linux-stable.git/include/linux, branch v5.1.9

x86/power: Fix 'nosmt' vs hibernation triple fault during resume

2019-06-11T10:19:17+00:00

commit ec527c318036a65a083ef68d8ba95789d2212246 upstream.

As explained in

	0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once")

we always, no matter what, have to bring up x86 HT siblings during boot at
least once in order to avoid first MCE bringing the system to its knees.

That means that whenever 'nosmt' is supplied on the kernel command-line,
all the HT siblings are as a result sitting in mwait or cpudile after
going through the online-offline cycle at least once.

This causes a serious issue though when a kernel, which saw 'nosmt' on its
commandline, is going to perform resume from hibernation: if the resume
from the hibernated image is successful, cr3 is flipped in order to point
to the address space of the kernel that is being resumed, which in turn
means that all the HT siblings are all of a sudden mwaiting on address
which is no longer valid.

That results in triple fault shortly after cr3 is switched, and machine
reboots.

Fix this by always waking up all the SMT siblings before initiating the
'restore from hibernation' process; this guarantees that all the HT
siblings will be properly carried over to the resumed kernel waiting in
resume_play_dead(), and acted upon accordingly afterwards, based on the
target kernel configuration.

Symmetricaly, the resumed kernel has to push the SMT siblings to mwait
again in case it has SMT disabled; this means it has to online all
the siblings when resuming (so that they come out of hlt) and offline
them again to let them reach mwait.

Cc: 4.19+  # v4.19+
Debugged-by: Thomas Gleixner 
Fixes: 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once")
Signed-off-by: Jiri Kosina 
Acked-by: Pavel Machek 
Reviewed-by: Thomas Gleixner 
Reviewed-by: Josh Poimboeuf 
Signed-off-by: Rafael J. Wysocki 
Signed-off-by: Greg Kroah-Hartman

rcu: locking and unlocking need to always be at least barriers

2019-06-11T10:19:14+00:00

commit 66be4e66a7f422128748e3c3ef6ee72b20a6197b upstream.

Herbert Xu pointed out that commit bb73c52bad36 ("rcu: Don't disable
preemption for Tiny and Tree RCU readers") was incorrect in making the
preempt_disable/enable() be conditional on CONFIG_PREEMPT_COUNT.

If CONFIG_PREEMPT_COUNT isn't enabled, the preemption enable/disable is
a no-op, but still is a compiler barrier.

And RCU locking still _needs_ that compiler barrier.

It is simply fundamentally not true that RCU locking would be a complete
no-op: we still need to guarantee (for example) that things that can
trap and cause preemption cannot migrate into the RCU locked region.

The way we do that is by making it a barrier.

See for example commit 386afc91144b ("spinlocks and preemption points
need to be at least compiler barriers") from back in 2013 that had
similar issues with spinlocks that become no-ops on UP: they must still
constrain the compiler from moving other operations into the critical
region.

Now, it is true that a lot of RCU operations already use READ_ONCE() and
WRITE_ONCE() (which in practice likely would never be re-ordered wrt
anything remotely interesting), but it is also true that that is not
globally the case, and that it's not even necessarily always possible
(ie bitfields etc).

Reported-by: Herbert Xu 
Fixes: bb73c52bad36 ("rcu: Don't disable preemption for Tiny and Tree RCU readers")
Cc: stable@kernel.org
Cc: Boqun Feng 
Cc: Paul E. McKenney 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

memcg: make it work on sparse non-0-node systems

2019-06-09T07:16:13+00:00

commit 3e8589963773a5c23e2f1fe4bcad0e9a90b7f471 upstream.

We have a single node system with node 0 disabled:
  Scanning NUMA topology in Northbridge 24
  Number of physical nodes 2
  Skipping disabled node 0
  Node 1 MemBase 0000000000000000 Limit 00000000fbff0000
  NODE_DATA(1) allocated [mem 0xfbfda000-0xfbfeffff]

This causes crashes in memcg when system boots:
  BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
  #PF error: [normal kernel read fault]
...
  RIP: 0010:list_lru_add+0x94/0x170
...
  Call Trace:
   d_lru_add+0x44/0x50
   dput.part.34+0xfc/0x110
   __fput+0x108/0x230
   task_work_run+0x9f/0xc0
   exit_to_usermode_loop+0xf5/0x100

It is reproducible as far as 4.12.  I did not try older kernels.  You have
to have a new enough systemd, e.g.  241 (the reason is unknown -- was not
investigated).  Cannot be reproduced with systemd 234.

