1 files changed, 173 insertions, 34 deletions

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 3b9d4d24c361..6db9ef288ec3 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -31,14 +31,21 @@ static phys_addr_t __ro_after_init hyp_idmap_vector;
 
 static unsigned long __ro_after_init io_map_base;
 
-static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end)
+static phys_addr_t __stage2_range_addr_end(phys_addr_t addr, phys_addr_t end,
+					   phys_addr_t size)
 {
-	phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL);
 	phys_addr_t boundary = ALIGN_DOWN(addr + size, size);
 
 	return (boundary - 1 < end - 1) ? boundary : end;
 }
 
+static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL);
+
+	return __stage2_range_addr_end(addr, end, size);
+}
+
 /*
  * Release kvm_mmu_lock periodically if the memory region is large. Otherwise,
  * we may see kernel panics with CONFIG_DETECT_HUNG_TASK,
@@ -75,6 +82,79 @@ static int stage2_apply_range(struct kvm_s2_mmu *mmu, phys_addr_t addr,
 #define stage2_apply_range_resched(mmu, addr, end, fn)			\
 	stage2_apply_range(mmu, addr, end, fn, true)
 
+/*
+ * Get the maximum number of page-tables pages needed to split a range
+ * of blocks into PAGE_SIZE PTEs. It assumes the range is already
+ * mapped at level 2, or at level 1 if allowed.
+ */
+static int kvm_mmu_split_nr_page_tables(u64 range)
+{
+	int n = 0;
+
+	if (KVM_PGTABLE_MIN_BLOCK_LEVEL < 2)
+		n += DIV_ROUND_UP(range, PUD_SIZE);
+	n += DIV_ROUND_UP(range, PMD_SIZE);
+	return n;
+}
+
+static bool need_split_memcache_topup_or_resched(struct kvm *kvm)
+{
+	struct kvm_mmu_memory_cache *cache;
+	u64 chunk_size, min;
+
+	if (need_resched() || rwlock_needbreak(&kvm->mmu_lock))
+		return true;
+
+	chunk_size = kvm->arch.mmu.split_page_chunk_size;
+	min = kvm_mmu_split_nr_page_tables(chunk_size);
+	cache = &kvm->arch.mmu.split_page_cache;
+	return kvm_mmu_memory_cache_nr_free_objects(cache) < min;
+}
+
+static int kvm_mmu_split_huge_pages(struct kvm *kvm, phys_addr_t addr,
+				    phys_addr_t end)
+{
+	struct kvm_mmu_memory_cache *cache;
+	struct kvm_pgtable *pgt;
+	int ret, cache_capacity;
+	u64 next, chunk_size;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	chunk_size = kvm->arch.mmu.split_page_chunk_size;
+	cache_capacity = kvm_mmu_split_nr_page_tables(chunk_size);
+
+	if (chunk_size == 0)
+		return 0;
+
+	cache = &kvm->arch.mmu.split_page_cache;
+
+	do {
+		if (need_split_memcache_topup_or_resched(kvm)) {
+			write_unlock(&kvm->mmu_lock);
+			cond_resched();
+			/* Eager page splitting is best-effort. */
+			ret = __kvm_mmu_topup_memory_cache(cache,
+							   cache_capacity,
+							   cache_capacity);
+			write_lock(&kvm->mmu_lock);
+			if (ret)
+				break;
+		}
+
+		pgt = kvm->arch.mmu.pgt;
+		if (!pgt)
+			return -EINVAL;
+
+		next = __stage2_range_addr_end(addr, end, chunk_size);
+		ret = kvm_pgtable_stage2_split(pgt, addr, next - addr, cache);
+		if (ret)
+			break;
+	} while (addr = next, addr != end);
+
+	return ret;
+}
+
 static bool memslot_is_logging(struct kvm_memory_slot *memslot)
 {
 	return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY);
@@ -131,21 +211,21 @@ static void kvm_s2_free_pages_exact(void *virt, size_t size)
 
 static struct kvm_pgtable_mm_ops kvm_s2_mm_ops;
 
