#include "kvm_cache_regs.h"
#include "cpuid.h"
-#define PT64_PT_BITS 9
-#define PT64_ENT_PER_PAGE __PT_ENT_PER_PAGE(PT64_PT_BITS)
-#define PT32_PT_BITS 10
-#define PT32_ENT_PER_PAGE __PT_ENT_PER_PAGE(PT32_PT_BITS)
-
#define PT_WRITABLE_SHIFT 1
#define PT_USER_SHIFT 2
#define PTE_PREFETCH_NUM 8
-#define PT32_LEVEL_BITS 10
-
-#define PT32_LEVEL_SHIFT(level) __PT_LEVEL_SHIFT(level, PT32_LEVEL_BITS)
-
-#define PT32_LVL_OFFSET_MASK(level) \
- __PT_LVL_OFFSET_MASK(PT32_BASE_ADDR_MASK, level, PT32_LEVEL_BITS)
-
-#define PT32_INDEX(address, level) __PT_INDEX(address, level, PT32_LEVEL_BITS)
-
-#define PT32_BASE_ADDR_MASK PAGE_MASK
-
-#define PT32_LVL_ADDR_MASK(level) \
- __PT_LVL_ADDR_MASK(PT32_BASE_ADDR_MASK, level, PT32_LEVEL_BITS)
-
#include <trace/events/kvm.h>
/* make pte_list_desc fit well in cache lines */
if (!sp->role.direct)
return sp->gfns[index];
- return sp->gfn + (index << ((sp->role.level - 1) * PT64_LEVEL_BITS));
+ return sp->gfn + (index << ((sp->role.level - 1) * SPTE_LEVEL_BITS));
}
static void kvm_mmu_page_set_gfn(struct kvm_mmu_page *sp, int index, gfn_t gfn)
continue;
}
- child = to_shadow_page(ent & PT64_BASE_ADDR_MASK);
+ child = to_shadow_page(ent & SPTE_BASE_ADDR_MASK);
if (child->unsync_children) {
if (mmu_pages_add(pvec, child, i))
role.direct = direct;
role.access = access;
if (role.has_4_byte_gpte) {
- quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
- quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
+ /*
+ * If the guest has 4-byte PTEs then that means it's using 32-bit,
+ * 2-level, non-PAE paging. KVM shadows such guests with PAE paging
+ * (i.e. 8-byte PTEs). The difference in PTE size means that KVM must
+ * shadow each guest page table with multiple shadow page tables, which
+ * requires extra bookkeeping in the role.
+ *
+ * Specifically, to shadow the guest's page directory (which covers a
+ * 4GiB address space), KVM uses 4 PAE page directories, each mapping
+ * 1GiB of the address space. @role.quadrant encodes which quarter of
+ * the address space each maps.
+ *
+ * To shadow the guest's page tables (which each map a 4MiB region), KVM
+ * uses 2 PAE page tables, each mapping a 2MiB region. For these,
+ * @role.quadrant encodes which half of the region they map.
+ */
+ quadrant = gaddr >> (PAGE_SHIFT + (SPTE_LEVEL_BITS * level));
+ quadrant &= (1 << level) - 1;
role.quadrant = quadrant;
}
if (level <= vcpu->arch.mmu->cpu_role.base.level)
iterator->shadow_addr
= vcpu->arch.mmu->pae_root[(addr >> 30) & 3];
- iterator->shadow_addr &= PT64_BASE_ADDR_MASK;
+ iterator->shadow_addr &= SPTE_BASE_ADDR_MASK;
--iterator->level;
if (!iterator->shadow_addr)
iterator->level = 0;
if (iterator->level < PG_LEVEL_4K)
return false;
- iterator->index = SHADOW_PT_INDEX(iterator->addr, iterator->level);
+ iterator->index = SPTE_INDEX(iterator->addr, iterator->level);
iterator->sptep = ((u64 *)__va(iterator->shadow_addr)) + iterator->index;
return true;
}
return;
}
- iterator->shadow_addr = spte & PT64_BASE_ADDR_MASK;
+ iterator->shadow_addr = spte & SPTE_BASE_ADDR_MASK;
--iterator->level;
}
* so we should update the spte at this point to get
* a new sp with the correct access.
