Commit 9f073ac2 authored by Sean Christopherson's avatar Sean Christopherson
Browse files

KVM: selftests: Add "struct kvm_mmu" to track a given MMU instance 



Add a "struct kvm_mmu" to track a given MMU instance, e.g. a VM's stage-1
MMU versus a VM's stage-2 MMU, so that x86 can share MMU functionality for
both stage-1 and stage-2 MMUs, without creating the potential for subtle
bugs, e.g. due to consuming on vm->pgtable_levels when operating a stage-2
MMU.

Encapsulate the existing de facto MMU in "struct kvm_vm", e.g instead of
burying the MMU details in "struct kvm_vm_arch", to avoid more #ifdefs in
____vm_create(), and in the hopes that other architectures can utilize the
formalized MMU structure if/when they too support stage-2 page tables.

No functional change intended.

Reviewed-by: default avatarYosry Ahmed <yosry.ahmed@linux.dev>
Link: https://patch.msgid.link/20251230230150.4150236-7-seanjc@google.com


Signed-off-by: default avatarSean Christopherson <seanjc@google.com>
parent 3cd50028

tools/testing/selftests/kvm/include/kvm_util.h

+8 −3
Original line number Diff line number Diff line
@@ -88,12 +88,17 @@ enum kvm_mem_region_type { 
	NR_MEM_REGIONS,

};



struct kvm_mmu {

	bool pgd_created;

	uint64_t pgd;

	int pgtable_levels;

};



struct kvm_vm {

	int mode;

	unsigned long type;

	int kvm_fd;

	int fd;

	unsigned int pgtable_levels;

	unsigned int page_size;

	unsigned int page_shift;

	unsigned int pa_bits;
@@ -104,13 +109,13 @@ struct kvm_vm { 
	struct sparsebit *vpages_valid;

	struct sparsebit *vpages_mapped;

	bool has_irqchip;

	bool pgd_created;

	vm_paddr_t ucall_mmio_addr;

	vm_paddr_t pgd;

	vm_vaddr_t handlers;

	uint32_t dirty_ring_size;

	uint64_t gpa_tag_mask;



	struct kvm_mmu mmu;



	struct kvm_vm_arch arch;



	struct kvm_binary_stats stats;

tools/testing/selftests/kvm/lib/arm64/processor.c

+19 −19
Original line number Diff line number Diff line
@@ -28,7 +28,7 @@ static uint64_t page_align(struct kvm_vm *vm, uint64_t v) 


static uint64_t pgd_index(struct kvm_vm *vm, vm_vaddr_t gva)

{

	unsigned int shift = (vm->pgtable_levels - 1) * (vm->page_shift - 3) + vm->page_shift;

	unsigned int shift = (vm->mmu.pgtable_levels - 1) * (vm->page_shift - 3) + vm->page_shift;

	uint64_t mask = (1UL << (vm->va_bits - shift)) - 1;



	return (gva >> shift) & mask;
@@ -39,7 +39,7 @@ static uint64_t pud_index(struct kvm_vm *vm, vm_vaddr_t gva) 
	unsigned int shift = 2 * (vm->page_shift - 3) + vm->page_shift;

	uint64_t mask = (1UL << (vm->page_shift - 3)) - 1;



	TEST_ASSERT(vm->pgtable_levels == 4,

	TEST_ASSERT(vm->mmu.pgtable_levels == 4,

		"Mode %d does not have 4 page table levels", vm->mode);



	return (gva >> shift) & mask;
@@ -50,7 +50,7 @@ static uint64_t pmd_index(struct kvm_vm *vm, vm_vaddr_t gva) 
	unsigned int shift = (vm->page_shift - 3) + vm->page_shift;

	uint64_t mask = (1UL << (vm->page_shift - 3)) - 1;



	TEST_ASSERT(vm->pgtable_levels >= 3,

	TEST_ASSERT(vm->mmu.pgtable_levels >= 3,

		"Mode %d does not have >= 3 page table levels", vm->mode);



	return (gva >> shift) & mask;
@@ -104,7 +104,7 @@ static uint64_t pte_addr(struct kvm_vm *vm, uint64_t pte) 


static uint64_t ptrs_per_pgd(struct kvm_vm *vm)

{

	unsigned int shift = (vm->pgtable_levels - 1) * (vm->page_shift - 3) + vm->page_shift;

	unsigned int shift = (vm->mmu.pgtable_levels - 1) * (vm->page_shift - 3) + vm->page_shift;

	return 1 << (vm->va_bits - shift);

