06 Oct, 2012
1 commit
-
Using a recursive call add a non-conflicting region in
__reserve_region_with_split() could result in a stack overflow in the case
that the recursive calls are too deep. Convert the recursive calls to an
iterative loop to avoid the problem.Tested on a machine containing 135 regions. The kernel no longer panicked
with stack overflow.Also tested with code arbitrarily adding regions with no conflict,
embedding two consecutive conflicts and embedding two non-consecutive
conflicts.Signed-off-by: T Makphaibulchoke
Reviewed-by: Ram Pai
Cc: Paul Gortmaker
Cc: Wei Yang
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
31 Jul, 2012
1 commit
-
When the requested range is outside of the root range the logic in
__reserve_region_with_split will cause an infinite recursion which will
overflow the stack as seen in the warning bellow.This particular stack overflow was caused by requesting the
(100000000-107ffffff) range while the root range was (0-ffffffff). In
this case __request_resource would return the whole root range as
conflict range (i.e. 0-ffffffff). Then, the logic in
__reserve_region_with_split would continue the recursion requesting the
new range as (conflict->end+1, end) which incidentally in this case
equals the originally requested range.This patch aborts looking for an usable range when the request does not
intersect with the root range. When the request partially overlaps with
the root range, it ajust the request to fall in the root range and then
continues with the new request.When the request is modified or aborted errors and a stack trace are
logged to allow catching the errors in the upper layers.[ 5.968374] WARNING: at kernel/sched.c:4129 sub_preempt_count+0x63/0x89()
[ 5.975150] Modules linked in:
[ 5.978184] Pid: 1, comm: swapper Not tainted 3.0.22-mid27-00004-gb72c817 #46
[ 5.985324] Call Trace:
[ 5.987759] [] ? console_unlock+0x17b/0x18d
[ 5.992891] [] warn_slowpath_common+0x48/0x5d
[ 5.998194] [] ? sub_preempt_count+0x63/0x89
[ 6.003412] [] warn_slowpath_null+0xf/0x13
[ 6.008453] [] sub_preempt_count+0x63/0x89
[ 6.013499] [] _raw_spin_unlock+0x27/0x3f
[ 6.018453] [] add_partial+0x36/0x3b
[ 6.022973] [] deactivate_slab+0x96/0xb4
[ 6.027842] [] __slab_alloc.isra.54.constprop.63+0x204/0x241
[ 6.034456] [] ? kzalloc.constprop.5+0x29/0x38
[ 6.039842] [] ? kzalloc.constprop.5+0x29/0x38
[ 6.045232] [] kmem_cache_alloc_trace+0x51/0xb0
[ 6.050710] [] ? kzalloc.constprop.5+0x29/0x38
[ 6.056100] [] kzalloc.constprop.5+0x29/0x38
[ 6.061320] [] __reserve_region_with_split+0x1c/0xd1
[ 6.067230] [] __reserve_region_with_split+0xc6/0xd1
...
[ 7.179057] [] __reserve_region_with_split+0xc6/0xd1
[ 7.184970] [] reserve_region_with_split+0x30/0x42
[ 7.190709] [] e820_reserve_resources_late+0xd1/0xe9
[ 7.196623] [] pcibios_resource_survey+0x23/0x2a
[ 7.202184] [] pcibios_init+0x23/0x35
[ 7.206789] [] pci_subsys_init+0x3f/0x44
[ 7.211659] [] do_one_initcall+0x72/0x122
[ 7.216615] [] ? pci_legacy_init+0x3d/0x3d
[ 7.221659] [] kernel_init+0xa6/0x118
[ 7.226265] [] ? start_kernel+0x334/0x334
[ 7.231223] [] kernel_thread_helper+0x6/0x10Signed-off-by: Octavian Purdila
Signed-off-by: Ram Pai
Cc: Jesse Barnes
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
14 Jun, 2012
1 commit
-
If a resource has no parent, allow its start/end to be set arbitrarily
as long as any children are still contained within the new range.[bhelgaas: changelog]
Signed-off-by: Yinghai Lu
Signed-off-by: Bjorn Helgaas
01 Jun, 2012
1 commit
-
In the comment of allocate_resource(), the explanation of parameter max
and min is not correct.Actually, these two parameters are used to specify the range of the
resource that will be allocated, not the min/max size that will be
allocated.Signed-off-by: Wei Yang
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
04 Feb, 2012
1 commit
-
EXPORT_SYMBOL(adjust_resource) should be right after adjust_resource().
