1 files changed, 134 insertions, 49 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 43700480d897..66f7e9fdfbc4 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -142,17 +142,6 @@ static void page_cache_delete(struct address_space *mapping,
 
 	page->mapping = NULL;
 	/* Leave page->index set: truncation lookup relies upon it */
-
-	if (shadow) {
-		mapping->nrexceptional += nr;
-		/*
-		 * Make sure the nrexceptional update is committed before
-		 * the nrpages update so that final truncate racing
-		 * with reclaim does not see both counters 0 at the
-		 * same time and miss a shadow entry.
-		 */
-		smp_wmb();
-	}
 	mapping->nrpages -= nr;
 }
 
@@ -629,13 +618,53 @@ 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)
 {
-	if (dax_mapping(mapping))
-		return mapping->nrexceptional;
-
 	return mapping->nrpages;
 }
 
 /**
+ * filemap_range_needs_writeback - check if range potentially needs writeback
+ * @mapping:           address space within which to check
+ * @start_byte:        offset in bytes where the range starts
+ * @end_byte:          offset in bytes where the range ends (inclusive)
+ *
+ * Find at least one page in the range supplied, usually used to check if
+ * direct writing in this range will trigger a writeback. Used by O_DIRECT
+ * read/write with IOCB_NOWAIT, to see if the caller needs to do
+ * filemap_write_and_wait_range() before proceeding.
+ *
+ * Return: %true if the caller should do filemap_write_and_wait_range() before
+ * doing O_DIRECT to a page in this range, %false otherwise.
+ */
+bool filemap_range_needs_writeback(struct address_space *mapping,
+				   loff_t start_byte, loff_t end_byte)
+{
+	XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT);
+	pgoff_t max = end_byte >> PAGE_SHIFT;
+	struct page *page;
+
+	if (!mapping_needs_writeback(mapping))
+		return false;
+	if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) &&
+	    !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK))
+		return false;
+	if (end_byte < start_byte)
+		return false;
+
+	rcu_read_lock();
+	xas_for_each(&xas, page, max) {
+		if (xas_retry(&xas, page))
+			continue;
+		if (xa_is_value(page))
+			continue;
+		if (PageDirty(page) || PageLocked(page) || PageWriteback(page))
+			break;
+	}
+	rcu_read_unlock();
+	return page != NULL;
+}
+EXPORT_SYMBOL_GPL(filemap_range_needs_writeback);
+
+/**
  * filemap_write_and_wait_range - write out & wait on a file range
  * @mapping:	the address_space for the pages
  * @lstart:	offset in bytes where the range starts
@@ -882,8 +911,6 @@ noinline int __add_to_page_cache_locked(struct page *page,
 		if (xas_error(&xas))
 			goto unlock;
 
-		if (old)
-			mapping->nrexceptional--;
 		mapping->nrpages++;
 
 		/* hugetlb pages do not participate in page cache accounting */
@@ -1433,6 +1460,67 @@ void unlock_page(struct page *page)
 EXPORT_SYMBOL(unlock_page);
 
 /**
+ * end_page_private_2 - Clear PG_private_2 and release any waiters
+ * @page: The page
+ *
+ * Clear the PG_private_2 bit on a page and wake up any sleepers waiting for
+ * this.  The page ref held for PG_private_2 being set is released.
+ *
+ * This is, for example, used when a netfs page is being written to a local
+ * disk cache, thereby allowing writes to the cache for the same page to be
+ * serialised.
+ */
+void end_page_private_2(struct page *page)
+{
+	page = compound_head(page);
+	VM_BUG_ON_PAGE(!PagePrivate2(page), page);
+	clear_bit_unlock(PG_private_2, &page->flags);
+	wake_up_page_bit(page, PG_private_2);
+	put_page(page);
+}
+EXPORT_SYMBOL(end_page_private_2);
+
+/**
+ * wait_on_page_private_2 - Wait for PG_private_2 to be cleared on a page
+ * @page: The page to wait on
+ *
+ * Wait for PG_private_2 (aka PG_fscache) to be cleared on a page.
+ */
+void wait_on_page_private_2(struct page *page)
+{
+	page = compound_head(page);
+	while (PagePrivate2(page))
+		wait_on_page_bit(page, PG_private_2);
+}
+EXPORT_SYMBOL(wait_on_page_private_2);
+
+/**
+ * wait_on_page_private_2_killable - Wait for PG_private_2 to be cleared on a page
+ * @page: The page to wait on
+ *
+ * Wait for PG_private_2 (aka PG_fscache) to be cleared on a page or until a
+ * fatal signal is received by the calling task.
+ *
+ * Return:
+ * - 0 if successful.
+ * - -EINTR if a fatal signal was encountered.
+ */
+int wait_on_page_private_2_killable(struct page *page)
+{
+	int ret = 0;
+
+	page = compound_head(page);
+	while (PagePrivate2(page)) {
+		ret = wait_on_page_bit_killable(page, PG_private_2);
+		if (ret < 0)
+			break;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(wait_on_page_private_2_killable);
+
+/**
  * end_page_writeback - end writeback against a page
  * @page: the page
  */
@@ -1663,7 +1751,7 @@ EXPORT_SYMBOL(page_cache_prev_miss);
  * @mapping: the address_space to search
  * @index: The page cache index.
  *
- * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * Looks up the page cache slot at @mapping & @index.  If there is a
  * page cache page, the head page is returned with an increased refcount.
  *
  * If the slot holds a shadow entry of a previously evicted page, or a
@@ -1969,8 +2057,14 @@ unlock:
 put:
 		put_page(page);
 next:
-		if (!xa_is_value(page) && PageTransHuge(page))
-			xas_set(&xas, page->index + thp_nr_pages(page));
+		if (!xa_is_value(page) && PageTransHuge(page)) {
+			unsigned int nr_pages = thp_nr_pages(page);
+
+			/* Final THP may cross MAX_LFS_FILESIZE on 32-bit */
+			xas_set(&xas, page->index + nr_pages);
+			if (xas.xa_index < nr_pages)
+				break;
+		}
 	}
 	rcu_read_unlock();
 