}
@@ -117,13 +117,13 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm) 
{

	size_t nr_pages = page_align(vm, ptrs_per_pgd(vm) * 8) / vm->page_size;



	if (vm->pgd_created)

	if (vm->mmu.pgd_created)

		return;



	vm->pgd = vm_phy_pages_alloc(vm, nr_pages,

	vm->mmu.pgd = vm_phy_pages_alloc(vm, nr_pages,

					 KVM_GUEST_PAGE_TABLE_MIN_PADDR,

					 vm->memslots[MEM_REGION_PT]);

	vm->pgd_created = true;

	vm->mmu.pgd_created = true;

}



static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
@@ -147,12 +147,12 @@ static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, 
		"  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->pgd) + pgd_index(vm, vaddr) * 8;

	ptep = addr_gpa2hva(vm, vm->mmu.pgd) + pgd_index(vm, vaddr) * 8;

	if (!*ptep)

		*ptep = addr_pte(vm, vm_alloc_page_table(vm),

				 PGD_TYPE_TABLE | PTE_VALID);



	switch (vm->pgtable_levels) {

	switch (vm->mmu.pgtable_levels) {

	case 4:

		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, vaddr) * 8;

		if (!*ptep)
@@ -190,16 +190,16 @@ uint64_t *virt_get_pte_hva_at_level(struct kvm_vm *vm, vm_vaddr_t gva, int level 
{

	uint64_t *ptep;



	if (!vm->pgd_created)

	if (!vm->mmu.pgd_created)

		goto unmapped_gva;



	ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, gva) * 8;

	ptep = addr_gpa2hva(vm, vm->mmu.pgd) + pgd_index(vm, gva) * 8;

	if (!ptep)

		goto unmapped_gva;

	if (level == 0)

		return ptep;



	switch (vm->pgtable_levels) {

	switch (vm->mmu.pgtable_levels) {

	case 4:

		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, gva) * 8;

		if (!ptep)
@@ -263,13 +263,13 @@ static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t p 


void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)

{

	int level = 4 - (vm->pgtable_levels - 1);

	int level = 4 - (vm->mmu.pgtable_levels - 1);

	uint64_t pgd, *ptep;



	if (!vm->pgd_created)

	if (!vm->mmu.pgd_created)

		return;



	for (pgd = vm->pgd; pgd < vm->pgd + ptrs_per_pgd(vm) * 8; pgd += 8) {

	for (pgd = vm->mmu.pgd; pgd < vm->mmu.pgd + ptrs_per_pgd(vm) * 8; pgd += 8) {

		ptep = addr_gpa2hva(vm, pgd);

		if (!*ptep)

			continue;
@@ -350,7 +350,7 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) 
		TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);

	}



	ttbr0_el1 = vm->pgd & GENMASK(47, vm->page_shift);

	ttbr0_el1 = vm->mmu.pgd & GENMASK(47, vm->page_shift);



	/* Configure output size */

	switch (vm->mode) {
@@ -358,7 +358,7 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) 
	case VM_MODE_P52V48_16K:

	case VM_MODE_P52V48_64K:

		tcr_el1 |= TCR_IPS_52_BITS;

		ttbr0_el1 |= FIELD_GET(GENMASK(51, 48), vm->pgd) << 2;

		ttbr0_el1 |= FIELD_GET(GENMASK(51, 48), vm->mmu.pgd) << 2;

		break;

	case VM_MODE_P48V48_4K:

	case VM_MODE_P48V48_16K:

tools/testing/selftests/kvm/lib/kvm_util.c

+14 −14
Original line number Diff line number Diff line
@@ -281,34 +281,34 @@ struct kvm_vm *____vm_create(struct vm_shape shape) 
	/* Setup mode specific traits. */

	switch (vm->mode) {

	case VM_MODE_P52V48_4K:

		vm->pgtable_levels = 4;

		vm->mmu.pgtable_levels = 4;

		break;

	case VM_MODE_P52V48_64K:

		vm->pgtable_levels = 3;

		vm->mmu.pgtable_levels = 3;

		break;

	case VM_MODE_P48V48_4K:

		vm->pgtable_levels = 4;

		vm->mmu.pgtable_levels = 4;

		break;

	case VM_MODE_P48V48_64K:

		vm->pgtable_levels = 3;

		vm->mmu.pgtable_levels = 3;

		break;

	case VM_MODE_P40V48_4K:

	case VM_MODE_P36V48_4K:

		vm->pgtable_levels = 4;

		vm->mmu.pgtable_levels = 4;

