#include <linux/compiler.h>
#include <assert.h>
#include "guest_modes.h"
#include "kvm_util.h"
#include "processor.h"
#include "ucall_common.h"
#define DEFAULT_RISCV_GUEST_STACK_VADDR_MIN 0xac0000
static vm_vaddr_t exception_handlers;
bool __vcpu_has_ext(struct kvm_vcpu *vcpu, uint64_t ext)
{
unsigned long value = 0;
int ret;
ret = __vcpu_get_reg(vcpu, ext, &value);
return !ret && !!value;
}
static uint64_t pte_addr(struct kvm_vm *vm, uint64_t entry)
{
return ((entry & PGTBL_PTE_ADDR_MASK) >> PGTBL_PTE_ADDR_SHIFT) <<
PGTBL_PAGE_SIZE_SHIFT;
}
static uint64_t ptrs_per_pte(struct kvm_vm *vm)
{
return PGTBL_PAGE_SIZE / sizeof(uint64_t);
}
static uint64_t pte_index_mask[] = {
PGTBL_L0_INDEX_MASK,
PGTBL_L1_INDEX_MASK,
PGTBL_L2_INDEX_MASK,
PGTBL_L3_INDEX_MASK,
};
static uint32_t pte_index_shift[] = {
PGTBL_L0_INDEX_SHIFT,
PGTBL_L1_INDEX_SHIFT,
PGTBL_L2_INDEX_SHIFT,
PGTBL_L3_INDEX_SHIFT,
};
static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva, int level)
{
TEST_ASSERT(level > -1,
"Negative page table level (%d) not possible", level);
TEST_ASSERT(level < vm->mmu.pgtable_levels,
"Invalid page table level (%d)", level);
return (gva & pte_index_mask[level]) >> pte_index_shift[level];
}
void virt_arch_pgd_alloc(struct kvm_vm *vm)
{
size_t nr_pages = vm_page_align(vm, ptrs_per_pte(vm) * 8) / vm->page_size;
if (vm->mmu.pgd_created)
return;
vm->mmu.pgd = vm_phy_pages_alloc(vm, nr_pages,
KVM_GUEST_PAGE_TABLE_MIN_PADDR,
vm->memslots[MEM_REGION_PT]);
vm->mmu.pgd_created = true;
}
void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
{
uint64_t *ptep, next_ppn;
int level = vm->mmu.pgtable_levels - 1;
TEST_ASSERT((vaddr % vm->page_size) == 0,
"Virtual address not on page boundary,\n"
" vaddr: 0x%lx vm->page_size: 0x%x", vaddr, vm->page_size);
TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
(vaddr >> vm->page_shift)),
"Invalid virtual address, vaddr: 0x%lx", vaddr);
TEST_ASSERT((paddr % vm->page_size) == 0,
"Physical address not on page boundary,\n"
" paddr: 0x%lx vm->page_size: 0x%x", paddr, vm->page_size);
TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
"Physical address beyond maximum supported,\n"
" paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
paddr, vm->max_gfn, vm->page_size);
ptep = addr_gpa2hva(vm, vm->mmu.pgd) + pte_index(vm, vaddr, level) * 8;
if (!*ptep) {
next_ppn = vm_alloc_page_table(vm) >> PGTBL_PAGE_SIZE_SHIFT;
*ptep = (next_ppn << PGTBL_PTE_ADDR_SHIFT) |
PGTBL_PTE_VALID_MASK;
}
level--;
while (level > -1) {
ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) +
pte_index(vm, vaddr, level) * 8;
if (!*ptep && level > 0) {
next_ppn = vm_alloc_page_table(vm) >>
PGTBL_PAGE_SIZE_SHIFT;
*ptep = (next_ppn << PGTBL_PTE_ADDR_SHIFT) |
PGTBL_PTE_VALID_MASK;
}
level--;
}
paddr = paddr >> PGTBL_PAGE_SIZE_SHIFT;
*ptep = (paddr << PGTBL_PTE_ADDR_SHIFT) |
PGTBL_PTE_PERM_MASK | PGTBL_PTE_VALID_MASK;
}
vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
{
uint64_t *ptep;
int level = vm->mmu.pgtable_levels - 1;
if (!vm->mmu.pgd_created)
goto unmapped_gva;
ptep = addr_gpa2hva(vm, vm->mmu.pgd) + pte_index(vm, gva, level) * 8;
if (!ptep)
goto unmapped_gva;
level--;
while (level > -1) {
ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) +
pte_index(vm, gva, level) * 8;
if (!ptep)
goto unmapped_gva;
level--;
}
return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1));
unmapped_gva:
TEST_FAIL("No mapping for vm virtual address gva: 0x%lx level: %d",
gva, level);
exit(1);
}
static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent,
uint64_t page, int level)
{
#ifdef DEBUG
static const char *const type[] = { "pte", "pmd", "pud", "p4d"};
uint64_t pte, *ptep;
if (level < 0)
return;
