The runqueue clock update should obviously not be skipped for
prolonged times (otherwise the consumed time is not correctly kept
track of). This patch measures the time between setting and clearing
the rq->skip_clock_update flag. The maximum observed value is exported
in /proc/sched_debug.

On Sun, 2010-12-05 at 13:28 +0800, Yong Zhang wrote:

> when we init idle task, we doesn't mark it on_rq.
> My test show the concern is smoothed by below patch.

Close :)

The skip_clock_update flag should only be set if rq->curr is on_rq,
because it it _that_ clock update during dequeue, and subsequent
microscopic vruntime update it causes that we're trying to avoid.

I think the below fixes it up properly.

Sched: fix skip_clock_update optimization

idle_balance() drops/retakes rq->lock, leaving the previous task
vulnerable to set_tsk_need_resched().  Clear it after we return
from balancing instead, and in setup_thread_stack() as well, so
no successfully descheduled or never scheduled task has it set.

Need resched confused the skip_clock_update logic, which assumes
that the next call to update_rq_clock() will come nearly immediately
after being set.  Make the optimization robust against the waking
a sleeper before it sucessfully deschedules case by checking that
the current task has not been dequeued before setting the flag,
since it is that useless clock update we're trying to save, and
clear in update_rq_clock() to ensure that ONE call may be skipped.

Signed-off-by: Mike Galbraith <efault@gmx.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Bjoern B. Brandenburg <bbb.lst@gmail.com>
Reported-by: Bjoern B. Brandenburg <bbb.lst@gmail.com>

If a user manages to trigger an oops with fs set to KERNEL_DS, fs is not
otherwise reset before do_exit().  do_exit may later (via mm_release in
fork.c) do a put_user to a user-controlled address, potentially allowing
a user to leverage an oops into a controlled write into kernel memory.

This is only triggerable in the presence of another bug, but this
potentially turns a lot of DoS bugs into privilege escalations, so it's
worth fixing.  I have proof-of-concept code which uses this bug along
with CVE-2010-3849 to write a zero to an arbitrary kernel address, so
I've tested that this is not theoretical.

A more logical place to put this fix might be when we know an oops has
occurred, before we call do_exit(), but that would involve changing
every architecture, in multiple places.

Let's just stick it in do_exit instead.

[akpm@linux-foundation.org: update code comment]
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  perf: Fix the software context switch counter
  perf, x86: Fixup Kconfig deps
  x86, perf, nmi: Disable perf if counters are not accessible
  perf: Fix inherit vs. context rotation bug

* 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  posix-cpu-timers: Rcu_read_lock/unlock protect find_task_by_vpid call

* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  perf symbols: Remove incorrect open-coded container_of()
  perf record: Handle restrictive permissions in /proc/{kallsyms,modules}
  x86/kprobes: Prevent kprobes to probe on save_args()
  irq_work: Drop cmpxchg() result
  perf: Fix owner-list vs exit
  x86, hw_nmi: Move backtrace_mask declaration under ARCH_HAS_NMI_WATCHDOG
  tracing: Fix recursive user stack trace
  perf,hw_breakpoint: Initialize hardware api earlier
  x86: Ignore trap bits on single step exceptions
  tracing: Force arch_local_irq_* notrace for paravirt
  tracing: Fix module use of trace_bprintk()

* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  sched: Fix idle balancing
  sched: Fix volanomark performance regression

Stephane noticed that because the perf_sw_event() call is inside the
perf_event_task_sched_out() call it won't get called unless we
have a per-task counter.

Reported-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

It was found that sometimes children of tasks with inherited events had
one extra event. Eventually it turned out to be due to the list rotation
no being exclusive with the list iteration in the inheritance code.

Cure this by temporarily disabling the rotation while we inherit the events.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Cc: <stable@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

This reverts commit 59365d136d205cc20fe666ca7f89b1c5001b0d5a.

It turns out that this can break certain existing user land setups.
Quoth Sarah Sharp:

 "On Wednesday, I updated my branch to commit 460781b from linus' tree,
  and my box would not boot.  klogd segfaulted, which stalled the whole
  system.

  At first I thought it actually hung the box, but it continued booting
  after 5 minutes, and I was able to log in.  It dropped back to the
  text console instead of the graphical bootup display for that period
  of time.  dmesg surprisingly still works.  I've bisected the problem
  down to this commit (commit 59365d136d205cc20fe666ca7f89b1c5001b0d5a)

  The box is running klogd 1.5.5ubuntu3 (from Jaunty).  Yes, I know
  that's old.  I read the bit in the commit about changing the
  permissions of kallsyms after boot, but if I can't boot that doesn't
  help."

So let's just keep the old default, and encourage distributions to do
the "chmod -r /proc/kallsyms" in their bootup scripts.  This is not
worth a kernel option to change default behavior, since it's so easily
done in user space.

Reported-and-bisected-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Cc: Marcus Meissner <meissner@suse.de>
Cc: Tejun Heo <tj@kernel.org>
Cc: Eugene Teo <eugeneteo@kernel.org>
Cc: Jesper Juhl <jj@chaosbits.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>