mm, oom: OOM sysrq should always kill a process
authorJann Horn <jannh@google.com>
Fri, 14 Jan 2022 22:08:27 +0000 (14:08 -0800)
committerLinus Torvalds <torvalds@linux-foundation.org>
Sat, 15 Jan 2022 14:30:30 +0000 (16:30 +0200)
commitf530243a172d2ff03f88d0056f838928d6445c6d
tree6994a5c26a2c615e93fc703eadb90159c7acc19c
parentdad5b0232949818ae581ebd089c7013e2fdbb093
mm, oom: OOM sysrq should always kill a process

The OOM kill sysrq (alt+sysrq+F) should allow the user to kill the
process with the highest OOM badness with a single execution.

However, at the moment, the OOM kill can bail out if an OOM notifier
(e.g.  the i915 one) says that it reclaimed a tiny amount of memory from
somewhere.  That's probably not what the user wants, so skip the bailout
if the OOM was triggered via sysrq.

Link: https://lkml.kernel.org/r/20220106102605.635656-1-jannh@google.com
Signed-off-by: Jann Horn <jannh@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mm/oom_kill.c