1 files changed, 198 insertions, 104 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 3ca89e0279a7..ee335d96fc39 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -8,7 +8,6 @@
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
-#include <linux/sched/coredump.h>
 #include <linux/sched/numa_balancing.h>
 #include <linux/highmem.h>
 #include <linux/hugetlb.h>
@@ -84,6 +83,21 @@ unsigned long huge_anon_orders_madvise __read_mostly;
 unsigned long huge_anon_orders_inherit __read_mostly;
 static bool anon_orders_configured __initdata;
 
+static inline bool file_thp_enabled(struct vm_area_struct *vma)
+{
+	struct inode *inode;
+
+	if (!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS))
+		return false;
+
+	if (!vma->vm_file)
+		return false;
+
+	inode = file_inode(vma->vm_file);
+
+	return !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode);
+}
+
 unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
 					 unsigned long vm_flags,
 					 unsigned long tva_flags,
@@ -109,18 +123,7 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
 	if (!vma->vm_mm)		/* vdso */
 		return 0;
 
-	/*
-	 * Explicitly disabled through madvise or prctl, or some
-	 * architectures may disable THP for some mappings, for
-	 * example, s390 kvm.
-	 * */
-	if ((vm_flags & VM_NOHUGEPAGE) ||
-	    test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
-		return 0;
-	/*
-	 * If the hardware/firmware marked hugepage support disabled.
-	 */
-	if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED))
+	if (thp_disabled_by_hw() || vma_thp_disabled(vma, vm_flags))
 		return 0;
 
 	/* khugepaged doesn't collapse DAX vma, but page fault is fine. */
@@ -612,6 +615,8 @@ static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
 DEFINE_MTHP_STAT_ATTR(anon_fault_alloc, MTHP_STAT_ANON_FAULT_ALLOC);
 DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK);
 DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
+DEFINE_MTHP_STAT_ATTR(zswpout, MTHP_STAT_ZSWPOUT);
+DEFINE_MTHP_STAT_ATTR(swpin, MTHP_STAT_SWPIN);
 DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT);
 DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK);
 #ifdef CONFIG_SHMEM
@@ -630,6 +635,8 @@ static struct attribute *anon_stats_attrs[] = {
 	&anon_fault_fallback_attr.attr,
 	&anon_fault_fallback_charge_attr.attr,
 #ifndef CONFIG_SHMEM
+	&zswpout_attr.attr,
+	&swpin_attr.attr,
 	&swpout_attr.attr,
 	&swpout_fallback_attr.attr,
 #endif
@@ -660,6 +667,8 @@ static struct attribute_group file_stats_attr_grp = {
 
 static struct attribute *any_stats_attrs[] = {
 #ifdef CONFIG_SHMEM
+	&zswpout_attr.attr,
+	&swpin_attr.attr,
 	&swpout_attr.attr,
 	&swpout_fallback_attr.attr,
 #endif
@@ -949,26 +958,6 @@ out:
 }
 __setup("transparent_hugepage=", setup_transparent_hugepage);
 
-static inline int get_order_from_str(const char *size_str)
-{
-	unsigned long size;
-	char *endptr;
-	int order;
-
-	size = memparse(size_str, &endptr);
-
-	if (!is_power_of_2(size))
-		goto err;
-	order = get_order(size);
-	if (BIT(order) & ~THP_ORDERS_ALL_ANON)
-		goto err;
-
-	return order;
-err:
-	pr_err("invalid size %s in thp_anon boot parameter\n", size_str);
-	return -EINVAL;
-}
-
 static char str_dup[PAGE_SIZE] __initdata;
 static int __init setup_thp_anon(char *str)
 {
@@ -980,7 +969,7 @@ static int __init setup_thp_anon(char *str)
 
 	if (!str || strlen(str) + 1 > PAGE_SIZE)
 		goto err;
-	strcpy(str_dup, str);
+	strscpy(str_dup, str);
 
 	always = huge_anon_orders_always;
 	madvise = huge_anon_orders_madvise;
@@ -998,10 +987,22 @@ static int __init setup_thp_anon(char *str)
 				start_size = strsep(&subtoken, "-");
 				end_size = subtoken;
 
-				start = get_order_from_str(start_size);
-				end = get_order_from_str(end_size);
+				start = get_order_from_str(start_size, THP_ORDERS_ALL_ANON);
+				end = get_order_from_str(end_size, THP_ORDERS_ALL_ANON);
 			} else {
-				start = end = get_order_from_str(subtoken);
+				start_size = end_size = subtoken;
+				start = end = get_order_from_str(subtoken,
+								 THP_ORDERS_ALL_ANON);
+			}
+
+			if (start == -EINVAL) {
+				pr_err("invalid size %s in thp_anon boot parameter\n", start_size);
+				goto err;
+			}
+
+			if (end == -EINVAL) {
+				pr_err("invalid size %s in thp_anon boot parameter\n", end_size);
+				goto err;
 			}
 
 			if (start < 0 || end < 0 || start > end)
@@ -1148,47 +1149,87 @@ unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
 }
 EXPORT_SYMBOL_GPL(thp_get_unmapped_area);
 
