On Sat, 21 Jan 2023 02:07:38 +0000
Kechen Lu <kechenl@xxxxxxxxxx> wrote:
It works on my box now. LGTM. I was curious if there is any other userspace
application using this? It would be interesting to see their strategies.
> Add selftests for KVM cap KVM_CAP_X86_DISABLE_EXITS overriding flags
> in VM and vCPU scope both working as expected.
>
> Suggested-by: Chao Gao <chao.gao@xxxxxxxxx>
> Suggested-by: Shaoqin Huang <shaoqin.huang@xxxxxxxxx>
> Suggested-by: Zhi Wang <zhi.wang.linux@xxxxxxxxx>
> Signed-off-by: Kechen Lu <kechenl@xxxxxxxxxx>
> ---
> tools/testing/selftests/kvm/Makefile | 1 +
> .../selftests/kvm/x86_64/disable_exits_test.c | 363 ++++++++++++++++++
> 2 files changed, 364 insertions(+)
> create mode 100644 tools/testing/selftests/kvm/x86_64/disable_exits_test.c
>
> diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
> index 1750f91dd936..eeeba35e2536 100644
> --- a/tools/testing/selftests/kvm/Makefile
> +++ b/tools/testing/selftests/kvm/Makefile
> @@ -114,6 +114,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests
> TEST_GEN_PROGS_x86_64 += x86_64/amx_test
> TEST_GEN_PROGS_x86_64 += x86_64/max_vcpuid_cap_test
> TEST_GEN_PROGS_x86_64 += x86_64/triple_fault_event_test
> +TEST_GEN_PROGS_x86_64 += x86_64/disable_exits_test
> TEST_GEN_PROGS_x86_64 += access_tracking_perf_test
> TEST_GEN_PROGS_x86_64 += demand_paging_test
> TEST_GEN_PROGS_x86_64 += dirty_log_test
> diff --git a/tools/testing/selftests/kvm/x86_64/disable_exits_test.c b/tools/testing/selftests/kvm/x86_64/disable_exits_test.c
> new file mode 100644
> index 000000000000..74a2152b35dd
> --- /dev/null
> +++ b/tools/testing/selftests/kvm/x86_64/disable_exits_test.c
> @@ -0,0 +1,363 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/*
> + * Test per-VM and per-vCPU disable exits cap
> + * 1) Per-VM scope
> + * 2) Per-vCPU scope
> + *
> + */
> +
> +#define _GNU_SOURCE /* for program_invocation_short_name */
> +#include <pthread.h>
> +#include <inttypes.h>
> +#include <string.h>
> +#include <time.h>
> +#include <sys/ioctl.h>
> +
> +#include "test_util.h"
> +#include "kvm_util.h"
> +#include "svm_util.h"
> +#include "vmx.h"
> +#include "processor.h"
> +#include "asm/kvm.h"
> +#include "linux/kvm.h"
> +
> +/* Arbitrary chosen IPI vector value from sender to halter vCPU */
> +#define IPI_VECTOR 0xa5
> +/* Number of HLTs halter vCPU thread executes */
> +#define LOOP_DURATION 3
> +
> +struct guest_stats {
> + uint32_t halter_apic_id;
> + volatile uint64_t hlt_count;
> + volatile uint64_t wake_count;
> +};
> +
> +static u64 read_vcpu_stats_halt_exits(struct kvm_vcpu *vcpu)
> +{
> + int i;
> + struct kvm_stats_header header;
> + u64 *stats_data;
> + u64 ret = 0;
> + struct kvm_stats_desc *stats_desc;
> + struct kvm_stats_desc *pdesc;
> + int stats_fd = vcpu_get_stats_fd(vcpu);
> +
> + read_stats_header(stats_fd, &header);
> + if (header.num_desc == 0) {
> + fprintf(stderr,
> + "Cannot read halt exits since no KVM stats defined\n");
> + return ret;
> + }
> +
> + stats_desc = read_stats_descriptors(stats_fd, &header);
> + for (i = 0; i < header.num_desc; ++i) {
> + pdesc = get_stats_descriptor(stats_desc, i, &header);
> + if (!strncmp(pdesc->name, "halt_exits", 10)) {
> + stats_data = malloc(pdesc->size * sizeof(*stats_data));
