[PATCH] block, nvme: export and use passthrough stats

[PATCH] block, nvme: export and use passthrough stats

[Keith Busch]

From: Keith Busch <kbusch@kernel.org>

So stacking drivers can also report passthrough workloads through
iostat.

Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 block/blk-mq.c                | 30 ------------------------------
 drivers/nvme/host/multipath.c |  4 +++-
 include/linux/blk-mq.h        | 29 +++++++++++++++++++++++++++++
 3 files changed, 32 insertions(+), 31 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 28c2d931e75ea..c794b70fefe26 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1088,36 +1088,6 @@ static inline void blk_account_io_done(struct request *req, u64 now)
 	}
 }
 
-static inline bool blk_rq_passthrough_stats(struct request *req)
-{
-	struct bio *bio = req->bio;
-
-	if (!blk_queue_passthrough_stat(req->q))
-		return false;
-
-	/* Requests without a bio do not transfer data. */
-	if (!bio)
-		return false;
-
-	/*
-	 * Stats are accumulated in the bdev, so must have one attached to a
-	 * bio to track stats. Most drivers do not set the bdev for passthrough
-	 * requests, but nvme is one that will set it.
-	 */
-	if (!bio->bi_bdev)
-		return false;
-
-	/*
-	 * We don't know what a passthrough command does, but we know the
-	 * payload size and data direction. Ensuring the size is aligned to the
-	 * block size filters out most commands with payloads that don't
-	 * represent sector access.
-	 */
-	if (blk_rq_bytes(req) & (bdev_logical_block_size(bio->bi_bdev) - 1))
-		return false;
-	return true;
-}
-
 static inline void blk_account_io_start(struct request *req)
 {
 	trace_block_io_start(req);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 263161cb8ac06..435fab0be6401 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -175,9 +175,11 @@ void nvme_mpath_start_request(struct request *rq)
 		nvme_req(rq)->flags |= NVME_MPATH_CNT_ACTIVE;
 	}
 
-	if (!blk_queue_io_stat(disk->queue) || blk_rq_is_passthrough(rq) ||
+	if (!blk_queue_io_stat(disk->queue) ||
 	    (nvme_req(rq)->flags & NVME_MPATH_IO_STATS))
 		return;
+	if (blk_rq_is_passthrough(rq) && !blk_rq_passthrough_stats(rq))
+		return;
 
 	nvme_req(rq)->flags |= NVME_MPATH_IO_STATS;
 	nvme_req(rq)->start_time = bdev_start_io_acct(disk->part0, req_op(rq),
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 18a2388ba581d..8301830ece8b7 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -1243,4 +1243,33 @@ static inline int blk_rq_map_sg(struct request *rq, struct scatterlist *sglist)
 }
 void blk_dump_rq_flags(struct request *, char *);
 
+static inline bool blk_rq_passthrough_stats(struct request *req)
+{
+	struct bio *bio = req->bio;
+
+	if (!blk_queue_passthrough_stat(req->q))
+		return false;
+
+	/* Requests without a bio do not transfer data. */
+	if (!bio)
+		return false;
+
+	/*
+	 * Stats are accumulated in the bdev, so must have one attached to a
+	 * bio to track stats. Most drivers do not set the bdev for passthrough
+	 * requests, but nvme is one that will set it.
+	 */
+	if (!bio->bi_bdev)
+		return false;
+
+	/*
+	 * We don't know what a passthrough command does, but we know the
+	 * payload size and data direction. Ensuring the size is aligned to the
+	 * block size filters out most commands with payloads that don't
+	 * represent sector access.
+	 */
+	if (blk_rq_bytes(req) & (bdev_logical_block_size(bio->bi_bdev) - 1))
+		return false;
+	return true;
+}
 #endif /* BLK_MQ_H */
-- 
2.53.0-Meta

Re: [PATCH] block, nvme: export and use passthrough stats

[Nilay Shroff]

On 5/22/26 8:45 PM, Keith Busch wrote:
> diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
> index 263161cb8ac06..435fab0be6401 100644
> --- a/drivers/nvme/host/multipath.c
> +++ b/drivers/nvme/host/multipath.c
> @@ -175,9 +175,11 @@ void nvme_mpath_start_request(struct request *rq)
>   		nvme_req(rq)->flags |= NVME_MPATH_CNT_ACTIVE;
>   	}
>   
> -	if (!blk_queue_io_stat(disk->queue) || blk_rq_is_passthrough(rq) ||
> +	if (!blk_queue_io_stat(disk->queue) ||
>   	    (nvme_req(rq)->flags & NVME_MPATH_IO_STATS))
>   		return;
> +	if (blk_rq_is_passthrough(rq) && !blk_rq_passthrough_stats(rq))
> +		return;
>   
>   	nvme_req(rq)->flags |= NVME_MPATH_IO_STATS;
>   	nvme_req(rq)->start_time = bdev_start_io_acct(disk->part0, req_op(rq),

Thanks for this patch! It will be very useful for nvme top dashboard for
displaying passthru I/O stat under head node.

Well, I see an issue here with @rq being passed to blk_rq_passthrough_stats()
as the @rq->q points to nvme path queue object rather than the head node queue
object. The intention here is to account passthrough I/O statistics at the
head node level, but with the current implementation the decision depends
on the path queue's iostats_passthrough setting instead of the head queue's
setting. As a result, head-node passthrough I/O statistics may get accounted
based on whether the underlying path queue has iostats_passthrough enabled,
irrespective of the head queue configuration.