The system crashes because the size of lru array is never updated in
memcg_update_all_list_lrus and the reads are past the zero-sized array,
causing dereferences of random memory.

The root cause are list_lru_memcg_aware checks in the list_lru code.  The
test in list_lru_memcg_aware is broken: it assumes node 0 is always
present, but it is not true on some systems as can be seen above.

So fix this by avoiding checks on node 0.  Remember the memcg-awareness by
a bool flag in struct list_lru.

Link: http://lkml.kernel.org/r/20190522091940.3615-1-jslaby@suse.cz
Fixes: 60d3fd32a7a9 ("list_lru: introduce per-memcg lists")
Signed-off-by: Jiri Slaby 
Acked-by: Michal Hocko 
Suggested-by: Vladimir Davydov 
Acked-by: Vladimir Davydov 
Reviewed-by: Shakeel Butt 
Cc: Johannes Weiner 
Cc: Raghavendra K T 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

mm, memcg: consider subtrees in memory.events

2019-06-09T07:16:13+00:00

commit 9852ae3fe5293264f01c49f2571ef7688f7823ce upstream.

memory.stat and other files already consider subtrees in their output, and
we should too in order to not present an inconsistent interface.

The current situation is fairly confusing, because people interacting with
cgroups expect hierarchical behaviour in the vein of memory.stat,
cgroup.events, and other files.  For example, this causes confusion when
debugging reclaim events under low, as currently these always read "0" at
non-leaf memcg nodes, which frequently causes people to misdiagnose breach
behaviour.  The same confusion applies to other counters in this file when
debugging issues.

Aggregation is done at write time instead of at read-time since these
counters aren't hot (unlike memory.stat which is per-page, so it does it
at read time), and it makes sense to bundle this with the file
notifications.

After this patch, events are propagated up the hierarchy:

    [root@ktst ~]# cat /sys/fs/cgroup/system.slice/memory.events
    low 0
    high 0
    max 0
    oom 0
    oom_kill 0
    [root@ktst ~]# systemd-run -p MemoryMax=1 true
    Running as unit: run-r251162a189fb4562b9dabfdc9b0422f5.service
    [root@ktst ~]# cat /sys/fs/cgroup/system.slice/memory.events
    low 0
    high 0
    max 7
    oom 1
    oom_kill 1

As this is a change in behaviour, this can be reverted to the old
behaviour by mounting with the `memory_localevents' flag set.  However, we
use the new behaviour by default as there's a lack of evidence that there
are any current users of memory.events that would find this change
undesirable.

akpm: this is a behaviour change, so Cc:stable.  THis is so that
forthcoming distros which use cgroup v2 are more likely to pick up the
revised behaviour.

Link: http://lkml.kernel.org/r/20190208224419.GA24772@chrisdown.name
Signed-off-by: Chris Down 
Acked-by: Johannes Weiner 
Reviewed-by: Shakeel Butt 
Cc: Michal Hocko 
Cc: Tejun Heo 
Cc: Roman Gushchin 
Cc: Dennis Zhou 
Cc: Suren Baghdasaryan 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

include/linux/bitops.h: sanitize rotate primitives

2019-06-09T07:16:06+00:00

commit ef4d6f6b275c498f8e5626c99dbeefdc5027f843 upstream.

The ror32 implementation (word >> shift) | (word << (32 - shift) has
undefined behaviour if shift is outside the [1, 31] range.  Similarly
for the 64 bit variants.  Most callers pass a compile-time constant
(naturally in that range), but there's an UBSAN report that these may
actually be called with a shift count of 0.

