Merge tag 'amd-drm-fixes-5.10-2020-10-14' of git://people.freedesktop.org/~agd5f/linux into drm-next

amd-drm-fixes-5.10-2020-10-14:

amdgpu:
- eDP fix
- BACO fix
- Kernel documentation fixes
- SMU7 mclk fix
- VCN1 hw bug workaround

amdkfd:
- kvfree vs kfree fix

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201014195403.4558-1-alexander.deucher@amd.com

Documentation/gpu/amdgpu.rst

@@ -206,8 +206,8 @@ pp_power_profile_mode
 .. kernel-doc:: drivers/gpu/drm/amd/pm/amdgpu_pm.c
    :doc: pp_power_profile_mode
 
-*_busy_percent
-~~~~~~~~~~~~~~
+\*_busy_percent
+~~~~~~~~~~~~~~~
 
 .. kernel-doc:: drivers/gpu/drm/amd/pm/amdgpu_pm.c
    :doc: gpu_busy_percent

drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c

@@ -68,6 +68,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 
 	INIT_DELAYED_WORK(&adev->vcn.idle_work, amdgpu_vcn_idle_work_handler);
 	mutex_init(&adev->vcn.vcn_pg_lock);
+	mutex_init(&adev->vcn.vcn1_jpeg1_workaround);
 	atomic_set(&adev->vcn.total_submission_cnt, 0);
 	for (i = 0; i < adev->vcn.num_vcn_inst; i++)
 		atomic_set(&adev->vcn.inst[i].dpg_enc_submission_cnt, 0);
@@ -237,6 +238,7 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
 	}
 
 	release_firmware(adev->vcn.fw);
+	mutex_destroy(&adev->vcn.vcn1_jpeg1_workaround);
 	mutex_destroy(&adev->vcn.vcn_pg_lock);
 
 	return 0;

drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h

@@ -220,6 +220,7 @@ struct amdgpu_vcn {
 	struct amdgpu_vcn_inst	 inst[AMDGPU_MAX_VCN_INSTANCES];
 	struct amdgpu_vcn_reg	 internal;
 	struct mutex		 vcn_pg_lock;
+	struct mutex		vcn1_jpeg1_workaround;
 	atomic_t		 total_submission_cnt;
 
 	unsigned	harvest_config;

drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c

@@ -33,6 +33,7 @@
 
 static void jpeg_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev);
+static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring);
 
 static void jpeg_v1_0_decode_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val)
 {
@@ -564,8 +565,8 @@ static const struct amdgpu_ring_funcs jpeg_v1_0_decode_ring_vm_funcs = {
 	.insert_start = jpeg_v1_0_decode_ring_insert_start,
 	.insert_end = jpeg_v1_0_decode_ring_insert_end,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
-	.begin_use = vcn_v1_0_ring_begin_use,
-	.end_use = amdgpu_vcn_ring_end_use,
+	.begin_use = jpeg_v1_0_ring_begin_use,
+	.end_use = vcn_v1_0_ring_end_use,
 	.emit_wreg = jpeg_v1_0_decode_ring_emit_wreg,
 	.emit_reg_wait = jpeg_v1_0_decode_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
@@ -586,3 +587,22 @@ static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev)
 {
 	adev->jpeg.inst->irq.funcs = &jpeg_v1_0_irq_funcs;
 }
+
+static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring)
+{
+	struct	amdgpu_device *adev = ring->adev;
+	bool	set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work);
+	int		cnt = 0;
+
+	mutex_lock(&adev->vcn.vcn1_jpeg1_workaround);
+
+	if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_dec))
+		DRM_ERROR("JPEG dec: vcn dec ring may not be empty\n");
+
+	for (cnt = 0; cnt < adev->vcn.num_enc_rings; cnt++) {
+		if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_enc[cnt]))
+			DRM_ERROR("JPEG dec: vcn enc ring[%d] may not be empty\n", cnt);
+	}
+
+	vcn_v1_0_set_pg_for_begin_use(ring, set_clocks);
+}

drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c

@@ -54,6 +54,7 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
 				int inst_idx, struct dpg_pause_state *new_state);
 
 static void vcn_v1_0_idle_work_handler(struct work_struct *work);
+static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring);
 
 /**
  * vcn_v1_0_early_init - set function pointers
@@ -1804,10 +1805,23 @@ static void vcn_v1_0_idle_work_handler(struct work_struct *work)
 	}
 }
 
-void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring)
+static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring)
+{
+	struct	amdgpu_device *adev = ring->adev;
+	bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work);
+
+	mutex_lock(&adev->vcn.vcn1_jpeg1_workaround);
+
+	if (amdgpu_fence_wait_empty(&ring->adev->jpeg.inst->ring_dec))
+		DRM_ERROR("VCN dec: jpeg dec ring may not be empty\n");
+
+	vcn_v1_0_set_pg_for_begin_use(ring, set_clocks);
+
+}
+
+void vcn_v1_0_set_pg_for_begin_use(struct amdgpu_ring *ring, bool set_clocks)
 {
 	struct amdgpu_device *adev = ring->adev;
-	bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work);
 
 	if (set_clocks) {
 		amdgpu_gfx_off_ctrl(adev, false);
@@ -1844,6 +1858,12 @@ void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring)
 	}
 }
 
