sched/fair: Fix wrong negative conversion in find_energy_efficient_cpu()
PATCH 1/1 sched/fair: Fix wrong negative conversion in find_energy_efficient_cpu()
In find_energy_efficient_cpu() 'cpu_cap' could be less that 'util'. It might be because of RT, DL (so higher sched class than CFS), irq or thermal pressure signal, which reduce the capacity value.
In such situation the result of 'cpu_cap - util' might be negative but stored in the unsigned long. Then it might be compared with other unsigned long when uclamp_rq_util_with() reduced the 'util' such that is passes the fits_capacity() check.
Prevent this situation and make the arithmetic more safe.
--- kernel/sched/fair.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
kernel/sched/fair.c +2 -1
@@ -6594,7 +6594,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) util =cpu_util_next (cpu, p, cpu); cpu_cap =capacity_of (cpu); - spare_cap = cpu_cap - util; + spare_cap = cpu_cap; +lsub_positive (&spare_cap, util);/* * Skip CPUs that cannot satisfy the capacity request.
Signature · 1 line
2.17.1
Quoted 8 lines · Lukasz Luba
In
find_energy_efficient_cpu()'cpu_cap' could be less that 'util'. It might be because of RT, DL (so higher sched class than CFS), irq or thermal pressure signal, which reduce the capacity value.
In such situation the result of 'cpu_cap- util' might be negative but stored in the unsigned long. Then it might be compared with other unsigned long whenuclamp_rq_util_with()reduced the 'util' such that is passes thefits_capacity()check.
Quoted 4 lines
Prevent this situation and make the arithmetic more safe.
Fixes 1d42509e475cd ("sched/fair: Make EAS wakeup placement consideruclamp restrictions")
I was going to say that might even go as far back as:
732cd75b8c92 ("sched/fair: Select an energy-efficient CPU on task wake-up")
but we had a capacity fitness check in the right place back then, which I screwed over with that uclamp_rq_util_with() :/
LGTM, thanks for figuring that one out.
Quoted 19 lines
Signed-off-by Lukasz Luba <[email protected]>--- kernel/sched/fair.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)kernel/sched/fair.c +2
-1@@ -6594,7 +6594,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) util =cpu_util_next (cpu, p, cpu); cpu_cap =capacity_of (cpu); - spare_cap = cpu_cap - util; + spare_cap = cpu_cap; +lsub_positive (&spare_cap, util);/* * Skip CPUs that cannot satisfy the capacity request.
[email protected]
maintainerQuoted 17 lines · Valentin Schneider
Quoted 8 lines · Lukasz Luba
In
find_energy_efficient_cpu()'cpu_cap' could be less that 'util'. It might be because of RT, DL (so higher sched class than CFS), irq or thermal pressure signal, which reduce the capacity value.
In such situation the result of 'cpu_cap- util' might be negative but stored in the unsigned long. Then it might be compared with other unsigned long whenuclamp_rq_util_with()reduced the 'util' such that is passes thefits_capacity()check.Quoted 4 lines
Prevent this situation and make the arithmetic more safe.
Fixes 1d42509e475cd ("sched/fair: Make EAS wakeup placement consideruclamp restrictions")
I was going to say that might even go as far back as:
Quoted 8 lines
732cd75b8c92("sched/fair: Select an energy-efficient CPU on task wake-up")but we had a capacity fitness check in the right place back then, which I screwed over with that
uclamp_rq_util_with():/LGTM, thanks for figuring that one out.
Reviewed-by Valentin Schneider <[email protected]>
Thanks guys!
The following commit has been merged into the sched/core branch of tip:
The following commit has been merged into the sched/core branch of tip:
Commit-ID: da0777d35f47892f359c3f73ea155870bb595700 Gitweb: https://git.kernel.org/tip/da0777d35f47892f359c3f73ea155870bb595700 Author: Lukasz Luba <[email protected]> AuthorDate: Mon, 10 Aug 2020 09:30:04 +01:00 Committer: Peter Zijlstra <[email protected]> CommitterDate: Wed, 26 Aug 2020 12:41:57 +02:00
sched/fair: Fix wrong negative conversion in find_energy_efficient_cpu()
In find_energy_efficient_cpu() 'cpu_cap' could be less that 'util'. It might be because of RT, DL (so higher sched class than CFS), irq or thermal pressure signal, which reduce the capacity value.
In such situation the result of 'cpu_cap - util' might be negative but stored in the unsigned long. Then it might be compared with other unsigned long when uclamp_rq_util_with() reduced the 'util' such that is passes the fits_capacity() check.
Prevent this situation and make the arithmetic more safe.
--- kernel/sched/fair.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
kernel/sched/fair.c +2 -1
@@ -6594,7 +6594,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) util =cpu_util_next (cpu, p, cpu); cpu_cap =capacity_of (cpu); - spare_cap = cpu_cap - util; + spare_cap = cpu_cap; +lsub_positive (&spare_cap, util);/* * Skip CPUs that cannot satisfy the capacity request.