It is preferable that WALT window rollover occurs just
before a tick, since the tick is an opportune moment
to record a complete window's statistics, as well as report
those stats to the cpu frequency governor. When CONFIG_HZ
results in a TICK_NSEC that isn't a integral number, this
requirement may be violated. Account for this by reducing
the WALT window size to the nearest multiple of TICK_NSEC.
Commit d368c6faa1 ("sched: walt: fix window misalignment
when HZ=300") attempted to do this but WALT isn't using
MIN_SCHED_RAVG_WINDOW as the window size and the patch was
doing nothing.
Also, change the type of 'walt_disabled' to bool and warn
if an invalid window size causes WALT to be disabled.
Change-Id: Ie3dcfc21a3df4408254ca1165a355bbe391ed5c7
Signed-off-by: Vikram Mulukutla <markivx@codeaurora.org>
(from https://patchwork.kernel.org/patch/9895261/)
This patch adds a parameter to select_task_rq, sibling_count_hint
allowing the caller, where it has this information, to inform the
sched_class the number of tasks that are being woken up as part of
the same event.
The wake_q mechanism is one case where this information is available.
select_task_rq_fair can then use the information to detect that it
needs to widen the search space for task placement in order to avoid
overloading the last-level cache domain's CPUs.
* * *
The reason I am investigating this change is the following use case
on ARM big.LITTLE (asymmetrical CPU capacity): 1 task per CPU, which
all repeatedly do X amount of work then
pthread_barrier_wait (i.e. sleep until the last task finishes its X
and hits the barrier). On big.LITTLE, the tasks which get a "big" CPU
finish faster, and then those CPUs pull over the tasks that are still
running:
v CPU v ->time->
-------------
0 (big) 11111 /333
-------------
1 (big) 22222 /444|
-------------
2 (LITTLE) 333333/
-------------
3 (LITTLE) 444444/
-------------
Now when task 4 hits the barrier (at |) and wakes the others up,
there are 4 tasks with prev_cpu=<big> and 0 tasks with
prev_cpu=<little>. want_affine therefore means that we'll only look
in CPUs 0 and 1 (sd_llc), so tasks will be unnecessarily coscheduled
on the bigs until the next load balance, something like this:
v CPU v ->time->
------------------------
0 (big) 11111 /333 31313\33333
------------------------
1 (big) 22222 /444|424\4444444
------------------------
2 (LITTLE) 333333/ \222222
------------------------
3 (LITTLE) 444444/ \1111
------------------------
^^^
underutilization
So, I'm trying to get want_affine = 0 for these tasks.
I don't _think_ any incarnation of the wakee_flips mechanism can help
us here because which task is waker and which tasks are wakees
generally changes with each iteration.
However pthread_barrier_wait (or more accurately FUTEX_WAKE) has the
nice property that we know exactly how many tasks are being woken, so
we can cheat.
It might be a disadvantage that we "widen" _every_ task that's woken in
an event, while select_idle_sibling would work fine for the first
sd_llc_size - 1 tasks.
IIUC, if wake_affine() behaves correctly this trick wouldn't be
necessary on SMP systems, so it might be best guarded by the presence
of SD_ASYM_CPUCAPACITY?
* * *
Final note..
In order to observe "perfect" behaviour for this use case, I also had
to disable the TTWU_QUEUE sched feature. Suppose during the wakeup
above we are working through the work queue and have placed tasks 3
and 2, and are about to place task 1:
v CPU v ->time->
--------------
0 (big) 11111 /333 3
--------------
1 (big) 22222 /444|4
--------------
2 (LITTLE) 333333/ 2
--------------
3 (LITTLE) 444444/ <- Task 1 should go here
--------------
If TTWU_QUEUE is enabled, we will not yet have enqueued task
2 (having instead sent a reschedule IPI) or attached its load to CPU
2. So we are likely to also place task 1 on cpu 2. Disabling
TTWU_QUEUE means that we enqueue task 2 before placing task 1,
solving this issue. TTWU_QUEUE is there to minimise rq lock
contention, and I guess that this contention is less of an issue on
big.LITTLE systems since they have relatively few CPUs, which
suggests the trade-off makes sense here.
Change-Id: I2080302839a263e0841a89efea8589ea53bbda9c
Signed-off-by: Brendan Jackman <brendan.jackman@arm.com>
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Energy cost estimation has been a long lasting challenge for WALT
because WALT guides CPU frequency based on the CPU utilization of
previous window. Consequently it's not possible to know newly
waking-up task's energy cost until WALT's end of the current window.
The WALT already tracks 'Previous Runnable Sum' (prev_runnable_sum)
and 'Cumulative Runnable Average' (cr_avg). They are designed for
CPU frequency guidance and task placement but unfortunately both
are not suitable for the energy cost estimation.
It's because using prev_runnable_sum for energy cost calculation would
make us to account CPU and task's energy solely based on activity in the
previous window so for example, any task didn't have an activity in the
previous window will be accounted as a 'zero energy cost' task.
Energy estimation with cr_avg is what energy_diff() relies on at present.
However cr_avg can only represent instantaneous picture of energy cost
thus for example, if a CPU was fully occupied for an entire WALT window
and became idle just before window boundary, and if there is a wake-up,
energy_diff() accounts that CPU is a 'zero energy cost' CPU.
As a result, introduce a new accounting unit 'Cumulative Window Demand'.
The cumulative window demand tracks all the tasks' demands have seen in
current window which is neither instantaneous nor actual execution time.
