* [BACKPORT PATCH] nvme-pci: Remap CMB SQ entries on every controller reset
@ 2018-07-12 21:27 Scott Bauer
2018-07-12 22:14 ` Derrick, Jonathan
` (2 more replies)
0 siblings, 3 replies; 5+ messages in thread
From: Scott Bauer @ 2018-07-12 21:27 UTC (permalink / raw)
To: stable; +Cc: Scott Bauer, Jon Derrick, Keith Busch
Commit 815c6704bf9f1c59f3a6be380a4032b9c57b12f1 upstream.
The controller memory buffer is remapped into a kernel address on each
reset, but the driver was setting the submission queue base address
only on the very first queue creation. The remapped address is likely to
change after a reset, so accessing the old address will hit a kernel bug.
This patch fixes that by setting the queue's CMB base address each time
the queue is created.
Fixes: f63572dff1421 ("nvme: unmap CMB and remove sysfs file in reset path")
Reported-by: Christian Black <christian.d.black@intel.com>
Cc: Jon Derrick <jonathan.derrick@intel.com>
Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Scott Bauer <scott.bauer@intel.com>
---
drivers/nvme/host/pci.c | 27 ++++++++++++++++-----------
1 file changed, 16 insertions(+), 11 deletions(-)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 3d4724e38aa9..4cac4755abef 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1233,17 +1233,15 @@ static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
int qid, int depth)
{
- if (qid && dev->cmb && use_cmb_sqes && NVME_CMB_SQS(dev->cmbsz)) {
- unsigned offset = (qid - 1) * roundup(SQ_SIZE(depth),
- dev->ctrl.page_size);
- nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset;
- nvmeq->sq_cmds_io = dev->cmb + offset;
- } else {
- nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
- &nvmeq->sq_dma_addr, GFP_KERNEL);
- if (!nvmeq->sq_cmds)
- return -ENOMEM;
- }
+
+ /* CMB SQEs will be mapped before creation */
+ if (qid && dev->cmb && use_cmb_sqes && NVME_CMB_SQS(dev->cmbsz))
+ return 0;
+
+ nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
+ &nvmeq->sq_dma_addr, GFP_KERNEL);
+ if (!nvmeq->sq_cmds)
+ return -ENOMEM;
return 0;
}
@@ -1320,6 +1318,13 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
struct nvme_dev *dev = nvmeq->dev;
int result;
+ if (qid && dev->cmb && use_cmb_sqes && NVME_CMB_SQS(dev->cmbsz)) {
+ unsigned offset = (qid - 1) * roundup(SQ_SIZE(nvmeq->q_depth),
+ dev->ctrl.page_size);
+ nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset;
+ nvmeq->sq_cmds_io = dev->cmb + offset;
+ }
+
nvmeq->cq_vector = qid - 1;
result = adapter_alloc_cq(dev, qid, nvmeq);
if (result < 0)
--
2.17.1
^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [BACKPORT PATCH] nvme-pci: Remap CMB SQ entries on every controller reset
2018-07-12 21:27 [BACKPORT PATCH] nvme-pci: Remap CMB SQ entries on every controller reset Scott Bauer
@ 2018-07-12 22:14 ` Derrick, Jonathan
2018-07-13 12:01 ` Greg KH
2018-07-15 10:21 ` Greg KH
2 siblings, 0 replies; 5+ messages in thread
From: Derrick, Jonathan @ 2018-07-12 22:14 UTC (permalink / raw)
To: Bauer, Scott, stable; +Cc: Busch, Keith
[-- Attachment #1: Type: text/plain, Size: 2853 bytes --]
Thank you, Scott
Reviewed-by: Jon Derrick <jonathan.derrick@intel.com>
On Thu, 2018-07-12 at 15:27 -0600, Scott Bauer wrote:
> Commit 815c6704bf9f1c59f3a6be380a4032b9c57b12f1 upstream.
>
> The controller memory buffer is remapped into a kernel address on
> each
> reset, but the driver was setting the submission queue base address
> only on the very first queue creation. The remapped address is likely
> to
> change after a reset, so accessing the old address will hit a kernel
> bug.
>
> This patch fixes that by setting the queue's CMB base address each
> time
> the queue is created.
