From 2a44ae76a6d840acace27c8bf588773215b3c180 Mon Sep 17 00:00:00 2001
From: Dave Stevenson <dave.stevenson@raspberrypi.com>
Date: Thu, 3 Sep 2020 10:00:37 +0200
Subject: drm/vc4: plane: Optimize the LBM allocation size
Git-commit: 5630b27ec577953bde59f0e6414c382f0745387a
Patch-mainline: v5.10-rc1
References: jsc#SLE-15318

The current code is using the maximum of the source line size and the
destination line size to compute the size of the LBM to allocate.

While this is simpler, it starts to be an issue with modes such as 4k with
a quite long that will consume all the available memory, so we no longer
have that luxury.

Signed-off-by: Dave Stevenson <dave.stevenson@raspberrypi.com>
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Link: https://patchwork.freedesktop.org/patch/msgid/b9e091883a4f7395c5b6a4f7c6070225934293db.1599120059.git-series.maxime@cerno.tech
Signed-off-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/vc4/vc4_plane.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index d0771ebd5f75..23916814b4e3 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -437,10 +437,7 @@ static void vc4_write_ppf(struct vc4_plane_state *vc4_state, u32 src, u32 dst)
 static u32 vc4_lbm_size(struct drm_plane_state *state)
 {
 	struct vc4_plane_state *vc4_state = to_vc4_plane_state(state);
-	/* This is the worst case number.  One of the two sizes will
-	 * be used depending on the scaling configuration.
-	 */
-	u32 pix_per_line = max(vc4_state->src_w[0], (u32)vc4_state->crtc_w);
+	u32 pix_per_line;
 	u32 lbm;
 
 	/* LBM is not needed when there's no vertical scaling. */
@@ -448,6 +445,18 @@ static u32 vc4_lbm_size(struct drm_plane_state *state)
 	    vc4_state->y_scaling[1] == VC4_SCALING_NONE)
 		return 0;
 
+	/*
+	 * This can be further optimized in the RGB/YUV444 case if the PPF
+	 * decimation factor is between 0.5 and 1.0 by using crtc_w.
+	 *
+	 * It's not an issue though, since in that case since src_w[0] is going
+	 * to be greater than or equal to crtc_w.
+	 */
+	if (vc4_state->x_scaling[0] == VC4_SCALING_TPZ)
+		pix_per_line = vc4_state->crtc_w;
+	else
+		pix_per_line = vc4_state->src_w[0];
+
 	if (!vc4_state->is_yuv) {
 		if (vc4_state->y_scaling[0] == VC4_SCALING_TPZ)
 			lbm = pix_per_line * 8;
-- 
2.29.2