commit b6345879cc upstream.
A bug was found with Li Zefan's ftrace_stress_test that caused applications
to segfault during the test.
Placing a tracing_off() in the segfault code, and examining several
traces, I found that the following was always the case. The lock tracer
was enabled (lockdep being required) and userstack was enabled. Testing
this out, I just enabled the two, but that was not good enough. I needed
to run something else that could trigger it. Running a load like hackbench
did not work, but executing a new program would. The following would
trigger the segfault within seconds:
# echo 1 > /debug/tracing/options/userstacktrace
# echo 1 > /debug/tracing/events/lock/enable
# while :; do ls > /dev/null ; done
Enabling the function graph tracer and looking at what was happening
I finally noticed that all cashes happened just after an NMI.
1) | copy_user_handle_tail() {
1) | bad_area_nosemaphore() {
1) | __bad_area_nosemaphore() {
1) | no_context() {
1) | fixup_exception() {
1) 0.319 us | search_exception_tables();
1) 0.873 us | }
[...]
1) 0.314 us | __rcu_read_unlock();
1) 0.325 us | native_apic_mem_write();
1) 0.943 us | }
1) 0.304 us | rcu_nmi_exit();
[...]
1) 0.479 us | find_vma();
1) | bad_area() {
1) | __bad_area() {
After capturing several traces of failures, all of them happened
after an NMI. Curious about this, I added a trace_printk() to the NMI
handler to read the regs->ip to see where the NMI happened. In which I
found out it was here:
ffffffff8135b660 <page_fault>:
ffffffff8135b660: 48 83 ec 78 sub $0x78,%rsp
ffffffff8135b664: e8 97 01 00 00 callq ffffffff8135b800 <error_entry>
What was happening is that the NMI would happen at the place that a page
fault occurred. It would call rcu_read_lock() which was traced by
the lock events, and the user_stack_trace would run. This would trigger
a page fault inside the NMI. I do not see where the CR2 register is
saved or restored in NMI handling. This means that it would corrupt
the page fault handling that the NMI interrupted.
The reason the while loop of ls helped trigger the bug, was that
each execution of ls would cause lots of pages to be faulted in, and
increase the chances of the race happening.
The simple solution is to not allow user stack traces in NMI context.
After this patch, I ran the above "ls" test for a couple of hours
without any issues. Without this patch, the bug would trigger in less
than a minute.
Reported-by: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit a2f8071428 upstream.
When the trace iterator is read, tracing_start() and tracing_stop()
is called to stop tracing while the iterator is processing the trace
output.
These functions disable both the standard buffer and the max latency
buffer. But if the wakeup tracer is running, it can switch these
buffers between the two disables:
buffer = global_trace.buffer;
if (buffer)
ring_buffer_record_disable(buffer);
<<<--------- swap happens here
buffer = max_tr.buffer;
if (buffer)
ring_buffer_record_disable(buffer);
What happens is that we disabled the same buffer twice. On tracing_start()
we can enable the same buffer twice. All ring_buffer_record_disable()
must be matched with a ring_buffer_record_enable() or the buffer
can be disable permanently, or enable prematurely, and cause a bug
where a reset happens while a trace is commiting.
This patch protects these two by taking the ftrace_max_lock to prevent
a switch from occurring.
Found with Li Zefan's ftrace_stress_test.
Reported-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 283740c619 upstream.
In the ftrace code that resets the ring buffer it references the
buffer with a local variable, but then uses the tr->buffer as the
parameter to reset. If the wakeup tracer is running, which can
switch the tr->buffer with the max saved buffer, this can break
the requirement of disabling the buffer before the reset.
buffer = tr->buffer;
ring_buffer_record_disable(buffer);
synchronize_sched();
__tracing_reset(tr->buffer, cpu);
If the tr->buffer is swapped, then the reset is not happening to the
buffer that was disabled. This will cause the ring buffer to fail.
Found with Li Zefan's ftrace_stress_test.
Reported-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit ea14eb7140 upstream.
If the graph tracer is active, and a task is forked but the allocating of
the processes graph stack fails, it can cause crash later on.
This is due to the temporary stack being NULL, but the curr_ret_stack
variable is copied from the parent. If it is not -1, then in
ftrace_graph_probe_sched_switch() the following:
for (index = next->curr_ret_stack; index >= 0; index--)
next->ret_stack[index].calltime += timestamp;
Will cause a kernel OOPS.
