summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm/mmu/mmu.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm/mmu/mmu.c')
-rw-r--r--arch/x86/kvm/mmu/mmu.c344
1 files changed, 313 insertions, 31 deletions
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index c57e181bba..982cf41e14 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -271,15 +271,11 @@ static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu,
static inline bool kvm_available_flush_remote_tlbs_range(void)
{
+#if IS_ENABLED(CONFIG_HYPERV)
return kvm_x86_ops.flush_remote_tlbs_range;
-}
-
-int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages)
-{
- if (!kvm_x86_ops.flush_remote_tlbs_range)
- return -EOPNOTSUPP;
-
- return static_call(kvm_x86_flush_remote_tlbs_range)(kvm, gfn, nr_pages);
+#else
+ return false;
+#endif
}
static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index);
@@ -795,16 +791,26 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn,
return &slot->arch.lpage_info[level - 2][idx];
}
+/*
+ * The most significant bit in disallow_lpage tracks whether or not memory
+ * attributes are mixed, i.e. not identical for all gfns at the current level.
+ * The lower order bits are used to refcount other cases where a hugepage is
+ * disallowed, e.g. if KVM has shadow a page table at the gfn.
+ */
+#define KVM_LPAGE_MIXED_FLAG BIT(31)
+
static void update_gfn_disallow_lpage_count(const struct kvm_memory_slot *slot,
gfn_t gfn, int count)
{
struct kvm_lpage_info *linfo;
- int i;
+ int old, i;
for (i = PG_LEVEL_2M; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) {
linfo = lpage_info_slot(gfn, slot, i);
+
+ old = linfo->disallow_lpage;
linfo->disallow_lpage += count;
- WARN_ON_ONCE(linfo->disallow_lpage < 0);
+ WARN_ON_ONCE((old ^ linfo->disallow_lpage) & KVM_LPAGE_MIXED_FLAG);
}
}
@@ -987,7 +993,7 @@ static void pte_list_desc_remove_entry(struct kvm *kvm,
/*
* The head descriptor is empty. If there are no tail descriptors,
- * nullify the rmap head to mark the list as emtpy, else point the rmap
+ * nullify the rmap head to mark the list as empty, else point the rmap
* head at the next descriptor, i.e. the new head.
*/
if (!head_desc->more)
@@ -1382,7 +1388,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
gfn_t end = slot->base_gfn + gfn_offset + __fls(mask);
if (READ_ONCE(eager_page_split))
- kvm_mmu_try_split_huge_pages(kvm, slot, start, end, PG_LEVEL_4K);
+ kvm_mmu_try_split_huge_pages(kvm, slot, start, end + 1, PG_LEVEL_4K);
kvm_mmu_slot_gfn_write_protect(kvm, slot, start, PG_LEVEL_2M);
@@ -2840,9 +2846,9 @@ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot,
/*
* Recheck after taking the spinlock, a different vCPU
* may have since marked the page unsync. A false
- * positive on the unprotected check above is not
+ * negative on the unprotected check above is not
* possible as clearing sp->unsync _must_ hold mmu_lock
- * for write, i.e. unsync cannot transition from 0->1
+ * for write, i.e. unsync cannot transition from 1->0
* while this CPU holds mmu_lock for read (or write).
*/
if (READ_ONCE(sp->unsync))
@@ -3056,7 +3062,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
*
* There are several ways to safely use this helper:
*
- * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before
+ * - Check mmu_invalidate_retry_gfn() after grabbing the mapping level, before
* consuming it. In this case, mmu_lock doesn't need to be held during the
* lookup, but it does need to be held while checking the MMU notifier.
