Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e50799d..594368f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -63,7 +63,14 @@
 struct page *huge_zero_page __read_mostly;
 unsigned long huge_zero_pfn __read_mostly = ~0UL;
 
-bool transparent_hugepage_enabled(struct vm_area_struct *vma)
+static inline bool file_thp_enabled(struct vm_area_struct *vma)
+{
+	return transhuge_vma_enabled(vma, vma->vm_flags) && vma->vm_file &&
+	       !inode_is_open_for_write(vma->vm_file->f_inode) &&
+	       (vma->vm_flags & VM_EXEC);
+}
+
+bool transparent_hugepage_active(struct vm_area_struct *vma)
 {
 	/* The addr is used to check if the vma size fits */
 	unsigned long addr = (vma->vm_end & HPAGE_PMD_MASK) - HPAGE_PMD_SIZE;
@@ -74,6 +81,8 @@
 		return __transparent_hugepage_enabled(vma);
 	if (vma_is_shmem(vma))
 		return shmem_huge_enabled(vma);
+	if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS))
+		return file_thp_enabled(vma);
 
 	return false;
 }
@@ -306,35 +315,14 @@
 static struct kobj_attribute hpage_pmd_size_attr =
 	__ATTR_RO(hpage_pmd_size);
 
-#ifdef CONFIG_DEBUG_VM
-static ssize_t debug_cow_show(struct kobject *kobj,
-				struct kobj_attribute *attr, char *buf)
-{
-	return single_hugepage_flag_show(kobj, attr, buf,
-				TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG);
-}
-static ssize_t debug_cow_store(struct kobject *kobj,
-			       struct kobj_attribute *attr,
-			       const char *buf, size_t count)
-{
-	return single_hugepage_flag_store(kobj, attr, buf, count,
-				 TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG);
-}
-static struct kobj_attribute debug_cow_attr =
-	__ATTR(debug_cow, 0644, debug_cow_show, debug_cow_store);
-#endif /* CONFIG_DEBUG_VM */
-
 static struct attribute *hugepage_attr[] = {
 	&enabled_attr.attr,
 	&defrag_attr.attr,
 	&use_zero_page_attr.attr,
 	&hpage_pmd_size_attr.attr,
-#if defined(CONFIG_SHMEM) && defined(CONFIG_TRANSPARENT_HUGE_PAGECACHE)
+#ifdef CONFIG_SHMEM
 	&shmem_enabled_attr.attr,
 #endif
-#ifdef CONFIG_DEBUG_VM
-	&debug_cow_attr.attr,
-#endif
 	NULL,
 };
 
@@ -396,7 +384,11 @@
 	struct kobject *hugepage_kobj;
 
 	if (!has_transparent_hugepage()) {
-		transparent_hugepage_flags = 0;
+		/*
+		 * Hardware doesn't support hugepages, hence disable
+		 * DAX PMD support.
+		 */
+		transparent_hugepage_flags = 1 << TRANSPARENT_HUGEPAGE_NEVER_DAX;
 		return -EINVAL;
 	}
 
@@ -522,6 +514,17 @@
 	set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
 }
 
+bool is_transparent_hugepage(struct page *page)
+{
+	if (!PageCompound(page))
+		return false;
+
+	page = compound_head(page);
+	return is_huge_zero_page(page) ||
+	       page[1].compound_dtor == TRANSHUGE_PAGE_DTOR;
+}
+EXPORT_SYMBOL_GPL(is_transparent_hugepage);
+
 static unsigned long __thp_get_unmapped_area(struct file *filp,
 		unsigned long addr, unsigned long len,
 		loff_t off, unsigned long flags, unsigned long size)
@@ -579,18 +582,19 @@
 			struct page *page, gfp_t gfp)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	struct mem_cgroup *memcg;
 	pgtable_t pgtable;
 	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
 	vm_fault_t ret = 0;
 
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 
-	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg, true)) {
+	if (mem_cgroup_charge(page, vma->vm_mm, gfp)) {
 		put_page(page);
 		count_vm_event(THP_FAULT_FALLBACK);
+		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
 		return VM_FAULT_FALLBACK;
 	}
+	cgroup_throttle_swaprate(page, gfp);
 
 	pgtable = pte_alloc_one(vma->vm_mm);
 	if (unlikely(!pgtable)) {
@@ -621,7 +625,6 @@
 			vm_fault_t ret2;
 
 			spin_unlock(vmf->ptl);
-			mem_cgroup_cancel_charge(page, memcg, true);
 			put_page(page);
 			pte_free(vma->vm_mm, pgtable);
 			ret2 = handle_userfault(vmf, VM_UFFD_MISSING);
@@ -632,15 +635,14 @@
 		entry = mk_huge_pmd(page, vma->vm_page_prot);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 		page_add_new_anon_rmap(page, vma, haddr, true);
-		mem_cgroup_commit_charge(page, memcg, false, true);
-		lru_cache_add_active_or_unevictable(page, vma);
+		lru_cache_add_inactive_or_unevictable(page, vma);
 		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
 		set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
 		add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
 		mm_inc_nr_ptes(vma->vm_mm);
 		spin_unlock(vmf->ptl);
 		count_vm_event(THP_FAULT_ALLOC);
-		count_memcg_events(memcg, THP_FAULT_ALLOC, 1);
+		count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC);
 	}
 
 	return 0;
@@ -649,7 +651,6 @@
 release:
 	if (pgtable)
 		pte_free(vma->vm_mm, pgtable);
-	mem_cgroup_cancel_charge(page, memcg, true);
 	put_page(page);
 	return ret;
 