*/
- child = to_shadow_page(*sptep & PT64_BASE_ADDR_MASK);
+ child = to_shadow_page(*sptep & SPTE_BASE_ADDR_MASK);
if (child->role.access == direct_access)
return;
if (is_last_spte(pte, sp->role.level)) {
drop_spte(kvm, spte);
} else {
- child = to_shadow_page(pte & PT64_BASE_ADDR_MASK);
+ child = to_shadow_page(pte & SPTE_BASE_ADDR_MASK);
drop_parent_pte(child, spte);
/*
int zapped = 0;
unsigned i;
- for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
+ for (i = 0; i < SPTE_ENT_PER_PAGE; ++i)
zapped += mmu_page_zap_pte(kvm, sp, sp->spt + i, invalid_list);
return zapped;
struct kvm_mmu_page *child;
u64 pte = *sptep;
- child = to_shadow_page(pte & PT64_BASE_ADDR_MASK);
+ child = to_shadow_page(pte & SPTE_BASE_ADDR_MASK);
drop_parent_pte(child, sptep);
flush = true;
} else if (pfn != spte_to_pfn(*sptep)) {
if (!VALID_PAGE(*root_hpa))
return;
- sp = to_shadow_page(*root_hpa & PT64_BASE_ADDR_MASK);
+ sp = to_shadow_page(*root_hpa & SPTE_BASE_ADDR_MASK);
if (WARN_ON(!sp))
return;
hpa_t root = vcpu->arch.mmu->pae_root[i];
if (IS_VALID_PAE_ROOT(root)) {
- root &= PT64_BASE_ADDR_MASK;
+ root &= SPTE_BASE_ADDR_MASK;
sp = to_shadow_page(root);
mmu_sync_children(vcpu, sp, true);
}
return false;
if (!is_shadow_present_pte(new))
return true;
- if ((old ^ new) & PT64_BASE_ADDR_MASK)
+ if ((old ^ new) & SPTE_BASE_ADDR_MASK)
return true;
old ^= shadow_nx_mask;
new ^= shadow_nx_mask;
- return (old & ~new & PT64_PERM_MASK) != 0;
+ return (old & ~new & SPTE_PERM_MASK) != 0;
}
static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
#define GUEST_PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
+#define PT64_LEVEL_BITS 9
+
+#define PT64_INDEX(address, level) __PT_INDEX(address, level, PT64_LEVEL_BITS)
+
#define PT64_LVL_ADDR_MASK(level) \
__PT_LVL_ADDR_MASK(GUEST_PT64_BASE_ADDR_MASK, level, PT64_LEVEL_BITS)
#define PT64_LVL_OFFSET_MASK(level) \
__PT_LVL_OFFSET_MASK(GUEST_PT64_BASE_ADDR_MASK, level, PT64_LEVEL_BITS)
+
+#define PT32_LEVEL_SHIFT(level) __PT_LEVEL_SHIFT(level, PT32_LEVEL_BITS)
+
+#define PT32_LVL_OFFSET_MASK(level) \
+ __PT_LVL_OFFSET_MASK(PT32_BASE_ADDR_MASK, level, PT32_LEVEL_BITS)
+
+#define PT32_INDEX(address, level) __PT_INDEX(address, level, PT32_LEVEL_BITS)
+
+#define PT32_BASE_ADDR_MASK PAGE_MASK
+
+#define PT32_LVL_ADDR_MASK(level) \
+ __PT_LVL_ADDR_MASK(PT32_BASE_ADDR_MASK, level, PT32_LEVEL_BITS)
+
#endif /* __KVM_X86_PAGING_H */
#define PT_LVL_ADDR_MASK(lvl) PT32_LVL_ADDR_MASK(lvl)
#define PT_LVL_OFFSET_MASK(lvl) PT32_LVL_OFFSET_MASK(lvl)
#define PT_INDEX(addr, level) PT32_INDEX(addr, level)
- #define PT_LEVEL_BITS PT32_LEVEL_BITS
+ #define PT_LEVEL_BITS 10
#define PT_MAX_FULL_LEVELS 2
#define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
WARN_ON(sp->role.level != PG_LEVEL_4K);
if (PTTYPE == 32)
- offset = sp->role.quadrant << PT64_LEVEL_BITS;
+ offset = sp->role.quadrant << SPTE_LEVEL_BITS;
return gfn_to_gpa(sp->gfn) + offset * sizeof(pt_element_t);
}
first_pte_gpa = FNAME(get_level1_sp_gpa)(sp);
- for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
+ for (i = 0; i < SPTE_ENT_PER_PAGE; i++) {
u64 *sptep, spte;
struct kvm_memory_slot *slot;
unsigned pte_access;
{
u64 new_spte;
- new_spte = old_spte & ~PT64_BASE_ADDR_MASK;
+ new_spte = old_spte & ~SPTE_BASE_ADDR_MASK;
new_spte |= (u64)new_pfn << PAGE_SHIFT;
new_spte &= ~PT_WRITABLE_MASK;
static_assert(SPTE_TDP_AD_ENABLED_MASK == 0);
#ifdef CONFIG_DYNAMIC_PHYSICAL_MASK
