Update Linux to v5.4.2

Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/mm/filemap.c b/mm/filemap.c
index 52517f2..85b7d08 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *	linux/mm/filemap.c
  *
@@ -24,6 +25,7 @@
 #include <linux/pagemap.h>
 #include <linux/file.h>
 #include <linux/uio.h>
+#include <linux/error-injection.h>
 #include <linux/hash.h>
 #include <linux/writeback.h>
 #include <linux/backing-dev.h>
@@ -36,6 +38,9 @@
 #include <linux/cleancache.h>
 #include <linux/shmem_fs.h>
 #include <linux/rmap.h>
+#include <linux/delayacct.h>
+#include <linux/psi.h>
+#include <linux/ramfs.h>
 #include "internal.h"
 
 #define CREATE_TRACE_POINTS
@@ -96,8 +101,8 @@
  *    ->swap_lock		(try_to_unmap_one)
  *    ->private_lock		(try_to_unmap_one)
  *    ->i_pages lock		(try_to_unmap_one)
- *    ->zone_lru_lock(zone)	(follow_page->mark_page_accessed)
- *    ->zone_lru_lock(zone)	(check_pte_range->isolate_lru_page)
+ *    ->pgdat->lru_lock		(follow_page->mark_page_accessed)
+ *    ->pgdat->lru_lock		(check_pte_range->isolate_lru_page)
  *    ->private_lock		(page_remove_rmap->set_page_dirty)
  *    ->i_pages lock		(page_remove_rmap->set_page_dirty)
  *    bdi.wb->list_lock		(page_remove_rmap->set_page_dirty)
@@ -111,60 +116,26 @@
  *   ->tasklist_lock            (memory_failure, collect_procs_ao)
  */
 
-static int page_cache_tree_insert(struct address_space *mapping,
-				  struct page *page, void **shadowp)
-{
-	struct radix_tree_node *node;
-	void **slot;
-	int error;
-
-	error = __radix_tree_create(&mapping->i_pages, page->index, 0,
-				    &node, &slot);
-	if (error)
-		return error;
-	if (*slot) {
-		void *p;
-
-		p = radix_tree_deref_slot_protected(slot,
-						    &mapping->i_pages.xa_lock);
-		if (!radix_tree_exceptional_entry(p))
-			return -EEXIST;
-
-		mapping->nrexceptional--;
-		if (shadowp)
-			*shadowp = p;
-	}
-	__radix_tree_replace(&mapping->i_pages, node, slot, page,
-			     workingset_lookup_update(mapping));
-	mapping->nrpages++;
-	return 0;
-}
-
-static void page_cache_tree_delete(struct address_space *mapping,
+static void page_cache_delete(struct address_space *mapping,
 				   struct page *page, void *shadow)
 {
-	int i, nr;
+	XA_STATE(xas, &mapping->i_pages, page->index);
+	unsigned int nr = 1;
 
-	/* hugetlb pages are represented by one entry in the radix tree */
-	nr = PageHuge(page) ? 1 : hpage_nr_pages(page);
+	mapping_set_update(&xas, mapping);
+
+	/* hugetlb pages are represented by a single entry in the xarray */
+	if (!PageHuge(page)) {
+		xas_set_order(&xas, page->index, compound_order(page));
+		nr = compound_nr(page);
+	}
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(PageTail(page), page);
 	VM_BUG_ON_PAGE(nr != 1 && shadow, page);
 
-	for (i = 0; i < nr; i++) {
-		struct radix_tree_node *node;
-		void **slot;
-
-		__radix_tree_lookup(&mapping->i_pages, page->index + i,
-				    &node, &slot);
-
-		VM_BUG_ON_PAGE(!node && nr != 1, page);
-
-		radix_tree_clear_tags(&mapping->i_pages, node, slot);
-		__radix_tree_replace(&mapping->i_pages, node, slot, shadow,
-				workingset_lookup_update(mapping));
-	}
+	xas_store(&xas, shadow);
+	xas_init_marks(&xas);
 
 	page->mapping = NULL;
 	/* Leave page->index set: truncation lookup relies upon it */
@@ -233,8 +204,9 @@
 		__mod_node_page_state(page_pgdat(page), NR_SHMEM, -nr);
 		if (PageTransHuge(page))
 			__dec_node_page_state(page, NR_SHMEM_THPS);
-	} else {
-		VM_BUG_ON_PAGE(PageTransHuge(page), page);
+	} else if (PageTransHuge(page)) {
+		__dec_node_page_state(page, NR_FILE_THPS);
+		filemap_nr_thps_dec(mapping);
 	}
 
 	/*
@@ -263,7 +235,7 @@
 	trace_mm_filemap_delete_from_page_cache(page);
 
 	unaccount_page_cache_page(mapping, page);
-	page_cache_tree_delete(mapping, page, shadow);
+	page_cache_delete(mapping, page, shadow);
 }
 
 static void page_cache_free_page(struct address_space *mapping,
@@ -306,61 +278,62 @@
 EXPORT_SYMBOL(delete_from_page_cache);
 
 /*
- * page_cache_tree_delete_batch - delete several pages from page cache
+ * page_cache_delete_batch - delete several pages from page cache
  * @mapping: the mapping to which pages belong
  * @pvec: pagevec with pages to delete
  *
  * The function walks over mapping->i_pages and removes pages passed in @pvec
- * from the mapping. The function expects @pvec to be sorted by page index.
+ * from the mapping. The function expects @pvec to be sorted by page index
+ * and is optimised for it to be dense.
  * It tolerates holes in @pvec (mapping entries at those indices are not
  * modified). The function expects only THP head pages to be present in the
- * @pvec and takes care to delete all corresponding tail pages from the
- * mapping as well.
+ * @pvec.
  *
  * The function expects the i_pages lock to be held.
  */
-static void
-page_cache_tree_delete_batch(struct address_space *mapping,
+static void page_cache_delete_batch(struct address_space *mapping,
 			     struct pagevec *pvec)
 {
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index);
 	int total_pages = 0;
-	int i = 0, tail_pages = 0;
+	int i = 0;
 	struct page *page;
-	pgoff_t start;
 
-	start = pvec->pages[0]->index;
-	radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) {
-		if (i >= pagevec_count(pvec) && !tail_pages)
+	mapping_set_update(&xas, mapping);
+	xas_for_each(&xas, page, ULONG_MAX) {
+		if (i >= pagevec_count(pvec))
 			break;
-		page = radix_tree_deref_slot_protected(slot,
-						       &mapping->i_pages.xa_lock);
-		if (radix_tree_exceptional_entry(page))
+
+		/* A swap/dax/shadow entry got inserted? Skip it. */
+		if (xa_is_value(page))
 			continue;
-		if (!tail_pages) {
-			/*
-			 * Some page got inserted in our range? Skip it. We
-			 * have our pages locked so they are protected from
-			 * being removed.
-			 */
-			if (page != pvec->pages[i])
-				continue;
-			WARN_ON_ONCE(!PageLocked(page));
-			if (PageTransHuge(page) && !PageHuge(page))
-				tail_pages = HPAGE_PMD_NR - 1;
-			page->mapping = NULL;
-			/*
-			 * Leave page->index set: truncation lookup relies
-			 * upon it
-			 */
-			i++;
-		} else {
-			tail_pages--;
+		/*
+		 * A page got inserted in our range? Skip it. We have our
+		 * pages locked so they are protected from being removed.
+		 * If we see a page whose index is higher than ours, it
+		 * means our page has been removed, which shouldn't be
+		 * possible because we're holding the PageLock.
+		 */
+		if (page != pvec->pages[i]) {
+			VM_BUG_ON_PAGE(page->index > pvec->pages[i]->index,
+					page);
+			continue;
 		}
-		radix_tree_clear_tags(&mapping->i_pages, iter.node, slot);
-		__radix_tree_replace(&mapping->i_pages, iter.node, slot, NULL,
-				workingset_lookup_update(mapping));
+
+		WARN_ON_ONCE(!PageLocked(page));
+
+		if (page->index == xas.xa_index)
+			page->mapping = NULL;
+		/* Leave page->index set: truncation lookup relies on it */
+
+		/*
+		 * Move to the next page in the vector if this is a regular
+		 * page or the index is of the last sub-page of this compound
+		 * page.
+		 */
+		if (page->index + compound_nr(page) - 1 == xas.xa_index)
+			i++;
+		xas_store(&xas, NULL);
 		total_pages++;
 	}
 	mapping->nrpages -= total_pages;
@@ -381,7 +354,7 @@
 
 		unaccount_page_cache_page(mapping, pvec->pages[i]);
 	}
-	page_cache_tree_delete_batch(mapping, pvec);
+	page_cache_delete_batch(mapping, pvec);
 	xa_unlock_irqrestore(&mapping->i_pages, flags);
 
 	for (i = 0; i < pagevec_count(pvec); i++)
@@ -426,6 +399,8 @@
  * opposed to a regular memory cleansing writeback.  The difference between
  * these two operations is that if a dirty page/buffer is encountered, it must
  * be waited upon, and not just skipped over.
+ *
+ * Return: %0 on success, negative error code otherwise.
  */
 int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
 				loff_t end, int sync_mode)
@@ -438,7 +413,8 @@
 		.range_end = end,
 	};
 