Another issue is that nvme_mpath_start_request() is only reached from
nvme_start_request() when REQ_NVME_MPATH is set. Normal bio based I/O
through the head gets that flag in nvme_ns_head_submit_bio(), but the
passthrough ioctl/uring path in the quoted patch does not set it. So
head passthrough I/O would not enter nvme_mpath_start_request() and
would not get head-node stats.

Thanks,
--Nilay

Re: [PATCH] block, nvme: export and use passthrough stats

[Christoph Hellwig]

On Fri, May 22, 2026 at 08:15:37AM -0700, Keith Busch wrote:
> From: Keith Busch <kbusch@kernel.org>
> 
> So stacking drivers can also report passthrough workloads through
> iostat.

Except that this patch also wires it up in nvme.  So please split
it and write proper commit messages for both parts.

> +static inline bool blk_rq_passthrough_stats(struct request *req)
> +{

And maybe add a kerneldoc comment now that this is public.

Re: [PATCH] block, nvme: export and use passthrough stats

[Christoph Hellwig]

On Mon, May 25, 2026 at 09:32:19AM +0200, Christoph Hellwig wrote:
> On Fri, May 22, 2026 at 08:15:37AM -0700, Keith Busch wrote:
> > From: Keith Busch <kbusch@kernel.org>
> > 
> > So stacking drivers can also report passthrough workloads through
> > iostat.
> 
> Except that this patch also wires it up in nvme.  So please split
> it and write proper commit messages for both parts.

.. and while we're at it - it actually is called from the lower nvme
drivers, just conditional on being a mpath request.  So this is
in many ways a bit weird, and the comments / commit logs should
probably explain it a bit.

[PATCH] block, nvme: export and use passthrough stats

[Keith Busch]

From: Keith Busch <kbusch@kernel.org>

So stacking drivers can also report passthrough workloads through
iostat.

Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 block/blk-mq.c                | 30 ------------------------------
 drivers/nvme/host/multipath.c |  4 +++-
 include/linux/blk-mq.h        | 29 +++++++++++++++++++++++++++++
 3 files changed, 32 insertions(+), 31 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 28c2d931e75ea..c794b70fefe26 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1088,36 +1088,6 @@ static inline void blk_account_io_done(struct request *req, u64 now)
 	}
 }
 
-static inline bool blk_rq_passthrough_stats(struct request *req)
-{
-	struct bio *bio = req->bio;
-
-	if (!blk_queue_passthrough_stat(req->q))
-		return false;
-
-	/* Requests without a bio do not transfer data. */
-	if (!bio)
-		return false;
-
-	/*
-	 * Stats are accumulated in the bdev, so must have one attached to a
-	 * bio to track stats. Most drivers do not set the bdev for passthrough
-	 * requests, but nvme is one that will set it.
-	 */
-	if (!bio->bi_bdev)
-		return false;
-
-	/*
-	 * We don't know what a passthrough command does, but we know the
-	 * payload size and data direction. Ensuring the size is aligned to the
-	 * block size filters out most commands with payloads that don't
-	 * represent sector access.
-	 */
-	if (blk_rq_bytes(req) & (bdev_logical_block_size(bio->bi_bdev) - 1))
-		return false;
-	return true;
-}
-
 static inline void blk_account_io_start(struct request *req)
 {
 	trace_block_io_start(req);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 263161cb8ac06..435fab0be6401 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -175,9 +175,11 @@ void nvme_mpath_start_request(struct request *rq)
 		nvme_req(rq)->flags |= NVME_MPATH_CNT_ACTIVE;
 	}
 
-	if (!blk_queue_io_stat(disk->queue) || blk_rq_is_passthrough(rq) ||
+	if (!blk_queue_io_stat(disk->queue) ||
 	    (nvme_req(rq)->flags & NVME_MPATH_IO_STATS))
 		return;
+	if (blk_rq_is_passthrough(rq) && !blk_rq_passthrough_stats(rq))
+		return;
 
 	nvme_req(rq)->flags |= NVME_MPATH_IO_STATS;
 	nvme_req(rq)->start_time = bdev_start_io_acct(disk->part0, req_op(rq),
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 18a2388ba581d..8301830ece8b7 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -1243,4 +1243,33 @@ static inline int blk_rq_map_sg(struct request *rq, struct scatterlist *sglist)
 }
 void blk_dump_rq_flags(struct request *, char *);
 
+static inline bool blk_rq_passthrough_stats(struct request *req)
+{
+	struct bio *bio = req->bio;
+
+	if (!blk_queue_passthrough_stat(req->q))
+		return false;
+
+	/* Requests without a bio do not transfer data. */
+	if (!bio)
+		return false;
+
+	/*
+	 * Stats are accumulated in the bdev, so must have one attached to a
+	 * bio to track stats. Most drivers do not set the bdev for passthrough
+	 * requests, but nvme is one that will set it.
+	 */
+	if (!bio->bi_bdev)
+		return false;
+
+	/*
+	 * We don't know what a passthrough command does, but we know the
+	 * payload size and data direction. Ensuring the size is aligned to the
+	 * block size filters out most commands with payloads that don't
+	 * represent sector access.
+	 */
+	if (blk_rq_bytes(req) & (bdev_logical_block_size(bio->bi_bdev) - 1))
+		return false;
+	return true;
+}
 #endif /* BLK_MQ_H */
-- 
2.53.0-Meta

Re: [PATCH] block, nvme: export and use passthrough stats

[Keith Busch]

Sorry, please disregard. I pointed send-email to the v1 directory by
mistake.