Because task demand represents estimated scaled execution time when the
task runs a full window, accumulation of all the demands represents
predicted CPU load at the end of window.
Thus we can estimate CPU's frequency at the end of current WALT window
with the cumulative window demand.
The use of prev_runnable_sum for the CPU frequency guidance and cr_avg
for the task placement have not changed and these are going to be used
for both purpose while this patch aims to add an additional statistics.
Change-Id: I9908c77ead9973a26dea2b36c001c2baf944d4f5
Signed-off-by: Joonwoo Park <joonwoop@codeaurora.org>
Patch 5680f23f20 ("sched/fair: streamline find_best_target
heuristics") has reworked function find_best_target, as result the
variable "target_util" is useless now. So remove it.
Change-Id: I5447062419e5828a49115119984fac6cd37db034
Signed-off-by: Leo Yan <leo.yan@linaro.org>
schedtune_initialized is protected by CONFIG_CGROUP_SCHEDTUNE, but
is being used without CONFIG_CGROUP_SCHEDTUNE being defined. Add
appropriate ifdefs around the usage of schedtune_initialized to
avoid a compilation error when CONFIG_CGROUP_SCHEDTUNE is not
defined.
Change-Id: Iab79bf053d74db3eeb84c09d71d43b4e39746ed2
Signed-off-by: Russ Weight <russell.h.weight@intel.com>
Signed-off-by: Fei Yang <fei.yang@intel.com>
The group_max_util() function is used to compute the maximum utilization
across the CPUs of a certain energy_env configuration.
Its main client is the energy_diff function when it needs to compute the
SG capacity for one of the before/after scheduling candidates.
Currently, the energy_diff function sets util_delta = 0 when it wants to
compute the energy corresponding to the scheduling candidate where the
task runs in the previous CPU. This implies that, for the task waking up
in the previous CPU we consider only its blocked load tracked by the CPU
RQ. However, in case of a medium-big task which is waking up on a long
time idle CPU, this blocked load can be already completely decayed.
More in general, the current approach is biased towards under-estimating
the capacity requirements for the "before" scheduling candidate.
This patch fixes this by:
- always use the cpu_util_wake() to properly get the utilization of a CPU
without any (partially decayed) contribution of the waking up task
- adding the task utilization to the cpu_util_wake just for the target
cpu
The "target CPU" is defined by the energy_env to be either the src_cpu or
the dst_cpu, depending on which scheduling candidate we are considering.
Finally, since this update removes the last usage of calc_util_delta()
this function is now safely removed.
Change-Id: I20ee1bcf40cee6bf6e265fb2d32ef79061ad6ced
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
The group_norm_util() function is used to compute the normalized
utilization of a SG given a certain energy_env configuration.
The main client of this function is the energy_diff function when it
comes to compute the SG energy for one of the before/after scheduling
candidates.
Currently, the energy_diff function sets util_delta = 0 when it wants to
compute the energy corresponding to the scheduling candidate where the
task runs in the previous CPU. This implies that, for the task waking up
in the previous CPU we consider only its blocked load tracked by the CPU
RQ. However, in case of a medium-big task which is waking up on a long
time idle CPU, this blocked load can be already completely decayed.
More in general, the current approach is biased towards under-estimating
the energy consumption for the "before" scheduling candidate.
This patch fixes this by:
- always use the cpu_util_wake() to properly get the utilization of a CPU
without any (partially decayed) contribution of the waking up task
- adding the task utilization to the cpu_util_wake just for the
target cpu
The "target CPU" is defined by the energy_env to be either the src_cpu
or the dst_cpu, depending on which scheduling candidate we are
considering.
This patch update also the definition of __cpu_norm_util(), which is
currently called just by the group_norm_util() function. This allows to
simplify the code by using this function just to normalize a specified
utilization with respect to a given capacity.
This update allows to completely remove any dependency of
group_norm_util() from calc_util_delta().
Change-Id: I3b6ec50ce8decb1521faae660e326ab3319d3c82
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
For non latency sensitive tasks the goal is to optimize for energy efficiency.
Thus, we should try our best to avoid moving a task on a CPU which is then
going to be marked as overutilized.
Let's use the capacity_margin metric to verify if a candidate target CPU
should be considered without risking to bail out of EAS mode.
Change-Id: Ib3697106f4073aedf4a6c6ce42bd5d000fa8c007
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
The find_best_target can sometimes not return a valid backup CPU, either
because it cannot find one or just becasue it returns prev_cpu as a backup.
In these cases we should skip the energy_diff evaluation for the backup CPU.
Change-Id: I3787dbdfe74122348dd7a7485b88c4679051bd32
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
In systems where SchedTune is enabled, we do not report energy diff for non
boosted tasks. Let's fix this by always genereting an energy_diff event where
however:
nrg.delta = 0, since we skip energy normalization
payoff = nrg.diff, since the payoff is defined just by the energy difference
Change-Id: I9a11ec19b6f56da04147f5ae5b47daf1dd180445
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
We use task_util() in find_idlest_group() via capacity_spare_wake().
This task_util() updated in wake_cap(). However wake_cap() is not the
only reason for ending up in find_idlest_group() - we could have been sent
there by wake_wide(). So explicitly sync the task util with prev_cpu
when we are about to head to find_idlest_group().
We could simply do this at the beginning of
select_task_rq_fair() (i.e. irrespective of whether we're heading to
select_idle_sibling() or find_idlest_group() & co), but I didn't want to
slow down the select_idle_sibling() path more than necessary.
