* [PATCH v10 1/9] block: rename __bio_add_pc_page to bio_add_hw_page
2020-05-06 16:11 [PATCH v10 0/9] Introduce Zone Append for writing to zoned block devices Johannes Thumshirn
@ 2020-05-06 16:11 ` Johannes Thumshirn
2020-05-06 18:16 ` Hannes Reinecke
2020-05-06 16:11 ` [PATCH v10 2/9] block: Introduce REQ_OP_ZONE_APPEND Johannes Thumshirn
` (7 subsequent siblings)
8 siblings, 1 reply; 12+ messages in thread
From: Johannes Thumshirn @ 2020-05-06 16:11 UTC (permalink / raw)
To: Jens Axboe
Cc: Christoph Hellwig, linux-block, Damien Le Moal, Keith Busch,
linux-scsi @ vger . kernel . org, Martin K . Petersen,
linux-fsdevel @ vger . kernel . org, Christoph Hellwig,
Johannes Thumshirn, Daniel Wagner
From: Christoph Hellwig <hch@lst.de>
Rename __bio_add_pc_page() to bio_add_hw_page() and explicitly pass in a
max_sectors argument.
This max_sectors argument can be used to specify constraints from the
hardware.
Signed-off-by: Christoph Hellwig <hch@lst.de>
[ jth: rebased and made public for blk-map.c ]
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
---
block/bio.c | 65 ++++++++++++++++++++++++++++++-------------------
block/blk-map.c | 5 ++--
block/blk.h | 4 +--
3 files changed, 45 insertions(+), 29 deletions(-)
diff --git a/block/bio.c b/block/bio.c
index 21cbaa6a1c20..aad0a6dad4f9 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -748,9 +748,14 @@ static inline bool page_is_mergeable(const struct bio_vec *bv,
return true;
}
-static bool bio_try_merge_pc_page(struct request_queue *q, struct bio *bio,
- struct page *page, unsigned len, unsigned offset,
- bool *same_page)
+/*
+ * Try to merge a page into a segment, while obeying the hardware segment
+ * size limit. This is not for normal read/write bios, but for passthrough
+ * or Zone Append operations that we can't split.
+ */
+static bool bio_try_merge_hw_seg(struct request_queue *q, struct bio *bio,
+ struct page *page, unsigned len,
+ unsigned offset, bool *same_page)
{
struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
unsigned long mask = queue_segment_boundary(q);
@@ -765,38 +770,32 @@ static bool bio_try_merge_pc_page(struct request_queue *q, struct bio *bio,
}
/**
- * __bio_add_pc_page - attempt to add page to passthrough bio
- * @q: the target queue
- * @bio: destination bio
- * @page: page to add
- * @len: vec entry length
- * @offset: vec entry offset
- * @same_page: return if the merge happen inside the same page
- *
- * Attempt to add a page to the bio_vec maplist. This can fail for a
- * number of reasons, such as the bio being full or target block device
- * limitations. The target block device must allow bio's up to PAGE_SIZE,
- * so it is always possible to add a single page to an empty bio.
+ * bio_add_hw_page - attempt to add a page to a bio with hw constraints
+ * @q: the target queue
+ * @bio: destination bio
+ * @page: page to add
+ * @len: vec entry length
+ * @offset: vec entry offset
+ * @max_sectors: maximum number of sectors that can be added
+ * @same_page: return if the segment has been merged inside the same page
*
- * This should only be used by passthrough bios.
+ * Add a page to a bio while respecting the hardware max_sectors, max_segment
+ * and gap limitations.
*/
-int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
+int bio_add_hw_page(struct request_queue *q, struct bio *bio,
struct page *page, unsigned int len, unsigned int offset,
- bool *same_page)
+ unsigned int max_sectors, bool *same_page)
{
struct bio_vec *bvec;
- /*
- * cloned bio must not modify vec list
- */
- if (unlikely(bio_flagged(bio, BIO_CLONED)))
+ if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
return 0;
- if (((bio->bi_iter.bi_size + len) >> 9) > queue_max_hw_sectors(q))
+ if (((bio->bi_iter.bi_size + len) >> 9) > max_sectors)
return 0;
if (bio->bi_vcnt > 0) {
- if (bio_try_merge_pc_page(q, bio, page, len, offset, same_page))
+ if (bio_try_merge_hw_seg(q, bio, page, len, offset, same_page))
return len;
/*
@@ -823,11 +822,27 @@ int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
return len;
}
+/**
+ * bio_add_pc_page - attempt to add page to passthrough bio
+ * @q: the target queue
+ * @bio: destination bio
+ * @page: page to add
+ * @len: vec entry length
+ * @offset: vec entry offset
+ *
+ * Attempt to add a page to the bio_vec maplist. This can fail for a
+ * number of reasons, such as the bio being full or target block device
+ * limitations. The target block device must allow bio's up to PAGE_SIZE,
+ * so it is always possible to add a single page to an empty bio.
+ *
+ * This should only be used by passthrough bios.
+ */
int bio_add_pc_page(struct request_queue *q, struct bio *bio,
struct page *page, unsigned int len, unsigned int offset)
{
bool same_page = false;
- return __bio_add_pc_page(q, bio, page, len, offset, &same_page);
+ return bio_add_hw_page(q, bio, page, len, offset,
+ queue_max_hw_sectors(q), &same_page);
}
EXPORT_SYMBOL(bio_add_pc_page);
diff --git a/block/blk-map.c b/block/blk-map.c
index b6fa343fea9f..e3e4ac48db45 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -257,6 +257,7 @@ static struct bio *bio_copy_user_iov(struct request_queue *q,
static struct bio *bio_map_user_iov(struct request_queue *q,
struct iov_iter *iter, gfp_t gfp_mask)
{
+ unsigned int max_sectors = queue_max_hw_sectors(q);
int j;
struct bio *bio;
int ret;
@@ -294,8 +295,8 @@ static struct bio *bio_map_user_iov(struct request_queue *q,
if (n > bytes)
n = bytes;
- if (!__bio_add_pc_page(q, bio, page, n, offs,
- &same_page)) {
+ if (!bio_add_hw_page(q, bio, page, n, offs,
+ max_sectors, &same_page)) {
if (same_page)
put_page(page);
break;
diff --git a/block/blk.h b/block/blk.h
index 73bd3b1c6938..1ae3279df712 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -453,8 +453,8 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
struct request_queue *__blk_alloc_queue(int node_id);
-int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
+int bio_add_hw_page(struct request_queue *q, struct bio *bio,
struct page *page, unsigned int len, unsigned int offset,
- bool *same_page);
+ unsigned int max_sectors, bool *same_page);
#endif /* BLK_INTERNAL_H */
--
2.24.1
^ permalink raw reply [flat|nested] 12+ messages in thread* Re: [PATCH v10 1/9] block: rename __bio_add_pc_page to bio_add_hw_page
2020-05-06 16:11 ` [PATCH v10 1/9] block: rename __bio_add_pc_page to bio_add_hw_page Johannes Thumshirn
@ 2020-05-06 18:16 ` Hannes Reinecke
0 siblings, 0 replies; 12+ messages in thread
From: Hannes Reinecke @ 2020-05-06 18:16 UTC (permalink / raw)
To: Johannes Thumshirn, Jens Axboe
Cc: Christoph Hellwig, linux-block, Damien Le Moal, Keith Busch,
linux-scsi @ vger . kernel . org, Martin K . Petersen,
linux-fsdevel @ vger . kernel . org, Christoph Hellwig,
Daniel Wagner
On 5/6/20 6:11 PM, Johannes Thumshirn wrote:
> From: Christoph Hellwig <hch@lst.de>
>
> Rename __bio_add_pc_page() to bio_add_hw_page() and explicitly pass in a
> max_sectors argument.
>
> This max_sectors argument can be used to specify constraints from the
> hardware.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> [ jth: rebased and made public for blk-map.c ]
> Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
> Reviewed-by: Daniel Wagner <dwagner@suse.de>
> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
> ---
> block/bio.c | 65 ++++++++++++++++++++++++++++++-------------------
> block/blk-map.c | 5 ++--
> block/blk.h | 4 +--
> 3 files changed, 45 insertions(+), 29 deletions(-)
>
> diff --git a/block/bio.c b/block/bio.c
> index 21cbaa6a1c20..aad0a6dad4f9 100644
> --- a/block/bio.c
> +++ b/block/bio.c
> @@ -748,9 +748,14 @@ static inline bool page_is_mergeable(const struct bio_vec *bv,
> return true;
> }
>
> -static bool bio_try_merge_pc_page(struct request_queue *q, struct bio *bio,
> - struct page *page, unsigned len, unsigned offset,
> - bool *same_page)
> +/*
> + * Try to merge a page into a segment, while obeying the hardware segment
> + * size limit. This is not for normal read/write bios, but for passthrough
> + * or Zone Append operations that we can't split.
> + */
> +static bool bio_try_merge_hw_seg(struct request_queue *q, struct bio *bio,
> + struct page *page, unsigned len,
> + unsigned offset, bool *same_page)
> {
> struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
> unsigned long mask = queue_segment_boundary(q);
> @@ -765,38 +770,32 @@ static bool bio_try_merge_pc_page(struct request_queue *q, struct bio *bio,
> }
>
> /**
> - * __bio_add_pc_page - attempt to add page to passthrough bio
> - * @q: the target queue
> - * @bio: destination bio
> - * @page: page to add
> - * @len: vec entry length
> - * @offset: vec entry offset
> - * @same_page: return if the merge happen inside the same page
> - *
> - * Attempt to add a page to the bio_vec maplist. This can fail for a
> - * number of reasons, such as the bio being full or target block device
> - * limitations. The target block device must allow bio's up to PAGE_SIZE,
> - * so it is always possible to add a single page to an empty bio.
> + * bio_add_hw_page - attempt to add a page to a bio with hw constraints
> + * @q: the target queue
> + * @bio: destination bio
> + * @page: page to add
> + * @len: vec entry length
> + * @offset: vec entry offset
> + * @max_sectors: maximum number of sectors that can be added
> + * @same_page: return if the segment has been merged inside the same page
> *
> - * This should only be used by passthrough bios.
