diff options
| -rw-r--r-- | kernel/gsp_sema_service.c | 41 |
1 files changed, 41 insertions, 0 deletions
diff --git a/kernel/gsp_sema_service.c b/kernel/gsp_sema_service.c index dd7a5e1..6a1595e 100644 --- a/kernel/gsp_sema_service.c +++ b/kernel/gsp_sema_service.c @@ -15323,6 +15323,47 @@ static void svc_pump_channels(struct nv_vgpu_device *vgpu) ch->h_object, ch->ce_index, put, (u32)ch->last_get); ch->last_get = put; + } else if (!ch->engine_type && ch->gpfifo_entries && + ch->last_get > put && + ch->submissions < ch->gpfifo_entries / 2) { + /* + * m181 (r203 GR ctx-init stall): a GR channel's + * ring/USERD live in fixed VRAM slots + * (fb 0x140000 + rank*0x3000) that keep the + * PREVIOUS session's final state across the + * session flush (m176 reset learned counter + * state but not the ring-consumption + * bookkeeping). A new session's first pump + * pass therefore sees the residual put (e.g. + * 107 = the last session's final GP_PUT) and + * consumes the stale ring up to it, advancing + * last_get before the client has written its + * own entries. The client's fresh put then + * drops below put_prev, and without this + * rewind last_get stays ahead of the producer: + * the live ctx-init entries are never decoded, + * their REPORT_SEM releases are never applied + * (the completion word freezes at the first + * stale-decoded payload), and the client's + * ctx-init wait polls forever - r203 rank 0 + * hung exactly so in multikernel / streams2 / + * victory_mail / smiley whenever the prior + * session had reached a high put (the sessions + * after a hung one, whose final put is 1, + * proceeded - a perfect alternation). Rewind + * to slot 0 like the r48 resync: a fresh + * session restarts its push sequence at slot + * 0, and re-decoding slot 0 is idempotent + * (the stale pass could only have authored the + * same payload, and the forward-only apply + * drops a duplicate). A genuine wrap cannot be + * this fresh (submissions guard), mirroring + * the r73 CE rewind. + */ + pr_info_ratelimited("sema-chan: fresh put drop (GR) h=0x%x rank=%u put=%u last=%u -> rewind to 0\n", + ch->h_object, ch->gr_index, put, + (u32)ch->last_get); + ch->last_get = 0; } bitmap_zero(ch->slot_done_epoch, SVC_GPFIFO_MAX_BITS); } |