Signed-off-by: WANG Cong
Signed-off-by: Jiri Kosina
31 Oct, 2011
1 commit
-
The changed files were only including linux/module.h for the
EXPORT_SYMBOL infrastructure, and nothing else. Revector them
onto the isolated export header for faster compile times.Nothing to see here but a whole lot of instances of:
-#include
+#includeThis commit is only changing the kernel dir; next targets
will probably be mm, fs, the arch dirs, etc.Signed-off-by: Paul Gortmaker
30 Sep, 2011
1 commit
-
__find_resource() incorrectly returns a resource window which overlaps
an existing allocated window. This happens when the parent's
resource-window spans 0x00000000 to 0xffffffff and is entirely allocated
to all its children resource-windows.__find_resource() looks for gaps in resource allocation among the
children resource windows. When it encounters the last child window it
blindly tries the range next to one allocated to the last child. Since
the last child's window ends at 0xffffffff the calculation overflows,
leading the algorithm to believe that any window in the range 0x0000000
to 0xfffffff is available for allocation. This leads to a conflicting
window allocation.Michal Ludvig reported this issue seen on his platform. The following
patch fixes the problem and has been verified by Michal. I believe this
bug has been there for ages. It got exposed by git commit 2bbc6942273b
("PCI : ability to relocate assigned pci-resources")Signed-off-by: Ram Pai
Tested-by: Michal Ludvig
Signed-off-by: Linus Torvalds
31 Jul, 2011
1 commit
-
Add a function to find an existing resource by a resource start address.
This allows to implement simple allocators (with a malloc/free-alike API)
on top of the resource system.Signed-off-by: Geert Uytterhoeven
07 Jul, 2011
1 commit
-
Provides the ability to resize a resource that is already allocated.
This functionality is put in place to support reallocation needs of
pci resources.Signed-off-by: Ram Pai
Acked-by: Jesse Barnes
Signed-off-by: Linus Torvalds
18 Dec, 2010
2 commits
-
This adds arch_remove_reservations(), which an arch can implement if it
needs to protect part of the address space from allocation.Sometimes that can be done by just putting a region in the resource tree,
but there are cases where that doesn't work well. For example, x86 BIOS
E820 reservations are not related to devices, so they may overlap part of,
all of, or more than a device resource, so they may not end up at the
correct spot in the resource tree.Acked-by: H. Peter Anvin
Signed-off-by: Bjorn Helgaas
Signed-off-by: Jesse Barnes -
This reverts commit e7f8567db9a7f6b3151b0b275e245c1cef0d9c70.
Acked-by: H. Peter Anvin
Signed-off-by: Bjorn Helgaas
Signed-off-by: Jesse Barnes
29 Oct, 2010
1 commit
-
* 'linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6: (27 commits)
x86: allocate space within a region top-down
x86: update iomem_resource end based on CPU physical address capabilities
x86/PCI: allocate space from the end of a region, not the beginning
PCI: allocate bus resources from the top down
resources: support allocating space within a region from the top down
resources: handle overflow when aligning start of available area
resources: ensure callback doesn't allocate outside available space
resources: factor out resource_clip() to simplify find_resource()
resources: add a default alignf to simplify find_resource()
x86/PCI: MMCONFIG: fix region end calculation
PCI: Add support for polling PME state on suspended legacy PCI devices
PCI: Export some PCI PM functionality
PCI: fix message typo
PCI: log vendor/device ID always
PCI: update Intel chipset names and defines
PCI: use new ccflags variable in Makefile
PCI: add PCI_MSIX_TABLE/PBA defines
PCI: add PCI vendor id for STmicroelectronics
x86/PCI: irq and pci_ids patch for Intel Patsburg DeviceIDs
PCI: OLPC: Only enable PCI configuration type override on XO-1
...