Don't do this during fork balancing, we won't need the task_util and
we'd just clobber the last_update_time, which is supposed to be 0.
Change-Id: I935f4bfdfec3e8b914457aac3387ce264d5fd484
Signed-off-by: Brendan Jackman <brendan.jackman@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andres Oportus <andresoportus@google.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Link: http://lkml.kernel.org/r/20170808095519.10077-1-brendan.jackman@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
(cherry-picked-from: commit ea16f0ea6c tip:sched/core)
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
The "goto force_balance" here is intended to mitigate the fact that
avg_load calculations can result in bad placement decisions when
priority is asymmetrical.
The original commit that adds it:
fab476228b ("sched: Force balancing on newidle balance if local group has capacity")
explains:
Under certain situations, such as a niced down task (i.e. nice =
-15) in the presence of nr_cpus NICE0 tasks, the niced task lands
on a sched group and kicks away other tasks because of its large
weight. This leads to sub-optimal utilization of the
machine. Even though the sched group has capacity, it does not
pull tasks because sds.this_load >> sds.max_load, and f_b_g()
returns NULL.
A similar but inverted issue also affects ARM big.LITTLE (asymmetrical CPU
capacity) systems - consider 8 always-running, same-priority tasks on a
system with 4 "big" and 4 "little" CPUs. Suppose that 5 of them end up on
the "big" CPUs (which will be represented by one sched_group in the DIE
sched_domain) and 3 on the "little" (the other sched_group in DIE), leaving
one CPU unused. Because the "big" group has a higher group_capacity its
avg_load may not present an imbalance that would cause migrating a
task to the idle "little".
The force_balance case here solves the problem but currently only for
CPU_NEWLY_IDLE balances, which in theory might never happen on the
unused CPU. Including CPU_IDLE in the force_balance case means
there's an upper bound on the time before we can attempt to solve the
underutilization: after DIE's sd->balance_interval has passed the
next nohz balance kick will help us out.
Change-Id: I807ba5cba0ef1b8bbec02cbcd4755fd32af10135
Signed-off-by: Brendan Jackman <brendan.jackman@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170807163900.25180-1-brendan.jackman@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
(cherry-picked-from: commit 583ffd99d7 tip:sched/core)
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
Add the update_rq_clock() call at the top of the callstack instead of
at the bottom where we find it missing, this to aid later effort to
minimize the number of update_rq_lock() calls.
WARNING: CPU: 30 PID: 194 at ../kernel/sched/sched.h:797 assert_clock_updated()
rq->clock_update_flags < RQCF_ACT_SKIP
Call Trace:
dump_stack()
__warn()
warn_slowpath_fmt()
assert_clock_updated.isra.63.part.64()
can_migrate_task()
load_balance()
pick_next_task_fair()
__schedule()
schedule()
worker_thread()
kthread()
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
(cherry picked from commit 3bed5e2166)
Change-Id: Ief5070dcce486535334dcb739ee16b989ea9df42
Signed-off-by: Brendan Jackman <brendan.jackman@arm.com>
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
Instead of adding the update_rq_clock() all the way at the bottom of
the callstack, add one at the top, this to aid later effort to
minimize update_rq_lock() calls.
WARNING: CPU: 0 PID: 1 at ../kernel/sched/sched.h:797 detach_task_cfs_rq()
rq->clock_update_flags < RQCF_ACT_SKIP
Call Trace:
dump_stack()
__warn()
warn_slowpath_fmt()
detach_task_cfs_rq()
switched_from_fair()
__sched_setscheduler()
_sched_setscheduler()
sched_set_stop_task()
cpu_stop_create()
__smpboot_create_thread.part.2()
smpboot_register_percpu_thread_cpumask()
cpu_stop_init()
do_one_initcall()
? print_cpu_info()
kernel_init_freeable()
? rest_init()
kernel_init()
ret_from_fork()
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
(cherry picked from commit 80f5c1b84b)
Change-Id: Ibffde077d18eabec4c2984158bd9d6d73bd0fb96
Signed-off-by: Brendan Jackman <brendan.jackman@arm.com>
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
During fork, the utilization of a task is init once the rq has been
selected because the current utilization level of the rq is used to
set the utilization of the fork task. As the task's utilization is
still 0 at this step of the fork sequence, it doesn't make sense to
look for some spare capacity that can fit the task's utilization.
Furthermore, I can see perf regressions for the test:
hackbench -P -g 1
because the least loaded policy is always bypassed and tasks are not
spread during fork.
With this patch and the fix below, we are back to same performances as
for v4.8. The fix below is only a temporary one used for the test
until a smarter solution is found because we can't simply remove the
test which is useful for others benchmarks
| @@ -5708,13 +5708,6 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
|
| avg_cost = this_sd->avg_scan_cost;
|
| - /*
| - * Due to large variance we need a large fuzz factor; hackbench in
| - * particularly is sensitive here.
| - */
| - if ((avg_idle / 512) < avg_cost)
| - return -1;
| -
| time = local_clock();
|
| for_each_cpu_wrap(cpu, sched_domain_span(sd), target, wrap) {
Tested-by: Matt Fleming <matt@codeblueprint.co.uk>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Matt Fleming <matt@codeblueprint.co.uk>
Acked-by: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: dietmar.eggemann@arm.com
Cc: kernellwp@gmail.com
Cc: umgwanakikbuti@gmail.com
Cc: yuyang.du@intel.comc
Link: http://lkml.kernel.org/r/1481216215-24651-2-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
(cherry picked from commit f519a3f1c6)
Signed-off-by: Brendan Jackman <brendan.jackman@arm.com>
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
Change-Id: I86cc2ad81af3467c0b2f82b995111f428248baa4
Vincent and Yuyang found another few scenarios in which entity
tracking goes wobbly.
