[PATCH 01/18] drm/i915/selftests: Ensure we don't clamp a random offset to 32b

[PATCH 01/18] drm/i915/selftests: Ensure we don't clamp a random offset to 32b

[Chris Wilson]

Specify that we do want a 64b value for sizeof(u32) as we want to
compute the mask of the upper 62bits.

v2: Use round_down() for automatic type promotion

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c | 2 +-
 drivers/gpu/drm/i915/gt/intel_gpu_commands.h          | 7 +++++++
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 3abe15a08b6d..695bfb18b0d4 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -1539,7 +1539,7 @@ static int igt_vm_isolation(void *arg)
 
 			div64_u64_rem(i915_prandom_u64_state(&prng),
 				      vm_total, &offset);
-			offset &= -sizeof(u32);
+			offset = round_down(offset, alignof_dword);
 			offset += I915_GTT_PAGE_SIZE;
 
 			err = write_to_scratch(ctx_a, engine,
diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index eec31e36aca7..69f34737325f 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -7,6 +7,13 @@
 #ifndef _INTEL_GPU_COMMANDS_H_
 #define _INTEL_GPU_COMMANDS_H_
 
+/*
+ * Target address alignments required for GPU access e.g.
+ * MI_STORE_DWORD_IMM.
+ */
+#define alignof_dword 4
+#define alignof_qword 8
+
 /*
  * Instruction field definitions used by the command parser
  */
-- 
2.22.0

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

[PATCH 02/18] drm/i915/selftests: Hold the vma manager lock while modifying mmap_offset

[Chris Wilson]

Right idea, wrong lock. We already drop struct_mutex before we free the
mmap_offset when freeing the object, so we need to take the vma manager
lock when manipulating the mmap_offset address space for our selftests.

Fixes: 8221d21b0664 ("drm/i915/selftests: Lock the drm_mm while modifying")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Imre Deak <imre.deak@intel.com>
---
 .../drm/i915/gem/selftests/i915_gem_mman.c    | 20 +++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index b95fdc2b6bfc..5635cbb4af22 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -401,6 +401,18 @@ static void restore_retire_worker(struct drm_i915_private *i915)
 	i915_gem_shrinker_register(i915);
 }
 
+static void mmap_offset_lock(struct drm_i915_private *i915)
+	__acquires(&i915->drm.vma_offset_manager->vm_lock)
+{
+	write_lock(&i915->drm.vma_offset_manager->vm_lock);
+}
+
+static void mmap_offset_unlock(struct drm_i915_private *i915)
+	__releases(&i915->drm.vma_offset_manager->vm_lock)
+{
+	write_unlock(&i915->drm.vma_offset_manager->vm_lock);
+}
+
 static int igt_mmap_offset_exhaustion(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
@@ -419,9 +431,9 @@ static int igt_mmap_offset_exhaustion(void *arg)
 	drm_mm_for_each_hole(hole, mm, hole_start, hole_end) {
 		resv.start = hole_start;
 		resv.size = hole_end - hole_start - 1; /* PAGE_SIZE units */
-		mutex_lock(&i915->drm.struct_mutex);
+		mmap_offset_lock(i915);
 		err = drm_mm_reserve_node(mm, &resv);
-		mutex_unlock(&i915->drm.struct_mutex);
+		mmap_offset_unlock(i915);
 		if (err) {
 			pr_err("Failed to trim VMA manager, err=%d\n", err);
 			goto out_park;
@@ -485,9 +497,9 @@ static int igt_mmap_offset_exhaustion(void *arg)
 	}
 
 out:
-	mutex_lock(&i915->drm.struct_mutex);
+	mmap_offset_lock(i915);
 	drm_mm_remove_node(&resv);
-	mutex_unlock(&i915->drm.struct_mutex);
+	mmap_offset_unlock(i915);
 out_park:
 	restore_retire_worker(i915);
 	return err;
-- 
2.22.0

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

[PATCH 06/18] drm/i915: Add to timeline requires the timeline mutex

[Chris Wilson]

Modifying a remote context requires careful serialisation with requests
on that context, and that serialisation requires us to take their
timeline->mutex. Make it so.

Note that while struct_mutex rules, we can't create more than one
request in parallel, but that age is soon coming to an end.

v2: Though it doesn't affect the current users, contexts may share
timelines so check if we already hold the right mutex.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c | 16 ++-------
 drivers/gpu/drm/i915/gt/intel_context.c     | 38 +++++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_context.h     |  3 ++
 drivers/gpu/drm/i915/i915_perf.c            |  7 +---
 4 files changed, 44 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 1f0d10bb88c1..6000177472ee 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -1192,20 +1192,8 @@ gen8_modify_rpcs(struct intel_context *ce, struct intel_sseu sseu)
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
-	/* Queue this switch after all other activity by this context. */
-	ret = i915_active_request_set(&ce->ring->timeline->last_request, rq);
-	if (ret)
-		goto out_add;
-
-	/*
-	 * Guarantee context image and the timeline remains pinned until the
-	 * modifying request is retired by setting the ce activity tracker.
-	 *
-	 * But we only need to take one pin on the account of it. Or in other
-	 * words transfer the pinned ce object to tracked active request.
-	 */
-	GEM_BUG_ON(i915_active_is_idle(&ce->active));
-	ret = i915_active_ref(&ce->active, rq->fence.context, rq);
+	/* Serialise with the remote context */
+	ret = intel_context_prepare_remote_request(ce, rq);
 	if (ret)
 		goto out_add;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 1110fc8f657a..b1e2e4b60027 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -239,6 +239,44 @@ void intel_context_exit_engine(struct intel_context *ce)
 	intel_engine_pm_put(ce->engine);
 }
 
+int intel_context_prepare_remote_request(struct intel_context *ce,
+					 struct i915_request *rq)
+{
+	struct intel_timeline *tl = ce->ring->timeline;
+	int err;
+
+	/* Only suitable for use in remotely modifying this context */
+	GEM_BUG_ON(rq->hw_context == ce);
+
+	if (rq->timeline != tl) { /* beware timeline sharing */
+		err = mutex_lock_interruptible_nested(&tl->mutex,
+						      SINGLE_DEPTH_NESTING);
+		if (err)
+			return err;
+	}
+	lockdep_assert_held(&tl->mutex);
+
+	/* Queue this switch after all other activity by this context. */
+	err = i915_active_request_set(&tl->last_request, rq);
+	if (err)
+		goto unlock;
+
+	/*
+	 * Guarantee context image and the timeline remains pinned until the
+	 * modifying request is retired by setting the ce activity tracker.
+	 *
+	 * But we only need to take one pin on the account of it. Or in other
+	 * words transfer the pinned ce object to tracked active request.
+	 */
+	GEM_BUG_ON(i915_active_is_idle(&ce->active));
+	err = i915_active_ref(&ce->active, rq->fence.context, rq);
+
+unlock:
+	if (rq->timeline != tl)
+		mutex_unlock(&tl->mutex);
+	return err;
+}
+
 struct i915_request *intel_context_create_request(struct intel_context *ce)
 {
 	struct i915_request *rq;
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index 40cd8320fcc3..b41c610c2ce6 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -139,6 +139,9 @@ static inline void intel_context_timeline_unlock(struct intel_context *ce)
 	mutex_unlock(&ce->ring->timeline->mutex);
 }
 
+int intel_context_prepare_remote_request(struct intel_context *ce,
+					 struct i915_request *rq);
+
 struct i915_request *intel_context_create_request(struct intel_context *ce);
 
 #endif /* __INTEL_CONTEXT_H__ */
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 98a13947f618..8664d8d34aaa 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1768,12 +1768,7 @@ static int gen8_modify_context(struct intel_context *ce,
 		return PTR_ERR(rq);
 
 	/* Serialise with the remote context */
-	err = i915_active_request_set(&ce->ring->timeline->last_request, rq);
-	if (err)
-		goto out_add;
-
-	/* Keep the remote context alive until after we finish editing */
-	err = i915_active_ref(&ce->active, rq->fence.context, rq);
+	err = intel_context_prepare_remote_request(ce, rq);
 	if (err)
 		goto out_add;
 
-- 
2.22.0

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

[PATCH 07/18] drm/i915: Teach execbuffer to take the engine wakeref not GT

[Chris Wilson]

In the next patch, we would like to couple into the engine wakeref to
free the batch pool on idling. The caveat here is that we therefore want
to track the engine wakeref more precisely and to hold it instead of the
broader GT wakeref as we process the ioctl.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 36 ++++++++++++-------
 drivers/gpu/drm/i915/gt/intel_context.h       |  7 ++++
 2 files changed, 31 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 1c5dfbfad71b..f43eaaa5db5f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2143,13 +2143,35 @@ static int eb_pin_context(struct i915_execbuffer *eb, struct intel_context *ce)
 	if (err)
 		return err;
 
+	/*
+	 * Take a local wakeref for preparing to dispatch the execbuf as
+	 * we expect to access the hardware fairly frequently in the
+	 * process. Upon first dispatch, we acquire another prolonged
+	 * wakeref that we hold until the GPU has been idle for at least
+	 * 100ms.
+	 */
+	err = intel_context_timeline_lock(ce);
+	if (err)
+		goto err_unpin;
+
+	intel_context_enter(ce);
+	intel_context_timeline_unlock(ce);
+
 	eb->engine = ce->engine;
 	eb->context = ce;
 	return 0;
+
+err_unpin:
+	intel_context_unpin(ce);
+	return err;
 }
 
 static void eb_unpin_context(struct i915_execbuffer *eb)
 {
+	__intel_context_timeline_lock(eb->context);
+	intel_context_exit(eb->context);
+	intel_context_timeline_unlock(eb->context);
+
 	intel_context_unpin(eb->context);
 }
 
@@ -2430,18 +2452,9 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	if (unlikely(err))
 		goto err_destroy;
 
-	/*
-	 * Take a local wakeref for preparing to dispatch the execbuf as
-	 * we expect to access the hardware fairly frequently in the
-	 * process. Upon first dispatch, we acquire another prolonged
-	 * wakeref that we hold until the GPU has been idle for at least
-	 * 100ms.
-	 */
-	intel_gt_pm_get(&eb.i915->gt);
-
 	err = i915_mutex_lock_interruptible(dev);
 	if (err)
-		goto err_rpm;
+		goto err_context;
 
 	err = eb_select_engine(&eb, file, args);
 	if (unlikely(err))
@@ -2606,8 +2619,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	eb_unpin_context(&eb);
 err_unlock:
 	mutex_unlock(&dev->struct_mutex);
-err_rpm:
-	intel_gt_pm_put(&eb.i915->gt);
+err_context:
 	i915_gem_context_put(eb.gem_context);
 err_destroy:
 	eb_destroy(&eb);
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index b41c610c2ce6..99bd8210a234 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -126,6 +126,13 @@ static inline void intel_context_put(struct intel_context *ce)
 	kref_put(&ce->ref, ce->ops->destroy);
 }
 
+static inline void
+__intel_context_timeline_lock(struct intel_context *ce)
+	__acquires(&ce->ring->timeline->mutex)
+{
+	mutex_lock(&ce->ring->timeline->mutex);
+}
+
 static inline int __must_check
 intel_context_timeline_lock(struct intel_context *ce)
 	__acquires(&ce->ring->timeline->mutex)
-- 
2.22.0

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

[PATCH 10/18] drm/i915/gt: Guard timeline pinning with its own mutex

[Chris Wilson]

In preparation for removing struct_mutex from around context retirement,
we need to make timeline pinning safe. Since multiple engines/contexts
can share a single timeline, it needs to be protected by a mutex.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_timeline.c      | 27 +++++++++----------
 .../gpu/drm/i915/gt/intel_timeline_types.h    |  2 +-
 drivers/gpu/drm/i915/gt/mock_engine.c         |  6 ++---
 3 files changed, 16 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 355dfc52c804..7b476cd55dac 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -211,9 +211,9 @@ int intel_timeline_init(struct intel_timeline *timeline,
 	void *vaddr;
 
 	kref_init(&timeline->kref);
+	atomic_set(&timeline->pin_count, 0);
 
 	timeline->gt = gt;
-	timeline->pin_count = 0;
 
 	timeline->has_initial_breadcrumb = !hwsp;
 	timeline->hwsp_cacheline = NULL;
@@ -280,7 +280,7 @@ void intel_timelines_init(struct drm_i915_private *i915)
 
 void intel_timeline_fini(struct intel_timeline *timeline)
 {
-	GEM_BUG_ON(timeline->pin_count);
+	GEM_BUG_ON(atomic_read(&timeline->pin_count));
 	GEM_BUG_ON(!list_empty(&timeline->requests));
 
 	if (timeline->hwsp_cacheline)
@@ -314,33 +314,31 @@ int intel_timeline_pin(struct intel_timeline *tl)
 {
 	int err;
 
-	if (tl->pin_count++)
+	if (atomic_add_unless(&tl->pin_count, 1, 0))
 		return 0;
-	GEM_BUG_ON(!tl->pin_count);
-	GEM_BUG_ON(tl->active_count);
 
 	err = i915_vma_pin(tl->hwsp_ggtt, 0, 0, PIN_GLOBAL | PIN_HIGH);
 	if (err)
-		goto unpin;
+		return err;
 
 	tl->hwsp_offset =
 		i915_ggtt_offset(tl->hwsp_ggtt) +
 		offset_in_page(tl->hwsp_offset);
 
 	cacheline_acquire(tl->hwsp_cacheline);
+	if (atomic_fetch_inc(&tl->pin_count)) {
+		cacheline_release(tl->hwsp_cacheline);
+		__i915_vma_unpin(tl->hwsp_ggtt);
+	}
 
 	return 0;
-
-unpin:
-	tl->pin_count = 0;
-	return err;
 }
 
 void intel_timeline_enter(struct intel_timeline *tl)
 {
 	struct intel_gt_timelines *timelines = &tl->gt->timelines;
 
-	GEM_BUG_ON(!tl->pin_count);
+	GEM_BUG_ON(!atomic_read(&tl->pin_count));
 	if (tl->active_count++)
 		return;
 	GEM_BUG_ON(!tl->active_count); /* overflow? */
@@ -372,7 +370,7 @@ void intel_timeline_exit(struct intel_timeline *tl)
 
 static u32 timeline_advance(struct intel_timeline *tl)
 {
-	GEM_BUG_ON(!tl->pin_count);
+	GEM_BUG_ON(!atomic_read(&tl->pin_count));
 	GEM_BUG_ON(tl->seqno & tl->has_initial_breadcrumb);
 
 	return tl->seqno += 1 + tl->has_initial_breadcrumb;
@@ -523,11 +521,10 @@ int intel_timeline_read_hwsp(struct i915_request *from,
 
 void intel_timeline_unpin(struct intel_timeline *tl)
 {
-	GEM_BUG_ON(!tl->pin_count);
-	if (--tl->pin_count)
+	GEM_BUG_ON(!atomic_read(&tl->pin_count));
+	if (!atomic_dec_and_test(&tl->pin_count))
 		return;
 
-	GEM_BUG_ON(tl->active_count);
 	cacheline_release(tl->hwsp_cacheline);
 
 	__i915_vma_unpin(tl->hwsp_ggtt);
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline_types.h b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
index b820ee76b7f5..8dd14a2b8781 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
@@ -25,7 +25,7 @@ struct intel_timeline {
 
 	struct mutex mutex; /* protects the flow of requests */
 
-	unsigned int pin_count;
+	atomic_t pin_count;
 	const u32 *hwsp_seqno;
 	struct i915_vma *hwsp_ggtt;
 	u32 hwsp_offset;
diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c
index 490ebd121f4c..a48b36d31e65 100644
--- a/drivers/gpu/drm/i915/gt/mock_engine.c
+++ b/drivers/gpu/drm/i915/gt/mock_engine.c
@@ -38,13 +38,13 @@ struct mock_ring {
 
 static void mock_timeline_pin(struct intel_timeline *tl)
 {
-	tl->pin_count++;
+	atomic_inc(&tl->pin_count);
 }
 
 static void mock_timeline_unpin(struct intel_timeline *tl)
 {
-	GEM_BUG_ON(!tl->pin_count);
-	tl->pin_count--;
+	GEM_BUG_ON(!atomic_read(&tl->pin_count));
+	atomic_dec(&tl->pin_count);
 }
 
 static struct intel_ring *mock_ring(struct intel_engine_cs *engine)
-- 
2.22.0

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

[PATCH 14/18] drm/i915: Forgo last_fence active request tracking

[Chris Wilson]

We were using the last_fence to track the last request that used this
vma that might be interpreted by a fence register and forced ourselves
to wait for this request before modifying any fence register that
overlapped our vma. Due to requirement that we need to track any XY_BLT
command, linear or tiled, this in effect meant that we have to track the
vma for its active lifespan anyway, so we can forgo the explicit
last_fence tracking and just use the whole vma->active.

Another solution would be to pipeline the register updates, and would
help resolve some long running stalls for gen3 (but only gen 2 and 3!)

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
---
 drivers/gpu/drm/i915/i915_debugfs.c       |  4 +---
 drivers/gpu/drm/i915/i915_gem_fence_reg.c |  6 ++----
 drivers/gpu/drm/i915/i915_gem_gtt.c       |  1 -
 drivers/gpu/drm/i915/i915_vma.c           | 13 -------------
 drivers/gpu/drm/i915/i915_vma.h           |  1 -
 5 files changed, 3 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index ce1b6568515e..2c2d2a01853a 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -210,9 +210,7 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 			}
 		}
 		if (vma->fence)
-			seq_printf(m, " , fence: %d%s",
-				   vma->fence->id,
-				   i915_active_request_isset(&vma->last_fence) ? "*" : "");
+			seq_printf(m, " , fence: %d", vma->fence->id);
 		seq_puts(m, ")");
 
 		spin_lock(&obj->vma.lock);
diff --git a/drivers/gpu/drm/i915/i915_gem_fence_reg.c b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
index bcac359ec661..c9654f1a468f 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence_reg.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
@@ -230,16 +230,14 @@ static int fence_update(struct i915_fence_reg *fence,
 			 i915_gem_object_get_tiling(vma->obj)))
 			return -EINVAL;
 
-		ret = i915_active_request_retire(&vma->last_fence,
-					     &vma->obj->base.dev->struct_mutex);
+		ret = i915_active_wait(&vma->active);
 		if (ret)
 			return ret;
 	}
 
 	old = xchg(&fence->vma, NULL);
 	if (old) {
-		ret = i915_active_request_retire(&old->last_fence,
-					     &old->obj->base.dev->struct_mutex);
+		ret = i915_active_wait(&old->active);
 		if (ret) {
 			fence->vma = old;
 			return ret;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index e0645ce4fb84..5281ddb0e408 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2033,7 +2033,6 @@ static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size)
 		return ERR_PTR(-ENOMEM);
 
 	i915_active_init(i915, &vma->active, NULL, NULL);
-	INIT_ACTIVE_REQUEST(&vma->last_fence);
 
 	vma->vm = &ggtt->vm;
 	vma->ops = &pd_vma_ops;
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index ee73baf29415..f4bc5be3cfe5 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -119,7 +119,6 @@ vma_create(struct drm_i915_gem_object *obj,
 
 	i915_active_init(vm->i915, &vma->active,
 			 __i915_vma_active, __i915_vma_retire);
-	INIT_ACTIVE_REQUEST(&vma->last_fence);
 
 	/* Declare ourselves safe for use inside shrinkers */
 	if (IS_ENABLED(CONFIG_LOCKDEP)) {
@@ -801,8 +800,6 @@ static void __i915_vma_destroy(struct i915_vma *vma)
 	GEM_BUG_ON(vma->node.allocated);
 	GEM_BUG_ON(vma->fence);
 
-	GEM_BUG_ON(i915_active_request_isset(&vma->last_fence));
-
 	mutex_lock(&vma->vm->mutex);
 	list_del(&vma->vm_link);
 	mutex_unlock(&vma->vm->mutex);
@@ -938,9 +935,6 @@ int i915_vma_move_to_active(struct i915_vma *vma,
 	obj->read_domains |= I915_GEM_GPU_DOMAINS;
 	obj->mm.dirty = true;
 
-	if (flags & EXEC_OBJECT_NEEDS_FENCE)
-		__i915_active_request_set(&vma->last_fence, rq);
-
 	export_fence(vma, rq, flags);
 
 	GEM_BUG_ON(!i915_vma_is_active(vma));
@@ -973,14 +967,7 @@ int i915_vma_unbind(struct i915_vma *vma)
 		 * before we are finished).
 		 */
 		__i915_vma_pin(vma);
-
 		ret = i915_active_wait(&vma->active);
-		if (ret)
-			goto unpin;
-
-		ret = i915_active_request_retire(&vma->last_fence,
-					      &vma->vm->i915->drm.struct_mutex);
-unpin:
 		__i915_vma_unpin(vma);
 		if (ret)
 			return ret;
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 4b769db649bf..17e6a038bd36 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -111,7 +111,6 @@ struct i915_vma {
 #define I915_VMA_GGTT_WRITE	BIT(14)
 
 	struct i915_active active;
-	struct i915_active_request last_fence;
 
 	/**
 	 * Support different GGTT views into the same object.
-- 
2.22.0

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

[PATCH 15/18] drm/i915/overlay: Switch to using i915_active tracking

[Chris Wilson]

Remove the raw i915_active_request tracking in favour of the higher
level i915_active tracking for the sole purpose of making the lockless
transition easier in later patches.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/display/intel_overlay.c | 129 +++++++++----------
 drivers/gpu/drm/i915/i915_active.h           |  19 ---
 2 files changed, 64 insertions(+), 84 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c
index 07929726b780..9b3f4f6644f3 100644
--- a/drivers/gpu/drm/i915/display/intel_overlay.c
+++ b/drivers/gpu/drm/i915/display/intel_overlay.c
@@ -191,7 +191,8 @@ struct intel_overlay {
 	struct overlay_registers __iomem *regs;
 	u32 flip_addr;
 	/* flip handling */
-	struct i915_active_request last_flip;
+	struct i915_active last_flip;
+	void (*flip_complete)(struct intel_overlay *ovl);
 };
 
 static void i830_overlay_clock_gating(struct drm_i915_private *dev_priv,
@@ -217,30 +218,25 @@ static void i830_overlay_clock_gating(struct drm_i915_private *dev_priv,
 				  PCI_DEVFN(0, 0), I830_CLOCK_GATE, val);
 }
 
-static void intel_overlay_submit_request(struct intel_overlay *overlay,
-					 struct i915_request *rq,
-					 i915_active_retire_fn retire)
+static struct i915_request *
+alloc_request(struct intel_overlay *overlay, void (*fn)(struct intel_overlay *))
 {
-	GEM_BUG_ON(i915_active_request_peek(&overlay->last_flip,
-					    &overlay->i915->drm.struct_mutex));
-	i915_active_request_set_retire_fn(&overlay->last_flip, retire,
-					  &overlay->i915->drm.struct_mutex);
-	__i915_active_request_set(&overlay->last_flip, rq);
-	i915_request_add(rq);
-}
+	struct i915_request *rq;
+	int err;
 
-static int intel_overlay_do_wait_request(struct intel_overlay *overlay,
-					 struct i915_request *rq,
-					 i915_active_retire_fn retire)
-{
-	intel_overlay_submit_request(overlay, rq, retire);
-	return i915_active_request_retire(&overlay->last_flip,
-					  &overlay->i915->drm.struct_mutex);
-}
+	overlay->flip_complete = fn;
 
-static struct i915_request *alloc_request(struct intel_overlay *overlay)
-{
-	return i915_request_create(overlay->context);
+	rq = i915_request_create(overlay->context);
+	if (IS_ERR(rq))
+		return rq;
+
+	err = i915_active_ref(&overlay->last_flip, rq->fence.context, rq);
+	if (err) {
+		i915_request_add(rq);
+		return ERR_PTR(err);
+	}
+
+	return rq;
 }
 
 /* overlay needs to be disable in OCMD reg */
@@ -252,7 +248,7 @@ static int intel_overlay_on(struct intel_overlay *overlay)
 
 	WARN_ON(overlay->active);
 
-	rq = alloc_request(overlay);
+	rq = alloc_request(overlay, NULL);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
@@ -273,7 +269,9 @@ static int intel_overlay_on(struct intel_overlay *overlay)
 	*cs++ = MI_NOOP;
 	intel_ring_advance(rq, cs);
 
-	return intel_overlay_do_wait_request(overlay, rq, NULL);
+	i915_request_add(rq);
+
+	return i915_active_wait(&overlay->last_flip);
 }
 
 static void intel_overlay_flip_prepare(struct intel_overlay *overlay,
@@ -317,7 +315,7 @@ static int intel_overlay_continue(struct intel_overlay *overlay,
 	if (tmp & (1 << 17))
 		DRM_DEBUG("overlay underrun, DOVSTA: %x\n", tmp);
 
-	rq = alloc_request(overlay);
+	rq = alloc_request(overlay, NULL);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
@@ -332,8 +330,7 @@ static int intel_overlay_continue(struct intel_overlay *overlay,
 	intel_ring_advance(rq, cs);
 
 	intel_overlay_flip_prepare(overlay, vma);
-
-	intel_overlay_submit_request(overlay, rq, NULL);
+	i915_request_add(rq);
 
 	return 0;
 }
@@ -354,20 +351,13 @@ static void intel_overlay_release_old_vma(struct intel_overlay *overlay)
 }
 
 static void
-intel_overlay_release_old_vid_tail(struct i915_active_request *active,
-				   struct i915_request *rq)
+intel_overlay_release_old_vid_tail(struct intel_overlay *overlay)
 {
-	struct intel_overlay *overlay =
-		container_of(active, typeof(*overlay), last_flip);
-
 	intel_overlay_release_old_vma(overlay);
 }
 
-static void intel_overlay_off_tail(struct i915_active_request *active,
-				   struct i915_request *rq)
+static void intel_overlay_off_tail(struct intel_overlay *overlay)
 {
-	struct intel_overlay *overlay =
-		container_of(active, typeof(*overlay), last_flip);
 	struct drm_i915_private *dev_priv = overlay->i915;
 
 	intel_overlay_release_old_vma(overlay);
@@ -380,6 +370,16 @@ static void intel_overlay_off_tail(struct i915_active_request *active,
 		i830_overlay_clock_gating(dev_priv, true);
 }
 
+static void
+intel_overlay_last_flip_retire(struct i915_active *active)
+{
+	struct intel_overlay *overlay =
+		container_of(active, typeof(*overlay), last_flip);
+
+	if (overlay->flip_complete)
+		overlay->flip_complete(overlay);
+}
+
 /* overlay needs to be disabled in OCMD reg */
 static int intel_overlay_off(struct intel_overlay *overlay)
 {
@@ -394,7 +394,7 @@ static int intel_overlay_off(struct intel_overlay *overlay)
 	 * of the hw. Do it in both cases */
 	flip_addr |= OFC_UPDATE;
 
-	rq = alloc_request(overlay);
+	rq = alloc_request(overlay, intel_overlay_off_tail);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
@@ -417,17 +417,16 @@ static int intel_overlay_off(struct intel_overlay *overlay)
 	intel_ring_advance(rq, cs);
 
 	intel_overlay_flip_prepare(overlay, NULL);
+	i915_request_add(rq);
 
-	return intel_overlay_do_wait_request(overlay, rq,
-					     intel_overlay_off_tail);
+	return i915_active_wait(&overlay->last_flip);
 }
 
 /* recover from an interruption due to a signal
  * We have to be careful not to repeat work forever an make forward progess. */
 static int intel_overlay_recover_from_interrupt(struct intel_overlay *overlay)
 {
-	return i915_active_request_retire(&overlay->last_flip,
-					  &overlay->i915->drm.struct_mutex);
+	return i915_active_wait(&overlay->last_flip);
 }
 
 /* Wait for pending overlay flip and release old frame.
@@ -437,43 +436,40 @@ static int intel_overlay_recover_from_interrupt(struct intel_overlay *overlay)
 static int intel_overlay_release_old_vid(struct intel_overlay *overlay)
 {
 	struct drm_i915_private *dev_priv = overlay->i915;
+	struct i915_request *rq;
 	u32 *cs;
-	int ret;
 
 	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 
-	/* Only wait if there is actually an old frame to release to
+	/*
+	 * Only wait if there is actually an old frame to release to
 	 * guarantee forward progress.
 	 */
 	if (!overlay->old_vma)
 		return 0;
 
-	if (I915_READ(GEN2_ISR) & I915_OVERLAY_PLANE_FLIP_PENDING_INTERRUPT) {
-		/* synchronous slowpath */
-		struct i915_request *rq;
+	if (!(I915_READ(GEN2_ISR) & I915_OVERLAY_PLANE_FLIP_PENDING_INTERRUPT)) {
+		intel_overlay_release_old_vid_tail(overlay);
+		return 0;
+	}
 
-		rq = alloc_request(overlay);
-		if (IS_ERR(rq))
-			return PTR_ERR(rq);
+	rq = alloc_request(overlay, intel_overlay_release_old_vid_tail);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
 
-		cs = intel_ring_begin(rq, 2);
-		if (IS_ERR(cs)) {
-			i915_request_add(rq);
-			return PTR_ERR(cs);
-		}
+	cs = intel_ring_begin(rq, 2);
+	if (IS_ERR(cs)) {
+		i915_request_add(rq);
+		return PTR_ERR(cs);
+	}
 
-		*cs++ = MI_WAIT_FOR_EVENT | MI_WAIT_FOR_OVERLAY_FLIP;
-		*cs++ = MI_NOOP;
-		intel_ring_advance(rq, cs);
+	*cs++ = MI_WAIT_FOR_EVENT | MI_WAIT_FOR_OVERLAY_FLIP;
+	*cs++ = MI_NOOP;
+	intel_ring_advance(rq, cs);
 
-		ret = intel_overlay_do_wait_request(overlay, rq,
-						    intel_overlay_release_old_vid_tail);
-		if (ret)
-			return ret;
-	} else
-		intel_overlay_release_old_vid_tail(&overlay->last_flip, NULL);
+	i915_request_add(rq);
 
-	return 0;
+	return i915_active_wait(&overlay->last_flip);
 }
 
 void intel_overlay_reset(struct drm_i915_private *dev_priv)
@@ -1375,7 +1371,9 @@ void intel_overlay_setup(struct drm_i915_private *dev_priv)
 	overlay->contrast = 75;
 	overlay->saturation = 146;
 
-	INIT_ACTIVE_REQUEST(&overlay->last_flip);
+	i915_active_init(dev_priv,
+			 &overlay->last_flip,
+			 NULL, intel_overlay_last_flip_retire);
 
 	ret = get_registers(overlay, OVERLAY_NEEDS_PHYSICAL(dev_priv));
 	if (ret)
@@ -1409,6 +1407,7 @@ void intel_overlay_cleanup(struct drm_i915_private *dev_priv)
 	WARN_ON(overlay->active);
 
 	i915_gem_object_put(overlay->reg_bo);
+	i915_active_fini(&overlay->last_flip);
 
 	kfree(overlay);
 }
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
index 134166d31251..911a8338007a 100644
--- a/drivers/gpu/drm/i915/i915_active.h
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -89,25 +89,6 @@ int __must_check
 i915_active_request_set(struct i915_active_request *active,
 			struct i915_request *rq);
 
-/**
- * i915_active_request_set_retire_fn - updates the retirement callback
- * @active - the active tracker
- * @fn - the routine called when the request is retired
- * @mutex - struct_mutex used to guard retirements
- *
- * i915_active_request_set_retire_fn() updates the function pointer that
- * is called when the final request associated with the @active tracker
- * is retired.
- */
-static inline void
-i915_active_request_set_retire_fn(struct i915_active_request *active,
-				  i915_active_retire_fn fn,
-				  struct mutex *mutex)
-{
-	lockdep_assert_held(mutex);
-	active->retire = fn ?: i915_active_retire_noop;
-}
-
 /**
  * i915_active_request_raw - return the active request
  * @active - the active tracker
-- 
2.22.0

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

[PATCH 16/18] drm/i915: Extract intel_frontbuffer active tracking

[Chris Wilson]

Move the active tracking for the frontbuffer operations out of the
i915_gem_object and into its own first class (refcounted) object. In the
process of detangling, we switch from low level request tracking to the
easier i915_active -- with the plan that this avoids any potential
atomic callbacks as the frontbuffer tracking wishes to sleep as it
flushes.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/display/intel_display.c  |  70 +++--
 drivers/gpu/drm/i915/display/intel_fbdev.c    |  40 ++-
 .../gpu/drm/i915/display/intel_frontbuffer.c  | 255 +++++++++++++-----
 .../gpu/drm/i915/display/intel_frontbuffer.h  |  70 +++--
 drivers/gpu/drm/i915/display/intel_overlay.c  |   8 +-
 drivers/gpu/drm/i915/gem/i915_gem_clflush.c   |   2 +-
 drivers/gpu/drm/i915/gem/i915_gem_domain.c    |  14 +-
 drivers/gpu/drm/i915/gem/i915_gem_mman.c      |   4 -
 drivers/gpu/drm/i915/gem/i915_gem_object.c    |  27 +-
 drivers/gpu/drm/i915/gem/i915_gem_object.h    |   2 +-
 .../gpu/drm/i915/gem/i915_gem_object_types.h  |   8 +-
 drivers/gpu/drm/i915/i915_debugfs.c           |   5 -
 drivers/gpu/drm/i915/i915_drv.h               |   4 -
 drivers/gpu/drm/i915/i915_gem.c               |  47 +---
 drivers/gpu/drm/i915/i915_vma.c               |   6 +-
 drivers/gpu/drm/i915/intel_drv.h              |   1 +
 16 files changed, 306 insertions(+), 257 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 0286b97caa22..ed3532e4c8ad 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -3049,12 +3049,13 @@ intel_alloc_initial_plane_obj(struct intel_crtc *crtc,
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct drm_i915_gem_object *obj = NULL;
 	struct drm_mode_fb_cmd2 mode_cmd = { 0 };
 	struct drm_framebuffer *fb = &plane_config->fb->base;
 	u32 base_aligned = round_down(plane_config->base, PAGE_SIZE);
 	u32 size_aligned = round_up(plane_config->base + plane_config->size,
 				    PAGE_SIZE);
+	struct drm_i915_gem_object *obj;
+	bool ret = false;
 
 	size_aligned -= base_aligned;
 
@@ -3096,7 +3097,7 @@ intel_alloc_initial_plane_obj(struct intel_crtc *crtc,
 		break;
 	default:
 		MISSING_CASE(plane_config->tiling);
-		return false;
+		goto out;
 	}
 
 	mode_cmd.pixel_format = fb->format->format;
@@ -3108,16 +3109,15 @@ intel_alloc_initial_plane_obj(struct intel_crtc *crtc,
 
 	if (intel_framebuffer_init(to_intel_framebuffer(fb), obj, &mode_cmd)) {
 		DRM_DEBUG_KMS("intel fb init failed\n");
-		goto out_unref_obj;
+		goto out;
 	}
 
 
 	DRM_DEBUG_KMS("initial plane fb obj %p\n", obj);
-	return true;
-
-out_unref_obj:
+	ret = true;
+out:
 	i915_gem_object_put(obj);
-	return false;
+	return ret;
 }
 
 static void
@@ -3174,6 +3174,12 @@ static void intel_plane_disable_noatomic(struct intel_crtc *crtc,
 	intel_disable_plane(plane, crtc_state);
 }
 
+static struct intel_frontbuffer *
+to_intel_frontbuffer(struct drm_framebuffer *fb)
+{
+	return fb ? to_intel_framebuffer(fb)->frontbuffer : NULL;
+}
+
 static void
 intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 			     struct intel_initial_plane_config *plane_config)
@@ -3181,7 +3187,6 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 	struct drm_device *dev = intel_crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *c;
-	struct drm_i915_gem_object *obj;
 	struct drm_plane *primary = intel_crtc->base.primary;
 	struct drm_plane_state *plane_state = primary->state;
 	struct intel_plane *intel_plane = to_intel_plane(primary);
@@ -3257,8 +3262,7 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 		return;
 	}
 
