Merge branch 'kvm-coco-pagefault-prep' into HEAD

A combination of prep work for TDX and SNP, and a clean up of the
page fault path to (hopefully) make it easier to follow the rules for
private memory, noslot faults, writes to read-only slots, etc.

Author: bonzini

arch/x86/include/asm/kvm_host.h

@@ -254,28 +254,31 @@ enum x86_intercept_stage;
 	KVM_GUESTDBG_INJECT_DB | \
 	KVM_GUESTDBG_BLOCKIRQ)
 
+#define PFERR_PRESENT_MASK	BIT(0)
+#define PFERR_WRITE_MASK	BIT(1)
+#define PFERR_USER_MASK		BIT(2)
+#define PFERR_RSVD_MASK		BIT(3)
+#define PFERR_FETCH_MASK	BIT(4)
+#define PFERR_PK_MASK		BIT(5)
+#define PFERR_SGX_MASK		BIT(15)
+#define PFERR_GUEST_RMP_MASK	BIT_ULL(31)
+#define PFERR_GUEST_FINAL_MASK	BIT_ULL(32)
+#define PFERR_GUEST_PAGE_MASK	BIT_ULL(33)
+#define PFERR_GUEST_ENC_MASK	BIT_ULL(34)
+#define PFERR_GUEST_SIZEM_MASK	BIT_ULL(35)
+#define PFERR_GUEST_VMPL_MASK	BIT_ULL(36)
 
-#define PFERR_PRESENT_BIT 0
-#define PFERR_WRITE_BIT 1
-#define PFERR_USER_BIT 2
-#define PFERR_RSVD_BIT 3
-#define PFERR_FETCH_BIT 4
-#define PFERR_PK_BIT 5
-#define PFERR_SGX_BIT 15
-#define PFERR_GUEST_FINAL_BIT 32
-#define PFERR_GUEST_PAGE_BIT 33
-#define PFERR_IMPLICIT_ACCESS_BIT 48
-
-#define PFERR_PRESENT_MASK	BIT(PFERR_PRESENT_BIT)
-#define PFERR_WRITE_MASK	BIT(PFERR_WRITE_BIT)
-#define PFERR_USER_MASK		BIT(PFERR_USER_BIT)
-#define PFERR_RSVD_MASK		BIT(PFERR_RSVD_BIT)
-#define PFERR_FETCH_MASK	BIT(PFERR_FETCH_BIT)
-#define PFERR_PK_MASK		BIT(PFERR_PK_BIT)
-#define PFERR_SGX_MASK		BIT(PFERR_SGX_BIT)
-#define PFERR_GUEST_FINAL_MASK	BIT_ULL(PFERR_GUEST_FINAL_BIT)
-#define PFERR_GUEST_PAGE_MASK	BIT_ULL(PFERR_GUEST_PAGE_BIT)
-#define PFERR_IMPLICIT_ACCESS	BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT)
+/*
+ * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP checks
+ * when emulating instructions that triggers implicit access.
+ */
+#define PFERR_IMPLICIT_ACCESS	BIT_ULL(48)
+/*
+ * PRIVATE_ACCESS is a KVM-defined flag us to indicate that a fault occurred
+ * when the guest was accessing private memory.
+ */
+#define PFERR_PRIVATE_ACCESS   BIT_ULL(49)
+#define PFERR_SYNTHETIC_MASK   (PFERR_IMPLICIT_ACCESS | PFERR_PRIVATE_ACCESS)
 
 #define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK |	\
 				 PFERR_WRITE_MASK |		\
@@ -1848,6 +1851,7 @@ struct kvm_arch_async_pf {
 	gfn_t gfn;
 	unsigned long cr3;
 	bool direct_map;
+	u64 error_code;
 };
 
 extern u32 __read_mostly kvm_nr_uret_msrs;

arch/x86/kvm/mmu.h

@@ -213,7 +213,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	 */
 	u64 implicit_access = access & PFERR_IMPLICIT_ACCESS;
 	bool not_smap = ((rflags & X86_EFLAGS_AC) | implicit_access) == X86_EFLAGS_AC;
-	int index = (pfec + (not_smap << PFERR_RSVD_BIT)) >> 1;
+	int index = (pfec | (not_smap ? PFERR_RSVD_MASK : 0)) >> 1;
 	u32 errcode = PFERR_PRESENT_MASK;
 	bool fault;
 
