - uint64_t ipis_sent; - uint64_t migrations_attempted; - uint64_t migrations_completed; - uint32_t icr; - uint32_t icr2; - uint32_t halter_tpr; - uint32_t halter_ppr; + u32 halter_apic_id; + volatile u64 hlt_count; + volatile u64 wake_count; + u64 ipis_sent; + u64 migrations_attempted; + u64 migrations_completed; + u32 icr; + u32 icr2; + u32 halter_tpr; + u32 halter_ppr; /* * Record local version register as a cross-check that APIC access @@ -69,19 +69,19 @@ struct test_data_page { * arch/x86/kvm/lapic.c). If test is failing, check that values match * to determine whether APIC access exits are working. */ - uint32_t halter_lvr; + u32 halter_lvr; }; struct thread_params { struct test_data_page *data; struct kvm_vcpu *vcpu; - uint64_t *pipis_rcvd; /* host address of ipis_rcvd global */ + u64 *pipis_rcvd; /* host address of ipis_rcvd global */ }; void verify_apic_base_addr(void) { - uint64_t msr = rdmsr(MSR_IA32_APICBASE); - uint64_t base = GET_APIC_BASE(msr); + u64 msr = rdmsr(MSR_IA32_APICBASE); + u64 base = GET_APIC_BASE(msr); GUEST_ASSERT(base == APIC_DEFAULT_GPA); } @@ -106,7 +106,8 @@ static void halter_guest_code(struct test_data_page *data) data->halter_tpr = xapic_read_reg(APIC_TASKPRI); data->halter_ppr = xapic_read_reg(APIC_PROCPRI); data->hlt_count++; - asm volatile("sti; hlt; cli"); + safe_halt(); + cli(); data->wake_count++; } } @@ -124,12 +125,12 @@ static void guest_ipi_handler(struct ex_regs *regs) static void sender_guest_code(struct test_data_page *data) { - uint64_t last_wake_count; - uint64_t last_hlt_count; - uint64_t last_ipis_rcvd_count; - uint32_t icr_val; - uint32_t icr2_val; - uint64_t tsc_start; + u64 last_wake_count; + u64 last_hlt_count; + u64 last_ipis_rcvd_count; + u32 icr_val; + u32 icr2_val; + u64 tsc_start; verify_apic_base_addr(); xapic_enable(); @@ -247,7 +248,7 @@ static void cancel_join_vcpu_thread(pthread_t thread, struct kvm_vcpu *vcpu) } void do_migrations(struct test_data_page *data, int run_secs, int delay_usecs, - uint64_t *pipis_rcvd) + u64 *pipis_rcvd) { long pages_not_moved; unsigned long nodemask = 0; @@ -255,20 +256,19 @@ void do_migrations(struct test_data_page *data, int run_secs, int delay_usecs, int nodes = 0; time_t start_time, last_update, now; time_t interval_secs = 1; - int i, r; + int i; int from, to; unsigned long bit; - uint64_t hlt_count; - uint64_t wake_count; - uint64_t ipis_sent; + u64 hlt_count; + u64 wake_count; + u64 ipis_sent; fprintf(stderr, "Calling migrate_pages every %d microseconds\n", delay_usecs); /* Get set of first 64 numa nodes available */ - r = get_mempolicy(NULL, &nodemask, sizeof(nodemask) * 8, + kvm_get_mempolicy(NULL, &nodemask, sizeof(nodemask) * 8, 0, MPOL_F_MEMS_ALLOWED); - TEST_ASSERT(r == 0, "get_mempolicy failed errno=%d", errno); fprintf(stderr, "Numa nodes found amongst first %lu possible nodes " "(each 1-bit indicates node is present): %#lx\n", @@ -393,12 +393,12 @@ int main(int argc, char *argv[]) int run_secs = 0; int delay_usecs = 0; struct test_data_page *data; - vm_vaddr_t test_data_page_vaddr; + gva_t test_data_page_gva; bool migrate = false; pthread_t threads[2]; struct thread_params params[2]; struct kvm_vm *vm; - uint64_t *pipis_rcvd; + u64 *pipis_rcvd; get_cmdline_args(argc, argv, &run_secs, &migrate, &delay_usecs); if (run_secs <= 0) @@ -414,16 +414,16 @@ int main(int argc, char *argv[]) params[1].vcpu = vm_vcpu_add(vm, 1, sender_guest_code); - test_data_page_vaddr = vm_vaddr_alloc_page(vm); - data = addr_gva2hva(vm, test_data_page_vaddr); + test_data_page_gva = vm_alloc_page(vm); + data = addr_gva2hva(vm, test_data_page_gva); memset(data, 0, sizeof(*data)); params[0].data = data; params[1].data = data; - vcpu_args_set(params[0].vcpu, 1, test_data_page_vaddr); - vcpu_args_set(params[1].vcpu, 1, test_data_page_vaddr); + vcpu_args_set(params[0].vcpu, 1, test_data_page_gva); + vcpu_args_set(params[1].vcpu, 1, test_data_page_gva); - pipis_rcvd = (uint64_t *)addr_gva2hva(vm, (uint64_t)&ipis_rcvd); + pipis_rcvd = (u64 *)addr_gva2hva(vm, (u64)&ipis_rcvd); params[0].pipis_rcvd = pipis_rcvd; params[1].pipis_rcvd = pipis_rcvd; @@ -465,6 +465,19 @@ int main(int argc, char *argv[]) cancel_join_vcpu_thread(threads[0], params[0].vcpu); cancel_join_vcpu_thread(threads[1], params[1].vcpu); + /* + * If the host support Idle HLT, i.e. KVM *might* be using Idle HLT, + * then the number of HLT exits may be less than the number of HLTs + * that were executed, as Idle HLT elides the exit if the vCPU has an + * unmasked, pending IRQ (or NMI). + */ + if (this_cpu_has(X86_FEATURE_IDLE_HLT)) + TEST_ASSERT(data->hlt_count >= vcpu_get_stat(params[0].vcpu, halt_exits), + "HLT insns = %lu, HLT exits = %lu", + data->hlt_count, vcpu_get_stat(params[0].vcpu, halt_exits)); + else + TEST_ASSERT_EQ(data->hlt_count, vcpu_get_stat(params[0].vcpu, halt_exits)); + fprintf(stderr, "Test successful after running for %d seconds.\n" "Sending vCPU sent %lu IPIs to halting vCPU\n" diff --git a/tools/testing/selftests/kvm/x86/xapic_state_test.c b/tools/testing/selftests/kvm/x86/xapic_state_test.c index 88bcca188799..637bb90c1d93 100644 --- a/tools/testing/selftests/kvm/x86/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86/xapic_state_test.c @@ -18,12 +18,12 @@ struct xapic_vcpu { static void xapic_guest_code(void) { - asm volatile("cli"); + cli(); xapic_enable(); while (1) { - uint64_t val = (u64)xapic_read_reg(APIC_IRR) | + u64 val = (u64)xapic_read_reg(APIC_IRR) | (u64)xapic_read_reg(APIC_IRR + 0x10) << 32; xapic_write_reg(APIC_ICR2, val >> 32); @@ -38,12 +38,12 @@ static void xapic_guest_code(void) static void x2apic_guest_code(void) { - asm volatile("cli"); + cli(); x2apic_enable(); do { - uint64_t val = x2apic_read_reg(APIC_IRR) | + u64 val = x2apic_read_reg(APIC_IRR) | x2apic_read_reg(APIC_IRR + 0x10) << 32; if (val & X2APIC_RSVD_BITS_MASK) { @@ -56,12 +56,12 @@ static void x2apic_guest_code(void) } while (1); } -static void ____test_icr(struct xapic_vcpu *x, uint64_t val) +static void ____test_icr(struct xapic_vcpu *x, u64 val) { struct kvm_vcpu *vcpu = x->vcpu; struct kvm_lapic_state xapic; struct ucall uc; - uint64_t icr; + u64 icr; /* * Tell the guest what ICR value to write. Use the IRR to pass info, @@ -93,7 +93,7 @@ static void ____test_icr(struct xapic_vcpu *x, uint64_t val) TEST_ASSERT_EQ(icr, val & ~APIC_ICR_BUSY); } -static void __test_icr(struct xapic_vcpu *x, uint64_t val) +static void __test_icr(struct xapic_vcpu *x, u64 val) { /* * The BUSY bit is reserved on