Commit 1cb9e2ef authored by Karol Herbst's avatar Karol Herbst
Browse files

drm/nouveau/gr: enable memory loads on helper invocation on all channels



We have a lurking bug where Fragment Shader Helper Invocations can't load
from memory. But this is actually required in OpenGL and is causing random
hangs or failures in random shaders.

It is unknown how widespread this issue is, but shaders hitting this can
end up with infinite loops.

We enable those only on all Kepler and newer GPUs where we use our own
Firmware.

Nvidia's firmware provides a way to set a kernelspace controlled list of
mmio registers in the gr space from push buffers via MME macros.

v2: drop code for gm200 and newer.

Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: David Airlie <airlied@gmail.com>
Cc: nouveau@lists.freedesktop.org
Cc: stable@vger.kernel.org # 4.19+
Signed-off-by: default avatarKarol Herbst <kherbst@redhat.com>
Reviewed-by: default avatarDave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230622152017.2512101-1-kherbst@redhat.com
parent e9d699af
Loading
Loading
Loading
Loading
+1 −0
Original line number Diff line number Diff line
@@ -117,6 +117,7 @@ void gk104_grctx_generate_r418800(struct gf100_gr *);

extern const struct gf100_grctx_func gk110_grctx;
void gk110_grctx_generate_r419eb0(struct gf100_gr *);
void gk110_grctx_generate_r419f78(struct gf100_gr *);

extern const struct gf100_grctx_func gk110b_grctx;
extern const struct gf100_grctx_func gk208_grctx;
+3 −1
Original line number Diff line number Diff line
@@ -906,7 +906,9 @@ static void
gk104_grctx_generate_r419f78(struct gf100_gr *gr)
{
	struct nvkm_device *device = gr->base.engine.subdev.device;
	nvkm_mask(device, 0x419f78, 0x00000001, 0x00000000);

	/* bit 3 set disables loads in fp helper invocations, we need it enabled */
	nvkm_mask(device, 0x419f78, 0x00000009, 0x00000000);
}

void
+10 −0
Original line number Diff line number Diff line
@@ -820,6 +820,15 @@ gk110_grctx_generate_r419eb0(struct gf100_gr *gr)
	nvkm_mask(device, 0x419eb0, 0x00001000, 0x00001000);
}

void
gk110_grctx_generate_r419f78(struct gf100_gr *gr)
{
	struct nvkm_device *device = gr->base.engine.subdev.device;

	/* bit 3 set disables loads in fp helper invocations, we need it enabled */
	nvkm_mask(device, 0x419f78, 0x00000008, 0x00000000);
}

const struct gf100_grctx_func
gk110_grctx = {
	.main  = gf100_grctx_generate_main,
@@ -854,4 +863,5 @@ gk110_grctx = {
	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
	.r418800 = gk104_grctx_generate_r418800,
	.r419eb0 = gk110_grctx_generate_r419eb0,
	.r419f78 = gk110_grctx_generate_r419f78,
};
+1 −0
Original line number Diff line number Diff line
@@ -103,4 +103,5 @@ gk110b_grctx = {
	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
	.r418800 = gk104_grctx_generate_r418800,
	.r419eb0 = gk110_grctx_generate_r419eb0,
	.r419f78 = gk110_grctx_generate_r419f78,
};
+1 −0
Original line number Diff line number Diff line
@@ -568,4 +568,5 @@ gk208_grctx = {
	.dist_skip_table = gf117_grctx_generate_dist_skip_table,
	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
	.r418800 = gk104_grctx_generate_r418800,
	.r419f78 = gk110_grctx_generate_r419f78,
};
Loading