intel-gfx.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
To: Chris Wilson <chris@chris-wilson.co.uk>, intel-gfx@lists.freedesktop.org
Cc: Lionel Landwerlin <lionel.g.landwerlin@linux.intel.com>,
	Daniel Vetter <daniel.vetter@ffwll.ch>
Subject: Re: [PATCH 07/15] drm/i915: Check the timeout passed to i915_wait_request
Date: Mon, 30 Nov 2015 10:14:04 +0000	[thread overview]
Message-ID: <565C216C.60505@linux.intel.com> (raw)
In-Reply-To: <1448786893-2522-8-git-send-email-chris@chris-wilson.co.uk>


On 29/11/15 08:48, Chris Wilson wrote:
> We have relied upon the sole caller (wait_ioctl) validating the timeout
> argument. However, when waiting for multiple requests I forgot to ensure
> that the timeout was still positive on the later requests. This is more
> simply done inside __i915_wait_request.

As discussed on IRC please mention that the extra jiffie happens because 
nsecs_to_jiffies_timeout adds it. Otherwise it is not immediately clear 
why would it wait an extra one since __i915_wait_request has explicit 
code to ensure timeout does not go negative already.

With that clarified,

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Regards,

Tvrtko

> Fixes a minor regression introduced in
>
> commit b47161858ba13c9c7e03333132230d66e008dd55
> Author: Chris Wilson <chris@chris-wilson.co.uk>
> Date:   Mon Apr 27 13:41:17 2015 +0100
>
>      drm/i915: Implement inter-engine read-read optimisations
>
> where we may end up waiting for an extra jiffie for each active ring
> after consuming all of the user's timeout.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Lionel Landwerlin <lionel.g.landwerlin@linux.intel.com>
> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
> ---
>   drivers/gpu/drm/i915/i915_gem.c | 12 ++++++++++--
>   1 file changed, 10 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index f33c35c6130f..65d101b47d8e 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -1251,8 +1251,16 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
>   	if (i915_gem_request_completed(req, true))
>   		return 0;
>
> -	timeout_expire = timeout ?
> -		jiffies + nsecs_to_jiffies_timeout((u64)*timeout) : 0;
> +	timeout_expire = 0;
> +	if (timeout) {
> +		if (WARN_ON(*timeout < 0))
> +			return -EINVAL;
> +
> +		if (*timeout == 0)
> +			return -ETIME;
> +
> +		timeout_expire = jiffies + nsecs_to_jiffies_timeout(*timeout);
> +	}
>
>   	if (INTEL_INFO(dev_priv)->gen >= 6)
>   		gen6_rps_boost(dev_priv, rps, req->emitted_jiffies);
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

  reply	other threads:[~2015-11-30 10:14 UTC|newest]

Thread overview: 92+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-11-29  8:47 i915_wait_request scaling Chris Wilson
2015-11-29  8:47 ` [PATCH 01/15] drm/i915: Break busywaiting for requests on pending signals Chris Wilson
2015-11-30 10:01   ` Tvrtko Ursulin
2015-11-29  8:48 ` [PATCH 02/15] drm/i915: Limit the busy wait on requests to 10us not 10ms! Chris Wilson
2015-11-30 10:02   ` Tvrtko Ursulin
2015-11-30 10:08     ` Chris Wilson
2015-11-29  8:48 ` [PATCH 03/15] drm/i915: Only spin whilst waiting on the current request Chris Wilson
2015-11-30 10:06   ` Tvrtko Ursulin
2015-12-01 15:47     ` Dave Gordon
2015-12-01 15:58       ` Chris Wilson
2015-12-01 16:44         ` Dave Gordon
2015-12-03  8:52           ` Daniel Vetter
2015-11-29  8:48 ` [PATCH 04/15] drm/i915: Cache the reset_counter for the request Chris Wilson
2015-12-01  8:31   ` Daniel Vetter
2015-12-01  8:47     ` Chris Wilson
2015-12-01  9:15       ` Chris Wilson
2015-12-01 11:05         ` [PATCH 1/3] drm/i915: Hide the atomic_read(reset_counter) behind a helper Chris Wilson
2015-12-01 11:05           ` [PATCH 2/3] drm/i915: Store the reset counter when constructing a request Chris Wilson
2015-12-03  8:59             ` Daniel Vetter
2015-12-01 11:05           ` [PATCH 3/3] drm/i915: Prevent leaking of -EIO from i915_wait_request() Chris Wilson
2015-12-03  9:14             ` Daniel Vetter
2015-12-03  9:41               ` Chris Wilson
2015-12-11  9:02               ` Chris Wilson
2015-12-11 16:46                 ` Daniel Vetter
2015-12-03  8:57           ` [PATCH 1/3] drm/i915: Hide the atomic_read(reset_counter) behind a helper Daniel Vetter
2015-12-03  9:02             ` Chris Wilson
2015-12-03  9:20               ` Daniel Vetter
2015-11-29  8:48 ` [PATCH 05/15] drm/i915: Suppress error message when GPU resets are disabled Chris Wilson
2015-12-01  8:30   ` Daniel Vetter
2015-11-29  8:48 ` [PATCH 06/15] drm/i915: Delay queuing hangcheck to wait-request Chris Wilson
2015-11-29  8:48 ` [PATCH 07/15] drm/i915: Check the timeout passed to i915_wait_request Chris Wilson
2015-11-30 10:14   ` Tvrtko Ursulin [this message]
2015-11-30 10:19     ` Chris Wilson
2015-11-30 10:27       ` Tvrtko Ursulin
2015-11-30 10:22   ` Chris Wilson
2015-11-30 10:28     ` Tvrtko Ursulin
2015-11-29  8:48 ` [PATCH 08/15] drm/i915: Slaughter the thundering i915_wait_request herd Chris Wilson
2015-11-30 10:53   ` Chris Wilson
2015-11-30 12:09     ` Tvrtko Ursulin
2015-11-30 12:38       ` Chris Wilson
2015-11-30 13:33         ` Tvrtko Ursulin
2015-11-30 14:30           ` Chris Wilson
2015-11-30 12:05   ` Tvrtko Ursulin
2015-11-30 12:30     ` Chris Wilson
2015-11-30 13:32       ` Tvrtko Ursulin
2015-11-30 14:18         ` Chris Wilson
2015-12-01 17:06           ` Dave Gordon
2015-11-30 14:26         ` Chris Wilson
2015-11-30 14:34   ` [PATCH v4] " Chris Wilson
2015-11-30 16:30     ` Chris Wilson
2015-11-30 16:40       ` Chris Wilson
2015-12-01 18:34     ` Dave Gordon
2015-12-03 16:22       ` [PATCH v7] " Chris Wilson
2015-12-07 15:08         ` Tvrtko Ursulin
2015-12-08 10:44           ` Chris Wilson
2015-12-08 14:03             ` Tvrtko Ursulin
2015-12-08 14:33               ` Chris Wilson
2015-11-23 11:34                 ` [RFC 00/12] Convert requests to use struct fence John.C.Harrison
2015-11-23 11:34                   ` [RFC 01/12] staging/android/sync: Support sync points created from dma-fences John.C.Harrison
2015-11-23 13:29                     ` Maarten Lankhorst
2015-11-23 13:31                     ` [Intel-gfx] " Tvrtko Ursulin
2015-11-23 11:34                   ` [RFC 02/12] staging/android/sync: add sync_fence_create_dma John.C.Harrison
2015-11-23 13:27                     ` Maarten Lankhorst
2015-11-23 13:38                       ` John Harrison
2015-11-23 13:44                         ` Tvrtko Ursulin
2015-11-23 13:48                           ` Maarten Lankhorst
2015-11-23 11:34                   ` [RFC 03/12] staging/android/sync: Move sync framework out of staging John.C.Harrison
2015-11-23 11:34                   ` [RFC 04/12] drm/i915: Convert requests to use struct fence John.C.Harrison
2015-11-23 11:34                   ` [RFC 05/12] drm/i915: Removed now redudant parameter to i915_gem_request_completed() John.C.Harrison
2015-11-23 11:34                   ` [RFC 06/12] drm/i915: Add per context timelines to fence object John.C.Harrison
2015-11-23 11:34                   ` [RFC 07/12] drm/i915: Delay the freeing of requests until retire time John.C.Harrison
2015-11-23 11:34                   ` [RFC 08/12] drm/i915: Interrupt driven fences John.C.Harrison
2015-12-11 12:17                     ` Tvrtko Ursulin
2015-11-23 11:34                   ` [RFC 09/12] drm/i915: Updated request structure tracing John.C.Harrison
2015-11-23 11:34                   ` [RFC 10/12] android/sync: Fix reversed sense of signaled fence John.C.Harrison
2015-11-23 11:34                   ` [RFC 11/12] drm/i915: Add sync framework support to execbuff IOCTL John.C.Harrison
2015-11-23 11:34                   ` [RFC 12/12] drm/i915: Cache last IRQ seqno to reduce IRQ overhead John.C.Harrison
2015-11-23 11:38                   ` [RFC 00/12] Convert requests to use struct fence John Harrison
2015-12-08 14:53                   ` [PATCH v7] drm/i915: Slaughter the thundering i915_wait_request herd Dave Gordon
2015-11-30 15:45   ` [PATCH] drm/i915: Convert trace-irq to the breadcrumb waiter Chris Wilson
2015-11-29  8:48 ` [PATCH 09/15] drm/i915: Separate out the seqno-barrier from engine->get_seqno Chris Wilson
2015-11-29  8:48 ` [PATCH 10/15] drm/i915: Remove the lazy_coherency parameter from request-completed? Chris Wilson
2015-11-29  8:48 ` [PATCH 11/15] drm/i915: Use HWS for seqno tracking everywhere Chris Wilson
2015-11-29  8:48 ` [PATCH 12/15] drm/i915: Reduce seqno/irq barrier to a clflush on legacy gen6+ Chris Wilson
2015-11-29  8:48 ` [PATCH 13/15] drm/i915: Stop setting wraparound seqno on initialisation Chris Wilson
2015-12-01 16:57   ` Dave Gordon
2015-12-04  9:36     ` Daniel Vetter
2015-12-04  9:51       ` Chris Wilson
2015-11-29  8:48 ` [PATCH 14/15] drm/i915: Only query timestamp when measuring elapsed time Chris Wilson
2015-11-30 10:19   ` Tvrtko Ursulin
2015-11-30 14:31     ` Chris Wilson
2015-11-29  8:48 ` [PATCH 15/15] drm/i915: On GPU reset, set the HWS breadcrumb to the last seqno Chris Wilson

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=565C216C.60505@linux.intel.com \
    --to=tvrtko.ursulin@linux.intel.com \
    --cc=chris@chris-wilson.co.uk \
    --cc=daniel.vetter@ffwll.ch \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=lionel.g.landwerlin@linux.intel.com \
    /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;
as well as URLs for NNTP newsgroup(s).