-	if (!mapping_cap_writeback_dirty(mapping))
+	if (!mapping_cap_writeback_dirty(mapping) ||
+	    !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
 		return 0;
 
 	wbc_attach_fdatawrite_inode(&wbc, mapping->host);
@@ -472,6 +448,8 @@
  *
  * This is a mostly non-blocking flush.  Not suitable for data-integrity
  * purposes - I/O may not be started against all dirty pages.
+ *
+ * Return: %0 on success, negative error code otherwise.
  */
 int filemap_flush(struct address_space *mapping)
 {
@@ -487,24 +465,38 @@
  *
  * Find at least one page in the range supplied, usually used to check if
  * direct writing in this range will trigger a writeback.
+ *
+ * Return: %true if at least one page exists in the specified range,
+ * %false otherwise.
  */
 bool filemap_range_has_page(struct address_space *mapping,
 			   loff_t start_byte, loff_t end_byte)
 {
-	pgoff_t index = start_byte >> PAGE_SHIFT;
-	pgoff_t end = end_byte >> PAGE_SHIFT;
 	struct page *page;
+	XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT);
+	pgoff_t max = end_byte >> PAGE_SHIFT;
 
 	if (end_byte < start_byte)
 		return false;
 
-	if (mapping->nrpages == 0)
-		return false;
+	rcu_read_lock();
+	for (;;) {
+		page = xas_find(&xas, max);
+		if (xas_retry(&xas, page))
+			continue;
+		/* Shadow entries don't count */
+		if (xa_is_value(page))
+			continue;
+		/*
+		 * We don't need to try to pin this page; we're about to
+		 * release the RCU lock anyway.  It is enough to know that
+		 * there was a page here recently.
+		 */
+		break;
+	}
+	rcu_read_unlock();
 
-	if (!find_get_pages_range(mapping, &index, end, 1, &page))
-		return false;
-	put_page(page);
-	return true;
+	return page != NULL;
 }
 EXPORT_SYMBOL(filemap_range_has_page);
 
@@ -552,6 +544,8 @@
  * Since the error status of the address space is cleared by this function,
  * callers are responsible for checking the return value and handling and/or
  * reporting the error.
+ *
+ * Return: error status of the address space.
  */
 int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
 			    loff_t end_byte)
@@ -562,6 +556,28 @@
 EXPORT_SYMBOL(filemap_fdatawait_range);
 
 /**
+ * filemap_fdatawait_range_keep_errors - wait for writeback to complete
+ * @mapping:		address space structure to wait for
+ * @start_byte:		offset in bytes where the range starts
+ * @end_byte:		offset in bytes where the range ends (inclusive)
+ *
+ * Walk the list of under-writeback pages of the given address space in the
+ * given range and wait for all of them.  Unlike filemap_fdatawait_range(),
+ * this function does not clear error status of the address space.
+ *
+ * Use this function if callers don't handle errors themselves.  Expected
+ * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
+ * fsfreeze(8)
+ */
+int filemap_fdatawait_range_keep_errors(struct address_space *mapping,
+		loff_t start_byte, loff_t end_byte)
+{
+	__filemap_fdatawait_range(mapping, start_byte, end_byte);
+	return filemap_check_and_keep_errors(mapping);
+}
+EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors);
+
+/**
  * file_fdatawait_range - wait for writeback to complete
  * @file:		file pointing to address space structure to wait for
  * @start_byte:		offset in bytes where the range starts
@@ -574,6 +590,8 @@
  * Since the error status of the file is advanced by this function,
  * callers are responsible for checking the return value and handling and/or
  * reporting the error.
+ *
+ * Return: error status of the address space vs. the file->f_wb_err cursor.
  */
 int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte)
 {
@@ -595,6 +613,8 @@
  * Use this function if callers don't handle errors themselves.  Expected
  * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
  * fsfreeze(8)
+ *
+ * Return: error status of the address space.
  */
 int filemap_fdatawait_keep_errors(struct address_space *mapping)
 {
@@ -603,10 +623,13 @@
 }
 EXPORT_SYMBOL(filemap_fdatawait_keep_errors);
 
+/* Returns true if writeback might be needed or already in progress. */
 static bool mapping_needs_writeback(struct address_space *mapping)
 {
-	return (!dax_mapping(mapping) && mapping->nrpages) ||
-	    (dax_mapping(mapping) && mapping->nrexceptional);
+	if (dax_mapping(mapping))
+		return mapping->nrexceptional;
+
+	return mapping->nrpages;
 }
 
 int filemap_write_and_wait(struct address_space *mapping)
@@ -646,6 +669,8 @@
  *
  * Note that @lend is inclusive (describes the last byte to be written) so
  * that this function can be used to write to the very end-of-file (end = -1).
+ *
+ * Return: error status of the address space.
  */
 int filemap_write_and_wait_range(struct address_space *mapping,
 				 loff_t lstart, loff_t lend)
@@ -701,6 +726,8 @@
  * While we handle mapping->wb_err with atomic operations, the f_wb_err
  * value is protected by the f_lock since we must ensure that it reflects
  * the latest value swapped in for this file descriptor.
+ *
+ * Return: %0 on success, negative error code otherwise.
  */
 int file_check_and_advance_wb_err(struct file *file)
 {
@@ -743,6 +770,8 @@
  *
  * After writing out and waiting on the data, we check and advance the
  * f_wb_err cursor to the latest value, and return any errors detected there.
+ *
+ * Return: %0 on success, negative error code otherwise.
  */
 int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend)
 {
@@ -775,51 +804,46 @@
  * locked.  This function does not add the new page to the LRU, the
  * caller must do that.
  *
- * The remove + add is atomic.  The only way this function can fail is
- * memory allocation failure.
+ * The remove + add is atomic.  This function cannot fail.
+ *
+ * Return: %0
  */
 int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 {
-	int error;
+	struct address_space *mapping = old->mapping;
+	void (*freepage)(struct page *) = mapping->a_ops->freepage;
+	pgoff_t offset = old->index;
+	XA_STATE(xas, &mapping->i_pages, offset);
+	unsigned long flags;
 
 	VM_BUG_ON_PAGE(!PageLocked(old), old);
 	VM_BUG_ON_PAGE(!PageLocked(new), new);
 	VM_BUG_ON_PAGE(new->mapping, new);
 
-	error = radix_tree_preload(gfp_mask & GFP_RECLAIM_MASK);
-	if (!error) {
-		struct address_space *mapping = old->mapping;
-		void (*freepage)(struct page *);
-		unsigned long flags;
+	get_page(new);
+	new->mapping = mapping;
+	new->index = offset;
 
-		pgoff_t offset = old->index;
-		freepage = mapping->a_ops->freepage;
+	xas_lock_irqsave(&xas, flags);
+	xas_store(&xas, new);
 
-		get_page(new);
-		new->mapping = mapping;
-		new->index = offset;
+	old->mapping = NULL;
+	/* hugetlb pages do not participate in page cache accounting. */
+	if (!PageHuge(old))
+		__dec_node_page_state(new, NR_FILE_PAGES);
+	if (!PageHuge(new))
+		__inc_node_page_state(new, NR_FILE_PAGES);
+	if (PageSwapBacked(old))
+		__dec_node_page_state(new, NR_SHMEM);
+	if (PageSwapBacked(new))
+		__inc_node_page_state(new, NR_SHMEM);
+	xas_unlock_irqrestore(&xas, flags);
+	mem_cgroup_migrate(old, new);
+	if (freepage)
+		freepage(old);
+	put_page(old);
 
-		xa_lock_irqsave(&mapping->i_pages, flags);
-		__delete_from_page_cache(old, NULL);
-		error = page_cache_tree_insert(mapping, new, NULL);
-		BUG_ON(error);
-
-		/*
-		 * hugetlb pages do not participate in page cache accounting.
-		 */
-		if (!PageHuge(new))
-			__inc_node_page_state(new, NR_FILE_PAGES);
-		if (PageSwapBacked(new))
-			__inc_node_page_state(new, NR_SHMEM);
-		xa_unlock_irqrestore(&mapping->i_pages, flags);
-		mem_cgroup_migrate(old, new);
-		radix_tree_preload_end();
-		if (freepage)
-			freepage(old);
-		put_page(old);
-	}
-
-	return error;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(replace_page_cache_page);
 
@@ -828,12 +852,15 @@
 				      pgoff_t offset, gfp_t gfp_mask,
 				      void **shadowp)
 {
+	XA_STATE(xas, &mapping->i_pages, offset);
 	int huge = PageHuge(page);
 	struct mem_cgroup *memcg;
 	int error;
+	void *old;
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(PageSwapBacked(page), page);
+	mapping_set_update(&xas, mapping);
 
 	if (!huge) {
 		error = mem_cgroup_try_charge(page, current->mm,
@@ -842,40 +869,49 @@
 			return error;
 	}
 
-	error = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK);
-	if (error) {
-		if (!huge)
-			mem_cgroup_cancel_charge(page, memcg, false);
-		return error;
-	}
-
 	get_page(page);
 	page->mapping = mapping;
 	page->index = offset;
 
-	xa_lock_irq(&mapping->i_pages);
-	error = page_cache_tree_insert(mapping, page, shadowp);
-	radix_tree_preload_end();
-	if (unlikely(error))
-		goto err_insert;
+	do {
+		xas_lock_irq(&xas);
+		old = xas_load(&xas);
+		if (old && !xa_is_value(old))
+			xas_set_err(&xas, -EEXIST);
+		xas_store(&xas, page);
+		if (xas_error(&xas))
+			goto unlock;
 
-	/* hugetlb pages do not participate in page cache accounting. */
-	if (!huge)
-		__inc_node_page_state(page, NR_FILE_PAGES);
-	xa_unlock_irq(&mapping->i_pages);
+		if (xa_is_value(old)) {
+			mapping->nrexceptional--;
+			if (shadowp)
+				*shadowp = old;
+		}
+		mapping->nrpages++;
+
+		/* hugetlb pages do not participate in page cache accounting */
+		if (!huge)
+			__inc_node_page_state(page, NR_FILE_PAGES);
+unlock:
+		xas_unlock_irq(&xas);
+	} while (xas_nomem(&xas, gfp_mask & GFP_RECLAIM_MASK));
+
+	if (xas_error(&xas))
+		goto error;
+
 	if (!huge)
 		mem_cgroup_commit_charge(page, memcg, false, false);
 	trace_mm_filemap_add_to_page_cache(page);
 	return 0;
-err_insert:
+error:
 	page->mapping = NULL;
 	/* Leave page->index set: truncation relies upon it */
-	xa_unlock_irq(&mapping->i_pages);
 	if (!huge)
 		mem_cgroup_cancel_charge(page, memcg, false);
 	put_page(page);
-	return error;
+	return xas_error(&xas);
 }
+ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO);
 
