| Message ID | 20210525212501.226888-9-damien.lemoal@wdc.com (mailing list archive) |
|---|---|
| State | Accepted, archived |
| Delegated to: | Mike Snitzer |
| Headers | show |
| Series | dm: Improve zoned block device support | expand |
On Tue, May 25 2021 at 5:24P -0400, Damien Le Moal <damien.lemoal@wdc.com> wrote: > A target map method requesting the requeue of a bio with > DM_MAPIO_REQUEUE or completing it with DM_ENDIO_REQUEUE can cause > unaligned write errors if the bio is a write operation targeting a > sequential zone. If a zoned target request such a requeue, warn about > it and kill the IO. > > The function dm_is_zone_write() is introduced to detect write operations > to zoned targets. > > This change does not affect the target drivers supporting zoned devices > and exposing a zoned device, namely dm-crypt, dm-linear and dm-flakey as > none of these targets ever request a requeue. > > Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> > Reviewed-by: Hannes Reinecke <hare@suse.de> > Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com> > --- > drivers/md/dm-zone.c | 17 +++++++++++++++++ > drivers/md/dm.c | 18 +++++++++++++++--- > drivers/md/dm.h | 5 +++++ > 3 files changed, 37 insertions(+), 3 deletions(-) > > diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c > index b42474043249..edc3bbb45637 100644 > --- a/drivers/md/dm-zone.c > +++ b/drivers/md/dm-zone.c > @@ -104,6 +104,23 @@ int dm_report_zones(struct block_device *bdev, sector_t start, sector_t sector, > } > EXPORT_SYMBOL_GPL(dm_report_zones); > > +bool dm_is_zone_write(struct mapped_device *md, struct bio *bio) > +{ > + struct request_queue *q = md->queue; > + > + if (!blk_queue_is_zoned(q)) > + return false; > + > + switch (bio_op(bio)) { > + case REQ_OP_WRITE_ZEROES: > + case REQ_OP_WRITE_SAME: > + case REQ_OP_WRITE: > + return !op_is_flush(bio->bi_opf) && bio_sectors(bio); > + default: > + return false; > + } > +} > + > void dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q) > { > if (!blk_queue_is_zoned(q)) > diff --git a/drivers/md/dm.c b/drivers/md/dm.c > index c49976cc4e44..ed8c5a8df2e5 100644 > --- a/drivers/md/dm.c > +++ b/drivers/md/dm.c > @@ -846,11 +846,15 @@ static void dec_pending(struct dm_io *io, blk_status_t error) > * Target requested pushing back the I/O. > */ > spin_lock_irqsave(&md->deferred_lock, flags); > - if (__noflush_suspending(md)) > + if (__noflush_suspending(md) && > + !WARN_ON_ONCE(dm_is_zone_write(md, bio))) > /* NOTE early return due to BLK_STS_DM_REQUEUE below */ > bio_list_add_head(&md->deferred, io->orig_bio); > else > - /* noflush suspend was interrupted. */ > + /* > + * noflush suspend was interrupted or this is > + * a write to a zoned target. > + */ > io->status = BLK_STS_IOERR; > spin_unlock_irqrestore(&md->deferred_lock, flags); > } So I now see this incremental fix: https://patchwork.kernel.org/project/dm-devel/patch/20210604004703.408562-1-damien.lemoal@opensource.wdc.com/ And I've folded it in... > @@ -947,7 +951,15 @@ static void clone_endio(struct bio *bio) > int r = endio(tio->ti, bio, &error); > switch (r) { > case DM_ENDIO_REQUEUE: > - error = BLK_STS_DM_REQUEUE; > + /* > + * Requeuing writes to a sequential zone of a zoned > + * target will break the sequential write pattern: > + * fail such IO. > + */ > + if (WARN_ON_ONCE(dm_is_zone_write(md, bio))) > + error = BLK_STS_IOERR; > + else > + error = BLK_STS_DM_REQUEUE; > fallthrough; > case DM_ENDIO_DONE: > break; But I'm left wondering why dec_pending, now dm_io_dec_pending, needs to be modified to also check dm_is_zone_write() if clone_endio() is already dealing with it? Not that big a deal, just not loving how we're sprinkling special zoned code around... Mike -- dm-devel mailing list dm-devel@redhat.com https://listman.redhat.com/mailman/listinfo/dm-devel
