selftest: kvm: Add amx selftest

This selftest covers two aspects of AMX.  The first is triggering #NM
exception and checking the MSR XFD_ERR value.  The second case is
loading tile config and tile data into guest registers and trapping to
the host side for a complete save/load of the guest state.  TMM0
is also checked against memory data after save/restore.

Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20211223145322.2914028-4-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This commit is contained in:
Yang Zhong 2021-12-23 09:53:22 -05:00 committed by Paolo Bonzini
parent 6559b4a523
commit bf70636d94
2 changed files with 449 additions and 0 deletions

View File

@ -82,6 +82,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test
TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_pi_mmio_test
TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests
TEST_GEN_PROGS_x86_64 += x86_64/amx_test
TEST_GEN_PROGS_x86_64 += demand_paging_test
TEST_GEN_PROGS_x86_64 += dirty_log_test
TEST_GEN_PROGS_x86_64 += dirty_log_perf_test

View File

@ -0,0 +1,448 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
* amx tests
*
* Copyright (C) 2021, Intel, Inc.
*
* Tests for amx #NM exception and save/restore.
*/
#define _GNU_SOURCE /* for program_invocation_short_name */
#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/ioctl.h>
#include <sys/syscall.h>
#include "test_util.h"
#include "kvm_util.h"
#include "processor.h"
#include "vmx.h"
#ifndef __x86_64__
# error This test is 64-bit only
#endif
#define VCPU_ID 0
#define X86_FEATURE_XSAVE (1 << 26)
#define X86_FEATURE_OSXSAVE (1 << 27)
#define PAGE_SIZE (1 << 12)
#define NUM_TILES 8
#define TILE_SIZE 1024
#define XSAVE_SIZE ((NUM_TILES * TILE_SIZE) + PAGE_SIZE)
/* Tile configuration associated: */
#define MAX_TILES 16
#define RESERVED_BYTES 14
#define XFEATURE_XTILECFG 17
#define XFEATURE_XTILEDATA 18
#define XFEATURE_MASK_XTILECFG (1 << XFEATURE_XTILECFG)
#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA)
#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA)
#define TILE_CPUID 0x1d
#define XSTATE_CPUID 0xd
#define TILE_PALETTE_CPUID_SUBLEAVE 0x1
#define XSTATE_USER_STATE_SUBLEAVE 0x0
#define XSAVE_HDR_OFFSET 512
struct xsave_data {
u8 area[XSAVE_SIZE];
} __aligned(64);
struct tile_config {
u8 palette_id;
u8 start_row;
u8 reserved[RESERVED_BYTES];
u16 colsb[MAX_TILES];
u8 rows[MAX_TILES];
};
struct tile_data {
u8 data[NUM_TILES * TILE_SIZE];
};
struct xtile_info {
u16 bytes_per_tile;
u16 bytes_per_row;
u16 max_names;
u16 max_rows;
u32 xsave_offset;
u32 xsave_size;
};
static struct xtile_info xtile;
static inline u64 __xgetbv(u32 index)
{
u32 eax, edx;
asm volatile("xgetbv;"
: "=a" (eax), "=d" (edx)
: "c" (index));
return eax + ((u64)edx << 32);
}
static inline void __xsetbv(u32 index, u64 value)
{
u32 eax = value;
u32 edx = value >> 32;
asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index));
}
static inline void __ldtilecfg(void *cfg)
{
asm volatile(".byte 0xc4,0xe2,0x78,0x49,0x00"
: : "a"(cfg));
}
static inline void __tileloadd(void *tile)
{
asm volatile(".byte 0xc4,0xe2,0x7b,0x4b,0x04,0x10"
: : "a"(tile), "d"(0));
}
static inline void __tilerelease(void)
{
asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ::);
}
static inline void __xsavec(struct xsave_data *data, uint64_t rfbm)
{
uint32_t rfbm_lo = rfbm;
uint32_t rfbm_hi = rfbm >> 32;
asm volatile("xsavec (%%rdi)"
: : "D" (data), "a" (rfbm_lo), "d" (rfbm_hi)
: "memory");
}
static inline void check_cpuid_xsave(void)
{
uint32_t eax, ebx, ecx, edx;
eax = 1;
ecx = 0;
cpuid(&eax, &ebx, &ecx, &edx);
if (!(ecx & X86_FEATURE_XSAVE))
GUEST_ASSERT(!"cpuid: no CPU xsave support!");
if (!(ecx & X86_FEATURE_OSXSAVE))
GUEST_ASSERT(!"cpuid: no OS xsave support!");
}
static bool check_xsave_supports_xtile(void)
{
return __xgetbv(0) & XFEATURE_MASK_XTILE;
}
static bool enum_xtile_config(void)
{
u32 eax, ebx, ecx, edx;
eax = TILE_CPUID;
ecx = TILE_PALETTE_CPUID_SUBLEAVE;
cpuid(&eax, &ebx, &ecx, &edx);
if (!eax || !ebx || !ecx)
return false;
xtile.max_names = ebx >> 16;
if (xtile.max_names < NUM_TILES)
return false;
xtile.bytes_per_tile = eax >> 16;
if (xtile.bytes_per_tile < TILE_SIZE)
return false;
xtile.bytes_per_row = ebx;
xtile.max_rows = ecx;
return true;
}
static bool enum_xsave_tile(void)
{
u32 eax, ebx, ecx, edx;
eax = XSTATE_CPUID;
ecx = XFEATURE_XTILEDATA;
cpuid(&eax, &ebx, &ecx, &edx);
if (!eax || !ebx)
return false;
xtile.xsave_offset = ebx;
xtile.xsave_size = eax;
return true;
}
static bool check_xsave_size(void)
{
u32 eax, ebx, ecx, edx;
bool valid = false;
eax = XSTATE_CPUID;
ecx = XSTATE_USER_STATE_SUBLEAVE;
cpuid(&eax, &ebx, &ecx, &edx);
if (ebx && ebx <= XSAVE_SIZE)
valid = true;
return valid;
}
static bool check_xtile_info(void)
{
bool ret = false;
if (!check_xsave_size())
return ret;
if (!enum_xsave_tile())
return ret;
if (!enum_xtile_config())
return ret;
if (sizeof(struct tile_data) >= xtile.xsave_size)
ret = true;
return ret;
}
static void set_tilecfg(struct tile_config *cfg)
{
int i;
/* Only palette id 1 */
cfg->palette_id = 1;
for (i = 0; i < xtile.max_names; i++) {
cfg->colsb[i] = xtile.bytes_per_row;
cfg->rows[i] = xtile.max_rows;
}
}
static void set_xstatebv(void *data, uint64_t bv)
{
*(uint64_t *)(data + XSAVE_HDR_OFFSET) = bv;
}
static u64 get_xstatebv(void *data)
{
return *(u64 *)(data + XSAVE_HDR_OFFSET);
}
static void init_regs(void)
{
uint64_t cr4, xcr0;
/* turn on CR4.OSXSAVE */
cr4 = get_cr4();
cr4 |= X86_CR4_OSXSAVE;
set_cr4(cr4);
xcr0 = __xgetbv(0);
xcr0 |= XFEATURE_MASK_XTILE;
__xsetbv(0x0, xcr0);
}
static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg,
struct tile_data *tiledata,
struct xsave_data *xsave_data)
{
init_regs();
check_cpuid_xsave();
GUEST_ASSERT(check_xsave_supports_xtile());
GUEST_ASSERT(check_xtile_info());
/* check xtile configs */
GUEST_ASSERT(xtile.xsave_offset == 2816);
GUEST_ASSERT(xtile.xsave_size == 8192);
GUEST_ASSERT(xtile.max_names == 8);
GUEST_ASSERT(xtile.bytes_per_tile == 1024);
GUEST_ASSERT(xtile.bytes_per_row == 64);
GUEST_ASSERT(xtile.max_rows == 16);
GUEST_SYNC(1);
/* xfd=0, enable amx */
wrmsr(MSR_IA32_XFD, 0);
GUEST_SYNC(2);
GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == 0);
set_tilecfg(amx_cfg);
__ldtilecfg(amx_cfg);
GUEST_SYNC(3);
/* Check save/restore when trap to userspace */
__tileloadd(tiledata);
GUEST_SYNC(4);
__tilerelease();
GUEST_SYNC(5);
/* bit 18 not in the XCOMP_BV after xsavec() */
set_xstatebv(xsave_data, XFEATURE_MASK_XTILEDATA);
__xsavec(xsave_data, XFEATURE_MASK_XTILEDATA);
GUEST_ASSERT((get_xstatebv(xsave_data) & XFEATURE_MASK_XTILEDATA) == 0);
/* xfd=0x40000, disable amx tiledata */
wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILEDATA);
GUEST_SYNC(6);
GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILEDATA);
set_tilecfg(amx_cfg);
__ldtilecfg(amx_cfg);
/* Trigger #NM exception */
__tileloadd(tiledata);
GUEST_SYNC(10);
GUEST_DONE();
}
void guest_nm_handler(struct ex_regs *regs)
{
/* Check if #NM is triggered by XFEATURE_MASK_XTILEDATA */
GUEST_SYNC(7);
GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA);
GUEST_SYNC(8);
GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA);
