All of lore.kernel.org
 help / color / mirror / Atom feed
From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx@lists.freedesktop.org
Subject: [Intel-gfx] [PATCH 28/33] drm/i915/gt: Expose timeslice duration to sysfs
Date: Thu, 12 Dec 2019 14:04:54 +0000	[thread overview]
Message-ID: <20191212140459.1307617-28-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20191212140459.1307617-1-chris@chris-wilson.co.uk>

Execlists uses a scheduling quantum (a timeslice) to alternate execution
between ready-to-run contexts of equal priority. This ensures that all
users (though only if they of equal importance) have the opportunity to
run and prevents livelocks where contexts may have implicit ordering due
to userspace semaphores.

The timeslicing mechanism can be compiled out with

	./scripts/config --set-val DRM_I915_TIMESLICE_DURATION 0

The timeslice duration can be adjusted per-engine using,

	/sys/class/drm/card?/engine/*/timeslice_duration_ms

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/Kconfig.profile         |  3 ++
 drivers/gpu/drm/i915/gt/intel_engine_sysfs.c | 46 ++++++++++++++++++++
 2 files changed, 49 insertions(+)

diff --git a/drivers/gpu/drm/i915/Kconfig.profile b/drivers/gpu/drm/i915/Kconfig.profile
index c280b6ae38eb..d8d4a16179bd 100644
--- a/drivers/gpu/drm/i915/Kconfig.profile
+++ b/drivers/gpu/drm/i915/Kconfig.profile
@@ -73,4 +73,7 @@ config DRM_I915_TIMESLICE_DURATION
 	  is scheduled for execution for the timeslice duration, before
 	  switching to the next context.
 
+	  This is adjustable via
+	  /sys/class/drm/card?/engine/*/timeslice_duration_ms
+
 	  May be 0 to disable timeslicing.
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_sysfs.c b/drivers/gpu/drm/i915/gt/intel_engine_sysfs.c
index abddd8d0f9ae..b1bd768b13d7 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_sysfs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_sysfs.c
@@ -142,6 +142,48 @@ all_caps_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 static struct kobj_attribute all_caps_attr =
 __ATTR(known_capabilities, 0444, all_caps_show, NULL);
 
+static ssize_t
+timeslice_store(struct kobject *kobj, struct kobj_attribute *attr,
+		const char *buf, size_t count)
+{
+	struct intel_engine_cs *engine = kobj_to_engine(kobj);
+	unsigned long long duration;
+	int err;
+
+	/*
+	 * Execlists uses a scheduling quantum (a timeslice) to alternate
+	 * execution between ready-to-run contexts of equal priority. This
+	 * ensures that all users (though only if they of equal importance)
+	 * have the opportunity to run and prevents livelocks where contexts
+	 * may have implicit ordering due to userspace semaphores.
+	 */
+
+	err = kstrtoull(buf, 0, &duration);
+	if (err)
+		return err;
+
+	if (duration > jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT))
+		return -EINVAL;
+
+	WRITE_ONCE(engine->props.timeslice_duration_ms, duration);
+
+	if (execlists_active(&engine->execlists))
+		set_timer_ms(&engine->execlists.timer, duration);
+
+	return count;
+}
+
+static ssize_t
+timeslice_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
+{
+	struct intel_engine_cs *engine = kobj_to_engine(kobj);
+
+	return sprintf(buf, "%lu\n", engine->props.timeslice_duration_ms);
+}
+
+static struct kobj_attribute timeslice_duration_attr =
+__ATTR(timeslice_duration_ms, 0644, timeslice_show, timeslice_store);
+
 static void kobj_engine_release(struct kobject *kobj)
 {
 	kfree(kobj);
@@ -206,6 +248,10 @@ void intel_engines_add_sysfs(struct drm_i915_private *i915)
 		if (sysfs_create_files(kobj, files))
 			goto err_object;
 
+		if (intel_engine_has_timeslices(engine) &&
+		    sysfs_create_file(kobj, &timeslice_duration_attr.attr))
+			goto err_engine;
+
 		if (0) {
 err_object:
 			kobject_put(kobj);
-- 
2.24.0