On 2021/06/04 23:56, Mike Snitzer wrote: > On Tue, May 25 2021 at 5:24P -0400, > Damien Le Moal <damien.lemoal@wdc.com> wrote: > >> A target map method requesting the requeue of a bio with >> DM_MAPIO_REQUEUE or completing it with DM_ENDIO_REQUEUE can cause >> unaligned write errors if the bio is a write operation targeting a >> sequential zone. If a zoned target request such a requeue, warn about >> it and kill the IO. >> >> The function dm_is_zone_write() is introduced to detect write operations >> to zoned targets. >> >> This change does not affect the target drivers supporting zoned devices >> and exposing a zoned device, namely dm-crypt, dm-linear and dm-flakey as >> none of these targets ever request a requeue. >> >> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> >> Reviewed-by: Hannes Reinecke <hare@suse.de> >> Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com> >> --- >> drivers/md/dm-zone.c | 17 +++++++++++++++++ >> drivers/md/dm.c | 18 +++++++++++++++--- >> drivers/md/dm.h | 5 +++++ >> 3 files changed, 37 insertions(+), 3 deletions(-) >> >> diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c >> index b42474043249..edc3bbb45637 100644 >> --- a/drivers/md/dm-zone.c >> +++ b/drivers/md/dm-zone.c >> @@ -104,6 +104,23 @@ int dm_report_zones(struct block_device *bdev, sector_t start, sector_t sector, >> } >> EXPORT_SYMBOL_GPL(dm_report_zones); >> >> +bool dm_is_zone_write(struct mapped_device *md, struct bio *bio) >> +{ >> + struct request_queue *q = md->queue; >> + >> + if (!blk_queue_is_zoned(q)) >> + return false; >> + >> + switch (bio_op(bio)) { >> + case REQ_OP_WRITE_ZEROES: >> + case REQ_OP_WRITE_SAME: >> + case REQ_OP_WRITE: >> + return !op_is_flush(bio->bi_opf) && bio_sectors(bio); >> + default: >> + return false; >> + } >> +} >> + >> void dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q) >> { >> if (!blk_queue_is_zoned(q)) >> diff --git a/drivers/md/dm.c b/drivers/md/dm.c >> index c49976cc4e44..ed8c5a8df2e5 100644 >> --- a/drivers/md/dm.c >> +++ b/drivers/md/dm.c >> @@ -846,11 +846,15 @@ static void dec_pending(struct dm_io *io, blk_status_t error) >> * Target requested pushing back the I/O. >> */ >> spin_lock_irqsave(&md->deferred_lock, flags); >> - if (__noflush_suspending(md)) >> + if (__noflush_suspending(md) && >> + !WARN_ON_ONCE(dm_is_zone_write(md, bio))) >> /* NOTE early return due to BLK_STS_DM_REQUEUE below */ >> bio_list_add_head(&md->deferred, io->orig_bio); >> else >> - /* noflush suspend was interrupted. */ >> + /* >> + * noflush suspend was interrupted or this is >> + * a write to a zoned target. >> + */ >> io->status = BLK_STS_IOERR; >> spin_unlock_irqrestore(&md->deferred_lock, flags); >> } > > So I now see this incremental fix: > https://patchwork.kernel.org/project/dm-devel/patch/20210604004703.408562-1-damien.lemoal@opensource.wdc.com/ > > And I've folded it in... Thanks. >> @@ -947,7 +951,15 @@ static void clone_endio(struct bio *bio) >> int r = endio(tio->ti, bio, &error); >> switch (r) { >> case DM_ENDIO_REQUEUE: >> - error = BLK_STS_DM_REQUEUE; >> + /* >> + * Requeuing writes to a sequential zone of a zoned >> + * target will break the sequential write pattern: >> + * fail such