getcpu reads the required values for cpu and node with two
instructions. This might lead to an inconsistent result if user space
gets preempted and migrated to a different CPU between the two
instructions.
Fix this by using just a single instruction to read both values at
once.
This is currently rather a theoretical bug, since there is no real
NUMA support available (except for NUMA emulation).
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
When a secondary CPU is brought up it must initialize its control
registers. CPU A which triggers that a secondary CPU B is brought up
stores its control register contents into the lowcore of new CPU B,
which then loads these values on startup.
This is problematic in various ways: the control register which
contains the home space ASCE will correctly contain the kernel ASCE;
however control registers for primary and secondary ASCEs are
initialized with whatever values were present in CPU A.
Typically:
- the primary ASCE will contain the user process ASCE of the process
that triggered onlining of CPU B.
- the secondary ASCE will contain the percpu VDSO ASCE of CPU A.
Due to lazy ASCE handling we may also end up with other combinations.
When then CPU B switches to a different process (!= idle) it will
fixup the primary ASCE. However the problem is that the (wrong) ASCE
from CPU A was loaded into control register 1: as soon as an ASCE is
attached (aka loaded) a CPU is free to generate TLB entries using that
address space.
Even though it is very unlikey that CPU B will actually generate such
entries, this could result in TLB entries of the address space of the
process that ran on CPU A. These entries shouldn't exist at all and
could cause problems later on.
Furthermore the secondary ASCE of CPU B will not be updated correctly.
This means that processes may see wrong results or even crash if they
access VDSO data on CPU B. The correct VDSO ASCE will eventually be
loaded on return to user space as soon as the kernel executed a call
to strnlen_user or an atomic futex operation on CPU B.
Fix both issues by intializing the to be loaded control register
contents with the correct ASCEs and also enforce (re-)loading of the
ASCEs upon first context switch and return to user space.
Fixes: 0aaba41b58 ("s390: remove all code using the access register mode")
Cc: stable@vger.kernel.org # v4.15+
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
This patch introduces support for a new architectured reply
code 0x8B indicating that a hypervisor layer (if any) has
rejected an ap message.
Linux may run as a guest on top of a hypervisor like zVM
or KVM. So the crypto hardware seen by the ap bus may be
restricted by the hypervisor for example only a subset like
only clear key crypto requests may be supported. Other
requests will be filtered out - rejected by the hypervisor.
The new reply code 0x8B will appear in such cases and needs
to get recognized by the ap bus and zcrypt device driver zoo.
Signed-off-by: Harald Freudenberger <freude@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
On s390 bpf_get_stack_raw_tp() returns 0 entries for both kernel and
user stacks. While there is no practical unwinding solution for userspace
on s390 at this moment, there certainly is a kernel unwinder. However,
it is not properly integrated with BPF.
In order to start unwinding, bpf_get_stack_raw_tp() obtains the current
kernel register values using perf_fetch_caller_regs(), which is not
implemented for s390. The actual unwinding then happens by passing those
registers to perf_callchain_kernel().
Implement perf_arch_fetch_caller_regs() for s390, where
__builtin_frame_address(0) points to back_chain.
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
system_call assembly code always pushes pointer to struct pt_regs as the
last additional parameter for all system calls. The only user of this
feature is xtensa_rt_sigreturn.
Avoid this special case. Define xtensa_rt_sigreturn as accepting no
argiments. Use current_pt_regs to get pointer to struct pt_regs in
xtensa_rt_sigreturn. Don't pass additional parameter from system_call
code.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Don't overwrite return value if system call was cancelled at entry by
ptrace. Return status code from do_syscall_trace_enter so that
pt_regs::syscall doesn't need to be changed to skip syscall.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
system_call saves and restores syscall number across system call to make
clone and execv entry and exit tracing match. This complicates things
when syscall code may be changed by ptrace.
Preserve syscall code in copy_thread and start_thread directly instead of
doing tricks in system_call.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Some versions of iproute2 will output more than one line per entry, which
will cause the test to fail, like:
TEST: ipv6: list and flush cached exceptions [FAIL]
can't list cached exceptions
That happens, for example, with iproute2 4.15.0. When using the -oneline
option, this will work just fine:
TEST: ipv6: list and flush cached exceptions [ OK ]
This also works just fine with a more recent version of iproute2, like
5.4.0.