*
@@ -3120,7 +3126,7 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
if (pud_none(pud) || !pud_present(pud))
goto out;
- if (pud_large(pud)) {
+ if (pud_leaf(pud)) {
level = PG_LEVEL_1G;
goto out;
}
@@ -3137,9 +3143,9 @@ out:
return level;
}
-int kvm_mmu_max_mapping_level(struct kvm *kvm,
- const struct kvm_memory_slot *slot, gfn_t gfn,
- int max_level)
+static int __kvm_mmu_max_mapping_level(struct kvm *kvm,
+ const struct kvm_memory_slot *slot,
+ gfn_t gfn, int max_level, bool is_private)
{
struct kvm_lpage_info *linfo;
int host_level;
@@ -3151,6 +3157,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
break;
}
+ if (is_private)
+ return max_level;
+
if (max_level == PG_LEVEL_4K)
return PG_LEVEL_4K;
@@ -3158,6 +3167,16 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
return min(host_level, max_level);
}
+int kvm_mmu_max_mapping_level(struct kvm *kvm,
+ const struct kvm_memory_slot *slot, gfn_t gfn,
+ int max_level)
+{
+ bool is_private = kvm_slot_can_be_private(slot) &&
+ kvm_mem_is_private(kvm, gfn);
+
+ return __kvm_mmu_max_mapping_level(kvm, slot, gfn, max_level, is_private);
+}
+
void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
{
struct kvm_memory_slot *slot = fault->slot;
@@ -3178,8 +3197,9 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
* Enforce the iTLB multihit workaround after capturing the requested
* level, which will be used to do precise, accurate accounting.
*/
- fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot,
- fault->gfn, fault->max_level);
+ fault->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot,
+ fault->gfn, fault->max_level,
+ fault->is_private);
if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
return;
@@ -3556,7 +3576,7 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
return;
if (is_tdp_mmu_page(sp))
- kvm_tdp_mmu_put_root(kvm, sp, false);
+ kvm_tdp_mmu_put_root(kvm, sp);
else if (!--sp->root_count && sp->role.invalid)
kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
@@ -3739,7 +3759,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm)
kvm_page_track_write_tracking_enabled(kvm))
goto out_success;
- for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+ for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
slots = __kvm_memslots(kvm, i);
kvm_for_each_memslot(slot, bkt, slots) {
/*
@@ -3782,7 +3802,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
hpa_t root;
root_pgd = kvm_mmu_get_guest_pgd(vcpu, mmu);
- root_gfn = root_pgd >> PAGE_SHIFT;
+ root_gfn = (root_pgd & __PT_BASE_ADDR_MASK) >> PAGE_SHIFT;
if (!kvm_vcpu_is_visible_gfn(vcpu, root_gfn)) {
mmu->root.hpa = kvm_mmu_get_dummy_root();
@@ -4259,6 +4279,55 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL);
}
+static inline u8 kvm_max_level_for_order(int order)
+{
+ BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G);
+
+ KVM_MMU_WARN_ON(order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G) &&
+ order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M) &&
+ order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K));
+
+ if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G))
+ return PG_LEVEL_1G;
+
+ if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
+ return PG_LEVEL_2M;
+
+ return PG_LEVEL_4K;
+}
+
+static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
+ struct kvm_page_fault *fault)
+{
+ kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT,
+ PAGE_SIZE, fault->write, fault->exec,
+ fault->is_private);
+}
+
+static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
+ struct kvm_page_fault *fault)
+{
+ int max_order, r;
+
+ if (!kvm_slot_can_be_private(fault->slot)) {
+ kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+ return -EFAULT;
+ }
+
+ r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn,
+ &max_order);
+ if (r) {
+ kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+ return r;
+ }
+
+ fault->max_level = min(kvm_max_level_for_order(max_order),
+ fault->max_level);
+ fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY);
+
+ return RET_PF_CONTINUE;
+}
+
static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
{
struct kvm_memory_slot *slot = fault->slot;
@@ -4291,6 +4360,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
return RET_PF_EMULATE;
}
+ if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
+ kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+ return -EFAULT;
+ }
+
+ if (fault->is_private)
+ return kvm_faultin_pfn_private(vcpu, fault);
+
async = false;
fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
fault->write, &fault->map_writable,
@@ -4328,6 +4405,31 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq;
smp_rmb();
+ /*
+ * Check for a relevant mmu_notifier invalidation event before getting
+ * the pfn from the primary MMU, and before acquiring mmu_lock.
+ *
+ * For mmu_lock, if there is an in-progress invalidation and the kernel
+ * allows preemption, the invalidation task may drop mmu_lock and yield
+ * in response to mmu_lock being contended, which is *very* counter-
+ * productive as this vCPU can't actually make forward progress until
+ * the invalidation completes.
+ *
+ * Retrying now can also avoid unnessary lock contention in the primary
+ * MMU, as the primary MMU doesn't necessarily hold a single lock for
+ * the duration of the invalidation, i.e. faulting in a conflicting pfn
+ * can cause the invalidation to take longer by holding locks that are
+ * needed to complete the invalidation.
