Add a new VM mode, VM_MODE_PXXV57_4K, to support tests that require
5-level paging on x86. This mode sets up a 57-bit virtual address
space and sets CR4.LA57 in the guest.
Signed-off-by: Jim Mattson <jmattson@google.com>
---
.../testing/selftests/kvm/include/kvm_util.h | 1 +
tools/testing/selftests/kvm/lib/kvm_util.c | 21 +++++++++++++++++
.../testing/selftests/kvm/lib/x86/processor.c | 23 ++++++++++++-------
tools/testing/selftests/kvm/lib/x86/vmx.c | 7 +++---
4 files changed, 41 insertions(+), 11 deletions(-)
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 23a506d7eca3..b6ea5d966715 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -175,6 +175,7 @@ enum vm_guest_mode {
VM_MODE_P40V48_16K,
VM_MODE_P40V48_64K,
VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */
+ VM_MODE_PXXV57_4K, /* For 48bits VA but ANY bits PA */
VM_MODE_P47V64_4K,
VM_MODE_P44V64_4K,
VM_MODE_P36V48_4K,
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index c3f5142b0a54..6b0e499c6e91 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -232,6 +232,7 @@ const char *vm_guest_mode_string(uint32_t i)
[VM_MODE_P40V48_16K] = "PA-bits:40, VA-bits:48, 16K pages",
[VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages",
[VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages",
+ [VM_MODE_PXXV57_4K] = "PA-bits:ANY, VA-bits:57, 4K pages",
[VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages",
[VM_MODE_P44V64_4K] = "PA-bits:44, VA-bits:64, 4K pages",
[VM_MODE_P36V48_4K] = "PA-bits:36, VA-bits:48, 4K pages",
@@ -259,6 +260,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = {
[VM_MODE_P40V48_16K] = { 40, 48, 0x4000, 14 },
[VM_MODE_P40V48_64K] = { 40, 48, 0x10000, 16 },
[VM_MODE_PXXV48_4K] = { 0, 0, 0x1000, 12 },
+ [VM_MODE_PXXV57_4K] = { 0, 0, 0x1000, 12 },
[VM_MODE_P47V64_4K] = { 47, 64, 0x1000, 12 },
[VM_MODE_P44V64_4K] = { 44, 64, 0x1000, 12 },
[VM_MODE_P36V48_4K] = { 36, 48, 0x1000, 12 },
@@ -358,6 +360,25 @@ struct kvm_vm *____vm_create(struct vm_shape shape)
vm->va_bits = 48;
#else
TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms");
+#endif
+ break;
+ case VM_MODE_PXXV57_4K:
+#ifdef __x86_64__
+ kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits);
+ kvm_init_vm_address_properties(vm);
+ /*
+ * For 5-level paging, KVM requires LA57 to be enabled, which
+ * requires a 57-bit virtual address space.
+ */
+ TEST_ASSERT(vm->va_bits == 57,
+ "Linear address width (%d bits) not supported for VM_MODE_PXXV57_4K",
+ vm->va_bits);
+ pr_debug("Guest physical address width detected: %d\n",
+ vm->pa_bits);
+ vm->pgtable_levels = 5;
+ vm->va_bits = 57;
+#else
+ TEST_FAIL("VM_MODE_PXXV57_4K not supported on non-x86 platforms");
#endif
break;
case VM_MODE_P47V64_4K:
diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c
index 433365c8196d..d566190ea488 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -124,10 +124,11 @@ bool kvm_is_tdp_enabled(void)
void virt_arch_pgd_alloc(struct kvm_vm *vm)
{
- TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
- "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+ TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K ||
+ vm->mode == VM_MODE_PXXV57_4K,
+ "Unknown or unsupported guest mode: 0x%x", vm->mode);
- /* If needed, create page map l4 table. */
+ /* If needed, create the top-level page table. */
if (!vm->pgd_created) {
vm->pgd = vm_alloc_page_table(vm);
vm->pgd_created = true;
@@ -187,8 +188,9 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
uint64_t *pte = &vm->pgd;
int current_level;
- TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K,
- "Unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+ TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K ||
+ vm->mode == VM_MODE_PXXV57_4K,
+ "Unknown or unsupported guest mode: 0x%x", vm->mode);
TEST_ASSERT((vaddr % pg_size) == 0,
"Virtual address not aligned,\n"
@@ -279,8 +281,9 @@ uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr,
TEST_ASSERT(*level >= PG_LEVEL_NONE && *level < PG_LEVEL_NUM,
"Invalid PG_LEVEL_* '%d'", *level);
- TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
- "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+ TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K ||
+ vm->mode == VM_MODE_PXXV57_4K,
+ "Unknown or unsupported guest mode: 0x%x", vm->mode);
TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
(vaddr >> vm->page_shift)),
"Invalid virtual address, vaddr: 0x%lx",
