linux-kernel - [RFC v5 0/5] Add support length of each segment in the segcblist (breaks TREE04)

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20200921012152.2831904-1-joel@joelfernandes.org>
Date:   Sun, 20 Sep 2020 21:21:47 -0400
From:   "Joel Fernandes (Google)" <joel@...lfernandes.org>
To:     linux-kernel@...r.kernel.org
Cc:     "Joel Fernandes (Google)" <joel@...lfernandes.org>,
        Ingo Molnar <mingo@...hat.com>,
        Josh Triplett <josh@...htriplett.org>,
        Lai Jiangshan <jiangshanlai@...il.com>,
        Marco Elver <elver@...gle.com>,
        Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
        neeraj.iitr10@...il.com, "Paul E. McKenney" <paulmck@...nel.org>,
        rcu@...r.kernel.org, Steven Rostedt <rostedt@...dmis.org>,
        "Uladzislau Rezki (Sony)" <urezki@...il.com>
Subject: [RFC v5 0/5] Add support length of each segment in the segcblist (breaks TREE04)


NOTE: I marked as RFC since TREE 04 fails even though TREE03 passes. I don't
see any RCU errors in the counters, however when shutdown thread tries to
shutdown the system, it hangs when trying to shutdown the rcu_barrier thread.
My suspicion is this is becaues I broke rcu_barrier() however I can't figure
out how/where.  I added a patch in this series that could fix it, but it still
does not alleviate TREE04's issues.  I also have a feeling this issue is
related to nocb mode.

This is required for several usecases identified. One of them being tracing how
the segmented callback list changes. Tracing this has identified issues in RCU
code in the past.

>From Paul:
Another use case is of course more accurately determining whether a given CPU's
large pile of callbacks can be best served by making grace periods go faster,
invoking callbacks more vigorously, or both.  It should also be possible to
simplify some of the callback handling a bit, given that some of the unnatural
acts are due to there having been no per-batch counts.

Revision history:
v5: Various changes, bug fixes. Discovery of rcu_barrier issue.

v4: Restructured rcu_do_batch() and segcblist merging to avoid issues.
    Fixed minor nit from Davidlohr.
v1->v3: minor nits.
(https://lore.kernel.org/lkml/20200719034210.2382053-1-joel@joelfernandes.org/)

Joel Fernandes (Google) (5):
rcu/tree: Make rcu_do_batch count how many callbacks were executed
rcu/segcblist: Add counters to segcblist datastructure
rcu: Fix rcu_barrier() breakage from earlier patch
rcu/trace: Add tracing for how segcb list changes
rcu/segcblist: Remove useless rcupdate.h include

include/linux/rcu_segcblist.h |   3 +
include/trace/events/rcu.h    |  25 +++++
kernel/rcu/rcu_segcblist.c    | 174 +++++++++++++++++++++++-----------
kernel/rcu/rcu_segcblist.h    |  33 +++++--
kernel/rcu/srcutree.c         |   1 -
kernel/rcu/tree.c             |  22 +++--
6 files changed, 192 insertions(+), 66 deletions(-)

--
2.28.0.681.g6f77f65b4e-goog