[PATCH 11/32] drm/amd/display: Add 16 lines margin for SubVP

[Tom Chung]

From: Alvin Lee <alvin.lee2 at amd.com>

[Description]
SUBVP_START_LINE must be aligned to 2 swaths, so add
16 lines of margin so the start line can be adjusted by
up to 16 lines for alignment purposes in FW.

Reviewed-by: Jun Lei <Jun.Lei at amd.com>
Reviewed-by: Jun Lei <Jun.Lei at amd.com>
Acked-by: Tom Chung <chiahsuan.chung at amd.com>
Signed-off-by: Alvin Lee <alvin.lee2 at amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h                     | 1 +
 drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c            | 4 ++--
 drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c       | 2 +-
 drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c   | 1 +
 drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c | 1 +
 drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c    | 5 ++++-
 6 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index d73e68c2fd51..f2accacae85b 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -213,6 +213,7 @@ struct dc_caps {
 	uint32_t cache_num_ways;
 	uint16_t subvp_fw_processing_delay_us;
 	uint16_t subvp_prefetch_end_to_mall_start_us;
+	uint8_t subvp_swath_height_margin_lines; // subvp start line must be aligned to 2 x swath height	
 	uint16_t subvp_pstate_allow_width_us;
 	uint16_t subvp_vertical_int_margin_us;
 	bool seamless_odm;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
index ffa1c0148330..759d54843eff 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -275,8 +275,7 @@ void dc_dmub_srv_set_drr_manual_trigger_cmd(struct dc *dc, uint32_t tg_inst)
 	union dmub_rb_cmd cmd = { 0 };
 
 	cmd.drr_update.header.type = DMUB_CMD__FW_ASSISTED_MCLK_SWITCH;
-	// TODO: Uncomment once FW headers are promoted
-	//cmd.drr_update.header.sub_type = DMUB_CMD__FAMS_SET_MANUAL_TRIGGER;
+	cmd.drr_update.header.sub_type = DMUB_CMD__FAMS_SET_MANUAL_TRIGGER;
 	cmd.drr_update.dmub_optc_state_req.tg_inst = tg_inst;
 
 	cmd.drr_update.header.payload_bytes = sizeof(cmd.drr_update) - sizeof(cmd.drr_update.header);
@@ -611,6 +610,7 @@ static void populate_subvp_cmd_pipe_info(struct dc *dc,
 			main_timing->v_total - main_timing->v_front_porch - main_timing->v_addressable;
 	pipe_data->pipe_config.subvp_data.mall_region_lines = phantom_timing->v_addressable;
 	pipe_data->pipe_config.subvp_data.main_pipe_index = subvp_pipe->pipe_idx;
+	pipe_data->pipe_config.subvp_data.is_drr = subvp_pipe->stream->ignore_msa_timing_param;	
 
 	// Prefetch lines is equal to VACTIVE + BP + VSYNC
 	pipe_data->pipe_config.subvp_data.prefetch_lines =
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c
index 992e56c6907e..9861be1dc063 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c
@@ -282,7 +282,7 @@ static struct timing_generator_funcs dcn32_tg_funcs = {
 		.lock_doublebuffer_disable = optc3_lock_doublebuffer_disable,
 		.enable_optc_clock = optc1_enable_optc_clock,
 		.set_vrr_m_const = optc3_set_vrr_m_const,
-		.set_drr = optc31_set_drr, // TODO: Update to optc32_set_drr once FW headers are promoted
+		.set_drr = optc32_set_drr,
 		.get_last_used_drr_vtotal = optc2_get_last_used_drr_vtotal,
 		.set_vtotal_min_max = optc3_set_vtotal_min_max,
 		.set_static_screen_control = optc1_set_static_screen_control,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
index 9a26d24b579f..96076d633273 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
@@ -2051,6 +2051,7 @@ static bool dcn32_resource_construct(
 	dc->caps.max_cab_allocation_bytes = 67108864; // 64MB = 1024 * 1024 * 64
 	dc->caps.subvp_fw_processing_delay_us = 15;
 	dc->caps.subvp_prefetch_end_to_mall_start_us = 15;
+	dc->caps.subvp_swath_height_margin_lines = 16;
 	dc->caps.subvp_pstate_allow_width_us = 20;
 	dc->caps.subvp_vertical_int_margin_us = 30;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
index 8157e40d2c7e..f627b494737a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
@@ -1662,6 +1662,7 @@ static bool dcn321_resource_construct(
 	dc->caps.max_cab_allocation_bytes = 33554432; // 32MB = 1024 * 1024 * 32
 	dc->caps.subvp_fw_processing_delay_us = 15;
 	dc->caps.subvp_prefetch_end_to_mall_start_us = 15;
+	dc->caps.subvp_swath_height_margin_lines = 16;
 	dc->caps.subvp_pstate_allow_width_us = 20;
 
 	dc->caps.max_slave_planes = 1;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index f8023cfe79f8..988e28a8e90e 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -473,8 +473,11 @@ void dcn32_set_phantom_stream_timing(struct dc *dc,
 
 	// DML calculation for MALL region doesn't take into account FW delay
 	// and required pstate allow width for multi-display cases
+	/* Add 16 lines margin to the MALL REGION because SUB_VP_START_LINE must be aligned
+	 * to 2 swaths (i.e. 16 lines)
+	 */
 	phantom_vactive = get_subviewport_lines_needed_in_mall(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx) +
-				pstate_width_fw_delay_lines;
+				pstate_width_fw_delay_lines + dc->caps.subvp_swath_height_margin_lines;
 
 	// For backporch of phantom pipe, use vstartup of the main pipe
 	phantom_bp = get_vstartup(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx);
-- 
2.25.1