Merge tag 'iomap-5.10-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull iomap updates from Darrick Wong:
 "There's not a lot of new stuff going on here -- a little bit of code
  refactoring to make iomap workable with btrfs' fsync locking model,
  cleanups in preparation for adding THP support for filesystems, and
  fixing a data corruption issue for blocksize < pagesize filesystems.

  Summary:

   - Don't WARN_ON weird states that unprivileged users can create.

   - Don't invalidate page cache when direct writes want to fall back to
     buffered.

   - Fix some problems when readahead ios fail.

   - Fix a problem where inline data pages weren't getting flushed
     during an unshare operation.

   - Rework iomap to support arbitrarily many blocks per page in
     preparation to support THP for the page cache.

   - Fix a bug in the blocksize < pagesize buffered io path where we
     could fail to initialize the many-blocks-per-page uptodate bitmap
     correctly when the backing page is actually up to date. This could
     cause us to forget to write out dirty pages.

   - Split out the generic_write_sync at the end of the directio write
     path so that btrfs can drop the inode lock before sync'ing the
     file.

   - Call inode_dio_end before trying to sync the file after a O_DSYNC
     direct write (instead of afterwards) to match the behavior of the
     old directio code"

* tag 'iomap-5.10-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  iomap: Call inode_dio_end() before generic_write_sync()
  iomap: Allow filesystem to call iomap_dio_complete without i_rwsem
  iomap: Set all uptodate bits for an Uptodate page
  iomap: Change calling convention for zeroing
  iomap: Convert iomap_write_end types
  iomap: Convert write_count to write_bytes_pending
  iomap: Convert read_count to read_bytes_pending
  iomap: Support arbitrarily many blocks per page
  iomap: Use bitmap ops to set uptodate bits
  iomap: Use kzalloc to allocate iomap_page
  fs: Introduce i_blocks_per_page
  iomap: Fix misplaced page flushing
  iomap: Use round_down/round_up macros in __iomap_write_begin
  iomap: Mark read blocks uptodate in write_begin
  iomap: Clear page error before beginning a write
  iomap: Fix direct I/O write consistency check
  iomap: fix WARN_ON_ONCE() from unprivileged users

fs/dax.c

@@ -1037,18 +1037,18 @@ static vm_fault_t dax_load_hole(struct xa_state *xas,
 	return ret;
 }
 
-int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
-		   struct iomap *iomap)
+s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
 {
 	sector_t sector = iomap_sector(iomap, pos & PAGE_MASK);
 	pgoff_t pgoff;
 	long rc, id;
 	void *kaddr;
 	bool page_aligned = false;
-
+	unsigned offset = offset_in_page(pos);
+	unsigned size = min_t(u64, PAGE_SIZE - offset, length);
 
 	if (IS_ALIGNED(sector << SECTOR_SHIFT, PAGE_SIZE) &&
-	    IS_ALIGNED(size, PAGE_SIZE))
+	    (size == PAGE_SIZE))
 		page_aligned = true;
 
 	rc = bdev_dax_pgoff(iomap->bdev, sector, PAGE_SIZE, &pgoff);
@@ -1058,8 +1058,7 @@ int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
 	id = dax_read_lock();
 
 	if (page_aligned)
-		rc = dax_zero_page_range(iomap->dax_dev, pgoff,
-					 size >> PAGE_SHIFT);
+		rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
 	else
 		rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL);
 	if (rc < 0) {
@@ -1072,7 +1071,7 @@ int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
 		dax_flush(iomap->dax_dev, kaddr + offset, size);
 	}
 	dax_read_unlock(id);
-	return 0;
+	return size;
 }
 
 static loff_t

fs/iomap/direct-io.c

@@ -76,7 +76,7 @@ static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap,
 		dio->submit.cookie = submit_bio(bio);
 }
 
-static ssize_t iomap_dio_complete(struct iomap_dio *dio)
+ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
 	const struct iomap_dio_ops *dops = dio->dops;
 	struct kiocb *iocb = dio->iocb;
@@ -108,7 +108,7 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	 * ->end_io() when necessary, otherwise a racing buffer read would cache
 	 * zeros from unwritten extents.
 	 */
-	if (!dio->error &&
+	if (!dio->error && dio->size &&
 	    (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
 		int err;
 		err = invalidate_inode_pages2_range(inode->i_mapping,
@@ -118,6 +118,7 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 			dio_warn_stale_pagecache(iocb->ki_filp);
 	}
 
+	inode_dio_end(file_inode(iocb->ki_filp));
 	/*
 	 * If this is a DSYNC write, make sure we push it to stable storage now
 	 * that we've written data.
@@ -125,11 +126,11 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC))
 		ret = generic_write_sync(iocb, ret);
 
-	inode_dio_end(file_inode(iocb->ki_filp));
 	kfree(dio);
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(iomap_dio_complete);
 
 static void iomap_dio_complete_work(struct work_struct *work)
 {
@@ -388,6 +389,16 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 		return iomap_dio_bio_actor(inode, pos, length, dio, iomap);
 	case IOMAP_INLINE:
 		return iomap_dio_inline_actor(inode, pos, length, dio, iomap);
+	case IOMAP_DELALLOC:
+		/*
+		 * DIO is not serialised against mmap() access at all, and so
+		 * if the page_mkwrite occurs between the writeback and the
+		 * iomap_apply() call in the DIO path, then it will see the
+		 * DELALLOC block that the page-mkwrite allocated.
+		 */
+		pr_warn_ratelimited("Direct I/O collision with buffered writes! File: %pD4 Comm: %.20s\n",
+				    dio->iocb->ki_filp, current->comm);
+		return -EIO;
 	default:
 		WARN_ON_ONCE(1);
 		return -EIO;
@@ -406,8 +417,8 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
  * Returns -ENOTBLK In case of a page invalidation invalidation failure for
  * writes.  The callers needs to fall back to buffered I/O in this case.
  */
-ssize_t
-iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+struct iomap_dio *
+__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		bool wait_for_completion)
 {
@@ -421,14 +432,14 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	struct iomap_dio *dio;
 
 	if (!count)
-		return 0;
+		return NULL;
 
 	if (WARN_ON(is_sync_kiocb(iocb) && !wait_for_completion))
-		return -EIO;
+		return ERR_PTR(-EIO);
 
 	dio = kmalloc(sizeof(*dio), GFP_KERNEL);
 	if (!dio)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	dio->iocb = iocb;
 	atomic_set(&dio->ref, 1);
@@ -558,7 +569,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	dio->wait_for_completion = wait_for_completion;
 	if (!atomic_dec_and_test(&dio->ref)) {
 		if (!wait_for_completion)
-			return -EIOCBQUEUED;
+			return ERR_PTR(-EIOCBQUEUED);
 
 		for (;;) {
 			set_current_state(TASK_UNINTERRUPTIBLE);
@@ -574,10 +585,26 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		__set_current_state(TASK_RUNNING);
 	}
 
-	return iomap_dio_complete(dio);
+	return dio;
 
 out_free_dio:
 	kfree(dio);
-	return ret;
+	if (ret)
+		return ERR_PTR(ret);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(__iomap_dio_rw);
+
+ssize_t
+iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
+		bool wait_for_completion)
+{
+	struct iomap_dio *dio;
+
+	dio = __iomap_dio_rw(iocb, iter, ops, dops, wait_for_completion);
+	if (IS_ERR_OR_NULL(dio))
+		return PTR_ERR_OR_ZERO(dio);
+	return iomap_dio_complete(dio);
 }
 EXPORT_SYMBOL_GPL(iomap_dio_rw);

fs/jfs/jfs_metapage.c

@@ -473,7 +473,7 @@ static int metapage_readpage(struct file *fp, struct page *page)
 	struct inode *inode = page->mapping->host;
 	struct bio *bio = NULL;
 	int block_offset;
-	int blocks_per_page = PAGE_SIZE >> inode->i_blkbits;
+	int blocks_per_page = i_blocks_per_page(inode, page);
 	sector_t page_start;	/* address of page in fs blocks */
 	sector_t pblock;
 	int xlen;

fs/xfs/xfs_aops.c

@@ -544,7 +544,7 @@ xfs_discard_page(
 			page, ip->i_ino, offset);
 
 	error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
-			PAGE_SIZE / i_blocksize(inode));
+			i_blocks_per_page(inode, page));
 	if (error && !XFS_FORCED_SHUTDOWN(mp))
 		xfs_alert(mp, "page discard unable to remove delalloc mapping.");
 out_invalidate:

include/linux/dax.h

@@ -231,8 +231,7 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index);
-int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
-			struct iomap *iomap);
+s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap);
 static inline bool dax_mapping(struct address_space *mapping)
 {
 	return mapping->host && IS_DAX(mapping->host);

include/linux/iomap.h

@@ -13,6 +13,7 @@
 struct address_space;
 struct fiemap_extent_info;
 struct inode;
+struct iomap_dio;
 struct iomap_writepage_ctx;
 struct iov_iter;
 struct kiocb;
@@ -258,6 +259,10 @@ struct iomap_dio_ops {
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		bool wait_for_completion);
+struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
+		bool wait_for_completion);
+ssize_t iomap_dio_complete(struct iomap_dio *dio);
 int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
 
 #ifdef CONFIG_SWAP

include/linux/pagemap.h

@@ -927,4 +927,20 @@ static inline int page_mkwrite_check_truncate(struct page *page,
 	return offset;
 }
 
+/**
+ * i_blocks_per_page - How many blocks fit in this page.
+ * @inode: The inode which contains the blocks.
+ * @page: The page (head page if the page is a THP).
+ *
+ * If the block size is larger than the size of this page, return zero.
+ *
+ * Context: The caller should hold a refcount on the page to prevent it
+ * from being split.
+ * Return: The number of filesystem blocks covered by this page.
+ */
+static inline
+unsigned int i_blocks_per_page(struct inode *inode, struct page *page)
+{
+	return thp_size(page) >> inode->i_blkbits;
+}
 #endif /* _LINUX_PAGEMAP_H */