KVM: x86/mmu: Move slot checks from __kvm_faultin_pfn() to kvm_faultin_pfn()

Move the checks related to the validity of an access to a memslot from the
inner __kvm_faultin_pfn() to its sole caller, kvm_faultin_pfn().  This
allows emulating accesses to the APIC access page, which don't need to
resolve a pfn, even if there is a relevant in-progress mmu_notifier
invalidation.  Ditto for accesses to KVM internal memslots from L2, which
KVM also treats as emulated MMIO.

More importantly, this will allow for future cleanup by having the
"no memslot" case bail from kvm_faultin_pfn() very early on.

Go to rather extreme and gross lengths to make the change a glorified
nop, e.g. call into __kvm_faultin_pfn() even when there is no slot, as the
related code is very subtle.  E.g. fault->slot can be nullified if it
points at the APIC access page, some flows in KVM x86 expect fault->pfn
to be KVM_PFN_NOSLOT, while others check only fault->slot, etc.

No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Message-ID: <20240228024147.41573-13-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/mmu/mmu.c

@@ -4291,52 +4291,15 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
 
 static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
-	struct kvm_memory_slot *slot = fault->slot;
 	bool async;
 
-	/*
-	 * Retry the page fault if the gfn hit a memslot that is being deleted
-	 * or moved.  This ensures any existing SPTEs for the old memslot will
-	 * be zapped before KVM inserts a new MMIO SPTE for the gfn.
-	 */
-	if (slot && (slot->flags & KVM_MEMSLOT_INVALID))
-		return RET_PF_RETRY;
-
-	if (slot && slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT) {
-		/*
-		 * Don't map L1's APIC access page into L2, KVM doesn't support
-		 * using APICv/AVIC to accelerate L2 accesses to L1's APIC,
-		 * i.e. the access needs to be emulated.  Emulating access to
-		 * L1's APIC is also correct if L1 is accelerating L2's own
-		 * virtual APIC, but for some reason L1 also maps _L1's_ APIC
-		 * into L2.  Note, vcpu_is_mmio_gpa() always treats access to
-		 * the APIC as MMIO.  Allow an MMIO SPTE to be created, as KVM
-		 * uses different roots for L1 vs. L2, i.e. there is no danger
-		 * of breaking APICv/AVIC for L1.
-		 */
-		if (is_guest_mode(vcpu)) {
-			fault->slot = NULL;
-			fault->pfn = KVM_PFN_NOSLOT;
-			fault->map_writable = false;
-			return RET_PF_CONTINUE;
-		}
-		/*
-		 * If the APIC access page exists but is disabled, go directly
-		 * to emulation without caching the MMIO access or creating a
-		 * MMIO SPTE.  That way the cache doesn't need to be purged
-		 * when the AVIC is re-enabled.
-		 */
-		if (!kvm_apicv_activated(vcpu->kvm))
-			return RET_PF_EMULATE;
-	}
-
 	if (fault->is_private)
 		return kvm_faultin_pfn_private(vcpu, fault);
 
 	async = false;
-	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
-					  fault->write, &fault->map_writable,
-					  &fault->hva);
+	fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, false, false,
+					  &async, fault->write,
+					  &fault->map_writable, &fault->hva);
 	if (!async)
 		return RET_PF_CONTINUE; /* *pfn has correct page already */
 
@@ -4356,15 +4319,16 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	 * to wait for IO.  Note, gup always bails if it is unable to quickly
 	 * get a page and a fatal signal, i.e. SIGKILL, is pending.
 	 */
-	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, true, NULL,
-					  fault->write, &fault->map_writable,
-					  &fault->hva);
+	fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, false, true,
+					  NULL, fault->write,
+					  &fault->map_writable, &fault->hva);
 	return RET_PF_CONTINUE;
 }
 
 static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 			   unsigned int access)
 {
+	struct kvm_memory_slot *slot = fault->slot;
 	int ret;
 
 	/*
@@ -4385,6 +4349,42 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 		return -EFAULT;
 	}
 
+	/*
+	 * Retry the page fault if the gfn hit a memslot that is being deleted
+	 * or moved.  This ensures any existing SPTEs for the old memslot will
+	 * be zapped before KVM inserts a new MMIO SPTE for the gfn.
+	 */
+	if (slot && (slot->flags & KVM_MEMSLOT_INVALID))
+		return RET_PF_RETRY;
+
+	if (slot && slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT) {
+		/*
+		 * Don't map L1's APIC access page into L2, KVM doesn't support
+		 * using APICv/AVIC to accelerate L2 accesses to L1's APIC,
+		 * i.e. the access needs to be emulated.  Emulating access to
+		 * L1's APIC is also correct if L1 is accelerating L2's own
+		 * virtual APIC, but for some reason L1 also maps _L1's_ APIC
+		 * into L2.  Note, vcpu_is_mmio_gpa() always treats access to
+		 * the APIC as MMIO.  Allow an MMIO SPTE to be created, as KVM
+		 * uses different roots for L1 vs. L2, i.e. there is no danger
+		 * of breaking APICv/AVIC for L1.
+		 */
+		if (is_guest_mode(vcpu)) {
+			fault->slot = NULL;
+			fault->pfn = KVM_PFN_NOSLOT;
+			fault->map_writable = false;
+			goto faultin_done;
+		}
+		/*
+		 * If the APIC access page exists but is disabled, go directly
+		 * to emulation without caching the MMIO access or creating a
+		 * MMIO SPTE.  That way the cache doesn't need to be purged
+		 * when the AVIC is re-enabled.
+		 */
+		if (!kvm_apicv_activated(vcpu->kvm))
+			return RET_PF_EMULATE;
+	}
+
 	/*
 	 * Check for a relevant mmu_notifier invalidation event before getting
 	 * the pfn from the primary MMU, and before acquiring mmu_lock.
@@ -4414,6 +4414,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 	if (ret != RET_PF_CONTINUE)
 		return ret;
 
+faultin_done:
 	if (unlikely(is_error_pfn(fault->pfn)))
 		return kvm_handle_error_pfn(vcpu, fault);