KVM: x86: hyper-v: HVCALL_SEND_IPI_EX is an XMM fast hypercall

It has been proven on practice that at least Windows Server 2019 tries
using HVCALL_SEND_IPI_EX in 'XMM fast' mode when it has more than 64 vCPUs
and it needs to send an IPI to a vCPU > 63. Similarly to other XMM Fast
hypercalls (HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE}{,_EX}), this
information is missing in TLFS as of 6.0b. Currently, KVM returns an error
(HV_STATUS_INVALID_HYPERCALL_INPUT) and Windows crashes.

Note, HVCALL_SEND_IPI is a 'standard' fast hypercall (not 'XMM fast') as
all its parameters fit into RDX:R8 and this is handled by KVM correctly.

Cc: stable@vger.kernel.org # 5.14.x: 3244867a: KVM: x86: Ignore sparse banks size for an "all CPUs", non-sparse IPI req
Cc: stable@vger.kernel.org # 5.14.x
Fixes: d8f5537a ("KVM: hyper-v: Advertise support for fast XMM hypercalls")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20220222154642.684285-5-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/hyperv.c

@@ -1889,6 +1889,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 	int sparse_banks_len;
 	u32 vector;
 	bool all_cpus;
+	int i;
 
 	if (hc->code == HVCALL_SEND_IPI) {
 		if (!hc->fast) {
@@ -1909,9 +1910,15 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 
 		trace_kvm_hv_send_ipi(vector, sparse_banks[0]);
 	} else {
+		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,
@@ -1919,8 +1926,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 
 		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]);
+		sparse_banks_len = bitmap_weight(&valid_bank_mask, 64);
 
 		all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL;
 
@@ -1930,12 +1936,27 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 		if (!sparse_banks_len)
 			goto ret_success;
 
+		if (!hc->fast) {
 			if (kvm_read_guest(kvm,
 					   hc->ingpa + offsetof(struct hv_send_ipi_ex,
 								vp_set.bank_contents),
 					   sparse_banks,
-				   sparse_banks_len))
+					   sparse_banks_len * sizeof(sparse_banks[0])))
 				return HV_STATUS_INVALID_HYPERCALL_INPUT;
+		} else {
+			/*
+			 * The lower half of XMM0 is already consumed, each XMM holds
+			 * two sparse banks.
+			 */
+			if (sparse_banks_len > (2 * HV_HYPERCALL_MAX_XMM_REGISTERS - 1))
+				return HV_STATUS_INVALID_HYPERCALL_INPUT;
+			for (i = 0; i < sparse_banks_len; i++) {
+				if (i % 2)
+					sparse_banks[i] = sse128_lo(hc->xmm[(i + 1) / 2]);
+				else
+					sparse_banks[i] = sse128_hi(hc->xmm[i / 2]);
+			}
+		}
 	}
 
 check_and_send_ipi:
@@ -2097,6 +2118,7 @@ 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;
 	}
 
@@ -2264,14 +2286,8 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 		ret = kvm_hv_flush_tlb(vcpu, &hc);
 		break;
 	case HVCALL_SEND_IPI:
-		if (unlikely(hc.rep)) {
-			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
-			break;
-		}
-		ret = kvm_hv_send_ipi(vcpu, &hc);
-		break;
 	case HVCALL_SEND_IPI_EX:
-		if (unlikely(hc.fast || hc.rep)) {
+		if (unlikely(hc.rep)) {
 			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
 			break;
 		}