1 files changed, 143 insertions, 99 deletions

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 6e38a7d22e97..a32f54ab84a2 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -112,6 +112,9 @@ static void synic_update_vector(struct kvm_vcpu_hv_synic *synic,
 	if (!!auto_eoi_old == !!auto_eoi_new)
 		return;
 
+	if (!enable_apicv)
+		return;
+
 	down_write(&vcpu->kvm->arch.apicv_update_lock);
 
 	if (auto_eoi_new)
@@ -1710,32 +1713,47 @@ int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host)
 		return kvm_hv_get_msr(vcpu, msr, pdata, host);
 }
 
-static __always_inline unsigned long *sparse_set_to_vcpu_mask(
-	struct kvm *kvm, u64 *sparse_banks, u64 valid_bank_mask,
-	u64 *vp_bitmap, unsigned long *vcpu_bitmap)
+static void sparse_set_to_vcpu_mask(struct kvm *kvm, u64 *sparse_banks,
+				    u64 valid_bank_mask, unsigned long *vcpu_mask)
 {
 	struct kvm_hv *hv = to_kvm_hv(kvm);
+	bool has_mismatch = atomic_read(&hv->num_mismatched_vp_indexes);
+	u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
 	struct kvm_vcpu *vcpu;
 	int bank, sbank = 0;
 	unsigned long i;
+	u64 *bitmap;
+
+	BUILD_BUG_ON(sizeof(vp_bitmap) >
+		     sizeof(*vcpu_mask) * BITS_TO_LONGS(KVM_MAX_VCPUS));
+
+	/*
+	 * If vp_index == vcpu_idx for all vCPUs, fill vcpu_mask directly, else
+	 * fill a temporary buffer and manually test each vCPU's VP index.
+	 */
+	if (likely(!has_mismatch))
+		bitmap = (u64 *)vcpu_mask;
+	else
+		bitmap = vp_bitmap;
 
-	memset(vp_bitmap, 0,
-	       KVM_HV_MAX_SPARSE_VCPU_SET_BITS * sizeof(*vp_bitmap));
+	/*
+	 * Each set of 64 VPs is packed into sparse_banks, with valid_bank_mask
+	 * having a '1' for each bank that exists in sparse_banks.  Sets must
+	 * be in ascending order, i.e. bank0..bankN.
+	 */
+	memset(bitmap, 0, sizeof(vp_bitmap));
 	for_each_set_bit(bank, (unsigned long *)&valid_bank_mask,
 			 KVM_HV_MAX_SPARSE_VCPU_SET_BITS)
-		vp_bitmap[bank] = sparse_banks[sbank++];
+		bitmap[bank] = sparse_banks[sbank++];
 
-	if (likely(!atomic_read(&hv->num_mismatched_vp_indexes))) {
-		/* for all vcpus vp_index == vcpu_idx */
-		return (unsigned long *)vp_bitmap;
-	}
+	if (likely(!has_mismatch))
+		return;
 
-	bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS);
+	bitmap_zero(vcpu_mask, KVM_MAX_VCPUS);
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		if (test_bit(kvm_hv_get_vpindex(vcpu), (unsigned long *)vp_bitmap))
-			__set_bit(i, vcpu_bitmap);
+			__set_bit(i, vcpu_mask);
 	}
-	return vcpu_bitmap;
 }
 
 struct kvm_hv_hcall {
@@ -1743,6 +1761,7 @@ struct kvm_hv_hcall {
 	u64 ingpa;
 	u64 outgpa;
 	u16 code;
+	u16 var_cnt;
 	u16 rep_cnt;
 	u16 rep_idx;
 	bool fast;
@@ -1750,22 +1769,60 @@ struct kvm_hv_hcall {
 	sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS];
 };
 