-	obj = intel_fb_obj(fb);
-	intel_fb_obj_flush(obj, ORIGIN_DIRTYFB);
+	intel_frontbuffer_flush(to_intel_frontbuffer(fb), ORIGIN_DIRTYFB);
 
 	plane_state->src_x = 0;
 	plane_state->src_y = 0;
@@ -3273,14 +3277,14 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 	intel_state->base.src = drm_plane_state_src(plane_state);
 	intel_state->base.dst = drm_plane_state_dest(plane_state);
 
-	if (i915_gem_object_is_tiled(obj))
+	if (plane_config->tiling)
 		dev_priv->preserve_bios_swizzle = true;
 
 	plane_state->fb = fb;
 	plane_state->crtc = &intel_crtc->base;
 
 	atomic_or(to_intel_plane(primary)->frontbuffer_bit,
-		  &obj->frontbuffer_bits);
+		  &to_intel_frontbuffer(fb)->bits);
 }
 
 static int skl_max_plane_width(const struct drm_framebuffer *fb,
@@ -14109,9 +14113,9 @@ static void intel_atomic_track_fbs(struct drm_atomic_state *state)
 	int i;
 
 	for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i)
-		i915_gem_track_fb(intel_fb_obj(old_plane_state->fb),
-				  intel_fb_obj(new_plane_state->fb),
-				  to_intel_plane(plane)->frontbuffer_bit);
+		intel_frontbuffer_track(to_intel_frontbuffer(old_plane_state->fb),
+					to_intel_frontbuffer(new_plane_state->fb),
+					to_intel_plane(plane)->frontbuffer_bit);
 }
 
 /**
@@ -14409,7 +14413,7 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 		return ret;
 
 	fb_obj_bump_render_priority(obj);
-	intel_fb_obj_flush(obj, ORIGIN_DIRTYFB);
+	intel_frontbuffer_flush(obj->frontbuffer, ORIGIN_DIRTYFB);
 
 	if (!new_state->fence) { /* implicit fencing */
 		struct dma_fence *fence;
@@ -14672,13 +14676,12 @@ intel_legacy_cursor_update(struct drm_plane *plane,
 			   struct drm_modeset_acquire_ctx *ctx)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
-	int ret;
 	struct drm_plane_state *old_plane_state, *new_plane_state;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
-	struct drm_framebuffer *old_fb;
 	struct intel_crtc_state *crtc_state =
 		to_intel_crtc_state(crtc->state);
 	struct intel_crtc_state *new_crtc_state;
+	int ret;
 
 	/*
 	 * When crtc is inactive or there is a modeset pending,
@@ -14746,11 +14749,10 @@ intel_legacy_cursor_update(struct drm_plane *plane,
 	if (ret)
 		goto out_unlock;
 
-	intel_fb_obj_flush(intel_fb_obj(fb), ORIGIN_FLIP);
-
-	old_fb = old_plane_state->fb;
-	i915_gem_track_fb(intel_fb_obj(old_fb), intel_fb_obj(fb),
-			  intel_plane->frontbuffer_bit);
+	intel_frontbuffer_flush(to_intel_frontbuffer(fb), ORIGIN_FLIP);
+	intel_frontbuffer_track(to_intel_frontbuffer(old_plane_state->fb),
+				to_intel_frontbuffer(fb),
+				intel_plane->frontbuffer_bit);
 
 	/* Swap plane state */
 	plane->state = new_plane_state;
@@ -15525,15 +15527,9 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 static void intel_user_framebuffer_destroy(struct drm_framebuffer *fb)
 {
 	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
-	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 
 	drm_framebuffer_cleanup(fb);
-
-	i915_gem_object_lock(obj);
-	WARN_ON(!obj->framebuffer_references--);
-	i915_gem_object_unlock(obj);
-
-	i915_gem_object_put(obj);
+	intel_frontbuffer_put(intel_fb->frontbuffer);
 
 	kfree(intel_fb);
 }
@@ -15561,7 +15557,7 @@ static int intel_user_framebuffer_dirty(struct drm_framebuffer *fb,
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 
 	i915_gem_object_flush_if_display(obj);
-	intel_fb_obj_flush(obj, ORIGIN_DIRTYFB);
+	intel_frontbuffer_flush(to_intel_frontbuffer(fb), ORIGIN_DIRTYFB);
 
 	return 0;
 }
@@ -15583,8 +15579,11 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 	int ret = -EINVAL;
 	int i;
 
+	intel_fb->frontbuffer = intel_frontbuffer_get(obj);
+	if (!intel_fb->frontbuffer)
+		return -ENOMEM;
+
 	i915_gem_object_lock(obj);
-	obj->framebuffer_references++;
 	tiling = i915_gem_object_get_tiling(obj);
 	stride = i915_gem_object_get_stride(obj);
 	i915_gem_object_unlock(obj);
@@ -15701,9 +15700,7 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 	return 0;
 
 err:
-	i915_gem_object_lock(obj);
-	obj->framebuffer_references--;
-	i915_gem_object_unlock(obj);
+	intel_frontbuffer_put(intel_fb->frontbuffer);
 	return ret;
 }
 
@@ -15721,8 +15718,7 @@ intel_user_framebuffer_create(struct drm_device *dev,
 		return ERR_PTR(-ENOENT);
 
 	fb = intel_framebuffer_create(obj, &mode_cmd);
-	if (IS_ERR(fb))
-		i915_gem_object_put(obj);
+	i915_gem_object_put(obj);
 
 	return fb;
 }
diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c
index 1edd44ee32b2..4b57cdd76699 100644
--- a/drivers/gpu/drm/i915/display/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/display/intel_fbdev.c
@@ -47,13 +47,14 @@
 #include "intel_fbdev.h"
 #include "intel_frontbuffer.h"
 
-static void intel_fbdev_invalidate(struct intel_fbdev *ifbdev)
+static struct intel_frontbuffer *to_frontbuffer(struct intel_fbdev *ifbdev)
 {
-	struct drm_i915_gem_object *obj = intel_fb_obj(&ifbdev->fb->base);
-	unsigned int origin =
-		ifbdev->vma_flags & PLANE_HAS_FENCE ? ORIGIN_GTT : ORIGIN_CPU;
+	return ifbdev->fb->frontbuffer;
+}
 
-	intel_fb_obj_invalidate(obj, origin);
+static void intel_fbdev_invalidate(struct intel_fbdev *ifbdev)
+{
+	intel_frontbuffer_invalidate(to_frontbuffer(ifbdev), ORIGIN_CPU);
 }
 
 static int intel_fbdev_set_par(struct fb_info *info)
@@ -120,7 +121,7 @@ static int intelfb_alloc(struct drm_fb_helper *helper,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_mode_fb_cmd2 mode_cmd = {};
 	struct drm_i915_gem_object *obj;
-	int size, ret;
+	int size;
 
 	/* we don't do packed 24bpp */
 	if (sizes->surface_bpp == 24)
@@ -147,24 +148,16 @@ static int intelfb_alloc(struct drm_fb_helper *helper,
 		obj = i915_gem_object_create_shmem(dev_priv, size);
 	if (IS_ERR(obj)) {
 		DRM_ERROR("failed to allocate framebuffer\n");
-		ret = PTR_ERR(obj);
-		goto err;
+		return PTR_ERR(obj);
 	}
 
 	fb = intel_framebuffer_create(obj, &mode_cmd);
-	if (IS_ERR(fb)) {
-		ret = PTR_ERR(fb);
-		goto err_obj;
-	}
+	i915_gem_object_put(obj);
+	if (IS_ERR(fb))
+		return PTR_ERR(fb);
 
 	ifbdev->fb = to_intel_framebuffer(fb);
-
 	return 0;
-
-err_obj:
-	i915_gem_object_put(obj);
-err:
-	return ret;
 }
 
 static int intelfb_create(struct drm_fb_helper *helper,
@@ -180,7 +173,6 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	const struct i915_ggtt_view view = {
 		.type = I915_GGTT_VIEW_NORMAL,
 	};
-	struct drm_framebuffer *fb;
 	intel_wakeref_t wakeref;
 	struct fb_info *info;
 	struct i915_vma *vma;
@@ -226,8 +218,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 		goto out_unlock;
 	}
 
-	fb = &ifbdev->fb->base;
-	intel_fb_obj_flush(intel_fb_obj(fb), ORIGIN_DIRTYFB);
+	intel_frontbuffer_flush(to_frontbuffer(ifbdev), ORIGIN_DIRTYFB);
 
 	info = drm_fb_helper_alloc_fbi(helper);
 	if (IS_ERR(info)) {
@@ -236,7 +227,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 		goto out_unpin;
 	}
 
-	ifbdev->helper.fb = fb;
+	ifbdev->helper.fb = &ifbdev->fb->base;
 
 	info->fbops = &intelfb_ops;
 
@@ -262,13 +253,14 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	 * If the object is stolen however, it will be full of whatever
 	 * garbage was left in there.
 	 */
-	if (intel_fb_obj(fb)->stolen && !prealloc)
+	if (vma->obj->stolen && !prealloc)
 		memset_io(info->screen_base, 0, info->screen_size);
 
 	/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
 
 	DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08x\n",
-		      fb->width, fb->height, i915_ggtt_offset(vma));
+		      ifbdev->fb->base.width, ifbdev->fb->base.height,
+		      i915_ggtt_offset(vma));
 	ifbdev->vma = vma;
 	ifbdev->vma_flags = flags;
 
diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.c b/drivers/gpu/drm/i915/display/intel_frontbuffer.c
index 44273c10cea5..d11031811a48 100644
--- a/drivers/gpu/drm/i915/display/intel_frontbuffer.c
+++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.c
@@ -30,11 +30,11 @@
  * Many features require us to track changes to the currently active
  * frontbuffer, especially rendering targeted at the frontbuffer.
  *
- * To be able to do so GEM tracks frontbuffers using a bitmask for all possible
- * frontbuffer slots through i915_gem_track_fb(). The function in this file are
- * then called when the contents of the frontbuffer are invalidated, when
- * frontbuffer rendering has stopped again to flush out all the changes and when
- * the frontbuffer is exchanged with a flip. Subsystems interested in
+ * To be able to do so we track frontbuffers using a bitmask for all possible
+ * frontbuffer slots through intel_frontbuffer_track(). The functions in this
+ * file are then called when the contents of the frontbuffer are invalidated,
+ * when frontbuffer rendering has stopped again to flush out all the changes
+ * and when the frontbuffer is exchanged with a flip. Subsystems interested in
  * frontbuffer changes (e.g. PSR, FBC, DRRS) should directly put their callbacks
  * into the relevant places and filter for the frontbuffer slots that they are
  * interested int.
@@ -63,28 +63,9 @@
 #include "intel_frontbuffer.h"
 #include "intel_psr.h"
 
-void __intel_fb_obj_invalidate(struct drm_i915_gem_object *obj,
-			       enum fb_op_origin origin,
-			       unsigned int frontbuffer_bits)
-{
-	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
-
-	if (origin == ORIGIN_CS) {
-		spin_lock(&dev_priv->fb_tracking.lock);
-		dev_priv->fb_tracking.busy_bits |= frontbuffer_bits;
-		dev_priv->fb_tracking.flip_bits &= ~frontbuffer_bits;
-		spin_unlock(&dev_priv->fb_tracking.lock);
-	}
-
-	might_sleep();
-	intel_psr_invalidate(dev_priv, frontbuffer_bits, origin);
-	intel_edp_drrs_invalidate(dev_priv, frontbuffer_bits);
-	intel_fbc_invalidate(dev_priv, frontbuffer_bits, origin);
-}
-
 /**
- * intel_frontbuffer_flush - flush frontbuffer
- * @dev_priv: i915 device
+ * frontbuffer_flush - flush frontbuffer
+ * @i915: i915 device
  * @frontbuffer_bits: frontbuffer plane tracking bits
  * @origin: which operation caused the flush
  *
@@ -94,45 +75,27 @@ void __intel_fb_obj_invalidate(struct drm_i915_gem_object *obj,
  *
  * Can be called without any locks held.
  */
-static void intel_frontbuffer_flush(struct drm_i915_private *dev_priv,
-				    unsigned frontbuffer_bits,
-				    enum fb_op_origin origin)
+static void frontbuffer_flush(struct drm_i915_private *i915,
+			      unsigned int frontbuffer_bits,
+			      enum fb_op_origin origin)
 {
 	/* Delay flushing when rings are still busy.*/
-	spin_lock(&dev_priv->fb_tracking.lock);
-	frontbuffer_bits &= ~dev_priv->fb_tracking.busy_bits;
-	spin_unlock(&dev_priv->fb_tracking.lock);
+	spin_lock(&i915->fb_tracking.lock);
+	frontbuffer_bits &= ~i915->fb_tracking.busy_bits;
+	spin_unlock(&i915->fb_tracking.lock);
 
 	if (!frontbuffer_bits)
 		return;
 
 	might_sleep();
-	intel_edp_drrs_flush(dev_priv, frontbuffer_bits);
-	intel_psr_flush(dev_priv, frontbuffer_bits, origin);
-	intel_fbc_flush(dev_priv, frontbuffer_bits, origin);
-}
-
-void __intel_fb_obj_flush(struct drm_i915_gem_object *obj,
-			  enum fb_op_origin origin,
-			  unsigned int frontbuffer_bits)
-{
-	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
-
-	if (origin == ORIGIN_CS) {
-		spin_lock(&dev_priv->fb_tracking.lock);
-		/* Filter out new bits since rendering started. */
-		frontbuffer_bits &= dev_priv->fb_tracking.busy_bits;
-		dev_priv->fb_tracking.busy_bits &= ~frontbuffer_bits;
-		spin_unlock(&dev_priv->fb_tracking.lock);
-	}
-
-	if (frontbuffer_bits)
-		intel_frontbuffer_flush(dev_priv, frontbuffer_bits, origin);
+	intel_edp_drrs_flush(i915, frontbuffer_bits);
+	intel_psr_flush(i915, frontbuffer_bits, origin);
+	intel_fbc_flush(i915, frontbuffer_bits, origin);
 }
 
 /**
  * intel_frontbuffer_flip_prepare - prepare asynchronous frontbuffer flip
- * @dev_priv: i915 device
+ * @i915: i915 device
  * @frontbuffer_bits: frontbuffer plane tracking bits
  *
  * This function gets called after scheduling a flip on @obj. The actual
@@ -142,19 +105,19 @@ void __intel_fb_obj_flush(struct drm_i915_gem_object *obj,
  *
  * Can be called without any locks held.
  */
-void intel_frontbuffer_flip_prepare(struct drm_i915_private *dev_priv,
+void intel_frontbuffer_flip_prepare(struct drm_i915_private *i915,
 				    unsigned frontbuffer_bits)
 {
-	spin_lock(&dev_priv->fb_tracking.lock);
-	dev_priv->fb_tracking.flip_bits |= frontbuffer_bits;
+	spin_lock(&i915->fb_tracking.lock);
+	i915->fb_tracking.flip_bits |= frontbuffer_bits;
 	/* Remove stale busy bits due to the old buffer. */
-	dev_priv->fb_tracking.busy_bits &= ~frontbuffer_bits;
-	spin_unlock(&dev_priv->fb_tracking.lock);
+	i915->fb_tracking.busy_bits &= ~frontbuffer_bits;
+	spin_unlock(&i915->fb_tracking.lock);
 }
 
 /**
  * intel_frontbuffer_flip_complete - complete asynchronous frontbuffer flip
- * @dev_priv: i915 device
+ * @i915: i915 device
  * @frontbuffer_bits: frontbuffer plane tracking bits
  *
  * This function gets called after the flip has been latched and will complete
@@ -162,23 +125,22 @@ void intel_frontbuffer_flip_prepare(struct drm_i915_private *dev_priv,
  *
  * Can be called without any locks held.
  */
-void intel_frontbuffer_flip_complete(struct drm_i915_private *dev_priv,
+void intel_frontbuffer_flip_complete(struct drm_i915_private *i915,
 				     unsigned frontbuffer_bits)
 {
-	spin_lock(&dev_priv->fb_tracking.lock);
+	spin_lock(&i915->fb_tracking.lock);
 	/* Mask any cancelled flips. */
-	frontbuffer_bits &= dev_priv->fb_tracking.flip_bits;
-	dev_priv->fb_tracking.flip_bits &= ~frontbuffer_bits;
-	spin_unlock(&dev_priv->fb_tracking.lock);
+	frontbuffer_bits &= i915->fb_tracking.flip_bits;
+	i915->fb_tracking.flip_bits &= ~frontbuffer_bits;
+	spin_unlock(&i915->fb_tracking.lock);
 
 	if (frontbuffer_bits)
-		intel_frontbuffer_flush(dev_priv,
-					frontbuffer_bits, ORIGIN_FLIP);
+		frontbuffer_flush(i915, frontbuffer_bits, ORIGIN_FLIP);
 }
 
 /**
  * intel_frontbuffer_flip - synchronous frontbuffer flip
- * @dev_priv: i915 device
+ * @i915: i915 device
  * @frontbuffer_bits: frontbuffer plane tracking bits
  *
  * This function gets called after scheduling a flip on @obj. This is for
@@ -187,13 +149,160 @@ void intel_frontbuffer_flip_complete(struct drm_i915_private *dev_priv,
  *
  * Can be called without any locks held.
  */
-void intel_frontbuffer_flip(struct drm_i915_private *dev_priv,
+void intel_frontbuffer_flip(struct drm_i915_private *i915,
 			    unsigned frontbuffer_bits)
 {
-	spin_lock(&dev_priv->fb_tracking.lock);
+	spin_lock(&i915->fb_tracking.lock);
 	/* Remove stale busy bits due to the old buffer. */
-	dev_priv->fb_tracking.busy_bits &= ~frontbuffer_bits;
-	spin_unlock(&dev_priv->fb_tracking.lock);
+	i915->fb_tracking.busy_bits &= ~frontbuffer_bits;
+	spin_unlock(&i915->fb_tracking.lock);
 
-	intel_frontbuffer_flush(dev_priv, frontbuffer_bits, ORIGIN_FLIP);
+	frontbuffer_flush(i915, frontbuffer_bits, ORIGIN_FLIP);
+}
+
+void __intel_fb_invalidate(struct intel_frontbuffer *front,
+			   enum fb_op_origin origin,
+			   unsigned int frontbuffer_bits)
+{
+	struct drm_i915_private *i915 = to_i915(front->obj->base.dev);
+
+	if (origin == ORIGIN_CS) {
+		spin_lock(&i915->fb_tracking.lock);
+		i915->fb_tracking.busy_bits |= frontbuffer_bits;
+		i915->fb_tracking.flip_bits &= ~frontbuffer_bits;
+		spin_unlock(&i915->fb_tracking.lock);
+	}
+
+	might_sleep();
+	intel_psr_invalidate(i915, frontbuffer_bits, origin);
+	intel_edp_drrs_invalidate(i915, frontbuffer_bits);
+	intel_fbc_invalidate(i915, frontbuffer_bits, origin);
+}
+
+void __intel_fb_flush(struct intel_frontbuffer *front,
+		      enum fb_op_origin origin,
+		      unsigned int frontbuffer_bits)
+{
+	struct drm_i915_private *i915 = to_i915(front->obj->base.dev);
+
+	if (origin == ORIGIN_CS) {
+		spin_lock(&i915->fb_tracking.lock);
+		/* Filter out new bits since rendering started. */
+		frontbuffer_bits &= i915->fb_tracking.busy_bits;
+		i915->fb_tracking.busy_bits &= ~frontbuffer_bits;
+		spin_unlock(&i915->fb_tracking.lock);
+	}
+
+	if (frontbuffer_bits)
+		frontbuffer_flush(i915, frontbuffer_bits, origin);
+}
+
+static int frontbuffer_active(struct i915_active *ref)
+{
+	struct intel_frontbuffer *front =
+		container_of(ref, typeof(*front), write);
+
+	kref_get(&front->ref);
+	return 0;
+}
+
+static void frontbuffer_retire(struct i915_active *ref)
+{
+	struct intel_frontbuffer *front =
+		container_of(ref, typeof(*front), write);
+
+	intel_frontbuffer_flush(front, ORIGIN_CS);
+	intel_frontbuffer_put(front);
+}
+
+static void frontbuffer_release(struct kref *ref)
+	__releases(&to_i915(front->obj->base.dev)->fb_tracking.lock)
+{
+	struct intel_frontbuffer *front =
+		container_of(ref, typeof(*front), ref);
+
+	front->obj->frontbuffer = NULL;
+	spin_unlock(&to_i915(front->obj->base.dev)->fb_tracking.lock);
+
+	i915_gem_object_put(front->obj);
+	kfree(front);
+}
+
+struct intel_frontbuffer *
+intel_frontbuffer_get(struct drm_i915_gem_object *obj)
+{
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	struct intel_frontbuffer *front;
+
+	spin_lock(&i915->fb_tracking.lock);
+	front = obj->frontbuffer;
+	if (front)
+		kref_get(&front->ref);
+	spin_unlock(&i915->fb_tracking.lock);
+	if (front)
+		return front;
+
+	front = kmalloc(sizeof(*front), GFP_KERNEL);
+	if (!front)
+		return NULL;
+
+	front->obj = obj;
+	kref_init(&front->ref);
+	atomic_set(&front->bits, 0);
+	i915_active_init(i915, &front->write,
+			 frontbuffer_active, frontbuffer_retire);
+
+	spin_lock(&i915->fb_tracking.lock);
+	if (obj->frontbuffer) {
+		kfree(front);
+		front = obj->frontbuffer;
+		kref_get(&front->ref);
+	} else {
+		i915_gem_object_get(obj);
+		obj->frontbuffer = front;
+	}
+	spin_unlock(&i915->fb_tracking.lock);
+
+	return front;
+}
+
+void intel_frontbuffer_put(struct intel_frontbuffer *front)
+{
+	kref_put_lock(&front->ref,
+		      frontbuffer_release,
+		      &to_i915(front->obj->base.dev)->fb_tracking.lock);
+}
+
+/**
+ * intel_frontbuffer_track - update frontbuffer tracking
+ * @old: current buffer for the frontbuffer slots
+ * @new: new buffer for the frontbuffer slots
+ * @frontbuffer_bits: bitmask of frontbuffer slots
+ *
+ * This updates the frontbuffer tracking bits @frontbuffer_bits by clearing them
+ * from @old and setting them in @new. Both @old and @new can be NULL.
+ */
+void intel_frontbuffer_track(struct intel_frontbuffer *old,
+			     struct intel_frontbuffer *new,
+			     unsigned int frontbuffer_bits)
+{
+	/*
+	 * Control of individual bits within the mask are guarded by
+	 * the owning plane->mutex, i.e. we can never see concurrent
+	 * manipulation of individual bits. But since the bitfield as a whole
+	 * is updated using RMW, we need to use atomics in order to update
+	 * the bits.
+	 */
+	BUILD_BUG_ON(INTEL_FRONTBUFFER_BITS_PER_PIPE * I915_MAX_PIPES >
+		     BITS_PER_TYPE(atomic_t));
+
+	if (old) {
+		WARN_ON(!(atomic_read(&old->bits) & frontbuffer_bits));
+		atomic_andnot(frontbuffer_bits, &old->bits);
+	}
+
+	if (new) {
+		WARN_ON(atomic_read(&new->bits) & frontbuffer_bits);
+		atomic_or(frontbuffer_bits, &new->bits);
+	}
 }
diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.h b/drivers/gpu/drm/i915/display/intel_frontbuffer.h
index 5727320c8084..adc64d61a4a5 100644
--- a/drivers/gpu/drm/i915/display/intel_frontbuffer.h
+++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.h
@@ -24,7 +24,10 @@
 #ifndef __INTEL_FRONTBUFFER_H__
 #define __INTEL_FRONTBUFFER_H__
 
-#include "gem/i915_gem_object.h"
+#include <linux/atomic.h>
+#include <linux/kref.h>
+
+#include "i915_active.h"
 
 struct drm_i915_private;
 struct drm_i915_gem_object;
@@ -37,23 +40,30 @@ enum fb_op_origin {
 	ORIGIN_DIRTYFB,
 };
 
-void intel_frontbuffer_flip_prepare(struct drm_i915_private *dev_priv,
+struct intel_frontbuffer {
+	struct kref ref;
+	atomic_t bits;
+	struct i915_active write;
+	struct drm_i915_gem_object *obj;
+};
+
+void intel_frontbuffer_flip_prepare(struct drm_i915_private *i915,
 				    unsigned frontbuffer_bits);
-void intel_frontbuffer_flip_complete(struct drm_i915_private *dev_priv,
+void intel_frontbuffer_flip_complete(struct drm_i915_private *i915,
 				     unsigned frontbuffer_bits);
-void intel_frontbuffer_flip(struct drm_i915_private *dev_priv,
+void intel_frontbuffer_flip(struct drm_i915_private *i915,
 			    unsigned frontbuffer_bits);
 
-void __intel_fb_obj_invalidate(struct drm_i915_gem_object *obj,
-			       enum fb_op_origin origin,
-			       unsigned int frontbuffer_bits);
-void __intel_fb_obj_flush(struct drm_i915_gem_object *obj,
-			  enum fb_op_origin origin,
-			  unsigned int frontbuffer_bits);
+struct intel_frontbuffer *
+intel_frontbuffer_get(struct drm_i915_gem_object *obj);
+
+void __intel_fb_invalidate(struct intel_frontbuffer *front,
+			   enum fb_op_origin origin,
+			   unsigned int frontbuffer_bits);
 
 /**
- * intel_fb_obj_invalidate - invalidate frontbuffer object
- * @obj: GEM object to invalidate
+ * intel_frontbuffer_invalidate - invalidate frontbuffer object
+ * @front: GEM object to invalidate
  * @origin: which operation caused the invalidation
  *
  * This function gets called every time rendering on the given object starts and
@@ -62,37 +72,53 @@ void __intel_fb_obj_flush(struct drm_i915_gem_object *obj,
  * until the rendering completes or a flip on this frontbuffer plane is
  * scheduled.
  */
-static inline bool intel_fb_obj_invalidate(struct drm_i915_gem_object *obj,
-					   enum fb_op_origin origin)
+static inline bool intel_frontbuffer_invalidate(struct intel_frontbuffer *front,
+						enum fb_op_origin origin)
 {
 	unsigned int frontbuffer_bits;
 
-	frontbuffer_bits = atomic_read(&obj->frontbuffer_bits);
+	if (!front)
+		return false;
+
+	frontbuffer_bits = atomic_read(&front->bits);
 	if (!frontbuffer_bits)
 		return false;
 
-	__intel_fb_obj_invalidate(obj, origin, frontbuffer_bits);
+	__intel_fb_invalidate(front, origin, frontbuffer_bits);
 	return true;
 }
 
+void __intel_fb_flush(struct intel_frontbuffer *front,
+		      enum fb_op_origin origin,
+		      unsigned int frontbuffer_bits);
+
 /**
- * intel_fb_obj_flush - flush frontbuffer object
- * @obj: GEM object to flush
+ * intel_frontbuffer_flush - flush frontbuffer object
+ * @front: GEM object to flush
  * @origin: which operation caused the flush
  *
  * This function gets called every time rendering on the given object has
  * completed and frontbuffer caching can be started again.
  */
-static inline void intel_fb_obj_flush(struct drm_i915_gem_object *obj,
-				      enum fb_op_origin origin)
+static inline void intel_frontbuffer_flush(struct intel_frontbuffer *front,
+					   enum fb_op_origin origin)
 {
 	unsigned int frontbuffer_bits;
 
-	frontbuffer_bits = atomic_read(&obj->frontbuffer_bits);
+	if (!front)
+		return;
+
+	frontbuffer_bits = atomic_read(&front->bits);
 	if (!frontbuffer_bits)
 		return;
 
-	__intel_fb_obj_flush(obj, origin, frontbuffer_bits);
+	__intel_fb_flush(front, origin, frontbuffer_bits);
 }
 
+void intel_frontbuffer_track(struct intel_frontbuffer *old,
+			     struct intel_frontbuffer *new,
+			     unsigned int frontbuffer_bits);
+
+void intel_frontbuffer_put(struct intel_frontbuffer *front);
+
 #endif /* __INTEL_FRONTBUFFER_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c
index 9b3f4f6644f3..1a15fa34205c 100644
--- a/drivers/gpu/drm/i915/display/intel_overlay.c
+++ b/drivers/gpu/drm/i915/display/intel_overlay.c
@@ -281,9 +281,9 @@ static void intel_overlay_flip_prepare(struct intel_overlay *overlay,
 
 	WARN_ON(overlay->old_vma);
 
-	i915_gem_track_fb(overlay->vma ? overlay->vma->obj : NULL,
-			  vma ? vma->obj : NULL,
-			  INTEL_FRONTBUFFER_OVERLAY(pipe));
+	intel_frontbuffer_track(overlay->vma ? overlay->vma->obj->frontbuffer : NULL,
+				vma ? vma->obj->frontbuffer : NULL,
+				INTEL_FRONTBUFFER_OVERLAY(pipe));
 
 	intel_frontbuffer_flip_prepare(overlay->i915,
 				       INTEL_FRONTBUFFER_OVERLAY(pipe));
@@ -768,7 +768,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 		ret = PTR_ERR(vma);
 		goto out_pin_section;
 	}
-	intel_fb_obj_flush(new_bo, ORIGIN_DIRTYFB);
+	intel_frontbuffer_flush(new_bo->frontbuffer, ORIGIN_DIRTYFB);
 
 	ret = i915_vma_put_fence(vma);
 	if (ret)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
index 5295285d5843..a65d401f891c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
@@ -48,7 +48,7 @@ static void __i915_do_clflush(struct drm_i915_gem_object *obj)
 {
 	GEM_BUG_ON(!i915_gem_object_has_pages(obj));
 	drm_clflush_sg(obj->mm.pages);
-	intel_fb_obj_flush(obj, ORIGIN_CPU);
+	intel_frontbuffer_flush(obj->frontbuffer, ORIGIN_CPU);
 }
 
 static void i915_clflush_work(struct work_struct *work)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index 2e3ce2a69653..a1afc2690e9e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -551,13 +551,6 @@ i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write)
 	return 0;
 }
 
-static inline enum fb_op_origin
-fb_write_origin(struct drm_i915_gem_object *obj, unsigned int domain)
-{
-	return (domain == I915_GEM_DOMAIN_GTT ?
-		obj->frontbuffer_ggtt_origin : ORIGIN_CPU);
-}
-
 /**
  * Called when user space prepares to use an object with the CPU, either
  * through the mmap ioctl's mapping or a GTT mapping.
@@ -661,9 +654,8 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
 
 	i915_gem_object_unlock(obj);
 
-	if (write_domain != 0)
-		intel_fb_obj_invalidate(obj,
-					fb_write_origin(obj, write_domain));
+	if (write_domain)
+		intel_frontbuffer_invalidate(obj->frontbuffer, ORIGIN_CPU);
 
 out_unpin:
 	i915_gem_object_unpin_pages(obj);
@@ -783,7 +775,7 @@ int i915_gem_object_prepare_write(struct drm_i915_gem_object *obj,
 	}
 
 out:
-	intel_fb_obj_invalidate(obj, ORIGIN_CPU);
+	intel_frontbuffer_invalidate(obj->frontbuffer, ORIGIN_CPU);
 	obj->mm.dirty = true;
 	/* return with the pages pinned */
 	return 0;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 391621ee3cbb..bcc53c2b4f69 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -99,9 +99,6 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
 		up_write(&mm->mmap_sem);
 		if (IS_ERR_VALUE(addr))
 			goto err;
-
-		/* This may race, but that's ok, it only gets set */
-		WRITE_ONCE(obj->frontbuffer_ggtt_origin, ORIGIN_CPU);
 	}
 	i915_gem_object_put(obj);
 
@@ -281,7 +278,6 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 		 * Userspace is now writing through an untracked VMA, abandon
 		 * all hope that the hardware is able to track future writes.
 		 */
-		obj->frontbuffer_ggtt_origin = ORIGIN_CPU;
 
 		vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, flags);
 		if (IS_ERR(vma) && !view.type) {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index aded95375096..3b9c61f0646f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -45,16 +45,6 @@ void i915_gem_object_free(struct drm_i915_gem_object *obj)
 	return kmem_cache_free(global.slab_objects, obj);
 }
 
-static void
-frontbuffer_retire(struct i915_active_request *active,
-		   struct i915_request *request)
-{
-	struct drm_i915_gem_object *obj =
-		container_of(active, typeof(*obj), frontbuffer_write);
-
-	intel_fb_obj_flush(obj, ORIGIN_CS);
-}
-
 void i915_gem_object_init(struct drm_i915_gem_object *obj,
 			  const struct drm_i915_gem_object_ops *ops)
 {
@@ -69,10 +59,6 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 
 	obj->ops = ops;
 
-	obj->frontbuffer_ggtt_origin = ORIGIN_GTT;
-	i915_active_request_init(&obj->frontbuffer_write,
-				 NULL, frontbuffer_retire);
-
 	obj->mm.madv = I915_MADV_WILLNEED;
 	INIT_RADIX_TREE(&obj->mm.get_page.radix, GFP_KERNEL | __GFP_NOWARN);
 	mutex_init(&obj->mm.get_page.lock);
@@ -184,7 +170,6 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 
 		GEM_BUG_ON(atomic_read(&obj->bind_count));
 		GEM_BUG_ON(obj->userfault_count);
-		GEM_BUG_ON(atomic_read(&obj->frontbuffer_bits));
 		GEM_BUG_ON(!list_empty(&obj->lut_list));
 
 		atomic_set(&obj->mm.pages_pin_count, 0);
@@ -257,6 +242,8 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 	struct drm_i915_gem_object *obj = to_intel_bo(gem_obj);
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 
+	GEM_BUG_ON(i915_gem_object_is_framebuffer(obj));
+
 	/*
 	 * Before we free the object, make sure any pure RCU-only
 	 * read-side critical sections are complete, e.g.
@@ -295,13 +282,6 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 		queue_work(i915->wq, &i915->mm.free_work);
 }
 
-static inline enum fb_op_origin
-fb_write_origin(struct drm_i915_gem_object *obj, unsigned int domain)
-{
-	return (domain == I915_GEM_DOMAIN_GTT ?
-		obj->frontbuffer_ggtt_origin : ORIGIN_CPU);
-}
-
 static bool gpu_write_needs_clflush(struct drm_i915_gem_object *obj)
 {
 	return !(obj->cache_level == I915_CACHE_NONE ||
@@ -324,8 +304,7 @@ i915_gem_object_flush_write_domain(struct drm_i915_gem_object *obj,
 		for_each_ggtt_vma(vma, obj)
 			intel_gt_flush_ggtt_writes(vma->vm->gt);
 
-		intel_fb_obj_flush(obj,
-				   fb_write_origin(obj, I915_GEM_DOMAIN_GTT));
+		intel_frontbuffer_flush(obj->frontbuffer, ORIGIN_CPU);
 
 		for_each_ggtt_vma(vma, obj) {
 			if (vma->iomap)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 20754c15412a..b3340647ab7f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -161,7 +161,7 @@ i915_gem_object_needs_async_cancel(const struct drm_i915_gem_object *obj)
 static inline bool
 i915_gem_object_is_framebuffer(const struct drm_i915_gem_object *obj)
 {
-	return READ_ONCE(obj->framebuffer_references);
+	return READ_ONCE(obj->frontbuffer);
 }
 
 static inline unsigned int
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index d474c6ac4100..ede0eb4218a8 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -13,6 +13,7 @@
 #include "i915_selftest.h"
 
 struct drm_i915_gem_object;
+struct intel_fronbuffer;
 