+ *
+ * Do the pre-check even for non-preemtible kernels, i.e. even if KVM
+ * will never yield mmu_lock in response to contention, as this vCPU is
+ * *guaranteed* to need to retry, i.e. waiting until mmu_lock is held
+ * to detect retry guarantees the worst case latency for the vCPU.
+ */
+ if (fault->slot &&
+ mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn))
+ return RET_PF_RETRY;
+
ret = __kvm_faultin_pfn(vcpu, fault);
if (ret != RET_PF_CONTINUE)
return ret;
@@ -4338,6 +4440,18 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
if (unlikely(!fault->slot))
return kvm_handle_noslot_fault(vcpu, fault, access);
+ /*
+ * Check again for a relevant mmu_notifier invalidation event purely to
+ * avoid contending mmu_lock. Most invalidations will be detected by
+ * the previous check, but checking is extremely cheap relative to the
+ * overall cost of failing to detect the invalidation until after
+ * mmu_lock is acquired.
+ */
+ if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) {
+ kvm_release_pfn_clean(fault->pfn);
+ return RET_PF_RETRY;
+ }
+
return RET_PF_CONTINUE;
}
@@ -4365,8 +4479,13 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
if (!sp && kvm_test_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu))
return true;
+ /*
+ * Check for a relevant mmu_notifier invalidation event one last time
+ * now that mmu_lock is held, as the "unsafe" checks performed without
+ * holding mmu_lock can get false negatives.
+ */
return fault->slot &&
- mmu_invalidate_retry_hva(vcpu->kvm, fault->mmu_seq, fault->hva);
+ mmu_invalidate_retry_gfn(vcpu->kvm, fault->mmu_seq, fault->gfn);
}
static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
@@ -4803,7 +4922,7 @@ static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu,
context->cpu_role.base.level, is_efer_nx(context),
guest_can_use(vcpu, X86_FEATURE_GBPAGES),
is_cr4_pse(context),
- guest_cpuid_is_amd_or_hygon(vcpu));
+ guest_cpuid_is_amd_compatible(vcpu));
}
static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
@@ -6228,7 +6347,7 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e
if (!kvm_memslots_have_rmaps(kvm))
return flush;
- for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+ for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
slots = __kvm_memslots(kvm, i);
kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) {
@@ -6260,7 +6379,9 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
write_lock(&kvm->mmu_lock);
- kvm_mmu_invalidate_begin(kvm, 0, -1ul);
+ kvm_mmu_invalidate_begin(kvm);
+
+ kvm_mmu_invalidate_range_add(kvm, gfn_start, gfn_end);
flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end);
@@ -6270,7 +6391,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
if (flush)
kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start);
- kvm_mmu_invalidate_end(kvm, 0, -1ul);
+ kvm_mmu_invalidate_end(kvm);
write_unlock(&kvm->mmu_lock);
}
@@ -6544,7 +6665,7 @@ void kvm_mmu_try_split_huge_pages(struct kvm *kvm,
kvm_tdp_mmu_try_split_huge_pages(kvm, memslot, start, end, target_level, false);
/*
- * A TLB flush is unnecessary at this point for the same resons as in
+ * A TLB flush is unnecessary at this point for the same reasons as in
* kvm_mmu_slot_try_split_huge_pages().
*/
}
@@ -6723,7 +6844,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen)
* modifier prior to checking for a wrap of the MMIO generation so
* that a wrap in any address space is detected.
*/
- gen &= ~((u64)KVM_ADDRESS_SPACE_NUM - 1);
+ gen &= ~((u64)kvm_arch_nr_memslot_as_ids(kvm) - 1);
/*
* The very rare case: if the MMIO generation number has wrapped,
@@ -7176,3 +7297,164 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
if (kvm->arch.nx_huge_page_recovery_thread)
kthread_stop(kvm->arch.nx_huge_page_recovery_thread);
}
+
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
+ struct kvm_gfn_range *range)
+{
+ /*
+ * Zap SPTEs even if the slot can't be mapped PRIVATE. KVM x86 only
+ * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM
+ * can simply ignore such slots. But if userspace is making memory
+ * PRIVATE, then KVM must prevent the guest from accessing the memory
+ * as shared. And if userspace is making memory SHARED and this point
+ * is reached, then at least one page within the range was previously
+ * PRIVATE, i.e. the slot's possible hugepage ranges are changing.
+ * Zapping SPTEs in this case ensures KVM will reassess whether or not
+ * a hugepage can be used for affected ranges.