-static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool ex)
+static u64 kvm_get_sparse_vp_set(struct kvm *kvm, struct kvm_hv_hcall *hc,
+				 int consumed_xmm_halves,
+				 u64 *sparse_banks, gpa_t offset)
 {
+	u16 var_cnt;
 	int i;
-	gpa_t gpa;
+
+	if (hc->var_cnt > 64)
+		return -EINVAL;
+
+	/* Ignore banks that cannot possibly contain a legal VP index. */
+	var_cnt = min_t(u16, hc->var_cnt, KVM_HV_MAX_SPARSE_VCPU_SET_BITS);
+
+	if (hc->fast) {
+		/*
+		 * Each XMM holds two sparse banks, but do not count halves that
+		 * have already been consumed for hypercall parameters.
+		 */
+		if (hc->var_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - consumed_xmm_halves)
+			return HV_STATUS_INVALID_HYPERCALL_INPUT;
+		for (i = 0; i < var_cnt; i++) {
+			int j = i + consumed_xmm_halves;
+			if (j % 2)
+				sparse_banks[i] = sse128_hi(hc->xmm[j / 2]);
+			else
+				sparse_banks[i] = sse128_lo(hc->xmm[j / 2]);
+		}
+		return 0;
+	}
+
+	return kvm_read_guest(kvm, hc->ingpa + offset, sparse_banks,
+			      var_cnt * sizeof(*sparse_banks));
+}
+
+static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
+{
 	struct kvm *kvm = vcpu->kvm;
 	struct hv_tlb_flush_ex flush_ex;
 	struct hv_tlb_flush flush;
-	u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
-	DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
-	unsigned long *vcpu_mask;
+	DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
 	u64 valid_bank_mask;
-	u64 sparse_banks[64];
-	int sparse_banks_len;
+	u64 sparse_banks[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
 	bool all_cpus;
 
-	if (!ex) {
+	/*
+	 * The Hyper-V TLFS doesn't allow more than 64 sparse banks, e.g. the
+	 * valid mask is a u64.  Fail the build if KVM's max allowed number of
+	 * vCPUs (>4096) would exceed this limit, KVM will additional changes
+	 * for Hyper-V support to avoid setting the guest up to fail.
+	 */
+	BUILD_BUG_ON(KVM_HV_MAX_SPARSE_VCPU_SET_BITS > 64);
+
+	if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST ||
+	    hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE) {
 		if (hc->fast) {
 			flush.address_space = hc->ingpa;
 			flush.flags = hc->outgpa;
@@ -1812,30 +1869,22 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
 		all_cpus = flush_ex.hv_vp_set.format !=
 			HV_GENERIC_SET_SPARSE_4K;
 
-		sparse_banks_len = bitmap_weight((unsigned long *)&valid_bank_mask, 64);
+		if (hc->var_cnt != bitmap_weight((unsigned long *)&valid_bank_mask, 64))
+			return HV_STATUS_INVALID_HYPERCALL_INPUT;
 
-		if (!sparse_banks_len && !all_cpus)
+		if (all_cpus)
+			goto do_flush;
+
+		if (!hc->var_cnt)
 			goto ret_success;
 
-		if (!all_cpus) {
-			if (hc->fast) {
-				if (sparse_banks_len > HV_HYPERCALL_MAX_XMM_REGISTERS - 1)
-					return HV_STATUS_INVALID_HYPERCALL_INPUT;
-				for (i = 0; i < sparse_banks_len; i += 2) {
-					sparse_banks[i] = sse128_lo(hc->xmm[i / 2 + 1]);
-					sparse_banks[i + 1] = sse128_hi(hc->xmm[i / 2 + 1]);
-				}
-			} else {
-				gpa = hc->ingpa + offsetof(struct hv_tlb_flush_ex,
-							   hv_vp_set.bank_contents);
-				if (unlikely(kvm_read_guest(kvm, gpa, sparse_banks,
-							    sparse_banks_len *
-							    sizeof(sparse_banks[0]))))
-					return HV_STATUS_INVALID_HYPERCALL_INPUT;
-			}
-		}
+		if (kvm_get_sparse_vp_set(kvm, hc, 2, sparse_banks,
+					  offsetof(struct hv_tlb_flush_ex,
+						   hv_vp_set.bank_contents)))
+			return HV_STATUS_INVALID_HYPERCALL_INPUT;
 	}
 
+do_flush:
 	/*
 	 * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't
 	 * analyze it here, flush TLB regardless of the specified address space.
@@ -1843,11 +1892,9 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
 	if (all_cpus) {
 		kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH_GUEST);
 	} else {
-		vcpu_mask = sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask,
-						    vp_bitmap, vcpu_bitmap);
+		sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask, vcpu_mask);
 
-		kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH_GUEST,
-					    vcpu_mask);
+		kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH_GUEST, vcpu_mask);
 	}
 
 ret_success:
@@ -1875,21 +1922,18 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector,
 	}
 }
 
-static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool ex)
+static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 {
 	struct kvm *kvm = vcpu->kvm;
 	struct hv_send_ipi_ex send_ipi_ex;
 	struct hv_send_ipi send_ipi;
-	u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
-	DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
-	unsigned long *vcpu_mask;
+	DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
 	unsigned long valid_bank_mask;
-	u64 sparse_banks[64];
-	int sparse_banks_len;
+	u64 sparse_banks[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
 	u32 vector;
 	bool all_cpus;
 