The scenarios are basically due to the fact that new tasks are not
immediately attached and thereby differ from the normal situation -- a
task is always attached to a cfs_rq load average (such that it
includes its blocked contribution) and are explicitly
detached/attached on migration to another cfs_rq.
Scenario 1: switch to fair class
p->sched_class = fair_class;
if (queued)
enqueue_task(p);
...
enqueue_entity()
enqueue_entity_load_avg()
migrated = !sa->last_update_time (true)
if (migrated)
attach_entity_load_avg()
check_class_changed()
switched_from() (!fair)
switched_to() (fair)
switched_to_fair()
attach_entity_load_avg()
If @p is a new task that hasn't been fair before, it will have
!last_update_time and, per the above, end up in
attach_entity_load_avg() _twice_.
Scenario 2: change between cgroups
sched_move_group(p)
if (queued)
dequeue_task()
task_move_group_fair()
detach_task_cfs_rq()
detach_entity_load_avg()
set_task_rq()
attach_task_cfs_rq()
attach_entity_load_avg()
if (queued)
enqueue_task();
...
enqueue_entity()
enqueue_entity_load_avg()
migrated = !sa->last_update_time (true)
if (migrated)
attach_entity_load_avg()
Similar as with scenario 1, if @p is a new task, it will have
!load_update_time and we'll end up in attach_entity_load_avg()
_twice_.
Furthermore, notice how we do a detach_entity_load_avg() on something
that wasn't attached to begin with.
As stated above; the problem is that the new task isn't yet attached
to the load tracking and thereby violates the invariant assumption.
This patch remedies this by ensuring a new task is indeed properly
attached to the load tracking on creation, through
post_init_entity_util_avg().
Of course, this isn't entirely as straightforward as one might think,
since the task is hashed before we call wake_up_new_task() and thus
can be poked at. We avoid this by adding TASK_NEW and teaching
cpu_cgroup_can_attach() to refuse such tasks.
.:: BACKPORT
Complicated by the fact that mch of the lines changed by the original
of this commit were then changed by:
df217913e7 sched/fair: Factorize attach/detach entity <Vincent Guittot>
and then
d31b1a66cb sched/fair: Factorize PELT update <Vincent Guittot>
, which have both already been backported here.
Reported-by: Yuyang Du <yuyang.du@intel.com>
Reported-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
(cherry picked from commit 7dc603c902)
Change-Id: Ibc59eb52310a62709d49a744bd5a24e8b97c4ae8
Signed-off-by: Brendan Jackman <brendan.jackman@arm.com>
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
A new fair task is detached and attached from/to task_group with:
cgroup_post_fork()
ss->fork(child) := cpu_cgroup_fork()
sched_move_task()
task_move_group_fair()
Which is wrong, because at this point in fork() the task isn't fully
initialized and it cannot 'move' to another group, because its not
attached to any group as yet.
In fact, cpu_cgroup_fork() needs a small part of sched_move_task() so we
can just call this small part directly instead sched_move_task(). And
the task doesn't really migrate because it is not yet attached so we
need the following sequence:
do_fork()
sched_fork()
__set_task_cpu()
cgroup_post_fork()
set_task_rq() # set task group and runqueue
wake_up_new_task()
select_task_rq() can select a new cpu
__set_task_cpu
post_init_entity_util_avg
attach_task_cfs_rq()
activate_task
enqueue_task
This patch makes that happen.
BACKPORT: Difference from original commit:
- Removed use of DEQUEUE_MOVE (which isn't defined in 4.4) in
dequeue_task flags
- Replaced "struct rq_flags rf" with "unsigned long flags".
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
[ Added TASK_SET_GROUP to set depth properly. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
(cherry picked from commit ea86cb4b76)
Change-Id: I8126fd923288acf961218431ffd29d6bf6fd8d72
Signed-off-by: Brendan Jackman <brendan.jackman@arm.com>
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
The task_fork_fair() callback already calls __set_task_cpu() and takes
rq->lock.
If we move the sched_class::task_fork callback in sched_fork() under
the existing p->pi_lock, right after its set_task_cpu() call, we can
avoid doing two such calls and omit the IRQ disabling on the rq->lock.
Change to __set_task_cpu() to skip the migration bits, this is a new
task, not a migration. Similarly, make wake_up_new_task() use
__set_task_cpu() for the same reason, the task hasn't actually
migrated as it hasn't ever ran.
This cures the problem of calling migrate_task_rq_fair(), which does
remove_entity_from_load_avg() on tasks that have never been added to
the load avg to begin with.
This bug would result in transiently messed up load_avg values, averaged
out after a few dozen milliseconds. This is probably the reason why
this bug was not found for such a long time.
Reported-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
(cherry picked from commit e210bffd39)
Change-Id: Icbddbaa6e8c1071859673d8685bc3f38955cf144
Signed-off-by: Brendan Jackman <brendan.jackman@arm.com>
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
While set_task_rq_fair() is introduced in mainline by commit ad936d8658
("sched/fair: Make it possible to account fair load avg consistently"),
the function results to be introduced here by the backport of
commit 09a43ace1f ("sched/fair: Propagate load during synchronous
attach/detach"). The problem (apart from the confusion introduced by the
backport) is actually that set_task_rq_fair() is currently not called at
all.