@@ -815,11 +816,24 @@
 		pte_free(mm, pgtable);
 }
 
-vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
+/**
+ * vmf_insert_pfn_pmd_prot - insert a pmd size pfn
+ * @vmf: Structure describing the fault
+ * @pfn: pfn to insert
+ * @pgprot: page protection to use
+ * @write: whether it's a write fault
+ *
+ * Insert a pmd size pfn. See vmf_insert_pfn() for additional info and
+ * also consult the vmf_insert_mixed_prot() documentation when
+ * @pgprot != @vmf->vma->vm_page_prot.
+ *
+ * Return: vm_fault_t value.
+ */
+vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn,
+				   pgprot_t pgprot, bool write)
 {
 	unsigned long addr = vmf->address & PMD_MASK;
 	struct vm_area_struct *vma = vmf->vma;
-	pgprot_t pgprot = vma->vm_page_prot;
 	pgtable_t pgtable = NULL;
 
 	/*
@@ -847,7 +861,7 @@
 	insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, pgtable);
 	return VM_FAULT_NOPAGE;
 }
-EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
+EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd_prot);
 
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma)
@@ -893,11 +907,24 @@
 	spin_unlock(ptl);
 }
 
-vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
+/**
+ * vmf_insert_pfn_pud_prot - insert a pud size pfn
+ * @vmf: Structure describing the fault
+ * @pfn: pfn to insert
+ * @pgprot: page protection to use
+ * @write: whether it's a write fault
+ *
+ * Insert a pud size pfn. See vmf_insert_pfn() for additional info and
+ * also consult the vmf_insert_mixed_prot() documentation when
+ * @pgprot != @vmf->vma->vm_page_prot.
+ *
+ * Return: vm_fault_t value.
+ */
+vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn,
+				   pgprot_t pgprot, bool write)
 {
 	unsigned long addr = vmf->address & PUD_MASK;
 	struct vm_area_struct *vma = vmf->vma;
-	pgprot_t pgprot = vma->vm_page_prot;
 
 	/*
 	 * If we had pud_special, we could avoid all these restrictions,
@@ -918,7 +945,7 @@
 	insert_pfn_pud(vma, addr, vmf->pud, pfn, pgprot, write);
 	return VM_FAULT_NOPAGE;
 }
-EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud);
+EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud_prot);
 #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
 
 static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
@@ -949,6 +976,11 @@
 	 */
 	WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set");
 
+	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
+	if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
+			 (FOLL_PIN | FOLL_GET)))
+		return NULL;
+
 	if (flags & FOLL_WRITE && !pmd_write(*pmd))
 		return NULL;
 
@@ -964,7 +996,7 @@
 	 * device mapped pages can only be returned if the
 	 * caller will manage the page reference count.
 	 */
-	if (!(flags & FOLL_GET))
+	if (!(flags & (FOLL_GET | FOLL_PIN)))
 		return ERR_PTR(-EEXIST);
 
 	pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT;
@@ -972,14 +1004,15 @@
 	if (!*pgmap)
 		return ERR_PTR(-EFAULT);
 	page = pfn_to_page(pfn);
-	get_page(page);
+	if (!try_grab_page(page, flags))
+		page = ERR_PTR(-ENOMEM);
 
 	return page;
 }
 
 int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		  pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
-		  struct vm_area_struct *vma)
+		  struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 {
 	spinlock_t *dst_ptl, *src_ptl;
 	struct page *src_page;
@@ -988,7 +1021,7 @@
 	int ret = -ENOMEM;
 
 	/* Skip if can be re-fill on fault */
-	if (!vma_is_anonymous(vma))
+	if (!vma_is_anonymous(dst_vma))
 		return 0;
 
 	pgtable = pte_alloc_one(dst_mm);
@@ -1012,11 +1045,15 @@
 			pmd = swp_entry_to_pmd(entry);
 			if (pmd_swp_soft_dirty(*src_pmd))
 				pmd = pmd_swp_mksoft_dirty(pmd);
+			if (pmd_swp_uffd_wp(*src_pmd))
+				pmd = pmd_swp_mkuffd_wp(pmd);
 			set_pmd_at(src_mm, addr, src_pmd, pmd);
 		}
 		add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
 		mm_inc_nr_ptes(dst_mm);
 		pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
+		if (!userfaultfd_wp(dst_vma))
+			pmd = pmd_swp_clear_uffd_wp(pmd);
 		set_pmd_at(dst_mm, addr, dst_pmd, pmd);
 		ret = 0;
 		goto out_unlock;
@@ -1033,28 +1070,44 @@
 	 * a page table.
 	 */
 	if (is_huge_zero_pmd(pmd)) {
-		struct page *zero_page;
 		/*
 		 * get_huge_zero_page() will never allocate a new page here,
 		 * since we already have a zero page to copy. It just takes a
 		 * reference.
 		 */
-		zero_page = mm_get_huge_zero_page(dst_mm);
-		set_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd,
-				zero_page);
-		ret = 0;
-		goto out_unlock;
+		mm_get_huge_zero_page(dst_mm);
+		goto out_zero_page;
 	}
 
