Skip to content

K
kernel_linux

OpenHarmony / kernel_linux
上一次同步 4 年多

通知 15
Star 8
Fork 2
K
kernel_linux
切换分支/标签
  1. 10 10月, 2017 19 次提交
    • S
      sched/rt: Simplify the IPI based RT balancing logic · 4bdced5c
      由 Steven Rostedt (Red Hat) 提交于 
      When a CPU lowers its priority (schedules out a high priority task for a
lower priority one), a check is made to see if any other CPU has overloaded
RT tasks (more than one). It checks the rto_mask to determine this and if so
it will request to pull one of those tasks to itself if the non running RT
task is of higher priority than the new priority of the next task to run on
the current CPU.

When we deal with large number of CPUs, the original pull logic suffered
from large lock contention on a single CPU run queue, which caused a huge
latency across all CPUs. This was caused by only having one CPU having
overloaded RT tasks and a bunch of other CPUs lowering their priority. To
solve this issue, commit:

  b6366f04 ("sched/rt: Use IPI to trigger RT task push migration instead of pulling")

changed the way to request a pull. Instead of grabbing the lock of the
overloaded CPU's runqueue, it simply sent an IPI to that CPU to do the work.

Although the IPI logic worked very well in removing the large latency build
up, it still could suffer from a large number of IPIs being sent to a single
CPU. On a 80 CPU box, I measured over 200us of processing IPIs. Worse yet,
when I tested this on a 120 CPU box, with a stress test that had lots of
RT tasks scheduling on all CPUs, it actually triggered the hard lockup
detector! One CPU had so many IPIs sent to it, and due to the restart
mechanism that is triggered when the source run queue has a priority status
change, the CPU spent minutes! processing the IPIs.

Thinking about this further, I realized there's no reason for each run queue
to send its own IPI. As all CPUs with overloaded tasks must be scanned
regardless if there's one or many CPUs lowering their priority, because
there's no current way to find the CPU with the highest priority task that
can schedule to one of these CPUs, there really only needs to be one IPI
being sent around at a time.

This greatly simplifies the code!

The new approach is to have each root domain have its own irq work, as the
rto_mask is per root domain. The root domain has the following fields
attached to it:

  rto_push_work	 - the irq work to process each CPU set in rto_mask
  rto_lock	 - the lock to protect some of the other rto fields
  rto_loop_start - an atomic that keeps contention down on rto_lock
		    the first CPU scheduling in a lower priority task
		    is the one to kick off the process.
  rto_loop_next	 - an atomic that gets incremented for each CPU that
		    schedules in a lower priority task.
  rto_loop	 - a variable protected by rto_lock that is used to
		    compare against rto_loop_next
  rto_cpu	 - The cpu to send the next IPI to, also protected by
		    the rto_lock.

When a CPU schedules in a lower priority task and wants to make sure
overloaded CPUs know about it. It increments the rto_loop_next. Then it
atomically sets rto_loop_start with a cmpxchg. If the old value is not "0",
then it is done, as another CPU is kicking off the IPI loop. If the old
value is "0", then it will take the rto_lock to synchronize with a possible
IPI being sent around to the overloaded CPUs.

If rto_cpu is greater than or equal to nr_cpu_ids, then there's either no
IPI being sent around, or one is about to finish. Then rto_cpu is set to the
first CPU in rto_mask and an IPI is sent to that CPU. If there's no CPUs set
in rto_mask, then there's nothing to be done.

When the CPU receives the IPI, it will first try to push any RT tasks that is
queued on the CPU but can't run because a higher priority RT task is
currently running on that CPU.

Then it takes the rto_lock and looks for the next CPU in the rto_mask. If it
finds one, it simply sends an IPI to that CPU and the process continues.

If there's no more CPUs in the rto_mask, then rto_loop is compared with
rto_loop_next. If they match, everything is done and the process is over. If
they do not match, then a CPU scheduled in a lower priority task as the IPI
was being passed around, and the process needs to start again. The first CPU
in rto_mask is sent the IPI.

This change removes this duplication of work in the IPI logic, and greatly
lowers the latency caused by the IPIs. This removed the lockup happening on
the 120 CPU machine. It also simplifies the code tremendously. What else
could anyone ask for?