 /*
  * struct i915_lut_handle tracks the fast lookups from handle to vma used
@@ -141,9 +142,7 @@ struct drm_i915_gem_object {
 	 */
 	u16 write_domain;
 
-	atomic_t frontbuffer_bits;
-	unsigned int frontbuffer_ggtt_origin; /* write once */
-	struct i915_active_request frontbuffer_write;
+	struct intel_frontbuffer *frontbuffer;
 
 	/** Current tiling stride for the object, if it's tiled. */
 	unsigned int tiling_and_stride;
@@ -224,9 +223,6 @@ struct drm_i915_gem_object {
 		bool quirked:1;
 	} mm;
 
-	/** References from framebuffers, locks out tiling changes. */
-	unsigned int framebuffer_references;
-
 	/** Record of address bit 17 of each page at last unbind. */
 	unsigned long *bit_17;
 
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 2c2d2a01853a..bc5af2d2909a 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -136,7 +136,6 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	struct intel_engine_cs *engine;
 	struct i915_vma *vma;
-	unsigned int frontbuffer_bits;
 	int pin_count = 0;
 
 	seq_printf(m, "%pK: %c%c%c%c %8zdKiB %02x %02x %s%s%s",
@@ -226,10 +225,6 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 	engine = i915_gem_object_last_write_engine(obj);
 	if (engine)
 		seq_printf(m, " (%s)", engine->name);
-
-	frontbuffer_bits = atomic_read(&obj->frontbuffer_bits);
-	if (frontbuffer_bits)
-		seq_printf(m, " (frontbuffer: 0x%03x)", frontbuffer_bits);
 }
 
 struct file_stats {
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f9878cbef4d9..64d8de4d7716 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2504,10 +2504,6 @@ int i915_gem_mmap_gtt(struct drm_file *file_priv, struct drm_device *dev,
 		      u32 handle, u64 *offset);
 int i915_gem_mmap_gtt_version(void);
 
-void i915_gem_track_fb(struct drm_i915_gem_object *old,
-		       struct drm_i915_gem_object *new,
-		       unsigned frontbuffer_bits);
-
 int __must_check i915_gem_set_global_seqno(struct drm_device *dev, u32 seqno);
 
 static inline bool __i915_wedged(struct i915_gpu_error *error)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index b6f3baa74da4..c42f2146675c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -138,17 +138,19 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj,
 	void *vaddr = obj->phys_handle->vaddr + args->offset;
 	char __user *user_data = u64_to_user_ptr(args->data_ptr);
 
-	/* We manually control the domain here and pretend that it
+	/*
+	 * We manually control the domain here and pretend that it
 	 * remains coherent i.e. in the GTT domain, like shmem_pwrite.
 	 */
-	intel_fb_obj_invalidate(obj, ORIGIN_CPU);
+	intel_frontbuffer_invalidate(obj->frontbuffer, ORIGIN_CPU);
+
 	if (copy_from_user(vaddr, user_data, args->size))
 		return -EFAULT;
 
 	drm_clflush_virt_range(vaddr, args->size);
 	intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt);
 
-	intel_fb_obj_flush(obj, ORIGIN_CPU);
+	intel_frontbuffer_flush(obj->frontbuffer, ORIGIN_CPU);
 	return 0;
 }
 
@@ -596,7 +598,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 		goto out_unpin;
 	}
 
-	intel_fb_obj_invalidate(obj, ORIGIN_CPU);
+	intel_frontbuffer_invalidate(obj->frontbuffer, ORIGIN_CPU);
 
 	user_data = u64_to_user_ptr(args->data_ptr);
 	offset = args->offset;
@@ -637,7 +639,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 		user_data += page_length;
 		offset += page_length;
 	}
-	intel_fb_obj_flush(obj, ORIGIN_CPU);
+	intel_frontbuffer_flush(obj->frontbuffer, ORIGIN_CPU);
 
 	i915_gem_object_unlock_fence(obj, fence);
 out_unpin:
@@ -730,7 +732,7 @@ i915_gem_shmem_pwrite(struct drm_i915_gem_object *obj,
 		offset = 0;
 	}
 
-	intel_fb_obj_flush(obj, ORIGIN_CPU);
+	intel_frontbuffer_flush(obj->frontbuffer, ORIGIN_CPU);
 	i915_gem_object_unlock_fence(obj, fence);
 
 	return ret;
@@ -1783,39 +1785,6 @@ int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file)
 	return ret;
 }
 
-/**
- * i915_gem_track_fb - update frontbuffer tracking
- * @old: current GEM buffer for the frontbuffer slots
- * @new: new GEM buffer for the frontbuffer slots
- * @frontbuffer_bits: bitmask of frontbuffer slots
- *
- * This updates the frontbuffer tracking bits @frontbuffer_bits by clearing them
- * from @old and setting them in @new. Both @old and @new can be NULL.
- */
-void i915_gem_track_fb(struct drm_i915_gem_object *old,
-		       struct drm_i915_gem_object *new,
-		       unsigned frontbuffer_bits)
-{
-	/* Control of individual bits within the mask are guarded by
-	 * the owning plane->mutex, i.e. we can never see concurrent
-	 * manipulation of individual bits. But since the bitfield as a whole
-	 * is updated using RMW, we need to use atomics in order to update
-	 * the bits.
-	 */
-	BUILD_BUG_ON(INTEL_FRONTBUFFER_BITS_PER_PIPE * I915_MAX_PIPES >
-		     BITS_PER_TYPE(atomic_t));
-
-	if (old) {
-		WARN_ON(!(atomic_read(&old->frontbuffer_bits) & frontbuffer_bits));
-		atomic_andnot(frontbuffer_bits, &old->frontbuffer_bits);
-	}
-
-	if (new) {
-		WARN_ON(atomic_read(&new->frontbuffer_bits) & frontbuffer_bits);
-		atomic_or(frontbuffer_bits, &new->frontbuffer_bits);
-	}
-}
-
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/mock_gem_device.c"
 #include "selftests/i915_gem.c"
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index f4bc5be3cfe5..40fd08ab47dc 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -927,8 +927,10 @@ int i915_vma_move_to_active(struct i915_vma *vma,
 	if (flags & EXEC_OBJECT_WRITE) {
 		obj->write_domain = I915_GEM_DOMAIN_RENDER;
 
-		if (intel_fb_obj_invalidate(obj, ORIGIN_CS))
-			__i915_active_request_set(&obj->frontbuffer_write, rq);
+		if (intel_frontbuffer_invalidate(obj->frontbuffer, ORIGIN_CS))
+			i915_active_ref(&obj->frontbuffer->write,
+					rq->fence.context,
+					rq);
 
 		obj->read_domains = 0;
 	}
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 770f9f6aad84..f73179de61a0 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -69,6 +69,7 @@ enum intel_output_type {
 
 struct intel_framebuffer {
 	struct drm_framebuffer base;
+	struct intel_frontbuffer *frontbuffer;
 	struct intel_rotation_info rot_info;
 
 	/* for each plane in the normal GTT view */
-- 
2.22.0

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

[PATCH 18/18] drm/i915/gt: Use intel_gt as the primary object for handling resets

[Chris Wilson]

Having taken the first step in encapsulating the functionality by moving
the related files under gt/, the next step is to start encapsulating by
passing around the relevant structs rather than the global
drm_i915_private. In this step, we pass intel_gt to intel_reset.c

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c  |  22 +-
 drivers/gpu/drm/i915/gem/i915_gem_context.c   |   2 +-
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    |   2 +-
 drivers/gpu/drm/i915/gem/i915_gem_mman.c      |   8 +-
 drivers/gpu/drm/i915/gem/i915_gem_pm.c        |  25 +-
 drivers/gpu/drm/i915/gem/i915_gem_throttle.c  |   2 +-
 .../gpu/drm/i915/gem/selftests/huge_pages.c   |  20 +-
 .../i915/gem/selftests/i915_gem_client_blt.c  |   4 +-
 .../i915/gem/selftests/i915_gem_coherency.c   |   6 +-
 .../drm/i915/gem/selftests/i915_gem_context.c |  17 +-
 .../drm/i915/gem/selftests/i915_gem_mman.c    |   2 +-
 .../i915/gem/selftests/i915_gem_object_blt.c  |   4 +-
 drivers/gpu/drm/i915/gt/intel_engine.h        |   8 +-
 drivers/gpu/drm/i915/gt/intel_engine_cs.c     |  16 +-
 drivers/gpu/drm/i915/gt/intel_engine_pm.c     |   3 +-
 drivers/gpu/drm/i915/gt/intel_gt.c            |   7 +
 drivers/gpu/drm/i915/gt/intel_gt.h            |  12 +
 drivers/gpu/drm/i915/gt/intel_gt_pm.c         |  22 +-
 drivers/gpu/drm/i915/gt/intel_gt_types.h      |  12 +
 drivers/gpu/drm/i915/gt/intel_hangcheck.c     |  67 ++-
 drivers/gpu/drm/i915/gt/intel_lrc.c           |   2 +-
 drivers/gpu/drm/i915/gt/intel_reset.c         | 435 ++++++++---------
 drivers/gpu/drm/i915/gt/intel_reset.h         |  73 +--
 drivers/gpu/drm/i915/gt/intel_reset_types.h   |  50 ++
 drivers/gpu/drm/i915/gt/intel_ringbuffer.c    |   2 +-
 drivers/gpu/drm/i915/gt/selftest_hangcheck.c  | 461 +++++++++---------
 drivers/gpu/drm/i915/gt/selftest_lrc.c        |  38 +-
 drivers/gpu/drm/i915/gt/selftest_reset.c      |  93 ++--
 drivers/gpu/drm/i915/gt/selftest_timeline.c   |   3 +-
 .../gpu/drm/i915/gt/selftest_workarounds.c    |  33 +-
 drivers/gpu/drm/i915/i915_debugfs.c           |  63 +--
 drivers/gpu/drm/i915/i915_drv.c               |   5 +-
 drivers/gpu/drm/i915/i915_drv.h               |  35 +-
 drivers/gpu/drm/i915/i915_gem.c               |  31 +-
 drivers/gpu/drm/i915/i915_gpu_error.h         |  52 +-
 drivers/gpu/drm/i915/i915_request.c           |   5 +-
 drivers/gpu/drm/i915/i915_selftest.h          |   9 +
 drivers/gpu/drm/i915/intel_guc_submission.c   |   2 +-
 drivers/gpu/drm/i915/intel_uc.c               |   2 +-
 drivers/gpu/drm/i915/selftests/i915_active.c  |   3 +-
 drivers/gpu/drm/i915/selftests/i915_gem.c     |   3 +-
 .../gpu/drm/i915/selftests/i915_gem_evict.c   |   3 +-
 drivers/gpu/drm/i915/selftests/i915_request.c |   4 +-
 .../gpu/drm/i915/selftests/i915_selftest.c    |  23 +-
 .../gpu/drm/i915/selftests/igt_flush_test.c   |   5 +-
 drivers/gpu/drm/i915/selftests/igt_reset.c    |  38 +-
 drivers/gpu/drm/i915/selftests/igt_reset.h    |  10 +-
 drivers/gpu/drm/i915/selftests/igt_wedge_me.h |  58 ---
 .../gpu/drm/i915/selftests/mock_gem_device.c  |   5 -
 49 files changed, 897 insertions(+), 910 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/gt/intel_reset_types.h
 delete mode 100644 drivers/gpu/drm/i915/selftests/igt_wedge_me.h

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index ed3532e4c8ad..736a781ea302 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -4275,12 +4275,13 @@ void intel_prepare_reset(struct drm_i915_private *dev_priv)
 		return;
 
 	/* We have a modeset vs reset deadlock, defensively unbreak it. */
-	set_bit(I915_RESET_MODESET, &dev_priv->gpu_error.flags);
-	wake_up_all(&dev_priv->gpu_error.wait_queue);
+	set_bit(I915_RESET_MODESET, &dev_priv->gt.reset.flags);
+	smp_mb__after_atomic();
+	wake_up_bit(&dev_priv->gt.reset.flags, I915_RESET_MODESET);
 
 	if (atomic_read(&dev_priv->gpu_error.pending_fb_pin)) {
 		DRM_DEBUG_KMS("Modeset potentially stuck, unbreaking through wedging\n");
-		i915_gem_set_wedged(dev_priv);
+		intel_gt_set_wedged(&dev_priv->gt);
 	}
 
 	/*
@@ -4326,7 +4327,7 @@ void intel_finish_reset(struct drm_i915_private *dev_priv)
 	int ret;
 
 	/* reset doesn't touch the display */
-	if (!test_bit(I915_RESET_MODESET, &dev_priv->gpu_error.flags))
+	if (!test_bit(I915_RESET_MODESET, &dev_priv->gt.reset.flags))
 		return;
 
 	state = fetch_and_zero(&dev_priv->modeset_restore_state);
@@ -4366,7 +4367,7 @@ void intel_finish_reset(struct drm_i915_private *dev_priv)
 	drm_modeset_acquire_fini(ctx);
 	mutex_unlock(&dev->mode_config.mutex);
 
-	clear_bit(I915_RESET_MODESET, &dev_priv->gpu_error.flags);
+	clear_bit_unlock(I915_RESET_MODESET, &dev_priv->gt.reset.flags);
 }
 
 static void icl_set_pipe_chicken(struct intel_crtc *crtc)
@@ -13861,18 +13862,21 @@ static void intel_atomic_commit_fence_wait(struct intel_atomic_state *intel_stat
 	for (;;) {
 		prepare_to_wait(&intel_state->commit_ready.wait,
 				&wait_fence, TASK_UNINTERRUPTIBLE);
-		prepare_to_wait(&dev_priv->gpu_error.wait_queue,
+		prepare_to_wait(bit_waitqueue(&dev_priv->gt.reset.flags,
+					      I915_RESET_MODESET),
 				&wait_reset, TASK_UNINTERRUPTIBLE);
 
 
-		if (i915_sw_fence_done(&intel_state->commit_ready)
-		    || test_bit(I915_RESET_MODESET, &dev_priv->gpu_error.flags))
+		if (i915_sw_fence_done(&intel_state->commit_ready) ||
+		    test_bit(I915_RESET_MODESET, &dev_priv->gt.reset.flags))
 			break;
 
 		schedule();
 	}
 	finish_wait(&intel_state->commit_ready.wait, &wait_fence);
-	finish_wait(&dev_priv->gpu_error.wait_queue, &wait_reset);
+	finish_wait(bit_waitqueue(&dev_priv->gt.reset.flags,
+				  I915_RESET_MODESET),
+		    &wait_reset);
 }
 
 static void intel_atomic_cleanup_work(struct work_struct *work)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 9d4ba6928884..cea56884cfd2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -2134,7 +2134,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 	if (args->flags & I915_CONTEXT_CREATE_FLAGS_UNKNOWN)
 		return -EINVAL;
 
-	ret = i915_terminally_wedged(i915);
+	ret = intel_gt_terminally_wedged(&i915->gt);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 0ea2d49bc8b9..3506aafada6c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2148,7 +2148,7 @@ static int __eb_pin_engine(struct i915_execbuffer *eb, struct intel_context *ce)
 	 * ABI: Before userspace accesses the GPU (e.g. execbuffer), report
 	 * EIO if the GPU is already wedged.
 	 */
-	err = i915_terminally_wedged(eb->i915);
+	err = intel_gt_terminally_wedged(ce->engine->gt);
 	if (err)
 		return err;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index bcc53c2b4f69..71d10ae90922 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -7,6 +7,8 @@
 #include <linux/mman.h>
 #include <linux/sizes.h>
 
+#include "gt/intel_gt.h"
+
 #include "i915_drv.h"
 #include "i915_gem_gtt.h"
 #include "i915_gem_ioctls.h"
@@ -243,7 +245,7 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 
 	wakeref = intel_runtime_pm_get(rpm);
 
-	srcu = i915_reset_trylock(i915);
+	srcu = intel_gt_reset_trylock(ggtt->vm.gt);
 	if (srcu < 0) {
 		ret = srcu;
 		goto err_rpm;
@@ -322,7 +324,7 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 err_unlock:
 	mutex_unlock(&dev->struct_mutex);
 err_reset:
-	i915_reset_unlock(i915, srcu);
+	intel_gt_reset_unlock(ggtt->vm.gt, srcu);
 err_rpm:
 	intel_runtime_pm_put(rpm, wakeref);
 	i915_gem_object_unpin_pages(obj);
@@ -335,7 +337,7 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 		 * fail). But any other -EIO isn't ours (e.g. swap in failure)
 		 * and so needs to be reported.
 		 */
-		if (!i915_terminally_wedged(i915))
+		if (!intel_gt_is_wedged(ggtt->vm.gt))
 			return VM_FAULT_SIGBUS;
 		/* else: fall through */
 	case -EAGAIN:
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index bf085b0cb7c6..8e2eeaec06cb 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -5,6 +5,7 @@
  */
 
 #include "gem/i915_gem_pm.h"
+#include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
 
 #include "i915_drv.h"
@@ -103,18 +104,18 @@ static int pm_notifier(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
-static bool switch_to_kernel_context_sync(struct drm_i915_private *i915)
+static bool switch_to_kernel_context_sync(struct intel_gt *gt)
 {
-	bool result = !i915_terminally_wedged(i915);
+	bool result = !intel_gt_is_wedged(gt);
 
 	do {
-		if (i915_gem_wait_for_idle(i915,
+		if (i915_gem_wait_for_idle(gt->i915,
 					   I915_WAIT_LOCKED |
 					   I915_WAIT_FOR_IDLE_BOOST,
 					   I915_GEM_IDLE_TIMEOUT) == -ETIME) {
 			/* XXX hide warning from gem_eio */
 			if (i915_modparams.reset) {
-				dev_err(i915->drm.dev,
+				dev_err(gt->i915->drm.dev,
 					"Failed to idle engines, declaring wedged!\n");
 				GEM_TRACE_DUMP();
 			}
@@ -123,18 +124,18 @@ static bool switch_to_kernel_context_sync(struct drm_i915_private *i915)
 			 * Forcibly cancel outstanding work and leave
 			 * the gpu quiet.
 			 */
-			i915_gem_set_wedged(i915);
+			intel_gt_set_wedged(gt);
 			result = false;
 		}
-	} while (i915_retire_requests(i915) && result);
+	} while (i915_retire_requests(gt->i915) && result);
 
-	GEM_BUG_ON(i915->gt.awake);
+	GEM_BUG_ON(gt->awake);
 	return result;
 }
 
 bool i915_gem_load_power_context(struct drm_i915_private *i915)
 {
-	return switch_to_kernel_context_sync(i915);
+	return switch_to_kernel_context_sync(&i915->gt);
 }
 
 void i915_gem_suspend(struct drm_i915_private *i915)
@@ -155,7 +156,7 @@ void i915_gem_suspend(struct drm_i915_private *i915)
 	 * state. Fortunately, the kernel_context is disposable and we do
 	 * not rely on its state.
 	 */
-	switch_to_kernel_context_sync(i915);
+	switch_to_kernel_context_sync(&i915->gt);
 
 	mutex_unlock(&i915->drm.struct_mutex);
 
@@ -166,7 +167,7 @@ void i915_gem_suspend(struct drm_i915_private *i915)
 	GEM_BUG_ON(i915->gt.awake);
 	flush_work(&i915->gem.idle_work);
 
-	cancel_delayed_work_sync(&i915->gpu_error.hangcheck_work);
+	cancel_delayed_work_sync(&i915->gt.hangcheck.work);
 
 	i915_gem_drain_freed_objects(i915);
 
@@ -274,10 +275,10 @@ void i915_gem_resume(struct drm_i915_private *i915)
 	return;
 
 err_wedged:
-	if (!i915_reset_failed(i915)) {
+	if (!intel_gt_is_wedged(&i915->gt)) {
 		dev_err(i915->drm.dev,
 			"Failed to re-initialize GPU, declaring it wedged!\n");
-		i915_gem_set_wedged(i915);
+		intel_gt_set_wedged(&i915->gt);
 	}
 	goto out_unlock;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_throttle.c b/drivers/gpu/drm/i915/gem/i915_gem_throttle.c
index adb3074d9ce2..1e372420771b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_throttle.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_throttle.c
@@ -41,7 +41,7 @@ i915_gem_throttle_ioctl(struct drm_device *dev, void *data,
 	long ret;
 
 	/* ABI: return -EIO if already wedged */
-	ret = i915_terminally_wedged(to_i915(dev));
+	ret = intel_gt_terminally_wedged(&to_i915(dev)->gt);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index 86eed4c3ae2b..6cbd4a668c9a 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -1753,7 +1753,7 @@ int i915_gem_huge_page_mock_selftests(void)
 	return err;
 }
 
-int i915_gem_huge_page_live_selftests(struct drm_i915_private *dev_priv)
+int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_shrink_thp),
@@ -1768,22 +1768,22 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *dev_priv)
 	intel_wakeref_t wakeref;
 	int err;
 
-	if (!HAS_PPGTT(dev_priv)) {
+	if (!HAS_PPGTT(i915)) {
 		pr_info("PPGTT not supported, skipping live-selftests\n");
 		return 0;
 	}
 
-	if (i915_terminally_wedged(dev_priv))
+	if (intel_gt_is_wedged(&i915->gt))
 		return 0;
 
-	file = mock_file(dev_priv);
+	file = mock_file(i915);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&dev_priv->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
+	mutex_lock(&i915->drm.struct_mutex);
+	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 
-	ctx = live_context(dev_priv, file);
+	ctx = live_context(i915, file);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
 		goto out_unlock;
@@ -1795,10 +1795,10 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *dev_priv)
 	err = i915_subtests(tests, ctx);
 
 out_unlock:
-	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
+	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
+	mutex_unlock(&i915->drm.struct_mutex);
 
-	mock_file_free(dev_priv, file);
+	mock_file_free(i915, file);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
index fa79233093eb..275c28926067 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
@@ -5,6 +5,8 @@
 
 #include "i915_selftest.h"
 
+#include "gt/intel_gt.h"
+
 #include "selftests/igt_flush_test.h"
 #include "selftests/mock_drm.h"
 #include "mock_context.h"
@@ -101,7 +103,7 @@ int i915_gem_client_blt_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_client_fill),
 	};
 
-	if (i915_terminally_wedged(i915))
+	if (intel_gt_is_wedged(&i915->gt))
 		return 0;
 
 	if (!HAS_ENGINE(i915, BCS0))
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
index 861f32be7d46..a1a4b53cdc4a 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
@@ -6,6 +6,8 @@
 
 #include <linux/prime_numbers.h>
 
+#include "gt/intel_gt.h"
+
 #include "i915_selftest.h"
 #include "selftests/i915_random.h"
 
@@ -242,12 +244,12 @@ static bool always_valid(struct drm_i915_private *i915)
 
 static bool needs_fence_registers(struct drm_i915_private *i915)
 {
-	return !i915_terminally_wedged(i915);
+	return !intel_gt_is_wedged(&i915->gt);
 }
 
 static bool needs_mi_store_dword(struct drm_i915_private *i915)
 {
-	if (i915_terminally_wedged(i915))
+	if (intel_gt_is_wedged(&i915->gt))
 		return false;
 
 	if (!HAS_ENGINE(i915, RCS0))
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 695bfb18b0d4..db7856f0f31e 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -7,6 +7,7 @@
 #include <linux/prime_numbers.h>
 
 #include "gem/i915_gem_pm.h"
+#include "gt/intel_gt.h"
 #include "gt/intel_reset.h"
 #include "i915_selftest.h"
 
@@ -83,7 +84,7 @@ static int live_nop_switch(void *arg)
 		}
 		if (i915_request_wait(rq, 0, HZ / 5) < 0) {
 			pr_err("Failed to populated %d contexts\n", nctx);
-			i915_gem_set_wedged(i915);
+			intel_gt_set_wedged(&i915->gt);
 			err = -EIO;
 			goto out_unlock;
 		}
@@ -127,7 +128,7 @@ static int live_nop_switch(void *arg)
 			if (i915_request_wait(rq, 0, HZ / 5) < 0) {
 				pr_err("Switching between %ld contexts timed out\n",
 				       prime);
-				i915_gem_set_wedged(i915);
+				intel_gt_set_wedged(&i915->gt);
 				break;
 			}
 
@@ -956,7 +957,7 @@ __sseu_finish(struct drm_i915_private *i915,
 	int ret = 0;
 
 	if (flags & TEST_RESET) {
-		ret = i915_reset_engine(ce->engine, "sseu");
+		ret = intel_engine_reset(ce->engine, "sseu");
 		if (ret)
 			goto out;
 	}
@@ -1059,7 +1060,7 @@ __igt_ctx_sseu(struct drm_i915_private *i915,
 		return PTR_ERR(file);
 
 	if (flags & TEST_RESET)
-		igt_global_reset_lock(i915);
+		igt_global_reset_lock(&i915->gt);
 
 	mutex_lock(&i915->drm.struct_mutex);
 
@@ -1120,7 +1121,7 @@ __igt_ctx_sseu(struct drm_i915_private *i915,
 	mutex_unlock(&i915->drm.struct_mutex);
 
 	if (flags & TEST_RESET)
-		igt_global_reset_unlock(i915);
+		igt_global_reset_unlock(&i915->gt);
 
 	mock_file_free(i915, file);
 
@@ -1722,7 +1723,7 @@ int i915_gem_context_mock_selftests(void)
 	return err;
 }
 
-int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv)
+int i915_gem_context_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(live_nop_switch),
@@ -1733,8 +1734,8 @@ int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv)
 		SUBTEST(igt_vm_isolation),
 	};
 
-	if (i915_terminally_wedged(dev_priv))
+	if (intel_gt_is_wedged(&i915->gt))
 		return 0;
 
-	return i915_live_subtests(tests, dev_priv);
+	return i915_live_subtests(tests, i915);
 }
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index 5635cbb4af22..01857c12f12f 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -478,7 +478,7 @@ static int igt_mmap_offset_exhaustion(void *arg)
 
 	/* Now fill with busy dead objects that we expect to reap */
 	for (loop = 0; loop < 3; loop++) {
-		if (i915_terminally_wedged(i915))
+		if (intel_gt_is_wedged(&i915->gt))
 			break;
 
 		obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
index 11d37238c62c..19843acc84d3 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
@@ -3,6 +3,8 @@
  * Copyright © 2019 Intel Corporation
  */
 
+#include "gt/intel_gt.h"
+
 #include "i915_selftest.h"
 
 #include "selftests/igt_flush_test.h"
@@ -95,7 +97,7 @@ int i915_gem_object_blt_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_fill_blt),
 	};
 
-	if (i915_terminally_wedged(i915))
+	if (intel_gt_is_wedged(&i915->gt))
 		return 0;
 
 	if (!HAS_ENGINE(i915, BCS0))
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index faaa164267f4..a4db4dd22b4f 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -410,8 +410,8 @@ gen8_emit_ggtt_write(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
 	return cs;
 }
 
-static inline void intel_engine_reset(struct intel_engine_cs *engine,
-				      bool stalled)
+static inline void __intel_engine_reset(struct intel_engine_cs *engine,
+					bool stalled)
 {
 	if (engine->reset.reset)
 		engine->reset.reset(engine, stalled);
@@ -419,9 +419,9 @@ static inline void intel_engine_reset(struct intel_engine_cs *engine,
 }
 
 bool intel_engine_is_idle(struct intel_engine_cs *engine);
-bool intel_engines_are_idle(struct drm_i915_private *dev_priv);
+bool intel_engines_are_idle(struct intel_gt *gt);
 
-void intel_engines_reset_default_submission(struct drm_i915_private *i915);
+void intel_engines_reset_default_submission(struct intel_gt *gt);
 unsigned int intel_engines_has_context_isolation(struct drm_i915_private *i915);
 
 bool intel_engine_can_store_dword(struct intel_engine_cs *engine);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index e3edf474c377..ee9f9a0cec19 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1147,7 +1147,7 @@ static bool ring_is_idle(struct intel_engine_cs *engine)
 bool intel_engine_is_idle(struct intel_engine_cs *engine)
 {
 	/* More white lies, if wedged, hw state is inconsistent */
-	if (i915_reset_failed(engine->i915))
+	if (intel_gt_is_wedged(engine->gt))
 		return true;
 
 	if (!intel_engine_pm_is_awake(engine))
@@ -1183,7 +1183,7 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 	return ring_is_idle(engine);
 }
 
-bool intel_engines_are_idle(struct drm_i915_private *i915)
+bool intel_engines_are_idle(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -1192,14 +1192,14 @@ bool intel_engines_are_idle(struct drm_i915_private *i915)
 	 * If the driver is wedged, HW state may be very inconsistent and
 	 * report that it is still busy, even though we have stopped using it.
 	 */
-	if (i915_reset_failed(i915))
+	if (intel_gt_is_wedged(gt))
 		return true;
 
 	/* Already parked (and passed an idleness test); must still be idle */
-	if (!READ_ONCE(i915->gt.awake))
+	if (!READ_ONCE(gt->awake))
 		return true;
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		if (!intel_engine_is_idle(engine))
 			return false;
 	}
@@ -1207,12 +1207,12 @@ bool intel_engines_are_idle(struct drm_i915_private *i915)
 	return true;
 }
 
-void intel_engines_reset_default_submission(struct drm_i915_private *i915)
+void intel_engines_reset_default_submission(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	for_each_engine(engine, i915, id)
+	for_each_engine(engine, gt->i915, id)
 		engine->set_default_submission(engine);
 }
 
@@ -1490,7 +1490,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		va_end(ap);
 	}
 
-	if (i915_reset_failed(engine->i915))
+	if (intel_gt_is_wedged(engine->gt))
 		drm_printf(m, "*** WEDGED ***\n");
 
 	drm_printf(m, "\tAwake? %d\n", atomic_read(&engine->wakeref.count));
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 34376d33e4ca..1218b7d53b88 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -9,6 +9,7 @@
 #include "intel_engine.h"
 #include "intel_engine_pool.h"
 #include "intel_engine_pm.h"
+#include "intel_gt.h"
 #include "intel_gt_pm.h"
 
 static int __engine_unpark(struct intel_wakeref *wf)
@@ -77,7 +78,7 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 		return true;
 
 	/* GPU is pointing to the void, as good as in the kernel context. */
-	if (i915_reset_failed(engine->i915))
+	if (intel_gt_is_wedged(engine->gt))
 		return true;
 
 	/*
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 46d24d9d62ac..90ed79285ff8 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -18,6 +18,8 @@ void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
 
 	spin_lock_init(&gt->closed_lock);
 
+	intel_gt_init_hangcheck(gt);
+	intel_gt_init_reset(gt);
 	intel_gt_pm_init_early(gt);
 }
 
@@ -240,3 +242,8 @@ void intel_gt_fini_scratch(struct intel_gt *gt)
 {
 	i915_vma_unpin_and_release(&gt->scratch, 0);
 }
+
+void intel_gt_cleanup_early(struct intel_gt *gt)
+{
+	intel_gt_fini_reset(gt);
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index 1093dcf36f63..49c0085385a0 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -8,12 +8,15 @@
 
 #include "intel_engine_types.h"
 #include "intel_gt_types.h"
+#include "intel_reset.h"
 
 struct drm_i915_private;
 
 void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915);
 void intel_gt_init_hw(struct drm_i915_private *i915);
 
+void intel_gt_cleanup_early(struct intel_gt *gt);
+
 void intel_gt_check_and_clear_faults(struct intel_gt *gt);
 void intel_gt_clear_error_registers(struct intel_gt *gt,
 				    intel_engine_mask_t engine_mask);
@@ -21,6 +24,8 @@ void intel_gt_clear_error_registers(struct intel_gt *gt,
 void intel_gt_flush_ggtt_writes(struct intel_gt *gt);
 void intel_gt_chipset_flush(struct intel_gt *gt);
 
+void intel_gt_init_hangcheck(struct intel_gt *gt);
+
 int intel_gt_init_scratch(struct intel_gt *gt, unsigned int size);
 void intel_gt_fini_scratch(struct intel_gt *gt);
 
@@ -30,4 +35,11 @@ static inline u32 intel_gt_scratch_offset(const struct intel_gt *gt,
 	return i915_ggtt_offset(gt->scratch) + field;
 }
 
+static inline bool intel_gt_is_wedged(struct intel_gt *gt)
+{
+	return __intel_reset_failed(&gt->reset);
+}
+
+void intel_gt_queue_hangcheck(struct intel_gt *gt);
+
 #endif /* __INTEL_GT_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index 36ba80e6a0b7..1013ba0f4984 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -5,7 +5,9 @@
  */
 
 #include "i915_drv.h"
+#include "i915_params.h"
 #include "intel_engine_pm.h"
+#include "intel_gt.h"
 #include "intel_gt_pm.h"
 #include "intel_pm.h"
 #include "intel_wakeref.h"
@@ -17,8 +19,8 @@ static void pm_notify(struct drm_i915_private *i915, int state)
 
 static int intel_gt_unpark(struct intel_wakeref *wf)
 {
-	struct drm_i915_private *i915 =
-		container_of(wf, typeof(*i915), gt.wakeref);
+	struct intel_gt *gt = container_of(wf, typeof(*gt), wakeref);
+	struct drm_i915_private *i915 = gt->i915;
 
 	GEM_TRACE("\n");
 
@@ -33,8 +35,8 @@ static int intel_gt_unpark(struct intel_wakeref *wf)
 	 * Work around it by grabbing a GT IRQ power domain whilst there is any
 	 * GT activity, preventing any DC state transitions.
 	 */
-	i915->gt.awake = intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
-	GEM_BUG_ON(!i915->gt.awake);
+	gt->awake = intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
+	GEM_BUG_ON(!gt->awake);
 
 	intel_enable_gt_powersave(i915);
 
@@ -44,7 +46,7 @@ static int intel_gt_unpark(struct intel_wakeref *wf)
 
 	i915_pmu_gt_unparked(i915);
 
-	i915_queue_hangcheck(i915);
+	intel_gt_queue_hangcheck(gt);
 
 	pm_notify(i915, INTEL_GT_UNPARK);
 
@@ -91,12 +93,12 @@ void intel_gt_pm_init_early(struct intel_gt *gt)
 	BLOCKING_INIT_NOTIFIER_HEAD(&gt->pm_notifications);
 }
 
-static bool reset_engines(struct drm_i915_private *i915)
+static bool reset_engines(struct intel_gt *gt)
 {
-	if (INTEL_INFO(i915)->gpu_reset_clobbers_display)
+	if (INTEL_INFO(gt->i915)->gpu_reset_clobbers_display)
 		return false;
 
-	return intel_gpu_reset(i915, ALL_ENGINES) == 0;
+	return intel_gpu_reset(gt, ALL_ENGINES) == 0;
 }
 
 /**
@@ -116,11 +118,11 @@ void intel_gt_sanitize(struct intel_gt *gt, bool force)
 
 	GEM_TRACE("\n");
 
-	if (!reset_engines(gt->i915) && !force)
+	if (!reset_engines(gt) && !force)
 		return;
 
 	for_each_engine(engine, gt->i915, id)
-		intel_engine_reset(engine, false);
+		__intel_engine_reset(engine, false);
 }
 
 int intel_gt_resume(struct intel_gt *gt)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index b55644132b8f..f35c66b8c67e 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -14,12 +14,21 @@
 #include <linux/types.h>
 
 #include "i915_vma.h"
+#include "intel_reset_types.h"
 #include "intel_wakeref.h"
 
 struct drm_i915_private;
 struct i915_ggtt;
 struct intel_uncore;
 