 /**
  * add_to_page_cache_locked - add a locked page to the pagecache
@@ -886,6 +922,8 @@
  *
  * This function is used to add a page to the pagecache. It must be locked.
  * This function does not add the page to the LRU.  The caller must do that.
+ *
+ * Return: %0 on success, negative error code otherwise.
  */
 int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 		pgoff_t offset, gfp_t gfp_mask)
@@ -915,12 +953,9 @@
 		 * data from the working set, only to cache data that will
 		 * get overwritten with something else, is a waste of memory.
 		 */
-		if (!(gfp_mask & __GFP_WRITE) &&
-		    shadow && workingset_refault(shadow)) {
-			SetPageActive(page);
-			workingset_activation(page);
-		} else
-			ClearPageActive(page);
+		WARN_ON_ONCE(PageActive(page));
+		if (!(gfp_mask & __GFP_WRITE) && shadow)
+			workingset_refault(page, shadow);
 		lru_cache_add(page);
 	}
 	return ret;
@@ -1003,7 +1038,14 @@
 	if (wait_page->bit_nr != key->bit_nr)
 		return 0;
 
-	/* Stop walking if it's locked */
+	/*
+	 * Stop walking if it's locked.
+	 * Is this safe if put_and_wait_on_page_locked() is in use?
+	 * Yes: the waker must hold a reference to this page, and if PG_locked
+	 * has now already been set by another task, that task must also hold
+	 * a reference to the *same usage* of this page; so there is no need
+	 * to walk on to wake even the put_and_wait_on_page_locked() callers.
+	 */
 	if (test_bit(key->bit_nr, &key->page->flags))
 		return -1;
 
@@ -1071,15 +1113,44 @@
 	wake_up_page_bit(page, bit);
 }
 
+/*
+ * A choice of three behaviors for wait_on_page_bit_common():
+ */
+enum behavior {
+	EXCLUSIVE,	/* Hold ref to page and take the bit when woken, like
+			 * __lock_page() waiting on then setting PG_locked.
+			 */
+	SHARED,		/* Hold ref to page and check the bit when woken, like
+			 * wait_on_page_writeback() waiting on PG_writeback.
+			 */
+	DROP,		/* Drop ref to page before wait, no check when woken,
+			 * like put_and_wait_on_page_locked() on PG_locked.
+			 */
+};
+
 static inline int wait_on_page_bit_common(wait_queue_head_t *q,
-		struct page *page, int bit_nr, int state, bool lock)
+	struct page *page, int bit_nr, int state, enum behavior behavior)
 {
 	struct wait_page_queue wait_page;
 	wait_queue_entry_t *wait = &wait_page.wait;
+	bool bit_is_set;
+	bool thrashing = false;
+	bool delayacct = false;
+	unsigned long pflags;
 	int ret = 0;
 
+	if (bit_nr == PG_locked &&
+	    !PageUptodate(page) && PageWorkingset(page)) {
+		if (!PageSwapBacked(page)) {
+			delayacct_thrashing_start();
+			delayacct = true;
+		}
+		psi_memstall_enter(&pflags);
+		thrashing = true;
+	}
+
 	init_wait(wait);
-	wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0;
+	wait->flags = behavior == EXCLUSIVE ? WQ_FLAG_EXCLUSIVE : 0;
 	wait->func = wake_page_function;
 	wait_page.page = page;
 	wait_page.bit_nr = bit_nr;
@@ -1096,26 +1167,46 @@
 
 		spin_unlock_irq(&q->lock);
 
-		if (likely(test_bit(bit_nr, &page->flags))) {
-			io_schedule();
-		}
+		bit_is_set = test_bit(bit_nr, &page->flags);
+		if (behavior == DROP)
+			put_page(page);
 
-		if (lock) {
+		if (likely(bit_is_set))
+			io_schedule();
+
+		if (behavior == EXCLUSIVE) {
 			if (!test_and_set_bit_lock(bit_nr, &page->flags))
 				break;
-		} else {
+		} else if (behavior == SHARED) {
 			if (!test_bit(bit_nr, &page->flags))
 				break;
 		}
 
-		if (unlikely(signal_pending_state(state, current))) {
+		if (signal_pending_state(state, current)) {
 			ret = -EINTR;
 			break;
 		}
+
+		if (behavior == DROP) {
+			/*
+			 * We can no longer safely access page->flags:
+			 * even if CONFIG_MEMORY_HOTREMOVE is not enabled,
+			 * there is a risk of waiting forever on a page reused
+			 * for something that keeps it locked indefinitely.
+			 * But best check for -EINTR above before breaking.
+			 */
+			break;
+		}
 	}
 
 	finish_wait(q, wait);
 
+	if (thrashing) {
+		if (delayacct)
+			delayacct_thrashing_end();
+		psi_memstall_leave(&pflags);
+	}
+
 	/*
 	 * A signal could leave PageWaiters set. Clearing it here if
 	 * !waitqueue_active would be possible (by open-coding finish_wait),
@@ -1130,18 +1221,37 @@
 void wait_on_page_bit(struct page *page, int bit_nr)
 {
 	wait_queue_head_t *q = page_waitqueue(page);
-	wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, false);
+	wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, SHARED);
 }
 EXPORT_SYMBOL(wait_on_page_bit);
 
 int wait_on_page_bit_killable(struct page *page, int bit_nr)
 {
 	wait_queue_head_t *q = page_waitqueue(page);
-	return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, false);
+	return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, SHARED);
 }
 EXPORT_SYMBOL(wait_on_page_bit_killable);
 
 /**
+ * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked
+ * @page: The page to wait for.
+ *
+ * The caller should hold a reference on @page.  They expect the page to
+ * become unlocked relatively soon, but do not wish to hold up migration
+ * (for example) by holding the reference while waiting for the page to
+ * come unlocked.  After this function returns, the caller should not
+ * dereference @page.
+ */
+void put_and_wait_on_page_locked(struct page *page)
+{
+	wait_queue_head_t *q;
+
+	page = compound_head(page);
+	q = page_waitqueue(page);
+	wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, DROP);
+}
+
+/**
  * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
  * @page: Page defining the wait queue of interest
  * @waiter: Waiter to add to the queue
@@ -1270,7 +1380,8 @@
 {
 	struct page *page = compound_head(__page);
 	wait_queue_head_t *q = page_waitqueue(page);
-	wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, true);
+	wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE,
+				EXCLUSIVE);
 }
 EXPORT_SYMBOL(__lock_page);
 
@@ -1278,7 +1389,8 @@
 {
 	struct page *page = compound_head(__page);
 	wait_queue_head_t *q = page_waitqueue(page);
-	return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, true);
+	return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE,
+					EXCLUSIVE);
 }
 EXPORT_SYMBOL_GPL(__lock_page_killable);
 
@@ -1326,86 +1438,76 @@
 }
 
 /**
- * page_cache_next_hole - find the next hole (not-present entry)
- * @mapping: mapping
- * @index: index
- * @max_scan: maximum range to search
+ * page_cache_next_miss() - Find the next gap in the page cache.
+ * @mapping: Mapping.
+ * @index: Index.
+ * @max_scan: Maximum range to search.
  *
- * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the
- * lowest indexed hole.
+ * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the
+ * gap with the lowest index.
  *
- * Returns: the index of the hole if found, otherwise returns an index
- * outside of the set specified (in which case 'return - index >=
- * max_scan' will be true). In rare cases of index wrap-around, 0 will
- * be returned.
+ * This function may be called under the rcu_read_lock.  However, this will
+ * not atomically search a snapshot of the cache at a single point in time.
+ * For example, if a gap is created at index 5, then subsequently a gap is
+ * created at index 10, page_cache_next_miss covering both indices may
+ * return 10 if called under the rcu_read_lock.
  *
- * page_cache_next_hole may be called under rcu_read_lock. However,
- * like radix_tree_gang_lookup, this will not atomically search a
- * snapshot of the tree at a single point in time. For example, if a
- * hole is created at index 5, then subsequently a hole is created at
- * index 10, page_cache_next_hole covering both indexes may return 10
- * if called under rcu_read_lock.
+ * Return: The index of the gap if found, otherwise an index outside the
+ * range specified (in which case 'return - index >= max_scan' will be true).
+ * In the rare case of index wrap-around, 0 will be returned.
  */
-pgoff_t page_cache_next_hole(struct address_space *mapping,
+pgoff_t page_cache_next_miss(struct address_space *mapping,
 			     pgoff_t index, unsigned long max_scan)
 {
-	unsigned long i;
+	XA_STATE(xas, &mapping->i_pages, index);
 
-	for (i = 0; i < max_scan; i++) {
-		struct page *page;
-
-		page = radix_tree_lookup(&mapping->i_pages, index);
-		if (!page || radix_tree_exceptional_entry(page))
+	while (max_scan--) {
+		void *entry = xas_next(&xas);
+		if (!entry || xa_is_value(entry))
 			break;
-		index++;
-		if (index == 0)
+		if (xas.xa_index == 0)
 			break;
 	}
 