+void vcn_v1_0_ring_end_use(struct amdgpu_ring *ring)
+{
+	schedule_delayed_work(&ring->adev->vcn.idle_work, VCN_IDLE_TIMEOUT);
+	mutex_unlock(&ring->adev->vcn.vcn1_jpeg1_workaround);
+}
+
 static const struct amd_ip_funcs vcn_v1_0_ip_funcs = {
 	.name = "vcn_v1_0",
 	.early_init = vcn_v1_0_early_init,
@@ -1891,7 +1911,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = {
 	.insert_end = vcn_v1_0_dec_ring_insert_end,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.begin_use = vcn_v1_0_ring_begin_use,
-	.end_use = amdgpu_vcn_ring_end_use,
+	.end_use = vcn_v1_0_ring_end_use,
 	.emit_wreg = vcn_v1_0_dec_ring_emit_wreg,
 	.emit_reg_wait = vcn_v1_0_dec_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
@@ -1923,7 +1943,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_enc_ring_vm_funcs = {
 	.insert_end = vcn_v1_0_enc_ring_insert_end,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.begin_use = vcn_v1_0_ring_begin_use,
-	.end_use = amdgpu_vcn_ring_end_use,
+	.end_use = vcn_v1_0_ring_end_use,
 	.emit_wreg = vcn_v1_0_enc_ring_emit_wreg,
 	.emit_reg_wait = vcn_v1_0_enc_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,

drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h

@@ -24,7 +24,8 @@
 #ifndef __VCN_V1_0_H__
 #define __VCN_V1_0_H__
 
-void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring);
+void vcn_v1_0_ring_end_use(struct amdgpu_ring *ring);
+void vcn_v1_0_set_pg_for_begin_use(struct amdgpu_ring *ring, bool set_clocks);
 
 extern const struct amdgpu_ip_block_version vcn_v1_0_ip_block;
 

drivers/gpu/drm/amd/amdkfd/kfd_crat.c

@@ -1426,5 +1426,5 @@ int kfd_create_crat_image_virtual(void **crat_image, size_t *size,
  */
 void kfd_destroy_crat_image(void *crat_image)
 {
-	kfree(crat_image);
+	kvfree(crat_image);
 }

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h

@@ -149,6 +149,8 @@ struct amdgpu_dm_backlight_caps {
  * @cached_state: Caches device atomic state for suspend/resume
  * @cached_dc_state: Cached state of content streams
  * @compressor: Frame buffer compression buffer. See &struct dm_comressor_info
+ * @force_timing_sync: set via debugfs. When set, indicates that all connected
+ *		       displays will be forced to synchronize.
  */
 struct amdgpu_display_manager {
 

drivers/gpu/drm/amd/display/dc/core/dc.c

@@ -848,7 +848,7 @@ static void disable_vbios_mode_if_required(
 		struct dc *dc,
 		struct dc_state *context)
 {
-	unsigned int i;
+	unsigned int i, j;
 
 	/* check if timing_changed, disable stream*/
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
@@ -872,10 +872,10 @@ static void disable_vbios_mode_if_required(
 
 			enc_inst = link->link_enc->funcs->get_dig_frontend(link->link_enc);
 			if (enc_inst != ENGINE_ID_UNKNOWN) {
-				for (i = 0; i < dc->res_pool->stream_enc_count; i++) {
-					if (dc->res_pool->stream_enc[i]->id == enc_inst) {
-						tg_inst = dc->res_pool->stream_enc[i]->funcs->dig_source_otg(
-							dc->res_pool->stream_enc[i]);
+				for (j = 0; j < dc->res_pool->stream_enc_count; j++) {
+					if (dc->res_pool->stream_enc[j]->id == enc_inst) {
+						tg_inst = dc->res_pool->stream_enc[j]->funcs->dig_source_otg(
+							dc->res_pool->stream_enc[j]);
 						break;
 					}
 				}

drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c

@@ -2883,7 +2883,7 @@ static int smu7_vblank_too_short(struct pp_hwmgr *hwmgr,
 		if (hwmgr->is_kicker)
 			switch_limit_us = data->is_memory_gddr5 ? 450 : 150;
 		else
-			switch_limit_us = data->is_memory_gddr5 ? 190 : 150;
+			switch_limit_us = data->is_memory_gddr5 ? 200 : 150;
 		break;
 	case CHIP_VEGAM:
 		switch_limit_us = 30;

drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c

@@ -417,6 +417,9 @@ static int smu_early_init(void *handle)
 	smu->pm_enabled = !!amdgpu_dpm;
 	smu->is_apu = false;
 	mutex_init(&smu->mutex);
+	mutex_init(&smu->smu_baco.mutex);
+	smu->smu_baco.state = SMU_BACO_STATE_EXIT;
+	smu->smu_baco.platform_support = false;
 
 	return smu_set_funcs(adev);
 }
@@ -795,10 +798,6 @@ static int smu_sw_init(void *handle)
 	bitmap_zero(smu->smu_feature.enabled, SMU_FEATURE_MAX);
 	bitmap_zero(smu->smu_feature.allowed, SMU_FEATURE_MAX);
 
-	mutex_init(&smu->smu_baco.mutex);
-	smu->smu_baco.state = SMU_BACO_STATE_EXIT;
-	smu->smu_baco.platform_support = false;
-
 	mutex_init(&smu->sensor_lock);
 	mutex_init(&smu->metrics_lock);
 	mutex_init(&smu->message_lock);