> + read_stat_data(stats_fd, &header, pdesc, stats_data,
> + pdesc->size);
> + ret = *stats_data;
> + free(stats_data);
> + break;
> + }
> + }
> + free(stats_desc);
> + return ret;
> +}
> +
> +/* HLT multiple times in one vCPU */
> +static void halter_guest_code(struct guest_stats *data)
> +{
> + xapic_enable();
> + data->halter_apic_id = GET_APIC_ID_FIELD(xapic_read_reg(APIC_ID));
> +
> + for (;;) {
> + data->hlt_count++;
> + asm volatile("sti; hlt; cli");
> + data->wake_count++;
> + }
> +}
> +
> +/* Runs on halter vCPU when IPI arrives */
> +static void guest_ipi_handler(struct ex_regs *regs)
> +{
> + xapic_write_reg(APIC_EOI, 11);
> +}
> +
> +/* Sender vCPU waits for ~1sec to assume HLT executed */
> +static void sender_wait_loop(struct guest_stats *data, uint64_t old_hlt_count,
> + uint64_t old_wake_count)
> +{
> + uint64_t tsc_start = rdtsc();
> +
> + while (rdtsc() - tsc_start < 4000000000) {
> + if ((data->wake_count != old_wake_count) &&
> + (data->hlt_count != old_hlt_count))
> + break;
> + }
> + GUEST_ASSERT((data->wake_count != old_wake_count) &&
> + (data->hlt_count != old_hlt_count));
> +}
> +
> +/* Sender vCPU loops sending IPI to halter vCPU every ~1sec */
> +static void sender_guest_code(struct guest_stats *data)
> +{
> + uint32_t icr_val;
> + uint32_t icr2_val;
> + uint64_t old_hlt_count = 0;
> + uint64_t old_wake_count = 0;
> +
> + xapic_enable();
> + /* Init interrupt command register for sending IPIs */
> + icr_val = (APIC_DEST_PHYSICAL | APIC_DM_FIXED | IPI_VECTOR);
> + icr2_val = SET_APIC_DEST_FIELD(data->halter_apic_id);
> +
> + for (;;) {
> + /*
> + * Send IPI to halted vCPU
> + * First IPI sends here as already waited before sender vCPU
> + * thread creation
> + */
> + xapic_write_reg(APIC_ICR2, icr2_val);
> + xapic_write_reg(APIC_ICR, icr_val);
> + sender_wait_loop(data, old_hlt_count, old_wake_count);
> + old_wake_count = data->wake_count;
> + old_hlt_count = data->hlt_count;
> + }
> +}
> +
> +static void *vcpu_thread(void *arg)
> +{
> + struct kvm_vcpu *vcpu = (struct kvm_vcpu *)arg;
> + int old;
> + int r;
> +
> + r = pthread_setcanceltype(PTHREAD_CANCEL_ASYNCHRONOUS, &old);
> + TEST_ASSERT(r == 0,
> + "pthread_setcanceltype failed on vcpu_id=%u with errno=%d",
> + vcpu->id, r);
> + fprintf(stderr, "vCPU thread running vCPU %u\n", vcpu->id);
> + vcpu_run(vcpu);
> + return NULL;
> +}
> +
> +static void cancel_join_vcpu_thread(pthread_t thread, struct kvm_vcpu *vcpu)
> +{
> + void *retval;
> + int r;
> +
> + r = pthread_cancel(thread);
> + TEST_ASSERT(r == 0,
> + "pthread_cancel on vcpu_id=%d failed with errno=%d",
> + vcpu->id, r);
> +
> + r = pthread_join(thread, &retval);
> + TEST_ASSERT(r == 0,
> + "pthread_join on vcpu_id=%d failed with errno=%d",
> + vcpu->id, r);
> +}
> +
> +static void vm_run_with_threads(struct kvm_vcpu *halter_vcpu,
> + struct kvm_vcpu *sender_vcpu)
> +{
> + int r;
> + pthread_t threads[2];
> +
> + /* Start halter vCPU thread and wait for it to execute first HLT. */
> + r = pthread_create(&threads[0], NULL, vcpu_thread, halter_vcpu);
> + TEST_ASSERT(r == 0,
> + "pthread_create halter failed errno=%d", errno);
> + fprintf(stderr, "Halter vCPU thread started\n");
> +
> + sleep(1);
> +
> + /*
> + * After guest halter vCPU executed first HLT, start the sender
