Fixes for 5.4

Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/queue-5.4/sched-fair-correctly-insert-cfs_rq-s-to-list-on-unth.patch b/queue-5.4/sched-fair-correctly-insert-cfs_rq-s-to-list-on-unth.patch
new file mode 100644 (file)
index 0000000..959e8f0
--- /dev/null
+++ b/queue-5.4/sched-fair-correctly-insert-cfs_rq-s-to-list-on-unth.patch
@@ -0,0 +1,120 @@
+From 2ce8185d181f56f500e24da1d506d97c762927b6 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Sat, 12 Jun 2021 13:28:15 +0200
+Subject: sched/fair: Correctly insert cfs_rq's to list on unthrottle
+
+From: Odin Ugedal <odin@uged.al>
+
+[ Upstream commit a7b359fc6a37faaf472125867c8dc5a068c90982 ]
+
+Fix an issue where fairness is decreased since cfs_rq's can end up not
+being decayed properly. For two sibling control groups with the same
+priority, this can often lead to a load ratio of 99/1 (!!).
+
+This happens because when a cfs_rq is throttled, all the descendant
+cfs_rq's will be removed from the leaf list. When they initial cfs_rq
+is unthrottled, it will currently only re add descendant cfs_rq's if
+they have one or more entities enqueued. This is not a perfect
+heuristic.
+
+Instead, we insert all cfs_rq's that contain one or more enqueued
+entities, or it its load is not completely decayed.
+
+Can often lead to situations like this for equally weighted control
+groups:
+
+  $ ps u -C stress
+  USER         PID %CPU %MEM    VSZ   RSS TTY      STAT START   TIME COMMAND
+  root       10009 88.8  0.0   3676   100 pts/1    R+   11:04   0:13 stress --cpu 1
+  root       10023  3.0  0.0   3676   104 pts/1    R+   11:04   0:00 stress --cpu 1
+
+Fixes: 31bc6aeaab1d ("sched/fair: Optimize update_blocked_averages()")
+[vingo: !SMP build fix]
+Signed-off-by: Odin Ugedal <odin@uged.al>
+Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
+Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
+Link: https://lore.kernel.org/r/20210612112815.61678-1-odin@uged.al
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ kernel/sched/fair.c | 44 +++++++++++++++++++++++++-------------------
+ 1 file changed, 25 insertions(+), 19 deletions(-)
+
+diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
+index d3f4113e87de..877672df822f 100644
+--- a/kernel/sched/fair.c
++++ b/kernel/sched/fair.c
+@@ -3131,6 +3131,24 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)
+ 
+ #ifdef CONFIG_SMP
+ #ifdef CONFIG_FAIR_GROUP_SCHED
++
++static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
++{
++      if (cfs_rq->load.weight)
++              return false;
++
++      if (cfs_rq->avg.load_sum)
++              return false;
++
++      if (cfs_rq->avg.util_sum)
++              return false;
++
++      if (cfs_rq->avg.runnable_load_sum)
++              return false;
++
++      return true;
++}
++
+ /**
+  * update_tg_load_avg - update the tg's load avg
+  * @cfs_rq: the cfs_rq whose avg changed
+@@ -3833,6 +3851,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
+ 
+ #else /* CONFIG_SMP */
+ 
++static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
++{
++      return true;
++}
++
+ #define UPDATE_TG     0x0
+ #define SKIP_AGE_LOAD 0x0
+ #define DO_ATTACH     0x0
+@@ -4488,8 +4511,8 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
+               cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
+                                            cfs_rq->throttled_clock_task;
+ 
+-              /* Add cfs_rq with already running entity in the list */
+-              if (cfs_rq->nr_running >= 1)
++              /* Add cfs_rq with load or one or more already running entities to the list */
++              if (!cfs_rq_is_decayed(cfs_rq) || cfs_rq->nr_running)
+                       list_add_leaf_cfs_rq(cfs_rq);
+       }
+ 
+@@ -7620,23 +7643,6 @@ static bool __update_blocked_others(struct rq *rq, bool *done)
+ 
+ #ifdef CONFIG_FAIR_GROUP_SCHED
+ 
+-static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
+-{
+-      if (cfs_rq->load.weight)
+-              return false;
+-
+-      if (cfs_rq->avg.load_sum)
+-              return false;
+-
+-      if (cfs_rq->avg.util_sum)
+-              return false;
+-
+-      if (cfs_rq->avg.runnable_load_sum)
+-              return false;
+-
+-      return true;
+-}
+-
+ static bool __update_blocked_fair(struct rq *rq, bool *done)
+ {
+       struct cfs_rq *cfs_rq, *pos;
+-- 
+2.30.2
+

diff --git a/queue-5.4/series b/queue-5.4/series
index 4eb724de23ba18f358d9c0887978a0e05a08011b..3b2cd0f6b4438dc6e044acc1881968e0ace0c2af 100644 (file)
--- a/queue-5.4/series
+++ b/queue-5.4/series
@@ -46,3 +46,4 @@ spi-stm32-qspi-always-wait-busy-bit-to-be-cleared-in.patch
 pinctrl-ralink-rt2880-avoid-to-error-in-calls-is-pin.patch
 radeon-use-memcpy_to-fromio-for-uvd-fw-upload.patch
 hwmon-scpi-hwmon-shows-the-negative-temperature-prop.patch
+sched-fair-correctly-insert-cfs_rq-s-to-list-on-unth.patch