Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
1 年多 前同步成功

通知 160
Star 36
Fork 7
cloud-kernel
cloud-kernel
切换分支/标签
  1. 06 3月, 2019 1 次提交
    • P
      sched/wake_q: Fix wakeup ordering for wake_q · 653a1dbc
      由 Peter Zijlstra 提交于 
      [ Upstream commit 4c4e3731564c8945ac5ac90fc2a1e1f21cb79c92 ]

Notable cmpxchg() does not provide ordering when it fails, however
wake_q_add() requires ordering in this specific case too. Without this
it would be possible for the concurrent wakeup to not observe our
prior state.

Andrea Parri provided:

  C wake_up_q-wake_q_add

  {
	int next = 0;
	int y = 0;
  }

  P0(int *next, int *y)
  {
	int r0;

	/* in wake_up_q() */

	WRITE_ONCE(*next, 1);   /* node->next = NULL */
	smp_mb();               /* implied by wake_up_process() */
	r0 = READ_ONCE(*y);
  }

  P1(int *next, int *y)
  {
	int r1;

	/* in wake_q_add() */

	WRITE_ONCE(*y, 1);      /* wake_cond = true */
	smp_mb__before_atomic();
	r1 = cmpxchg_relaxed(next, 1, 2);
  }

  exists (0:r0=0 /\ 1:r1=0)

  This "exists" clause cannot be satisfied according to the LKMM:

  Test wake_up_q-wake_q_add Allowed
  States 3
  0:r0=0; 1:r1=1;
  0:r0=1; 1:r1=0;
  0:r0=1; 1:r1=1;
  No
  Witnesses
  Positive: 0 Negative: 3
  Condition exists (0:r0=0 /\ 1:r1=0)
  Observation wake_up_q-wake_q_add Never 0 3
Reported-by: NYongji Xie <elohimes@gmail.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <longman@redhat.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: NIngo Molnar <mingo@kernel.org>
Signed-off-by: NSasha Levin <sashal@kernel.org>
      653a1dbc
  3. 20 12月, 2018 1 次提交
  5. 06 12月, 2018 1 次提交
    • P
      sched/smt: Make sched_smt_present track topology · a2c09481
      由 Peter Zijlstra (Intel) 提交于 
      commit c5511d03ec090980732e929c318a7a6374b5550e upstream

Currently the 'sched_smt_present' static key is enabled when at CPU bringup
SMT topology is observed, but it is never disabled. However there is demand
to also disable the key when the topology changes such that there is no SMT
present anymore.

Implement this by making the key count the number of cores that have SMT
enabled.

In particular, the SMT topology bits are set before interrrupts are enabled
and similarly, are cleared after interrupts are disabled for the last time
and the CPU dies.
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Reviewed-by: NIngo Molnar <mingo@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Woodhouse <dwmw@amazon.co.uk>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Casey Schaufler <casey.schaufler@intel.com>
Cc: Asit Mallick <asit.k.mallick@intel.com>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Jon Masters <jcm@redhat.com>
Cc: Waiman Long <longman9394@gmail.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Dave Stewart <david.c.stewart@intel.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20181125185004.246110444@linutronix.deSigned-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      a2c09481
  7. 27 11月, 2018 1 次提交
    • V
      sched/core: Take the hotplug lock in sched_init_smp() · b1e814e4
      由 Valentin Schneider 提交于 
      [ Upstream commit 40fa3780bac2b654edf23f6b13f4e2dd550aea10 ]

When running on linux-next (8c60c36d0b8c ("Add linux-next specific files
for 20181019")) + CONFIG_PROVE_LOCKING=y on a big.LITTLE system (e.g.
Juno or HiKey960), we get the following report:

 [    0.748225] Call trace:
 [    0.750685]  lockdep_assert_cpus_held+0x30/0x40
 [    0.755236]  static_key_enable_cpuslocked+0x20/0xc8
 [    0.760137]  build_sched_domains+0x1034/0x1108
 [    0.764601]  sched_init_domains+0x68/0x90
 [    0.768628]  sched_init_smp+0x30/0x80
 [    0.772309]  kernel_init_freeable+0x278/0x51c
 [    0.776685]  kernel_init+0x10/0x108
 [    0.780190]  ret_from_fork+0x10/0x18

The static_key in question is 'sched_asym_cpucapacity' introduced by
commit:

  df054e8445a4 ("sched/topology: Add static_key for asymmetric CPU capacity optimizations")

In this particular case, we enable it because smp_prepare_cpus() will
end up fetching the capacity-dmips-mhz entry from the devicetree,
so we already have some asymmetry detected when entering sched_init_smp().

This didn't get detected in tip/sched/core because we were missing:

  commit cb538267ea1e ("jump_label/lockdep: Assert we hold the hotplug lock for _cpuslocked() operations")

Calls to build_sched_domains() post sched_init_smp() will hold the
hotplug lock, it just so happens that this very first call is a
special case. As stated by a comment in sched_init_smp(), "There's no
userspace yet to cause hotplug operations" so this is a harmless
warning.

However, to both respect the semantics of underlying
callees and make lockdep happy, take the hotplug lock in
sched_init_smp(). This also satisfies the comment atop
sched_init_domains() that says "Callers must hold the hotplug lock".
Reported-by: NSudeep Holla <sudeep.holla@arm.com>
Tested-by: NSudeep Holla <sudeep.holla@arm.com>
Signed-off-by: NValentin Schneider <valentin.schneider@arm.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Dietmar.Eggemann@arm.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: morten.rasmussen@arm.com
Cc: quentin.perret@arm.com
Link: http://lkml.kernel.org/r/1540301851-3048-1-git-send-email-valentin.schneider@arm.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
Signed-off-by: NSasha Levin <sashal@kernel.org>
      b1e814e4
  9. 02 10月, 2018 1 次提交
    • S
      sched/numa: Pass destination CPU as a parameter to migrate_task_rq · 1327237a
      由 Srikar Dronamraju 提交于 
      This additional parameter (new_cpu) is used later for identifying if
task migration is across nodes.

No functional change.