> + * Add a page to a bio while respecting the hardware max_sectors, max_segment
> + * and gap limitations.
> */
> -int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
> +int bio_add_hw_page(struct request_queue *q, struct bio *bio,
> struct page *page, unsigned int len, unsigned int offset,
> - bool *same_page)
> + unsigned int max_sectors, bool *same_page)
> {
> struct bio_vec *bvec;
>
> - /*
> - * cloned bio must not modify vec list
> - */
> - if (unlikely(bio_flagged(bio, BIO_CLONED)))
> + if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
> return 0;
>
> - if (((bio->bi_iter.bi_size + len) >> 9) > queue_max_hw_sectors(q))
> + if (((bio->bi_iter.bi_size + len) >> 9) > max_sectors)
> return 0;
>
> if (bio->bi_vcnt > 0) {
> - if (bio_try_merge_pc_page(q, bio, page, len, offset, same_page))
> + if (bio_try_merge_hw_seg(q, bio, page, len, offset, same_page))
> return len;
>
> /*
> @@ -823,11 +822,27 @@ int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
> return len;
> }
>
> +/**
> + * bio_add_pc_page - attempt to add page to passthrough bio
> + * @q: the target queue
> + * @bio: destination bio
> + * @page: page to add
> + * @len: vec entry length
> + * @offset: vec entry offset
> + *
> + * Attempt to add a page to the bio_vec maplist. This can fail for a
> + * number of reasons, such as the bio being full or target block device
> + * limitations. The target block device must allow bio's up to PAGE_SIZE,
> + * so it is always possible to add a single page to an empty bio.
> + *
> + * This should only be used by passthrough bios.
> + */
> int bio_add_pc_page(struct request_queue *q, struct bio *bio,
> struct page *page, unsigned int len, unsigned int offset)
> {
> bool same_page = false;
> - return __bio_add_pc_page(q, bio, page, len, offset, &same_page);
> + return bio_add_hw_page(q, bio, page, len, offset,
> + queue_max_hw_sectors(q), &same_page);
> }
> EXPORT_SYMBOL(bio_add_pc_page);
>
> diff --git a/block/blk-map.c b/block/blk-map.c
> index b6fa343fea9f..e3e4ac48db45 100644
> --- a/block/blk-map.c
> +++ b/block/blk-map.c
> @@ -257,6 +257,7 @@ static struct bio *bio_copy_user_iov(struct request_queue *q,
> static struct bio *bio_map_user_iov(struct request_queue *q,
> struct iov_iter *iter, gfp_t gfp_mask)
> {
> + unsigned int max_sectors = queue_max_hw_sectors(q);
> int j;
> struct bio *bio;
> int ret;
> @@ -294,8 +295,8 @@ static struct bio *bio_map_user_iov(struct request_queue *q,
> if (n > bytes)
> n = bytes;
>
> - if (!__bio_add_pc_page(q, bio, page, n, offs,
> - &same_page)) {
> + if (!bio_add_hw_page(q, bio, page, n, offs,
> + max_sectors, &same_page)) {
> if (same_page)
> put_page(page);
> break;
> diff --git a/block/blk.h b/block/blk.h
> index 73bd3b1c6938..1ae3279df712 100644
> --- a/block/blk.h
> +++ b/block/blk.h
> @@ -453,8 +453,8 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
>
> struct request_queue *__blk_alloc_queue(int node_id);
>
> -int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
> +int bio_add_hw_page(struct request_queue *q, struct bio *bio,
> struct page *page, unsigned int len, unsigned int offset,
> - bool *same_page);
> + unsigned int max_sectors, bool *same_page);
>
> #endif /* BLK_INTERNAL_H */
>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Cheers,
Hannes
--
Dr. Hannes Reinecke Teamlead Storage & Networking
hare@suse.de +49 911 74053 688
SUSE Software Solutions GmbH, Maxfeldstr. 5, 90409 Nürnberg
HRB 36809 (AG Nürnberg), Geschäftsführer: Felix Imendörffer
^ permalink raw reply [flat|nested] 12+ messages in thread
* [PATCH v10 2/9] block: Introduce REQ_OP_ZONE_APPEND
2020-05-06 16:11 [PATCH v10 0/9] Introduce Zone Append for writing to zoned block devices Johannes Thumshirn
2020-05-06 16:11 ` [PATCH v10 1/9] block: rename __bio_add_pc_page to bio_add_hw_page Johannes Thumshirn
@ 2020-05-06 16:11 ` Johannes Thumshirn
2020-05-06 16:11 ` [PATCH v10 3/9] block: introduce blk_req_zone_write_trylock Johannes Thumshirn
` (6 subsequent siblings)
8 siblings, 0 replies; 12+ messages in thread
From: Johannes Thumshirn @ 2020-05-06 16:11 UTC (permalink / raw)
To: Jens Axboe
Cc: Christoph Hellwig, linux-block, Damien Le Moal, Keith Busch,
linux-scsi @ vger . kernel . org, Martin K . Petersen,
linux-fsdevel @ vger . kernel . org, Johannes Thumshirn,
Christoph Hellwig, Hannes Reinecke
From: Keith Busch <kbusch@kernel.org>
Define REQ_OP_ZONE_APPEND to append-write sectors to a zone of a zoned
block device. This is a no-merge write operation.
A zone append write BIO must:
* Target a zoned block device
* Have a sector position indicating the start sector of the target zone
* The target zone must be a sequential write zone
* The BIO must not cross a zone boundary
* The BIO size must not be split to ensure that a single range of LBAs
is written with a single command.
Implement these checks in generic_make_request_checks() using the
helper function blk_check_zone_append(). To avoid write append BIO
splitting, introduce the new max_zone_append_sectors queue limit
attribute and ensure that a BIO size is always lower than this limit.
Export this new limit through sysfs and check these limits in bio_full().
Also when a LLDD can't dispatch a request to a specific zone, it
will return BLK_STS_ZONE_RESOURCE indicating this request needs to
be delayed, e.g. because the zone it will be dispatched to is still
write-locked. If this happens set the request aside in a local list
to continue trying dispatching requests such as READ requests or a
WRITE/ZONE_APPEND requests targetting other zones. This way we can
still keep a high queue depth without starving other requests even if
one request can't be served due to zone write-locking.
Finally, make sure that the bio sector position indicates the actual
write position as indicated by the device on completion.
Signed-off-by: Keith Busch <kbusch@kernel.org>
[ jth: added zone-append specific add_page and merge_page helpers ]
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
---
block/bio.c | 62 ++++++++++++++++++++++++++++++++++++---
block/blk-core.c | 52 ++++++++++++++++++++++++++++++++
block/blk-mq.c | 27 +++++++++++++++++
block/blk-settings.c | 31 ++++++++++++++++++++
block/blk-sysfs.c | 13 ++++++++
drivers/scsi/scsi_lib.c | 1 +
include/linux/blk_types.h | 14 +++++++++
include/linux/blkdev.h | 11 +++++++
8 files changed, 207 insertions(+), 4 deletions(-)
diff --git a/block/bio.c b/block/bio.c
index aad0a6dad4f9..3aa3c4ce2e5e 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1025,6 +1025,50 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
return 0;
}
+static int __bio_iov_append_get_pages(struct bio *bio, struct iov_iter *iter)
+{
+ unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
+ unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
+ struct request_queue *q = bio->bi_disk->queue;
+ unsigned int max_append_sectors = queue_max_zone_append_sectors(q);
+ struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
+ struct page **pages = (struct page **)bv;
+ ssize_t size, left;
+ unsigned len, i;
+ size_t offset;
+
+ if (WARN_ON_ONCE(!max_append_sectors))
+ return 0;
+
+ /*
+ * Move page array up in the allocated memory for the bio vecs as far as
+ * possible so that we can start filling biovecs from the beginning
+ * without overwriting the temporary page array.
+ */
+ BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
+ pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);
+
+ size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
+ if (unlikely(size <= 0))
+ return size ? size : -EFAULT;
+
+ for (left = size, i = 0; left > 0; left -= len, i++) {
+ struct page *page = pages[i];
+ bool same_page = false;
+
+ len = min_t(size_t, PAGE_SIZE - offset, left);
+ if (bio_add_hw_page(q, bio, page, len, offset,
+ max_append_sectors, &same_page) != len)
+ return -EINVAL;
+ if (same_page)
+ put_page(page);
+ offset = 0;
+ }
+
+ iov_iter_advance(iter, size);
+ return 0;
+}
+
/**
* bio_iov_iter_get_pages - add user or kernel pages to a bio
* @bio: bio to add pages to
@@ -1054,10 +1098,16 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
return -EINVAL;
do {
- if (is_bvec)
- ret = __bio_iov_bvec_add_pages(bio, iter);
- else
- ret = __bio_iov_iter_get_pages(bio, iter);
+ if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
+ if (WARN_ON_ONCE(is_bvec))
+ return -EINVAL;
+ ret = __bio_iov_append_get_pages(bio, iter);
+ } else {
+ if (is_bvec)
+ ret = __bio_iov_bvec_add_pages(bio, iter);
+ else
+ ret = __bio_iov_iter_get_pages(bio, iter);
+ }
} while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));
if (is_bvec)
@@ -1460,6 +1510,10 @@ struct bio *bio_split(struct bio *bio, int sectors,
BUG_ON(sectors <= 0);
BUG_ON(sectors >= bio_sectors(bio));
+ /* Zone append commands cannot be split */
+ if (WARN_ON_ONCE(bio_op(bio) == REQ_OP_ZONE_APPEND))
+ return NULL;
+
split = bio_clone_fast(bio, gfp, bs);
if (!split)
return NULL;
diff --git a/block/blk-core.c b/block/blk-core.c
index dffff2100888..7cdcc76399d6 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -135,6 +135,7 @@ static const char *const blk_op_name[] = {
REQ_OP_NAME(ZONE_OPEN),
REQ_OP_NAME(ZONE_CLOSE),
REQ_OP_NAME(ZONE_FINISH),
+ REQ_OP_NAME(ZONE_APPEND),
REQ_OP_NAME(WRITE_SAME),
REQ_OP_NAME(WRITE_ZEROES),
REQ_OP_NAME(SCSI_IN),
@@ -240,6 +241,17 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
bio_advance(bio, nbytes);
+ if (req_op(rq) == REQ_OP_ZONE_APPEND && error == BLK_STS_OK) {
+ /*
+ * Partial zone append completions cannot be supported as the
+ * BIO fragments may end up not being written sequentially.
