drm/amd/display: Use pre-allocated temp struct for bounding box update

[Why]

There is a theoretical problem in prior patches for reducing the stack
size of *update_bw_bounding_box() functions.

By modifying the soc.clock_limits[n] struct directly, this can cause
unintended behavior as the for loop attempts to swap rows in
clock_limits[n]. A temporary struct is still required to make sure we
stay functinoally equivalent.

[How]

Add a temporary clock_limits table to the SOC struct, and use it when
swapping rows.

Signed-off-by: Leo Li <sunpeng.li@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 18 insertions, 15 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
index c2fec0d85da4..e247b2270b1d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
@@ -2015,9 +2015,8 @@ void dcn21_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 
 	ASSERT(clk_table->num_entries);
 	/* Copy dcn2_1_soc.clock_limits to clock_limits to avoid copying over null states later */
-	for (i = 0; i < dcn2_1_soc.num_states + 1; i++) {
-		dcn2_1_soc.clock_limits[i] = dcn2_1_soc.clock_limits[i];
-	}
+	memcpy(&dcn2_1_soc._clock_tmp, &dcn2_1_soc.clock_limits,
+	       sizeof(dcn2_1_soc.clock_limits));
 
 	for (i = 0; i < clk_table->num_entries; i++) {
 		/* loop backwards*/
@@ -2032,22 +2031,26 @@ void dcn21_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 		if (i == 1)
 			k++;
 
-		dcn2_1_soc.clock_limits[k].state = k;
-		dcn2_1_soc.clock_limits[k].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz;
-		dcn2_1_soc.clock_limits[k].fabricclk_mhz = clk_table->entries[i].fclk_mhz;
-		dcn2_1_soc.clock_limits[k].socclk_mhz = clk_table->entries[i].socclk_mhz;
-		dcn2_1_soc.clock_limits[k].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2;
+		dcn2_1_soc._clock_tmp[k].state = k;
+		dcn2_1_soc._clock_tmp[k].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz;
+		dcn2_1_soc._clock_tmp[k].fabricclk_mhz = clk_table->entries[i].fclk_mhz;
+		dcn2_1_soc._clock_tmp[k].socclk_mhz = clk_table->entries[i].socclk_mhz;
+		dcn2_1_soc._clock_tmp[k].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2;
 
-		dcn2_1_soc.clock_limits[k].dispclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dispclk_mhz;
-		dcn2_1_soc.clock_limits[k].dppclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dppclk_mhz;
-		dcn2_1_soc.clock_limits[k].dram_bw_per_chan_gbps = dcn2_1_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps;
-		dcn2_1_soc.clock_limits[k].dscclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dscclk_mhz;
-		dcn2_1_soc.clock_limits[k].dtbclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dtbclk_mhz;
-		dcn2_1_soc.clock_limits[k].phyclk_d18_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz;
-		dcn2_1_soc.clock_limits[k].phyclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].phyclk_mhz;
+		dcn2_1_soc._clock_tmp[k].dispclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dispclk_mhz;
+		dcn2_1_soc._clock_tmp[k].dppclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dppclk_mhz;
+		dcn2_1_soc._clock_tmp[k].dram_bw_per_chan_gbps = dcn2_1_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps;
+		dcn2_1_soc._clock_tmp[k].dscclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dscclk_mhz;
+		dcn2_1_soc._clock_tmp[k].dtbclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dtbclk_mhz;
+		dcn2_1_soc._clock_tmp[k].phyclk_d18_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz;
+		dcn2_1_soc._clock_tmp[k].phyclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].phyclk_mhz;
 
 		k++;
 	}
+
+	memcpy(&dcn2_1_soc.clock_limits, &dcn2_1_soc._clock_tmp,
+	       sizeof(dcn2_1_soc.clock_limits));
+
 	if (clk_table->num_entries) {
 		dcn2_1_soc.num_states = clk_table->num_entries + 1;
 		/* fill in min DF PState */