Specjbb2005 results (8 warehouses)
Higher bops are better

2 Socket - 2  Node Haswell - X86
JVMS  Prev    Current  %Change
4     203353  200668   -1.32036
1     328205  321791   -1.95427

2 Socket - 4 Node Power8 - PowerNV
JVMS  Prev    Current  %Change
1     214384  204848   -4.44809

2 Socket - 2  Node Power9 - PowerNV
JVMS  Prev    Current  %Change
4     188553  188098   -0.241311
1     196273  200351   2.07772

4 Socket - 4  Node Power7 - PowerVM
JVMS  Prev     Current  %Change
8     57581.2  58145.9  0.980702
1     103468   103798   0.318939

Brings out the variance between different specjbb2005 runs.

Some events stats before and after applying the patch.

perf stats 8th warehouse Multi JVM 2 Socket - 2  Node Haswell - X86
Event                     Before          After
cs                        13,941,377      13,912,183
migrations                1,157,323       1,155,931
faults                    382,175         367,139
cache-misses              54,993,823,500  54,240,196,814
sched:sched_move_numa     2,005           1,571
sched:sched_stick_numa    14              9
sched:sched_swap_numa     529             463
migrate:mm_migrate_pages  1,573           703

vmstat 8th warehouse Multi JVM 2 Socket - 2  Node Haswell - X86
Event                   Before  After
numa_hint_faults        67099   50155
numa_hint_faults_local  58456   45264
numa_hit                240416  239652
numa_huge_pte_updates   18      36
numa_interleave         65      68
numa_local              240339  239576
numa_other              77      76
numa_pages_migrated     1574    680
numa_pte_updates        77182   71146

perf stats 8th warehouse Single JVM 2 Socket - 2  Node Haswell - X86
Event                     Before          After
cs                        3,176,453       3,156,720
migrations                30,238          30,354
faults                    87,869          97,261
cache-misses              12,544,479,391  12,400,026,826
sched:sched_move_numa     23              4
sched:sched_stick_numa    0               0
sched:sched_swap_numa     6               1
migrate:mm_migrate_pages  10              20

vmstat 8th warehouse Single JVM 2 Socket - 2  Node Haswell - X86
Event                   Before  After
numa_hint_faults        236     272
numa_hint_faults_local  201     186
numa_hit                72293   71362
numa_huge_pte_updates   0       0
numa_interleave         26      23
numa_local              72233   71299
numa_other              60      63
numa_pages_migrated     8       2
numa_pte_updates        0       0

perf stats 8th warehouse Multi JVM 2 Socket - 2  Node Power9 - PowerNV
Event                     Before       After
cs                        8,478,820    8,606,824
migrations                171,323      155,352
faults                    307,499      301,409
cache-misses              240,353,599  157,759,224
sched:sched_move_numa     214          168
sched:sched_stick_numa    0            0
sched:sched_swap_numa     4            3
migrate:mm_migrate_pages  89           125

vmstat 8th warehouse Multi JVM 2 Socket - 2  Node Power9 - PowerNV
Event                   Before  After
numa_hint_faults        5301    4650
numa_hint_faults_local  4745    3946
numa_hit                92943   90489
numa_huge_pte_updates   0       0
numa_interleave         899     892
numa_local              92345   90034
numa_other              598     455
numa_pages_migrated     88      124
numa_pte_updates        5505    4818

perf stats 8th warehouse Single JVM 2 Socket - 2  Node Power9 - PowerNV
Event                     Before      After
cs                        2,066,172   2,113,167
migrations                11,076      10,533
faults                    149,544     142,727
cache-misses              10,398,067  5,594,192
sched:sched_move_numa     43          10
sched:sched_stick_numa    0           0
sched:sched_swap_numa     0           0
migrate:mm_migrate_pages  6           6

vmstat 8th warehouse Single JVM 2 Socket - 2  Node Power9 - PowerNV
Event                   Before  After
numa_hint_faults        3552    744
numa_hint_faults_local  3347    584
numa_hit                25611   25551
numa_huge_pte_updates   0       0
numa_interleave         213     263
numa_local              25583   25302
numa_other              28      249
numa_pages_migrated     6       6
numa_pte_updates        3535    744

perf stats 8th warehouse Multi JVM 4 Socket - 4  Node Power7 - PowerVM
Event                     Before           After
cs                        99,358,136       101,227,352
migrations                4,041,607        4,151,829
faults                    749,653          745,233
cache-misses              225,562,543,251  224,669,561,766
sched:sched_move_numa     771              617
sched:sched_stick_numa    14               2
sched:sched_swap_numa     204              187
migrate:mm_migrate_pages  1,180            316

vmstat 8th warehouse Multi JVM 4 Socket - 4  Node Power7 - PowerVM
Event                   Before  After
numa_hint_faults        27409   24195
numa_hint_faults_local  20677   21639
numa_hit                239988  238331
numa_huge_pte_updates   0       0
numa_interleave         0       0
numa_local              239983  238331
numa_other              5       0
numa_pages_migrated     1016    204
numa_pte_updates        27916   24561

perf stats 8th warehouse Single JVM 4 Socket - 4  Node Power7 - PowerVM
Event                     Before          After
cs                        60,899,307      62,738,978
migrations                544,668         562,702
faults                    270,834         228,465
cache-misses              74,543,455,635  75,778,067,952
sched:sched_move_numa     735             648
sched:sched_stick_numa    25              13
sched:sched_swap_numa     174             137
migrate:mm_migrate_pages  816             733

vmstat 8th warehouse Single JVM 4 Socket - 4  Node Power7 - PowerVM
Event                   Before  After
numa_hint_faults        11059   10281
numa_hint_faults_local  4733    3242
numa_hit                41384   36338
numa_huge_pte_updates   0       0
numa_interleave         0       0
numa_local              41383   36338
numa_other              1       0
numa_pages_migrated     815     706
numa_pte_updates        11323   10176
Signed-off-by: NSrikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Jirka Hladky <jhladky@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1537552141-27815-3-git-send-email-srikar@linux.vnet.ibm.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      1327237a
  11. 04 8月, 2018 1 次提交
    • E
      signal: Add calculate_sigpending() · 088fe47c
      由 Eric W. Biederman 提交于 
      Add a function calculate_sigpending to test to see if any signals are
pending for a new task immediately following fork.  Signals have to
happen either before or after fork.  Today our practice is to push
all of the signals to before the fork, but that has the downside that
frequent or periodic signals can make fork take much much longer than
normal or prevent fork from completing entirely.