+struct intel_hangcheck {
+	/* For hangcheck timer */
+#define DRM_I915_HANGCHECK_PERIOD 1500 /* in ms */
+#define DRM_I915_HANGCHECK_JIFFIES msecs_to_jiffies(DRM_I915_HANGCHECK_PERIOD)
+
+	struct delayed_work work;
+};
+
 struct intel_gt {
 	struct drm_i915_private *i915;
 	struct intel_uncore *uncore;
@@ -39,6 +48,9 @@ struct intel_gt {
 	struct list_head closed_vma;
 	spinlock_t closed_lock; /* guards the list of closed_vma */
 
+	struct intel_hangcheck hangcheck;
+	struct intel_reset reset;
+
 	/**
 	 * Is the GPU currently considered idle, or busy executing
 	 * userspace requests? Whilst idle, we allow runtime power
diff --git a/drivers/gpu/drm/i915/gt/intel_hangcheck.c b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
index 797d8ef0969c..88177f47b4d8 100644
--- a/drivers/gpu/drm/i915/gt/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
@@ -22,8 +22,10 @@
  *
  */
 
-#include "intel_reset.h"
 #include "i915_drv.h"
+#include "intel_engine.h"
+#include "intel_gt.h"
+#include "intel_reset.h"
 
 struct hangcheck {
 	u64 acthd;
@@ -100,7 +102,6 @@ head_stuck(struct intel_engine_cs *engine, u64 acthd)
 static enum intel_engine_hangcheck_action
 engine_stuck(struct intel_engine_cs *engine, u64 acthd)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
 	enum intel_engine_hangcheck_action ha;
 	u32 tmp;
 
@@ -108,7 +109,7 @@ engine_stuck(struct intel_engine_cs *engine, u64 acthd)
 	if (ha != ENGINE_DEAD)
 		return ha;
 
-	if (IS_GEN(dev_priv, 2))
+	if (IS_GEN(engine->i915, 2))
 		return ENGINE_DEAD;
 
 	/* Is the chip hanging on a WAIT_FOR_EVENT?
@@ -118,8 +119,8 @@ engine_stuck(struct intel_engine_cs *engine, u64 acthd)
 	 */
 	tmp = ENGINE_READ(engine, RING_CTL);
 	if (tmp & RING_WAIT) {
-		i915_handle_error(dev_priv, engine->mask, 0,
-				  "stuck wait on %s", engine->name);
+		intel_gt_handle_error(engine->gt, engine->mask, 0,
+				      "stuck wait on %s", engine->name);
 		ENGINE_WRITE(engine, RING_CTL, tmp);
 		return ENGINE_WAIT_KICK;
 	}
@@ -219,7 +220,7 @@ static void hangcheck_accumulate_sample(struct intel_engine_cs *engine,
 				 I915_ENGINE_WEDGED_TIMEOUT);
 }
 
-static void hangcheck_declare_hang(struct drm_i915_private *i915,
+static void hangcheck_declare_hang(struct intel_gt *gt,
 				   intel_engine_mask_t hung,
 				   intel_engine_mask_t stuck)
 {
@@ -235,12 +236,12 @@ static void hangcheck_declare_hang(struct drm_i915_private *i915,
 		hung &= ~stuck;
 	len = scnprintf(msg, sizeof(msg),
 			"%s on ", stuck == hung ? "no progress" : "hang");
-	for_each_engine_masked(engine, i915, hung, tmp)
+	for_each_engine_masked(engine, gt->i915, hung, tmp)
 		len += scnprintf(msg + len, sizeof(msg) - len,
 				 "%s, ", engine->name);
 	msg[len-2] = '\0';
 
-	return i915_handle_error(i915, hung, I915_ERROR_CAPTURE, "%s", msg);
+	return intel_gt_handle_error(gt, hung, I915_ERROR_CAPTURE, "%s", msg);
 }
 
 /*
@@ -251,11 +252,10 @@ static void hangcheck_declare_hang(struct drm_i915_private *i915,
  * we kick the ring. If we see no progress on three subsequent calls
  * we assume chip is wedged and try to fix it by resetting the chip.
  */
-static void i915_hangcheck_elapsed(struct work_struct *work)
+static void hangcheck_elapsed(struct work_struct *work)
 {
-	struct drm_i915_private *dev_priv =
-		container_of(work, typeof(*dev_priv),
-			     gpu_error.hangcheck_work.work);
+	struct intel_gt *gt =
+		container_of(work, typeof(*gt), hangcheck.work.work);
 	intel_engine_mask_t hung = 0, stuck = 0, wedged = 0;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -264,13 +264,13 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 	if (!i915_modparams.enable_hangcheck)
 		return;
 
-	if (!READ_ONCE(dev_priv->gt.awake))
+	if (!READ_ONCE(gt->awake))
 		return;
 
-	if (i915_terminally_wedged(dev_priv))
+	if (intel_gt_is_wedged(gt))
 		return;
 
-	wakeref = intel_runtime_pm_get_if_in_use(&dev_priv->runtime_pm);
+	wakeref = intel_runtime_pm_get_if_in_use(&gt->i915->runtime_pm);
 	if (!wakeref)
 		return;
 
@@ -278,9 +278,9 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 	 * periodically arm the mmio checker to see if we are triggering
 	 * any invalid access.
 	 */
-	intel_uncore_arm_unclaimed_mmio_detection(&dev_priv->uncore);
+	intel_uncore_arm_unclaimed_mmio_detection(gt->uncore);
 
-	for_each_engine(engine, dev_priv, id) {
+	for_each_engine(engine, gt->i915, id) {
 		struct hangcheck hc;
 
 		intel_engine_signal_breadcrumbs(engine);
@@ -302,7 +302,7 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 	if (GEM_SHOW_DEBUG() && (hung | stuck)) {
 		struct drm_printer p = drm_debug_printer("hangcheck");
 
-		for_each_engine(engine, dev_priv, id) {
+		for_each_engine(engine, gt->i915, id) {
 			if (intel_engine_is_idle(engine))
 				continue;
 
@@ -311,20 +311,36 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 	}
 
 	if (wedged) {
-		dev_err(dev_priv->drm.dev,
+		dev_err(gt->i915->drm.dev,
 			"GPU recovery timed out,"
 			" cancelling all in-flight rendering.\n");
 		GEM_TRACE_DUMP();
-		i915_gem_set_wedged(dev_priv);
+		intel_gt_set_wedged(gt);
 	}
 
 	if (hung)
-		hangcheck_declare_hang(dev_priv, hung, stuck);
+		hangcheck_declare_hang(gt, hung, stuck);
 
-	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
+	intel_runtime_pm_put(&gt->i915->runtime_pm, wakeref);
 
 	/* Reset timer in case GPU hangs without another request being added */
-	i915_queue_hangcheck(dev_priv);
+	intel_gt_queue_hangcheck(gt);
+}
+
+void intel_gt_queue_hangcheck(struct intel_gt *gt)
+{
+	unsigned long delay;
+
+	if (unlikely(!i915_modparams.enable_hangcheck))
+		return;
+
+	/* Don't continually defer the hangcheck so that it is always run at
+	 * least once after work has been scheduled on any ring. Otherwise,
+	 * we will ignore a hung ring if a second ring is kept busy.
+	 */
+
+	delay = round_jiffies_up_relative(DRM_I915_HANGCHECK_JIFFIES);
+	queue_delayed_work(system_long_wq, &gt->hangcheck.work, delay);
 }
 
 void intel_engine_init_hangcheck(struct intel_engine_cs *engine)
@@ -333,10 +349,9 @@ void intel_engine_init_hangcheck(struct intel_engine_cs *engine)
 	engine->hangcheck.action_timestamp = jiffies;
 }
 
-void intel_hangcheck_init(struct drm_i915_private *i915)
+void intel_gt_init_hangcheck(struct intel_gt *gt)
 {
-	INIT_DELAYED_WORK(&i915->gpu_error.hangcheck_work,
-			  i915_hangcheck_elapsed);
+	INIT_DELAYED_WORK(&gt->hangcheck.work, hangcheck_elapsed);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index f3539147c7b1..18d9ddc5cd58 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2297,7 +2297,7 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	 * and have to at least restore the RING register in the context
 	 * image back to the expected values to skip over the guilty request.
 	 */
-	i915_reset_request(rq, stalled);
+	__i915_request_reset(rq, stalled);
 	if (!stalled)
 		goto out_replay;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 72002c0f9698..67c06231b004 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -114,7 +114,7 @@ static void context_mark_innocent(struct i915_gem_context *ctx)
 	atomic_inc(&ctx->active_count);
 }
 
-void i915_reset_request(struct i915_request *rq, bool guilty)
+void __i915_request_reset(struct i915_request *rq, bool guilty)
 {
 	GEM_TRACE("%s rq=%llx:%lld, guilty? %s\n",
 		  rq->engine->name,
@@ -164,16 +164,15 @@ static void gen3_stop_engine(struct intel_engine_cs *engine)
 			  intel_uncore_read_fw(uncore, RING_HEAD(base)));
 }
 
-static void i915_stop_engines(struct drm_i915_private *i915,
-			      intel_engine_mask_t engine_mask)
+static void stop_engines(struct intel_gt *gt, intel_engine_mask_t engine_mask)
 {
 	struct intel_engine_cs *engine;
 	intel_engine_mask_t tmp;
 
-	if (INTEL_GEN(i915) < 3)
+	if (INTEL_GEN(gt->i915) < 3)
 		return;
 
-	for_each_engine_masked(engine, i915, engine_mask, tmp)
+	for_each_engine_masked(engine, gt->i915, engine_mask, tmp)
 		gen3_stop_engine(engine);
 }
 
@@ -185,11 +184,11 @@ static bool i915_in_reset(struct pci_dev *pdev)
 	return gdrst & GRDOM_RESET_STATUS;
 }
 
-static int i915_do_reset(struct drm_i915_private *i915,
+static int i915_do_reset(struct intel_gt *gt,
 			 intel_engine_mask_t engine_mask,
 			 unsigned int retry)
 {
-	struct pci_dev *pdev = i915->drm.pdev;
+	struct pci_dev *pdev = gt->i915->drm.pdev;
 	int err;
 
 	/* Assert reset for at least 20 usec, and wait for acknowledgement. */
@@ -214,22 +213,22 @@ static bool g4x_reset_complete(struct pci_dev *pdev)
 	return (gdrst & GRDOM_RESET_ENABLE) == 0;
 }
 
-static int g33_do_reset(struct drm_i915_private *i915,
+static int g33_do_reset(struct intel_gt *gt,
 			intel_engine_mask_t engine_mask,
 			unsigned int retry)
 {
-	struct pci_dev *pdev = i915->drm.pdev;
+	struct pci_dev *pdev = gt->i915->drm.pdev;
 
 	pci_write_config_byte(pdev, I915_GDRST, GRDOM_RESET_ENABLE);
 	return wait_for_atomic(g4x_reset_complete(pdev), 50);
 }
 
-static int g4x_do_reset(struct drm_i915_private *i915,
+static int g4x_do_reset(struct intel_gt *gt,
 			intel_engine_mask_t engine_mask,
 			unsigned int retry)
 {
-	struct pci_dev *pdev = i915->drm.pdev;
-	struct intel_uncore *uncore = &i915->uncore;
+	struct pci_dev *pdev = gt->i915->drm.pdev;
+	struct intel_uncore *uncore = gt->uncore;
 	int ret;
 
 	/* WaVcpClkGateDisableForMediaReset:ctg,elk */
@@ -261,11 +260,11 @@ static int g4x_do_reset(struct drm_i915_private *i915,
 	return ret;
 }
 
-static int ironlake_do_reset(struct drm_i915_private *i915,
+static int ironlake_do_reset(struct intel_gt *gt,
 			     intel_engine_mask_t engine_mask,
 			     unsigned int retry)
 {
-	struct intel_uncore *uncore = &i915->uncore;
+	struct intel_uncore *uncore = gt->uncore;
 	int ret;
 
 	intel_uncore_write_fw(uncore, ILK_GDSR,
@@ -297,10 +296,9 @@ static int ironlake_do_reset(struct drm_i915_private *i915,
 }
 
 /* Reset the hardware domains (GENX_GRDOM_*) specified by mask */
-static int gen6_hw_domain_reset(struct drm_i915_private *i915,
-				u32 hw_domain_mask)
+static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask)
 {
-	struct intel_uncore *uncore = &i915->uncore;
+	struct intel_uncore *uncore = gt->uncore;
 	int err;
 
 	/*
@@ -322,7 +320,7 @@ static int gen6_hw_domain_reset(struct drm_i915_private *i915,
 	return err;
 }
 
-static int gen6_reset_engines(struct drm_i915_private *i915,
+static int gen6_reset_engines(struct intel_gt *gt,
 			      intel_engine_mask_t engine_mask,
 			      unsigned int retry)
 {
@@ -342,13 +340,13 @@ static int gen6_reset_engines(struct drm_i915_private *i915,
 		intel_engine_mask_t tmp;
 
 		hw_mask = 0;
-		for_each_engine_masked(engine, i915, engine_mask, tmp) {
+		for_each_engine_masked(engine, gt->i915, engine_mask, tmp) {
 			GEM_BUG_ON(engine->id >= ARRAY_SIZE(hw_engine_mask));
 			hw_mask |= hw_engine_mask[engine->id];
 		}
 	}
 
-	return gen6_hw_domain_reset(i915, hw_mask);
+	return gen6_hw_domain_reset(gt, hw_mask);
 }
 
 static u32 gen11_lock_sfc(struct intel_engine_cs *engine)
@@ -446,7 +444,7 @@ static void gen11_unlock_sfc(struct intel_engine_cs *engine)
 	rmw_clear_fw(uncore, sfc_forced_lock, sfc_forced_lock_bit);
 }
 
-static int gen11_reset_engines(struct drm_i915_private *i915,
+static int gen11_reset_engines(struct intel_gt *gt,
 			       intel_engine_mask_t engine_mask,
 			       unsigned int retry)
 {
@@ -469,17 +467,17 @@ static int gen11_reset_engines(struct drm_i915_private *i915,
 		hw_mask = GEN11_GRDOM_FULL;
 	} else {
 		hw_mask = 0;
-		for_each_engine_masked(engine, i915, engine_mask, tmp) {
+		for_each_engine_masked(engine, gt->i915, engine_mask, tmp) {
 			GEM_BUG_ON(engine->id >= ARRAY_SIZE(hw_engine_mask));
 			hw_mask |= hw_engine_mask[engine->id];
 			hw_mask |= gen11_lock_sfc(engine);
 		}
 	}
 
-	ret = gen6_hw_domain_reset(i915, hw_mask);
+	ret = gen6_hw_domain_reset(gt, hw_mask);
 
 	if (engine_mask != ALL_ENGINES)
-		for_each_engine_masked(engine, i915, engine_mask, tmp)
+		for_each_engine_masked(engine, gt->i915, engine_mask, tmp)
 			gen11_unlock_sfc(engine);
 
 	return ret;
@@ -529,7 +527,7 @@ static void gen8_engine_reset_cancel(struct intel_engine_cs *engine)
 			      _MASKED_BIT_DISABLE(RESET_CTL_REQUEST_RESET));
 }
 
-static int gen8_reset_engines(struct drm_i915_private *i915,
+static int gen8_reset_engines(struct intel_gt *gt,
 			      intel_engine_mask_t engine_mask,
 			      unsigned int retry)
 {
@@ -538,7 +536,7 @@ static int gen8_reset_engines(struct drm_i915_private *i915,
 	intel_engine_mask_t tmp;
 	int ret;
 
-	for_each_engine_masked(engine, i915, engine_mask, tmp) {
+	for_each_engine_masked(engine, gt->i915, engine_mask, tmp) {
 		ret = gen8_engine_reset_prepare(engine);
 		if (ret && !reset_non_ready)
 			goto skip_reset;
@@ -554,23 +552,23 @@ static int gen8_reset_engines(struct drm_i915_private *i915,
 		 * We rather take context corruption instead of
 		 * failed reset with a wedged driver/gpu. And
 		 * active bb execution case should be covered by
-		 * i915_stop_engines we have before the reset.
+		 * stop_engines() we have before the reset.
 		 */
 	}
 
-	if (INTEL_GEN(i915) >= 11)
-		ret = gen11_reset_engines(i915, engine_mask, retry);
+	if (INTEL_GEN(gt->i915) >= 11)
+		ret = gen11_reset_engines(gt, engine_mask, retry);
 	else
-		ret = gen6_reset_engines(i915, engine_mask, retry);
+		ret = gen6_reset_engines(gt, engine_mask, retry);
 
 skip_reset:
-	for_each_engine_masked(engine, i915, engine_mask, tmp)
+	for_each_engine_masked(engine, gt->i915, engine_mask, tmp)
 		gen8_engine_reset_cancel(engine);
 
 	return ret;
 }
 
-typedef int (*reset_func)(struct drm_i915_private *,
+typedef int (*reset_func)(struct intel_gt *,
 			  intel_engine_mask_t engine_mask,
 			  unsigned int retry);
 
@@ -592,15 +590,14 @@ static reset_func intel_get_gpu_reset(struct drm_i915_private *i915)
 		return NULL;
 }
 
-int intel_gpu_reset(struct drm_i915_private *i915,
-		    intel_engine_mask_t engine_mask)
+int intel_gpu_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask)
 {
 	const int retries = engine_mask == ALL_ENGINES ? RESET_MAX_RETRIES : 1;
 	reset_func reset;
 	int ret = -ETIMEDOUT;
 	int retry;
 
-	reset = intel_get_gpu_reset(i915);
+	reset = intel_get_gpu_reset(gt->i915);
 	if (!reset)
 		return -ENODEV;
 
@@ -608,7 +605,7 @@ int intel_gpu_reset(struct drm_i915_private *i915,
 	 * If the power well sleeps during the reset, the reset
 	 * request may be dropped and never completes (causing -EIO).
 	 */
-	intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
+	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
 	for (retry = 0; ret == -ETIMEDOUT && retry < retries; retry++) {
 		/*
 		 * We stop engines, otherwise we might get failed reset and a
@@ -625,14 +622,14 @@ int intel_gpu_reset(struct drm_i915_private *i915,
 		 * FIXME: Wa for more modern gens needs to be validated
 		 */
 		if (retry)
-			i915_stop_engines(i915, engine_mask);
+			stop_engines(gt, engine_mask);
 
 		GEM_TRACE("engine_mask=%x\n", engine_mask);
 		preempt_disable();
-		ret = reset(i915, engine_mask, retry);
+		ret = reset(gt, engine_mask, retry);
 		preempt_enable();
 	}
-	intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
+	intel_uncore_forcewake_put(gt->uncore, FORCEWAKE_ALL);
 
 	return ret;
 }
@@ -650,17 +647,17 @@ bool intel_has_reset_engine(struct drm_i915_private *i915)
 	return INTEL_INFO(i915)->has_reset_engine && i915_modparams.reset >= 2;
 }
 
-int intel_reset_guc(struct drm_i915_private *i915)
+int intel_reset_guc(struct intel_gt *gt)
 {
 	u32 guc_domain =
-		INTEL_GEN(i915) >= 11 ? GEN11_GRDOM_GUC : GEN9_GRDOM_GUC;
+		INTEL_GEN(gt->i915) >= 11 ? GEN11_GRDOM_GUC : GEN9_GRDOM_GUC;
 	int ret;
 
-	GEM_BUG_ON(!HAS_GUC(i915));
+	GEM_BUG_ON(!HAS_GUC(gt->i915));
 
-	intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
-	ret = gen6_hw_domain_reset(i915, guc_domain);
-	intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
+	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
+	ret = gen6_hw_domain_reset(gt, guc_domain);
+	intel_uncore_forcewake_put(gt->uncore, FORCEWAKE_ALL);
 
 	return ret;
 }
@@ -682,56 +679,55 @@ static void reset_prepare_engine(struct intel_engine_cs *engine)
 	engine->reset.prepare(engine);
 }
 
-static void revoke_mmaps(struct drm_i915_private *i915)
+static void revoke_mmaps(struct intel_gt *gt)
 {
 	int i;
 
-	for (i = 0; i < i915->ggtt.num_fences; i++) {
+	for (i = 0; i < gt->ggtt->num_fences; i++) {
 		struct drm_vma_offset_node *node;
 		struct i915_vma *vma;
 		u64 vma_offset;
 
-		vma = READ_ONCE(i915->ggtt.fence_regs[i].vma);
+		vma = READ_ONCE(gt->ggtt->fence_regs[i].vma);
 		if (!vma)
 			continue;
 
 		if (!i915_vma_has_userfault(vma))
 			continue;
 
-		GEM_BUG_ON(vma->fence != &i915->ggtt.fence_regs[i]);
+		GEM_BUG_ON(vma->fence != &gt->ggtt->fence_regs[i]);
 		node = &vma->obj->base.vma_node;
 		vma_offset = vma->ggtt_view.partial.offset << PAGE_SHIFT;
-		unmap_mapping_range(i915->drm.anon_inode->i_mapping,
+		unmap_mapping_range(gt->i915->drm.anon_inode->i_mapping,
 				    drm_vma_node_offset_addr(node) + vma_offset,
 				    vma->size,
 				    1);
 	}
 }
 
-static intel_engine_mask_t reset_prepare(struct drm_i915_private *i915)
+static intel_engine_mask_t reset_prepare(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
 	intel_engine_mask_t awake = 0;
 	enum intel_engine_id id;
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		if (intel_engine_pm_get_if_awake(engine))
 			awake |= engine->mask;
 		reset_prepare_engine(engine);
 	}
 
-	intel_uc_reset_prepare(i915);
+	intel_uc_reset_prepare(gt->i915);
 
 	return awake;
 }
 
-static void gt_revoke(struct drm_i915_private *i915)
+static void gt_revoke(struct intel_gt *gt)
 {
-	revoke_mmaps(i915);
+	revoke_mmaps(gt);
 }
 
-static int gt_reset(struct drm_i915_private *i915,
-		    intel_engine_mask_t stalled_mask)
+static int gt_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -741,14 +737,14 @@ static int gt_reset(struct drm_i915_private *i915,
 	 * Everything depends on having the GTT running, so we need to start
 	 * there.
 	 */
-	err = i915_ggtt_enable_hw(i915);
+	err = i915_ggtt_enable_hw(gt->i915);
 	if (err)
 		return err;
 
-	for_each_engine(engine, i915, id)
-		intel_engine_reset(engine, stalled_mask & engine->mask);
+	for_each_engine(engine, gt->i915, id)
+		__intel_engine_reset(engine, stalled_mask & engine->mask);
 
-	i915_gem_restore_fences(i915);
+	i915_gem_restore_fences(gt->i915);
 
 	return err;
 }
@@ -761,13 +757,12 @@ static void reset_finish_engine(struct intel_engine_cs *engine)
 	intel_engine_signal_breadcrumbs(engine);
 }
 
-static void reset_finish(struct drm_i915_private *i915,
-			 intel_engine_mask_t awake)
+static void reset_finish(struct intel_gt *gt, intel_engine_mask_t awake)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		reset_finish_engine(engine);
 		if (awake & engine->mask)
 			intel_engine_pm_put(engine);
@@ -791,20 +786,19 @@ static void nop_submit_request(struct i915_request *request)
 	intel_engine_queue_breadcrumbs(engine);
 }
 
-static void __i915_gem_set_wedged(struct drm_i915_private *i915)
+static void __intel_gt_set_wedged(struct intel_gt *gt)
 {
-	struct i915_gpu_error *error = &i915->gpu_error;
 	struct intel_engine_cs *engine;
 	intel_engine_mask_t awake;
 	enum intel_engine_id id;
 
-	if (test_bit(I915_WEDGED, &error->flags))
+	if (test_bit(I915_WEDGED, &gt->reset.flags))
 		return;
 
-	if (GEM_SHOW_DEBUG() && !intel_engines_are_idle(i915)) {
+	if (GEM_SHOW_DEBUG() && !intel_engines_are_idle(gt)) {
 		struct drm_printer p = drm_debug_printer(__func__);
 
-		for_each_engine(engine, i915, id)
+		for_each_engine(engine, gt->i915, id)
 			intel_engine_dump(engine, &p, "%s\n", engine->name);
 	}
 
@@ -815,17 +809,17 @@ static void __i915_gem_set_wedged(struct drm_i915_private *i915)
 	 * rolling the global seqno forward (since this would complete requests
 	 * for which we haven't set the fence error to EIO yet).
 	 */
-	awake = reset_prepare(i915);
+	awake = reset_prepare(gt);
 
 	/* Even if the GPU reset fails, it should still stop the engines */
-	if (!INTEL_INFO(i915)->gpu_reset_clobbers_display)
-		intel_gpu_reset(i915, ALL_ENGINES);
+	if (!INTEL_INFO(gt->i915)->gpu_reset_clobbers_display)
+		intel_gpu_reset(gt, ALL_ENGINES);
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		engine->submit_request = nop_submit_request;
 		engine->schedule = NULL;
 	}
-	i915->caps.scheduler = 0;
+	gt->i915->caps.scheduler = 0;
 
 	/*
 	 * Make sure no request can slip through without getting completed by
@@ -833,38 +827,36 @@ static void __i915_gem_set_wedged(struct drm_i915_private *i915)
 	 * in nop_submit_request.
 	 */
 	synchronize_rcu_expedited();
-	set_bit(I915_WEDGED, &error->flags);
+	set_bit(I915_WEDGED, &gt->reset.flags);
 
 	/* Mark all executing requests as skipped */
-	for_each_engine(engine, i915, id)
+	for_each_engine(engine, gt->i915, id)
 		engine->cancel_requests(engine);
 
-	reset_finish(i915, awake);
+	reset_finish(gt, awake);
 
 	GEM_TRACE("end\n");
 }
 
-void i915_gem_set_wedged(struct drm_i915_private *i915)
+void intel_gt_set_wedged(struct intel_gt *gt)
 {
-	struct i915_gpu_error *error = &i915->gpu_error;
 	intel_wakeref_t wakeref;
 
-	mutex_lock(&error->wedge_mutex);
-	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
-		__i915_gem_set_wedged(i915);
-	mutex_unlock(&error->wedge_mutex);
+	mutex_lock(&gt->reset.mutex);
+	with_intel_runtime_pm(&gt->i915->runtime_pm, wakeref)
+		__intel_gt_set_wedged(gt);
+	mutex_unlock(&gt->reset.mutex);
 }
 
-static bool __i915_gem_unset_wedged(struct drm_i915_private *i915)
+static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 {
-	struct i915_gpu_error *error = &i915->gpu_error;
-	struct intel_gt_timelines *timelines = &i915->gt.timelines;
+	struct intel_gt_timelines *timelines = &gt->timelines;
 	struct intel_timeline *tl;
 
-	if (!test_bit(I915_WEDGED, &error->flags))
+	if (!test_bit(I915_WEDGED, &gt->reset.flags))
 		return true;
 
-	if (!i915->gt.scratch) /* Never full initialised, recovery impossible */
+	if (!gt->scratch) /* Never full initialised, recovery impossible */
 		return false;
 
 	GEM_TRACE("start\n");
@@ -905,7 +897,7 @@ static bool __i915_gem_unset_wedged(struct drm_i915_private *i915)
 	}
 	spin_unlock(&timelines->lock);
 
-	intel_gt_sanitize(&i915->gt, false);
+	intel_gt_sanitize(gt, false);
 
 	/*
 	 * Undo nop_submit_request. We prevent all new i915 requests from
@@ -916,53 +908,51 @@ static bool __i915_gem_unset_wedged(struct drm_i915_private *i915)
 	 * the nop_submit_request on reset, we can do this from normal
 	 * context and do not require stop_machine().
 	 */
-	intel_engines_reset_default_submission(i915);
+	intel_engines_reset_default_submission(gt);
 
 	GEM_TRACE("end\n");
 
 	smp_mb__before_atomic(); /* complete takeover before enabling execbuf */
-	clear_bit(I915_WEDGED, &i915->gpu_error.flags);
+	clear_bit(I915_WEDGED, &gt->reset.flags);
 
 	return true;
 }
 
-bool i915_gem_unset_wedged(struct drm_i915_private *i915)
+bool intel_gt_unset_wedged(struct intel_gt *gt)
 {
-	struct i915_gpu_error *error = &i915->gpu_error;
 	bool result;
 
-	mutex_lock(&error->wedge_mutex);
-	result = __i915_gem_unset_wedged(i915);
-	mutex_unlock(&error->wedge_mutex);
+	mutex_lock(&gt->reset.mutex);
+	result = __intel_gt_unset_wedged(gt);
+	mutex_unlock(&gt->reset.mutex);
 
 	return result;
 }
 
-static int do_reset(struct drm_i915_private *i915,
-		    intel_engine_mask_t stalled_mask)
+static int do_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask)
 {
 	int err, i;
 
-	gt_revoke(i915);
+	gt_revoke(gt);
 
-	err = intel_gpu_reset(i915, ALL_ENGINES);
+	err = intel_gpu_reset(gt, ALL_ENGINES);
 	for (i = 0; err && i < RESET_MAX_RETRIES; i++) {
 		msleep(10 * (i + 1));
-		err = intel_gpu_reset(i915, ALL_ENGINES);
+		err = intel_gpu_reset(gt, ALL_ENGINES);
 	}
 	if (err)
 		return err;
 
-	return gt_reset(i915, stalled_mask);
+	return gt_reset(gt, stalled_mask);
 }
 
-static int resume(struct drm_i915_private *i915)
+static int resume(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	int ret;
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		ret = engine->resume(engine);
 		if (ret)
 			return ret;
@@ -972,8 +962,8 @@ static int resume(struct drm_i915_private *i915)
 }
 
 /**
- * i915_reset - reset chip after a hang
- * @i915: #drm_i915_private to reset
+ * intel_gt_reset - reset chip after a hang
+ * @gt: #intel_gt to reset
  * @stalled_mask: mask of the stalled engines with the guilty requests
  * @reason: user error message for why we are resetting
  *
@@ -988,50 +978,50 @@ static int resume(struct drm_i915_private *i915)
  *   - re-init interrupt state
  *   - re-init display
  */
-void i915_reset(struct drm_i915_private *i915,
-		intel_engine_mask_t stalled_mask,
-		const char *reason)
+void intel_gt_reset(struct intel_gt *gt,
+		    intel_engine_mask_t stalled_mask,
+		    const char *reason)
 {
-	struct i915_gpu_error *error = &i915->gpu_error;
 	intel_engine_mask_t awake;
 	int ret;
 
-	GEM_TRACE("flags=%lx\n", error->flags);
+	GEM_TRACE("flags=%lx\n", gt->reset.flags);
 
 	might_sleep();
-	GEM_BUG_ON(!test_bit(I915_RESET_BACKOFF, &error->flags));
-	mutex_lock(&error->wedge_mutex);
+	GEM_BUG_ON(!test_bit(I915_RESET_BACKOFF, &gt->reset.flags));
+	mutex_lock(&gt->reset.mutex);
 
 	/* Clear any previous failed attempts at recovery. Time to try again. */
-	if (!__i915_gem_unset_wedged(i915))
+	if (!__intel_gt_unset_wedged(gt))
 		goto unlock;
 
 	if (reason)
-		dev_notice(i915->drm.dev, "Resetting chip for %s\n", reason);
-	error->reset_count++;
+		dev_notice(gt->i915->drm.dev,
+			   "Resetting chip for %s\n", reason);
+	atomic_inc(&gt->i915->gpu_error.reset_count);
 
-	awake = reset_prepare(i915);
+	awake = reset_prepare(gt);
 
-	if (!intel_has_gpu_reset(i915)) {
+	if (!intel_has_gpu_reset(gt->i915)) {
 		if (i915_modparams.reset)
-			dev_err(i915->drm.dev, "GPU reset not supported\n");
+			dev_err(gt->i915->drm.dev, "GPU reset not supported\n");
 		else
 			DRM_DEBUG_DRIVER("GPU reset disabled\n");
 		goto error;
 	}
 
-	if (INTEL_INFO(i915)->gpu_reset_clobbers_display)
-		intel_runtime_pm_disable_interrupts(i915);
+	if (INTEL_INFO(gt->i915)->gpu_reset_clobbers_display)
+		intel_runtime_pm_disable_interrupts(gt->i915);
 
-	if (do_reset(i915, stalled_mask)) {
-		dev_err(i915->drm.dev, "Failed to reset chip\n");
+	if (do_reset(gt, stalled_mask)) {
+		dev_err(gt->i915->drm.dev, "Failed to reset chip\n");
 		goto taint;
 	}
 
-	if (INTEL_INFO(i915)->gpu_reset_clobbers_display)
-		intel_runtime_pm_enable_interrupts(i915);
+	if (INTEL_INFO(gt->i915)->gpu_reset_clobbers_display)
+		intel_runtime_pm_enable_interrupts(gt->i915);
 
-	intel_overlay_reset(i915);
+	intel_overlay_reset(gt->i915);
 
 	/*
 	 * Next we need to restore the context, but we don't use those
@@ -1041,23 +1031,23 @@ void i915_reset(struct drm_i915_private *i915,
 	 * was running at the time of the reset (i.e. we weren't VT
 	 * switched away).
 	 */
-	ret = i915_gem_init_hw(i915);
+	ret = i915_gem_init_hw(gt->i915);
 	if (ret) {
 		DRM_ERROR("Failed to initialise HW following reset (%d)\n",
 			  ret);
 		goto taint;
 	}
 
-	ret = resume(i915);
+	ret = resume(gt);
 	if (ret)
 		goto taint;
 
-	i915_queue_hangcheck(i915);
+	intel_gt_queue_hangcheck(gt);
 
 finish:
-	reset_finish(i915, awake);
+	reset_finish(gt, awake);
 unlock:
-	mutex_unlock(&error->wedge_mutex);
+	mutex_unlock(&gt->reset.mutex);
 	return;
 
 taint:
@@ -1075,18 +1065,17 @@ void i915_reset(struct drm_i915_private *i915,
 	 */
 	add_taint_for_CI(TAINT_WARN);
 error:
-	__i915_gem_set_wedged(i915);
+	__intel_gt_set_wedged(gt);
 	goto finish;
 }
 
-static inline int intel_gt_reset_engine(struct drm_i915_private *i915,
-					struct intel_engine_cs *engine)
+static inline int intel_gt_reset_engine(struct intel_engine_cs *engine)
 {
-	return intel_gpu_reset(i915, engine->mask);
+	return intel_gpu_reset(engine->gt, engine->mask);
 }
 
 /**
- * i915_reset_engine - reset GPU engine to recover from a hang
+ * intel_engine_reset - reset GPU engine to recover from a hang
  * @engine: engine to reset
  * @msg: reason for GPU reset; or NULL for no dev_notice()
  *
@@ -1098,13 +1087,13 @@ static inline int intel_gt_reset_engine(struct drm_i915_private *i915,
  *  - reset engine (which will force the engine to idle)
  *  - re-init/configure engine
  */
-int i915_reset_engine(struct intel_engine_cs *engine, const char *msg)
+int intel_engine_reset(struct intel_engine_cs *engine, const char *msg)
 {
-	struct i915_gpu_error *error = &engine->i915->gpu_error;
+	struct intel_gt *gt = engine->gt;
 	int ret;
 
