public inbox for linux-nvme@lists.infradead.org
 help / color / mirror / Atom feed
From: John Levon <levon@movementarian.org>
To: Keith Busch <kbusch@kernel.org>
Cc: linux-nvme@lists.infradead.org, hch@lst.de, sagi@grimberg.me
Subject: Re: [PATCHv2 1/2] nvme-pci: clear shadow doorbell memory on resets
Date: Thu, 14 Oct 2021 22:21:25 +0100	[thread overview]
Message-ID: <YWifVXN5cP3JpQ0A@movementarian.org> (raw)
In-Reply-To: <20211014164543.1821327-2-kbusch@kernel.org>

On Thu, Oct 14, 2021 at 09:45:42AM -0700, Keith Busch wrote:

> The host memory doorbell and event buffers need to be initialized on
> each reset so the driver doesn't observe stale values from the previous
> instantiation.
> 
> Signed-off-by: Keith Busch <kbusch@kernel.org>

I reverted our workaround and tried this patch with my simple test case:

mkfs /dev/nvme0n1
echo 1 >/sys/devices/pci0000:00/0000:00:06.0/reset
mkfs /dev/nvme0n1

Works fine where previously it would essentially permanently hang the
controller.

Tested-by: John Levon <john.levon@nutanix.com>

thanks
john

> ---
>  drivers/nvme/host/pci.c | 9 ++++++++-
>  1 file changed, 8 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
> index 0dd4b44b59cd..9dd173bfa57b 100644
> --- a/drivers/nvme/host/pci.c
> +++ b/drivers/nvme/host/pci.c
> @@ -245,8 +245,15 @@ static int nvme_dbbuf_dma_alloc(struct nvme_dev *dev)
>  {
>  	unsigned int mem_size = nvme_dbbuf_size(dev);
>  
> -	if (dev->dbbuf_dbs)
> +	if (dev->dbbuf_dbs) {
> +		/*
> +		 * Clear the dbbuf memory so the driver doesn't observe stale
> +		 * values from the previous instantiation.
> +		 */
> +		memset(dev->dbbuf_dbs, 0, mem_size);
> +		memset(dev->dbbuf_eis, 0, mem_size);
>  		return 0;
> +	}
>  
>  	dev->dbbuf_dbs = dma_alloc_coherent(dev->dev, mem_size,
>  					    &dev->dbbuf_dbs_dma_addr,


  reply	other threads:[~2021-10-14 21:21 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-10-14 16:45 [PATCHv2 0/2] nvme shadow doorbel buf fixes Keith Busch
2021-10-14 16:45 ` [PATCHv2 1/2] nvme-pci: clear shadow doorbell memory on resets Keith Busch
2021-10-14 21:21   ` John Levon [this message]
2021-10-20 17:23   ` Christoph Hellwig
2021-10-14 16:45 ` [PATCHv2 2/2] nvme-pci: remove cached shadow doorbell offsets Keith Busch
2021-10-14 16:53   ` Christoph Hellwig
2021-10-14 17:09   ` John Levon
2021-10-14 17:49     ` Keith Busch
2021-10-14 18:33       ` John Levon

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=YWifVXN5cP3JpQ0A@movementarian.org \
    --to=levon@movementarian.org \
    --cc=hch@lst.de \
    --cc=kbusch@kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=sagi@grimberg.me \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox