| Commit message (Collapse) | Author | Age |
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
eng89i admitted the 14837-word window and chunked it into 6 chunks, but
6*384 words covers only 18% of the window - the DRAW_IAB call at the end
was never replayed. Raise SVC_GL_STREAM_CHUNK_MAX 6 -> 40 (39 chunks for
14837 words at the proven 384-word chunk) and the candidate ring 32 -> 48
so the chunks are not evicted before the pump drains them.
Context: c952-c957 submitted chunk 0 and got a FECS priv-error (badf1201,
mme_pc=513 mac=0xf1) before the release; c956 reached MME-CARRY-ARM
(off=1632/2799) and CALL-HOLD window=121, then CANCEL reason=
chan-ctx-reset. The chunk-0 poison and the carry fire remain the next
gates after full-window coverage.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
c946-c951 admitted the big 14865-word draw window but refused it at
raw_ok=0: the raw[] capture kept only the last 4096 words of a 14895-word
push. Raise GSP_PHYS_GR_RAW_WORDS/SVC_GR_PUSH_WORDS to 16384 (64 KB
static each; the IR pack stays 4096 and its maxa bound unchanged) and the
candidate ring 8 -> 32 so a three-chunk window is not truncated.
Add WIN-START-SNAP: c949-c951 admitted start=0x78 where w0=0x3f800000
parses as op=1 count=0xf80 (data, not a method header; the real BEGIN
run is at 0xe8). If the start word is not a plausible method header, scan
forward up to 0x400 bytes for the first plausible one and replay from
there; bounded receipt names old/new.
c949 was the first boot with guest surface stores from the engine
(GUEST-WIT 601/2030 pages, va=0x120400000, post=0xff000000); the beef
big-window replay is now the remaining gate.
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
c940-c945: VP-METHOD 0x1618 op=1 in push 0x400108c while every
RT-ADMIT-BLOCK kept has_draw=0. The marker sits inside a counted INC run,
not at a run header, so the guard never saw it. Accept a marker covered
by the run's method span (m <= target < m + cnt*4 + 4) for the 0x1618 /
0xd78 / 0x3910 family in ops 1/3/5, keeping the op=4/5 exact match.
Context: c944 was the first boot with surface stores - GUEST-WIT 601/2027
pages changed at va=0x120400000 post=0xff000000 on the X/2D lane - so the
engine does write the surface; the beef draw window is the remaining
admission gate.
|
| |
|
|
|
|
|
|
|
|
| |
RT-ADMIT-BLOCK on c934-c938 showed the persisted bind (mask=1,
pchan=0x1000013, B=0x20400000 W=0x780 H=0x438) was always refused by the
draw-marker guard: the client encodes BEGIN 0x1618 as an immd13 (op 4)
and CALL_MME_MACRO(34) 0x3910 as ONE_INCR (op 5, 0xa00a0e44), while the
guard only accepted the op=1 INC form. Accept ops 1/3/4/5 and match the
method, which flips has_draw to 1 and lets the persisted admission reach
the replay lane.
|
| |
|
|
|
|
|
|
| |
The receipt prints state_push/rt_valid/rt0_first/rtp/mask/pchan/has_draw
at the beef draw-synth reject, so the next boot names which of the five
conjoined admission predicates failed. Runner: wait at most GZ_SECS+120
for mission-done (the mission itself writes it by GZ_SECS+30 when the
guest is alive; a dead boot no longer costs 7.5 minutes).
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
c918-c921 had no RT-PERSIST and every beef draw was rejected on the
missing colour-target bind, while c910 had the bind on the X/2D channel.
RT-SCAN logs the last A/B/W/H candidates and seen flags for every beef
channel push (bounded to 32) so the next boot answers whether the bind is
absent from the push, filtered by the surface-class checks, or never
authored.
The batch runner also streams the kernel log with 'dmesg -w' per cycle
and merges it into the per-cycle evidence; the ring wraps in under four
minutes at this debug volume and had truncated c921's key receipts.
|
| |
|
|
|
|
|
|
|
| |
c910 proved the persisted bind arrives on the X/2D channel
(RT-PERSIST h=0x1000013 B=0x20400000 W=0x780 H=0x438) while the beef
draw window is on 0xbeef0100, so the eng89c channel equality refused the
exact window it was meant to admit. The stored channel is now
diagnostic only; the draw-marker guard, the surface-class validity and
the per-session clear remain.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Four fixes from a code audit of eng89/eng89b, each of which could have
made the maps=6 experiment unobservable or harmful:
- Draw-move anchor: use the FIRST 0x3810 run only. The 247-word window
also carries its own 0x3810 later; the old code moved the draw to the
last one, i.e. behind the setup calls it must precede. Removed the
post-scan promotion.
- Prelude/stage budget: the raster-enable words (8) pushed the prelude
toward the 96-word cap and could skip the whole stage-bind block
(SPH-BIND-STAGE-SKIP reason=budget), hiding the GS bind. Array and
gates grown to 128.
- RT persistence: require B/W/H only (A optional, matching the existing
first-valid check), store the channel and require it for admission,
require a real draw marker (0x1618/0xd78/0x3910) in the window, and
clear the state in svc_session_flush so a recycled channel cannot
inherit a dead session's target.
- GS live map: moved out of the SPH-AUTHOR copy branch and derived from
the family page's actual VTG image at +0x900 (not the source record),
so an overlap skip no longer makes maps=6 inert. New gs_addr=0
parameter set (GS at 0x780) keeps the GS header clear of the VTG copy.
Test matrix: params-r1624-maps6-780.txt (maps=6, gs_addr=0).
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Most beef draw pushes carry no colour-target bind of their own (the
client binds the target once per context/target switch in an earlier
state push), so the per-window admission refused the real frame pushes
on most boots ('beef draw-synth: no valid last colour-target bind', the
shallow-boot lottery). Track the last complete, plausible bind seen on a
trusted push (same surface-class validity as the first-bind check; an
invalid later write never overwrites a valid state) and admit a beef
draw window on it: RT-PERSIST + '3D mark admitted (persisted
colour-target bind)' receipts. Knob sema_gl_win_rt_persist, default 1.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
capture
Kernel (deterministic fixes, each with an A/B knob):
- sema_gl_sph_gs_maps=6: derive the whole 216-bit GS IMAP/OMAP blocks
from the bound VTG image's OMAP and the PS image's IMAP at authoring
time (SPH-GS-MAP receipt; SPH-GS-SKIP names ps-invalid/gs-invalid/
vtg-overlap/vtg-short). maps=4 stays as the fallback.