+ */
+ if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
+ return false;
+
+ return kvm_unmap_gfn_range(kvm, range);
+}
+
+static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+ int level)
+{
+ return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+ int level)
+{
+ lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+ int level)
+{
+ lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG;
+}
+
+static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot,
+ gfn_t gfn, int level, unsigned long attrs)
+{
+ const unsigned long start = gfn;
+ const unsigned long end = start + KVM_PAGES_PER_HPAGE(level);
+
+ if (level == PG_LEVEL_2M)
+ return kvm_range_has_memory_attributes(kvm, start, end, attrs);
+
+ for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) {
+ if (hugepage_test_mixed(slot, gfn, level - 1) ||
+ attrs != kvm_get_memory_attributes(kvm, gfn))
+ return false;
+ }
+ return true;
+}
+
+bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
+ struct kvm_gfn_range *range)
+{
+ unsigned long attrs = range->arg.attributes;
+ struct kvm_memory_slot *slot = range->slot;
+ int level;
+
+ lockdep_assert_held_write(&kvm->mmu_lock);
+ lockdep_assert_held(&kvm->slots_lock);
+
+ /*
+ * Calculate which ranges can be mapped with hugepages even if the slot
+ * can't map memory PRIVATE. KVM mustn't create a SHARED hugepage over
+ * a range that has PRIVATE GFNs, and conversely converting a range to
+ * SHARED may now allow hugepages.
+ */
+ if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
+ return false;
+
+ /*
+ * The sequence matters here: upper levels consume the result of lower
+ * level's scanning.
+ */
+ for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+ gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level);
+ gfn_t gfn = gfn_round_for_level(range->start, level);
+
+ /* Process the head page if it straddles the range. */
+ if (gfn != range->start || gfn + nr_pages > range->end) {
+ /*
+ * Skip mixed tracking if the aligned gfn isn't covered
+ * by the memslot, KVM can't use a hugepage due to the
+ * misaligned address regardless of memory attributes.
+ */
+ if (gfn >= slot->base_gfn &&
+ gfn + nr_pages <= slot->base_gfn + slot->npages) {
+ if (hugepage_has_attrs(kvm, slot, gfn, level, attrs))
+ hugepage_clear_mixed(slot, gfn, level);
+ else
+ hugepage_set_mixed(slot, gfn, level);
+ }
+ gfn += nr_pages;
+ }
+
+ /*
+ * Pages entirely covered by the range are guaranteed to have
+ * only the attributes which were just set.
+ */
+ for ( ; gfn + nr_pages <= range->end; gfn += nr_pages)
+ hugepage_clear_mixed(slot, gfn, level);
+
+ /*
+ * Process the last tail page if it straddles the range and is
+ * contained by the memslot. Like the head page, KVM can't
+ * create a hugepage if the slot size is misaligned.
+ */
+ if (gfn < range->end &&
+ (gfn + nr_pages) <= (slot->base_gfn + slot->npages)) {
+ if (hugepage_has_attrs(kvm, slot, gfn, level, attrs))
+ hugepage_clear_mixed(slot, gfn, level);
+ else
+ hugepage_set_mixed(slot, gfn, level);
+ }
+ }
+ return false;
+}
+
+void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm,
+ struct kvm_memory_slot *slot)
+{
+ int level;
+
+ if (!kvm_arch_has_private_mem(kvm))
+ return;
+
+ for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+ /*
+ * Don't bother tracking mixed attributes for pages that can't
+ * be huge due to alignment, i.e. process only pages that are
+ * entirely contained by the memslot.
+ */
+ gfn_t end = gfn_round_for_level(slot->base_gfn + slot->npages, level);
+ gfn_t start = gfn_round_for_level(slot->base_gfn, level);
+ gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level);
+ gfn_t gfn;
+
+ if (start < slot->base_gfn)
+ start += nr_pages;
+
+ /*
+ * Unlike setting attributes, every potential hugepage needs to
+ * be manually checked as the attributes may already be mixed.
+ */
+ for (gfn = start; gfn < end; gfn += nr_pages) {
+ unsigned long attrs = kvm_get_memory_attributes(kvm, gfn);
+
+ if (hugepage_has_attrs(kvm, slot, gfn, level, attrs))
+ hugepage_clear_mixed(slot, gfn, level);
+ else
+ hugepage_set_mixed(slot, gfn, level);
+ }
+ }
+}
+#endif