Found with Li Zefan's ftrace_stress_test.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 52fbe9cde7 upstream.
The ring buffer resizing and resetting relies on a schedule RCU
action. The buffers are disabled, a synchronize_sched() is called
and then the resize or reset takes place.
But this only works if the disabling of the buffers are within the
preempt disabled section, otherwise a window exists that the buffers
can be written to while a reset or resize takes place.
Reported-by: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
LKML-Reference: <4B949E43.2010906@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit ad6759fbf3 upstream.
Aaro Koskinen reported an issue in kernel.org bugzilla #15366, where
on non-GENERIC_TIME systems, accessing
/sys/devices/system/clocksource/clocksource0/current_clocksource
results in an oops.
It seems the timekeeper/clocksource rework missed initializing the
curr_clocksource value in the !GENERIC_TIME case.
Thanks to Aaro for reporting and diagnosing the issue as well as
testing the fix!
Reported-by: Aaro Koskinen <aaro.koskinen@iki.fi>
Signed-off-by: John Stultz <johnstul@us.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
LKML-Reference: <1267475683.4216.61.camel@localhost.localdomain>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 83ab0aa0d5 upstream.
setscheduler() saves task->sched_class outside of the rq->lock held
region for a check after the setscheduler changes have become
effective. That might result in checking a stale value.
rtmutex_setprio() has the same problem, though it is protected by
p->pi_lock against setscheduler(), but for correctness sake (and to
avoid bad examples) it needs to be fixed as well.
Retrieve task->sched_class inside of the rq->lock held region.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 9000f05c6d upstream.
Fix a SMT scheduler performance regression that is leading to a scenario
where SMT threads in one core are completely idle while both the SMT threads
in another core (on the same socket) are busy.
This is caused by this commit (with the problematic code highlighted)
commit bdb94aa5db
Author: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Tue Sep 1 10:34:38 2009 +0200
sched: Try to deal with low capacity
@@ -4203,15 +4223,18 @@ find_busiest_queue()
...
for_each_cpu(i, sched_group_cpus(group)) {
+ unsigned long power = power_of(i);
...
- wl = weighted_cpuload(i);
+ wl = weighted_cpuload(i) * SCHED_LOAD_SCALE;
+ wl /= power;
- if (rq->nr_running == 1 && wl > imbalance)
+ if (capacity && rq->nr_running == 1 && wl > imbalance)
continue;
On a SMT system, power of the HT logical cpu will be 589 and
the scheduler load imbalance (for scenarios like the one mentioned above)
can be approximately 1024 (SCHED_LOAD_SCALE). The above change of scaling
the weighted load with the power will result in "wl > imbalance" and
ultimately resulting in find_busiest_queue() return NULL, causing
load_balance() to think that the load is well balanced. But infact
one of the tasks can be moved to the idle core for optimal performance.
We don't need to use the weighted load (wl) scaled by the cpu power to
compare with imabalance. In that condition, we already know there is only a
single task "rq->nr_running == 1" and the comparison between imbalance,
wl is to make sure that we select the correct priority thread which matches
imbalance. So we really need to compare the imabalnce with the original
weighted load of the cpu and not the scaled load.
But in other conditions where we want the most hammered(busiest) cpu, we can
use scaled load to ensure that we consider the cpu power in addition to the
actual load on that cpu, so that we can move the load away from the
guy that is getting most hammered with respect to the actual capacity,
as compared with the rest of the cpu's in that busiest group.
Fix it.
Reported-by: Ma Ling <ling.ma@intel.com>
Initial-Analysis-by: Zhang, Yanmin <yanmin_zhang@linux.intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1266023662.2808.118.camel@sbs-t61.sc.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit ced5b697a7 upstream.
Keep chip_data in create_irq_nr and destroy_irq.