 	src_page = pmd_page(pmd);
 	VM_BUG_ON_PAGE(!PageHead(src_page), src_page);
+
+	/*
+	 * If this page is a potentially pinned page, split and retry the fault
+	 * with smaller page size.  Normally this should not happen because the
+	 * userspace should use MADV_DONTFORK upon pinned regions.  This is a
+	 * best effort that the pinned pages won't be replaced by another
+	 * random page during the coming copy-on-write.
+	 */
+	if (unlikely(is_cow_mapping(src_vma->vm_flags) &&
+		     atomic_read(&src_mm->has_pinned) &&
+		     page_maybe_dma_pinned(src_page))) {
+		pte_free(dst_mm, pgtable);
+		spin_unlock(src_ptl);
+		spin_unlock(dst_ptl);
+		__split_huge_pmd(src_vma, src_pmd, addr, false, NULL);
+		return -EAGAIN;
+	}
+
 	get_page(src_page);
 	page_dup_rmap(src_page, true);
 	add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
+out_zero_page:
 	mm_inc_nr_ptes(dst_mm);
 	pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
-
 	pmdp_set_wrprotect(src_mm, addr, src_pmd);
+	if (!userfaultfd_wp(dst_vma))
+		pmd = pmd_clear_uffd_wp(pmd);
 	pmd = pmd_mkold(pmd_wrprotect(pmd));
 	set_pmd_at(dst_mm, addr, dst_pmd, pmd);
 
@@ -1092,6 +1145,11 @@
 	if (flags & FOLL_WRITE && !pud_write(*pud))
 		return NULL;
 
+	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
+	if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
+			 (FOLL_PIN | FOLL_GET)))
+		return NULL;
+
 	if (pud_present(*pud) && pud_devmap(*pud))
 		/* pass */;
 	else
@@ -1103,8 +1161,10 @@
 	/*
 	 * device mapped pages can only be returned if the
 	 * caller will manage the page reference count.
+	 *
+	 * At least one of FOLL_GET | FOLL_PIN must be set, so assert that here:
 	 */
-	if (!(flags & FOLL_GET))
+	if (!(flags & (FOLL_GET | FOLL_PIN)))
 		return ERR_PTR(-EEXIST);
 
 	pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT;
@@ -1112,7 +1172,8 @@
 	if (!*pgmap)
 		return ERR_PTR(-EFAULT);
 	page = pfn_to_page(pfn);
-	get_page(page);
+	if (!try_grab_page(page, flags))
+		page = ERR_PTR(-ENOMEM);
 
 	return page;
 }
@@ -1143,6 +1204,16 @@
 		/* No huge zero pud yet */
 	}
 
+	/* Please refer to comments in copy_huge_pmd() */
+	if (unlikely(is_cow_mapping(vma->vm_flags) &&
+		     atomic_read(&src_mm->has_pinned) &&
+		     page_maybe_dma_pinned(pud_page(pud)))) {
+		spin_unlock(src_ptl);
+		spin_unlock(dst_ptl);
+		__split_huge_pud(vma, src_pud, addr);
+		return -EAGAIN;
+	}
+
 	pudp_set_wrprotect(src_mm, addr, src_pud);
 	pud = pud_mkold(pud_wrprotect(pud));
 	set_pud_at(dst_mm, addr, dst_pud, pud);
@@ -1197,271 +1268,73 @@
 	spin_unlock(vmf->ptl);
 }
 
