linux-stable.git/kernel, branch v4.9.69

jump_label: Invoke jump_label_test() via early_initcall()

2017-12-14T08:28:24+00:00

[ Upstream commit 92ee46efeb505ead3ab06d3c5ce695637ed5f152 ]

Fengguang Wu reported that running the rcuperf test during boot can cause
the jump_label_test() to hit a WARN_ON(). The issue is that the core jump
label code relies on kernel_text_address() to detect when it can no longer
update branches that may be contained in __init sections. The
kernel_text_address() in turn assumes that if the system_state variable is
greter than or equal to SYSTEM_RUNNING then __init sections are no longer
valid (since the assumption is that they have been freed). However, when
rcuperf is setup to run in early boot it can call kernel_power_off() which
sets the system_state to SYSTEM_POWER_OFF.

Since rcuperf initialization is invoked via a module_init(), we can make
the dependency of jump_label_test() needing to complete before rcuperf
explicit by calling it via early_initcall().

Reported-by: Fengguang Wu 
Signed-off-by: Jason Baron 
Acked-by: Paul E. McKenney 
Cc: Linus Torvalds 
Cc: Peter Zijlstra 
Cc: Steven Rostedt 
Cc: Thomas Gleixner 
Link: http://lkml.kernel.org/r/1510609727-2238-1-git-send-email-jbaron@akamai.com
Signed-off-by: Ingo Molnar 
Signed-off-by: Sasha Levin 
Signed-off-by: Greg Kroah-Hartman

bpf: fix lockdep splat

2017-12-14T08:28:23+00:00

[ Upstream commit 89ad2fa3f043a1e8daae193bcb5fe34d5f8caf28 ]

pcpu_freelist_pop() needs the same lockdep awareness than
pcpu_freelist_populate() to avoid a false positive.

 [ INFO: SOFTIRQ-safe -> SOFTIRQ-unsafe lock order detected ]

 switchto-defaul/12508 [HC0[0]:SC0[6]:HE0:SE0] is trying to acquire:
  (&htab->buckets[i].lock){......}, at: [] __htab_percpu_map_update_elem+0x1cb/0x300

 and this task is already holding:
  (dev_queue->dev->qdisc_class ?: &qdisc_tx_lock#2){+.-...}, at: [] __dev_queue_xmit+0
x868/0x1240
 which would create a new lock dependency:
  (dev_queue->dev->qdisc_class ?: &qdisc_tx_lock#2){+.-...} -> (&htab->buckets[i].lock){......}

 but this new dependency connects a SOFTIRQ-irq-safe lock:
  (dev_queue->dev->qdisc_class ?: &qdisc_tx_lock#2){+.-...}
 ... which became SOFTIRQ-irq-safe at:
   [] __lock_acquire+0x42b/0x1f10
   [] lock_acquire+0xbc/0x1b0
   [] _raw_spin_lock+0x38/0x50
   [] __dev_queue_xmit+0x868/0x1240
   [] dev_queue_xmit+0x10/0x20
   [] ip_finish_output2+0x439/0x590
   [] ip_finish_output+0x150/0x2f0
   [] ip_output+0x7d/0x260
   [] ip_local_out+0x5e/0xe0
   [] ip_queue_xmit+0x205/0x620
   [] tcp_transmit_skb+0x5a8/0xcb0
   [] tcp_write_xmit+0x242/0x1070
   [] __tcp_push_pending_frames+0x3c/0xf0
   [] tcp_rcv_established+0x312/0x700
   [] tcp_v4_do_rcv+0x11c/0x200
   [] tcp_v4_rcv+0xaa2/0xc30
   [] ip_local_deliver_finish+0xa7/0x240
   [] ip_local_deliver+0x66/0x200
   [] ip_rcv_finish+0xdd/0x560
   [] ip_rcv+0x295/0x510
   [] __netif_receive_skb_core+0x988/0x1020
   [] __netif_receive_skb+0x21/0x70
   [] process_backlog+0x6f/0x230
   [] net_rx_action+0x229/0x420
   [] __do_softirq+0xd8/0x43d
   [] do_softirq_own_stack+0x1c/0x30
   [] do_softirq+0x55/0x60
   [] __local_bh_enable_ip+0xa8/0xb0
   [] cpu_startup_entry+0x1c7/0x500
   [] start_secondary+0x113/0x140

