tree c64d29f37f519521cc79a880c514e2fd890dfa8d
parent 35bcb83c787161feaf3bc7bec9f6b88309cdf209
author Xuewei Zhang <xueweiz@google.com> 1570061836 -0700
committer Commit Bot <commit-bot@chromium.org> 1570228461 +0000

FROMLIST: sched/fair: scale quota and period without losing quota/period ratio precision

quota/period ratio is used to ensure a child task group won't get more
bandwidth than the parent task group, and is calculated as:
normalized_cfs_quota() = [(quota_us << 20) / period_us]

If the quota/period ratio was changed during this scaling due to
precision loss, it will cause inconsistency between parent and child
task groups. See below example:
A userspace container manager (kubelet) does three operations:
1) Create a parent cgroup, set quota to 1,000us and period to 10,000us.
2) Create a few children cgroups.
3) Set quota to 1,000us and period to 10,000us on a child cgroup.

These operations are expected to succeed. However, if the scaling of
147/128 happens before step 3), quota and period of the parent cgroup
will be changed:
new_quota: 1148437ns, 1148us
new_period: 11484375ns, 11484us

And when step 3) comes in, the ratio of the child cgroup will be 104857,
which will be larger than the parent cgroup ratio (104821), and will
fail.

Scaling them by a factor of 2 will fix the problem.

Fixes: 2e8e19226398 ("sched/fair: Limit sched_cfs_period_timer() loop to avoid hard lockup")
Signed-off-by: Xuewei Zhang <xueweiz@google.com>
(am from https://lore.kernel.org/patchwork/patch/1135155/)

BUG=b:140873154
TEST=Manually verified with repro at b/140873154

Change-Id: Id39409753442fbf7f6d945c2bbd7f30f12cb1f99
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/third_party/kernel/+/1841892
Reviewed-by: Vaibhav Rustagi <vaibhavrustagi@google.com>
Commit-Queue: Xuewei Zhang <xueweiz@google.com>
Tested-by: Xuewei Zhang <xueweiz@google.com>