Fix the problem by backporting again commit ad936d8658
("sched/fair: Make it possible to account fair load avg consistently").
Original change log:
The current code accounts for the time a task was absent from the fair
class (per ATTACH_AGE_LOAD). However it does not work correctly when a
task got migrated or moved to another cgroup while outside of the fair
class.
This patch tries to address that by aging on migration. We locklessly
read the 'last_update_time' stamp from both the old and new cfs_rq,
ages the load upto the old time, and sets it to the new time.
These timestamps should in general not be more than 1 tick apart from
one another, so there is a definite bound on things.
Signed-off-by: Byungchul Park <byungchul.park@lge.com>
[ Changelog, a few edits and !SMP build fix ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1445616981-29904-2-git-send-email-byungchul.park@lge.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
(cherry-picked from ad936d8658)
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
Change-Id: I17294ab0ada3901d35895014715fd60952949358
Signed-off-by: Brendan Jackman <brendan.jackman@arm.com>
When using schedfreq on cpus with max capacity significantly smaller than
1024, the tick update uses non-normalised capacities - this leads to
selecting an incorrect OPP as we were scaling the frequency as if the
max capacity achievable was 1024 rather than the max for that particular
cpu or group. This could result in a cpu being stuck at the lowest OPP
and unable to generate enough utilisation to climb out if the max
capacity is significantly smaller than 1024.
Instead, normalize the capacity to be in the range 0-1024 in the tick
so that when we later select a frequency, we get the correct one.
Also comments updated to be clearer about what is needed.
Change-Id: Id84391c7ac015311002ada21813a353ee13bee60
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
Show the high watermark of the index into the alloc->pages
array, to facilitate sizing the buffer on a per-process
basis.
Change-Id: I2b40cd16628e0ee45216c51dc9b3c5b0c862032e
Signed-off-by: Martijn Coenen <maco@android.com>
This flag determines whether the thread should currently
process the work in the thread->todo worklist.
The prime usecase for this is improving the performance
of synchronous transactions: all synchronous transactions
post a BR_TRANSACTION_COMPLETE to the calling thread,
but there's no reason to return that command to userspace
right away - userspace anyway needs to wait for the reply.
Likewise, a synchronous transaction that contains a binder
object can cause a BC_ACQUIRE/BC_INCREFS to be returned to
userspace; since the caller must anyway hold a strong/weak
ref for the duration of the call, postponing these commands
until the reply comes in is not a problem.
Note that this flag is not used to determine whether a
thread can handle process work; a thread should never pick
up process work when thread work is still pending.
Before patch:
------------------------------------------------------------------
Benchmark Time CPU Iterations
------------------------------------------------------------------
BM_sendVec_binderize/4 45959 ns 20288 ns 34351
BM_sendVec_binderize/8 45603 ns 20080 ns 34909
BM_sendVec_binderize/16 45528 ns 20113 ns 34863
BM_sendVec_binderize/32 45551 ns 20122 ns 34881
BM_sendVec_binderize/64 45701 ns 20183 ns 34864
BM_sendVec_binderize/128 45824 ns 20250 ns 34576
BM_sendVec_binderize/256 45695 ns 20171 ns 34759
BM_sendVec_binderize/512 45743 ns 20211 ns 34489
BM_sendVec_binderize/1024 46169 ns 20430 ns 34081
After patch:
------------------------------------------------------------------
Benchmark Time CPU Iterations
------------------------------------------------------------------
BM_sendVec_binderize/4 42939 ns 17262 ns 40653
BM_sendVec_binderize/8 42823 ns 17243 ns 40671
BM_sendVec_binderize/16 42898 ns 17243 ns 40594
BM_sendVec_binderize/32 42838 ns 17267 ns 40527
BM_sendVec_binderize/64 42854 ns 17249 ns 40379
BM_sendVec_binderize/128 42881 ns 17288 ns 40427
BM_sendVec_binderize/256 42917 ns 17297 ns 40429
BM_sendVec_binderize/512 43184 ns 17395 ns 40411
BM_sendVec_binderize/1024 43119 ns 17357 ns 40432
Signed-off-by: Martijn Coenen <maco@android.com>
Change-Id: Ia70287066d62aba64e98ac44ff1214e37ca75693
(cherry picked from commit 82d24d114f)
Commit a1d5ebaf8c ("arm64: big-endian: don't treat code as data when
copying sigret code") moved the 32-bit sigreturn trampoline code from
the aarch32_sigret_code array to kuser32.S. The commit removed the
array definition from signal32.c, but not its declaration in
signal32.h. Remove the leftover declaration.
Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com>
Signed-off-by: Mark Salyzyn <salyzyn@android.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Bug: 20045882
Bug: 63737556
Change-Id: Ic8a5f0e367f0ecd5c5ddd9e3885d0285f91cf89e
The util returned from group_max_util is not capped at the max util
present in the group, so it can be larger than the capacity stored in
the array. Ensure that when this happens, we always use the last entry
in the array to fetch energy from.
Tested with synthetics on Juno board.
Bug: 38159576
Change-Id: I89fb52fb7e68fa3e682e308acc232596672d03f7
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
The code is to get the CPU util by accumulate different scheduling
classes and when the total util value is larger than CPU capacity
then it clamps util to CPU maximum capacity. So we can get correct util
value when use PELT signal but if with WALT signal it misses to clamp
util value.
