diff options
| -rw-r--r-- | kernel/gsp_phys_booter.c | 25 |
1 files changed, 21 insertions, 4 deletions
diff --git a/kernel/gsp_phys_booter.c b/kernel/gsp_phys_booter.c index 8e3f25f..d61df37 100644 --- a/kernel/gsp_phys_booter.c +++ b/kernel/gsp_phys_booter.c @@ -20758,6 +20758,22 @@ static void gsp_phys_gr_ctx_wipe_latches(void) * stream3d lane only, so CUDA/QMD and CE submissions are untouched. */ static u32 gsp_phys_gr_cwd_clears; +/* + * eng16: 0x40706c (our "cwd3") is a read-only hardware sentinel - it reads + * 0xbadf5040 on every read (305/305 samples, write 0x0 -> readback unchanged; + * eng15 receipts). Gating the pre-replay clear on it made the clear fire on + * EVERY stream3d launch (7x/boot observed c250-254), running a TSG + * preempt/resched + MME latch wipe before each replay while the noQMD replay + * lane carries no context re-load - i.e. the clear itself destroyed the + * context the incremental chunks ran against. The predicate now uses only + * the real poison sources (esr 0x404490, grfifo 0x400504); cwd3 is read for + * the log line only. knob sema_gl_cwd_clear (default 1) = A/B switch. + */ +static bool gsp_phys_gr_cwd_clear_en = true; +module_param_named(sema_gl_cwd_clear, gsp_phys_gr_cwd_clear_en, bool, 0644); +MODULE_PARM_DESC(sema_gl_cwd_clear, + "Pre-replay FE priv-error clear on the stream3d lane. Predicate = real poison sources only (esr 0x404490 / grfifo 0x400504; cwd3 0x40706c excluded - hardware read sentinel). 0 = fully off (A/B knob)"); + static void gsp_phys_gr_cwd_clear_locked(void __iomem *bar0, u32 h_object, u64 push_va) { @@ -20766,7 +20782,6 @@ static void gsp_phys_gr_cwd_clear_locked(void __iomem *bar0, u32 h_object, u32 gf = ioread32(bar0 + 0x00400504u); if ((esr & 0xffff0000u) != 0xbadf0000u && - (cwd3 & 0xffff0000u) != 0xbadf0000u && (gf & 0xffff0000u) != 0xbadf0000u) return; gsp_phys_gr_cwd_clears++; @@ -31023,11 +31038,13 @@ gr_page_unmapped: * CONT.474 CWD-CLEAR: clear a pre-existing 0xbadf FE priv-error latch * BEFORE this replay is emitted (see gsp_phys_gr_cwd_clear_locked). * Bounded to one attempt per launch; stream3d lane only, so the - * CUDA/QMD and CE paths never reach this site. Gated by the same - * sema_gr_wedge_recover knob as the mid-launch recovery, which stays - * available for a poison the replay itself causes. + * CUDA/QMD and CE paths never reach this site. Gated by + * sema_gl_cwd_clear (eng16 A/B knob) and the same sema_gr_wedge_recover + * knob as the mid-launch recovery, which stays available for a poison + * the replay itself causes. */ if (stream3d && bar0 && !cwd_clear_done && + READ_ONCE(gsp_phys_gr_cwd_clear_en) && READ_ONCE(gsp_phys_gr_wedge_recover)) { cwd_clear_done = true; gsp_phys_gr_cwd_clear_locked(bar0, req->h_object, req->push_va); |