When two drivers are setting up MSI-X at the same time via
pci_enable_msix() there is a race. See this dmesg excerpt:
[ 85.170610] ixgbe 0000:02:00.1: irq 97 for MSI/MSI-X
[ 85.170611] alloc irq_desc for 99 on node -1
[ 85.170613] igb 0000:08:00.1: irq 98 for MSI/MSI-X
[ 85.170614] alloc kstat_irqs on node -1
[ 85.170616] alloc irq_2_iommu on node -1
[ 85.170617] alloc irq_desc for 100 on node -1
[ 85.170619] alloc kstat_irqs on node -1
[ 85.170621] alloc irq_2_iommu on node -1
[ 85.170625] ixgbe 0000:02:00.1: irq 99 for MSI/MSI-X
[ 85.170626] alloc irq_desc for 101 on node -1
[ 85.170628] igb 0000:08:00.1: irq 100 for MSI/MSI-X
[ 85.170630] alloc kstat_irqs on node -1
[ 85.170631] alloc irq_2_iommu on node -1
[ 85.170635] alloc irq_desc for 102 on node -1
[ 85.170636] alloc kstat_irqs on node -1
[ 85.170639] alloc irq_2_iommu on node -1
[ 85.170646] BUG: unable to handle kernel NULL pointer dereference
at 0000000000000088
As you can see igb and ixgbe are both alternating on create_irq_nr()
via pci_enable_msix() in their probe function.
ixgbe: While looping through irq_desc_ptrs[] via create_irq_nr() ixgbe
choses irq_desc_ptrs[102] and exits the loop, drops vector_lock and
calls dynamic_irq_init. Then it sets irq_desc_ptrs[102]->chip_data =
NULL via dynamic_irq_init().
igb: Grabs the vector_lock now and starts looping over irq_desc_ptrs[]
via create_irq_nr(). It gets to irq_desc_ptrs[102] and does this:
cfg_new = irq_desc_ptrs[102]->chip_data;
if (cfg_new->vector != 0)
continue;
This hits the NULL deref.
Another possible race exists via pci_disable_msix() in a driver or in
the number of error paths that call free_msi_irqs():
destroy_irq()
dynamic_irq_cleanup() which sets desc->chip_data = NULL
...race window...
desc->chip_data = cfg;
Remove the save and restore code for cfg in create_irq_nr() and
destroy_irq() and take the desc->lock when checking the irq_cfg.
Reported-and-analyzed-by: Brandon Philips <bphilips@suse.de>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <1265793639-15071-3-git-send-email-yinghai@kernel.org>
Signed-off-by: Brandon Phililps <bphilips@suse.de>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit a9c9b4429d upstream.
The hibernate memory preallocation code allocates memory to push some
user space data out of physical RAM, so that the hibernation image is
not too large. It allocates more memory than necessary for creating
the image, so it has to release some pages to make room for
allocations made while suspending devices and disabling nonboot CPUs,
or the system will hang due to the lack of free pages to allocate
from. Unfortunately, the function used for freeing these pages,
free_unnecessary_pages(), contains a bug that prevents it from doing
the job on all systems without highmem.
Fix this problem, which is a regression from the 2.6.30 kernel, by
using the right condition for the termination of the loop in
free_unnecessary_pages().
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Reported-and-tested-by: Alan Jenkins <sourcejedi.lkml@googlemail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit c93d89f3db upstream.
Export getboottime and monotonic_to_bootbased in order to let them
could be used by following patch.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 59647b6ac3 upstream.
The WARN_ON in lookup_pi_state which complains about a mismatch
between pi_state->owner->pid and the pid which we retrieved from the
user space futex is completely bogus.
The code just emits the warning and then continues despite the fact
that it detected an inconsistent state of the futex. A conveniant way
for user space to spam the syslog.
Replace the WARN_ON by a consistency check. If the values do not match
return -EINVAL and let user space deal with the mess it created.
This also fixes the missing task_pid_vnr() when we compare the
pi_state->owner pid with the futex value.
Reported-by: Jermome Marchand <jmarchan@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Darren Hart <dvhltc@us.ibm.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 51246bfd18 upstream.
If the owner of a PI futex dies we fix up the pi_state and set
pi_state->owner to NULL. When a malicious or just sloppy programmed
user space application sets the futex value to 0 e.g. by calling
pthread_mutex_init(), then the futex can be acquired again. A new
waiter manages to enqueue itself on the pi_state w/o damage, but on
unlock the kernel dereferences pi_state->owner and oopses.
Prevent this by checking pi_state->owner in the unlock path. If
pi_state->owner is not current we know that user space manipulated the
futex value. Ignore the mess and return -EINVAL.
This catches the above case and also the case where a task hijacks the
futex by setting the tid value and then tries to unlock it.