/* Clear xfd_err */
wrmsr(MSR_IA32_XFD_ERR, 0);
/* xfd=0, enable amx */
wrmsr(MSR_IA32_XFD, 0);
GUEST_SYNC(9);
}
int main(int argc, char *argv[])
{
struct kvm_cpuid_entry2 *entry;
struct kvm_regs regs1, regs2;
bool amx_supported = false;
struct kvm_vm *vm;
struct kvm_run *run;
struct kvm_x86_state *state;
int xsave_restore_size = 0;
vm_vaddr_t amx_cfg, tiledata, xsavedata;
struct ucall uc;
u32 amx_offset;
int stage, ret;
/* Create VM */
vm = vm_create_default(VCPU_ID, 0, guest_code);
entry = kvm_get_supported_cpuid_entry(1);
if (!(entry->ecx & X86_FEATURE_XSAVE)) {
print_skip("XSAVE feature not supported");
exit(KSFT_SKIP);
}
if (kvm_get_cpuid_max_basic() >= 0xd) {
entry = kvm_get_supported_cpuid_index(0xd, 0);
amx_supported = entry && !!(entry->eax & XFEATURE_MASK_XTILE);
if (!amx_supported) {
print_skip("AMX is not supported by the vCPU (eax=0x%x)", entry->eax);
exit(KSFT_SKIP);
}
/* Get xsave/restore max size */
xsave_restore_size = entry->ecx;
}
run = vcpu_state(vm, VCPU_ID);
vcpu_regs_get(vm, VCPU_ID, &regs1);
/* Register #NM handler */
vm_init_descriptor_tables(vm);
vcpu_init_descriptor_tables(vm, VCPU_ID);
vm_install_exception_handler(vm, NM_VECTOR, guest_nm_handler);
/* amx cfg for guest_code */
amx_cfg = vm_vaddr_alloc_page(vm);
memset(addr_gva2hva(vm, amx_cfg), 0x0, getpagesize());
/* amx tiledata for guest_code */
tiledata = vm_vaddr_alloc_pages(vm, 2);
memset(addr_gva2hva(vm, tiledata), rand() | 1, 2 * getpagesize());
/* xsave data for guest_code */
xsavedata = vm_vaddr_alloc_pages(vm, 3);
memset(addr_gva2hva(vm, xsavedata), 0, 3 * getpagesize());
vcpu_args_set(vm, VCPU_ID, 3, amx_cfg, tiledata, xsavedata);
for (stage = 1; ; stage++) {
_vcpu_run(vm, VCPU_ID);
TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
"Stage %d: unexpected exit reason: %u (%s),\n",
stage, run->exit_reason,
exit_reason_str(run->exit_reason));
switch (get_ucall(vm, VCPU_ID, &uc)) {
case UCALL_ABORT:
TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
__FILE__, uc.args[1]);
/* NOT REACHED */
case UCALL_SYNC:
switch (uc.args[1]) {
case 1:
case 2:
case 3:
case 5:
case 6:
case 7:
case 8:
fprintf(stderr, "GUEST_SYNC(%ld)\n", uc.args[1]);
break;
case 4:
case 10:
fprintf(stderr,
"GUEST_SYNC(%ld), check save/restore status\n", uc.args[1]);
/* Compacted mode, get amx offset by xsave area
* size subtract 8K amx size.
*/
amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE;
state = vcpu_save_state(vm, VCPU_ID);
void *amx_start = (void *)state->xsave + amx_offset;
void *tiles_data = (void *)addr_gva2hva(vm, tiledata);
/* Only check TMM0 register, 1 tile */
ret = memcmp(amx_start, tiles_data, TILE_SIZE);
TEST_ASSERT(ret == 0, "memcmp failed, ret=%d\n", ret);
kvm_x86_state_cleanup(state);
break;
case 9:
fprintf(stderr,
"GUEST_SYNC(%ld), #NM exception and enable amx\n", uc.args[1]);
break;
}
break;
case UCALL_DONE:
fprintf(stderr, "UCALL_DONE\n");
goto done;
default:
TEST_FAIL("Unknown ucall %lu", uc.cmd);
}
state = vcpu_save_state(vm, VCPU_ID);
memset(&regs1, 0, sizeof(regs1));
vcpu_regs_get(vm, VCPU_ID, &regs1);
kvm_vm_release(vm);
/* Restore state in a new VM. */
kvm_vm_restart(vm, O_RDWR);
vm_vcpu_add(vm, VCPU_ID);
vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
vcpu_load_state(vm, VCPU_ID, state);
run = vcpu_state(vm, VCPU_ID);
kvm_x86_state_cleanup(state);
memset(&regs2, 0, sizeof(regs2));
vcpu_regs_get(vm, VCPU_ID, &regs2);
TEST_ASSERT(!memcmp(&regs1, &regs2, sizeof(regs2)),
"Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx",
(ulong) regs2.rdi, (ulong) regs2.rsi);
}
done:
kvm_vm_free(vm);
}