-	return index;
+	return xas.xa_index;
 }
-EXPORT_SYMBOL(page_cache_next_hole);
+EXPORT_SYMBOL(page_cache_next_miss);
 
 /**
- * page_cache_prev_hole - find the prev hole (not-present entry)
- * @mapping: mapping
- * @index: index
- * @max_scan: maximum range to search
+ * page_cache_prev_miss() - Find the previous gap in the page cache.
+ * @mapping: Mapping.
+ * @index: Index.
+ * @max_scan: Maximum range to search.
  *
- * Search backwards in the range [max(index-max_scan+1, 0), index] for
- * the first hole.
+ * Search the range [max(index - max_scan + 1, 0), index] for the
+ * gap with the highest index.
  *
- * Returns: the index of the hole if found, otherwise returns an index
- * outside of the set specified (in which case 'index - return >=
- * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX
- * will be returned.
+ * This function may be called under the rcu_read_lock.  However, this will
+ * not atomically search a snapshot of the cache at a single point in time.
+ * For example, if a gap is created at index 10, then subsequently a gap is
+ * created at index 5, page_cache_prev_miss() covering both indices may
+ * return 5 if called under the rcu_read_lock.
  *
- * page_cache_prev_hole may be called under rcu_read_lock. However,
- * like radix_tree_gang_lookup, this will not atomically search a
- * snapshot of the tree at a single point in time. For example, if a
- * hole is created at index 10, then subsequently a hole is created at
- * index 5, page_cache_prev_hole covering both indexes may return 5 if
- * called under rcu_read_lock.
+ * Return: The index of the gap if found, otherwise an index outside the
+ * range specified (in which case 'index - return >= max_scan' will be true).
+ * In the rare case of wrap-around, ULONG_MAX will be returned.
  */
-pgoff_t page_cache_prev_hole(struct address_space *mapping,
+pgoff_t page_cache_prev_miss(struct address_space *mapping,
 			     pgoff_t index, unsigned long max_scan)
 {
-	unsigned long i;
+	XA_STATE(xas, &mapping->i_pages, index);
 
-	for (i = 0; i < max_scan; i++) {
-		struct page *page;
-
-		page = radix_tree_lookup(&mapping->i_pages, index);
-		if (!page || radix_tree_exceptional_entry(page))
+	while (max_scan--) {
+		void *entry = xas_prev(&xas);
+		if (!entry || xa_is_value(entry))
 			break;
-		index--;
-		if (index == ULONG_MAX)
+		if (xas.xa_index == ULONG_MAX)
 			break;
 	}
 
-	return index;
+	return xas.xa_index;
 }
-EXPORT_SYMBOL(page_cache_prev_hole);
+EXPORT_SYMBOL(page_cache_prev_miss);
 
 /**
  * find_get_entry - find and get a page cache entry
@@ -1418,52 +1520,39 @@
  * If the slot holds a shadow entry of a previously evicted page, or a
  * swap entry from shmem/tmpfs, it is returned.
  *
- * Otherwise, %NULL is returned.
+ * Return: the found page or shadow entry, %NULL if nothing is found.
  */
 struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
 {
-	void **pagep;
-	struct page *head, *page;
+	XA_STATE(xas, &mapping->i_pages, offset);
+	struct page *page;
 
 	rcu_read_lock();
 repeat:
-	page = NULL;
-	pagep = radix_tree_lookup_slot(&mapping->i_pages, offset);
-	if (pagep) {
-		page = radix_tree_deref_slot(pagep);
-		if (unlikely(!page))
-			goto out;
-		if (radix_tree_exception(page)) {
-			if (radix_tree_deref_retry(page))
-				goto repeat;
-			/*
-			 * A shadow entry of a recently evicted page,
-			 * or a swap entry from shmem/tmpfs.  Return
-			 * it without attempting to raise page count.
-			 */
-			goto out;
-		}
+	xas_reset(&xas);
+	page = xas_load(&xas);
+	if (xas_retry(&xas, page))
+		goto repeat;
+	/*
+	 * A shadow entry of a recently evicted page, or a swap entry from
+	 * shmem/tmpfs.  Return it without attempting to raise page count.
+	 */
+	if (!page || xa_is_value(page))
+		goto out;
 
-		head = compound_head(page);
-		if (!page_cache_get_speculative(head))
-			goto repeat;
+	if (!page_cache_get_speculative(page))
+		goto repeat;
 
-		/* The page was split under us? */
-		if (compound_head(page) != head) {
-			put_page(head);
-			goto repeat;
-		}
-
-		/*
-		 * Has the page moved?
-		 * This is part of the lockless pagecache protocol. See
-		 * include/linux/pagemap.h for details.
-		 */
-		if (unlikely(page != *pagep)) {
-			put_page(head);
-			goto repeat;
-		}
+	/*
+	 * Has the page moved or been split?
+	 * This is part of the lockless pagecache protocol. See
+	 * include/linux/pagemap.h for details.
+	 */
+	if (unlikely(page != xas_reload(&xas))) {
+		put_page(page);
+		goto repeat;
 	}
+	page = find_subpage(page, offset);
 out:
 	rcu_read_unlock();
 
@@ -1483,9 +1572,9 @@
  * If the slot holds a shadow entry of a previously evicted page, or a
  * swap entry from shmem/tmpfs, it is returned.
  *
- * Otherwise, %NULL is returned.
- *
  * find_lock_entry() may sleep.
+ *
+ * Return: the found page or shadow entry, %NULL if nothing is found.
  */
 struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset)
 {
@@ -1493,7 +1582,7 @@
 
 repeat:
 	page = find_get_entry(mapping, offset);
-	if (page && !radix_tree_exception(page)) {
+	if (page && !xa_is_value(page)) {
 		lock_page(page);
 		/* Has the page been truncated? */
 		if (unlikely(page_mapping(page) != mapping)) {
@@ -1525,12 +1614,17 @@
  * - FGP_CREAT: If page is not present then a new page is allocated using
  *   @gfp_mask and added to the page cache and the VM's LRU
  *   list. The page is returned locked and with an increased
- *   refcount. Otherwise, NULL is returned.
+ *   refcount.
+ * - FGP_FOR_MMAP: Similar to FGP_CREAT, only we want to allow the caller to do
+ *   its own locking dance if the page is already in cache, or unlock the page
+ *   before returning if we had to add the page to pagecache.
  *
  * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even
  * if the GFP flags specified for FGP_CREAT are atomic.
  *
  * If there is a page cache page, it is returned with an increased refcount.
+ *
+ * Return: the found page or %NULL otherwise.
  */
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
 	int fgp_flags, gfp_t gfp_mask)
@@ -1539,7 +1633,7 @@
 
 repeat:
 	page = find_get_entry(mapping, offset);
-	if (radix_tree_exceptional_entry(page))
+	if (xa_is_value(page))
 		page = NULL;
 	if (!page)
 		goto no_page;
@@ -1555,7 +1649,7 @@
 		}
 
 		/* Has the page been truncated? */
-		if (unlikely(page->mapping != mapping)) {
+		if (unlikely(compound_head(page)->mapping != mapping)) {
 			unlock_page(page);
 			put_page(page);
 			goto repeat;
@@ -1563,7 +1657,7 @@
 		VM_BUG_ON_PAGE(page->index != offset, page);
 	}
 
-	if (page && (fgp_flags & FGP_ACCESSED))
+	if (fgp_flags & FGP_ACCESSED)
 		mark_page_accessed(page);
 
 no_page:
@@ -1578,7 +1672,7 @@
 		if (!page)
 			return NULL;
 
-		if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK)))
+		if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP))))
 			fgp_flags |= FGP_LOCK;
 
 		/* Init accessed so avoid atomic mark_page_accessed later */
@@ -1592,6 +1686,13 @@
 			if (err == -EEXIST)
 				goto repeat;
 		}
+
+		/*
+		 * add_to_page_cache_lru locks the page, and for mmap we expect
+		 * an unlocked page.
+		 */
+		if (page && (fgp_flags & FGP_FOR_MMAP))
+			unlock_page(page);
 	}
 
 	return page;
@@ -1618,60 +1719,49 @@
  * Any shadow entries of evicted pages, or swap entries from
  * shmem/tmpfs, are included in the returned array.
  *
- * find_get_entries() returns the number of pages and shadow entries
- * which were found.
+ * Return: the number of pages and shadow entries which were found.
  */
 unsigned find_get_entries(struct address_space *mapping,
 			  pgoff_t start, unsigned int nr_entries,
 			  struct page **entries, pgoff_t *indices)
 {
-	void **slot;
+	XA_STATE(xas, &mapping->i_pages, start);
+	struct page *page;
 	unsigned int ret = 0;
-	struct radix_tree_iter iter;
 
 	if (!nr_entries)
 		return 0;
 
 	rcu_read_lock();
-	radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) {
-		struct page *head, *page;
-repeat:
-		page = radix_tree_deref_slot(slot);
-		if (unlikely(!page))
+	xas_for_each(&xas, page, ULONG_MAX) {
+		if (xas_retry(&xas, page))
 			continue;
-		if (radix_tree_exception(page)) {
-			if (radix_tree_deref_retry(page)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
-			/*
-			 * A shadow entry of a recently evicted page, a swap
-			 * entry from shmem/tmpfs or a DAX entry.  Return it
-			 * without attempting to raise page count.
-			 */
+		/*
+		 * A shadow entry of a recently evicted page, a swap
+		 * entry from shmem/tmpfs or a DAX entry.  Return it
+		 * without attempting to raise page count.
+		 */
+		if (xa_is_value(page))
 			goto export;
-		}
 
-		head = compound_head(page);
-		if (!page_cache_get_speculative(head))
-			goto repeat;
+		if (!page_cache_get_speculative(page))
+			goto retry;
 