Reported-by: Jermome Marchand <jmarchan@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Darren Hart <dvhltc@us.ibm.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 5ecb01cfdf upstream.
This fixes a futex key reference count bug in futex_lock_pi(),
where a key's reference count is incremented twice but decremented
only once, causing the backing object to not be released.
If the futex is created in a temporary file in an ext3 file system,
this bug causes the file's inode to become an "undead" orphan,
which causes an oops from a BUG_ON() in ext3_put_super() when the
file system is unmounted. glibc's test suite is known to trigger this,
see <http://bugzilla.kernel.org/show_bug.cgi?id=14256>.
The bug is a regression from 2.6.28-git3, namely Peter Zijlstra's
38d47c1b70 "[PATCH] futex: rely on
get_user_pages() for shared futexes". That commit made get_futex_key()
also increment the reference count of the futex key, and updated its
callers to decrement the key's reference count before returning.
Unfortunately the normal exit path in futex_lock_pi() wasn't corrected:
the reference count is incremented by get_futex_key() and queue_lock(),
but the normal exit path only decrements once, via unqueue_me_pi().
The fix is to put_futex_key() after unqueue_me_pi(), since 2.6.31
this is easily done by 'goto out_put_key' rather than 'goto out'.
Signed-off-by: Mikael Pettersson <mikpe@it.uu.se>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Darren Hart <dvhltc@us.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This fixes the boot time oops on the 2.6.32-stable tree. It is needed
only in this tree due to the divergance from upstream.
From: jamal <hadi@cyberus.ca>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit b8a1d37c5f upstream.
Free memory allocated using kmem_cache_zalloc using kmem_cache_free rather
than kfree.
The semantic patch that makes this change is as follows:
(http://coccinelle.lip6.fr/)
// <smpl>
@@
expression x,E,c;
@@
x = \(kmem_cache_alloc\|kmem_cache_zalloc\|kmem_cache_alloc_node\)(c,...)
... when != x = E
when != &x
?-kfree(x)
+kmem_cache_free(c,x)
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
Acked-by: David Howells <dhowells@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: Steve Dickson <steved@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: James Morris <jmorris@namei.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit a362c638bd upstream
Commit a9238ce3bb broke compilation on
platforms that do not implement GENERIC_TIME (e.g. iop32x):
kernel/time/clocksource.c: In function 'clocksource_register':
kernel/time/clocksource.c:556: error: implicit declaration of function 'clocksource_max_deferment'
Provide the implementation of clocksource_max_deferment() also for
such platforms.
Signed-off-by: Aaro Koskinen <aaro.koskinen@iki.fi>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 98962465ed upstream.
The dynamic tick allows the kernel to sleep for periods longer than a
single tick, but it does not limit the sleep time currently. In the
worst case the kernel could sleep longer than the wrap around time of
the time keeping clock source which would result in losing track of
time.
Prevent this by limiting it to the safe maximum sleep time of the
current time keeping clock source. The value is calculated when the
clock source is registered.
[ tglx: simplified the code a bit and massaged the commit msg ]
Signed-off-by: Jon Hunter <jon-hunter@ti.com>
Cc: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <1250617512-23567-2-git-send-email-jon-hunter@ti.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit bdddd2963c upstream.
Anton Blanchard wrote:
> We allocate and zero cpu_isolated_map after the isolcpus
> __setup option has run. This means cpu_isolated_map always
> ends up empty and if CPUMASK_OFFSTACK is enabled we write to a
> cpumask that hasn't been allocated.
I introduced this regression in 49557e6203 (sched: Fix
boot crash by zalloc()ing most of the cpu masks).
Use the bootmem allocator if they set isolcpus=, otherwise
allocate and zero like normal.
Reported-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: peterz@infradead.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: <stable@kernel.org>
LKML-Reference: <200912021409.17013.rusty@rustcorp.com.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Tested-by: Anton Blanchard <anton@samba.org>
commit ea9d8e3f45 upstream.
Marc reported that the BUG_ON in clockevents_notify() triggers on his
system. This happens because the kernel tries to remove an active
clock event device (used for broadcasting) from the device list.
The handling of devices which can be used as per cpu device and as a
global broadcast device is suboptimal.
The simplest solution for now (and for stable) is to check whether the
device is used as global broadcast device, but this needs to be
revisited.