-static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
-			struct page *page, gfp_t gfp)
+static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct *vma,
+		unsigned long addr)
 {
-	struct vm_area_struct *vma = vmf->vma;
-	struct folio *folio = page_folio(page);
-	pgtable_t pgtable;
-	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
-	vm_fault_t ret = 0;
+	gfp_t gfp = vma_thp_gfp_mask(vma);
+	const int order = HPAGE_PMD_ORDER;
+	struct folio *folio;
 
-	VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
+	folio = vma_alloc_folio(gfp, order, vma, addr & HPAGE_PMD_MASK);
+
+	if (unlikely(!folio)) {
+		count_vm_event(THP_FAULT_FALLBACK);
+		count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK);
+		return NULL;
+	}
 
+	VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
 	if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) {
 		folio_put(folio);
 		count_vm_event(THP_FAULT_FALLBACK);
 		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
-		count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK);
-		count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
-		return VM_FAULT_FALLBACK;
+		count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK);
+		count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
+		return NULL;
 	}
 	folio_throttle_swaprate(folio, gfp);
 
-	pgtable = pte_alloc_one(vma->vm_mm);
-	if (unlikely(!pgtable)) {
-		ret = VM_FAULT_OOM;
-		goto release;
-	}
-
-	folio_zero_user(folio, vmf->address);
+       /*
+	* When a folio is not zeroed during allocation (__GFP_ZERO not used),
+	* folio_zero_user() is used to make sure that the page corresponding
+	* to the faulting address will be hot in the cache after zeroing.
+	*/
+	if (!alloc_zeroed())
+		folio_zero_user(folio, addr);
 	/*
 	 * The memory barrier inside __folio_mark_uptodate makes sure that
 	 * folio_zero_user writes become visible before the set_pmd_at()
 	 * write.
 	 */
 	__folio_mark_uptodate(folio);
+	return folio;
+}
+
+static void map_anon_folio_pmd(struct folio *folio, pmd_t *pmd,
+		struct vm_area_struct *vma, unsigned long haddr)
+{
+	pmd_t entry;
+
+	entry = mk_huge_pmd(&folio->page, vma->vm_page_prot);
+	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+	folio_add_new_anon_rmap(folio, vma, haddr, RMAP_EXCLUSIVE);
+	folio_add_lru_vma(folio, vma);
+	set_pmd_at(vma->vm_mm, haddr, pmd, entry);
+	update_mmu_cache_pmd(vma, haddr, pmd);
+	add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
+	count_vm_event(THP_FAULT_ALLOC);
+	count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC);
+	count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC);
+}
+
+static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf)
+{
+	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
+	struct vm_area_struct *vma = vmf->vma;
+	struct folio *folio;
+	pgtable_t pgtable;
+	vm_fault_t ret = 0;
+
+	folio = vma_alloc_anon_folio_pmd(vma, vmf->address);
+	if (unlikely(!folio))
+		return VM_FAULT_FALLBACK;
+
+	pgtable = pte_alloc_one(vma->vm_mm);
+	if (unlikely(!pgtable)) {
+		ret = VM_FAULT_OOM;
+		goto release;
+	}
 
 	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
 	if (unlikely(!pmd_none(*vmf->pmd))) {
 		goto unlock_release;
 	} else {
-		pmd_t entry;
-
 		ret = check_stable_address_space(vma->vm_mm);
 		if (ret)
 			goto unlock_release;
@@ -1202,21 +1243,11 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 			VM_BUG_ON(ret & VM_FAULT_FALLBACK);
 			return ret;
 		}
-
-		entry = mk_huge_pmd(page, vma->vm_page_prot);
-		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
-		folio_add_new_anon_rmap(folio, vma, haddr, RMAP_EXCLUSIVE);
-		folio_add_lru_vma(folio, vma);
 		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
-		set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
-		update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
-		add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
+		map_anon_folio_pmd(folio, vmf->pmd, vma, haddr);
 		mm_inc_nr_ptes(vma->vm_mm);
 		deferred_split_folio(folio, false);
 		spin_unlock(vmf->ptl);
-		count_vm_event(THP_FAULT_ALLOC);
-		count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC);
-		count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC);
 	}
 
 	return 0;
@@ -1283,8 +1314,6 @@ static void set_huge_zero_folio(pgtable_t pgtable, struct mm_struct *mm,
 vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	gfp_t gfp;
-	struct folio *folio;
 	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
 	vm_fault_t ret;
 
