Merge branch kvm-arm64/mmu/mapping-levels into kvmarm-master/next

Revamp the KVM/arm64 THP code by parsing the userspace
page tables instead of relying on an infrastructure that
is about to disappear (we are the last user).

* kvm-arm64/mmu/mapping-levels:
  KVM: Get rid of kvm_get_pfn()
  KVM: arm64: Use get_page() instead of kvm_get_pfn()
  KVM: Remove kvm_is_transparent_hugepage() and PageTransCompoundMap()
  KVM: arm64: Avoid mapping size adjustment on permission fault
  KVM: arm64: Walk userspace page tables to compute the THP mapping size
  KVM: arm64: Introduce helper to retrieve a PTE and its level

Signed-off-by: Marc Zyngier <maz@kernel.org>

arch/arm64/include/asm/kvm_pgtable.h

@@ -432,6 +432,26 @@ int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size);
 int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
 		     struct kvm_pgtable_walker *walker);
 
+/**
+ * kvm_pgtable_get_leaf() - Walk a page-table and retrieve the leaf entry
+ *			    with its level.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_*_init()
+ *		or a similar initialiser.
+ * @addr:	Input address for the start of the walk.
+ * @ptep:	Pointer to storage for the retrieved PTE.
+ * @level:	Pointer to storage for the level of the retrieved PTE.
+ *
+ * The offset of @addr within a page is ignored.
+ *
+ * The walker will walk the page-table entries corresponding to the input
+ * address specified, retrieving the leaf corresponding to this address.
+ * Invalid entries are treated as leaf entries.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
+			 kvm_pte_t *ptep, u32 *level);
+
 /**
  * kvm_pgtable_stage2_find_range() - Find a range of Intermediate Physical
  *				     Addresses with compatible permission

arch/arm64/kvm/hyp/pgtable.c

@@ -326,6 +326,45 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
 	return _kvm_pgtable_walk(&walk_data);
 }
 
+struct leaf_walk_data {
+	kvm_pte_t	pte;
+	u32		level;
+};
+
+static int leaf_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
+		       enum kvm_pgtable_walk_flags flag, void * const arg)
+{
+	struct leaf_walk_data *data = arg;
+
+	data->pte   = *ptep;
+	data->level = level;
+
+	return 0;
+}
+
+int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
+			 kvm_pte_t *ptep, u32 *level)
+{
+	struct leaf_walk_data data;
+	struct kvm_pgtable_walker walker = {
+		.cb	= leaf_walker,
+		.flags	= KVM_PGTABLE_WALK_LEAF,
+		.arg	= &data,
+	};
+	int ret;
+
+	ret = kvm_pgtable_walk(pgt, ALIGN_DOWN(addr, PAGE_SIZE),
+			       PAGE_SIZE, &walker);
+	if (!ret) {
+		if (ptep)
+			*ptep  = data.pte;
+		if (level)
+			*level = data.level;
+	}
+
+	return ret;
+}
+
 struct hyp_map_data {
 	u64				phys;
 	kvm_pte_t			attr;

arch/arm64/kvm/mmu.c

@@ -433,6 +433,32 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 	return 0;
 }
 
+static struct kvm_pgtable_mm_ops kvm_user_mm_ops = {
+	/* We shouldn't need any other callback to walk the PT */
+	.phys_to_virt		= kvm_host_va,
+};
+
+static int get_user_mapping_size(struct kvm *kvm, u64 addr)
+{
+	struct kvm_pgtable pgt = {
+		.pgd		= (kvm_pte_t *)kvm->mm->pgd,
+		.ia_bits	= VA_BITS,
+		.start_level	= (KVM_PGTABLE_MAX_LEVELS -
+				   CONFIG_PGTABLE_LEVELS),
+		.mm_ops		= &kvm_user_mm_ops,
+	};
+	kvm_pte_t pte = 0;	/* Keep GCC quiet... */
+	u32 level = ~0;
+	int ret;
+
+	ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level);
+	VM_BUG_ON(ret);
+	VM_BUG_ON(level >= KVM_PGTABLE_MAX_LEVELS);
+	VM_BUG_ON(!(pte & PTE_VALID));
+
+	return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level));
+}
+
 static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = {
 	.zalloc_page		= stage2_memcache_zalloc_page,
 	.zalloc_pages_exact	= kvm_host_zalloc_pages_exact,
@@ -780,7 +806,7 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot,
  * Returns the size of the mapping.
  */
 static unsigned long
-transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
+transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			    unsigned long hva, kvm_pfn_t *pfnp,
 			    phys_addr_t *ipap)
 {
@@ -791,8 +817,8 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
 	 * sure that the HVA and IPA are sufficiently aligned and that the
 	 * block map is contained within the memslot.
 	 */
-	if (kvm_is_transparent_hugepage(pfn) &&
-	    fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) {
+	if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE) &&
+	    get_user_mapping_size(kvm, hva) >= PMD_SIZE) {
 		/*
 		 * The address we faulted on is backed by a transparent huge
 		 * page.  However, because we map the compound huge page and
@@ -814,7 +840,7 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
 		*ipap &= PMD_MASK;
 		kvm_release_pfn_clean(pfn);
 		pfn &= ~(PTRS_PER_PMD - 1);
-		kvm_get_pfn(pfn);
+		get_page(pfn_to_page(pfn));
 		*pfnp = pfn;
 
