1 files changed, 91 insertions, 45 deletions

diff --git a/block/fops.c b/block/fops.c
index 82b672d15ea4..82451ac8ff25 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -73,6 +73,7 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 	}
 	bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT;
 	bio.bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
+	bio.bi_write_stream = iocb->ki_write_stream;
 	bio.bi_ioprio = iocb->ki_ioprio;
 	if (iocb->ki_flags & IOCB_ATOMIC)
 		bio.bi_opf |= REQ_ATOMIC;
@@ -206,6 +207,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	for (;;) {
 		bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
 		bio->bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
+		bio->bi_write_stream = iocb->ki_write_stream;
 		bio->bi_private = dio;
 		bio->bi_end_io = blkdev_bio_end_io;
 		bio->bi_ioprio = iocb->ki_ioprio;
@@ -333,6 +335,7 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 	dio->iocb = iocb;
 	bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
 	bio->bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
+	bio->bi_write_stream = iocb->ki_write_stream;
 	bio->bi_end_io = blkdev_bio_end_io_async;
 	bio->bi_ioprio = iocb->ki_ioprio;
 
@@ -398,6 +401,26 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	if (blkdev_dio_invalid(bdev, iocb, iter))
 		return -EINVAL;
 
+	if (iov_iter_rw(iter) == WRITE) {
+		u16 max_write_streams = bdev_max_write_streams(bdev);
+
+		if (iocb->ki_write_stream) {
+			if (iocb->ki_write_stream > max_write_streams)
+				return -EINVAL;
+		} else if (max_write_streams) {
+			enum rw_hint write_hint =
+				file_inode(iocb->ki_filp)->i_write_hint;
+
+			/*
+			 * Just use the write hint as write stream for block
+			 * device writes.  This assumes no file system is
+			 * mounted that would use the streams differently.
+			 */
+			if (write_hint <= max_write_streams)
+				iocb->ki_write_stream = write_hint;
+		}
+	}
+
 	nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
 	if (likely(nr_pages <= BIO_MAX_VECS)) {
 		if (is_sync_kiocb(iocb))
@@ -451,12 +474,13 @@ static int blkdev_get_block(struct inode *inode, sector_t iblock,
 static int blkdev_writepages(struct address_space *mapping,
 		struct writeback_control *wbc)
 {
+	struct folio *folio = NULL;
 	struct blk_plug plug;
 	int err;
 
 	blk_start_plug(&plug);
-	err = write_cache_pages(mapping, wbc, block_write_full_folio,
-			blkdev_get_block);
+	while ((folio = writeback_iter(mapping, wbc, folio, &err)))
+		err = block_write_full_folio(folio, wbc, blkdev_get_block);
 	blk_finish_plug(&plug);
 
 	return err;
@@ -472,18 +496,21 @@ static void blkdev_readahead(struct readahead_control *rac)
 	mpage_readahead(rac, blkdev_get_block);
 }
 
-static int blkdev_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
+static int blkdev_write_begin(const struct kiocb *iocb,
+			      struct address_space *mapping, loff_t pos,
+			      unsigned len, struct folio **foliop,
+			      void **fsdata)
 {
 	return block_write_begin(mapping, pos, len, foliop, blkdev_get_block);
 }
 
-static int blkdev_write_end(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned copied, struct folio *folio,
-		void *fsdata)
+static int blkdev_write_end(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len, unsigned copied,
+			    struct folio *folio, void *fsdata)
 {
 	int ret;
-	ret = block_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	ret = block_write_end(pos, len, copied, folio);
 
 	folio_unlock(folio);
 	folio_put(folio);
@@ -513,30 +540,42 @@ static void blkdev_readahead(struct readahead_control *rac)
 	iomap_readahead(rac, &blkdev_iomap_ops);
 }
 
-static int blkdev_map_blocks(struct iomap_writepage_ctx *wpc,
-		struct inode *inode, loff_t offset, unsigned int len)
+static ssize_t blkdev_writeback_range(struct iomap_writepage_ctx *wpc,
+		struct folio *folio, u64 offset, unsigned int len, u64 end_pos)
 {
-	loff_t isize = i_size_read(inode);
+	loff_t isize = i_size_read(wpc->inode);
 
 	if (WARN_ON_ONCE(offset >= isize))
 		return -EIO;
-	if (offset >= wpc->iomap.offset &&
-	    offset < wpc->iomap.offset + wpc->iomap.length)
-		return 0;
-	return blkdev_iomap_begin(inode, offset, isize - offset,
-				  IOMAP_WRITE, &wpc->iomap, NULL);
+
+	if (offset < wpc->iomap.offset ||
+	    offset >= wpc->iomap.offset + wpc->iomap.length) {
+		int error;
+
+		error = blkdev_iomap_begin(wpc->inode, offset, isize - offset,
+				IOMAP_WRITE, &wpc->iomap, NULL);
+		if (error)
+			return error;
+	}
+
+	return iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
 }
 
 static const struct iomap_writeback_ops blkdev_writeback_ops = {
-	.map_blocks		= blkdev_map_blocks,
+	.writeback_range	= blkdev_writeback_range,
+	.writeback_submit	= iomap_ioend_writeback_submit,
 };
 
 static int blkdev_writepages(struct address_space *mapping,
 		struct writeback_control *wbc)
 {
-	struct iomap_writepage_ctx wpc = { };
+	struct iomap_writepage_ctx wpc = {
+		.inode		= mapping->host,
+		.wbc		= wbc,
+		.ops		= &blkdev_writeback_ops
+	};
 