-	GEM_TRACE("%s flags=%lx\n", engine->name, error->flags);
-	GEM_BUG_ON(!test_bit(I915_RESET_ENGINE + engine->id, &error->flags));
+	GEM_TRACE("%s flags=%lx\n", engine->name, gt->reset.flags);
+	GEM_BUG_ON(!test_bit(I915_RESET_ENGINE + engine->id, &gt->reset.flags));
 
 	if (!intel_engine_pm_get_if_awake(engine))
 		return 0;
@@ -1114,10 +1103,10 @@ int i915_reset_engine(struct intel_engine_cs *engine, const char *msg)
 	if (msg)
 		dev_notice(engine->i915->drm.dev,
 			   "Resetting %s for %s\n", engine->name, msg);
-	error->reset_engine_count[engine->id]++;
+	atomic_inc(&engine->i915->gpu_error.reset_engine_count[engine->uabi_class]);
 
 	if (!engine->i915->guc.execbuf_client)
-		ret = intel_gt_reset_engine(engine->i915, engine);
+		ret = intel_gt_reset_engine(engine);
 	else
 		ret = intel_guc_reset_engine(&engine->i915->guc, engine);
 	if (ret) {
@@ -1133,7 +1122,7 @@ int i915_reset_engine(struct intel_engine_cs *engine, const char *msg)
 	 * active request and can drop it, adjust head to skip the offending
 	 * request to resume executing remaining requests in the queue.
 	 */
-	intel_engine_reset(engine, true);
+	__intel_engine_reset(engine, true);
 
 	/*
 	 * The engine and its registers (and workarounds in case of render)
@@ -1149,16 +1138,15 @@ int i915_reset_engine(struct intel_engine_cs *engine, const char *msg)
 	return ret;
 }
 
-static void i915_reset_device(struct drm_i915_private *i915,
-			      u32 engine_mask,
-			      const char *reason)
+static void intel_gt_reset_global(struct intel_gt *gt,
+				  u32 engine_mask,
+				  const char *reason)
 {
-	struct i915_gpu_error *error = &i915->gpu_error;
-	struct kobject *kobj = &i915->drm.primary->kdev->kobj;
+	struct kobject *kobj = &gt->i915->drm.primary->kdev->kobj;
 	char *error_event[] = { I915_ERROR_UEVENT "=1", NULL };
 	char *reset_event[] = { I915_RESET_UEVENT "=1", NULL };
 	char *reset_done_event[] = { I915_ERROR_UEVENT "=0", NULL };
-	struct i915_wedge_me w;
+	struct intel_wedge_me w;
 
 	kobject_uevent_env(kobj, KOBJ_CHANGE, error_event);
 
@@ -1166,24 +1154,24 @@ static void i915_reset_device(struct drm_i915_private *i915,
 	kobject_uevent_env(kobj, KOBJ_CHANGE, reset_event);
 
 	/* Use a watchdog to ensure that our reset completes */
-	i915_wedge_on_timeout(&w, i915, 5 * HZ) {
-		intel_prepare_reset(i915);
+	intel_wedge_on_timeout(&w, gt, 5 * HZ) {
+		intel_prepare_reset(gt->i915);
 
 		/* Flush everyone using a resource about to be clobbered */
-		synchronize_srcu_expedited(&error->reset_backoff_srcu);
+		synchronize_srcu_expedited(&gt->reset.backoff_srcu);
 
-		i915_reset(i915, engine_mask, reason);
+		intel_gt_reset(gt, engine_mask, reason);
 
-		intel_finish_reset(i915);
+		intel_finish_reset(gt->i915);
 	}
 
-	if (!test_bit(I915_WEDGED, &error->flags))
+	if (!test_bit(I915_WEDGED, &gt->reset.flags))
 		kobject_uevent_env(kobj, KOBJ_CHANGE, reset_done_event);
 }
 
 /**
- * i915_handle_error - handle a gpu error
- * @i915: i915 device private
+ * intel_gt_handle_error - handle a gpu error
+ * @gt: the intel_gt
  * @engine_mask: mask representing engines that are hung
  * @flags: control flags
  * @fmt: Error message format string
@@ -1194,12 +1182,11 @@ static void i915_reset_device(struct drm_i915_private *i915,
  * so userspace knows something bad happened (should trigger collection
  * of a ring dump etc.).
  */
-void i915_handle_error(struct drm_i915_private *i915,
-		       intel_engine_mask_t engine_mask,
-		       unsigned long flags,
-		       const char *fmt, ...)
+void intel_gt_handle_error(struct intel_gt *gt,
+			   intel_engine_mask_t engine_mask,
+			   unsigned long flags,
+			   const char *fmt, ...)
 {
-	struct i915_gpu_error *error = &i915->gpu_error;
 	struct intel_engine_cs *engine;
 	intel_wakeref_t wakeref;
 	intel_engine_mask_t tmp;
@@ -1223,33 +1210,31 @@ void i915_handle_error(struct drm_i915_private *i915,
 	 * isn't the case at least when we get here by doing a
 	 * simulated reset via debugfs, so get an RPM reference.
 	 */
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
+	wakeref = intel_runtime_pm_get(&gt->i915->runtime_pm);
 
-	engine_mask &= INTEL_INFO(i915)->engine_mask;
+	engine_mask &= INTEL_INFO(gt->i915)->engine_mask;
 
 	if (flags & I915_ERROR_CAPTURE) {
-		i915_capture_error_state(i915, engine_mask, msg);
-		intel_gt_clear_error_registers(&i915->gt, engine_mask);
+		i915_capture_error_state(gt->i915, engine_mask, msg);
+		intel_gt_clear_error_registers(gt, engine_mask);
 	}
 
 	/*
 	 * Try engine reset when available. We fall back to full reset if
 	 * single reset fails.
 	 */
-	if (intel_has_reset_engine(i915) && !__i915_wedged(error)) {
-		for_each_engine_masked(engine, i915, engine_mask, tmp) {
+	if (intel_has_reset_engine(gt->i915) && !intel_gt_is_wedged(gt)) {
+		for_each_engine_masked(engine, gt->i915, engine_mask, tmp) {
 			BUILD_BUG_ON(I915_RESET_MODESET >= I915_RESET_ENGINE);
 			if (test_and_set_bit(I915_RESET_ENGINE + engine->id,
-					     &error->flags))
+					     &gt->reset.flags))
 				continue;
 
-			if (i915_reset_engine(engine, msg) == 0)
+			if (intel_engine_reset(engine, msg) == 0)
 				engine_mask &= ~engine->mask;
 
-			clear_bit(I915_RESET_ENGINE + engine->id,
-				  &error->flags);
-			wake_up_bit(&error->flags,
-				    I915_RESET_ENGINE + engine->id);
+			clear_and_wake_up_bit(I915_RESET_ENGINE + engine->id,
+					      &gt->reset.flags);
 		}
 	}
 
@@ -1257,9 +1242,9 @@ void i915_handle_error(struct drm_i915_private *i915,
 		goto out;
 
 	/* Full reset needs the mutex, stop any other user trying to do so. */
-	if (test_and_set_bit(I915_RESET_BACKOFF, &error->flags)) {
-		wait_event(error->reset_queue,
-			   !test_bit(I915_RESET_BACKOFF, &error->flags));
+	if (test_and_set_bit(I915_RESET_BACKOFF, &gt->reset.flags)) {
+		wait_event(gt->reset.queue,
+			   !test_bit(I915_RESET_BACKOFF, &gt->reset.flags));
 		goto out; /* piggy-back on the other reset */
 	}
 
@@ -1267,113 +1252,119 @@ void i915_handle_error(struct drm_i915_private *i915,
 	synchronize_rcu_expedited();
 
 	/* Prevent any other reset-engine attempt. */
-	for_each_engine(engine, i915, tmp) {
+	for_each_engine(engine, gt->i915, tmp) {
 		while (test_and_set_bit(I915_RESET_ENGINE + engine->id,
-					&error->flags))
-			wait_on_bit(&error->flags,
+					&gt->reset.flags))
+			wait_on_bit(&gt->reset.flags,
 				    I915_RESET_ENGINE + engine->id,
 				    TASK_UNINTERRUPTIBLE);
 	}
 
-	i915_reset_device(i915, engine_mask, msg);
+	intel_gt_reset_global(gt, engine_mask, msg);
 
-	for_each_engine(engine, i915, tmp) {
-		clear_bit(I915_RESET_ENGINE + engine->id,
-			  &error->flags);
-	}
-
-	clear_bit(I915_RESET_BACKOFF, &error->flags);
-	wake_up_all(&error->reset_queue);
+	for_each_engine(engine, gt->i915, tmp)
+		clear_bit_unlock(I915_RESET_ENGINE + engine->id,
+				 &gt->reset.flags);
+	clear_bit_unlock(I915_RESET_BACKOFF, &gt->reset.flags);
+	smp_mb__after_atomic();
+	wake_up_all(&gt->reset.queue);
 
 out:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
+	intel_runtime_pm_put(&gt->i915->runtime_pm, wakeref);
 }
 
-int i915_reset_trylock(struct drm_i915_private *i915)
+int intel_gt_reset_trylock(struct intel_gt *gt)
 {
-	struct i915_gpu_error *error = &i915->gpu_error;
 	int srcu;
 
-	might_lock(&error->reset_backoff_srcu);
+	might_lock(&gt->reset.backoff_srcu);
 	might_sleep();
 
 	rcu_read_lock();
-	while (test_bit(I915_RESET_BACKOFF, &error->flags)) {
+	while (test_bit(I915_RESET_BACKOFF, &gt->reset.flags)) {
 		rcu_read_unlock();
 
-		if (wait_event_interruptible(error->reset_queue,
+		if (wait_event_interruptible(gt->reset.queue,
 					     !test_bit(I915_RESET_BACKOFF,
-						       &error->flags)))
+						       &gt->reset.flags)))
 			return -EINTR;
 
 		rcu_read_lock();
 	}
-	srcu = srcu_read_lock(&error->reset_backoff_srcu);
+	srcu = srcu_read_lock(&gt->reset.backoff_srcu);
 	rcu_read_unlock();
 
 	return srcu;
 }
 
-void i915_reset_unlock(struct drm_i915_private *i915, int tag)
-__releases(&i915->gpu_error.reset_backoff_srcu)
+void intel_gt_reset_unlock(struct intel_gt *gt, int tag)
+__releases(&gt->reset.backoff_srcu)
 {
-	struct i915_gpu_error *error = &i915->gpu_error;
-
-	srcu_read_unlock(&error->reset_backoff_srcu, tag);
+	srcu_read_unlock(&gt->reset.backoff_srcu, tag);
 }
 
-int i915_terminally_wedged(struct drm_i915_private *i915)
+int intel_gt_terminally_wedged(struct intel_gt *gt)
 {
-	struct i915_gpu_error *error = &i915->gpu_error;
-
 	might_sleep();
 
-	if (!__i915_wedged(error))
+	if (!intel_gt_is_wedged(gt))
 		return 0;
 
 	/* Reset still in progress? Maybe we will recover? */
-	if (!test_bit(I915_RESET_BACKOFF, &error->flags))
+	if (!test_bit(I915_RESET_BACKOFF, &gt->reset.flags))
 		return -EIO;
 
 	/* XXX intel_reset_finish() still takes struct_mutex!!! */
-	if (mutex_is_locked(&i915->drm.struct_mutex))
+	if (mutex_is_locked(&gt->i915->drm.struct_mutex))
 		return -EAGAIN;
 
-	if (wait_event_interruptible(error->reset_queue,
+	if (wait_event_interruptible(gt->reset.queue,
 				     !test_bit(I915_RESET_BACKOFF,
-					       &error->flags)))
+					       &gt->reset.flags)))
 		return -EINTR;
 
-	return __i915_wedged(error) ? -EIO : 0;
+	return intel_gt_is_wedged(gt) ? -EIO : 0;
+}
+
+void intel_gt_init_reset(struct intel_gt *gt)
+{
+	init_waitqueue_head(&gt->reset.queue);
+	mutex_init(&gt->reset.mutex);
+	init_srcu_struct(&gt->reset.backoff_srcu);
+}
+
+void intel_gt_fini_reset(struct intel_gt *gt)
+{
+	cleanup_srcu_struct(&gt->reset.backoff_srcu);
 }
 
-static void i915_wedge_me(struct work_struct *work)
+static void intel_wedge_me(struct work_struct *work)
 {
-	struct i915_wedge_me *w = container_of(work, typeof(*w), work.work);
+	struct intel_wedge_me *w = container_of(work, typeof(*w), work.work);
 
-	dev_err(w->i915->drm.dev,
+	dev_err(w->gt->i915->drm.dev,
 		"%s timed out, cancelling all in-flight rendering.\n",
 		w->name);
-	i915_gem_set_wedged(w->i915);
+	intel_gt_set_wedged(w->gt);
 }
 
-void __i915_init_wedge(struct i915_wedge_me *w,
-		       struct drm_i915_private *i915,
-		       long timeout,
-		       const char *name)
+void __intel_init_wedge(struct intel_wedge_me *w,
+			struct intel_gt *gt,
+			long timeout,
+			const char *name)
 {
-	w->i915 = i915;
+	w->gt = gt;
 	w->name = name;
 
-	INIT_DELAYED_WORK_ONSTACK(&w->work, i915_wedge_me);
+	INIT_DELAYED_WORK_ONSTACK(&w->work, intel_wedge_me);
 	schedule_delayed_work(&w->work, timeout);
 }
 
-void __i915_fini_wedge(struct i915_wedge_me *w)
+void __intel_fini_wedge(struct intel_wedge_me *w)
 {
 	cancel_delayed_work_sync(&w->work);
 	destroy_delayed_work_on_stack(&w->work);
-	w->i915 = NULL;
+	w->gt = NULL;
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h
index 03fba0ab3868..62f6cb520f96 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.h
+++ b/drivers/gpu/drm/i915/gt/intel_reset.h
@@ -11,56 +11,67 @@
 #include <linux/types.h>
 #include <linux/srcu.h>
 
-#include "gt/intel_engine_types.h"
+#include "intel_engine_types.h"
+#include "intel_reset_types.h"
 
 struct drm_i915_private;
 struct i915_request;
 struct intel_engine_cs;
+struct intel_gt;
 struct intel_guc;
 
+void intel_gt_init_reset(struct intel_gt *gt);
+void intel_gt_fini_reset(struct intel_gt *gt);
+
 __printf(4, 5)
-void i915_handle_error(struct drm_i915_private *i915,
-		       intel_engine_mask_t engine_mask,
-		       unsigned long flags,
-		       const char *fmt, ...);
+void intel_gt_handle_error(struct intel_gt *gt,
+			   intel_engine_mask_t engine_mask,
+			   unsigned long flags,
+			   const char *fmt, ...);
 #define I915_ERROR_CAPTURE BIT(0)
 
-void i915_reset(struct drm_i915_private *i915,
-		intel_engine_mask_t stalled_mask,
-		const char *reason);
-int i915_reset_engine(struct intel_engine_cs *engine,
-		      const char *reason);
-
-void i915_reset_request(struct i915_request *rq, bool guilty);
+void intel_gt_reset(struct intel_gt *gt,
+		    intel_engine_mask_t stalled_mask,
+		    const char *reason);
+int intel_engine_reset(struct intel_engine_cs *engine,
+		       const char *reason);
 
-int __must_check i915_reset_trylock(struct drm_i915_private *i915);
-void i915_reset_unlock(struct drm_i915_private *i915, int tag);
+void __i915_request_reset(struct i915_request *rq, bool guilty);
 
-int i915_terminally_wedged(struct drm_i915_private *i915);
+int __must_check intel_gt_reset_trylock(struct intel_gt *gt);
+void intel_gt_reset_unlock(struct intel_gt *gt, int tag);
 
-bool intel_has_gpu_reset(struct drm_i915_private *i915);
-bool intel_has_reset_engine(struct drm_i915_private *i915);
+void intel_gt_set_wedged(struct intel_gt *gt);
+bool intel_gt_unset_wedged(struct intel_gt *gt);
+int intel_gt_terminally_wedged(struct intel_gt *gt);
 
-int intel_gpu_reset(struct drm_i915_private *i915,
-		    intel_engine_mask_t engine_mask);
+int intel_gpu_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask);
 
-int intel_reset_guc(struct drm_i915_private *i915);
+int intel_reset_guc(struct intel_gt *gt);
 
-struct i915_wedge_me {
+struct intel_wedge_me {
 	struct delayed_work work;
-	struct drm_i915_private *i915;
+	struct intel_gt *gt;
 	const char *name;
 };
 
-void __i915_init_wedge(struct i915_wedge_me *w,
-		       struct drm_i915_private *i915,
-		       long timeout,
-		       const char *name);
-void __i915_fini_wedge(struct i915_wedge_me *w);
+void __intel_init_wedge(struct intel_wedge_me *w,
+			struct intel_gt *gt,
+			long timeout,
+			const char *name);
+void __intel_fini_wedge(struct intel_wedge_me *w);
 
-#define i915_wedge_on_timeout(W, DEV, TIMEOUT)				\
-	for (__i915_init_wedge((W), (DEV), (TIMEOUT), __func__);	\
-	     (W)->i915;							\
-	     __i915_fini_wedge((W)))
+#define intel_wedge_on_timeout(W, GT, TIMEOUT)				\
+	for (__intel_init_wedge((W), (GT), (TIMEOUT), __func__);	\
+	     (W)->gt;							\
+	     __intel_fini_wedge((W)))
+
+static inline bool __intel_reset_failed(const struct intel_reset *reset)
+{
+	return unlikely(test_bit(I915_WEDGED, &reset->flags));
+}
+
+bool intel_has_gpu_reset(struct drm_i915_private *i915);
+bool intel_has_reset_engine(struct drm_i915_private *i915);
 
 #endif /* I915_RESET_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_reset_types.h b/drivers/gpu/drm/i915/gt/intel_reset_types.h
new file mode 100644
index 000000000000..31968356e0c0
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_reset_types.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef __INTEL_RESET_TYPES_H_
+#define __INTEL_RESET_TYPES_H_
+
+#include <linux/mutex.h>
+#include <linux/wait.h>
+#include <linux/srcu.h>
+
+struct intel_reset {
+	/**
+	 * flags: Control various stages of the GPU reset
+	 *
+	 * #I915_RESET_BACKOFF - When we start a global reset, we need to
+	 * serialise with any other users attempting to do the same, and
+	 * any global resources that may be clobber by the reset (such as
+	 * FENCE registers).
+	 *
+	 * #I915_RESET_ENGINE[num_engines] - Since the driver doesn't need to
+	 * acquire the struct_mutex to reset an engine, we need an explicit
+	 * flag to prevent two concurrent reset attempts in the same engine.
+	 * As the number of engines continues to grow, allocate the flags from
+	 * the most significant bits.
+	 *
+	 * #I915_WEDGED - If reset fails and we can no longer use the GPU,
+	 * we set the #I915_WEDGED bit. Prior to command submission, e.g.
+	 * i915_request_alloc(), this bit is checked and the sequence
+	 * aborted (with -EIO reported to userspace) if set.
+	 */
+	unsigned long flags;
+#define I915_RESET_BACKOFF	0
+#define I915_RESET_MODESET	1
+#define I915_RESET_ENGINE	2
+#define I915_WEDGED		(BITS_PER_LONG - 1)
+
+	struct mutex mutex; /* serialises wedging/unwedging */
+
+	/**
+	 * Waitqueue to signal when the reset has completed. Used by clients
+	 * that wait for dev_priv->mm.wedged to settle.
+	 */
+	wait_queue_head_t queue;
+
+	struct srcu_struct backoff_srcu;
+};
+
+#endif /* _INTEL_RESET_TYPES_H_ */
diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
index e2b5de58913c..189b75074121 100644
--- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
@@ -795,7 +795,7 @@ static void reset_ring(struct intel_engine_cs *engine, bool stalled)
 		 * If the request was innocent, we try to replay the request
 		 * with the restored context.
 		 */
-		i915_reset_request(rq, stalled);
+		__i915_request_reset(rq, stalled);
 
 		GEM_BUG_ON(rq->ring != engine->buffer);
 		head = rq->head;
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 2d9cc3cd1f27..e2fa38a1ff0f 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -32,7 +32,6 @@
 #include "selftests/i915_random.h"
 #include "selftests/igt_flush_test.h"
 #include "selftests/igt_reset.h"
-#include "selftests/igt_wedge_me.h"
 #include "selftests/igt_atomic.h"
 
 #include "selftests/mock_drm.h"
@@ -43,7 +42,6 @@
 #define IGT_IDLE_TIMEOUT 50 /* ms; time to wait after flushing between tests */
 
 struct hang {
-	struct drm_i915_private *i915;
 	struct intel_gt *gt;
 	struct drm_i915_gem_object *hws;
 	struct drm_i915_gem_object *obj;
@@ -52,27 +50,27 @@ struct hang {
 	u32 *batch;
 };
 
-static int hang_init(struct hang *h, struct drm_i915_private *i915)
+static int hang_init(struct hang *h, struct intel_gt *gt)
 {
 	void *vaddr;
 	int err;
 
 	memset(h, 0, sizeof(*h));
-	h->i915 = i915;
+	h->gt = gt;
 
-	h->ctx = kernel_context(i915);
+	h->ctx = kernel_context(gt->i915);
 	if (IS_ERR(h->ctx))
 		return PTR_ERR(h->ctx);
 
 	GEM_BUG_ON(i915_gem_context_is_bannable(h->ctx));
 
-	h->hws = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	h->hws = i915_gem_object_create_internal(gt->i915, PAGE_SIZE);
 	if (IS_ERR(h->hws)) {
 		err = PTR_ERR(h->hws);
 		goto err_ctx;
 	}
 
-	h->obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	h->obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE);
 	if (IS_ERR(h->obj)) {
 		err = PTR_ERR(h->obj);
 		goto err_hws;
@@ -87,7 +85,7 @@ static int hang_init(struct hang *h, struct drm_i915_private *i915)
 	h->seqno = memset(vaddr, 0xff, PAGE_SIZE);
 
 	vaddr = i915_gem_object_pin_map(h->obj,
-					i915_coherent_map_type(i915));
+					i915_coherent_map_type(gt->i915));
 	if (IS_ERR(vaddr)) {
 		err = PTR_ERR(vaddr);
 		goto err_unpin_hws;
@@ -129,7 +127,7 @@ static int move_to_active(struct i915_vma *vma,
 static struct i915_request *
 hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *i915 = h->i915;
+	struct intel_gt *gt = h->gt;
 	struct i915_address_space *vm = h->ctx->vm ?: &engine->gt->ggtt->vm;
 	struct drm_i915_gem_object *obj;
 	struct i915_request *rq = NULL;
@@ -139,11 +137,11 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 	u32 *batch;
 	int err;
 
-	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE);
 	if (IS_ERR(obj))
 		return ERR_CAST(obj);
 
-	vaddr = i915_gem_object_pin_map(obj, i915_coherent_map_type(i915));
+	vaddr = i915_gem_object_pin_map(obj, i915_coherent_map_type(gt->i915));
 	if (IS_ERR(vaddr)) {
 		i915_gem_object_put(obj);
 		return ERR_CAST(vaddr);
@@ -186,7 +184,7 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 		goto cancel_rq;
 
 	batch = h->batch;
-	if (INTEL_GEN(i915) >= 8) {
+	if (INTEL_GEN(gt->i915) >= 8) {
 		*batch++ = MI_STORE_DWORD_IMM_GEN4;
 		*batch++ = lower_32_bits(hws_address(hws, rq));
 		*batch++ = upper_32_bits(hws_address(hws, rq));
@@ -200,7 +198,7 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 		*batch++ = MI_BATCH_BUFFER_START | 1 << 8 | 1;
 		*batch++ = lower_32_bits(vma->node.start);
 		*batch++ = upper_32_bits(vma->node.start);
-	} else if (INTEL_GEN(i915) >= 6) {
+	} else if (INTEL_GEN(gt->i915) >= 6) {
 		*batch++ = MI_STORE_DWORD_IMM_GEN4;
 		*batch++ = 0;
 		*batch++ = lower_32_bits(hws_address(hws, rq));
@@ -213,7 +211,7 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 		*batch++ = MI_ARB_CHECK;
 		*batch++ = MI_BATCH_BUFFER_START | 1 << 8;
 		*batch++ = lower_32_bits(vma->node.start);
-	} else if (INTEL_GEN(i915) >= 4) {
+	} else if (INTEL_GEN(gt->i915) >= 4) {
 		*batch++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
 		*batch++ = 0;
 		*batch++ = lower_32_bits(hws_address(hws, rq));
@@ -249,7 +247,7 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 	}
 
 	flags = 0;
-	if (INTEL_GEN(i915) <= 5)
+	if (INTEL_GEN(gt->i915) <= 5)
 		flags |= I915_DISPATCH_SECURE;
 
 	err = rq->engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, flags);
@@ -286,7 +284,7 @@ static void hang_fini(struct hang *h)
 
 	kernel_context_close(h->ctx);
 
-	igt_flush_test(h->i915, I915_WAIT_LOCKED);
+	igt_flush_test(h->gt->i915, I915_WAIT_LOCKED);
 }
 
 static bool wait_until_running(struct hang *h, struct i915_request *rq)
@@ -301,7 +299,7 @@ static bool wait_until_running(struct hang *h, struct i915_request *rq)
 
 static int igt_hang_sanitycheck(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct i915_request *rq;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -310,13 +308,13 @@ static int igt_hang_sanitycheck(void *arg)
 
 	/* Basic check that we can execute our hanging batch */
 
-	mutex_lock(&i915->drm.struct_mutex);
-	err = hang_init(&h, i915);
+	mutex_lock(&gt->i915->drm.struct_mutex);
+	err = hang_init(&h, gt);
 	if (err)
 		goto unlock;
 
-	for_each_engine(engine, i915, id) {
-		struct igt_wedge_me w;
+	for_each_engine(engine, gt->i915, id) {
+		struct intel_wedge_me w;
 		long timeout;
 
 		if (!intel_engine_can_store_dword(engine))
@@ -338,10 +336,10 @@ static int igt_hang_sanitycheck(void *arg)
 		i915_request_add(rq);
 
 		timeout = 0;
-		igt_wedge_on_timeout(&w, i915, HZ / 10 /* 100ms timeout*/)
+		intel_wedge_on_timeout(&w, gt, HZ / 10 /* 100ms */)
 			timeout = i915_request_wait(rq, 0,
 						    MAX_SCHEDULE_TIMEOUT);
-		if (i915_reset_failed(i915))
+		if (intel_gt_is_wedged(gt))
 			timeout = -EIO;
 
 		i915_request_put(rq);
@@ -357,7 +355,7 @@ static int igt_hang_sanitycheck(void *arg)
 fini:
 	hang_fini(&h);
 unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
+	mutex_unlock(&gt->i915->drm.struct_mutex);
 	return err;
 }
 
@@ -368,7 +366,8 @@ static bool wait_for_idle(struct intel_engine_cs *engine)
 
 static int igt_reset_nop(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
+	struct i915_gpu_error *global = &gt->i915->gpu_error;
 	struct intel_engine_cs *engine;
 	struct i915_gem_context *ctx;
 	unsigned int reset_count, count;
@@ -379,25 +378,25 @@ static int igt_reset_nop(void *arg)
 
 	/* Check that we can reset during non-user portions of requests */
 
-	file = mock_file(i915);
+	file = mock_file(gt->i915);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&i915->drm.struct_mutex);
-	ctx = live_context(i915, file);
-	mutex_unlock(&i915->drm.struct_mutex);
+	mutex_lock(&gt->i915->drm.struct_mutex);
+	ctx = live_context(gt->i915, file);
+	mutex_unlock(&gt->i915->drm.struct_mutex);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
 		goto out;
 	}
 
 	i915_gem_context_clear_bannable(ctx);
-	reset_count = i915_reset_count(&i915->gpu_error);
+	reset_count = i915_reset_count(global);
 	count = 0;
 	do {
-		mutex_lock(&i915->drm.struct_mutex);
+		mutex_lock(&gt->i915->drm.struct_mutex);
 
-		for_each_engine(engine, i915, id) {
+		for_each_engine(engine, gt->i915, id) {
 			int i;
 
 			for (i = 0; i < 16; i++) {
@@ -413,43 +412,43 @@ static int igt_reset_nop(void *arg)
 			}
 		}
 
-		igt_global_reset_lock(i915);
-		i915_reset(i915, ALL_ENGINES, NULL);
-		igt_global_reset_unlock(i915);
+		igt_global_reset_lock(gt);
+		intel_gt_reset(gt, ALL_ENGINES, NULL);
+		igt_global_reset_unlock(gt);
 
-		mutex_unlock(&i915->drm.struct_mutex);
-		if (i915_reset_failed(i915)) {
+		mutex_unlock(&gt->i915->drm.struct_mutex);
+		if (intel_gt_is_wedged(gt)) {
 			err = -EIO;
 			break;
 		}
 
-		if (i915_reset_count(&i915->gpu_error) !=
-		    reset_count + ++count) {
+		if (i915_reset_count(global) != reset_count + ++count) {
 			pr_err("Full GPU reset not recorded!\n");
 			err = -EINVAL;
 			break;
 		}
 
-		err = igt_flush_test(i915, 0);
+		err = igt_flush_test(gt->i915, 0);
 		if (err)
 			break;
 	} while (time_before(jiffies, end_time));
 	pr_info("%s: %d resets\n", __func__, count);
 
-	mutex_lock(&i915->drm.struct_mutex);
-	err = igt_flush_test(i915, I915_WAIT_LOCKED);
-	mutex_unlock(&i915->drm.struct_mutex);
+	mutex_lock(&gt->i915->drm.struct_mutex);
+	err = igt_flush_test(gt->i915, I915_WAIT_LOCKED);
+	mutex_unlock(&gt->i915->drm.struct_mutex);
 
 out:
-	mock_file_free(i915, file);
-	if (i915_reset_failed(i915))
+	mock_file_free(gt->i915, file);
+	if (intel_gt_is_wedged(gt))
 		err = -EIO;
 	return err;
 }
 
 static int igt_reset_nop_engine(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
+	struct i915_gpu_error *global = &gt->i915->gpu_error;
 	struct intel_engine_cs *engine;
 	struct i915_gem_context *ctx;
 	enum intel_engine_id id;
@@ -458,33 +457,32 @@ static int igt_reset_nop_engine(void *arg)
 
 	/* Check that we can engine-reset during non-user portions */
 
-	if (!intel_has_reset_engine(i915))
+	if (!intel_has_reset_engine(gt->i915))
 		return 0;
 
-	file = mock_file(i915);
+	file = mock_file(gt->i915);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&i915->drm.struct_mutex);
-	ctx = live_context(i915, file);
-	mutex_unlock(&i915->drm.struct_mutex);
+	mutex_lock(&gt->i915->drm.struct_mutex);
+	ctx = live_context(gt->i915, file);
+	mutex_unlock(&gt->i915->drm.struct_mutex);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
 		goto out;
 	}
 
 	i915_gem_context_clear_bannable(ctx);
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		unsigned int reset_count, reset_engine_count;
 		unsigned int count;
 		IGT_TIMEOUT(end_time);
 
-		reset_count = i915_reset_count(&i915->gpu_error);
-		reset_engine_count = i915_reset_engine_count(&i915->gpu_error,
-							     engine);
+		reset_count = i915_reset_count(global);
+		reset_engine_count = i915_reset_engine_count(global, engine);
 		count = 0;
 
-		set_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		do {
 			int i;
 
@@ -495,7 +493,7 @@ static int igt_reset_nop_engine(void *arg)
 				break;
 			}
 
-			mutex_lock(&i915->drm.struct_mutex);
+			mutex_lock(&gt->i915->drm.struct_mutex);
 			for (i = 0; i < 16; i++) {
 				struct i915_request *rq;
 
@@ -507,20 +505,20 @@ static int igt_reset_nop_engine(void *arg)
 
 				i915_request_add(rq);
 			}
-			err = i915_reset_engine(engine, NULL);
-			mutex_unlock(&i915->drm.struct_mutex);
+			err = intel_engine_reset(engine, NULL);
+			mutex_unlock(&gt->i915->drm.struct_mutex);
 			if (err) {
 				pr_err("i915_reset_engine failed\n");
 				break;
 			}
 
-			if (i915_reset_count(&i915->gpu_error) != reset_count) {
+			if (i915_reset_count(global) != reset_count) {
 				pr_err("Full GPU reset recorded! (engine reset expected)\n");
 				err = -EINVAL;
 				break;
 			}
 
-			if (i915_reset_engine_count(&i915->gpu_error, engine) !=
+			if (i915_reset_engine_count(global, engine) !=
 			    reset_engine_count + ++count) {
 				pr_err("%s engine reset not recorded!\n",
 				       engine->name);
@@ -528,30 +526,31 @@ static int igt_reset_nop_engine(void *arg)
 				break;
 			}
 		} while (time_before(jiffies, end_time));
-		clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		pr_info("%s(%s): %d resets\n", __func__, engine->name, count);
 
 		if (err)
 			break;
 
-		err = igt_flush_test(i915, 0);
+		err = igt_flush_test(gt->i915, 0);
 		if (err)
 			break;
 	}
 
-	mutex_lock(&i915->drm.struct_mutex);
-	err = igt_flush_test(i915, I915_WAIT_LOCKED);
-	mutex_unlock(&i915->drm.struct_mutex);
+	mutex_lock(&gt->i915->drm.struct_mutex);
+	err = igt_flush_test(gt->i915, I915_WAIT_LOCKED);
+	mutex_unlock(&gt->i915->drm.struct_mutex);
 
 out:
-	mock_file_free(i915, file);
-	if (i915_reset_failed(i915))
+	mock_file_free(gt->i915, file);
+	if (intel_gt_is_wedged(gt))
 		err = -EIO;
 	return err;
 }
 
-static int __igt_reset_engine(struct drm_i915_private *i915, bool active)
+static int __igt_reset_engine(struct intel_gt *gt, bool active)
 {
+	struct i915_gpu_error *global = &gt->i915->gpu_error;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	struct hang h;
@@ -559,18 +558,18 @@ static int __igt_reset_engine(struct drm_i915_private *i915, bool active)
 
 	/* Check that we can issue an engine reset on an idle engine (no-op) */
 
-	if (!intel_has_reset_engine(i915))
+	if (!intel_has_reset_engine(gt->i915))
 		return 0;
 
 	if (active) {
-		mutex_lock(&i915->drm.struct_mutex);
-		err = hang_init(&h, i915);
-		mutex_unlock(&i915->drm.struct_mutex);
+		mutex_lock(&gt->i915->drm.struct_mutex);
+		err = hang_init(&h, gt);
+		mutex_unlock(&gt->i915->drm.struct_mutex);
 		if (err)
 			return err;
 	}
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		unsigned int reset_count, reset_engine_count;
 		IGT_TIMEOUT(end_time);
 
@@ -584,30 +583,29 @@ static int __igt_reset_engine(struct drm_i915_private *i915, bool active)
 			break;
 		}
 
-		reset_count = i915_reset_count(&i915->gpu_error);
-		reset_engine_count = i915_reset_engine_count(&i915->gpu_error,
-							     engine);
+		reset_count = i915_reset_count(global);
+		reset_engine_count = i915_reset_engine_count(global, engine);
 
 		intel_engine_pm_get(engine);
-		set_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		do {
 			if (active) {
 				struct i915_request *rq;
 
-				mutex_lock(&i915->drm.struct_mutex);
+				mutex_lock(&gt->i915->drm.struct_mutex);
 				rq = hang_create_request(&h, engine);
 				if (IS_ERR(rq)) {
 					err = PTR_ERR(rq);
-					mutex_unlock(&i915->drm.struct_mutex);
+					mutex_unlock(&gt->i915->drm.struct_mutex);
 					break;
 				}
 
 				i915_request_get(rq);
 				i915_request_add(rq);
-				mutex_unlock(&i915->drm.struct_mutex);
+				mutex_unlock(&gt->i915->drm.struct_mutex);
 
 				if (!wait_until_running(&h, rq)) {
-					struct drm_printer p = drm_info_printer(i915->drm.dev);
+					struct drm_printer p = drm_info_printer(gt->i915->drm.dev);
 
 					pr_err("%s: Failed to start request %llx, at %x\n",
 					       __func__, rq->fence.seqno, hws_seqno(&h, rq));
@@ -622,19 +620,19 @@ static int __igt_reset_engine(struct drm_i915_private *i915, bool active)
 				i915_request_put(rq);
 			}
 