@@ -2238,8 +2332,6 @@ static int filemap_read_page(struct file *file, struct address_space *mapping,
 		return error;
 	if (PageUptodate(page))
 		return 0;
-	if (!page->mapping)	/* page truncated */
-		return AOP_TRUNCATED_PAGE;
 	shrink_readahead_size_eio(&file->f_ra);
 	return -EIO;
 }
@@ -2571,8 +2663,8 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 
 		size = i_size_read(inode);
 		if (iocb->ki_flags & IOCB_NOWAIT) {
-			if (filemap_range_has_page(mapping, iocb->ki_pos,
-						   iocb->ki_pos + count - 1))
+			if (filemap_range_needs_writeback(mapping, iocb->ki_pos,
+						iocb->ki_pos + count - 1))
 				return -EAGAIN;
 		} else {
 			retval = filemap_write_and_wait_range(mapping,
@@ -2663,7 +2755,7 @@ unsigned int seek_page_size(struct xa_state *xas, struct page *page)
  * entirely memory-based such as tmpfs, and filesystems which support
  * unwritten extents.
  *
- * Return: The requested offset on successs, or -ENXIO if @whence specifies
+ * Return: The requested offset on success, or -ENXIO if @whence specifies
  * SEEK_DATA and there is no data after @start.  There is an implicit hole
  * after @end - 1, so SEEK_HOLE returns @end if all the bytes between @start
  * and @end contain data.
@@ -2672,7 +2764,7 @@ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start,
 		loff_t end, int whence)
 {
 	XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT);
-	pgoff_t max = (end - 1) / PAGE_SIZE;
+	pgoff_t max = (end - 1) >> PAGE_SHIFT;
 	bool seek_data = (whence == SEEK_DATA);
 	struct page *page;
 
@@ -2681,7 +2773,8 @@ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start,
 
 	rcu_read_lock();
 	while ((page = find_get_entry(&xas, max, XA_PRESENT))) {
-		loff_t pos = xas.xa_index * PAGE_SIZE;
+		loff_t pos = (u64)xas.xa_index << PAGE_SHIFT;
+		unsigned int seek_size;
 
 		if (start < pos) {
 			if (!seek_data)
@@ -2689,25 +2782,25 @@ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start,
 			start = pos;
 		}
 
-		pos += seek_page_size(&xas, page);
+		seek_size = seek_page_size(&xas, page);
+		pos = round_up(pos + 1, seek_size);
 		start = page_seek_hole_data(&xas, mapping, page, start, pos,
 				seek_data);
 		if (start < pos)
 			goto unlock;
+		if (start >= end)
+			break;
+		if (seek_size > PAGE_SIZE)
+			xas_set(&xas, pos >> PAGE_SHIFT);
 		if (!xa_is_value(page))
 			put_page(page);
 	}
-	rcu_read_unlock();
-
 	if (seek_data)
-		return -ENXIO;
-	goto out;
-
+		start = -ENXIO;
 unlock:
 	rcu_read_unlock();
-	if (!xa_is_value(page))
+	if (page && !xa_is_value(page))
 		put_page(page);
-out:
 	if (start > end)
 		return end;
 	return start;
@@ -2771,7 +2864,7 @@ 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;
-	DEFINE_READAHEAD(ractl, file, mapping, vmf->pgoff);
+	DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff);
 	struct file *fpin = NULL;
 	unsigned int mmap_miss;
 
@@ -2783,7 +2876,7 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 
 	if (vmf->vma->vm_flags & VM_SEQ_READ) {
 		fpin = maybe_unlock_mmap_for_io(vmf, fpin);
-		page_cache_sync_ra(&ractl, ra, ra->ra_pages);
+		page_cache_sync_ra(&ractl, ra->ra_pages);
 		return fpin;
 	}
 
@@ -2869,7 +2962,6 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 	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;
 	pgoff_t offset = vmf->pgoff;
 	pgoff_t max_off;
@@ -2956,14 +3048,8 @@ page_not_uptodate:
 	 * because there really aren't any performance issues here
 	 * 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;
-	}
+	error = filemap_read_page(file, mapping, page);
 	if (fpin)
 		goto out_retry;
 	put_page(page);
@@ -2971,7 +3057,6 @@ page_not_uptodate:
 	if (!error || error == AOP_TRUNCATED_PAGE)
 		goto retry_find;
 
-	shrink_readahead_size_eio(ra);
 	return VM_FAULT_SIGBUS;
 
 out_retry:
@@ -3182,7 +3267,7 @@ const struct vm_operations_struct generic_file_vm_ops = {
 
 /* This is used for a general mmap of a disk file */
 
-int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
+int generic_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct address_space *mapping = file->f_mapping;
 
@@ -3207,11 +3292,11 @@ vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
 {
 	return VM_FAULT_SIGBUS;
 }
-int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
+int generic_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	return -ENOSYS;
 }
-int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma)
+int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	return -ENOSYS;
 }
@@ -3639,7 +3724,7 @@ EXPORT_SYMBOL(generic_perform_write);
 ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
-	struct address_space * mapping = file->f_mapping;
+	struct address_space *mapping = file->f_mapping;
 	struct inode 	*inode = mapping->host;
 	ssize_t		written = 0;
 	ssize_t		err;