		break;

	case VM_MODE_P40V48_64K:

	case VM_MODE_P36V48_64K:

		vm->pgtable_levels = 3;

		vm->mmu.pgtable_levels = 3;

		break;

	case VM_MODE_P52V48_16K:

	case VM_MODE_P48V48_16K:

	case VM_MODE_P40V48_16K:

	case VM_MODE_P36V48_16K:

		vm->pgtable_levels = 4;

		vm->mmu.pgtable_levels = 4;

		break;

	case VM_MODE_P47V47_16K:

	case VM_MODE_P36V47_16K:

		vm->pgtable_levels = 3;

		vm->mmu.pgtable_levels = 3;

		break;

	case VM_MODE_PXXVYY_4K:

#ifdef __x86_64__
@@ -321,22 +321,22 @@ struct kvm_vm *____vm_create(struct vm_shape shape) 
			 vm->va_bits);



		if (vm->va_bits == 57) {

			vm->pgtable_levels = 5;

			vm->mmu.pgtable_levels = 5;

		} else {

			TEST_ASSERT(vm->va_bits == 48,

				    "Unexpected guest virtual address width: %d",

				    vm->va_bits);

			vm->pgtable_levels = 4;

			vm->mmu.pgtable_levels = 4;

		}

#else

		TEST_FAIL("VM_MODE_PXXVYY_4K not supported on non-x86 platforms");

#endif

		break;

	case VM_MODE_P47V64_4K:

		vm->pgtable_levels = 5;

		vm->mmu.pgtable_levels = 5;

		break;

	case VM_MODE_P44V64_4K:

		vm->pgtable_levels = 5;

		vm->mmu.pgtable_levels = 5;

		break;

	default:

		TEST_FAIL("Unknown guest mode: 0x%x", vm->mode);
@@ -1956,8 +1956,8 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) 
	fprintf(stream, "%*sMapped Virtual Pages:\n", indent, "");

	sparsebit_dump(stream, vm->vpages_mapped, indent + 2);

	fprintf(stream, "%*spgd_created: %u\n", indent, "",

		vm->pgd_created);

	if (vm->pgd_created) {

		vm->mmu.pgd_created);

	if (vm->mmu.pgd_created) {

		fprintf(stream, "%*sVirtual Translation Tables:\n",

			indent + 2, "");

		virt_dump(stream, vm, indent + 4);

tools/testing/selftests/kvm/lib/loongarch/processor.c

+14 −14
Original line number Diff line number Diff line
@@ -50,11 +50,11 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm) 
	int i;

	vm_paddr_t child, table;



	if (vm->pgd_created)

	if (vm->mmu.pgd_created)

		return;



	child = table = 0;

	for (i = 0; i < vm->pgtable_levels; i++) {

	for (i = 0; i < vm->mmu.pgtable_levels; i++) {

		invalid_pgtable[i] = child;

		table = vm_phy_page_alloc(vm, LOONGARCH_PAGE_TABLE_PHYS_MIN,

				vm->memslots[MEM_REGION_PT]);
@@ -62,8 +62,8 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm) 
		virt_set_pgtable(vm, table, child);

		child = table;

	}

	vm->pgd = table;

	vm->pgd_created = true;

	vm->mmu.pgd = table;

	vm->mmu.pgd_created = true;

}



static int virt_pte_none(uint64_t *ptep, int level)
@@ -77,11 +77,11 @@ static uint64_t *virt_populate_pte(struct kvm_vm *vm, vm_vaddr_t gva, int alloc) 
	uint64_t *ptep;

	vm_paddr_t child;



	if (!vm->pgd_created)

	if (!vm->mmu.pgd_created)

		goto unmapped_gva;



	child = vm->pgd;

	level = vm->pgtable_levels - 1;

	child = vm->mmu.pgd;

	level = vm->mmu.pgtable_levels - 1;

	while (level > 0) {

		ptep = addr_gpa2hva(vm, child) + virt_pte_index(vm, gva, level) * 8;

		if (virt_pte_none(ptep, level)) {
@@ -161,11 +161,11 @@ void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) 
{

	int level;



	if (!vm->pgd_created)

	if (!vm->mmu.pgd_created)

		return;



	level = vm->pgtable_levels - 1;

	pte_dump(stream, vm, indent, vm->pgd, level);

	level = vm->mmu.pgtable_levels - 1;

	pte_dump(stream, vm, indent, vm->mmu.pgd, level);

