This doesn't much - just always returns the start block number for each
iomap instead of increasing it. This is because we'll keep building bios
unconstrained by the hardware limits and just split them in file system
submission handler.
Maybe we should find another name for it, because it might be useful for
btrfs compressed bio submissions as well, but I can't come up with a
good one.
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
---
fs/iomap/buffered-io.c | 19 ++++++++++++++++---
include/linux/iomap.h | 7 +++++++
2 files changed, 23 insertions(+), 3 deletions(-)
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 3176dc996fb7..129cd96c6c96 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1744,9 +1744,22 @@ static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos,
return false;
if (pos != wpc->ioend->io_offset + wpc->ioend->io_size)
return false;
- if (iomap_sector(&wpc->iomap, pos) !=
- bio_end_sector(&wpc->ioend->io_bio))
- return false;
+ if (wpc->iomap.flags & IOMAP_F_ZONE_APPEND) {
+ /*
+ * For Zone Append command, bi_sector points to the zone start
+ * before submission. We can merge all I/O for the same zone.
+ */
+ if (iomap_sector(&wpc->iomap, pos) !=
+ wpc->ioend->io_bio.bi_iter.bi_sector)
+ return false;
+ } else {
+ /*
+ * For regular writes, the disk blocks needs to be contiguous.
+ */
+ if (iomap_sector(&wpc->iomap, pos) !=
+ bio_end_sector(&wpc->ioend->io_bio))
+ return false;
+ }
/*
* Limit ioend bio chain lengths to minimise IO completion latency. This
* also prevents long tight loops ending page writeback on all the
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 1d8658c7beb8..173d490c20ba 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -56,6 +56,10 @@ struct vm_fault;
*
* IOMAP_F_BOUNDARY indicates that I/O and I/O completions for this iomap must
* never be merged with the mapping before it.
+ *
+ * IOMAP_F_ZONE_APPEND indicates that (write) I/O should be done as a zone
+ * append command for zoned devices. Note that the file system needs to
+ * override the bi_end_io handler to record the actual written sector.
*/
#define IOMAP_F_NEW (1U << 0)
#define IOMAP_F_DIRTY (1U << 1)
@@ -68,6 +72,7 @@ struct vm_fault;
#endif /* CONFIG_BUFFER_HEAD */
#define IOMAP_F_XATTR (1U << 5)
#define IOMAP_F_BOUNDARY (1U << 6)
+#define IOMAP_F_ZONE_APPEND (1U << 7)
/*
* Flags set by the core iomap code during operations:
@@ -111,6 +116,8 @@ struct iomap {
static inline sector_t iomap_sector(const struct iomap *iomap, loff_t pos)
{
+ if (iomap->flags & IOMAP_F_ZONE_APPEND)
+ return iomap->addr >> SECTOR_SHIFT;
return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT;
}
--
2.45.2
