1 files changed, 93 insertions, 69 deletions

diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index 8f7eb3ad88fc..cfce03d8f123 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -24,6 +24,8 @@ static bool __ro_after_init allow_mmio_caching;
 module_param_named(mmio_caching, enable_mmio_caching, bool, 0444);
 EXPORT_SYMBOL_GPL(enable_mmio_caching);
 
+bool __read_mostly kvm_ad_enabled;
+
 u64 __read_mostly shadow_host_writable_mask;
 u64 __read_mostly shadow_mmu_writable_mask;
 u64 __read_mostly shadow_nx_mask;
@@ -35,7 +37,6 @@ u64 __read_mostly shadow_mmio_value;
 u64 __read_mostly shadow_mmio_mask;
 u64 __read_mostly shadow_mmio_access_mask;
 u64 __read_mostly shadow_present_mask;
-u64 __read_mostly shadow_memtype_mask;
 u64 __read_mostly shadow_me_value;
 u64 __read_mostly shadow_me_mask;
 u64 __read_mostly shadow_acc_track_mask;
@@ -94,8 +95,6 @@ u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access)
 	u64 spte = generation_mmio_spte_mask(gen);
 	u64 gpa = gfn << PAGE_SHIFT;
 
-	WARN_ON_ONCE(!vcpu->kvm->arch.shadow_mmio_value);
-
 	access &= shadow_mmio_access_mask;
 	spte |= vcpu->kvm->arch.shadow_mmio_value | access;
 	spte |= gpa | shadow_nonpresent_or_rsvd_mask;
@@ -127,37 +126,38 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn)
 }
 
 /*
- * Returns true if the SPTE has bits that may be set without holding mmu_lock.
- * The caller is responsible for checking if the SPTE is shadow-present, and
- * for determining whether or not the caller cares about non-leaf SPTEs.
+ * Returns true if the SPTE needs to be updated atomically due to having bits
+ * that may be changed without holding mmu_lock, and for which KVM must not
+ * lose information.  E.g. KVM must not drop Dirty bit information.  The caller
+ * is responsible for checking if the SPTE is shadow-present, and for
+ * determining whether or not the caller cares about non-leaf SPTEs.
  */
-bool spte_has_volatile_bits(u64 spte)
+bool spte_needs_atomic_update(u64 spte)
 {
-	/*
-	 * Always atomically update spte if it can be updated
-	 * out of mmu-lock, it can ensure dirty bit is not lost,
-	 * also, it can help us to get a stable is_writable_pte()
-	 * to ensure tlb flush is not missed.
-	 */
+	/* SPTEs can be made Writable bit by KVM's fast page fault handler. */
 	if (!is_writable_pte(spte) && is_mmu_writable_spte(spte))
 		return true;
 
-	if (is_access_track_spte(spte))
+	/*
+	 * A/D-disabled SPTEs can be access-tracked by aging, and access-tracked
+	 * SPTEs can be restored by KVM's fast page fault handler.
+	 */
+	if (!spte_ad_enabled(spte))
 		return true;
 
-	if (spte_ad_enabled(spte)) {
-		if (!(spte & shadow_accessed_mask) ||
-		    (is_writable_pte(spte) && !(spte & shadow_dirty_mask)))
-			return true;
-	}
-
-	return false;
+	/*
+	 * Dirty and Accessed bits can be set by the CPU.  Ignore the Accessed
+	 * bit, as KVM tolerates false negatives/positives, e.g. KVM doesn't
+	 * invalidate TLBs when aging SPTEs, and so it's safe to clobber the
+	 * Accessed bit (and rare in practice).
+	 */
+	return is_writable_pte(spte) && !(spte & shadow_dirty_mask);
 }
 
 bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	       const struct kvm_memory_slot *slot,
 	       unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn,
-	       u64 old_spte, bool prefetch, bool can_unsync,
+	       u64 old_spte, bool prefetch, bool synchronizing,
 	       bool host_writable, u64 *new_spte)
 {
 	int level = sp->role.level;
@@ -174,12 +174,12 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 
 	if (sp->role.ad_disabled)
 		spte |= SPTE_TDP_AD_DISABLED;
-	else if (kvm_mmu_page_ad_need_write_protect(sp))
+	else if (kvm_mmu_page_ad_need_write_protect(vcpu->kvm, sp))
 		spte |= SPTE_TDP_AD_WRPROT_ONLY;
 
 	spte |= shadow_present_mask;
-	if (!prefetch)
-		spte |= spte_shadow_accessed_mask(spte);
+	if (!prefetch || synchronizing)
+		spte |= shadow_accessed_mask;
 
 	/*
 	 * For simplicity, enforce the NX huge page mitigation even if not
@@ -209,9 +209,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	if (level > PG_LEVEL_4K)
 		spte |= PT_PAGE_SIZE_MASK;
 