- DS-MAP census line: dump stage-4/5 w5/w10/w13/w17 next to DS-IMAGE so
the fetched maps are visible without a new probe.
- MME pack carrier: reject maxa > 4096 (the IR pack array) instead of
64K, with MME-PACK-REJECT reason=bound.
- MME-DRAW-MOVE: anchor the slot-34 move after a 0x3810 VERTEX_STREAM
run. c848 moved CALL(34) to 0x204, ahead of the prepended stream bind,
so the 8x3 fetch used stale stream state.
- sema_gl_raster_enable=1: emit SET_RASTER_ENABLE=1 and
SET_GLOBAL_RENDER_ENABLE MODE_TRUE in the raster prelude (fresh replay
contexts may carry 0 for both, discarding every fragment).
Guest tooling (unblocks the render loop and capture):
- sdl_cap.c: asynchronous PBO+fence capture with a 5 s abandonment
bound; no glFinish/blocking readback (c899 wedged gzdoom in an
uninterruptible nv ioctl); clean sentinel from a destructor.
- gz_pbuf.c: request depth 24/stencil 8, log GL_DEPTH_BITS, and swap
with glFlush only.
- mission-gz.sh: gl_frames probe off by default; GZDoom launched
detached with a bounded wait, per-attempt X restart and retry;
capture in /dev/shm with GZCAP_MAXF.
- gzdoom_pbuf_run.sh: gl_pipeline_depth=2, gl_finishbeforeswap=0,
GZCAP_MAXF default, rc-file support for the detached run.
- run_cycles_long.sh: durable multi-cycle runner (the previous one lived
in /tmp and was lost on reboot); pushes tools, runs the mission, grabs
dmesg + guest logs + capture per cycle, stops on pixels.
Test matrix: params-r1624-maps{4,6}.txt.
|
| |
|
|
|
|
|
|
|
| |
CONT.548/c886: a clean 247 window (VS-BIND base=0x450c1f4) reached
MME-CARRY-FIRE gen=4 and was immediately cancelled with reason=
request-busy: svc_gr_carrier_request() claimed the armed carrier (the
take clears the arm) before taking the forwarding slot, so the lost
slot lock left the pack uncompleted. Probe SVC_FWD_INFLIGHT before the
take so the retryable busy case returns without consuming the arm.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
CONT.545/c880: the armed pack carrier (MME-CARRY-ARM gen=3 off=1506/2799)
never fired because the pump needs a matching CLIENT beef candidate and
the 2-frame mission ended before one re-appeared; it expired with no
FIRE/CANCEL/WAIT receipt. The pump's carry block now, when there is no
candidate but the channel's golden pack is still contiguously loaded
(gsp_phys_gr_mme_carry_ctx_alive: pack_load_h==carry_h && golden ready),
submits svc_gr_carrier_request() as its own synthetic candidate
(MME-CARRY-FIRE reason=self-candidate). A truly gone context is
reported MME-CARRY-CANCEL reason=ctx-gone, never silent. Release stays
beef-only; the eng68 chain still runs after the carrier fire (pack
complete -> release replay -> mac=0x22).
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
c836 proved the client's VERTEX_STREAM CALL(2) payload is
[stream, end_hi, end_lo, base_hi, base_lo] (MME-VSTREAM:
end=0x1e02100 base=0x1e001f4, MME-VSTREAM-LINE base=0x450c1f4
end=0x450e100 pages=3 first8=...3f800000 3e4ccccd...). eng79 wrongly
took d[2] (the END 0x450e100, a zero page) as the stream base; the base
d[4]=0x450c1f4 carries the float2 vertices. The Doris slot-2 sim with
the full 5-word payload emits LOCATION 0x1c08<-base and SIZE
0x604<-end-base.
- service: svc_gl_vs_call[5] (getter out[5]) - capture v0..v4, log 5
words; eng82 page-set collection adds the end (v2) and base (v4).
- booter eng79: slot-2 base = vcall[4] (require vcall[1]==0,
vcall[3]==0, aligned), end = vcall[2]; size pair = end-base; receipt
base=.. end=..; VS-BLOB2 dumps at the base.
- booter eng77: emit the FULL 5-word 0x3810 call (op=5 cnt=5) even when
the window carries its own call (the slot-34 reorder moves the draw
ahead of it); the 0x3810 MME-VSTREAM patch maps [base,end] into one
contiguous shadow line.
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
c840: VS-BLOB2 va=0x450e100 unresolved - the slot-2 VERTEX_STREAM
payload's VB page (0x450e000) was never part of the forwarded launch's
page set, so the sema resolver cannot map it and the synthesized
stream-location pair cannot be relocated (the engine would fetch an
unmapped guest VA).
svc_gl_field now handles 0x3810: every plausible address word
(>=0x100000, <2^40, 4-byte aligned) in the CALL(2) payload is added
via svc_gl_add_ptr, so the candidate/forward page set includes the VB
page and the release's pair relocation can resolve it.
|
| |
|
|
|
|
|
| |
The 16-hit cap hid later CALL slots (the VARRAY_STAGING_BUF_TURING
slot 1 / 0x3808 base binder) in the 728-byte beef push. 32 hits and a
1600-byte line keep the whole 0x100..0x1ff + 0x3800..0x39fc set in
one receipt.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The beef 728-byte push carries CALL_MME_MACRO(2) (method 0x3810,
golden slot 2 = VERTEX_STREAM_TURING) with payload [0,0,0x0450e100]:
the Mesa mme_tu104_sim of golden slot 2 with those args emits
SET_VERTEX_STREAM_A_LOCATION 0x1c04<-0, 0x1c08<-0, and the Turing size
pair 0x600<-0, 0x604<-<the VA> - the VTG stream state the per-frame
DRAW window slices omit. The census (eng76, 0x100..0x1ff) finds it at
0x148 of the 728 push; the 247-word window carries the relocated call
at 0x2e0 (d2=0x1e22100), the 151-word DRAW window does not.
- service: sticky svc_gl_vs_call[3] from every 0x3810 run (VS-CALL
receipt), getter gsp_sema_gl_vs_call().
- booter release_save: when the window has no 0x3810 run, prepend the
captured ONE_INCR run (0x3810<-payload) ahead of the DRAW window;
the normal patch relocates the VA payload (sema_gl_mme_reloc).