@@ -1335,14 +1364,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 		}
 		return ret;
 	}
-	gfp = vma_thp_gfp_mask(vma);
-	folio = vma_alloc_folio(gfp, HPAGE_PMD_ORDER, vma, haddr, true);
-	if (unlikely(!folio)) {
-		count_vm_event(THP_FAULT_FALLBACK);
-		count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK);
-		return VM_FAULT_FALLBACK;
-	}
-	return __do_huge_pmd_anonymous_page(vmf, &folio->page, gfp);
+
+	return __do_huge_pmd_anonymous_page(vmf);
 }
 
 static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
@@ -1586,7 +1609,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	int ret = -ENOMEM;
 
 	pmd = pmdp_get_lockless(src_pmd);
-	if (unlikely(pmd_special(pmd))) {
+	if (unlikely(pmd_present(pmd) && pmd_special(pmd))) {
 		dst_ptl = pmd_lock(dst_mm, dst_pmd);
 		src_ptl = pmd_lockptr(src_mm, src_pmd);
 		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
@@ -1774,6 +1797,38 @@ unlock:
 	spin_unlock(vmf->ptl);
 }
 
+static vm_fault_t do_huge_zero_wp_pmd(struct vm_fault *vmf)
+{
+	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
+	struct vm_area_struct *vma = vmf->vma;
+	struct mmu_notifier_range range;
+	struct folio *folio;
+	vm_fault_t ret = 0;
+
+	folio = vma_alloc_anon_folio_pmd(vma, vmf->address);
+	if (unlikely(!folio))
+		return VM_FAULT_FALLBACK;
+
+	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, 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(pmdp_get(vmf->pmd), vmf->orig_pmd)))
+		goto release;
+	ret = check_stable_address_space(vma->vm_mm);
+	if (ret)
+		goto release;
+	(void)pmdp_huge_clear_flush(vma, haddr, vmf->pmd);
+	map_anon_folio_pmd(folio, vmf->pmd, vma, haddr);
+	goto unlock;
+release:
+	folio_put(folio);
+unlock:
+	spin_unlock(vmf->ptl);
+	mmu_notifier_invalidate_range_end(&range);
+	return ret;
+}
+
 vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf)
 {
 	const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
@@ -1786,8 +1841,15 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf)
 	vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd);
 	VM_BUG_ON_VMA(!vma->anon_vma, vma);
 
-	if (is_huge_zero_pmd(orig_pmd))
+	if (is_huge_zero_pmd(orig_pmd)) {
+		vm_fault_t ret = do_huge_zero_wp_pmd(vmf);
+
+		if (!(ret & VM_FAULT_FALLBACK))
+			return ret;
+
+		/* Fallback to splitting PMD if THP cannot be allocated */
 		goto fallback;
+	}
 
 	spin_lock(vmf->ptl);
 
@@ -3135,8 +3197,8 @@ static void __split_huge_page_tail(struct folio *folio, int tail,
 	/* ->mapping in first and second tail page is replaced by other uses */
 	VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
 			page_tail);
-	page_tail->mapping = head->mapping;
-	page_tail->index = head->index + tail;
+	new_folio->mapping = folio->mapping;
+	new_folio->index = folio->index + tail;
 
 	/*
 	 * page->private should not be set in tail pages. Fix up and warn once
@@ -3212,11 +3274,11 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	ClearPageHasHWPoisoned(head);
 
 	for (i = nr - new_nr; i >= new_nr; i -= new_nr) {
+		struct folio *tail;
 		__split_huge_page_tail(folio, i, lruvec, list, new_order);
+		tail = page_folio(head + i);
 		/* Some pages can be beyond EOF: drop them from page cache */
-		if (head[i].index >= end) {
-			struct folio *tail = page_folio(head + i);
-
+		if (tail->index >= end) {
 			if (shmem_mapping(folio->mapping))
 				nr_dropped++;
 			else if (folio_test_clear_dirty(tail))
@@ -3224,12 +3286,12 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 					inode_to_wb(folio->mapping->host));
 			__filemap_remove_folio(tail, NULL);
 			folio_put(tail);
-		} else if (!PageAnon(page)) {
-			__xa_store(&folio->mapping->i_pages, head[i].index,
-					head + i, 0);
+		} else if (!folio_test_anon(folio)) {
+			__xa_store(&folio->mapping->i_pages, tail->index,
+					tail, 0);
 		} else if (swap_cache) {
 			__xa_store(&swap_cache->i_pages, offset + i,
-					head + i, 0);
+					tail, 0);
 		}
 	}
 