-	if (shadow_memtype_mask)
-		spte |= kvm_x86_call(get_mt_mask)(vcpu, gfn,
-						  kvm_is_mmio_pfn(pfn));
+	spte |= kvm_x86_call(get_mt_mask)(vcpu, gfn, kvm_is_mmio_pfn(pfn));
 	if (host_writable)
 		spte |= shadow_host_writable_mask;
 	else
@@ -223,41 +221,39 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	spte |= (u64)pfn << PAGE_SHIFT;
 
 	if (pte_access & ACC_WRITE_MASK) {
-		spte |= PT_WRITABLE_MASK | shadow_mmu_writable_mask;
-
-		/*
-		 * Optimization: for pte sync, if spte was writable the hash
-		 * lookup is unnecessary (and expensive). Write protection
-		 * is responsibility of kvm_mmu_get_page / kvm_mmu_sync_roots.
-		 * Same reasoning can be applied to dirty page accounting.
-		 */
-		if (is_writable_pte(old_spte))
-			goto out;
-
 		/*
 		 * Unsync shadow pages that are reachable by the new, writable
 		 * SPTE.  Write-protect the SPTE if the page can't be unsync'd,
 		 * e.g. it's write-tracked (upper-level SPs) or has one or more
 		 * shadow pages and unsync'ing pages is not allowed.
+		 *
+		 * When overwriting an existing leaf SPTE, and the old SPTE was
+		 * writable, skip trying to unsync shadow pages as any relevant
+		 * shadow pages must already be unsync, i.e. the hash lookup is
+		 * unnecessary (and expensive).  Note, this relies on KVM not
+		 * changing PFNs without first zapping the old SPTE, which is
+		 * guaranteed by both the shadow MMU and the TDP MMU.
 		 */
-		if (mmu_try_to_unsync_pages(vcpu->kvm, slot, gfn, can_unsync, prefetch)) {
+		if ((!is_last_spte(old_spte, level) || !is_writable_pte(old_spte)) &&
+		    mmu_try_to_unsync_pages(vcpu->kvm, slot, gfn, synchronizing, prefetch))
 			wrprot = true;
-			pte_access &= ~ACC_WRITE_MASK;
-			spte &= ~(PT_WRITABLE_MASK | shadow_mmu_writable_mask);
-		}
+		else
+			spte |= PT_WRITABLE_MASK | shadow_mmu_writable_mask |
+				shadow_dirty_mask;
 	}
 
-	if (pte_access & ACC_WRITE_MASK)
-		spte |= spte_shadow_dirty_mask(spte);
-
-out:
-	if (prefetch)
+	if (prefetch && !synchronizing)
 		spte = mark_spte_for_access_track(spte);
 
 	WARN_ONCE(is_rsvd_spte(&vcpu->arch.mmu->shadow_zero_check, spte, level),
 		  "spte = 0x%llx, level = %d, rsvd bits = 0x%llx", spte, level,
 		  get_rsvd_bits(&vcpu->arch.mmu->shadow_zero_check, spte, level));
 
+	/*
+	 * Mark the memslot dirty *after* modifying it for access tracking.
+	 * Unlike folios, memslots can be safely marked dirty out of mmu_lock,
+	 * i.e. in the fast page fault handler.
+	 */
 	if ((spte & PT_WRITABLE_MASK) && kvm_slot_dirty_track_enabled(slot)) {
 		/* Enforced by kvm_mmu_hugepage_adjust. */
 		WARN_ON_ONCE(level > PG_LEVEL_4K);
@@ -268,15 +264,15 @@ out:
 	return wrprot;
 }
 
-static u64 make_spte_executable(u64 spte)
+static u64 modify_spte_protections(u64 spte, u64 set, u64 clear)
 {
 	bool is_access_track = is_access_track_spte(spte);
 
 	if (is_access_track)
 		spte = restore_acc_track_spte(spte);
 
-	spte &= ~shadow_nx_mask;
-	spte |= shadow_x_mask;
+	KVM_MMU_WARN_ON(set & clear);
+	spte = (spte | set) & ~clear;
 
 	if (is_access_track)
 		spte = mark_spte_for_access_track(spte);
@@ -284,6 +280,16 @@ static u64 make_spte_executable(u64 spte)
 	return spte;
 }
 
+static u64 make_spte_executable(u64 spte)
+{
+	return modify_spte_protections(spte, shadow_x_mask, shadow_nx_mask);
+}
+
+static u64 make_spte_nonexecutable(u64 spte)
+{
+	return modify_spte_protections(spte, shadow_nx_mask, shadow_x_mask);
+}
+
 /*
  * Construct an SPTE that maps a sub-page of the given huge page SPTE where
  * `index` identifies which sub-page.
@@ -291,8 +297,8 @@ static u64 make_spte_executable(u64 spte)
  * This is used during huge page splitting to build the SPTEs that make up the
  * new page table.
  */
-u64 make_huge_page_split_spte(struct kvm *kvm, u64 huge_spte,
-			      union kvm_mmu_page_role role, int index)
+u64 make_small_spte(struct kvm *kvm, u64 huge_spte,
+		    union kvm_mmu_page_role role, int index)
 {
 	u64 child_spte = huge_spte;
 
