KVM: x86: use static calls to reduce kvm_x86_ops overhead

Convert kvm_x86_ops to use static calls. Note that all kvm_x86_ops are
covered here except for 'pmu_ops and 'nested ops'.

Here are some numbers running cpuid in a loop of 1 million calls averaged
over 5 runs, measured in the vm (lower is better).

Intel Xeon 3000MHz:

           |default    |mitigations=off
-------------------------------------
vanilla    |.671s      |.486s
static call|.573s(-15%)|.458s(-6%)

AMD EPYC 2500MHz:

           |default    |mitigations=off
-------------------------------------
vanilla    |.710s      |.609s
static call|.664s(-6%) |.609s(0%)

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Jason Baron <jbaron@akamai.com>
Message-Id: <e057bf1b8a7ad15652df6eeba3f907ae758d3399.1610680941.git.jbaron@akamai.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 8 insertions, 7 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 8740ac1a48cb..bc63406850c9 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -190,7 +190,7 @@ static void kvm_flush_remote_tlbs_with_range(struct kvm *kvm,
 	int ret = -ENOTSUPP;
 
 	if (range && kvm_x86_ops.tlb_remote_flush_with_range)
-		ret = kvm_x86_ops.tlb_remote_flush_with_range(kvm, range);
+		ret = static_call(kvm_x86_tlb_remote_flush_with_range)(kvm, range);
 
 	if (ret)
 		kvm_flush_remote_tlbs(kvm);
@@ -1283,8 +1283,9 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 				gfn_t gfn_offset, unsigned long mask)
 {
 	if (kvm_x86_ops.enable_log_dirty_pt_masked)
-		kvm_x86_ops.enable_log_dirty_pt_masked(kvm, slot, gfn_offset,
-				mask);
+		static_call(kvm_x86_enable_log_dirty_pt_masked)(kvm, slot,
+								gfn_offset,
+								mask);
 	else
 		kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
 }
@@ -1292,7 +1293,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 int kvm_cpu_dirty_log_size(void)
 {
 	if (kvm_x86_ops.cpu_dirty_log_size)
-		return kvm_x86_ops.cpu_dirty_log_size();
+		return static_call(kvm_x86_cpu_dirty_log_size)();
 
 	return 0;
 }
@@ -4799,7 +4800,7 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu)
 	if (r)
 		goto out;
 	kvm_mmu_load_pgd(vcpu);
-	kvm_x86_ops.tlb_flush_current(vcpu);
+	static_call(kvm_x86_tlb_flush_current)(vcpu);
 out:
 	return r;
 }
@@ -5080,7 +5081,7 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 		if (is_noncanonical_address(gva, vcpu))
 			return;
 
-		kvm_x86_ops.tlb_flush_gva(vcpu, gva);
+		static_call(kvm_x86_tlb_flush_gva)(vcpu, gva);
 	}
 
 	if (!mmu->invlpg)
@@ -5137,7 +5138,7 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid)
 	}
 
 	if (tlb_flush)
-		kvm_x86_ops.tlb_flush_gva(vcpu, gva);
+		static_call(kvm_x86_tlb_flush_gva)(vcpu, gva);
 
 	++vcpu->stat.invlpg;