drm/nouveau: Add support for BLCG on Kepler1

This enables BLCG optimization for kepler1. When using clockgating,
nvidia's firmware has a set of registers which are initially programmed
by the vbios with various engine delays and other mysterious settings
that are safe enough to bring up the GPU. However, the values used by
the vbios are more power hungry then they need to be, so the nvidia driver
writes it's own more optimized set of BLCG settings before enabling
CG_CTRL. This adds support for programming the optimized BLCG values
during engine/subdev init, which enables rather significant power
savings.

This introduces the nvkm_therm_clkgate_init() helper, which we use to
program the optimized BLCG settings before enabling clockgating with
nvkm_therm_clkgate_enable.

As well, this commit shares a lot more code with Fermi since BLCG is
mostly the same there as far as we can tell. In the future, it's likely
we'll reformat the clkgate_packs for kepler1 so that they share a list
of mmio packs with Fermi.

Signed-off-by: Lyude Paul <lyude@redhat.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>

1 files changed, 47 insertions, 0 deletions

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c
index 0a6e8ea..48fd98e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c
@@ -20,10 +20,56 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  *
  * Authors: Ben Skeggs
+ *          Lyude Paul
  */
+#include "gk104.h"
 #include "gf100.h"
 #include "ram.h"
 
+/*
+ *******************************************************************************
+ * PGRAPH registers for clockgating
+ *******************************************************************************
+ */
+const struct nvkm_therm_clkgate_init
+gk104_fb_clkgate_blcg_init_unk_0[] = {
+	{ 0x100d10, 1, 0x0000c244 },
+	{ 0x100d30, 1, 0x0000c242 },
+	{ 0x100d3c, 1, 0x00000242 },
+	{ 0x100d48, 1, 0x00000242 },
+	{ 0x100d1c, 1, 0x00000042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_fb_clkgate_blcg_init_vm_0[] = {
+	{ 0x100c98, 1, 0x00000242 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_fb_clkgate_blcg_init_main_0[] = {
+	{ 0x10f000, 1, 0x00000042 },
+	{ 0x17e030, 1, 0x00000044 },
+	{ 0x17e040, 1, 0x00000044 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_fb_clkgate_blcg_init_bcast_0[] = {
+	{ 0x17ea60, 4, 0x00000044 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_pack
+gk104_fb_clkgate_pack[] = {
+	{ gk104_fb_clkgate_blcg_init_unk_0 },
+	{ gk104_fb_clkgate_blcg_init_vm_0 },
+	{ gk104_fb_clkgate_blcg_init_main_0 },
+	{ gk104_fb_clkgate_blcg_init_bcast_0 },
+	{}
+};
+
 static const struct nvkm_fb_func
 gk104_fb = {
 	.dtor = gf100_fb_dtor,
@@ -33,6 +79,7 @@ gk104_fb = {
 	.intr = gf100_fb_intr,
 	.ram_new = gk104_ram_new,
 	.default_bigpage = 17,
+	.clkgate_pack = gk104_fb_clkgate_pack,
 };
 
 int