 to a SOFTIRQ-irq-unsafe lock:
  (&head->lock){+.+...}
 ... which became SOFTIRQ-irq-unsafe at:
 ...  [] __lock_acquire+0x82f/0x1f10
   [] lock_acquire+0xbc/0x1b0
   [] _raw_spin_lock+0x38/0x50
   [] pcpu_freelist_pop+0x7a/0xb0
   [] htab_map_alloc+0x50c/0x5f0
   [] SyS_bpf+0x265/0x1200
   [] entry_SYSCALL_64_fastpath+0x12/0x17

 other info that might help us debug this:

 Chain exists of:
   dev_queue->dev->qdisc_class ?: &qdisc_tx_lock#2 --> &htab->buckets[i].lock --> &head->lock

  Possible interrupt unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock(&head->lock);
                                local_irq_disable();
                                lock(dev_queue->dev->qdisc_class ?: &qdisc_tx_lock#2);
                                lock(&htab->buckets[i].lock);
   
     lock(dev_queue->dev->qdisc_class ?: &qdisc_tx_lock#2);

  *** DEADLOCK ***

Fixes: e19494edab82 ("bpf: introduce percpu_freelist")
Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller 
Signed-off-by: Sasha Levin 
Signed-off-by: Greg Kroah-Hartman

workqueue: trigger WARN if queue_delayed_work() is called with NULL @wq

2017-12-14T08:28:19+00:00

[ Upstream commit 637fdbae60d6cb9f6e963c1079d7e0445c86ff7d ]

If queue_delayed_work() gets called with NULL @wq, the kernel will
oops asynchronuosly on timer expiration which isn't too helpful in
tracking down the offender.  This actually happened with smc.

__queue_delayed_work() already does several input sanity checks
synchronously.  Add NULL @wq check.

Reported-by: Dave Jones 
Link: http://lkml.kernel.org/r/20170227171439.jshx3qplflyrgcv7@codemonkey.org.uk
Signed-off-by: Tejun Heo 
Signed-off-by: Sasha Levin 
Signed-off-by: Greg Kroah-Hartman

sched/fair: Make select_idle_cpu() more aggressive

2017-12-14T08:28:17+00:00

[ Upstream commit 4c77b18cf8b7ab37c7d5737b4609010d2ceec5f0 ]

Kitsunyan reported desktop latency issues on his Celeron 887 because
of commit:

  1b568f0aabf2 ("sched/core: Optimize SCHED_SMT")

... even though his CPU doesn't do SMT.

The effect of running the SMT code on a !SMT part is basically a more
aggressive select_idle_cpu(). Removing the avg condition fixed things
for him.

I also know FB likes this test gone, even though other workloads like
having it.

For now, take it out by default, until we get a better idea.

Reported-by: kitsunyan 
Signed-off-by: Peter Zijlstra (Intel) 
Cc: Chris Mason 
Cc: Linus Torvalds 
Cc: Mike Galbraith 
Cc: Mike Galbraith 
Cc: Peter Zijlstra 
Cc: Thomas Gleixner 
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar 
Signed-off-by: Sasha Levin 
Signed-off-by: Greg Kroah-Hartman

kdb: Fix handling of kallsyms_symbol_next() return value

2017-12-14T08:28:13+00:00

commit c07d35338081d107e57cf37572d8cc931a8e32e2 upstream.

kallsyms_symbol_next() returns a boolean (true on success). Currently
kdb_read() tests the return value with an inequality that
unconditionally evaluates to true.