both AMD and Intel, but only AMD treats @@ -109,7 +109,7 @@ static void __test_icr(struct xapic_vcpu *x, uint64_t val) static void test_icr(struct xapic_vcpu *x) { struct kvm_vcpu *vcpu = x->vcpu; - uint64_t icr, i, j; + u64 icr, i, j; icr = APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_FIXED; for (i = 0; i <= 0xff; i++) @@ -120,8 +120,8 @@ static void test_icr(struct xapic_vcpu *x) __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. + * Send all flavors of IPIs to non-existent vCPUs. Arbitrarily use + * vector 0xff. */ icr = APIC_INT_ASSERT | 0xff; for (i = 0; i < 0xff; i++) { @@ -142,9 +142,9 @@ static void test_icr(struct xapic_vcpu *x) __test_icr(x, -1ull & ~APIC_DM_FIXED_MASK); } -static void __test_apic_id(struct kvm_vcpu *vcpu, uint64_t apic_base) +static void __test_apic_id(struct kvm_vcpu *vcpu, u64 apic_base) { - uint32_t apic_id, expected; + u32 apic_id, expected; struct kvm_lapic_state xapic; vcpu_set_msr(vcpu, MSR_IA32_APICBASE, apic_base); @@ -170,9 +170,9 @@ static void __test_apic_id(struct kvm_vcpu *vcpu, uint64_t apic_base) */ static void test_apic_id(void) { - const uint32_t NR_VCPUS = 3; + const u32 NR_VCPUS = 3; struct kvm_vcpu *vcpus[NR_VCPUS]; - uint64_t apic_base; + u64 apic_base; struct kvm_vm *vm; int i; @@ -248,7 +248,7 @@ int main(int argc, char *argv[]) * drops writes, AMD does not). Account for the errata when checking * that KVM reads back what was written. */ - x.has_xavic_errata = host_cpu_is_amd && + x.has_xavic_errata = host_cpu_is_amd_compatible && get_kvm_amd_param_bool("avic"); vcpu_clear_cpuid_feature(x.vcpu, X86_FEATURE_X2APIC); diff --git a/tools/testing/selftests/kvm/x86/xapic_tpr_test.c b/tools/testing/selftests/kvm/x86/xapic_tpr_test.c new file mode 100644 index 000000000000..ab25db2235d5 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/xapic_tpr_test.c @@ -0,0 +1,276 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <fcntl.h> +#include <stdatomic.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <unistd.h> + +#include "apic.h" +#include "kvm_util.h" +#include "processor.h" +#include "test_util.h" + +static bool is_x2apic; + +#define IRQ_VECTOR 0x20 + +/* See also the comment at similar assertion in memslot_perf_test.c */ +static_assert(ATOMIC_INT_LOCK_FREE == 2, "atomic int is not lockless"); + +static atomic_uint tpr_guest_irq_sync_val; + +static void tpr_guest_irq_sync_flag_reset(void) +{ + atomic_store_explicit(&tpr_guest_irq_sync_val, 0, + memory_order_release); +} + +static unsigned int tpr_guest_irq_sync_val_get(void) +{ + return atomic_load_explicit(&tpr_guest_irq_sync_val, + memory_order_acquire); +} + +static void tpr_guest_irq_sync_val_inc(void) +{ + atomic_fetch_add_explicit(&tpr_guest_irq_sync_val, 1, + memory_order_acq_rel); +} + +static void tpr_guest_irq_handler_xapic(struct ex_regs *regs) +{ + tpr_guest_irq_sync_val_inc(); + + xapic_write_reg(APIC_EOI, 0); +} + +static void tpr_guest_irq_handler_x2apic(struct ex_regs *regs) +{ + tpr_guest_irq_sync_val_inc(); + + x2apic_write_reg(APIC_EOI, 0); +} + +static void tpr_guest_irq_queue(void) +{ + if (is_x2apic) { + x2apic_write_reg(APIC_SELF_IPI, IRQ_VECTOR); + } else { + u32 icr, icr2; + + icr = APIC_DEST_SELF | APIC_DEST_PHYSICAL | APIC_DM_FIXED | + IRQ_VECTOR; + icr2 = 0; + + xapic_write_reg(APIC_ICR2, icr2); + xapic_write_reg(APIC_ICR, icr); + } +} + +static u8 tpr_guest_tpr_get(void) +{ + u32 taskpri; + + if (is_x2apic) + taskpri = x2apic_read_reg(APIC_TASKPRI); + else + taskpri = xapic_read_reg(APIC_TASKPRI); + + return GET_APIC_PRI(taskpri); +} + +static u8 tpr_guest_ppr_get(void) +{ + u32 procpri; + + if (is_x2apic) + procpri = x2apic_read_reg(APIC_PROCPRI); + else + procpri = xapic_read_reg(APIC_PROCPRI); + + return GET_APIC_PRI(procpri); +} + +static u8 tpr_guest_cr8_get(void) +{ + u64 cr8; + + asm volatile ("mov %%cr8, %[cr8]\n\t" : [cr8] "=r"(cr8)); + + return cr8 & GENMASK(3, 0); +} + +static void tpr_guest_check_tpr_ppr_cr8_equal(void) +{ + u8 tpr; + + tpr = tpr_guest_tpr_get(); + + GUEST_ASSERT_EQ(tpr_guest_ppr_get(), tpr); + GUEST_ASSERT_EQ(tpr_guest_cr8_get(), tpr); +} + +static void tpr_guest_code(void) +{ + cli(); + + if (is_x2apic) + x2apic_enable(); + else + xapic_enable(); + + GUEST_ASSERT_EQ(tpr_guest_tpr_get(), 0); + tpr_guest_check_tpr_ppr_cr8_equal(); + + tpr_guest_irq_queue(); + + /* TPR = 0 but IRQ masked by IF=0, should not fire */ + udelay(1000); + GUEST_ASSERT_EQ(tpr_guest_irq_sync_val_get(), 0); + + sti(); + + /* IF=1 now, IRQ should fire */ + while (tpr_guest_irq_sync_val_get() == 0) + cpu_relax(); + GUEST_ASSERT_EQ(tpr_guest_irq_sync_val_get(), 1); + + GUEST_SYNC(true); + tpr_guest_check_tpr_ppr_cr8_equal(); + + tpr_guest_irq_queue(); + + /* IRQ masked by barely high enough TPR now, should not fire */ + udelay(1000); + GUEST_ASSERT_EQ(tpr_guest_irq_sync_val_get(), 1); + + GUEST_SYNC(false); + tpr_guest_check_tpr_ppr_cr8_equal(); + + /* TPR barely low enough now to unmask IRQ, should fire */ + while (tpr_guest_irq_sync_val_get() == 1) + cpu_relax(); + GUEST_ASSERT_EQ(tpr_guest_irq_sync_val_get(), 2); + + GUEST_DONE(); +} + +static u8 lapic_tpr_get(struct kvm_lapic_state *xapic) +{ + return GET_APIC_PRI(*((u32 *)&xapic->regs[APIC_TASKPRI])); +} + +static void lapic_tpr_set(struct kvm_lapic_state *xapic, u8 val) +{ + u32 *taskpri = (u32 *)&xapic->regs[APIC_TASKPRI]; + + *taskpri = SET_APIC_PRI(*taskpri, val); +} + +static u8 sregs_tpr(struct kvm_sregs *sregs) +{ + return sregs->cr8 & GENMASK(3, 0); +} + +static void test_tpr_check_tpr_zero(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic_state xapic; + + vcpu_ioctl(vcpu, KVM_GET_LAPIC, &xapic); + + TEST_ASSERT_EQ(lapic_tpr_get(&xapic), 0); +} + +static void test_tpr_check_tpr_cr8_equal(struct kvm_vcpu *vcpu) +{ + struct kvm_sregs sregs; + struct kvm_lapic_state xapic; + + vcpu_sregs_get(vcpu, &sregs); + vcpu_ioctl(vcpu, KVM_GET_LAPIC, &xapic); + + TEST_ASSERT_EQ(sregs_tpr(&sregs), lapic_tpr_get(&xapic)); +} + +static void test_tpr_set_tpr_for_irq(struct kvm_vcpu *vcpu, bool mask) +{ + struct kvm_lapic_state xapic; + u8 tpr; + + static_assert(IRQ_VECTOR >= 16, "invalid IRQ vector number"); + tpr = IRQ_VECTOR / 16; + if (!mask) + tpr--; + + vcpu_ioctl(vcpu, KVM_GET_LAPIC, &xapic); + lapic_tpr_set(&xapic, tpr); + vcpu_ioctl(vcpu, KVM_SET_LAPIC, &xapic); +} + +static void test_tpr(bool __is_x2apic) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + bool done = false; + + is_x2apic = __is_x2apic; + + vm = vm_create_with_one_vcpu(&vcpu, tpr_guest_code); + if (is_x2apic) { + vm_install_exception_handler(vm, IRQ_VECTOR, + tpr_guest_irq_handler_x2apic); + } else { + vm_install_exception_handler(vm, IRQ_VECTOR, + tpr_guest_irq_handler_xapic); + vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_X2APIC); + virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); + } + + sync_global_to_guest(vcpu->vm, is_x2apic); + + /* According to the SDM/APM the TPR value at reset is 0 */ + test_tpr_check_tpr_zero(vcpu); + test_tpr_check_tpr_cr8_equal(vcpu); + + tpr_guest_irq_sync_flag_reset(); + sync_global_to_guest(vcpu->vm, tpr_guest_irq_sync_val); + + while (!done) { + struct ucall uc; + + alarm(2); + vcpu_run(vcpu); + alarm(0); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + break; + case UCALL_DONE: + test_tpr_check_tpr_cr8_equal(vcpu); + done = true; + break; + case UCALL_SYNC: + test_tpr_check_tpr_cr8_equal(vcpu); + test_tpr_set_tpr_for_irq(vcpu, uc.args[1]); + break; + default: + TEST_FAIL("Unknown ucall result 0x%lx", uc.cmd); + break; + } + } + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + /* + * Use separate VMs for the xAPIC and x2APIC tests so that x2APIC can + * be fully hidden from the guest. KVM disallows changing CPUID after + * KVM_RUN and AVIC is disabled if _any_ vCPU is allowed to use x2APIC. + */ + test_tpr(false); + test_tpr(true); +} diff --git a/tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c index c8a5c5e51661..40dc9e6b3fad 100644 --- a/tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c +++ b/tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c @@ -21,7 +21,7 @@ */ #define ASSERT_XFEATURE_DEPENDENCIES(supported_xcr0, xfeatures, dependencies) \ do { \ - uint64_t __supported = (supported_xcr0) & ((xfeatures) | (dependencies)); \ + u64 __supported = (supported_xcr0) & ((xfeatures) | (dependencies)); \ \ __GUEST_ASSERT((__supported & (xfeatures)) != (xfeatures) || \ __supported == ((xfeatures) | (dependencies)), \ @@ -39,7 +39,7 @@ do { \ */ #define ASSERT_ALL_OR_NONE_XFEATURE(supported_xcr0, xfeatures) \ do { \ - uint64_t __supported = (supported_xcr0) & (xfeatures); \ + u64 __supported = (supported_xcr0) & (xfeatures); \ \ __GUEST_ASSERT(!__supported || __supported == (xfeatures), \ "supported = 0x%lx, xfeatures = 0x%llx", \ @@ -48,8 +48,8 @@ do { \ static void guest_code(void) { - uint64_t initial_xcr0; - uint64_t supported_xcr0; + u64 initial_xcr0; + u64 supported_xcr0; int i, vector; set_cr4(get_cr4() | X86_CR4_OSXSAVE); @@ -81,13 +81,13 @@ static void guest_code(void) vector = xsetbv_safe(0, XFEATURE_MASK_FP); __GUEST_ASSERT(!vector, - "Expected success on XSETBV(FP), got vector '0x%x'", - vector); + "Expected success on XSETBV(FP), got %s", + ex_str(vector)); vector = xsetbv_safe(0, supported_xcr0); __GUEST_ASSERT(!vector, - "Expected success on XSETBV(0x%lx), got vector '0x%x'", - supported_xcr0, vector); + "Expected success on XSETBV(0x%lx), got %s", + supported_xcr0, ex_str(vector)); for (i = 0; i < 64; i++) { if (supported_xcr0 & BIT_ULL(i)) @@ -95,8 +95,8 @@ static void guest_code(void) vector = xsetbv_safe(0, supported_xcr0 | BIT_ULL(i)); __GUEST_ASSERT(vector == GP_VECTOR, - "Expected #GP on XSETBV(0x%llx), supported XCR0 = %lx, got vector '0x%x'", - BIT_ULL(i), supported_xcr0, vector); + "Expected #GP on XSETBV(0x%llx), supported XCR0 = %lx, got %s", + BIT_ULL(i), supported_xcr0, ex_str(vector)); } GUEST_DONE(); diff --git a/tools/testing/selftests/kvm/x86/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86/xen_shinfo_test.c index a59b3c799bb2..5076f6a75455 100644 --- a/tools/testing/selftests/kvm/x86/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86/xen_shinfo_test.c @@ -116,15 +116,15 @@ struct pvclock_wall_clock { } __attribute__((__packed__)); struct vcpu_runstate_info { - uint32_t state; - uint64_t state_entry_time; - uint64_t time[5]; /* Extra field for overrun check */ + u32 state; + u64 state_entry_time; + u64 time[5]; /* Extra field for overrun check */ }; struct compat_vcpu_runstate_info { - uint32_t state; - uint64_t state_entry_time; - uint64_t time[5]; + u32 state; + u64 state_entry_time; + u64 time[5]; } __attribute__((__packed__)); struct arch_vcpu_info { @@ -133,8 +133,8 @@ struct arch_vcpu_info { }; struct vcpu_info { - uint8_t evtchn_upcall_pending; - uint8_t evtchn_upcall_mask; + u8 evtchn_upcall_pending; + u8 evtchn_upcall_mask; unsigned long evtchn_pending_sel; struct arch_vcpu_info arch; struct pvclock_vcpu_time_info time; @@ -145,7 +145,7 @@ struct shared_info { unsigned long evtchn_pending[64]; unsigned long evtchn_mask[64]; struct pvclock_wall_clock wc; - uint32_t wc_sec_hi; + u32 wc_sec_hi; /* arch_shared_info here */ }; @@ -191,10 +191,7 @@ static void guest_code(void) struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR; int i; - __asm__ __volatile__( - "sti\n" - "nop\n" - ); + sti_nop(); /* Trigger an interrupt injection */ GUEST_SYNC(TEST_INJECT_VECTOR); @@ -550,15 +547,9 @@ int main(int argc, char *argv[]) int irq_fd[2] = { -1, -1 }; if (do_eventfd_tests) { - irq_fd[0] = eventfd(0, 0); - irq_fd[1] = eventfd(0, 0); + irq_fd[0] = kvm_new_eventfd(); + irq_fd[1] = kvm_new_eventfd(); - /* 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; @@ -575,15 +566,8 @@ int main(int argc, char *argv[]) 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); + kvm_assign_irqfd(vm, 32, irq_fd[0]); + kvm_assign_irqfd(vm, 33, irq_fd[1]); struct sigaction sa = { }; sa.sa_handler = handle_alrm; @@ -674,7 +658,7 @@ int main(int argc, char *argv[]) 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; + rst.u.runstate.state = (u64)-1; rst.u.runstate.time_blocked = 0x5a - rs->time[RUNSTATE_blocked]; rst.u.runstate.time_offline = @@ -1129,7 +1113,7 @@ int main(int argc, char *argv[]) /* Don't change the address, just trigger a write */ struct kvm_xen_vcpu_attr adj = { .type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST, - .u.runstate.state = (uint64_t)-1 + .u.runstate.state = (u64)-1 }; vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &adj); diff --git a/tools/testing/selftests/kvm/x86/xss_msr_test.c b/tools/testing/selftests/kvm/x86/xss_msr_test.c index f331a4e9bae3..12c63df6bbce 100644 --- a/tools/testing/selftests/kvm/x86/xss_msr_test.c +++ b/tools/testing/selftests/kvm/x86/xss_msr_test.c @@ -17,7 +17,7 @@ int main(int argc, char *argv[]) bool xss_in_msr_list; struct kvm_vm *vm; struct kvm_vcpu *vcpu; - uint64_t xss_val; + u64 xss_val; int i, r; /* Create VM */ |