public inbox for intel-gfx@lists.freedesktop.org
 help / color / mirror / Atom feed
From: "Ville Syrjälä" <ville.syrjala@linux.intel.com>
To: intel-gfx@lists.freedesktop.org
Subject: Re: [PATCH] drm/i915: Unpin last_context at reset
Date: Mon, 23 Jun 2014 13:07:50 +0300	[thread overview]
Message-ID: <20140623100750.GU27580@intel.com> (raw)
In-Reply-To: <1403118289-19550-1-git-send-email-ville.syrjala@linux.intel.com>

On Wed, Jun 18, 2014 at 10:04:48PM +0300, ville.syrjala@linux.intel.com wrote:
> From: Ville Syrjälä <ville.syrjala@linux.intel.com>
> 
> We're forgetting to unpin the last_context from the ggtt at GPU reset
> time. This leads to the vma pin_count leaking at every reset if the
> last context wasn't the ring default context. Further use of the same
> context will trigger the pin_count check in i915_gem_object_pin() and
> userspace will be faced with EBUSY as a result.
> 
> This plaques kms_flip rather badly since it performs lots of resets,
> and every fd has its own default context these days.
> 
> Fix the problem by properly unpinning the last context at reset.
> 
> Testcase: igt/gem_ctx_exec/reset-pin-leak
> Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>

I pushed the igt, and also kms_flip hits this easily.

It looks to me that the bug has been there since the introduction of
i915_gem_context_reset() in [1], so I think we may want this patch
merged with cc: stable. Afterwards people can work on killing
i915_gem_context_reset() if they so wish.

[1]
 commit acce9ffa4807027965ebd948456fa8385bbee32e
 Author: Ben Widawsky <ben@bwidawsk.net>
 Date:   Fri Dec 6 14:11:03 2013 -0800

    drm/i915: Better reset handling for contexts

> ---
>  drivers/gpu/drm/i915/i915_gem_context.c | 3 +++
>  1 file changed, 3 insertions(+)
> 
> diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
> index 3ffe308..e362c96 100644
> --- a/drivers/gpu/drm/i915/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/i915_gem_context.c
> @@ -382,6 +382,9 @@ void i915_gem_context_reset(struct drm_device *dev)
>  			dctx->obj->active = 0;
>  		}
>  
> +		if (ring->last_context->obj && i == RCS)
> +			i915_gem_object_ggtt_unpin(ring->last_context->obj);
> +
>  		i915_gem_context_unreference(ring->last_context);
>  		i915_gem_context_reference(dctx);
>  		ring->last_context = dctx;
> -- 
> 1.8.5.5

-- 
Ville Syrjälä
Intel OTC

  parent reply	other threads:[~2014-06-23 10:10 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-06-18 19:04 [PATCH] drm/i915: Unpin last_context at reset ville.syrjala
2014-06-18 19:04 ` [PATCH igt] tests/gem_ctx_exec: Add reset-pin-leak subtest ville.syrjala
2014-06-19  7:47 ` [PATCH] drm/i915: Unpin last_context at reset Chris Wilson
2014-06-19 16:21   ` Mateo Lozano, Oscar
2014-06-23 10:07 ` Ville Syrjälä [this message]
2014-07-07 14:38   ` Daniel Vetter

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=20140623100750.GU27580@intel.com \
    --to=ville.syrjala@linux.intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    /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