This is fixed in the obvious way and, since the conditional branch is
supposed to be unreachable, we also add a WARN_ON().

Reported-by: Dan Carpenter 
Signed-off-by: Daniel Thompson 
Signed-off-by: Jason Wessel 
Signed-off-by: Greg Kroah-Hartman

smp/hotplug: Move step CPUHP_AP_SMPCFD_DYING to the correct place

2017-12-14T08:28:13+00:00

commit 46febd37f9c758b05cd25feae8512f22584742fe upstream.

Commit 31487f8328f2 ("smp/cfd: Convert core to hotplug state machine")
accidently put this step on the wrong place. The step should be at the
cpuhp_ap_states[] rather than the cpuhp_bp_states[].

grep smpcfd /sys/devices/system/cpu/hotplug/states
 40: smpcfd:prepare
129: smpcfd:dying

"smpcfd:dying" was missing before.
So was the invocation of the function smpcfd_dying_cpu().

Fixes: 31487f8328f2 ("smp/cfd: Convert core to hotplug state machine")
Signed-off-by: Lai Jiangshan 
Signed-off-by: Thomas Gleixner 
Cc: Peter Zijlstra 
Cc: Richard Weinberger 
Cc: Sebastian Andrzej Siewior 
Cc: Boris Ostrovsky 
Link: https://lkml.kernel.org/r/20171128131954.81229-1-jiangshanlai@gmail.com
Signed-off-by: Greg Kroah-Hartman

perf/x86/intel: Account interrupts for PEBS errors

2017-12-09T21:01:52+00:00

[ Upstream commit 475113d937adfd150eb82b5e2c5507125a68e7af ]

It's possible to set up PEBS events to get only errors and not
any data, like on SNB-X (model 45) and IVB-EP (model 62)
via 2 perf commands running simultaneously:

    taskset -c 1 ./perf record -c 4 -e branches:pp -j any -C 10

This leads to a soft lock up, because the error path of the
intel_pmu_drain_pebs_nhm() does not account event->hw.interrupt
for error PEBS interrupts, so in case you're getting ONLY
errors you don't have a way to stop the event when it's over
the max_samples_per_tick limit:

  NMI watchdog: BUG: soft lockup - CPU#22 stuck for 22s! [perf_fuzzer:5816]
  ...
  RIP: 0010:[]  [] smp_call_function_single+0xe2/0x140
  ...
  Call Trace:
   ? trace_hardirqs_on_caller+0xf5/0x1b0
   ? perf_cgroup_attach+0x70/0x70
   perf_install_in_context+0x199/0x1b0
   ? ctx_resched+0x90/0x90
   SYSC_perf_event_open+0x641/0xf90
   SyS_perf_event_open+0x9/0x10
   do_syscall_64+0x6c/0x1f0
   entry_SYSCALL64_slow_path+0x25/0x25

Add perf_event_account_interrupt() which does the interrupt
and frequency checks and call it from intel_pmu_drain_pebs_nhm()'s
error path.

We keep the pending_kill and pending_wakeup logic only in the
__perf_event_overflow() path, because they make sense only if
there's any data to deliver.

Signed-off-by: Jiri Olsa 
Signed-off-by: Peter Zijlstra (Intel) 
Cc: Alexander Shishkin 
Cc: Arnaldo Carvalho de Melo 
Cc: Arnaldo Carvalho de Melo 
Cc: Jiri Olsa 
Cc: Linus Torvalds 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Cc: Thomas Gleixner 
Cc: Vince Weaver 
Cc: Vince Weaver 
Link: http://lkml.kernel.org/r/1482931866-6018-2-git-send-email-jolsa@kernel.org
Signed-off-by: Ingo Molnar 
Signed-off-by: Sasha Levin 
Signed-off-by: Greg Kroah-Hartman

sched/rt: Simplify the IPI based RT balancing logic

2017-11-30T08:39:09+00:00

commit 4bdced5c9a2922521e325896a7bbbf0132c94e56 upstream.