On the other hand, WALT doesn't accumulate different class utilization
but it needs to applying boost margin for WALT signal the CPU util
value is possible to be larger than CPU capacity; so this patch is to
always clamp util to CPU maximum capacity.
Change-Id: I05481ddbf20246bb9be15b6bd21b6ec039015ea8
Signed-off-by: Leo Yan <leo.yan@linaro.org>
When we convert capacity into frequency, we used policy->max to get
the max freq of the cpu. Since this can be changed by userspace policy
or thermal events, we are potentially asking for a lower frequency
than the utilization demands.
Change over to using cpuinfo.max which is the max freq supported by
that cpu rather than the currently-chosen max. Frequency granted still
honours the max policy.
Tested by setting a userspace policy and observing the relevant vars
in a trace. In this instance, we ask for around 1ghz instead of 620MHz.
freq_new=1013512
unfixed_freq_new=624487
capacity=546
cpuinfo_max=1900800
policy_max=1171200
Change-Id: I8c5694db42243c6fb78bb9be9046b06ac81295e7
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
Changes in 4.4.94
percpu: make this_cpu_generic_read() atomic w.r.t. interrupts
drm/dp/mst: save vcpi with payloads
MIPS: Fix minimum alignment requirement of IRQ stack
sctp: potential read out of bounds in sctp_ulpevent_type_enabled()
bpf/verifier: reject BPF_ALU64|BPF_END
udpv6: Fix the checksum computation when HW checksum does not apply
ip6_gre: skb_push ipv6hdr before packing the header in ip6gre_header
net: emac: Fix napi poll list corruption
packet: hold bind lock when rebinding to fanout hook
bpf: one perf event close won't free bpf program attached by another perf event
isdn/i4l: fetch the ppp_write buffer in one shot
vti: fix use after free in vti_tunnel_xmit/vti6_tnl_xmit
l2tp: Avoid schedule while atomic in exit_net
l2tp: fix race condition in l2tp_tunnel_delete
tun: bail out from tun_get_user() if the skb is empty
packet: in packet_do_bind, test fanout with bind_lock held
packet: only test po->has_vnet_hdr once in packet_snd
net: Set sk_prot_creator when cloning sockets to the right proto
tipc: use only positive error codes in messages
Revert "bsg-lib: don't free job in bsg_prepare_job"
locking/lockdep: Add nest_lock integrity test
watchdog: kempld: fix gcc-4.3 build
irqchip/crossbar: Fix incorrect type of local variables
mac80211_hwsim: check HWSIM_ATTR_RADIO_NAME length
mac80211: fix power saving clients handling in iwlwifi
net/mlx4_en: fix overflow in mlx4_en_init_timestamp()
netfilter: nf_ct_expect: Change __nf_ct_expect_check() return value.
iio: adc: xilinx: Fix error handling
Btrfs: send, fix failure to rename top level inode due to name collision
f2fs: do not wait for writeback in write_begin
md/linear: shutup lockdep warnning
sparc64: Migrate hvcons irq to panicked cpu
net/mlx4_core: Fix VF overwrite of module param which disables DMFS on new probed PFs
crypto: xts - Add ECB dependency
ocfs2/dlmglue: prepare tracking logic to avoid recursive cluster lock
slub: do not merge cache if slub_debug contains a never-merge flag
scsi: scsi_dh_emc: return success in clariion_std_inquiry()
net: mvpp2: release reference to txq_cpu[] entry after unmapping
i2c: at91: ensure state is restored after suspending
ceph: clean up unsafe d_parent accesses in build_dentry_path
uapi: fix linux/rds.h userspace compilation errors
uapi: fix linux/mroute6.h userspace compilation errors
target/iscsi: Fix unsolicited data seq_end_offset calculation
nfsd/callback: Cleanup callback cred on shutdown
cpufreq: CPPC: add ACPI_PROCESSOR dependency
Revert "tty: goldfish: Fix a parameter of a call to free_irq"
Linux 4.4.94
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
[ Upstream commit a578884fa0 ]
Without the Kconfig dependency, we can get this warning:
warning: ACPI_CPPC_CPUFREQ selects ACPI_CPPC_LIB which has unmet direct dependencies (ACPI && ACPI_PROCESSOR)
Fixes: 5477fb3bd1 (ACPI / CPPC: Add a CPUFreq driver for use with CPPC)
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 4d65491c26 ]
In case of unsolicited data for the first sequence
seq_end_offset must be set to minimum of total data length
and FirstBurstLength, so do not add cmd->write_data_done
to the min of total data length and FirstBurstLength.
This patch avoids that with ImmediateData=Yes, InitialR2T=No,
MaxXmitDataSegmentLength < FirstBurstLength that a WRITE command
with IO size above FirstBurstLength triggers sequence error
messages, for example
Set following parameters on target (linux-4.8.12)
ImmediateData = Yes
InitialR2T = No
MaxXmitDataSegmentLength = 8k
FirstBurstLength = 64k
Log in from Open iSCSI initiator and execute
dd if=/dev/zero of=/dev/sdb bs=128k count=1 oflag=direct
Error messages on target
Command ITT: 0x00000035 with Offset: 65536, Length: 8192 outside
of Sequence 73728:131072 while DataSequenceInOrder=Yes.
Command ITT: 0x00000035, received DataSN: 0x00000001 higher than
expected 0x00000000.
Unable to perform within-command recovery while ERL=0.
