[PATCH v4 1/6] KVM: x86/mmu: Avoid indirect call for get_cr3

[Mathias Krause <minipli@grsecurity.net>]

From: Paolo Bonzini <pbonzini@redhat.com>

Most of the time, calls to get_guest_pgd result in calling
kvm_read_cr3 (the exception is only nested TDP).  Hardcode
the default instead of using the get_cr3 function, avoiding
a retpoline if they are enabled.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Mathias Krause <minipli@grsecurity.net>
---
 arch/x86/kvm/mmu/mmu.c         | 31 ++++++++++++++++++++-----------
 arch/x86/kvm/mmu/paging_tmpl.h |  2 +-
 2 files changed, 21 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 144c5a01cd77..9046a892998e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -242,6 +242,20 @@ static struct kvm_mmu_role_regs vcpu_to_role_regs(struct kvm_vcpu *vcpu)
 	return regs;
 }
 
+static unsigned long get_guest_cr3(struct kvm_vcpu *vcpu)
+{
+	return kvm_read_cr3(vcpu);
+}
+
+static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu,
+						  struct kvm_mmu *mmu)
+{
+	if (IS_ENABLED(CONFIG_RETPOLINE) && mmu->get_guest_pgd == get_guest_cr3)
+		return kvm_read_cr3(vcpu);
+
+	return mmu->get_guest_pgd(vcpu);
+}
+
 static inline bool kvm_available_flush_tlb_with_range(void)
 {
 	return kvm_x86_ops.tlb_remote_flush_with_range;
@@ -3731,7 +3745,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 	int quadrant, i, r;
 	hpa_t root;
 
-	root_pgd = mmu->get_guest_pgd(vcpu);
+	root_pgd = kvm_mmu_get_guest_pgd(vcpu, mmu);
 	root_gfn = root_pgd >> PAGE_SHIFT;
 
 	if (mmu_check_root(vcpu, root_gfn))
@@ -4181,7 +4195,7 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 	arch.token = alloc_apf_token(vcpu);
 	arch.gfn = gfn;
 	arch.direct_map = vcpu->arch.mmu->root_role.direct;
-	arch.cr3 = vcpu->arch.mmu->get_guest_pgd(vcpu);
+	arch.cr3 = kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu);
 
 	return kvm_setup_async_pf(vcpu, cr2_or_gpa,
 				  kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
@@ -4200,7 +4214,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 		return;
 
 	if (!vcpu->arch.mmu->root_role.direct &&
-	      work->arch.cr3 != vcpu->arch.mmu->get_guest_pgd(vcpu))
+	      work->arch.cr3 != kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu))
 		return;
 
 	kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL);
@@ -4604,11 +4618,6 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd);
 
-static unsigned long get_cr3(struct kvm_vcpu *vcpu)
-{
-	return kvm_read_cr3(vcpu);
-}
-
 static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
 			   unsigned int access)
 {
@@ -5159,7 +5168,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu,
 	context->page_fault = kvm_tdp_page_fault;
 	context->sync_page = nonpaging_sync_page;
 	context->invlpg = NULL;
-	context->get_guest_pgd = get_cr3;
+	context->get_guest_pgd = get_guest_cr3;
 	context->get_pdptr = kvm_pdptr_read;
 	context->inject_page_fault = kvm_inject_page_fault;
 
@@ -5309,7 +5318,7 @@ static void init_kvm_softmmu(struct kvm_vcpu *vcpu,
 
 	kvm_init_shadow_mmu(vcpu, cpu_role);
 
-	context->get_guest_pgd     = get_cr3;
+	context->get_guest_pgd     = get_guest_cr3;
 	context->get_pdptr         = kvm_pdptr_read;
 	context->inject_page_fault = kvm_inject_page_fault;
 }
@@ -5323,7 +5332,7 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu,
 		return;
 
 	g_context->cpu_role.as_u64   = new_mode.as_u64;
-	g_context->get_guest_pgd     = get_cr3;
+	g_context->get_guest_pgd     = get_guest_cr3;
 	g_context->get_pdptr         = kvm_pdptr_read;
 	g_context->inject_page_fault = kvm_inject_page_fault;
 
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index a056f2773dd9..8417ecbc3887 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -324,7 +324,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	trace_kvm_mmu_pagetable_walk(addr, access);
 retry_walk:
 	walker->level = mmu->cpu_role.base.level;
-	pte           = mmu->get_guest_pgd(vcpu);
+	pte           = kvm_mmu_get_guest_pgd(vcpu, mmu);
 	have_ad       = PT_HAVE_ACCESSED_DIRTY(mmu);
 
 #if PTTYPE == 64
-- 
2.39.2