From 6075628d72aae72e7ff4a882cb7ce28707ac220a Mon Sep 17 00:00:00 2001 From: Arthur Hanson Rasmusson Date: Thu, 22 Oct 2026 00:10:36 -0400 Subject: r445 wedge hard re-arm experiment (gsp_phys_gr_wedge_rearm, default off): on the proven engine-wedged warm-sem-probe failure, one bounded recovery attempt - TSG PREEMPT bWait=1 (forced context save/unload) + the m155 extended re-arm (mode-35 lane-enable tail + GPFIFO schedules + doorbell) + a repeated probe - before the historical WEDGED break --- kernel/gsp_phys_gpu.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'kernel/gsp_phys_gpu.c') diff --git a/kernel/gsp_phys_gpu.c b/kernel/gsp_phys_gpu.c index eadb4c2..b61929e 100644 --- a/kernel/gsp_phys_gpu.c +++ b/kernel/gsp_phys_gpu.c @@ -1173,6 +1173,30 @@ int gsp_phys_gr_nowrite_retries_value(void) } EXPORT_SYMBOL_GPL(gsp_phys_gr_nowrite_retries_value); +/* + * r445 wedge hard re-arm (gsp_phys_gr_wedge_rearm; default 0 = off). When the + * outcome-retry's warm GR semaphore probe proves the engine wedged for the + * context (the proven-sticky post-dispatch no-store state), this knob makes + * the submit attempt ONE bounded recovery instead of breaking immediately: + * a TSG PREEMPT(bWait=1) forces the FECS to save/unload the channel's + * context, then the mode-35 lane-enable tail + GPFIFO schedules are re-issued + * (the m155 extended re-arm) and the semaphore probe is repeated. A pass + * means the lane revived for this launch and the normal retry ladder + * continues; a fail leaves the historical WEDGED break. Read once per wedge + * episode. Off by default for A/B. + */ +static int gsp_phys_gr_wedge_rearm_param; +module_param_named(gsp_phys_gr_wedge_rearm, gsp_phys_gr_wedge_rearm_param, + int, 0644); +MODULE_PARM_DESC(gsp_phys_gr_wedge_rearm, + "r445: on the proven engine-wedged sem probe, attempt a bounded preempt+resched hard re-arm before giving up (default 0=off)"); + +int gsp_phys_gr_wedge_rearm_value(void) +{ + return gsp_phys_gr_wedge_rearm_param ? 1 : 0; +} +EXPORT_SYMBOL_GPL(gsp_phys_gr_wedge_rearm_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 -- cgit v1.2.3