-		/* The page was split under us? */
-		if (compound_head(page) != head) {
-			put_page(head);
-			goto repeat;
-		}
+		/* Has the page moved or been split? */
+		if (unlikely(page != xas_reload(&xas)))
+			goto put_page;
+		page = find_subpage(page, xas.xa_index);
 
-		/* Has the page moved? */
-		if (unlikely(page != *slot)) {
-			put_page(head);
-			goto repeat;
-		}
 export:
-		indices[ret] = iter.index;
+		indices[ret] = xas.xa_index;
 		entries[ret] = page;
 		if (++ret == nr_entries)
 			break;
+		continue;
+put_page:
+		put_page(page);
+retry:
+		xas_reset(&xas);
 	}
 	rcu_read_unlock();
 	return ret;
@@ -1694,72 +1784,52 @@
  * indexes.  There may be holes in the indices due to not-present pages.
  * We also update @start to index the next page for the traversal.
  *
- * find_get_pages_range() returns the number of pages which were found. If this
- * number is smaller than @nr_pages, the end of specified range has been
+ * Return: the number of pages which were found. If this number is
+ * smaller than @nr_pages, the end of specified range has been
  * reached.
  */
 unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
 			      pgoff_t end, unsigned int nr_pages,
 			      struct page **pages)
 {
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, &mapping->i_pages, *start);
+	struct page *page;
 	unsigned ret = 0;
 
 	if (unlikely(!nr_pages))
 		return 0;
 
 	rcu_read_lock();
-	radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, *start) {
-		struct page *head, *page;
-
-		if (iter.index > end)
-			break;
-repeat:
-		page = radix_tree_deref_slot(slot);
-		if (unlikely(!page))
+	xas_for_each(&xas, page, end) {
+		if (xas_retry(&xas, page))
+			continue;
+		/* Skip over shadow, swap and DAX entries */
+		if (xa_is_value(page))
 			continue;
 
-		if (radix_tree_exception(page)) {
-			if (radix_tree_deref_retry(page)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
-			/*
-			 * A shadow entry of a recently evicted page,
-			 * or a swap entry from shmem/tmpfs.  Skip
-			 * over it.
-			 */
-			continue;
-		}
+		if (!page_cache_get_speculative(page))
+			goto retry;
 
-		head = compound_head(page);
-		if (!page_cache_get_speculative(head))
-			goto repeat;
+		/* Has the page moved or been split? */
+		if (unlikely(page != xas_reload(&xas)))
+			goto put_page;
 
-		/* The page was split under us? */
-		if (compound_head(page) != head) {
-			put_page(head);
-			goto repeat;
-		}
-
-		/* Has the page moved? */
-		if (unlikely(page != *slot)) {
-			put_page(head);
-			goto repeat;
-		}
-
-		pages[ret] = page;
+		pages[ret] = find_subpage(page, xas.xa_index);
 		if (++ret == nr_pages) {
-			*start = pages[ret - 1]->index + 1;
+			*start = xas.xa_index + 1;
 			goto out;
 		}
+		continue;
+put_page:
+		put_page(page);
+retry:
+		xas_reset(&xas);
 	}
 
 	/*
 	 * We come here when there is no page beyond @end. We take care to not
 	 * overflow the index @start as it confuses some of the callers. This
-	 * breaks the iteration when there is page at index -1 but that is
+	 * breaks the iteration when there is a page at index -1 but that is
 	 * already broken anyway.
 	 */
 	if (end == (pgoff_t)-1)
@@ -1782,69 +1852,44 @@
  * find_get_pages_contig() works exactly like find_get_pages(), except
  * that the returned number of pages are guaranteed to be contiguous.
  *
- * find_get_pages_contig() returns the number of pages which were found.
+ * Return: the number of pages which were found.
  */
 unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
 			       unsigned int nr_pages, struct page **pages)
 {
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, &mapping->i_pages, index);
+	struct page *page;
 	unsigned int ret = 0;
 
 	if (unlikely(!nr_pages))
 		return 0;
 
 	rcu_read_lock();
-	radix_tree_for_each_contig(slot, &mapping->i_pages, &iter, index) {
-		struct page *head, *page;
-repeat:
-		page = radix_tree_deref_slot(slot);
-		/* The hole, there no reason to continue */
-		if (unlikely(!page))
-			break;
-
-		if (radix_tree_exception(page)) {
-			if (radix_tree_deref_retry(page)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
-			/*
-			 * A shadow entry of a recently evicted page,
-			 * or a swap entry from shmem/tmpfs.  Stop
-			 * looking for contiguous pages.
-			 */
-			break;
-		}
-
-		head = compound_head(page);
-		if (!page_cache_get_speculative(head))
-			goto repeat;
-
-		/* The page was split under us? */
-		if (compound_head(page) != head) {
-			put_page(head);
-			goto repeat;
-		}
-
-		/* Has the page moved? */
-		if (unlikely(page != *slot)) {
-			put_page(head);
-			goto repeat;
-		}
-
+	for (page = xas_load(&xas); page; page = xas_next(&xas)) {
+		if (xas_retry(&xas, page))
+			continue;
 		/*
-		 * must check mapping and index after taking the ref.
-		 * otherwise we can get both false positives and false
-		 * negatives, which is just confusing to the caller.
+		 * If the entry has been swapped out, we can stop looking.
+		 * No current caller is looking for DAX entries.
 		 */
-		if (page->mapping == NULL || page_to_pgoff(page) != iter.index) {
-			put_page(page);
+		if (xa_is_value(page))
 			break;
-		}
 
-		pages[ret] = page;
+		if (!page_cache_get_speculative(page))
+			goto retry;
+
+		/* Has the page moved or been split? */
+		if (unlikely(page != xas_reload(&xas)))
+			goto put_page;
+
+		pages[ret] = find_subpage(page, xas.xa_index);
 		if (++ret == nr_pages)
 			break;
+		continue;
+put_page:
+		put_page(page);
+retry:
+		xas_reset(&xas);
 	}
 	rcu_read_unlock();
 	return ret;
@@ -1862,76 +1907,56 @@
  *
  * Like find_get_pages, except we only return pages which are tagged with
  * @tag.   We update @index to index the next page for the traversal.
+ *
+ * Return: the number of pages which were found.
  */
 unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
-			pgoff_t end, int tag, unsigned int nr_pages,
+			pgoff_t end, xa_mark_t tag, unsigned int nr_pages,
 			struct page **pages)
 {
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, &mapping->i_pages, *index);
+	struct page *page;
 	unsigned ret = 0;
 
 	if (unlikely(!nr_pages))
 		return 0;
 
 	rcu_read_lock();
-	radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, *index, tag) {
-		struct page *head, *page;
-
-		if (iter.index > end)
-			break;
-repeat:
-		page = radix_tree_deref_slot(slot);
-		if (unlikely(!page))
+	xas_for_each_marked(&xas, page, end, tag) {
+		if (xas_retry(&xas, page))
+			continue;
+		/*
+		 * Shadow entries should never be tagged, but this iteration
+		 * is lockless so there is a window for page reclaim to evict
+		 * a page we saw tagged.  Skip over it.
+		 */
+		if (xa_is_value(page))
 			continue;
 
-		if (radix_tree_exception(page)) {
-			if (radix_tree_deref_retry(page)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
-			/*
-			 * A shadow entry of a recently evicted page.
-			 *
-			 * Those entries should never be tagged, but
-			 * this tree walk is lockless and the tags are
-			 * looked up in bulk, one radix tree node at a
-			 * time, so there is a sizable window for page
-			 * reclaim to evict a page we saw tagged.
-			 *
-			 * Skip over it.
-			 */
-			continue;
-		}
+		if (!page_cache_get_speculative(page))
+			goto retry;
 
-		head = compound_head(page);
-		if (!page_cache_get_speculative(head))
-			goto repeat;
+		/* Has the page moved or been split? */
+		if (unlikely(page != xas_reload(&xas)))
+			goto put_page;
 
-		/* The page was split under us? */
-		if (compound_head(page) != head) {
-			put_page(head);
-			goto repeat;
-		}
-
-		/* Has the page moved? */
-		if (unlikely(page != *slot)) {
-			put_page(head);
-			goto repeat;
-		}
-
-		pages[ret] = page;
+		pages[ret] = find_subpage(page, xas.xa_index);
 		if (++ret == nr_pages) {
-			*index = pages[ret - 1]->index + 1;
+			*index = xas.xa_index + 1;
 			goto out;
 		}
+		continue;
+put_page:
+		put_page(page);
+retry:
+		xas_reset(&xas);
 	}
 
 	/*
-	 * We come here when we got at @end. We take care to not overflow the
+	 * We come here when we got to @end. We take care to not overflow the
 	 * index @index as it confuses some of the callers. This breaks the
-	 * iteration when there is page at index -1 but that is already broken
-	 * anyway.
+	 * iteration when there is a page at index -1 but that is already
+	 * broken anyway.
 	 */
 	if (end == (pgoff_t)-1)
 		*index = (pgoff_t)-1;
@@ -1944,76 +1969,6 @@
 }
 EXPORT_SYMBOL(find_get_pages_range_tag);
 
