linux-stable.git/kernel, branch v3.12.59

pipe: limit the per-user amount of pages allocated in pipes

2016-04-21T11:11:54+00:00

commit 759c01142a5d0f364a462346168a56de28a80f52 upstream.

On no-so-small systems, it is possible for a single process to cause an
OOM condition by filling large pipes with data that are never read. A
typical process filling 4000 pipes with 1 MB of data will use 4 GB of
memory. On small systems it may be tricky to set the pipe max size to
prevent this from happening.

This patch makes it possible to enforce a per-user soft limit above
which new pipes will be limited to a single page, effectively limiting
them to 4 kB each, as well as a hard limit above which no new pipes may
be created for this user. This has the effect of protecting the system
against memory abuse without hurting other users, and still allowing
pipes to work correctly though with less data at once.

The limit are controlled by two new sysctls : pipe-user-pages-soft, and
pipe-user-pages-hard. Both may be disabled by setting them to zero. The
default soft limit allows the default number of FDs per process (1024)
to create pipes of the default size (64kB), thus reaching a limit of 64MB
before starting to create only smaller pipes. With 256 processes limited
to 1024 FDs each, this results in 1024*64kB + (256*1024 - 1024) * 4kB =
1084 MB of memory allocated for a user. The hard limit is disabled by
default to avoid breaking existing applications that make intensive use
of pipes (eg: for splicing).

Reported-by: socketpair@gmail.com
Reported-by: Tetsuo Handa 
Mitigates: CVE-2013-4312 (Linux 2.0+)
Suggested-by: Linus Torvalds 
Signed-off-by: Willy Tarreau 
Signed-off-by: Al Viro 
Signed-off-by: Jiri Slaby

perf: Cure event->pending_disable race

2016-04-20T06:46:49+00:00

commit 28a967c3a2f99fa3b5f762f25cb2a319d933571b upstream.

Because event_sched_out() checks event->pending_disable _before_
actually disabling the event, it can happen that the event fires after
it checks but before it gets disabled.

This would leave event->pending_disable set and the queued irq_work
will try and process it.

However, if the event trigger was during schedule(), the event might
have been de-scheduled by the time the irq_work runs, and
perf_event_disable_local() will fail.

Fix this by checking event->pending_disable _after_ we call
event->pmu->del(). This depends on the latter being a compiler
barrier, such that the compiler does not lift the load and re-creates
the problem.

Tested-by: Alexander Shishkin 
Signed-off-by: Peter Zijlstra (Intel) 
Reviewed-by: Alexander Shishkin 
Cc: Arnaldo Carvalho de Melo 
Cc: Jiri Olsa 
Cc: Linus Torvalds 
Cc: Peter Zijlstra 
Cc: Thomas Gleixner 
Cc: dvyukov@google.com
Cc: eranian@google.com
Cc: oleg@redhat.com
Cc: panand@redhat.com
Cc: sasha.levin@oracle.com
Cc: vince@deater.net
Link: http://lkml.kernel.org/r/20160224174948.040469884@infradead.org
Signed-off-by: Ingo Molnar 
Signed-off-by: Jiri Slaby

sched/cputime: Fix steal time accounting vs. CPU hotplug

2016-04-11T14:44:28+00:00

commit e9532e69b8d1d1284e8ecf8d2586de34aec61244 upstream.

On CPU hotplug the steal time accounting can keep a stale rq->prev_steal_time
value over CPU down and up. So after the CPU comes up again the delta
calculation in steal_account_process_tick() wreckages itself due to the
unsigned math:

	 u64 steal = paravirt_steal_clock(smp_processor_id());

	 steal -= this_rq()->prev_steal_time;

So if steal is smaller than rq->prev_steal_time we end up with an insane large
value which then gets added to rq->prev_steal_time, resulting in a permanent
wreckage of the accounting. As a consequence the per CPU stats in /proc/stat
become stale.

Nice trick to tell the world how idle the system is (100%) while the CPU is
100% busy running tasks. Though we prefer realistic numbers.

None of the accounting values which use a previous value to account for
fractions is reset at CPU hotplug time. update_rq_clock_task() has a sanity
check for prev_irq_time and prev_steal_time_rq, but that sanity check solely
deals with clock warps and limits the /proc/stat visible wreckage. The
prev_time values are still wrong.

Solution is simple: Reset rq->prev_*_time when the CPU is plugged in again.

Signed-off-by: Thomas Gleixner 
Acked-by: Rik van Riel 
Cc: Frederic Weisbecker 
Cc: Glauber Costa 
Cc: Linus Torvalds 
Cc: Peter Zijlstra 
Fixes: commit 095c0aa83e52 "sched: adjust scheduler cpu power for stolen time"
Fixes: commit aa483808516c "sched: Remove irq time from available CPU power"
Fixes: commit e6e6685accfa "KVM guest: Steal time accounting"
Link: http://lkml.kernel.org/r/alpine.DEB.2.11.1603041539490.3686@nanos
Signed-off-by: Ingo Molnar 
Signed-off-by: Jiri Slaby

tracing: Fix trace_printk() to print when not using bprintk()

2016-04-11T14:44:23+00:00

commit 3debb0a9ddb16526de8b456491b7db60114f7b5e upstream.