- vs_pre buffer 12->24 words. Census range stays 0x100..0x1ff (eng76).
|
| |
|
|
|
|
|
|
| |
The beef pushes carry 0x114/0x11c/0x124 runs; extend sema_mme_census
from 0x114..0x124 to the whole 0x100..0x1ff page so every setup
method in that family (3 data words/hit) is visible in the beef
windows (128/151/247/324/491 words) and the X 221-word window. The
existing 0x1c00..0x1cf8/0x600..0x61c ranges stay in the same line.
|
| |
|
|
|
|
|
|
|
|
| |
The per-draw VB bind is still located: extend sema_mme_census to
0x1c00..0x1cf8 (vertex stream FORMAT/LOCATION/SIZE) and 0x600..0x61c
(stream sizes), print up to 3 data words per hit (the location pairs
need UPPER,LOWER), and add a second DRAW-STATE line with the stream
sizes (SZ0/SZ1/SZ3) and the first SET_VERTEX_ATTRIBUTE_A(0..2) words
(ATTR0), so a zero-size stream or a mismatched attribute format is
visible next to VS0 and the viewport.
|
| |
|
|
|
|
|
|
| |
The driver may bind the vertex stream as LOCATION_A(j) (0x1c04+j*0x10,
[UPPER, LOWER]) plus LOCATION_B(j) (0x1c08+j*0x10, [LOWER]) instead of
the combined [FORMAT, UPPER, LOWER] run at 0x1c00. Track the A upper
byte per stream and publish the same sticky base for either shape, so
eng69's release-window prepend works for both client encodings.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
c807: the release DRAW window carries only SET_VERTEX_STREAM_A_FORMAT
(0x1c00 <- 0x1014); its [fmt, UPPER, LOWER] location pair lives in the
client's setup push, so the replay context's stream address is unbound
(DRAW-STATE VS0=0) and the 8x3-vertex DRAW_IAB fetches nothing (wrote=0).
- service: sticky svc_gl_vs_base[8] from every decoded 0x1c00..0x1cf0
count>=3 pair (VS-BIND receipt); re-add those pages to every GL draw
section's candidate page set so the launch can map them; getter
gsp_sema_gl_vs_base().
- booter release_save: when the held window carries the FORMAT but no
count>=3 location pair, prepend a normal INC run
[fmt, UPPER, LOWER] for streams 0 and 3 to the saved window
(MME-VS-BIND synth receipt, MME-CARRY-SAVE vs_pre=N). The normal
window patch relocates the pair to a shadow VA using the saved page
set, so the release draw can fetch its vertices.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
c796: the release armed (MME-CARRY-ARM mode=release, held=68) when the
client's own launch completed the pack, but that launch's poll owned
the forwarding slot; the beef channel unregistered 0.99 s later
(+0.1 s ARM) and the release only saw request-inflight/no-channel.
The client's pack-completing launch is often its last push.
Generalize eng64's chain: after ANY successful GR launch of the
release's own beef handle, if the release is still owed
(gsp_phys_gr_mme_release_owed_for), wait the settle grace in the same
slot, claim and run the release work directly. The synthetic pack
carrier path is unchanged; the release work still owns the outcome
publish and INFLIGHT clear.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
carrier's gate
c779: the pack-continuation carrier completed the pack
(MME-CARRY-COMPLETE gen=4 off=2799/2799) and armed the release
(MME-CARRY-ARM mode=release), but its launch poll held the single
forwarding slot for 2801 ms; the armed release then deferred
request-inflight until the beef channel unregistered at +2.2 s, so the
release ended in MME-CARRY-HOLD reason=no-channel.
- svc_fwd_gr_work: after a successful synthetic pack carrier, wait out
the release grace in the same slot, claim it and run the release work
directly (chained MME-CARRY-FIRE mode=release ... receipt). Gate:
sema_gl_mme_release_chain (default 1; release carrier still default 0).
- pump pack-carry block: an armed due carrier that cannot go out now
names its blocker (MME-CARRY-WAIT reason=no-channel/client-candidate/
request-inflight/fe-defer), so the c781-class silent stall is visible.
- booter: gsp_phys_gr_mme_release_waiting()/chain_enabled() helpers.
c783-c785 (a03a68ea build) were all shallow (author=0, no MME window).
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
default off
The golden overlay writes all 55 slot bodies, but the CALL_MME_MACRO(34)
DRAW_IAB run targets SA[34]; the client's captured SA table only covered
slots 0-11 (c772), so slot 34 resolved to IR 0 (the slot-0 body) and the
macro never produced mac=0x22. Add sema_gl_mme_sa_golden_fill (bool, 0):
for every slot whose client SA entry is missing/zero and whose golden body
exists (kernel/golden-mme-tu104.h golden_mme_tu104_sa[64]), set the SA entry
to the golden body's IR entry (slot 34 = 0x265, 75 words) and mark it
present. Nonzero client entries are never overwritten. Fill runs in the
golden overlay, in the submit path before the stub/call-drop walk, and in
the SA re-arm (the release-carrier path); the release path re-fetches and
emits the filled 0x11c pairs. New MME-GOLDEN sa-fill/sa-census receipts.
c774 proves the fill: `MME-GOLDEN sa-fill slot=34 entry=0x265
(client=missing)`. Enable in params-r1624. Build rc 0; the mac=0x22
validation needs a c772-class release boot.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
re-arm in the pump
The saved-window release carrier was armed inside the pack-completing
launch's own build, and the client-first cancel treated that same launch
(and its retries) as the next client launch, silently dropping the claim.
c762: MME-CARRY-SAVE (win=240 held=68) -> MME-CARRY-ARM mode=release ->
the arming launch ran mac=0 (LOAD-ONLY, window dropped, held CALLs still
owed) -> no FIRE, no synthetic push, no mac=0x22.
Track the arming launch identity (h + push) and keep the claim armed across
it; only the MME-PACK-REARM edge (calls actually released), a real consumer,
context/handle changes, or a launch error cancels/consumes. Add a pump-side
re-arm once pack_done_gen is set, and bounded MME-CARRY-HOLD receipts for
every skip. One fire per pack completion, no retries.
Build rc 0; validation pending (c762-class boot with
sema_gl_mme_pack_release=1).
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
(default off)
When a 324 B draw window holds its CALL runs while the 2799-word pack is
incomplete, the pack can complete later (X lane or a 728 B window) but the
next client launch that would release the held calls is a per-frame lottery
(c756: MME-CALL-HOLD 18, pack complete, no next launch -> no REARM/mac=0x22).
Save the held window at MME-CALL-HOLD (raw pre-relocation stream + the
launch capture fields) into module memory. When the pack is complete and
resident and no client launch consumes the release within
sema_gl_mme_pack_release_ms, re-submit the saved capture through the normal
fill/build path with the held CALL runs KEPT (mme_hold_calls=false), no
prelude emission, and gr_synthetic/no guest release. The released
CALL(34) runs DRAW_IAB against the resident pack, the shape c716 proved.