Thanks to Peter Zijlstra for simplifying the rto_loop_start atomic logic and
supplying me with the rto_start_trylock() and rto_start_unlock() helper
functions.
Signed-off-by: NSteven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Clark Williams <williams@redhat.com>
Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott Wood <swood@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170424114732.1aac6dc4@gandalf.local.homeSigned-off-by: NIngo Molnar <mingo@kernel.org>
      4bdced5c
    • B
      sched/fair: Fix usage of find_idlest_group() when the local group is idlest · 93f50f90
      由 Brendan Jackman 提交于 
      find_idlest_group() returns NULL when the local group is idlest. The
caller then continues the find_idlest_group() search at a lower level
of the current CPU's sched_domain hierarchy. find_idlest_group_cpu() is
not consulted and, crucially, @new_cpu is not updated. This means the
search is pointless and we return @prev_cpu from select_task_rq_fair().

This is fixed by initialising @new_cpu to @cpu instead of @prev_cpu.
Signed-off-by: NBrendan Jackman <brendan.jackman@arm.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NJosef Bacik <jbacik@fb.com>
Reviewed-by: NVincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.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>
Link: http://lkml.kernel.org/r/20171005114516.18617-6-brendan.jackman@arm.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      93f50f90
    • B
      sched/fair: Fix usage of find_idlest_group() when no groups are allowed · 6fee85cc
      由 Brendan Jackman 提交于 
      When 'p' is not allowed on any of the CPUs in the sched_domain, we
currently return NULL from find_idlest_group(), and pointlessly
continue the search on lower sched_domain levels (where 'p' is also not
allowed) before returning prev_cpu regardless (as we have not updated
new_cpu).

Add an explicit check for this case, and add a comment to
find_idlest_group(). Now when find_idlest_group() returns NULL, it always
means that the local group is allowed and idlest.
Signed-off-by: NBrendan Jackman <brendan.jackman@arm.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NVincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: NJosef Bacik <jbacik@fb.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.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>
Link: http://lkml.kernel.org/r/20171005114516.18617-5-brendan.jackman@arm.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      6fee85cc
    • B
      sched/fair: Fix find_idlest_group() when local group is not allowed · 0d10ab95
      由 Brendan Jackman 提交于 
      When the local group is not allowed we do not modify this_*_load from
their initial value of 0. That means that the load checks at the end
of find_idlest_group cause us to incorrectly return NULL. Fixing the
initial values to ULONG_MAX means we will instead return the idlest
remote group in that case.
Signed-off-by: NBrendan Jackman <brendan.jackman@arm.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NVincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: NJosef Bacik <jbacik@fb.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.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>
Link: http://lkml.kernel.org/r/20171005114516.18617-4-brendan.jackman@arm.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      0d10ab95
    • B
      sched/fair: Remove unnecessary comparison with -1 · e90381ea
      由 Brendan Jackman 提交于 
      Since commit:

  83a0a96a ("sched/fair: Leverage the idle state info when choosing the "idlest" cpu")

find_idlest_group_cpu() (formerly find_idlest_cpu) no longer returns -1,
so we can simplify the checking of the return value in find_idlest_cpu().
Signed-off-by: NBrendan Jackman <brendan.jackman@arm.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NJosef Bacik <jbacik@fb.com>
Reviewed-by: NVincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.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>
Link: http://lkml.kernel.org/r/20171005114516.18617-3-brendan.jackman@arm.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      e90381ea
    • B
      sched/fair: Move select_task_rq_fair() slow-path into its own function · 18bd1b4b
      由 Brendan Jackman 提交于 
      In preparation for changes that would otherwise require adding a new
level of indentation to the while(sd) loop, create a new function
find_idlest_cpu() which contains this loop, and rename the existing
find_idlest_cpu() to find_idlest_group_cpu().