@@ -481,7 +484,9 @@ static void vcpu_init_sregs(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
{
struct kvm_sregs sregs;
- TEST_ASSERT_EQ(vm->mode, VM_MODE_PXXV48_4K);
+ TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K ||
+ vm->mode == VM_MODE_PXXV57_4K,
+ "Unknown or unsupported guest mode: 0x%x", vm->mode);
/* Set mode specific system register values. */
vcpu_sregs_get(vcpu, &sregs);
@@ -495,6 +500,8 @@ static void vcpu_init_sregs(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR;
if (kvm_cpu_has(X86_FEATURE_XSAVE))
sregs.cr4 |= X86_CR4_OSXSAVE;
+ if (vm->pgtable_levels == 5)
+ sregs.cr4 |= X86_CR4_LA57;
sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
kvm_seg_set_unusable(&sregs.ldt);
diff --git a/tools/testing/selftests/kvm/lib/x86/vmx.c b/tools/testing/selftests/kvm/lib/x86/vmx.c
index d4d1208dd023..1b6d4a007798 100644
--- a/tools/testing/selftests/kvm/lib/x86/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86/vmx.c
@@ -401,11 +401,12 @@ void __nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
struct eptPageTableEntry *pt = vmx->eptp_hva, *pte;
uint16_t index;
- TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
- "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+ TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K ||
+ vm->mode == VM_MODE_PXXV57_4K,
+ "Unknown or unsupported guest mode: 0x%x", vm->mode);
TEST_ASSERT((nested_paddr >> 48) == 0,
- "Nested physical address 0x%lx requires 5-level paging",
+ "Nested physical address 0x%lx is > 48-bits and requires 5-level EPT",
nested_paddr);
TEST_ASSERT((nested_paddr % page_size) == 0,
"Nested physical address not on page boundary,\n"
--
2.51.0.470.ga7dc726c21-googOn Wed, Sep 17, 2025, Jim Mattson wrote:
> Add a new VM mode, VM_MODE_PXXV57_4K, to support tests that require
> 5-level paging on x86. This mode sets up a 57-bit virtual address
> space and sets CR4.LA57 in the guest.
> @@ -358,6 +360,25 @@ struct kvm_vm *____vm_create(struct vm_shape shape)
> vm->va_bits = 48;
> #else
> TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms");
> +#endif
> + break;
> + case VM_MODE_PXXV57_4K:
> +#ifdef __x86_64__
> + kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits);
> + kvm_init_vm_address_properties(vm);
> + /*
> + * For 5-level paging, KVM requires LA57 to be enabled, which
> + * requires a 57-bit virtual address space.
> + */
> + TEST_ASSERT(vm->va_bits == 57,
> + "Linear address width (%d bits) not supported for VM_MODE_PXXV57_4K",
> + vm->va_bits);
> + pr_debug("Guest physical address width detected: %d\n",
> + vm->pa_bits);
> + vm->pgtable_levels = 5;
> + vm->va_bits = 57;
> +#else
> + TEST_FAIL("VM_MODE_PXXV57_4K not supported on non-x86 platforms");
> #endif
That's a lot of copy+paste, especially given the #ifdefs. How about this (untested)?
case VM_MODE_PXXV48_4K:
case VM_MODE_PXXV57_4K:
#ifdef __x86_64__
kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits);
kvm_init_vm_address_properties(vm);
/*
* Ignore KVM support for 5-level paging (vm->va_bits == 57) if
* the target mode is 4-level paging (48-bit virtual address
* space), as 5-level paging only takes effect if CR4.LA57=1.
*/
TEST_ASSERT(vm->va_bits == 57 ||
(vm->va_bits == 48 && vm->mode == VM_MODE_PXXV48_4K),
"Linear address width (%d bits) not supported",
vm->va_bits);
pr_debug("Guest physical address width detected: %d\n",
vm->pa_bits);
if (vm->mode == VM_MODE_PXXV48_4K) {
vm->pgtable_levels = 4;
vm->va_bits = 48;
} else {
vm->pgtable_levels = 5;
vm->va_bits = 57;
}
#else
TEST_FAIL("VM_MODE_PXXV{48,57}_4K not supported on non-x86 platforms");
#endif
break;
On Wed, Oct 15, 2025, Sean Christopherson wrote:
> On Wed, Sep 17, 2025, Jim Mattson wrote:
> > Add a new VM mode, VM_MODE_PXXV57_4K, to support tests that require
> > 5-level paging on x86. This mode sets up a 57-bit virtual address
> > space and sets CR4.LA57 in the guest.
Thinking about this more, unless it's _really_ painful, e.g. because tests assume
4-level paging or 48-bit non-canonical address, I would rather turn VM_MODE_PXXV48_4K
into VM_MODE_PXXVXX_4K and have ____vm_create() create the "maximal" VM. That
way tests don't need to go out of their way just to use 5-level paging, e.g. a
"TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_LA57))" is all that is needed. It will also
gives quite a bit of coverage for free, e.g. that save/restore works with and
without 5-level paging (contrived example, but you get the point).