@@ -3599,10 +3661,27 @@ int split_folio_to_list(struct folio *folio, struct list_head *list)
 	return split_huge_page_to_list_to_order(&folio->page, list, ret);
 }
 
-void __folio_undo_large_rmappable(struct folio *folio)
+/*
+ * __folio_unqueue_deferred_split() is not to be called directly:
+ * the folio_unqueue_deferred_split() inline wrapper in mm/internal.h
+ * limits its calls to those folios which may have a _deferred_list for
+ * queueing THP splits, and that list is (racily observed to be) non-empty.
+ *
+ * It is unsafe to call folio_unqueue_deferred_split() until folio refcount is
+ * zero: because even when split_queue_lock is held, a non-empty _deferred_list
+ * might be in use on deferred_split_scan()'s unlocked on-stack list.
+ *
+ * If memory cgroups are enabled, split_queue_lock is in the mem_cgroup: it is
+ * therefore important to unqueue deferred split before changing folio memcg.
+ */
+bool __folio_unqueue_deferred_split(struct folio *folio)
 {
 	struct deferred_split *ds_queue;
 	unsigned long flags;
+	bool unqueued = false;
+
+	WARN_ON_ONCE(folio_ref_count(folio));
+	WARN_ON_ONCE(!mem_cgroup_disabled() && !folio_memcg(folio));
 
 	ds_queue = get_deferred_split_queue(folio);
 	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
@@ -3614,8 +3693,11 @@ void __folio_undo_large_rmappable(struct folio *folio)
 				      MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
 		}
 		list_del_init(&folio->_deferred_list);
+		unqueued = true;
 	}
 	spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
+
+	return unqueued;	/* useful for debug warnings */
 }
 
 /* partially_mapped=false won't clear PG_partially_mapped folio flag */
@@ -3638,14 +3720,11 @@ void deferred_split_folio(struct folio *folio, bool partially_mapped)
 		return;
 
 	/*
-	 * The try_to_unmap() in page reclaim path might reach here too,
-	 * this may cause a race condition to corrupt deferred split queue.
-	 * And, if page reclaim is already handling the same folio, it is
-	 * unnecessary to handle it again in shrinker.
-	 *
-	 * Check the swapcache flag to determine if the folio is being
-	 * handled by page reclaim since THP swap would add the folio into
-	 * swap cache before calling try_to_unmap().
+	 * Exclude swapcache: originally to avoid a corrupt deferred split
+	 * queue. Nowadays that is fully prevented by mem_cgroup_swapout();
+	 * but if page reclaim is already handling the same folio, it is
+	 * unnecessary to handle it again in the shrinker, so excluding
+	 * swapcache here may still be a useful optimization.
 	 */
 	if (folio_test_swapcache(folio))
 		return;
@@ -3729,8 +3808,8 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 	struct deferred_split *ds_queue = &pgdata->deferred_split_queue;
 	unsigned long flags;
 	LIST_HEAD(list);
-	struct folio *folio, *next;
-	int split = 0;
+	struct folio *folio, *next, *prev = NULL;
+	int split = 0, removed = 0;
 
 #ifdef CONFIG_MEMCG
 	if (sc->memcg)
@@ -3784,17 +3863,32 @@ next:
 		 * in the case it was underused, then consider it used and
 		 * don't add it back to split_queue.
 		 */
-		if (!did_split && !folio_test_partially_mapped(folio)) {
+		if (did_split) {
+			; /* folio already removed from list */
+		} else if (!folio_test_partially_mapped(folio)) {
 			list_del_init(&folio->_deferred_list);
-			ds_queue->split_queue_len--;
+			removed++;
+		} else {
+			/*
+			 * That unlocked list_del_init() above would be unsafe,
+			 * unless its folio is separated from any earlier folios
+			 * left on the list (which may be concurrently unqueued)
+			 * by one safe folio with refcount still raised.
+			 */
+			swap(folio, prev);
 		}
-		folio_put(folio);
+		if (folio)
+			folio_put(folio);
 	}
 
 	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
 	list_splice_tail(&list, &ds_queue->split_queue);
+	ds_queue->split_queue_len -= removed;
 	spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
 
+	if (prev)
+		folio_put(prev);
+
 	/*
 	 * Stop shrinker if we didn't split any page, but the queue is empty.
 	 * This can happen if pages were freed under us.
@@ -4075,7 +4169,7 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
 
 		tok = strsep(&buf, ",");
 		if (tok) {
-			strcpy(file_path, tok);
+			strscpy(file_path, tok);
 		} else {
 			ret = -EINVAL;
 			goto out;