-static vm_fault_t do_huge_pmd_wp_page_fallback(struct vm_fault *vmf,
-			pmd_t orig_pmd, struct page *page)
-{
-	struct vm_area_struct *vma = vmf->vma;
-	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
-	struct mem_cgroup *memcg;
-	pgtable_t pgtable;
-	pmd_t _pmd;
-	int i;
-	vm_fault_t ret = 0;
-	struct page **pages;
-	struct mmu_notifier_range range;
-
-	pages = kmalloc_array(HPAGE_PMD_NR, sizeof(struct page *),
-			      GFP_KERNEL);
-	if (unlikely(!pages)) {
-		ret |= VM_FAULT_OOM;
-		goto out;
-	}
-
-	for (i = 0; i < HPAGE_PMD_NR; i++) {
-		pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE, vma,
-					       vmf->address, page_to_nid(page));
-		if (unlikely(!pages[i] ||
-			     mem_cgroup_try_charge_delay(pages[i], vma->vm_mm,
-				     GFP_KERNEL, &memcg, false))) {
-			if (pages[i])
-				put_page(pages[i]);
-			while (--i >= 0) {
-				memcg = (void *)page_private(pages[i]);
-				set_page_private(pages[i], 0);
-				mem_cgroup_cancel_charge(pages[i], memcg,
-						false);
-				put_page(pages[i]);
-			}
-			kfree(pages);
-			ret |= VM_FAULT_OOM;
-			goto out;
-		}
-		set_page_private(pages[i], (unsigned long)memcg);
-	}
-
-	for (i = 0; i < HPAGE_PMD_NR; i++) {
-		copy_user_highpage(pages[i], page + i,
-				   haddr + PAGE_SIZE * i, vma);
-		__SetPageUptodate(pages[i]);
-		cond_resched();
-	}
-
-	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
-				haddr, haddr + HPAGE_PMD_SIZE);
-	mmu_notifier_invalidate_range_start(&range);
-
-	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
-	if (unlikely(!pmd_same(*vmf->pmd, orig_pmd)))
-		goto out_free_pages;
-	VM_BUG_ON_PAGE(!PageHead(page), page);
-
-	/*
-	 * Leave pmd empty until pte is filled note we must notify here as
-	 * concurrent CPU thread might write to new page before the call to
-	 * mmu_notifier_invalidate_range_end() happens which can lead to a
-	 * device seeing memory write in different order than CPU.
-	 *
-	 * See Documentation/vm/mmu_notifier.rst
-	 */
-	pmdp_huge_clear_flush_notify(vma, haddr, vmf->pmd);
-
-	pgtable = pgtable_trans_huge_withdraw(vma->vm_mm, vmf->pmd);
-	pmd_populate(vma->vm_mm, &_pmd, pgtable);
-
-	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
-		pte_t entry;
-		entry = mk_pte(pages[i], vma->vm_page_prot);
-		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
-		memcg = (void *)page_private(pages[i]);
-		set_page_private(pages[i], 0);
-		page_add_new_anon_rmap(pages[i], vmf->vma, haddr, false);
-		mem_cgroup_commit_charge(pages[i], memcg, false, false);
-		lru_cache_add_active_or_unevictable(pages[i], vma);
-		vmf->pte = pte_offset_map(&_pmd, haddr);
-		VM_BUG_ON(!pte_none(*vmf->pte));
-		set_pte_at(vma->vm_mm, haddr, vmf->pte, entry);
-		pte_unmap(vmf->pte);
-	}
-	kfree(pages);
-
-	smp_wmb(); /* make pte visible before pmd */
-	pmd_populate(vma->vm_mm, vmf->pmd, pgtable);
-	page_remove_rmap(page, true);
-	spin_unlock(vmf->ptl);
-
-	/*
-	 * No need to double call mmu_notifier->invalidate_range() callback as
-	 * the above pmdp_huge_clear_flush_notify() did already call it.
-	 */
-	mmu_notifier_invalidate_range_only_end(&range);
-
-	ret |= VM_FAULT_WRITE;
-	put_page(page);
-
-out:
-	return ret;
-
-out_free_pages:
-	spin_unlock(vmf->ptl);
-	mmu_notifier_invalidate_range_end(&range);
-	for (i = 0; i < HPAGE_PMD_NR; i++) {
-		memcg = (void *)page_private(pages[i]);
-		set_page_private(pages[i], 0);
-		mem_cgroup_cancel_charge(pages[i], memcg, false);
-		put_page(pages[i]);
-	}
-	kfree(pages);
-	goto out;
-}
-
 vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	struct page *page = NULL, *new_page;
-	struct mem_cgroup *memcg;
+	struct page *page;
 	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
-	struct mmu_notifier_range range;
-	gfp_t huge_gfp;			/* for allocation and charge */
-	vm_fault_t ret = 0;
 
 	vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd);
 	VM_BUG_ON_VMA(!vma->anon_vma, vma);
+
 	if (is_huge_zero_pmd(orig_pmd))
-		goto alloc;
+		goto fallback;
+
 	spin_lock(vmf->ptl);
-	if (unlikely(!pmd_same(*vmf->pmd, orig_pmd)))
-		goto out_unlock;
+
+	if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) {
+		spin_unlock(vmf->ptl);
+		return 0;
+	}
 