New: sema_gl_mme_pack_release (bool, 0) / _ms (uint, 100); MME-CARRY-SAVE /
ARM/FIRE/COMPLETE/CANCEL/ABORT mode=release receipts. Beef-only, one fire per
pack completion, fail-closed on context/handle changes or launch errors. The
existing pack-continuation carrier is unchanged with its knob off.
Build rc 0; validation pending.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
image, and harden the author window-head decode
- gsp_phys_booter.c: after authoring the VTG SPH at family+0x900, scan the
patched 3D window for its own 0x2054 slot-1 pair and rewrite an operand
whose low 12 bits are 0x600/0x300 (client family VA or pair-cache shadow
line) to <page>|0x900. The window's own later pair otherwise overwrites
the synthesized prelude j1 and the DS validates the client's SASS page
(c743: DS-IMAGE st1=0b0b7208). New SPH-SLOT1-REWRITE / SPH-SLOT1 receipts.
- gsp_phys_booter.c: reject an inline VTG candidate whose IMAP word (w6,
offset 24) is zero; fall back to the builtin image. A 640 B w6=0 record
authored a zero-map SPH and the DS went to the FECS/PRI sentinel
(c749 fam 0x4350000: ds 80000000->badf1201).
- gsp_sema_service.c: the DDX ring-head decode scans past zero-payload
and unreadable entries within the 8-entry bound instead of stopping
(c746: the ring head is a zero dummy and the C36F release sits later);
it still never fabricates a payload.
Validation: c749 is the first boot with DS-IMAGE st0=st1=020a0481
(code ff007321, the authored VSA/VSB image), a clean slot-1 rewrite
(old=0x01e00300 new=0x01e00900), beef MME-PACK-REARM, and the DS latch
reduced from 86040626 to 84000420; stores are still 0 and the DRAW_IAB
macro is the next gap.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
decode, MME pack carrier, and the pump atomic-sleep hoist
- gsp_phys_booter.c: sema_gl_sph_vtg_auth (default 1) authors the client's
live VTG SPH image at family+0x900 and binds VSA/VSB there; new
SPH-AUTHOR / SPH-ALIAS-auth receipts and a DS-IMAGE stage census at the
DS latch (stage-start w0 + code word through the pair cache).
- gsp_phys_booter.c: sema_gl_mme_pack_carry (default 0) + _ms (default 100)
host-initiated windowless continuation carrier for a split MME pack;
MME-CARRY-ARM/FIRE/COMPLETE/CANCEL/ABORT receipts, beef-only, bounded.
- gsp_sema_service.c: sema_ddx_tracker_auth (default 0) ring-head decode
for the DDX channel when the USERD is missing/reset (guest-authored
C36F release applied verbatim); sema_gr_scan_top default raised to
0x300000000 for the 12 GiB campaign guest.
- gsp_sema_service.c: hoist the r707e VAS candidate verify out of
svc.chan_lock (its vfio_dma_rw path can sleep) and add in_atomic guards
to svc_read/svc_write; fixes the gsp-sema-svc "scheduling while atomic"
pump stall that lost the marked draw-window launch.
- tools: enable sema_ddx_tracker_auth=1 in params-r1624; use timeout -k in
the guest GL/GZDoom wrappers so a wedged GPU wait cannot hang a cycle.
Validation: c741/c743 boots (VTG author byte readback, cross-lane and beef
pack completion + REARM, DS-IMAGE census) and the c743 DS-FAST chain; A/B
for the carrier and the tracker decode is still open.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
draw-synth windows, preserve the last beef push, and default the DS stage-image A/B safe
- gsp_phys_booter.c: the synthesized SPH-BIND stage-block guard
double-counted the already-emitted raster words (101 > 96), silently
skipping j0/j2/j4/j5; pre=29 -> pre=84 and the DS stage VAs populate.
Add the SPH-BIND-STAGE-SKIP receipt.
- gsp_sema_service.c: sema_gl_win_rt0_admit (default 1) admits a beef
draw-synth window whose FIRST colour-target write is a usable
surface-class bind (RT0-FIRST-MISS witness); preserve the most recent
beef push (>=256 B) for the gsp-phys-last-push debugfs dump; skip the
non-RAM windows in the linear ring scan; fix the MME shadow-RAM index
shift to (mthd >> 2) & 0xfff.
- gsp_phys_booter.c: sema_gl_sph_vtg600 (default 0) and
sema_gl_sph_vtg_j1 (default 0) are the stage-image A/B: binding
family+0x600 poisons the DS (the engine-visible alias shadow there is
the client's SASS upload), so keep the historical +0x900 zero page
until a real VTG SPH is authored at an engine-visible VA.
- tools/guest-diag/params-r1624.txt: enable sema_gl_win_rt0_admit.
- wiki/Project-Status.md: 2026-11-15 status (MME chain completes and
executes DRAW_IAB; DS stage image is the named gate).
|
| |
|
|
|
|
|
|
|
| |
Follows the same any-channel rule as sema_mme_prelude_cap_any and emits
'sema-mme-xscan: ... hits=0' when a push yields no MME-family ops (scan
coverage evidence). c693: X-lane pushes (0x120010000/0x1200a0000/0x120010004)
show hits=0 - the indirect-mode X pushes carry no MME setup runs, so the
prelude feed has nothing; the MME setup runs likely ride the beef ring (whose
entries the walk skips as garbage in the read lottery).
|
| |
|
|
|
|
|
|
|
|
|
| |
(sema_mme_prelude_cap_any, default 0) (eng48)
The X DDX indirect lane (h=0x1000013) replays its 3D windows verbatim but
never builds the MME pack because svc_mme_prelude_capture rejects every
non-beef channel, so pl_n=0 and emit_prelude skips. c487 proved the X lane
emits a 2799-word pack when pl_n>0. New bool sema_mme_prelude_cap_any=1
bypasses the beef gate and feeds the same signature-deduped capture;
default 0 keeps legacy beef-only behaviour bit-for-bit. Validation pending.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
window-0 shadow instead of leaving the QMD pointer at an unmapped guest VA (eng33)
The client's MME-expanded draw builds a QMD whose program page (qmd[48])
classifies CODESRC-SUSPECT (empty-page): the engine's GPCCLIENT_GCC I-fetch
then read the guest VA above every engine-PDB window, raised FAULT_PDE and
the FIFO parked for the rest of the boot (the TSG re-arm cannot revive a
parked PBDMA). c361-c368 receipts.
