nvme: Return BLK_STS_TARGET if the DNR bit is set
PATCH 1/1 nvme: Return BLK_STS_TARGET if the DNR bit is set
If the DNR bit is set we should not retry the command, even if the standard status evaluation indicates so.
--- drivers/nvme/host/core.c | 7 +++++++ 1 file changed, 7 insertions(+)
drivers/nvme/host/core.c +7 -0
@@ -279,6 +279,13 @@ void nvme_complete_rq(struct request *req)return ; } } +/* +* Any pathing error might be retried, but the DNR bit takes +* precedence. So return BLK_STS_TARGET if the DNR bit is set +* to avoid retrying. +*/ +if (blk_path_error (status) &&nvme_req (req)->status &NVME_SC_DNR ) + status =BLK_STS_TARGET ;blk_mq_end_request (req, status); }EXPORT_SYMBOL_GPL (nvme_complete_rq);
Signature · 1 line
2.16.4
PATCH 1/1 nvme: Return BLK_STS_TARGET if the DNR bit is set
Quoted 17 lines · Hannes Reinecke
If the DNR bit is set we should not retry the command, even if the standard status evaluation indicates so.
Signed-off-by Hannes Reinecke <hare at suse.com>--- drivers/nvme/host/core.c | 7 +++++++ 1 file changed, 7 insertions(+)drivers/nvme/host/core.c +0
-0@@ -279,6 +279,13 @@ void nvme_complete_rq(struct request *req)return ; } }
drivers/nvme/host/core.c void nvme_complete_rq(struct request *req) · line 291
Quoted 10 lines
drivers/nvme/host/core.c +7
-0+/* +* Any pathing error might be retried, but the DNR bit takes +* precedence. So return BLK_STS_TARGET if the DNR bit is set +* to avoid retrying. +*/ +if (blk_path_error (status) &&nvme_req (req)->status &NVME_SC_DNR ) + status =BLK_STS_TARGET ;blk_mq_end_request (req, status); }EXPORT_SYMBOL_GPL (nvme_complete_rq);
- If DNR always takes precedence, is the blk_path_error() check still needed?
- Can/Should this be done in nvme_error_status()?
Ed
PATCH 1/1 nvme: Return BLK_STS_TARGET if the DNR bit is set
Quoted 23 lines · Edmund
Quoted 22 lines · Hannes Reinecke
If the DNR bit is set we should not retry the command, even if the standard status evaluation indicates so.
Signed-off-by Hannes Reinecke <hare at suse.com>---
?drivers/nvme/host/core.c| 7 +++++++
? 1 file changed, 7 insertions(+)drivers/nvme/host/core.c +6
-0@@ -279,6 +279,13 @@ void nvme_complete_rq(struct request *req) ????????????? return; ????????? } ????? } +??? /* +???? * Any pathing error might be retried, but the DNR bit takes +???? * precedence. So return BLK_STS_TARGET if the DNR bit is set +???? * to avoid retrying. +???? */ +??? if (blk_path_error(status) && nvme_req(req)->status & NVME_SC_DNR)
Quoted 9 lines
drivers/nvme/host/core.c void nvme_complete_rq(struct request *req) · line 291
Quoted 5 lines
drivers/nvme/host/core.c +1
-0+??????? status = BLK_STS_TARGET; ????? blk_mq_end_request(req, status); ? } ? EXPORT_SYMBOL_GPL(nvme_complete_rq);- If DNR always takes precedence, is the
blk_path_error()check still needed?
It takes precedence in the sense that it should cause the command not to be retried. It should not overwrite any error code indicating a non-retryable error.
Quoted 2 lines
- Can/Should this be done in
nvme_error_status()?
Possibly; I don't mind.