So we need move signals that we can after the fork to prevent that.

This updates the code to set TIF_SIGPENDING on a new task if there
are signals or other activities that have moved so that they appear
to happen after the fork.

As the code today restarts if it sees any such activity this won't
immediately have an effect, as there will be no reason for it
to set TIF_SIGPENDING immediately after the fork.

Adding calculate_sigpending means the code in fork can safely be
changed to not always restart if a signal is pending.

The new calculate_sigpending function sets sigpending if there
are pending bits in jobctl, pending signals, the freezer needs
to freeze the new task or the live kernel patching framework
need the new thread to take the slow path to userspace.

I have verified that setting TIF_SIGPENDING does make a new process
take the slow path to userspace before it executes it's first userspace
instruction.

I have looked at the callers of signal_wake_up and the code paths
setting TIF_SIGPENDING and I don't see anything else that needs to be
handled.  The code probably doesn't need to set TIF_SIGPENDING for the
kernel live patching as it uses a separate thread flag as well.  But
at this point it seems safer reuse the recalc_sigpending logic and get
the kernel live patching folks to sort out their story later.

V2: I have moved the test into schedule_tail where siglock can
    be grabbed and recalc_sigpending can be reused directly.
    Further as the last action of setting up a new task this
    guarantees that TIF_SIGPENDING will be properly set in the
    new process.

    The helper calculate_sigpending takes the siglock and
    uncontitionally sets TIF_SIGPENDING and let's recalc_sigpending
    clear TIF_SIGPENDING if it is unnecessary.  This allows reusing
    the existing code and keeps maintenance of the conditions simple.

    Oleg Nesterov <oleg@redhat.com>  suggested the movement
    and pointed out the need to take siglock if this code
    was going to be called while the new task is discoverable.
Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com>
      088fe47c
  13. 31 7月, 2018 1 次提交
    • J
      tracing: Centralize preemptirq tracepoints and unify their usage · c3bc8fd6
      由 Joel Fernandes (Google) 提交于 
      This patch detaches the preemptirq tracepoints from the tracers and
keeps it separate.

Advantages:
* Lockdep and irqsoff event can now run in parallel since they no longer
have their own calls.

* This unifies the usecase of adding hooks to an irqsoff and irqson
event, and a preemptoff and preempton event.
  3 users of the events exist:
  - Lockdep
  - irqsoff and preemptoff tracers
  - irqs and preempt trace events

The unification cleans up several ifdefs and makes the code in preempt
tracer and irqsoff tracers simpler. It gets rid of all the horrific
ifdeferry around PROVE_LOCKING and makes configuration of the different
users of the tracepoints more easy and understandable. It also gets rid
of the time_* function calls from the lockdep hooks used to call into
the preemptirq tracer which is not needed anymore. The negative delta in
lines of code in this patch is quite large too.

In the patch we introduce a new CONFIG option PREEMPTIRQ_TRACEPOINTS
as a single point for registering probes onto the tracepoints. With
this,
the web of config options for preempt/irq toggle tracepoints and its
users becomes:

 PREEMPT_TRACER   PREEMPTIRQ_EVENTS  IRQSOFF_TRACER PROVE_LOCKING
       |                 |     \         |           |
       \    (selects)    /      \        \ (selects) /
      TRACE_PREEMPT_TOGGLE       ----> TRACE_IRQFLAGS
                      \                  /
                       \ (depends on)   /
                     PREEMPTIRQ_TRACEPOINTS

Other than the performance tests mentioned in the previous patch, I also
ran the locking API test suite. I verified that all tests cases are
passing.

I also injected issues by not registering lockdep probes onto the
tracepoints and I see failures to confirm that the probes are indeed
working.

This series + lockdep probes not registered (just to inject errors):
[    0.000000]      hard-irqs-on + irq-safe-A/21:  ok  |  ok  |  ok  |
[    0.000000]      soft-irqs-on + irq-safe-A/21:  ok  |  ok  |  ok  |
[    0.000000]        sirq-safe-A => hirqs-on/12:FAILED|FAILED|  ok  |
[    0.000000]        sirq-safe-A => hirqs-on/21:FAILED|FAILED|  ok  |
[    0.000000]          hard-safe-A + irqs-on/12:FAILED|FAILED|  ok  |
[    0.000000]          soft-safe-A + irqs-on/12:FAILED|FAILED|  ok  |
[    0.000000]          hard-safe-A + irqs-on/21:FAILED|FAILED|  ok  |
[    0.000000]          soft-safe-A + irqs-on/21:FAILED|FAILED|  ok  |
[    0.000000]     hard-safe-A + unsafe-B #1/123:  ok  |  ok  |  ok  |
[    0.000000]     soft-safe-A + unsafe-B #1/123:  ok  |  ok  |  ok  |

With this series + lockdep probes registered, all locking tests pass:

[    0.000000]      hard-irqs-on + irq-safe-A/21:  ok  |  ok  |  ok  |
[    0.000000]      soft-irqs-on + irq-safe-A/21:  ok  |  ok  |  ok  |
[    0.000000]        sirq-safe-A => hirqs-on/12:  ok  |  ok  |  ok  |
[    0.000000]        sirq-safe-A => hirqs-on/21:  ok  |  ok  |  ok  |
[    0.000000]          hard-safe-A + irqs-on/12:  ok  |  ok  |  ok  |
[    0.000000]          soft-safe-A + irqs-on/12:  ok  |  ok  |  ok  |
[    0.000000]          hard-safe-A + irqs-on/21:  ok  |  ok  |  ok  |
[    0.000000]          soft-safe-A + irqs-on/21:  ok  |  ok  |  ok  |
[    0.000000]     hard-safe-A + unsafe-B #1/123:  ok  |  ok  |  ok  |
[    0.000000]     soft-safe-A + unsafe-B #1/123:  ok  |  ok  |  ok  |

Link: http://lkml.kernel.org/r/20180730222423.196630-4-joel@joelfernandes.orgAcked-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NNamhyung Kim <namhyung@kernel.org>
Signed-off-by: NJoel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: NSteven Rostedt (VMware) <rostedt@goodmis.org>
      c3bc8fd6
  15. 25 7月, 2018 3 次提交
  17. 20 7月, 2018 1 次提交
  19. 17 7月, 2018 2 次提交
  21. 16 7月, 2018 4 次提交
  23. 03 7月, 2018 2 次提交
    • P
      kthread, sched/core: Fix kthread_parkme() (again...) · 1cef1150
      由 Peter Zijlstra 提交于 
      Gaurav reports that commit:

  85f1abe0 ("kthread, sched/wait: Fix kthread_parkme() completion issue")

isn't working for him. Because of the following race:

> controller Thread                               CPUHP Thread
> takedown_cpu
> kthread_park
> kthread_parkme
> Set KTHREAD_SHOULD_PARK
>                                                 smpboot_thread_fn
>                                                 set Task interruptible
>
>
> wake_up_process
>  if (!(p->state & state))
>                 goto out;
>
>                                                 Kthread_parkme
>                                                 SET TASK_PARKED
>                                                 schedule
>                                                 raw_spin_lock(&rq->lock)
> ttwu_remote
> waiting for __task_rq_lock
>                                                 context_switch
>
>                                                 finish_lock_switch
>
>
>
>                                                 Case TASK_PARKED
>                                                 kthread_park_complete
>
>
> SET Running

Furthermore, Oleg noticed that the whole scheduler TASK_PARKED
handling is buggered because the TASK_DEAD thing is done with
preemption disabled, the current code can still complete early on
preemption :/

So basically revert that earlier fix and go with a variant of the
alternative mentioned in the commit. Promote TASK_PARKED to special
state to avoid the store-store issue on task->state leading to the
WARN in kthread_unpark() -> __kthread_bind().

But in addition, add wait_task_inactive() to kthread_park() to ensure
the task really is PARKED when we return from kthread_park(). This
avoids the whole kthread still gets migrated nonsense -- although it
would be really good to get this done differently.
Reported-by: NGaurav Kohli <gkohli@codeaurora.org>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 85f1abe0 ("kthread, sched/wait: Fix kthread_parkme() completion issue")
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      1cef1150
    • F
      sched/nohz: Skip remote tick on idle task entirely · d9c0ffca
      由 Frederic Weisbecker 提交于 
      Some people have reported that the warning in sched_tick_remote()
occasionally triggers, especially in favour of some RCU-Torture
pressure:

	WARNING: CPU: 11 PID: 906 at kernel/sched/core.c:3138 sched_tick_remote+0xb6/0xc0
	Modules linked in:
	CPU: 11 PID: 906 Comm: kworker/u32:3 Not tainted 4.18.0-rc2+ #1
	Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
	Workqueue: events_unbound sched_tick_remote
	RIP: 0010:sched_tick_remote+0xb6/0xc0
	Code: e8 0f 06 b8 00 c6 03 00 fb eb 9d 8b 43 04 85 c0 75 8d 48 8b 83 e0 0a 00 00 48 85 c0 75 81 eb 88 48 89 df e8 bc fe ff ff eb aa <0f> 0b eb
	+c5 66 0f 1f 44 00 00 bf 17 00 00 00 e8 b6 2e fe ff 0f b6
	Call Trace:
	 process_one_work+0x1df/0x3b0
	 worker_thread+0x44/0x3d0
	 kthread+0xf3/0x130
	 ? set_worker_desc+0xb0/0xb0
	 ? kthread_create_worker_on_cpu+0x70/0x70
	 ret_from_fork+0x35/0x40

This happens when the remote tick applies on an idle task. Usually the
idle_cpu() check avoids that, but it is performed before we lock the
runqueue and it is therefore racy. It was intended to be that way in
order to prevent from useless runqueue locks since idle task tick
callback is a no-op.

Now if the racy check slips out of our hands and we end up remotely
ticking an idle task, the empty task_tick_idle() is harmless. Still
it won't pass the WARN_ON_ONCE() test that ensures rq_clock_task() is
not too far from curr->se.exec_start because update_curr_idle() doesn't
update the exec_start value like other scheduler policies. Hence the
reported false positive.

So let's have another check, while the rq is locked, to make sure we
don't remote tick on an idle task. The lockless idle_cpu() still applies
to avoid unecessary rq lock contention.
Reported-by: NJacek Tomaka <jacekt@dug.com>
Reported-by: NPaul E. McKenney <paulmck@linux.vnet.ibm.com>
Reported-by: NAnna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: NFrederic Weisbecker <frederic@kernel.org>
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>
Link: http://lkml.kernel.org/r/1530203381-31234-1-git-send-email-frederic@kernel.orgSigned-off-by: NIngo Molnar <mingo@kernel.org>
      d9c0ffca
  25. 21 6月, 2018 1 次提交
  27. 15 6月, 2018 1 次提交
    • M
      sched/core / kcov: avoid kcov_area during task switch · 0ed557aa
      由 Mark Rutland 提交于 
      During a context switch, we first switch_mm() to the next task's mm,
then switch_to() that new task.  This means that vmalloc'd regions which
had previously been faulted in can transiently disappear in the context
of the prev task.

Functions instrumented by KCOV may try to access a vmalloc'd kcov_area
during this window, and as the fault handling code is instrumented, this
results in a recursive fault.

We must avoid accessing any kcov_area during this window.  We can do so
with a new flag in kcov_mode, set prior to switching the mm, and cleared
once the new task is live.  Since task_struct::kcov_mode isn't always a
specific enum kcov_mode value, this is made an unsigned int.

The manipulation is hidden behind kcov_{prepare,finish}_switch() helpers,
which are empty for !CONFIG_KCOV kernels.

The code uses macros because I can't use static inline functions without a
circular include dependency between <linux/sched.h> and <linux/kcov.h>,
since the definition of task_struct uses things defined in <linux/kcov.h>

Link: http://lkml.kernel.org/r/20180504135535.53744-4-mark.rutland@arm.comSigned-off-by: NMark Rutland <mark.rutland@arm.com>
Acked-by: NAndrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      0ed557aa
  29. 06 6月, 2018 1 次提交
    • M
      rseq: Introduce restartable sequences system call · d7822b1e
      由 Mathieu Desnoyers 提交于 
      Expose a new system call allowing each thread to register one userspace
memory area to be used as an ABI between kernel and user-space for two
purposes: user-space restartable sequences and quick access to read the
current CPU number value from user-space.

* Restartable sequences (per-cpu atomics)

Restartables sequences allow user-space to perform update operations on
per-cpu data without requiring heavy-weight atomic operations.

The restartable critical sections (percpu atomics) work has been started
by Paul Turner and Andrew Hunter. It lets the kernel handle restart of
critical sections. [1] [2] The re-implementation proposed here brings a
few simplifications to the ABI which facilitates porting to other
architectures and speeds up the user-space fast path.

Here are benchmarks of various rseq use-cases.

Test hardware:

arm32: ARMv7 Processor rev 4 (v7l) "Cubietruck", 2-core
x86-64: Intel E5-2630 v3@2.40GHz, 16-core, hyperthreading

The following benchmarks were all performed on a single thread.

* Per-CPU statistic counter increment

                getcpu+atomic (ns/op)    rseq (ns/op)    speedup
arm32:                344.0                 31.4          11.0
x86-64:                15.3                  2.0           7.7

* LTTng-UST: write event 32-bit header, 32-bit payload into tracer
             per-cpu buffer

                getcpu+atomic (ns/op)    rseq (ns/op)    speedup
arm32:               2502.0                 2250.0         1.1
x86-64:               117.4                   98.0         1.2

* liburcu percpu: lock-unlock pair, dereference, read/compare word

                getcpu+atomic (ns/op)    rseq (ns/op)    speedup
arm32:                751.0                 128.5          5.8
x86-64:                53.4                  28.6          1.9

* jemalloc memory allocator adapted to use rseq

Using rseq with per-cpu memory pools in jemalloc at Facebook (based on
rseq 2016 implementation):

The production workload response-time has 1-2% gain avg. latency, and
the P99 overall latency drops by 2-3%.

* Reading the current CPU number

Speeding up reading the current CPU number on which the caller thread is
running is done by keeping the current CPU number up do date within the
cpu_id field of the memory area registered by the thread. This is done
by making scheduler preemption set the TIF_NOTIFY_RESUME flag on the
current thread. Upon return to user-space, a notify-resume handler
updates the current CPU value within the registered user-space memory
area. User-space can then read the current CPU number directly from
memory.

Keeping the current cpu id in a memory area shared between kernel and
user-space is an improvement over current mechanisms available to read
the current CPU number, which has the following benefits over
alternative approaches:

- 35x speedup on ARM vs system call through glibc
- 20x speedup on x86 compared to calling glibc, which calls vdso
  executing a "lsl" instruction,
- 14x speedup on x86 compared to inlined "lsl" instruction,
- Unlike vdso approaches, this cpu_id value can be read from an inline
  assembly, which makes it a useful building block for restartable
  sequences.
- The approach of reading the cpu id through memory mapping shared
  between kernel and user-space is portable (e.g. ARM), which is not the
  case for the lsl-based x86 vdso.

On x86, yet another possible approach would be to use the gs segment
selector to point to user-space per-cpu data. This approach performs
similarly to the cpu id cache, but it has two disadvantages: it is
not portable, and it is incompatible with existing applications already
using the gs segment selector for other purposes.

Benchmarking various approaches for reading the current CPU number:

ARMv7 Processor rev 4 (v7l)
Machine model: Cubietruck
- Baseline (empty loop):                                    8.4 ns
- Read CPU from rseq cpu_id:                               16.7 ns
- Read CPU from rseq cpu_id (lazy register):               19.8 ns
- glibc 2.19-0ubuntu6.6 getcpu:                           301.8 ns
- getcpu system call:                                     234.9 ns

x86-64 Intel(R) Xeon(R) CPU E5-2630 v3 @ 2.40GHz:
- Baseline (empty loop):                                    0.8 ns
- Read CPU from rseq cpu_id:                                0.8 ns
- Read CPU from rseq cpu_id (lazy register):                0.8 ns
- Read using gs segment selector:                           0.8 ns
- "lsl" inline assembly:                                   13.0 ns
- glibc 2.19-0ubuntu6 getcpu:                              16.6 ns
- getcpu system call:                                      53.9 ns

- Speed (benchmark taken on v8 of patchset)

Running 10 runs of hackbench -l 100000 seems to indicate, contrary to
expectations, that enabling CONFIG_RSEQ slightly accelerates the
scheduler:

Configuration: 2 sockets * 8-core Intel(R) Xeon(R) CPU E5-2630 v3 @
2.40GHz (directly on hardware, hyperthreading disabled in BIOS, energy
saving disabled in BIOS, turboboost disabled in BIOS, cpuidle.off=1
kernel parameter), with a Linux v4.6 defconfig+localyesconfig,
restartable sequences series applied.

* CONFIG_RSEQ=n

avg.:      41.37 s
std.dev.:   0.36 s

* CONFIG_RSEQ=y

avg.:      40.46 s
std.dev.:   0.33 s

- Size

On x86-64, between CONFIG_RSEQ=n/y, the text size increase of vmlinux is
567 bytes, and the data size increase of vmlinux is 5696 bytes.

[1] https://lwn.net/Articles/650333/
[2] http://www.linuxplumbersconf.org/2013/ocw/system/presentations/1695/original/LPC%20-%20PerCpu%20Atomics.pdfSigned-off-by: NMathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Andrew Hunter <ahh@google.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: linux-api@vger.kernel.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20151027235635.16059.11630.stgit@pjt-glaptop.roam.corp.google.com
Link: http://lkml.kernel.org/r/20150624222609.6116.86035.stgit@kitami.mtv.corp.google.com
Link: https://lkml.kernel.org/r/20180602124408.8430-3-mathieu.desnoyers@efficios.com
      d7822b1e
  31. 31 5月, 2018 2 次提交
    • P
      sched/core: Require cpu_active() in select_task_rq(), for user tasks · 7af443ee
      由 Paul Burton 提交于 
      select_task_rq() is used in a few paths to select the CPU upon which a
thread should be run - for example it is used by try_to_wake_up() & by
fork or exec balancing. As-is it allows use of any online CPU that is
present in the task's cpus_allowed mask.

This presents a problem because there is a period whilst CPUs are
brought online where a CPU is marked online, but is not yet fully
initialized - ie. the period where CPUHP_AP_ONLINE_IDLE <= state <
CPUHP_ONLINE. Usually we don't run any user tasks during this window,
but there are corner cases where this can happen. An example observed
is:

  - Some user task A, running on CPU X, forks to create task B.

  - sched_fork() calls __set_task_cpu() with cpu=X, setting task B's
    task_struct::cpu field to X.

  - CPU X is offlined.

  - Task A, currently somewhere between the __set_task_cpu() in
    copy_process() and the call to wake_up_new_task(), is migrated to
    CPU Y by migrate_tasks() when CPU X is offlined.

  - CPU X is onlined, but still in the CPUHP_AP_ONLINE_IDLE state. The
    scheduler is now active on CPU X, but there are no user tasks on
    the runqueue.

  - Task A runs on CPU Y & reaches wake_up_new_task(). This calls
    select_task_rq() with cpu=X, taken from task B's task_struct,
    and select_task_rq() allows CPU X to be returned.

  - Task A enqueues task B on CPU X's runqueue, via activate_task() &
    enqueue_task().

  - CPU X now has a user task on its runqueue before it has reached the
    CPUHP_ONLINE state.

In most cases, the user tasks that schedule on the newly onlined CPU
have no idea that anything went wrong, but one case observed to be
problematic is if the task goes on to invoke the sched_setaffinity
syscall. The newly onlined CPU reaches the CPUHP_AP_ONLINE_IDLE state
before the CPU that brought it online calls stop_machine_unpark(). This
means that for a portion of the window of time between
CPUHP_AP_ONLINE_IDLE & CPUHP_ONLINE the newly onlined CPU's struct
cpu_stopper has its enabled field set to false. If a user thread is
executed on the CPU during this window and it invokes sched_setaffinity
with a CPU mask that does not include the CPU it's running on, then when
__set_cpus_allowed_ptr() calls stop_one_cpu() intending to invoke
migration_cpu_stop() and perform the actual migration away from the CPU
it will simply return -ENOENT rather than calling migration_cpu_stop().
We then return from the sched_setaffinity syscall back to the user task
that is now running on a CPU which it just asked not to run on, and
which is not present in its cpus_allowed mask.

This patch resolves the problem by having select_task_rq() enforce that
user tasks run on CPUs that are active - the same requirement that
select_fallback_rq() already enforces. This should ensure that newly
onlined CPUs reach the CPUHP_AP_ACTIVE state before being able to
schedule user tasks, and also implies that bringup_wait_for_ap() will
have called stop_machine_unpark() which resolves the sched_setaffinity
issue above.

I haven't yet investigated them, but it may be of interest to review
whether any of the actions performed by hotplug states between
CPUHP_AP_ONLINE_IDLE & CPUHP_AP_ACTIVE could have similar unintended
effects on user tasks that might schedule before they are reached, which
might widen the scope of the problem from just affecting the behaviour
of sched_setaffinity.
Signed-off-by: NPaul Burton <paul.burton@mips.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>
Link: http://lkml.kernel.org/r/20180526154648.11635-2-paul.burton@mips.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      7af443ee
    • P
      sched/core: Fix rules for running on online && !active CPUs · 175f0e25
      由 Peter Zijlstra 提交于 
      As already enforced by the WARN() in __set_cpus_allowed_ptr(), the rules
for running on an online && !active CPU are stricter than just being a
kthread, you need to be a per-cpu kthread.

If you're not strictly per-CPU, you have better CPUs to run on and
don't need the partially booted one to get your work done.

The exception is to allow smpboot threads to bootstrap the CPU itself
and get kernel 'services' initialized before we allow userspace on it.
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 955dbdf4 ("sched: Allow migrating kthreads into online but inactive CPUs")
Link: http://lkml.kernel.org/r/20170725165821.cejhb7v2s3kecems@hirez.programming.kicks-ass.netSigned-off-by: NIngo Molnar <mingo@kernel.org>
      175f0e25
  33. 16 5月, 2018 1 次提交
  35. 14 5月, 2018 2 次提交
    • R
      sched/core: Distinguish between idle_cpu() calls based on desired effect,... · 943d355d
      由 Rohit Jain 提交于 
      sched/core: Distinguish between idle_cpu() calls based on desired effect, introduce available_idle_cpu()

In the following commit:

  247f2f6f ("sched/core: Don't schedule threads on pre-empted vCPUs")

... we distinguish between idle_cpu() when the vCPU is not running for
scheduling threads.

However, the idle_cpu() function is used in other places for
actually checking whether the state of the CPU is idle or not.

Hence split the use of that function based on the desired return value,
by introducing the available_idle_cpu() function.

This fixes a (slight) regression in that initial vCPU commit, because
some code paths (like the load-balancer) don't care and shouldn't care
if the vCPU is preempted or not, they just want to know if there's any
tasks on the CPU.
Signed-off-by: NRohit Jain <rohit.k.jain@oracle.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: dhaval.giani@oracle.com
Cc: linux-kernel@vger.kernel.org
Cc: matt@codeblueprint.co.uk
Cc: steven.sistare@oracle.com
Cc: subhra.mazumdar@oracle.com
Link: http://lkml.kernel.org/r/1525883988-10356-1-git-send-email-rohit.k.jain@oracle.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      943d355d
    • M
      sched/numa: Stagger NUMA balancing scan periods for new threads · 13784475
      由 Mel Gorman 提交于 
      Threads share an address space and each can change the protections of the
same address space to trap NUMA faults. This is redundant and potentially
counter-productive as any thread doing the update will suffice. Potentially
only one thread is required but that thread may be idle or it may not have
any locality concerns and pick an unsuitable scan rate.

This patch uses independent scan period but they are staggered based on
the number of address space users when the thread is created.  The intent
is that threads will avoid scanning at the same time and have a chance
to adapt their scan rate later if necessary. This reduces the total scan
activity early in the lifetime of the threads.

The different in headline performance across a range of machines and
workloads is marginal but the system CPU usage is reduced as well as overall
scan activity.  The following is the time reported by NAS Parallel Benchmark
using unbound openmp threads and a D size class:

			      4.17.0-rc1             4.17.0-rc1
				 vanilla           stagger-v1r1
	Time bt.D      442.77 (   0.00%)      419.70 (   5.21%)
	Time cg.D      171.90 (   0.00%)      180.85 (  -5.21%)
	Time ep.D       33.10 (   0.00%)       32.90 (   0.60%)
	Time is.D        9.59 (   0.00%)        9.42 (   1.77%)
	Time lu.D      306.75 (   0.00%)      304.65 (   0.68%)
	Time mg.D       54.56 (   0.00%)       52.38 (   4.00%)
	Time sp.D     1020.03 (   0.00%)      903.77 (  11.40%)
	Time ua.D      400.58 (   0.00%)      386.49 (   3.52%)

Note it's not a universal win but we have no prior knowledge of which
thread matters but the number of threads created often exceeds the size
of the node when the threads are not bound. However, there is a reducation
of overall system CPU usage:

				    4.17.0-rc1             4.17.0-rc1
				       vanilla           stagger-v1r1
	sys-time-bt.D         48.78 (   0.00%)       48.22 (   1.15%)
	sys-time-cg.D         25.31 (   0.00%)       26.63 (  -5.22%)
	sys-time-ep.D          1.65 (   0.00%)        0.62 (  62.42%)
	sys-time-is.D         40.05 (   0.00%)       24.45 (  38.95%)
	sys-time-lu.D         37.55 (   0.00%)       29.02 (  22.72%)
	sys-time-mg.D         47.52 (   0.00%)       34.92 (  26.52%)
	sys-time-sp.D        119.01 (   0.00%)      109.05 (   8.37%)
	sys-time-ua.D         51.52 (   0.00%)       45.13 (  12.40%)

NUMA scan activity is also reduced:

	NUMA alloc local               1042828     1342670
	NUMA base PTE updates        140481138    93577468
	NUMA huge PMD updates           272171      180766
	NUMA page range updates      279832690   186129660
	NUMA hint faults               1395972     1193897
	NUMA hint local faults          877925      855053
	NUMA hint local percent             62          71
	NUMA pages migrated           12057909     9158023

Similar observations are made for other thread-intensive workloads. System
CPU usage is lower even though the headline gains in performance tend to be
small. For example, specjbb 2005 shows almost no difference in performance
but scan activity is reduced by a third on a 4-socket box. I didn't find
a workload (thread intensive or otherwise) that suffered badly.
Signed-off-by: NMel Gorman <mgorman@techsingularity.net>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Link: http://lkml.kernel.org/r/20180504154109.mvrha2qo5wdl65vr@techsingularity.netSigned-off-by: NIngo Molnar <mingo@kernel.org>
      13784475
  37. 05 5月, 2018 1 次提交
  39. 04 5月, 2018 2 次提交
    • R
      sched/core: Don't schedule threads on pre-empted vCPUs · 247f2f6f
      由 Rohit Jain 提交于 
      In paravirt configurations today, spinlocks figure out whether a vCPU is
running to determine whether or not spinlock should bother spinning. We
can use the same logic to prioritize CPUs when scheduling threads. If a
vCPU has been pre-empted, it will incur the extra cost of VMENTER and
the time it actually spends to be running on the host CPU. If we had
other vCPUs which were actually running on the host CPU and idle we
should schedule threads there.

Performance numbers:

Note: With patch is referred to as Paravirt in the following and without
patch is referred to as Base.

1) When only 1 VM is running:

    a) Hackbench test on KVM 8 vCPUs, 10,000 loops (lower is better):

	+-------+-----------------+----------------+
	|Number |Paravirt         |Base            |
	|of     +---------+-------+-------+--------+
	|Threads|Average  |Std Dev|Average| Std Dev|
	+-------+---------+-------+-------+--------+
	|1      |1.817    |0.076  |1.721  | 0.067  |
	|2      |3.467    |0.120  |3.468  | 0.074  |
	|4      |6.266    |0.035  |6.314  | 0.068  |
	|8      |11.437   |0.105  |11.418 | 0.132  |
	|16     |21.862   |0.167  |22.161 | 0.129  |
	|25     |33.341   |0.326  |33.692 | 0.147  |
	+-------+---------+-------+-------+--------+

2) When two VMs are running with same CPU affinities:

    a) tbench test on VM 8 cpus

    Base:

	VM1:

	Throughput 220.59 MB/sec   1 clients  1 procs  max_latency=12.872 ms
	Throughput 448.716 MB/sec  2 clients  2 procs  max_latency=7.555 ms
	Throughput 861.009 MB/sec  4 clients  4 procs  max_latency=49.501 ms
	Throughput 1261.81 MB/sec  7 clients  7 procs  max_latency=76.990 ms

	VM2:

	Throughput 219.937 MB/sec  1 clients  1 procs  max_latency=12.517 ms
	Throughput 470.99 MB/sec   2 clients  2 procs  max_latency=12.419 ms
	Throughput 841.299 MB/sec  4 clients  4 procs  max_latency=37.043 ms
	Throughput 1240.78 MB/sec  7 clients  7 procs  max_latency=77.489 ms

    Paravirt:

	VM1:

	Throughput 222.572 MB/sec  1 clients  1 procs  max_latency=7.057 ms
	Throughput 485.993 MB/sec  2 clients  2 procs  max_latency=26.049 ms
	Throughput 947.095 MB/sec  4 clients  4 procs  max_latency=45.338 ms
	Throughput 1364.26 MB/sec  7 clients  7 procs  max_latency=145.124 ms

	VM2:

	Throughput 224.128 MB/sec  1 clients  1 procs  max_latency=4.564 ms
	Throughput 501.878 MB/sec  2 clients  2 procs  max_latency=11.061 ms
	Throughput 965.455 MB/sec  4 clients  4 procs  max_latency=45.370 ms
	Throughput 1359.08 MB/sec  7 clients  7 procs  max_latency=168.053 ms

    b) Hackbench with 4 fd 1,000,000 loops

	+-------+--------------------------------------+----------------------------------------+
	|Number |Paravirt                              |Base                                    |
	|of     +----------+--------+---------+--------+----------+--------+---------+----------+
	|Threads|Average1  |Std Dev1|Average2 | Std Dev|Average1  |Std Dev1|Average2 | Std Dev 2|
	+-------+----------+--------+---------+--------+----------+--------+---------+----------+
	|  1    | 3.748    | 0.620  | 3.576   | 0.432  | 4.006    | 0.395  | 3.446   | 0.787    |
	+-------+----------+--------+---------+--------+----------+--------+---------+----------+

