diff options
Diffstat (limited to 'kernel/gsp_phys_gpu.c')
| -rw-r--r-- | kernel/gsp_phys_gpu.c | 31 |
1 files changed, 31 insertions, 0 deletions
diff --git a/kernel/gsp_phys_gpu.c b/kernel/gsp_phys_gpu.c index e896664..b93c254 100644 --- a/kernel/gsp_phys_gpu.c +++ b/kernel/gsp_phys_gpu.c @@ -1124,6 +1124,37 @@ int gsp_phys_gr_nowrite_retries_value(void) EXPORT_SYMBOL_GPL(gsp_phys_gr_nowrite_retries_value); /* + * r410 wedge quiet window (gsp_phys_gr_wedge_quiet_ms; default 40000, clamped + * [0,120000]; 0 disables). The sticky per-lane no-execute wedge (100% of + * launches no-write while kept busy) is proven to CLEAR when the lane stays + * quiet for tens of seconds (r409: a ~37 s client gap healed a wedged run; + * r416: 58 consecutive no-write launches during a 126 s client run, first + * launches green again after the lane sat ~52 s idle; r417: a 20 s host hold + * did not heal, a 40 s hold did - "WEDGE-QUIET healed: engine wrote 1 + * page(s) after the 40000 ms hold"). Immediate retries and + * re-arms do not heal it (r409/r154). So when a zero-write outcome follows a + * previous accepted zero-write launch, the retry loop first holds this many ms + * with NO submissions to the engine, then re-arms (lane enable + schedules) + * and re-publishes once. The value doubles per further quiet retry. The + * quiet window is recovery-only: a launch that wrote anything never enters it. + */ +static unsigned int gsp_phys_gr_wedge_quiet_ms_param = 40000u; +module_param_named(gsp_phys_gr_wedge_quiet_ms, + gsp_phys_gr_wedge_quiet_ms_param, uint, 0644); +MODULE_PARM_DESC(gsp_phys_gr_wedge_quiet_ms, + "Quiet-window ms before retrying a launch on a lane whose previous launch also no-wrote (0=disable, default 40000; r417: a 20 s hold did not heal, 40 s healed)"); + +unsigned int gsp_phys_gr_wedge_quiet_ms_value(void) +{ + unsigned int v = gsp_phys_gr_wedge_quiet_ms_param; + + if (v > 120000u) + v = 120000u; + return v; +} +EXPORT_SYMBOL_GPL(gsp_phys_gr_wedge_quiet_ms_value); + +/* * m69 window-0 shadow pool (gsp_phys_rmcall_gr_shadow_win0; default 0). When * set, the forwarded GR launch copies the QMD's program/param pages into the * window-0 shadow pool (module pages at VAs 0x108000..0x10f000, PTEs planted |