[RFC PATCH v2 08/11] KVM: arm64: Handle guest_memfd()-backed guest page faults

[Fuad Tabba <tabba@google.com>]

Add arm64 support for handling guest page faults on guest_memfd
backed memslots.

For now, the fault granule is restricted to PAGE_SIZE.

Signed-off-by: Fuad Tabba <tabba@google.com>
---
 arch/arm64/kvm/mmu.c     | 84 ++++++++++++++++++++++++++--------------
 include/linux/kvm_host.h |  5 +++
 virt/kvm/kvm_main.c      |  5 ---
 3 files changed, 61 insertions(+), 33 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 1ec362d0d093..c1f3ddb88cb9 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1430,6 +1430,33 @@ static bool kvm_vma_mte_allowed(struct vm_area_struct *vma)
 	return vma->vm_flags & VM_MTE_ALLOWED;
 }
 
+static kvm_pfn_t faultin_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+			     gfn_t gfn, bool write_fault, bool *writable,
+			     struct page **page, bool is_private)
+{
+	kvm_pfn_t pfn;
+	int ret;
+
+	if (!is_private)
+		return __kvm_faultin_pfn(slot, gfn, write_fault ? FOLL_WRITE : 0, writable, page);
+
+	*writable = false;
+
+	if (WARN_ON_ONCE(write_fault && memslot_is_readonly(slot)))
+		return KVM_PFN_ERR_NOSLOT_MASK;
+
+	ret = kvm_gmem_get_pfn(kvm, slot, gfn, &pfn, page, NULL);
+	if (!ret) {
+		*writable = write_fault;
+		return pfn;
+	}
+
+	if (ret == -EHWPOISON)
+		return KVM_PFN_ERR_HWPOISON;
+
+	return KVM_PFN_ERR_NOSLOT_MASK;
+}
+
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			  struct kvm_s2_trans *nested,
 			  struct kvm_memory_slot *memslot, unsigned long hva,
@@ -1437,24 +1464,25 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 {
 	int ret = 0;
 	bool write_fault, writable;
-	bool exec_fault, mte_allowed;
+	bool exec_fault, mte_allowed = false;
 	bool device = false, vfio_allow_any_uc = false;
 	unsigned long mmu_seq;
 	phys_addr_t ipa = fault_ipa;
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma = NULL;
 	short vma_shift;
-	gfn_t gfn;
+	gfn_t gfn = ipa >> PAGE_SHIFT;
 	kvm_pfn_t pfn;
 	bool logging_active = memslot_is_logging(memslot);
-	bool force_pte = logging_active;
-	long vma_pagesize, fault_granule;
+	bool is_private = kvm_mem_is_private(kvm, gfn);
+	bool force_pte = logging_active || is_private;
+	long vma_pagesize, fault_granule = PAGE_SIZE;
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
 	struct kvm_pgtable *pgt;
 	struct page *page;
 
-	if (fault_is_perm)
+	if (fault_is_perm && !is_private)
 		fault_granule = kvm_vcpu_trap_get_perm_fault_granule(vcpu);
 	write_fault = kvm_is_write_fault(vcpu);
 	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
@@ -1478,24 +1506,30 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			return ret;
 	}
 
+	mmap_read_lock(current->mm);
+
 	/*
 	 * Let's check if we will get back a huge page backed by hugetlbfs, or
 	 * get block mapping for device MMIO region.
 	 */
-	mmap_read_lock(current->mm);
-	vma = vma_lookup(current->mm, hva);
-	if (unlikely(!vma)) {
-		kvm_err("Failed to find VMA for hva 0x%lx\n", hva);
-		mmap_read_unlock(current->mm);
-		return -EFAULT;
-	}
+	if (!is_private) {
+		vma = vma_lookup(current->mm, hva);
+		if (unlikely(!vma)) {
+			kvm_err("Failed to find VMA for hva 0x%lx\n", hva);
+			mmap_read_unlock(current->mm);
+			return -EFAULT;
+		}
 
-	/*
-	 * logging_active is guaranteed to never be true for VM_PFNMAP
-	 * memslots.
-	 */
-	if (WARN_ON_ONCE(logging_active && (vma->vm_flags & VM_PFNMAP)))
-		return -EFAULT;
+		/*
+		 * logging_active is guaranteed to never be true for VM_PFNMAP
+		 * memslots.
+		 */
+		if (WARN_ON_ONCE(logging_active && (vma->vm_flags & VM_PFNMAP)))
+			return -EFAULT;
+
+		vfio_allow_any_uc = vma->vm_flags & VM_ALLOW_ANY_UNCACHED;
+		mte_allowed = kvm_vma_mte_allowed(vma);
+	}
 
 	if (force_pte)
 		vma_shift = PAGE_SHIFT;
@@ -1565,18 +1599,13 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		ipa &= ~(vma_pagesize - 1);
 	}
 
-	gfn = ipa >> PAGE_SHIFT;
-	mte_allowed = kvm_vma_mte_allowed(vma);
-
-	vfio_allow_any_uc = vma->vm_flags & VM_ALLOW_ANY_UNCACHED;
-
 	/* Don't use the VMA after the unlock -- it may have vanished */
 	vma = NULL;
 
 	/*
 	 * Read mmu_invalidate_seq so that KVM can detect if the results of
-	 * vma_lookup() or __kvm_faultin_pfn() become stale prior to
-	 * acquiring kvm->mmu_lock.
+	 * vma_lookup() or faultin_pfn() become stale prior to acquiring
+	 * kvm->mmu_lock.
 	 *
 	 * Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs
 	 * with the smp_wmb() in kvm_mmu_invalidate_end().
@@ -1584,8 +1613,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	mmu_seq = vcpu->kvm->mmu_invalidate_seq;
 	mmap_read_unlock(current->mm);
 
-	pfn = __kvm_faultin_pfn(memslot, gfn, write_fault ? FOLL_WRITE : 0,
-				&writable, &page);
+	pfn = faultin_pfn(kvm, memslot, gfn, write_fault, &writable, &page, is_private);
 	if (pfn == KVM_PFN_ERR_HWPOISON) {
 		kvm_send_hwpoison_signal(hva, vma_shift);
 		return 0;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index e57cdf4e3f3f..42397fc4a1fb 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1864,6 +1864,11 @@ static inline int memslot_id(struct kvm *kvm, gfn_t gfn)
 	return gfn_to_memslot(kvm, gfn)->id;
 }
 
+static inline bool memslot_is_readonly(const struct kvm_memory_slot *slot)
+{
+	return slot->flags & KVM_MEM_READONLY;
+}
+
 static inline gfn_t
 hva_to_gfn_memslot(unsigned long hva, struct kvm_memory_slot *slot)
 {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 40e4ed512923..9f913a7fc44b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2622,11 +2622,6 @@ unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn)
 	return size;
 }
 
-static bool memslot_is_readonly(const struct kvm_memory_slot *slot)
-{
-	return slot->flags & KVM_MEM_READONLY;
-}
-
 static unsigned long __gfn_to_hva_many(const struct kvm_memory_slot *slot, gfn_t gfn,
 				       gfn_t *nr_pages, bool write)
 {
-- 
2.48.1.262.g85cc9f2d1e-goog