28 Oct, 2010
1 commit
-
If the same resource is inserted to the resource tree (maybe not on
purpose), a dead loop will be created. In this situation, The kernel does
not report any warning or error :(The command below will show a endless print.
#cat /proc/iomem[akpm@linux-foundation.org: add WARN_ON()]
Signed-off-by: Huang Shijie
Cc: Jesse Barnes
Cc: Bjorn Helgaas
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
27 Oct, 2010
5 commits
-
Allocate space from the top of a region first, then work downward,
if an architecture desires this.When we allocate space from a resource, we look for gaps between children
of the resource. Previously, we always looked at gaps from the bottom up.
For example, given this:[mem 0xbff00000-0xf7ffffff] PCI Bus 0000:00
[mem 0xbff00000-0xbfffffff] gap -- available
[mem 0xc0000000-0xdfffffff] PCI Bus 0000:02
[mem 0xe0000000-0xf7ffffff] gap -- availablewe attempted to allocate from the [mem 0xbff00000-0xbfffffff] gap first,
then the [mem 0xe0000000-0xf7ffffff] gap.With this patch an architecture can choose to allocate from the top gap
[mem 0xe0000000-0xf7ffffff] first.We can't do this across the board because iomem_resource.end is initialized
to 0xffffffff_ffffffff on 64-bit architectures, and most machines can't
address the entire 64-bit physical address space. Therefore, we only
allocate top-down if the arch requests it by clearing
"resource_alloc_from_bottom".Signed-off-by: Bjorn Helgaas
Signed-off-by: Jesse Barnes -
If tmp.start is near ~0, ALIGN(tmp.start) may overflow, which would
make us think there's more available space than there really is. We
would likely return something that conflicts with a previous resource,
which would cause a failure when allocate_resource() requests the newly-
allocated region.Reference: https://bugzilla.redhat.com/show_bug.cgi?id=646027
Reported-by: Fabrice Bellet
Signed-off-by: Bjorn Helgaas
Signed-off-by: Jesse Barnes -
The alignment callback returns a proposed location, which may have been
adjusted to avoid ISA aliases or for other architecture-specific reasons.We already had a check ("tmp.start < tmp.end") to make sure the callback
doesn't return an area that extends past the available area. This patch
reworks the check to make sure it doesn't return an area that extends
either below or above the available area.Signed-off-by: Bjorn Helgaas
Signed-off-by: Jesse Barnes -
This factors out the min/max clipping to simplify find_resource().
No functional change.Signed-off-by: Bjorn Helgaas
Signed-off-by: Jesse Barnes -
This removes a test from find_resource(), which is getting cluttered.
No functional change.Signed-off-by: Bjorn Helgaas
Signed-off-by: Jesse Barnes
12 May, 2010
1 commit
-
SuperIO devices share regions and use lock/unlock operations to chip
select. We therefore need to be able to request a resource and wait for
it to be freed by whichever other SuperIO device currently hogs it.
Right now you have to poll which is horrible.Add a MUXED field to IO port resources. If the MUXED field is set on the
resource and on the request (via request_muxed_region) then we block
until the previous owner of the muxed resource releases their region.This allows us to implement proper resource sharing and locking for
superio chips using code of the formenable_my_superio_dev() {
request_muxed_region(0x44, 0x02, "superio:watchdog");
outb() ..sequence to enable chip
}disable_my_superio_dev() {
outb() .. sequence of disable chip
release_region(0x44, 0x02);
}Signed-off-by: Giel van Schijndel
Signed-off-by: Alan Cox
Signed-off-by: Jesse Barnes
24 Mar, 2010
1 commit
-
request_resource() and insert_resource() only return success or failure,
which no information about what existing resource conflicted with the
proposed new reservation. This patch adds request_resource_conflict()
and insert_resource_conflict(), which return the conflicting resource.Callers may use this for better error messages or to adjust the new
resource and retry the request.Signed-off-by: Bjorn Helgaas
Signed-off-by: Jesse Barnes
04 Mar, 2010
1 commit
-
* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
resource: Fix broken indentation
resource: Fix generic page_is_ram() for partial RAM pages
x86, paravirt: Remove kmap_atomic_pte paravirt op.