> + * vCPU thread to wakeup halter vCPU
> + */
> + r = pthread_create(&threads[1], NULL, vcpu_thread, sender_vcpu);
> + TEST_ASSERT(r == 0, "pthread_create sender failed errno=%d", errno);
> +
> + sleep(LOOP_DURATION);
> +
> + cancel_join_vcpu_thread(threads[0], halter_vcpu);
> + cancel_join_vcpu_thread(threads[1], sender_vcpu);
> +}
> +
> +/*
> + * Test case 1:
> + * Normal VM running with one vCPU keeps executing HLTs,
> + * another vCPU sending IPIs to wake it up, should expect
> + * all HLTs exiting to host
> + * and Test case 2:
> + * VM scoped exits disabling, HLT instructions
> + * stay inside guest without exits
> + */
> +static void test_vm_disable_exits_cap(bool cap_enabled)
> +{
> + uint64_t kvm_halt_exits;
> + struct kvm_vm *vm;
> + struct kvm_vcpu *halter_vcpu;
> + struct kvm_vcpu *sender_vcpu;
> + struct guest_stats *data;
> + vm_vaddr_t guest_stats_page_vaddr;
> +
> + /* Create VM */
> + vm = vm_create(2);
> +
> + /*
> + * Before adding any vCPUs, enable the KVM_X86_DISABLE_EXITS cap
> + * with flag KVM_X86_DISABLE_EXITS_HLT
> + */
> + if (cap_enabled)
> + vm_enable_cap(vm, KVM_CAP_X86_DISABLE_EXITS,
> + KVM_X86_DISABLE_EXITS_HLT);
> +
> + /* Add vCPU with loops halting */
> + halter_vcpu = vm_vcpu_add(vm, 0, halter_guest_code);
> +
> + vm_init_descriptor_tables(vm);
> + vcpu_init_descriptor_tables(halter_vcpu);
> + vm_install_exception_handler(vm, IPI_VECTOR, guest_ipi_handler);
> + virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA);
> +
> + /* Add vCPU with IPIs waking up halter vCPU */
> + sender_vcpu = vm_vcpu_add(vm, 1, sender_guest_code);
> +
> + guest_stats_page_vaddr = vm_vaddr_alloc_page(vm);
> + data = addr_gva2hva(vm, guest_stats_page_vaddr);
> + memset(data, 0, sizeof(*data));
> +
> + vcpu_args_set(halter_vcpu, 1, guest_stats_page_vaddr);
> + vcpu_args_set(sender_vcpu, 1, guest_stats_page_vaddr);
> +
> + vm_run_with_threads(halter_vcpu, sender_vcpu);
> + kvm_halt_exits = read_vcpu_stats_halt_exits(halter_vcpu);
> + if (cap_enabled)
> + TEST_ASSERT(kvm_halt_exits == 0,
> + "Halter vCPU had unexpected halt exits occurring after disabling VM-scoped halt exits cap\n");
> + else
> + TEST_ASSERT(kvm_halt_exits == data->hlt_count,
> + "Halter vCPU had unmatched %lu halt exits - %lu HLTs executed, when not disabling VM halt exits\n",
> + kvm_halt_exits, data->hlt_count);
> + fprintf(stderr, "Halter vCPU had %lu halt exits\n",
> + kvm_halt_exits);
> + fprintf(stderr, "Guest records %lu HLTs executed, waked %lu times\n",
> + data->hlt_count, data->wake_count);
> +
> + kvm_vm_free(vm);
> +}
> +
> +/*
> + * Test case 3:
> + * VM overrides exits disable flags after vCPU created,
> + * which is not allowed
> + */
> +static void test_vm_disable_exits_cap_with_vcpu_created(void)
> +{
> + int r;
> + struct kvm_vm *vm;
> + struct kvm_enable_cap cap = {
> + .cap = KVM_CAP_X86_DISABLE_EXITS,
> + .args[0] = KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_OVERRIDE,
> + };
> +
> + /* Create VM */
> + vm = vm_create(1);
> + /* Add vCPU with loops halting */
> + vm_vcpu_add(vm, 0, halter_guest_code);
> +
> + /*
> + * After creating vCPU, the current VM-scoped ABI should
> + * discard the cap enable of KVM_CAP_X86_DISABLE_EXITS
> + * and return non-zero. Since vm_enabled_cap() not able