The trace_printk() code will allocate extra buffers if the compile detects
that a trace_printk() is used. To do this, the format of the trace_printk()
is saved to the __trace_printk_fmt section, and if that section is bigger
than zero, the buffers are allocated (along with a message that this has
happened).

If trace_printk() uses a format that is not a constant, and thus something
not guaranteed to be around when the print happens, the compiler optimizes
the fmt out, as it is not used, and the __trace_printk_fmt section is not
filled. This means the kernel will not allocate the special buffers needed
for the trace_printk() and the trace_printk() will not write anything to the
tracing buffer.

Adding a "__used" to the variable in the __trace_printk_fmt section will
keep it around, even though it is set to NULL. This will keep the string
from being printed in the debugfs/tracing/printk_formats section as it is
not needed.

Reported-by: Vlastimil Babka 
Fixes: 07d777fe8c398 "tracing: Add percpu buffers for trace_printk()"
Signed-off-by: Steven Rostedt 
Signed-off-by: Jiri Slaby

tracing: Fix crash from reading trace_pipe with sendfile

2016-04-11T14:44:22+00:00

commit a29054d9478d0435ab01b7544da4f674ab13f533 upstream.

If tracing contains data and the trace_pipe file is read with sendfile(),
then it can trigger a NULL pointer dereference and various BUG_ON within the
VM code.

There's a patch to fix this in the splice_to_pipe() code, but it's also a
good idea to not let that happen from trace_pipe either.

Link: http://lkml.kernel.org/r/1457641146-9068-1-git-send-email-rabin@rab.in

Reported-by: Rabin Vincent 
Signed-off-by: Steven Rostedt 
Signed-off-by: Jiri Slaby

tracing: Have preempt(irqs)off trace preempt disabled functions

2016-04-11T14:44:22+00:00

commit cb86e05390debcc084cfdb0a71ed4c5dbbec517d upstream.

Joel Fernandes reported that the function tracing of preempt disabled
sections was not being reported when running either the preemptirqsoff or
preemptoff tracers. This was due to the fact that the function tracer
callback for those tracers checked if irqs were disabled before tracing. But
this fails when we want to trace preempt off locations as well.

Joel explained that he wanted to see funcitons where interrupts are enabled
but preemption was disabled. The expected output he wanted:

   <...>-2265    1d.h1 3419us : preempt_count_sub <-irq_exit
   <...>-2265    1d..1 3419us : __do_softirq <-irq_exit
   <...>-2265    1d..1 3419us : msecs_to_jiffies <-__do_softirq
   <...>-2265    1d..1 3420us : irqtime_account_irq <-__do_softirq
   <...>-2265    1d..1 3420us : __local_bh_disable_ip <-__do_softirq
   <...>-2265    1..s1 3421us : run_timer_softirq <-__do_softirq
   <...>-2265    1..s1 3421us : hrtimer_run_pending <-run_timer_softirq
   <...>-2265    1..s1 3421us : _raw_spin_lock_irq <-run_timer_softirq
   <...>-2265    1d.s1 3422us : preempt_count_add <-_raw_spin_lock_irq
   <...>-2265    1d.s2 3422us : _raw_spin_unlock_irq <-run_timer_softirq
   <...>-2265    1..s2 3422us : preempt_count_sub <-_raw_spin_unlock_irq
   <...>-2265    1..s1 3423us : rcu_bh_qs <-__do_softirq
   <...>-2265    1d.s1 3423us : irqtime_account_irq <-__do_softirq
   <...>-2265    1d.s1 3423us : __local_bh_enable <-__do_softirq

There's a comment saying that the irq disabled check is because there's a
possible race that tracing_cpu may be set when the function is executed. But
I don't remember that race. For now, I added a check for preemption being
enabled too to not record the function, as there would be no race if that
was the case. I need to re-investigate this, as I'm now thinking that the
tracing_cpu will always be correct. But no harm in keeping the check for
now, except for the slight performance hit.

Link: http://lkml.kernel.org/r/1457770386-88717-1-git-send-email-agnel.joel@gmail.com

Fixes: 5e6d2b9cfa3a "tracing: Use one prologue for the preempt irqs off tracer function tracers"
Reported-by: Joel Fernandes 
Signed-off-by: Steven Rostedt 
Signed-off-by: Jiri Slaby

fs/coredump: prevent fsuid=0 dumps into user-controlled directories

2016-04-11T14:44:20+00:00

commit 378c6520e7d29280f400ef2ceaf155c86f05a71a upstream.

This commit fixes the following security hole affecting systems where
all of the following conditions are fulfilled:

 - The fs.suid_dumpable sysctl is set to 2.
 - The kernel.core_pattern sysctl's value starts with "/". (Systems
   where kernel.core_pattern starts with "|/" are not affected.)
 - Unprivileged user namespace creation is permitted. (This is
   true on Linux >=3.8, but some distributions disallow it by
   default using a distro patch.)