 	page = pmd_page(orig_pmd);
 	VM_BUG_ON_PAGE(!PageCompound(page) || !PageHead(page), page);
-	/*
-	 * We can only reuse the page if nobody else maps the huge page or it's
-	 * part.
-	 */
+
+	/* Lock page for reuse_swap_page() */
 	if (!trylock_page(page)) {
 		get_page(page);
 		spin_unlock(vmf->ptl);
 		lock_page(page);
 		spin_lock(vmf->ptl);
 		if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) {
+			spin_unlock(vmf->ptl);
 			unlock_page(page);
 			put_page(page);
-			goto out_unlock;
+			return 0;
 		}
 		put_page(page);
 	}
+
+	/*
+	 * We can only reuse the page if nobody else maps the huge page or it's
+	 * part.
+	 */
 	if (reuse_swap_page(page, NULL)) {
 		pmd_t entry;
 		entry = pmd_mkyoung(orig_pmd);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
-		if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry,  1))
+		if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1))
 			update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
-		ret |= VM_FAULT_WRITE;
 		unlock_page(page);
-		goto out_unlock;
-	}
-	unlock_page(page);
-	get_page(page);
-	spin_unlock(vmf->ptl);
-alloc:
-	if (__transparent_hugepage_enabled(vma) &&
-	    !transparent_hugepage_debug_cow()) {
-		huge_gfp = alloc_hugepage_direct_gfpmask(vma);
-		new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER);
-	} else
-		new_page = NULL;
-
-	if (likely(new_page)) {
-		prep_transhuge_page(new_page);
-	} else {
-		if (!page) {
-			split_huge_pmd(vma, vmf->pmd, vmf->address);
-			ret |= VM_FAULT_FALLBACK;
-		} else {
-			ret = do_huge_pmd_wp_page_fallback(vmf, orig_pmd, page);
-			if (ret & VM_FAULT_OOM) {
-				split_huge_pmd(vma, vmf->pmd, vmf->address);
-				ret |= VM_FAULT_FALLBACK;
-			}
-			put_page(page);
-		}
-		count_vm_event(THP_FAULT_FALLBACK);
-		goto out;
-	}
-
-	if (unlikely(mem_cgroup_try_charge_delay(new_page, vma->vm_mm,
-					huge_gfp, &memcg, true))) {
-		put_page(new_page);
-		split_huge_pmd(vma, vmf->pmd, vmf->address);
-		if (page)
-			put_page(page);
-		ret |= VM_FAULT_FALLBACK;
-		count_vm_event(THP_FAULT_FALLBACK);
-		goto out;
-	}
-
-	count_vm_event(THP_FAULT_ALLOC);
-	count_memcg_events(memcg, THP_FAULT_ALLOC, 1);
-
-	if (!page)
-		clear_huge_page(new_page, vmf->address, HPAGE_PMD_NR);
-	else
-		copy_user_huge_page(new_page, page, vmf->address,
-				    vma, HPAGE_PMD_NR);
-	__SetPageUptodate(new_page);
-
-	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
-				haddr, haddr + HPAGE_PMD_SIZE);
-	mmu_notifier_invalidate_range_start(&range);
-
-	spin_lock(vmf->ptl);
-	if (page)
-		put_page(page);
-	if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) {
 		spin_unlock(vmf->ptl);
-		mem_cgroup_cancel_charge(new_page, memcg, true);
-		put_page(new_page);
-		goto out_mn;
-	} else {
-		pmd_t entry;
-		entry = mk_huge_pmd(new_page, vma->vm_page_prot);
-		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
-		pmdp_huge_clear_flush_notify(vma, haddr, vmf->pmd);
-		page_add_new_anon_rmap(new_page, vma, haddr, true);
-		mem_cgroup_commit_charge(new_page, memcg, false, true);
-		lru_cache_add_active_or_unevictable(new_page, vma);
-		set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
-		update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
-		if (!page) {
-			add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
-		} else {
-			VM_BUG_ON_PAGE(!PageHead(page), page);
-			page_remove_rmap(page, true);
-			put_page(page);
-		}
-		ret |= VM_FAULT_WRITE;
+		return VM_FAULT_WRITE;
 	}
+
+	unlock_page(page);
 	spin_unlock(vmf->ptl);
-out_mn:
-	/*
-	 * No need to double call mmu_notifier->invalidate_range() callback as
-	 * the above pmdp_huge_clear_flush_notify() did already call it.
-	 */
-	mmu_notifier_invalidate_range_only_end(&range);
-out:
-	return ret;
-out_unlock:
-	spin_unlock(vmf->ptl);
-	return ret;
+fallback:
+	__split_huge_pmd(vma, vmf->pmd, vmf->address, false, NULL);
+	return VM_FAULT_FALLBACK;
 }
 
 /*
- * FOLL_FORCE or a forced COW break can write even to unwritable pmd's,
- * but only after we've gone through a COW cycle and they are dirty.
+ * FOLL_FORCE can write to even unwritable pmd's, but only
+ * after we've gone through a COW cycle and they are dirty.
  */
 static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
 {
-	return pmd_write(pmd) || ((flags & FOLL_COW) && pmd_dirty(pmd));
+	return pmd_write(pmd) ||
+	       ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
 }
 
 struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
@@ -1487,8 +1360,13 @@
 
 	page = pmd_page(*pmd);
 	VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
+
+	if (!try_grab_page(page, flags))
+		return ERR_PTR(-ENOMEM);
+
 	if (flags & FOLL_TOUCH)
 		touch_pmd(vma, addr, pmd, flags);
+
 	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
 		/*
 		 * We don't mlock() pte-mapped THPs. This way we can avoid
@@ -1517,7 +1395,6 @@
 			goto skip_mlock;
 		if (!trylock_page(page))
 			goto skip_mlock;
-		lru_add_drain();
 		if (page->mapping && !PageDoubleMap(page))
 			mlock_vma_page(page);
 		unlock_page(page);
@@ -1525,8 +1402,6 @@
 skip_mlock:
 	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
 	VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page);
-	if (flags & FOLL_GET)
-		get_page(page);
 
 out:
 	return page;
@@ -1789,10 +1664,10 @@
 	 * pgtable_trans_huge_withdraw after finishing pmdp related
 	 * operations.
 	 */
-	orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd,
-			tlb->fullmm);
+	orig_pmd = pmdp_huge_get_and_clear_full(vma, addr, pmd,
+						tlb->fullmm);
 	tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
-	if (vma_is_dax(vma)) {
+	if (vma_is_special_huge(vma)) {
 		if (arch_needs_pgtable_deposit())
 			zap_deposited_table(tlb->mm, pmd);
 		spin_unlock(ptl);
@@ -1864,19 +1739,13 @@
 }
 
 bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
-		  unsigned long new_addr, unsigned long old_end,
-		  pmd_t *old_pmd, pmd_t *new_pmd)
+		  unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd)
 {
 	spinlock_t *old_ptl, *new_ptl;
 	pmd_t pmd;
 	struct mm_struct *mm = vma->vm_mm;
 	bool force_flush = false;
 
-	if ((old_addr & ~HPAGE_PMD_MASK) ||
-	    (new_addr & ~HPAGE_PMD_MASK) ||
-	    old_end - old_addr < HPAGE_PMD_SIZE)
-		return false;
-
 	/*
 	 * The destination pmd shouldn't be established, free_pgtables()
 	 * should have release it.
@@ -1888,7 +1757,7 @@
 
