[Intel-gfx] [PATCH 07/13] drm/i915: Tweak plane ddb allocation tracking

[Ville Syrjala <ville.syrjala@linux.intel.com>]

From: Ville Syrjälä <ville.syrjala@linux.intel.com>

Let's store the plane allocation in a manner which more closely
matches how the hw operates. That is, we store the packed/CbCr
ddb in one struct, and the Y ddb in another. Currently we're
storing packed/Y in one struct, CbCr in the other.

This also works pretty well for icl+ where the UV plane is
the main plane and the Y plane is subservient to it. Although
in this case we do not even use ddb_y as we do the ddb allocation
in terms of hw planes.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
 .../gpu/drm/i915/display/intel_atomic_plane.c | 32 +++---
 drivers/gpu/drm/i915/display/intel_bw.c       |  6 +-
 drivers/gpu/drm/i915/display/intel_display.c  | 12 +--
 .../drm/i915/display/intel_display_debugfs.c  |  4 +-
 .../drm/i915/display/intel_display_types.h    |  7 +-
 drivers/gpu/drm/i915/intel_pm.c               | 97 ++++++++-----------
 6 files changed, 71 insertions(+), 87 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
index 7e9f84b00859..eaa1e83b6fdd 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
@@ -399,8 +399,8 @@ int intel_plane_atomic_check(struct intel_atomic_state *state,
 static struct intel_plane *
 skl_next_plane_to_commit(struct intel_atomic_state *state,
 			 struct intel_crtc *crtc,
-			 struct skl_ddb_entry entries_y[I915_MAX_PLANES],
-			 struct skl_ddb_entry entries_uv[I915_MAX_PLANES],
+			 struct skl_ddb_entry ddb[I915_MAX_PLANES],
+			 struct skl_ddb_entry ddb_y[I915_MAX_PLANES],
 			 unsigned int *update_mask)
 {
 	struct intel_crtc_state *crtc_state =
@@ -419,17 +419,15 @@ skl_next_plane_to_commit(struct intel_atomic_state *state,
 		    !(*update_mask & BIT(plane_id)))
 			continue;
 
-		if (skl_ddb_allocation_overlaps(&crtc_state->wm.skl.plane_ddb_y[plane_id],
-						entries_y,
-						I915_MAX_PLANES, plane_id) ||
-		    skl_ddb_allocation_overlaps(&crtc_state->wm.skl.plane_ddb_uv[plane_id],
-						entries_uv,
-						I915_MAX_PLANES, plane_id))
+		if (skl_ddb_allocation_overlaps(&crtc_state->wm.skl.plane_ddb[plane_id],
+						ddb, I915_MAX_PLANES, plane_id) ||
+		    skl_ddb_allocation_overlaps(&crtc_state->wm.skl.plane_ddb_y[plane_id],
+						ddb_y, I915_MAX_PLANES, plane_id))
 			continue;
 
 		*update_mask &= ~BIT(plane_id);
-		entries_y[plane_id] = crtc_state->wm.skl.plane_ddb_y[plane_id];
-		entries_uv[plane_id] = crtc_state->wm.skl.plane_ddb_uv[plane_id];
+		ddb[plane_id] = crtc_state->wm.skl.plane_ddb[plane_id];
+		ddb_y[plane_id] = crtc_state->wm.skl.plane_ddb_y[plane_id];
 
 		return plane;
 	}
@@ -470,19 +468,17 @@ void skl_update_planes_on_crtc(struct intel_atomic_state *state,
 		intel_atomic_get_old_crtc_state(state, crtc);
 	struct intel_crtc_state *new_crtc_state =
 		intel_atomic_get_new_crtc_state(state, crtc);
-	struct skl_ddb_entry entries_y[I915_MAX_PLANES];
-	struct skl_ddb_entry entries_uv[I915_MAX_PLANES];
+	struct skl_ddb_entry ddb[I915_MAX_PLANES];
+	struct skl_ddb_entry ddb_y[I915_MAX_PLANES];
 	u32 update_mask = new_crtc_state->update_planes;
 	struct intel_plane *plane;
 
