[Intel-gfx] [PATCH 1/2] drm/i915/pmu: Handle PCI unbind

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin at intel.com>

Mark the device as closed and keep references to driver data alive to
allow for safe driver unbind with active PMU clients. Perf core does not
otherwise handle this case so we have to do it manually like this.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
Reviewed-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_pmu.c | 39 +++++++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/i915_pmu.h |  4 ++++
 2 files changed, 41 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 69c0fa20eba1..51ed7d0efcdc 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -445,6 +445,8 @@ static void i915_pmu_event_destroy(struct perf_event *event)
 		container_of(event->pmu, typeof(*i915), pmu.base);
 
 	drm_WARN_ON(&i915->drm, event->parent);
+
+	drm_dev_put(&i915->drm);
 }
 
 static int
@@ -510,8 +512,12 @@ static int i915_pmu_event_init(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
 		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct i915_pmu *pmu = &i915->pmu;
 	int ret;
 
+	if (pmu->closed)
+		return -ENODEV;
+
 	if (event->attr.type != event->pmu->type)
 		return -ENOENT;
 
@@ -536,8 +542,10 @@ static int i915_pmu_event_init(struct perf_event *event)
 	if (ret)
 		return ret;
 
-	if (!event->parent)
+	if (!event->parent) {
+		drm_dev_get(&i915->drm);
 		event->destroy = i915_pmu_event_destroy;
+	}
 
 	return 0;
 }
@@ -594,9 +602,16 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 
 static void i915_pmu_event_read(struct perf_event *event)
 {
+	struct drm_i915_private *i915 =
+		container_of(event->pmu, typeof(*i915), pmu.base);
 	struct hw_perf_event *hwc = &event->hw;
+	struct i915_pmu *pmu = &i915->pmu;
 	u64 prev, new;
 
+	if (pmu->closed) {
+		event->hw.state = PERF_HES_STOPPED;
+		return;
+	}
 again:
 	prev = local64_read(&hwc->prev_count);
 	new = __i915_pmu_event_read(event);
@@ -724,6 +739,13 @@ static void i915_pmu_disable(struct perf_event *event)
 
 static void i915_pmu_event_start(struct perf_event *event, int flags)
 {
+	struct drm_i915_private *i915 =
+		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct i915_pmu *pmu = &i915->pmu;
+
+	if (pmu->closed)
+		return;
+
 	i915_pmu_enable(event);
 	event->hw.state = 0;
 }
@@ -738,6 +760,13 @@ static void i915_pmu_event_stop(struct perf_event *event, int flags)
 
 static int i915_pmu_event_add(struct perf_event *event, int flags)
 {
+	struct drm_i915_private *i915 =
+		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct i915_pmu *pmu = &i915->pmu;
+
+	if (pmu->closed)
+		return -ENODEV;
+
 	if (flags & PERF_EF_START)
 		i915_pmu_event_start(event, flags);
 
@@ -1167,7 +1196,13 @@ void i915_pmu_unregister(struct drm_i915_private *i915)
 	if (!pmu->base.event_init)
 		return;
 
-	drm_WARN_ON(&i915->drm, pmu->enable);
+	/*
+	 * "Disconnect" the PMU callbacks - since all are atomic synchronize_rcu
+	 * ensures all currently executing ones will have exited before we
+	 * proceed with unregistration.
+	 */
+	pmu->closed = true;
+	synchronize_rcu();
 
 	hrtimer_cancel(&pmu->timer);
 
diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h
index 941f0c14037c..59a0d19afb67 100644
--- a/drivers/gpu/drm/i915/i915_pmu.h
+++ b/drivers/gpu/drm/i915/i915_pmu.h
@@ -49,6 +49,10 @@ struct i915_pmu {
 	 * @base: PMU base.
 	 */
 	struct pmu base;
+	/**
+	 * @closed: i915 is unregistering.
+	 */
+	bool closed;
 	/**
 	 * @name: Name as registered with perf core.
 	 */
-- 
2.25.1