x86, vmi: Disable highmem PTE allocation even when CONFIG_HIGHPTE=y
x86, xen: Disable highmem PTE allocation even when CONFIG_HIGHPTE=y
03 Mar, 2010
1 commit
-
Fix broken indentation in patch
37b99dd5372cff42f83210c280f314f10f99138e.Reported-by: Linus Torvalds
Cc: Wu Fengguang
LKML-Reference:
Signed-off-by: H. Peter Anvin
02 Mar, 2010
1 commit
-
The System RAM walk shall skip partial RAM pages and avoid calling
func() on them. So that page_is_ram() return 0 for a partial RAM page.In particular, it shall not call func() with len=0.
This fixes a boot time bug reported by Sachin and root caused by Thomas:> >>> WARNING: at arch/x86/mm/ioremap.c:111 __ioremap_caller+0x169/0x2f1()
> >>> Hardware name: BladeCenter LS21 -[79716AA]-
> >>> Modules linked in:
> >>> Pid: 0, comm: swapper Not tainted 2.6.33-git6-autotest #1
> >>> Call Trace:
> >>> [] ? __ioremap_caller+0x169/0x2f1
> >>> [] warn_slowpath_common+0x77/0xa4
> >>> [] warn_slowpath_null+0xf/0x11
> >>> [] __ioremap_caller+0x169/0x2f1
> >>> [] ? acpi_os_map_memory+0x12/0x1b
> >>> [] ioremap_nocache+0x12/0x14
> >>> [] acpi_os_map_memory+0x12/0x1b
> >>> [] acpi_tb_verify_table+0x29/0x5b
> >>> [] acpi_load_tables+0x39/0x15a
> >>> [] acpi_early_init+0x60/0xf5
> >>> [] start_kernel+0x397/0x3a7
> >>> [] x86_64_start_reservations+0xa5/0xa9
> >>> [] x86_64_start_kernel+0xe1/0xe8
> >>> ---[ end trace 4eaa2a86a8e2da22 ]---
> >>> ioremap reserve_memtype failed -22The return code is -EINVAL, so it failed in the is_ram check, which is
not too surprising> BIOS-provided physical RAM map:
> BIOS-e820: 0000000000000000 - 000000000009c000 (usable)
> BIOS-e820: 000000000009c000 - 00000000000a0000 (reserved)
> BIOS-e820: 00000000000e0000 - 0000000000100000 (reserved)
> BIOS-e820: 0000000000100000 - 00000000cffa3900 (usable)
> BIOS-e820: 00000000cffa3900 - 00000000cffa7400 (ACPI data)The ACPI data is not starting on a page boundary and neither does the
usable RAM area end on a page boundary. Very useful !> ACPI: DSDT 00000000cffa3900 036CE (v01 IBM SERLEWIS 00001000 INTL 20060912)
ACPI is trying to map DSDT at cffa3900, which results in a check
vs. cffa3000 which is the relevant page boundary. The generic is_ram
check correctly identifies that as RAM because it's in the usable
resource area. The old e820 based is_ram check does not take
overlapping resource areas into account. That's why it works.CC: Sachin Sant
CC: Thomas Gleixner
CC: KAMEZAWA Hiroyuki
Signed-off-by: Wu Fengguang
LKML-Reference:
Signed-off-by: H. Peter Anvin
01 Mar, 2010
1 commit
-
* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86, mm: Unify kernel_physical_mapping_init() API
x86, mm: Allow highmem user page tables to be disabled at boot time
x86: Do not reserve brk for DMI if it's not going to be used
x86: Convert tlbstate_lock to raw_spinlock
x86: Use the generic page_is_ram()
x86: Remove BIOS data range from e820
Move page_is_ram() declaration to mm.h
Generic page_is_ram: use __weak
resources: introduce generic page_is_ram()
23 Feb, 2010
3 commits
-
Useful for freeing a portion of the resource tree, e.g. when trying to
reallocate resources more efficiently.Signed-off-by: Yinghai Lu
Acked-by: Linus Torvalds
Signed-off-by: Jesse Barnes -
Now that we return the new resource start position, there is no
need to update "struct resource" inside the align function.
