1 files changed, 119 insertions, 226 deletions

diff --git a/fs/xfs/scrub/xfile.c b/fs/xfs/scrub/xfile.c
index 090c3ead43fd..8cdd863db585 100644
--- a/fs/xfs/scrub/xfile.c
+++ b/fs/xfs/scrub/xfile.c
@@ -34,13 +34,6 @@
  * xfiles assume that the caller will handle all required concurrency
  * management; standard vfs locks (freezer and inode) are not taken.  Reads
  * and writes are satisfied directly from the page cache.
- *
- * NOTE: The current shmemfs implementation has a quirk that in-kernel reads
- * of a hole cause a page to be mapped into the file.  If you are going to
- * create a sparse xfile, please be careful about reading from uninitialized
- * parts of the file.  These pages are !Uptodate and will eventually be
- * reclaimed if not written, but in the short term this boosts memory
- * consumption.
  */
 
 /*
@@ -62,38 +55,27 @@ xfile_create(
 {
 	struct inode		*inode;
 	struct xfile		*xf;
-	int			error = -ENOMEM;
+	int			error;
 
 	xf = kmalloc(sizeof(struct xfile), XCHK_GFP_FLAGS);
 	if (!xf)
 		return -ENOMEM;
 
-	xf->file = shmem_file_setup(description, isize, 0);
-	if (!xf->file)
-		goto out_xfile;
+	xf->file = shmem_kernel_file_setup(description, isize, VM_NORESERVE);
 	if (IS_ERR(xf->file)) {
 		error = PTR_ERR(xf->file);
 		goto out_xfile;
 	}
 
-	/*
-	 * We want a large sparse file that we can pread, pwrite, and seek.
-	 * xfile users are responsible for keeping the xfile hidden away from
-	 * all other callers, so we skip timestamp updates and security checks.
-	 * Make the inode only accessible by root, just in case the xfile ever
-	 * escapes.
-	 */
-	xf->file->f_mode |= FMODE_PREAD | FMODE_PWRITE | FMODE_NOCMTIME |
-			    FMODE_LSEEK;
-	xf->file->f_flags |= O_RDWR | O_LARGEFILE | O_NOATIME;
 	inode = file_inode(xf->file);
-	inode->i_flags |= S_PRIVATE | S_NOCMTIME | S_NOATIME;
-	inode->i_mode &= ~0177;
-	inode->i_uid = GLOBAL_ROOT_UID;
-	inode->i_gid = GLOBAL_ROOT_GID;
-
 	lockdep_set_class(&inode->i_rwsem, &xfile_i_mutex_key);
 
+	/*
+	 * We don't want to bother with kmapping data during repair, so don't
+	 * allow highmem pages to back this mapping.
+	 */
+	mapping_set_gfp_mask(inode->i_mapping, GFP_KERNEL);
+
 	trace_xfile_create(xf);
 
 	*xfilep = xf;
@@ -118,164 +100,128 @@ xfile_destroy(
 }
 
 /*
- * Read a memory object directly from the xfile's page cache.  Unlike regular
- * pread, we return -E2BIG and -EFBIG for reads that are too large or at too
- * high an offset, instead of truncating the read.  Otherwise, we return
- * bytes read or an error code, like regular pread.
+ * Load an object.  Since we're treating this file as "memory", any error or
+ * short IO is treated as a failure to allocate memory.
  */
-ssize_t
-xfile_pread(
+int
+xfile_load(
 	struct xfile		*xf,
 	void			*buf,
 	size_t			count,
 	loff_t			pos)
 {
 	struct inode		*inode = file_inode(xf->file);
-	struct address_space	*mapping = inode->i_mapping;
-	struct page		*page = NULL;
-	ssize_t			read = 0;
 	unsigned int		pflags;
-	int			error = 0;
 
 	if (count > MAX_RW_COUNT)
-		return -E2BIG;
+		return -ENOMEM;
 	if (inode->i_sb->s_maxbytes - pos < count)
-		return -EFBIG;
+		return -ENOMEM;
 
-	trace_xfile_pread(xf, pos, count);
+	trace_xfile_load(xf, pos, count);
 
 	pflags = memalloc_nofs_save();
 	while (count > 0) {
-		void		*p, *kaddr;
+		struct folio	*folio;
 		unsigned int	len;
+		unsigned int	offset;
 
