@@ -465,13 +465,19 @@ void vcpu_set_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
void vm_xsave_req_perm(int bit);
-enum x86_page_size {
- X86_PAGE_SIZE_4K = 0,
- X86_PAGE_SIZE_2M,
- X86_PAGE_SIZE_1G,
+enum pg_level {
+ PG_LEVEL_NONE,
+ PG_LEVEL_4K,
+ PG_LEVEL_2M,
+ PG_LEVEL_1G,
+ PG_LEVEL_512G,
+ PG_LEVEL_NUM
};
-void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
- enum x86_page_size page_size);
+
+#define PG_LEVEL_SHIFT(_level) ((_level - 1) * 9 + 12)
+#define PG_LEVEL_SIZE(_level) (1ull << PG_LEVEL_SHIFT(_level))
+
+void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level);
/*
* Basic CPU control in CR0
@@ -190,7 +190,7 @@ static void *virt_get_pte(struct kvm_vm *vm, uint64_t pt_pfn, uint64_t vaddr,
int level)
{
uint64_t *page_table = addr_gpa2hva(vm, pt_pfn << vm->page_shift);
- int index = vaddr >> (vm->page_shift + level * 9) & 0x1ffu;
+ int index = (vaddr >> PG_LEVEL_SHIFT(level)) & 0x1ffu;
return &page_table[index];
}
@@ -199,15 +199,15 @@ static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm,
uint64_t pt_pfn,
uint64_t vaddr,
uint64_t paddr,
- int level,
- enum x86_page_size page_size)
+ int current_level,
+ int target_level)
{
- struct pageUpperEntry *pte = virt_get_pte(vm, pt_pfn, vaddr, level);
+ struct pageUpperEntry *pte = virt_get_pte(vm, pt_pfn, vaddr, current_level);
if (!pte->present) {
pte->writable = true;
pte->present = true;
- pte->page_size = (level == page_size);
+ pte->page_size = (current_level == target_level);
if (pte->page_size)
pte->pfn = paddr >> vm->page_shift;
else
@@ -218,20 +218,19 @@ static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm,
* a hugepage at this level, and that there isn't a hugepage at
* this level.
*/
- TEST_ASSERT(level != page_size,
+ TEST_ASSERT(current_level != target_level,
"Cannot create hugepage at level: %u, vaddr: 0x%lx\n",
- page_size, vaddr);
+ current_level, vaddr);
TEST_ASSERT(!pte->page_size,
"Cannot create page table at level: %u, vaddr: 0x%lx\n",
- level, vaddr);
+ current_level, vaddr);
}
return pte;
}
-void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
- enum x86_page_size page_size)
+void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
{
- const uint64_t pg_size = 1ull << ((page_size * 9) + 12);
+ const uint64_t pg_size = PG_LEVEL_SIZE(level);
struct pageUpperEntry *pml4e, *pdpe, *pde;
struct pageTableEntry *pte;
@@ -256,20 +255,22 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
* early if a hugepage was created.
*/
pml4e = virt_create_upper_pte(vm, vm->pgd >> vm->page_shift,
- vaddr, paddr, 3, page_size);
+ vaddr, paddr, PG_LEVEL_512G, level);
if (pml4e->page_size)
return;
- pdpe = virt_create_upper_pte(vm, pml4e->pfn, vaddr, paddr, 2, page_size);
+ pdpe = virt_create_upper_pte(vm, pml4e->pfn, vaddr, paddr, PG_LEVEL_1G,
+ level);
if (pdpe->page_size)
return;
- pde = virt_create_upper_pte(vm, pdpe->pfn, vaddr, paddr, 1, page_size);
+ pde = virt_create_upper_pte(vm, pdpe->pfn, vaddr, paddr, PG_LEVEL_2M,
+ level);
if (pde->page_size)
return;
/* Fill in page table entry. */
- pte = virt_get_pte(vm, pde->pfn, vaddr, 0);
+ pte = virt_get_pte(vm, pde->pfn, vaddr, PG_LEVEL_4K);
TEST_ASSERT(!pte->present,
"PTE already present for 4k page at vaddr: 0x%lx\n", vaddr);
pte->pfn = paddr >> vm->page_shift;
@@ -279,7 +280,7 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
{
- __virt_pg_map(vm, vaddr, paddr, X86_PAGE_SIZE_4K);
+ __virt_pg_map(vm, vaddr, paddr, PG_LEVEL_4K);
}
static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid,
@@ -244,7 +244,7 @@ int main(int argc, char *argv[])
#ifdef __x86_64__
/* Identity map memory in the guest using 1gb pages. */
for (i = 0; i < slot_size; i += size_1gb)
- __virt_pg_map(vm, gpa + i, gpa + i, X86_PAGE_SIZE_1G);
+ __virt_pg_map(vm, gpa + i, gpa + i, PG_LEVEL_1G);
#else
for (i = 0; i < slot_size; i += vm_get_page_size(vm))
virt_pg_map(vm, gpa + i, gpa + i);
@@ -35,7 +35,7 @@ static void mmu_role_test(u32 *cpuid_reg, u32 evil_cpuid_val)
run = vcpu_state(vm, VCPU_ID);
/* Map 1gb page without a backing memlot. */
- __virt_pg_map(vm, MMIO_GPA, MMIO_GPA, X86_PAGE_SIZE_1G);
+ __virt_pg_map(vm, MMIO_GPA, MMIO_GPA, PG_LEVEL_1G);
r = _vcpu_run(vm, VCPU_ID);
x86_page_size is an enum used to communicate the desired page size with which to map a range of memory. Under the hood they just encode the desired level at which to map the page. This ends up being clunky in a few ways: - The name suggests it encodes the size of the page rather than the level. - In other places in x86_64/processor.c we just use a raw int to encode the level. Simplify this by adopting the kernel style of PG_LEVEL_XX enums and pass around raw ints when referring to the level. This makes the code easier to understand since these macros are very common in KVM MMU code. Signed-off-by: David Matlack <dmatlack@google.com> --- .../selftests/kvm/include/x86_64/processor.h | 18 ++++++---- .../selftests/kvm/lib/x86_64/processor.c | 33 ++++++++++--------- .../selftests/kvm/max_guest_memory_test.c | 2 +- .../selftests/kvm/x86_64/mmu_role_test.c | 2 +- 4 files changed, 31 insertions(+), 24 deletions(-)