Instead of special-casing that, we can make them DTRT for all values of
shift while also avoiding UB.  For some reason, this was already partly
done for rol32 (which was well-defined for [0, 31]).  gcc 8 recognizes
these patterns as rotates, so for example

  __u32 rol32(__u32 word, unsigned int shift)
  {
	return (word << (shift & 31)) | (word >> ((-shift) & 31));
  }

compiles to

0000000000000020 :
  20:   89 f8                   mov    %edi,%eax
  22:   89 f1                   mov    %esi,%ecx
  24:   d3 c0                   rol    %cl,%eax
  26:   c3                      retq

Older compilers unfortunately do not do as well, but this only affects
the small minority of users that don't pass constants.

Due to integer promotions, ro[lr]8 were already well-defined for shifts
in [0, 8], and ro[lr]16 were mostly well-defined for shifts in [0, 16]
(only mostly - u16 gets promoted to _signed_ int, so if bit 15 is set,
word << 16 is undefined).  For consistency, update those as well.

Link: http://lkml.kernel.org/r/20190410211906.2190-1-linux@rasmusvillemoes.dk
Signed-off-by: Rasmus Villemoes 
Reported-by: Ido Schimmel 
Tested-by: Ido Schimmel 
Reviewed-by: Will Deacon 
Cc: Vadim Pasternak 
Cc: Andrey Ryabinin 
Cc: Jacek Anaszewski 
Cc: Pavel Machek 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

inet: switch IP ID generator to siphash

2019-06-04T05:59:40+00:00

[ Upstream commit df453700e8d81b1bdafdf684365ee2b9431fb702 ]

According to Amit Klein and Benny Pinkas, IP ID generation is too weak
and might be used by attackers.

Even with recent net_hash_mix() fix (netns: provide pure entropy for net_hash_mix())
having 64bit key and Jenkins hash is risky.

It is time to switch to siphash and its 128bit keys.

Signed-off-by: Eric Dumazet 
Reported-by: Amit Klein 
Reported-by: Benny Pinkas 
Signed-off-by: David S. Miller 
Signed-off-by: Greg Kroah-Hartman

regulator: add regulator_get_linear_step() stub helper

2019-05-31T13:43:50+00:00

[ Upstream commit 7287275b4301e230be9e4569431c7dacb67ebc13 ]

The regulator header has empty inline functions for most interfaces,
but not regulator_get_linear_step(), which has just grown a user
that does not depend on regulators otherwise:

drivers/clk/tegra/clk-tegra124-dfll-fcpu.c: In function 'get_alignment_from_regulator':
drivers/clk/tegra/clk-tegra124-dfll-fcpu.c:555:19: error: implicit declaration of function 'regulator_get_linear_step'; did you mean 'regulator_get_drvdata'? [-Werror=implicit-function-declaration]
  align->step_uv = regulator_get_linear_step(reg);
                   ^~~~~~~~~~~~~~~~~~~~~~~~~
                   regulator_get_drvdata
cc1: all warnings being treated as errors
scripts/Makefile.build:278: recipe for target 'drivers/clk/tegra/clk-tegra124-dfll-fcpu.o' failed

Add the missing stub along the others.

Fixes: b3cf8d069505 ("clk: tegra: dfll: CVB calculation alignment with the regulator")
Signed-off-by: Arnd Bergmann 
Signed-off-by: Mark Brown 
Signed-off-by: Sasha Levin

rcu: Do a single rhp->func read in rcu_head_after_call_rcu()

2019-05-31T13:43:48+00:00

[ Upstream commit b699cce1604e828f19c39845252626eb78cdf38a ]

The rcu_head_after_call_rcu() function reads the rhp->func pointer twice,
which can result in a false-positive WARN_ON_ONCE() if the callback
were passed to call_rcu() between the two reads.  Although racing
rcu_head_after_call_rcu() with call_rcu() is to be a dubious use case
(the return value is not reliable in that case), intermittent and
irreproducible warnings are also quite dubious.  This commit therefore
uses a single READ_ONCE() to pick up the value of rhp->func once, then
tests that value twice, thus guaranteeing consistent processing within
rcu_head_after_call_rcu()().

