drm/amd/display: add DCN support for aarch64

This adds ARM64 support into the DCN. This mainly enables support
for Navi graphics cards. The dcn10 changes haven't been tested,
since I don't have the relevant hardware available, but there
is no way to conditionally disable them, so I've done them anyway.

Signed-off-by: Daniel Kolesa <daniel@octaforge.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 50 insertions, 31 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 17d5cb422025..07571f84e0f8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -1331,6 +1331,47 @@ static uint32_t read_pipe_fuses(struct dc_context *ctx)
 	return value;
 }
 
+/*
+ * Some architectures don't support soft-float (e.g. aarch64), on those
+ * this function has to be called with hardfloat enabled, make sure not
+ * to inline it so whatever fp stuff is done stays inside
+ */
+static noinline void dcn10_resource_construct_fp(
+	struct dc *dc)
+{
+	if (dc->ctx->dce_version == DCN_VERSION_1_01) {
+		struct dcn_soc_bounding_box *dcn_soc = dc->dcn_soc;
+		struct dcn_ip_params *dcn_ip = dc->dcn_ip;
+		struct display_mode_lib *dml = &dc->dml;
+
+		dml->ip.max_num_dpp = 3;
+		/* TODO how to handle 23.84? */
+		dcn_soc->dram_clock_change_latency = 23;
+		dcn_ip->max_num_dpp = 3;
+	}
+	if (ASICREV_IS_RV1_F0(dc->ctx->asic_id.hw_internal_rev)) {
+		dc->dcn_soc->urgent_latency = 3;
+		dc->debug.disable_dmcu = true;
+		dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 41.60f;
+	}
+
+
+	dc->dcn_soc->number_of_channels = dc->ctx->asic_id.vram_width / ddr4_dram_width;
+	ASSERT(dc->dcn_soc->number_of_channels < 3);
+	if (dc->dcn_soc->number_of_channels == 0)/*old sbios bug*/
+		dc->dcn_soc->number_of_channels = 2;
+
+	if (dc->dcn_soc->number_of_channels == 1) {
+		dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 19.2f;
+		dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 = 17.066f;
+		dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 = 14.933f;
+		dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = 12.8f;
+		if (ASICREV_IS_RV1_F0(dc->ctx->asic_id.hw_internal_rev)) {
+			dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 20.80f;
+		}
+	}
+}
+
 static bool dcn10_resource_construct(
 	uint8_t num_virtual_links,
 	struct dc *dc,
@@ -1482,37 +1523,15 @@ static bool dcn10_resource_construct(
 	memcpy(dc->dcn_ip, &dcn10_ip_defaults, sizeof(dcn10_ip_defaults));
 	memcpy(dc->dcn_soc, &dcn10_soc_defaults, sizeof(dcn10_soc_defaults));
 
-	if (dc->ctx->dce_version == DCN_VERSION_1_01) {
-		struct dcn_soc_bounding_box *dcn_soc = dc->dcn_soc;
-		struct dcn_ip_params *dcn_ip = dc->dcn_ip;
-		struct display_mode_lib *dml = &dc->dml;
-
-		dml->ip.max_num_dpp = 3;
-		/* TODO how to handle 23.84? */
-		dcn_soc->dram_clock_change_latency = 23;
-		dcn_ip->max_num_dpp = 3;
-	}
-	if (ASICREV_IS_RV1_F0(dc->ctx->asic_id.hw_internal_rev)) {
-		dc->dcn_soc->urgent_latency = 3;
-		dc->debug.disable_dmcu = true;
-		dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 41.60f;
-	}
-
-
-	dc->dcn_soc->number_of_channels = dc->ctx->asic_id.vram_width / ddr4_dram_width;
-	ASSERT(dc->dcn_soc->number_of_channels < 3);
-	if (dc->dcn_soc->number_of_channels == 0)/*old sbios bug*/
-		dc->dcn_soc->number_of_channels = 2;
-
-	if (dc->dcn_soc->number_of_channels == 1) {
-		dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 19.2f;
-		dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 = 17.066f;
-		dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 = 14.933f;
-		dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = 12.8f;
-		if (ASICREV_IS_RV1_F0(dc->ctx->asic_id.hw_internal_rev)) {
-			dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 20.80f;
-		}
-	}
+#if defined(CONFIG_ARM64)
+	/* Aarch64 does not support -msoft-float/-mfloat-abi=soft */
+	DC_FP_START();
+	dcn10_resource_construct_fp(dc);
+	DC_FP_END();
+#else
+	/* Other architectures we build for build this with soft-float */
+	dcn10_resource_construct_fp(dc);
+#endif
 
 	pool->base.pp_smu = dcn10_pp_smu_create(ctx);