[ tglx: restored the cpuweight check and massaged the changelog ]
Reported-by: Marc Dionne <marc.c.dionne@gmail.com>
Tested-by: Marc Dionne <marc.c.dionne@gmail.com>
Signed-off-by: Xiaotian Feng <dfeng@redhat.com>
LKML-Reference: <1262834564-13033-1-git-send-email-dfeng@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 22e190851f upstream.
Anton reported that perf record kept receiving events even after calling
ioctl(PERF_EVENT_IOC_DISABLE). It turns out that FORK,COMM and MMAP
events didn't respect the disabled state and kept flowing in.
Reported-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Anton Blanchard <anton@samba.org>
LKML-Reference: <1263459187.4244.265.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 57785df5ac upstream.
83f9ac removed a call to effective_prio() in wake_up_new_task(), which
leads to tasks running at MAX_PRIO.
This is caused by the idle thread being set to MAX_PRIO before forking
off init. O(1) used that to make sure idle was always preempted, CFS
uses check_preempt_curr_idle() for that so we can savely remove this bit
of legacy code.
Reported-by: Mike Galbraith <efault@gmx.de>
Tested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1259754383.4003.610.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit b9f8fcd55b upstream.
Relax stable-sched-clock architectures to not save/disable/restore
hardirqs in cpu_clock().
The background is that I was trying to resolve a sparc64 perf
issue when I discovered this problem.
On sparc64 I implement pseudo NMIs by simply running the kernel
at IRQ level 14 when local_irq_disable() is called, this allows
performance counter events to still come in at IRQ level 15.
This doesn't work if any code in an NMI handler does
local_irq_save() or local_irq_disable() since the "disable" will
kick us back to cpu IRQ level 14 thus letting NMIs back in and
we recurse.
The only path which that does that in the perf event IRQ
handling path is the code supporting frequency based events. It
uses cpu_clock().
cpu_clock() simply invokes sched_clock() with IRQs disabled.
And that's a fundamental bug all on it's own, particularly for
the HAVE_UNSTABLE_SCHED_CLOCK case. NMIs can thus get into the
sched_clock() code interrupting the local IRQ disable code
sections of it.
Furthermore, for the not-HAVE_UNSTABLE_SCHED_CLOCK case, the IRQ
disabling done by cpu_clock() is just pure overhead and
completely unnecessary.
So the core problem is that sched_clock() is not NMI safe, but
we are invoking it from NMI contexts in the perf events code
(via cpu_clock()).
A less important issue is the overhead of IRQ disabling when it
isn't necessary in cpu_clock().
CONFIG_HAVE_UNSTABLE_SCHED_CLOCK architectures are not
affected by this patch.
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
LKML-Reference: <20091213.182502.215092085.davem@davemloft.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 7485d0d375 upstream.
Currently, futexes have two problem:
A) The current futex code doesn't handle private file mappings properly.
get_futex_key() uses PageAnon() to distinguish file and
anon, which can cause the following bad scenario:
1) thread-A call futex(private-mapping, FUTEX_WAIT), it
sleeps on file mapping object.
2) thread-B writes a variable and it makes it cow.
3) thread-B calls futex(private-mapping, FUTEX_WAKE), it
wakes up blocked thread on the anonymous page. (but it's nothing)
B) Current futex code doesn't handle zero page properly.
Read mode get_user_pages() can return zero page, but current
futex code doesn't handle it at all. Then, zero page makes
infinite loop internally.
The solution is to use write mode get_user_page() always for
page lookup. It prevents the lookup of both file page of private
mappings and zero page.
Performance concerns:
Probaly very little, because glibc always initialize variables
for futex before to call futex(). It means glibc users never see
the overhead of this patch.
Compatibility concerns:
This patch has few compatibility issues. After this patch,
FUTEX_WAIT require writable access to futex variables (read-only
mappings makes EFAULT). But practically it's not a problem,
glibc always initalizes variables for futexes explicitly - nobody
uses read-only mappings.
Reported-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Darren Hart <dvhltc@us.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Ulrich Drepper <drepper@gmail.com>
LKML-Reference: <20100105162633.45A2.A69D9226@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit b4c30aad39 upstream.
