diff options
Diffstat (limited to 'tools')
51 files changed, 1876 insertions, 341 deletions
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index a792a599b9d6..1c13bfa2d38a 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -428,6 +428,7 @@ enum { #define KVM_DEV_ARM_ITS_RESTORE_TABLES 2 #define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3 #define KVM_DEV_ARM_ITS_CTRL_RESET 4 +#define KVM_DEV_ARM_VGIC_USERSPACE_PPIS 5 /* Device Control API on vcpu fd */ #define KVM_ARM_VCPU_PMU_V3_CTRL 0 diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 80364d4dbebb..d0c0c8605976 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1224,6 +1224,8 @@ enum kvm_device_type { #define KVM_DEV_TYPE_LOONGARCH_EIOINTC KVM_DEV_TYPE_LOONGARCH_EIOINTC KVM_DEV_TYPE_LOONGARCH_PCHPIC, #define KVM_DEV_TYPE_LOONGARCH_PCHPIC KVM_DEV_TYPE_LOONGARCH_PCHPIC + KVM_DEV_TYPE_ARM_VGIC_V5, +#define KVM_DEV_TYPE_ARM_VGIC_V5 KVM_DEV_TYPE_ARM_VGIC_V5 KVM_DEV_TYPE_MAX, diff --git a/tools/testing/selftests/ftrace/test.d/remotes/functions b/tools/testing/selftests/ftrace/test.d/remotes/functions index 97a09d564a34..05224fac3653 100644 --- a/tools/testing/selftests/ftrace/test.d/remotes/functions +++ b/tools/testing/selftests/ftrace/test.d/remotes/functions @@ -24,12 +24,21 @@ setup_remote_test() assert_loaded() { - grep -q "(loaded)" buffer_size_kb + grep -q "(loaded)" buffer_size_kb || return 1 } assert_unloaded() { - grep -q "(unloaded)" buffer_size_kb + grep -q "(unloaded)" buffer_size_kb || return 1 +} + +reload_remote() +{ + echo 0 > tracing_on + clear_trace + assert_unloaded + echo 1 > tracing_on + assert_loaded } dump_trace_pipe() @@ -79,10 +88,12 @@ get_cpu_ids() sed -n 's/^processor\s*:\s*\([0-9]\+\).*/\1/p' /proc/cpuinfo } -get_page_size() { +get_page_size() +{ sed -ne 's/^.*data.*size:\([0-9][0-9]*\).*/\1/p' events/header_page } -get_selftest_event_size() { +get_selftest_event_size() +{ sed -ne 's/^.*field:.*;.*size:\([0-9][0-9]*\);.*/\1/p' events/*/selftest/format | awk '{s+=$1} END {print s}' } diff --git a/tools/testing/selftests/ftrace/test.d/remotes/hotplug.tc b/tools/testing/selftests/ftrace/test.d/remotes/hotplug.tc new file mode 100644 index 000000000000..145617eb8061 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/remotes/hotplug.tc @@ -0,0 +1,88 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Test trace remote read with an offline CPU +# requires: remotes/test + +. $TEST_DIR/remotes/functions + +hotunplug_one_cpu() +{ + [ "$(get_cpu_ids | wc -l)" -ge 2 ] || return 1 + + for cpu in $(get_cpu_ids); do + echo 0 > /sys/devices/system/cpu/cpu$cpu/online || return 1 + break + done + + echo $cpu +} + +# Check non-consuming and consuming read +check_read() +{ + for i in $(seq 1 8); do + echo $i > write_event + done + + check_trace 1 8 trace + + output=$(dump_trace_pipe) + check_trace 1 8 $output + rm $output +} + +test_hotplug() +{ + echo 0 > trace + assert_loaded + + # + # Test a trace buffer containing an offline CPU + # + + cpu=$(hotunplug_one_cpu) || exit_unsupported + trap "echo 1 > /sys/devices/system/cpu/cpu$cpu/online" EXIT + + check_read + + # + # Test a trace buffer with a missing CPU + # + + reload_remote + + check_read + + # + # Test a trace buffer with a CPU added later + # + + echo 1 > /sys/devices/system/cpu/cpu$cpu/online + trap "" EXIT + assert_loaded + + check_read + + # Test if the ring-buffer for the newly added CPU is both writable and + # readable + for i in $(seq 1 8); do + taskset -c $cpu echo $i > write_event + done + + cd per_cpu/cpu$cpu/ + + check_trace 1 8 trace + + output=$(dump_trace_pipe) + check_trace 1 8 $output + rm $output + + cd - +} + +if [ -z "$SOURCE_REMOTE_TEST" ]; then + set -e + + setup_remote_test + test_hotplug +fi diff --git a/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/buffer_size.tc b/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/buffer_size.tc new file mode 100644 index 000000000000..64bf859d6406 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/buffer_size.tc @@ -0,0 +1,11 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Test hypervisor trace buffer size +# requires: remotes/hypervisor/write_event + +SOURCE_REMOTE_TEST=1 +. $TEST_DIR/remotes/buffer_size.tc + +set -e +setup_remote "hypervisor" +test_buffer_size diff --git a/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/hotplug.tc b/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/hotplug.tc new file mode 100644 index 000000000000..580ec32c8f81 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/hotplug.tc @@ -0,0 +1,11 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Test hypervisor trace read with an offline CPU +# requires: remotes/hypervisor/write_event + +SOURCE_REMOTE_TEST=1 +. $TEST_DIR/remotes/hotplug.tc + +set -e +setup_remote "hypervisor" +test_hotplug diff --git a/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/reset.tc b/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/reset.tc new file mode 100644 index 000000000000..7fe3b09b34e3 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/reset.tc @@ -0,0 +1,11 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Test hypervisor trace buffer reset +# requires: remotes/hypervisor/write_event + +SOURCE_REMOTE_TEST=1 +. $TEST_DIR/remotes/reset.tc + +set -e +setup_remote "hypervisor" +test_reset diff --git a/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/trace.tc b/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/trace.tc new file mode 100644 index 000000000000..b937c19ca7f9 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/trace.tc @@ -0,0 +1,11 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Test hypervisor non-consuming trace read +# requires: remotes/hypervisor/write_event + +SOURCE_REMOTE_TEST=1 +. $TEST_DIR/remotes/trace.tc + +set -e +setup_remote "hypervisor" +test_trace diff --git a/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/trace_pipe.tc b/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/trace_pipe.tc new file mode 100644 index 000000000000..66aa1b76c147 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/trace_pipe.tc @@ -0,0 +1,11 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Test hypervisor consuming trace read +# requires: remotes/hypervisor/write_event + +SOURCE_REMOTE_TEST=1 +. $TEST_DIR/remotes/trace_pipe.tc + +set -e +setup_remote "hypervisor" +test_trace_pipe diff --git a/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/unloading.tc b/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/unloading.tc new file mode 100644 index 000000000000..1dafde3414ab --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/remotes/hypervisor/unloading.tc @@ -0,0 +1,11 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Test hypervisor trace buffer unloading +# requires: remotes/hypervisor/write_event + +SOURCE_REMOTE_TEST=1 +. $TEST_DIR/remotes/unloading.tc + +set -e +setup_remote "hypervisor" +test_unloading diff --git a/tools/testing/selftests/ftrace/test.d/remotes/trace.tc b/tools/testing/selftests/ftrace/test.d/remotes/trace.tc index 170f7648732a..bc9377a70e8d 100644 --- a/tools/testing/selftests/ftrace/test.d/remotes/trace.tc +++ b/tools/testing/selftests/ftrace/test.d/remotes/trace.tc @@ -58,11 +58,7 @@ test_trace() # # Ensure the writer is not on the reader page by reloading the buffer - echo 0 > tracing_on - echo 0 > trace - assert_unloaded - echo 1 > tracing_on - assert_loaded + reload_remote # Ensure ring-buffer overflow by emitting events from the same CPU for cpu in $(get_cpu_ids); do @@ -96,27 +92,6 @@ test_trace() cd - > /dev/null done - - # - # Test with hotplug - # - - [ "$(get_cpu_ids | wc -l)" -ge 2 ] || return 0 - - echo 0 > trace - - for cpu in $(get_cpu_ids); do - echo 0 > /sys/devices/system/cpu/cpu$cpu/online || return 0 - break - done - - for i in $(seq 1 8); do - echo $i > write_event - done - - check_trace 1 8 trace - - echo 1 > /sys/devices/system/cpu/cpu$cpu/online } if [ -z "$SOURCE_REMOTE_TEST" ]; then diff --git a/tools/testing/selftests/ftrace/test.d/remotes/trace_pipe.tc b/tools/testing/selftests/ftrace/test.d/remotes/trace_pipe.tc index 669a7288ed7c..7f7b7b79c490 100644 --- a/tools/testing/selftests/ftrace/test.d/remotes/trace_pipe.tc +++ b/tools/testing/selftests/ftrace/test.d/remotes/trace_pipe.tc @@ -92,31 +92,6 @@ test_trace_pipe() rm $output cd - > /dev/null done - - # - # Test interaction with hotplug - # - - [ "$(get_cpu_ids | wc -l)" -ge 2 ] || return 0 - - echo 0 > trace - - for cpu in $(get_cpu_ids); do - echo 0 > /sys/devices/system/cpu/cpu$cpu/online || return 0 - break - done - - for i in $(seq 1 8); do - echo $i > write_event - done - - output=$(dump_trace_pipe) - - check_trace 1 8 $output - - rm $output - - echo 1 > /sys/devices/system/cpu/cpu$cpu/online } if [ -z "$SOURCE_REMOTE_TEST" ]; then diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index 6471fa214a9f..9118a5a51b89 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -64,6 +64,8 @@ TEST_GEN_PROGS_COMMON += kvm_binary_stats_test TEST_GEN_PROGS_COMMON += kvm_create_max_vcpus TEST_GEN_PROGS_COMMON += kvm_page_table_test TEST_GEN_PROGS_COMMON += set_memory_region_test +TEST_GEN_PROGS_COMMON += memslot_modification_stress_test +TEST_GEN_PROGS_COMMON += memslot_perf_test # Compiled test targets TEST_GEN_PROGS_x86 = $(TEST_GEN_PROGS_COMMON) @@ -111,8 +113,11 @@ TEST_GEN_PROGS_x86 += x86/state_test TEST_GEN_PROGS_x86 += x86/vmx_preemption_timer_test TEST_GEN_PROGS_x86 += x86/svm_vmcall_test TEST_GEN_PROGS_x86 += x86/svm_int_ctl_test +TEST_GEN_PROGS_x86 += x86/svm_nested_clear_efer_svme TEST_GEN_PROGS_x86 += x86/svm_nested_shutdown_test TEST_GEN_PROGS_x86 += x86/svm_nested_soft_inject_test +TEST_GEN_PROGS_x86 += x86/svm_nested_vmcb12_gpa +TEST_GEN_PROGS_x86 += x86/svm_lbr_nested_state TEST_GEN_PROGS_x86 += x86/tsc_scaling_sync TEST_GEN_PROGS_x86 += x86/sync_regs_test TEST_GEN_PROGS_x86 += x86/ucna_injection_test @@ -148,8 +153,6 @@ TEST_GEN_PROGS_x86 += coalesced_io_test TEST_GEN_PROGS_x86 += dirty_log_perf_test TEST_GEN_PROGS_x86 += guest_memfd_test TEST_GEN_PROGS_x86 += hardware_disable_test -TEST_GEN_PROGS_x86 += memslot_modification_stress_test -TEST_GEN_PROGS_x86 += memslot_perf_test TEST_GEN_PROGS_x86 += mmu_stress_test TEST_GEN_PROGS_x86 += rseq_test TEST_GEN_PROGS_x86 += steal_time @@ -177,8 +180,9 @@ TEST_GEN_PROGS_arm64 += arm64/vcpu_width_config TEST_GEN_PROGS_arm64 += arm64/vgic_init TEST_GEN_PROGS_arm64 += arm64/vgic_irq TEST_GEN_PROGS_arm64 += arm64/vgic_lpi_stress +TEST_GEN_PROGS_arm64 += arm64/vgic_v5 TEST_GEN_PROGS_arm64 += arm64/vpmu_counter_access -TEST_GEN_PROGS_arm64 += arm64/no-vgic-v3 +TEST_GEN_PROGS_arm64 += arm64/no-vgic TEST_GEN_PROGS_arm64 += arm64/idreg-idst TEST_GEN_PROGS_arm64 += arm64/kvm-uuid TEST_GEN_PROGS_arm64 += access_tracking_perf_test @@ -187,8 +191,6 @@ TEST_GEN_PROGS_arm64 += coalesced_io_test TEST_GEN_PROGS_arm64 += dirty_log_perf_test TEST_GEN_PROGS_arm64 += get-reg-list TEST_GEN_PROGS_arm64 += guest_memfd_test -TEST_GEN_PROGS_arm64 += memslot_modification_stress_test -TEST_GEN_PROGS_arm64 += memslot_perf_test TEST_GEN_PROGS_arm64 += mmu_stress_test TEST_GEN_PROGS_arm64 += rseq_test TEST_GEN_PROGS_arm64 += steal_time @@ -207,6 +209,7 @@ TEST_GEN_PROGS_s390 += s390/user_operexec TEST_GEN_PROGS_s390 += s390/keyop TEST_GEN_PROGS_s390 += rseq_test TEST_GEN_PROGS_s390 += s390/irq_routing +TEST_GEN_PROGS_s390 += mmu_stress_test TEST_GEN_PROGS_riscv = $(TEST_GEN_PROGS_COMMON) TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test @@ -216,13 +219,12 @@ TEST_GEN_PROGS_riscv += arch_timer TEST_GEN_PROGS_riscv += coalesced_io_test TEST_GEN_PROGS_riscv += dirty_log_perf_test TEST_GEN_PROGS_riscv += get-reg-list -TEST_GEN_PROGS_riscv += memslot_modification_stress_test -TEST_GEN_PROGS_riscv += memslot_perf_test TEST_GEN_PROGS_riscv += mmu_stress_test TEST_GEN_PROGS_riscv += rseq_test TEST_GEN_PROGS_riscv += steal_time -TEST_GEN_PROGS_loongarch = arch_timer +TEST_GEN_PROGS_loongarch = loongarch/pmu_test +TEST_GEN_PROGS_loongarch += arch_timer TEST_GEN_PROGS_loongarch += coalesced_io_test TEST_GEN_PROGS_loongarch += demand_paging_test TEST_GEN_PROGS_loongarch += dirty_log_perf_test diff --git a/tools/testing/selftests/kvm/arm64/at.c b/tools/testing/selftests/kvm/arm64/at.c index c8ee6f520734..ce5d312ef6ba 100644 --- a/tools/testing/selftests/kvm/arm64/at.c +++ b/tools/testing/selftests/kvm/arm64/at.c @@ -13,7 +13,6 @@ enum { CLEAR_ACCESS_FLAG, - TEST_ACCESS_FLAG, }; static u64 *ptep_hva; @@ -49,7 +48,6 @@ do { \ GUEST_ASSERT_EQ(FIELD_GET(SYS_PAR_EL1_ATTR, par), MAIR_ATTR_NORMAL); \ GUEST_ASSERT_EQ(FIELD_GET(SYS_PAR_EL1_SH, par), PTE_SHARED >> 8); \ GUEST_ASSERT_EQ(par & SYS_PAR_EL1_PA, TEST_ADDR); \ - GUEST_SYNC(TEST_ACCESS_FLAG); \ } \ } while (0) @@ -85,10 +83,6 @@ static void guest_code(void) if (!SYS_FIELD_GET(ID_AA64MMFR1_EL1, HAFDBS, read_sysreg(id_aa64mmfr1_el1))) GUEST_DONE(); - /* - * KVM's software PTW makes the implementation choice that the AT - * instruction sets the access flag. - */ sysreg_clear_set(tcr_el1, 0, TCR_HA); isb(); test_at(false); @@ -102,8 +96,8 @@ static void handle_sync(struct kvm_vcpu *vcpu, struct ucall *uc) case CLEAR_ACCESS_FLAG: /* * Delete + reinstall the memslot to invalidate stage-2 - * mappings of the stage-1 page tables, forcing KVM to - * use the 'slow' AT emulation path. + * mappings of the stage-1 page tables, allowing KVM to + * potentially use the 'slow' AT emulation path. * * This and clearing the access flag from host userspace * ensures that the access flag cannot be set speculatively @@ -112,10 +106,6 @@ static void handle_sync(struct kvm_vcpu *vcpu, struct ucall *uc) clear_bit(__ffs(PTE_AF), ptep_hva); vm_mem_region_reload(vcpu->vm, vcpu->vm->memslots[MEM_REGION_PT]); break; - case TEST_ACCESS_FLAG: - TEST_ASSERT(test_bit(__ffs(PTE_AF), ptep_hva), - "Expected access flag to be set (desc: %lu)", *ptep_hva); - break; default: TEST_FAIL("Unexpected SYNC arg: %lu", uc->args[1]); } diff --git a/tools/testing/selftests/kvm/arm64/no-vgic-v3.c b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c deleted file mode 100644 index 152c34776981..000000000000 --- a/tools/testing/selftests/kvm/arm64/no-vgic-v3.c +++ /dev/null @@ -1,177 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -// Check that, on a GICv3 system, not configuring GICv3 correctly -// results in all of the sysregs generating an UNDEF exception. - -#include <test_util.h> -#include <kvm_util.h> -#include <processor.h> - -static volatile bool handled; - -#define __check_sr_read(r) \ - ({ \ - uint64_t val; \ - \ - handled = false; \ - dsb(sy); \ - val = read_sysreg_s(SYS_ ## r); \ - val; \ - }) - -#define __check_sr_write(r) \ - do { \ - handled = false; \ - dsb(sy); \ - write_sysreg_s(0, SYS_ ## r); \ - isb(); \ - } while(0) - -/* Fatal checks */ -#define check_sr_read(r) \ - do { \ - __check_sr_read(r); \ - __GUEST_ASSERT(handled, #r " no read trap"); \ - } while(0) - -#define check_sr_write(r) \ - do { \ - __check_sr_write(r); \ - __GUEST_ASSERT(handled, #r " no write trap"); \ - } while(0) - -#define check_sr_rw(r) \ - do { \ - check_sr_read(r); \ - check_sr_write(r); \ - } while(0) - -static void guest_code(void) -{ - uint64_t val; - - /* - * Check that we advertise that ID_AA64PFR0_EL1.GIC == 0, having - * hidden the feature at runtime without any other userspace action. - */ - __GUEST_ASSERT(FIELD_GET(ID_AA64PFR0_EL1_GIC, - read_sysreg(id_aa64pfr0_el1)) == 0, - "GICv3 wrongly advertised"); - - /* - * Access all GICv3 registers, and fail if we don't get an UNDEF. - * Note that we happily access all the APxRn registers without - * checking their existance, as all we want to see is a failure. - */ - check_sr_rw(ICC_PMR_EL1); - check_sr_read(ICC_IAR0_EL1); - check_sr_write(ICC_EOIR0_EL1); - check_sr_rw(ICC_HPPIR0_EL1); - check_sr_rw(ICC_BPR0_EL1); - check_sr_rw(ICC_AP0R0_EL1); - check_sr_rw(ICC_AP0R1_EL1); - check_sr_rw(ICC_AP0R2_EL1); - check_sr_rw(ICC_AP0R3_EL1); - check_sr_rw(ICC_AP1R0_EL1); - check_sr_rw(ICC_AP1R1_EL1); - check_sr_rw(ICC_AP1R2_EL1); - check_sr_rw(ICC_AP1R3_EL1); - check_sr_write(ICC_DIR_EL1); - check_sr_read(ICC_RPR_EL1); - check_sr_write(ICC_SGI1R_EL1); - check_sr_write(ICC_ASGI1R_EL1); - check_sr_write(ICC_SGI0R_EL1); - check_sr_read(ICC_IAR1_EL1); - check_sr_write(ICC_EOIR1_EL1); - check_sr_rw(ICC_HPPIR1_EL1); - check_sr_rw(ICC_BPR1_EL1); - check_sr_rw(ICC_CTLR_EL1); - check_sr_rw(ICC_IGRPEN0_EL1); - check_sr_rw(ICC_IGRPEN1_EL1); - - /* - * ICC_SRE_EL1 may not be trappable, as ICC_SRE_EL2.Enable can - * be RAO/WI. Engage in non-fatal accesses, starting with a - * write of 0 to try and disable SRE, and let's see if it - * sticks. - */ - __check_sr_write(ICC_SRE_EL1); - if (!handled) - GUEST_PRINTF("ICC_SRE_EL1 write not trapping (OK)\n"); - - val = __check_sr_read(ICC_SRE_EL1); - if (!handled) { - __GUEST_ASSERT((val & BIT(0)), - "ICC_SRE_EL1 not trapped but ICC_SRE_EL1.SRE not set\n"); - GUEST_PRINTF("ICC_SRE_EL1 read not trapping (OK)\n"); - } - - GUEST_DONE(); -} - -static void guest_undef_handler(struct ex_regs *regs) -{ - /* Success, we've gracefully exploded! */ - handled = true; - regs->pc += 4; -} - -static void test_run_vcpu(struct kvm_vcpu *vcpu) -{ - struct ucall uc; - - do { - vcpu_run(vcpu); - - switch (get_ucall(vcpu, &uc)) { - case UCALL_ABORT: - REPORT_GUEST_ASSERT(uc); - break; - case UCALL_PRINTF: - printf("%s", uc.buffer); - break; - case UCALL_DONE: - break; - default: - TEST_FAIL("Unknown ucall %lu", uc.cmd); - } - } while (uc.cmd != UCALL_DONE); -} - -static void test_guest_no_gicv3(void) -{ - struct kvm_vcpu *vcpu; - struct kvm_vm *vm; - - /* Create a VM without a GICv3 */ - vm = vm_create_with_one_vcpu(&vcpu, guest_code); - - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - - vm_install_sync_handler(vm, VECTOR_SYNC_CURRENT, - ESR_ELx_EC_UNKNOWN, guest_undef_handler); - - test_run_vcpu(vcpu); - - kvm_vm_free(vm); -} - -int main(int argc, char *argv[]) -{ - struct kvm_vcpu *vcpu; - struct kvm_vm *vm; - uint64_t pfr0; - - test_disable_default_vgic(); - - vm = vm_create_with_one_vcpu(&vcpu, NULL); - pfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); - __TEST_REQUIRE(FIELD_GET(ID_AA64PFR0_EL1_GIC, pfr0), - "GICv3 not supported."); - kvm_vm_free(vm); - - test_guest_no_gicv3(); - - return 0; -} diff --git a/tools/testing/selftests/kvm/arm64/no-vgic.c b/tools/testing/selftests/kvm/arm64/no-vgic.c new file mode 100644 index 000000000000..b14686ef17d1 --- /dev/null +++ b/tools/testing/selftests/kvm/arm64/no-vgic.c @@ -0,0 +1,297 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Check that, on a GICv3-capable system (GICv3 native, or GICv5 with +// FEAT_GCIE_LEGACY), not configuring GICv3 correctly results in all +// of the sysregs generating an UNDEF exception. Do the same for GICv5 +// on a GICv5 host. + +#include <test_util.h> +#include <kvm_util.h> +#include <processor.h> + +#include <arm64/gic_v5.h> + +static volatile bool handled; + +#define __check_sr_read(r) \ + ({ \ + uint64_t val; \ + \ + handled = false; \ + dsb(sy); \ + val = read_sysreg_s(SYS_ ## r); \ + val; \ + }) + +#define __check_sr_write(r) \ + do { \ + handled = false; \ + dsb(sy); \ + write_sysreg_s(0, SYS_ ## r); \ + isb(); \ + } while (0) + +#define __check_gicv5_gicr_op(r) \ + ({ \ + uint64_t val; \ + \ + handled = false; \ + dsb(sy); \ + val = read_sysreg_s(GICV5_OP_GICR_ ## r); \ + val; \ + }) + +#define __check_gicv5_gic_op(r) \ + do { \ + handled = false; \ + dsb(sy); \ + write_sysreg_s(0, GICV5_OP_GIC_ ## r); \ + isb(); \ + } while (0) + +/* Fatal checks */ +#define check_sr_read(r) \ + do { \ + __check_sr_read(r); \ + __GUEST_ASSERT(handled, #r " no read trap"); \ + } while (0) + +#define check_sr_write(r) \ + do { \ + __check_sr_write(r); \ + __GUEST_ASSERT(handled, #r " no write trap"); \ + } while (0) + +#define check_sr_rw(r) \ + do { \ + check_sr_read(r); \ + check_sr_write(r); \ + } while (0) + +#define check_gicv5_gicr_op(r) \ + do { \ + __check_gicv5_gicr_op(r); \ + __GUEST_ASSERT(handled, #r " no read trap"); \ + } while (0) + +#define check_gicv5_gic_op(r) \ + do { \ + __check_gicv5_gic_op(r); \ + __GUEST_ASSERT(handled, #r " no write trap"); \ + } while (0) + +static void guest_code_gicv3(void) +{ + uint64_t val; + + /* + * Check that we advertise that ID_AA64PFR0_EL1.GIC == 0, having + * hidden the feature at runtime without any other userspace action. + */ + __GUEST_ASSERT(FIELD_GET(ID_AA64PFR0_EL1_GIC, + read_sysreg(id_aa64pfr0_el1)) == 0, + "GICv3 wrongly advertised"); + + /* + * Access all GICv3 registers, and fail if we don't get an UNDEF. + * Note that we happily access all the APxRn registers without + * checking their existence, as all we want to see is a failure. + */ + check_sr_rw(ICC_PMR_EL1); + check_sr_read(ICC_IAR0_EL1); + check_sr_write(ICC_EOIR0_EL1); + check_sr_rw(ICC_HPPIR0_EL1); + check_sr_rw(ICC_BPR0_EL1); + check_sr_rw(ICC_AP0R0_EL1); + check_sr_rw(ICC_AP0R1_EL1); + check_sr_rw(ICC_AP0R2_EL1); + check_sr_rw(ICC_AP0R3_EL1); + check_sr_rw(ICC_AP1R0_EL1); + check_sr_rw(ICC_AP1R1_EL1); + check_sr_rw(ICC_AP1R2_EL1); + check_sr_rw(ICC_AP1R3_EL1); + check_sr_write(ICC_DIR_EL1); + check_sr_read(ICC_RPR_EL1); + check_sr_write(ICC_SGI1R_EL1); + check_sr_write(ICC_ASGI1R_EL1); + check_sr_write(ICC_SGI0R_EL1); + check_sr_read(ICC_IAR1_EL1); + check_sr_write(ICC_EOIR1_EL1); + check_sr_rw(ICC_HPPIR1_EL1); + check_sr_rw(ICC_BPR1_EL1); + check_sr_rw(ICC_CTLR_EL1); + check_sr_rw(ICC_IGRPEN0_EL1); + check_sr_rw(ICC_IGRPEN1_EL1); + + /* + * ICC_SRE_EL1 may not be trappable, as ICC_SRE_EL2.Enable can + * be RAO/WI. Engage in non-fatal accesses, starting with a + * write of 0 to try and disable SRE, and let's see if it + * sticks. + */ + __check_sr_write(ICC_SRE_EL1); + if (!handled) + GUEST_PRINTF("ICC_SRE_EL1 write not trapping (OK)\n"); + + val = __check_sr_read(ICC_SRE_EL1); + if (!handled) { + __GUEST_ASSERT((val & BIT(0)), + "ICC_SRE_EL1 not trapped but ICC_SRE_EL1.SRE not set\n"); + GUEST_PRINTF("ICC_SRE_EL1 read not trapping (OK)\n"); + } + + GUEST_DONE(); +} + +static void guest_code_gicv5(void) +{ + /* + * Check that we advertise that ID_AA64PFR2_EL1.GCIE == 0, having + * hidden the feature at runtime without any other userspace action. + */ + __GUEST_ASSERT(FIELD_GET(ID_AA64PFR2_EL1_GCIE, + read_sysreg_s(SYS_ID_AA64PFR2_EL1)) == 0, + "GICv5 wrongly advertised"); + + /* + * Try all GICv5 instructions, and fail if we don't get an UNDEF. + */ + check_gicv5_gic_op(CDAFF); + check_gicv5_gic_op(CDDI); + check_gicv5_gic_op(CDDIS); + check_gicv5_gic_op(CDEOI); + check_gicv5_gic_op(CDHM); + check_gicv5_gic_op(CDPEND); + check_gicv5_gic_op(CDPRI); + check_gicv5_gic_op(CDRCFG); + check_gicv5_gicr_op(CDIA); + check_gicv5_gicr_op(CDNMIA); + + /* Check General System Register acccesses */ + check_sr_rw(ICC_APR_EL1); + check_sr_rw(ICC_CR0_EL1); + check_sr_read(ICC_HPPIR_EL1); + check_sr_read(ICC_IAFFIDR_EL1); + check_sr_rw(ICC_ICSR_EL1); + check_sr_read(ICC_IDR0_EL1); + check_sr_rw(ICC_PCR_EL1); + + /* Check PPI System Register accessess */ + check_sr_rw(ICC_PPI_CACTIVER0_EL1); + check_sr_rw(ICC_PPI_CACTIVER1_EL1); + check_sr_rw(ICC_PPI_SACTIVER0_EL1); + check_sr_rw(ICC_PPI_SACTIVER1_EL1); + check_sr_rw(ICC_PPI_CPENDR0_EL1); + check_sr_rw(ICC_PPI_CPENDR1_EL1); + check_sr_rw(ICC_PPI_SPENDR0_EL1); + check_sr_rw(ICC_PPI_SPENDR1_EL1); + check_sr_rw(ICC_PPI_ENABLER0_EL1); + check_sr_rw(ICC_PPI_ENABLER1_EL1); + check_sr_read(ICC_PPI_HMR0_EL1); + check_sr_read(ICC_PPI_HMR1_EL1); + check_sr_rw(ICC_PPI_PRIORITYR0_EL1); + check_sr_rw(ICC_PPI_PRIORITYR1_EL1); + check_sr_rw(ICC_PPI_PRIORITYR2_EL1); + check_sr_rw(ICC_PPI_PRIORITYR3_EL1); + check_sr_rw(ICC_PPI_PRIORITYR4_EL1); + check_sr_rw(ICC_PPI_PRIORITYR5_EL1); + check_sr_rw(ICC_PPI_PRIORITYR6_EL1); + check_sr_rw(ICC_PPI_PRIORITYR7_EL1); + check_sr_rw(ICC_PPI_PRIORITYR8_EL1); + check_sr_rw(ICC_PPI_PRIORITYR9_EL1); + check_sr_rw(ICC_PPI_PRIORITYR10_EL1); + check_sr_rw(ICC_PPI_PRIORITYR11_EL1); + check_sr_rw(ICC_PPI_PRIORITYR12_EL1); + check_sr_rw(ICC_PPI_PRIORITYR13_EL1); + check_sr_rw(ICC_PPI_PRIORITYR14_EL1); + check_sr_rw(ICC_PPI_PRIORITYR15_EL1); + + GUEST_DONE(); +} + +static void guest_undef_handler(struct ex_regs *regs) +{ + /* Success, we've gracefully exploded! */ + handled = true; + regs->pc += 4; +} + +static void test_run_vcpu(struct kvm_vcpu *vcpu) +{ + struct ucall uc; + + do { + vcpu_run(vcpu); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + break; + case UCALL_PRINTF: + printf("%s", uc.buffer); + break; + case UCALL_DONE: + break; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + } while (uc.cmd != UCALL_DONE); +} + +static void test_guest_no_vgic(void *guest_code) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + /* Create a VM without a GIC */ + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + + vm_install_sync_handler(vm, VECTOR_SYNC_CURRENT, + ESR_ELx_EC_UNKNOWN, guest_undef_handler); + + test_run_vcpu(vcpu); + + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + bool has_v3, has_v5; + uint64_t pfr; + + test_disable_default_vgic(); + + vm = vm_create_with_one_vcpu(&vcpu, NULL); + + pfr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); + has_v3 = !!FIELD_GET(ID_AA64PFR0_EL1_GIC, pfr); + + pfr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR2_EL1)); + has_v5 = !!FIELD_GET(ID_AA64PFR2_EL1_GCIE, pfr); + + kvm_vm_free(vm); + + __TEST_REQUIRE(has_v3 || has_v5, + "Neither GICv3 nor GICv5 supported."); + + if (has_v3) { + pr_info("Testing no-vgic-v3\n"); + test_guest_no_vgic(guest_code_gicv3); + } else { + pr_info("No GICv3 support: skipping no-vgic-v3 test\n"); + } + + if (has_v5) { + pr_info("Testing no-vgic-v5\n"); + test_guest_no_vgic(guest_code_gicv5); + } else { + pr_info("No GICv5 support: skipping no-vgic-v5 test\n"); + } + + return 0; +} diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c index fa3478a6c914..3a7e5fe9ae7a 100644 --- a/tools/testing/selftests/kvm/arm64/set_id_regs.c +++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c @@ -37,6 +37,9 @@ struct reg_ftr_bits { * For FTR_LOWER_SAFE, safe_val is used as the minimal safe value. */ int64_t safe_val; + + /* Allowed to be changed by the host after run */ + bool mutable; }; struct test_feature_reg { @@ -44,7 +47,7 @@ struct test_feature_reg { const struct reg_ftr_bits *ftr_bits; }; -#define __REG_FTR_BITS(NAME, SIGNED, TYPE, SHIFT, MASK, SAFE_VAL) \ +#define __REG_FTR_BITS(NAME, SIGNED, TYPE, SHIFT, MASK, SAFE_VAL, MUT) \ { \ .name = #NAME, \ .sign = SIGNED, \ @@ -52,15 +55,20 @@ struct test_feature_reg { .shift = SHIFT, \ .mask = MASK, \ .safe_val = SAFE_VAL, \ + .mutable = MUT, \ } #define REG_FTR_BITS(type, reg, field, safe_val) \ __REG_FTR_BITS(reg##_##field, FTR_UNSIGNED, type, reg##_##field##_SHIFT, \ - reg##_##field##_MASK, safe_val) + reg##_##field##_MASK, safe_val, false) + +#define REG_FTR_BITS_MUTABLE(type, reg, field, safe_val) \ + __REG_FTR_BITS(reg##_##field, FTR_UNSIGNED, type, reg##_##field##_SHIFT, \ + reg##_##field##_MASK, safe_val, true) #define S_REG_FTR_BITS(type, reg, field, safe_val) \ __REG_FTR_BITS(reg##_##field, FTR_SIGNED, type, reg##_##field##_SHIFT, \ - reg##_##field##_MASK, safe_val) + reg##_##field##_MASK, safe_val, false) #define REG_FTR_END \ { \ @@ -135,7 +143,8 @@ static const struct reg_ftr_bits ftr_id_aa64pfr0_el1[] = { REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, CSV2, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, DIT, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, SEL2, 0), - REG_FTR_BITS(FTR_EXACT, ID_AA64PFR0_EL1, GIC, 0), + /* GICv3 support will be forced at run time if available */ + REG_FTR_BITS_MUTABLE(FTR_EXACT, ID_AA64PFR0_EL1, GIC, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL3, 1), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL2, 1), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL1, 1), @@ -635,12 +644,38 @@ static void test_user_set_mte_reg(struct kvm_vcpu *vcpu) ksft_test_result_pass("ID_AA64PFR1_EL1.MTE_frac no longer 0xF\n"); } +static uint64_t reset_mutable_bits(uint32_t id, uint64_t val) +{ + struct test_feature_reg *reg = NULL; + + for (int i = 0; i < ARRAY_SIZE(test_regs); i++) { + if (test_regs[i].reg == id) { + reg = &test_regs[i]; + break; + } + } + + if (!reg) + return val; + + for (const struct reg_ftr_bits *bits = reg->ftr_bits; bits->type != FTR_END; bits++) { + if (bits->mutable) { + val &= ~bits->mask; + val |= bits->safe_val << bits->shift; + } + } + + return val; +} + static void test_guest_reg_read(struct kvm_vcpu *vcpu) { bool done = false; struct ucall uc; while (!done) { + uint64_t val; + vcpu_run(vcpu); switch (get_ucall(vcpu, &uc)) { @@ -648,9 +683,11 @@ static void test_guest_reg_read(struct kvm_vcpu *vcpu) REPORT_GUEST_ASSERT(uc); break; case UCALL_SYNC: + val = test_reg_vals[encoding_to_range_idx(uc.args[2])]; + val = reset_mutable_bits(uc.args[2], val); + /* Make sure the written values are seen by guest */ - TEST_ASSERT_EQ(test_reg_vals[encoding_to_range_idx(uc.args[2])], - uc.args[3]); + TEST_ASSERT_EQ(val, reset_mutable_bits(uc.args[2], uc.args[3])); break; case UCALL_DONE: done = true; @@ -741,7 +778,8 @@ static void test_assert_id_reg_unchanged(struct kvm_vcpu *vcpu, uint32_t encodin uint64_t observed; observed = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(encoding)); - TEST_ASSERT_EQ(test_reg_vals[idx], observed); + TEST_ASSERT_EQ(reset_mutable_bits(encoding, test_reg_vals[idx]), + reset_mutable_bits(encoding, observed)); } static void test_reset_preserves_id_regs(struct kvm_vcpu *vcpu) diff --git a/tools/testing/selftests/kvm/arm64/vgic_v5.c b/tools/testing/selftests/kvm/arm64/vgic_v5.c new file mode 100644 index 000000000000..3ce6cf37a629 --- /dev/null +++ b/tools/testing/selftests/kvm/arm64/vgic_v5.c @@ -0,0 +1,228 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/kernel.h> +#include <sys/syscall.h> +#include <asm/kvm.h> +#include <asm/kvm_para.h> + +#include <arm64/gic_v5.