[PATCH v12 16/46] KVM: x86: hyper-v: Don't use sparse_set_to_vcpu_mask() in kvm_hv_send_ipi()

[Vitaly Kuznetsov]

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@xxxxxxxxxx>
---
 arch/x86/kvm/hyperv.c | 42 +++++++++++++++++++++++++++++++-----------
 1 file changed, 31 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index df9f9aeedc7c..1d1a65903eb5 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1741,6 +1741,28 @@ 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 valid_bit_nr = vp_id / HV_VCPUS_PER_SPARSE_BANK;
+	unsigned long sbank;
+
+	if (!test_bit(valid_bit_nr, (unsigned long *)&valid_bank_mask))
+		return false;
+
+	/*
+	 * The index into the sparse bank is the number of preceding bits in
+	 * the valid mask.  Optimize for VMs with <64 vCPUs by skipping the
+	 * fancy math if there can't possibly be preceding bits.
+	 */
+	if (valid_bit_nr)
+		sbank = hweight64(valid_bank_mask & GENMASK_ULL(valid_bit_nr - 1, 0));
+	else
+		sbank = 0;
+
+	return test_bit(vp_id % HV_VCPUS_PER_SPARSE_BANK,
+			(unsigned long *)&sparse_banks[sbank]);
+}
+
 struct kvm_hv_hcall {
 	u64 param;
 	u64 ingpa;
@@ -2028,8 +2050,8 @@ 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,
@@ -2039,7 +2061,9 @@ 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 */
@@ -2052,7 +2076,6 @@ 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);
 	u64 valid_bank_mask;
 	u64 sparse_banks[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
 	u32 vector;
@@ -2114,13 +2137,10 @@ 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);
-	}
+	if (all_cpus)
+		kvm_hv_send_ipi_to_many(kvm, vector, NULL, 0);
+	else
+		kvm_hv_send_ipi_to_many(kvm, vector, sparse_banks, valid_bank_mask);
 
 ret_success:
 	return HV_STATUS_SUCCESS;
-- 
2.37.3