From 37b556606d1217b4367e622d88cef11c65764386 Mon Sep 17 00:00:00 2001 From: Ben Skeggs Date: Tue, 31 Mar 2020 16:08:44 +1000 Subject: [PATCH 2/2] drm/nouveau/gr/gp107,gp108: implement workaround for HW hanging during init Certain boards with GP107/GP108 chipsets hang (often, but randomly) for unknown reasons during GR initialisation. The first tell-tale symptom of this issue is: nouveau 0000:01:00.0: bus: MMIO read of 00000000 FAULT at 409800 [ TIMEOUT ] appearing in dmesg, likely followed by many other failures being logged. Karol found this WAR for the issue a while back, but efforts to isolate the root cause and proper fix have not yielded success so far. I've modified the original patch to include a few more details, limit it to GP107/GP108 by default, and added a config option to override this choice. Signed-off-by: Ben Skeggs Reviewed-by: Karol Herbst --- .../gpu/drm/nouveau/nvkm/engine/gr/gf100.c | 26 +++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c index dd8f85b8b3a7..f2f5636efac4 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c @@ -1981,8 +1981,34 @@ gf100_gr_init_(struct nvkm_gr *base) { struct gf100_gr *gr = gf100_gr(base); struct nvkm_subdev *subdev = &base->engine.subdev; + struct nvkm_device *device = subdev->device; + bool reset = device->chipset == 0x137 || device->chipset == 0x138; u32 ret; + /* On certain GP107/GP108 boards, we trigger a weird issue where + * GR will stop responding to PRI accesses after we've asked the + * SEC2 RTOS to boot the GR falcons. This happens with far more + * frequency when cold-booting a board (ie. returning from D3). + * + * The root cause for this is not known and has proven difficult + * to isolate, with many avenues being dead-ends. + * + * A workaround was discovered by Karol, whereby putting GR into + * reset for an extended period right before initialisation + * prevents the problem from occuring. + * + * XXX: As RM does not require any such workaround, this is more + * of a hack than a true fix. + */ + reset = nvkm_boolopt(device->cfgopt, "NvGrResetWar", reset); + if (reset) { + nvkm_mask(device, 0x000200, 0x00001000, 0x00000000); + nvkm_rd32(device, 0x000200); + msleep(50); + nvkm_mask(device, 0x000200, 0x00001000, 0x00001000); + nvkm_rd32(device, 0x000200); + } + nvkm_pmu_pgob(gr->base.engine.subdev.device->pmu, false); ret = nvkm_falcon_get(&gr->fecs.falcon, subdev); -- 2.25.1