Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
From:   Vitaly Kuznetsov <vkuznets@redhat.com>
To:     kvm@vger.kernel.org, Paolo Bonzini <pbonzini@redhat.com>
Cc:     Sean Christopherson <seanjc@google.com>,
        Wanpeng Li <wanpengli@tencent.com>,
        Jim Mattson <jmattson@google.com>,
        Michael Kelley <mikelley@microsoft.com>,
        Siddharth Chandrasekaran <sidcha@amazon.de>,
        linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH v3 09/34] KVM: x86: hyper-v: Don't use sparse_set_to_vcpu_mask() in kvm_hv_send_ipi()
Date:   Thu, 14 Apr 2022 15:19:48 +0200
Message-Id: <20220414132013.1588929-10-vkuznets@redhat.com>
In-Reply-To: <20220414132013.1588929-1-vkuznets@redhat.com>
References: <20220414132013.1588929-1-vkuznets@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain
Content-Transfer-Encoding: 8bit
Precedence: bulk

Get rid of on-stack allocation of vcpu_mask and optimize kvm_hv_send_ipi()
for a smaller number of vCPUs in the request. When Hyper-V TLB flush
is in  use, HvSendSyntheticClusterIpi{,Ex} calls are not commonly used to
send IPIs to a large number of vCPUs (and are rarely used in general).

Introduce hv_is_vp_in_sparse_set() to directly check if the specified
VP_ID is present in sparse vCPU set.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
---
 arch/x86/kvm/hyperv.c | 37 ++++++++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 3cf68645a2e6..aebbb598ad1d 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1746,6 +1746,25 @@ static void sparse_set_to_vcpu_mask(struct kvm *kvm, u64 *sparse_banks,
 	}
 }
 
+static bool hv_is_vp_in_sparse_set(u32 vp_id, u64 valid_bank_mask, u64 sparse_banks[])
+{
+	int bank, sbank = 0;
+
+	if (!test_bit(vp_id / HV_VCPUS_PER_SPARSE_BANK,
+		      (unsigned long *)&valid_bank_mask))
+		return false;
+
+	for_each_set_bit(bank, (unsigned long *)&valid_bank_mask,
+			 KVM_HV_MAX_SPARSE_VCPU_SET_BITS) {
+		if (bank == vp_id / HV_VCPUS_PER_SPARSE_BANK)
+			break;
+		sbank++;
+	}
+
+	return test_bit(vp_id % HV_VCPUS_PER_SPARSE_BANK,
+			(unsigned long *)&sparse_banks[sbank]);
+}
+
 struct kvm_hv_hcall {
 	u64 param;
 	u64 ingpa;
@@ -2089,8 +2108,8 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 		((u64)hc->rep_cnt << HV_HYPERCALL_REP_COMP_OFFSET);
 }
 
-static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector,
-				 unsigned long *vcpu_bitmap)
+static void kvm_hv_send_ipi_to_many(struct kvm *kvm, u32 vector,
+				    u64 *sparse_banks, u64 valid_bank_mask)
 {
 	struct kvm_lapic_irq irq = {
 		.delivery_mode = APIC_DM_FIXED,
@@ -2100,7 +2119,10 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector,
 	unsigned long i;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (vcpu_bitmap && !test_bit(i, vcpu_bitmap))
+		if (sparse_banks &&
+		    !hv_is_vp_in_sparse_set(kvm_hv_get_vpindex(vcpu),
+					    valid_bank_mask,
+					    sparse_banks))
 			continue;
 
 		/* We fail only when APIC is disabled */
@@ -2113,7 +2135,6 @@ 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;
-	DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
 	unsigned long valid_bank_mask;
 	u64 sparse_banks[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
 	u32 vector;
@@ -2175,13 +2196,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 	if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
 		return HV_STATUS_INVALID_HYPERCALL_INPUT;
 
-	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_hv_send_ipi_to_many(kvm, vector, all_cpus ? NULL : sparse_banks, valid_bank_mask);
 
 ret_success:
 	return HV_STATUS_SUCCESS;
-- 
2.35.1