-	memcpy(entries_y, old_crtc_state->wm.skl.plane_ddb_y,
+	memcpy(ddb, old_crtc_state->wm.skl.plane_ddb,
+	       sizeof(old_crtc_state->wm.skl.plane_ddb));
+	memcpy(ddb_y, old_crtc_state->wm.skl.plane_ddb_y,
 	       sizeof(old_crtc_state->wm.skl.plane_ddb_y));
-	memcpy(entries_uv, old_crtc_state->wm.skl.plane_ddb_uv,
-	       sizeof(old_crtc_state->wm.skl.plane_ddb_uv));
 
-	while ((plane = skl_next_plane_to_commit(state, crtc,
-						 entries_y, entries_uv,
-						 &update_mask))) {
+	while ((plane = skl_next_plane_to_commit(state, crtc, ddb, ddb_y, &update_mask))) {
 		struct intel_plane_state *new_plane_state =
 			intel_atomic_get_new_plane_state(state, plane);
 
diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c
index f6de0b9bca90..a33a8a2784e9 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.c
+++ b/drivers/gpu/drm/i915/display/intel_bw.c
@@ -442,16 +442,16 @@ static void skl_crtc_calc_dbuf_bw(struct intel_bw_state *bw_state,
 		return;
 
 	for_each_plane_id_on_crtc(crtc, plane_id) {
+		const struct skl_ddb_entry *ddb =
+			&crtc_state->wm.skl.plane_ddb[plane_id];
 		const struct skl_ddb_entry *ddb_y =
 			&crtc_state->wm.skl.plane_ddb_y[plane_id];
-		const struct skl_ddb_entry *ddb_uv =
-			&crtc_state->wm.skl.plane_ddb_uv[plane_id];
 		unsigned int data_rate = crtc_state->data_rate[plane_id];
 		unsigned int dbuf_mask = 0;
 		int slice_id;
 
+		dbuf_mask |= skl_ddb_dbuf_slice_mask(i915, ddb);
 		dbuf_mask |= skl_ddb_dbuf_slice_mask(i915, ddb_y);
-		dbuf_mask |= skl_ddb_dbuf_slice_mask(i915, ddb_uv);
 
 		/*
 		 * FIXME: To calculate that more properly we probably
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 5c07c74d4397..09f74e87a303 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -14460,8 +14460,8 @@ static void verify_wm_state(struct intel_crtc *crtc,
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct skl_hw_state {
+		struct skl_ddb_entry ddb[I915_MAX_PLANES];
 		struct skl_ddb_entry ddb_y[I915_MAX_PLANES];
-		struct skl_ddb_entry ddb_uv[I915_MAX_PLANES];
 		struct skl_pipe_wm wm;
 	} *hw;
 	struct skl_pipe_wm *sw_wm;
@@ -14480,7 +14480,7 @@ static void verify_wm_state(struct intel_crtc *crtc,
 	skl_pipe_wm_get_hw_state(crtc, &hw->wm);
 	sw_wm = &new_crtc_state->wm.skl.optimal;
 
-	skl_pipe_ddb_get_hw_state(crtc, hw->ddb_y, hw->ddb_uv);
+	skl_pipe_ddb_get_hw_state(crtc, hw->ddb, hw->ddb_y);
 
 	hw_enabled_slices = intel_enabled_dbuf_slices_mask(dev_priv);
 
@@ -14531,8 +14531,8 @@ static void verify_wm_state(struct intel_crtc *crtc,
 		}
 
 		/* DDB */
-		hw_ddb_entry = &hw->ddb_y[plane];
-		sw_ddb_entry = &new_crtc_state->wm.skl.plane_ddb_y[plane];
+		hw_ddb_entry = &hw->ddb[plane];
+		sw_ddb_entry = &new_crtc_state->wm.skl.plane_ddb[plane];
 
 		if (!skl_ddb_entry_equal(hw_ddb_entry, sw_ddb_entry)) {
 			drm_err(&dev_priv->drm,
@@ -14588,8 +14588,8 @@ static void verify_wm_state(struct intel_crtc *crtc,
 		}
 