With gsp_phys_gr_codesrc_reloc=1 (default) the builder copies the page into
the window-0 shadow (empty sources only; PTE/module pages are never
republished), overlays the client's own known-good SPH+SASS stage image at
the original QMD program offset (gsp_sema_gl_prog_img, stage-typed from the
section bind; truncated at a 128-bit boundary with a terminal EXIT when the
image is larger than the remaining page), and the existing QMD w48/49 +
prefetch rewrite publishes the shadow VA. If the shadow mapping cannot be
installed the page stays unmapped and the existing refusal drops the launch,
so an unmapped QMD program pointer is never published. 0 restores the old
guest-VA behaviour for a one-flip A/B.
Validation (c373, params-r1624): 31 CODESRC-RELOC events (img_len=384,
off=0xb00, 0 truncations), 51 GR LAUNCH submitted, 11 MME-FAST end
events=3, 79 FETCH-WIT with GP_GET advancing engine-fetched, 0 FAULT_PDE,
0 vgsp-fault, 0 WEDGE-REARM/PARK-RECOVER; work_gr backend_ok=35 fault=0.
The draws still write nothing (NOWRITE, no clear run in the emitted
window), so px0 stays 0 - the store wall is unchanged and is the next
target.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
them to the 3D replay lane, and let the forced golden MME overlay satisfy the prelude maturity gate (eng28)
The direct-GL client's draw-state pushes (476/624/728/324 B; invariant lead
90110087 = IMMD NVC597_INVALIDATE_SHADER_CACHES 0x21C<-0x1011) are
intermittently unreadable while byte-identical copies park in the LOW
framebuffer; the copies do not share the VA's in-page offset, so the
page-stepped rescue scan could never land on them. Add a word-granular
LOW-band sweep gated on the two recognisable push images (state lead via the
method-stream window gate; 256-B VTG SPH upload by exact signature) and pin
hits exactly like the existing rescue.
The same pushes carry the frame's real state (SET_COLOR_CLEAR_VALUE 0xD80,
NVC597_CLEAR_SURFACE 0x19D0, MME macro calls, vertex state) but no BEGIN/RT
opener, so they never opened a C597 section and the state stream never
reached the replay lane; admit the 0x21C lead as an opener on beef channels
and exempt state-led windows from the eng25 colour-target guard (the guard's
data-blob rejects continue unchanged - only the invariant state lead passes).
Where the client's 0x114 IRAM upload is not captured (code words stay <= 4
on every boot observed), the forced golden overlay (sema_gl_mme_golden +
_force; golden-only, fail-closed) can serve every called macro slot; add
gsp_phys_gr_golden_ready() and skip the IMMATURE-SKIP software completion
while it holds (see the golden-slot/pack machinery).
Live (c348/c350/c351, r1624 params): the LOW-band rescue fired (VTG SPH
256-B push -> fb 0x2010200, pinned); the 324-B state push opened a section,
captured (recs=4 nprog=1) and was marked for the verbatim 3D lane; with the
bypass the lane submitted it to the engine for the first time (GR LAUNCH
submitted + GUEST GR LAUNCH OK, MME-PRELUDE pack 1701 IR words, MME-GOLDEN
slot 0 accepted). The emitted 51-word window still omits the 0xD80/0x19D0
clear runs (marked window 81), so pixel stores remain 0 and frames black;
receipts under /tmp/opencode/eng28-*.
Refs: CONT.490.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
push (eng26 instrument)
One green cycle must answer 'which push carries the direct-GL draw'. The
census scans every non-engine push with the canonical op/cnt run grammar and
logs one bounded row per push containing any draw-family method id (BEGIN
0x1618, END 0x1614, VA_START 0xd74, DRAW_VERTEX_ARRAY 0xd78, index
0x17c8/0x17d8/0x17e0, draw list 0x1b0, vertex streams 0x1c00/0x1c10), with
the hit's word index inside its run so a run that merely NUMERICALLY spans a
method address is distinguishable from a real method data word. Beef pushes
without hits are enumerated once per (va,len) so the cycle yields a full push
inventory. Module param sema_draw_census (default 0), 256 hit + 256 push rows,
read-only.
Live result (c346): full beef push inventory captured; every marker 'hit' is
a k>0 lattice artifact of a data blob (e.g. the 59580-B push's single m=0 run
at off=0x78 covers 0x1b0..0x1c10 at fixed word indices, and its BEGIN-address
word value changes between reads - 0x00058202 then 0x01047220), i.e. no push
carries a real draw method stream. Companion to a4215afa; docs in CONT.487.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
unusable (eng25 correctness guard)
The direct-GL lane's draw-synth captures join the verbatim 3D replay lane by
numerical run-cover alone, so a non-method data blob whose INC run merely
spans the C597 RT block is replayed as state: its last A/B/W/H write per
colour target is an unmapped 40-bit VA (c344: RT1 -> 0xff000480a0) and the
engine retires with no stores (NOWRITE wrote=0). Gate the beef 'd' admission
(single-block and chunk-split) on svc_gl_window_rt_valid(): walk the window
with the run grammar, keep the last A/B/W/H write per colour target, and
require at least one usable bind (A[7:0]<=1, B<2^30 aligned, 1<=W,H<=0x4000).
Validated live (c346, mdev 53dc06b5, ENG26 instrument cycle): 23 bounded
'3D mark rejected (beef draw-synth: no valid last colour-target bind)' rows,
including the 14865-word 59580-B blob window @off=0x78 and the 542-word
0x4010ed0 twin; the one timing-variant window that does carry a usable RT
bind still passed and replayed (wrote=0), and the X lane is unregressed
(15x '3D stream marked h=0x1000013' + 'GUEST GR LAUNCH OK' ok=16/17).
Refs: CONT.486/487; eng25/eng26 evidence under /tmp/opencode/eng26-*.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
lane; beef rel_mod launches may take the ch_rel release branch (eng24)
Clause 1 (gsp_sema_service.c, svc_gl_flush): the direct-GL (beef-family)
section captures opened by the eng23 inside-run openers carry synthesized
PROG/PARAM/REL (src=draw-synth) but a REAL method window; include 'd' in
the stream-3d marking (single 448-word block and the method-aligned chunk
split) so the window replays verbatim on the engine like the X/stream/hold
lanes, instead of waiting on a synthesized compute-QMD release the engine
never writes. Verified live: '3D stream chunked h=0xbeef0100 push=0x4250110
window=779 words -> 3 chunk(s)' and 'GR LAUNCH submitted h=0xbeef0100 ...
polling qmd_rel=0'.