for (pte = page; pte < page + ptrs_per_pte(vm) * 8; pte += 8) {
ptep = addr_gpa2hva(vm, pte);
if (!*ptep)
continue;
fprintf(stream, "%*s%s: %lx: %lx at %p\n", indent, "",
type[level], pte, *ptep, ptep);
pte_dump(stream, vm, indent + 1,
pte_addr(vm, *ptep), level - 1);
}
#endif
}
void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
{
struct kvm_mmu *mmu = &vm->mmu;
int level = mmu->pgtable_levels - 1;
uint64_t pgd, *ptep;
if (!mmu->pgd_created)
return;
for (pgd = mmu->pgd; pgd < mmu->pgd + ptrs_per_pte(vm) * 8; pgd += 8) {
ptep = addr_gpa2hva(vm, pgd);
if (!*ptep)
continue;
fprintf(stream, "%*spgd: %lx: %lx at %p\n", indent, "",
pgd, *ptep, ptep);
pte_dump(stream, vm, indent + 1,
pte_addr(vm, *ptep), level - 1);
}
}
void riscv_vcpu_mmu_setup(struct kvm_vcpu *vcpu)
{
struct kvm_vm *vm = vcpu->vm;
unsigned long satp;
unsigned long satp_mode;
unsigned long max_satp_mode;
switch (vm->mode) {
case VM_MODE_P56V57_4K:
case VM_MODE_P50V57_4K:
case VM_MODE_P41V57_4K:
satp_mode = SATP_MODE_57;
break;
case VM_MODE_P56V48_4K:
case VM_MODE_P50V48_4K:
case VM_MODE_P41V48_4K:
satp_mode = SATP_MODE_48;
break;
case VM_MODE_P56V39_4K:
case VM_MODE_P50V39_4K:
case VM_MODE_P41V39_4K:
satp_mode = SATP_MODE_39;
break;
default:
TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
}
max_satp_mode = vcpu_get_reg(vcpu, RISCV_CONFIG_REG(satp_mode));
if ((satp_mode >> SATP_MODE_SHIFT) > max_satp_mode)
TEST_FAIL("Unable to set satp mode 0x%lx, max mode 0x%lx\n",
satp_mode >> SATP_MODE_SHIFT, max_satp_mode);
satp = (vm->mmu.pgd >> PGTBL_PAGE_SIZE_SHIFT) & SATP_PPN;
satp |= satp_mode;
vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(satp), satp);
}
void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent)
{
struct kvm_riscv_core core;
core.mode = vcpu_get_reg(vcpu, RISCV_CORE_REG(mode));
core.regs.pc = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc));
core.regs.ra = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.ra));
core.regs.sp = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.sp));
core.regs.gp = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.gp));
core.regs.tp = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.tp));
core.regs.t0 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t0));
core.regs.t1 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t1));
core.regs.t2 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t2));
core.regs.s0 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s0));
core.regs.s1 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s1));
core.regs.a0 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a0));
core.regs.a1 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a1));
core.regs.a2 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a2));
core.regs.a3 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a3));
core.regs.a4 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a4));
core.regs.a5 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a5));
core.regs.a6 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a6));
core.regs.a7 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a7));
core.regs.s2 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s2));
core.regs.s3 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s3));
core.regs.s4 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s4));
core.regs.s5 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s5));
core.regs.s6 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s6));
core.regs.s7 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s7));
core.regs.s8 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s8));
core.regs.s9 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s9));
core.regs.s10 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s10));