The NONCANONICAL #define works for LA57, so hopefully making tests play nice with
LA57 is straightforward?
> > @@ -358,6 +360,25 @@ struct kvm_vm *____vm_create(struct vm_shape shape)
> > vm->va_bits = 48;
> > #else
> > TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms");
> > +#endif
> > + break;
> > + case VM_MODE_PXXV57_4K:
> > +#ifdef __x86_64__
> > + kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits);
> > + kvm_init_vm_address_properties(vm);
> > + /*
> > + * For 5-level paging, KVM requires LA57 to be enabled, which
> > + * requires a 57-bit virtual address space.
> > + */
> > + TEST_ASSERT(vm->va_bits == 57,
> > + "Linear address width (%d bits) not supported for VM_MODE_PXXV57_4K",
> > + vm->va_bits);
> > + pr_debug("Guest physical address width detected: %d\n",
> > + vm->pa_bits);
> > + vm->pgtable_levels = 5;
> > + vm->va_bits = 57;
> > +#else
> > + TEST_FAIL("VM_MODE_PXXV57_4K not supported on non-x86 platforms");
> > #endif
>
> That's a lot of copy+paste, especially given the #ifdefs. How about this (untested)?
>
> case VM_MODE_PXXV48_4K:
> case VM_MODE_PXXV57_4K:
> #ifdef __x86_64__
> kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits);
> kvm_init_vm_address_properties(vm);
>
> /*
> * Ignore KVM support for 5-level paging (vm->va_bits == 57) if
> * the target mode is 4-level paging (48-bit virtual address
> * space), as 5-level paging only takes effect if CR4.LA57=1.
> */
> TEST_ASSERT(vm->va_bits == 57 ||
> (vm->va_bits == 48 && vm->mode == VM_MODE_PXXV48_4K),
> "Linear address width (%d bits) not supported",
> vm->va_bits);
> pr_debug("Guest physical address width detected: %d\n",
> vm->pa_bits);
> if (vm->mode == VM_MODE_PXXV48_4K) {
> vm->pgtable_levels = 4;
> vm->va_bits = 48;
> } else {
> vm->pgtable_levels = 5;
> vm->va_bits = 57;
> }
> #else
> TEST_FAIL("VM_MODE_PXXV{48,57}_4K not supported on non-x86 platforms");
> #endif
> break;
On Wed, Oct 15, 2025 at 5:40 PM Sean Christopherson <seanjc@google.com> wrote: > > On Wed, Oct 15, 2025, Sean Christopherson wrote: > > On Wed, Sep 17, 2025, Jim Mattson wrote: > > > Add a new VM mode, VM_MODE_PXXV57_4K, to support tests that require > > > 5-level paging on x86. This mode sets up a 57-bit virtual address > > > space and sets CR4.LA57 in the guest. > > Thinking about this more, unless it's _really_ painful, e.g. because tests assume > 4-level paging or 48-bit non-canonical address, I would rather turn VM_MODE_PXXV48_4K > into VM_MODE_PXXVXX_4K and have ____vm_create() create the "maximal" VM. That > way tests don't need to go out of their way just to use 5-level paging, e.g. a > "TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_LA57))" is all that is needed. It will also > gives quite a bit of coverage for free, e.g. that save/restore works with and > without 5-level paging (contrived example, but you get the point). > > The NONCANONICAL #define works for LA57, so hopefully making tests play nice with > LA57 is straightforward? I will see what I can do. :)
On Wed, Sep 17, 2025 at 02:48:39PM -0700, Jim Mattson wrote:
> Add a new VM mode, VM_MODE_PXXV57_4K, to support tests that require
> 5-level paging on x86. This mode sets up a 57-bit virtual address
> space and sets CR4.LA57 in the guest.