-	if (!ex) {
+	if (hc->code == HVCALL_SEND_IPI) {
 		if (!hc->fast) {
 			if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi,
 						    sizeof(send_ipi))))
@@ -1908,9 +1952,15 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
 
 		trace_kvm_hv_send_ipi(vector, sparse_banks[0]);
 	} else {
-		if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi_ex,
-					    sizeof(send_ipi_ex))))
-			return HV_STATUS_INVALID_HYPERCALL_INPUT;
+		if (!hc->fast) {
+			if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi_ex,
+						    sizeof(send_ipi_ex))))
+				return HV_STATUS_INVALID_HYPERCALL_INPUT;
+		} else {
+			send_ipi_ex.vector = (u32)hc->ingpa;
+			send_ipi_ex.vp_set.format = hc->outgpa;
+			send_ipi_ex.vp_set.valid_bank_mask = sse128_lo(hc->xmm[0]);
+		}
 
 		trace_kvm_hv_send_ipi_ex(send_ipi_ex.vector,
 					 send_ipi_ex.vp_set.format,
@@ -1918,22 +1968,20 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
 
 		vector = send_ipi_ex.vector;
 		valid_bank_mask = send_ipi_ex.vp_set.valid_bank_mask;
-		sparse_banks_len = bitmap_weight(&valid_bank_mask, 64) *
-			sizeof(sparse_banks[0]);
-
 		all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL;
 
+		if (hc->var_cnt != bitmap_weight(&valid_bank_mask, 64))
+			return HV_STATUS_INVALID_HYPERCALL_INPUT;
+
 		if (all_cpus)
 			goto check_and_send_ipi;
 
-		if (!sparse_banks_len)
+		if (!hc->var_cnt)
 			goto ret_success;
 
-		if (kvm_read_guest(kvm,
-				   hc->ingpa + offsetof(struct hv_send_ipi_ex,
-							vp_set.bank_contents),
-				   sparse_banks,
-				   sparse_banks_len))
+		if (kvm_get_sparse_vp_set(kvm, hc, 1, sparse_banks,
+					  offsetof(struct hv_send_ipi_ex,
+						   vp_set.bank_contents)))
 			return HV_STATUS_INVALID_HYPERCALL_INPUT;
 	}
 
@@ -1941,11 +1989,13 @@ check_and_send_ipi:
 	if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
 		return HV_STATUS_INVALID_HYPERCALL_INPUT;
 
-	vcpu_mask = all_cpus ? NULL :
-		sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask,
-					vp_bitmap, vcpu_bitmap);
+	if (all_cpus) {
+		kvm_send_ipi_to_many(kvm, vector, NULL);
+	} else {
+		sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask, vcpu_mask);
 
-	kvm_send_ipi_to_many(kvm, vector, vcpu_mask);
+		kvm_send_ipi_to_many(kvm, vector, vcpu_mask);
+	}
 
 ret_success:
 	return HV_STATUS_SUCCESS;
@@ -2017,11 +2067,6 @@ int kvm_hv_set_enforce_cpuid(struct kvm_vcpu *vcpu, bool enforce)
 	return ret;
 }
 
-bool kvm_hv_hypercall_enabled(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.hyperv_enabled && to_kvm_hv(vcpu->kvm)->hv_guest_os_id;
-}
-
 static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
 {
 	bool longmode;
@@ -2096,6 +2141,7 @@ static bool is_xmm_fast_hypercall(struct kvm_hv_hcall *hc)
 	case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE:
 	case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX:
 	case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX:
+	case HVCALL_SEND_IPI_EX:
 		return true;
 	}
 
@@ -2191,19 +2237,25 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	}
 
 	hc.code = hc.param & 0xffff;
+	hc.var_cnt = (hc.param & HV_HYPERCALL_VARHEAD_MASK) >> HV_HYPERCALL_VARHEAD_OFFSET;
 	hc.fast = !!(hc.param & HV_HYPERCALL_FAST_BIT);
 	hc.rep_cnt = (hc.param >> HV_HYPERCALL_REP_COMP_OFFSET) & 0xfff;
 	hc.rep_idx = (hc.param >> HV_HYPERCALL_REP_START_OFFSET) & 0xfff;
 	hc.rep = !!(hc.rep_cnt || hc.rep_idx);
 