 		/* DDB */
-		hw_ddb_entry = &hw->ddb_y[PLANE_CURSOR];
-		sw_ddb_entry = &new_crtc_state->wm.skl.plane_ddb_y[PLANE_CURSOR];
+		hw_ddb_entry = &hw->ddb[PLANE_CURSOR];
+		sw_ddb_entry = &new_crtc_state->wm.skl.plane_ddb[PLANE_CURSOR];
 
 		if (!skl_ddb_entry_equal(hw_ddb_entry, sw_ddb_entry)) {
 			drm_err(&dev_priv->drm,
diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
index ca41e8c00ad7..42e9179f2e02 100644
--- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c
+++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
@@ -1072,13 +1072,13 @@ static int i915_ddb_info(struct seq_file *m, void *unused)
 		seq_printf(m, "Pipe %c\n", pipe_name(pipe));
 
 		for_each_plane_id_on_crtc(crtc, plane_id) {
-			entry = &crtc_state->wm.skl.plane_ddb_y[plane_id];
+			entry = &crtc_state->wm.skl.plane_ddb[plane_id];
 			seq_printf(m, "  Plane%-8d%8u%8u%8u\n", plane_id + 1,
 				   entry->start, entry->end,
 				   skl_ddb_entry_size(entry));
 		}
 
-		entry = &crtc_state->wm.skl.plane_ddb_y[PLANE_CURSOR];
+		entry = &crtc_state->wm.skl.plane_ddb[PLANE_CURSOR];
 		seq_printf(m, "  %-13s%8u%8u%8u\n", "Cursor", entry->start,
 			   entry->end, skl_ddb_entry_size(entry));
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index ce82d654d0f2..2f0738646cfd 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -770,8 +770,13 @@ struct intel_crtc_wm_state {
 			/* gen9+ only needs 1-step wm programming */
 			struct skl_pipe_wm optimal;
 			struct skl_ddb_entry ddb;
+			/*
+			 * pre-icl: for packed/planar CbCr
+			 * icl+: for everything
+			 */
+			struct skl_ddb_entry plane_ddb[I915_MAX_PLANES];
+			/* pre-icl: for planar Y */
 			struct skl_ddb_entry plane_ddb_y[I915_MAX_PLANES];
-			struct skl_ddb_entry plane_ddb_uv[I915_MAX_PLANES];
 		} skl;
 
 		struct {
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index c2851bb1975d..5608ae5dc977 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3921,7 +3921,7 @@ static bool tgl_crtc_can_enable_sagv(const struct intel_crtc_state *crtc_state)
 
 	for_each_plane_id_on_crtc(crtc, plane_id) {
 		const struct skl_ddb_entry *plane_alloc =
-			&crtc_state->wm.skl.plane_ddb_y[plane_id];
+			&crtc_state->wm.skl.plane_ddb[plane_id];
 		const struct skl_plane_wm *wm =
 			&crtc_state->wm.skl.optimal.planes[plane_id];
 
@@ -4296,46 +4296,31 @@ static void
 skl_ddb_get_hw_plane_state(struct drm_i915_private *dev_priv,
 			   const enum pipe pipe,
 			   const enum plane_id plane_id,
-			   struct skl_ddb_entry *ddb_y,
-			   struct skl_ddb_entry *ddb_uv)
+			   struct skl_ddb_entry *ddb,
+			   struct skl_ddb_entry *ddb_y)
 {
-	u32 val, val2;
-	u32 fourcc = 0;
+	u32 val;
 
 	/* Cursor doesn't support NV12/planar, so no extra calculation needed */
 	if (plane_id == PLANE_CURSOR) {
 		val = I915_READ(CUR_BUF_CFG(pipe));
-		skl_ddb_entry_init_from_hw(ddb_y, val);
+		skl_ddb_entry_init_from_hw(ddb, val);
 		return;
 	}
 
-	val = I915_READ(PLANE_CTL(pipe, plane_id));
+	val = I915_READ(PLANE_BUF_CFG(pipe, plane_id));
+	skl_ddb_entry_init_from_hw(ddb, val);
 
-	/* No DDB allocated for disabled planes */
-	if (val & PLANE_CTL_ENABLE)
-		fourcc = skl_format_to_fourcc(val & PLANE_CTL_FORMAT_MASK,
-					      val & PLANE_CTL_ORDER_RGBX,
-					      val & PLANE_CTL_ALPHA_MASK);
-
-	if (INTEL_GEN(dev_priv) >= 11) {
-		val = I915_READ(PLANE_BUF_CFG(pipe, plane_id));
-		skl_ddb_entry_init_from_hw(ddb_y, val);
-	} else {
-		val = I915_READ(PLANE_BUF_CFG(pipe, plane_id));
-		val2 = I915_READ(PLANE_NV12_BUF_CFG(pipe, plane_id));
-
-		if (fourcc &&
-		    drm_format_info_is_yuv_semiplanar(drm_format_info(fourcc)))
-			swap(val, val2);
+	if (INTEL_GEN(dev_priv) >= 11)
+		return;
 
