13 files changed, 107 insertions, 32 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index bc62bf41b7e9..5dc349173e4f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -212,6 +212,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 	}
 
 	if (amdgpu_device_is_px(dev)) {
+		dev_pm_set_driver_flags(dev->dev, DPM_FLAG_NEVER_SKIP);
 		pm_runtime_use_autosuspend(dev->dev);
 		pm_runtime_set_autosuspend_delay(dev->dev, 5000);
 		pm_runtime_set_active(dev->dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index aadd0fa42e43..3aa42c64484a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -405,6 +405,7 @@ struct amdgpu_crtc {
 	struct amdgpu_flip_work *pflip_works;
 	enum amdgpu_flip_status pflip_status;
 	int deferred_flip_completion;
+	u64 last_flip_vblank;
 	/* pll sharing */
 	struct amdgpu_atom_ss ss;
 	bool ss_enabled;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 8fab0d637ee5..3a9b48b227ac 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -90,8 +90,10 @@ static int psp_sw_fini(void *handle)
 	adev->psp.sos_fw = NULL;
 	release_firmware(adev->psp.asd_fw);
 	adev->psp.asd_fw = NULL;
-	release_firmware(adev->psp.ta_fw);
-	adev->psp.ta_fw = NULL;
+	if (adev->psp.ta_fw) {
+		release_firmware(adev->psp.ta_fw);
+		adev->psp.ta_fw = NULL;
+	}
 	return 0;
 }
 
@@ -435,6 +437,9 @@ static int psp_xgmi_initialize(struct psp_context *psp)
 	struct ta_xgmi_shared_memory *xgmi_cmd;
 	int ret;
 
+	if (!psp->adev->psp.ta_fw)
+		return -ENOENT;
+
 	if (!psp->xgmi_context.initialized) {
 		ret = psp_xgmi_init_shared_buf(psp);
 		if (ret)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 7c108e687683..698bcb8ce61d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -638,12 +638,14 @@ void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev,
 	struct ttm_bo_global *glob = adev->mman.bdev.glob;
 	struct amdgpu_vm_bo_base *bo_base;
 
+#if 0
 	if (vm->bulk_moveable) {
 		spin_lock(&glob->lru_lock);
 		ttm_bo_bulk_move_lru_tail(&vm->lru_bulk_move);
 		spin_unlock(&glob->lru_lock);
 		return;
 	}
+#endif
 
 	memset(&vm->lru_bulk_move, 0, sizeof(vm->lru_bulk_move));
 
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index 0c6e7f9b143f..189fcb004579 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -152,18 +152,22 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name);
 	err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev);
-	if (err)
-		goto out2;
-
-	err = amdgpu_ucode_validate(adev->psp.ta_fw);
-	if (err)
-		goto out2;
-
-	ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data;
-	adev->psp.ta_xgmi_ucode_version = le32_to_cpu(ta_hdr->ta_xgmi_ucode_version);
-	adev->psp.ta_xgmi_ucode_size = le32_to_cpu(ta_hdr->ta_xgmi_size_bytes);
-	adev->psp.ta_xgmi_start_addr = (uint8_t *)ta_hdr +
-		le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes);
+	if (err) {
+		release_firmware(adev->psp.ta_fw);
+		adev->psp.ta_fw = NULL;
+		dev_info(adev->dev,
+			 "psp v11.0: Failed to load firmware \"%s\"\n", fw_name);
+	} else {
+		err = amdgpu_ucode_validate(adev->psp.ta_fw);
+		if (err)
+			goto out2;
+
+		ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data;
+		adev->psp.ta_xgmi_ucode_version = le32_to_cpu(ta_hdr->ta_xgmi_ucode_version);
+		adev->psp.ta_xgmi_ucode_size = le32_to_cpu(ta_hdr->ta_xgmi_size_bytes);
+		adev->psp.ta_xgmi_start_addr = (uint8_t *)ta_hdr +
+			le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes);
+	}
 
 	return 0;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 6811a5d05b27..aa2f71cc1eba 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -128,7 +128,7 @@ static const struct soc15_reg_golden golden_settings_sdma0_4_2_init[] = {
 
 static const struct soc15_reg_golden golden_settings_sdma0_4_2[] =
 {
-	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_CHICKEN_BITS, 0xfe931f07, 0x02831d07),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_CHICKEN_BITS, 0xfe931f07, 0x02831f07),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_CLK_CTRL, 0xffffffff, 0x3f000100),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_GB_ADDR_CONFIG, 0x0000773f, 0x00004002),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_GB_ADDR_CONFIG_READ, 0x0000773f, 0x00004002),
@@ -158,7 +158,7 @@ static const struct soc15_reg_golden golden_settings_sdma0_4_2[] =
 };
 
 static const struct soc15_reg_golden golden_settings_sdma1_4_2[] = {
-	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_CHICKEN_BITS, 0xfe931f07, 0x02831d07),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_CHICKEN_BITS, 0xfe931f07, 0x02831f07),
 	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_CLK_CTRL, 0xffffffff, 0x3f000100),
 	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_GB_ADDR_CONFIG, 0x0000773f, 0x00004002),
 	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_GB_ADDR_CONFIG_READ, 0x0000773f, 0x00004002),
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 0b392bfca284..636d14a60952 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -303,12 +303,11 @@ static void dm_pflip_high_irq(void *interrupt_params)
 		return;
 	}
 
+	/* Update to correct count(s) if racing with vblank irq */
+	amdgpu_crtc->last_flip_vblank = drm_crtc_accurate_vblank_count(&amdgpu_crtc->base);
 
 	/* wake up userspace */
 	if (amdgpu_crtc->event) {
-		/* Update to correct count(s) if racing with vblank irq */
-		drm_crtc_accurate_vblank_count(&amdgpu_crtc->base);
-
 		drm_crtc_send_vblank_event(&amdgpu_crtc->base, amdgpu_crtc->event);
 
 		/* page flip completed. clean up */
@@ -786,12 +785,13 @@ static int dm_suspend(void *handle)
 	struct amdgpu_display_manager *dm = &adev->dm;
 	int ret = 0;
 
+	WARN_ON(adev->dm.cached_state);
+	adev->dm.cached_state = drm_atomic_helper_suspend(adev->ddev);
+
 	s3_handle_mst(adev->ddev, true);
 
 	amdgpu_dm_irq_suspend(adev);
 
-	WARN_ON(adev->dm.cached_state);
-	adev->dm.cached_state = drm_atomic_helper_suspend(adev->ddev);
 
 	dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D3);
 
@@ -4827,6 +4827,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			to_dm_crtc_state(drm_atomic_get_old_crtc_state(state, pcrtc));
 	int planes_count = 0;
 	unsigned long flags;
+	u64 last_flip_vblank;
+	bool vrr_active = acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE;
 
 	/* update planes when needed */
 	for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i) {
@@ -4858,6 +4860,16 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			/* In commit tail framework this cannot happen */
 			WARN_ON(1);
 		}
+
+		/* For variable refresh rate mode only:
+		 * Get vblank of last completed flip to avoid > 1 vrr flips per
+		 * video frame by use of throttling, but allow flip programming
+		 * anywhere in the possibly large variable vrr vblank interval
+		 * for fine-grained flip timing control and more opportunity to
+		 * avoid stutter on late submission of amdgpu_dm_do_flip() calls.
+		 */
+		last_flip_vblank = acrtc_attach->last_flip_vblank;
+
 		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
 
 		if (!pflip_needed || plane->type == DRM_PLANE_TYPE_OVERLAY) {
@@ -4881,10 +4893,18 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			if (plane->type == DRM_PLANE_TYPE_PRIMARY)
 				drm_crtc_vblank_get(crtc);
 
+			/* Use old throttling in non-vrr fixed refresh rate mode
+			 * to keep flip scheduling based on target vblank counts
+			 * working in a backwards compatible way, e.g., clients
+			 * using GLX_OML_sync_control extension.
+			 */
+			if (!vrr_active)
+				last_flip_vblank = drm_crtc_vblank_count(crtc);
+
 			amdgpu_dm_do_flip(
 				crtc,
 				fb,
-				(uint32_t)drm_crtc_vblank_count(crtc) + *wait_for_vblank,
+				(uint32_t) last_flip_vblank + *wait_for_vblank,
 				dc_state);
 		}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index 9a7ac58eb18e..ddd75a4d8ba5 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -671,6 +671,25 @@ static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __us
 	return bytes_from_user;
 }
 
+/*
+ * Returns the min and max vrr vfreq through the connector's debugfs file.
+ * Example usage: cat /sys/kernel/debug/dri/0/DP-1/vrr_range
+ */
+static int vrr_range_show(struct seq_file *m, void *data)
+{
+	struct drm_connector *connector = m->private;
+	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
+
+	if (connector->status != connector_status_connected)
+		return -ENODEV;
+
+	seq_printf(m, "Min: %u\n", (unsigned int)aconnector->min_vfreq);
+	seq_printf(m, "Max: %u\n", (unsigned int)aconnector->max_vfreq);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(vrr_range);
+
 static const struct file_operations dp_link_settings_debugfs_fops = {
 	.owner = THIS_MODULE,
 	.read = dp_link_settings_read,
@@ -697,7 +716,8 @@ static const struct {
 } dp_debugfs_entries[] = {
 		{"link_settings", &dp_link_settings_debugfs_fops},
 		{"phy_settings", &dp_phy_settings_debugfs_fop},
-		{"test_pattern", &dp_phy_test_pattern_fops}
+		{"test_pattern", &dp_phy_test_pattern_fops},
+		{"vrr_range", &vrr_range_fops}
 };
 
 int connector_debugfs_init(struct amdgpu_dm_connector *connector)
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c
index 19801bdba0d2..7a72ee46f14b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c
@@ -662,6 +662,11 @@ static void dce11_update_clocks(struct clk_mgr *clk_mgr,
 {
 	struct dce_clk_mgr *clk_mgr_dce = TO_DCE_CLK_MGR(clk_mgr);
 	struct dm_pp_power_level_change_request level_change_req;
+	int patched_disp_clk = context->bw.dce.dispclk_khz;
+
+	/*TODO: W/A for dal3 linux, investigate why this works */
+	if (!clk_mgr_dce->dfs_bypass_active)
+		patched_disp_clk = patched_disp_clk * 115 / 100;
 
 	level_change_req.power_level = dce_get_required_clocks_state(clk_mgr, context);
 	/* get max clock state from PPLIB */
@@ -671,9 +676,9 @@ static void dce11_update_clocks(struct clk_mgr *clk_mgr,
 			clk_mgr_dce->cur_min_clks_state = level_change_req.power_level;
 	}
 
-	if (should_set_clock(safe_to_lower, context->bw.dce.dispclk_khz, clk_mgr->clks.dispclk_khz)) {
-		context->bw.dce.dispclk_khz = dce_set_clock(clk_mgr, context->bw.dce.dispclk_khz);
-		clk_mgr->clks.dispclk_khz = context->bw.dce.dispclk_khz;
+	if (should_set_clock(safe_to_lower, patched_disp_clk, clk_mgr->clks.dispclk_khz)) {
+		context->bw.dce.dispclk_khz = dce_set_clock(clk_mgr, patched_disp_clk);
+		clk_mgr->clks.dispclk_khz = patched_disp_clk;
 	}
 	dce11_pplib_apply_display_requirements(clk_mgr->ctx->dc, context);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.h
index acd418515346..a6b80fdaa666 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.h
@@ -37,6 +37,10 @@ void dce100_prepare_bandwidth(
 		struct dc *dc,
 		struct dc_state *context);
 
+void dce100_optimize_bandwidth(
+		struct dc *dc,
+		struct dc_state *context);
+
 bool dce100_enable_display_power_gating(struct dc *dc, uint8_t controller_id,
 					struct dc_bios *dcb,
 					enum pipe_gating_control power_gating);
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.c
index a60a90e68d91..c4543178ba20 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.c
@@ -77,6 +77,6 @@ void dce80_hw_sequencer_construct(struct dc *dc)
 	dc->hwss.enable_display_power_gating = dce100_enable_display_power_gating;
 	dc->hwss.pipe_control_lock = dce_pipe_control_lock;
 	dc->hwss.prepare_bandwidth = dce100_prepare_bandwidth;
-	dc->hwss.optimize_bandwidth = dce100_prepare_bandwidth;
+	dc->hwss.optimize_bandwidth = dce100_optimize_bandwidth;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
index cdd1d6b7b9f2..4e9ea50141bd 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -790,9 +790,22 @@ bool dce80_validate_bandwidth(
 	struct dc *dc,
 	struct dc_state *context)
 {
-	/* TODO implement when needed but for now hardcode max value*/
-	context->bw.dce.dispclk_khz = 681000;
-	context->bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER_CZ;
+	int i;
+	bool at_least_one_pipe = false;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		if (context->res_ctx.pipe_ctx[i].stream)
+			at_least_one_pipe = true;
+	}
+
+	if (at_least_one_pipe) {
+		/* TODO implement when needed but for now hardcode max value*/
+		context->bw.dce.dispclk_khz = 681000;
+		context->bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER_CZ;
+	} else {
+		context->bw.dce.dispclk_khz = 0;
+		context->bw.dce.yclk_khz = 0;
+	}
 
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 58a12ddf12f3..41883c981789 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -2658,8 +2658,8 @@ static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 		.mirror = pipe_ctx->plane_state->horizontal_mirror
 	};
 
-	pos_cpy.x -= pipe_ctx->plane_state->dst_rect.x;
-	pos_cpy.y -= pipe_ctx->plane_state->dst_rect.y;
+	pos_cpy.x_hotspot += pipe_ctx->plane_state->dst_rect.x;
+	pos_cpy.y_hotspot += pipe_ctx->plane_state->dst_rect.y;
 
 	if (pipe_ctx->plane_state->address.type
 			== PLN_ADDR_TYPE_VIDEO_PROGRESSIVE)