linux-toradex.git/kernel, branch v3.8.8

sched_clock: Prevent 64bit inatomicity on 32bit systems

2013-04-17T04:48:29+00:00

commit a1cbcaa9ea87b87a96b9fc465951dcf36e459ca2 upstream.

The sched_clock_remote() implementation has the following inatomicity
problem on 32bit systems when accessing the remote scd->clock, which
is a 64bit value.

CPU0			CPU1

sched_clock_local()	sched_clock_remote(CPU0)
...
			remote_clock = scd[CPU0]->clock
			    read_low32bit(scd[CPU0]->clock)
cmpxchg64(scd->clock,...)
			    read_high32bit(scd[CPU0]->clock)

While the update of scd->clock is using an atomic64 mechanism, the
readout on the remote cpu is not, which can cause completely bogus
readouts.

It is a quite rare problem, because it requires the update to hit the
narrow race window between the low/high readout and the update must go
across the 32bit boundary.

The resulting misbehaviour is, that CPU1 will see the sched_clock on
CPU1 ~4 seconds ahead of it's own and update CPU1s sched_clock value
to this bogus timestamp. This stays that way due to the clamping
implementation for about 4 seconds until the synchronization with
CLOCK_MONOTONIC undoes the problem.

The issue is hard to observe, because it might only result in a less
accurate SCHED_OTHER timeslicing behaviour. To create observable
damage on realtime scheduling classes, it is necessary that the bogus
update of CPU1 sched_clock happens in the context of an realtime
thread, which then gets charged 4 seconds of RT runtime, which results
in the RT throttler mechanism to trigger and prevent scheduling of RT
tasks for a little less than 4 seconds. So this is quite unlikely as
well.

The issue was quite hard to decode as the reproduction time is between
2 days and 3 weeks and intrusive tracing makes it less likely, but the
following trace recorded with trace_clock=global, which uses
sched_clock_local(), gave the final hint:

  -0   0d..30 400269.477150: hrtimer_cancel: hrtimer=0xf7061e80
  -0   0d..30 400269.477151: hrtimer_start:  hrtimer=0xf7061e80 ...
irq/20-S-587 1d..32 400273.772118: sched_wakeup:   comm= ... target_cpu=0
  -0   0dN.30 400273.772118: hrtimer_cancel: hrtimer=0xf7061e80

What happens is that CPU0 goes idle and invokes
sched_clock_idle_sleep_event() which invokes sched_clock_local() and
CPU1 runs a remote wakeup for CPU0 at the same time, which invokes
sched_remote_clock(). The time jump gets propagated to CPU0 via
sched_remote_clock() and stays stale on both cores for ~4 seconds.

There are only two other possibilities, which could cause a stale
sched clock:

1) ktime_get() which reads out CLOCK_MONOTONIC returns a sporadic
   wrong value.

2) sched_clock() which reads the TSC returns a sporadic wrong value.

#1 can be excluded because sched_clock would continue to increase for
   one jiffy and then go stale.

#2 can be excluded because it would not make the clock jump
   forward. It would just result in a stale sched_clock for one jiffy.

After quite some brain twisting and finding the same pattern on other
traces, sched_clock_remote() remained the only place which could cause
such a problem and as explained above it's indeed racy on 32bit
systems.

So while on 64bit systems the readout is atomic, we need to verify the
remote readout on 32bit machines. We need to protect the local->clock
readout in sched_clock_remote() on 32bit as well because an NMI could
hit between the low and the high readout, call sched_clock_local() and
modify local->clock.

Thanks to Siegfried Wulsch for bearing with my debug requests and
going through the tedious tasks of running a bunch of reproducer
systems to generate the debug information which let me decode the
issue.

Reported-by: Siegfried Wulsch 
Acked-by: Peter Zijlstra 
Cc: Steven Rostedt 
Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304051544160.21884@ionos
Signed-off-by: Thomas Gleixner 
Signed-off-by: Greg Kroah-Hartman

ftrace: Move ftrace_filter_lseek out of CONFIG_DYNAMIC_FTRACE section

2013-04-17T04:48:29+00:00

commit 7f49ef69db6bbf756c0abca7e9b65b32e999eec8 upstream.

As ftrace_filter_lseek is now used with ftrace_pid_fops, it needs to
be moved out of the #ifdef CONFIG_DYNAMIC_FTRACE section as the
ftrace_pid_fops is defined when DYNAMIC_FTRACE is not.

Signed-off-by: Steven Rostedt 
Cc: Namhyung Kim 
Signed-off-by: Greg Kroah-Hartman

tracing: Fix possible NULL pointer dereferences

2013-04-17T04:48:29+00:00

commit 6a76f8c0ab19f215af2a3442870eeb5f0e81998d upstream.

Currently set_ftrace_pid and set_graph_function files use seq_lseek
for their fops.  However seq_open() is called only for FMODE_READ in
the fops->open() so that if an user tries to seek one of those file
when she open it for writing, it sees NULL seq_file and then panic.

It can be easily reproduced with following command:

  $ cd /sys/kernel/debug/tracing
  $ echo 1234 | sudo tee -a set_ftrace_pid

In this example, GNU coreutils' tee opens the file with fopen(, "a")
and then the fopen() internally calls lseek().

Link: http://lkml.kernel.org/r/1365663302-2170-1-git-send-email-namhyung@kernel.org

Signed-off-by: Namhyung Kim 
Cc: Frederic Weisbecker 
Cc: Ingo Molnar 
Cc: Namhyung Kim 
Cc: stable@vger.kernel.org
Signed-off-by: Steven Rostedt 
Signed-off-by: Greg Kroah-Hartman

PM / reboot: call syscore_shutdown() after disable_nonboot_cpus()

2013-04-17T04:48:28+00:00

commit 6f389a8f1dd22a24f3d9afc2812b30d639e94625 upstream.