Therefore, mark the struct resource as const.Cc: Bjorn Helgaas
Cc: Yinghai Lu
Signed-off-by: Dominik Brodowski
Signed-off-by: Jesse Barnes -
As suggested by Linus, align functions should return the start
of a resource, not void. An update of "res->start" is no longer
necessary.Cc: Bjorn Helgaas
Cc: Yinghai Lu
Signed-off-by: Dominik Brodowski
Signed-off-by: Jesse Barnes
18 Feb, 2010
1 commit
-
x86/mm is on 32-rc4 and missing the spinlock namespace changes which
are needed for further commits into this topic.Signed-off-by: Thomas Gleixner
02 Feb, 2010
2 commits
-
Use __weak instead of __attribute__((weak)).
Cc: Wu Fengguang
Signed-off-by: Andrew Morton
Signed-off-by: H. Peter Anvin -
It's based on walk_system_ram_range(), for archs that don't have
their own page_is_ram().The static verions in MIPS and SCORE are also made global.
v4: prefer plain 1 instead of PAGE_IS_RAM (H. Peter Anvin)
v3: add comment (KAMEZAWA Hiroyuki)
"AFAIK, this "System RAM" information has been used for kdump to
grab valid memory area and seems good for the kernel itself."
v2: add PAGE_IS_RAM macro (Américo Wang)Cc: Chen Liqin
Cc: Lennox Wu
Cc: Américo Wang
Cc: linux-mips@linux-mips.org
Cc: Yinghai Lu
Acked-by: Ralf Baechle
Reviewed-by: KAMEZAWA Hiroyuki
Signed-off-by: Wu Fengguang
LKML-Reference:
Cc: Andrew Morton
Signed-off-by: H. Peter Anvin
22 Dec, 2009
1 commit
-
The second parameter to alignf() in allocate_resource() must
reflect what new resource is attempted to be allocated, else
functions like pcibios_align_resource() (at least on x86) or
pcmcia_align() can't work correctly.Commit 1e5ad9679016275d422e36b12a98b0927d76f556 broke this by
setting the "new" resource until we're about to return success.
To keep the resource untouched when allocate_resource() fails,
a "tmp" resource is introduced.Signed-off-by: Dominik Brodowski
Acked-by: Bjorn Helgaas
Cc: Yinghai Lu
Cc: Jesse Barnes
Signed-off-by: Linus Torvalds
05 Nov, 2009
1 commit
-
When "allocate_resource(root, new, size, ...)" fails, we currently
clobber "new". This is inconvenient for the caller, who might care
about the original contents of the resource.For example, when pci_bus_alloc_resource() fails, the "can't allocate
mem resource %pR" message from pci_assign_resources() currently contains
junk for the resource start/end.This patch delays the "new" update until we're about to return success.
Acked-by: Linus Torvalds
Acked-by: Yinghai Lu
Signed-off-by: Bjorn Helgaas
Signed-off-by: Jesse Barnes
23 Sep, 2009
1 commit
-
Originally, walk_memory_resource() was introduced to traverse all memory
of "System RAM" for detecting memory hotplug/unplug range. For doing so,
flags of IORESOUCE_MEM|IORESOURCE_BUSY was used and this was enough for
memory hotplug.But for using other purpose, /proc/kcore, this may includes some firmware
area marked as IORESOURCE_BUSY | IORESOUCE_MEM. This patch makes the
check strict to find out busy "System RAM".Note: PPC64 keeps their own walk_memory_resouce(), which walk through
ppc64's lmb informaton. Because old kclist_add() is called per lmb, this
patch makes no difference in behavior, finally.And this patch removes CONFIG_MEMORY_HOTPLUG check from this function.