Code inside the while(sd) loop is unchanged. @new_cpu is added as a
variable in the new function, with the same initial value as the
@new_cpu in select_task_rq_fair().
Suggested-by: NPeter Zijlstra <peterz@infradead.org>
Signed-off-by: NBrendan Jackman <brendan.jackman@arm.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NJosef Bacik <jbacik@fb.com>
Reviewed-by: NVincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.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: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20171005114516.18617-2-brendan.jackman@arm.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      18bd1b4b
    • B
      sched/fair: Force balancing on NOHZ balance if local group has capacity · 583ffd99
      由 Brendan Jackman 提交于 
      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:

  fab47622 ("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.
Signed-off-by: NBrendan Jackman <brendan.jackman@arm.com>
Signed-off-by: NPeter 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.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      583ffd99
    • B
      sched/fair: Sync task util before slow-path wakeup · ea16f0ea
      由 Brendan Jackman 提交于 
      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.
Signed-off-by: NBrendan Jackman <brendan.jackman@arm.com>
Signed-off-by: NPeter 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.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      ea16f0ea
    • U
      sched/fair: Search a task from the tail of the queue · 93824900
      由 Uladzislau Rezki 提交于 
      As a first step this patch makes cfs_tasks list as MRU one.
It means, that when a next task is picked to run on physical
CPU it is moved to the front of the list.

Therefore, the cfs_tasks list is more or less sorted (except
woken tasks) starting from recently given CPU time tasks toward
tasks with max wait time in a run-queue, i.e. MRU list.

Second, as part of the load balance operation, this approach
starts detach_tasks()/detach_one_task() from the tail of the
queue instead of the head, giving some advantages:

 - tends to pick a task with highest wait time;

 - tasks located in the tail are less likely cache-hot,
   therefore the can_migrate_task() decision is higher.

hackbench illustrates slightly better performance. For example
doing 1000 samples and 40 groups on i5-3320M CPU, it shows below
figures:

 default: 0.657 avg
 patched: 0.646 avg
Signed-off-by: NUladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Kirill Tkhai <tkhai@yandex.ru>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com>
Cc: Paul Turner <pjt@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Link: http://lkml.kernel.org/r/20170913102430.8985-2-urezki@gmail.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      93824900
    • S
      sched/topology: Introduce NUMA identity node sched domain · 051f3ca0
      由 Suravee Suthikulpanit 提交于 
      On AMD Family17h-based (EPYC) system, a logical NUMA node can contain
upto 8 cores (16 threads) with the following topology.

             ----------------------------
         C0  | T0 T1 |    ||    | T0 T1 | C4
             --------|    ||    |--------
         C1  | T0 T1 | L3 || L3 | T0 T1 | C5
             --------|    ||    |--------
         C2  | T0 T1 | #0 || #1 | T0 T1 | C6
             --------|    ||    |--------
         C3  | T0 T1 |    ||    | T0 T1 | C7
             ----------------------------

Here, there are 2 last-level (L3) caches per logical NUMA node.
A socket can contain upto 4 NUMA nodes, and a system can support
upto 2 sockets. With full system configuration, current scheduler
creates 4 sched domains:

  domain0 SMT       (span a core)
  domain1 MC        (span a last-level-cache)
  domain2 NUMA      (span a socket: 4 nodes)
  domain3 NUMA      (span a system: 8 nodes)

Note that there is no domain to represent cpus spaning a logical
NUMA node.  With this hierarchy of sched domains, the scheduler does
not balance properly in the following cases:

Case1:

 When running 8 tasks, a properly balanced system should
 schedule a task per logical NUMA node. This is not the case for
 the current scheduler.

Case2:

 In some cases, threads are scheduled on the same cpu, while other
 cpus are idle. This results in run-to-run inconsistency. For example:

  taskset -c 0-7 sysbench --num-threads=8 --test=cpu \
                          --cpu-max-prime=100000 run

Total execution time ranges from 25.1s to 33.5s depending on threads
placement, where 25.1s is when all 8 threads are balanced properly
on 8 cpus.

Introducing NUMA identity node sched domain, which is based on how
SRAT/SLIT table define a logical NUMA node. This results in the following
hierarchy of sched domains on the same system described above.

  domain0 SMT       (span a core)
  domain1 MC        (span a last-level-cache)
  domain2 NODE      (span a logical NUMA node)
  domain3 NUMA      (span a socket: 4 nodes)
  domain4 NUMA      (span a system: 8 nodes)

This fixes the improper load balancing cases mentioned above.
Signed-off-by: NSuravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: NPeter 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: bp@suse.de
Link: http://lkml.kernel.org/r/1504768805-46716-1-git-send-email-suravee.suthikulpanit@amd.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      051f3ca0
    • P
      sched/topology: Restore SD_PREFER_SIBLING on MC domains · ed4ad1ca
      由 Peter Zijlstra 提交于 
      The normal x86_topology on NHM+ machines degenerates because the MC
and CPU domains are of the same size, therefore MC inherits
SD_PREFER_SIBLING from CPU (which then gets taken out). The result is
that we'll spread tasks across the first NUMA level in order to
maximize cache utilization.

However, for the x86_numa_in_package_topology we loose the CPU domain,
and we'll not have SD_PREFER_SIBLING set anywhere, giving a distinct
difference in behaviour.

Commit:

  8e7fbcbc ("sched: Remove stale power aware scheduling remnants and dysfunctional knobs")

made a fail by not preserving the SD_PREFER_SIBLING for the !power_saving
case on both CPU and MC.

Then commit:

  6956dc56 ("sched/numa: Add SD_PERFER_SIBLING to CPU domain")

adds it back to the CPU but not MC.

Restore that now, such that we get consistent spreading behaviour wrt
L3 and NUMA.
Signed-off-by: NPeter 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: NIngo Molnar <mingo@kernel.org>
      ed4ad1ca
    • P
      sched/deadline: Rename __dl_clear() to __dl_sub() · 8c0944ce
      由 Peter Zijlstra 提交于 
      __dl_sub() is more meaningful as a name, and is more consistent
with the naming of the dual function (__dl_add()).
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: NLuca Abeni <luca.abeni@santannapisa.it>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NDaniel Bristot de Oliveira <bristot@redhat.com>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1504778971-13573-4-git-send-email-luca.abeni@santannapisa.itSigned-off-by: NIngo Molnar <mingo@kernel.org>
      8c0944ce
    • L
      sched/deadline: Fix switching to -deadline · 295d6d5e
      由 Luca Abeni 提交于 
      Fix a bug introduced in:

  72f9f3fd ("sched/deadline: Remove dl_new from struct sched_dl_entity")

After that commit, when switching to -deadline if the scheduling
deadline of a task is in the past then switched_to_dl() calls
setup_new_entity() to properly initialize the scheduling deadline
and runtime.

The problem is that the task is enqueued _before_ having its parameters
initialized by setup_new_entity(), and this can cause problems.
For example, a task with its out-of-date deadline in the past will
potentially be enqueued as the highest priority one; however, its
adjusted deadline may not be the earliest one.

This patch fixes the problem by initializing the task's parameters before
enqueuing it.
Signed-off-by: Nluca abeni <luca.abeni@santannapisa.it>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NDaniel Bristot de Oliveira <bristot@redhat.com>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1504778971-13573-3-git-send-email-luca.abeni@santannapisa.itSigned-off-by: NIngo Molnar <mingo@kernel.org>
      295d6d5e
    • L
      sched/headers: Remove duplicate prototype of __dl_clear_params() · e964d350
      由 luca abeni 提交于 
      Signed-off-by: Nluca abeni <luca.abeni@santannapisa.it>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NDaniel Bristot de Oliveira <bristot@redhat.com>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1504778971-13573-2-git-send-email-luca.abeni@santannapisa.itSigned-off-by: NIngo Molnar <mingo@kernel.org>
      e964d350
    • P
      sched/debug: Rename task-state printing helpers · 1d48b080
      由 Peter Zijlstra 提交于 
      Steve requested better names for the new task-state helper functions.

So introduce the concept of task-state index for the printing and
rename __get_task_state() to task_state_index() and
__task_state_to_char() to task_index_to_char().
Requested-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: NSteven Rostedt <rostedt@goodmis.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/20170929115016.pzlqc7ss3ccystyg@hirez.programming.kicks-ass.netSigned-off-by: NIngo Molnar <mingo@kernel.org>
      1d48b080
    • P
      sched/idle: Move quiet_vmstate() into the NOHZ code · 62cb1188
      由 Peter Zijlstra 提交于 
      quiet_vmstat() is an expensive function that only makes sense when we
go into NOHZ.
Signed-off-by: NPeter 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: aubrey.li@linux.intel.com
Cc: cl@linux.com
Cc: fweisbec@gmail.com
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      62cb1188
    • P
      sched/core: Ensure load_balance() respects the active_mask · 024c9d2f
      由 Peter Zijlstra 提交于 
      While load_balance() masks the source CPUs against active_mask, it had
a hole against the destination CPU. Ensure the destination CPU is also
part of the 'domain-mask & active-mask' set.
Reported-by: NLevin, Alexander (Sasha Levin) <alexander.levin@verizon.com>
Signed-off-by: NPeter 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>
Fixes: 77d1dfda ("sched/topology, cpuset: Avoid spurious/wrong domain rebuilds")
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      024c9d2f
    • P
      sched/core: Address more wake_affine() regressions · f2cdd9cc
      由 Peter Zijlstra 提交于 
      The trivial wake_affine_idle() implementation is very good for a
number of workloads, but it comes apart at the moment there are no
idle CPUs left, IOW. the overloaded case.

hackbench:

		NO_WA_WEIGHT		WA_WEIGHT

hackbench-20  : 7.362717561 seconds	6.450509391 seconds

(win)

netperf:

		  NO_WA_WEIGHT		WA_WEIGHT

TCP_SENDFILE-1	: Avg: 54524.6		Avg: 52224.3
TCP_SENDFILE-10	: Avg: 48185.2          Avg: 46504.3
TCP_SENDFILE-20	: Avg: 29031.2          Avg: 28610.3
TCP_SENDFILE-40	: Avg: 9819.72          Avg: 9253.12
TCP_SENDFILE-80	: Avg: 5355.3           Avg: 4687.4

TCP_STREAM-1	: Avg: 41448.3          Avg: 42254
TCP_STREAM-10	: Avg: 24123.2          Avg: 25847.9
TCP_STREAM-20	: Avg: 15834.5          Avg: 18374.4
TCP_STREAM-40	: Avg: 5583.91          Avg: 5599.57
TCP_STREAM-80	: Avg: 2329.66          Avg: 2726.41

TCP_RR-1	: Avg: 80473.5          Avg: 82638.8
TCP_RR-10	: Avg: 72660.5          Avg: 73265.1
TCP_RR-20	: Avg: 52607.1          Avg: 52634.5
TCP_RR-40	: Avg: 57199.2          Avg: 56302.3
TCP_RR-80	: Avg: 25330.3          Avg: 26867.9

UDP_RR-1	: Avg: 108266           Avg: 107844
UDP_RR-10	: Avg: 95480            Avg: 95245.2
UDP_RR-20	: Avg: 68770.8          Avg: 68673.7
UDP_RR-40	: Avg: 76231            Avg: 75419.1
UDP_RR-80	: Avg: 34578.3          Avg: 35639.1

UDP_STREAM-1	: Avg: 64684.3          Avg: 66606
UDP_STREAM-10	: Avg: 52701.2          Avg: 52959.5
UDP_STREAM-20	: Avg: 30376.4          Avg: 29704
UDP_STREAM-40	: Avg: 15685.8          Avg: 15266.5
UDP_STREAM-80	: Avg: 8415.13          Avg: 7388.97

(wins and losses)

sysbench:

		    NO_WA_WEIGHT		WA_WEIGHT

sysbench-mysql-2  :  2135.17 per sec.		 2142.51 per sec.
sysbench-mysql-5  :  4809.68 per sec.            4800.19 per sec.
sysbench-mysql-10 :  9158.59 per sec.            9157.05 per sec.
sysbench-mysql-20 : 14570.70 per sec.           14543.55 per sec.
sysbench-mysql-40 : 22130.56 per sec.           22184.82 per sec.
sysbench-mysql-80 : 20995.56 per sec.           21904.18 per sec.

sysbench-psql-2   :  1679.58 per sec.            1705.06 per sec.
sysbench-psql-5   :  3797.69 per sec.            3879.93 per sec.
sysbench-psql-10  :  7253.22 per sec.            7258.06 per sec.
sysbench-psql-20  : 11166.75 per sec.           11220.00 per sec.
sysbench-psql-40  : 17277.28 per sec.           17359.78 per sec.
sysbench-psql-80  : 17112.44 per sec.           17221.16 per sec.

(increase on the top end)

tbench:

NO_WA_WEIGHT

Throughput 685.211 MB/sec   2 clients   2 procs  max_latency=0.123 ms
Throughput 1596.64 MB/sec   5 clients   5 procs  max_latency=0.119 ms
Throughput 2985.47 MB/sec  10 clients  10 procs  max_latency=0.262 ms
Throughput 4521.15 MB/sec  20 clients  20 procs  max_latency=0.506 ms
Throughput 9438.1  MB/sec  40 clients  40 procs  max_latency=2.052 ms
Throughput 8210.5  MB/sec  80 clients  80 procs  max_latency=8.310 ms

WA_WEIGHT

Throughput 697.292 MB/sec   2 clients   2 procs  max_latency=0.127 ms
Throughput 1596.48 MB/sec   5 clients   5 procs  max_latency=0.080 ms
Throughput 2975.22 MB/sec  10 clients  10 procs  max_latency=0.254 ms
Throughput 4575.14 MB/sec  20 clients  20 procs  max_latency=0.502 ms
Throughput 9468.65 MB/sec  40 clients  40 procs  max_latency=2.069 ms
Throughput 8631.73 MB/sec  80 clients  80 procs  max_latency=8.605 ms

(increase on the top end)
Signed-off-by: NPeter 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: Rik van Riel <riel@redhat.com>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      f2cdd9cc
    • P
      sched/core: Fix wake_affine() performance regression · d153b153
      由 Peter Zijlstra 提交于 
      Eric reported a sysbench regression against commit:

  3fed382b ("sched/numa: Implement NUMA node level wake_affine()")

Similarly, Rik was looking at the NAS-lu.C benchmark, which regressed
against his v3.10 enterprise kernel.

PRE (current tip/master):

 ivb-ep sysbench:

   2: [30 secs]     transactions:                        64110  (2136.94 per sec.)
   5: [30 secs]     transactions:                        143644 (4787.99 per sec.)
  10: [30 secs]     transactions:                        274298 (9142.93 per sec.)
  20: [30 secs]     transactions:                        418683 (13955.45 per sec.)
  40: [30 secs]     transactions:                        320731 (10690.15 per sec.)
  80: [30 secs]     transactions:                        355096 (11834.28 per sec.)

 hsw-ex NAS:

 OMP_PROC_BIND/lu.C.x_threads_144_run_1.log: Time in seconds =                    18.01
 OMP_PROC_BIND/lu.C.x_threads_144_run_2.log: Time in seconds =                    17.89
 OMP_PROC_BIND/lu.C.x_threads_144_run_3.log: Time in seconds =                    17.93
 lu.C.x_threads_144_run_1.log: Time in seconds =                   434.68
 lu.C.x_threads_144_run_2.log: Time in seconds =                   405.36
 lu.C.x_threads_144_run_3.log: Time in seconds =                   433.83

POST (+patch):

 ivb-ep sysbench:

   2: [30 secs]     transactions:                        64494  (2149.75 per sec.)
   5: [30 secs]     transactions:                        145114 (4836.99 per sec.)
  10: [30 secs]     transactions:                        278311 (9276.69 per sec.)
  20: [30 secs]     transactions:                        437169 (14571.60 per sec.)
  40: [30 secs]     transactions:                        669837 (22326.73 per sec.)
  80: [30 secs]     transactions:                        631739 (21055.88 per sec.)

 hsw-ex NAS:

 lu.C.x_threads_144_run_1.log: Time in seconds =                    23.36
 lu.C.x_threads_144_run_2.log: Time in seconds =                    22.96
 lu.C.x_threads_144_run_3.log: Time in seconds =                    22.52

This patch takes out all the shiny wake_affine() stuff and goes back to
utter basics. Between the two CPUs involved with the wakeup (the CPU
doing the wakeup and the CPU we ran on previously) pick the CPU we can
run on _now_.

This restores much of the regressions against the older kernels,
but leaves some ground in the overloaded case. The default-enabled
WA_WEIGHT (which will be introduced in the next patch) is an attempt
to address the overloaded situation.
Reported-by: NEric Farman <farman@linux.vnet.ibm.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matthew Rosato <mjrosato@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: jinpuwang@gmail.com
Cc: vcaputo@pengaru.com
Fixes: 3fed382b ("sched/numa: Implement NUMA node level wake_affine()")
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      d153b153
  3. 09 10月, 2017 1 次提交
    • S
      netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1' · 98589a09
      由 Shmulik Ladkani 提交于 
      Commit 2c16d603 ("netfilter: xt_bpf: support ebpf") introduced
support for attaching an eBPF object by an fd, with the
'bpf_mt_check_v1' ABI expecting the '.fd' to be specified upon each
IPT_SO_SET_REPLACE call.