core.regs.s11 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s11));
core.regs.t3 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t3));
core.regs.t4 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t4));
core.regs.t5 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t5));
core.regs.t6 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t6));
fprintf(stream,
" MODE: 0x%lx\n", core.mode);
fprintf(stream,
" PC: 0x%016lx RA: 0x%016lx SP: 0x%016lx GP: 0x%016lx\n",
core.regs.pc, core.regs.ra, core.regs.sp, core.regs.gp);
fprintf(stream,
" TP: 0x%016lx T0: 0x%016lx T1: 0x%016lx T2: 0x%016lx\n",
core.regs.tp, core.regs.t0, core.regs.t1, core.regs.t2);
fprintf(stream,
" S0: 0x%016lx S1: 0x%016lx A0: 0x%016lx A1: 0x%016lx\n",
core.regs.s0, core.regs.s1, core.regs.a0, core.regs.a1);
fprintf(stream,
" A2: 0x%016lx A3: 0x%016lx A4: 0x%016lx A5: 0x%016lx\n",
core.regs.a2, core.regs.a3, core.regs.a4, core.regs.a5);
fprintf(stream,
" A6: 0x%016lx A7: 0x%016lx S2: 0x%016lx S3: 0x%016lx\n",
core.regs.a6, core.regs.a7, core.regs.s2, core.regs.s3);
fprintf(stream,
" S4: 0x%016lx S5: 0x%016lx S6: 0x%016lx S7: 0x%016lx\n",
core.regs.s4, core.regs.s5, core.regs.s6, core.regs.s7);
fprintf(stream,
" S8: 0x%016lx S9: 0x%016lx S10: 0x%016lx S11: 0x%016lx\n",
core.regs.s8, core.regs.s9, core.regs.s10, core.regs.s11);
fprintf(stream,
" T3: 0x%016lx T4: 0x%016lx T5: 0x%016lx T6: 0x%016lx\n",
core.regs.t3, core.regs.t4, core.regs.t5, core.regs.t6);
}
static void __aligned(16) guest_unexp_trap(void)
{
sbi_ecall(KVM_RISCV_SELFTESTS_SBI_EXT,
KVM_RISCV_SELFTESTS_SBI_UNEXP,
0, 0, 0, 0, 0, 0);
}
void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code)
{
vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.pc), (unsigned long)guest_code);
}
struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
{
int r;
size_t stack_size;
unsigned long stack_vaddr;
unsigned long current_gp = 0;
struct kvm_mp_state mps;
struct kvm_vcpu *vcpu;
stack_size = vm->page_size == 4096 ? DEFAULT_STACK_PGS * vm->page_size :
vm->page_size;
stack_vaddr = __vm_vaddr_alloc(vm, stack_size,
DEFAULT_RISCV_GUEST_STACK_VADDR_MIN,
MEM_REGION_DATA);
vcpu = __vm_vcpu_add(vm, vcpu_id);
riscv_vcpu_mmu_setup(vcpu);
mps.mp_state = KVM_MP_STATE_RUNNABLE;
r = __vcpu_ioctl(vcpu, KVM_SET_MP_STATE, &mps);
TEST_ASSERT(!r, "IOCTL KVM_SET_MP_STATE failed (error %d)", r);
asm volatile (
"add %0, gp, zero" : "=r" (current_gp) : : "memory");
vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.gp), current_gp);
vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.sp), stack_vaddr + stack_size);
vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(sscratch), vcpu_id);
vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(stvec), (unsigned long)guest_unexp_trap);
return vcpu;
}
void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
{
va_list ap;
uint64_t id = RISCV_CORE_REG(regs.a0);
int i;
TEST_ASSERT(num >= 1 && num <= 8, "Unsupported number of args,\n"
" num: %u", num);
va_start(ap, num);
for (i = 0; i < num; i++) {
switch (i) {
case 0:
id = RISCV_CORE_REG(regs.a0);
break;
case 1:
id = RISCV_CORE_REG(regs.a1);
break;
case 2:
id = RISCV_CORE_REG(regs.a2);
break;
case 3:
id = RISCV_CORE_REG(regs.a3);
break;
case 4:
id = RISCV_CORE_REG(regs.a4);
break;
case 5:
id = RISCV_CORE_REG(regs.a5);
break;
case 6:
id = RISCV_CORE_REG(regs.a6);
break;
case 7:
id = RISCV_CORE_REG(regs.a7);
break;
}
vcpu_set_reg(vcpu, id, va_arg(ap, uint64_t));
}
va_end(ap);
}
void kvm_exit_unexpected_exception(int vector, int ec)
{
ucall(UCALL_UNHANDLED, 2, vector, ec);
}
void assert_on_unhandled_exception(struct kvm_vcpu *vcpu)
{
struct ucall uc;
if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED) {