-			err = i915_reset_engine(engine, NULL);
+			err = intel_engine_reset(engine, NULL);
 			if (err) {
 				pr_err("i915_reset_engine failed\n");
 				break;
 			}
 
-			if (i915_reset_count(&i915->gpu_error) != reset_count) {
+			if (i915_reset_count(global) != reset_count) {
 				pr_err("Full GPU reset recorded! (engine reset expected)\n");
 				err = -EINVAL;
 				break;
 			}
 
-			if (i915_reset_engine_count(&i915->gpu_error, engine) !=
+			if (i915_reset_engine_count(global, engine) !=
 			    ++reset_engine_count) {
 				pr_err("%s engine reset not recorded!\n",
 				       engine->name);
@@ -642,24 +640,24 @@ static int __igt_reset_engine(struct drm_i915_private *i915, bool active)
 				break;
 			}
 		} while (time_before(jiffies, end_time));
-		clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		intel_engine_pm_put(engine);
 
 		if (err)
 			break;
 
-		err = igt_flush_test(i915, 0);
+		err = igt_flush_test(gt->i915, 0);
 		if (err)
 			break;
 	}
 
-	if (i915_reset_failed(i915))
+	if (intel_gt_is_wedged(gt))
 		err = -EIO;
 
 	if (active) {
-		mutex_lock(&i915->drm.struct_mutex);
+		mutex_lock(&gt->i915->drm.struct_mutex);
 		hang_fini(&h);
-		mutex_unlock(&i915->drm.struct_mutex);
+		mutex_unlock(&gt->i915->drm.struct_mutex);
 	}
 
 	return err;
@@ -701,7 +699,7 @@ static int active_request_put(struct i915_request *rq)
 			  rq->fence.seqno);
 		GEM_TRACE_DUMP();
 
-		i915_gem_set_wedged(rq->i915);
+		intel_gt_set_wedged(rq->engine->gt);
 		err = -EIO;
 	}
 
@@ -778,10 +776,11 @@ static int active_engine(void *data)
 	return err;
 }
 
-static int __igt_reset_engines(struct drm_i915_private *i915,
+static int __igt_reset_engines(struct intel_gt *gt,
 			       const char *test_name,
 			       unsigned int flags)
 {
+	struct i915_gpu_error *global = &gt->i915->gpu_error;
 	struct intel_engine_cs *engine, *other;
 	enum intel_engine_id id, tmp;
 	struct hang h;
@@ -791,13 +790,13 @@ static int __igt_reset_engines(struct drm_i915_private *i915,
 	 * with any other engine.
 	 */
 
-	if (!intel_has_reset_engine(i915))
+	if (!intel_has_reset_engine(gt->i915))
 		return 0;
 
 	if (flags & TEST_ACTIVE) {
-		mutex_lock(&i915->drm.struct_mutex);
-		err = hang_init(&h, i915);
-		mutex_unlock(&i915->drm.struct_mutex);
+		mutex_lock(&gt->i915->drm.struct_mutex);
+		err = hang_init(&h, gt);
+		mutex_unlock(&gt->i915->drm.struct_mutex);
 		if (err)
 			return err;
 
@@ -805,9 +804,9 @@ static int __igt_reset_engines(struct drm_i915_private *i915,
 			h.ctx->sched.priority = 1024;
 	}
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		struct active_engine threads[I915_NUM_ENGINES] = {};
-		unsigned long global = i915_reset_count(&i915->gpu_error);
+		unsigned long device = i915_reset_count(global);
 		unsigned long count = 0, reported;
 		IGT_TIMEOUT(end_time);
 
@@ -823,12 +822,11 @@ static int __igt_reset_engines(struct drm_i915_private *i915,
 		}
 
 		memset(threads, 0, sizeof(threads));
-		for_each_engine(other, i915, tmp) {
+		for_each_engine(other, gt->i915, tmp) {
 			struct task_struct *tsk;
 
 			threads[tmp].resets =
-				i915_reset_engine_count(&i915->gpu_error,
-							other);
+				i915_reset_engine_count(global, other);
 
 			if (!(flags & TEST_OTHERS))
 				continue;
@@ -851,25 +849,25 @@ static int __igt_reset_engines(struct drm_i915_private *i915,
 		}
 
 		intel_engine_pm_get(engine);
-		set_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		do {
 			struct i915_request *rq = NULL;
 
 			if (flags & TEST_ACTIVE) {
-				mutex_lock(&i915->drm.struct_mutex);
+				mutex_lock(&gt->i915->drm.struct_mutex);
 				rq = hang_create_request(&h, engine);
 				if (IS_ERR(rq)) {
 					err = PTR_ERR(rq);
-					mutex_unlock(&i915->drm.struct_mutex);
+					mutex_unlock(&gt->i915->drm.struct_mutex);
 					break;
 				}
 
 				i915_request_get(rq);
 				i915_request_add(rq);
-				mutex_unlock(&i915->drm.struct_mutex);
+				mutex_unlock(&gt->i915->drm.struct_mutex);
 
 				if (!wait_until_running(&h, rq)) {
-					struct drm_printer p = drm_info_printer(i915->drm.dev);
+					struct drm_printer p = drm_info_printer(gt->i915->drm.dev);
 
 					pr_err("%s: Failed to start request %llx, at %x\n",
 					       __func__, rq->fence.seqno, hws_seqno(&h, rq));
@@ -882,7 +880,7 @@ static int __igt_reset_engines(struct drm_i915_private *i915,
 				}
 			}
 
-			err = i915_reset_engine(engine, NULL);
+			err = intel_engine_reset(engine, NULL);
 			if (err) {
 				pr_err("i915_reset_engine(%s:%s): failed, err=%d\n",
 				       engine->name, test_name, err);
@@ -894,7 +892,7 @@ static int __igt_reset_engines(struct drm_i915_private *i915,
 			if (rq) {
 				if (i915_request_wait(rq, 0, HZ / 5) < 0) {
 					struct drm_printer p =
-						drm_info_printer(i915->drm.dev);
+						drm_info_printer(gt->i915->drm.dev);
 
 					pr_err("i915_reset_engine(%s:%s):"
 					       " failed to complete request after reset\n",
@@ -904,7 +902,7 @@ static int __igt_reset_engines(struct drm_i915_private *i915,
 					i915_request_put(rq);
 
 					GEM_TRACE_DUMP();
-					i915_gem_set_wedged(i915);
+					intel_gt_set_wedged(gt);
 					err = -EIO;
 					break;
 				}
@@ -914,7 +912,7 @@ static int __igt_reset_engines(struct drm_i915_private *i915,
 
 			if (!(flags & TEST_SELF) && !wait_for_idle(engine)) {
 				struct drm_printer p =
-					drm_info_printer(i915->drm.dev);
+					drm_info_printer(gt->i915->drm.dev);
 
 				pr_err("i915_reset_engine(%s:%s):"
 				       " failed to idle after reset\n",
@@ -926,12 +924,12 @@ static int __igt_reset_engines(struct drm_i915_private *i915,
 				break;
 			}
 		} while (time_before(jiffies, end_time));
-		clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		intel_engine_pm_put(engine);
 		pr_info("i915_reset_engine(%s:%s): %lu resets\n",
 			engine->name, test_name, count);
 
-		reported = i915_reset_engine_count(&i915->gpu_error, engine);
+		reported = i915_reset_engine_count(global, engine);
 		reported -= threads[engine->id].resets;
 		if (reported != count) {
 			pr_err("i915_reset_engine(%s:%s): reset %lu times, but reported %lu\n",
@@ -941,7 +939,7 @@ static int __igt_reset_engines(struct drm_i915_private *i915,
 		}
 
 unwind:
-		for_each_engine(other, i915, tmp) {
+		for_each_engine(other, gt->i915, tmp) {
 			int ret;
 
 			if (!threads[tmp].task)
@@ -956,22 +954,21 @@ static int __igt_reset_engines(struct drm_i915_private *i915,
 			}
 			put_task_struct(threads[tmp].task);
 
-			if (other != engine &&
+			if (other->uabi_class != engine->uabi_class &&
 			    threads[tmp].resets !=
-			    i915_reset_engine_count(&i915->gpu_error, other)) {
+			    i915_reset_engine_count(global, other)) {
 				pr_err("Innocent engine %s was reset (count=%ld)\n",
 				       other->name,
-				       i915_reset_engine_count(&i915->gpu_error,
-							       other) -
+				       i915_reset_engine_count(global, other) -
 				       threads[tmp].resets);
 				if (!err)
 					err = -EINVAL;
 			}
 		}
 
-		if (global != i915_reset_count(&i915->gpu_error)) {
+		if (device != i915_reset_count(global)) {
 			pr_err("Global reset (count=%ld)!\n",
-			       i915_reset_count(&i915->gpu_error) - global);
+			       i915_reset_count(global) - device);
 			if (!err)
 				err = -EINVAL;
 		}
@@ -979,20 +976,20 @@ static int __igt_reset_engines(struct drm_i915_private *i915,
 		if (err)
 			break;
 
-		mutex_lock(&i915->drm.struct_mutex);
-		err = igt_flush_test(i915, I915_WAIT_LOCKED);
-		mutex_unlock(&i915->drm.struct_mutex);
+		mutex_lock(&gt->i915->drm.struct_mutex);
+		err = igt_flush_test(gt->i915, I915_WAIT_LOCKED);
+		mutex_unlock(&gt->i915->drm.struct_mutex);
 		if (err)
 			break;
 	}
 
-	if (i915_reset_failed(i915))
+	if (intel_gt_is_wedged(gt))
 		err = -EIO;
 
 	if (flags & TEST_ACTIVE) {
-		mutex_lock(&i915->drm.struct_mutex);
+		mutex_lock(&gt->i915->drm.struct_mutex);
 		hang_fini(&h);
-		mutex_unlock(&i915->drm.struct_mutex);
+		mutex_unlock(&gt->i915->drm.struct_mutex);
 	}
 
 	return err;
@@ -1018,13 +1015,13 @@ static int igt_reset_engines(void *arg)
 		},
 		{ }
 	};
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	typeof(*phases) *p;
 	int err;
 
 	for (p = phases; p->name; p++) {
 		if (p->flags & TEST_PRIORITY) {
-			if (!(i915->caps.scheduler & I915_SCHEDULER_CAP_PRIORITY))
+			if (!(gt->i915->caps.scheduler & I915_SCHEDULER_CAP_PRIORITY))
 				continue;
 		}
 
@@ -1036,38 +1033,39 @@ static int igt_reset_engines(void *arg)
 	return 0;
 }
 
-static u32 fake_hangcheck(struct drm_i915_private *i915,
-			  intel_engine_mask_t mask)
+static u32 fake_hangcheck(struct intel_gt *gt, intel_engine_mask_t mask)
 {
-	u32 count = i915_reset_count(&i915->gpu_error);
+	u32 count = i915_reset_count(&gt->i915->gpu_error);
 
-	i915_reset(i915, mask, NULL);
+	intel_gt_reset(gt, mask, NULL);
 
 	return count;
 }
 
 static int igt_reset_wait(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
+	struct i915_gpu_error *global = &gt->i915->gpu_error;
+	struct intel_engine_cs *engine = gt->i915->engine[RCS0];
 	struct i915_request *rq;
 	unsigned int reset_count;
 	struct hang h;
 	long timeout;
 	int err;
 
-	if (!intel_engine_can_store_dword(i915->engine[RCS0]))
+	if (!engine || !intel_engine_can_store_dword(engine))
 		return 0;
 
 	/* Check that we detect a stuck waiter and issue a reset */
 
-	igt_global_reset_lock(i915);
+	igt_global_reset_lock(gt);
 
-	mutex_lock(&i915->drm.struct_mutex);
-	err = hang_init(&h, i915);
+	mutex_lock(&gt->i915->drm.struct_mutex);
+	err = hang_init(&h, gt);
 	if (err)
 		goto unlock;
 
-	rq = hang_create_request(&h, i915->engine[RCS0]);
+	rq = hang_create_request(&h, engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto fini;
@@ -1077,19 +1075,19 @@ static int igt_reset_wait(void *arg)
 	i915_request_add(rq);
 
 	if (!wait_until_running(&h, rq)) {
-		struct drm_printer p = drm_info_printer(i915->drm.dev);
+		struct drm_printer p = drm_info_printer(gt->i915->drm.dev);
 
 		pr_err("%s: Failed to start request %llx, at %x\n",
 		       __func__, rq->fence.seqno, hws_seqno(&h, rq));
 		intel_engine_dump(rq->engine, &p, "%s\n", rq->engine->name);
 
-		i915_gem_set_wedged(i915);
+		intel_gt_set_wedged(gt);
 
 		err = -EIO;
 		goto out_rq;
 	}
 
-	reset_count = fake_hangcheck(i915, ALL_ENGINES);
+	reset_count = fake_hangcheck(gt, ALL_ENGINES);
 
 	timeout = i915_request_wait(rq, 0, 10);
 	if (timeout < 0) {
@@ -1099,7 +1097,7 @@ static int igt_reset_wait(void *arg)
 		goto out_rq;
 	}
 
-	if (i915_reset_count(&i915->gpu_error) == reset_count) {
+	if (i915_reset_count(global) == reset_count) {
 		pr_err("No GPU reset recorded!\n");
 		err = -EINVAL;
 		goto out_rq;
@@ -1110,10 +1108,10 @@ static int igt_reset_wait(void *arg)
 fini:
 	hang_fini(&h);
 unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
-	igt_global_reset_unlock(i915);
+	mutex_unlock(&gt->i915->drm.struct_mutex);
+	igt_global_reset_unlock(gt);
 
-	if (i915_reset_failed(i915))
+	if (intel_gt_is_wedged(gt))
 		return -EIO;
 
 	return err;
@@ -1172,11 +1170,12 @@ static int evict_fence(void *data)
 	return err;
 }
 
-static int __igt_reset_evict_vma(struct drm_i915_private *i915,
+static int __igt_reset_evict_vma(struct intel_gt *gt,
 				 struct i915_address_space *vm,
 				 int (*fn)(void *),
 				 unsigned int flags)
 {
+	struct intel_engine_cs *engine = gt->i915->engine[RCS0];
 	struct drm_i915_gem_object *obj;
 	struct task_struct *tsk = NULL;
 	struct i915_request *rq;
@@ -1184,17 +1183,17 @@ static int __igt_reset_evict_vma(struct drm_i915_private *i915,
 	struct hang h;
 	int err;
 
-	if (!intel_engine_can_store_dword(i915->engine[RCS0]))
+	if (!engine || !intel_engine_can_store_dword(engine))
 		return 0;
 
 	/* Check that we can recover an unbind stuck on a hanging request */
 
-	mutex_lock(&i915->drm.struct_mutex);
-	err = hang_init(&h, i915);
+	mutex_lock(&gt->i915->drm.struct_mutex);
+	err = hang_init(&h, gt);
 	if (err)
 		goto unlock;
 
-	obj = i915_gem_object_create_internal(i915, SZ_1M);
+	obj = i915_gem_object_create_internal(gt->i915, SZ_1M);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
 		goto fini;
@@ -1214,7 +1213,7 @@ static int __igt_reset_evict_vma(struct drm_i915_private *i915,
 		goto out_obj;
 	}
 
-	rq = hang_create_request(&h, i915->engine[RCS0]);
+	rq = hang_create_request(&h, engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto out_obj;
@@ -1252,16 +1251,16 @@ static int __igt_reset_evict_vma(struct drm_i915_private *i915,
 	if (err)
 		goto out_rq;
 
-	mutex_unlock(&i915->drm.struct_mutex);
+	mutex_unlock(&gt->i915->drm.struct_mutex);
 
 	if (!wait_until_running(&h, rq)) {
-		struct drm_printer p = drm_info_printer(i915->drm.dev);
+		struct drm_printer p = drm_info_printer(gt->i915->drm.dev);
 
 		pr_err("%s: Failed to start request %llx, at %x\n",
 		       __func__, rq->fence.seqno, hws_seqno(&h, rq));
 		intel_engine_dump(rq->engine, &p, "%s\n", rq->engine->name);
 
-		i915_gem_set_wedged(i915);
+		intel_gt_set_wedged(gt);
 		goto out_reset;
 	}
 
@@ -1278,31 +1277,31 @@ static int __igt_reset_evict_vma(struct drm_i915_private *i915,
 	wait_for_completion(&arg.completion);
 
 	if (wait_for(!list_empty(&rq->fence.cb_list), 10)) {
-		struct drm_printer p = drm_info_printer(i915->drm.dev);
+		struct drm_printer p = drm_info_printer(gt->i915->drm.dev);
 
 		pr_err("igt/evict_vma kthread did not wait\n");
 		intel_engine_dump(rq->engine, &p, "%s\n", rq->engine->name);
 
-		i915_gem_set_wedged(i915);
+		intel_gt_set_wedged(gt);
 		goto out_reset;
 	}
 
 out_reset:
-	igt_global_reset_lock(i915);
-	fake_hangcheck(rq->i915, rq->engine->mask);
-	igt_global_reset_unlock(i915);
+	igt_global_reset_lock(gt);
+	fake_hangcheck(gt, rq->engine->mask);
+	igt_global_reset_unlock(gt);
 
 	if (tsk) {
-		struct igt_wedge_me w;
+		struct intel_wedge_me w;
 
 		/* The reset, even indirectly, should take less than 10ms. */
-		igt_wedge_on_timeout(&w, i915, HZ / 10 /* 100ms timeout*/)
+		intel_wedge_on_timeout(&w, gt, HZ / 10 /* 100ms */)
 			err = kthread_stop(tsk);
 
 		put_task_struct(tsk);
 	}
 
-	mutex_lock(&i915->drm.struct_mutex);
+	mutex_lock(&gt->i915->drm.struct_mutex);
 out_rq:
 	i915_request_put(rq);
 out_obj:
@@ -1310,9 +1309,9 @@ static int __igt_reset_evict_vma(struct drm_i915_private *i915,
 fini:
 	hang_fini(&h);
 unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
+	mutex_unlock(&gt->i915->drm.struct_mutex);
 
-	if (i915_reset_failed(i915))
+	if (intel_gt_is_wedged(gt))
 		return -EIO;
 
 	return err;
@@ -1320,26 +1319,26 @@ static int __igt_reset_evict_vma(struct drm_i915_private *i915,
 
 static int igt_reset_evict_ggtt(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 
-	return __igt_reset_evict_vma(i915, &i915->ggtt.vm,
+	return __igt_reset_evict_vma(gt, &gt->ggtt->vm,
 				     evict_vma, EXEC_OBJECT_WRITE);
 }
 
 static int igt_reset_evict_ppgtt(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct i915_gem_context *ctx;
 	struct drm_file *file;
 	int err;
 
-	file = mock_file(i915);
+	file = mock_file(gt->i915);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&i915->drm.struct_mutex);
-	ctx = live_context(i915, file);
-	mutex_unlock(&i915->drm.struct_mutex);
+	mutex_lock(&gt->i915->drm.struct_mutex);
+	ctx = live_context(gt->i915, file);
+	mutex_unlock(&gt->i915->drm.struct_mutex);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
 		goto out;
@@ -1347,29 +1346,29 @@ static int igt_reset_evict_ppgtt(void *arg)
 
 	err = 0;
 	if (ctx->vm) /* aliasing == global gtt locking, covered above */
-		err = __igt_reset_evict_vma(i915, ctx->vm,
+		err = __igt_reset_evict_vma(gt, ctx->vm,
 					    evict_vma, EXEC_OBJECT_WRITE);
 
 out:
-	mock_file_free(i915, file);
+	mock_file_free(gt->i915, file);
 	return err;
 }
 
 static int igt_reset_evict_fence(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 
-	return __igt_reset_evict_vma(i915, &i915->ggtt.vm,
+	return __igt_reset_evict_vma(gt, &gt->ggtt->vm,
 				     evict_fence, EXEC_OBJECT_NEEDS_FENCE);
 }
 
-static int wait_for_others(struct drm_i915_private *i915,
+static int wait_for_others(struct intel_gt *gt,
 			   struct intel_engine_cs *exclude)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		if (engine == exclude)
 			continue;
 
@@ -1382,7 +1381,8 @@ static int wait_for_others(struct drm_i915_private *i915,
 
 static int igt_reset_queue(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
+	struct i915_gpu_error *global = &gt->i915->gpu_error;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	struct hang h;
@@ -1390,14 +1390,14 @@ static int igt_reset_queue(void *arg)
 
 	/* Check that we replay pending requests following a hang */
 
-	igt_global_reset_lock(i915);
+	igt_global_reset_lock(gt);
 
-	mutex_lock(&i915->drm.struct_mutex);
-	err = hang_init(&h, i915);
+	mutex_lock(&gt->i915->drm.struct_mutex);
+	err = hang_init(&h, gt);
 	if (err)
 		goto unlock;
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		struct i915_request *prev;
 		IGT_TIMEOUT(end_time);
 		unsigned int count;
@@ -1438,7 +1438,7 @@ static int igt_reset_queue(void *arg)
 			 * (hangcheck), or we focus on resetting just one
 			 * engine and so avoid repeatedly resetting innocents.
 			 */
-			err = wait_for_others(i915, engine);
+			err = wait_for_others(gt, engine);
 			if (err) {
 				pr_err("%s(%s): Failed to idle other inactive engines after device reset\n",
 				       __func__, engine->name);
@@ -1446,12 +1446,12 @@ static int igt_reset_queue(void *arg)
 				i915_request_put(prev);
 
 				GEM_TRACE_DUMP();
-				i915_gem_set_wedged(i915);
+				intel_gt_set_wedged(gt);
 				goto fini;
 			}
 
 			if (!wait_until_running(&h, prev)) {
-				struct drm_printer p = drm_info_printer(i915->drm.dev);
+				struct drm_printer p = drm_info_printer(gt->i915->drm.dev);
 
 				pr_err("%s(%s): Failed to start request %llx, at %x\n",
 				       __func__, engine->name,
@@ -1462,13 +1462,13 @@ static int igt_reset_queue(void *arg)
 				i915_request_put(rq);
 				i915_request_put(prev);
 
-				i915_gem_set_wedged(i915);
+				intel_gt_set_wedged(gt);
 
 				err = -EIO;
 				goto fini;
 			}
 
-			reset_count = fake_hangcheck(i915, BIT(id));
+			reset_count = fake_hangcheck(gt, BIT(id));
 
 			if (prev->fence.error != -EIO) {
 				pr_err("GPU reset not recorded on hanging request [fence.error=%d]!\n",
@@ -1488,7 +1488,7 @@ static int igt_reset_queue(void *arg)
 				goto fini;
 			}
 
-			if (i915_reset_count(&i915->gpu_error) == reset_count) {
+			if (i915_reset_count(global) == reset_count) {
 				pr_err("No GPU reset recorded!\n");
 				i915_request_put(rq);
 				i915_request_put(prev);
@@ -1507,7 +1507,7 @@ static int igt_reset_queue(void *arg)
 
 		i915_request_put(prev);
 
-		err = igt_flush_test(i915, I915_WAIT_LOCKED);
+		err = igt_flush_test(gt->i915, I915_WAIT_LOCKED);
 		if (err)
 			break;
 	}
@@ -1515,10 +1515,10 @@ static int igt_reset_queue(void *arg)
 fini:
 	hang_fini(&h);
 unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
-	igt_global_reset_unlock(i915);
+	mutex_unlock(&gt->i915->drm.struct_mutex);
+	igt_global_reset_unlock(gt);
 
-	if (i915_reset_failed(i915))
+	if (intel_gt_is_wedged(gt))
 		return -EIO;
 
 	return err;
@@ -1526,8 +1526,9 @@ static int igt_reset_queue(void *arg)
 
 static int igt_handle_error(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
-	struct intel_engine_cs *engine = i915->engine[RCS0];
+	struct intel_gt *gt = arg;
+	struct i915_gpu_error *global = &gt->i915->gpu_error;
+	struct intel_engine_cs *engine = gt->i915->engine[RCS0];
 	struct hang h;
 	struct i915_request *rq;
 	struct i915_gpu_state *error;
@@ -1535,15 +1536,15 @@ static int igt_handle_error(void *arg)
 
 	/* Check that we can issue a global GPU and engine reset */
 
-	if (!intel_has_reset_engine(i915))
+	if (!intel_has_reset_engine(gt->i915))
 		return 0;
 
 	if (!engine || !intel_engine_can_store_dword(engine))
 		return 0;
 
-	mutex_lock(&i915->drm.struct_mutex);
+	mutex_lock(&gt->i915->drm.struct_mutex);
 
-	err = hang_init(&h, i915);
+	err = hang_init(&h, gt);
 	if (err)
 		goto err_unlock;
 
@@ -1557,28 +1558,28 @@ static int igt_handle_error(void *arg)
 	i915_request_add(rq);
 
 	if (!wait_until_running(&h, rq)) {
-		struct drm_printer p = drm_info_printer(i915->drm.dev);
+		struct drm_printer p = drm_info_printer(gt->i915->drm.dev);
 
 		pr_err("%s: Failed to start request %llx, at %x\n",
 		       __func__, rq->fence.seqno, hws_seqno(&h, rq));
 		intel_engine_dump(rq->engine, &p, "%s\n", rq->engine->name);
 
-		i915_gem_set_wedged(i915);
+		intel_gt_set_wedged(gt);
 
 		err = -EIO;
 		goto err_request;
 	}
 
-	mutex_unlock(&i915->drm.struct_mutex);
+	mutex_unlock(&gt->i915->drm.struct_mutex);
 
 	/* Temporarily disable error capture */
-	error = xchg(&i915->gpu_error.first_error, (void *)-1);
+	error = xchg(&global->first_error, (void *)-1);
 
-	i915_handle_error(i915, engine->mask, 0, NULL);
+	intel_gt_handle_error(gt, engine->mask, 0, NULL);
 
-	xchg(&i915->gpu_error.first_error, error);
+	xchg(&global->first_error, error);
 
-	mutex_lock(&i915->drm.struct_mutex);
+	mutex_lock(&gt->i915->drm.struct_mutex);
 
 	if (rq->fence.error != -EIO) {
 		pr_err("Guilty request not identified!\n");
@@ -1591,7 +1592,7 @@ static int igt_handle_error(void *arg)
 err_fini:
 	hang_fini(&h);
 err_unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
+	mutex_unlock(&gt->i915->drm.struct_mutex);
 	return err;
 }
 
@@ -1608,7 +1609,7 @@ static int __igt_atomic_reset_engine(struct intel_engine_cs *engine,
 	tasklet_disable_nosync(t);
 	p->critical_section_begin();
 
-	err = i915_reset_engine(engine, NULL);
+	err = intel_engine_reset(engine, NULL);
 
 	p->critical_section_end();
 	tasklet_enable(t);
@@ -1623,7 +1624,6 @@ static int __igt_atomic_reset_engine(struct intel_engine_cs *engine,
 static int igt_atomic_reset_engine(struct intel_engine_cs *engine,
 				   const struct igt_atomic_section *p)
 {
-	struct drm_i915_private *i915 = engine->i915;
 	struct i915_request *rq;
 	struct hang h;
 	int err;
@@ -1632,7 +1632,7 @@ static int igt_atomic_reset_engine(struct intel_engine_cs *engine,
 	if (err)
 		return err;
 
-	err = hang_init(&h, i915);
+	err = hang_init(&h, engine->gt);
 	if (err)
 		return err;
 
@@ -1651,16 +1651,16 @@ static int igt_atomic_reset_engine(struct intel_engine_cs *engine,
 		pr_err("%s(%s): Failed to start request %llx, at %x\n",
 		       __func__, engine->name,
 		       rq->fence.seqno, hws_seqno(&h, rq));
-		i915_gem_set_wedged(i915);
+		intel_gt_set_wedged(engine->gt);
 		err = -EIO;
 	}
 
 	if (err == 0) {
-		struct igt_wedge_me w;
+		struct intel_wedge_me w;
 
-		igt_wedge_on_timeout(&w, i915, HZ / 20 /* 50ms timeout*/)
+		intel_wedge_on_timeout(&w, engine->gt, HZ / 20 /* 50ms */)
 			i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT);
-		if (i915_reset_failed(i915))
+		if (intel_gt_is_wedged(engine->gt))
 			err = -EIO;
 	}
 
@@ -1672,30 +1672,30 @@ static int igt_atomic_reset_engine(struct intel_engine_cs *engine,
 
 static int igt_reset_engines_atomic(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	const typeof(*igt_atomic_phases) *p;
 	int err = 0;
 
 	/* Check that the engines resets are usable from atomic context */
 
-	if (!intel_has_reset_engine(i915))
+	if (!intel_has_reset_engine(gt->i915))
 		return 0;
 
-	if (USES_GUC_SUBMISSION(i915))
+	if (USES_GUC_SUBMISSION(gt->i915))
 		return 0;
 
-	igt_global_reset_lock(i915);
-	mutex_lock(&i915->drm.struct_mutex);
+	igt_global_reset_lock(gt);
+	mutex_lock(&gt->i915->drm.struct_mutex);
 
 	/* Flush any requests before we get started and check basics */
-	if (!igt_force_reset(i915))
+	if (!igt_force_reset(gt))
 		goto unlock;
 
 	for (p = igt_atomic_phases; p->name; p++) {
 		struct intel_engine_cs *engine;
 		enum intel_engine_id id;
 
-		for_each_engine(engine, i915, id) {
+		for_each_engine(engine, gt->i915, id) {
 			err = igt_atomic_reset_engine(engine, p);
 			if (err)
 				goto out;
@@ -1704,11 +1704,11 @@ static int igt_reset_engines_atomic(void *arg)
 
 out:
 	/* As we poke around the guts, do a full reset before continuing. */
-	igt_force_reset(i915);
+	igt_force_reset(gt);
 
 unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
-	igt_global_reset_unlock(i915);
+	mutex_unlock(&gt->i915->drm.struct_mutex);
+	igt_global_reset_unlock(gt);
 
 	return err;
 }
@@ -1730,28 +1730,29 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_reset_evict_fence),
 		SUBTEST(igt_handle_error),
 	};
+	struct intel_gt *gt = &i915->gt;
 	intel_wakeref_t wakeref;
 	bool saved_hangcheck;
 	int err;
 
-	if (!intel_has_gpu_reset(i915))
+	if (!intel_has_gpu_reset(gt->i915))
 		return 0;
 
-	if (i915_terminally_wedged(i915))
+	if (intel_gt_is_wedged(gt))
 		return -EIO; /* we're long past hope of a successful reset */
 
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
+	wakeref = intel_runtime_pm_get(&gt->i915->runtime_pm);
 	saved_hangcheck = fetch_and_zero(&i915_modparams.enable_hangcheck);
-	drain_delayed_work(&i915->gpu_error.hangcheck_work); /* flush param */
+	drain_delayed_work(&gt->hangcheck.work); /* flush param */
 
-	err = i915_live_subtests(tests, i915);
+	err = intel_gt_live_subtests(tests, gt);
 
-	mutex_lock(&i915->drm.struct_mutex);
-	igt_flush_test(i915, I915_WAIT_LOCKED);
-	mutex_unlock(&i915->drm.struct_mutex);
+	mutex_lock(&gt->i915->drm.struct_mutex);
+	igt_flush_test(gt->i915, I915_WAIT_LOCKED);
+	mutex_unlock(&gt->i915->drm.struct_mutex);
 
 	i915_modparams.enable_hangcheck = saved_hangcheck;
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
+	intel_runtime_pm_put(&gt->i915->runtime_pm, wakeref);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index b9b881ab8e7c..678e9b2edf8d 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -55,7 +55,7 @@ static int live_sanitycheck(void *arg)
 		if (!igt_wait_for_spinner(&spin, rq)) {
 			GEM_TRACE("spinner failed to start\n");
 			GEM_TRACE_DUMP();
-			i915_gem_set_wedged(i915);
+			intel_gt_set_wedged(&i915->gt);
 			err = -EIO;
 			goto err_ctx;
 		}
@@ -211,7 +211,7 @@ slice_semaphore_queue(struct intel_engine_cs *outer,
 		pr_err("Failed to slice along semaphore chain of length (%d, %d)!\n",
 		       count, n);
 		GEM_TRACE_DUMP();
-		i915_gem_set_wedged(outer->i915);
+		intel_gt_set_wedged(outer->gt);
 		err = -EIO;
 	}
 
@@ -445,7 +445,7 @@ static int live_busywait_preempt(void *arg)
 			intel_engine_dump(engine, &p, "%s\n", engine->name);
 			GEM_TRACE_DUMP();
 
-			i915_gem_set_wedged(i915);
+			intel_gt_set_wedged(&i915->gt);
 			err = -EIO;
 			goto err_vma;
 		}
@@ -534,7 +534,7 @@ static int live_preempt(void *arg)
 		if (!igt_wait_for_spinner(&spin_lo, rq)) {
 			GEM_TRACE("lo spinner failed to start\n");
 			GEM_TRACE_DUMP();
-			i915_gem_set_wedged(i915);
+			intel_gt_set_wedged(&i915->gt);
 			err = -EIO;
 			goto err_ctx_lo;
 		}
@@ -551,7 +551,7 @@ static int live_preempt(void *arg)
 		if (!igt_wait_for_spinner(&spin_hi, rq)) {
 			GEM_TRACE("hi spinner failed to start\n");
 			GEM_TRACE_DUMP();
-			i915_gem_set_wedged(i915);
+			intel_gt_set_wedged(&i915->gt);
 			err = -EIO;
 			goto err_ctx_lo;
 		}
@@ -688,7 +688,7 @@ static int live_late_preempt(void *arg)
 err_wedged:
 	igt_spinner_end(&spin_hi);
 	igt_spinner_end(&spin_lo);
-	i915_gem_set_wedged(i915);
+	intel_gt_set_wedged(&i915->gt);
 	err = -EIO;
 	goto err_ctx_lo;
 }
@@ -824,7 +824,7 @@ static int live_nopreempt(void *arg)
 err_wedged:
 	igt_spinner_end(&b.spin);
 	igt_spinner_end(&a.spin);
-	i915_gem_set_wedged(i915);
+	intel_gt_set_wedged(&i915->gt);
 	err = -EIO;
 	goto err_client_b;
 }
@@ -934,7 +934,7 @@ static int live_suppress_self_preempt(void *arg)
 err_wedged:
 	igt_spinner_end(&b.spin);
 	igt_spinner_end(&a.spin);
-	i915_gem_set_wedged(i915);
+	intel_gt_set_wedged(&i915->gt);
 	err = -EIO;
 	goto err_client_b;
 }
@@ -1105,7 +1105,7 @@ static int live_suppress_wait_preempt(void *arg)
 err_wedged:
 	for (i = 0; i < ARRAY_SIZE(client); i++)
 		igt_spinner_end(&client[i].spin);
-	i915_gem_set_wedged(i915);
+	intel_gt_set_wedged(&i915->gt);
 	err = -EIO;
 	goto err_client_3;
 }
@@ -1251,7 +1251,7 @@ static int live_chain_preempt(void *arg)
 err_wedged:
 	igt_spinner_end(&hi.spin);
 	igt_spinner_end(&lo.spin);
-	i915_gem_set_wedged(i915);
+	intel_gt_set_wedged(&i915->gt);
 	err = -EIO;
 	goto err_client_lo;
 }
@@ -1310,7 +1310,7 @@ static int live_preempt_hang(void *arg)
 		if (!igt_wait_for_spinner(&spin_lo, rq)) {
 			GEM_TRACE("lo spinner failed to start\n");
 			GEM_TRACE_DUMP();
-			i915_gem_set_wedged(i915);
+			intel_gt_set_wedged(&i915->gt);
 			err = -EIO;
 			goto err_ctx_lo;
 		}
@@ -1332,21 +1332,21 @@ static int live_preempt_hang(void *arg)
 						 HZ / 10)) {
 			pr_err("Preemption did not occur within timeout!");
 			GEM_TRACE_DUMP();
-			i915_gem_set_wedged(i915);
+			intel_gt_set_wedged(&i915->gt);
 			err = -EIO;
 			goto err_ctx_lo;
 		}
 