-/**
- * find_get_entries_tag - find and return entries that match @tag
- * @mapping:	the address_space to search
- * @start:	the starting page cache index
- * @tag:	the tag index
- * @nr_entries:	the maximum number of entries
- * @entries:	where the resulting entries are placed
- * @indices:	the cache indices corresponding to the entries in @entries
- *
- * Like find_get_entries, except we only return entries which are tagged with
- * @tag.
- */
-unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
-			int tag, unsigned int nr_entries,
-			struct page **entries, pgoff_t *indices)
-{
-	void **slot;
-	unsigned int ret = 0;
-	struct radix_tree_iter iter;
-
-	if (!nr_entries)
-		return 0;
-
-	rcu_read_lock();
-	radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, start, tag) {
-		struct page *head, *page;
-repeat:
-		page = radix_tree_deref_slot(slot);
-		if (unlikely(!page))
-			continue;
-		if (radix_tree_exception(page)) {
-			if (radix_tree_deref_retry(page)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
-
-			/*
-			 * A shadow entry of a recently evicted page, a swap
-			 * entry from shmem/tmpfs or a DAX entry.  Return it
-			 * without attempting to raise page count.
-			 */
-			goto export;
-		}
-
-		head = compound_head(page);
-		if (!page_cache_get_speculative(head))
-			goto repeat;
-
-		/* The page was split under us? */
-		if (compound_head(page) != head) {
-			put_page(head);
-			goto repeat;
-		}
-
-		/* Has the page moved? */
-		if (unlikely(page != *slot)) {
-			put_page(head);
-			goto repeat;
-		}
-export:
-		indices[ret] = iter.index;
-		entries[ret] = page;
-		if (++ret == nr_entries)
-			break;
-	}
-	rcu_read_unlock();
-	return ret;
-}
-EXPORT_SYMBOL(find_get_entries_tag);
-
 /*
  * CD/DVDs are error prone. When a medium error occurs, the driver may fail
  * a _large_ part of the i/o request. Imagine the worst scenario:
@@ -2046,6 +2001,10 @@
  *
  * This is really ugly. But the goto's actually try to clarify some
  * of the logic when it comes to error handling etc.
+ *
+ * Return:
+ * * total number of bytes copied, including those the were already @written
+ * * negative error code if nothing was copied
  */
 static ssize_t generic_file_buffered_read(struct kiocb *iocb,
 		struct iov_iter *iter, ssize_t written)
@@ -2122,7 +2081,7 @@
 					!mapping->a_ops->is_partially_uptodate)
 				goto page_not_up_to_date;
 			/* pipes can't handle partially uptodate pages */
-			if (unlikely(iter->type & ITER_PIPE))
+			if (unlikely(iov_iter_is_pipe(iter)))
 				goto page_not_up_to_date;
 			if (!trylock_page(page))
 				goto page_not_up_to_date;
@@ -2307,6 +2266,9 @@
  *
  * This is the "read_iter()" routine for all filesystems
  * that can use the page cache directly.
+ * Return:
+ * * number of bytes copied, even for partial reads
+ * * negative error code if nothing was read
  */
 ssize_t
 generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
@@ -2366,62 +2328,98 @@
 EXPORT_SYMBOL(generic_file_read_iter);
 
 #ifdef CONFIG_MMU
-/**
- * page_cache_read - adds requested page to the page cache if not already there
- * @file:	file to read
- * @offset:	page index
- * @gfp_mask:	memory allocation flags
- *
- * This adds the requested page to the page cache if it isn't already there,
- * and schedules an I/O to read in its contents from disk.
- */
-static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask)
+#define MMAP_LOTSAMISS  (100)
+static struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
+					     struct file *fpin)
 {
-	struct address_space *mapping = file->f_mapping;
-	struct page *page;
-	int ret;
+	int flags = vmf->flags;
 
-	do {
-		page = __page_cache_alloc(gfp_mask);
-		if (!page)
-			return -ENOMEM;
+	if (fpin)
+		return fpin;
 
-		ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
-		if (ret == 0)
-			ret = mapping->a_ops->readpage(file, page);
-		else if (ret == -EEXIST)
-			ret = 0; /* losing race to add is OK */
-
-		put_page(page);
-
-	} while (ret == AOP_TRUNCATED_PAGE);
-
-	return ret;
+	/*
+	 * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or
+	 * anything, so we only pin the file and drop the mmap_sem if only
+	 * FAULT_FLAG_ALLOW_RETRY is set.
+	 */
+	if ((flags & (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT)) ==
+	    FAULT_FLAG_ALLOW_RETRY) {
+		fpin = get_file(vmf->vma->vm_file);
+		up_read(&vmf->vma->vm_mm->mmap_sem);
+	}
+	return fpin;
 }
 
-#define MMAP_LOTSAMISS  (100)
+/*
+ * lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_sem
+ * @vmf - the vm_fault for this fault.
+ * @page - the page to lock.
+ * @fpin - the pointer to the file we may pin (or is already pinned).
+ *
+ * This works similar to lock_page_or_retry in that it can drop the mmap_sem.
+ * It differs in that it actually returns the page locked if it returns 1 and 0
+ * if it couldn't lock the page.  If we did have to drop the mmap_sem then fpin
+ * will point to the pinned file and needs to be fput()'ed at a later point.
+ */
+static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page,
+				     struct file **fpin)
+{
+	if (trylock_page(page))
+		return 1;
+
+	/*
+	 * NOTE! This will make us return with VM_FAULT_RETRY, but with
+	 * the mmap_sem still held. That's how FAULT_FLAG_RETRY_NOWAIT
+	 * is supposed to work. We have way too many special cases..
+	 */
+	if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
+		return 0;
+
+	*fpin = maybe_unlock_mmap_for_io(vmf, *fpin);
+	if (vmf->flags & FAULT_FLAG_KILLABLE) {
+		if (__lock_page_killable(page)) {
+			/*
+			 * We didn't have the right flags to drop the mmap_sem,
+			 * but all fault_handlers only check for fatal signals
+			 * if we return VM_FAULT_RETRY, so we need to drop the
+			 * mmap_sem here and return 0 if we don't have a fpin.
+			 */
+			if (*fpin == NULL)
+				up_read(&vmf->vma->vm_mm->mmap_sem);
+			return 0;
+		}
+	} else
+		__lock_page(page);
+	return 1;
+}
+
 
 /*
- * Synchronous readahead happens when we don't even find
- * a page in the page cache at all.
+ * Synchronous readahead happens when we don't even find a page in the page
+ * cache at all.  We don't want to perform IO under the mmap sem, so if we have
+ * to drop the mmap sem we return the file that was pinned in order for us to do
+ * that.  If we didn't pin a file then we return NULL.  The file that is
+ * returned needs to be fput()'ed when we're done with it.
  */
-static void do_sync_mmap_readahead(struct vm_area_struct *vma,
-				   struct file_ra_state *ra,
-				   struct file *file,
-				   pgoff_t offset)
+static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 {
+	struct file *file = vmf->vma->vm_file;
+	struct file_ra_state *ra = &file->f_ra;
 	struct address_space *mapping = file->f_mapping;
+	struct file *fpin = NULL;
+	pgoff_t offset = vmf->pgoff;
 
 	/* If we don't want any read-ahead, don't bother */
-	if (vma->vm_flags & VM_RAND_READ)
-		return;
+	if (vmf->vma->vm_flags & VM_RAND_READ)
+		return fpin;
 	if (!ra->ra_pages)
-		return;
+		return fpin;
 
-	if (vma->vm_flags & VM_SEQ_READ) {
+	if (vmf->vma->vm_flags & VM_SEQ_READ) {
+		fpin = maybe_unlock_mmap_for_io(vmf, fpin);
 		page_cache_sync_readahead(mapping, ra, file, offset,
 					  ra->ra_pages);
-		return;
+		return fpin;
 	}
 
 	/* Avoid banging the cache line if not needed */
@@ -2433,37 +2431,44 @@
 	 * stop bothering with read-ahead. It will only hurt.
 	 */
 	if (ra->mmap_miss > MMAP_LOTSAMISS)
-		return;
+		return fpin;
 
 	/*
 	 * mmap read-around
 	 */
+	fpin = maybe_unlock_mmap_for_io(vmf, fpin);
 	ra->start = max_t(long, 0, offset - ra->ra_pages / 2);
 	ra->size = ra->ra_pages;
 	ra->async_size = ra->ra_pages / 4;
 	ra_submit(ra, mapping, file);
+	return fpin;
 }
 
 /*
  * Asynchronous readahead happens when we find the page and PG_readahead,
- * so we want to possibly extend the readahead further..
+ * so we want to possibly extend the readahead further.  We return the file that
+ * was pinned if we have to drop the mmap_sem in order to do IO.
  */
-static void do_async_mmap_readahead(struct vm_area_struct *vma,
-				    struct file_ra_state *ra,
-				    struct file *file,
-				    struct page *page,
-				    pgoff_t offset)
+static struct file *do_async_mmap_readahead(struct vm_fault *vmf,
+					    struct page *page)
 {
+	struct file *file = vmf->vma->vm_file;
+	struct file_ra_state *ra = &file->f_ra;
 	struct address_space *mapping = file->f_mapping;
+	struct file *fpin = NULL;
+	pgoff_t offset = vmf->pgoff;
 
 	/* If we don't want any read-ahead, don't bother */
-	if (vma->vm_flags & VM_RAND_READ)
-		return;
+	if (vmf->vma->vm_flags & VM_RAND_READ)
+		return fpin;
 	if (ra->mmap_miss > 0)
 		ra->mmap_miss--;
-	if (PageReadahead(page))
+	if (PageReadahead(page)) {
+		fpin = maybe_unlock_mmap_for_io(vmf, fpin);
 		page_cache_async_readahead(mapping, ra, file,
 					   page, offset, ra->ra_pages);
+	}
+	return fpin;
 }
 
 /**
@@ -2479,20 +2484,21 @@
  *
  * vma->vm_mm->mmap_sem must be held on entry.
  *
- * If our return value has VM_FAULT_RETRY set, it's because
- * lock_page_or_retry() returned 0.
- * The mmap_sem has usually been released in this case.
- * See __lock_page_or_retry() for the exception.
+ * If our return value has VM_FAULT_RETRY set, it's because the mmap_sem
+ * may be dropped before doing I/O or by lock_page_maybe_drop_mmap().
  *
  * If our return value does not have VM_FAULT_RETRY set, the mmap_sem
  * has not been released.
  *
  * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set.
+ *
+ * Return: bitwise-OR of %VM_FAULT_ codes.
  */
 vm_fault_t filemap_fault(struct vm_fault *vmf)
 {
 	int error;
 	struct file *file = vmf->vma->vm_file;
+	struct file *fpin = NULL;
 	struct address_space *mapping = file->f_mapping;
 	struct file_ra_state *ra = &file->f_ra;
 	struct inode *inode = mapping->host;
@@ -2514,31 +2520,34 @@
 		 * We found the page, so try async readahead before
 		 * waiting for the lock.
 		 */
-		do_async_mmap_readahead(vmf->vma, ra, file, page, offset);
+		fpin = do_async_mmap_readahead(vmf, page);
 	} else if (!page) {
 		/* No page in the page cache at all */
-		do_sync_mmap_readahead(vmf->vma, ra, file, offset);
 		count_vm_event(PGMAJFAULT);
 		count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
 		ret = VM_FAULT_MAJOR;
+		fpin = do_sync_mmap_readahead(vmf);
 retry_find:
-		page = find_get_page(mapping, offset);
-		if (!page)
-			goto no_cached_page;
+		page = pagecache_get_page(mapping, offset,
+					  FGP_CREAT|FGP_FOR_MMAP,
+					  vmf->gfp_mask);
+		if (!page) {
+			if (fpin)
+				goto out_retry;
+			return vmf_error(-ENOMEM);
+		}
 	}
 
-	if (!lock_page_or_retry(page, vmf->vma->vm_mm, vmf->flags)) {
-		put_page(page);
-		return ret | VM_FAULT_RETRY;
-	}
+	if (!lock_page_maybe_drop_mmap(vmf, page, &fpin))
+		goto out_retry;
 
 	/* Did it get truncated? */
-	if (unlikely(page->mapping != mapping)) {
+	if (unlikely(compound_head(page)->mapping != mapping)) {
 		unlock_page(page);
 		put_page(page);
 		goto retry_find;
 	}
-	VM_BUG_ON_PAGE(page->index != offset, page);
+	VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page);
 
 	/*
 	 * We have a locked page in the page cache, now we need to check
@@ -2548,6 +2557,16 @@
 		goto page_not_uptodate;
 
 	/*
+	 * We've made it this far and we had to drop our mmap_sem, now is the
+	 * time to return to the upper layer and have it re-find the vma and
+	 * redo the fault.
+	 */
+	if (fpin) {
+		unlock_page(page);
+		goto out_retry;
+	}
+
+	/*
 	 * Found the page and have a reference on it.
 	 * We must recheck i_size under page lock.
 	 */
@@ -2561,30 +2580,6 @@
 	vmf->page = page;
 	return ret | VM_FAULT_LOCKED;
 
-no_cached_page:
-	/*
-	 * We're only likely to ever get here if MADV_RANDOM is in
-	 * effect.
-	 */
-	error = page_cache_read(file, offset, vmf->gfp_mask);
-
-	/*
-	 * The page we want has now been added to the page cache.
-	 * In the unlikely event that someone removed it in the
-	 * meantime, we'll just come back here and read it again.
-	 */
-	if (error >= 0)
-		goto retry_find;
-
-	/*
-	 * An error return from page_cache_read can result if the
-	 * system is low on memory, or a problem occurs while trying
-	 * to schedule I/O.
-	 */
-	if (error == -ENOMEM)
-		return VM_FAULT_OOM;
-	return VM_FAULT_SIGBUS;
-
 page_not_uptodate:
 	/*
 	 * Umm, take care of errors if the page isn't up-to-date.
@@ -2593,12 +2588,15 @@
 	 * and we need to check for errors.
 	 */
 	ClearPageError(page);
+	fpin = maybe_unlock_mmap_for_io(vmf, fpin);
 	error = mapping->a_ops->readpage(file, page);
 	if (!error) {
 		wait_on_page_locked(page);
 		if (!PageUptodate(page))
 			error = -EIO;
 	}
+	if (fpin)
+		goto out_retry;
 	put_page(page);
 
 	if (!error || error == AOP_TRUNCATED_PAGE)
@@ -2607,51 +2605,51 @@
 	/* Things didn't work out. Return zero to tell the mm layer so. */
 	shrink_readahead_size_eio(file, ra);
 	return VM_FAULT_SIGBUS;
+
+out_retry:
+	/*
+	 * We dropped the mmap_sem, we need to return to the fault handler to
+	 * re-find the vma and come back and find our hopefully still populated
+	 * page.
+	 */
+	if (page)
+		put_page(page);
+	if (fpin)
+		fput(fpin);
+	return ret | VM_FAULT_RETRY;
 }
 EXPORT_SYMBOL(filemap_fault);
 
 void filemap_map_pages(struct vm_fault *vmf,
 		pgoff_t start_pgoff, pgoff_t end_pgoff)
 {
-	struct radix_tree_iter iter;
-	void **slot;
 	struct file *file = vmf->vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
 	pgoff_t last_pgoff = start_pgoff;
 	unsigned long max_idx;
-	struct page *head, *page;
+	XA_STATE(xas, &mapping->i_pages, start_pgoff);
+	struct page *page;
 
 	rcu_read_lock();
-	radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start_pgoff) {
-		if (iter.index > end_pgoff)
-			break;
-repeat:
-		page = radix_tree_deref_slot(slot);
-		if (unlikely(!page))
+	xas_for_each(&xas, page, end_pgoff) {
+		if (xas_retry(&xas, page))
+			continue;
+		if (xa_is_value(page))
 			goto next;
-		if (radix_tree_exception(page)) {
-			if (radix_tree_deref_retry(page)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
+
+		/*
+		 * Check for a locked page first, as a speculative
+		 * reference may adversely influence page migration.
+		 */
+		if (PageLocked(page))
 			goto next;
-		}
+		if (!page_cache_get_speculative(page))
+			goto next;
 
-		head = compound_head(page);
-		if (!page_cache_get_speculative(head))
-			goto repeat;
-
-		/* The page was split under us? */
-		if (compound_head(page) != head) {
-			put_page(head);
-			goto repeat;
-		}
-
-		/* Has the page moved? */
-		if (unlikely(page != *slot)) {
-			put_page(head);
-			goto repeat;
-		}
+		/* Has the page moved or been split? */
+		if (unlikely(page != xas_reload(&xas)))
+			goto skip;
+		page = find_subpage(page, xas.xa_index);
 
 		if (!PageUptodate(page) ||
 				PageReadahead(page) ||
@@ -2670,10 +2668,10 @@
 		if (file->f_ra.mmap_miss > 0)
 			file->f_ra.mmap_miss--;
 
-		vmf->address += (iter.index - last_pgoff) << PAGE_SHIFT;
+		vmf->address += (xas.xa_index - last_pgoff) << PAGE_SHIFT;
 		if (vmf->pte)
-			vmf->pte += iter.index - last_pgoff;
-		last_pgoff = iter.index;
+			vmf->pte += xas.xa_index - last_pgoff;
+		last_pgoff = xas.xa_index;
 		if (alloc_set_pte(vmf, NULL, page))
 			goto unlock;
 		unlock_page(page);
@@ -2686,8 +2684,6 @@
 		/* Huge page is mapped? No need to proceed. */
 		if (pmd_trans_huge(*vmf->pmd))
 			break;
-		if (iter.index == end_pgoff)
-			break;
 	}
 	rcu_read_unlock();
 }
@@ -2748,9 +2744,9 @@
 	return generic_file_mmap(file, vma);
 }
 #else
-int filemap_page_mkwrite(struct vm_fault *vmf)
+vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
 {
-	return -ENOSYS;
+	return VM_FAULT_SIGBUS;
 }
 int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
 {
@@ -2797,12 +2793,16 @@
 			put_page(page);
 			if (err == -EEXIST)
 				goto repeat;
-			/* Presumably ENOMEM for radix tree node */
+			/* Presumably ENOMEM for xarray node */
 			return ERR_PTR(err);
 		}
 
 filler:
-		err = filler(data, page);
+		if (filler)
+			err = filler(data, page);
+		else
+			err = mapping->a_ops->readpage(data, page);
+
 		if (err < 0) {
 			put_page(page);
 			return ERR_PTR(err);
@@ -2884,13 +2884,16 @@
  * not set, try to fill the page and wait for it to become unlocked.
  *
  * If the page does not get brought uptodate, return -EIO.
+ *
+ * Return: up to date page on success, ERR_PTR() on failure.
  */
 struct page *read_cache_page(struct address_space *mapping,
 				pgoff_t index,
 				int (*filler)(void *, struct page *),
 				void *data)
 {
-	return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping));
+	return do_read_cache_page(mapping, index, filler, data,
+			mapping_gfp_mask(mapping));
 }
 EXPORT_SYMBOL(read_cache_page);
 
@@ -2904,18 +2907,49 @@
  * any new page allocations done using the specified allocation flags.
  *
  * If the page does not get brought uptodate, return -EIO.
+ *
+ * Return: up to date page on success, ERR_PTR() on failure.
  */
 struct page *read_cache_page_gfp(struct address_space *mapping,
 				pgoff_t index,
 				gfp_t gfp)
 {
-	filler_t *filler = (filler_t *)mapping->a_ops->readpage;
-
-	return do_read_cache_page(mapping, index, filler, NULL, gfp);
+	return do_read_cache_page(mapping, index, NULL, NULL, gfp);
 }
 EXPORT_SYMBOL(read_cache_page_gfp);
 