Because pfn_valid() just show "there is memmap or not* and cannot be used
for "there is physical memory or not", this function is useful in generic
to scan physical memory range.Signed-off-by: KAMEZAWA Hiroyuki
Cc: Ralf Baechle
Cc: Benjamin Herrenschmidt
Cc: WANG Cong
Cc: Américo Wang
Cc: David Rientjes
Cc: Roland Dreier
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
01 Jul, 2009
1 commit
-
When the 32-bit signed quantities get assigned to the u64 resource_size_t,
they are incorrectly sign-extended.Addresses http://bugzilla.kernel.org/show_bug.cgi?id=13253
Addresses http://bugzilla.kernel.org/show_bug.cgi?id=9905Signed-off-by: Zhang Rui
Reported-by: Leann Ogasawara
Cc: Pierre Ossman
Reported-by:
Tested-by:
Cc:
Cc: Jesse Barnes
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
19 Apr, 2009
1 commit
-
This function is not actually used right now, since the original use
case for it was done with insert_resource_expand_to_fit() instead.However, we now have another usage case that wants to basically do a
"reserve IO resource, splitting around existing resources", however that
one doesn't actually want the "recurse into the conflicting resource"
logic at all.And since recursing into the conflicting resource was the most complex
part, and isn't wanted, just remove it. Maybe we'll some day want both
versions, but we can just resurrect the logic then.Tested-by: Yinghai Lu
Signed-off-by: Linus Torvalds
16 Jan, 2009
1 commit
-
Fix __request_region() parameter kernel-doc notation and parameter name:
Warning(linux-2.6.28-git10//kernel/resource.c:627): No description found for parameter 'flags'
Signed-off-by: Randy Dunlap
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
08 Jan, 2009
1 commit
-
Device drivers that use pci_request_regions() (and similar APIs) have a
reasonable expectation that they are the only ones accessing their device.
As part of the e1000e hunt, we were afraid that some userland (X or some
bootsplash stuff) was mapping the MMIO region that the driver thought it
had exclusively via /dev/mem or via various sysfs resource mappings.This patch adds the option for device drivers to cause their reserved
regions to the "banned from /dev/mem use" list, so now both kernel memory
and device-exclusive MMIO regions are banned.
NOTE: This is only active when CONFIG_STRICT_DEVMEM is set.In addition to the config option, a kernel parameter iomem=relaxed is
provided for the cases where developers want to diagnose, in the field,
drivers issues from userspace.Reviewed-by: Matthew Wilcox
Signed-off-by: Arjan van de Ven
Signed-off-by: Jesse Barnes
17 Dec, 2008
1 commit
-
Impact: reduce false positives in iomem_map_sanity_check()
Some drivers (vesafb) only map/reserve a portion of a resource.
If then some other driver comes in and maps the whole resource,
the current code WARN_ON's. This is not the intent of the checks
in iomem_map_sanity_check(); rather these checks want to
warn when crossing *hardware* resources only.This patch skips BUSY resources as suggested by Linus.
Note: having two drivers talk to the same hardware at the same
time is obviously not optimal behavior, but that's a separate story.Signed-off-by: Arjan van de Ven
Signed-off-by: Ingo Molnar
02 Nov, 2008
1 commit
-
This one apparently doesn't generate any warnings, because the function
is only used during system bootup, when the warnings are disabled. But
it's still very wrong.The __reserve_region_with_split() function is called with the
resource_lock held for writing, so it must only ever do GFP_ATOMIC
allocations.Signed-off-by: Linus Torvalds
29 Oct, 2008
1 commit
-
Impact: avoid false-positive WARN_ON()
Andi Kleen reported:
> When running x86info on a 2.6.27-git8 system I get
>
> resource map sanity check conflict: 0x9e000 0x9efff 0x10000 0x9e7ff System RAM
> ------------[ cut here ]------------
> WARNING: at /home/lsrc/linux/arch/x86/mm/ioremap.c:226 __ioremap_caller+0xf2/0x2d6()
> ...Some of the pages below the 1MB ISA addresses will be shared typically by both
BIOS and system usable RAM. For example:
BIOS-e820: 0000000000000000 - 000000000009f800 (usable)
BIOS-e820: 000000000009f800 - 00000000000a0000 (reserved)x86info reads the low physical address using /dev/mem, which internally
uses ioremap() for accessing non RAM pages. ioremap() of such low
pages conflicts with multiple resource entities leading to the
above warning.Change the iomem_map_sanity_check() to allow mapping a page spanning multiple
resource entities (minimum granularity that one can map is a page anyhow).Signed-off-by: Suresh Siddha
Signed-off-by: Ingo Molnar