-	trace_kvm_hv_hypercall(hc.code, hc.fast, hc.rep_cnt, hc.rep_idx,
-			       hc.ingpa, hc.outgpa);
+	trace_kvm_hv_hypercall(hc.code, hc.fast, hc.var_cnt, hc.rep_cnt,
+			       hc.rep_idx, hc.ingpa, hc.outgpa);
 
 	if (unlikely(!hv_check_hypercall_access(hv_vcpu, hc.code))) {
 		ret = HV_STATUS_ACCESS_DENIED;
 		goto hypercall_complete;
 	}
 
+	if (unlikely(hc.param & HV_HYPERCALL_RSVD_MASK)) {
+		ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
+		goto hypercall_complete;
+	}
+
 	if (hc.fast && is_xmm_fast_hypercall(&hc)) {
 		if (unlikely(hv_vcpu->enforce_cpuid &&
 			     !(hv_vcpu->cpuid_cache.features_edx &
@@ -2217,14 +2269,14 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 
 	switch (hc.code) {
 	case HVCALL_NOTIFY_LONG_SPIN_WAIT:
-		if (unlikely(hc.rep)) {
+		if (unlikely(hc.rep || hc.var_cnt)) {
 			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
 			break;
 		}
 		kvm_vcpu_on_spin(vcpu, true);
 		break;
 	case HVCALL_SIGNAL_EVENT:
-		if (unlikely(hc.rep)) {
+		if (unlikely(hc.rep || hc.var_cnt)) {
 			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
 			break;
 		}
@@ -2234,7 +2286,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 		fallthrough;	/* maybe userspace knows this conn_id */
 	case HVCALL_POST_MESSAGE:
 		/* don't bother userspace if it has no way to handle it */
-		if (unlikely(hc.rep || !to_hv_synic(vcpu)->active)) {
+		if (unlikely(hc.rep || hc.var_cnt || !to_hv_synic(vcpu)->active)) {
 			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
 			break;
 		}
@@ -2247,46 +2299,43 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 				kvm_hv_hypercall_complete_userspace;
 		return 0;
 	case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST:
-		if (unlikely(!hc.rep_cnt || hc.rep_idx)) {
+		if (unlikely(hc.var_cnt)) {
 			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
 			break;
 		}
-		ret = kvm_hv_flush_tlb(vcpu, &hc, false);
-		break;
-	case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE:
-		if (unlikely(hc.rep)) {
+		fallthrough;
+	case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX:
+		if (unlikely(!hc.rep_cnt || hc.rep_idx)) {
 			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
 			break;
 		}
-		ret = kvm_hv_flush_tlb(vcpu, &hc, false);
+		ret = kvm_hv_flush_tlb(vcpu, &hc);
 		break;
-	case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX:
-		if (unlikely(!hc.rep_cnt || hc.rep_idx)) {
+	case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE:
+		if (unlikely(hc.var_cnt)) {
 			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
 			break;
 		}
-		ret = kvm_hv_flush_tlb(vcpu, &hc, true);
-		break;
+		fallthrough;
 	case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX:
 		if (unlikely(hc.rep)) {
 			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
 			break;
 		}
-		ret = kvm_hv_flush_tlb(vcpu, &hc, true);
+		ret = kvm_hv_flush_tlb(vcpu, &hc);
 		break;
 	case HVCALL_SEND_IPI:
-		if (unlikely(hc.rep)) {
+		if (unlikely(hc.var_cnt)) {
 			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
 			break;
 		}
-		ret = kvm_hv_send_ipi(vcpu, &hc, false);
-		break;
+		fallthrough;
 	case HVCALL_SEND_IPI_EX:
-		if (unlikely(hc.fast || hc.rep)) {
+		if (unlikely(hc.rep)) {
 			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
 			break;
 		}
-		ret = kvm_hv_send_ipi(vcpu, &hc, true);
+		ret = kvm_hv_send_ipi(vcpu, &hc);
 		break;
 	case HVCALL_POST_DEBUG_DATA:
 	case HVCALL_RETRIEVE_DEBUG_DATA:
@@ -2417,10 +2466,6 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
 	if (kvm_x86_ops.nested_ops->get_evmcs_version)
 		evmcs_ver = kvm_x86_ops.nested_ops->get_evmcs_version(vcpu);
 
-	/* Skip NESTED_FEATURES if eVMCS is not supported */
-	if (!evmcs_ver)
-		--nent;
-
 	if (cpuid->nent < nent)
 		return -E2BIG;
 
@@ -2520,8 +2565,7 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
 
 		case HYPERV_CPUID_NESTED_FEATURES:
 			ent->eax = evmcs_ver;
-			if (evmcs_ver)
-				ent->eax |= HV_X64_NESTED_MSR_BITMAP;
+			ent->eax |= HV_X64_NESTED_MSR_BITMAP;
 
 			break;