[RFC PATCH 10/18] KVM: arm64: Add KVM Userfault support

[James Houghton <jthoughton@google.com>]

Support comes in three parts:
1. When KVM Userfault is enabled, only install PAGE_SIZE PTEs. This
   prevents us from being able to map a userfault-enabled pfn with a
   huge PTE in response to a fault on a non-userfault pfn.
2. When we get KVM_PFN_ERR_USERFAULT from __gfn_to_pfn_memslot, return a
   memory fault to userspace.
3. When KVM Userfault is enabled for a particular kvm_gfn_range, unmap
   it, so that we can get faults on it.

Signed-off-by: James Houghton <jthoughton@google.com>
---
 arch/arm64/kvm/Kconfig |  1 +
 arch/arm64/kvm/mmu.c   | 36 ++++++++++++++++++++++++++++++++++--
 2 files changed, 35 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 58f09370d17e..358153d91d58 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -37,6 +37,7 @@ menuconfig KVM
 	select HAVE_KVM_VCPU_RUN_PID_CHANGE
 	select SCHED_INFO
 	select GUEST_PERF_EVENTS if PERF_EVENTS
+	select KVM_USERFAULT
 	help
 	  Support hosting virtualized guest machines.
 
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 8bcab0cc3fe9..ac283e606516 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1434,7 +1434,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * logging_active is guaranteed to never be true for VM_PFNMAP
 	 * memslots.
 	 */
-	if (logging_active) {
+	if (logging_active || kvm->userfault) {
 		force_pte = true;
 		vma_shift = PAGE_SHIFT;
 	} else {
@@ -1494,8 +1494,15 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		kvm_send_hwpoison_signal(hva, vma_shift);
 		return 0;
 	}
-	if (is_error_noslot_pfn(pfn))
+	if (is_error_noslot_pfn(pfn)) {
+		if (pfn == KVM_PFN_ERR_USERFAULT)
+			kvm_prepare_memory_fault_exit(vcpu, gfn << PAGE_SHIFT,
+						      PAGE_SIZE, write_fault,
+						      /*exec=*/false,
+						      /*private=*/false,
+						      /*userfault=*/true);
 		return -EFAULT;
+	}
 
 	if (kvm_is_device_pfn(pfn)) {
 		/*
@@ -2105,3 +2112,28 @@ void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled)
 
 	trace_kvm_toggle_cache(*vcpu_pc(vcpu), was_enabled, now_enabled);
 }
+
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
+					struct kvm_gfn_range *range)
+{
+	unsigned long attrs = range->arg.attributes;
+
+	/*
+	 * We only need to unmap if we're enabling userfault. Disabling it
+	 * does not need an unmap. An unmap to get huge mappings will come
+	 * later.
+	 */
+	if (attrs & KVM_MEMORY_ATTRIBUTE_USERFAULT)
+		kvm_unmap_gfn_range(kvm, range);
+
+	return false;
+}
+
+bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
+					 struct kvm_gfn_range *range)
+{
+	/* Nothing to do! */
+	return false;
+}
+#endif
-- 
2.45.2.993.g49e7a77208-goog