>
> Signed-off-by: Jim Mattson <jmattson@google.com>
> ---
> .../testing/selftests/kvm/include/kvm_util.h | 1 +
> tools/testing/selftests/kvm/lib/kvm_util.c | 21 +++++++++++++++++
> .../testing/selftests/kvm/lib/x86/processor.c | 23 ++++++++++++-------
> tools/testing/selftests/kvm/lib/x86/vmx.c | 7 +++---
> 4 files changed, 41 insertions(+), 11 deletions(-)
>
> diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
> index 23a506d7eca3..b6ea5d966715 100644
> --- a/tools/testing/selftests/kvm/include/kvm_util.h
> +++ b/tools/testing/selftests/kvm/include/kvm_util.h
> @@ -175,6 +175,7 @@ enum vm_guest_mode {
> VM_MODE_P40V48_16K,
> VM_MODE_P40V48_64K,
> VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */
> + VM_MODE_PXXV57_4K, /* For 48bits VA but ANY bits PA */
> VM_MODE_P47V64_4K,
> VM_MODE_P44V64_4K,
> VM_MODE_P36V48_4K,
> diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
> index c3f5142b0a54..6b0e499c6e91 100644
> --- a/tools/testing/selftests/kvm/lib/kvm_util.c
> +++ b/tools/testing/selftests/kvm/lib/kvm_util.c
> @@ -232,6 +232,7 @@ const char *vm_guest_mode_string(uint32_t i)
> [VM_MODE_P40V48_16K] = "PA-bits:40, VA-bits:48, 16K pages",
> [VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages",
> [VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages",
> + [VM_MODE_PXXV57_4K] = "PA-bits:ANY, VA-bits:57, 4K pages",
> [VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages",
> [VM_MODE_P44V64_4K] = "PA-bits:44, VA-bits:64, 4K pages",
> [VM_MODE_P36V48_4K] = "PA-bits:36, VA-bits:48, 4K pages",
> @@ -259,6 +260,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = {
> [VM_MODE_P40V48_16K] = { 40, 48, 0x4000, 14 },
> [VM_MODE_P40V48_64K] = { 40, 48, 0x10000, 16 },
> [VM_MODE_PXXV48_4K] = { 0, 0, 0x1000, 12 },
> + [VM_MODE_PXXV57_4K] = { 0, 0, 0x1000, 12 },
> [VM_MODE_P47V64_4K] = { 47, 64, 0x1000, 12 },
> [VM_MODE_P44V64_4K] = { 44, 64, 0x1000, 12 },
> [VM_MODE_P36V48_4K] = { 36, 48, 0x1000, 12 },
> @@ -358,6 +360,25 @@ struct kvm_vm *____vm_create(struct vm_shape shape)
> vm->va_bits = 48;
> #else
> TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms");
We should probably update TEST_ASSERT(vm->va_bits == 48 || vm->va_bits == 57)
above to only assert 48 bits now, right?
> +#endif
> + break;
> + case VM_MODE_PXXV57_4K:
> +#ifdef __x86_64__
> + kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits);
> + kvm_init_vm_address_properties(vm);
> + /*
> + * For 5-level paging, KVM requires LA57 to be enabled, which
> + * requires a 57-bit virtual address space.
> + */
> + TEST_ASSERT(vm->va_bits == 57,
> + "Linear address width (%d bits) not supported for VM_MODE_PXXV57_4K",
> + vm->va_bits);
> + pr_debug("Guest physical address width detected: %d\n",
> + vm->pa_bits);
> + vm->pgtable_levels = 5;
> + vm->va_bits = 57;
> +#else
> + TEST_FAIL("VM_MODE_PXXV57_4K not supported on non-x86 platforms");
> #endif
> break;
> case VM_MODE_P47V64_4K:
> diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c
> index 433365c8196d..d566190ea488 100644
> --- a/tools/testing/selftests/kvm/lib/x86/processor.c
> +++ b/tools/testing/selftests/kvm/lib/x86/processor.c
> @@ -124,10 +124,11 @@ bool kvm_is_tdp_enabled(void)
>
> void virt_arch_pgd_alloc(struct kvm_vm *vm)
> {
> - TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
> - "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
> + TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K ||
> + vm->mode == VM_MODE_PXXV57_4K,
> + "Unknown or unsupported guest mode: 0x%x", vm->mode);
>
> - /* If needed, create page map l4 table. */
> + /* If needed, create the top-level page table. */
> if (!vm->pgd_created) {
> vm->pgd = vm_alloc_page_table(vm);
> vm->pgd_created = true;
> @@ -187,8 +188,9 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
> uint64_t *pte = &vm->pgd;
> int current_level;
>
> - TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K,
> - "Unknown or unsupported guest mode, mode: 0x%x", vm->mode);
> + TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K ||
> + vm->mode == VM_MODE_PXXV57_4K,
> + "Unknown or unsupported guest mode: 0x%x", vm->mode);
>
> TEST_ASSERT((vaddr % pg_size) == 0,
> "Virtual address not aligned,\n"
> @@ -279,8 +281,9 @@ uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr,
> TEST_ASSERT(*level >= PG_LEVEL_NONE && *level < PG_LEVEL_NUM,
> "Invalid PG_LEVEL_* '%d'", *level);
>
> - TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
> - "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
> + TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K ||
> + vm->mode == VM_MODE_PXXV57_4K,
