Merge patch series "iomap preliminaries for large atomic write for xfs with CoW"

Bring in the iomap changes required for xfs to support large atomic
write with CoW.

* patches from https://lore.kernel.org/r/20250303171120.2837067-1-john.g.garry@oracle.com:
  iomap: Lift blocksize restriction on atomic writes
  iomap: Support SW-based atomic writes
  iomap: Rename IOMAP_ATOMIC -> IOMAP_ATOMIC_HW

Link: https://lore.kernel.org/r/20250303171120.2837067-1-john.g.garry@oracle.com
Signed-off-by: Christian Brauner <brauner@kernel.org>

Author: brauner

Documentation/filesystems/iomap/operations.rst

@@ -514,8 +514,8 @@ IOMAP_WRITE`` with any combination of the following enhancements:
    if the mapping is unwritten and the filesystem cannot handle zeroing
    the unaligned regions without exposing stale contents.
 
- * ``IOMAP_ATOMIC``: This write is being issued with torn-write
-   protection.
+ * ``IOMAP_ATOMIC_HW``: This write is being issued with torn-write
+   protection based on HW-offload support.
    Only a single bio can be created for the write, and the write must
    not be split into multiple I/O requests, i.e. flag REQ_ATOMIC must be
    set.
@@ -526,8 +526,20 @@ IOMAP_WRITE`` with any combination of the following enhancements:
    conversion or copy on write), all updates for the entire file range
    must be committed atomically as well.
    Only one space mapping is allowed per untorn write.
-   Untorn writes must be aligned to, and must not be longer than, a
-   single file block.
+   Untorn writes may be longer than a single file block. In all cases,
+   the mapping start disk block must have at least the same alignment as
+   the write offset.
+
+ * ``IOMAP_ATOMIC_SW``: This write is being issued with torn-write
+   protection via a software mechanism provided by the filesystem.
+   All the disk block alignment and single bio restrictions which apply
+   to IOMAP_ATOMIC_HW do not apply here.
+   SW-based untorn writes would typically be used as a fallback when
+   HW-based untorn writes may not be issued, e.g. the range of the write
+   covers multiple extents, meaning that it is not possible to issue
+   a single bio.
+   All filesystem metadata updates for the entire file range must be
+   committed atomically as well.
 
 Callers commonly hold ``i_rwsem`` in shared or exclusive mode before
 calling this function.

fs/ext4/inode.c

@@ -3467,7 +3467,7 @@ static inline bool ext4_want_directio_fallback(unsigned flags, ssize_t written)
 		return false;
 
 	/* atomic writes are all-or-nothing */
-	if (flags & IOMAP_ATOMIC)
+	if (flags & IOMAP_ATOMIC_HW)
 		return false;
 
 	/* can only try again if we wrote nothing */

fs/iomap/direct-io.c

@@ -317,7 +317,7 @@ 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, bool atomic)
+		const struct iomap *iomap, bool use_fua, bool atomic_hw)
 {
 	blk_opf_t opflags = REQ_SYNC | REQ_IDLE;
 
@@ -329,7 +329,7 @@ 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)
+	if (atomic_hw)
 		opflags |= REQ_ATOMIC;
 
 	return opflags;
@@ -340,8 +340,8 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 	const struct iomap *iomap = &iter->iomap;
 	struct inode *inode = iter->inode;
 	unsigned int fs_block_size = i_blocksize(inode), pad;
+	bool atomic_hw = iter->flags & IOMAP_ATOMIC_HW;
 	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;
@@ -351,7 +351,7 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 	u64 copied = 0;
 	size_t orig_count;
 
-	if (atomic && length != fs_block_size)
+	if (atomic_hw && length != iter->len)
 		return -EINVAL;
 
 	if ((pos | length) & (bdev_logical_block_size(iomap->bdev) - 1) ||
@@ -428,7 +428,7 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 			goto out;
 	}
 
-	bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua, atomic);
+	bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua, atomic_hw);
 
 	nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS);
 	do {
@@ -461,7 +461,7 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 		}
 
 		n = bio->bi_iter.bi_size;
-		if (WARN_ON_ONCE(atomic && n != length)) {
+		if (WARN_ON_ONCE(atomic_hw && n != length)) {
 			/*
 			 * This bio should have covered the complete length,
 			 * which it doesn't, so error. We may need to zero out
@@ -652,9 +652,6 @@ __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;
@@ -689,6 +686,11 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 			iomi.flags |= IOMAP_OVERWRITE_ONLY;
 		}
 
+		if (dio_flags & IOMAP_DIO_ATOMIC_SW)
+			iomi.flags |= IOMAP_ATOMIC_SW;
+		else if (iocb->ki_flags & IOCB_ATOMIC)
+			iomi.flags |= IOMAP_ATOMIC_HW;
+
 		/* for data sync or sync, we need sync completion processing */
 		if (iocb_is_dsync(iocb)) {
 			dio->flags |= IOMAP_DIO_NEED_SYNC;

fs/iomap/trace.h

@@ -99,7 +99,7 @@ DEFINE_RANGE_EVENT(iomap_dio_rw_queued);
 	{ IOMAP_FAULT,		"FAULT" }, \
 	{ IOMAP_DIRECT,		"DIRECT" }, \
 	{ IOMAP_NOWAIT,		"NOWAIT" }, \
-	{ IOMAP_ATOMIC,		"ATOMIC" }
+	{ IOMAP_ATOMIC_HW,	"ATOMIC_HW" }
 
 #define IOMAP_F_FLAGS_STRINGS \
 	{ IOMAP_F_NEW,		"NEW" }, \

include/linux/iomap.h

@@ -189,8 +189,9 @@ struct iomap_folio_ops {
 #else
 #define IOMAP_DAX		0
 #endif /* CONFIG_FS_DAX */
-#define IOMAP_ATOMIC		(1 << 9)
+#define IOMAP_ATOMIC_HW		(1 << 9) /* HW-based torn-write protection */
 #define IOMAP_DONTCACHE		(1 << 10)
+#define IOMAP_ATOMIC_SW		(1 << 11)/* SW-based torn-write protection */
 
 struct iomap_ops {
 	/*
@@ -502,6 +503,11 @@ struct iomap_dio_ops {
  */
 #define IOMAP_DIO_PARTIAL		(1 << 2)
 
+/*
+ * Use software-based torn-write protection.
+ */
+#define IOMAP_DIO_ATOMIC_SW		(1 << 3)
+
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		unsigned int dio_flags, void *private, size_t done_before);