Several leaks in audit_tree didn't get caught by commit
318b6d3d7d, including the leak on normal
exit in case of multiple rules refering to the same chunk.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 6f5d511489 upstream.
... aka "Al had badly fscked up when writing that thing and nobody
noticed until Eric had fixed leaks that used to mask the breakage".
The function essentially creates a copy of old array sans one element
and replaces the references to elements of original (they are on cyclic
lists) with those to corresponding elements of new one. After that the
old one is fair game for freeing.
First of all, there's a dumb braino: when we get to list_replace_init we
use indices for wrong arrays - position in new one with the old array
and vice versa.
Another bug is more subtle - termination condition is wrong if the
element to be excluded happens to be the last one. We shouldn't go
until we fill the new array, we should go until we'd finished the old
one. Otherwise the element we are trying to kill will remain on the
cyclic lists...
That crap used to be masked by several leaks, so it was not quite
trivial to hit. Eric had fixed some of those leaks a while ago and the
shit had hit the fan...
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Stable commit 0399123f3d didn't match the
original upstream commit. The CONFIG_MMU check was added much too early
in the list disabling a lot of proc entries in the process.
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit b45c6e76bc upstream.
When print-fatal-signals is enabled it's possible to dump any memory
reachable by the kernel to the log by simply jumping to that address from
user space.
Or crash the system if there's some hardware with read side effects.
The fatal signals handler will dump 16 bytes at the execution address,
which is fully controlled by ring 3.
In addition when something jumps to a unmapped address there will be up to
16 additional useless page faults, which might be potentially slow (and at
least is not very efficient)
Fortunately this option is off by default and only there on i386.
But fix it by checking for kernel addresses and also stopping when there's
a page fault.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit bd4f490a07 upstream.
The LTP cgroup test suite generates a "kernel BUG at kernel/cgroup.c:790!"
here in cgroup_diput():
/*
* if we're getting rid of the cgroup, refcount should ensure
* that there are no pidlists left.
*/
BUG_ON(!list_empty(&cgrp->pidlists));
The cgroup pidlist rework in 2.6.32 generates the BUG_ON, which is caused
when pidlist_array_load() calls cgroup_pidlist_find():
(1) if a matching cgroup_pidlist is found, it down_write's the mutex of the
pre-existing cgroup_pidlist, and increments its use_count.
(2) if no matching cgroup_pidlist is found, then a new one is allocated, it
down_write's its mutex, and the use_count is set to 0.
(3) the matching, or new, cgroup_pidlist gets returned back to pidlist_array_load(),
which increments its use_count -- regardless whether new or pre-existing --
and up_write's the mutex.
So if a matching list is ever encountered by cgroup_pidlist_find() during
the life of a cgroup directory, it results in an inflated use_count value,
preventing it from ever getting released by cgroup_release_pid_array().
Then if the directory is subsequently removed, cgroup_diput() hits the
BUG_ON() when it finds that the directory's cgroup is still populated with
a pidlist.
The patch simply removes the use_count increment when a matching pidlist
is found by cgroup_pidlist_find(), because it gets bumped by the calling
pidlist_array_load() function while still protected by the list's mutex.
Signed-off-by: Dave Anderson <anderson@redhat.com>
Reviewed-by: Li Zefan <lizf@cn.fujitsu.com>
Acked-by: Ben Blum <bblum@andrew.cmu.edu>
Cc: Paul Menage <menage@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 10b465aaf9 upstream.
Commit 35dead4 "modules: don't export section names of empty sections
via sysfs" changed the set of sections that have attributes, but did
not change the iteration over these attributes in add_notes_attrs().
This can lead to add_notes_attrs() creating attributes with the wrong
names or with null name pointers.
Introduce a sect_empty() function and use it in both add_sect_attrs()
and add_notes_attrs().
Reported-by: Martin Michlmayr <tbm@cyrius.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Tested-by: Martin Michlmayr <tbm@cyrius.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 047106adcc upstream.
Heiko reported a case where a timer interrupt managed to
reference a root_domain structure that was already freed by a
concurrent hot-un-plug operation.
Solve this like the regular sched_domain stuff is also
synchronized, by adding a synchronize_sched() stmt to the free
path, this ensures that a root_domain stays present for any
atomic section that could have observed it.
Reported-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Gregory Haskins <ghaskins@novell.com>
Cc: Siddha Suresh B <suresh.b.siddha@intel.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
LKML-Reference: <1258363873.26714.83.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 6ad4c18884 upstream.