> + "Unknown or unsupported guest mode: 0x%x", vm->mode);
> TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
> (vaddr >> vm->page_shift)),
> "Invalid virtual address, vaddr: 0x%lx",
> @@ -481,7 +484,9 @@ static void vcpu_init_sregs(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
> {
> struct kvm_sregs sregs;
>
> - TEST_ASSERT_EQ(vm->mode, VM_MODE_PXXV48_4K);
> + TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K ||
> + vm->mode == VM_MODE_PXXV57_4K,
> + "Unknown or unsupported guest mode: 0x%x", vm->mode);
>
> /* Set mode specific system register values. */
> vcpu_sregs_get(vcpu, &sregs);
> @@ -495,6 +500,8 @@ static void vcpu_init_sregs(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
> sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR;
> if (kvm_cpu_has(X86_FEATURE_XSAVE))
> sregs.cr4 |= X86_CR4_OSXSAVE;
> + if (vm->pgtable_levels == 5)
> + sregs.cr4 |= X86_CR4_LA57;
> sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
>
> kvm_seg_set_unusable(&sregs.ldt);
> diff --git a/tools/testing/selftests/kvm/lib/x86/vmx.c b/tools/testing/selftests/kvm/lib/x86/vmx.c
> index d4d1208dd023..1b6d4a007798 100644
> --- a/tools/testing/selftests/kvm/lib/x86/vmx.c
> +++ b/tools/testing/selftests/kvm/lib/x86/vmx.c
> @@ -401,11 +401,12 @@ void __nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
> struct eptPageTableEntry *pt = vmx->eptp_hva, *pte;
> uint16_t index;
>
> - TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
> - "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
> + TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K ||
> + vm->mode == VM_MODE_PXXV57_4K,
> + "Unknown or unsupported guest mode: 0x%x", vm->mode);
>
> TEST_ASSERT((nested_paddr >> 48) == 0,
> - "Nested physical address 0x%lx requires 5-level paging",
> + "Nested physical address 0x%lx is > 48-bits and requires 5-level EPT",
> nested_paddr);
> TEST_ASSERT((nested_paddr % page_size) == 0,
> "Nested physical address not on page boundary,\n"
> --
> 2.51.0.470.ga7dc726c21-goog
>
On Wed, Oct 15, 2025, Yosry Ahmed wrote:
> On Wed, Sep 17, 2025 at 02:48:39PM -0700, Jim Mattson wrote:
> > Add a new VM mode, VM_MODE_PXXV57_4K, to support tests that require
> > 5-level paging on x86. This mode sets up a 57-bit virtual address
> > space and sets CR4.LA57 in the guest.
> >
> > Signed-off-by: Jim Mattson <jmattson@google.com>
> > ---
> > .../testing/selftests/kvm/include/kvm_util.h | 1 +
> > tools/testing/selftests/kvm/lib/kvm_util.c | 21 +++++++++++++++++
> > .../testing/selftests/kvm/lib/x86/processor.c | 23 ++++++++++++-------
> > tools/testing/selftests/kvm/lib/x86/vmx.c | 7 +++---
> > 4 files changed, 41 insertions(+), 11 deletions(-)
> >
> > diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
> > index 23a506d7eca3..b6ea5d966715 100644
> > --- a/tools/testing/selftests/kvm/include/kvm_util.h
> > +++ b/tools/testing/selftests/kvm/include/kvm_util.h
> > @@ -175,6 +175,7 @@ enum vm_guest_mode {
> > VM_MODE_P40V48_16K,
> > VM_MODE_P40V48_64K,
> > VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */
> > + VM_MODE_PXXV57_4K, /* For 48bits VA but ANY bits PA */
> > VM_MODE_P47V64_4K,
> > VM_MODE_P44V64_4K,
> > VM_MODE_P36V48_4K,
> > diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
> > index c3f5142b0a54..6b0e499c6e91 100644
> > --- a/tools/testing/selftests/kvm/lib/kvm_util.c
> > +++ b/tools/testing/selftests/kvm/lib/kvm_util.c
> > @@ -232,6 +232,7 @@ const char *vm_guest_mode_string(uint32_t i)
> > [VM_MODE_P40V48_16K] = "PA-bits:40, VA-bits:48, 16K pages",
> > [VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages",
> > [VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages",
> > + [VM_MODE_PXXV57_4K] = "PA-bits:ANY, VA-bits:57, 4K pages",
> > [VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages",
> > [VM_MODE_P44V64_4K] = "PA-bits:44, VA-bits:64, 4K pages",
> > [VM_MODE_P36V48_4K] = "PA-bits:36, VA-bits:48, 4K pages",
> > @@ -259,6 +260,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = {
> > [VM_MODE_P40V48_16K] = { 40, 48, 0x4000, 14 },
> > [VM_MODE_P40V48_64K] = { 40, 48, 0x10000, 16 },
> > [VM_MODE_PXXV48_4K] = { 0, 0, 0x1000, 12 },
> > + [VM_MODE_PXXV57_4K] = { 0, 0, 0x1000, 12 },
> > [VM_MODE_P47V64_4K] = { 47, 64, 0x1000, 12 },
> > [VM_MODE_P44V64_4K] = { 44, 64, 0x1000, 12 },
> > [VM_MODE_P36V48_4K] = { 36, 48, 0x1000, 12 },
> > @@ -358,6 +360,25 @@ struct kvm_vm *____vm_create(struct vm_shape shape)
> > vm->va_bits = 48;
> > #else
> > TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms");
>
> We should probably update TEST_ASSERT(vm->va_bits == 48 || vm->va_bits == 57)
> above to only assert 48 bits now, right?
