| Message ID | 20241025213645.3464331-6-kbusch@meta.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | write hints with nvme fdp, scsi streams | expand |
On Sat, Oct 26, 2024 at 3:13 AM Keith Busch <kbusch@meta.com> wrote: > > From: Kanchan Joshi <joshi.k@samsung.com> > > With F_SET_RW_HINT fcntl, user can set a hint on the file inode, and > all the subsequent writes on the file pass that hint value down. This > can be limiting for block device as all the writes will be tagged with > only one lifetime hint value. Concurrent writes (with different hint > values) are hard to manage. Per-IO hinting solves that problem. > > Allow userspace to pass additional metadata in the SQE. > > __u16 write_hint; > > If the hint is provided, filesystems may optionally use it. A filesytem > may ignore this field if it does not support per-io hints, or if the > value is invalid for its backing storage. Just like the inode hints, > requesting values that are not supported by the hardware are not an > error. > > Reviewed-by: Hannes Reinecke <hare@suse.de> > Signed-off-by: Kanchan Joshi <joshi.k@samsung.com> > Signed-off-by: Nitesh Shetty <nj.shetty@samsung.com> > Signed-off-by: Keith Busch <kbusch@kernel.org> > --- > include/uapi/linux/io_uring.h | 4 ++++ > io_uring/rw.c | 3 ++- > 2 files changed, 6 insertions(+), 1 deletion(-) > > diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h > index 60b9c98595faf..8cdcc461d464c 100644 > --- a/include/uapi/linux/io_uring.h > +++ b/include/uapi/linux/io_uring.h > @@ -92,6 +92,10 @@ struct io_uring_sqe { > __u16 addr_len; > __u16 __pad3[1]; > }; > + struct { > + __u16 write_hint; > + __u16 __pad4[1]; > + }; > }; > union { > struct { > diff --git a/io_uring/rw.c b/io_uring/rw.c > index 8080ffd6d5712..5a1231bfecc3a 100644 > --- a/io_uring/rw.c > +++ b/io_uring/rw.c > @@ -279,7 +279,8 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, > rw->kiocb.ki_ioprio = get_current_ioprio(); > } > rw->kiocb.dio_complete = NULL; > - > + if (ddir == ITER_SOURCE) > + rw->kiocb.ki_write_hint = READ_ONCE(sqe->write_hint); > rw->addr = READ_ONCE(sqe->addr); > rw->len = READ_ONCE(sqe->len); > rw->flags = READ_ONCE(sqe->rw_flags); > -- > 2.43.5 > Since this patch adds a couple of new fields, it makes sense to add BUILD_BUG_ON() checks in io_uring_init for these fields to assert the layout of struct io_uring_sqe. And probably a zero check for pad4 in io_prep_rw. -- Anuj Gupta
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 60b9c98595faf..8cdcc461d464c 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -92,6 +92,10 @@ struct io_uring_sqe { __u16 addr_len; __u16 __pad3[1]; }; + struct { + __u16 write_hint; + __u16 __pad4[1]; + }; }; union { struct { diff --git a/io_uring/rw.c b/io_uring/rw.c index 8080ffd6d5712..5a1231bfecc3a 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -279,7 +279,8 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, rw->kiocb.ki_ioprio = get_current_ioprio(); } rw->kiocb.dio_complete = NULL; - + if (ddir == ITER_SOURCE) + rw->kiocb.ki_write_hint = READ_ONCE(sqe->write_hint); rw->addr = READ_ONCE(sqe->addr); rw->len = READ_ONCE(sqe->len); rw->flags = READ_ONCE(sqe->rw_flags);