-		len = min_t(ssize_t, count, PAGE_SIZE - offset_in_page(pos));
-
-		/*
-		 * In-kernel reads of a shmem file cause it to allocate a page
-		 * if the mapping shows a hole.  Therefore, if we hit ENOMEM
-		 * we can continue by zeroing the caller's buffer.
-		 */
-		page = shmem_read_mapping_page_gfp(mapping, pos >> PAGE_SHIFT,
-				__GFP_NOWARN);
-		if (IS_ERR(page)) {
-			error = PTR_ERR(page);
-			if (error != -ENOMEM)
-				break;
-
-			memset(buf, 0, len);
-			goto advance;
-		}
-
-		if (PageUptodate(page)) {
+		if (shmem_get_folio(inode, pos >> PAGE_SHIFT, &folio,
+				SGP_READ) < 0)
+			break;
+		if (!folio) {
 			/*
-			 * xfile pages must never be mapped into userspace, so
-			 * we skip the dcache flush.
+			 * No data stored at this offset, just zero the output
+			 * buffer until the next page boundary.
 			 */
-			kaddr = kmap_local_page(page);
-			p = kaddr + offset_in_page(pos);
-			memcpy(buf, p, len);
-			kunmap_local(kaddr);
-		} else {
+			len = min_t(ssize_t, count,
+				PAGE_SIZE - offset_in_page(pos));
 			memset(buf, 0, len);
-		}
-		put_page(page);
+		} else {
+			if (filemap_check_wb_err(inode->i_mapping, 0)) {
+				folio_unlock(folio);
+				folio_put(folio);
+				break;
+			}
+
+			offset = offset_in_folio(folio, pos);
+			len = min_t(ssize_t, count, folio_size(folio) - offset);
+			memcpy(buf, folio_address(folio) + offset, len);
 
-advance:
+			folio_unlock(folio);
+			folio_put(folio);
+		}
 		count -= len;
 		pos += len;
 		buf += len;
-		read += len;
 	}
 	memalloc_nofs_restore(pflags);
 
-	if (read > 0)
-		return read;
-	return error;
+	if (count)
+		return -ENOMEM;
+	return 0;
 }
 
 /*
- * Write a memory object directly to the xfile's page cache.  Unlike regular
- * pwrite, we return -E2BIG and -EFBIG for writes that are too large or at too
- * high an offset, instead of truncating the write.  Otherwise, we return
- * bytes written or an error code, like regular pwrite.
+ * Store an object.  Since we're treating this file as "memory", any error or
+ * short IO is treated as a failure to allocate memory.
  */
-ssize_t
-xfile_pwrite(
+int
+xfile_store(
 	struct xfile		*xf,
 	const void		*buf,
 	size_t			count,
 	loff_t			pos)
 {
 	struct inode		*inode = file_inode(xf->file);
-	struct address_space	*mapping = inode->i_mapping;
-	const struct address_space_operations *aops = mapping->a_ops;
-	struct page		*page = NULL;
-	ssize_t			written = 0;
 	unsigned int		pflags;
-	int			error = 0;
 
 	if (count > MAX_RW_COUNT)
-		return -E2BIG;
+		return -ENOMEM;
 	if (inode->i_sb->s_maxbytes - pos < count)
-		return -EFBIG;
+		return -ENOMEM;
 
-	trace_xfile_pwrite(xf, pos, count);
+	trace_xfile_store(xf, pos, count);
+
+	/*
+	 * Increase the file size first so that shmem_get_folio(..., SGP_CACHE),
+	 * actually allocates a folio instead of erroring out.
+	 */
+	if (pos + count > i_size_read(inode))
+		i_size_write(inode, pos + count);
 
 	pflags = memalloc_nofs_save();
 	while (count > 0) {
-		void		*fsdata = NULL;
-		void		*p, *kaddr;
+		struct folio	*folio;
 		unsigned int	len;
-		int		ret;
-
-		len = min_t(ssize_t, count, PAGE_SIZE - offset_in_page(pos));
-
-		/*
-		 * We call write_begin directly here to avoid all the freezer
-		 * protection lock-taking that happens in the normal path.
-		 * shmem doesn't support fs freeze, but lockdep doesn't know
-		 * that and will trip over that.
-		 */
-		error = aops->write_begin(NULL, mapping, pos, len, &page,
-				&fsdata);
-		if (error)
-			break;
+		unsigned int	offset;
 
-		/*
-		 * xfile pages must never be mapped into userspace, so we skip
-		 * the dcache flush.  If the page is not uptodate, zero it
-		 * before writing data.
-		 */
-		kaddr = kmap_local_page(page);
-		if (!PageUptodate(page)) {
-			memset(kaddr, 0, PAGE_SIZE);
-			SetPageUptodate(page);
-		}
-		p = kaddr + offset_in_page(pos);
-		memcpy(p, buf, len);
-		kunmap_local(kaddr);
-
-		ret = aops->write_end(NULL, mapping, pos, len, len, page,
-				fsdata);
-		if (ret < 0) {
-			error = ret;
+		if (shmem_get_folio(inode, pos >> PAGE_SHIFT, &folio,
+				SGP_CACHE) < 0)
+			break;
+		if (filemap_check_wb_err(inode->i_mapping, 0)) {
+			folio_unlock(folio);
+			folio_put(folio);
 			break;
 		}
 
-		written += ret;
-		if (ret != len)
-			break;
+		offset = offset_in_folio(folio, pos);
+		len = min_t(ssize_t, count, folio_size(folio) - offset);
+		memcpy(folio_address(folio) + offset, buf, len);
+
+		folio_mark_dirty(folio);
+		folio_unlock(folio);
+		folio_put(folio);
 
-		count -= ret;
-		pos += ret;
-		buf += ret;
+		count -= len;
+		pos += len;
+		buf += len;
 	}
 	memalloc_nofs_restore(pflags);
 
-	if (written > 0)
-		return written;
-	return error;
+	if (count)
+		return -ENOMEM;
+	return 0;
 }
 
 /* Find the next written area in the xfile data for a given offset. */
@@ -291,129 +237,76 @@ xfile_seek_data(
 	return ret;
 }
 
-/* Query stat information for an xfile. */
-int
-xfile_stat(
-	struct xfile		*xf,
-	struct xfile_stat	*statbuf)
-{
-	struct kstat		ks;
-	int			error;
-
-	error = vfs_getattr_nosec(&xf->file->f_path, &ks,
-			STATX_SIZE | STATX_BLOCKS, AT_STATX_DONT_SYNC);
-	if (error)
-		return error;
-
-	statbuf->size = ks.size;
-	statbuf->bytes = ks.blocks << SECTOR_SHIFT;
-	return 0;
-}
-
 /*
- * Grab the (locked) page for a memory object.  The object cannot span a page
- * boundary.  Returns 0 (and a locked page) if successful, -ENOTBLK if we
- * cannot grab the page, or the usual negative errno.
+ * Grab the (locked) folio for a memory object.  The object cannot span a folio
+ * boundary.  Returns the locked folio if successful, NULL if there was no
+ * folio or it didn't cover the range requested, or an ERR_PTR on failure.
  */
-int
-xfile_get_page(
+struct folio *
+xfile_get_folio(
 	struct xfile		*xf,
 	loff_t			pos,
-	unsigned int		len,
-	struct xfile_page	*xfpage)
+	size_t			len,
+	unsigned int		flags)
 {
 	struct inode		*inode = file_inode(xf->file);
-	struct address_space	*mapping = inode->i_mapping;
-	const struct address_space_operations *aops = mapping->a_ops;
-	struct page		*page = NULL;
-	void			*fsdata = NULL;
-	loff_t			key = round_down(pos, PAGE_SIZE);
+	struct folio		*folio = NULL;
 	unsigned int		pflags;
 	int			error;
 
 	if (inode->i_sb->s_maxbytes - pos < len)
-		return -ENOMEM;
-	if (len > PAGE_SIZE - offset_in_page(pos))
-		return -ENOTBLK;
-
-	trace_xfile_get_page(xf, pos, len);
+		return ERR_PTR(-ENOMEM);
 
