Hi Guilherme,
On 10/14/22 15:05, Guilherme G. Piccoli wrote:
Commit b041b525dab9 ("x86/split_lock: Make life miserable for split lockers")
changed the way the split lock detector works when in "warn" mode;
basically, not only it shows the warn message, but also intentionally
introduces a slowdown (through sleeping plus serialization mechanism)
on such task. Based on discussions in [0], seems the warning alone
wasn't enough motivation for userspace developers to fix their
applications.
Happens that originally the proposal in [0] was to add a new mode
which would warns + slowdown the "split locking" task, keeping the
old warn mode untouched. In the end, that idea was discarded and
the regular/default "warn" mode now slowdowns the applications. This
is quite aggressive with regards proprietary/legacy programs that
basically are unable to properly run in kernel with this change.
While is understandable that a malicious application could try a DoS
by split locking, it seems unacceptable to regress old/proprietary
userspace programs through a default configuration that previously
worked. An example of such breakage was reported in [1].
So let's add a sysctl to allow controlling the "misery mode" behavior,
as per Thomas suggestion on [2]. This way, users running legacy and/or
proprietary software are allowed to still execute them with a decent
performance while still observe the warning messages on kernel log.
[0] https://lore.kernel.org/lkml/20220217012721.9694-1-tony.luck@xxxxxxxxx/
[1] https://github.com/doitsujin/dxvk/issues/2938
[2] https://lore.kernel.org/lkml/87pmf4bter.ffs@tglx/
Fixes: b041b525dab9 ("x86/split_lock: Make life miserable for split lockers")
Cc: Andre Almeida <andrealmeid@xxxxxxxxxx>
Cc: Fenghua Yu <fenghua.yu@xxxxxxxxx>
Cc: Joshua Ashton <joshua@xxxxxxxxx>
Cc: Melissa Wen <mwen@xxxxxxxxxx>
Cc: Paul Gofman <pgofman@xxxxxxxxxxxxxxx>
Cc: Pavel Machek <pavel@xxxxxxx>
Cc: Pierre-Loup Griffais <pgriffais@xxxxxxxxxxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Zebediah Figura <zfigura@xxxxxxxxxxxxxxx>
Suggested-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Guilherme G. Piccoli <gpiccoli@xxxxxxxxxx>
Tested-by: André Almeida <andrealmeid@xxxxxxxxxx>
Tested on an Intel i7-1165G7 using a small benchmarking script, the
behavior is effectively reverted when using the sysctl option.
Also, you might want to document this option somewhere? Maybe at
Documentation/admin-guide/sysctl/kernel.rst
