From: Dave Gordon <david.s.gordon@intel.com>
To: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>,
Intel-gfx@lists.freedesktop.org
Subject: Re: [PATCH 1/3] drm/i915: Use consistent forcewake auto-release timeout across kernel configs
Date: Mon, 4 Apr 2016 19:58:11 +0100 [thread overview]
Message-ID: <5702B943.9050901@intel.com> (raw)
In-Reply-To: <1459788671-17501-1-git-send-email-tvrtko.ursulin@linux.intel.com>
On 04/04/16 17:51, Tvrtko Ursulin wrote:
> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>
> Current implementation releases the forcewake at any time between
> straight away, and one jiffie from the last put, or first automatic
> grab.
>
> This does not sound like what was desired since jiffies are typically
> between 1 and 10ms depending on the kernel configuration.
>
> Change the auto-release mechanism to use hrtimers and set the timeout
> to 1ms with a 1ms of slack. This should make the GPU power consistent
> across kernel configs and the slack should enable some timer coallescing
"coalescing"
> where multiple force-wake domains exist, or with unrelated timers.
>
> For GlBench/T-Rex this decreases the number of forcewake releases from
> ~480 to ~300 per second, and for a heavy combined OGL/OCL test from
> ~670 to ~360.
>
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
LGTM.
Reviewed-by: Dave Gordon <david.s.gordon@intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 2 +-
> drivers/gpu/drm/i915/intel_uncore.c | 25 ++++++++++++++++---------
> 2 files changed, 17 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index dd187727c813..7d4c704d7d75 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -666,7 +666,7 @@ struct intel_uncore {
> struct drm_i915_private *i915;
> enum forcewake_domain_id id;
> unsigned wake_count;
> - struct timer_list timer;
> + struct hrtimer timer;
> i915_reg_t reg_set;
> u32 val_set;
> u32 val_clear;
> diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
> index ac1c545436af..76ac990de354 100644
> --- a/drivers/gpu/drm/i915/intel_uncore.c
> +++ b/drivers/gpu/drm/i915/intel_uncore.c
> @@ -60,7 +60,11 @@ fw_domain_reset(const struct intel_uncore_forcewake_domain *d)
> static inline void
> fw_domain_arm_timer(struct intel_uncore_forcewake_domain *d)
> {
> - mod_timer_pinned(&d->timer, jiffies + 1);
> + d->wake_count++;
> + hrtimer_start_range_ns(&d->timer,
> + ktime_set(0, NSEC_PER_MSEC),
> + NSEC_PER_MSEC,
> + HRTIMER_MODE_REL);
> }
>
> static inline void
> @@ -224,9 +228,11 @@ static int __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
> return ret;
> }
>
> -static void intel_uncore_fw_release_timer(unsigned long arg)
> +static enum hrtimer_restart
> +intel_uncore_fw_release_timer(struct hrtimer *timer)
> {
> - struct intel_uncore_forcewake_domain *domain = (void *)arg;
> + struct intel_uncore_forcewake_domain *domain =
> + container_of(timer, struct intel_uncore_forcewake_domain, timer);
> unsigned long irqflags;
>
> assert_rpm_device_not_suspended(domain->i915);
> @@ -240,6 +246,8 @@ static void intel_uncore_fw_release_timer(unsigned long arg)
> 1 << domain->id);
>
> spin_unlock_irqrestore(&domain->i915->uncore.lock, irqflags);
> +
> + return HRTIMER_NORESTART;
> }
>
> void intel_uncore_forcewake_reset(struct drm_device *dev, bool restore)
> @@ -259,16 +267,16 @@ void intel_uncore_forcewake_reset(struct drm_device *dev, bool restore)
> active_domains = 0;
>
> for_each_fw_domain(domain, dev_priv, id) {
> - if (del_timer_sync(&domain->timer) == 0)
> + if (hrtimer_cancel(&domain->timer) == 0)
> continue;
>
> - intel_uncore_fw_release_timer((unsigned long)domain);
> + intel_uncore_fw_release_timer(&domain->timer);
> }
>
> spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
>
> for_each_fw_domain(domain, dev_priv, id) {
> - if (timer_pending(&domain->timer))
> + if (hrtimer_active(&domain->timer))
> active_domains |= (1 << id);
> }
>
> @@ -491,7 +499,6 @@ static void __intel_uncore_forcewake_put(struct drm_i915_private *dev_priv,
> if (--domain->wake_count)
> continue;
>
> - domain->wake_count++;
> fw_domain_arm_timer(domain);
> }
> }
> @@ -732,7 +739,6 @@ static inline void __force_wake_auto(struct drm_i915_private *dev_priv,
> continue;
> }
>
> - domain->wake_count++;
> fw_domain_arm_timer(domain);
> }
>
> @@ -1150,7 +1156,8 @@ static void fw_domain_init(struct drm_i915_private *dev_priv,
> d->i915 = dev_priv;
> d->id = domain_id;
>
> - setup_timer(&d->timer, intel_uncore_fw_release_timer, (unsigned long)d);
> + hrtimer_init(&d->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
> + d->timer.function = intel_uncore_fw_release_timer;
>
> dev_priv->uncore.fw_domains |= (1 << domain_id);
>
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2016-04-04 18:58 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-04-04 16:51 [PATCH 1/3] drm/i915: Use consistent forcewake auto-release timeout across kernel configs Tvrtko Ursulin
2016-04-04 16:51 ` [PATCH 2/3] drm/i915: Simplify for_each_fw_domain iterators Tvrtko Ursulin
2016-04-04 19:00 ` Chris Wilson
2016-04-04 19:14 ` Dave Gordon
2016-04-05 9:05 ` Tvrtko Ursulin
2016-04-05 9:36 ` Chris Wilson
2016-04-04 16:51 ` [PATCH 3/3] drm/i915: Do not serialize forcewake acquire across domains Tvrtko Ursulin
2016-04-04 19:07 ` Chris Wilson
2016-04-05 9:02 ` Tvrtko Ursulin
2016-04-05 9:47 ` Chris Wilson
2016-04-04 18:58 ` [PATCH 1/3] drm/i915: Use consistent forcewake auto-release timeout across kernel configs Chris Wilson
2016-04-04 19:41 ` Dave Gordon
2016-04-04 20:22 ` Chris Wilson
2016-04-05 8:54 ` Tvrtko Ursulin
2016-04-05 8:59 ` Chris Wilson
2016-04-05 10:02 ` Tvrtko Ursulin
2016-04-05 10:44 ` Chris Wilson
2016-04-04 18:58 ` Dave Gordon [this message]
2016-04-05 6:26 ` ✗ Fi.CI.BAT: failure for series starting with [1/3] " Patchwork
2016-04-05 11:01 ` [PATCH v2 1/3] " Tvrtko Ursulin
2016-04-05 11:01 ` [PATCH v2 2/3] drm/i915: Simplify for_each_fw_domain iterators Tvrtko Ursulin
2016-04-05 11:01 ` [PATCH v2 3/3] drm/i915: Do not serialize forcewake acquire across domains Tvrtko Ursulin
2016-04-05 11:22 ` [PATCH v2 1/3] drm/i915: Use consistent forcewake auto-release timeout across kernel configs 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=5702B943.9050901@intel.com \
--to=david.s.gordon@intel.com \
--cc=Intel-gfx@lists.freedesktop.org \
--cc=tvrtko.ursulin@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