As commit 40dc166c (PM / Core: Introduce struct syscore_ops for core
subsystems PM) say, syscore_ops operations should be carried with one
CPU on-line and interrupts disabled. However, after commit f96972f2d
(kernel/sys.c: call disable_nonboot_cpus() in kernel_restart()),
syscore_shutdown() is called before disable_nonboot_cpus(), so break
the rules. We have a MIPS machine with a 8259A PIC, and there is an
external timer (HPET) linked at 8259A. Since 8259A has been shutdown
too early (by syscore_shutdown()), disable_nonboot_cpus() runs without
timer interrupt, so it hangs and reboot fails. This patch call
syscore_shutdown() a little later (after disable_nonboot_cpus()) to
avoid reboot failure, this is the same way as poweroff does.

For consistency, add disable_nonboot_cpus() to kernel_halt().

Signed-off-by: Huacai Chen 
Signed-off-by: Rafael J. Wysocki 
Signed-off-by: Greg Kroah-Hartman

tracing: Fix double free when function profile init failed

2013-04-17T04:48:27+00:00

commit 83e03b3fe4daffdebbb42151d5410d730ae50bd1 upstream.

On the failure path, stat->start and stat->pages will refer same page.
So it'll attempt to free the same page again and get kernel panic.

Link: http://lkml.kernel.org/r/1364820385-32027-1-git-send-email-namhyung@kernel.org

Signed-off-by: Namhyung Kim 
Cc: Frederic Weisbecker 
Cc: Namhyung Kim 
Signed-off-by: Steven Rostedt 
Signed-off-by: Greg Kroah-Hartman

ftrace: Consistently restore trace function on sysctl enabling

2013-04-12T16:52:07+00:00

commit 5000c418840b309251c5887f0b56503aae30f84c upstream.

If we reenable ftrace via syctl, we currently set ftrace_trace_function
based on the previous simplistic algorithm. This is inconsistent with
what update_ftrace_function does. So better call that helper instead.

Link: http://lkml.kernel.org/r/5151D26F.1070702@siemens.com

Signed-off-by: Jan Kiszka 
Signed-off-by: Steven Rostedt 
Signed-off-by: Greg Kroah-Hartman

tracing: Prevent buffer overwrite disabled for latency tracers

2013-04-05T16:26:16+00:00

commit 613f04a0f51e6e68ac6fe571ab79da3c0a5eb4da upstream.

The latency tracers require the buffers to be in overwrite mode,
otherwise they get screwed up. Force the buffers to stay in overwrite
mode when latency tracers are enabled.

Added a flag_changed() method to the tracer structure to allow
the tracers to see what flags are being changed, and also be able
to prevent the change from happing.

Signed-off-by: Steven Rostedt 
Signed-off-by: Lingzhu Xiang 
Reviewed-by: CAI Qian 
Signed-off-by: Greg Kroah-Hartman

kernel/signal.c: use __ARCH_HAS_SA_RESTORER instead of SA_RESTORER

2013-04-05T16:26:05+00:00

commit 522cff142d7d2f9230839c9e1f21a4d8bcc22a4a upstream.

__ARCH_HAS_SA_RESTORER is the preferred conditional for use in 3.9 and
later kernels, per Kees.

Signed-off-by: Andrew Morton 
Cc: Emese Revfy 
Cc: Emese Revfy 
Cc: PaX Team 
Cc: Al Viro 
Cc: Oleg Nesterov 
Cc: "Eric W. Biederman" 
Cc: Serge Hallyn 
Cc: Julien Tinnes 
Signed-off-by: Linus Torvalds 
Cc: Ben Hutchings 
Signed-off-by: Greg Kroah-Hartman

userns: Restrict when proc and sysfs can be mounted

2013-04-05T16:26:02+00:00

commit 87a8ebd637dafc255070f503909a053cf0d98d3f upstream.

Only allow unprivileged mounts of proc and sysfs if they are already
mounted when the user namespace is created.

proc and sysfs are interesting because they have content that is
per namespace, and so fresh mounts are needed when new namespaces
are created while at the same time proc and sysfs have content that
is shared between every instance.

Respect the policy of who may see the shared content of proc and sysfs
by only allowing new mounts if there was an existing mount at the time
the user namespace was created.

In practice there are only two interesting cases: proc and sysfs are
mounted at their usual places, proc and sysfs are not mounted at all
(some form of mount namespace jail).

Acked-by: Serge Hallyn 
Signed-off-by: "Eric W. Biederman" 
Signed-off-by: Greg Kroah-Hartman

userns: Don't allow creation if the user is chrooted

2013-04-05T16:26:01+00:00

commit 3151527ee007b73a0ebd296010f1c0454a919c7d upstream.

Guarantee that the policy of which files may be access that is
established by setting the root directory will not be violated
by user namespaces by verifying that the root directory points
to the root of the mount namespace at the time of user namespace
creation.

Changing the root is a privileged operation, and as a matter of policy
it serves to limit unprivileged processes to files below the current
root directory.

For reasons of simplicity and comprehensibility the privilege to
change the root directory is gated solely on the CAP_SYS_CHROOT
capability in the user namespace.  Therefore when creating a user
namespace we must ensure that the policy of which files may be access
can not be violated by changing the root directory.

Anyone who runs a processes in a chroot and would like to use user
namespace can setup the same view of filesystems with a mount
namespace instead.  With this result that this is not a practical
limitation for using user namespaces.

Acked-by: Serge Hallyn 
Reported-by: Andy Lutomirski 
Signed-off-by: "Eric W. Biederman" 
Signed-off-by: Greg Kroah-Hartman