-#define PT64_BASE_ADDR_MASK (physical_mask & ~(u64)(PAGE_SIZE-1))
+#define SPTE_BASE_ADDR_MASK (physical_mask & ~(u64)(PAGE_SIZE-1))
#else
-#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
+#define SPTE_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
#endif
-#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \
+#define SPTE_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \
| shadow_x_mask | shadow_nx_mask | shadow_me_mask)
#define ACC_EXEC_MASK 1
#define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK)
/* The mask for the R/X bits in EPT PTEs */
-#define PT64_EPT_READABLE_MASK 0x1ull
-#define PT64_EPT_EXECUTABLE_MASK 0x4ull
+#define SPTE_EPT_READABLE_MASK 0x1ull
+#define SPTE_EPT_EXECUTABLE_MASK 0x4ull
-#define PT64_LEVEL_BITS 9
-
-#define PT64_LEVEL_SHIFT(level) __PT_LEVEL_SHIFT(level, PT64_LEVEL_BITS)
-
-#define PT64_INDEX(address, level) __PT_INDEX(address, level, PT64_LEVEL_BITS)
-
-#define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
+#define SPTE_LEVEL_BITS 9
+#define SPTE_LEVEL_SHIFT(level) __PT_LEVEL_SHIFT(level, SPTE_LEVEL_BITS)
+#define SPTE_INDEX(address, level) __PT_INDEX(address, level, SPTE_LEVEL_BITS)
+#define SPTE_ENT_PER_PAGE __PT_ENT_PER_PAGE(SPTE_LEVEL_BITS)
/*
* The mask/shift to use for saving the original R/X bits when marking the PTE
* restored only when a write is attempted to the page. This mask obviously
* must not overlap the A/D type mask.
*/
-#define SHADOW_ACC_TRACK_SAVED_BITS_MASK (PT64_EPT_READABLE_MASK | \
- PT64_EPT_EXECUTABLE_MASK)
+#define SHADOW_ACC_TRACK_SAVED_BITS_MASK (SPTE_EPT_READABLE_MASK | \
+ SPTE_EPT_EXECUTABLE_MASK)
#define SHADOW_ACC_TRACK_SAVED_BITS_SHIFT 54
#define SHADOW_ACC_TRACK_SAVED_MASK (SHADOW_ACC_TRACK_SAVED_BITS_MASK << \
SHADOW_ACC_TRACK_SAVED_BITS_SHIFT)
static inline kvm_pfn_t spte_to_pfn(u64 pte)
{
- return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
+ return (pte & SPTE_BASE_ADDR_MASK) >> PAGE_SHIFT;
}
static inline bool is_accessed_spte(u64 spte)
static void tdp_iter_refresh_sptep(struct tdp_iter *iter)
{
iter->sptep = iter->pt_path[iter->level - 1] +
- SHADOW_PT_INDEX(iter->gfn << PAGE_SHIFT, iter->level);
+ SPTE_INDEX(iter->gfn << PAGE_SHIFT, iter->level);
iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep);
}
* Check if the iterator is already at the end of the current page
* table.
*/
- if (SHADOW_PT_INDEX(iter->gfn << PAGE_SHIFT, iter->level) ==
- (PT64_ENT_PER_PAGE - 1))
+ if (SPTE_INDEX(iter->gfn << PAGE_SHIFT, iter->level) ==
+ (SPTE_ENT_PER_PAGE - 1))
return false;
iter->gfn += KVM_PAGES_PER_HPAGE(iter->level);
tdp_mmu_unlink_sp(kvm, sp, shared);
- for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
+ for (i = 0; i < SPTE_ENT_PER_PAGE; i++) {
tdp_ptep_t sptep = pt + i;
gfn_t gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level);
u64 old_spte;
* No need for atomics when writing to sp->spt since the page table has
* not been linked in yet and thus is not reachable from any other CPU.
*/
- for (i = 0; i < PT64_ENT_PER_PAGE; i++)
+ for (i = 0; i < SPTE_ENT_PER_PAGE; i++)
sp->spt[i] = make_huge_page_split_spte(huge_spte, level, i);
/*
* are overwriting from the page stats. But we have to manually update
* the page stats with the new present child pages.
*/
- kvm_update_page_stats(kvm, level - 1, PT64_ENT_PER_PAGE);
+ kvm_update_page_stats(kvm, level - 1, SPTE_ENT_PER_PAGE);
out:
trace_kvm_mmu_split_huge_page(iter->gfn, huge_spte, level, ret);
projects / kernel.git / commitdiff