+ */
+ if (bio->bi_iter.bi_size)
+ bio->bi_status = BLK_STS_IOERR;
+ else
+ bio->bi_iter.bi_sector = rq->__sector;
+ }
+
/* don't actually finish bio if it's part of flush sequence */
if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
bio_endio(bio);
@@ -871,6 +883,41 @@ static inline int blk_partition_remap(struct bio *bio)
return ret;
}
+/*
+ * Check write append to a zoned block device.
+ */
+static inline blk_status_t blk_check_zone_append(struct request_queue *q,
+ struct bio *bio)
+{
+ sector_t pos = bio->bi_iter.bi_sector;
+ int nr_sectors = bio_sectors(bio);
+
+ /* Only applicable to zoned block devices */
+ if (!blk_queue_is_zoned(q))
+ return BLK_STS_NOTSUPP;
+
+ /* The bio sector must point to the start of a sequential zone */
+ if (pos & (blk_queue_zone_sectors(q) - 1) ||
+ !blk_queue_zone_is_seq(q, pos))
+ return BLK_STS_IOERR;
+
+ /*
+ * Not allowed to cross zone boundaries. Otherwise, the BIO will be
+ * split and could result in non-contiguous sectors being written in
+ * different zones.
+ */
+ if (nr_sectors > q->limits.chunk_sectors)
+ return BLK_STS_IOERR;
+
+ /* Make sure the BIO is small enough and will not get split */
+ if (nr_sectors > q->limits.max_zone_append_sectors)
+ return BLK_STS_IOERR;
+
+ bio->bi_opf |= REQ_NOMERGE;
+
+ return BLK_STS_OK;
+}
+
static noinline_for_stack bool
generic_make_request_checks(struct bio *bio)
{
@@ -943,6 +990,11 @@ generic_make_request_checks(struct bio *bio)
if (!q->limits.max_write_same_sectors)
goto not_supported;
break;
+ case REQ_OP_ZONE_APPEND:
+ status = blk_check_zone_append(q, bio);
+ if (status != BLK_STS_OK)
+ goto end_io;
+ break;
case REQ_OP_ZONE_RESET:
case REQ_OP_ZONE_OPEN:
case REQ_OP_ZONE_CLOSE:
diff --git a/block/blk-mq.c b/block/blk-mq.c
index bcc3a2397d4a..0b8567ef23bb 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1183,6 +1183,19 @@ static void blk_mq_handle_dev_resource(struct request *rq,
__blk_mq_requeue_request(rq);
}
+static void blk_mq_handle_zone_resource(struct request *rq,
+ struct list_head *zone_list)
+{
+ /*
+ * If we end up here it is because we cannot dispatch a request to a
+ * specific zone due to LLD level zone-write locking or other zone
+ * related resource not being available. In this case, set the request
+ * aside in zone_list for retrying it later.
+ */
+ list_add(&rq->queuelist, zone_list);
+ __blk_mq_requeue_request(rq);
+}
+
/*
* Returns true if we did some work AND can potentially do more.
*/
@@ -1195,6 +1208,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
int errors, queued;
blk_status_t ret = BLK_STS_OK;
bool no_budget_avail = false;
+ LIST_HEAD(zone_list);
if (list_empty(list))
return false;
@@ -1256,6 +1270,16 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) {
blk_mq_handle_dev_resource(rq, list);
break;
+ } else if (ret == BLK_STS_ZONE_RESOURCE) {
+ /*
+ * Move the request to zone_list and keep going through
+ * the dispatch list to find more requests the drive can
+ * accept.
+ */
+ blk_mq_handle_zone_resource(rq, &zone_list);
+ if (list_empty(list))
+ break;
+ continue;
}
if (unlikely(ret != BLK_STS_OK)) {
@@ -1267,6 +1291,9 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
queued++;
} while (!list_empty(list));
+ if (!list_empty(&zone_list))
+ list_splice_tail_init(&zone_list, list);
+
hctx->dispatched[queued_to_index(queued)]++;
/*
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 2ab1967b9716..9a2c23cd9700 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -48,6 +48,7 @@ void blk_set_default_limits(struct queue_limits *lim)
lim->chunk_sectors = 0;
lim->max_write_same_sectors = 0;
lim->max_write_zeroes_sectors = 0;
+ lim->max_zone_append_sectors = 0;
lim->max_discard_sectors = 0;
lim->max_hw_discard_sectors = 0;
lim->discard_granularity = 0;
@@ -83,6 +84,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
lim->max_dev_sectors = UINT_MAX;
lim->max_write_same_sectors = UINT_MAX;
lim->max_write_zeroes_sectors = UINT_MAX;
+ lim->max_zone_append_sectors = UINT_MAX;
}
EXPORT_SYMBOL(blk_set_stacking_limits);
@@ -221,6 +223,33 @@ void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
}
EXPORT_SYMBOL(blk_queue_max_write_zeroes_sectors);
+/**
+ * blk_queue_max_zone_append_sectors - set max sectors for a single zone append
+ * @q: the request queue for the device
+ * @max_zone_append_sectors: maximum number of sectors to write per command
+ **/
+void blk_queue_max_zone_append_sectors(struct request_queue *q,
+ unsigned int max_zone_append_sectors)
+{
+ unsigned int max_sectors;
+
+ if (WARN_ON(!blk_queue_is_zoned(q)))
+ return;
+
+ max_sectors = min(q->limits.max_hw_sectors, max_zone_append_sectors);
+ max_sectors = min(q->limits.chunk_sectors, max_sectors);
+
+ /*
+ * Signal eventual driver bugs resulting in the max_zone_append sectors limit
+ * being 0 due to a 0 argument, the chunk_sectors limit (zone size) not set,
+ * or the max_hw_sectors limit not set.
+ */
+ WARN_ON(!max_sectors);
+
+ q->limits.max_zone_append_sectors = max_sectors;
+}
+EXPORT_SYMBOL_GPL(blk_queue_max_zone_append_sectors);
+
/**
* blk_queue_max_segments - set max hw segments for a request for this queue
* @q: the request queue for the device
@@ -470,6 +499,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
b->max_write_same_sectors);
t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors,
b->max_write_zeroes_sectors);
+ t->max_zone_append_sectors = min(t->max_zone_append_sectors,
+ b->max_zone_append_sectors);
t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index fca9b158f4a0..02643e149d5e 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -218,6 +218,13 @@ static ssize_t queue_write_zeroes_max_show(struct request_queue *q, char *page)
(unsigned long long)q->limits.max_write_zeroes_sectors << 9);
}
+static ssize_t queue_zone_append_max_show(struct request_queue *q, char *page)
+{
+ unsigned long long max_sectors = q->limits.max_zone_append_sectors;
+
+ return sprintf(page, "%llu\n", max_sectors << SECTOR_SHIFT);
+}
+
static ssize_t
queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
{
@@ -639,6 +646,11 @@ static struct queue_sysfs_entry queue_write_zeroes_max_entry = {
.show = queue_write_zeroes_max_show,
};
+static struct queue_sysfs_entry queue_zone_append_max_entry = {
+ .attr = {.name = "zone_append_max_bytes", .mode = 0444 },
+ .show = queue_zone_append_max_show,
+};
+
static struct queue_sysfs_entry queue_nonrot_entry = {
.attr = {.name = "rotational", .mode = 0644 },
.show = queue_show_nonrot,
@@ -749,6 +761,7 @@ static struct attribute *queue_attrs[] = {
&queue_discard_zeroes_data_entry.attr,
&queue_write_same_max_entry.attr,
&queue_write_zeroes_max_entry.attr,
+ &queue_zone_append_max_entry.attr,
&queue_nonrot_entry.attr,
&queue_zoned_entry.attr,
&queue_nr_zones_entry.attr,
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index f0cb26b3da6a..af00e4a3f006 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1712,6 +1712,7 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
case BLK_STS_OK:
break;
case BLK_STS_RESOURCE:
+ case BLK_STS_ZONE_RESOURCE:
if (atomic_read(&sdev->device_busy) ||
scsi_device_blocked(sdev))
ret = BLK_STS_DEV_RESOURCE;
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 31eb92876be7..dbee2b0d56b6 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -63,6 +63,18 @@ typedef u8 __bitwise blk_status_t;
*/
#define BLK_STS_DEV_RESOURCE ((__force blk_status_t)13)
+/*
+ * BLK_STS_ZONE_RESOURCE is returned from the driver to the block layer if zone
+ * related resources are unavailable, but the driver can guarantee the queue
+ * will be rerun in the future once the resources become available again.
+ *
+ * This is different from BLK_STS_DEV_RESOURCE in that it explicitly references
+ * a zone specific resource and IO to a different zone on the same device could
+ * still be served. Examples of that are zones that are write-locked, but a read
+ * to the same zone could be served.
