From: Karol Herbst <kherbst@xxxxxxxxxx> commit 1cb9e2ef66d53b020842b18762e30d0eb4384de8 upstream. 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@xxxxxxxxxx> Cc: David Airlie <airlied@xxxxxxxxx> Cc: nouveau@xxxxxxxxxxxxxxxxxxxxx Cc: stable@xxxxxxxxxxxxxxx # 4.19+ Signed-off-by: Karol Herbst <kherbst@xxxxxxxxxx> Reviewed-by: Dave Airlie <airlied@xxxxxxxxxx> Link: https://patchwork.freedesktop.org/patch/msgid/20230622152017.2512101-1-kherbst@xxxxxxxxxx Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h | 1 + drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c | 4 +++- drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c | 10 ++++++++++ drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c | 1 + drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c | 1 + drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c | 1 + 6 files changed, 17 insertions(+), 1 deletion(-) --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h @@ -123,6 +123,7 @@ void gk104_grctx_generate_r418800(struct 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; --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c @@ -916,7 +916,9 @@ 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 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c @@ -820,6 +820,15 @@ gk110_grctx_generate_r419eb0(struct gf10 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, @@ -852,4 +861,5 @@ 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, }; --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c @@ -101,4 +101,5 @@ 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, }; --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c @@ -566,4 +566,5 @@ 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, }; --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c @@ -991,4 +991,5 @@ gm107_grctx = { .r406500 = gm107_grctx_generate_r406500, .gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr, .r419e00 = gm107_grctx_generate_r419e00, + .r419f78 = gk110_grctx_generate_r419f78, };