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "vgic.h" + +#define NR_VCPUS 1 + +struct vm_gic { + struct kvm_vm *vm; + int gic_fd; + uint32_t gic_dev_type; +}; + +static uint64_t max_phys_size; + +#define GUEST_CMD_IRQ_CDIA 10 +#define GUEST_CMD_IRQ_DIEOI 11 +#define GUEST_CMD_IS_AWAKE 12 +#define GUEST_CMD_IS_READY 13 + +static void guest_irq_handler(struct ex_regs *regs) +{ + bool valid; + u32 hwirq; + u64 ia; + static int count; + + /* + * We have pending interrupts. Should never actually enter WFI + * here! + */ + wfi(); + GUEST_SYNC(GUEST_CMD_IS_AWAKE); + + ia = gicr_insn(CDIA); + valid = GICV5_GICR_CDIA_VALID(ia); + + GUEST_SYNC(GUEST_CMD_IRQ_CDIA); + + if (!valid) + return; + + gsb_ack(); + isb(); + + hwirq = FIELD_GET(GICV5_GICR_CDIA_INTID, ia); + + gic_insn(hwirq, CDDI); + gic_insn(0, CDEOI); + + GUEST_SYNC(GUEST_CMD_IRQ_DIEOI); + + if (++count >= 2) + GUEST_DONE(); + + /* Ask for the next interrupt to be injected */ + GUEST_SYNC(GUEST_CMD_IS_READY); +} + +static void guest_code(void) +{ + local_irq_disable(); + + gicv5_cpu_enable_interrupts(); + local_irq_enable(); + + /* Enable the SW_PPI (3) */ + write_sysreg_s(BIT_ULL(3), SYS_ICC_PPI_ENABLER0_EL1); + + /* Ask for the first interrupt to be injected */ + GUEST_SYNC(GUEST_CMD_IS_READY); + + /* Loop forever waiting for interrupts */ + while (1); +} + + +/* we don't want to assert on run execution, hence that helper */ +static int run_vcpu(struct kvm_vcpu *vcpu) +{ + return __vcpu_run(vcpu) ? -errno : 0; +} + +static void vm_gic_destroy(struct vm_gic *v) +{ + close(v->gic_fd); + kvm_vm_free(v->vm); +} + +static void test_vgic_v5_ppis(uint32_t gic_dev_type) +{ + struct kvm_vcpu *vcpus[NR_VCPUS]; + struct ucall uc; + u64 user_ppis[2]; + struct vm_gic v; + int ret, i; + + v.gic_dev_type = gic_dev_type; + v.vm = __vm_create(VM_SHAPE_DEFAULT, NR_VCPUS, 0); + + v.gic_fd = kvm_create_device(v.vm, gic_dev_type); + + for (i = 0; i < NR_VCPUS; i++) + vcpus[i] = vm_vcpu_add(v.vm, i, guest_code); + + vm_init_descriptor_tables(v.vm); + vm_install_exception_handler(v.vm, VECTOR_IRQ_CURRENT, guest_irq_handler); + + for (i = 0; i < NR_VCPUS; i++) + vcpu_init_descriptor_tables(vcpus[i]); + + kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, + KVM_DEV_ARM_VGIC_CTRL_INIT, NULL); + + /* Read out the PPIs that user space is allowed to drive. */ + kvm_device_attr_get(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, + KVM_DEV_ARM_VGIC_USERSPACE_PPIS, &user_ppis); + + /* We should always be able to drive the SW_PPI. */ + TEST_ASSERT(user_ppis[0] & BIT(GICV5_ARCH_PPI_SW_PPI), + "SW_PPI is not drivable by userspace"); + + while (1) { + ret = run_vcpu(vcpus[0]); + + switch (get_ucall(vcpus[0], &uc)) { + case UCALL_SYNC: + /* + * The guest is ready for the next level change. Set + * high if ready, and lower if it has been consumed. + */ + if (uc.args[1] == GUEST_CMD_IS_READY || + uc.args[1] == GUEST_CMD_IRQ_DIEOI) { + u64 irq; + bool level = uc.args[1] == GUEST_CMD_IRQ_DIEOI ? 0 : 1; + + irq = FIELD_PREP(KVM_ARM_IRQ_NUM_MASK, 3); + irq |= KVM_ARM_IRQ_TYPE_PPI << KVM_ARM_IRQ_TYPE_SHIFT; + + _kvm_irq_line(v.vm, irq, level); + } else if (uc.args[1] == GUEST_CMD_IS_AWAKE) { + pr_info("Guest skipping WFI due to pending IRQ\n"); + } else if (uc.args[1] == GUEST_CMD_IRQ_CDIA) { + pr_info("Guest acknowledged IRQ\n"); + } + + continue; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + break; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + } + +done: + TEST_ASSERT(ret == 0, "Failed to test GICv5 PPIs"); + + vm_gic_destroy(&v); +} + +/* + * Returns 0 if it's possible to create GIC device of a given type (V5). + */ +int test_kvm_device(uint32_t gic_dev_type) +{ + struct kvm_vcpu *vcpus[NR_VCPUS]; + struct vm_gic v; + int ret; + + v.vm = vm_create_with_vcpus(NR_VCPUS, guest_code, vcpus); + + /* try to create a non existing KVM device */ + ret = __kvm_test_create_device(v.vm, 0); + TEST_ASSERT(ret && errno == ENODEV, "unsupported device"); + + /* trial mode */ + ret = __kvm_test_create_device(v.vm, gic_dev_type); + if (ret) + return ret; + v.gic_fd = kvm_create_device(v.vm, gic_dev_type); + + ret = __kvm_create_device(v.vm, gic_dev_type); + TEST_ASSERT(ret < 0 && errno == EEXIST, "create GIC device twice"); + + vm_gic_destroy(&v); + + return 0; +} + +void run_tests(uint32_t gic_dev_type) +{ + pr_info("Test VGICv5 PPIs\n"); + test_vgic_v5_ppis(gic_dev_type); +} + +int main(int ac, char **av) +{ + int ret; + int pa_bits; + + test_disable_default_vgic(); + + pa_bits = vm_guest_mode_params[VM_MODE_DEFAULT].pa_bits; + max_phys_size = 1ULL << pa_bits; + + ret = test_kvm_device(KVM_DEV_TYPE_ARM_VGIC_V5); + if (ret) { + pr_info("No GICv5 support; Not running GIC_v5 tests.\n"); + exit(KSFT_SKIP); + } + + pr_info("Running VGIC_V5 tests.\n"); + run_tests(KVM_DEV_TYPE_ARM_VGIC_V5); + + return 0; +} diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index d58a641b0e6a..7627b328f18a 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -641,9 +641,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) } #ifdef __s390x__ - /* Align to 1M (segment size) */ - guest_test_phys_mem = align_down(guest_test_phys_mem, 1 << 20); - /* * The workaround in guest_code() to write all pages prior to the first * iteration isn't compatible with the dirty ring, as the dirty ring diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index cc329b57ce2e..ec7644aae999 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -171,6 +171,64 @@ static void test_numa_allocation(int fd, size_t total_size) kvm_munmap(mem, total_size); } +static void test_collapse(int fd, uint64_t flags) +{ + const size_t pmd_size = get_trans_hugepagesz(); + void *reserved_addr; + void *aligned_addr; + char *mem; + off_t i; + + /* + * To even reach the point where the guest_memfd folios will + * get collapsed, both the userspace address and the offset + * within the guest_memfd have to be aligned to pmd_size. + * + * To achieve that alignment, reserve virtual address space + * with regular mmap, then use MAP_FIXED to allocate memory + * from a pmd_size-aligned offset (0) at a known, available + * virtual address. + */ + reserved_addr = kvm_mmap(pmd_size * 2, PROT_NONE, + MAP_PRIVATE | MAP_ANONYMOUS, -1); + aligned_addr = align_ptr_up(reserved_addr, pmd_size); + + mem = mmap(aligned_addr, pmd_size, PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_SHARED, fd, 0); + TEST_ASSERT(IS_ALIGNED((u64)mem, pmd_size), + "Userspace address must be aligned to PMD size."); + + /* + * Use reads to populate page table to avoid setting dirty + * flag on page. + */ + for (i = 0; i < pmd_size; i += getpagesize()) + READ_ONCE(mem[i]); + + /* + * Advising the use of huge pages in guest_memfd should be + * fine... + */ + kvm_madvise(mem, pmd_size, MADV_HUGEPAGE); + + /* + * ... but collapsing folios must not be supported to avoid + * mapping beyond shared ranges into host userspace page + * tables. + */ + TEST_ASSERT_EQ(madvise(mem, pmd_size, MADV_COLLAPSE), -1); + TEST_ASSERT_EQ(errno, EINVAL); + + /* + * Removing from host page tables and re-faulting should be + * fine; should not end up faulting in a collapsed/huge folio. + */ + kvm_madvise(mem, pmd_size, MADV_DONTNEED); + READ_ONCE(mem[0]); + + kvm_munmap(reserved_addr, pmd_size * 2); +} + static void test_fault_sigbus(int fd, size_t accessible_size, size_t map_size) { const char val = 0xaa; @@ -350,14 +408,17 @@ static void test_guest_memfd_flags(struct kvm_vm *vm) } } -#define gmem_test(__test, __vm, __flags) \ +#define __gmem_test(__test, __vm, __flags, __gmem_size) \ do { \ - int fd = vm_create_guest_memfd(__vm, page_size * 4, __flags); \ + int fd = vm_create_guest_memfd(__vm, __gmem_size, __flags); \ \ - test_##__test(fd, page_size * 4); \ + test_##__test(fd, __gmem_size); \ close(fd); \ } while (0) +#define gmem_test(__test, __vm, __flags) \ + __gmem_test(__test, __vm, __flags, page_size * 4) + static void __test_guest_memfd(struct kvm_vm *vm, uint64_t flags) { test_create_guest_memfd_multiple(vm); @@ -367,9 +428,12 @@ static void __test_guest_memfd(struct kvm_vm *vm, uint64_t flags) if (flags & GUEST_MEMFD_FLAG_MMAP) { if (flags & GUEST_MEMFD_FLAG_INIT_SHARED) { + size_t pmd_size = get_trans_hugepagesz(); + gmem_test(mmap_supported, vm, flags); gmem_test(fault_overflow, vm, flags); gmem_test(numa_allocation, vm, flags); + __gmem_test(collapse, vm, flags, pmd_size); } else { gmem_test(fault_private, vm, flags); } diff --git a/tools/testing/selftests/kvm/include/arm64/gic_v5.h b/tools/testing/selftests/kvm/include/arm64/gic_v5.h new file mode 100644 index 000000000000..eb523d9277cf --- /dev/null +++ b/tools/testing/selftests/kvm/include/arm64/gic_v5.h @@ -0,0 +1,150 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __SELFTESTS_GIC_V5_H +#define __SELFTESTS_GIC_V5_H + +#include <asm/barrier.h> +#include <asm/sysreg.h> + +#include <linux/bitfield.h> + +#include "processor.h" + +/* + * Definitions for GICv5 instructions for the Current Domain + */ +#define GICV5_OP_GIC_CDAFF sys_insn(1, 0, 12, 1, 3) +#define GICV5_OP_GIC_CDDI sys_insn(1, 0, 12, 2, 0) +#define GICV5_OP_GIC_CDDIS sys_insn(1, 0, 12, 1, 0) +#define GICV5_OP_GIC_CDHM sys_insn(1, 0, 12, 2, 1) +#define GICV5_OP_GIC_CDEN sys_insn(1, 0, 12, 1, 1) +#define GICV5_OP_GIC_CDEOI sys_insn(1, 0, 12, 1, 7) +#define GICV5_OP_GIC_CDPEND sys_insn(1, 0, 12, 1, 4) +#define GICV5_OP_GIC_CDPRI sys_insn(1, 0, 12, 1, 2) +#define GICV5_OP_GIC_CDRCFG sys_insn(1, 0, 12, 1, 5) +#define GICV5_OP_GICR_CDIA sys_insn(1, 0, 12, 3, 0) +#define GICV5_OP_GICR_CDNMIA sys_insn(1, 0, 12, 3, 1) + +/* Definitions for GIC CDAFF */ +#define GICV5_GIC_CDAFF_IAFFID_MASK GENMASK_ULL(47, 32) +#define GICV5_GIC_CDAFF_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GIC_CDAFF_IRM_MASK BIT_ULL(28) +#define GICV5_GIC_CDAFF_ID_MASK GENMASK_ULL(23, 0) + +/* Definitions for GIC CDDI */ +#define GICV5_GIC_CDDI_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GIC_CDDI_ID_MASK GENMASK_ULL(23, 0) + +/* Definitions for GIC CDDIS */ +#define GICV5_GIC_CDDIS_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GIC_CDDIS_TYPE(r) FIELD_GET(GICV5_GIC_CDDIS_TYPE_MASK, r) +#define GICV5_GIC_CDDIS_ID_MASK GENMASK_ULL(23, 0) +#define GICV5_GIC_CDDIS_ID(r) FIELD_GET(GICV5_GIC_CDDIS_ID_MASK, r) + +/* Definitions for GIC CDEN */ +#define GICV5_GIC_CDEN_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GIC_CDEN_ID_MASK GENMASK_ULL(23, 0) + +/* Definitions for GIC CDHM */ +#define GICV5_GIC_CDHM_HM_MASK BIT_ULL(32) +#define GICV5_GIC_CDHM_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GIC_CDHM_ID_MASK GENMASK_ULL(23, 0) + +/* Definitions for GIC CDPEND */ +#define GICV5_GIC_CDPEND_PENDING_MASK BIT_ULL(32) +#define GICV5_GIC_CDPEND_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GIC_CDPEND_ID_MASK GENMASK_ULL(23, 0) + +/* Definitions for GIC CDPRI */ +#define GICV5_GIC_CDPRI_PRIORITY_MASK GENMASK_ULL(39, 35) +#define GICV5_GIC_CDPRI_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GIC_CDPRI_ID_MASK GENMASK_ULL(23, 0) + +/* Definitions for GIC CDRCFG */ +#define GICV5_GIC_CDRCFG_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GIC_CDRCFG_ID_MASK GENMASK_ULL(23, 0) + +/* Definitions for GICR CDIA */ +#define GICV5_GICR_CDIA_VALID_MASK BIT_ULL(32) +#define GICV5_GICR_CDIA_VALID(r) FIELD_GET(GICV5_GICR_CDIA_VALID_MASK, r) +#define GICV5_GICR_CDIA_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GICR_CDIA_ID_MASK GENMASK_ULL(23, 0) +#define GICV5_GICR_CDIA_INTID GENMASK_ULL(31, 0) + +/* Definitions for GICR CDNMIA */ +#define GICV5_GICR_CDNMIA_VALID_MASK BIT_ULL(32) +#define GICV5_GICR_CDNMIA_VALID(r) FIELD_GET(GICV5_GICR_CDNMIA_VALID_MASK, r) +#define GICV5_GICR_CDNMIA_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GICR_CDNMIA_ID_MASK GENMASK_ULL(23, 0) + +#define gicr_insn(insn) read_sysreg_s(GICV5_OP_GICR_##insn) +#define gic_insn(v, insn) write_sysreg_s(v, GICV5_OP_GIC_##insn) + +#define __GIC_BARRIER_INSN(op0, op1, CRn, CRm, op2, Rt) \ + __emit_inst(0xd5000000 | \ + sys_insn((op0), (op1), (CRn), (CRm), (op2)) | \ + ((Rt) & 0x1f)) + +#define GSB_SYS_BARRIER_INSN __GIC_BARRIER_INSN(1, 0, 12, 0, 0, 31) +#define GSB_ACK_BARRIER_INSN __GIC_BARRIER_INSN(1, 0, 12, 0, 1, 31) + +#define gsb_ack() asm volatile(GSB_ACK_BARRIER_INSN : : : "memory") +#define gsb_sys() asm volatile(GSB_SYS_BARRIER_INSN : : : "memory") + +#define REPEAT_BYTE(x) ((~0ul / 0xff) * (x)) + +#define GICV5_IRQ_DEFAULT_PRI 0b10000 + +#define GICV5_ARCH_PPI_SW_PPI 0x3 + +void gicv5_ppi_priority_init(void) +{ + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR0_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR1_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR2_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR3_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR4_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR5_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR6_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR7_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR8_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR9_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR10_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR11_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR12_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR13_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR14_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR15_EL1); + + /* + * Context syncronization required to make sure system register writes + * effects are synchronised. + */ + isb(); +} + +void gicv5_cpu_disable_interrupts(void) +{ + u64 cr0; + + cr0 = FIELD_PREP(ICC_CR0_EL1_EN, 0); + write_sysreg_s(cr0, SYS_ICC_CR0_EL1); +} + +void gicv5_cpu_enable_interrupts(void) +{ + u64 cr0, pcr; + + write_sysreg_s(0, SYS_ICC_PPI_ENABLER0_EL1); + write_sysreg_s(0, SYS_ICC_PPI_ENABLER1_EL1); + + gicv5_ppi_priority_init(); + + pcr = FIELD_PREP(ICC_PCR_EL1_PRIORITY, GICV5_IRQ_DEFAULT_PRI); + write_sysreg_s(pcr, SYS_ICC_PCR_EL1); + + cr0 = FIELD_PREP(ICC_CR0_EL1_EN, 1); + write_sysreg_s(cr0, SYS_ICC_CR0_EL1); +} + +#endif diff --git a/tools/testing/selftests/kvm/include/kvm_syscalls.h b/tools/testing/selftests/kvm/include/kvm_syscalls.h index d4e613162bba..843c9904c46f 100644 --- a/tools/testing/selftests/kvm/include/kvm_syscalls.h +++ b/tools/testing/selftests/kvm/include/kvm_syscalls.h @@ -77,5 +77,6 @@ __KVM_SYSCALL_DEFINE(munmap, 2, void *, mem, size_t, size); __KVM_SYSCALL_DEFINE(close, 1, int, fd); __KVM_SYSCALL_DEFINE(fallocate, 4, int, fd, int, mode, loff_t, offset, loff_t, len); __KVM_SYSCALL_DEFINE(ftruncate, 2, unsigned int, fd, off_t, length); +__KVM_SYSCALL_DEFINE(madvise, 3, void *, addr, size_t, length, int, advice); #endif /* SELFTEST_KVM_SYSCALLS_H */ diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 8b39cb919f4f..f861242b4ae8 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -1127,10 +1127,6 @@ vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) { unsigned int n; n = vm_num_guest_pages(mode, vm_num_host_pages(mode, num_guest_pages)); -#ifdef __s390x__ - /* s390 requires 1M aligned guest sizes */ - n = (n + 255) & ~255; -#endif return n; } diff --git a/tools/testing/selftests/kvm/include/kvm_util_types.h b/tools/testing/selftests/kvm/include/kvm_util_types.h index ec787b97cf18..0366e9bce7f9 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_types.h +++ b/tools/testing/selftests/kvm/include/kvm_util_types.h @@ -17,4 +17,6 @@ typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */ +#define INVALID_GPA (~(uint64_t)0) + #endif /* SELFTEST_KVM_UTIL_TYPES_H */ diff --git a/tools/testing/selftests/kvm/include/loongarch/pmu.h b/tools/testing/selftests/kvm/include/loongarch/pmu.h new file mode 100644 index 000000000000..478e6a9bbb2b --- /dev/null +++ b/tools/testing/selftests/kvm/include/loongarch/pmu.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * LoongArch PMU specific interface + */ +#ifndef SELFTEST_KVM_PMU_H +#define SELFTEST_KVM_PMU_H + +#include "processor.h" + +#define LOONGARCH_CPUCFG6 0x6 +#define CPUCFG6_PMP BIT(0) +#define CPUCFG6_PAMVER GENMASK(3, 1) +#define CPUCFG6_PMNUM GENMASK(7, 4) +#define CPUCFG6_PMNUM_SHIFT 4 +#define CPUCFG6_PMBITS GENMASK(13, 8) +#define CPUCFG6_PMBITS_SHIFT 8 +#define CPUCFG6_UPM BIT(14) + +/* Performance Counter registers */ +#define LOONGARCH_CSR_PERFCTRL0 0x200 /* perf event 0 config */ +#define LOONGARCH_CSR_PERFCNTR0 0x201 /* perf event 0 count value */ +#define LOONGARCH_CSR_PERFCTRL1 0x202 /* perf event 1 config */ +#define LOONGARCH_CSR_PERFCNTR1 0x203 /* perf event 1 count value */ +#define LOONGARCH_CSR_PERFCTRL2 0x204 /* perf event 2 config */ +#define LOONGARCH_CSR_PERFCNTR2 0x205 /* perf event 2 count value */ +#define LOONGARCH_CSR_PERFCTRL3 0x206 /* perf event 3 config */ +#define LOONGARCH_CSR_PERFCNTR3 0x207 /* perf event 3 count value */ +#define CSR_PERFCTRL_PLV0 BIT(16) +#define CSR_PERFCTRL_PLV1 BIT(17) +#define CSR_PERFCTRL_PLV2 BIT(18) +#define CSR_PERFCTRL_PLV3 BIT(19) +#define CSR_PERFCTRL_PMIE BIT(20) +#define PMU_ENVENT_ENABLED (CSR_PERFCTRL_PLV0 | CSR_PERFCTRL_PLV1 | CSR_PERFCTRL_PLV2 | CSR_PERFCTRL_PLV3) + +/* Hardware event codes (from LoongArch perf_event.c */ +#define LOONGARCH_PMU_EVENT_CYCLES 0x00 /* CPU cycles */ +#define LOONGARCH_PMU_EVENT_INSTR_RETIRED 0x01 /* Instructions retired */ +#define PERF_COUNT_HW_BRANCH_INSTRUCTIONS 0x02 /* Branch instructions */ +#define PERF_COUNT_HW_BRANCH_MISSES 0x03 /* Branch misses */ + +#define NUM_LOOPS 1000 +#define EXPECTED_INSTR_MIN (NUM_LOOPS + 10) /* Loop + overhead */ +#define EXPECTED_CYCLES_MIN NUM_LOOPS /* At least 1 cycle per iteration */ +#define UPPER_BOUND (10 * NUM_LOOPS) + +#define PMU_OVERFLOW (1ULL << 63) + +static inline void pmu_irq_enable(void) +{ + unsigned long val; + + val = csr_read(LOONGARCH_CSR_ECFG); + val |= ECFGF_PMU; + csr_write(val, LOONGARCH_CSR_ECFG); +} + +static inline void pmu_irq_disable(void) +{ + unsigned long val; + + val = csr_read(LOONGARCH_CSR_ECFG); + val &= ~ECFGF_PMU; + csr_write(val, LOONGARCH_CSR_ECFG); +} + +#endif diff --git a/tools/testing/selftests/kvm/include/loongarch/processor.h b/tools/testing/selftests/kvm/include/loongarch/processor.h index 76840ddda57d..93dc1fbd2e79 100644 --- a/tools/testing/selftests/kvm/include/loongarch/processor.h +++ b/tools/testing/selftests/kvm/include/loongarch/processor.h @@ -83,6 +83,8 @@ #define LOONGARCH_CSR_PRMD 0x1 #define LOONGARCH_CSR_EUEN 0x2 #define LOONGARCH_CSR_ECFG 0x4 +#define ECFGB_PMU 10 +#define ECFGF_PMU (BIT_ULL(ECFGB_PMU)) #define ECFGB_TIMER 11 #define ECFGF_TIMER (BIT_ULL(ECFGB_TIMER)) #define LOONGARCH_CSR_ESTAT 0x5 /* Exception status */ @@ -90,6 +92,7 @@ #define CSR_ESTAT_EXC_WIDTH 6 #define CSR_ESTAT_EXC (0x3f << CSR_ESTAT_EXC_SHIFT) #define EXCCODE_INT 0 /* Interrupt */ +#define INT_PMI 10 /* PMU interrupt */ #define INT_TI 11 /* Timer interrupt*/ #define LOONGARCH_CSR_ERA 0x6 /* ERA */ #define LOONGARCH_CSR_BADV 0x7 /* Bad virtual address */ @@ -128,6 +131,17 @@ #define CSR_TLBREHI_PS_SHIFT 0 #define CSR_TLBREHI_PS (0x3fUL << CSR_TLBREHI_PS_SHIFT) +#define read_cpucfg(reg) \ +({ \ + register unsigned long __v; \ + __asm__ __volatile__( \ + "cpucfg %0, %1\n\t" \ + : "=r" (__v) \ + : "r" (reg) \ + : "memory"); \ + __v; \ +}) + #define csr_read(csr) \ ({ \ register unsigned long __v; \ @@ -178,6 +192,7 @@ struct handlers { handler_fn exception_handlers[VECTOR_NUM]; }; +void loongarch_vcpu_setup(struct kvm_vcpu *vcpu); void vm_init_descriptor_tables(struct kvm_vm *vm); void vm_install_exception_handler(struct kvm_vm *vm, int vector, handler_fn handler); diff --git a/tools/testing/selftests/kvm/include/riscv/sbi.h b/tools/testing/selftests/kvm/include/riscv/sbi.h index 046b432ae896..16f1815ac48f 100644 --- a/tools/testing/selftests/kvm/include/riscv/sbi.h +++ b/tools/testing/selftests/kvm/include/riscv/sbi.h @@ -97,6 +97,43 @@ enum sbi_pmu_hw_generic_events_t { SBI_PMU_HW_GENERAL_MAX, }; +enum sbi_pmu_fw_generic_events_t { + SBI_PMU_FW_MISALIGNED_LOAD = 0, + SBI_PMU_FW_MISALIGNED_STORE = 1, + SBI_PMU_FW_ACCESS_LOAD = 2, + SBI_PMU_FW_ACCESS_STORE = 3, + SBI_PMU_FW_ILLEGAL_INSN = 4, + SBI_PMU_FW_SET_TIMER = 5, + SBI_PMU_FW_IPI_SENT = 6, + SBI_PMU_FW_IPI_RCVD = 7, + SBI_PMU_FW_FENCE_I_SENT = 8, + SBI_PMU_FW_FENCE_I_RCVD = 9, + SBI_PMU_FW_SFENCE_VMA_SENT = 10, + SBI_PMU_FW_SFENCE_VMA_RCVD = 11, + SBI_PMU_FW_SFENCE_VMA_ASID_SENT = 12, + SBI_PMU_FW_SFENCE_VMA_ASID_RCVD = 13, + + SBI_PMU_FW_HFENCE_GVMA_SENT = 14, + SBI_PMU_FW_HFENCE_GVMA_RCVD = 15, + SBI_PMU_FW_HFENCE_GVMA_VMID_SENT = 16, + SBI_PMU_FW_HFENCE_GVMA_VMID_RCVD = 17, + + SBI_PMU_FW_HFENCE_VVMA_SENT = 18, + SBI_PMU_FW_HFENCE_VVMA_RCVD = 19, + SBI_PMU_FW_HFENCE_VVMA_ASID_SENT = 20, + SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD = 21, + SBI_PMU_FW_MAX, +}; + +/* SBI PMU event types */ +enum sbi_pmu_event_type { + SBI_PMU_EVENT_TYPE_HW = 0x0, + SBI_PMU_EVENT_TYPE_CACHE = 0x1, + SBI_PMU_EVENT_TYPE_RAW = 0x2, + SBI_PMU_EVENT_TYPE_RAW_V2 = 0x3, + SBI_PMU_EVENT_TYPE_FW = 0xf, +}; + /* SBI PMU counter types */ enum sbi_pmu_ctr_type { SBI_PMU_CTR_TYPE_HW = 0x0, diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h index 469a22122157..d8634a760a60 100644 --- a/tools/testing/selftests/kvm/include/x86/processor.h +++ b/tools/testing/selftests/kvm/include/x86/processor.h @@ -21,6 +21,8 @@ extern bool host_cpu_is_intel; extern bool host_cpu_is_amd; +extern bool host_cpu_is_hygon; +extern bool host_cpu_is_amd_compatible; extern uint64_t guest_tsc_khz; #ifndef MAX_NR_CPUID_ENTRIES @@ -717,6 +719,11 @@ static inline bool this_cpu_is_amd(void) return this_cpu_vendor_string_is("AuthenticAMD"); } +static inline bool this_cpu_is_hygon(void) +{ + return this_cpu_vendor_string_is("HygonGenuine"); +} + static inline uint32_t __this_cpu_has(uint32_t function, uint32_t index, uint8_t reg, uint8_t lo, uint8_t hi) { @@ -1383,6 +1390,11 @@ static inline bool kvm_is_ignore_msrs(void) return get_kvm_param_bool("ignore_msrs"); } +static inline bool kvm_is_lbrv_enabled(void) +{ + return !!get_kvm_amd_param_integer("lbrv"); +} + uint64_t *vm_get_pte(struct kvm_vm *vm, uint64_t vaddr); uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, diff --git a/tools/testing/selftests/kvm/include/x86/svm.h b/tools/testing/selftests/kvm/include/x86/svm.h index 10b30b38bb3f..c8539166270e 100644 --- a/tools/testing/selftests/kvm/include/x86/svm.h +++ b/tools/testing/selftests/kvm/include/x86/svm.h @@ -97,13 +97,13 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u64 exit_info_2; u32 exit_int_info; u32 exit_int_info_err; - u64 nested_ctl; + u64 misc_ctl; u64 avic_vapic_bar; u8 reserved_4[8]; u32 event_inj; u32 event_inj_err; u64 nested_cr3; - u64 virt_ext; + u64 misc_ctl2; u32 clean; u32 reserved_5; u64 next_rip; @@ -155,9 +155,6 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define AVIC_ENABLE_SHIFT 31 #define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT) -#define LBR_CTL_ENABLE_MASK BIT_ULL(0) -#define VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK BIT_ULL(1) - #define SVM_INTERRUPT_SHADOW_MASK 1 #define SVM_IOIO_STR_SHIFT 2 @@ -175,8 +172,11 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL #define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL -#define SVM_NESTED_CTL_NP_ENABLE BIT(0) -#define SVM_NESTED_CTL_SEV_ENABLE BIT(1) +#define SVM_MISC_ENABLE_NP BIT(0) +#define SVM_MISC_ENABLE_SEV BIT(1) + +#define SVM_MISC2_ENABLE_V_LBR BIT_ULL(0) +#define SVM_MISC2_ENABLE_V_VMLOAD_VMSAVE BIT_ULL(1) struct __attribute__ ((__packed__)) vmcb_seg { u16 selector; diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index dd8b12f626d3..c60a24a92829 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -261,9 +261,6 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) guest_page_size; else guest_test_phys_mem = p->phys_offset; -#ifdef __s390x__ - alignment = max(0x100000UL, alignment); -#endif guest_test_phys_mem = align_down(guest_test_phys_mem, alignment); /* Set up the shared data structure test_args */ diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 1959bf556e88..f5e076591c64 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -985,7 +985,7 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, struct userspace_mem_region *region; size_t backing_src_pagesz = get_backing_src_pagesz(src_type); size_t mem_size = npages * vm->page_size; - size_t alignment; + size_t alignment = 1; TEST_REQUIRE_SET_USER_MEMORY_REGION2(); @@ -1039,13 +1039,6 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, TEST_ASSERT(region != NULL, "Insufficient Memory"); region->mmap_size = mem_size; -#ifdef __s390x__ - /* On s390x, the host address must be aligned to 1M (due to PGSTEs) */ - alignment = 0x100000; -#else - alignment = 1; -#endif - /* * When using THP mmap is not guaranteed to returned a hugepage aligned * address so we have to pad the mmap. Padding is not needed for HugeTLB diff --git a/tools/testing/selftests/kvm/lib/loongarch/processor.c b/tools/testing/selftests/kvm/lib/loongarch/processor.c index 17aa55a2047a..ee4ad3b1d2a4 100644 --- a/tools/testing/selftests/kvm/lib/loongarch/processor.c +++ b/tools/testing/selftests/kvm/lib/loongarch/processor.c @@ -5,6 +5,7 @@ #include <asm/kvm.h> #include "kvm_util.h" +#include "pmu.h" #include "processor.h" #include "ucall_common.h" @@ -251,6 +252,14 @@ static void loongarch_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) __vcpu_set_reg(vcpu, id, val); } +static void loongarch_set_cpucfg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) +{ + uint64_t cfgid; + + cfgid = KVM_REG_LOONGARCH_CPUCFG | KVM_REG_SIZE_U64 | 8 * id; + __vcpu_set_reg(vcpu, cfgid, val); +} + static void loongarch_get_csr(struct kvm_vcpu *vcpu, uint64_t id, void *addr) { uint64_t csrid; @@ -267,9 +276,10 @@ static void loongarch_set_csr(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) __vcpu_set_reg(vcpu, csrid, val); } -static void loongarch_vcpu_setup(struct kvm_vcpu *vcpu) +void loongarch_vcpu_setup(struct kvm_vcpu *vcpu) { int width; + unsigned int cfg; unsigned long val; struct kvm_vm *vm = vcpu->vm; @@ -282,6 +292,9 @@ static void loongarch_vcpu_setup(struct kvm_vcpu *vcpu) TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode); } + cfg = read_cpucfg(LOONGARCH_CPUCFG6); + loongarch_set_cpucfg(vcpu, LOONGARCH_CPUCFG6, cfg); + /* kernel mode and page enable mode */ val = PLV_KERN | CSR_CRMD_PG; loongarch_set_csr(vcpu, LOONGARCH_CSR_CRMD, val); diff --git a/tools/testing/selftests/kvm/lib/memstress.c b/tools/testing/selftests/kvm/lib/memstress.c index 557c0a0a5658..1ea735d66e15 100644 --- a/tools/testing/selftests/kvm/lib/memstress.c +++ b/tools/testing/selftests/kvm/lib/memstress.c @@ -196,10 +196,6 @@ struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus, args->gpa = (region_end_gfn - guest_num_pages - 1) * args->guest_page_size; args->gpa = align_down(args->gpa, backing_src_pagesz); -#ifdef __s390x__ - /* Align to 1M (segment size) */ - args->gpa = align_down(args->gpa, 1 << 20); -#endif args->size = guest_num_pages * args->guest_page_size; pr_info("guest physical test memory: [0x%lx, 0x%lx)\n", args->gpa, args->gpa + args->size); diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c index 51dd455ff52c..067c6b2c15b0 100644 --- a/tools/testing/selftests/kvm/lib/riscv/processor.c +++ b/tools/testing/selftests/kvm/lib/riscv/processor.c @@ -566,3 +566,8 @@ unsigned long riscv64_get_satp_mode(void) return val; } + +bool kvm_arch_has_default_irqchip(void) +{ + return kvm_check_cap(KVM_CAP_IRQCHIP); +} diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c index 23a44941e283..01f0f97d4430 100644 --- a/tools/testing/selftests/kvm/lib/x86/processor.c +++ b/tools/testing/selftests/kvm/lib/x86/processor.c @@ -24,6 +24,8 @@ vm_vaddr_t exception_handlers; bool host_cpu_is_amd; bool host_cpu_is_intel; +bool host_cpu_is_hygon; +bool host_cpu_is_amd_compatible; bool is_forced_emulation_enabled; uint64_t guest_tsc_khz; @@ -793,6 +795,8 @@ void kvm_arch_vm_post_create(struct kvm_vm *vm, unsigned int nr_vcpus) sync_global_to_guest(vm, host_cpu_is_intel); sync_global_to_guest(vm, host_cpu_is_amd); + sync_global_to_guest(vm, host_cpu_is_hygon); + sync_global_to_guest(vm, host_cpu_is_amd_compatible); sync_global_to_guest(vm, is_forced_emulation_enabled); sync_global_to_guest(vm, pmu_errata_mask); @@ -1349,7 +1353,8 @@ const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, "1: vmmcall\n\t" \ "2:" \ : "=a"(r) \ - : [use_vmmcall] "r" (host_cpu_is_amd), inputs); \ + : [use_vmmcall] "r" (host_cpu_is_amd_compatible), \ + inputs); \ \ r; \ }) @@ -1389,8 +1394,8 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) max_gfn = (1ULL << (guest_maxphyaddr - vm->page_shift)) - 1; - /* Avoid reserved HyperTransport region on AMD processors. */ - if (!host_cpu_is_amd) + /* Avoid reserved HyperTransport region on AMD or Hygon processors. */ + if (!host_cpu_is_amd_compatible) return max_gfn; /* On parts with <40 physical address bits, the area is fully hidden */ @@ -1404,7 +1409,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) /* * Otherwise it's at the top of the physical address space, possibly - * reduced due to SME by bits 11:6 of CPUID[0x8000001f].EBX. Use + * reduced due to SME or CSV by bits 11:6 of CPUID[0x8000001f].EBX. Use * the old conservative value if MAXPHYADDR is not enumerated. */ if (!this_cpu_has_p(X86_PROPERTY_MAX_PHY_ADDR)) @@ -1425,6 +1430,8 @@ void kvm_selftest_arch_init(void) { host_cpu_is_intel = this_cpu_is_intel(); host_cpu_is_amd = this_cpu_is_amd(); + host_cpu_is_hygon = this_cpu_is_hygon(); + host_cpu_is_amd_compatible = host_cpu_is_amd || host_cpu_is_hygon; is_forced_emulation_enabled = kvm_is_forced_emulation_enabled(); kvm_init_pmu_errata(); diff --git a/tools/testing/selftests/kvm/lib/x86/svm.c b/tools/testing/selftests/kvm/lib/x86/svm.c index 2e5c480c9afd..eb20b00112c7 100644 --- a/tools/testing/selftests/kvm/lib/x86/svm.c +++ b/tools/testing/selftests/kvm/lib/x86/svm.c @@ -126,7 +126,7 @@ void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_r guest_regs.rdi = (u64)svm; if (svm->ncr3_gpa) { - ctrl->nested_ctl |= SVM_NESTED_CTL_NP_ENABLE; + ctrl->misc_ctl |= SVM_MISC_ENABLE_NP; ctrl->nested_cr3 = svm->ncr3_gpa; } } diff --git a/tools/testing/selftests/kvm/loongarch/pmu_test.c b/tools/testing/selftests/kvm/loongarch/pmu_test.c new file mode 100644 index 000000000000..88bb530e336e --- /dev/null +++ b/tools/testing/selftests/kvm/loongarch/pmu_test.c @@ -0,0 +1,205 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * LoongArch KVM PMU event counting test + * + * Test hardware event counting: CPU_CYCLES, INSTR_RETIRED, + * BRANCH_INSTRUCTIONS and BRANCH_MISSES. + */ +#include <linux/bitops.h> +#include "kvm_util.h" +#include "pmu.h" +#include "loongarch/processor.h" + +static int pmu_irq_count; + +/* Check PMU support */ +static bool has_pmu_support(void) +{ + uint32_t cfg6; + + /* Read CPUCFG6 to check PMU */ + cfg6 = read_cpucfg(LOONGARCH_CPUCFG6); + + /* Check PMU present bit */ + if (!(cfg6 & CPUCFG6_PMP)) + return false; + + /* Check that at least one counter exists */ + if (((cfg6 & CPUCFG6_PMNUM) >> CPUCFG6_PMNUM_SHIFT) == 0) + return false; + + return true; +} + +/* Dump PMU capabilities */ +static void dump_pmu_caps(void) +{ + uint32_t cfg6; + int nr_counters, counter_bits; + + cfg6 = read_cpucfg(LOONGARCH_CPUCFG6); + nr_counters = ((cfg6 & CPUCFG6_PMNUM) >> CPUCFG6_PMNUM_SHIFT) + 1; + counter_bits = ((cfg6 & CPUCFG6_PMBITS) >> CPUCFG6_PMBITS_SHIFT) + 1; + + pr_info("PMU capabilities:\n"); + pr_info(" Counters present: %s\n", cfg6 & CPUCFG6_PMP ? "yes" : "no"); + pr_info(" Number of counters: %d\n", nr_counters); + pr_info(" Counter width: %d bits\n", counter_bits); +} + +/* Guest test code - runs inside VM */ +static void guest_pmu_base_test(void) +{ + int i; + uint32_t cfg6, pmnum; + uint64_t cnt[4]; + + cfg6 = read_cpucfg(LOONGARCH_CPUCFG6); + pmnum = (cfg6 >> 4) & 0xf; + GUEST_PRINTF("CPUCFG6 = 0x%x\n", cfg6); + GUEST_PRINTF("PMP enabled: %s\n", (cfg6 & 0x1) ? "YES" : "NO"); + GUEST_PRINTF("Number of counters (PMNUM): %x\n", pmnum + 1); + GUEST_ASSERT(pmnum == 3); + + GUEST_PRINTF("Clean csr_perfcntr0-3\n"); + csr_write(0, LOONGARCH_CSR_PERFCNTR0); + csr_write(0, LOONGARCH_CSR_PERFCNTR1); + csr_write(0, LOONGARCH_CSR_PERFCNTR2); + csr_write(0, LOONGARCH_CSR_PERFCNTR3); + GUEST_PRINTF("Set csr_perfctrl0 for cycles event\n"); + csr_write(PMU_ENVENT_ENABLED | + LOONGARCH_PMU_EVENT_CYCLES, LOONGARCH_CSR_PERFCTRL0); + GUEST_PRINTF("Set csr_perfctrl1 for instr_retired event\n"); + csr_write(PMU_ENVENT_ENABLED | + LOONGARCH_PMU_EVENT_INSTR_RETIRED, LOONGARCH_CSR_PERFCTRL1); + GUEST_PRINTF("Set csr_perfctrl2 for branch_instructions event\n"); + csr_write(PMU_ENVENT_ENABLED | + PERF_COUNT_HW_BRANCH_INSTRUCTIONS, LOONGARCH_CSR_PERFCTRL2); + GUEST_PRINTF("Set csr_perfctrl3 for branch_misses event\n"); + csr_write(PMU_ENVENT_ENABLED | + PERF_COUNT_HW_BRANCH_MISSES, LOONGARCH_CSR_PERFCTRL3); + + for (i = 0; i < NUM_LOOPS; i++) + cpu_relax(); + + cnt[0] = csr_read(LOONGARCH_CSR_PERFCNTR0); + GUEST_PRINTF("csr_perfcntr0 is %lx\n", cnt[0]); + cnt[1] = csr_read(LOONGARCH_CSR_PERFCNTR1); + GUEST_PRINTF("csr_perfcntr1 is %lx\n", cnt[1]); + cnt[2] = csr_read(LOONGARCH_CSR_PERFCNTR2); + GUEST_PRINTF("csr_perfcntr2 is %lx\n", cnt[2]); + cnt[3] = csr_read(LOONGARCH_CSR_PERFCNTR3); + GUEST_PRINTF("csr_perfcntr3 is %lx\n", cnt[3]); + + GUEST_PRINTF("assert csr_perfcntr0 >EXPECTED_CYCLES_MIN && csr_perfcntr0 < UPPER_BOUND\n"); + GUEST_ASSERT(cnt[0] > EXPECTED_CYCLES_MIN && cnt[0] < UPPER_BOUND); + GUEST_PRINTF("assert csr_perfcntr1 > EXPECTED_INSTR_MIN && csr_perfcntr1 < UPPER_BOUND\n"); + GUEST_ASSERT(cnt[1] > EXPECTED_INSTR_MIN && cnt[1] < UPPER_BOUND); + GUEST_PRINTF("assert csr_perfcntr2 > 0 && csr_perfcntr2 < UPPER_BOUND\n"); + GUEST_ASSERT(cnt[2] > 0 && cnt[2] < UPPER_BOUND); + GUEST_PRINTF("assert csr_perfcntr3 > 0 && csr_perfcntr3 < UPPER_BOUND\n"); + GUEST_ASSERT(cnt[3] > 0 && cnt[3] < UPPER_BOUND); +} + +static void guest_irq_handler(struct ex_regs *regs) +{ + unsigned int intid; + + pmu_irq_disable(); + intid = !!(regs->estat & BIT(INT_PMI)); + GUEST_ASSERT_EQ(intid, 1); + GUEST_PRINTF("Get PMU interrupt\n"); + WRITE_ONCE(pmu_irq_count, pmu_irq_count + 1); +} + +static void guest_pmu_interrupt_test(void) +{ + uint64_t cnt; + + csr_write(PMU_OVERFLOW - 1, LOONGARCH_CSR_PERFCNTR0); + csr_write(PMU_ENVENT_ENABLED | CSR_PERFCTRL_PMIE | LOONGARCH_PMU_EVENT_CYCLES, LOONGARCH_CSR_PERFCTRL0); + + cpu_relax(); + + GUEST_ASSERT_EQ(pmu_irq_count, 1); + cnt = csr_read(LOONGARCH_CSR_PERFCNTR0); + GUEST_PRINTF("csr_perfcntr0 is %lx\n", cnt); + GUEST_PRINTF("PMU interrupt test success\n"); + +} + +static void guest_code(void) +{ + guest_pmu_base_test(); + + pmu_irq_enable(); + local_irq_enable(); + guest_pmu_interrupt_test(); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + int ret = 0; + struct kvm_device_attr attr; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct ucall uc; + + /* Check host KVM PMU support */ + if (!has_pmu_support()) { + print_skip("PMU not supported by host hardware\n"); + dump_pmu_caps(); + return KSFT_SKIP; + } + pr_info("Host support PMU\n"); + + /* Dump PMU capabilities */ + dump_pmu_caps(); + + vm = vm_create(VM_MODE_P47V47_16K); + vcpu = vm_vcpu_add(vm, 0, guest_code); + + pmu_irq_count = 0; + vm_init_descriptor_tables(vm); + loongarch_vcpu_setup(vcpu); + vm_install_exception_handler(vm, EXCCODE_INT, guest_irq_handler); + sync_global_to_guest(vm, pmu_irq_count); + + attr.group = KVM_LOONGARCH_VM_FEAT_CTRL, + attr.attr = KVM_LOONGARCH_VM_FEAT_PMU, + + ret = ioctl(vm->fd, KVM_HAS_DEVICE_ATTR, &attr); + + if (ret == 0) { + pr_info("PMU is enabled in VM\n"); + } else { + print_skip("PMU not enabled by VM config\n"); + return KSFT_SKIP; + } + + while (1) { + vcpu_run(vcpu); + switch (get_ucall(vcpu, &uc)) { + case UCALL_PRINTF: + printf("%s", (const char *)uc.buffer); + break; + case UCALL_DONE: + printf("PMU test PASSED\n"); + goto done; + case UCALL_ABORT: + printf("PMU test FAILED\n"); + ret = -1; + goto done; + default: + printf("Unexpected exit\n"); + ret = -1; + goto done; + } + } + +done: + kvm_vm_free(vm); + return ret; +} diff --git a/tools/testing/selftests/kvm/pre_fault_memory_test.c b/tools/testing/selftests/kvm/pre_fault_memory_test.c index 93e603d91311..f3de0386ba7b 100644 --- a/tools/testing/selftests/kvm/pre_fault_memory_test.c +++ b/tools/testing/selftests/kvm/pre_fault_memory_test.c @@ -175,11 +175,7 @@ static void __test_pre_fault_memory(unsigned long vm_type, bool private) alignment = guest_page_size = vm_guest_mode_params[VM_MODE_DEFAULT].page_size; gpa = (vm->max_gfn - TEST_NPAGES) * guest_page_size; -#ifdef __s390x__ - alignment = max(0x100000UL, guest_page_size); -#else alignment = SZ_2M; -#endif gpa = align_down(gpa, alignment); gva = gpa & ((1ULL << (vm->va_bits - 1)) - 1); diff --git a/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c index 924a335d2262..cec1621ace23 100644 --- a/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c +++ b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c @@ -436,6 +436,7 @@ static void test_pmu_basic_sanity(void) struct sbiret ret; int num_counters = 0, i; union sbi_pmu_ctr_info ctrinfo; + unsigned long fw_eidx; probe = guest_sbi_probe_extension(SBI_EXT_PMU, &out_val); GUEST_ASSERT(probe && out_val == 1); @@ -461,7 +462,24 @@ static void test_pmu_basic_sanity(void) pmu_csr_read_num(ctrinfo.csr); GUEST_ASSERT(illegal_handler_invoked); } else if (ctrinfo.type == SBI_PMU_CTR_TYPE_FW) { - read_fw_counter(i, ctrinfo); + /* Read without configure should fail */ + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_FW_READ, + i, 0, 0, 0, 0, 0); + GUEST_ASSERT(ret.error == SBI_ERR_INVALID_PARAM); + + /* + * Try to configure with a common firmware event. + * If configuration succeeds, verify we can read it. + */ + fw_eidx = ((unsigned long)SBI_PMU_EVENT_TYPE_FW << 16) | + SBI_PMU_FW_ACCESS_LOAD; + + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, + i, 1, 0, fw_eidx, 0, 0); + if (ret.error == 0) { + GUEST_ASSERT(ret.value == i); + read_fw_counter(i, ctrinfo); + } } } diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index 7fe427ff9b38..a398dc3a8c4b 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -413,14 +413,7 @@ static void test_add_max_memory_regions(void) uint32_t max_mem_slots; uint32_t slot; void *mem, *mem_aligned, *mem_extra; - size_t alignment; - -#ifdef __s390x__ - /* On s390x, the host address must be aligned to 1M (due to PGSTEs) */ - alignment = 0x100000; -#else - alignment = 1; -#endif + size_t alignment = 1; max_mem_slots = kvm_check_cap(KVM_CAP_NR_MEMSLOTS); TEST_ASSERT(max_mem_slots > 0, diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index 7be8adfe5dd3..efe56a10d13e 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -69,16 +69,10 @@ static bool is_steal_time_supported(struct kvm_vcpu *vcpu) static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i) { - int ret; - /* ST_GPA_BASE is identity mapped */ st_gva[i] = (void *)(ST_GPA_BASE + i * STEAL_TIME_SIZE); sync_global_to_guest(vcpu->vm, st_gva[i]); - ret = _vcpu_set_msr(vcpu, MSR_KVM_STEAL_TIME, - (ulong)st_gva[i] | KVM_STEAL_RESERVED_MASK); - TEST_ASSERT(ret == 0, "Bad GPA didn't fail"); - vcpu_set_msr(vcpu, MSR_KVM_STEAL_TIME, (ulong)st_gva[i] | KVM_MSR_ENABLED); } @@ -99,6 +93,21 @@ static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx) st->pad[8], st->pad[9], st->pad[10]); } +static void check_steal_time_uapi(void) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + int ret; + + vm = vm_create_with_one_vcpu(&vcpu, NULL); + + ret = _vcpu_set_msr(vcpu, MSR_KVM_STEAL_TIME, + (ulong)ST_GPA_BASE | KVM_STEAL_RESERVED_MASK); + TEST_ASSERT(ret == 0, "Bad GPA didn't fail"); + + kvm_vm_free(vm); +} + #elif defined(__aarch64__) /* PV_TIME_ST must have 64-byte alignment */ @@ -170,7 +179,6 @@ static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i) { struct kvm_vm *vm = vcpu->vm; uint64_t st_ipa; - int ret; struct kvm_device_attr dev = { .group = KVM_ARM_VCPU_PVTIME_CTRL, @@ -178,21 +186,12 @@ static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i) .addr = (uint64_t)&st_ipa, }; - vcpu_ioctl(vcpu, KVM_HAS_DEVICE_ATTR, &dev); - /* ST_GPA_BASE is identity mapped */ st_gva[i] = (void *)(ST_GPA_BASE + i * STEAL_TIME_SIZE); sync_global_to_guest(vm, st_gva[i]); - st_ipa = (ulong)st_gva[i] | 1; - ret = __vcpu_ioctl(vcpu, KVM_SET_DEVICE_ATTR, &dev); - TEST_ASSERT(ret == -1 && errno == EINVAL, "Bad IPA didn't report EINVAL"); - st_ipa = (ulong)st_gva[i]; vcpu_ioctl(vcpu, KVM_SET_DEVICE_ATTR, &dev); - - ret = __vcpu_ioctl(vcpu, KVM_SET_DEVICE_ATTR, &dev); - TEST_ASSERT(ret == -1 && errno == EEXIST, "Set IPA twice without EEXIST"); } static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx) @@ -205,6 +204,36 @@ static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx) ksft_print_msg(" st_time: %ld\n", st->st_time); } +static void check_steal_time_uapi(void) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + uint64_t st_ipa; + int ret; + + vm = vm_create_with_one_vcpu(&vcpu, NULL); + + struct kvm_device_attr dev = { + .group = KVM_ARM_VCPU_PVTIME_CTRL, + .attr = KVM_ARM_VCPU_PVTIME_IPA, + .addr = (uint64_t)&st_ipa, + }; + + vcpu_ioctl(vcpu, KVM_HAS_DEVICE_ATTR, &dev); + + st_ipa = (ulong)ST_GPA_BASE | 1; + ret = __vcpu_ioctl(vcpu, KVM_SET_DEVICE_ATTR, &dev); + TEST_ASSERT(ret == -1 && errno == EINVAL, "Bad IPA didn't report EINVAL"); + + st_ipa = (ulong)ST_GPA_BASE; + vcpu_ioctl(vcpu, KVM_SET_DEVICE_ATTR, &dev); + + ret = __vcpu_ioctl(vcpu, KVM_SET_DEVICE_ATTR, &dev); + TEST_ASSERT(ret == -1 && errno == EEXIST, "Set IPA twice without EEXIST"); + + kvm_vm_free(vm); +} + #elif defined(__riscv) /* SBI STA shmem must have 64-byte alignment */ @@ -301,6 +330,41 @@ static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx) pr_info("\n"); } +static void check_steal_time_uapi(void) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + struct kvm_one_reg reg; + uint64_t shmem; + int ret; + + vm = vm_create_with_one_vcpu(&vcpu, NULL); + + reg.id = KVM_REG_RISCV | + KVM_REG_SIZE_ULONG | + KVM_REG_RISCV_SBI_STATE | + KVM_REG_RISCV_SBI_STA | + KVM_REG_RISCV_SBI_STA_REG(shmem_lo); + reg.addr = (uint64_t)&shmem; + + shmem = ST_GPA_BASE + 1; + ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "misaligned STA shmem returns -EINVAL"); + + shmem = ST_GPA_BASE; + ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); + TEST_ASSERT(ret == 0, + "aligned STA shmem succeeds"); + + shmem = INVALID_GPA; + ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); + TEST_ASSERT(ret == 0, + "all-ones for STA shmem succeeds"); + + kvm_vm_free(vm); +} + #elif defined(__loongarch__) /* steal_time must have 64-byte alignment */ @@ -465,6 +529,8 @@ int main(int ac, char **av) TEST_REQUIRE(is_steal_time_supported(vcpus[0])); ksft_set_plan(NR_VCPUS); + check_steal_time_uapi(); + /* Run test on each VCPU */ for (i = 0; i < NR_VCPUS; ++i) { steal_time_init(vcpus[i], i); diff --git a/tools/testing/selftests/kvm/x86/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86/fix_hypercall_test.c index 762628f7d4ba..00b6e85735dd 100644 --- a/tools/testing/selftests/kvm/x86/fix_hypercall_test.c +++ b/tools/testing/selftests/kvm/x86/fix_hypercall_test.c @@ -52,7 +52,7 @@ static void guest_main(void) 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 { diff --git a/tools/testing/selftests/kvm/x86/msrs_test.c b/tools/testing/selftests/kvm/x86/msrs_test.c index 40d918aedce6..f7e39bf887ad 100644 --- a/tools/testing/selftests/kvm/x86/msrs_test.c +++ b/tools/testing/selftests/kvm/x86/msrs_test.c @@ -81,7 +81,7 @@ static u64 fixup_rdmsr_val(u32 msr, u64 want) * 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) + if (!host_cpu_is_amd_compatible) return want; switch (msr) { @@ -175,7 +175,7 @@ void guest_test_reserved_val(const struct kvm_msr *msr) * 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) || + 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); diff --git a/tools/testing/selftests/kvm/x86/nested_vmsave_vmload_test.c b/tools/testing/selftests/kvm/x86/nested_vmsave_vmload_test.c index 6764a48f9d4d..71717118d692 100644 --- a/tools/testing/selftests/kvm/x86/nested_vmsave_vmload_test.c +++ b/tools/testing/selftests/kvm/x86/nested_vmsave_vmload_test.c @@ -79,8 +79,8 @@ static void l1_guest_code(struct svm_test_data *svm) svm->vmcb->control.intercept |= (BIT_ULL(INTERCEPT_VMSAVE) | BIT_ULL(INTERCEPT_VMLOAD)); - /* ..VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK cleared.. */ - svm->vmcb->control.virt_ext &= ~VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; + /* ..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); @@ -90,8 +90,8 @@ static void l1_guest_code(struct svm_test_data *svm) run_guest(svm->vmcb, svm->vmcb_gpa); GUEST_ASSERT_EQ(svm->vmcb->control.exit_code, SVM_EXIT_VMLOAD); - /* ..and VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK set */ - svm->vmcb->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; + /* ..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); @@ -106,20 +106,20 @@ static void l1_guest_code(struct svm_test_data *svm) BIT_ULL(INTERCEPT_VMLOAD)); /* - * Without VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK, the GPA will be + * 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.virt_ext &= ~VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; + 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 VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK, the GPA will be interpeted as + * 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.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; + 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); 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 1c5b7611db24..93b61c077991 100644 --- a/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c @@ -361,7 +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; } /* 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/state_test.c b/tools/testing/selftests/kvm/x86/state_test.c index f2c7a1c297e3..992a52504a4a 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); @@ -222,6 +226,35 @@ 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; @@ -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); 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..ff99438824d3 --- /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; + vm_vaddr_t svm_gva; + struct kvm_vm *vm; + struct ucall uc; + + 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..a521a9eed061 --- /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; + vm_vaddr_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_vmcb12_gpa.c b/tools/testing/selftests/kvm/x86/svm_nested_vmcb12_gpa.c new file mode 100644 index 000000000000..569869bed20b --- /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, u64 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, u64 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, u64 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, u64 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) +{ + vm_vaddr_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) +{ + vm_vaddr_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; + vm_vaddr_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/xapic_state_test.c b/tools/testing/selftests/kvm/x86/xapic_state_test.c index 3b4814c55722..0c5e12f5f14e 100644 --- a/tools/testing/selftests/kvm/x86/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86/xapic_state_test.c @@ -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); |