+ */
+#define BLK_STS_ZONE_RESOURCE ((__force blk_status_t)14)
+
/**
* blk_path_error - returns true if error may be path related
* @error: status the request was completed with
@@ -296,6 +308,8 @@ enum req_opf {
REQ_OP_ZONE_CLOSE = 11,
/* Transition a zone to full */
REQ_OP_ZONE_FINISH = 12,
+ /* write data at the current zone write pointer */
+ REQ_OP_ZONE_APPEND = 13,
/* SCSI passthrough using struct scsi_request */
REQ_OP_SCSI_IN = 32,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 91c6e413bf6b..158641fbc7cd 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -331,6 +331,7 @@ struct queue_limits {
unsigned int max_hw_discard_sectors;
unsigned int max_write_same_sectors;
unsigned int max_write_zeroes_sectors;
+ unsigned int max_zone_append_sectors;
unsigned int discard_granularity;
unsigned int discard_alignment;
@@ -749,6 +750,9 @@ static inline bool rq_mergeable(struct request *rq)
if (req_op(rq) == REQ_OP_WRITE_ZEROES)
return false;
+ if (req_op(rq) == REQ_OP_ZONE_APPEND)
+ return false;
+
if (rq->cmd_flags & REQ_NOMERGE_FLAGS)
return false;
if (rq->rq_flags & RQF_NOMERGE_FLAGS)
@@ -1083,6 +1087,8 @@ extern void blk_queue_max_write_same_sectors(struct request_queue *q,
extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
unsigned int max_write_same_sectors);
extern void blk_queue_logical_block_size(struct request_queue *, unsigned int);
+extern void blk_queue_max_zone_append_sectors(struct request_queue *q,
+ unsigned int max_zone_append_sectors);
extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
extern void blk_queue_alignment_offset(struct request_queue *q,
unsigned int alignment);
@@ -1300,6 +1306,11 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q)
return q->limits.max_segment_size;
}
+static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q)
+{
+ return q->limits.max_zone_append_sectors;
+}
+
static inline unsigned queue_logical_block_size(const struct request_queue *q)
{
int retval = 512;
--
2.24.1
^ permalink raw reply [flat|nested] 12+ messages in thread* [PATCH v10 3/9] block: introduce blk_req_zone_write_trylock
2020-05-06 16:11 [PATCH v10 0/9] Introduce Zone Append for writing to zoned block devices Johannes Thumshirn
2020-05-06 16:11 ` [PATCH v10 1/9] block: rename __bio_add_pc_page to bio_add_hw_page Johannes Thumshirn
2020-05-06 16:11 ` [PATCH v10 2/9] block: Introduce REQ_OP_ZONE_APPEND Johannes Thumshirn
@ 2020-05-06 16:11 ` Johannes Thumshirn
2020-05-06 16:11 ` [PATCH v10 4/9] block: Modify revalidate zones Johannes Thumshirn
` (5 subsequent siblings)
8 siblings, 0 replies; 12+ messages in thread
From: Johannes Thumshirn @ 2020-05-06 16:11 UTC (permalink / raw)
To: Jens Axboe
Cc: Christoph Hellwig, linux-block, Damien Le Moal, Keith Busch,
linux-scsi @ vger . kernel . org, Martin K . Petersen,
linux-fsdevel @ vger . kernel . org, Johannes Thumshirn,
Christoph Hellwig, Hannes Reinecke
Introduce blk_req_zone_write_trylock(), which either grabs the write-lock
for a sequential zone or returns false, if the zone is already locked.
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
---
block/blk-zoned.c | 14 ++++++++++++++
include/linux/blkdev.h | 1 +
2 files changed, 15 insertions(+)
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index f87956e0dcaf..c822cfa7a102 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -82,6 +82,20 @@ bool blk_req_needs_zone_write_lock(struct request *rq)
}
EXPORT_SYMBOL_GPL(blk_req_needs_zone_write_lock);
+bool blk_req_zone_write_trylock(struct request *rq)
+{
+ unsigned int zno = blk_rq_zone_no(rq);
+
+ if (test_and_set_bit(zno, rq->q->seq_zones_wlock))
+ return false;
+
+ WARN_ON_ONCE(rq->rq_flags & RQF_ZONE_WRITE_LOCKED);
+ rq->rq_flags |= RQF_ZONE_WRITE_LOCKED;
+
+ return true;
+}
+EXPORT_SYMBOL_GPL(blk_req_zone_write_trylock);
+
void __blk_req_zone_write_lock(struct request *rq)
{
if (WARN_ON_ONCE(test_and_set_bit(blk_rq_zone_no(rq),
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 158641fbc7cd..d6e6ce3dc656 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1737,6 +1737,7 @@ extern int bdev_write_page(struct block_device *, sector_t, struct page *,
#ifdef CONFIG_BLK_DEV_ZONED
bool blk_req_needs_zone_write_lock(struct request *rq);
+bool blk_req_zone_write_trylock(struct request *rq);
void __blk_req_zone_write_lock(struct request *rq);
void __blk_req_zone_write_unlock(struct request *rq);
--
2.24.1
^ permalink raw reply [flat|nested] 12+ messages in thread* [PATCH v10 4/9] block: Modify revalidate zones
2020-05-06 16:11 [PATCH v10 0/9] Introduce Zone Append for writing to zoned block devices Johannes Thumshirn
` (2 preceding siblings ...)
2020-05-06 16:11 ` [PATCH v10 3/9] block: introduce blk_req_zone_write_trylock Johannes Thumshirn
@ 2020-05-06 16:11 ` Johannes Thumshirn
2020-05-06 16:11 ` [PATCH v10 5/9] scsi: sd_zbc: factor out sanity checks for zoned commands Johannes Thumshirn
` (4 subsequent siblings)
8 siblings, 0 replies; 12+ messages in thread
From: Johannes Thumshirn @ 2020-05-06 16:11 UTC (permalink / raw)
To: Jens Axboe
Cc: Christoph Hellwig, linux-block, Damien Le Moal, Keith Busch,
linux-scsi @ vger . kernel . org, Martin K . Petersen,
linux-fsdevel @ vger . kernel . org, Damien Le Moal,
Johannes Thumshirn, Christoph Hellwig, Hannes Reinecke
From: Damien Le Moal <damien.lemoal@wdc.com>
Modify the interface of blk_revalidate_disk_zones() to add an optional
driver callback function that a driver can use to extend processing
done during zone revalidation. The callback, if defined, is executed
with the device request queue frozen, after all zones have been
inspected.
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
---
block/blk-zoned.c | 9 ++++++++-
drivers/block/null_blk_zoned.c | 2 +-
include/linux/blkdev.h | 3 ++-
3 files changed, 11 insertions(+), 3 deletions(-)
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index c822cfa7a102..23831fa8701d 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -471,14 +471,19 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
/**
* blk_revalidate_disk_zones - (re)allocate and initialize zone bitmaps
* @disk: Target disk
+ * @update_driver_data: Callback to update driver data on the frozen disk
*
* Helper function for low-level device drivers to (re) allocate and initialize
* a disk request queue zone bitmaps. This functions should normally be called
* within the disk ->revalidate method for blk-mq based drivers. For BIO based
* drivers only q->nr_zones needs to be updated so that the sysfs exposed value
* is correct.
+ * If the @update_driver_data callback function is not NULL, the callback is
+ * executed with the device request queue frozen after all zones have been
+ * checked.
*/
-int blk_revalidate_disk_zones(struct gendisk *disk)
+int blk_revalidate_disk_zones(struct gendisk *disk,
+ void (*update_driver_data)(struct gendisk *disk))
{
struct request_queue *q = disk->queue;
struct blk_revalidate_zone_args args = {
@@ -512,6 +517,8 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
q->nr_zones = args.nr_zones;
swap(q->seq_zones_wlock, args.seq_zones_wlock);
swap(q->conv_zones_bitmap, args.conv_zones_bitmap);
+ if (update_driver_data)
+ update_driver_data(disk);
ret = 0;
} else {
pr_warn("%s: failed to revalidate zones\n", disk->disk_name);
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
index 9e4bcdad1a80..46641df2e58e 100644
--- a/drivers/block/null_blk_zoned.c
+++ b/drivers/block/null_blk_zoned.c
@@ -73,7 +73,7 @@ int null_register_zoned_dev(struct nullb *nullb)
struct request_queue *q = nullb->q;
if (queue_is_mq(q))
- return blk_revalidate_disk_zones(nullb->disk);
+ return blk_revalidate_disk_zones(nullb->disk, NULL);
blk_queue_chunk_sectors(q, nullb->dev->zone_size_sects);
q->nr_zones = blkdev_nr_zones(nullb->disk);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d6e6ce3dc656..fd405dac8eb0 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -357,7 +357,8 @@ unsigned int blkdev_nr_zones(struct gendisk *disk);
extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
sector_t sectors, sector_t nr_sectors,
gfp_t gfp_mask);
-extern int blk_revalidate_disk_zones(struct gendisk *disk);
+int blk_revalidate_disk_zones(struct gendisk *disk,
+ void (*update_driver_data)(struct gendisk *disk));
extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg);
--
2.24.1
^ permalink raw reply [flat|nested] 12+ messages in thread* [PATCH v10 5/9] scsi: sd_zbc: factor out sanity checks for zoned commands
2020-05-06 16:11 [PATCH v10 0/9] Introduce Zone Append for writing to zoned block devices Johannes Thumshirn
` (3 preceding siblings ...)
2020-05-06 16:11 ` [PATCH v10 4/9] block: Modify revalidate zones Johannes Thumshirn
@ 2020-05-06 16:11 ` Johannes Thumshirn
2020-05-06 16:11 ` [PATCH v10 6/9] scsi: sd_zbc: emulate ZONE_APPEND commands Johannes Thumshirn
` (3 subsequent siblings)
8 siblings, 0 replies; 12+ messages in thread
From: Johannes Thumshirn @ 2020-05-06 16:11 UTC (permalink / raw)
To: Jens Axboe
Cc: Christoph Hellwig, linux-block, Damien Le Moal, Keith Busch,
linux-scsi @ vger . kernel . org, Martin K . Petersen,
linux-fsdevel @ vger . kernel . org, Johannes Thumshirn,
Christoph Hellwig, Bart Van Assche, Hannes Reinecke
Factor sanity checks for zoned commands from sd_zbc_setup_zone_mgmt_cmnd().
This will help with the introduction of an emulated ZONE_APPEND command.
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/sd_zbc.c | 36 +++++++++++++++++++++++++-----------
1 file changed, 25 insertions(+), 11 deletions(-)
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index f45c22b09726..ee156fbf3780 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -209,6 +209,26 @@ int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
return ret;
}
+static blk_status_t sd_zbc_cmnd_checks(struct scsi_cmnd *cmd)
+{
+ struct request *rq = cmd->request;
+ struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+ sector_t sector = blk_rq_pos(rq);
+
+ if (!sd_is_zoned(sdkp))
+ /* Not a zoned device */
+ return BLK_STS_IOERR;
+
+ if (sdkp->device->changed)
+ return BLK_STS_IOERR;
+
+ if (sector & (sd_zbc_zone_sectors(sdkp) - 1))
+ /* Unaligned request */
+ return BLK_STS_IOERR;
+
+ return BLK_STS_OK;
+}
+
/**
* sd_zbc_setup_zone_mgmt_cmnd - Prepare a zone ZBC_OUT command. The operations
* can be RESET WRITE POINTER, OPEN, CLOSE or FINISH.