 	/*
 	 * We don't have to worry about the ordering of src and dst
-	 * ptlocks because exclusive mmap_sem prevents deadlock.
+	 * ptlocks because exclusive mmap_lock prevents deadlock.
 	 */
 	old_ptl = __pmd_trans_huge_lock(old_pmd, vma);
 	if (old_ptl) {
@@ -1924,13 +1793,16 @@
  *  - HPAGE_PMD_NR is protections changed and TLB flush necessary
  */
 int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long addr, pgprot_t newprot, int prot_numa)
+		unsigned long addr, pgprot_t newprot, unsigned long cp_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	spinlock_t *ptl;
 	pmd_t entry;
 	bool preserve_write;
 	int ret;
+	bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
+	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
+	bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
 
 	ptl = __pmd_trans_huge_lock(pmd, vma);
 	if (!ptl)
@@ -1954,6 +1826,8 @@
 			newpmd = swp_entry_to_pmd(entry);
 			if (pmd_swp_soft_dirty(*pmd))
 				newpmd = pmd_swp_mksoft_dirty(newpmd);
+			if (pmd_swp_uffd_wp(*pmd))
+				newpmd = pmd_swp_mkuffd_wp(newpmd);
 			set_pmd_at(mm, addr, pmd, newpmd);
 		}
 		goto unlock;
@@ -1972,9 +1846,9 @@
 		goto unlock;
 
 	/*
-	 * In case prot_numa, we are under down_read(mmap_sem). It's critical
+	 * In case prot_numa, we are under mmap_read_lock(mm). It's critical
 	 * to not clear pmd intermittently to avoid race with MADV_DONTNEED
-	 * which is also under down_read(mmap_sem):
+	 * which is also under mmap_read_lock(mm):
 	 *
 	 *	CPU0:				CPU1:
 	 *				change_huge_pmd(prot_numa=1)
@@ -1997,6 +1871,17 @@
 	entry = pmd_modify(entry, newprot);
 	if (preserve_write)
 		entry = pmd_mk_savedwrite(entry);
+	if (uffd_wp) {
+		entry = pmd_wrprotect(entry);
+		entry = pmd_mkuffd_wp(entry);
+	} else if (uffd_wp_resolve) {
+		/*
+		 * Leave the write bit to be handled by PF interrupt
+		 * handler, then things like COW could be properly
+		 * handled.
+		 */
+		entry = pmd_clear_uffd_wp(entry);
+	}
 	ret = HPAGE_PMD_NR;
 	set_pmd_at(mm, addr, pmd, entry);
 	BUG_ON(vma_is_anonymous(vma) && !preserve_write && pmd_write(entry));
@@ -2056,7 +1941,7 @@
 	 */
 	pudp_huge_get_and_clear_full(tlb->mm, addr, pud, tlb->fullmm);
 	tlb_remove_pud_tlb_entry(tlb, pud, addr);
-	if (vma_is_dax(vma)) {
+	if (vma_is_special_huge(vma)) {
 		spin_unlock(ptl);
 		/* No zero page support yet */
 	} else {
@@ -2145,7 +2030,7 @@
 	struct page *page;
 	pgtable_t pgtable;
 	pmd_t old_pmd, _pmd;
-	bool young, write, soft_dirty, pmd_migration = false;
+	bool young, write, soft_dirty, pmd_migration = false, uffd_wp = false;
 	unsigned long addr;
 	int i;
 
@@ -2165,7 +2050,7 @@
 		 */
 		if (arch_needs_pgtable_deposit())
 			zap_deposited_table(mm, pmd);
-		if (vma_is_dax(vma))
+		if (vma_is_special_huge(vma))
 			return;
 		if (unlikely(is_pmd_migration_entry(old_pmd))) {
 			swp_entry_t entry;
@@ -2206,8 +2091,8 @@
 	 * free), userland could trigger a small page size TLB miss on the
 	 * small sized TLB while the hugepage TLB entry is still established in
 	 * the huge TLB. Some CPU doesn't like that.
-	 * See http://support.amd.com/us/Processor_TechDocs/41322.pdf, Erratum
-	 * 383 on page 93. Intel should be safe but is also warns that it's
+	 * See http://support.amd.com/TechDocs/41322_10h_Rev_Gd.pdf, Erratum
+	 * 383 on page 105. Intel should be safe but is also warns that it's
 	 * only safe if the permission and cache attributes of the two entries
 	 * loaded in the two TLB is identical (which should be the case here).
 	 * But it is generally safer to never allow small and huge TLB entries
@@ -2229,6 +2114,7 @@
 		write = is_write_migration_entry(entry);
 		young = false;
 		soft_dirty = pmd_swp_soft_dirty(old_pmd);
+		uffd_wp = pmd_swp_uffd_wp(old_pmd);
 	} else {
 		page = pmd_page(old_pmd);
 		if (pmd_dirty(old_pmd))
@@ -2236,6 +2122,7 @@
 		write = pmd_write(old_pmd);
 		young = pmd_young(old_pmd);
 		soft_dirty = pmd_soft_dirty(old_pmd);
+		uffd_wp = pmd_uffd_wp(old_pmd);
 	}
 	VM_BUG_ON_PAGE(!page_count(page), page);
 	page_ref_add(page, HPAGE_PMD_NR - 1);
@@ -2260,6 +2147,8 @@
 			entry = swp_entry_to_pte(swp_entry);
 			if (soft_dirty)
 				entry = pte_swp_mksoft_dirty(entry);
+			if (uffd_wp)
+				entry = pte_swp_mkuffd_wp(entry);
 		} else {
 			entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot));
 			entry = maybe_mkwrite(entry, vma);
@@ -2269,6 +2158,8 @@
 				entry = pte_mkold(entry);
 			if (soft_dirty)
 				entry = pte_mksoft_dirty(entry);
+			if (uffd_wp)
+				entry = pte_mkuffd_wp(entry);
 		}
 		pte = pte_offset_map(&_pmd, addr);
 		BUG_ON(!pte_none(*pte));
@@ -2444,13 +2335,13 @@
 