-static void stage2_free_removed_table_rcu_cb(struct rcu_head *head)
+static void stage2_free_unlinked_table_rcu_cb(struct rcu_head *head)
 {
 	struct page *page = container_of(head, struct page, rcu_head);
 	void *pgtable = page_to_virt(page);
 	u32 level = page_private(page);
 
-	kvm_pgtable_stage2_free_removed(&kvm_s2_mm_ops, pgtable, level);
+	kvm_pgtable_stage2_free_unlinked(&kvm_s2_mm_ops, pgtable, level);
 }
 
-static void stage2_free_removed_table(void *addr, u32 level)
+static void stage2_free_unlinked_table(void *addr, u32 level)
 {
 	struct page *page = virt_to_page(addr);
 
 	set_page_private(page, (unsigned long)level);
-	call_rcu(&page->rcu_head, stage2_free_removed_table_rcu_cb);
+	call_rcu(&page->rcu_head, stage2_free_unlinked_table_rcu_cb);
 }
 
 static void kvm_host_get_page(void *addr)
@@ -701,7 +781,7 @@ static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = {
 	.zalloc_page		= stage2_memcache_zalloc_page,
 	.zalloc_pages_exact	= kvm_s2_zalloc_pages_exact,
 	.free_pages_exact	= kvm_s2_free_pages_exact,
-	.free_removed_table	= stage2_free_removed_table,
+	.free_unlinked_table	= stage2_free_unlinked_table,
 	.get_page		= kvm_host_get_page,
 	.put_page		= kvm_s2_put_page,
 	.page_count		= kvm_host_page_count,
@@ -775,6 +855,10 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 	for_each_possible_cpu(cpu)
 		*per_cpu_ptr(mmu->last_vcpu_ran, cpu) = -1;
 
+	 /* The eager page splitting is disabled by default */
+	mmu->split_page_chunk_size = KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT;
+	mmu->split_page_cache.gfp_zero = __GFP_ZERO;
+
 	mmu->pgt = pgt;
 	mmu->pgd_phys = __pa(pgt->pgd);
 	return 0;
@@ -786,6 +870,12 @@ out_free_pgtable:
 	return err;
 }
 
+void kvm_uninit_stage2_mmu(struct kvm *kvm)
+{
+	kvm_free_stage2_pgd(&kvm->arch.mmu);
+	kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache);
+}
+
 static void stage2_unmap_memslot(struct kvm *kvm,
 				 struct kvm_memory_slot *memslot)
 {
@@ -989,39 +1079,66 @@ static void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
 }
 
 /**
- * kvm_mmu_write_protect_pt_masked() - write protect dirty pages
+ * kvm_mmu_split_memory_region() - split the stage 2 blocks into PAGE_SIZE
+ *				   pages for memory slot
  * @kvm:	The KVM pointer
- * @slot:	The memory slot associated with mask
- * @gfn_offset:	The gfn offset in memory slot
- * @mask:	The mask of dirty pages at offset 'gfn_offset' in this memory
- *		slot to be write protected
+ * @slot:	The memory slot to split
  *
- * Walks bits set in mask write protects the associated pte's. Caller must
- * acquire kvm_mmu_lock.
+ * Acquires kvm->mmu_lock. Called with kvm->slots_lock mutex acquired,
+ * serializing operations for VM memory regions.
  */
-static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
-		struct kvm_memory_slot *slot,
-		gfn_t gfn_offset, unsigned long mask)
+static void kvm_mmu_split_memory_region(struct kvm *kvm, int slot)
 {
-	phys_addr_t base_gfn = slot->base_gfn + gfn_offset;
-	phys_addr_t start = (base_gfn +  __ffs(mask)) << PAGE_SHIFT;
-	phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	phys_addr_t start, end;
 
