[PATCH 32/40] drm/i915/gt: Expose preempt reset timeout via sysfs

[Chris Wilson]

After initialising a preemption request, we give the current resident a
small amount of time to vacate the GPU. The preemption request is for a
higher priority context and should be immediate to maintain high
quality of service (and avoid priority inversion). However, the
preemption granularity of the GPU can be quite coarse and so we need a
compromise.

The preempt timeout can be adjusted per-engine using,

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

and can be disabled by setting it to 0.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/Kconfig.profile         |  3 ++
 drivers/gpu/drm/i915/gt/intel_engine_sysfs.c | 48 ++++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_lrc.c          |  2 +-
 3 files changed, 52 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/Kconfig.profile b/drivers/gpu/drm/i915/Kconfig.profile
index d0fece34933b..233bcdb6a6ca 100644
--- a/drivers/gpu/drm/i915/Kconfig.profile
+++ b/drivers/gpu/drm/i915/Kconfig.profile
@@ -33,6 +33,9 @@ config DRM_I915_PREEMPT_TIMEOUT
 	  expires, the HW will be reset to allow the more important context
 	  to execute.
 
+	  This is adjustable via
+	  /sys/class/drm/card?/engine/*/preempt_timeout_ms
+
 	  May be 0 to disable the timeout.
 
 config DRM_I915_MAX_REQUEST_BUSYWAIT
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_sysfs.c b/drivers/gpu/drm/i915/gt/intel_engine_sysfs.c
index 2b65fed76435..d299c66cf7ec 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_sysfs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_sysfs.c
@@ -271,6 +271,50 @@ stop_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 static struct kobj_attribute stop_timeout_attr =
 __ATTR(stop_timeout_ms, 0644, stop_show, stop_store);
 
+static ssize_t
+preempt_timeout_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 timeout;
+	int err;
+
+	/*
+	 * After initialising a preemption request, we give the current
+	 * resident a small amount of time to vacate the GPU. The preemption
+	 * request is for a higher priority context and should be immediate to
+	 * maintain high quality of service (and avoid priority inversion).
+	 * However, the preemption granularity of the GPU can be quite coarse
+	 * and so we need a compromise.
+	 */
+
+	err = kstrtoull(buf, 0, &timeout);
+	if (err)
+		return err;
+
+	if (timeout > jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT))
+		return -EINVAL;
+
+	WRITE_ONCE(engine->props.preempt_timeout_ms, timeout);
+
+	if (READ_ONCE(engine->execlists.pending[0]))
+		set_timer_ms(&engine->execlists.preempt, timeout);
+
+	return count;
+}
+
+static ssize_t
+preempt_timeout_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.preempt_timeout_ms);
+}
+
+static struct kobj_attribute preempt_timeout_attr =
+__ATTR(preempt_timeout_ms, 0644, preempt_timeout_show, preempt_timeout_store);
+
 static void kobj_engine_release(struct kobject *kobj)
 {
 	kfree(kobj);
@@ -341,6 +385,10 @@ void intel_engines_add_sysfs(struct drm_i915_private *i915)
 		    sysfs_create_file(kobj, &timeslice_duration_attr.attr))
 			goto err_engine;
 
+		if (intel_engine_has_preempt_reset(engine) &&
+		    sysfs_create_file(kobj, &preempt_timeout_attr.attr))
+			goto err_engine;
+
 		if (0) {
 err_object:
 			kobject_put(kobj);
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 18c781f5d83f..27459bec7cf7 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2218,7 +2218,7 @@ static noinline void preempt_reset(struct intel_engine_cs *engine)
 	const unsigned int bit = I915_RESET_ENGINE + engine->id;
 	unsigned long *lock = &engine->gt->reset.flags;
 
-	if (i915_modparams.reset < 3)
+	if (!intel_has_reset_engine(engine->gt))
 		return;
 
 	if (test_and_set_bit(bit, lock))
-- 
2.24.0