-		skl_ddb_entry_init_from_hw(ddb_y, val);
-		skl_ddb_entry_init_from_hw(ddb_uv, val2);
-	}
+	val = I915_READ(PLANE_NV12_BUF_CFG(pipe, plane_id));
+	skl_ddb_entry_init_from_hw(ddb_y, val);
 }
 
 void skl_pipe_ddb_get_hw_state(struct intel_crtc *crtc,
-			       struct skl_ddb_entry *ddb_y,
-			       struct skl_ddb_entry *ddb_uv)
+			       struct skl_ddb_entry *ddb,
+			       struct skl_ddb_entry *ddb_y)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum intel_display_power_domain power_domain;
@@ -4351,8 +4336,8 @@ void skl_pipe_ddb_get_hw_state(struct intel_crtc *crtc,
 	for_each_plane_id_on_crtc(crtc, plane_id)
 		skl_ddb_get_hw_plane_state(dev_priv, pipe,
 					   plane_id,
-					   &ddb_y[plane_id],
-					   &ddb_uv[plane_id]);
+					   &ddb[plane_id],
+					   &ddb_y[plane_id]);
 
 	intel_display_power_put(dev_priv, power_domain, wakeref);
 }
@@ -4839,8 +4824,8 @@ skl_allocate_pipe_ddb(struct intel_atomic_state *state,
 	int ret;
 
 	/* Clear the partitioning for disabled planes. */
+	memset(crtc_state->wm.skl.plane_ddb, 0, sizeof(crtc_state->wm.skl.plane_ddb));
 	memset(crtc_state->wm.skl.plane_ddb_y, 0, sizeof(crtc_state->wm.skl.plane_ddb_y));
-	memset(crtc_state->wm.skl.plane_ddb_uv, 0, sizeof(crtc_state->wm.skl.plane_ddb_uv));
 
 	if (!crtc_state->hw.active) {
 		struct intel_atomic_state *state =
@@ -4889,7 +4874,7 @@ skl_allocate_pipe_ddb(struct intel_atomic_state *state,
 	/* Allocate fixed number of blocks for cursor. */
 	iter.total[PLANE_CURSOR] = skl_cursor_allocation(crtc_state, num_active);
 	iter.size -= iter.total[PLANE_CURSOR];
-	skl_ddb_entry_init(&crtc_state->wm.skl.plane_ddb_y[PLANE_CURSOR],
+	skl_ddb_entry_init(&crtc_state->wm.skl.plane_ddb[PLANE_CURSOR],
 			   alloc->end - iter.total[PLANE_CURSOR], alloc->end);
 
 	if (iter.data_rate == 0)
@@ -4968,10 +4953,10 @@ skl_allocate_pipe_ddb(struct intel_atomic_state *state,
 	/* Set the actual DDB start/end points for each plane */
 	iter.start = alloc->start;
 	for_each_plane_id_on_crtc(crtc, plane_id) {
-		struct skl_ddb_entry *plane_alloc =
+		struct skl_ddb_entry *ddb =
+			&crtc_state->wm.skl.plane_ddb[plane_id];
+		struct skl_ddb_entry *ddb_y =
 			&crtc_state->wm.skl.plane_ddb_y[plane_id];
-		struct skl_ddb_entry *uv_plane_alloc =
-			&crtc_state->wm.skl.plane_ddb_uv[plane_id];
 
 		if (plane_id == PLANE_CURSOR)
 			continue;
@@ -4982,12 +4967,15 @@ skl_allocate_pipe_ddb(struct intel_atomic_state *state,
 
 		/* Leave disabled planes at (0,0) */
 		if (iter.total[plane_id])
-			iter.start = skl_ddb_entry_init(plane_alloc, iter.start,
+			iter.start = skl_ddb_entry_init(ddb, iter.start,
 							iter.start + iter.total[plane_id]);
 
-		if (iter.uv_total[plane_id])
-			iter.start = skl_ddb_entry_init(uv_plane_alloc, iter.start,
+		if (iter.uv_total[plane_id]) {
+			/* hardware wants these swapped */
+			*ddb_y = *ddb;
+			iter.start = skl_ddb_entry_init(ddb, iter.start,
 							iter.start + iter.uv_total[plane_id]);
+		}
 	}
 