>
> Fixes: f63572dff1421 ("nvme: unmap CMB and remove sysfs file in reset
> path")
> Reported-by: Christian Black <christian.d.black@intel.com>
> Cc: Jon Derrick <jonathan.derrick@intel.com>
> Signed-off-by: Keith Busch <keith.busch@intel.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> Signed-off-by: Scott Bauer <scott.bauer@intel.com>
> ---
> drivers/nvme/host/pci.c | 27 ++++++++++++++++-----------
> 1 file changed, 16 insertions(+), 11 deletions(-)
>
> diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
> index 3d4724e38aa9..4cac4755abef 100644
> --- a/drivers/nvme/host/pci.c
> +++ b/drivers/nvme/host/pci.c
> @@ -1233,17 +1233,15 @@ static int nvme_cmb_qdepth(struct nvme_dev
> *dev, int nr_io_queues,
> static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct
> nvme_queue *nvmeq,
> int qid, int depth)
> {
> - if (qid && dev->cmb && use_cmb_sqes && NVME_CMB_SQS(dev-
> >cmbsz)) {
> - unsigned offset = (qid - 1) *
> roundup(SQ_SIZE(depth),
> - dev-
> >ctrl.page_size);
> - nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset;
> - nvmeq->sq_cmds_io = dev->cmb + offset;
> - } else {
> - nvmeq->sq_cmds = dma_alloc_coherent(dev->dev,
> SQ_SIZE(depth),
> - &nvmeq->sq_dma_addr,
> GFP_KERNEL);
> - if (!nvmeq->sq_cmds)
> - return -ENOMEM;
> - }
> +
> + /* CMB SQEs will be mapped before creation */
> + if (qid && dev->cmb && use_cmb_sqes && NVME_CMB_SQS(dev-
> >cmbsz))
> + return 0;
> +
> + nvmeq->sq_cmds = dma_alloc_coherent(dev->dev,
> SQ_SIZE(depth),
> + &nvmeq->sq_dma_addr,
> GFP_KERNEL);
> + if (!nvmeq->sq_cmds)
> + return -ENOMEM;
>
> return 0;
> }
> @@ -1320,6 +1318,13 @@ static int nvme_create_queue(struct nvme_queue
> *nvmeq, int qid)
> struct nvme_dev *dev = nvmeq->dev;
> int result;
>
> + if (qid && dev->cmb && use_cmb_sqes && NVME_CMB_SQS(dev-
> >cmbsz)) {
> + unsigned offset = (qid - 1) * roundup(SQ_SIZE(nvmeq-
> >q_depth),
> + dev-
> >ctrl.page_size);
> + nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset;
> + nvmeq->sq_cmds_io = dev->cmb + offset;
> + }
> +
> nvmeq->cq_vector = qid - 1;
> result = adapter_alloc_cq(dev, qid, nvmeq);
> if (result < 0)
[-- Attachment #2: smime.p7s --]
[-- Type: application/x-pkcs7-signature, Size: 3278 bytes --]
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [BACKPORT PATCH] nvme-pci: Remap CMB SQ entries on every controller reset
2018-07-12 21:27 [BACKPORT PATCH] nvme-pci: Remap CMB SQ entries on every controller reset Scott Bauer
2018-07-12 22:14 ` Derrick, Jonathan
@ 2018-07-13 12:01 ` Greg KH
2018-07-13 15:51 ` Keith Busch
2018-07-15 10:21 ` Greg KH
2 siblings, 1 reply; 5+ messages in thread
From: Greg KH @ 2018-07-13 12:01 UTC (permalink / raw)
To: Scott Bauer; +Cc: stable, Jon Derrick, Keith Busch
On Thu, Jul 12, 2018 at 03:27:17PM -0600, Scott Bauer wrote:
> Commit 815c6704bf9f1c59f3a6be380a4032b9c57b12f1 upstream.
>
> The controller memory buffer is remapped into a kernel address on each
> reset, but the driver was setting the submission queue base address
> only on the very first queue creation. The remapped address is likely to
> change after a reset, so accessing the old address will hit a kernel bug.
>
> This patch fixes that by setting the queue's CMB base address each time
> the queue is created.
>
> Fixes: f63572dff1421 ("nvme: unmap CMB and remove sysfs file in reset path")
> Reported-by: Christian Black <christian.d.black@intel.com>
> Cc: Jon Derrick <jonathan.derrick@intel.com>
> Signed-off-by: Keith Busch <keith.busch@intel.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> Signed-off-by: Scott Bauer <scott.bauer@intel.com>
> Reviewed-by: Jon Derrick <jonathan.derrick@intel.com>
> ---
> drivers/nvme/host/pci.c | 27 ++++++++++++++++-----------
> 1 file changed, 16 insertions(+), 11 deletions(-)
"backport" to where? What kernel tree(s) do you want this applied to?
