From 2133dd1fd82b4fd37df45e134b9a073f081d49d1 Mon Sep 17 00:00:00 2001 From: Arthur Hanson Rasmusson Date: Mon, 28 Sep 2026 07:34:34 -0400 Subject: sema-svc: apply releases promptly and decode compute-push releases The content sweep now: - decodes a release whose method stream continues with any INC_METHOD, not only the CE LAUNCH_DMA group, so the releases at the head of a compute/GR channel's first push are applied too; - remembers releases whose target VA had no translation (deferred list) and retries them every service pass, so a VA->PA injection lands them immediately instead of after the next full sweep; - re-arms the fast sliced sweep for a few seconds after an injection; - treats a channel whose USERD/ring cannot be resolved as stalled, so the sweep keeps looking for the releases its unreadable pushes carry. tools: add per-cdt client-pin helper (sem pages + /dev/nvidia0 windows), sem-page scanner and memprobe fixes (short-read guard, --brief). Live-verified: injecting a client sem page applied 12 deferred releases within a second; the service kept applying (89 -> 202) while cdt ran. --- tools/guest-diag/sempages.py | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100755 tools/guest-diag/sempages.py (limited to 'tools/guest-diag/sempages.py') diff --git a/tools/guest-diag/sempages.py b/tools/guest-diag/sempages.py new file mode 100755 index 0000000..ad4dae6 --- /dev/null +++ b/tools/guest-diag/sempages.py @@ -0,0 +1,37 @@ +#!/usr/bin/env python3 +# Print the distinct pages of the semaphore VAs a process references +# (reuses memprobe.py's scanner; run in the guest as root). The VA window is +# derived from the process's /dev/nvidia* mappings unless lo/hi are given. +# usage: sudo python3 sempages.py [lo] [hi] +import os +import sys + +sys.path.insert(0, '/tmp') +import memprobe as m + +pid = int(sys.argv[1]) +if len(sys.argv) > 3: + lo = int(sys.argv[2], 16) + hi = int(sys.argv[3], 16) +else: + lo = 1 << 64 + hi = 0 + with open('/proc/%d/maps' % pid) as f: + for line in f: + parts = line.split() + if len(parts) < 6 or not parts[5].startswith('/dev/nvidia'): + continue + a, b = parts[0].split('-') + lo = min(lo, int(a, 16)) + hi = max(hi, int(b, 16)) + if hi == 0: + print('no /dev/nvidia mappings') + raise SystemExit(1) + +fd = os.open('/proc/%d/mem' % pid, os.O_RDONLY) +sems = m.sem_objs(pid, fd, lo, hi) +os.close(fd) +pages = sorted({va & ~0xfff for va in sems}) +print('sem VAs: %d pages: %d (window 0x%x..0x%x)' % (len(sems), len(pages), lo, hi)) +for pg in pages: + print('0x%x' % pg) -- cgit v1.2.3