@@ -320,6 +326,26 @@ u64 make_huge_page_split_spte(struct kvm *kvm, u64 huge_spte,
 	return child_spte;
 }
 
+u64 make_huge_spte(struct kvm *kvm, u64 small_spte, int level)
+{
+	u64 huge_spte;
+
+	KVM_BUG_ON(!is_shadow_present_pte(small_spte) || level == PG_LEVEL_4K, kvm);
+
+	huge_spte = small_spte | PT_PAGE_SIZE_MASK;
+
+	/*
+	 * huge_spte already has the address of the sub-page being collapsed
+	 * from small_spte, so just clear the lower address bits to create the
+	 * huge page address.
+	 */
+	huge_spte &= KVM_HPAGE_MASK(level) | ~PAGE_MASK;
+
+	if (is_nx_huge_page_enabled(kvm))
+		huge_spte = make_spte_nonexecutable(huge_spte);
+
+	return huge_spte;
+}
 
 u64 make_nonleaf_spte(u64 *child_pt, bool ad_disabled)
 {
@@ -352,7 +378,7 @@ u64 mark_spte_for_access_track(u64 spte)
 
 	spte |= (spte & SHADOW_ACC_TRACK_SAVED_BITS_MASK) <<
 		SHADOW_ACC_TRACK_SAVED_BITS_SHIFT;
-	spte &= ~shadow_acc_track_mask;
+	spte &= ~(shadow_acc_track_mask | shadow_accessed_mask);
 
 	return spte;
 }
@@ -409,6 +435,12 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);
 
+void kvm_mmu_set_mmio_spte_value(struct kvm *kvm, u64 mmio_value)
+{
+	kvm->arch.shadow_mmio_value = mmio_value;
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_value);
+
 void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask)
 {
 	/* shadow_me_value must be a subset of shadow_me_mask */
@@ -422,21 +454,17 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_me_spte_mask);
 
 void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only)
 {
+	kvm_ad_enabled		= has_ad_bits;
+
 	shadow_user_mask	= VMX_EPT_READABLE_MASK;
-	shadow_accessed_mask	= has_ad_bits ? VMX_EPT_ACCESS_BIT : 0ull;
-	shadow_dirty_mask	= has_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull;
+	shadow_accessed_mask	= VMX_EPT_ACCESS_BIT;
+	shadow_dirty_mask	= VMX_EPT_DIRTY_BIT;
 	shadow_nx_mask		= 0ull;
 	shadow_x_mask		= VMX_EPT_EXECUTABLE_MASK;
 	/* VMX_EPT_SUPPRESS_VE_BIT is needed for W or X violation. */
 	shadow_present_mask	=
 		(has_exec_only ? 0ull : VMX_EPT_READABLE_MASK) | VMX_EPT_SUPPRESS_VE_BIT;
-	/*
-	 * EPT overrides the host MTRRs, and so KVM must program the desired
-	 * memtype directly into the SPTEs.  Note, this mask is just the mask
-	 * of all bits that factor into the memtype, the actual memtype must be
-	 * dynamically calculated, e.g. to ensure host MMIO is mapped UC.
-	 */
-	shadow_memtype_mask	= VMX_EPT_MT_MASK | VMX_EPT_IPAT_BIT;
+
 	shadow_acc_track_mask	= VMX_EPT_RWX_MASK;
 	shadow_host_writable_mask = EPT_SPTE_HOST_WRITABLE;
 	shadow_mmu_writable_mask  = EPT_SPTE_MMU_WRITABLE;
@@ -455,6 +483,8 @@ void kvm_mmu_reset_all_pte_masks(void)
 	u8 low_phys_bits;
 	u64 mask;
 
+	kvm_ad_enabled = true;
+
 	/*
 	 * If the CPU has 46 or less physical address bits, then set an
 	 * appropriate mask to guard against L1TF attacks. Otherwise, it is
@@ -486,12 +516,6 @@ void kvm_mmu_reset_all_pte_masks(void)
 	shadow_x_mask		= 0;
 	shadow_present_mask	= PT_PRESENT_MASK;
 
-	/*
-	 * For shadow paging and NPT, KVM uses PAT entry '0' to encode WB
-	 * memtype in the SPTEs, i.e. relies on host MTRRs to provide the
-	 * correct memtype (WB is the "weakest" memtype).
-	 */
-	shadow_memtype_mask	= 0;
 	shadow_acc_track_mask	= 0;
 	shadow_me_mask		= 0;
 	shadow_me_value		= 0;