IO. >> + */ >> + if (WARN_ON_ONCE(dm_is_zone_write(md, bio))) >> + error = BLK_STS_IOERR; >> + else >> + error = BLK_STS_DM_REQUEUE; >> fallthrough; >> case DM_ENDIO_DONE: >> break; > > But I'm left wondering why dec_pending, now dm_io_dec_pending, needs > to be modified to also check dm_is_zone_write() if clone_endio() is > already dealing with it? The way I understand the code is that if the target ->map_bio() method returns DM_MAPIO_REQUEUE (in __map_bio()), then clone_endio() is not called since the clone BIO is not submitted. But we still need to fail orig_bio, hence the check in dm_io_dec_pending() to cover the submission path. Am I missing something ? Is clone_endio() also called in that case ? > Not that big a deal, just not loving how we're sprinkling special > zoned code around... I do not like it either. It makes maintenance harder. But as explained above, I did not see any other way to cover both the submission and completion cases. > > Mike >
diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c index b42474043249..edc3bbb45637 100644 --- a/drivers/md/dm-zone.c +++ b/drivers/md/dm-zone.c @@ -104,6 +104,23 @@ int dm_report_zones(struct block_device *bdev, sector_t start, sector_t sector, } EXPORT_SYMBOL_GPL(dm_report_zones); +bool dm_is_zone_write(struct mapped_device *md, struct bio *bio) +{ + struct request_queue *q = md->queue; + + if (!blk_queue_is_zoned(q)) + return false; + + switch (bio_op(bio)) { + case REQ_OP_WRITE_ZEROES: + case REQ_OP_WRITE_SAME: + case REQ_OP_WRITE: + return !op_is_flush(bio->bi_opf) && bio_sectors(bio); + default: + return false; + } +} + void dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q) { if (!blk_queue_is_zoned(q)) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index c49976cc4e44..ed8c5a8df2e5 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -846,11 +846,15 @@ static void dec_pending(struct dm_io *io, blk_status_t error) * Target requested pushing back the I/O. */ spin_lock_irqsave(&md->deferred_lock, flags); - if (__noflush_suspending(md)) + if (__noflush_suspending(md) && + !WARN_ON_ONCE(dm_is_zone_write(md, bio))) /* NOTE early return due to BLK_STS_DM_REQUEUE below */ bio_list_add_head(&md->deferred, io->orig_bio); else - /* noflush suspend was interrupted. */ + /* + * noflush suspend was interrupted or this is + * a write to a zoned target. + */ io->status = BLK_STS_IOERR; spin_unlock_irqrestore(&md->deferred_lock, flags); } @@ -947,7 +951,15 @@ static void clone_endio(struct bio *bio) int r = endio(tio->ti, bio, &error); switch (r) { case DM_ENDIO_REQUEUE: - error = BLK_STS_DM_REQUEUE; + /* + * Requeuing writes to a sequential zone of a zoned + * target will break the sequential write pattern: + * fail such IO. + */ + if (WARN_ON_ONCE(dm_is_zone_write(md, bio))) + error = BLK_STS_IOERR; + else + error = BLK_STS_DM_REQUEUE; fallthrough; case DM_ENDIO_DONE: break; diff --git a/drivers/md/dm.h b/drivers/md/dm.h index fdf1536a4b62..39c243258e24 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -107,8 +107,13 @@ void dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q); #ifdef CONFIG_BLK_DEV_ZONED int dm_blk_report_zones(struct gendisk *disk, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); +bool dm_is_zone_write(struct mapped_device *md, struct bio *bio); #else #define dm_blk_report_zones NULL +static inline bool dm_is_zone_write(struct mapped_device *md, struct bio *bio) +{ + return false; +} #endif /*-----------------------------------------------------------------