* [PATCH 1/3] nvme: add missing unmaps in nvme_queue_rq
[not found] <1444409756-7317-1-git-send-email-hch@lst.de>
@ 2015-10-09 16:55 ` Christoph Hellwig
2015-10-09 23:46 ` Sagi Grimberg
0 siblings, 1 reply; 3+ messages in thread
From: Christoph Hellwig @ 2015-10-09 16:55 UTC (permalink / raw)
To: Jens Axboe; +Cc: Keith Busch, linux-nvme, stable
When we fail various metadata related operations in nvme_queue_rq we
need to unmap the data SGL.
Cc: stable@vger.kernel.org
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/nvme/host/pci.c | 15 ++++++++++++---
1 file changed, 12 insertions(+), 3 deletions(-)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index a526696..0a85fab 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -904,19 +904,28 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
goto retry_cmd;
}
if (blk_integrity_rq(req)) {
- if (blk_rq_count_integrity_sg(req->q, req->bio) != 1)
+ if (blk_rq_count_integrity_sg(req->q, req->bio) != 1) {
+ dma_unmap_sg(dev->dev, iod->sg, iod->nents,
+ dma_dir);
goto error_cmd;
+ }
sg_init_table(iod->meta_sg, 1);
if (blk_rq_map_integrity_sg(
- req->q, req->bio, iod->meta_sg) != 1)
+ req->q, req->bio, iod->meta_sg) != 1) {
+ dma_unmap_sg(dev->dev, iod->sg, iod->nents,
+ dma_dir);
goto error_cmd;
+ }
if (rq_data_dir(req))
nvme_dif_remap(req, nvme_dif_prep);
- if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg, 1, dma_dir))
+ if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg, 1, dma_dir)) {
+ dma_unmap_sg(dev->dev, iod->sg, iod->nents,
+ dma_dir);
goto error_cmd;
+ }
}
}
--
1.9.1
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH 1/3] nvme: add missing unmaps in nvme_queue_rq
2015-10-09 16:55 ` [PATCH 1/3] nvme: add missing unmaps in nvme_queue_rq Christoph Hellwig
@ 2015-10-09 23:46 ` Sagi Grimberg
2015-10-10 6:55 ` Christoph Hellwig
0 siblings, 1 reply; 3+ messages in thread
From: Sagi Grimberg @ 2015-10-09 23:46 UTC (permalink / raw)
To: Christoph Hellwig, Jens Axboe; +Cc: Keith Busch, stable, linux-nvme
On 10/9/2015 7:55 PM, Christoph Hellwig wrote:
> When we fail various metadata related operations in nvme_queue_rq we
> need to unmap the data SGL.
>
> Cc: stable@vger.kernel.org
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
> drivers/nvme/host/pci.c | 15 ++++++++++++---
> 1 file changed, 12 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
> index a526696..0a85fab 100644
> --- a/drivers/nvme/host/pci.c
> +++ b/drivers/nvme/host/pci.c
> @@ -904,19 +904,28 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
> goto retry_cmd;
> }
> if (blk_integrity_rq(req)) {
> - if (blk_rq_count_integrity_sg(req->q, req->bio) != 1)
> + if (blk_rq_count_integrity_sg(req->q, req->bio) != 1) {
> + dma_unmap_sg(dev->dev, iod->sg, iod->nents,
> + dma_dir);
> goto error_cmd;
> + }
>
> sg_init_table(iod->meta_sg, 1);
> if (blk_rq_map_integrity_sg(
> - req->q, req->bio, iod->meta_sg) != 1)
> + req->q, req->bio, iod->meta_sg) != 1) {
> + dma_unmap_sg(dev->dev, iod->sg, iod->nents,
> + dma_dir);
> goto error_cmd;
> + }
>
> if (rq_data_dir(req))
> nvme_dif_remap(req, nvme_dif_prep);
>
> - if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg, 1, dma_dir))
> + if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg, 1, dma_dir)) {
> + dma_unmap_sg(dev->dev, iod->sg, iod->nents,
> + dma_dir);
> goto error_cmd;
> + }
> }
> }
>
>
Hi Christoph,
Would it be better to unmap the data sg once at error_cmd tag?
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH 1/3] nvme: add missing unmaps in nvme_queue_rq
2015-10-09 23:46 ` Sagi Grimberg
@ 2015-10-10 6:55 ` Christoph Hellwig
0 siblings, 0 replies; 3+ messages in thread
From: Christoph Hellwig @ 2015-10-10 6:55 UTC (permalink / raw)
To: Sagi Grimberg
Cc: Christoph Hellwig, Jens Axboe, Keith Busch, stable, linux-nvme
On Sat, Oct 10, 2015 at 02:46:51AM +0300, Sagi Grimberg wrote:
> Would it be better to unmap the data sg once at error_cmd tag?
We'd need unmap versions of the error_cmd and retry_cmd goto labels,
which was too much churn for this quick fix. Patch 3 now has a single
exit path with a ret variable for the helper this has been factored out
to, so this has been taken care off there.
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2015-10-10 6:55 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
[not found] <1444409756-7317-1-git-send-email-hch@lst.de>
2015-10-09 16:55 ` [PATCH 1/3] nvme: add missing unmaps in nvme_queue_rq Christoph Hellwig
2015-10-09 23:46 ` Sagi Grimberg
2015-10-10 6:55 ` Christoph Hellwig
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).