Here is a patch against crash v6.0.2 that adds duplicate node detection per-CPU for the CFS runqueue display in dump_CFS_runqueues() for the runq command.
This resolves the failure to bail-out of the unending looping display I get with the crash dump I have that has a corrupted CFS runqueue containing a loop. Signed-off-by: David Mair <[email protected]> --- task.c | 9 ++++++++- 1 files changed, 8 insertions(+), 1 deletions(-) diff --git a/task.c b/task.c index 433a043..0333fe8 100755 --- a/task.c +++ b/task.c @@ -7050,7 +7050,12 @@ dump_tasks_in_cfs_rq(ulong cfs_rq, ulong skip) OFFSET(sched_entity_run_node)); if (!tc) continue; - dump_task_runq_entry(tc); + if (hq_enter((ulong)tc)) { + dump_task_runq_entry(tc); + } else { + error(WARNING, "Duplicate CFS runqueue node, task %lx, probable loop\n", tc->task); + return total; + } total++; } @@ -7217,10 +7222,12 @@ dump_CFS_runqueues(void) fprintf(fp, " CFS RB_ROOT: %lx\n", (ulong)root); tot = 0; + hq_open(); if (curr_cfs_rq) tot += dump_tasks_in_cfs_rq(curr_cfs_rq, 0); if (cfs_rq != curr_cfs_rq) tot += dump_tasks_in_cfs_rq(cfs_rq, curr_cfs_rq); + hq_close(); if (!tot) { INDENT(5); fprintf(fp, "[no tasks queued]\n"); -- Crash-utility mailing list [email protected] https://www.redhat.com/mailman/listinfo/crash-utility
