1 files changed, 58 insertions, 34 deletions

diff --git a/fs/iomap.c b/fs/iomap.c
index be61cf742b5e..afd163586aa0 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -65,6 +65,8 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,
 		return ret;
 	if (WARN_ON(iomap.offset > pos))
 		return -EIO;
+	if (WARN_ON(iomap.length == 0))
+		return -EIO;
 
 	/*
 	 * Cut down the length to the one actually provided by the filesystem,
@@ -350,8 +352,8 @@ static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
 static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
 		struct iomap *iomap)
 {
-	sector_t sector = iomap->blkno +
-		(((pos & ~(PAGE_SIZE - 1)) - iomap->offset) >> 9);
+	sector_t sector = (iomap->addr +
+			   (pos & PAGE_MASK) - iomap->offset) >> 9;
 
 	return __dax_zero_page_range(iomap->bdev, iomap->dax_dev, sector,
 			offset, bytes);
@@ -510,11 +512,12 @@ static int iomap_to_fiemap(struct fiemap_extent_info *fi,
 		flags |= FIEMAP_EXTENT_MERGED;
 	if (iomap->flags & IOMAP_F_SHARED)
 		flags |= FIEMAP_EXTENT_SHARED;
+	if (iomap->flags & IOMAP_F_DATA_INLINE)
+		flags |= FIEMAP_EXTENT_DATA_INLINE;
 
 	return fiemap_fill_next_extent(fi, iomap->offset,
-			iomap->blkno != IOMAP_NULL_BLOCK ? iomap->blkno << 9: 0,
+			iomap->addr != IOMAP_NULL_ADDR ? iomap->addr : 0,
 			iomap->length, flags);
-
 }
 
 static loff_t
@@ -714,23 +717,9 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
 	struct kiocb *iocb = dio->iocb;
 	struct inode *inode = file_inode(iocb->ki_filp);
+	loff_t offset = iocb->ki_pos;
 	ssize_t ret;
 
-	/*
-	 * Try again to invalidate clean pages which might have been cached by
-	 * non-direct readahead, or faulted in by get_user_pages() if the source
-	 * of the write was an mmap'ed region of the file we're writing.  Either
-	 * one is a pretty crazy thing to do, so we don't support it 100%.  If
-	 * this invalidation fails, tough, the write still worked...
-	 */
-	if (!dio->error &&
-	    (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
-		ret = invalidate_inode_pages2_range(inode->i_mapping,
-				iocb->ki_pos >> PAGE_SHIFT,
-				(iocb->ki_pos + dio->size - 1) >> PAGE_SHIFT);
-		WARN_ON_ONCE(ret);
-	}
-
 	if (dio->end_io) {
 		ret = dio->end_io(iocb,
 				dio->error ? dio->error : dio->size,
@@ -742,12 +731,34 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	if (likely(!ret)) {
 		ret = dio->size;
 		/* check for short read */
-		if (iocb->ki_pos + ret > dio->i_size &&
+		if (offset + ret > dio->i_size &&
 		    !(dio->flags & IOMAP_DIO_WRITE))
-			ret = dio->i_size - iocb->ki_pos;
+			ret = dio->i_size - offset;
 		iocb->ki_pos += ret;
 	}
 
+	/*
+	 * Try again to invalidate clean pages which might have been cached by
+	 * non-direct readahead, or faulted in by get_user_pages() if the source
+	 * of the write was an mmap'ed region of the file we're writing.  Either
+	 * one is a pretty crazy thing to do, so we don't support it 100%.  If
+	 * this invalidation fails, tough, the write still worked...
+	 *
+	 * And this page cache invalidation has to be after dio->end_io(), as
+	 * some filesystems convert unwritten extents to real allocations in
+	 * end_io() when necessary, otherwise a racing buffer read would cache
+	 * zeros from unwritten extents.
+	 */
+	if (!dio->error &&
+	    (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
+		int err;
+		err = invalidate_inode_pages2_range(inode->i_mapping,
+				offset >> PAGE_SHIFT,
+				(offset + dio->size - 1) >> PAGE_SHIFT);
+		if (err)
+			dio_warn_stale_pagecache(iocb->ki_filp);
+	}
+
 	inode_dio_end(file_inode(iocb->ki_filp));
 	kfree(dio);
 
@@ -823,7 +834,7 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
 	bio = bio_alloc(GFP_KERNEL, 1);
 	bio_set_dev(bio, iomap->bdev);
 	bio->bi_iter.bi_sector =
-		iomap->blkno + ((pos - iomap->offset) >> 9);
+		(iomap->addr + pos - iomap->offset) >> 9;
 	bio->bi_private = dio;
 	bio->bi_end_io = iomap_dio_bio_end_io;
 
@@ -848,6 +859,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 	struct bio *bio;
 	bool need_zeroout = false;
 	int nr_pages, ret;
+	size_t copied = 0;
 
 	if ((pos | length | align) & ((1 << blkbits) - 1))
 		return -EINVAL;
@@ -859,7 +871,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 		/*FALLTHRU*/
 	case IOMAP_UNWRITTEN:
 		if (!(dio->flags & IOMAP_DIO_WRITE)) {
-			iov_iter_zero(length, dio->submit.iter);
+			length = iov_iter_zero(length, dio->submit.iter);
 			dio->size += length;
 			return length;
 		}
@@ -896,13 +908,16 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 	}
 
 	do {
-		if (dio->error)
+		size_t n;
+		if (dio->error) {
+			iov_iter_revert(dio->submit.iter, copied);
 			return 0;
+		}
 
 		bio = bio_alloc(GFP_KERNEL, nr_pages);
 		bio_set_dev(bio, iomap->bdev);
 		bio->bi_iter.bi_sector =
-			iomap->blkno + ((pos - iomap->offset) >> 9);
+			(iomap->addr + pos - iomap->offset) >> 9;
 		bio->bi_write_hint = dio->iocb->ki_hint;
 		bio->bi_private = dio;
 		bio->bi_end_io = iomap_dio_bio_end_io;
@@ -910,20 +925,24 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 		ret = bio_iov_iter_get_pages(bio, &iter);
 		if (unlikely(ret)) {
 			bio_put(bio);
-			return ret;
+			return copied ? copied : ret;
 		}
 
+		n = bio->bi_iter.bi_size;
 		if (dio->flags & IOMAP_DIO_WRITE) {
 			bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_SYNC | REQ_IDLE);
-			task_io_account_write(bio->bi_iter.bi_size);
+			task_io_account_write(n);
 		} else {
 			bio_set_op_attrs(bio, REQ_OP_READ, 0);
 			if (dio->flags & IOMAP_DIO_DIRTY)
 				bio_set_pages_dirty(bio);
 		}
 
-		dio->size += bio->bi_iter.bi_size;
-		pos += bio->bi_iter.bi_size;
+		iov_iter_advance(dio->submit.iter, n);
+
+		dio->size += n;
+		pos += n;
+		copied += n;
 
 		nr_pages = iov_iter_npages(&iter, BIO_MAX_PAGES);
 
@@ -939,9 +958,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 		if (pad)
 			iomap_dio_zero(dio, iomap, pos, fs_block_size - pad);
 	}
-
-	iov_iter_advance(dio->submit.iter, length);
-	return length;
+	return copied;
 }
 
 ssize_t
@@ -1004,9 +1021,16 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (ret)
 		goto out_free_dio;
 
+	/*
+	 * Try to invalidate cache pages for the range we're direct
+	 * writing.  If this invalidation fails, tough, the write will
+	 * still work, but racing two incompatible write paths is a
+	 * pretty crazy thing to do, so we don't support it 100%.
+	 */
 	ret = invalidate_inode_pages2_range(mapping,
 			start >> PAGE_SHIFT, end >> PAGE_SHIFT);
-	WARN_ON_ONCE(ret);
+	if (ret)
+		dio_warn_stale_pagecache(iocb->ki_filp);
 	ret = 0;
 
 	if (iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) &&
@@ -1049,7 +1073,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 
 			if (!(iocb->ki_flags & IOCB_HIPRI) ||
 			    !dio->submit.last_queue ||
-			    !blk_mq_poll(dio->submit.last_queue,
+			    !blk_poll(dio->submit.last_queue,
 					 dio->submit.cookie))
 				io_schedule();
 		}