summaryrefslogtreecommitdiff
path: root/arch/x86/kvm/mmu.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm/mmu.c')
-rw-r--r--arch/x86/kvm/mmu.c116
1 files changed, 71 insertions, 45 deletions
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 69088a1ba509..7d85bcae3332 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -818,14 +818,11 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
kvm->arch.indirect_shadow_pages--;
}
-static int has_wrprotected_page(struct kvm_vcpu *vcpu,
- gfn_t gfn,
- int level)
+static int __has_wrprotected_page(gfn_t gfn, int level,
+ struct kvm_memory_slot *slot)
{
- struct kvm_memory_slot *slot;
struct kvm_lpage_info *linfo;
- slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
if (slot) {
linfo = lpage_info_slot(gfn, slot, level);
return linfo->write_count;
@@ -834,6 +831,14 @@ static int has_wrprotected_page(struct kvm_vcpu *vcpu,
return 1;
}
+static int has_wrprotected_page(struct kvm_vcpu *vcpu, gfn_t gfn, int level)
+{
+ struct kvm_memory_slot *slot;
+
+ slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+ return __has_wrprotected_page(gfn, level, slot);
+}
+
static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
{
unsigned long page_size;
@@ -851,6 +856,17 @@ static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
return ret;
}
+static inline bool memslot_valid_for_gpte(struct kvm_memory_slot *slot,
+ bool no_dirty_log)
+{
+ if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
+ return false;
+ if (no_dirty_log && slot->dirty_bitmap)
+ return false;
+
+ return true;
+}
+
static struct kvm_memory_slot *
gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
bool no_dirty_log)
@@ -858,21 +874,25 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
struct kvm_memory_slot *slot;
slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
- if (!slot || slot->flags & KVM_MEMSLOT_INVALID ||
- (no_dirty_log && slot->dirty_bitmap))
+ if (!memslot_valid_for_gpte(slot, no_dirty_log))
slot = NULL;
return slot;
}
-static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn)
-{
- return !gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true);
-}
-
-static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
+static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn,
+ bool *force_pt_level)
{
int host_level, level, max_level;
+ struct kvm_memory_slot *slot;
+
+ if (unlikely(*force_pt_level))
+ return PT_PAGE_TABLE_LEVEL;
+
+ slot = kvm_vcpu_gfn_to_memslot(vcpu, large_gfn);
+ *force_pt_level = !memslot_valid_for_gpte(slot, true);
+ if (unlikely(*force_pt_level))
+ return PT_PAGE_TABLE_LEVEL;
host_level = host_mapping_level(vcpu->kvm, large_gfn);
@@ -882,7 +902,7 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
max_level = min(kvm_x86_ops->get_lpage_level(), host_level);
for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level)
- if (has_wrprotected_page(vcpu, large_gfn, level))
+ if (__has_wrprotected_page(large_gfn, level, slot))
break;
return level - 1;
@@ -2962,14 +2982,13 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
{
int r;
int level;
- int force_pt_level;
+ bool force_pt_level = false;
pfn_t pfn;
unsigned long mmu_seq;
bool map_writable, write = error_code & PFERR_WRITE_MASK;
- force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn);
+ level = mapping_level(vcpu, gfn, &force_pt_level);
if (likely(!force_pt_level)) {
- level = mapping_level(vcpu, gfn);
/*
* This path builds a PAE pagetable - so we can map
* 2mb pages at maximum. Therefore check if the level
@@ -2979,8 +2998,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
level = PT_DIRECTORY_LEVEL;
gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
- } else
- level = PT_PAGE_TABLE_LEVEL;
+ }
if (fast_page_fault(vcpu, v, level, error_code))
return 0;
@@ -3322,7 +3340,7 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
break;
reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte,
- leaf);
+ iterator.level);
}
walk_shadow_page_lockless_end(vcpu);
@@ -3427,7 +3445,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
static bool can_do_async_pf(struct kvm_vcpu *vcpu)
{
- if (unlikely(!irqchip_in_kernel(vcpu->kvm) ||
+ if (unlikely(!lapic_in_kernel(vcpu) ||
kvm_event_needs_reinjection(vcpu)))
return false;
@@ -3476,7 +3494,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
pfn_t pfn;
int r;
int level;
- int force_pt_level;
+ bool force_pt_level;
gfn_t gfn = gpa >> PAGE_SHIFT;
unsigned long mmu_seq;
int write = error_code & PFERR_WRITE_MASK;
@@ -3495,20 +3513,15 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
if (r)
return r;
- if (mapping_level_dirty_bitmap(vcpu, gfn) ||
- !check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL))
- force_pt_level = 1;
- else
- force_pt_level = 0;
-
+ force_pt_level = !check_hugepage_cache_consistency(vcpu, gfn,
+ PT_DIRECTORY_LEVEL);
+ level = mapping_level(vcpu, gfn, &force_pt_level);
if (likely(!force_pt_level)) {
- level = mapping_level(vcpu, gfn);
if (level > PT_DIRECTORY_LEVEL &&
!check_hugepage_cache_consistency(vcpu, gfn, level))
level = PT_DIRECTORY_LEVEL;
gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
- } else
- level = PT_PAGE_TABLE_LEVEL;
+ }
if (fast_page_fault(vcpu, gpa, level, error_code))
return 0;
@@ -3614,7 +3627,7 @@ static void
__reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
struct rsvd_bits_validate *rsvd_check,
int maxphyaddr, int level, bool nx, bool gbpages,
- bool pse)
+ bool pse, bool amd)
{
u64 exb_bit_rsvd = 0;
u64 gbpages_bit_rsvd = 0;
@@ -3631,7 +3644,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
* Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for
* leaf entries) on AMD CPUs only.