 	/*
 	 * If we're also updating the vma->vm_next->vm_start, if the new
-	 * vm_next->vm_start isn't page aligned and it could previously
+	 * vm_next->vm_start isn't hpage aligned and it could previously
 	 * contain an hugepage: check if we need to split an huge pmd.
 	 */
 	if (adjust_next > 0) {
 		struct vm_area_struct *next = vma->vm_next;
 		unsigned long nstart = next->vm_start;
-		nstart += adjust_next << PAGE_SHIFT;
+		nstart += adjust_next;
 		if (nstart & ~HPAGE_PMD_MASK &&
 		    (nstart & HPAGE_PMD_MASK) >= next->vm_start &&
 		    (nstart & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= next->vm_end)
@@ -2460,8 +2351,8 @@
 
 static void unmap_page(struct page *page)
 {
-	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
-		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC;
+	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_SYNC |
+		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
 
 	VM_BUG_ON_PAGE(!PageHead(page), page);
 
@@ -2473,13 +2364,13 @@
 	VM_WARN_ON_ONCE_PAGE(page_mapped(page), page);
 }
 
-static void remap_page(struct page *page)
+static void remap_page(struct page *page, unsigned int nr)
 {
 	int i;
 	if (PageTransHuge(page)) {
 		remove_migration_ptes(page, page, true);
 	} else {
-		for (i = 0; i < HPAGE_PMD_NR; i++)
+		for (i = 0; i < nr; i++)
 			remove_migration_ptes(page + i, page + i, true);
 	}
 }
@@ -2508,6 +2399,9 @@
 			 (1L << PG_workingset) |
 			 (1L << PG_locked) |
 			 (1L << PG_unevictable) |
+#ifdef CONFIG_64BIT
+			 (1L << PG_arch_2) |
+#endif
 			 (1L << PG_dirty)));
 
 	/* ->mapping in first tail page is compound_mapcount */
@@ -2554,12 +2448,13 @@
 	struct lruvec *lruvec;
 	struct address_space *swap_cache = NULL;
 	unsigned long offset = 0;
+	unsigned int nr = thp_nr_pages(head);
 	int i;
 
 	lruvec = mem_cgroup_page_lruvec(head, pgdat);
 
 	/* complete memcg works before add pages to LRU */
-	mem_cgroup_split_huge_fixup(head);
+	split_page_memcg(head, nr);
 
 	if (PageAnon(head) && PageSwapCache(head)) {
 		swp_entry_t entry = { .val = page_private(head) };
@@ -2569,7 +2464,7 @@
 		xa_lock(&swap_cache->i_pages);
 	}
 
-	for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
+	for (i = nr - 1; i >= 1; i--) {
 		__split_huge_page_tail(head, i, lruvec, list);
 		/* Some pages can be beyond i_size: drop them from page cache */
 		if (head[i].index >= end) {
@@ -2589,7 +2484,7 @@
 
 	ClearPageCompound(head);
 
-	split_page_owner(head, HPAGE_PMD_NR);
+	split_page_owner(head, nr);
 
 	/* See comment in __split_huge_page_tail() */
 	if (PageAnon(head)) {
@@ -2608,9 +2503,15 @@
 
 	spin_unlock_irqrestore(&pgdat->lru_lock, flags);
 
-	remap_page(head);
+	remap_page(head, nr);
 
-	for (i = 0; i < HPAGE_PMD_NR; i++) {
+	if (PageSwapCache(head)) {
+		swp_entry_t entry = { .val = page_private(head) };
+
+		split_swap_cluster(entry);
+	}
+
+	for (i = 0; i < nr; i++) {
 		struct page *subpage = head + i;
 		if (subpage == page)
 			continue;
@@ -2629,7 +2530,7 @@
 
 int total_mapcount(struct page *page)
 {
-	int i, compound, ret;
+	int i, compound, nr, ret;
 
 	VM_BUG_ON_PAGE(PageTail(page), page);
 
@@ -2637,16 +2538,17 @@
 		return atomic_read(&page->_mapcount) + 1;
 
 	compound = compound_mapcount(page);
+	nr = compound_nr(page);
 	if (PageHuge(page))
 		return compound;
 	ret = compound;
-	for (i = 0; i < HPAGE_PMD_NR; i++)
+	for (i = 0; i < nr; i++)
 		ret += atomic_read(&page[i]._mapcount) + 1;
 	/* File pages has compound_mapcount included in _mapcount */
 	if (!PageAnon(page))
-		return ret - compound * HPAGE_PMD_NR;
+		return ret - compound * nr;
 	if (PageDoubleMap(page))
-		ret -= HPAGE_PMD_NR;
+		ret -= nr;
 	return ret;
 }
 
