Merge v5.0 into drm-next

There is a really hairy resolution involving amdgpu fixes, that I'd rather confirm here.

Also some misc fixes are landed by me, but the pr has them as well.

Signed-off-by: Dave Airlie <airlied@redhat.com>

14 files changed, 63 insertions, 21 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index b65e18101108..e860412043bb 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 698fd8a2f775..889e443eeee7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -406,6 +406,7 @@ 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_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 942b5ebc6dc2..ead851413c0a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -652,12 +652,14 @@ 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/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 127b85983e8f..c816e55d43a9 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 c87fcda61b66..0642dfe22582 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);
 
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 bbe051736a18..6e142c2db986 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
@@ -696,6 +696,11 @@ 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 */
@@ -705,9 +710,9 @@ 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 2eca81b5cf2f..c109ace96be9 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -792,9 +792,22 @@ 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 8ba895c4b445..d1a8f1c302a9 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
@@ -2693,8 +2693,8 @@ 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)
diff --git a/drivers/gpu/drm/bochs/bochs_drv.c b/drivers/gpu/drm/bochs/bochs_drv.c
index cb55bdc36f3f..6b6e037258c3 100644
--- a/drivers/gpu/drm/bochs/bochs_drv.c
+++ b/drivers/gpu/drm/bochs/bochs_drv.c
@@ -145,6 +145,10 @@ static int bochs_pci_probe(struct pci_dev *pdev,
 	if (IS_ERR(dev))
 		return PTR_ERR(dev);
 
+	ret = pci_enable_device(pdev);
+	if (ret)
+		goto err_free_dev;
+
 	dev->pdev = pdev;
 	pci_set_drvdata(pdev, dev);
 
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index c53ecbd9abdd..540a77a2ade9 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1608,6 +1608,15 @@ int drm_atomic_helper_async_check(struct drm_device *dev,
 	    old_plane_state->crtc != new_plane_state->crtc)
 		return -EINVAL;
 
+	/*
+	 * FIXME: Since prepare_fb and cleanup_fb are always called on
+	 * the new_plane_state for async updates we need to block framebuffer
+	 * changes. This prevents use of a fb that's been cleaned up and
+	 * double cleanups from occuring.
+	 */
+	if (old_plane_state->fb != new_plane_state->fb)
+		return -EINVAL;
+
 	funcs = plane->helper_private;
 	if (!funcs->atomic_async_update)
 		return -EINVAL;
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index 376ffe842e26..e8f694b57b8a 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -338,8 +338,8 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 				    bool *enabled, int width, int height)
 {
 	struct drm_i915_private *dev_priv = to_i915(fb_helper->dev);
-	unsigned long conn_configured, conn_seq, mask;
 	unsigned int count = min(fb_helper->connector_count, BITS_PER_LONG);
+	unsigned long conn_configured, conn_seq;
 	int i, j;
 	bool *save_enabled;
 	bool fallback = true, ret = true;
@@ -357,10 +357,9 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 		drm_modeset_backoff(&ctx);
 
 	memcpy(save_enabled, enabled, count);
-	mask = GENMASK(count - 1, 0);
+	conn_seq = GENMASK(count - 1, 0);
 	conn_configured = 0;
 retry:
-	conn_seq = conn_configured;
 	for (i = 0; i < count; i++) {
 		struct drm_fb_helper_connector *fb_conn;
 		struct drm_connector *connector;
@@ -373,7 +372,8 @@ retry:
 		if (conn_configured & BIT(i))
 			continue;
 
-		if (conn_seq == 0 && !connector->has_tile)
+		/* First pass, only consider tiled connectors */
+		if (conn_seq == GENMASK(count - 1, 0) && !connector->has_tile)
 			continue;
 
 		if (connector->status == connector_status_connected)
@@ -477,8 +477,10 @@ retry:
 		conn_configured |= BIT(i);
 	}
 
-	if ((conn_configured & mask) != mask && conn_configured != conn_seq)
+	if (conn_configured != conn_seq) { /* repeat until no more are found */
+		conn_seq = conn_configured;
 		goto retry;
+	}
 
 	/*
 	 * If the BIOS didn't enable everything it could, fall back to have the
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index dec1e081f529..6a8fb6fd183c 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -172,6 +172,7 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags)
 	}
 
 	if (radeon_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);