*/
- if (guest_cpuid_is_amd(vcpu))
+ if (amd)
nonleaf_bit8_rsvd = rsvd_bits(8, 8);
switch (level) {
@@ -3699,14 +3712,14 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
__reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check,
cpuid_maxphyaddr(vcpu), context->root_level,
context->nx, guest_cpuid_has_gbpages(vcpu),
- is_pse(vcpu));
+ is_pse(vcpu), guest_cpuid_is_amd(vcpu));
}
static void
__reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
int maxphyaddr, bool execonly)
{
- int pte;
+ u64 bad_mt_xwr;
rsvd_check->rsvd_bits_mask[0][3] =
rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7);
@@ -3724,14 +3737,16 @@ __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 20);
rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0];
- for (pte = 0; pte < 64; pte++) {
- int rwx_bits = pte & 7;
- int mt = pte >> 3;
- if (mt == 0x2 || mt == 0x3 || mt == 0x7 ||
- rwx_bits == 0x2 || rwx_bits == 0x6 ||
- (rwx_bits == 0x4 && !execonly))
- rsvd_check->bad_mt_xwr |= (1ull << pte);
+ bad_mt_xwr = 0xFFull << (2 * 8); /* bits 3..5 must not be 2 */
+ bad_mt_xwr |= 0xFFull << (3 * 8); /* bits 3..5 must not be 3 */
+ bad_mt_xwr |= 0xFFull << (7 * 8); /* bits 3..5 must not be 7 */
+ bad_mt_xwr |= REPEAT_BYTE(1ull << 2); /* bits 0..2 must not be 010 */
+ bad_mt_xwr |= REPEAT_BYTE(1ull << 6); /* bits 0..2 must not be 110 */
+ if (!execonly) {
+ /* bits 0..2 must not be 100 unless VMX capabilities allow it */
+ bad_mt_xwr |= REPEAT_BYTE(1ull << 4);
}
+ rsvd_check->bad_mt_xwr = bad_mt_xwr;
}
static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
@@ -3749,13 +3764,24 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
void
reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
{
+ /*
+ * Passing "true" to the last argument is okay; it adds a check
+ * on bit 8 of the SPTEs which KVM doesn't use anyway.
+ */
__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
boot_cpu_data.x86_phys_bits,
context->shadow_root_level, context->nx,
- guest_cpuid_has_gbpages(vcpu), is_pse(vcpu));
+ guest_cpuid_has_gbpages(vcpu), is_pse(vcpu),
+ true);
}
EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask);
+static inline bool boot_cpu_is_amd(void)
+{
+ WARN_ON_ONCE(!tdp_enabled);
+ return shadow_x_mask == 0;
+}
+
/*
* the direct page table on host, use as much mmu features as
* possible, however, kvm currently does not do execution-protection.
@@ -3764,11 +3790,11 @@ static void
reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
struct kvm_mmu *context)
{
- if (guest_cpuid_is_amd(vcpu))
+ if (boot_cpu_is_amd())
__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
boot_cpu_data.x86_phys_bits,
context->shadow_root_level, false,
- cpu_has_gbpages, true);
+ cpu_has_gbpages, true, true);
else
__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
boot_cpu_data.x86_phys_bits,