@@ -223,20 +243,14 @@ blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
unsigned char op, bool all)
{
struct request *rq = cmd->request;
- struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
sector_t sector = blk_rq_pos(rq);
+ struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
sector_t block = sectors_to_logical(sdkp->device, sector);
+ blk_status_t ret;
- if (!sd_is_zoned(sdkp))
- /* Not a zoned device */
- return BLK_STS_IOERR;
-
- if (sdkp->device->changed)
- return BLK_STS_IOERR;
-
- if (sector & (sd_zbc_zone_sectors(sdkp) - 1))
- /* Unaligned request */
- return BLK_STS_IOERR;
+ ret = sd_zbc_cmnd_checks(cmd);
+ if (ret != BLK_STS_OK)
+ return ret;
cmd->cmd_len = 16;
memset(cmd->cmnd, 0, cmd->cmd_len);
--
2.24.1
^ permalink raw reply [flat|nested] 12+ messages in thread* [PATCH v10 6/9] scsi: sd_zbc: emulate ZONE_APPEND commands
2020-05-06 16:11 [PATCH v10 0/9] Introduce Zone Append for writing to zoned block devices Johannes Thumshirn
` (4 preceding siblings ...)
2020-05-06 16:11 ` [PATCH v10 5/9] scsi: sd_zbc: factor out sanity checks for zoned commands Johannes Thumshirn
@ 2020-05-06 16:11 ` Johannes Thumshirn
2020-05-06 18:18 ` Hannes Reinecke
2020-05-06 16:11 ` [PATCH v10 7/9] null_blk: Support REQ_OP_ZONE_APPEND Johannes Thumshirn
` (2 subsequent siblings)
8 siblings, 1 reply; 12+ messages in thread
From: Johannes Thumshirn @ 2020-05-06 16:11 UTC (permalink / raw)
To: Jens Axboe
Cc: Christoph Hellwig, linux-block, Damien Le Moal, Keith Busch,
linux-scsi @ vger . kernel . org, Martin K . Petersen,
linux-fsdevel @ vger . kernel . org, Johannes Thumshirn,
Christoph Hellwig
Emulate ZONE_APPEND for SCSI disks using a regular WRITE(16) command
with a start LBA set to the target zone write pointer position.
In order to always know the write pointer position of a sequential write
zone, the write pointer of all zones is tracked using an array of 32bits
zone write pointer offset attached to the scsi disk structure. Each
entry of the array indicate a zone write pointer position relative to
the zone start sector. The write pointer offsets are maintained in sync
with the device as follows:
1) the write pointer offset of a zone is reset to 0 when a
REQ_OP_ZONE_RESET command completes.
2) the write pointer offset of a zone is set to the zone size when a
REQ_OP_ZONE_FINISH command completes.
3) the write pointer offset of a zone is incremented by the number of
512B sectors written when a write, write same or a zone append
command completes.
4) the write pointer offset of all zones is reset to 0 when a
REQ_OP_ZONE_RESET_ALL command completes.
Since the block layer does not write lock zones for zone append
commands, to ensure a sequential ordering of the regular write commands
used for the emulation, the target zone of a zone append command is
locked when the function sd_zbc_prepare_zone_append() is called from
sd_setup_read_write_cmnd(). If the zone write lock cannot be obtained
(e.g. a zone append is in-flight or a regular write has already locked
the zone), the zone append command dispatching is delayed by returning
BLK_STS_ZONE_RESOURCE.
To avoid the need for write locking all zones for REQ_OP_ZONE_RESET_ALL
requests, use a spinlock to protect accesses and modifications of the
zone write pointer offsets. This spinlock is initialized from sd_probe()
using the new function sd_zbc_init().
Co-developed-by: Damien Le Moal <Damien.LeMoal@wdc.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/sd.c | 16 +-
drivers/scsi/sd.h | 43 ++++-
drivers/scsi/sd_zbc.c | 363 +++++++++++++++++++++++++++++++++++++++---
3 files changed, 392 insertions(+), 30 deletions(-)
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index a793cb08d025..7b0383e42b4c 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1206,6 +1206,12 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd)
}
}
+ if (req_op(rq) == REQ_OP_ZONE_APPEND) {
+ ret = sd_zbc_prepare_zone_append(cmd, &lba, nr_blocks);
+ if (ret)
+ return ret;
+ }
+
fua = rq->cmd_flags & REQ_FUA ? 0x8 : 0;
dix = scsi_prot_sg_count(cmd);
dif = scsi_host_dif_capable(cmd->device->host, sdkp->protection_type);
@@ -1287,6 +1293,7 @@ static blk_status_t sd_init_command(struct scsi_cmnd *cmd)
return sd_setup_flush_cmnd(cmd);
case REQ_OP_READ:
case REQ_OP_WRITE:
+ case REQ_OP_ZONE_APPEND:
return sd_setup_read_write_cmnd(cmd);
case REQ_OP_ZONE_RESET:
return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_RESET_WRITE_POINTER,
@@ -2055,7 +2062,7 @@ static int sd_done(struct scsi_cmnd *SCpnt)
out:
if (sd_is_zoned(sdkp))
- sd_zbc_complete(SCpnt, good_bytes, &sshdr);
+ good_bytes = sd_zbc_complete(SCpnt, good_bytes, &sshdr);
SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, SCpnt,
"sd_done: completed %d of %d bytes\n",
@@ -3372,6 +3379,10 @@ static int sd_probe(struct device *dev)
sdkp->first_scan = 1;
sdkp->max_medium_access_timeouts = SD_MAX_MEDIUM_TIMEOUTS;
+ error = sd_zbc_init_disk(sdkp);
+ if (error)
+ goto out_free_index;
+
sd_revalidate_disk(gd);
gd->flags = GENHD_FL_EXT_DEVT;
@@ -3409,6 +3420,7 @@ static int sd_probe(struct device *dev)
out_put:
put_disk(gd);
out_free:
+ sd_zbc_release_disk(sdkp);
kfree(sdkp);
out:
scsi_autopm_put_device(sdp);
@@ -3485,6 +3497,8 @@ static void scsi_disk_release(struct device *dev)
put_disk(disk);
put_device(&sdkp->device->sdev_gendev);
+ sd_zbc_release_disk(sdkp);
+
kfree(sdkp);
}
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 50fff0bf8c8e..3a74f4b45134 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -79,6 +79,12 @@ struct scsi_disk {
u32 zones_optimal_open;
u32 zones_optimal_nonseq;
u32 zones_max_open;
+ u32 *zones_wp_offset;
+ spinlock_t zones_wp_offset_lock;
+ u32 *rev_wp_offset;
+ struct mutex rev_mutex;
+ struct work_struct zone_wp_offset_work;
+ char *zone_wp_update_buf;
#endif
atomic_t openers;
sector_t capacity; /* size in logical blocks */
@@ -207,17 +213,35 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp)
#ifdef CONFIG_BLK_DEV_ZONED
+int sd_zbc_init_disk(struct scsi_disk *sdkp);
+void sd_zbc_release_disk(struct scsi_disk *sdkp);
extern int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer);
extern void sd_zbc_print_zones(struct scsi_disk *sdkp);
blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
unsigned char op, bool all);
-extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
- struct scsi_sense_hdr *sshdr);
+unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
+ struct scsi_sense_hdr *sshdr);
int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data);
+blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba,
+ unsigned int nr_blocks);
+
#else /* CONFIG_BLK_DEV_ZONED */
+static inline int sd_zbc_init(void)
+{
+ return 0;
+}
+
+static inline int sd_zbc_init_disk(struct scsi_disk *sdkp)
+{
+ return 0;
+}
+
+static inline void sd_zbc_exit(void) {}
+static inline void sd_zbc_release_disk(struct scsi_disk *sdkp) {}
+
static inline int sd_zbc_read_zones(struct scsi_disk *sdkp,
unsigned char *buf)
{
@@ -233,9 +257,18 @@ static inline blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
return BLK_STS_TARGET;
}
-static inline void sd_zbc_complete(struct scsi_cmnd *cmd,
- unsigned int good_bytes,
- struct scsi_sense_hdr *sshdr) {}
+static inline unsigned int sd_zbc_complete(struct scsi_cmnd *cmd,
+ unsigned int good_bytes, struct scsi_sense_hdr *sshdr)
+{
+ return 0;
+}
+
+static inline blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd,
+ sector_t *lba,
+ unsigned int nr_blocks)
+{
+ return BLK_STS_TARGET;
+}
#define sd_zbc_report_zones NULL
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index ee156fbf3780..bb87fbba2a09 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -11,6 +11,7 @@
#include <linux/blkdev.h>
#include <linux/vmalloc.h>
#include <linux/sched/mm.h>
+#include <linux/mutex.h>
#include <asm/unaligned.h>
@@ -19,11 +20,36 @@
#include "sd.h"
+static unsigned int sd_zbc_get_zone_wp_offset(struct blk_zone *zone)
+{
+ if (zone->type == ZBC_ZONE_TYPE_CONV)
+ return 0;
+
+ switch (zone->cond) {
+ case BLK_ZONE_COND_IMP_OPEN:
+ case BLK_ZONE_COND_EXP_OPEN:
+ case BLK_ZONE_COND_CLOSED:
+ return zone->wp - zone->start;
+ case BLK_ZONE_COND_FULL:
+ return zone->len;
+ case BLK_ZONE_COND_EMPTY:
+ case BLK_ZONE_COND_OFFLINE:
+ case BLK_ZONE_COND_READONLY:
+ default:
+ /*
+ * Offline and read-only zones do not have a valid
+ * write pointer. Use 0 as for an empty zone.
