Note: this patch is for this series.
https://lore.kernel.org/linux-btrfs/cover.1604065156.git.naohiro.aota@xxxxxxx/T/
The patch below uses IOMAP_F_ZONE_APPEND flag to make the iomap bio to be
REQ_OP_ZONE_APPEND.
https://lore.kernel.org/linux-btrfs/cover.1604065156.git.naohiro.aota@xxxxxxx/T/#m7b3f2d01ab554ea4cba244608655268211928799
On Fri, Oct 30, 2020 at 10:51:09PM +0900, Naohiro Aota wrote:
A ZONE_APPEND bio must follow hardware restrictions (e.g. not exceeding
max_zone_append_sectors) not to be split. bio_iov_iter_get_pages builds
such restricted bio using __bio_iov_append_get_pages if bio_op(bio) ==
REQ_OP_ZONE_APPEND.
To utilize it, we need to set the bio_op before calling
bio_iov_iter_get_pages(). This commit introduces IOMAP_F_ZONE_APPEND, so
that iomap user can set the flag to indicate they want REQ_OP_ZONE_APPEND
and restricted bio.
Cc: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Cc: "Darrick J. Wong" <darrick.wong@xxxxxxxxxx>
Cc: linux-xfs@xxxxxxxxxxxxxxx
Signed-off-by: Naohiro Aota <naohiro.aota@xxxxxxx>
---
fs/iomap/direct-io.c | 22 ++++++++++++++++------
include/linux/iomap.h | 1 +
2 files changed, 17 insertions(+), 6 deletions(-)
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index c1aafb2ab990..e534703c5594 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -210,6 +210,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
struct bio *bio;
bool need_zeroout = false;
bool use_fua = false;
+ bool zone_append = false;
int nr_pages, ret = 0;
size_t copied = 0;
size_t orig_count;
@@ -241,6 +242,8 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
use_fua = true;
}
+ zone_append = iomap->flags & IOMAP_F_ZONE_APPEND;
+
/*
* Save the original count and trim the iter to just the extent we
* are operating on right now. The iter will be re-expanded once
@@ -278,6 +281,19 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
bio->bi_private = dio;
bio->bi_end_io = iomap_dio_bio_end_io;
+ if (dio->flags & IOMAP_DIO_WRITE) {
+ bio->bi_opf = (zone_append ? REQ_OP_ZONE_APPEND : REQ_OP_WRITE) |
+ REQ_SYNC | REQ_IDLE;
+ if (use_fua)
+ bio->bi_opf |= REQ_FUA;
+ else
+ dio->flags &= ~IOMAP_DIO_WRITE_FUA;
+ } else {
+ WARN_ON_ONCE(zone_append);
+
+ bio->bi_opf = REQ_OP_READ;
+ }
+
ret = bio_iov_iter_get_pages(bio, dio->submit.iter);
if (unlikely(ret)) {
/*
@@ -292,14 +308,8 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
n = bio->bi_iter.bi_size;
if (dio->flags & IOMAP_DIO_WRITE) {
- bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
- if (use_fua)
- bio->bi_opf |= REQ_FUA;
- else
- dio->flags &= ~IOMAP_DIO_WRITE_FUA;
task_io_account_write(n);
} else {
- bio->bi_opf = REQ_OP_READ;
if (dio->flags & IOMAP_DIO_DIRTY)
bio_set_pages_dirty(bio);
}
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 4d1d3c3469e9..1bccd1880d0d 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -54,6 +54,7 @@ struct vm_fault;
#define IOMAP_F_SHARED 0x04
#define IOMAP_F_MERGED 0x08
#define IOMAP_F_BUFFER_HEAD 0x10
+#define IOMAP_F_ZONE_APPEND 0x20
/*
* Flags set by the core iomap code during operations:
--
2.27.0