@@ -234,8 +234,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 		pkru_bits = (vcpu->arch.pkru >> (pte_pkey * 2)) & 3;
 
 		/* clear present bit, replace PFEC.RSVD with ACC_USER_MASK. */
-		offset = (pfec & ~1) +
-			((pte_access & PT_USER_MASK) << (PFERR_RSVD_BIT - PT_USER_SHIFT));
+		offset = (pfec & ~1) | ((pte_access & PT_USER_MASK) ? PFERR_RSVD_MASK : 0);
 
 		pkru_bits &= mmu->pkru_mask >> offset;
 		errcode |= -pkru_bits & PFERR_PK_MASK;

arch/x86/kvm/mmu/mmu.c

@@ -3262,9 +3262,19 @@ static int kvm_handle_noslot_fault(struct kvm_vcpu *vcpu,
 {
 	gva_t gva = fault->is_tdp ? 0 : fault->addr;
 
+	if (fault->is_private) {
+		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+		return -EFAULT;
+	}
+
 	vcpu_cache_mmio_info(vcpu, gva, fault->gfn,
 			     access & shadow_mmio_access_mask);
 
+	fault->slot = NULL;
+	fault->pfn = KVM_PFN_NOSLOT;
+	fault->map_writable = false;
+	fault->hva = KVM_HVA_ERR_BAD;
+
 	/*
 	 * If MMIO caching is disabled, emulate immediately without
 	 * touching the shadow page tables as attempting to install an
@@ -4207,24 +4217,28 @@ static u32 alloc_apf_token(struct kvm_vcpu *vcpu)
 	return (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id;
 }
 
-static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
-				    gfn_t gfn)
+static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu,
+				    struct kvm_page_fault *fault)
 {
 	struct kvm_arch_async_pf arch;
 
 	arch.token = alloc_apf_token(vcpu);
-	arch.gfn = gfn;
+	arch.gfn = fault->gfn;
+	arch.error_code = fault->error_code;
 	arch.direct_map = vcpu->arch.mmu->root_role.direct;
 	arch.cr3 = kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu);
 
-	return kvm_setup_async_pf(vcpu, cr2_or_gpa,
-				  kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
+	return kvm_setup_async_pf(vcpu, fault->addr,
+				  kvm_vcpu_gfn_to_hva(vcpu, fault->gfn), &arch);
 }
 
 void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 {
 	int r;
 
+	if (WARN_ON_ONCE(work->arch.error_code & PFERR_PRIVATE_ACCESS))
+		return;
+
 	if ((vcpu->arch.mmu->root_role.direct != work->arch.direct_map) ||
 	      work->wakeup_all)
 		return;
@@ -4237,7 +4251,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 	      work->arch.cr3 != kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu))
 		return;
 
-	kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL);
+	kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, work->arch.error_code, true, NULL);
 }
 
 static inline u8 kvm_max_level_for_order(int order)
@@ -4257,14 +4271,6 @@ static inline u8 kvm_max_level_for_order(int order)
 	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)
 {
@@ -4291,48 +4297,15 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
 
 static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
-	struct kvm_memory_slot *slot = fault->slot;
 	bool async;
 