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply	other threads:[~2019-12-12 14:05 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-12-12 14:04 [Intel-gfx] [PATCH 01/33] drm/i915: Use EAGAIN for trylock failures Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 02/33] drm/i915: Eliminate the trylock for awaiting an earlier request Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 03/33] drm/i915/gt: Eliminate the trylock for reading a timeline's hwsp Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 04/33] drm/i915/uc: Ignore maybe-unused debug-only i915 local Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 05/33] drm/i915/gem: Prepare gen7 cmdparser for async execution Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 06/33] drm/i915/gem: Asynchronous cmdparser Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 07/33] drm/i915/gt: Mark up ips_mchdev pointer access Chris Wilson
2019-12-12 16:39   ` Venkata Sandeep Dhanalakota
2019-12-12 14:04 ` [Intel-gfx] [PATCH 08/33] drm/i915/gt: Mark context->state vma as active while pinned Chris Wilson
2019-12-12 19:55   ` Lionel Landwerlin
2019-12-12 21:35     ` Lionel Landwerlin
2019-12-12 21:46       ` Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 09/33] drm/i915/gt: Mark ring->vma " Chris Wilson
2019-12-12 19:55   ` Lionel Landwerlin
2019-12-12 14:04 ` [Intel-gfx] [PATCH 10/33] drm/i915/selftests: Disable heartbeats around long queues Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 11/33] drm/i915/selftests: Impose a timeout for request submission Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 12/33] drm/i915/gt: Remove direct invocation of breadcrumb signaling Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 13/33] drm/i915: Tweak scheduler's kick_submission() Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 14/33] drm/i915: Flush idle barriers when waiting Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 15/33] drm/i915: Allow userspace to specify ringsize on construction Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 16/33] drm/i915/gem: Honour O_NONBLOCK before throttling execbuf submissions Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 17/33] drm/i915/gt: Teach veng to defer the context allocation Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 18/33] drm/i915: Drop GEM context as a direct link from i915_request Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 19/33] drm/i915: Push the use-semaphore marker onto the intel_context Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 20/33] drm/i915: Remove i915->kernel_context Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 21/33] drm/i915: Move i915_gem_init_contexts() earlier Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 22/33] drm/i915/uc: Use an internal buffer for firmware images Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 23/33] drm/i915/gt: Pull GT initialisation under intel_gt_init() Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 24/33] drm/i915/gt: Pull intel_gt_init_hw() into intel_gt_resume() Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 25/33] drm/i915/gt: Merge engine init/setup loops Chris Wilson
2019-12-12 14:04 ` [Intel-gfx] [PATCH 26/33] drm/i915/gt: Expose engine properties via sysfs Chris Wilson
2020-01-22 21:13   ` [Intel-gfx] [26/33] " Steve Carbonari
2019-12-12 14:04 ` [Intel-gfx] [PATCH 27/33] drm/i915/gt: Expose engine->mmio_base " Chris Wilson
2020-01-22 21:18   ` [Intel-gfx] [27/33] " Steve Carbonari
2019-12-12 14:04 ` Chris Wilson [this message]
2020-01-22 21:25   ` [Intel-gfx] [28/33] drm/i915/gt: Expose timeslice duration to sysfs Steve Carbonari
2019-12-12 14:04 ` [Intel-gfx] [PATCH 29/33] drm/i915/gt: Expose busywait " Chris Wilson
2020-01-22 21:29   ` [Intel-gfx] [29/33] " Steve Carbonari
2019-12-12 14:04 ` [Intel-gfx] [PATCH 30/33] drm/i915/gt: Expose reset stop timeout via sysfs Chris Wilson
2020-01-22 21:34   ` [Intel-gfx] [30/33] " Steve Carbonari
2019-12-12 14:04 ` [Intel-gfx] [PATCH 31/33] drm/i915/gt: Expose preempt reset " Chris Wilson
2020-01-22 21:36   ` [Intel-gfx] [31/33] " Steve Carbonari
2019-12-12 14:04 ` [Intel-gfx] [PATCH 32/33] drm/i915/gt: Expose heartbeat interval " Chris Wilson
2020-01-22 21:38   ` [Intel-gfx] [32/33] " Steve Carbonari
2019-12-12 14:04 ` [Intel-gfx] [PATCH 33/33] HAX: Use aliasing-ppgtt for gen7 Chris Wilson
2019-12-12 18:09 ` [Intel-gfx] ✗ Fi.CI.BUILD: failure for series starting with [01/33] drm/i915: Use EAGAIN for trylock failures Patchwork

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=20191212140459.1307617-28-chris@chris-wilson.co.uk \
    --to=chris@chris-wilson.co.uk \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.