-	return iomap_writepages(mapping, wbc, &wpc, &blkdev_writeback_ops);
+	return iomap_writepages(&wpc);
 }
 
 const struct address_space_operations def_blk_aops = {
@@ -687,7 +726,8 @@ blkdev_direct_write(struct kiocb *iocb, struct iov_iter *from)
 
 static ssize_t blkdev_buffered_write(struct kiocb *iocb, struct iov_iter *from)
 {
-	return iomap_file_buffered_write(iocb, from, &blkdev_iomap_ops, NULL);
+	return iomap_file_buffered_write(iocb, from, &blkdev_iomap_ops, NULL,
+			NULL);
 }
 
 /*
@@ -817,7 +857,7 @@ reexpand:
 
 #define	BLKDEV_FALLOC_FL_SUPPORTED					\
 		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
-		 FALLOC_FL_ZERO_RANGE)
+		 FALLOC_FL_ZERO_RANGE | FALLOC_FL_WRITE_ZEROES)
 
 static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 			     loff_t len)
@@ -826,11 +866,19 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 	struct block_device *bdev = I_BDEV(inode);
 	loff_t end = start + len - 1;
 	loff_t isize;
+	unsigned int flags;
 	int error;
 
 	/* Fail if we don't recognize the flags. */
 	if (mode & ~BLKDEV_FALLOC_FL_SUPPORTED)
 		return -EOPNOTSUPP;
+	/*
+	 * Don't allow writing zeroes if the device does not enable the
+	 * unmap write zeroes operation.
+	 */
+	if ((mode & FALLOC_FL_WRITE_ZEROES) &&
+	    !bdev_write_zeroes_unmap_sectors(bdev))
+		return -EOPNOTSUPP;
 
 	/* Don't go off the end of the device. */
 	isize = bdev_nr_bytes(bdev);
@@ -853,48 +901,46 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 	inode_lock(inode);
 	filemap_invalidate_lock(inode->i_mapping);
 
-	/*
-	 * Invalidate the page cache, including dirty pages, for valid
-	 * de-allocate mode calls to fallocate().
-	 */
 	switch (mode) {
 	case FALLOC_FL_ZERO_RANGE:
 	case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
-		error = truncate_bdev_range(bdev, file_to_blk_mode(file), start, end);
-		if (error)
-			goto fail;
-
-		error = blkdev_issue_zeroout(bdev, start >> SECTOR_SHIFT,
-					     len >> SECTOR_SHIFT, GFP_KERNEL,
-					     BLKDEV_ZERO_NOUNMAP);
+		flags = BLKDEV_ZERO_NOUNMAP;
 		break;
 	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
-		error = truncate_bdev_range(bdev, file_to_blk_mode(file), start, end);
-		if (error)
-			goto fail;
-
-		error = blkdev_issue_zeroout(bdev, start >> SECTOR_SHIFT,
-					     len >> SECTOR_SHIFT, GFP_KERNEL,
-					     BLKDEV_ZERO_NOFALLBACK);
+		flags = BLKDEV_ZERO_NOFALLBACK;
+		break;
+	case FALLOC_FL_WRITE_ZEROES:
+		flags = 0;
 		break;
 	default:
 		error = -EOPNOTSUPP;
+		goto fail;
 	}
 
+	/*
+	 * Invalidate the page cache, including dirty pages, for valid
+	 * de-allocate mode calls to fallocate().
+	 */
+	error = truncate_bdev_range(bdev, file_to_blk_mode(file), start, end);
+	if (error)
+		goto fail;
+
+	error = blkdev_issue_zeroout(bdev, start >> SECTOR_SHIFT,
+				     len >> SECTOR_SHIFT, GFP_KERNEL, flags);
  fail:
 	filemap_invalidate_unlock(inode->i_mapping);
 	inode_unlock(inode);
 	return error;
 }
 
-static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
+static int blkdev_mmap_prepare(struct vm_area_desc *desc)
 {
-	struct inode *bd_inode = bdev_file_inode(file);
+	struct file *file = desc->file;
 
-	if (bdev_read_only(I_BDEV(bd_inode)))
-		return generic_file_readonly_mmap(file, vma);
+	if (bdev_read_only(I_BDEV(bdev_file_inode(file))))
+		return generic_file_readonly_mmap_prepare(desc);
 
-	return generic_file_mmap(file, vma);
+	return generic_file_mmap_prepare(desc);
 }
 
 const struct file_operations def_blk_fops = {
@@ -904,7 +950,7 @@ const struct file_operations def_blk_fops = {
 	.read_iter	= blkdev_read_iter,
 	.write_iter	= blkdev_write_iter,
 	.iopoll		= iocb_bio_iopoll,
-	.mmap		= blkdev_mmap,
+	.mmap_prepare	= blkdev_mmap_prepare,
 	.fsync		= blkdev_fsync,
 	.unlocked_ioctl	= blkdev_ioctl,
 #ifdef CONFIG_COMPAT