Clause 2 (gsp_phys_booter.c, gsp_phys_backend_guest_gr_submit): a
beef-family launch whose QMD release0 was redirected to the module
semaphore with the rel_mod sentinel (0x600df00d) may break its poll on the
channel release alone (the X lane's proven branch) once the engine has
retired the method block; witnessed by 'GR LAUNCH OK ch_rel branch (beef
rel_mod; ...)'. Verified live: 4+ beef launches now complete (engine fetch
OK, GUEST GR LAUNCH OK ok=22..25) where the c338 shape timed out
(qmd_rel=0xc0ffee01 want=0x600df00d).
Known residual (unchanged by this commit): the replayed beef windows retire
without stores (NOWRITE-CONFIRMED/AMBIGUOUS, wrote=0 -> px0=0), the same
engine-store wall the X lane shows; and with the default
sema_mme_immature_skip=1 the service soft-completes replayed beef windows
before any engine contact (A/B with the knob at 0 was used to put the real
window on the engine).
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
channel (eng23, mechanism validated)
The direct-GL (GZDoom/glx) channel family 0xbeef01xx never opened a C597
section because its class bind is channel-side: the client allocates
TURING_A (0xc597) with hParent = its own channel (measured: alloc 0xc597
h=0xbeef9097 parent=0xbeef0100 client=0xc1d00013) and never re-emits a
SET_OBJECT push, so the section recognizer's sticky-attachment gate
(svc_gl_att_accept_run) dropped every push. The X lane binds inline in
its init push and was unaffected.
- gsp_rm_emulation.c: report the 0xc597 allocation's hParent to the sema
service (gsp_sema_service_gl_attach), which applies it as the sticky 3D
attach on its own thread (pending-slot queue; no cross-thread writes to
the attachment tables).
- gsp_sema_service.[ch]: the queue + drain (svc_thread pass), and accept
the inside-run opener shapes on attached channels: the direct-GL client
emits NVC597_BEGIN (0x1618) and the RT-setup family (0x840) as methods
INSIDE multi-method INC runs (measured: run addr=0x80c count=256 covers
0x840..0xc0c; census decoded method=0x1618 op=1 from a run payload),
not as the one-word IMMD form the X lane emits.
- Also carries the eng22-rescue scan-cap widening (0x4000000 -> full 2 GiB
shadow; observed live: "no content-gated window in 0x80000000 shadow").
Validated live (c335/c337/c338, receipts /tmp/opencode/eng23-receipts-c331.txt):
- RM-record attach fires and applies for 0xbeef0100 (c335 12:49:04, c338).
- sections now open (c337) and capture (c338) on 0xbeef0100 incl. the
59556-B setup push and the 6400-B draw push (src=draw-synth).
- first GR LAUNCH submitted for 0xbeef0100 (c338 13:01:58) - fails at the
physical QMD release (qmd_rel=0xc0ffee01 want=0x600df00d); new frontier.
- px0 still 00000000; mission not launched.
A/B control: the same X-lane lottery behaviour was reproduced with the
pre-change module (c333), so no X-lane regression is attributable here.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
end-to-end validation pending)
The direct-GL client's one-shot 59,556 B setup push (VA 0x4001004) reads
zero at decode time: the live page is recycled before our decode runs, so
no C597 bind attaches for h=0xbeef0100. The rescue recovers the push body
from the FB shadow with strict content gates: reject fill windows (require
>=2 multi-word INC runs + >=8 distinct headers), scan at the push VA's
in-page offset (0x4041004 starts 4 B into a page), and log the channel
handle. eng20 refuted the unregistered-VAS hypothesis: the payload pages
DO walk via VAS 0xbeef0300 (0x4000000->pa=0x342ead000,
0x4001000->pa=0x342eae000, consistent delta). Also found: sema_gl_xlate
(absent from params-r1780; default 0) gates every C597 section-recognition
site - with it on, the lane produced its first C597 captures
(127x c305, 20x c307). Validation cyclic c308 (guest init panic) / c309
(QGA wedge) blocked; no observation yet. Unvalidated end to end.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
(svc_pa_max/svc_push_pa_ceiling)
The direct-GL client parks its VAS page directory and push pages in the 4-14
GiB high RAM band while the runtime bound stopped at 10 GiB (param/compile),
so svc_ap_ok rejected every walk read above 10 GiB before vfio_dma_rw could
answer: the client ring walk reported 'L0 read fail' / 'walk rc=-2' on the
one boot the RAM content scan latched the real ring (c296), and the push
bodies stayed unreadable (src=3 window garbage / src=255). svc_pa_max() now
never shrinks below the registered guest-RAM top (sanity-clamped to the scan
max), and svc_push_pa_ceiling() floors on the same live bound. c297 (first
boot with the fix): 'RING-VAS h=0xbeef0100 gpfifo=0x4020000 mapped by VAS
0xbeef0300 (pdb=0x110aae000) -> pa=0x23771f000' and pushdec 'src=4
plausible=1' with the read ceiling witness ceil=0x380000000.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
(entry0==entry1 gate)
The GL client ring content scan admitted the lookalike page measured at
pa 0x10a828000 / 0x10ad3e000 (dword 0x04000100 repeating) whose entry0 and
entry1 decode identically (va=0x4000100 len=262144) and which passed every
window/terminus gate. The pump then read a phantom 256 KiB push at VA
0x4000100 forever (sema-rdw rc=-2, sema-entry: unread, unregistered
submissions=0; c271/c285), poisoning the client-VAS verify chain. A real
ring does not repeat one entry verbatim in slots 0/1.
Partial validation: c288 (fixed module) resolved the REAL ring pair via the
VAS (pa=0x235f7c000, entry0 va=0x4000000 len=2236) and decoded real client
pushes (submissions=15, CB-DIAG match=67). End-to-end pixel validation
(gl_frames px0 != 0) is still pending; c286/c287 did not exercise the scan
(no channel created).
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
survives; zero-store persists)
(a) svc_gl_cb_upload_scan decode now follows the class definitions
(cla16f.h: method 11:0, subchannel 15:13): addr=(hdr&0xfff)<<2, subch=(hdr>>13)&7;
selector B/C swapped (0x2384=B=ADDRESS_UPPER high dword, 0x2388=C=lower,
cla097.h); 0x238c runs apply [offset][constants...] inline data. CB-DIAG
prints subch. Other classes untouched.
(b) Pre-replay CWD poison clear for the stream3d lane: new
gsp_phys_gr_cwd_clear_locked() (checks 0x404490/0x40706c/0x400504 for 0xbadf,
runs the wedge recovery's bounded TSG preempt/resched re-arm + shared latch
wipe) before build_gr_launch; once per launch, stream3d+sema_gr_wedge_recover
gated (CUDA/CE unaffected).