Cheers,
Hannes
Signature · 5 lines
Dr. Hannes Reinecke Teamlead Storage & Networking hare at suse.de +49 911 74053 688 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 N?rnberg GF: Felix Imend?rffer, Mary Higgins, Sri Rasiah HRB 21284 (AG N?rnberg)
Keith Busch
maintainerPATCH 1/1 nvme: Return BLK_STS_TARGET if the DNR bit is set
Quoted 33 lines · Hannes Reinecke
Quoted 23 lines · Edmund
Quoted 22 lines · Hannes Reinecke
If the DNR bit is set we should not retry the command, even if the standard status evaluation indicates so.
Signed-off-by Hannes Reinecke <hare at suse.com>---
?drivers/nvme/host/core.c| 7 +++++++
? 1 file changed, 7 insertions(+)drivers/nvme/host/core.c +6
-0@@ -279,6 +279,13 @@ void nvme_complete_rq(struct request *req) ????????????? return; ????????? } ????? } +??? /* +???? * Any pathing error might be retried, but the DNR bit takes +???? * precedence. So return BLK_STS_TARGET if the DNR bit is set +???? * to avoid retrying. +???? */ +??? if (blk_path_error(status) && nvme_req(req)->status & NVME_SC_DNR)Quoted 9 lines
drivers/nvme/host/core.c void nvme_complete_rq(struct request *req) · line 291
Quoted 5 lines
drivers/nvme/host/core.c +1
-0+??????? status = BLK_STS_TARGET; ????? blk_mq_end_request(req, status); ? } ? EXPORT_SYMBOL_GPL(nvme_complete_rq);- If DNR always takes precedence, is the
blk_path_error()check still needed?
Quoted 3 lines
It takes precedence in the sense that it should cause the command not to be retried. It should not overwrite any error code indicating a non-retryable error.
But we're already past the nvme retry logic, which also handles the DNR bit. Who is this telling not to retry?
PATCH 1/1 nvme: Return BLK_STS_TARGET if the DNR bit is set
Quoted 34 lines · Keith Busch
Quoted 33 lines · Hannes Reinecke
Quoted 32 lines · Edmund
Quoted 17 lines · Hannes Reinecke
If the DNR bit is set we should not retry the command, even if the standard status evaluation indicates so.
Signed-off-by Hannes Reinecke <hare at suse.com>--- ? drivers/nvme/host/core.c | 7 +++++++? 1 file changed, 7 insertions(+)
drivers/nvme/host/core.c +0
-0@@ -279,6 +279,13 @@ void nvme_complete_rq(struct request *req) ????????????? return; ????????? } ????? }drivers/nvme/host/core.c void nvme_complete_rq(struct request *req) · line 291
Quoted 10 lines
drivers/nvme/host/core.c +7
-0+??? /* +???? * Any pathing error might be retried, but the DNR bit takes +???? * precedence. So return BLK_STS_TARGET if the DNR bit is set +???? * to avoid retrying. +???? */ +??? if (blk_path_error(status) && nvme_req(req)->status & NVME_SC_DNR) +??????? status = BLK_STS_TARGET; ????? blk_mq_end_request(req, status); ? } ? EXPORT_SYMBOL_GPL(nvme_complete_rq);- If DNR always takes precedence, is the
blk_path_error()check still needed?
Quoted 7 lines
Quoted 3 lines
It takes precedence in the sense that it should cause the command not to be retried. It should not overwrite any error code indicating a non-retryable error.
But we're already past the nvme retry logic, which also handles the DNR bit. Who is this telling not to retry?
Anything layered on top of it, namely dm-multipath or MD.
Cheers,
Hannes
Signature · 5 lines
Dr. Hannes Reinecke Teamlead Storage & Networking hare at suse.de +49 911 74053 688 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 N?rnberg GF: Felix Imend?rffer, Mary Higgins, Sri Rasiah HRB 21284 (AG N?rnberg)
Keith Busch
maintainerPATCH 1/1 nvme: Return BLK_STS_TARGET if the DNR bit is set
Quoted 35 lines · Hannes Reinecke
Quoted 34 lines · Keith Busch
Quoted 33 lines · Hannes Reinecke
Quoted 32 lines · Edmund
Quoted 17 lines · Hannes Reinecke
If the DNR bit is set we should not retry the command, even if the standard status evaluation indicates so.