}



void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent)
@@ -297,7 +297,7 @@ static void loongarch_vcpu_setup(struct kvm_vcpu *vcpu) 


	width = vm->page_shift - 3;



	switch (vm->pgtable_levels) {

	switch (vm->mmu.pgtable_levels) {

	case 4:

		/* pud page shift and width */

		val = (vm->page_shift + width * 2) << 20 | (width << 25);
@@ -309,15 +309,15 @@ static void loongarch_vcpu_setup(struct kvm_vcpu *vcpu) 
		val |= vm->page_shift | width << 5;

		break;

	default:

		TEST_FAIL("Got %u page table levels, expected 3 or 4", vm->pgtable_levels);

		TEST_FAIL("Got %u page table levels, expected 3 or 4", vm->mmu.pgtable_levels);

	}



	loongarch_set_csr(vcpu, LOONGARCH_CSR_PWCTL0, val);



	/* PGD page shift and width */

	val = (vm->page_shift + width * (vm->pgtable_levels - 1)) | width << 6;

	val = (vm->page_shift + width * (vm->mmu.pgtable_levels - 1)) | width << 6;

	loongarch_set_csr(vcpu, LOONGARCH_CSR_PWCTL1, val);

	loongarch_set_csr(vcpu, LOONGARCH_CSR_PGDL, vm->pgd);

	loongarch_set_csr(vcpu, LOONGARCH_CSR_PGDL, vm->mmu.pgd);



	/*

	 * Refill exception runs on real mode

tools/testing/selftests/kvm/lib/riscv/processor.c

+16 −15
Original line number Diff line number Diff line
@@ -60,7 +60,7 @@ 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->pgtable_levels,

	TEST_ASSERT(level < vm->mmu.pgtable_levels,

		"Invalid page table level (%d)", level);



	return (gva & pte_index_mask[level]) >> pte_index_shift[level];
@@ -70,19 +70,19 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm) 
{

	size_t nr_pages = page_align(vm, ptrs_per_pte(vm) * 8) / vm->page_size;



	if (vm->pgd_created)

	if (vm->mmu.pgd_created)

		return;



	vm->pgd = vm_phy_pages_alloc(vm, nr_pages,

	vm->mmu.pgd = vm_phy_pages_alloc(vm, nr_pages,

					 KVM_GUEST_PAGE_TABLE_MIN_PADDR,

					 vm->memslots[MEM_REGION_PT]);

	vm->pgd_created = true;

	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->pgtable_levels - 1;

	int level = vm->mmu.pgtable_levels - 1;



	TEST_ASSERT((vaddr % vm->page_size) == 0,

		"Virtual address not on page boundary,\n"
@@ -98,7 +98,7 @@ void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) 
		"  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->pgd) + pte_index(vm, vaddr, level) * 8;

	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) |
@@ -126,12 +126,12 @@ void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) 
vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)

{

	uint64_t *ptep;

	int level = vm->pgtable_levels - 1;

	int level = vm->mmu.pgtable_levels - 1;



	if (!vm->pgd_created)

	if (!vm->mmu.pgd_created)

		goto unmapped_gva;



	ptep = addr_gpa2hva(vm, vm->pgd) + pte_index(vm, gva, level) * 8;

	ptep = addr_gpa2hva(vm, vm->mmu.pgd) + pte_index(vm, gva, level) * 8;

	if (!ptep)

		goto unmapped_gva;

	level--;
@@ -176,13 +176,14 @@ static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, 


void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)

{

	int level = vm->pgtable_levels - 1;

	struct kvm_mmu *mmu = &vm->mmu;

	int level = mmu->pgtable_levels - 1;

	uint64_t pgd, *ptep;



	if (!vm->pgd_created)

	if (!mmu->pgd_created)

		return;



	for (pgd = vm->pgd; pgd < vm->pgd + ptrs_per_pte(vm) * 8; pgd += 8) {

	for (pgd = mmu->pgd; pgd < mmu->pgd + ptrs_per_pte(vm) * 8; pgd += 8) {

		ptep = addr_gpa2hva(vm, pgd);

		if (!*ptep)

			continue;
@@ -211,7 +212,7 @@ void riscv_vcpu_mmu_setup(struct kvm_vcpu *vcpu) 
		TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);

	}



	satp = (vm->pgd >> PGTBL_PAGE_SIZE_SHIFT) & SATP_PPN;

	satp = (vm->mmu.pgd >> PGTBL_PAGE_SIZE_SHIFT) & SATP_PPN;

	satp |= SATP_MODE_48;



	vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(satp), satp);