-		set_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
-		i915_reset_engine(engine, NULL);
-		clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+		set_bit(I915_RESET_ENGINE + id, &i915->gt.reset.flags);
+		intel_engine_reset(engine, NULL);
+		clear_bit(I915_RESET_ENGINE + id, &i915->gt.reset.flags);
 
 		engine->execlists.preempt_hang.inject_hang = false;
 
 		if (!igt_wait_for_spinner(&spin_hi, rq)) {
 			GEM_TRACE("hi spinner failed to start\n");
 			GEM_TRACE_DUMP();
-			i915_gem_set_wedged(i915);
+			intel_gt_set_wedged(&i915->gt);
 			err = -EIO;
 			goto err_ctx_lo;
 		}
@@ -1726,7 +1726,7 @@ static int nop_virtual_engine(struct drm_i915_private *i915,
 					  request[nc]->fence.context,
 					  request[nc]->fence.seqno);
 				GEM_TRACE_DUMP();
-				i915_gem_set_wedged(i915);
+				intel_gt_set_wedged(&i915->gt);
 				break;
 			}
 		}
@@ -1873,7 +1873,7 @@ static int mask_virtual_engine(struct drm_i915_private *i915,
 				  request[n]->fence.context,
 				  request[n]->fence.seqno);
 			GEM_TRACE_DUMP();
-			i915_gem_set_wedged(i915);
+			intel_gt_set_wedged(&i915->gt);
 			err = -EIO;
 			goto out;
 		}
@@ -2150,7 +2150,7 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
 	if (!HAS_EXECLISTS(i915))
 		return 0;
 
-	if (i915_terminally_wedged(i915))
+	if (intel_gt_is_wedged(&i915->gt))
 		return 0;
 
 	return i915_live_subtests(tests, i915);
diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c
index 672e32e1ef95..813a9176c436 100644
--- a/drivers/gpu/drm/i915/gt/selftest_reset.c
+++ b/drivers/gpu/drm/i915/gt/selftest_reset.c
@@ -9,26 +9,29 @@
 
 static int igt_global_reset(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	unsigned int reset_count;
+	intel_wakeref_t wakeref;
 	int err = 0;
 
 	/* Check that we can issue a global GPU reset */
 
-	igt_global_reset_lock(i915);
+	igt_global_reset_lock(gt);
+	wakeref = intel_runtime_pm_get(&gt->i915->runtime_pm);
 
-	reset_count = i915_reset_count(&i915->gpu_error);
+	reset_count = i915_reset_count(&gt->i915->gpu_error);
 
-	i915_reset(i915, ALL_ENGINES, NULL);
+	intel_gt_reset(gt, ALL_ENGINES, NULL);
 
-	if (i915_reset_count(&i915->gpu_error) == reset_count) {
+	if (i915_reset_count(&gt->i915->gpu_error) == reset_count) {
 		pr_err("No GPU reset recorded!\n");
 		err = -EINVAL;
 	}
 
-	igt_global_reset_unlock(i915);
+	intel_runtime_pm_put(&gt->i915->runtime_pm, wakeref);
+	igt_global_reset_unlock(gt);
 
-	if (i915_reset_failed(i915))
+	if (intel_gt_is_wedged(gt))
 		err = -EIO;
 
 	return err;
@@ -36,38 +39,38 @@ static int igt_global_reset(void *arg)
 
 static int igt_wedged_reset(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	intel_wakeref_t wakeref;
 
 	/* Check that we can recover a wedged device with a GPU reset */
 
-	igt_global_reset_lock(i915);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
+	igt_global_reset_lock(gt);
+	wakeref = intel_runtime_pm_get(&gt->i915->runtime_pm);
 
-	i915_gem_set_wedged(i915);
+	intel_gt_set_wedged(gt);
 
-	GEM_BUG_ON(!i915_reset_failed(i915));
-	i915_reset(i915, ALL_ENGINES, NULL);
+	GEM_BUG_ON(!intel_gt_is_wedged(gt));
+	intel_gt_reset(gt, ALL_ENGINES, NULL);
 
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	igt_global_reset_unlock(i915);
+	intel_runtime_pm_put(&gt->i915->runtime_pm, wakeref);
+	igt_global_reset_unlock(gt);
 
-	return i915_reset_failed(i915) ? -EIO : 0;
+	return intel_gt_is_wedged(gt) ? -EIO : 0;
 }
 
 static int igt_atomic_reset(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	const typeof(*igt_atomic_phases) *p;
 	int err = 0;
 
 	/* Check that the resets are usable from atomic context */
 
-	intel_gt_pm_get(&i915->gt);
-	igt_global_reset_lock(i915);
+	intel_gt_pm_get(gt);
+	igt_global_reset_lock(gt);
 
 	/* Flush any requests before we get started and check basics */
-	if (!igt_force_reset(i915))
+	if (!igt_force_reset(gt))
 		goto unlock;
 
 	for (p = igt_atomic_phases; p->name; p++) {
@@ -75,13 +78,13 @@ static int igt_atomic_reset(void *arg)
 
 		GEM_TRACE("intel_gpu_reset under %s\n", p->name);
 
-		awake = reset_prepare(i915);
+		awake = reset_prepare(gt);
 		p->critical_section_begin();
 
-		err = intel_gpu_reset(i915, ALL_ENGINES);
+		err = intel_gpu_reset(gt, ALL_ENGINES);
 
 		p->critical_section_end();
-		reset_finish(i915, awake);
+		reset_finish(gt, awake);
 
 		if (err) {
 			pr_err("intel_gpu_reset failed under %s\n", p->name);
@@ -90,18 +93,18 @@ static int igt_atomic_reset(void *arg)
 	}
 
 	/* As we poke around the guts, do a full reset before continuing. */
-	igt_force_reset(i915);
+	igt_force_reset(gt);
 
 unlock:
-	igt_global_reset_unlock(i915);
-	intel_gt_pm_put(&i915->gt);
+	igt_global_reset_unlock(gt);
+	intel_gt_pm_put(gt);
 
 	return err;
 }
 
 static int igt_atomic_engine_reset(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	const typeof(*igt_atomic_phases) *p;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -109,33 +112,33 @@ static int igt_atomic_engine_reset(void *arg)
 
 	/* Check that the resets are usable from atomic context */
 
-	if (!intel_has_reset_engine(i915))
+	if (!intel_has_reset_engine(gt->i915))
 		return 0;
 
-	if (USES_GUC_SUBMISSION(i915))
+	if (USES_GUC_SUBMISSION(gt->i915))
 		return 0;
 
-	intel_gt_pm_get(&i915->gt);
-	igt_global_reset_lock(i915);
+	intel_gt_pm_get(gt);
+	igt_global_reset_lock(gt);
 
 	/* Flush any requests before we get started and check basics */
-	if (!igt_force_reset(i915))
+	if (!igt_force_reset(gt))
 		goto out_unlock;
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		tasklet_disable_nosync(&engine->execlists.tasklet);
 		intel_engine_pm_get(engine);
 
 		for (p = igt_atomic_phases; p->name; p++) {
-			GEM_TRACE("i915_reset_engine(%s) under %s\n",
+			GEM_TRACE("intel_engine_reset(%s) under %s\n",
 				  engine->name, p->name);
 
 			p->critical_section_begin();
-			err = i915_reset_engine(engine, NULL);
+			err = intel_engine_reset(engine, NULL);
 			p->critical_section_end();
 
 			if (err) {
-				pr_err("i915_reset_engine(%s) failed under %s\n",
+				pr_err("intel_engine_reset(%s) failed under %s\n",
 				       engine->name, p->name);
 				break;
 			}
@@ -148,11 +151,11 @@ static int igt_atomic_engine_reset(void *arg)
 	}
 
 	/* As we poke around the guts, do a full reset before continuing. */
-	igt_force_reset(i915);
+	igt_force_reset(gt);
 
 out_unlock:
-	igt_global_reset_unlock(i915);
-	intel_gt_pm_put(&i915->gt);
+	igt_global_reset_unlock(gt);
+	intel_gt_pm_put(gt);
 
 	return err;
 }
@@ -165,17 +168,13 @@ int intel_reset_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_atomic_reset),
 		SUBTEST(igt_atomic_engine_reset),
 	};
-	intel_wakeref_t wakeref;
-	int err = 0;
+	struct intel_gt *gt = &i915->gt;
 
-	if (!intel_has_gpu_reset(i915))
+	if (!intel_has_gpu_reset(gt->i915))
 		return 0;
 
-	if (i915_terminally_wedged(i915))
+	if (intel_gt_is_wedged(gt))
 		return -EIO; /* we're long past hope of a successful reset */
 
-	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
-		err = i915_subtests(tests, i915);
-
-	return err;
+	return intel_gt_live_subtests(tests, gt);
 }
diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index 4d72cef506ae..321481403165 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -7,6 +7,7 @@
 #include <linux/prime_numbers.h>
 
 #include "gem/i915_gem_pm.h"
+#include "intel_gt.h"
 
 #include "../selftests/i915_random.h"
 #include "../i915_selftest.h"
@@ -838,7 +839,7 @@ int intel_timeline_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_hwsp_wrap),
 	};
 
-	if (i915_terminally_wedged(i915))
+	if (intel_gt_is_wedged(&i915->gt))
 		return 0;
 
 	return i915_live_subtests(tests, i915);
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index fa01ea7855de..2978f435dcca 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -12,7 +12,6 @@
 #include "selftests/igt_flush_test.h"
 #include "selftests/igt_reset.h"
 #include "selftests/igt_spinner.h"
-#include "selftests/igt_wedge_me.h"
 #include "selftests/mock_drm.h"
 
 #include "gem/selftests/igt_gem_utils.h"
@@ -185,7 +184,7 @@ static int check_whitelist(struct i915_gem_context *ctx,
 			   struct intel_engine_cs *engine)
 {
 	struct drm_i915_gem_object *results;
-	struct igt_wedge_me wedge;
+	struct intel_wedge_me wedge;
 	u32 *vaddr;
 	int err;
 	int i;
@@ -196,10 +195,10 @@ static int check_whitelist(struct i915_gem_context *ctx,
 
 	err = 0;
 	i915_gem_object_lock(results);
-	igt_wedge_on_timeout(&wedge, ctx->i915, HZ / 5) /* a safety net! */
+	intel_wedge_on_timeout(&wedge, &ctx->i915->gt, HZ / 5) /* safety net! */
 		err = i915_gem_object_set_to_cpu_domain(results, false);
 	i915_gem_object_unlock(results);
-	if (i915_terminally_wedged(ctx->i915))
+	if (intel_gt_is_wedged(&ctx->i915->gt))
 		err = -EIO;
 	if (err)
 		goto out_put;
@@ -232,13 +231,13 @@ static int check_whitelist(struct i915_gem_context *ctx,
 
 static int do_device_reset(struct intel_engine_cs *engine)
 {
-	i915_reset(engine->i915, engine->mask, "live_workarounds");
+	intel_gt_reset(engine->gt, engine->mask, "live_workarounds");
 	return 0;
 }
 
 static int do_engine_reset(struct intel_engine_cs *engine)
 {
-	return i915_reset_engine(engine, "live_workarounds");
+	return intel_engine_reset(engine, "live_workarounds");
 }
 
 static int
@@ -574,7 +573,7 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx,
 		if (i915_request_wait(rq, 0, HZ / 5) < 0) {
 			pr_err("%s: Futzing %x timedout; cancelling test\n",
 			       engine->name, reg);
-			i915_gem_set_wedged(ctx->i915);
+			intel_gt_set_wedged(&ctx->i915->gt);
 			err = -EIO;
 			goto out_batch;
 		}
@@ -711,7 +710,7 @@ static int live_reset_whitelist(void *arg)
 	if (!engine || engine->whitelist.count == 0)
 		return 0;
 
-	igt_global_reset_lock(i915);
+	igt_global_reset_lock(&i915->gt);
 
 	if (intel_has_reset_engine(i915)) {
 		err = check_whitelist_across_reset(engine,
@@ -730,7 +729,7 @@ static int live_reset_whitelist(void *arg)
 	}
 
 out:
-	igt_global_reset_unlock(i915);
+	igt_global_reset_unlock(&i915->gt);
 	return err;
 }
 
@@ -1098,7 +1097,7 @@ live_gpu_reset_workarounds(void *arg)
 
 	pr_info("Verifying after GPU reset...\n");
 
-	igt_global_reset_lock(i915);
+	igt_global_reset_lock(&i915->gt);
 	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 
 	reference_lists_init(i915, &lists);
@@ -1107,7 +1106,7 @@ live_gpu_reset_workarounds(void *arg)
 	if (!ok)
 		goto out;
 
-	i915_reset(i915, ALL_ENGINES, "live_workarounds");
+	intel_gt_reset(&i915->gt, ALL_ENGINES, "live_workarounds");
 
 	ok = verify_wa_lists(ctx, &lists, "after reset");
 
@@ -1115,7 +1114,7 @@ live_gpu_reset_workarounds(void *arg)
 	kernel_context_close(ctx);
 	reference_lists_fini(i915, &lists);
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	igt_global_reset_unlock(i915);
+	igt_global_reset_unlock(&i915->gt);
 
 	return ok ? 0 : -ESRCH;
 }
@@ -1140,7 +1139,7 @@ live_engine_reset_workarounds(void *arg)
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
-	igt_global_reset_lock(i915);
+	igt_global_reset_lock(&i915->gt);
 	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 
 	reference_lists_init(i915, &lists);
@@ -1156,7 +1155,7 @@ live_engine_reset_workarounds(void *arg)
 			goto err;
 		}
 
-		i915_reset_engine(engine, "live_workarounds");
+		intel_engine_reset(engine, "live_workarounds");
 
 		ok = verify_wa_lists(ctx, &lists, "after idle reset");
 		if (!ok) {
@@ -1184,7 +1183,7 @@ live_engine_reset_workarounds(void *arg)
 			goto err;
 		}
 
-		i915_reset_engine(engine, "live_workarounds");
+		intel_engine_reset(engine, "live_workarounds");
 
 		igt_spinner_end(&spin);
 		igt_spinner_fini(&spin);
@@ -1199,7 +1198,7 @@ live_engine_reset_workarounds(void *arg)
 err:
 	reference_lists_fini(i915, &lists);
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	igt_global_reset_unlock(i915);
+	igt_global_reset_unlock(&i915->gt);
 	kernel_context_close(ctx);
 
 	igt_flush_test(i915, I915_WAIT_LOCKED);
@@ -1218,7 +1217,7 @@ int intel_workarounds_live_selftests(struct drm_i915_private *i915)
 	};
 	int err;
 
-	if (i915_terminally_wedged(i915))
+	if (intel_gt_is_wedged(&i915->gt))
 		return 0;
 
 	mutex_lock(&i915->drm.struct_mutex);
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index bc5af2d2909a..3405d8cab2e4 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1000,15 +1000,16 @@ static void i915_instdone_info(struct drm_i915_private *dev_priv,
 
 static int i915_hangcheck_info(struct seq_file *m, void *unused)
 {
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
+	struct drm_i915_private *i915 = node_to_i915(m->private);
+	struct intel_gt *gt = &i915->gt;
 	struct intel_engine_cs *engine;
 	intel_wakeref_t wakeref;
 	enum intel_engine_id id;
 
-	seq_printf(m, "Reset flags: %lx\n", dev_priv->gpu_error.flags);
-	if (test_bit(I915_WEDGED, &dev_priv->gpu_error.flags))
+	seq_printf(m, "Reset flags: %lx\n", gt->reset.flags);
+	if (test_bit(I915_WEDGED, &gt->reset.flags))
 		seq_puts(m, "\tWedged\n");
-	if (test_bit(I915_RESET_BACKOFF, &dev_priv->gpu_error.flags))
+	if (test_bit(I915_RESET_BACKOFF, &gt->reset.flags))
 		seq_puts(m, "\tDevice (global) reset in progress\n");
 
 	if (!i915_modparams.enable_hangcheck) {
@@ -1016,19 +1017,19 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 		return 0;
 	}
 
-	if (timer_pending(&dev_priv->gpu_error.hangcheck_work.timer))
+	if (timer_pending(&gt->hangcheck.work.timer))
 		seq_printf(m, "Hangcheck active, timer fires in %dms\n",
-			   jiffies_to_msecs(dev_priv->gpu_error.hangcheck_work.timer.expires -
+			   jiffies_to_msecs(gt->hangcheck.work.timer.expires -
 					    jiffies));
-	else if (delayed_work_pending(&dev_priv->gpu_error.hangcheck_work))
+	else if (delayed_work_pending(&gt->hangcheck.work))
 		seq_puts(m, "Hangcheck active, work pending\n");
 	else
 		seq_puts(m, "Hangcheck inactive\n");
 
-	seq_printf(m, "GT active? %s\n", yesno(dev_priv->gt.awake));
+	seq_printf(m, "GT active? %s\n", yesno(gt->awake));
 
-	with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref) {
-		for_each_engine(engine, dev_priv, id) {
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
+		for_each_engine(engine, i915, id) {
 			struct intel_instdone instdone;
 
 			seq_printf(m, "%s: %d ms ago\n",
@@ -1043,10 +1044,10 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 			intel_engine_get_instdone(engine, &instdone);
 
 			seq_puts(m, "\tinstdone read =\n");
-			i915_instdone_info(dev_priv, m, &instdone);
+			i915_instdone_info(i915, m, &instdone);
 
 			seq_puts(m, "\tinstdone accu =\n");
-			i915_instdone_info(dev_priv, m,
+			i915_instdone_info(i915, m,
 					   &engine->hangcheck.instdone);
 		}
 	}
@@ -1054,23 +1055,6 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 	return 0;
 }
 
-static int i915_reset_info(struct seq_file *m, void *unused)
-{
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct i915_gpu_error *error = &dev_priv->gpu_error;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-
-	seq_printf(m, "full gpu reset = %u\n", i915_reset_count(error));
-
-	for_each_engine(engine, dev_priv, id) {
-		seq_printf(m, "%s = %u\n", engine->name,
-			   i915_reset_engine_count(error, engine));
-	}
-
-	return 0;
-}
-
 static int ironlake_drpc_info(struct seq_file *m)
 {
 	struct drm_i915_private *i915 = node_to_i915(m->private);
@@ -3547,7 +3531,8 @@ static const struct file_operations i915_cur_wm_latency_fops = {
 static int
 i915_wedged_get(void *data, u64 *val)
 {
-	int ret = i915_terminally_wedged(data);
+	struct drm_i915_private *i915 = data;
+	int ret = intel_gt_terminally_wedged(&i915->gt);
 
 	switch (ret) {
 	case -EIO:
@@ -3567,11 +3552,11 @@ i915_wedged_set(void *data, u64 val)
 	struct drm_i915_private *i915 = data;
 
 	/* Flush any previous reset before applying for a new one */
-	wait_event(i915->gpu_error.reset_queue,
-		   !test_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags));
+	wait_event(i915->gt.reset.queue,
+		   !test_bit(I915_RESET_BACKOFF, &i915->gt.reset.flags));
 
-	i915_handle_error(i915, val, I915_ERROR_CAPTURE,
-			  "Manually set wedged engine mask = %llx", val);
+	intel_gt_handle_error(&i915->gt, val, I915_ERROR_CAPTURE,
+			      "Manually set wedged engine mask = %llx", val);
 	return 0;
 }
 
@@ -3614,8 +3599,9 @@ i915_drop_caches_set(void *data, u64 val)
 		  val, val & DROP_ALL);
 
 	if (val & DROP_RESET_ACTIVE &&
-	    wait_for(intel_engines_are_idle(i915), I915_IDLE_ENGINES_TIMEOUT))
-		i915_gem_set_wedged(i915);
+	    wait_for(intel_engines_are_idle(&i915->gt),
+		     I915_IDLE_ENGINES_TIMEOUT))
+		intel_gt_set_wedged(&i915->gt);
 
 	/* No need to check and wait for gpu resets, only libdrm auto-restarts
 	 * on ioctls on -EAGAIN. */
@@ -3650,8 +3636,8 @@ i915_drop_caches_set(void *data, u64 val)
 		mutex_unlock(&i915->drm.struct_mutex);
 	}
 
-	if (val & DROP_RESET_ACTIVE && i915_terminally_wedged(i915))
-		i915_handle_error(i915, ALL_ENGINES, 0, NULL);
+	if (val & DROP_RESET_ACTIVE && intel_gt_terminally_wedged(&i915->gt))
+		intel_gt_handle_error(&i915->gt, ALL_ENGINES, 0, NULL);
 
 	fs_reclaim_acquire(GFP_KERNEL);
 	if (val & DROP_BOUND)
@@ -4305,7 +4291,6 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_huc_load_status", i915_huc_load_status_info, 0},
 	{"i915_frequency_info", i915_frequency_info, 0},
 	{"i915_hangcheck_info", i915_hangcheck_info, 0},
-	{"i915_reset_info", i915_reset_info, 0},
 	{"i915_drpc_info", i915_drpc_info, 0},
 	{"i915_emon_status", i915_emon_status, 0},
 	{"i915_ring_freq_table", i915_ring_freq_table, 0},
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 794c6814a6d0..4b9860986a93 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -941,7 +941,6 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv)
 	if (ret < 0)
 		goto err_uc;
 	intel_irq_init(dev_priv);
-	intel_hangcheck_init(dev_priv);
 	intel_init_display_hooks(dev_priv);
 	intel_init_clock_gating_hooks(dev_priv);
 	intel_init_audio_hooks(dev_priv);
@@ -1960,7 +1959,7 @@ void i915_driver_unload(struct drm_device *dev)
 	 * all in-flight requests so that we can quickly unbind the active
 	 * resources.
 	 */
-	i915_gem_set_wedged(dev_priv);
+	intel_gt_set_wedged(&dev_priv->gt);
 
 	/* Flush any external code that still may be under the RCU lock */
 	synchronize_rcu();
@@ -1981,7 +1980,7 @@ void i915_driver_unload(struct drm_device *dev)
 	intel_csr_ucode_fini(dev_priv);
 
 	/* Free error state after interrupts are fully disabled. */
-	cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work);
+	cancel_delayed_work_sync(&dev_priv->gt.hangcheck.work);
 	i915_reset_error_state(dev_priv);
 
 	i915_gem_fini_hw(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 64d8de4d7716..1352293a368f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2400,28 +2400,10 @@ extern int i915_driver_load(struct pci_dev *pdev,
 extern void i915_driver_unload(struct drm_device *dev);
 
 extern void intel_engine_init_hangcheck(struct intel_engine_cs *engine);
-extern void intel_hangcheck_init(struct drm_i915_private *dev_priv);
 int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool on);
 
 u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv);
 
-static inline void i915_queue_hangcheck(struct drm_i915_private *dev_priv)
-{
-	unsigned long delay;
-
-	if (unlikely(!i915_modparams.enable_hangcheck))
-		return;
-
-	/* Don't continually defer the hangcheck so that it is always run at
-	 * least once after work has been scheduled on any ring. Otherwise,
-	 * we will ignore a hung ring if a second ring is kept busy.
-	 */
-
-	delay = round_jiffies_up_relative(DRM_I915_HANGCHECK_JIFFIES);
-	queue_delayed_work(system_long_wq,
-			   &dev_priv->gpu_error.hangcheck_work, delay);
-}
-
 static inline bool intel_gvt_active(struct drm_i915_private *dev_priv)
 {
 	return dev_priv->gvt;
@@ -2506,30 +2488,17 @@ int i915_gem_mmap_gtt_version(void);
 
 int __must_check i915_gem_set_global_seqno(struct drm_device *dev, u32 seqno);
 
-static inline bool __i915_wedged(struct i915_gpu_error *error)
-{
-	return unlikely(test_bit(I915_WEDGED, &error->flags));
-}
-
-static inline bool i915_reset_failed(struct drm_i915_private *i915)
-{
-	return __i915_wedged(&i915->gpu_error);
-}
-
 static inline u32 i915_reset_count(struct i915_gpu_error *error)
 {
-	return READ_ONCE(error->reset_count);
+	return atomic_read(&error->reset_count);
 }
 
 static inline u32 i915_reset_engine_count(struct i915_gpu_error *error,
 					  struct intel_engine_cs *engine)
 {
-	return READ_ONCE(error->reset_engine_count[engine->id]);
+	return atomic_read(&error->reset_engine_count[engine->uabi_class]);
 }
 
-void i915_gem_set_wedged(struct drm_i915_private *dev_priv);
-bool i915_gem_unset_wedged(struct drm_i915_private *dev_priv);
-
 void i915_gem_init_mmio(struct drm_i915_private *i915);
 int __must_check i915_gem_init(struct drm_i915_private *dev_priv);
 int __must_check i915_gem_init_hw(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index c42f2146675c..9c359d437bf5 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -896,13 +896,13 @@ void i915_gem_runtime_suspend(struct drm_i915_private *i915)
 	}
 }
 
-static int wait_for_engines(struct drm_i915_private *i915)
+static int wait_for_engines(struct intel_gt *gt)
 {
-	if (wait_for(intel_engines_are_idle(i915), I915_IDLE_ENGINES_TIMEOUT)) {
-		dev_err(i915->drm.dev,
+	if (wait_for(intel_engines_are_idle(gt), I915_IDLE_ENGINES_TIMEOUT)) {
+		dev_err(gt->i915->drm.dev,
 			"Failed to idle engines, declaring wedged!\n");
 		GEM_TRACE_DUMP();
-		i915_gem_set_wedged(i915);
+		intel_gt_set_wedged(gt);
 		return -EIO;
 	}
 
@@ -973,7 +973,7 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915,
 
 		lockdep_assert_held(&i915->drm.struct_mutex);
 
-		err = wait_for_engines(i915);
+		err = wait_for_engines(&i915->gt);
 		if (err)
 			return err;
 
@@ -1151,8 +1151,8 @@ void i915_gem_sanitize(struct drm_i915_private *i915)
 	 * back to defaults, recovering from whatever wedged state we left it
 	 * in and so worth trying to use the device once more.
 	 */
-	if (i915_terminally_wedged(i915))
-		i915_gem_unset_wedged(i915);
+	if (intel_gt_is_wedged(&i915->gt))
+		intel_gt_unset_wedged(&i915->gt);
 
 	/*
 	 * If we inherit context state from the BIOS or earlier occupants
@@ -1204,7 +1204,7 @@ int i915_gem_init_hw(struct drm_i915_private *i915)
 	int ret;
 
 	BUG_ON(!i915->kernel_context);
-	ret = i915_terminally_wedged(i915);
+	ret = intel_gt_terminally_wedged(gt);
 	if (ret)
 		return ret;
 
@@ -1386,7 +1386,7 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 	 * and ready to be torn-down. The quickest way we can accomplish
 	 * this is by declaring ourselves wedged.
 	 */
-	i915_gem_set_wedged(i915);
+	intel_gt_set_wedged(&i915->gt);
 	goto out_ctx;
 }
 
@@ -1541,7 +1541,7 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 err_gt:
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
-	i915_gem_set_wedged(dev_priv);
+	intel_gt_set_wedged(&dev_priv->gt);
 	i915_gem_suspend(dev_priv);
 	i915_gem_suspend_late(dev_priv);
 
@@ -1583,10 +1583,10 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 		 * wedged. But we only want to do this where the GPU is angry,
 		 * for all other failure, such as an allocation failure, bail.
 		 */
-		if (!i915_reset_failed(dev_priv)) {
+		if (!intel_gt_is_wedged(&dev_priv->gt)) {
 			i915_load_error(dev_priv,
 					"Failed to initialize GPU, declaring it wedged!\n");
-			i915_gem_set_wedged(dev_priv);
+			intel_gt_set_wedged(&dev_priv->gt);
 		}
 
 		/* Minimal basic recovery for KMS */
@@ -1668,11 +1668,6 @@ int i915_gem_init_early(struct drm_i915_private *dev_priv)
 	i915_gem_init__mm(dev_priv);
 	i915_gem_init__pm(dev_priv);
 
-	init_waitqueue_head(&dev_priv->gpu_error.wait_queue);
-	init_waitqueue_head(&dev_priv->gpu_error.reset_queue);
-	mutex_init(&dev_priv->gpu_error.wedge_mutex);
-	init_srcu_struct(&dev_priv->gpu_error.reset_backoff_srcu);
-
 	atomic_set(&dev_priv->mm.bsd_engine_dispatch_index, 0);
 
 	spin_lock_init(&dev_priv->fb_tracking.lock);
@@ -1691,7 +1686,7 @@ void i915_gem_cleanup_early(struct drm_i915_private *dev_priv)
 	GEM_BUG_ON(atomic_read(&dev_priv->mm.free_count));
 	WARN_ON(dev_priv->mm.shrink_count);
 
-	cleanup_srcu_struct(&dev_priv->gpu_error.reset_backoff_srcu);
+	intel_gt_cleanup_early(&dev_priv->gt);
 
 	i915_gemfs_fini(dev_priv);
 }
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index ed719c8a5bd6..5cc9dfea1e9e 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -7,6 +7,7 @@
 #ifndef _I915_GPU_ERROR_H_
 #define _I915_GPU_ERROR_H_
 
+#include <linux/atomic.h>
 #include <linux/kref.h>
 #include <linux/ktime.h>
 #include <linux/sched.h>
@@ -163,12 +164,6 @@ struct i915_gpu_state {
 };
 
 struct i915_gpu_error {
-	/* For hangcheck timer */
-#define DRM_I915_HANGCHECK_PERIOD 1500 /* in ms */
-#define DRM_I915_HANGCHECK_JIFFIES msecs_to_jiffies(DRM_I915_HANGCHECK_PERIOD)
-
-	struct delayed_work hangcheck_work;
-
 	/* For reset and error_state handling. */
 	spinlock_t lock;
 	/* Protected by the above dev->gpu_error.lock. */
@@ -176,52 +171,11 @@ struct i915_gpu_error {
 
 	atomic_t pending_fb_pin;
 
-	/**
-	 * flags: Control various stages of the GPU reset
-	 *
-	 * #I915_RESET_BACKOFF - When we start a global reset, we need to
-	 * serialise with any other users attempting to do the same, and
-	 * any global resources that may be clobber by the reset (such as
-	 * FENCE registers).
-	 *
-	 * #I915_RESET_ENGINE[num_engines] - Since the driver doesn't need to
-	 * acquire the struct_mutex to reset an engine, we need an explicit
-	 * flag to prevent two concurrent reset attempts in the same engine.
-	 * As the number of engines continues to grow, allocate the flags from
-	 * the most significant bits.
-	 *
-	 * #I915_WEDGED - If reset fails and we can no longer use the GPU,
-	 * we set the #I915_WEDGED bit. Prior to command submission, e.g.
-	 * i915_request_alloc(), this bit is checked and the sequence
-	 * aborted (with -EIO reported to userspace) if set.
-	 */
-	unsigned long flags;
-#define I915_RESET_BACKOFF	0
-#define I915_RESET_MODESET	1
-#define I915_RESET_ENGINE	2
-#define I915_WEDGED		(BITS_PER_LONG - 1)
-
 	/** Number of times the device has been reset (global) */
-	u32 reset_count;
+	atomic_t reset_count;
 
 	/** Number of times an engine has been reset */
-	u32 reset_engine_count[I915_NUM_ENGINES];
-
-	struct mutex wedge_mutex; /* serialises wedging/unwedging */
-
-	/**
-	 * Waitqueue to signal when a hang is detected. Used to for waiters
-	 * to release the struct_mutex for the reset to procede.
-	 */
-	wait_queue_head_t wait_queue;
-
-	/**
-	 * Waitqueue to signal when the reset has completed. Used by clients
-	 * that wait for dev_priv->mm.wedged to settle.
-	 */
-	wait_queue_head_t reset_queue;
-
-	struct srcu_struct reset_backoff_srcu;
+	atomic_t reset_engine_count[I915_NUM_ENGINES];
 };
 
 struct drm_i915_error_state_buf {
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 18568738fa30..92313a59563c 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1369,8 +1369,7 @@ long i915_request_wait(struct i915_request *rq,
 	 * serialise wait/reset with an explicit lock, we do want
 	 * lockdep to detect potential dependency cycles.
 	 */
-	mutex_acquire(&rq->i915->gpu_error.wedge_mutex.dep_map,
-		      0, 0, _THIS_IP_);
+	mutex_acquire(&rq->engine->gt->reset.mutex.dep_map, 0, 0, _THIS_IP_);
 
 	/*
 	 * Optimistic spin before touching IRQs.
@@ -1448,7 +1447,7 @@ long i915_request_wait(struct i915_request *rq,
 	dma_fence_remove_callback(&rq->fence, &wait.cb);
 
 out:
-	mutex_release(&rq->i915->gpu_error.wedge_mutex.dep_map, 0, _THIS_IP_);
+	mutex_release(&rq->engine->gt->reset.mutex.dep_map, 0, _THIS_IP_);
 	trace_i915_request_wait_end(rq);
 	return timeout;
 }
diff --git a/drivers/gpu/drm/i915/i915_selftest.h b/drivers/gpu/drm/i915/i915_selftest.h
index d9b17b9e6993..acdf6eb9e262 100644
--- a/drivers/gpu/drm/i915/i915_selftest.h
+++ b/drivers/gpu/drm/i915/i915_selftest.h
@@ -72,6 +72,9 @@ int __i915_nop_teardown(int err, void *data);
 int __i915_live_setup(void *data);
 int __i915_live_teardown(int err, void *data);
 
+int __intel_gt_live_setup(void *data);
+int __intel_gt_live_teardown(int err, void *data);
+
 int __i915_subtests(const char *caller,
 		    int (*setup)(void *data),
 		    int (*teardown)(int err, void *data),
@@ -88,6 +91,12 @@ int __i915_subtests(const char *caller,
 			__i915_live_setup, __i915_live_teardown, \
 			T, ARRAY_SIZE(T), data); \
 })
+#define intel_gt_live_subtests(T, data) ({ \
+	typecheck(struct intel_gt *, data); \
+	__i915_subtests(__func__, \
+			__intel_gt_live_setup, __intel_gt_live_teardown, \
+			T, ARRAY_SIZE(T), data); \
+})
 
 #define SUBTEST(x) { x, #x }
 
diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index f104b94c14ef..434ea3ff7e4c 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -887,7 +887,7 @@ static void guc_reset(struct intel_engine_cs *engine, bool stalled)
 	if (!i915_request_started(rq))
 		stalled = false;
 
-	i915_reset_request(rq, stalled);
+	__i915_request_reset(rq, stalled);
 	intel_lr_context_reset(engine, rq->hw_context, rq->head, stalled);
 
 out_unlock:
diff --git a/drivers/gpu/drm/i915/intel_uc.c b/drivers/gpu/drm/i915/intel_uc.c
index fdf00f1ebb57..b0e83e91ea6f 100644
--- a/drivers/gpu/drm/i915/intel_uc.c
+++ b/drivers/gpu/drm/i915/intel_uc.c
@@ -38,7 +38,7 @@ static int __intel_uc_reset_hw(struct drm_i915_private *dev_priv)
 	int ret;
 	u32 guc_status;
 