No, because CPUID reports the _max_ virtual address width. In theory, the assert
could be ">= 48", but in practice x86-64 only supports 48-bit and 57-bit VAs, so
selftests are paranoid and are sanity checking KVM at the same time.
On Wed, Sep 17, 2025 at 02:48:39PM -0700, Jim Mattson wrote:
> Add a new VM mode, VM_MODE_PXXV57_4K, to support tests that require
> 5-level paging on x86. This mode sets up a 57-bit virtual address
> space and sets CR4.LA57 in the guest.
>
> Signed-off-by: Jim Mattson <jmattson@google.com>
> ---
> .../testing/selftests/kvm/include/kvm_util.h | 1 +
> tools/testing/selftests/kvm/lib/kvm_util.c | 21 +++++++++++++++++
> .../testing/selftests/kvm/lib/x86/processor.c | 23 ++++++++++++-------
> tools/testing/selftests/kvm/lib/x86/vmx.c | 7 +++---
> 4 files changed, 41 insertions(+), 11 deletions(-)
>
> diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
> index 23a506d7eca3..b6ea5d966715 100644
> --- a/tools/testing/selftests/kvm/include/kvm_util.h
> +++ b/tools/testing/selftests/kvm/include/kvm_util.h
> @@ -175,6 +175,7 @@ enum vm_guest_mode {
> VM_MODE_P40V48_16K,
> VM_MODE_P40V48_64K,
> VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */
> + VM_MODE_PXXV57_4K, /* For 48bits VA but ANY bits PA */
> VM_MODE_P47V64_4K,
> VM_MODE_P44V64_4K,
> VM_MODE_P36V48_4K,
> diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
> index c3f5142b0a54..6b0e499c6e91 100644
> --- a/tools/testing/selftests/kvm/lib/kvm_util.c
> +++ b/tools/testing/selftests/kvm/lib/kvm_util.c
> @@ -232,6 +232,7 @@ const char *vm_guest_mode_string(uint32_t i)
> [VM_MODE_P40V48_16K] = "PA-bits:40, VA-bits:48, 16K pages",
> [VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages",
> [VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages",
> + [VM_MODE_PXXV57_4K] = "PA-bits:ANY, VA-bits:57, 4K pages",
> [VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages",
> [VM_MODE_P44V64_4K] = "PA-bits:44, VA-bits:64, 4K pages",
> [VM_MODE_P36V48_4K] = "PA-bits:36, VA-bits:48, 4K pages",
> @@ -259,6 +260,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = {
> [VM_MODE_P40V48_16K] = { 40, 48, 0x4000, 14 },
> [VM_MODE_P40V48_64K] = { 40, 48, 0x10000, 16 },
> [VM_MODE_PXXV48_4K] = { 0, 0, 0x1000, 12 },
> + [VM_MODE_PXXV57_4K] = { 0, 0, 0x1000, 12 },
> [VM_MODE_P47V64_4K] = { 47, 64, 0x1000, 12 },
> [VM_MODE_P44V64_4K] = { 44, 64, 0x1000, 12 },
> [VM_MODE_P36V48_4K] = { 36, 48, 0x1000, 12 },
> @@ -358,6 +360,25 @@ struct kvm_vm *____vm_create(struct vm_shape shape)
> vm->va_bits = 48;
> #else
> TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms");
> +#endif
> + break;
> + case VM_MODE_PXXV57_4K:
> +#ifdef __x86_64__
> + kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits);
> + kvm_init_vm_address_properties(vm);
> + /*
> + * For 5-level paging, KVM requires LA57 to be enabled, which
> + * requires a 57-bit virtual address space.
> + */
> + TEST_ASSERT(vm->va_bits == 57,
> + "Linear address width (%d bits) not supported for VM_MODE_PXXV57_4K",
> + vm->va_bits);
> + pr_debug("Guest physical address width detected: %d\n",
> + vm->pa_bits);
> + vm->pgtable_levels = 5;
> + vm->va_bits = 57;
We assert that vm->va_bits is 57, and then we set it here again. Seems
like we're doing the same for VM_MODE_PXXV48_4K too.