-	/*
-	 * Retry the page fault if the gfn hit a memslot that is being deleted
-	 * or moved.  This ensures any existing SPTEs for the old memslot will
-	 * be zapped before KVM inserts a new MMIO SPTE for the gfn.
-	 */
-	if (slot && (slot->flags & KVM_MEMSLOT_INVALID))
-		return RET_PF_RETRY;
-
-	if (!kvm_is_visible_memslot(slot)) {
-		/* Don't expose private memslots to L2. */
-		if (is_guest_mode(vcpu)) {
-			fault->slot = NULL;
-			fault->pfn = KVM_PFN_NOSLOT;
-			fault->map_writable = false;
-			return RET_PF_CONTINUE;
-		}
-		/*
-		 * If the APIC access page exists but is disabled, go directly
-		 * to emulation without caching the MMIO access or creating a
-		 * MMIO SPTE.  That way the cache doesn't need to be purged
-		 * when the AVIC is re-enabled.
-		 */
-		if (slot && slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT &&
-		    !kvm_apicv_activated(vcpu->kvm))
-			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,
-					  &fault->hva);
+	fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, false, false,
+					  &async, fault->write,
+					  &fault->map_writable, &fault->hva);
 	if (!async)
 		return RET_PF_CONTINUE; /* *pfn has correct page already */
 
@@ -4342,7 +4315,7 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 			trace_kvm_async_pf_repeated_fault(fault->addr, fault->gfn);
 			kvm_make_request(KVM_REQ_APF_HALT, vcpu);
 			return RET_PF_RETRY;
-		} else if (kvm_arch_setup_async_pf(vcpu, fault->addr, fault->gfn)) {
+		} else if (kvm_arch_setup_async_pf(vcpu, fault)) {
 			return RET_PF_RETRY;
 		}
 	}
@@ -4352,17 +4325,72 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	 * to wait for IO.  Note, gup always bails if it is unable to quickly
 	 * get a page and a fatal signal, i.e. SIGKILL, is pending.
 	 */
-	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, true, NULL,
-					  fault->write, &fault->map_writable,
-					  &fault->hva);
+	fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, false, true,
+					  NULL, fault->write,
+					  &fault->map_writable, &fault->hva);
 	return RET_PF_CONTINUE;
 }
 
 static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 			   unsigned int access)
 {
+	struct kvm_memory_slot *slot = fault->slot;
 	int ret;
 
+	/*
+	 * Note that the mmu_invalidate_seq also serves to detect a concurrent
+	 * change in attributes.  is_page_fault_stale() will detect an
+	 * invalidation relate to fault->fn and resume the guest without
+	 * installing a mapping in the page tables.
+	 */
+	fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq;
+	smp_rmb();
+
+	/*
+	 * Now that we have a snapshot of mmu_invalidate_seq we can check for a
+	 * private vs. shared mismatch.
+	 */
+	if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
+		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+		return -EFAULT;
+	}
+
+	if (unlikely(!slot))
+		return kvm_handle_noslot_fault(vcpu, fault, access);
+
+	/*
+	 * Retry the page fault if the gfn hit a memslot that is being deleted
+	 * or moved.  This ensures any existing SPTEs for the old memslot will
+	 * be zapped before KVM inserts a new MMIO SPTE for the gfn.
+	 */
+	if (slot->flags & KVM_MEMSLOT_INVALID)
+		return RET_PF_RETRY;
+
+	if (slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT) {
+		/*
+		 * Don't map L1's APIC access page into L2, KVM doesn't support
+		 * using APICv/AVIC to accelerate L2 accesses to L1's APIC,
+		 * i.e. the access needs to be emulated.  Emulating access to
+		 * L1's APIC is also correct if L1 is accelerating L2's own
+		 * virtual APIC, but for some reason L1 also maps _L1's_ APIC
+		 * into L2.  Note, vcpu_is_mmio_gpa() always treats access to
+		 * the APIC as MMIO.  Allow an MMIO SPTE to be created, as KVM
+		 * uses different roots for L1 vs. L2, i.e. there is no danger
+		 * of breaking APICv/AVIC for L1.
+		 */
+		if (is_guest_mode(vcpu))
+			return kvm_handle_noslot_fault(vcpu, fault, access);
+
+		/*
+		 * If the APIC access page exists but is disabled, go directly
+		 * to emulation without caching the MMIO access or creating a
+		 * MMIO SPTE.  That way the cache doesn't need to be purged
+		 * when the AVIC is re-enabled.
+		 */
+		if (!kvm_apicv_activated(vcpu->kvm))
+			return RET_PF_EMULATE;
+	}
+
 	fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq;
 	smp_rmb();
 