Signed-off-by: Varun Prakash <varun@chelsio.com>
[ bvanassche: Use min() instead of open-coding it / edited patch description ]
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 72aa107df6 ]
Include <linux/in6.h> to fix the following linux/mroute6.h userspace
compilation errors:
/usr/include/linux/mroute6.h:80:22: error: field 'mf6cc_origin' has incomplete type
struct sockaddr_in6 mf6cc_origin; /* Origin of mcast */
/usr/include/linux/mroute6.h:81:22: error: field 'mf6cc_mcastgrp' has incomplete type
struct sockaddr_in6 mf6cc_mcastgrp; /* Group in question */
/usr/include/linux/mroute6.h:91:22: error: field 'src' has incomplete type
struct sockaddr_in6 src;
/usr/include/linux/mroute6.h:92:22: error: field 'grp' has incomplete type
struct sockaddr_in6 grp;
/usr/include/linux/mroute6.h:132:18: error: field 'im6_src' has incomplete type
struct in6_addr im6_src, im6_dst;
/usr/include/linux/mroute6.h:132:27: error: field 'im6_dst' has incomplete type
struct in6_addr im6_src, im6_dst;
Signed-off-by: Dmitry V. Levin <ldv@altlinux.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit feb0869d90 ]
Consistently use types from linux/types.h to fix the following
linux/rds.h userspace compilation errors:
/usr/include/linux/rds.h:106:2: error: unknown type name 'uint8_t'
uint8_t name[32];
/usr/include/linux/rds.h:107:2: error: unknown type name 'uint64_t'
uint64_t value;
/usr/include/linux/rds.h:117:2: error: unknown type name 'uint64_t'
uint64_t next_tx_seq;
/usr/include/linux/rds.h:118:2: error: unknown type name 'uint64_t'
uint64_t next_rx_seq;
/usr/include/linux/rds.h:121:2: error: unknown type name 'uint8_t'
uint8_t transport[TRANSNAMSIZ]; /* null term ascii */
/usr/include/linux/rds.h:122:2: error: unknown type name 'uint8_t'
uint8_t flags;
/usr/include/linux/rds.h:129:2: error: unknown type name 'uint64_t'
uint64_t seq;
/usr/include/linux/rds.h:130:2: error: unknown type name 'uint32_t'
uint32_t len;
/usr/include/linux/rds.h:135:2: error: unknown type name 'uint8_t'
uint8_t flags;
/usr/include/linux/rds.h:139:2: error: unknown type name 'uint32_t'
uint32_t sndbuf;
/usr/include/linux/rds.h:144:2: error: unknown type name 'uint32_t'
uint32_t rcvbuf;
/usr/include/linux/rds.h:145:2: error: unknown type name 'uint64_t'
uint64_t inum;
/usr/include/linux/rds.h:153:2: error: unknown type name 'uint64_t'
uint64_t hdr_rem;
/usr/include/linux/rds.h:154:2: error: unknown type name 'uint64_t'
uint64_t data_rem;
/usr/include/linux/rds.h:155:2: error: unknown type name 'uint32_t'
uint32_t last_sent_nxt;
/usr/include/linux/rds.h:156:2: error: unknown type name 'uint32_t'
uint32_t last_expected_una;
/usr/include/linux/rds.h:157:2: error: unknown type name 'uint32_t'
uint32_t last_seen_una;
/usr/include/linux/rds.h:164:2: error: unknown type name 'uint8_t'
uint8_t src_gid[RDS_IB_GID_LEN];
/usr/include/linux/rds.h:165:2: error: unknown type name 'uint8_t'
uint8_t dst_gid[RDS_IB_GID_LEN];
/usr/include/linux/rds.h:167:2: error: unknown type name 'uint32_t'
uint32_t max_send_wr;
/usr/include/linux/rds.h:168:2: error: unknown type name 'uint32_t'
uint32_t max_recv_wr;
/usr/include/linux/rds.h:169:2: error: unknown type name 'uint32_t'
uint32_t max_send_sge;
/usr/include/linux/rds.h:170:2: error: unknown type name 'uint32_t'
uint32_t rdma_mr_max;
/usr/include/linux/rds.h:171:2: error: unknown type name 'uint32_t'
uint32_t rdma_mr_size;
/usr/include/linux/rds.h:212:9: error: unknown type name 'uint64_t'
typedef uint64_t rds_rdma_cookie_t;
/usr/include/linux/rds.h:215:2: error: unknown type name 'uint64_t'
uint64_t addr;
/usr/include/linux/rds.h:216:2: error: unknown type name 'uint64_t'
uint64_t bytes;
/usr/include/linux/rds.h:221:2: error: unknown type name 'uint64_t'
uint64_t cookie_addr;
/usr/include/linux/rds.h:222:2: error: unknown type name 'uint64_t'
uint64_t flags;
/usr/include/linux/rds.h:228:2: error: unknown type name 'uint64_t'
uint64_t cookie_addr;
/usr/include/linux/rds.h:229:2: error: unknown type name 'uint64_t'
uint64_t flags;
/usr/include/linux/rds.h:234:2: error: unknown type name 'uint64_t'
uint64_t flags;
/usr/include/linux/rds.h:240:2: error: unknown type name 'uint64_t'
uint64_t local_vec_addr;
/usr/include/linux/rds.h:241:2: error: unknown type name 'uint64_t'
uint64_t nr_local;
/usr/include/linux/rds.h:242:2: error: unknown type name 'uint64_t'
uint64_t flags;
/usr/include/linux/rds.h:243:2: error: unknown type name 'uint64_t'
uint64_t user_token;
/usr/include/linux/rds.h:248:2: error: unknown type name 'uint64_t'
uint64_t local_addr;
/usr/include/linux/rds.h:249:2: error: unknown type name 'uint64_t'
uint64_t remote_addr;
/usr/include/linux/rds.h:252:4: error: unknown type name 'uint64_t'
uint64_t compare;
/usr/include/linux/rds.h:253:4: error: unknown type name 'uint64_t'
uint64_t swap;
/usr/include/linux/rds.h:256:4: error: unknown type name 'uint64_t'
uint64_t add;
/usr/include/linux/rds.h:259:4: error: unknown type name 'uint64_t'