-	ret = intel_reset_guc(dev_priv);
+	ret = intel_reset_guc(&dev_priv->gt);
 	if (ret) {
 		DRM_ERROR("Failed to reset GuC, ret = %d\n", ret);
 		return ret;
diff --git a/drivers/gpu/drm/i915/selftests/i915_active.c b/drivers/gpu/drm/i915/selftests/i915_active.c
index 29603c5173c4..77d844ac8b71 100644
--- a/drivers/gpu/drm/i915/selftests/i915_active.c
+++ b/drivers/gpu/drm/i915/selftests/i915_active.c
@@ -7,6 +7,7 @@
 #include <linux/kref.h>
 
 #include "gem/i915_gem_pm.h"
+#include "gt/intel_gt.h"
 
 #include "i915_selftest.h"
 
@@ -220,7 +221,7 @@ int i915_active_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_active_retire),
 	};
 
-	if (i915_terminally_wedged(i915))
+	if (intel_gt_is_wedged(&i915->gt))
 		return 0;
 
 	return i915_subtests(tests, i915);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index b8ffae481730..bb6dd54a6ff3 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -8,6 +8,7 @@
 
 #include "gem/selftests/igt_gem_utils.h"
 #include "gem/selftests/mock_context.h"
+#include "gt/intel_gt.h"
 
 #include "i915_selftest.h"
 
@@ -206,7 +207,7 @@ int i915_gem_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_gem_hibernate),
 	};
 
-	if (i915_terminally_wedged(i915))
+	if (intel_gt_is_wedged(&i915->gt))
 		return 0;
 
 	return i915_live_subtests(tests, i915);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index a3cb0aade6f1..b6449d0a8c17 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -25,6 +25,7 @@
 #include "gem/i915_gem_pm.h"
 #include "gem/selftests/igt_gem_utils.h"
 #include "gem/selftests/mock_context.h"
+#include "gt/intel_gt.h"
 
 #include "i915_selftest.h"
 
@@ -557,7 +558,7 @@ int i915_gem_evict_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_evict_contexts),
 	};
 
-	if (i915_terminally_wedged(i915))
+	if (intel_gt_is_wedged(&i915->gt))
 		return 0;
 
 	return i915_subtests(tests, i915);
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 1bbfc43d4a9e..86c299663934 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -380,7 +380,7 @@ static int __igt_breadcrumbs_smoketest(void *arg)
 			       t->engine->name);
 			GEM_TRACE_DUMP();
 
-			i915_gem_set_wedged(t->engine->i915);
+			intel_gt_set_wedged(t->engine->gt);
 			GEM_BUG_ON(!i915_request_completed(rq));
 			i915_sw_fence_wait(wait);
 			err = -EIO;
@@ -1234,7 +1234,7 @@ int i915_request_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_breadcrumbs_smoketest),
 	};
 
-	if (i915_terminally_wedged(i915))
+	if (intel_gt_is_wedged(&i915->gt))
 		return 0;
 
 	return i915_subtests(tests, i915);
diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c
index f46ccf817ad5..db9c645bbdfe 100644
--- a/drivers/gpu/drm/i915/selftests/i915_selftest.c
+++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c
@@ -256,7 +256,7 @@ int __i915_live_setup(void *data)
 {
 	struct drm_i915_private *i915 = data;
 
-	return i915_terminally_wedged(i915);
+	return intel_gt_terminally_wedged(&i915->gt);
 }
 
 int __i915_live_teardown(int err, void *data)
@@ -273,6 +273,27 @@ int __i915_live_teardown(int err, void *data)
 	return err;
 }
 
+int __intel_gt_live_setup(void *data)
+{
+	struct intel_gt *gt = data;
+
+	return intel_gt_terminally_wedged(gt);
+}
+
+int __intel_gt_live_teardown(int err, void *data)
+{
+	struct intel_gt *gt = data;
+
+	mutex_lock(&gt->i915->drm.struct_mutex);
+	if (igt_flush_test(gt->i915, I915_WAIT_LOCKED))
+		err = -EIO;
+	mutex_unlock(&gt->i915->drm.struct_mutex);
+
+	i915_gem_drain_freed_objects(gt->i915);
+
+	return err;
+}
+
 int __i915_subtests(const char *caller,
 		    int (*setup)(void *data),
 		    int (*teardown)(int err, void *data),
diff --git a/drivers/gpu/drm/i915/selftests/igt_flush_test.c b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
index 5bfd1b2626a2..d3b5eb402d33 100644
--- a/drivers/gpu/drm/i915/selftests/igt_flush_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
@@ -5,6 +5,7 @@
  */
 
 #include "gem/i915_gem_context.h"
+#include "gt/intel_gt.h"
 
 #include "i915_drv.h"
 #include "i915_selftest.h"
@@ -13,7 +14,7 @@
 
 int igt_flush_test(struct drm_i915_private *i915, unsigned int flags)
 {
-	int ret = i915_terminally_wedged(i915) ? -EIO : 0;
+	int ret = intel_gt_is_wedged(&i915->gt) ? -EIO : 0;
 	int repeat = !!(flags & I915_WAIT_LOCKED);
 
 	cond_resched();
@@ -27,7 +28,7 @@ int igt_flush_test(struct drm_i915_private *i915, unsigned int flags)
 				  __builtin_return_address(0));
 			GEM_TRACE_DUMP();
 
-			i915_gem_set_wedged(i915);
+			intel_gt_set_wedged(&i915->gt);
 			repeat = 0;
 			ret = -EIO;
 		}
diff --git a/drivers/gpu/drm/i915/selftests/igt_reset.c b/drivers/gpu/drm/i915/selftests/igt_reset.c
index 587df6fd4ffe..7ec8f8b049c6 100644
--- a/drivers/gpu/drm/i915/selftests/igt_reset.c
+++ b/drivers/gpu/drm/i915/selftests/igt_reset.c
@@ -7,47 +7,45 @@
 #include "igt_reset.h"
 
 #include "gt/intel_engine.h"
+#include "gt/intel_gt.h"
 
 #include "../i915_drv.h"
 
-void igt_global_reset_lock(struct drm_i915_private *i915)
+void igt_global_reset_lock(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	pr_debug("%s: current gpu_error=%08lx\n",
-		 __func__, i915->gpu_error.flags);
+	pr_debug("%s: current gpu_error=%08lx\n", __func__, gt->reset.flags);
 
-	while (test_and_set_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags))
-		wait_event(i915->gpu_error.reset_queue,
-			   !test_bit(I915_RESET_BACKOFF,
-				     &i915->gpu_error.flags));
+	while (test_and_set_bit(I915_RESET_BACKOFF, &gt->reset.flags))
+		wait_event(gt->reset.queue,
+			   !test_bit(I915_RESET_BACKOFF, &gt->reset.flags));
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		while (test_and_set_bit(I915_RESET_ENGINE + id,
-					&i915->gpu_error.flags))
-			wait_on_bit(&i915->gpu_error.flags,
-				    I915_RESET_ENGINE + id,
+					&gt->reset.flags))
+			wait_on_bit(&gt->reset.flags, I915_RESET_ENGINE + id,
 				    TASK_UNINTERRUPTIBLE);
 	}
 }
 
-void igt_global_reset_unlock(struct drm_i915_private *i915)
+void igt_global_reset_unlock(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	for_each_engine(engine, i915, id)
-		clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+	for_each_engine(engine, gt->i915, id)
+		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 
-	clear_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
-	wake_up_all(&i915->gpu_error.reset_queue);
+	clear_bit(I915_RESET_BACKOFF, &gt->reset.flags);
+	wake_up_all(&gt->reset.queue);
 }
 
-bool igt_force_reset(struct drm_i915_private *i915)
+bool igt_force_reset(struct intel_gt *gt)
 {
-	i915_gem_set_wedged(i915);
-	i915_reset(i915, 0, NULL);
+	intel_gt_set_wedged(gt);
+	intel_gt_reset(gt, 0, NULL);
 
-	return !i915_reset_failed(i915);
+	return !intel_gt_is_wedged(gt);
 }
diff --git a/drivers/gpu/drm/i915/selftests/igt_reset.h b/drivers/gpu/drm/i915/selftests/igt_reset.h
index 363bd853e50f..851873b67ab3 100644
--- a/drivers/gpu/drm/i915/selftests/igt_reset.h
+++ b/drivers/gpu/drm/i915/selftests/igt_reset.h
@@ -7,10 +7,12 @@
 #ifndef __I915_SELFTESTS_IGT_RESET_H__
 #define __I915_SELFTESTS_IGT_RESET_H__
 
-#include "../i915_drv.h"
+#include <linux/types.h>
 
-void igt_global_reset_lock(struct drm_i915_private *i915);
-void igt_global_reset_unlock(struct drm_i915_private *i915);
-bool igt_force_reset(struct drm_i915_private *i915);
+struct intel_gt;
+
+void igt_global_reset_lock(struct intel_gt *gt);
+void igt_global_reset_unlock(struct intel_gt *gt);
+bool igt_force_reset(struct intel_gt *gt);
 
 #endif
diff --git a/drivers/gpu/drm/i915/selftests/igt_wedge_me.h b/drivers/gpu/drm/i915/selftests/igt_wedge_me.h
deleted file mode 100644
index 08e5ff11bbd9..000000000000
--- a/drivers/gpu/drm/i915/selftests/igt_wedge_me.h
+++ /dev/null
@@ -1,58 +0,0 @@
-/*
- * SPDX-License-Identifier: MIT
- *
- * Copyright © 2018 Intel Corporation
- */
-
-#ifndef IGT_WEDGE_ME_H
-#define IGT_WEDGE_ME_H
-
-#include <linux/workqueue.h>
-
-#include "../i915_gem.h"
-
-struct drm_i915_private;
-
-struct igt_wedge_me {
-	struct delayed_work work;
-	struct drm_i915_private *i915;
-	const char *name;
-};
-
-static void __igt_wedge_me(struct work_struct *work)
-{
-	struct igt_wedge_me *w = container_of(work, typeof(*w), work.work);
-
-	pr_err("%s timed out, cancelling test.\n", w->name);
-
-	GEM_TRACE("%s timed out.\n", w->name);
-	GEM_TRACE_DUMP();
-
-	i915_gem_set_wedged(w->i915);
-}
-
-static void __igt_init_wedge(struct igt_wedge_me *w,
-			     struct drm_i915_private *i915,
-			     long timeout,
-			     const char *name)
-{
-	w->i915 = i915;
-	w->name = name;
-
-	INIT_DELAYED_WORK_ONSTACK(&w->work, __igt_wedge_me);
-	schedule_delayed_work(&w->work, timeout);
-}
-
-static void __igt_fini_wedge(struct igt_wedge_me *w)
-{
-	cancel_delayed_work_sync(&w->work);
-	destroy_delayed_work_on_stack(&w->work);
-	w->i915 = NULL;
-}
-
-#define igt_wedge_on_timeout(W, DEV, TIMEOUT)				\
-	for (__igt_init_wedge((W), (DEV), (TIMEOUT), __func__);		\
-	     (W)->i915;							\
-	     __igt_fini_wedge((W)))
-
-#endif /* IGT_WEDGE_ME_H */
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 2741805b56c2..fd4cc4809eb8 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -183,11 +183,6 @@ struct drm_i915_private *mock_gem_device(void)
 	intel_gt_init_early(&i915->gt, i915);
 	atomic_inc(&i915->gt.wakeref.count); /* disable; no hw support */
 
-	init_waitqueue_head(&i915->gpu_error.wait_queue);
-	init_waitqueue_head(&i915->gpu_error.reset_queue);
-	init_srcu_struct(&i915->gpu_error.reset_backoff_srcu);
-	mutex_init(&i915->gpu_error.wedge_mutex);
-
 	i915->wq = alloc_ordered_workqueue("mock", 0);
 	if (!i915->wq)
 		goto err_drv;
-- 
2.22.0

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

Re: [PATCH 03/18] drm/i915: Lock the engine while dumping the active request

[Tvrtko Ursulin]

On 11/07/2019 07:52, Chris Wilson wrote:
> We cannot let the request be retired and freed while we are trying to
> dump it during error capture. It is not sufficient just to grab a
> reference to the request, as during retirement we may free the ring
> which we are also dumping. So take the engine lock to prevent retiring
> and freeing of the request.
> 
> Reported-by: Alex Shumsky <alexthreed@gmail.com>
> Fixes: 83c317832eb1 ("drm/i915: Dump the ringbuffer of the active request for debugging")
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
> Cc: Alex Shumsky <alexthreed@gmail.com>
> ---
>   drivers/gpu/drm/i915/gt/intel_engine_cs.c | 11 ++++-------
>   drivers/gpu/drm/i915/i915_gpu_error.c     |  6 ++++--
>   2 files changed, 8 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
> index bdf279fa3b2e..0a2e7a404c74 100644
> --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
> +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
> @@ -1484,6 +1484,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
>   	struct i915_gpu_error * const error = &engine->i915->gpu_error;
>   	struct i915_request *rq;
>   	intel_wakeref_t wakeref;
> +	unsigned long flags;
>   
>   	if (header) {
>   		va_list ap;
> @@ -1503,10 +1504,9 @@ void intel_engine_dump(struct intel_engine_cs *engine,
>   		   i915_reset_engine_count(error, engine),
>   		   i915_reset_count(error));
>   
> -	rcu_read_lock();
> -
>   	drm_printf(m, "\tRequests:\n");
>   
> +	spin_lock_irqsave(&engine->active.lock, flags);
>   	rq = intel_engine_find_active_request(engine);
>   	if (rq) {
>   		print_request(m, rq, "\t\tactive ");
> @@ -1526,8 +1526,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
>   
>   		print_request_ring(m, rq);
>   	}
> -
> -	rcu_read_unlock();
> +	spin_unlock_irqrestore(&engine->active.lock, flags);
>   
>   	wakeref = intel_runtime_pm_get_if_in_use(&engine->i915->runtime_pm);
>   	if (wakeref) {
> @@ -1689,7 +1688,6 @@ struct i915_request *
>   intel_engine_find_active_request(struct intel_engine_cs *engine)
>   {
>   	struct i915_request *request, *active = NULL;
> -	unsigned long flags;
>   
>   	/*
>   	 * We are called by the error capture, reset and to dump engine
> @@ -1702,7 +1700,7 @@ intel_engine_find_active_request(struct intel_engine_cs *engine)
>   	 * At all other times, we must assume the GPU is still running, but
>   	 * we only care about the snapshot of this moment.
>   	 */
> -	spin_lock_irqsave(&engine->active.lock, flags);
> +	lockdep_assert_held(&engine->active.lock);
>   	list_for_each_entry(request, &engine->active.requests, sched.link) {
>   		if (i915_request_completed(request))
>   			continue;
> @@ -1717,7 +1715,6 @@ intel_engine_find_active_request(struct intel_engine_cs *engine)
>   		active = request;
>   		break;
>   	}
> -	spin_unlock_irqrestore(&engine->active.lock, flags);
>   
>   	return active;
>   }
> diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
> index 5489cd879315..f297a43df1e9 100644
> --- a/drivers/gpu/drm/i915/i915_gpu_error.c
> +++ b/drivers/gpu/drm/i915/i915_gpu_error.c
> @@ -1411,6 +1411,7 @@ static void gem_record_rings(struct i915_gpu_state *error)
>   		struct intel_engine_cs *engine = i915->engine[i];
>   		struct drm_i915_error_engine *ee = &error->engine[i];
>   		struct i915_request *request;
> +		unsigned long flags;
>   
>   		ee->engine_id = -1;
>   
> @@ -1422,10 +1423,11 @@ static void gem_record_rings(struct i915_gpu_state *error)
>   		error_record_engine_registers(error, engine, ee);
>   		error_record_engine_execlists(engine, ee);
>   
> +		spin_lock_irqsave(&engine->active.lock, flags);
>   		request = intel_engine_find_active_request(engine);
>   		if (request) {
>   			struct i915_gem_context *ctx = request->gem_context;
> -			struct intel_ring *ring;
> +			struct intel_ring *ring = request->ring;
>   
>   			ee->vm = ctx->vm ?: &engine->gt->ggtt->vm;
>   
> @@ -1455,7 +1457,6 @@ static void gem_record_rings(struct i915_gpu_state *error)
>   			ee->rq_post = request->postfix;
>   			ee->rq_tail = request->tail;
>   
> -			ring = request->ring;
>   			ee->cpu_ring_head = ring->head;
>   			ee->cpu_ring_tail = ring->tail;
>   			ee->ringbuffer =
> @@ -1463,6 +1464,7 @@ static void gem_record_rings(struct i915_gpu_state *error)
>   

Aren't there allocations in this block?

>   			engine_record_requests(engine, request, ee);
>   		}
> +		spin_unlock_irqrestore(&engine->active.lock, flags);
>   
>   		ee->hws_page =
>   			i915_error_object_create(i915,
> 

Regards,

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

Re: [PATCH 03/18] drm/i915: Lock the engine while dumping the active request

[Chris Wilson]

Quoting Tvrtko Ursulin (2019-07-11 08:20:59)
> 
> On 11/07/2019 07:52, Chris Wilson wrote:
> > diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
> > index 5489cd879315..f297a43df1e9 100644
> > --- a/drivers/gpu/drm/i915/i915_gpu_error.c
> > +++ b/drivers/gpu/drm/i915/i915_gpu_error.c
> > @@ -1463,6 +1464,7 @@ static void gem_record_rings(struct i915_gpu_state *error)
> >   
> 
> Aren't there allocations in this block?

They are already atomic due to this being called under stop_machine().

Next patch gives up on stop_machine(), excludes that which is not under
spinlock, and relies on the engine->active.lock for capturing the
request and friends.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✗ Fi.CI.CHECKPATCH: warning for series starting with [01/18] drm/i915/selftests: Ensure we don't clamp a random offset to 32b

[Patchwork]

== Series Details ==

Series: series starting with [01/18] drm/i915/selftests: Ensure we don't clamp a random offset to 32b
URL   : https://patchwork.freedesktop.org/series/63533/
State : warning

== Summary ==

$ dim checkpatch origin/drm-tip
912dcfca3fc2 drm/i915/selftests: Ensure we don't clamp a random offset to 32b
b15f72d4a124 drm/i915/selftests: Hold the vma manager lock while modifying mmap_offset
a7c1d3b64fac drm/i915: Lock the engine while dumping the active request
f890aa2256c6 drm/i915: Rely on spinlock protection for GPU error capture
8c30f33da09c drm/i915/oa: Reconfigure contexts on the fly
aecf3ec7aac8 drm/i915: Add to timeline requires the timeline mutex
6b518a7d8705 drm/i915: Teach execbuffer to take the engine wakeref not GT
382d7993f6df drm/i915/gt: Track timeline activeness in enter/exit
28ee984d9e7d drm/i915/gt: Convert timeline tracking to spinlock
f05a2009711d drm/i915/gt: Guard timeline pinning with its own mutex
0f981d4ad129 drm/i915: Protect request retirement with timeline->mutex
35f7d0cd1411 drm/i915: Replace struct_mutex for batch pool serialisation
-:305: WARNING:FILE_PATH_CHANGES: added, moved or deleted file(s), does MAINTAINERS need updating?
#305: 
new file mode 100644

-:310: WARNING:SPDX_LICENSE_TAG: Missing or malformed SPDX-License-Identifier tag in line 1
#310: FILE: drivers/gpu/drm/i915/gt/intel_engine_pool.c:1:
+/*

-:311: WARNING:SPDX_LICENSE_TAG: Misplaced SPDX-License-Identifier tag - use line 1 instead
#311: FILE: drivers/gpu/drm/i915/gt/intel_engine_pool.c:2:
+ * SPDX-License-Identifier: MIT

-:500: WARNING:SPDX_LICENSE_TAG: Missing or malformed SPDX-License-Identifier tag in line 1
#500: FILE: drivers/gpu/drm/i915/gt/intel_engine_pool.h:1:
+/*

-:501: WARNING:SPDX_LICENSE_TAG: Misplaced SPDX-License-Identifier tag - use line 1 instead
#501: FILE: drivers/gpu/drm/i915/gt/intel_engine_pool.h:2:
+ * SPDX-License-Identifier: MIT

-:540: WARNING:SPDX_LICENSE_TAG: Missing or malformed SPDX-License-Identifier tag in line 1
#540: FILE: drivers/gpu/drm/i915/gt/intel_engine_pool_types.h:1:
+/*

-:541: WARNING:SPDX_LICENSE_TAG: Misplaced SPDX-License-Identifier tag - use line 1 instead
#541: FILE: drivers/gpu/drm/i915/gt/intel_engine_pool_types.h:2:
+ * SPDX-License-Identifier: MIT

-:557: CHECK:UNCOMMENTED_DEFINITION: spinlock_t definition without comment
#557: FILE: drivers/gpu/drm/i915/gt/intel_engine_pool_types.h:18:
+	spinlock_t lock;

total: 0 errors, 7 warnings, 1 checks, 613 lines checked
1e04df10d91b drm/i915/gt: Mark context->active_count as protected by timeline->mutex
b9d33aecc1c3 drm/i915: Forgo last_fence active request tracking
ba014d8c95c1 drm/i915/overlay: Switch to using i915_active tracking
88e901cf9678 drm/i915: Extract intel_frontbuffer active tracking
dbe8e637b2ac drm/i915: Markup expected timeline locks for i915_active
-:281: CHECK:UNCOMMENTED_DEFINITION: struct mutex definition without comment
#281: FILE: drivers/gpu/drm/i915/i915_active_types.h:28:
+	struct mutex *lock;

total: 0 errors, 0 warnings, 1 checks, 233 lines checked
fcc08729cca8 drm/i915/gt: Use intel_gt as the primary object for handling resets
-:27: WARNING:MEMORY_BARRIER: memory barrier without comment
#27: FILE: drivers/gpu/drm/i915/display/intel_display.c:4279:
+	smp_mb__after_atomic();

-:1826: WARNING:MEMORY_BARRIER: memory barrier without comment
#1826: FILE: drivers/gpu/drm/i915/gt/intel_reset.c:1269:
+	smp_mb__after_atomic();

-:2051: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'W' - possible side-effects?
#2051: FILE: drivers/gpu/drm/i915/gt/intel_reset.h:64:
+#define intel_wedge_on_timeout(W, GT, TIMEOUT)				\
+	for (__intel_init_wedge((W), (GT), (TIMEOUT), __func__);	\
+	     (W)->gt;							\
+	     __intel_fini_wedge((W)))

-:2066: WARNING:FILE_PATH_CHANGES: added, moved or deleted file(s), does MAINTAINERS need updating?
#2066: 
new file mode 100644

-:4479: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'T' - possible side-effects?
#4479: FILE: drivers/gpu/drm/i915/i915_selftest.h:94:
+#define intel_gt_live_subtests(T, data) ({ \
+	typecheck(struct intel_gt *, data); \
+	__i915_subtests(__func__, \
+			__intel_gt_live_setup, __intel_gt_live_teardown, \
+			T, ARRAY_SIZE(T), data); \
+})

total: 0 errors, 3 warnings, 2 checks, 4298 lines checked

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

✗ Fi.CI.SPARSE: warning for series starting with [01/18] drm/i915/selftests: Ensure we don't clamp a random offset to 32b

[Patchwork]

== Series Details ==

Series: series starting with [01/18] drm/i915/selftests: Ensure we don't clamp a random offset to 32b
URL   : https://patchwork.freedesktop.org/series/63533/
State : warning

== Summary ==

$ dim sparse origin/drm-tip
Sparse version: v0.5.2
Commit: drm/i915/selftests: Ensure we don't clamp a random offset to 32b
Okay!

Commit: drm/i915/selftests: Hold the vma manager lock while modifying mmap_offset
Okay!

Commit: drm/i915: Lock the engine while dumping the active request
Okay!

Commit: drm/i915: Rely on spinlock protection for GPU error capture
-O:drivers/gpu/drm/i915/i915_gpu_error.c:1007:21: warning: expression using sizeof(void)
-O:drivers/gpu/drm/i915/i915_gpu_error.c:1007:21: warning: expression using sizeof(void)
+drivers/gpu/drm/i915/i915_gpu_error.c:1017:21: warning: expression using sizeof(void)
+drivers/gpu/drm/i915/i915_gpu_error.c:1017:21: warning: expression using sizeof(void)
-./include/linux/slab.h:666:13: error: not a function <noident>
-./include/linux/slab.h:666:13: error: not a function <noident>

Commit: drm/i915/oa: Reconfigure contexts on the fly
Okay!

Commit: drm/i915: Add to timeline requires the timeline mutex
Okay!

Commit: drm/i915: Teach execbuffer to take the engine wakeref not GT
Okay!

Commit: drm/i915/gt: Track timeline activeness in enter/exit
Okay!

Commit: drm/i915/gt: Convert timeline tracking to spinlock
Okay!

Commit: drm/i915/gt: Guard timeline pinning with its own mutex
Okay!

Commit: drm/i915: Protect request retirement with timeline->mutex
Okay!

Commit: drm/i915: Replace struct_mutex for batch pool serialisation
+./include/uapi/linux/perf_event.h:147:56: warning: cast truncates bits from constant value (8000000000000000 becomes 0)

Commit: drm/i915/gt: Mark context->active_count as protected by timeline->mutex
Okay!

Commit: drm/i915: Forgo last_fence active request tracking
Okay!

Commit: drm/i915/overlay: Switch to using i915_active tracking
Okay!

Commit: drm/i915: Extract intel_frontbuffer active tracking
Okay!

Commit: drm/i915: Markup expected timeline locks for i915_active
Okay!

Commit: drm/i915/gt: Use intel_gt as the primary object for handling resets
-O:drivers/gpu/drm/i915/gt/intel_reset.c:1292:5: warning: context imbalance in 'i915_reset_trylock' - different lock contexts for basic block
+drivers/gpu/drm/i915/gt/intel_reset.c:1276:5: warning: context imbalance in 'intel_gt_reset_trylock' - different lock contexts for basic block
-./drivers/gpu/drm/i915/gt/selftest_timeline.c:91:38: warning: expression using sizeof(void)
-./drivers/gpu/drm/i915/gt/selftest_timeline.c:91:38: warning: expression using sizeof(void)
-./drivers/gpu/drm/i915/gt/selftest_timeline.c:94:44: warning: expression using sizeof(void)
-./drivers/gpu/drm/i915/gt/selftest_timeline.c:94:44: warning: expression using sizeof(void)
+./drivers/gpu/drm/i915/gt/selftest_timeline.c:92:38: warning: expression using sizeof(void)
+./drivers/gpu/drm/i915/gt/selftest_timeline.c:92:38: warning: expression using sizeof(void)
+./drivers/gpu/drm/i915/gt/selftest_timeline.c:95:44: warning: expression using sizeof(void)
+./drivers/gpu/drm/i915/gt/selftest_timeline.c:95:44: warning: expression using sizeof(void)

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

✓ Fi.CI.BAT: success for series starting with [01/18] drm/i915/selftests: Ensure we don't clamp a random offset to 32b

[Patchwork]

== Series Details ==

Series: series starting with [01/18] drm/i915/selftests: Ensure we don't clamp a random offset to 32b
URL   : https://patchwork.freedesktop.org/series/63533/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_6456 -> Patchwork_13618
====================================================

Summary
-------

  **SUCCESS**

  No regressions found.

  External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13618/

Known issues
------------

  Here are the changes found in Patchwork_13618 that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@i915_selftest@live_execlists:
    - fi-skl-gvtdvm:      [PASS][1] -> [DMESG-FAIL][2] ([fdo#111108])
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6456/fi-skl-gvtdvm/igt@i915_selftest@live_execlists.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13618/fi-skl-gvtdvm/igt@i915_selftest@live_execlists.html

  
#### Possible fixes ####

  * igt@i915_hangman@error-state-basic:
    - fi-bsw-kefka:       [SKIP][3] ([fdo#109271]) -> [PASS][4]
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6456/fi-bsw-kefka/igt@i915_hangman@error-state-basic.html
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13618/fi-bsw-kefka/igt@i915_hangman@error-state-basic.html
    - fi-bsw-n3050:       [SKIP][5] ([fdo#109271]) -> [PASS][6]
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6456/fi-bsw-n3050/igt@i915_hangman@error-state-basic.html
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13618/fi-bsw-n3050/igt@i915_hangman@error-state-basic.html

  * igt@kms_chamelium@hdmi-edid-read:
    - {fi-icl-u4}:        [FAIL][7] ([fdo#111045] / [fdo#111046 ]) -> [PASS][8]
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6456/fi-icl-u4/igt@kms_chamelium@hdmi-edid-read.html
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13618/fi-icl-u4/igt@kms_chamelium@hdmi-edid-read.html

  * igt@kms_chamelium@hdmi-hpd-fast:
    - fi-kbl-7500u:       [FAIL][9] ([fdo#109485]) -> [PASS][10]
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6456/fi-kbl-7500u/igt@kms_chamelium@hdmi-hpd-fast.html
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13618/fi-kbl-7500u/igt@kms_chamelium@hdmi-hpd-fast.html
    - fi-kbl-7567u:       [FAIL][11] ([fdo#109485]) -> [PASS][12]
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6456/fi-kbl-7567u/igt@kms_chamelium@hdmi-hpd-fast.html
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13618/fi-kbl-7567u/igt@kms_chamelium@hdmi-hpd-fast.html

  
  {name}: This element is suppressed. This means it is ignored when computing
          the status of the difference (SUCCESS, WARNING, or FAILURE).

  [fdo#107713]: https://bugs.freedesktop.org/show_bug.cgi?id=107713
  [fdo#109271]: https://bugs.freedesktop.org/show_bug.cgi?id=109271
  [fdo#109485]: https://bugs.freedesktop.org/show_bug.cgi?id=109485
  [fdo#111045]: https://bugs.freedesktop.org/show_bug.cgi?id=111045
  [fdo#111046 ]: https://bugs.freedesktop.org/show_bug.cgi?id=111046 
  [fdo#111096]: https://bugs.freedesktop.org/show_bug.cgi?id=111096
  [fdo#111108]: https://bugs.freedesktop.org/show_bug.cgi?id=111108


Participating hosts (52 -> 47)
------------------------------

  Additional (1): fi-icl-dsi 
  Missing    (6): fi-kbl-soraka fi-byt-squawks fi-bsw-cyan fi-icl-y fi-byt-clapper fi-bdw-samus 


Build changes
-------------

  * Linux: CI_DRM_6456 -> Patchwork_13618

  CI_DRM_6456: 43aa8c3633274d7cf0a6dca4b8734d84d9928cf9 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_5093: 86dc48ede7c33bf69e15f84179d2f9e5b84c179b @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_13618: fcc08729cca8e0b284f8bf9de05167cbbaa46e3d @ git://anongit.freedesktop.org/gfx-ci/linux


== Kernel 32bit build ==

Warning: Kernel 32bit buildtest failed:
https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13618/build_32bit.log

  CALL    scripts/checksyscalls.sh
  CALL    scripts/atomic/check-atomics.sh
  CHK     include/generated/compile.h
Kernel: arch/x86/boot/bzImage is ready  (#1)
  Building modules, stage 2.
  MODPOST 112 modules
ERROR: "__udivdi3" [drivers/gpu/drm/amd/amdgpu/amdgpu.ko] undefined!
ERROR: "__divdi3" [drivers/gpu/drm/amd/amdgpu/amdgpu.ko] undefined!
scripts/Makefile.modpost:91: recipe for target '__modpost' failed
make[1]: *** [__modpost] Error 1
Makefile:1287: recipe for target 'modules' failed
make: *** [modules] Error 2


== Linux commits ==

fcc08729cca8 drm/i915/gt: Use intel_gt as the primary object for handling resets
dbe8e637b2ac drm/i915: Markup expected timeline locks for i915_active
88e901cf9678 drm/i915: Extract intel_frontbuffer active tracking
ba014d8c95c1 drm/i915/overlay: Switch to using i915_active tracking
b9d33aecc1c3 drm/i915: Forgo last_fence active request tracking
1e04df10d91b drm/i915/gt: Mark context->active_count as protected by timeline->mutex
35f7d0cd1411 drm/i915: Replace struct_mutex for batch pool serialisation
0f981d4ad129 drm/i915: Protect request retirement with timeline->mutex
f05a2009711d drm/i915/gt: Guard timeline pinning with its own mutex
28ee984d9e7d drm/i915/gt: Convert timeline tracking to spinlock
382d7993f6df drm/i915/gt: Track timeline activeness in enter/exit
6b518a7d8705 drm/i915: Teach execbuffer to take the engine wakeref not GT
aecf3ec7aac8 drm/i915: Add to timeline requires the timeline mutex
8c30f33da09c drm/i915/oa: Reconfigure contexts on the fly
f890aa2256c6 drm/i915: Rely on spinlock protection for GPU error capture
a7c1d3b64fac drm/i915: Lock the engine while dumping the active request
b15f72d4a124 drm/i915/selftests: Hold the vma manager lock while modifying mmap_offset
912dcfca3fc2 drm/i915/selftests: Ensure we don't clamp a random offset to 32b

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13618/
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 02/18] drm/i915/selftests: Hold the vma manager lock while modifying mmap_offset

[Imre Deak]

On Thu, Jul 11, 2019 at 07:51:59AM +0100, Chris Wilson wrote:
> Right idea, wrong lock. We already drop struct_mutex before we free the
> mmap_offset when freeing the object, so we need to take the vma manager
> lock when manipulating the mmap_offset address space for our selftests.
> 
> Fixes: 8221d21b0664 ("drm/i915/selftests: Lock the drm_mm while modifying")
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Imre Deak <imre.deak@intel.com>

Looks correct to me, obj->refcount=0 while its mmap_offset is still not
removed is a valid scenario and for mmap_offset lookup/changes vm_lock
should be enough:

Reviewed-by: Imre Deak <imre.deak@intel.com>

> ---
>  .../drm/i915/gem/selftests/i915_gem_mman.c    | 20 +++++++++++++++----
>  1 file changed, 16 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
> index b95fdc2b6bfc..5635cbb4af22 100644
> --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
> +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
> @@ -401,6 +401,18 @@ static void restore_retire_worker(struct drm_i915_private *i915)
>  	i915_gem_shrinker_register(i915);
>  }
>  
> +static void mmap_offset_lock(struct drm_i915_private *i915)
> +	__acquires(&i915->drm.vma_offset_manager->vm_lock)
> +{
> +	write_lock(&i915->drm.vma_offset_manager->vm_lock);
> +}
> +
> +static void mmap_offset_unlock(struct drm_i915_private *i915)
> +	__releases(&i915->drm.vma_offset_manager->vm_lock)
> +{
> +	write_unlock(&i915->drm.vma_offset_manager->vm_lock);
> +}
> +
>  static int igt_mmap_offset_exhaustion(void *arg)
>  {
>  	struct drm_i915_private *i915 = arg;
> @@ -419,9 +431,9 @@ static int igt_mmap_offset_exhaustion(void *arg)
>  	drm_mm_for_each_hole(hole, mm, hole_start, hole_end) {
>  		resv.start = hole_start;
>  		resv.size = hole_end - hole_start - 1; /* PAGE_SIZE units */
> -		mutex_lock(&i915->drm.struct_mutex);
> +		mmap_offset_lock(i915);
>  		err = drm_mm_reserve_node(mm, &resv);
> -		mutex_unlock(&i915->drm.struct_mutex);
> +		mmap_offset_unlock(i915);
>  		if (err) {
>  			pr_err("Failed to trim VMA manager, err=%d\n", err);
>  			goto out_park;
> @@ -485,9 +497,9 @@ static int igt_mmap_offset_exhaustion(void *arg)
>  	}
>  
>  out:
> -	mutex_lock(&i915->drm.struct_mutex);
> +	mmap_offset_lock(i915);
>  	drm_mm_remove_node(&resv);
> -	mutex_unlock(&i915->drm.struct_mutex);
> +	mmap_offset_unlock(i915);
>  out_park:
>  	restore_retire_worker(i915);
>  	return err;
> -- 
> 2.22.0
> 
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx