drm/amdgpu: Do not fiddle with the idle workers too much

Idle workers only need to be canceled or pushed back if we are potentially
idle. Make the both operations conditional on the pre-increment and post-
decrement status of the in-flight job counter.

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

4 files changed, 20 insertions, 24 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 419992589df3..96c9d4f00b27 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -2733,9 +2733,8 @@ void amdgpu_gfx_profile_ring_begin_use(struct amdgpu_ring *ring)
 	else
 		profile = PP_SMC_POWER_PROFILE_COMPUTE;
 
-	atomic_inc(&adev->gfx.total_submission_cnt);
-
-	cancel_delayed_work_sync(&adev->gfx.idle_work);
+	if (!atomic_fetch_inc(&adev->gfx.total_submission_cnt))
+		cancel_delayed_work_sync(&adev->gfx.idle_work);
 
 	/* We can safely return early here because we've cancelled the
 	 * the delayed work so there is no one else to set it to false
@@ -2763,9 +2762,9 @@ void amdgpu_gfx_profile_ring_end_use(struct amdgpu_ring *ring)
 	if (amdgpu_dpm_is_overdrive_enabled(adev))
 		return;
 
-	atomic_dec(&ring->adev->gfx.total_submission_cnt);
-
-	schedule_delayed_work(&ring->adev->gfx.idle_work, GFX_PROFILE_IDLE_TIMEOUT);
+	if (atomic_dec_and_test(&ring->adev->gfx.total_submission_cnt))
+		schedule_delayed_work(&ring->adev->gfx.idle_work,
+				      GFX_PROFILE_IDLE_TIMEOUT);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
index 63ee6ba6a931..57935c321515 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
@@ -134,8 +134,8 @@ void amdgpu_jpeg_ring_begin_use(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	atomic_inc(&adev->jpeg.total_submission_cnt);
-	cancel_delayed_work_sync(&adev->jpeg.idle_work);
+	if (!atomic_fetch_inc(&adev->jpeg.total_submission_cnt))
+		cancel_delayed_work_sync(&adev->jpeg.idle_work);
 
 	mutex_lock(&adev->jpeg.jpeg_pg_lock);
 	amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_JPEG,
@@ -145,8 +145,9 @@ void amdgpu_jpeg_ring_begin_use(struct amdgpu_ring *ring)
 
 void amdgpu_jpeg_ring_end_use(struct amdgpu_ring *ring)
 {
-	atomic_dec(&ring->adev->jpeg.total_submission_cnt);
-	schedule_delayed_work(&ring->adev->jpeg.idle_work, JPEG_IDLE_TIMEOUT);
+	if (atomic_dec_and_test(&ring->adev->jpeg.total_submission_cnt))
+		schedule_delayed_work(&ring->adev->jpeg.idle_work,
+				      JPEG_IDLE_TIMEOUT);
 }
 
 int amdgpu_jpeg_dec_ring_test_ring(struct amdgpu_ring *ring)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index e4d435d4a629..fe504f1a3fc8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -506,9 +506,8 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_vcn_inst *vcn_inst = &adev->vcn.inst[ring->me];
 
-	atomic_inc(&vcn_inst->total_submission_cnt);
-
-	cancel_delayed_work_sync(&vcn_inst->idle_work);
+	if (!atomic_fetch_inc(&vcn_inst->total_submission_cnt))
+		cancel_delayed_work_sync(&vcn_inst->idle_work);
 
 	mutex_lock(&vcn_inst->vcn_pg_lock);
 	vcn_inst->set_pg_state(vcn_inst, AMD_PG_STATE_UNGATE);
@@ -550,10 +549,9 @@ void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring)
 	    !adev->vcn.inst[ring->me].using_unified_queue)
 		atomic_dec(&ring->adev->vcn.inst[ring->me].dpg_enc_submission_cnt);
 
-	atomic_dec(&ring->adev->vcn.inst[ring->me].total_submission_cnt);
-
-	schedule_delayed_work(&ring->adev->vcn.inst[ring->me].idle_work,
-			      VCN_IDLE_TIMEOUT);
+	if (atomic_dec_and_test(&ring->adev->vcn.inst[ring->me].total_submission_cnt))
+		schedule_delayed_work(&ring->adev->vcn.inst[ring->me].idle_work,
+				      VCN_IDLE_TIMEOUT);
 }
 
 int amdgpu_vcn_dec_ring_test_ring(struct amdgpu_ring *ring)
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index 8b8184fe6764..0d8a3cea63ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -159,9 +159,8 @@ static void vcn_v2_5_ring_begin_use(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_vcn_inst *v = &adev->vcn.inst[ring->me];
 
-	atomic_inc(&adev->vcn.inst[0].total_submission_cnt);
-
-	cancel_delayed_work_sync(&adev->vcn.inst[0].idle_work);
+	if (!atomic_fetch_inc(&adev->vcn.inst[0].total_submission_cnt))
+		cancel_delayed_work_sync(&adev->vcn.inst[0].idle_work);
 
 	/* We can safely return early here because we've cancelled the
 	 * the delayed work so there is no one else to set it to false
@@ -207,10 +206,9 @@ static void vcn_v2_5_ring_end_use(struct amdgpu_ring *ring)
 	    !adev->vcn.inst[ring->me].using_unified_queue)
 		atomic_dec(&adev->vcn.inst[ring->me].dpg_enc_submission_cnt);
 
-	atomic_dec(&adev->vcn.inst[0].total_submission_cnt);
-
-	schedule_delayed_work(&adev->vcn.inst[0].idle_work,
-			      VCN_IDLE_TIMEOUT);
+	if (atomic_dec_and_test(&adev->vcn.inst[0].total_submission_cnt))
+		schedule_delayed_work(&adev->vcn.inst[0].idle_work,
+				      VCN_IDLE_TIMEOUT);
 }
 
 /**