 	/*
@@ -5647,10 +5635,10 @@ void skl_write_plane_wm(struct intel_plane *plane,
 	enum pipe pipe = plane->pipe;
 	const struct skl_plane_wm *wm =
 		&crtc_state->wm.skl.optimal.planes[plane_id];
+	const struct skl_ddb_entry *ddb =
+		&crtc_state->wm.skl.plane_ddb[plane_id];
 	const struct skl_ddb_entry *ddb_y =
 		&crtc_state->wm.skl.plane_ddb_y[plane_id];
-	const struct skl_ddb_entry *ddb_uv =
-		&crtc_state->wm.skl.plane_ddb_uv[plane_id];
 
 	for (level = 0; level <= max_level; level++) {
 		const struct skl_wm_level *wm_level;
@@ -5663,19 +5651,14 @@ void skl_write_plane_wm(struct intel_plane *plane,
 	skl_write_wm_level(dev_priv, PLANE_WM_TRANS(pipe, plane_id),
 			   &wm->trans_wm);
 
-	if (INTEL_GEN(dev_priv) >= 11) {
-		skl_ddb_entry_write(dev_priv,
-				    PLANE_BUF_CFG(pipe, plane_id), ddb_y);
+	skl_ddb_entry_write(dev_priv,
+			    PLANE_BUF_CFG(pipe, plane_id), ddb);
+
+	if (INTEL_GEN(dev_priv) >= 11)
 		return;
-	}
 
-	if (wm->is_planar)
-		swap(ddb_y, ddb_uv);
-
-	skl_ddb_entry_write(dev_priv,
-			    PLANE_BUF_CFG(pipe, plane_id), ddb_y);
 	skl_ddb_entry_write(dev_priv,
-			    PLANE_NV12_BUF_CFG(pipe, plane_id), ddb_uv);
+			    PLANE_NV12_BUF_CFG(pipe, plane_id), ddb_y);
 }
 
 void skl_write_cursor_wm(struct intel_plane *plane,
@@ -5688,7 +5671,7 @@ void skl_write_cursor_wm(struct intel_plane *plane,
 	const struct skl_plane_wm *wm =
 		&crtc_state->wm.skl.optimal.planes[plane_id];
 	const struct skl_ddb_entry *ddb =
-		&crtc_state->wm.skl.plane_ddb_y[plane_id];
+		&crtc_state->wm.skl.plane_ddb[plane_id];
 
 	for (level = 0; level <= max_level; level++) {
 		const struct skl_wm_level *wm_level;
@@ -5765,10 +5748,10 @@ skl_ddb_add_affected_planes(const struct intel_crtc_state *old_crtc_state,
 		struct intel_plane_state *plane_state;
 		enum plane_id plane_id = plane->id;
 
-		if (skl_ddb_entry_equal(&old_crtc_state->wm.skl.plane_ddb_y[plane_id],
-					&new_crtc_state->wm.skl.plane_ddb_y[plane_id]) &&
-		    skl_ddb_entry_equal(&old_crtc_state->wm.skl.plane_ddb_uv[plane_id],
-					&new_crtc_state->wm.skl.plane_ddb_uv[plane_id]))
+		if (skl_ddb_entry_equal(&old_crtc_state->wm.skl.plane_ddb[plane_id],
+					&new_crtc_state->wm.skl.plane_ddb[plane_id]) &&
+		    skl_ddb_entry_equal(&old_crtc_state->wm.skl.plane_ddb_y[plane_id],
+					&new_crtc_state->wm.skl.plane_ddb_y[plane_id]))
 			continue;
 
 		plane_state = intel_atomic_get_plane_state(state, plane);
@@ -5847,8 +5830,8 @@ skl_print_wm_changes(struct intel_atomic_state *state)
 			enum plane_id plane_id = plane->id;
 			const struct skl_ddb_entry *old, *new;
 
-			old = &old_crtc_state->wm.skl.plane_ddb_y[plane_id];
-			new = &new_crtc_state->wm.skl.plane_ddb_y[plane_id];
+			old = &old_crtc_state->wm.skl.plane_ddb[plane_id];
+			new = &new_crtc_state->wm.skl.plane_ddb[plane_id];
 
 			if (skl_ddb_entry_equal(old, new))
 				continue;
-- 
2.26.2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx