diff options
Diffstat (limited to 'kernel/gsp_sema_service.c')
| -rw-r--r-- | kernel/gsp_sema_service.c | 23 |
1 files changed, 17 insertions, 6 deletions
diff --git a/kernel/gsp_sema_service.c b/kernel/gsp_sema_service.c index 587fb96..6c75a9e 100644 --- a/kernel/gsp_sema_service.c +++ b/kernel/gsp_sema_service.c @@ -8341,13 +8341,24 @@ static void svc_decode_stream(struct nv_vgpu_device *vgpu, const u8 *buf, struct svc_memset_op *lm = &ops[n_ops - 1]; /* - * fail4 A/B note: a CE-style auto-advance of - * st.offset_out per op was tried here and - * reverted - it did not change the memset - * coverage and the driver's per-op re-sets are - * already decoded, so the executed dsts match - * the stream. + * fail4 CE linear auto-advance, BOTH sides: the + * driver re-sets only ONE offset per op and the + * copy engine advances the other by the transfer + * size. H2D ops show an explicit advancing DST + * with a FIXED SRC base (every 1 MB chunk read + * the source base again: vector_add's device a + * held h_a[0..1MB) x4 -> 75% mismatch; the + * readbacks are the mirror image). Advance both + * registers; an explicit re-set simply overrides. */ + { + u64 adv = (lm->type == 1) ? lm->bytes : + (u64)lm->elem * lm->count; + + st.offset_out += adv; + if (lm->type == 1) + st.offset_in += adv; + } if (svc.opadd_log < 2048) { svc.opadd_log++; pr_info("sema-opadd: h=0x%x type=%u dst=0x%llx src=0x%llx bytes=%llu elem=%u count=%u ap=%u src_ap=%u phys=%u src_phys=%u\n", |