Validation (c250-c254, rich args, ladder armed): the re-arm probes green
('WEDGE-REARM probe rc=0 (engine ALIVE)') but the cwd3 latch does NOT move
('CWD-CLEAR after re-arm ... cwd3=badf5040') and wrote=0 persists (0/1024)
with the 0x1528 trap gone under sema_gl_shader_exc=0 - clause (b) is
falsified as sufficient: the poison is not the TSG/PBDMA context the re-arm
touches. CB-DIAG on these draws shows n3800/n39c8/n2390=0 because bit 12 is
0 on that stream (old/new decodes identical there) - the parser fix stands
on the class definition. X regressed to the DDX DMA wall on these cycles
(DMA-init 0x51 + per-start SIGSEGVs), so clean gl_frames windows were rare.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
pointer pairs (n_data 0->1024)
The final-pixel-wall data window: svc_gr_data_fill discarded a candidate page
that HAD resolved in gr_pages (launch_internal blanket skip: c203 evidence
'page[2] va=0x120400000 pa=0xa00000 ap=2 word=34' + '10 candidate ptrs, 0
pages resolved; 7 dropped' -> GR-DEC n_data=0), and the stream3d lane
(qmd=0x0) never seeded the capture's decoded operand pairs (inline-QMD words
34..47) as candidates. Serve word-34..47 pages from their resolved gr_pages
PA (li_pa, span=1; word 32/48/49 stay excluded as before) and seed the
pointer pairs from a request-carried copy (race-free vs the capture ring).
Live proof c215: 'li cand va=0x120400000 word=34 pa=0xa00000 ap=2' ->
'GR-DEC n_data=1024' (was 0). Residual: the 1524 B first-frame's pointer
pages are not yet resolvable at that instant (n_ptr_req=5 seed_add=0; frames
2+ resolve 1024) - resolver timing, documented.
Also documented (no change): the copy-out refusal for dst=0x120700000 (the
GL client's fixed-CB page) falls through to the forced-seed path and is
benign for pixels; the TRUE px0 blocker is engine-zero-write: every stream3d
launch ends 'NOWRITE-CONFIRMED ... n_data=1024 tracked=1024 wrote=0' +
'NOWRITE-REGS fe_esr=0x80000000 trap=0x8000022c/00000800/00000000' even with
the full RT window (SURF-PRELUDE target=0xa000000) - the engine executes but
stores nothing.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Thread A of the X longevity wall, validated c195/c198 (rich args + tick):
- Adoption grace: gr_ram_userd_adopt_at stamped at every DDX fresh-adopt
site; svc_userd_ddx_reprobe refuses a speculative switch within 1 s of an
adopt (kills the c190/c197 same-pass cascade to frozen lookalikes).
- Clause 3: the last CONFIRMED block is parked (pa/as/put/probes) on every
DDX confirm; svc_userd_ddx_park_probe checks it first in the re-probe and
discovery scan and prefers it when its PUT advances across two probes
(kick excluded, half-ring bound, reset re-syncs).
Receipts: c195 X GREEN >10 min with 0 DMA failures ('shape scan fb 0x8f0000
-> CONFIRMED 2->6 at +63 ms, zero SWITCHED/DEFERRED/REJECTED all boot');
c198 GREEN >2 min likewise (+69 ms confirm, zero switches). Residual
(documented): the RAM-scan 'LIVE' vote can still admit pool lookalikes on a
first generation before any block is parked; the grace only delays that
switch.
Thread B (documented, no change): in c195's green window gl_frames still
reads black (px0=0, ~12 s/frame) although the rich args capture the modern-GL
sections ('sema-gl: 3D stream marked', 'section captured len=1524' + 2 draw
sections, prog-images vs=1408 ps=384) - ZERO GR LAUNCH and zero
readback/copy-out lines; the beef0100 channel re-registers every ~13 s with
submissions=0. Modern-GL work is section-captured but never
executed/forwarded - the next frontier.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
speculative CONFIRM jump
Wall (a) garbage-admission fix, validated c190-c194 (rich args + tick):
- svc_gr_ram_userd_scan and the FB shape scan (svc_chan_userd) now refuse
get > put for the DDX family (svc_userd_ddx_family), dropping the
entries>1024 exemption that admitted c181's 'put=1 get=288190567' block;
bounded refusal logs ('RAM scan REFUSES ...', 'userdp ... REFUSES fb ...
(DDX get>put; c181 garbage class)').
- The pump's speculative CONFIRM bounds a non-wrap DDX (non-kick) forward PUT
jump to gpfifo_entries/2 (mirrors the wrap bound); a runaway jump like
c181's 'put 1 -> 1170688059' now falls to the DEFERRED/REJECT ladder
('forward PUT jump REFUSED ...'). Kick any-step and wrap paths unchanged;
SYS/CE/UVM untouched.
Receipts (5 cycles): 146 refusal lines (80 RAM, 66 FB), ZERO huge-jump
confirms (all 16 confirms are real small steps), real blocks serving 25+24
submissions from pristine fb 0x8f0000 and RAM 0x11ae6e000. Residual wall
(a): a same-pass re-probe switch to a frozen lookalike (c190) and a late
'Failed to idle DMA' at 60-130 s of X life; gl_frames still reads black
(px0=0, ~12 s/frame) in the windows it ran (c193/c194).
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
timeout); DDX latch reset clauses
Wall (b) 'Flip event timeout on head 0' fix (validated c171): NVKMS/kernel-
callback events register hSrcResource=0, so every display UPDATE completion
rode the all-events shotgun (6-7 POST_EVENT records each), the guest's
status-queue read cursor fell 20-44 slots behind (rc=-11 ring-full bursts)
and flip records arrived past the 3 s NvDrm window. Default the r1765 pair
ON - gsp_rm_ev_assoc (hSrc==0 -> alloc-parent channel) and
gsp_disp_events_strict (armed UPDATE posts only to that channel's events,
no fallback) - the exact combination r1771 measured as '0 flip WARNs'.
Validating cycle c171: registrations carry real sources (hEvent=0x1007a
hSrc=0x1001b etc.), UPDATE posts are exact 1:1 (posts=27), WARN count 1 for
the boot, serial timeouts=0 (c160 pre-fix: 34). Both stay runtime-writable.
Also stage the gsp_sema_service.c candidates for wall (a) (the later-DMA
0x51 is a consequence of 'Failed to idle DMA' on a recycled channel): the
served-refusal in svc_userd_ddx_reprobe now exempts a latch reset to put==0,
and the put-reset latch keep extends to the DDX family (was kick-only).
