drm/i915: Move ddb/wm programming into plane update/disable hooks on skl+

On SKL+ the plane WM/BUF_CFG registers are a proper part of each
plane's register set. That means accessing them will cancel any
pending plane update, and we would need a PLANE_SURF register write
to arm the wm/ddb change as well.

To avoid all the problems with that let's just move the wm/ddb
programming into the plane update/disable hooks. Now all plane
registers get written in one (hopefully atomic) operation.

To make that feasible we'll move the plane ddb tracking into
the crtc state. Watermarks were already tracked there.

v2: Rebase due to input CSC
v3: Split out a bunch of junk (Matt)
v4: Add skl_wm_add_affected_planes() to deal with
    cursor special case and non-zero wm register reset value
v5: Drop the unrelated for_each_intel_plane_mask() fix (Matt)
    Remove the redundant ddb memset() (Matt)

Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> #v3
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181127165900.31298-1-ville.syrjala@linux.intel.com

drivers/gpu/drm/i915/i915_debugfs.c

@@ -3441,31 +3441,32 @@ static int i915_ddb_info(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct drm_device *dev = &dev_priv->drm;
-	struct skl_ddb_allocation *ddb;
 	struct skl_ddb_entry *entry;
-	enum pipe pipe;
-	int plane;
+	struct intel_crtc *crtc;
 
 	if (INTEL_GEN(dev_priv) < 9)
 		return -ENODEV;
 
 	drm_modeset_lock_all(dev);
 
-	ddb = &dev_priv->wm.skl_hw.ddb;
-
 	seq_printf(m, "%-15s%8s%8s%8s\n", "", "Start", "End", "Size");
 
-	for_each_pipe(dev_priv, pipe) {
+	for_each_intel_crtc(&dev_priv->drm, crtc) {
+		struct intel_crtc_state *crtc_state =
+			to_intel_crtc_state(crtc->base.state);
+		enum pipe pipe = crtc->pipe;
+		enum plane_id plane_id;
+
 		seq_printf(m, "Pipe %c\n", pipe_name(pipe));
 
-		for_each_universal_plane(dev_priv, pipe, plane) {
-			entry = &ddb->plane[pipe][plane];
-			seq_printf(m, "  Plane%-8d%8u%8u%8u\n", plane + 1,
+		for_each_plane_id_on_crtc(crtc, plane_id) {
+			entry = &crtc_state->wm.skl.plane_ddb_y[plane_id];
+			seq_printf(m, "  Plane%-8d%8u%8u%8u\n", plane_id + 1,
 				   entry->start, entry->end,
 				   skl_ddb_entry_size(entry));
 		}
 
-		entry = &ddb->plane[pipe][PLANE_CURSOR];
+		entry = &crtc_state->wm.skl.plane_ddb_y[PLANE_CURSOR];
 		seq_printf(m, "  %-13s%8u%8u%8u\n", "Cursor", entry->start,
 			   entry->end, skl_ddb_entry_size(entry));
 	}

drivers/gpu/drm/i915/i915_drv.h

@@ -1095,9 +1095,6 @@ static inline bool skl_ddb_entry_equal(const struct skl_ddb_entry *e1,
 }
 
 struct skl_ddb_allocation {
-	/* packed/y */
-	struct skl_ddb_entry plane[I915_MAX_PIPES][I915_MAX_PLANES];
-	struct skl_ddb_entry uv_plane[I915_MAX_PIPES][I915_MAX_PLANES];
 	u8 enabled_slices; /* GEN11 has configurable 2 slices */
 };
 

drivers/gpu/drm/i915/intel_display.c

@@ -10114,6 +10114,10 @@ static void i9xx_update_cursor(struct intel_plane *plane,
 	 * except when the plane is getting enabled at which time
 	 * the CURCNTR write arms the update.
 	 */
+
+	if (INTEL_GEN(dev_priv) >= 9)
+		skl_write_cursor_wm(plane, crtc_state);
+
 	if (plane->cursor.base != base ||
 	    plane->cursor.size != fbc_ctl ||
 	    plane->cursor.cntl != cntl) {
@@ -11903,6 +11907,8 @@ static void verify_wm_state(struct drm_crtc *crtc,
 	struct skl_pipe_wm hw_wm, *sw_wm;
 	struct skl_plane_wm *hw_plane_wm, *sw_plane_wm;
 	struct skl_ddb_entry *hw_ddb_entry, *sw_ddb_entry;
+	struct skl_ddb_entry hw_ddb_y[I915_MAX_PLANES];
+	struct skl_ddb_entry hw_ddb_uv[I915_MAX_PLANES];
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	const enum pipe pipe = intel_crtc->pipe;
 	int plane, level, max_level = ilk_wm_max_level(dev_priv);
@@ -11913,6 +11919,8 @@ static void verify_wm_state(struct drm_crtc *crtc,
 	skl_pipe_wm_get_hw_state(crtc, &hw_wm);
 	sw_wm = &to_intel_crtc_state(new_state)->wm.skl.optimal;
 
+	skl_pipe_ddb_get_hw_state(intel_crtc, hw_ddb_y, hw_ddb_uv);
+
 	skl_ddb_get_hw_state(dev_priv, &hw_ddb);
 	sw_ddb = &dev_priv->wm.skl_hw.ddb;
 
@@ -11955,8 +11963,8 @@ static void verify_wm_state(struct drm_crtc *crtc,
 		}
 
 		/* DDB */
-		hw_ddb_entry = &hw_ddb.plane[pipe][plane];
-		sw_ddb_entry = &sw_ddb->plane[pipe][plane];
+		hw_ddb_entry = &hw_ddb_y[plane];
+		sw_ddb_entry = &to_intel_crtc_state(new_state)->wm.skl.plane_ddb_y[plane];
 
 		if (!skl_ddb_entry_equal(hw_ddb_entry, sw_ddb_entry)) {
 			DRM_ERROR("mismatch in DDB state pipe %c plane %d (expected (%u,%u), found (%u,%u))\n",
@@ -12005,8 +12013,8 @@ static void verify_wm_state(struct drm_crtc *crtc,
 		}
 
 		/* DDB */
-		hw_ddb_entry = &hw_ddb.plane[pipe][PLANE_CURSOR];
-		sw_ddb_entry = &sw_ddb->plane[pipe][PLANE_CURSOR];
+		hw_ddb_entry = &hw_ddb_y[PLANE_CURSOR];
+		sw_ddb_entry = &to_intel_crtc_state(new_state)->wm.skl.plane_ddb_y[PLANE_CURSOR];
 
 		if (!skl_ddb_entry_equal(hw_ddb_entry, sw_ddb_entry)) {
 			DRM_ERROR("mismatch in DDB state pipe %c cursor (expected (%u,%u), found (%u,%u))\n",

drivers/gpu/drm/i915/intel_display.h

@@ -431,6 +431,15 @@ struct intel_link_m_n {
 	     (__i)++) \
 		for_each_if(plane)
 
+#define for_each_oldnew_intel_crtc_in_state(__state, crtc, old_crtc_state, new_crtc_state, __i) \
+	for ((__i) = 0; \
+	     (__i) < (__state)->base.dev->mode_config.num_crtc && \
+		     ((crtc) = to_intel_crtc((__state)->base.crtcs[__i].ptr), \
+		      (old_crtc_state) = to_intel_crtc_state((__state)->base.crtcs[__i].old_state), \
+		      (new_crtc_state) = to_intel_crtc_state((__state)->base.crtcs[__i].new_state), 1); \
+	     (__i)++) \
+		for_each_if(crtc)
+
 void intel_link_compute_m_n(int bpp, int nlanes,
 			    int pixel_clock, int link_clock,
 			    struct intel_link_m_n *m_n,

drivers/gpu/drm/i915/intel_drv.h

@@ -706,6 +706,8 @@ struct intel_crtc_wm_state {
 			/* gen9+ only needs 1-step wm programming */
 			struct skl_pipe_wm optimal;
 			struct skl_ddb_entry ddb;
+			struct skl_ddb_entry plane_ddb_y[I915_MAX_PLANES];
+			struct skl_ddb_entry plane_ddb_uv[I915_MAX_PLANES];
 		} skl;
 
 		struct {
@@ -2185,6 +2187,9 @@ void g4x_wm_get_hw_state(struct drm_device *dev);
 void vlv_wm_get_hw_state(struct drm_device *dev);
 void ilk_wm_get_hw_state(struct drm_device *dev);
 void skl_wm_get_hw_state(struct drm_device *dev);
+void skl_pipe_ddb_get_hw_state(struct intel_crtc *crtc,
+			       struct skl_ddb_entry *ddb_y,
+			       struct skl_ddb_entry *ddb_uv);
 void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
 			  struct skl_ddb_allocation *ddb /* out */);
 void skl_pipe_wm_get_hw_state(struct drm_crtc *crtc,
@@ -2199,6 +2204,10 @@ bool skl_wm_level_equals(const struct skl_wm_level *l1,
 bool skl_ddb_allocation_overlaps(const struct skl_ddb_entry *ddb,
 				 const struct skl_ddb_entry entries[],
 				 int num_entries, int ignore_idx);
+void skl_write_plane_wm(struct intel_plane *plane,
+			const struct intel_crtc_state *crtc_state);
+void skl_write_cursor_wm(struct intel_plane *plane,
+			 const struct intel_crtc_state *crtc_state);
 bool ilk_disable_lp_wm(struct drm_device *dev);
 int skl_check_pipe_max_pixel_rate(struct intel_crtc *intel_crtc,
 				  struct intel_crtc_state *cstate);

drivers/gpu/drm/i915/intel_sprite.c

@@ -542,6 +542,8 @@ skl_program_plane(struct intel_plane *plane,
 	if (fb->format->is_yuv && icl_is_hdr_plane(plane))
 		icl_program_input_csc_coeff(crtc_state, plane_state);
 
+	skl_write_plane_wm(plane, crtc_state);
+
 	I915_WRITE_FW(PLANE_KEYVAL(pipe, plane_id), key->min_value);
 	I915_WRITE_FW(PLANE_KEYMSK(pipe, plane_id), keymsk);
 	I915_WRITE_FW(PLANE_KEYMAX(pipe, plane_id), keymax);
@@ -604,6 +606,8 @@ skl_disable_plane(struct intel_plane *plane,
 
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
 
+	skl_write_plane_wm(plane, crtc_state);
+
 	I915_WRITE_FW(PLANE_CTL(pipe, plane_id), 0);
 	I915_WRITE_FW(PLANE_SURF(pipe, plane_id), 0);