From 84f6193e860c6b2f59e123151d1be7bd53c70070 Mon Sep 17 00:00:00 2001
From: Aurabindo Pillai <aurabindo.pillai@amd.com>
Date: Fri, 15 Jul 2022 14:59:26 -0400
Subject: drm/amd/display: fix CAB allocation for multiple displays
Git-commit: 2de09ce41f484cbcc65e518905dae73da67ad35c
Patch-mainline: v6.0-rc2
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225 jsc#PED-2849

[Why & How]
When multiple displays are used, the underlying framebuffers could be
two separate framebuffers, or a single large framebuffer. Fix the
calculation logic for CAB to account for large framebuffer. Current
logic assumes that any FB that the plane points to are independent. When
a single FB is used on the system, this does 2 times allocation.

Add a check to prevent duplicate allocation by checking if the base
addresses are the same, and then ensuring that the if we allocate using
the pitch, whole of the other fbs will be accounted for in the first
allocation.

Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Acked-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
index d38341f68b17..5ba503d80728 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
@@ -250,6 +250,7 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c
 	uint32_t total_lines = 0;
 	uint32_t lines_per_way = 0;
 	uint32_t num_ways = 0;
+	uint32_t prev_addr_low = 0;
 
 	for (i = 0; i < ctx->stream_count; i++) {
 		stream = ctx->streams[i];
@@ -267,10 +268,20 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c
 			plane = ctx->stream_status[i].plane_states[j];
 
 			// Calculate total surface size
-			surface_size = plane->plane_size.surface_pitch *
+			if (prev_addr_low != plane->address.grph.addr.u.low_part) {
+				/* if plane address are different from prev FB, then userspace allocated separate FBs*/
+				surface_size += plane->plane_size.surface_pitch *
 					plane->plane_size.surface_size.height *
 					(plane->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4);
 
+				prev_addr_low = plane->address.grph.addr.u.low_part;
+			} else {
+				/* We have the same fb for all the planes.
+				 * Xorg always creates one giant fb that holds all surfaces,
+				 * so allocating it once is sufficient.
+				 * */
+				continue;
+			}
 			// Convert surface size + starting address to number of cache lines required
 			// (alignment accounted for)
 			cache_lines_used += dcn32_cache_lines_for_surface(dc, surface_size,
-- 
2.38.1