Merge tag 'vfs-6.13.untorn.writes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs untorn write support from Christian Brauner:
 "An atomic write is a write issed with torn-write protection. This
  means for a power failure or any hardware failure all or none of the
  data from the write will be stored, never a mix of old and new data.

  This work is already supported for block devices. If a block device is
  opened with O_DIRECT and the block device supports atomic write, then
  FMODE_CAN_ATOMIC_WRITE is added to the file of the opened block
  device.

  This contains the work to expand atomic write support to filesystems,
  specifically ext4 and XFS. Currently, only support for writing exactly
  one filesystem block atomically is added.

  Since it's now possible to have filesystem block size > page size for
  XFS, it's possible to write 4K+ blocks atomically on x86"

* tag 'vfs-6.13.untorn.writes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  iomap: drop an obsolete comment in iomap_dio_bio_iter
  ext4: Do not fallback to buffered-io for DIO atomic write
  ext4: Support setting FMODE_CAN_ATOMIC_WRITE
  ext4: Check for atomic writes support in write iter
  ext4: Add statx support for atomic writes
  xfs: Support setting FMODE_CAN_ATOMIC_WRITE
  xfs: Validate atomic writes
  xfs: Support atomic write for statx
  fs: iomap: Atomic write support
  fs: Export generic_atomic_write_valid()
  block: Add bdev atomic write limits helpers
  fs/block: Check for IOCB_DIRECT in generic_atomic_write_valid()
  block/fs: Pass an iocb to generic_atomic_write_valid()

1 files changed, 34 insertions, 9 deletions

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index f637aa0706a3..b521eb15759e 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -271,7 +271,7 @@ static int iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio,
  * clearing the WRITE_THROUGH flag in the dio request.
  */
 static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio,
-		const struct iomap *iomap, bool use_fua)
+		const struct iomap *iomap, bool use_fua, bool atomic)
 {
 	blk_opf_t opflags = REQ_SYNC | REQ_IDLE;
 
@@ -283,6 +283,8 @@ static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio,
 		opflags |= REQ_FUA;
 	else
 		dio->flags &= ~IOMAP_DIO_WRITE_THROUGH;
+	if (atomic)
+		opflags |= REQ_ATOMIC;
 
 	return opflags;
 }
@@ -293,7 +295,8 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 	const struct iomap *iomap = &iter->iomap;
 	struct inode *inode = iter->inode;
 	unsigned int fs_block_size = i_blocksize(inode), pad;
-	loff_t length = iomap_length(iter);
+	const loff_t length = iomap_length(iter);
+	bool atomic = iter->flags & IOMAP_ATOMIC;
 	loff_t pos = iter->pos;
 	blk_opf_t bio_opf;
 	struct bio *bio;
@@ -303,6 +306,9 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 	size_t copied = 0;
 	size_t orig_count;
 
+	if (atomic && length != fs_block_size)
+		return -EINVAL;
+
 	if ((pos | length) & (bdev_logical_block_size(iomap->bdev) - 1) ||
 	    !bdev_iter_is_aligned(iomap->bdev, dio->submit.iter))
 		return -EINVAL;
@@ -377,12 +383,7 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 			goto out;
 	}
 
-	/*
-	 * Set the operation flags early so that bio_iov_iter_get_pages
-	 * can set up the page vector appropriately for a ZONE_APPEND
-	 * operation.
-	 */
-	bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua);
+	bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua, atomic);
 
 	nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS);
 	do {
@@ -415,6 +416,17 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 		}
 
 		n = bio->bi_iter.bi_size;
+		if (WARN_ON_ONCE(atomic && n != length)) {
+			/*
+			 * This bio should have covered the complete length,
+			 * which it doesn't, so error. We may need to zero out
+			 * the tail (complete FS block), similar to when
+			 * bio_iov_iter_get_pages() returns an error, above.
+			 */
+			ret = -EINVAL;
+			bio_put(bio);
+			goto zero_tail;
+		}
 		if (dio->flags & IOMAP_DIO_WRITE) {
 			task_io_account_write(n);
 		} else {
@@ -598,6 +610,9 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (iocb->ki_flags & IOCB_NOWAIT)
 		iomi.flags |= IOMAP_NOWAIT;
 
+	if (iocb->ki_flags & IOCB_ATOMIC)
+		iomi.flags |= IOMAP_ATOMIC;
+
 	if (iov_iter_rw(iter) == READ) {
 		/* reads can always complete inline */
 		dio->flags |= IOMAP_DIO_INLINE_COMP;
@@ -659,7 +674,17 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 			if (ret != -EAGAIN) {
 				trace_iomap_dio_invalidate_fail(inode, iomi.pos,
 								iomi.len);
-				ret = -ENOTBLK;
+				if (iocb->ki_flags & IOCB_ATOMIC) {
+					/*
+					 * folio invalidation failed, maybe
+					 * this is transient, unlock and see if
+					 * the caller tries again.
+					 */
+					ret = -EAGAIN;
+				} else {
+					/* fall back to buffered write */
+					ret = -ENOTBLK;
+				}
 			}
 			goto out_free_dio;
 		}