diff options
Diffstat (limited to 'kernel/gsp_sema_service.c')
| -rw-r--r-- | kernel/gsp_sema_service.c | 51 |
1 files changed, 51 insertions, 0 deletions
diff --git a/kernel/gsp_sema_service.c b/kernel/gsp_sema_service.c index ba9d3da..abc9b06 100644 --- a/kernel/gsp_sema_service.c +++ b/kernel/gsp_sema_service.c @@ -819,6 +819,7 @@ struct sema_svc { u64 pushtrace_all; /* fail4: de-windowed push decode * trace (every push, bounded) */ u64 opadd_log; /* fail4: every op appended */ + u64 op2d_raw_log; /* r458: raw 2D-shaped copy pushes */ u64 dmatrace_log; /* fail4: denied-transfer trace */ u64 pend_dbg_log; /* fail4 r305: pending/hold witness */ u64 snap_gate_log; /* fail4 r311: capture-gate witness */ @@ -9907,6 +9908,23 @@ static void svc_decode_stream(struct nv_vgpu_device *vgpu, const u8 *buf, break; case CE_M_LINE_LENGTH_IN: st.line_length = v0; + /* + * r458 THE memset2d root cause: the driver encodes + * LINE_LENGTH_IN (0x418) and the adjacent LINE_COUNT + * (0x41c) as ONE count=2 method group - observed raw + * push bytes `20028106 00001000 00000100` = header + * (subch 4, count 2, addr 0x418), line length 4096, + * line count 0x100 = 256. Reading only v0 left + * line_count = 0, so the 2D-copy builder below took + * the single-row path: one 4 KB op per push, and a + * 4 MB cudaMemcpy2D delivered exactly one page per + * 1 MB block (memset2d probe: per-MB ok=4096, + * bad=12.5M/12.58M). The GRCE variant below has + * always decoded the count=2 form; the CE path did + * not. + */ + if (count >= 2) + st.line_count = v1; break; /* r402: 2D geometry (cudaMemset2D / cudaMemcpy2D). */ case CE_M_LINE_COUNT: @@ -10214,6 +10232,39 @@ static void svc_decode_stream(struct nv_vgpu_device *vgpu, const u8 *buf, m->spitch = spitch; } } + /* + * r458 memset2d forensics: the + * driver's cudaMemcpy2D pushes decode + * LINE_LENGTH=4096 with PITCH_IN/OUT + * present but LINE_COUNT absent + * (lc=0), so only one 4 KB row per + * push executes and a 4 MB copy + * delivers 4 pages. Dump the raw push + * (bounded) for every pitch-shaped + * copy so the method stream that + * carries the row count is on record. + */ + if (gsp_sema_dbg && + (st.have_pitch_out || + st.have_pitch_in) && + svc.op2d_raw_log < 12) { + u32 dl = len < 220 ? len : 220; + + svc.op2d_raw_log++; + pr_info("sema-op2d-raw: h=0x%x push=0x%llx len=%u off=0x%x line=%u lc=%u po=%u/%u pi=%u/%u out=0x%llx in=0x%llx bytes=%u dma=0x%08x\n", + ch->h_object, push_va, + len, off, + st.line_length, + st.line_count, + st.have_pitch_out, + st.pitch_out, + st.have_pitch_in, + st.pitch_in, + m->dst, m->src, + (u32)m->bytes, dma); + pr_info("sema-op2d-raw: raw %*phN\n", + dl, buf); + } n_ops++; ops_seq++; } else if (gsp_sema_dbg && svc.dma_skip_log < 32) { |