Under these conditions, if a program executes under secure exec rules,
causing it to run with the SUID_DUMP_ROOT flag, then unshares its user
namespace, changes its root directory and crashes, the coredump will be
written using fsuid=0 and a path derived from kernel.core_pattern - but
this path is interpreted relative to the root directory of the process,
allowing the attacker to control where a coredump will be written with
root privileges.

To fix the security issue, always interpret core_pattern for dumps that
are written under SUID_DUMP_ROOT relative to the root directory of init.

Signed-off-by: Jann Horn 
Acked-by: Kees Cook 
Cc: Al Viro 
Cc: "Eric W. Biederman" 
Cc: Andy Lutomirski 
Cc: Oleg Nesterov 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Jiri Slaby

sched: Fix race between task_group and sched_task_group

2016-04-11T14:43:49+00:00

commit eeb61e53ea19be0c4015b00b2e8b3b2185436f2b upstream.

The race may happen when somebody is changing task_group of a forking task.
Child's cgroup is the same as parent's after dup_task_struct() (there just
memory copying). Also, cfs_rq and rt_rq are the same as parent's.

But if parent changes its task_group before it's called cgroup_post_fork(),
we do not reflect this situation on child. Child's cfs_rq and rt_rq remain
the same, while child's task_group changes in cgroup_post_fork().

To fix this we introduce fork() method, which calls sched_move_task() directly.
This function changes sched_task_group on appropriate (also its logic has
no problem with freshly created tasks, so we shouldn't introduce something
special; we are able just to use it).

Possibly, this decides the Burke Libbey's problem: https://lkml.org/lkml/2014/10/24/456

Signed-off-by: Kirill Tkhai 
Signed-off-by: Peter Zijlstra (Intel) 
Cc: Linus Torvalds 
Link: http://lkml.kernel.org/r/1414405105.19914.169.camel@tkhai
Signed-off-by: Ingo Molnar 
Signed-off-by: Jiri Slaby

modules: fix longstanding /proc/kallsyms vs module insertion race.

2016-03-14T22:10:37+00:00

commit 8244062ef1e54502ef55f54cced659913f244c3e upstream.

For CONFIG_KALLSYMS, we keep two symbol tables and two string tables.
There's one full copy, marked SHF_ALLOC and laid out at the end of the
module's init section.  There's also a cut-down version that only
contains core symbols and strings, and lives in the module's core
section.

After module init (and before we free the module memory), we switch
the mod->symtab, mod->num_symtab and mod->strtab to point to the core
versions.  We do this under the module_mutex.

However, kallsyms doesn't take the module_mutex: it uses
preempt_disable() and rcu tricks to walk through the modules, because
it's used in the oops path.  It's also used in /proc/kallsyms.
There's nothing atomic about the change of these variables, so we can
get the old (larger!) num_symtab and the new symtab pointer; in fact
this is what I saw when trying to reproduce.

By grouping these variables together, we can use a
carefully-dereferenced pointer to ensure we always get one or the
other (the free of the module init section is already done in an RCU
callback, so that's safe).  We allocate the init one at the end of the
module init section, and keep the core one inside the struct module
itself (it could also have been allocated at the end of the module
core, but that's probably overkill).

[ Rebased for 4.4-stable and older, because the following changes aren't
  in the older trees:
  - e0224418516b4d8a6c2160574bac18447c354ef0: adds arg to is_core_symbol
  - 7523e4dc5057e157212b4741abd6256e03404cf1: module_init/module_core/init_size/core_size
    become init_layout.base/core_layout.base/init_layout.size/core_layout.size.

  Original commit: 8244062ef1e54502ef55f54cced659913f244c3e
]

Reported-by: Weilong Chen 
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=111541
Signed-off-by: Rusty Russell 
Signed-off-by: Jiri Slaby

kernel/resource.c: fix muxed resource handling in __request_region()

2016-03-03T11:46:07+00:00

commit 59ceeaaf355fa0fb16558ef7c24413c804932ada upstream.

In __request_region, if a conflict with a BUSY and MUXED resource is
detected, then the caller goes to sleep and waits for the resource to be
released.  A pointer on the conflicting resource is kept.  At wake-up
this pointer is used as a parent to retry to request the region.

A first problem is that this pointer might well be invalid (if for
example the conflicting resource have already been freed).  Another
problem is that the next call to __request_region() fails to detect a
remaining conflict.  The previously conflicting resource is passed as a
parameter and __request_region() will look for a conflict among the
children of this resource and not at the resource itself.  It is likely
to succeed anyway, even if there is still a conflict.

Instead, the parent of the conflicting resource should be passed to
__request_region().

As a fix, this patch doesn't update the parent resource pointer in the
case we have to wait for a muxed region right after.

Reported-and-tested-by: Vincent Pelletier 
Signed-off-by: Simon Guinot 
Tested-by: Vincent Donnefort 
Signed-off-by: Linus Torvalds 
Signed-off-by: Jiri Slaby