 		return PMD_SIZE;
@@ -1050,9 +1076,14 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * If we are not forced to use page mapping, check if we are
 	 * backed by a THP and thus use block mapping if possible.
 	 */
-	if (vma_pagesize == PAGE_SIZE && !(force_pte || device))
-		vma_pagesize = transparent_hugepage_adjust(memslot, hva,
-							   &pfn, &fault_ipa);
+	if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) {
+		if (fault_status == FSC_PERM && fault_granule > PAGE_SIZE)
+			vma_pagesize = fault_granule;
+		else
+			vma_pagesize = transparent_hugepage_adjust(kvm, memslot,
+								   hva, &pfn,
+								   &fault_ipa);
+	}
 
 	if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) {
 		/* Check the VMM hasn't introduced a new VM_SHARED VMA */

include/linux/kvm_host.h

@@ -824,7 +824,6 @@ void kvm_release_pfn_clean(kvm_pfn_t pfn);
 void kvm_release_pfn_dirty(kvm_pfn_t pfn);
 void kvm_set_pfn_dirty(kvm_pfn_t pfn);
 void kvm_set_pfn_accessed(kvm_pfn_t pfn);
-void kvm_get_pfn(kvm_pfn_t pfn);
 
 void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache);
 int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,

include/linux/page-flags.h

@@ -632,43 +632,6 @@ static inline int PageTransCompound(struct page *page)
 	return PageCompound(page);
 }
 
-/*
- * PageTransCompoundMap is the same as PageTransCompound, but it also
- * guarantees the primary MMU has the entire compound page mapped
- * through pmd_trans_huge, which in turn guarantees the secondary MMUs
- * can also map the entire compound page. This allows the secondary
- * MMUs to call get_user_pages() only once for each compound page and
- * to immediately map the entire compound page with a single secondary
- * MMU fault. If there will be a pmd split later, the secondary MMUs
- * will get an update through the MMU notifier invalidation through
- * split_huge_pmd().
- *
- * Unlike PageTransCompound, this is safe to be called only while
- * split_huge_pmd() cannot run from under us, like if protected by the
- * MMU notifier, otherwise it may result in page->_mapcount check false
- * positives.
- *
- * We have to treat page cache THP differently since every subpage of it
- * would get _mapcount inc'ed once it is PMD mapped.  But, it may be PTE
- * mapped in the current process so comparing subpage's _mapcount to
- * compound_mapcount to filter out PTE mapped case.
- */
-static inline int PageTransCompoundMap(struct page *page)
-{
-	struct page *head;
-
-	if (!PageTransCompound(page))
-		return 0;
-
-	if (PageAnon(page))
-		return atomic_read(&page->_mapcount) < 0;
-
-	head = compound_head(page);
-	/* File THP is PMD mapped and not PTE mapped */
-	return atomic_read(&page->_mapcount) ==
-	       atomic_read(compound_mapcount_ptr(head));
-}
-
 /*
  * PageTransTail returns true for both transparent huge pages
  * and hugetlbfs pages, so it should only be called when it's known

virt/kvm/kvm_main.c

@@ -189,16 +189,6 @@ bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
 	return true;
 }
 
-bool kvm_is_transparent_hugepage(kvm_pfn_t pfn)
-{
-	struct page *page = pfn_to_page(pfn);
-
-	if (!PageTransCompoundMap(page))
-		return false;
-
-	return is_transparent_hugepage(compound_head(page));
-}
-
 /*
  * Switches to specified vcpu, until a matching vcpu_put()
  */
@@ -2225,7 +2215,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
 	 * Get a reference here because callers of *hva_to_pfn* and
 	 * *gfn_to_pfn* ultimately call kvm_release_pfn_clean on the
 	 * returned pfn.  This is only needed if the VMA has VM_MIXEDMAP
-	 * set, but the kvm_get_pfn/kvm_release_pfn_clean pair will
+	 * set, but the kvm_try_get_pfn/kvm_release_pfn_clean pair will
 	 * simply do nothing for reserved pfns.
 	 *
 	 * Whoever called remap_pfn_range is also going to call e.g.
@@ -2622,13 +2612,6 @@ void kvm_set_pfn_accessed(kvm_pfn_t pfn)
 }
 EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
 
-void kvm_get_pfn(kvm_pfn_t pfn)
-{
-	if (!kvm_is_reserved_pfn(pfn))
-		get_page(pfn_to_page(pfn));
-}
-EXPORT_SYMBOL_GPL(kvm_get_pfn);
-
 static int next_segment(unsigned long len, int offset)
 {
 	if (len > PAGE_SIZE - offset)