@@ -4387,8 +4415,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 	 * *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))
+	if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn))
 		return RET_PF_RETRY;
 
 	ret = __kvm_faultin_pfn(vcpu, fault);
@@ -4398,7 +4425,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 	if (unlikely(is_error_pfn(fault->pfn)))
 		return kvm_handle_error_pfn(vcpu, fault);
 
-	if (unlikely(!fault->slot))
+	if (WARN_ON_ONCE(!fault->slot || is_noslot_pfn(fault->pfn)))
 		return kvm_handle_noslot_fault(vcpu, fault, access);
 
 	/*
@@ -4509,6 +4536,16 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 	if (WARN_ON_ONCE(fault_address >> 32))
 		return -EFAULT;
 #endif
+	/*
+	 * Legacy #PF exception only have a 32-bit error code.  Simply drop the
+	 * upper bits as KVM doesn't use them for #PF (because they are never
+	 * set), and to ensure there are no collisions with KVM-defined bits.
+	 */
+	if (WARN_ON_ONCE(error_code >> 32))
+		error_code = lower_32_bits(error_code);
+
+	/* Ensure the above sanity check also covers KVM-defined flags. */
+	BUILD_BUG_ON(lower_32_bits(PFERR_SYNTHETIC_MASK));
 
 	vcpu->arch.l1tf_flush_l1d = true;
 	if (!flags) {
@@ -5794,30 +5831,35 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
 	int r, emulation_type = EMULTYPE_PF;
 	bool direct = vcpu->arch.mmu->root_role.direct;
 
-	/*
-	 * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP
-	 * checks when emulating instructions that triggers implicit access.
-	 * WARN if hardware generates a fault with an error code that collides
-	 * with the KVM-defined value.  Clear the flag and continue on, i.e.
-	 * don't terminate the VM, as KVM can't possibly be relying on a flag
-	 * that KVM doesn't know about.
-	 */
-	if (WARN_ON_ONCE(error_code & PFERR_IMPLICIT_ACCESS))
-		error_code &= ~PFERR_IMPLICIT_ACCESS;
-
 	if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
 		return RET_PF_RETRY;
 
+	/*
+	 * Except for reserved faults (emulated MMIO is shared-only), set the
+	 * PFERR_PRIVATE_ACCESS flag for software-protected VMs based on the gfn's
+	 * current attributes, which are the source of truth for such VMs.  Note,
+	 * this wrong for nested MMUs as the GPA is an L2 GPA, but KVM doesn't
+	 * currently supported nested virtualization (among many other things)
+	 * for software-protected VMs.
+	 */
+	if (IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) &&
+	    !(error_code & PFERR_RSVD_MASK) &&
+	    vcpu->kvm->arch.vm_type == KVM_X86_SW_PROTECTED_VM &&
+	    kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(cr2_or_gpa)))
+		error_code |= PFERR_PRIVATE_ACCESS;
+
 	r = RET_PF_INVALID;
 	if (unlikely(error_code & PFERR_RSVD_MASK)) {
+		if (WARN_ON_ONCE(error_code & PFERR_PRIVATE_ACCESS))
+			return -EFAULT;
+
 		r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct);
 		if (r == RET_PF_EMULATE)
 			goto emulate;
 	}
 
 	if (r == RET_PF_INVALID) {
-		r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa,
-					  lower_32_bits(error_code), false,
+		r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, error_code, false,
 					  &emulation_type);
 		if (KVM_BUG_ON(r == RET_PF_INVALID, vcpu->kvm))
 			return -EIO;