@@ -2691,14 +2593,14 @@
 	page = compound_head(page);
 
 	_total_mapcount = ret = 0;
-	for (i = 0; i < HPAGE_PMD_NR; i++) {
+	for (i = 0; i < thp_nr_pages(page); i++) {
 		mapcount = atomic_read(&page[i]._mapcount) + 1;
 		ret = max(ret, mapcount);
 		_total_mapcount += mapcount;
 	}
 	if (PageDoubleMap(page)) {
 		ret -= 1;
-		_total_mapcount -= HPAGE_PMD_NR;
+		_total_mapcount -= thp_nr_pages(page);
 	}
 	mapcount = compound_mapcount(page);
 	ret += mapcount;
@@ -2715,9 +2617,9 @@
 
 	/* Additional pins from page cache */
 	if (PageAnon(page))
-		extra_pins = PageSwapCache(page) ? HPAGE_PMD_NR : 0;
+		extra_pins = PageSwapCache(page) ? thp_nr_pages(page) : 0;
 	else
-		extra_pins = HPAGE_PMD_NR;
+		extra_pins = thp_nr_pages(page);
 	if (pextra_pins)
 		*pextra_pins = extra_pins;
 	return total_mapcount(page) == page_count(page) - extra_pins - 1;
@@ -2746,24 +2648,23 @@
 {
 	struct page *head = compound_head(page);
 	struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
-	struct deferred_split *ds_queue = get_deferred_split_queue(page);
+	struct deferred_split *ds_queue = get_deferred_split_queue(head);
 	struct anon_vma *anon_vma = NULL;
 	struct address_space *mapping = NULL;
 	int extra_pins, ret;
-	bool mlocked;
 	unsigned long flags;
 	pgoff_t end;
 
 	VM_BUG_ON_PAGE(is_huge_zero_page(head), head);
-	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	VM_BUG_ON_PAGE(!PageCompound(page), page);
+	VM_BUG_ON_PAGE(!PageLocked(head), head);
+	VM_BUG_ON_PAGE(!PageCompound(head), head);
 
-	if (PageWriteback(page))
+	if (PageWriteback(head))
 		return -EBUSY;
 
 	if (PageAnon(head)) {
 		/*
-		 * The caller does not necessarily hold an mmap_sem that would
+		 * The caller does not necessarily hold an mmap_lock that would
 		 * prevent the anon_vma disappearing so we first we take a
 		 * reference to it and then lock the anon_vma for write. This
 		 * is similar to page_lock_anon_vma_read except the write lock
@@ -2809,13 +2710,8 @@
 		goto out_unlock;
 	}
 
-	mlocked = PageMlocked(page);
 	unmap_page(head);
 
-	/* Make sure the page is not on per-CPU pagevec as it takes pin */
-	if (mlocked)
-		lru_add_drain();
-
 	/* prevent PageLRU to go away from under us, and freeze lru stats */
 	spin_lock_irqsave(&pgdata->lru_lock, flags);
 
@@ -2838,28 +2734,23 @@
 			ds_queue->split_queue_len--;
 			list_del(page_deferred_list(head));
 		}
+		spin_unlock(&ds_queue->split_queue_lock);
 		if (mapping) {
-			if (PageSwapBacked(page))
-				__dec_node_page_state(page, NR_SHMEM_THPS);
+			if (PageSwapBacked(head))
+				__dec_node_page_state(head, NR_SHMEM_THPS);
 			else
-				__dec_node_page_state(page, NR_FILE_THPS);
+				__dec_node_page_state(head, NR_FILE_THPS);
 		}
 
-		spin_unlock(&ds_queue->split_queue_lock);
 		__split_huge_page(page, list, end, flags);
-		if (PageSwapCache(head)) {
-			swp_entry_t entry = { .val = page_private(head) };
-
-			ret = split_swap_cluster(entry);
-		} else
-			ret = 0;
+		ret = 0;
 	} else {
 		spin_unlock(&ds_queue->split_queue_lock);
 fail:
 		if (mapping)
 			xa_unlock(&mapping->i_pages);
 		spin_unlock_irqrestore(&pgdata->lru_lock, flags);
-		remap_page(head);
+		remap_page(head, thp_nr_pages(head));
 		ret = -EBUSY;
 	}
 
@@ -3045,7 +2936,7 @@
 
 	return 0;
 }
-DEFINE_SIMPLE_ATTRIBUTE(split_huge_pages_fops, NULL, split_huge_pages_set,
+DEFINE_DEBUGFS_ATTRIBUTE(split_huge_pages_fops, NULL, split_huge_pages_set,
 		"%llu\n");
 
 static int __init split_huge_pages_debugfs(void)
@@ -3103,6 +2994,8 @@
 		pmde = pmd_mksoft_dirty(pmde);
 	if (is_write_migration_entry(entry))
 		pmde = maybe_pmd_mkwrite(pmde, vma);
+	if (pmd_swp_uffd_wp(*pvmw->pmd))
+		pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde));
 
 	flush_cache_range(vma, mmun_start, mmun_start + HPAGE_PMD_SIZE);
 	if (PageAnon(new))