diff options
| -rw-r--r-- | kernel/gsp_sema_service.c | 32 |
1 files changed, 32 insertions, 0 deletions
diff --git a/kernel/gsp_sema_service.c b/kernel/gsp_sema_service.c index fa11f68..00d9b56 100644 --- a/kernel/gsp_sema_service.c +++ b/kernel/gsp_sema_service.c @@ -318,6 +318,21 @@ struct svc_channel { * the end with no operand left pending, so a * replay suppresses every op. When clear, the * done bitmap decides per op (retry path). */ + bool ever_ops; /* r611: this channel has decoded at least one + * transfer op (copy/fill), i.e. it carries the + * client's stream-ordered memory work. The r607 + * stream-order watermark considers only such + * channels: a sibling GR LAUNCH channel's ring + * legitimately holds future launches, and + * deferring on those creates mutual deferral + * between the client's own launch channels + * (streams2: launches on h=0x5c00001f/23 each + * saw the other's unconsumed entry, burned the + * 15 s cap and were refused fail-closed - the + * r610c stream class red). Measured r606/r609/ + * r610c: op-decoding channels are exactly the + * copy ranks (0x5c000059 family) and the CE + * ranks; launch channels decode no ops. */ u64 slot_ops_hash[SVC_GPFIFO_MAX_BITS]; /* Content witness for slot_ops_ident: the * FNV-1a hash of the push bytes the identity @@ -11560,6 +11575,11 @@ static void svc_decode_stream(struct nv_vgpu_device *vgpu, const u8 *buf, if (n_ops != n_ops_before) { struct svc_memset_op *lm = &ops[n_ops - 1]; + /* r611: this channel carries transfer work + * (see ever_ops) - the stream-order + * watermark's scope. */ + ch->ever_ops = true; + /* * fail4 CONT.53: H2D-shaped copies (virtual * device destination, virtual host source) @@ -21316,6 +21336,16 @@ static u32 svc_pass_local_n; * * Channels whose USERD is unreadable are skipped (their work cannot be * ordered by this mechanism anyway). + * + * r611: only channels that carry transfer ops are considered (ever_ops). + * The r607 blanket "every other ring" caught sibling GR LAUNCH channels + * whose rings hold the client's own future launches: streams2's two stream + * channels (h=0x5c00001f/23) each deferred on the other's published entry + * for the full 15 s cap, then the r586 fail-closed refused both kernels + * (measured r610c: every streams2 launch REFUSED, bad=65534). A launch + * channel decodes no ops (measured r606/r609/r610c: ops appear only on the + * 0x5c000059 copy family and the CE ranks), so the flag separates them + * cleanly while keeping the r606 red-draw copy channel in scope. */ static bool svc_ce_stream_backlog(struct nv_vgpu_device *vgpu, const struct svc_channel *self) @@ -21332,6 +21362,8 @@ static bool svc_ce_stream_backlog(struct nv_vgpu_device *vgpu, continue; if (self && c->h_object == self->h_object) continue; + if (!c->ever_ops) + continue; if (!c->gpfifo_entries || !c->userd_pa) continue; if (svc_read_ap(vgpu ? vgpu : c->vgpu, |