TEST_FAIL("Unexpected exception (vector:0x%lx, ec:0x%lx)",
uc.args[0], uc.args[1]);
}
}
struct handlers {
exception_handler_fn exception_handlers[NR_VECTORS][NR_EXCEPTIONS];
};
void route_exception(struct pt_regs *regs)
{
struct handlers *handlers = (struct handlers *)exception_handlers;
int vector = 0, ec;
ec = regs->cause & ~CAUSE_IRQ_FLAG;
if (ec >= NR_EXCEPTIONS)
goto unexpected_exception;
if (regs->cause & CAUSE_IRQ_FLAG) {
vector = 1;
ec = 0;
}
if (handlers && handlers->exception_handlers[vector][ec])
return handlers->exception_handlers[vector][ec](regs);
unexpected_exception:
return kvm_exit_unexpected_exception(vector, ec);
}
void vcpu_init_vector_tables(struct kvm_vcpu *vcpu)
{
extern char exception_vectors;
vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(stvec), (unsigned long)&exception_vectors);
}
void vm_init_vector_tables(struct kvm_vm *vm)
{
vm->handlers = __vm_vaddr_alloc(vm, sizeof(struct handlers),
vm->page_size, MEM_REGION_DATA);
*(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
}
void vm_install_exception_handler(struct kvm_vm *vm, int vector, exception_handler_fn handler)
{
struct handlers *handlers = addr_gva2hva(vm, vm->handlers);
assert(vector < NR_EXCEPTIONS);
handlers->exception_handlers[0][vector] = handler;
}
void vm_install_interrupt_handler(struct kvm_vm *vm, exception_handler_fn handler)
{
struct handlers *handlers = addr_gva2hva(vm, vm->handlers);
handlers->exception_handlers[1][0] = handler;
}
uint32_t guest_get_vcpuid(void)
{
return csr_read(CSR_SSCRATCH);
}
struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
unsigned long arg1, unsigned long arg2,
unsigned long arg3, unsigned long arg4,
unsigned long arg5)
{
register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0);
register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1);
register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2);
register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3);
register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4);
register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5);
register uintptr_t a6 asm ("a6") = (uintptr_t)(fid);
register uintptr_t a7 asm ("a7") = (uintptr_t)(ext);
struct sbiret ret;
asm volatile (
"ecall"
: "+r" (a0), "+r" (a1)
: "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7)
: "memory");
ret.error = a0;
ret.value = a1;
return ret;
}
bool guest_sbi_probe_extension(int extid, long *out_val)
{
struct sbiret ret;
ret = sbi_ecall(SBI_EXT_BASE, SBI_EXT_BASE_PROBE_EXT, extid,
0, 0, 0, 0, 0);
__GUEST_ASSERT(!ret.error || ret.error == SBI_ERR_NOT_SUPPORTED,
"ret.error=%ld, ret.value=%ld\n", ret.error, ret.value);
if (ret.error == SBI_ERR_NOT_SUPPORTED)
return false;
if (out_val)
*out_val = ret.value;
return true;
}
unsigned long get_host_sbi_spec_version(void)
{
struct sbiret ret;
ret = sbi_ecall(SBI_EXT_BASE, SBI_EXT_BASE_GET_SPEC_VERSION, 0,
0, 0, 0, 0, 0);
GUEST_ASSERT(!ret.error);
return ret.value;
}
void kvm_selftest_arch_init(void)
{
guest_modes_append_default();
}
unsigned long riscv64_get_satp_mode(void)
{
int kvm_fd, vm_fd, vcpu_fd, err;
uint64_t val;
struct kvm_one_reg reg = {
.id = RISCV_CONFIG_REG(satp_mode),
.addr = (uint64_t)&val,
};
kvm_fd = open_kvm_dev_path_or_exit();
vm_fd = __kvm_ioctl(kvm_fd, KVM_CREATE_VM, NULL);
TEST_ASSERT(vm_fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_VM, vm_fd));
vcpu_fd = ioctl(vm_fd, KVM_CREATE_VCPU, 0);
TEST_ASSERT(vcpu_fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_VCPU, vcpu_fd));
err = ioctl(vcpu_fd, KVM_GET_ONE_REG, ®);
TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_GET_ONE_REG, vcpu_fd));
close(vcpu_fd);
close(vm_fd);
close(kvm_fd);
return val;
}