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:

  b6366f048e0c ("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: Steven Rostedt (VMware) 
Signed-off-by: Peter Zijlstra (Intel) 
Cc: Clark Williams 
Cc: Daniel Bristot de Oliveira 
Cc: John Kacur 
Cc: Linus Torvalds 
Cc: Mike Galbraith 
Cc: Peter Zijlstra 
Cc: Scott Wood 
Cc: Thomas Gleixner 
Link: http://lkml.kernel.org/r/20170424114732.1aac6dc4@gandalf.local.home
Signed-off-by: Ingo Molnar 
Signed-off-by: Greg Kroah-Hartman

sched: Make resched_cpu() unconditional

2017-11-30T08:39:01+00:00

commit 7c2102e56a3f7d85b5d8f33efbd7aecc1f36fdd8 upstream.

The current implementation of synchronize_sched_expedited() incorrectly
assumes that resched_cpu() is unconditional, which it is not.  This means
that synchronize_sched_expedited() can hang when resched_cpu()'s trylock
fails as follows (analysis by Neeraj Upadhyay):

o	CPU1 is waiting for expedited wait to complete:

	sync_rcu_exp_select_cpus
	     rdp->exp_dynticks_snap & 0x1   // returns 1 for CPU5
	     IPI sent to CPU5

	synchronize_sched_expedited_wait
		 ret = swait_event_timeout(rsp->expedited_wq,
					   sync_rcu_preempt_exp_done(rnp_root),
					   jiffies_stall);

	expmask = 0x20, CPU 5 in idle path (in cpuidle_enter())

o	CPU5 handles IPI and fails to acquire rq lock.

	Handles IPI
	     sync_sched_exp_handler
		 resched_cpu
		     returns while failing to try lock acquire rq->lock
		 need_resched is not set

o	CPU5 calls  rcu_idle_enter() and as need_resched is not set, goes to
	idle (schedule() is not called).

o	CPU 1 reports RCU stall.

Given that resched_cpu() is now used only by RCU, this commit fixes the
assumption by making resched_cpu() unconditional.

Reported-by: Neeraj Upadhyay 
Suggested-by: Neeraj Upadhyay 
Signed-off-by: Paul E. McKenney 
Acked-by: Steven Rostedt (VMware) 
Acked-by: Peter Zijlstra (Intel) 
Signed-off-by: Greg Kroah-Hartman

workqueue: Fix NULL pointer dereference

2017-11-15T14:53:17+00:00

commit cef572ad9bd7f85035ba8272e5352040e8be0152 upstream.

When queue_work() is used in irq (not in task context), there is
a potential case that trigger NULL pointer dereference.
----------------------------------------------------------------
worker_thread()
|-spin_lock_irq()
|-process_one_work()
	|-worker->current_pwq = pwq
	|-spin_unlock_irq()
	|-worker->current_func(work)
	|-spin_lock_irq()
 	|-worker->current_pwq = NULL
|-spin_unlock_irq()

				//interrupt here
				|-irq_handler
					|-__queue_work()
						//assuming that the wq is draining
						|-is_chained_work(wq)
							|-current_wq_worker()
							//Here, 'current' is the interrupted worker!
								|-current->current_pwq is NULL here!
|-schedule()
----------------------------------------------------------------

Avoid it by checking for task context in current_wq_worker(), and
if not in task context, we shouldn't use the 'current' to check the
condition.

Reported-by: Xiaofei Tan 
Signed-off-by: Li Bin 
Reviewed-by: Lai Jiangshan 
Signed-off-by: Tejun Heo 
Fixes: 8d03ecfe4718 ("workqueue: reimplement is_chained_work() using current_wq_worker()")
Signed-off-by: Greg Kroah-Hartman