I need a hint please...
thanks,
greg k-h
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [BACKPORT PATCH] nvme-pci: Remap CMB SQ entries on every controller reset
2018-07-13 12:01 ` Greg KH
@ 2018-07-13 15:51 ` Keith Busch
0 siblings, 0 replies; 5+ messages in thread
From: Keith Busch @ 2018-07-13 15:51 UTC (permalink / raw)
To: Greg KH; +Cc: Scott Bauer, stable, Jon Derrick
On Fri, Jul 13, 2018 at 02:01:04PM +0200, Greg KH wrote:
> On Thu, Jul 12, 2018 at 03:27:17PM -0600, Scott Bauer wrote:
> > Commit 815c6704bf9f1c59f3a6be380a4032b9c57b12f1 upstream.
> >
> > The controller memory buffer is remapped into a kernel address on each
> > reset, but the driver was setting the submission queue base address
> > only on the very first queue creation. The remapped address is likely to
> > change after a reset, so accessing the old address will hit a kernel bug.
> >
> > This patch fixes that by setting the queue's CMB base address each time
> > the queue is created.
> >
> > Fixes: f63572dff1421 ("nvme: unmap CMB and remove sysfs file in reset path")
> > Reported-by: Christian Black <christian.d.black@intel.com>
> > Cc: Jon Derrick <jonathan.derrick@intel.com>
> > Signed-off-by: Keith Busch <keith.busch@intel.com>
> > Reviewed-by: Christoph Hellwig <hch@lst.de>
> > Signed-off-by: Scott Bauer <scott.bauer@intel.com>
> > Reviewed-by: Jon Derrick <jonathan.derrick@intel.com>
> > ---
> > drivers/nvme/host/pci.c | 27 ++++++++++++++++-----------
> > 1 file changed, 16 insertions(+), 11 deletions(-)
>
> "backport" to where? What kernel tree(s) do you want this applied to?
>
> I need a hint please...
Sorry about that. 4.9 and 4.14 are the applicable targets.
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [BACKPORT PATCH] nvme-pci: Remap CMB SQ entries on every controller reset
2018-07-12 21:27 [BACKPORT PATCH] nvme-pci: Remap CMB SQ entries on every controller reset Scott Bauer
2018-07-12 22:14 ` Derrick, Jonathan
2018-07-13 12:01 ` Greg KH
@ 2018-07-15 10:21 ` Greg KH
2 siblings, 0 replies; 5+ messages in thread
From: Greg KH @ 2018-07-15 10:21 UTC (permalink / raw)
To: Scott Bauer; +Cc: stable, Jon Derrick, Keith Busch
On Thu, Jul 12, 2018 at 03:27:17PM -0600, Scott Bauer wrote:
> Commit 815c6704bf9f1c59f3a6be380a4032b9c57b12f1 upstream.
>
> The controller memory buffer is remapped into a kernel address on each
> reset, but the driver was setting the submission queue base address
> only on the very first queue creation. The remapped address is likely to
> change after a reset, so accessing the old address will hit a kernel bug.
>
> This patch fixes that by setting the queue's CMB base address each time
> the queue is created.
>
> Fixes: f63572dff1421 ("nvme: unmap CMB and remove sysfs file in reset path")
> Reported-by: Christian Black <christian.d.black@intel.com>
> Cc: Jon Derrick <jonathan.derrick@intel.com>
> Signed-off-by: Keith Busch <keith.busch@intel.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> Signed-off-by: Scott Bauer <scott.bauer@intel.com>
> Reviewed-by: Jon Derrick <jonathan.derrick@intel.com>
> ---
> drivers/nvme/host/pci.c | 27 ++++++++++++++++-----------
> 1 file changed, 16 insertions(+), 11 deletions(-)
Now queued up, thanks.
greg k-h
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2018-07-15 10:43 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-07-12 21:27 [BACKPORT PATCH] nvme-pci: Remap CMB SQ entries on every controller reset Scott Bauer
2018-07-12 22:14 ` Derrick, Jonathan
2018-07-13 12:01 ` Greg KH
2018-07-13 15:51 ` Keith Busch
2018-07-15 10:21 ` Greg KH
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.