However this breaks subsequent iptables calls:

 # iptables -A INPUT -m bpf --object-pinned /sys/fs/bpf/xxx -j ACCEPT
 # iptables -A INPUT -s 5.6.7.8 -j ACCEPT
 iptables: Invalid argument. Run `dmesg' for more information.

That's because iptables works by loading existing rules using
IPT_SO_GET_ENTRIES to userspace, then issuing IPT_SO_SET_REPLACE with
the replacement set.

However, the loaded 'xt_bpf_info_v1' has an arbitrary '.fd' number
(from the initial "iptables -m bpf" invocation) - so when 2nd invocation
occurs, userspace passes a bogus fd number, which leads to
'bpf_mt_check_v1' to fail.

One suggested solution [1] was to hack iptables userspace, to perform a
"entries fixup" immediatley after IPT_SO_GET_ENTRIES, by opening a new,
process-local fd per every 'xt_bpf_info_v1' entry seen.

However, in [2] both Pablo Neira Ayuso and Willem de Bruijn suggested to
depricate the xt_bpf_info_v1 ABI dealing with pinned ebpf objects.

This fix changes the XT_BPF_MODE_FD_PINNED behavior to ignore the given
'.fd' and instead perform an in-kernel lookup for the bpf object given
the provided '.path'.

It also defines an alias for the XT_BPF_MODE_FD_PINNED mode, named
XT_BPF_MODE_PATH_PINNED, to better reflect the fact that the user is
expected to provide the path of the pinned object.

Existing XT_BPF_MODE_FD_ELF behavior (non-pinned fd mode) is preserved.

References: [1] https://marc.info/?l=netfilter-devel&m=150564724607440&w=2
            [2] https://marc.info/?l=netfilter-devel&m=150575727129880&w=2Reported-by: NRafael Buchbinder <rafi@rbk.ms>
Signed-off-by: NShmulik Ladkani <shmulik.ladkani@gmail.com>
Acked-by: NWillem de Bruijn <willemb@google.com>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
      98589a09
  5. 08 10月, 2017 1 次提交
    • A
      bpf: fix liveness marking · 8fe2d6cc
      由 Alexei Starovoitov 提交于 
      while processing Rx = Ry instruction the verifier does
regs[insn->dst_reg] = regs[insn->src_reg]
which often clears write mark (when Ry doesn't have it)
that was just set by check_reg_arg(Rx) prior to the assignment.
That causes mark_reg_read() to keep marking Rx in this block as
REG_LIVE_READ (since the logic incorrectly misses that it's
screened by the write) and in many of its parents (until lucky
write into the same Rx or beginning of the program).
That causes is_state_visited() logic to miss many pruning opportunities.

Furthermore mark_reg_read() logic propagates the read mark
for BPF_REG_FP as well (though it's readonly) which causes
harmless but unnecssary work during is_state_visited().
Note that do_propagate_liveness() skips FP correctly,
so do the same in mark_reg_read() as well.
It saves 0.2 seconds for the test below

program               before  after
bpf_lb-DLB_L3.o       2604    2304
bpf_lb-DLB_L4.o       11159   3723
bpf_lb-DUNKNOWN.o     1116    1110
bpf_lxc-DDROP_ALL.o   34566   28004
bpf_lxc-DUNKNOWN.o    53267   39026
bpf_netdev.o          17843   16943
bpf_overlay.o         8672    7929
time                  ~11 sec  ~4 sec

Fixes: dc503a8a ("bpf/verifier: track liveness for pruning")
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>
Acked-by: NEdward Cree <ecree@solarflare.com>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      8fe2d6cc
  7. 04 10月, 2017 14 次提交
  9. 03 10月, 2017 2 次提交
    • P
      rcu: Remove extraneous READ_ONCE()s from rcu_irq_{enter,exit}() · f39b536c
      由 Paul E. McKenney 提交于 
      The read of ->dynticks_nmi_nesting in rcu_irq_enter() and rcu_irq_exit()
is currently protected with READ_ONCE().  However, this protection is
unnecessary because (1) ->dynticks_nmi_nesting is updated only by the
current CPU, (2) Although NMI handlers can update this field, they reset
it back to its old value before return, and (3) Interrupts are disabled,
so nothing else can modify it.  The value of ->dynticks_nmi_nesting is
thus effectively constant, and so no protection is required.