These clauses target c171's observed reset/junk-adopt sequence; validation
pending on a roll where wall (a) is otherwise survivable.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
thrash)
In svc_userd_ddx_reprobe, refuse to switch while the current latch has just
delivered decoded entries (ch->submissions != gr_ram_userd_latch_sub), the
same 'served' criterion the pump's DEFERRED clause uses. The switch path
resets defers=0, so a defers-based guard would have stopped only the first
of c141's six switches; forward-only nput>oput is semantically wrong for
DDX generations (a fresh block starts with a tiny put) and would lock onto
the junk maximum. Validated c150-c153 (rich args + tick): latch SWITCHED
0/run (was 6-8 at ~2 s), sema-xchan uok=1 continuous, and c152/c153 Xorg
logs show ZERO 'Failed to (idle|initialize) DMA'/push-buffer/AddScreen
lines - the ScreenInit DMA instance is now stable on the deferral alone.
Residual (next): Xorg then spins in-kernel (95% CPU, SIGKILL-immune,
xdpyinfo unanswered; userd put=0 get=0 vs last=7098 in sema-xchan is the
lead) - gl_frames still hangs at BAR map.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
re-probe + FB backoff
The X DDX's push-on-demand generations allocate a new USERD control block
every 11-24 s, but the 15 s no-advance judge dropped the latch that had just
passed the DMA test, and the next scan adopted a frozen FB lookalike
(put=2 get=0) - the retry window then closed with 'Failed to idle DMA'.
For the DDX/kick handle families only (0x01xxxxxx / 0xbfef00xx; SYS/CE/UVM
untouched):
- svc_userd_ddx_family() gates all of it;
- a latch that HAS delivered decoded entries (submissions advanced since
adoption, no contradiction) is DEFERRED from rejection (bound 32; timer
reset) instead of dropped;
- before any latch decision (and on a 2 s cadence while unconfirmed) the
content scan re-probes the live path and switches the latch in place to a
newly validated block (svc_userd_ddx_reprobe; near-empty page + ring-entry
validation + PUT-step liveness are the ownership proof);
- after a rejection the FB shape scan backs off 6 s so the RAM scan wins the
window; the DDX re-probe is exempt from the retired slice budget
(rejects < 255).
Validated (c141, rich r1624 args, tick): X ScreenInit passed with ZERO
'Failed to (idle|initialize) DMA' / push-buffer / AddScreen lines; the
channel decoded a 5090+-entry burst and served across block moves
(latch SWITCHED 0x24128e100 -> 0x103774100 -> 0x122309d00, uok=1 held).
Known residual (next refinement): the switch is not yet forward-only/
rate-limited, so lookalike blocks can oscillate at ~2 s and starve the
client; make the switch require nput > latch_put and a >=10 s cadence (or
stop switching once defers>0), then the real block wins.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
One rate-limited (0.5 s) sema-xchan line per pass for the X DDX channel:
rrc/uok/upa/uas/put/get/last/ring_pa/entry0 - names the decode-gate state
independently of the shared userdp budget. Diagnostic only, no behaviour
change. params-r1624.txt is the rich r1624 insmod set as a durable
tools/guest-diag file (INSMOD_PARAMS=tools/guest-diag/params-r1624.txt).
Context (c130/c131 with the rich set): the DDX DMA test now PASSES on most
attempts (tracker release decoded + delivered); the remaining gap is the
USERD speculative-latch lifetime (a latch that delivered the test kick is
REJECTED 15 s later with no PUT advance; the next generation then adopts a
stale VRAM block, put=2 get=0, and the retry window closes) plus a later
'Push buffer object allocation failed: 0x51 NV_ERR_NO_MEMORY' (emulated heap
accounting; 1872 MiB free).
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
and use it on publish/flush
The X DDX/kick channels' nvPush progress semaphore is a 4 KB sysmem surface
whose GPU mapping resolves to the emulated VIDMEM aperture (va 0x20400ffe0 ->
vidmem pa 0x3f8ffe0), while svc_counter_derive only accepted SVC_APERTURE_SYS
translations; it therefore kept a false guest-RAM pair (a page holding
unrelated data) and svc_counter_publish's put-advance both read and wrote the
wrong page through the SYS aperture - the client's tracker never matched and
the DDX failed 'Failed to initialize DMA' after its 10 s push-buffer sanity
test. Carry the aperture with the registration (new svc_channel.counter_ap,
svc_cnt_der[].ap): accept FB translations in the derive chain (chanvas,
vaspaces, discovered; targeted stays SYS), probe with the found aperture,
keep it through pin override/re-registration; svc_counter_publish and
svc_counter_flush_pending read/write through it (release_pa stays SYS).
Live receipts (c109/c110, 12 GiB guest, params-r1780):
- counter derived h=0x1000013 ... pa=0x211c42fe0 (rank=1) with pub-adv
writing 14..26 (was silently skipped on a false page in c107);
- the DDX's OWN C36F tracker releases decode and land:
'sema-push h=0x1000013 va=0x1200a0000 ... rel=0x120001000 pay=1
have_rel=1' -> 'sema-sw h=0x1000013 va=0x120001000 pa=0x11cc68000 ap=1
val=0x1 rc=0 rb_ok=1' - the 10 s push-buffer test's exact wait word is
delivered and the DDX proceeds to further work (values advancing
0x4017e..0x24024f); previously no release ever decoded.
Remaining X-side flakiness (a later DMA init still failing on some
instances) is tracked in the handoff.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
ops tooling
The uncommitted keep-alive change wrote 0xFFFF into slot 0's status field
(u16 at notifier+0x0e) on the X DDX / GLX kick-idle channel families. Ground
truth (570.144 reference sources + stock nvidia_drv.so disassembly): slot 0
of an nvPush notifier block is the ERROR notifier; nvPushCheckChannelError
reads that status and 0xFFFF aborts every nvPushWaitForNotifier/idle wait as
a channel error. There is no pb_kickIfIdle in 570.144 - the DDX DMA-idle
test reads the progress-tracker semaphore word, not this slot. Leave slot 0
untouched; keep the 0x8000->0 completion ack for the remaining slots and the
r864 0xFFFF/0x8000 completion on the RC-watchdog/beef families. Correct the
CONT.408/409 comments accordingly.
New host/guest tooling: gpa.py (QMP gva2gpa), tick_gen.py (guest-RM timer
BO tick), guest_mode.sh (shared nvClip modeNum reader), gl_verify.sh
(X/GLX bring-up with ScreenInit-lottery retries), push_gl_tools.sh, the
gzdoom_pbuf_run.sh guest recipe and the test_tri SDL2 harness validation
program; ignore tools/guest-diag/build/.
|
| | |
|