uint64_t compare;
/usr/include/linux/rds.h:260:4: error: unknown type name 'uint64_t'
uint64_t swap;
/usr/include/linux/rds.h:261:4: error: unknown type name 'uint64_t'
uint64_t compare_mask;
/usr/include/linux/rds.h:262:4: error: unknown type name 'uint64_t'
uint64_t swap_mask;
/usr/include/linux/rds.h:265:4: error: unknown type name 'uint64_t'
uint64_t add;
/usr/include/linux/rds.h:266:4: error: unknown type name 'uint64_t'
uint64_t nocarry_mask;
/usr/include/linux/rds.h:269:2: error: unknown type name 'uint64_t'
uint64_t flags;
/usr/include/linux/rds.h:270:2: error: unknown type name 'uint64_t'
uint64_t user_token;
/usr/include/linux/rds.h:274:2: error: unknown type name 'uint64_t'
uint64_t user_token;
/usr/include/linux/rds.h:275:2: error: unknown type name 'int32_t'
int32_t status;
Signed-off-by: Dmitry V. Levin <ldv@altlinux.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit c6b0b656ca ]
While we hold a reference to the dentry when build_dentry_path is
called, we could end up racing with a rename that changes d_parent.
Handle that situation correctly, by using the rcu_read_lock to
ensure that the parent dentry and inode stick around long enough
to safely check ceph_snap and ceph_ino.
Link: http://tracker.ceph.com/issues/18148
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Reviewed-by: Yan, Zheng <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 36fb7435b6 ]
The mvpp2_txq_bufs_free() function is called upon TX completion to DMA
unmap TX buffers, and free the corresponding SKBs. It gets the
references to the SKB to free and the DMA buffer to unmap from a per-CPU
txq_pcpu data structure.
However, the code currently increments the pointer to the next entry
before doing the DMA unmap and freeing the SKB. It does not cause any
visible problem because for a given SKB the TX completion is guaranteed
to take place on the CPU where the TX was started. However, it is much
more logical to increment the pointer to the next entry once the current
entry has been completely unmapped/released.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Acked-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 439a36b8ef ]
We are in the situation that we have to avoid recursive cluster locking,
but there is no way to check if a cluster lock has been taken by a precess
already.
Mostly, we can avoid recursive locking by writing code carefully.
However, we found that it's very hard to handle the routines that are
invoked directly by vfs code. For instance:
const struct inode_operations ocfs2_file_iops = {
.permission = ocfs2_permission,
.get_acl = ocfs2_iop_get_acl,
.set_acl = ocfs2_iop_set_acl,
};
Both ocfs2_permission() and ocfs2_iop_get_acl() call ocfs2_inode_lock(PR):
do_sys_open
may_open
inode_permission
ocfs2_permission
ocfs2_inode_lock() <=== first time
generic_permission
get_acl
ocfs2_iop_get_acl
ocfs2_inode_lock() <=== recursive one
A deadlock will occur if a remote EX request comes in between two of
ocfs2_inode_lock(). Briefly describe how the deadlock is formed:
On one hand, OCFS2_LOCK_BLOCKED flag of this lockres is set in
BAST(ocfs2_generic_handle_bast) when downconvert is started on behalf of
the remote EX lock request. Another hand, the recursive cluster lock
(the second one) will be blocked in in __ocfs2_cluster_lock() because of
OCFS2_LOCK_BLOCKED. But, the downconvert never complete, why? because
there is no chance for the first cluster lock on this node to be
unlocked - we block ourselves in the code path.
The idea to fix this issue is mostly taken from gfs2 code.
1. introduce a new field: struct ocfs2_lock_res.l_holders, to keep track
of the processes' pid who has taken the cluster lock of this lock
resource;
2. introduce a new flag for ocfs2_inode_lock_full:
OCFS2_META_LOCK_GETBH; it means just getting back disk inode bh for
us if we've got cluster lock.
3. export a helper: ocfs2_is_locked_by_me() is used to check if we have
got the cluster lock in the upper code path.
The tracking logic should be used by some of the ocfs2 vfs's callbacks,
to solve the recursive locking issue cuased by the fact that vfs
routines can call into each other.
The performance penalty of processing the holder list should only be
seen at a few cases where the tracking logic is used, such as get/set
acl.
You may ask what if the first time we got a PR lock, and the second time
we want a EX lock? fortunately, this case never happens in the real
world, as far as I can see, including permission check,
(get|set)_(acl|attr), and the gfs2 code also do so.
[sfr@canb.auug.org.au remove some inlines]
Link: http://lkml.kernel.org/r/20170117100948.11657-2-zren@suse.com
Signed-off-by: Eric Ren <zren@suse.com>
Reviewed-by: Junxiao Bi <junxiao.bi@oracle.com>
Reviewed-by: Joseph Qi <jiangqi903@gmail.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Mark Fasheh <mfasheh@versity.com>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