    Note that this test was run just to show the interference effect
    over-subscription can have in baseline

    c) schbench results with 2 message groups on 8 vCPU VMs

	+-----------+-------+---------------+--------------+------------+
	|           |       | Paravirt      | Base         |            |
	+-----------+-------+-------+-------+-------+------+------------+
	|           |Threads| VM1   | VM2   |  VM1  | VM2  |%Improvement|
	+-----------+-------+-------+-------+-------+------+------------+
	|50.0000th  |    1  | 52    | 53    |  58   | 54   |  +6.25%    |
	|75.0000th  |    1  | 69    | 61    |  83   | 59   |  +8.45%    |
	|90.0000th  |    1  | 80    | 80    |  89   | 83   |  +6.98%    |
	|95.0000th  |    1  | 83    | 83    |  93   | 87   |  +7.78%    |
	|*99.0000th |    1  | 92    | 94    |  99   | 97   |  +5.10%    |
	|99.5000th  |    1  | 95    | 100   |  102  | 103  |  +4.88%    |
	|99.9000th  |    1  | 107   | 123   |  105  | 203  |  +25.32%   |
	+-----------+-------+-------+-------+-------+------+------------+
	|50.0000th  |    2  | 56    | 62    |  67   | 59   |  +6.35%    |
	|75.0000th  |    2  | 69    | 75    |  80   | 71   |  +4.64%    |
	|90.0000th  |    2  | 80    | 82    |  90   | 81   |  +5.26%    |
	|95.0000th  |    2  | 85    | 87    |  97   | 91   |  +8.51%    |
	|*99.0000th |    2  | 98    | 99    |  107  | 109  |  +8.79%    |
	|99.5000th  |    2  | 107   | 105   |  109  | 116  |  +5.78%    |
	|99.9000th  |    2  | 9968  | 609   |  875  | 3116 | -165.02%   |
	+-----------+-------+-------+-------+-------+------+------------+
	|50.0000th  |    4  | 78    | 77    |  78   | 79   |  +1.27%    |
	|75.0000th  |    4  | 98    | 106   |  100  | 104  |   0.00%    |
	|90.0000th  |    4  | 987   | 1001  |  995  | 1015 |  +1.09%    |
	|95.0000th  |    4  | 4136  | 5368  |  5752 | 5192 |  +13.16%   |
	|*99.0000th |    4  | 11632 | 11344 |  11024| 10736|  -5.59%    |
	|99.5000th  |    4  | 12624 | 13040 |  12720| 12144|  -3.22%    |
	|99.9000th  |    4  | 13168 | 18912 |  14992| 17824|  +2.24%    |
	+-----------+-------+-------+-------+-------+------+------------+

    Note: Improvement is measured for (VM1+VM2)
Signed-off-by: NRohit Jain <rohit.k.jain@oracle.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: dhaval.giani@oracle.com
Cc: matt@codeblueprint.co.uk
Cc: steven.sistare@oracle.com
Cc: subhra.mazumdar@oracle.com
Link: http://lkml.kernel.org/r/1525294330-7759-1-git-send-email-rohit.k.jain@oracle.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      247f2f6f
    • P
      sched/core: Introduce set_special_state() · b5bf9a90
      由 Peter Zijlstra 提交于 
      Gaurav reported a perceived problem with TASK_PARKED, which turned out
to be a broken wait-loop pattern in __kthread_parkme(), but the
reported issue can (and does) in fact happen for states that do not do
condition based sleeps.

When the 'current->state = TASK_RUNNING' store of a previous
(concurrent) try_to_wake_up() collides with the setting of a 'special'
sleep state, we can loose the sleep state.

Normal condition based wait-loops are immune to this problem, but for
sleep states that are not condition based are subject to this problem.

There already is a fix for TASK_DEAD. Abstract that and also apply it
to TASK_STOPPED and TASK_TRACED, both of which are also without
condition based wait-loop.
Reported-by: NGaurav Kohli <gkohli@codeaurora.org>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NOleg Nesterov <oleg@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      b5bf9a90
  41. 03 5月, 2018 1 次提交
    • P
      kthread, sched/wait: Fix kthread_parkme() completion issue · 85f1abe0
      由 Peter Zijlstra 提交于 
      Even with the wait-loop fixed, there is a further issue with
kthread_parkme(). Upon hotplug, when we do takedown_cpu(),
smpboot_park_threads() can return before all those threads are in fact
blocked, due to the placement of the complete() in __kthread_parkme().

When that happens, sched_cpu_dying() -> migrate_tasks() can end up
migrating such a still runnable task onto another CPU.

Normally the task will have hit schedule() and gone to sleep by the
time we do kthread_unpark(), which will then do __kthread_bind() to
re-bind the task to the correct CPU.

However, when we loose the initial TASK_PARKED store to the concurrent
wakeup issue described previously, do the complete(), get migrated, it
is possible to either:

 - observe kthread_unpark()'s clearing of SHOULD_PARK and terminate
   the park and set TASK_RUNNING, or

 - __kthread_bind()'s wait_task_inactive() to observe the competing
   TASK_RUNNING store.

Either way the WARN() in __kthread_bind() will trigger and fail to
correctly set the CPU affinity.

Fix this by only issuing the complete() when the kthread has scheduled
out. This does away with all the icky 'still running' nonsense.

The alternative is to promote TASK_PARKED to a special state, this
guarantees wait_task_inactive() cannot observe a 'stale' TASK_RUNNING
and we'll end up doing the right thing, but this preserves the whole
icky business of potentially migating the still runnable thing.
Reported-by: NGaurav Kohli <gkohli@codeaurora.org>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      85f1abe0
  43. 06 4月, 2018 1 次提交
  45. 05 4月, 2018 1 次提交
  47. 03 4月, 2018 1 次提交
  49. 27 3月, 2018 1 次提交
  51. 09 3月, 2018 4 次提交
  53. 04 3月, 2018 1 次提交