> +#else
> + TEST_FAIL("VM_MODE_PXXV57_4K not supported on non-x86 platforms");
> #endif
> break;
> case VM_MODE_P47V64_4K:
> diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c
> index 433365c8196d..d566190ea488 100644
> --- a/tools/testing/selftests/kvm/lib/x86/processor.c
> +++ b/tools/testing/selftests/kvm/lib/x86/processor.c
> @@ -124,10 +124,11 @@ bool kvm_is_tdp_enabled(void)
>
> void virt_arch_pgd_alloc(struct kvm_vm *vm)
> {
> - TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
> - "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
> + TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K ||
> + vm->mode == VM_MODE_PXXV57_4K,
> + "Unknown or unsupported guest mode: 0x%x", vm->mode);
>
> - /* If needed, create page map l4 table. */
> + /* If needed, create the top-level page table. */
> if (!vm->pgd_created) {
> vm->pgd = vm_alloc_page_table(vm);
> vm->pgd_created = true;
> @@ -187,8 +188,9 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
> uint64_t *pte = &vm->pgd;
> int current_level;
>
> - TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K,
> - "Unknown or unsupported guest mode, mode: 0x%x", vm->mode);
> + TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K ||
> + vm->mode == VM_MODE_PXXV57_4K,
> + "Unknown or unsupported guest mode: 0x%x", vm->mode);
>
> TEST_ASSERT((vaddr % pg_size) == 0,
> "Virtual address not aligned,\n"
> @@ -279,8 +281,9 @@ uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr,
> TEST_ASSERT(*level >= PG_LEVEL_NONE && *level < PG_LEVEL_NUM,
> "Invalid PG_LEVEL_* '%d'", *level);
>
> - TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
> - "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
> + TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K ||
> + vm->mode == VM_MODE_PXXV57_4K,
> + "Unknown or unsupported guest mode: 0x%x", vm->mode);
> TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
> (vaddr >> vm->page_shift)),
> "Invalid virtual address, vaddr: 0x%lx",
> @@ -481,7 +484,9 @@ static void vcpu_init_sregs(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
> {
> struct kvm_sregs sregs;
>
> - TEST_ASSERT_EQ(vm->mode, VM_MODE_PXXV48_4K);
> + TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K ||
> + vm->mode == VM_MODE_PXXV57_4K,
> + "Unknown or unsupported guest mode: 0x%x", vm->mode);
>
> /* Set mode specific system register values. */
> vcpu_sregs_get(vcpu, &sregs);
> @@ -495,6 +500,8 @@ static void vcpu_init_sregs(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
> sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR;
> if (kvm_cpu_has(X86_FEATURE_XSAVE))
> sregs.cr4 |= X86_CR4_OSXSAVE;
> + if (vm->pgtable_levels == 5)
> + sregs.cr4 |= X86_CR4_LA57;
> sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
>
> kvm_seg_set_unusable(&sregs.ldt);
> diff --git a/tools/testing/selftests/kvm/lib/x86/vmx.c b/tools/testing/selftests/kvm/lib/x86/vmx.c
> index d4d1208dd023..1b6d4a007798 100644
> --- a/tools/testing/selftests/kvm/lib/x86/vmx.c
> +++ b/tools/testing/selftests/kvm/lib/x86/vmx.c
> @@ -401,11 +401,12 @@ void __nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
> struct eptPageTableEntry *pt = vmx->eptp_hva, *pte;
> uint16_t index;
>
> - TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
> - "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
> + TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K ||
> + vm->mode == VM_MODE_PXXV57_4K,
> + "Unknown or unsupported guest mode: 0x%x", vm->mode);
>
> TEST_ASSERT((nested_paddr >> 48) == 0,
> - "Nested physical address 0x%lx requires 5-level paging",
> + "Nested physical address 0x%lx is > 48-bits and requires 5-level EPT",
Shouldn't this assertion be updated now? We technically support 5-level
EPT so it should only fire if the mode is VM_MODE_PXXV48_4K. Maybe we
should use vm->va_bits?