+ */
+ return 0;
+ }
+}
+
static int sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf,
unsigned int idx, report_zones_cb cb, void *data)
{
struct scsi_device *sdp = sdkp->device;
struct blk_zone zone = { 0 };
+ int ret;
zone.type = buf[0] & 0x0f;
zone.cond = (buf[1] >> 4) & 0xf;
@@ -39,7 +65,14 @@ static int sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf,
zone.cond == ZBC_ZONE_COND_FULL)
zone.wp = zone.start + zone.len;
- return cb(&zone, idx, data);
+ ret = cb(&zone, idx, data);
+ if (ret)
+ return ret;
+
+ if (sdkp->rev_wp_offset)
+ sdkp->rev_wp_offset[idx] = sd_zbc_get_zone_wp_offset(&zone);
+
+ return 0;
}
/**
@@ -229,6 +262,116 @@ static blk_status_t sd_zbc_cmnd_checks(struct scsi_cmnd *cmd)
return BLK_STS_OK;
}
+#define SD_ZBC_INVALID_WP_OFST (~0u)
+#define SD_ZBC_UPDATING_WP_OFST (SD_ZBC_INVALID_WP_OFST - 1)
+
+static int sd_zbc_update_wp_offset_cb(struct blk_zone *zone, unsigned int idx,
+ void *data)
+{
+ struct scsi_disk *sdkp = data;
+
+ lockdep_assert_held(&sdkp->zones_wp_offset_lock);
+
+ sdkp->zones_wp_offset[idx] = sd_zbc_get_zone_wp_offset(zone);
+
+ return 0;
+}
+
+static void sd_zbc_update_wp_offset_workfn(struct work_struct *work)
+{
+ struct scsi_disk *sdkp;
+ unsigned int zno;
+ int ret;
+
+ sdkp = container_of(work, struct scsi_disk, zone_wp_offset_work);
+
+ spin_lock_bh(&sdkp->zones_wp_offset_lock);
+ for (zno = 0; zno < sdkp->nr_zones; zno++) {
+ if (sdkp->zones_wp_offset[zno] != SD_ZBC_UPDATING_WP_OFST)
+ continue;
+
+ spin_unlock_bh(&sdkp->zones_wp_offset_lock);
+ ret = sd_zbc_do_report_zones(sdkp, sdkp->zone_wp_update_buf,
+ SD_BUF_SIZE,
+ zno * sdkp->zone_blocks, true);
+ spin_lock_bh(&sdkp->zones_wp_offset_lock);
+ if (!ret)
+ sd_zbc_parse_report(sdkp, sdkp->zone_wp_update_buf + 64,
+ zno, sd_zbc_update_wp_offset_cb,
+ sdkp);
+ }
+ spin_unlock_bh(&sdkp->zones_wp_offset_lock);
+
+ scsi_device_put(sdkp->device);
+}
+
+/**
+ * sd_zbc_prepare_zone_append() - Prepare an emulated ZONE_APPEND command.
+ * @cmd: the command to setup
+ * @lba: the LBA to patch
+ * @nr_blocks: the number of LBAs to be written
+ *
+ * Called from sd_setup_read_write_cmnd() for REQ_OP_ZONE_APPEND.
+ * @sd_zbc_prepare_zone_append() handles the necessary zone wrote locking and
+ * patching of the lba for an emulated ZONE_APPEND command.
+ *
+ * In case the cached write pointer offset is %SD_ZBC_INVALID_WP_OFST it will
+ * schedule a REPORT ZONES command and return BLK_STS_IOERR.
+ */
+blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba,
+ unsigned int nr_blocks)
+{
+ struct request *rq = cmd->request;
+ struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+ unsigned int wp_offset, zno = blk_rq_zone_no(rq);
+ blk_status_t ret;
+
+ ret = sd_zbc_cmnd_checks(cmd);
+ if (ret != BLK_STS_OK)
+ return ret;
+
+ if (!blk_rq_zone_is_seq(rq))
+ return BLK_STS_IOERR;
+
+ /* Unlock of the write lock will happen in sd_zbc_complete() */
+ if (!blk_req_zone_write_trylock(rq))
+ return BLK_STS_ZONE_RESOURCE;
+
+ spin_lock_bh(&sdkp->zones_wp_offset_lock);
+ wp_offset = sdkp->zones_wp_offset[zno];
+ switch (wp_offset) {
+ case SD_ZBC_INVALID_WP_OFST:
+ /*
+ * We are about to schedule work to update a zone write pointer
+ * offset, which will cause the zone append command to be
+ * requeued. So make sure that the scsi device does not go away
+ * while the work is being processed.
+ */
+ if (scsi_device_get(sdkp->device)) {
+ ret = BLK_STS_IOERR;
+ break;
+ }
+ sdkp->zones_wp_offset[zno] = SD_ZBC_UPDATING_WP_OFST;
+ schedule_work(&sdkp->zone_wp_offset_work);
+ fallthrough;
+ case SD_ZBC_UPDATING_WP_OFST:
+ ret = BLK_STS_DEV_RESOURCE;
+ break;
+ default:
+ wp_offset = sectors_to_logical(sdkp->device, wp_offset);
+ if (wp_offset + nr_blocks > sdkp->zone_blocks) {
+ ret = BLK_STS_IOERR;
+ break;
+ }
+
+ *lba += wp_offset;
+ }
+ spin_unlock_bh(&sdkp->zones_wp_offset_lock);
+ if (ret)
+ blk_req_zone_write_unlock(rq);
+ return ret;
+}
+
/**
* sd_zbc_setup_zone_mgmt_cmnd - Prepare a zone ZBC_OUT command. The operations
* can be RESET WRITE POINTER, OPEN, CLOSE or FINISH.
@@ -269,16 +412,105 @@ blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
return BLK_STS_OK;
}
+static bool sd_zbc_need_zone_wp_update(struct request *rq)
+{
+ switch (req_op(rq)) {
+ case REQ_OP_ZONE_APPEND:
+ case REQ_OP_ZONE_FINISH:
+ case REQ_OP_ZONE_RESET:
+ case REQ_OP_ZONE_RESET_ALL:
+ return true;
+ case REQ_OP_WRITE:
+ case REQ_OP_WRITE_ZEROES:
+ case REQ_OP_WRITE_SAME:
+ return blk_rq_zone_is_seq(rq);
+ default:
+ return false;
+ }
+}
+
+/**
+ * sd_zbc_zone_wp_update - Update cached zone write pointer upon cmd completion
+ * @cmd: Completed command
+ * @good_bytes: Command reply bytes
+ *
+ * Called from sd_zbc_complete() to handle the update of the cached zone write
+ * pointer value in case an update is needed.
+ */
+static unsigned int sd_zbc_zone_wp_update(struct scsi_cmnd *cmd,
+ unsigned int good_bytes)
+{
+ int result = cmd->result;
+ struct request *rq = cmd->request;
+ struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+ unsigned int zno = blk_rq_zone_no(rq);
+ enum req_opf op = req_op(rq);
+
+ /*
+ * If we got an error for a command that needs updating the write
+ * pointer offset cache, we must mark the zone wp offset entry as
+ * invalid to force an update from disk the next time a zone append
+ * command is issued.
+ */
+ spin_lock_bh(&sdkp->zones_wp_offset_lock);
+
+ if (result && op != REQ_OP_ZONE_RESET_ALL) {
+ if (op == REQ_OP_ZONE_APPEND) {
+ /* Force complete completion (no retry) */
+ good_bytes = 0;
+ scsi_set_resid(cmd, blk_rq_bytes(rq));
+ }
+
+ /*
+ * Force an update of the zone write pointer offset on
+ * the next zone append access.
+ */
+ if (sdkp->zones_wp_offset[zno] != SD_ZBC_UPDATING_WP_OFST)
+ sdkp->zones_wp_offset[zno] = SD_ZBC_INVALID_WP_OFST;
+ goto unlock_wp_offset;
+ }
+
+ switch (op) {
+ case REQ_OP_ZONE_APPEND:
+ rq->__sector += sdkp->zones_wp_offset[zno];
+ fallthrough;
+ case REQ_OP_WRITE_ZEROES:
+ case REQ_OP_WRITE_SAME:
+ case REQ_OP_WRITE:
+ if (sdkp->zones_wp_offset[zno] < sd_zbc_zone_sectors(sdkp))
+ sdkp->zones_wp_offset[zno] +=
+ good_bytes >> SECTOR_SHIFT;
+ break;
+ case REQ_OP_ZONE_RESET:
+ sdkp->zones_wp_offset[zno] = 0;
+ break;
+ case REQ_OP_ZONE_FINISH:
+ sdkp->zones_wp_offset[zno] = sd_zbc_zone_sectors(sdkp);
+ break;
+ case REQ_OP_ZONE_RESET_ALL:
+ memset(sdkp->zones_wp_offset, 0,
+ sdkp->nr_zones * sizeof(unsigned int));
+ break;
+ default:
+ break;
+ }
+
+unlock_wp_offset:
+ spin_unlock_bh(&sdkp->zones_wp_offset_lock);
+
+ return good_bytes;
+}
+
/**
* sd_zbc_complete - ZBC command post processing.
* @cmd: Completed command
* @good_bytes: Command reply bytes
* @sshdr: command sense header
*
- * Called from sd_done(). Process report zones reply and handle reset zone
- * and write commands errors.
+ * Called from sd_done() to handle zone commands errors and updates to the
+ * device queue zone write pointer offset cahce.
*/
-void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
+unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
struct scsi_sense_hdr *sshdr)
{
int result = cmd->result;
@@ -294,7 +526,13 @@ void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
* so be quiet about the error.
*/
rq->rq_flags |= RQF_QUIET;
- }
+ } else if (sd_zbc_need_zone_wp_update(rq))
+ good_bytes = sd_zbc_zone_wp_update(cmd, good_bytes);
+
+ if (req_op(rq) == REQ_OP_ZONE_APPEND)
+ blk_req_zone_write_unlock(rq);
+
+ return good_bytes;
}
/**
@@ -396,11 +634,67 @@ static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf,
return 0;
}
+static void sd_zbc_revalidate_zones_cb(struct gendisk *disk)
+{
+ struct scsi_disk *sdkp = scsi_disk(disk);
+
+ swap(sdkp->zones_wp_offset, sdkp->rev_wp_offset);
+}
+
+static int sd_zbc_revalidate_zones(struct scsi_disk *sdkp,
+ u32 zone_blocks,
+ unsigned int nr_zones)
+{
+ struct gendisk *disk = sdkp->disk;
+ int ret = 0;
+
+ /*
+ * Make sure revalidate zones are serialized to ensure exclusive
+ * updates of the scsi disk data.