-	stage2_wp_range(&kvm->arch.mmu, start, end);
+	lockdep_assert_held(&kvm->slots_lock);
+
+	slots = kvm_memslots(kvm);
+	memslot = id_to_memslot(slots, slot);
+
+	start = memslot->base_gfn << PAGE_SHIFT;
+	end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
+
+	write_lock(&kvm->mmu_lock);
+	kvm_mmu_split_huge_pages(kvm, start, end);
+	write_unlock(&kvm->mmu_lock);
 }
 
 /*
- * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected
- * dirty pages.
+ * kvm_arch_mmu_enable_log_dirty_pt_masked() - enable dirty logging for selected pages.
+ * @kvm:	The KVM pointer
+ * @slot:	The memory slot associated with mask
+ * @gfn_offset:	The gfn offset in memory slot
+ * @mask:	The mask of pages at offset 'gfn_offset' in this memory
+ *		slot to enable dirty logging on
  *
- * It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to
- * enable dirty logging for them.
+ * Writes protect selected pages to enable dirty logging, and then
+ * splits them to PAGE_SIZE. Caller must acquire kvm->mmu_lock.
  */
 void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 		struct kvm_memory_slot *slot,
 		gfn_t gfn_offset, unsigned long mask)
 {
-	kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
+	phys_addr_t base_gfn = slot->base_gfn + gfn_offset;
+	phys_addr_t start = (base_gfn +  __ffs(mask)) << PAGE_SHIFT;
+	phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	stage2_wp_range(&kvm->arch.mmu, start, end);
+
+	/*
+	 * Eager-splitting is done when manual-protect is set.  We
+	 * also check for initially-all-set because we can avoid
+	 * eager-splitting if initially-all-set is false.
+	 * Initially-all-set equal false implies that huge-pages were
+	 * already split when enabling dirty logging: no need to do it
+	 * again.
+	 */
+	if (kvm_dirty_log_manual_protect_and_init_set(kvm))
+		kvm_mmu_split_huge_pages(kvm, start, end);
 }
 
 static void kvm_send_hwpoison_signal(unsigned long address, short lsb)
@@ -1790,20 +1907,42 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				   const struct kvm_memory_slot *new,
 				   enum kvm_mr_change change)
 {
+	bool log_dirty_pages = new && new->flags & KVM_MEM_LOG_DIRTY_PAGES;
+
 	/*
 	 * At this point memslot has been committed and there is an
 	 * allocated dirty_bitmap[], dirty pages will be tracked while the
 	 * memory slot is write protected.
 	 */
-	if (change != KVM_MR_DELETE && new->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+	if (log_dirty_pages) {
+
+		if (change == KVM_MR_DELETE)
+			return;
+
 		/*
-		 * If we're with initial-all-set, we don't need to write
-		 * protect any pages because they're all reported as dirty.
-		 * Huge pages and normal pages will be write protect gradually.
+		 * Huge and normal pages are write-protected and split
+		 * on either of these two cases:
+		 *
+		 * 1. with initial-all-set: gradually with CLEAR ioctls,
 		 */
-		if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) {
-			kvm_mmu_wp_memory_region(kvm, new->id);
-		}
+		if (kvm_dirty_log_manual_protect_and_init_set(kvm))
+			return;
+		/*
+		 * or
+		 * 2. without initial-all-set: all in one shot when
+		 *    enabling dirty logging.
+		 */
+		kvm_mmu_wp_memory_region(kvm, new->id);
+		kvm_mmu_split_memory_region(kvm, new->id);
+	} else {
+		/*
+		 * Free any leftovers from the eager page splitting cache. Do
+		 * this when deleting, moving, disabling dirty logging, or
+		 * creating the memslot (a nop). Doing it for deletes makes
+		 * sure we don't leak memory, and there's no need to keep the
+		 * cache around for any of the other cases.
+		 */
+		kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache);
 	}
 }
 
@@ -1877,7 +2016,7 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)
 {
-	kvm_free_stage2_pgd(&kvm->arch.mmu);
+	kvm_uninit_stage2_mmu(kvm);
 }
 
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,