> nested_paddr);
> TEST_ASSERT((nested_paddr % page_size) == 0,
> "Nested physical address not on page boundary,\n"
> --
> 2.51.0.470.ga7dc726c21-goog
>
On Wed, Oct 15, 2025 at 2:23 PM Yosry Ahmed <yosry.ahmed@linux.dev> wrote: > > On Wed, Sep 17, 2025 at 02:48:39PM -0700, Jim Mattson wrote: > > Add a new VM mode, VM_MODE_PXXV57_4K, to support tests that require > > 5-level paging on x86. This mode sets up a 57-bit virtual address > > space and sets CR4.LA57 in the guest. > > > > Signed-off-by: Jim Mattson <jmattson@google.com> > > --- > > .../testing/selftests/kvm/include/kvm_util.h | 1 + > > tools/testing/selftests/kvm/lib/kvm_util.c | 21 +++++++++++++++++ > > .../testing/selftests/kvm/lib/x86/processor.c | 23 ++++++++++++------- > > tools/testing/selftests/kvm/lib/x86/vmx.c | 7 +++--- > > 4 files changed, 41 insertions(+), 11 deletions(-) > > > > ... > > diff --git a/tools/testing/selftests/kvm/lib/x86/vmx.c b/tools/testing/selftests/kvm/lib/x86/vmx.c > > index d4d1208dd023..1b6d4a007798 100644 > > --- a/tools/testing/selftests/kvm/lib/x86/vmx.c > > +++ b/tools/testing/selftests/kvm/lib/x86/vmx.c > > @@ -401,11 +401,12 @@ void __nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, > > struct eptPageTableEntry *pt = vmx->eptp_hva, *pte; > > uint16_t index; > > > > - TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " > > - "unknown or unsupported guest mode, mode: 0x%x", vm->mode); > > + TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K || > > + vm->mode == VM_MODE_PXXV57_4K, > > + "Unknown or unsupported guest mode: 0x%x", vm->mode); > > > > TEST_ASSERT((nested_paddr >> 48) == 0, > > - "Nested physical address 0x%lx requires 5-level paging", > > + "Nested physical address 0x%lx is > 48-bits and requires 5-level EPT", > > Shouldn't this assertion be updated now? We technically support 5-level > EPT so it should only fire if the mode is VM_MODE_PXXV48_4K. Maybe we > should use vm->va_bits? I did update the assertion! :) init_vmcs_control_fields() hardcodes a page-walk-length of 4 in the EPTP, and the loop in __nested_pg_map() counts down from PG_LEVEL_512G. There is no support for 5-level EPT here. > > > nested_paddr); > > TEST_ASSERT((nested_paddr % page_size) == 0, > > "Nested physical address not on page boundary,\n" > > -- > > 2.51.0.470.ga7dc726c21-goog > > >
On Tue, Oct 21, 2025 at 03:34:22PM -0700, Jim Mattson wrote: > On Wed, Oct 15, 2025 at 2:23 PM Yosry Ahmed <yosry.ahmed@linux.dev> wrote: > > > > On Wed, Sep 17, 2025 at 02:48:39PM -0700, Jim Mattson wrote: > > > Add a new VM mode, VM_MODE_PXXV57_4K, to support tests that require > > > 5-level paging on x86. This mode sets up a 57-bit virtual address > > > space and sets CR4.LA57 in the guest. > > > > > > Signed-off-by: Jim Mattson <jmattson@google.com> > > > --- > > > .../testing/selftests/kvm/include/kvm_util.h | 1 + > > > tools/testing/selftests/kvm/lib/kvm_util.c | 21 +++++++++++++++++ > > > .../testing/selftests/kvm/lib/x86/processor.c | 23 ++++++++++++------- > > > tools/testing/selftests/kvm/lib/x86/vmx.c | 7 +++--- > > > 4 files changed, 41 insertions(+), 11 deletions(-) > > > > > > ... > > > diff --git a/tools/testing/selftests/kvm/lib/x86/vmx.c b/tools/testing/selftests/kvm/lib/x86/vmx.c > > > index d4d1208dd023..1b6d4a007798 100644 > > > --- a/tools/testing/selftests/kvm/lib/x86/vmx.c > > > +++ b/tools/testing/selftests/kvm/lib/x86/vmx.c > > > @@ -401,11 +401,12 @@ void __nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, > > > struct eptPageTableEntry *pt = vmx->eptp_hva, *pte; > > > uint16_t index; > > > > > > - TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " > > > - "unknown or unsupported guest mode, mode: 0x%x", vm->mode); > > > + TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K || > > > + vm->mode == VM_MODE_PXXV57_4K, > > > + "Unknown or unsupported guest mode: 0x%x", vm->mode); > > > > > > TEST_ASSERT((nested_paddr >> 48) == 0, > > > - "Nested physical address 0x%lx requires 5-level paging", > > > + "Nested physical address 0x%lx is > 48-bits and requires 5-level EPT", > > > > Shouldn't this assertion be updated now? We technically support 5-level > > EPT so it should only fire if the mode is VM_MODE_PXXV48_4K. Maybe we > > should use vm->va_bits? > > I did update the assertion! :) > > init_vmcs_control_fields() hardcodes a page-walk-length of 4 in the > EPTP, and the loop in __nested_pg_map() counts down from > PG_LEVEL_512G. There is no support for 5-level EPT here. __nested_pg_map() will be gone with the series [1] moving nested mappings to use __virt_pg_map(), and with your series the latter does support 5-level EPTs. init_vmcs_control_fields() still hardcodes a page-walk-length of 4 tho. I actually just realized, my series will already drop these assertions and rely on the ones in __virt_pg_map(), which do use vm->page_shift, so the assertion won't fire if init_vmcs_control_fields() starts using 5-level EPTs. TL;DR nothing to do here. [1]https://lore.kernel.org/kvm/20251021074736.1324328-1-yosry.ahmed@linux.dev/ > > > > > > nested_paddr); > > > TEST_ASSERT((nested_paddr % page_size) == 0, > > > "Nested physical address not on page boundary,\n" > > > -- > > > 2.51.0.470.ga7dc726c21-goog > > > > >
© 2016 - 2026 Red Hat, Inc.