This commit therefore removes the READ_ONCE() protection from these
two accesses.

Link: http://lkml.kernel.org/r/20170926031902.GA2074@linux.vnet.ibm.comReported-by: NLinus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: NPaul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: NSteven Rostedt (VMware) <rostedt@goodmis.org>
      f39b536c
    • S
      ftrace: Fix kmemleak in unregister_ftrace_graph · 2b0b8499
      由 Shu Wang 提交于 
      The trampoline allocated by function tracer was overwriten by function_graph
tracer, and caused a memory leak. The save_global_trampoline should have
saved the previous trampoline in register_ftrace_graph() and restored it in
unregister_ftrace_graph(). But as it is implemented, save_global_trampoline was
only used in unregister_ftrace_graph as default value 0, and it overwrote the
previous trampoline's value. Causing the previous allocated trampoline to be
lost.

kmmeleak backtrace:
    kmemleak_vmalloc+0x77/0xc0
    __vmalloc_node_range+0x1b5/0x2c0
    module_alloc+0x7c/0xd0
    arch_ftrace_update_trampoline+0xb5/0x290
    ftrace_startup+0x78/0x210
    register_ftrace_function+0x8b/0xd0
    function_trace_init+0x4f/0x80
    tracing_set_tracer+0xe6/0x170
    tracing_set_trace_write+0x90/0xd0
    __vfs_write+0x37/0x170
    vfs_write+0xb2/0x1b0
    SyS_write+0x55/0xc0
    do_syscall_64+0x67/0x180
    return_from_SYSCALL_64+0x0/0x6a

[
  Looking further into this, I found that this was left over from when the
  function and function graph tracers shared the same ftrace_ops. But in
  commit 5f151b24 ("ftrace: Fix function_profiler and function tracer
  together"), the two were separated, and the save_global_trampoline no
  longer was necessary (and it may have been broken back then too).
  -- Steven Rostedt
]

Link: http://lkml.kernel.org/r/20170912021454.5976-1-shuwang@redhat.com

Cc: stable@vger.kernel.org
Fixes: 5f151b24 ("ftrace: Fix function_profiler and function tracer together")
Signed-off-by: NShu Wang <shuwang@redhat.com>
Signed-off-by: NSteven Rostedt (VMware) <rostedt@goodmis.org>
      2b0b8499
  11. 30 9月, 2017 3 次提交
    • A
      fix infoleak in waitid(2) · 6c85501f
      由 Al Viro 提交于 
      kernel_waitid() can return a PID, an error or 0.  rusage is filled in the first
case and waitid(2) rusage should've been copied out exactly in that case, *not*
whenever kernel_waitid() has not returned an error.  Compat variant shares that
braino; none of kernel_wait4() callers do, so the below ought to fix it.
Reported-and-tested-by: NAlexander Potapenko <glider@google.com>
Fixes: ce72a16f ("wait4(2)/waitid(2): separate copying rusage to userland")
Cc: stable@vger.kernel.org # v4.13
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
      6c85501f
    • P
      sched/fair: Update calc_group_*() comments · 17de4ee0
      由 Peter Zijlstra 提交于 
      I had a wee bit of trouble recalling how the calc_group_runnable()
stuff worked.. add hopefully better comments.
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      17de4ee0
    • J
      sched/fair: Calculate runnable_weight slightly differently · 2c8e4dce
      由 Josef Bacik 提交于 
      Our runnable_weight currently looks like this

runnable_weight = shares * runnable_load_avg / load_avg

The goal is to scale the runnable weight for the group based on its runnable to
load_avg ratio.  The problem with this is it biases us towards tasks that never
go to sleep.  Tasks that go to sleep are going to have their runnable_load_avg
decayed pretty hard, which will drastically reduce the runnable weight of groups
with interactive tasks.  To solve this imbalance we tweak this slightly, so in
the ideal case it is still the above, but in the interactive case it is

runnable_weight = shares * runnable_weight / load_weight

which will make the weight distribution fairer between interactive and
non-interactive groups.
Signed-off-by: NJosef Bacik <jbacik@fb.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: kernel-team@fb.com
Cc: linux-kernel@vger.kernel.org
Cc: riel@redhat.com
Cc: tj@kernel.org
Link: http://lkml.kernel.org/r/1501773219-18774-2-git-send-email-jbacik@fb.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      2c8e4dce