+ */
+ mutex_lock(&sdkp->rev_mutex);
+
+ /*
+ * Revalidate the disk zones to update the device request queue zone
+ * bitmaps and the zone write pointer offset array. Do this only once
+ * the device capacity is set on the second revalidate execution for
+ * disk scan or if something changed when executing a normal revalidate.
+ */
+ if (sdkp->first_scan) {
+ sdkp->zone_blocks = zone_blocks;
+ sdkp->nr_zones = nr_zones;
+ goto unlock;
+ }
+
+ if (sdkp->zone_blocks == zone_blocks &&
+ sdkp->nr_zones == nr_zones &&
+ disk->queue->nr_zones == nr_zones)
+ goto unlock;
+
+ sdkp->rev_wp_offset = kvcalloc(nr_zones, sizeof(u32), GFP_NOIO);
+ if (!sdkp->rev_wp_offset) {
+ ret = -ENOMEM;
+ goto unlock;
+ }
+
+ ret = blk_revalidate_disk_zones(disk, sd_zbc_revalidate_zones_cb);
+
+ kvfree(sdkp->rev_wp_offset);
+ sdkp->rev_wp_offset = NULL;
+
+unlock:
+ mutex_unlock(&sdkp->rev_mutex);
+
+ return ret;
+}
+
int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
{
struct gendisk *disk = sdkp->disk;
+ struct request_queue *q = disk->queue;
unsigned int nr_zones;
u32 zone_blocks = 0;
+ u32 max_append;
int ret;
if (!sd_is_zoned(sdkp))
@@ -421,35 +715,31 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
goto err;
/* The drive satisfies the kernel restrictions: set it up */
- blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, sdkp->disk->queue);
- blk_queue_required_elevator_features(sdkp->disk->queue,
- ELEVATOR_F_ZBD_SEQ_WRITE);
+ blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
+ blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
nr_zones = round_up(sdkp->capacity, zone_blocks) >> ilog2(zone_blocks);
/* READ16/WRITE16 is mandatory for ZBC disks */
sdkp->device->use_16_for_rw = 1;
sdkp->device->use_10_for_rw = 0;
+ ret = sd_zbc_revalidate_zones(sdkp, zone_blocks, nr_zones);
+ if (ret)
+ goto err;
+
/*
- * Revalidate the disk zone bitmaps once the block device capacity is
- * set on the second revalidate execution during disk scan and if
- * something changed when executing a normal revalidate.
+ * On the first scan 'chunk_sectors' isn't setup yet, so calling
+ * blk_queue_max_zone_append_sectors() will result in a WARN(). Defer
+ * this setting to the second scan.
*/
- if (sdkp->first_scan) {
- sdkp->zone_blocks = zone_blocks;
- sdkp->nr_zones = nr_zones;
+ if (sdkp->first_scan)
return 0;
- }
- if (sdkp->zone_blocks != zone_blocks ||
- sdkp->nr_zones != nr_zones ||
- disk->queue->nr_zones != nr_zones) {
- ret = blk_revalidate_disk_zones(disk);
- if (ret != 0)
- goto err;
- sdkp->zone_blocks = zone_blocks;
- sdkp->nr_zones = nr_zones;
- }
+ max_append = min_t(u32, logical_to_sectors(sdkp->device, zone_blocks),
+ q->limits.max_segments << (PAGE_SHIFT - 9));
+ max_append = min_t(u32, max_append, queue_max_hw_sectors(q));
+
+ blk_queue_max_zone_append_sectors(q, max_append);
return 0;
@@ -475,3 +765,28 @@ void sd_zbc_print_zones(struct scsi_disk *sdkp)
sdkp->nr_zones,
sdkp->zone_blocks);
}
+
+int sd_zbc_init_disk(struct scsi_disk *sdkp)
+{
+ if (!sd_is_zoned(sdkp))
+ return 0;
+
+ sdkp->zones_wp_offset = NULL;
+ spin_lock_init(&sdkp->zones_wp_offset_lock);
+ sdkp->rev_wp_offset = NULL;
+ mutex_init(&sdkp->rev_mutex);
+ INIT_WORK(&sdkp->zone_wp_offset_work, sd_zbc_update_wp_offset_workfn);
+ sdkp->zone_wp_update_buf = kzalloc(SD_BUF_SIZE, GFP_KERNEL);
+ if (!sdkp->zone_wp_update_buf)
+ return -ENOMEM;
+
+ return 0;
+}
+
+void sd_zbc_release_disk(struct scsi_disk *sdkp)
+{
+ kvfree(sdkp->zones_wp_offset);
+ sdkp->zones_wp_offset = NULL;
+ kfree(sdkp->zone_wp_update_buf);
+ sdkp->zone_wp_update_buf = NULL;
+}
--
2.24.1
^ permalink raw reply [flat|nested] 12+ messages in thread* Re: [PATCH v10 6/9] scsi: sd_zbc: emulate ZONE_APPEND commands
2020-05-06 16:11 ` [PATCH v10 6/9] scsi: sd_zbc: emulate ZONE_APPEND commands Johannes Thumshirn
@ 2020-05-06 18:18 ` Hannes Reinecke
0 siblings, 0 replies; 12+ messages in thread
From: Hannes Reinecke @ 2020-05-06 18:18 UTC (permalink / raw)
To: Johannes Thumshirn, Jens Axboe
Cc: Christoph Hellwig, linux-block, Damien Le Moal, Keith Busch,
linux-scsi @ vger . kernel . org, Martin K . Petersen,
linux-fsdevel @ vger . kernel . org, Christoph Hellwig
On 5/6/20 6:11 PM, Johannes Thumshirn wrote:
> Emulate ZONE_APPEND for SCSI disks using a regular WRITE(16) command
> with a start LBA set to the target zone write pointer position.
>
> In order to always know the write pointer position of a sequential write
> zone, the write pointer of all zones is tracked using an array of 32bits
> zone write pointer offset attached to the scsi disk structure. Each
> entry of the array indicate a zone write pointer position relative to
> the zone start sector. The write pointer offsets are maintained in sync
> with the device as follows:
> 1) the write pointer offset of a zone is reset to 0 when a
> REQ_OP_ZONE_RESET command completes.
> 2) the write pointer offset of a zone is set to the zone size when a
> REQ_OP_ZONE_FINISH command completes.
> 3) the write pointer offset of a zone is incremented by the number of
> 512B sectors written when a write, write same or a zone append
> command completes.
> 4) the write pointer offset of all zones is reset to 0 when a
> REQ_OP_ZONE_RESET_ALL command completes.
>
> Since the block layer does not write lock zones for zone append
> commands, to ensure a sequential ordering of the regular write commands
> used for the emulation, the target zone of a zone append command is
> locked when the function sd_zbc_prepare_zone_append() is called from
> sd_setup_read_write_cmnd(). If the zone write lock cannot be obtained
> (e.g. a zone append is in-flight or a regular write has already locked
> the zone), the zone append command dispatching is delayed by returning
> BLK_STS_ZONE_RESOURCE.
>
> To avoid the need for write locking all zones for REQ_OP_ZONE_RESET_ALL
> requests, use a spinlock to protect accesses and modifications of the
> zone write pointer offsets. This spinlock is initialized from sd_probe()
> using the new function sd_zbc_init().
>
> Co-developed-by: Damien Le Moal <Damien.LeMoal@wdc.com>
> Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
> ---
> drivers/scsi/sd.c | 16 +-
> drivers/scsi/sd.h | 43 ++++-
> drivers/scsi/sd_zbc.c | 363 +++++++++++++++++++++++++++++++++++++++---
> 3 files changed, 392 insertions(+), 30 deletions(-)
>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Cheers,
Hannes
--
Dr. Hannes Reinecke Teamlead Storage & Networking
hare@suse.de +49 911 74053 688
SUSE Software Solutions GmbH, Maxfeldstr. 5, 90409 Nürnberg
HRB 36809 (AG Nürnberg), Geschäftsführer: Felix Imendörffer
^ permalink raw reply [flat|nested] 12+ messages in thread
* [PATCH v10 7/9] null_blk: Support REQ_OP_ZONE_APPEND
2020-05-06 16:11 [PATCH v10 0/9] Introduce Zone Append for writing to zoned block devices Johannes Thumshirn
` (5 preceding siblings ...)
2020-05-06 16:11 ` [PATCH v10 6/9] scsi: sd_zbc: emulate ZONE_APPEND commands Johannes Thumshirn
@ 2020-05-06 16:11 ` Johannes Thumshirn
2020-05-06 16:11 ` [PATCH v10 8/9] block: export bio_release_pages and bio_iov_iter_get_pages Johannes Thumshirn
2020-05-06 16:11 ` [PATCH v10 9/9] zonefs: use REQ_OP_ZONE_APPEND for sync DIO Johannes Thumshirn
8 siblings, 0 replies; 12+ messages in thread
From: Johannes Thumshirn @ 2020-05-06 16:11 UTC (permalink / raw)
To: Jens Axboe
Cc: Christoph Hellwig, linux-block, Damien Le Moal, Keith Busch,
linux-scsi @ vger . kernel . org, Martin K . Petersen,
linux-fsdevel @ vger . kernel . org, Damien Le Moal,
Hannes Reinecke, Christoph Hellwig, Johannes Thumshirn
From: Damien Le Moal <damien.lemoal@wdc.com>
Support REQ_OP_ZONE_APPEND requests for null_blk devices with zoned
mode enabled. Use the internally tracked zone write pointer position
as the actual write position and return it using the command request
__sector field in the case of an mq device and using the command BIO
sector in the case of a BIO device.