> + * to assert the return value, so use the __vm_ioctl()
> + */
> + r = __vm_ioctl(vm, KVM_ENABLE_CAP, &cap);
> +
> + TEST_ASSERT(r != 0,
> + "Setting VM-scoped KVM_CAP_X86_DISABLE_EXITS after vCPUs created is not allowed, but it succeeds here\n");
> +}
> +
> +/*
> + * Test case 4:
> + * vCPU scoped halt exits disabling and enabling tests,
> + * verify overides are working after vCPU created
> + */
> +static void test_vcpu_toggling_disable_exits_cap(void)
> +{
> + uint64_t kvm_halt_exits;
> + uint64_t kvm_halt_exits_in_guest;
> + struct kvm_vm *vm;
> + struct kvm_vcpu *halter_vcpu;
> + struct kvm_vcpu *sender_vcpu;
> + struct guest_stats *data;
> + vm_vaddr_t guest_stats_page_vaddr;
> +
> + /* Create VM */
> + vm = vm_create(2);
> +
> + /* Add vCPU with loops halting */
> + halter_vcpu = vm_vcpu_add(vm, 0, halter_guest_code);
> + /* Set KVM_CAP_X86_DISABLE_EXITS_HLT for halter vCPU */
> + vcpu_enable_cap(halter_vcpu, KVM_CAP_X86_DISABLE_EXITS,
> + KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_OVERRIDE);
> +
> + vm_init_descriptor_tables(vm);
> + vcpu_init_descriptor_tables(halter_vcpu);
> + vm_install_exception_handler(vm, IPI_VECTOR, guest_ipi_handler);
> + virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA);
> +
> + /* Add vCPU with IPIs waking up halter vCPU */
> + sender_vcpu = vm_vcpu_add(vm, 1, sender_guest_code);
> +
> + guest_stats_page_vaddr = vm_vaddr_alloc_page(vm);
> + data = addr_gva2hva(vm, guest_stats_page_vaddr);
> + memset(data, 0, sizeof(*data));
> +
> + vcpu_args_set(halter_vcpu, 1, guest_stats_page_vaddr);
> + vcpu_args_set(sender_vcpu, 1, guest_stats_page_vaddr);
> +
> + /*
> + * For the first phase of the running, halt exits
> + * are disabled, halter vCPU executes HLT instruction
> + * but never exits to host
> + */
> + vm_run_with_threads(halter_vcpu, sender_vcpu);
> + kvm_halt_exits_in_guest = data->hlt_count;
> + fprintf(stderr, "Guest records %lu HLTs with halt exits disabled\n",
> + data->hlt_count);
> + /*
> + * Override and clean KVM_CAP_X86_DISABLE_EXITS flags
> + * for halter vCPU. Expect to see halt exits occurs then.
> + */
> + vcpu_enable_cap(halter_vcpu, KVM_CAP_X86_DISABLE_EXITS,
> + KVM_X86_DISABLE_EXITS_OVERRIDE);
> + /*
> + * Second phase of the test, after guest halter vCPU
> + * reenabled halt exits, start the sender
> + * vCPU thread to wakeup halter vCPU
> + */
> + vm_run_with_threads(halter_vcpu, sender_vcpu);
> + kvm_halt_exits = read_vcpu_stats_halt_exits(halter_vcpu);
> + TEST_ASSERT(kvm_halt_exits == data->hlt_count - kvm_halt_exits_in_guest,
> + "Halter vCPU had unexpected %lu (should be %lu) halt exits\n",
> + kvm_halt_exits, data->hlt_count - kvm_halt_exits_in_guest);
> + fprintf(stderr, "Halter vCPU had %lu halt exits\n",
> + kvm_halt_exits);
> + fprintf(stderr, "Guest records %lu HLTs executed, waked %lu times\n",
> + data->hlt_count, data->wake_count);
> +
> + kvm_vm_free(vm);
> +}
> +
> +int main(int argc, char *argv[])
> +{
> + fprintf(stderr, "VM-scoped tests start\n");
> + test_vm_disable_exits_cap(false);
> + test_vm_disable_exits_cap(true);
> + test_vm_disable_exits_cap_with_vcpu_created();
> + fprintf(stderr, "vCPU-scoped test starts\n");
> + test_vcpu_toggling_disable_exits_cap();
> + return 0;
> +}