 /*
+ * Don't operate on ranges the page cache doesn't support, and don't exceed the
+ * LFS limits.  If pos is under the limit it becomes a short access.  If it
+ * exceeds the limit we return -EFBIG.
+ */
+static int generic_write_check_limits(struct file *file, loff_t pos,
+				      loff_t *count)
+{
+	struct inode *inode = file->f_mapping->host;
+	loff_t max_size = inode->i_sb->s_maxbytes;
+	loff_t limit = rlimit(RLIMIT_FSIZE);
+
+	if (limit != RLIM_INFINITY) {
+		if (pos >= limit) {
+			send_sig(SIGXFSZ, current, 0);
+			return -EFBIG;
+		}
+		*count = min(*count, limit - pos);
+	}
+
+	if (!(file->f_flags & O_LARGEFILE))
+		max_size = MAX_NON_LFS;
+
+	if (unlikely(pos >= max_size))
+		return -EFBIG;
+
+	*count = min(*count, max_size - pos);
+
+	return 0;
+}
+
+/*
  * Performs necessary checks before doing a write
  *
  * Can adjust writing position or amount of bytes to write.
@@ -2926,8 +2960,11 @@
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
-	unsigned long limit = rlimit(RLIMIT_FSIZE);
-	loff_t pos;
+	loff_t count;
+	int ret;
+
+	if (IS_SWAPFILE(inode))
+		return -ETXTBSY;
 
 	if (!iov_iter_count(from))
 		return 0;
@@ -2936,44 +2973,173 @@
 	if (iocb->ki_flags & IOCB_APPEND)
 		iocb->ki_pos = i_size_read(inode);
 
-	pos = iocb->ki_pos;
-
 	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
 		return -EINVAL;
 
-	if (limit != RLIM_INFINITY) {
-		if (iocb->ki_pos >= limit) {
-			send_sig(SIGXFSZ, current, 0);
-			return -EFBIG;
-		}
-		iov_iter_truncate(from, limit - (unsigned long)pos);
-	}
+	count = iov_iter_count(from);
+	ret = generic_write_check_limits(file, iocb->ki_pos, &count);
+	if (ret)
+		return ret;
 
-	/*
-	 * LFS rule
-	 */
-	if (unlikely(pos + iov_iter_count(from) > MAX_NON_LFS &&
-				!(file->f_flags & O_LARGEFILE))) {
-		if (pos >= MAX_NON_LFS)
-			return -EFBIG;
-		iov_iter_truncate(from, MAX_NON_LFS - (unsigned long)pos);
-	}
-
-	/*
-	 * Are we about to exceed the fs block limit ?
-	 *
-	 * If we have written data it becomes a short write.  If we have
-	 * exceeded without writing data we send a signal and return EFBIG.
-	 * Linus frestrict idea will clean these up nicely..
-	 */
-	if (unlikely(pos >= inode->i_sb->s_maxbytes))
-		return -EFBIG;
-
-	iov_iter_truncate(from, inode->i_sb->s_maxbytes - pos);
+	iov_iter_truncate(from, count);
 	return iov_iter_count(from);
 }
 EXPORT_SYMBOL(generic_write_checks);
 
+/*
+ * Performs necessary checks before doing a clone.
+ *
+ * Can adjust amount of bytes to clone via @req_count argument.
+ * Returns appropriate error code that caller should return or
+ * zero in case the clone should be allowed.
+ */
+int generic_remap_checks(struct file *file_in, loff_t pos_in,
+			 struct file *file_out, loff_t pos_out,
+			 loff_t *req_count, unsigned int remap_flags)
+{
+	struct inode *inode_in = file_in->f_mapping->host;
+	struct inode *inode_out = file_out->f_mapping->host;
+	uint64_t count = *req_count;
+	uint64_t bcount;
+	loff_t size_in, size_out;
+	loff_t bs = inode_out->i_sb->s_blocksize;
+	int ret;
+
+	/* The start of both ranges must be aligned to an fs block. */
+	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs))
+		return -EINVAL;
+
+	/* Ensure offsets don't wrap. */
+	if (pos_in + count < pos_in || pos_out + count < pos_out)
+		return -EINVAL;
+
+	size_in = i_size_read(inode_in);
+	size_out = i_size_read(inode_out);
+
+	/* Dedupe requires both ranges to be within EOF. */
+	if ((remap_flags & REMAP_FILE_DEDUP) &&
+	    (pos_in >= size_in || pos_in + count > size_in ||
+	     pos_out >= size_out || pos_out + count > size_out))
+		return -EINVAL;
+
+	/* Ensure the infile range is within the infile. */
+	if (pos_in >= size_in)
+		return -EINVAL;
+	count = min(count, size_in - (uint64_t)pos_in);
+
+	ret = generic_write_check_limits(file_out, pos_out, &count);
+	if (ret)
+		return ret;
+
+	/*
+	 * If the user wanted us to link to the infile's EOF, round up to the
+	 * next block boundary for this check.
+	 *
+	 * Otherwise, make sure the count is also block-aligned, having
+	 * already confirmed the starting offsets' block alignment.
+	 */
+	if (pos_in + count == size_in) {
+		bcount = ALIGN(size_in, bs) - pos_in;
+	} else {
+		if (!IS_ALIGNED(count, bs))
+			count = ALIGN_DOWN(count, bs);
+		bcount = count;
+	}
+
+	/* Don't allow overlapped cloning within the same file. */
+	if (inode_in == inode_out &&
+	    pos_out + bcount > pos_in &&
+	    pos_out < pos_in + bcount)
+		return -EINVAL;
+
+	/*
+	 * We shortened the request but the caller can't deal with that, so
+	 * bounce the request back to userspace.
+	 */
+	if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN))
+		return -EINVAL;
+
+	*req_count = count;
+	return 0;
+}
+
+
+/*
+ * Performs common checks before doing a file copy/clone
+ * from @file_in to @file_out.
+ */
+int generic_file_rw_checks(struct file *file_in, struct file *file_out)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+
+	/* Don't copy dirs, pipes, sockets... */
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		return -EISDIR;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		return -EINVAL;
+
+	if (!(file_in->f_mode & FMODE_READ) ||
+	    !(file_out->f_mode & FMODE_WRITE) ||
+	    (file_out->f_flags & O_APPEND))
+		return -EBADF;
+
+	return 0;
+}
+
+/*
+ * Performs necessary checks before doing a file copy
+ *
+ * Can adjust amount of bytes to copy via @req_count argument.
+ * Returns appropriate error code that caller should return or
+ * zero in case the copy should be allowed.
+ */
+int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
+			     struct file *file_out, loff_t pos_out,
+			     size_t *req_count, unsigned int flags)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+	uint64_t count = *req_count;
+	loff_t size_in;
+	int ret;
+
+	ret = generic_file_rw_checks(file_in, file_out);
+	if (ret)
+		return ret;
+
+	/* Don't touch certain kinds of inodes */
+	if (IS_IMMUTABLE(inode_out))
+		return -EPERM;
+
+	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
+		return -ETXTBSY;
+
+	/* Ensure offsets don't wrap. */
+	if (pos_in + count < pos_in || pos_out + count < pos_out)
+		return -EOVERFLOW;
+
+	/* Shorten the copy to EOF */
+	size_in = i_size_read(inode_in);
+	if (pos_in >= size_in)
+		count = 0;
+	else
+		count = min(count, size_in - (uint64_t)pos_in);
+
+	ret = generic_write_check_limits(file_out, pos_out, &count);
+	if (ret)
+		return ret;
+
+	/* Don't allow overlapped copying within the same file. */
+	if (inode_in == inode_out &&
+	    pos_out + count > pos_in &&
+	    pos_out < pos_in + count)
+		return -EINVAL;
+
+	*req_count = count;
+	return 0;
+}
+
 int pagecache_write_begin(struct file *file, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned flags,
 				struct page **pagep, void **fsdata)
@@ -3012,7 +3178,7 @@
 	if (iocb->ki_flags & IOCB_NOWAIT) {
 		/* If there are pages to writeback, return */
 		if (filemap_range_has_page(inode->i_mapping, pos,
-					   pos + iov_iter_count(from)))
+					   pos + write_len - 1))
 			return -EAGAIN;
 	} else {
 		written = filemap_write_and_wait_range(mapping, pos,
@@ -3195,6 +3361,10 @@
  * This function does *not* take care of syncing data in case of O_SYNC write.
  * A caller has to handle it. This is mainly due to the fact that we want to
  * avoid syncing under i_mutex.
+ *
+ * Return:
+ * * number of bytes written, even for truncated writes
+ * * negative error code if no data has been written at all
  */
 ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
@@ -3279,6 +3449,10 @@
  * This is a wrapper around __generic_file_write_iter() to be used by most
  * filesystems. It takes care of syncing the file in case of O_SYNC file
  * and acquires i_mutex as needed.
+ * Return:
+ * * negative error code if no data has been written at all of
+ *   vfs_fsync_range() failed for a synchronous write
+ * * number of bytes written, even for truncated writes
  */
 ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
@@ -3305,8 +3479,7 @@
  * @gfp_mask: memory allocation flags (and I/O mode)
  *
  * The address_space is to try to release any data against the page
- * (presumably at page->private).  If the release was successful, return '1'.
- * Otherwise return zero.
+ * (presumably at page->private).
  *
  * This may also be called if PG_fscache is set on a page, indicating that the
  * page is known to the local caching routines.
@@ -3314,6 +3487,7 @@
  * The @gfp_mask argument specifies whether I/O may be performed to release
  * this page (__GFP_IO), and whether the call may block (__GFP_RECLAIM & __GFP_FS).
  *
+ * Return: %1 if the release was successful, otherwise return zero.
  */
 int try_to_release_page(struct page *page, gfp_t gfp_mask)
 {