Signed-off-by Hannes Reinecke <hare at suse.com>--- ? drivers/nvme/host/core.c | 7 +++++++? 1 file changed, 7 insertions(+)
drivers/nvme/host/core.c +0
-0@@ -279,6 +279,13 @@ void nvme_complete_rq(struct request *req) ????????????? return; ????????? } ????? }drivers/nvme/host/core.c void nvme_complete_rq(struct request *req) · line 291
Quoted 10 lines
drivers/nvme/host/core.c +7
-0+??? /* +???? * Any pathing error might be retried, but the DNR bit takes +???? * precedence. So return BLK_STS_TARGET if the DNR bit is set +???? * to avoid retrying. +???? */ +??? if (blk_path_error(status) && nvme_req(req)->status & NVME_SC_DNR) +??????? status = BLK_STS_TARGET; ????? blk_mq_end_request(req, status); ? } ? EXPORT_SYMBOL_GPL(nvme_complete_rq);- If DNR always takes precedence, is the
blk_path_error()check still needed?
Quoted 8 lines
Quoted 7 lines
Quoted 3 lines
It takes precedence in the sense that it should cause the command not to be retried. It should not overwrite any error code indicating a non-retryable error.
But we're already past the nvme retry logic, which also handles the DNR bit. Who is this telling not to retry?
Anything layered on top of it, namely dm-multipath or MD.
Okay, that's what I thought. Can we just move this check to fit in the unlikely() error case just above where you have it?
PATCH 1/1 nvme: Return BLK_STS_TARGET if the DNR bit is set
Quoted 40 lines · Keith Busch
Quoted 39 lines · Hannes Reinecke
Quoted 38 lines · Keith Busch
Quoted 36 lines · Hannes Reinecke
Quoted 23 lines · Edmund
Quoted 22 lines · Hannes Reinecke
If the DNR bit is set we should not retry the command, even if the standard status evaluation indicates so.
Signed-off-by Hannes Reinecke <hare at suse.com>--- ? drivers/nvme/host/core.c | 7 +++++++? 1 file changed, 7 insertions(+)
drivers/nvme/host/core.c +6
-0@@ -279,6 +279,13 @@ void nvme_complete_rq(struct request *req) ????????????? return; ????????? } ????? } +??? /* +???? * Any pathing error might be retried, but the DNR bit takes +???? * precedence. So return BLK_STS_TARGET if the DNR bit is set +???? * to avoid retrying. +???? */ +??? if (blk_path_error(status) && nvme_req(req)->status & NVME_SC_DNR)Quoted 9 lines
drivers/nvme/host/core.c void nvme_complete_rq(struct request *req) · line 291
Quoted 5 lines
drivers/nvme/host/core.c +1
-0+??????? status = BLK_STS_TARGET; ????? blk_mq_end_request(req, status); ? } ? EXPORT_SYMBOL_GPL(nvme_complete_rq);- If DNR always takes precedence, is the
blk_path_error()check still needed?It takes precedence in the sense that it should cause the command not to be retried. It should not overwrite any error code indicating a non-retryable error.
Quoted 8 lines
Quoted 4 lines
Quoted 3 lines
But we're already past the nvme retry logic, which also handles the DNR bit. Who is this telling not to retry?
Anything layered on top of it, namely dm-multipath or MD.
Okay, that's what I thought. Can we just move this check to fit in the
unlikely()error case just above where you have it?
Why, sure, of course.
Will be sending an updated patch.
Cheers,
Hannes
Signature · 5 lines
Dr. Hannes Reinecke Teamlead Storage & Networking hare at suse.de +49 911 74053 688 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 N?rnberg GF: Felix Imend?rffer, Mary Higgins, Sri Rasiah HRB 21284 (AG N?rnberg)