-	pflags = memalloc_nofs_save();
+	trace_xfile_get_folio(xf, pos, len);
 
 	/*
-	 * We call write_begin directly here to avoid all the freezer
-	 * protection lock-taking that happens in the normal path.  shmem
-	 * doesn't support fs freeze, but lockdep doesn't know that and will
-	 * trip over that.
+	 * Increase the file size first so that shmem_get_folio(..., SGP_CACHE),
+	 * actually allocates a folio instead of erroring out.
 	 */
-	error = aops->write_begin(NULL, mapping, key, PAGE_SIZE, &page,
-			&fsdata);
+	if ((flags & XFILE_ALLOC) && pos + len > i_size_read(inode))
+		i_size_write(inode, pos + len);
+
+	pflags = memalloc_nofs_save();
+	error = shmem_get_folio(inode, pos >> PAGE_SHIFT, &folio,
+			(flags & XFILE_ALLOC) ? SGP_CACHE : SGP_READ);
+	memalloc_nofs_restore(pflags);
 	if (error)
-		goto out_pflags;
+		return ERR_PTR(error);
 
-	/* We got the page, so make sure we push out EOF. */
-	if (i_size_read(inode) < pos + len)
-		i_size_write(inode, pos + len);
+	if (!folio)
+		return NULL;
 
-	/*
-	 * If the page isn't up to date, fill it with zeroes before we hand it
-	 * to the caller and make sure the backing store will hold on to them.
-	 */
-	if (!PageUptodate(page)) {
-		void	*kaddr;
+	if (len > folio_size(folio) - offset_in_folio(folio, pos)) {
+		folio_unlock(folio);
+		folio_put(folio);
+		return NULL;
+	}
 
-		kaddr = kmap_local_page(page);
-		memset(kaddr, 0, PAGE_SIZE);
-		kunmap_local(kaddr);
-		SetPageUptodate(page);
+	if (filemap_check_wb_err(inode->i_mapping, 0)) {
+		folio_unlock(folio);
+		folio_put(folio);
+		return ERR_PTR(-EIO);
 	}
 
 	/*
-	 * Mark each page dirty so that the contents are written to some
-	 * backing store when we drop this buffer, and take an extra reference
-	 * to prevent the xfile page from being swapped or removed from the
-	 * page cache by reclaim if the caller unlocks the page.
+	 * Mark the folio dirty so that it won't be reclaimed once we drop the
+	 * (potentially last) reference in xfile_put_folio.
 	 */
-	set_page_dirty(page);
-	get_page(page);
-
-	xfpage->page = page;
-	xfpage->fsdata = fsdata;
-	xfpage->pos = key;
-out_pflags:
-	memalloc_nofs_restore(pflags);
-	return error;
+	if (flags & XFILE_ALLOC)
+		folio_set_dirty(folio);
+	return folio;
 }
 
 /*
- * Release the (locked) page for a memory object.  Returns 0 or a negative
- * errno.
+ * Release the (locked) folio for a memory object.
  */
-int
-xfile_put_page(
+void
+xfile_put_folio(
 	struct xfile		*xf,
-	struct xfile_page	*xfpage)
+	struct folio		*folio)
 {
-	struct inode		*inode = file_inode(xf->file);
-	struct address_space	*mapping = inode->i_mapping;
-	const struct address_space_operations *aops = mapping->a_ops;
-	unsigned int		pflags;
-	int			ret;
-
-	trace_xfile_put_page(xf, xfpage->pos, PAGE_SIZE);
-
-	/* Give back the reference that we took in xfile_get_page. */
-	put_page(xfpage->page);
+	trace_xfile_put_folio(xf, folio_pos(folio), folio_size(folio));
 
-	pflags = memalloc_nofs_save();
-	ret = aops->write_end(NULL, mapping, xfpage->pos, PAGE_SIZE, PAGE_SIZE,
-			xfpage->page, xfpage->fsdata);
-	memalloc_nofs_restore(pflags);
-	memset(xfpage, 0, sizeof(struct xfile_page));
-
-	if (ret < 0)
-		return ret;
-	if (ret != PAGE_SIZE)
-		return -EIO;
-	return 0;
+	folio_unlock(folio);
+	folio_put(folio);
 }