Neverthless, racing rcu_head_after_call_rcu() with call_rcu() is still
a dubious use case.

Signed-off-by: Neeraj Upadhyay 
[ paulmck: Add blank line after declaration per checkpatch.pl. ]
Signed-off-by: Paul E. McKenney 
Signed-off-by: Sasha Levin

overflow: Fix -Wtype-limits compilation warnings

2019-05-31T13:43:47+00:00

[ Upstream commit dc7fe518b0493faa0af0568d6d8c2a33c00f58d0 ]

Attempt to use check_shl_overflow() with inputs of unsigned type
produces the following compilation warnings.

drivers/infiniband/hw/mlx5/qp.c: In function _set_user_rq_size_:
./include/linux/overflow.h:230:6: warning: comparison of unsigned
expression >= 0 is always true [-Wtype-limits]
   _s >= 0 && _s < 8 * sizeof(*d) ? _s : 0;  \
      ^~
drivers/infiniband/hw/mlx5/qp.c:5820:6: note: in expansion of macro _check_shl_overflow_
  if (check_shl_overflow(rwq->wqe_count, rwq->wqe_shift,
&rwq->buf_size))
      ^~~~~~~~~~~~~~~~~~
./include/linux/overflow.h:232:26: warning: comparison of unsigned expression < 0 is always false [-Wtype-limits]
  (_to_shift != _s || *_d < 0 || _a < 0 ||   \
                          ^
drivers/infiniband/hw/mlx5/qp.c:5820:6: note: in expansion of macro _check_shl_overflow_
  if (check_shl_overflow(rwq->wqe_count, rwq->wqe_shift, &rwq->buf_size))
      ^~~~~~~~~~~~~~~~~~
./include/linux/overflow.h:232:36: warning: comparison of unsigned expression < 0 is always false [-Wtype-limits]
  (_to_shift != _s || *_d < 0 || _a < 0 ||   \
                                    ^
drivers/infiniband/hw/mlx5/qp.c:5820:6: note: in expansion of macro _check_shl_overflow_
  if (check_shl_overflow(rwq->wqe_count, rwq->wqe_shift,&rwq->buf_size))
      ^~~~~~~~~~~~~~~~~~

Fixes: 0c66847793d1 ("overflow.h: Add arithmetic shift helper")
Reviewed-by: Bart Van Assche 
Acked-by: Kees Cook 
Signed-off-by: Leon Romanovsky 
Signed-off-by: Jason Gunthorpe 
Signed-off-by: Sasha Levin

timekeeping: Force upper bound for setting CLOCK_REALTIME

2019-05-31T13:43:46+00:00

[ Upstream commit 7a8e61f8478639072d402a26789055a4a4de8f77 ]

Several people reported testing failures after setting CLOCK_REALTIME close
to the limits of the kernel internal representation in nanoseconds,
i.e. year 2262.

The failures are exposed in subsequent operations, i.e. when arming timers
or when the advancing CLOCK_MONOTONIC makes the calculation of
CLOCK_REALTIME overflow into negative space.

Now people start to paper over the underlying problem by clamping
calculations to the valid range, but that's just wrong because such
workarounds will prevent detection of real issues as well.

It is reasonable to force an upper bound for the various methods of setting
CLOCK_REALTIME. Year 2262 is the absolute upper bound. Assume a maximum
uptime of 30 years which is plenty enough even for esoteric embedded
systems. That results in an upper bound of year 2232 for setting the time.

Once that limit is reached in reality this limit is only a small part of
the problem space. But until then this stops people from trying to paper
over the problem at the wrong places.

Reported-by: Xiongfeng Wang 
Reported-by: Hongbo Yao 
Signed-off-by: Thomas Gleixner 
Cc: John Stultz 
Cc: Stephen Boyd 
Cc: Miroslav Lichvar 
Cc: Arnd Bergmann 
Cc: Richard Cochran 
Cc: Peter Zijlstra 
Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1903231125480.2157@nanos.tec.linutronix.de
Signed-off-by: Sasha Levin