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
---
drivers/block/null_blk_zoned.c | 37 ++++++++++++++++++++++++++--------
1 file changed, 29 insertions(+), 8 deletions(-)
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
index 46641df2e58e..9c19f747f394 100644
--- a/drivers/block/null_blk_zoned.c
+++ b/drivers/block/null_blk_zoned.c
@@ -70,13 +70,20 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
int null_register_zoned_dev(struct nullb *nullb)
{
+ struct nullb_device *dev = nullb->dev;
struct request_queue *q = nullb->q;
- if (queue_is_mq(q))
- return blk_revalidate_disk_zones(nullb->disk, NULL);
+ if (queue_is_mq(q)) {
+ int ret = blk_revalidate_disk_zones(nullb->disk, NULL);
+
+ if (ret)
+ return ret;
+ } else {
+ blk_queue_chunk_sectors(q, dev->zone_size_sects);
+ q->nr_zones = blkdev_nr_zones(nullb->disk);
+ }
- blk_queue_chunk_sectors(q, nullb->dev->zone_size_sects);
- q->nr_zones = blkdev_nr_zones(nullb->disk);
+ blk_queue_max_zone_append_sectors(q, dev->zone_size_sects);
return 0;
}
@@ -138,7 +145,7 @@ size_t null_zone_valid_read_len(struct nullb *nullb,
}
static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
- unsigned int nr_sectors)
+ unsigned int nr_sectors, bool append)
{
struct nullb_device *dev = cmd->nq->dev;
unsigned int zno = null_zone_no(dev, sector);
@@ -158,9 +165,21 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
case BLK_ZONE_COND_IMP_OPEN:
case BLK_ZONE_COND_EXP_OPEN:
case BLK_ZONE_COND_CLOSED:
- /* Writes must be at the write pointer position */
- if (sector != zone->wp)
+ /*
+ * Regular writes must be at the write pointer position.
+ * Zone append writes are automatically issued at the write
+ * pointer and the position returned using the request or BIO
+ * sector.
+ */
+ if (append) {
+ sector = zone->wp;
+ if (cmd->bio)
+ cmd->bio->bi_iter.bi_sector = sector;
+ else
+ cmd->rq->__sector = sector;
+ } else if (sector != zone->wp) {
return BLK_STS_IOERR;
+ }
if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
zone->cond = BLK_ZONE_COND_IMP_OPEN;
@@ -242,7 +261,9 @@ blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, enum req_opf op,
{
switch (op) {
case REQ_OP_WRITE:
- return null_zone_write(cmd, sector, nr_sectors);
+ return null_zone_write(cmd, sector, nr_sectors, false);
+ case REQ_OP_ZONE_APPEND:
+ return null_zone_write(cmd, sector, nr_sectors, true);
case REQ_OP_ZONE_RESET:
case REQ_OP_ZONE_RESET_ALL:
case REQ_OP_ZONE_OPEN:
--
2.24.1
^ permalink raw reply [flat|nested] 12+ messages in thread* [PATCH v10 8/9] block: export bio_release_pages and bio_iov_iter_get_pages
2020-05-06 16:11 [PATCH v10 0/9] Introduce Zone Append for writing to zoned block devices Johannes Thumshirn
` (6 preceding siblings ...)
2020-05-06 16:11 ` [PATCH v10 7/9] null_blk: Support REQ_OP_ZONE_APPEND Johannes Thumshirn
@ 2020-05-06 16:11 ` Johannes Thumshirn
2020-05-06 16:11 ` [PATCH v10 9/9] zonefs: use REQ_OP_ZONE_APPEND for sync DIO Johannes Thumshirn
8 siblings, 0 replies; 12+ messages in thread
From: Johannes Thumshirn @ 2020-05-06 16:11 UTC (permalink / raw)
To: Jens Axboe
Cc: Christoph Hellwig, linux-block, Damien Le Moal, Keith Busch,
linux-scsi @ vger . kernel . org, Martin K . Petersen,
linux-fsdevel @ vger . kernel . org, Johannes Thumshirn,
Hannes Reinecke
Export bio_release_pages and bio_iov_iter_get_pages, so they can be used
from modular code.
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
block/bio.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/block/bio.c b/block/bio.c
index 3aa3c4ce2e5e..e4c46e2bd5ba 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -951,6 +951,7 @@ void bio_release_pages(struct bio *bio, bool mark_dirty)
put_page(bvec->bv_page);
}
}
+EXPORT_SYMBOL_GPL(bio_release_pages);
static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter)
{
@@ -1114,6 +1115,7 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
bio_set_flag(bio, BIO_NO_PAGE_REF);
return bio->bi_vcnt ? 0 : ret;
}
+EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
static void submit_bio_wait_endio(struct bio *bio)
{
--
2.24.1
^ permalink raw reply [flat|nested] 12+ messages in thread* [PATCH v10 9/9] zonefs: use REQ_OP_ZONE_APPEND for sync DIO
2020-05-06 16:11 [PATCH v10 0/9] Introduce Zone Append for writing to zoned block devices Johannes Thumshirn
` (7 preceding siblings ...)
2020-05-06 16:11 ` [PATCH v10 8/9] block: export bio_release_pages and bio_iov_iter_get_pages Johannes Thumshirn
@ 2020-05-06 16:11 ` Johannes Thumshirn
8 siblings, 0 replies; 12+ messages in thread
From: Johannes Thumshirn @ 2020-05-06 16:11 UTC (permalink / raw)
To: Jens Axboe
Cc: Christoph Hellwig, linux-block, Damien Le Moal, Keith Busch,
linux-scsi @ vger . kernel . org, Martin K . Petersen,
linux-fsdevel @ vger . kernel . org, Johannes Thumshirn,
Damien Le Moal
Synchronous direct I/O to a sequential write only zone can be issued using
the new REQ_OP_ZONE_APPEND request operation. As dispatching multiple
BIOs can potentially result in reordering, we cannot support asynchronous
IO via this interface.
We also can only dispatch up to queue_max_zone_append_sectors() via the
new zone-append method and have to return a short write back to user-space
in case an IO larger than queue_max_zone_append_sectors() has been issued.
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Acked-by: Damien Le Moal <damien.lemoal@wdc.com>
---
fs/zonefs/super.c | 80 ++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 72 insertions(+), 8 deletions(-)
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 3ce9829a6936..0bf7009f50a2 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -20,6 +20,7 @@
#include <linux/mman.h>
#include <linux/sched/mm.h>
#include <linux/crc32.h>
+#include <linux/task_io_accounting_ops.h>
#include "zonefs.h"
@@ -596,6 +597,61 @@ static const struct iomap_dio_ops zonefs_write_dio_ops = {
.end_io = zonefs_file_write_dio_end_io,
};
+static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
+{
+ struct inode *inode = file_inode(iocb->ki_filp);
+ struct zonefs_inode_info *zi = ZONEFS_I(inode);
+ struct block_device *bdev = inode->i_sb->s_bdev;
+ unsigned int max;
+ struct bio *bio;
+ ssize_t size;
+ int nr_pages;
+ ssize_t ret;
+
+ nr_pages = iov_iter_npages(from, BIO_MAX_PAGES);
+ if (!nr_pages)
+ return 0;
+
+ max = queue_max_zone_append_sectors(bdev_get_queue(bdev));
+ max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize);
+ iov_iter_truncate(from, max);
+
+ bio = bio_alloc_bioset(GFP_NOFS, nr_pages, &fs_bio_set);
+ if (!bio)
+ return -ENOMEM;
+
+ bio_set_dev(bio, bdev);
+ bio->bi_iter.bi_sector = zi->i_zsector;
+ bio->bi_write_hint = iocb->ki_hint;
+ bio->bi_ioprio = iocb->ki_ioprio;
+ bio->bi_opf = REQ_OP_ZONE_APPEND | REQ_SYNC | REQ_IDLE;
+ if (iocb->ki_flags & IOCB_DSYNC)
+ bio->bi_opf |= REQ_FUA;
+
+ ret = bio_iov_iter_get_pages(bio, from);
+ if (unlikely(ret)) {
+ bio_io_error(bio);
+ return ret;
+ }
+ size = bio->bi_iter.bi_size;
+ task_io_account_write(ret);
+
+ if (iocb->ki_flags & IOCB_HIPRI)
+ bio_set_polled(bio, iocb);
+
+ ret = submit_bio_wait(bio);
+
+ bio_put(bio);
+
+ zonefs_file_write_dio_end_io(iocb, size, ret, 0);
+ if (ret >= 0) {
+ iocb->ki_pos += size;
+ return size;
+ }
+
+ return ret;
+}
+
/*
* Handle direct writes. For sequential zone files, this is the only possible
* write path. For these files, check that the user is issuing writes
@@ -611,6 +667,8 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
struct inode *inode = file_inode(iocb->ki_filp);
struct zonefs_inode_info *zi = ZONEFS_I(inode);
struct super_block *sb = inode->i_sb;
+ bool sync = is_sync_kiocb(iocb);
+ bool append = false;
size_t count;
ssize_t ret;
@@ -619,7 +677,7 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
* as this can cause write reordering (e.g. the first aio gets EAGAIN
* on the inode lock but the second goes through but is now unaligned).
*/
- if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && !is_sync_kiocb(iocb) &&
+ if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && !sync &&
(iocb->ki_flags & IOCB_NOWAIT))
return -EOPNOTSUPP;
@@ -643,16 +701,22 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
}
/* Enforce sequential writes (append only) in sequential zones */
- mutex_lock(&zi->i_truncate_mutex);
- if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && iocb->ki_pos != zi->i_wpoffset) {
+ if (zi->i_ztype == ZONEFS_ZTYPE_SEQ) {
+ mutex_lock(&zi->i_truncate_mutex);
+ if (iocb->ki_pos != zi->i_wpoffset) {
+ mutex_unlock(&zi->i_truncate_mutex);
+ ret = -EINVAL;
+ goto inode_unlock;
+ }
mutex_unlock(&zi->i_truncate_mutex);
- ret = -EINVAL;
- goto inode_unlock;
+ append = sync;
}
- mutex_unlock(&zi->i_truncate_mutex);
- ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops,
- &zonefs_write_dio_ops, is_sync_kiocb(iocb));
+ if (append)
+ ret = zonefs_file_dio_append(iocb, from);
+ else
+ ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops,
+ &zonefs_write_dio_ops, sync);
if (zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
(ret > 0 || ret == -EIOCBQUEUED)) {
if (ret > 0)
--
2.24.1
^ permalink raw reply [flat|nested] 12+ messages in thread