Since (e761b77: cpu hotplug, sched: Introduce cpu_active_map and redo
sched domain managment) we have cpu_active_mask which is suppose to rule
scheduler migration and load-balancing, except it never (fully) did.
The particular problem being solved here is a crash in try_to_wake_up()
where select_task_rq() ends up selecting an offline cpu because
select_task_rq_fair() trusts the sched_domain tree to reflect the
current state of affairs, similarly select_task_rq_rt() trusts the
root_domain.
However, the sched_domains are updated from CPU_DEAD, which is after the
cpu is taken offline and after stop_machine is done. Therefore it can
race perfectly well with code assuming the domains are right.
Cure this by building the domains from cpu_active_mask on
CPU_DOWN_PREPARE.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Holger Hoffstätte <holger.hoffstaette@googlemail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 70da2340fb upstream.
Jan Engelhardt reported we have this problem:
setting max_map_count to a value large enough results in programs dying at
first try. This is on 2.6.31.6:
15:59 borg:/proc/sys/vm # echo $[1<<31-1] >max_map_count
15:59 borg:/proc/sys/vm # cat max_map_count
1073741824
15:59 borg:/proc/sys/vm # echo $[1<<31] >max_map_count
15:59 borg:/proc/sys/vm # cat max_map_count
Killed
This is because we have a chance to make 'max_map_count' negative. but
it's meaningless. Make it only accept non-negative values.
Reported-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: WANG Cong <amwang@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: James Morris <jmorris@namei.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 6e14154676 upstream.
In NOMMU mode clamp dac_mmap_min_addr to zero to cause the tests on it to be
skipped by the compiler. We do this as the minimum mmap address doesn't make
any sense in NOMMU mode.
mmap_min_addr and round_hint_to_min() can be discarded entirely in NOMMU mode.
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Eric Paris <eparis@redhat.com>
Signed-off-by: James Morris <jmorris@namei.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit bb6eddf767 upstream.
Xiaotian Feng triggered a list corruption in the clock events list on
CPU hotplug and debugged the root cause.
If a CPU registers more than one per cpu clock event device, then only
the active clock event device is removed on CPU_DEAD. The unused
devices are kept in the clock events device list.
On CPU up the clock event devices are registered again, which means
that we list_add an already enqueued list_head. That results in list
corruption.
Resolve this by removing all devices which are associated to the dead
CPU on CPU_DEAD.
Reported-by: Xiaotian Feng <dfeng@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Xiaotian Feng <dfeng@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit 0f624e7e56 upstream.
It is quite legitimate for CPUs to be numbered sparsely, meaning
that it possible for an online CPU to have a number which is
greater than the total count of possible CPUs.
Currently find_get_context() has a sanity check on the cpu
number where it checks it against num_possible_cpus(). This
test can fail for a legitimate cpu number if the
cpu_possible_mask is sparsely populated.
This fixes the problem by checking the CPU number against
nr_cpumask_bits instead, since that is the appropriate check to
ensure that the cpu number is same to pass to cpu_isset()
subsequently.
Reported-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Tested-by: Michael Neuling <mikey@neuling.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20091215084032.GA18661@brick.ozlabs.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit eae0c9dfb5 upstream.
Commit 1b9508f, "Rate-limit newidle" has been confirmed to fix
the netperf UDP loopback regression reported by Alex Shi.
This is a cleanup and a fix:
- moved to a more out of the way spot
- fix to ensure that balancing doesn't try to balance
runqueues which haven't gone online yet, which can
mess up CPU enumeration during boot.
Reported-by: Alex Shi <alex.shi@intel.com>
Reported-by: Zhang, Yanmin <yanmin_zhang@linux.intel.com>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1257821402.5648.17.camel@marge.simson.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
commit a1f84a3ab8 upstream.
When waking affine, check for an idle shared cache, and if
found, wake to that CPU/sibling instead of the waker's CPU.
This improves pgsql+oltp ramp up by roughly 8%. Possibly more
for other loads, depending on overlap. The trade-off is a
roughly 1% peak downturn if tasks are truly synchronous.
Signed-off-by: Mike Galbraith <efault@gmx.de>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <1256654138.17752.7.camel@marge.simson.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