For some reason, two lines are printed for the IPv4 test no matter what
version of iproute2 is used. Use the same -oneline parameter there instead
of counting the lines twice.
Fixes: b964641e99 ("selftests: pmtu: Make list_flush_ipv6_exception test more demanding")
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Acked-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
I forgot to fill in the map_symbol->maps field in append_inlines() which
then makes code down the line segfault when trying to deref it.
It doesn't make any sense to have an addr_location with its 'map' member
not NULL while its 'maps' is NULL, after all al->maps is where al->map
is in.
It is done that way so that we don't have to have in each 'struct map' a
pointer to the 'struct maps' it is in, as we had in the past when we
would have 'map->mg', before 'struct maps' was combined with 'struct
map_groups', because there was always a one-to-one relationship for
these structs.
This fixes a segfault when processing DWARF callgraphs in 'perf report'.
Reported-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Fixes: 08f6680e62 ("perf tools: Add a 'struct map_groups' pointer to 'struct map_symbol'")
Link: http://lore.kernel.org/lkml/20191129160631.GD26963@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
KVM: Add support for secure guests under the Protected Execution
Framework (PEF) Ultravisor on POWER.
This enables secure memory to be represented as device memory,
which provides a way for the host to keep track of which pages of a
secure guest have been moved into secure memory managed by the
ultravisor and are no longer accessible by the host, and manage
movement of pages between secure and normal memory.
In api.txt it is said that KVM ioctls belong to three classes
but in reality it is four. Fixed this, but do not count categories
anymore to avoid such as outdated information in the future.
Signed-off-by: Wainer dos Santos Moschetta <wainersm@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Christophe reports that current master fails building on powerpc with
this error:
CC fs/io_uring.o
fs/io_uring.c: In function ‘loop_rw_iter’:
fs/io_uring.c:1628:21: error: implicit declaration of function ‘kmap’
[-Werror=implicit-function-declaration]
iovec.iov_base = kmap(iter->bvec->bv_page)
^
fs/io_uring.c:1628:19: warning: assignment makes pointer from integer
without a cast [-Wint-conversion]
iovec.iov_base = kmap(iter->bvec->bv_page)
^
fs/io_uring.c:1643:4: error: implicit declaration of function ‘kunmap’
[-Werror=implicit-function-declaration]
kunmap(iter->bvec->bv_page);
^
which is caused by a missing highmem.h include. Fix it by including
it.
Fixes: 311ae9e159 ("io_uring: fix dead-hung for non-iter fixed rw")
Reported-by: Christophe Leroy <christophe.leroy@c-s.fr>
Tested-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Restructure event enabling/disabling to use affinity, which
minimizes the number of IPIs needed.
Before on a large test case with 94 CPUs:
% time seconds usecs/call calls errors syscall
------ ----------- ----------- --------- --------- ----------------
54.65 1.899986 22 84812 660 ioctl
after:
39.21 0.930451 10 84796 644 ioctl
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lore.kernel.org/lkml/20191121001522.180827-13-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Restructure event reading to use affinity to minimize the number of IPIs
needed.
Before on a large test case with 94 CPUs:
% time seconds usecs/call calls errors syscall
------ ----------- ----------- --------- --------- ----------------
3.16 0.106079 4 22082 read
After:
3.43 0.081295 3 22082 read
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lore.kernel.org/lkml/20191121001522.180827-11-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Restructure the event opening in perf stat to cycle through the events
by CPU after setting affinity to that CPU.
This eliminates IPI overhead in the perf API.
We have to loop through the CPU in the outter builtin-stat code instead
of leaving that to low level functions.
It has to change the weak group fallback strategy slightly. Since we
cannot easily undo the opens for other CPUs move the weak group retry to
a separate loop.
Before with a large test case with 94 CPUs:
% time seconds usecs/call calls errors syscall
------ ----------- ----------- --------- --------- ----------------
42.75 4.050910 67 60046 110 perf_event_open
After:
26.86 0.944396 16 58069 110 perf_event_open
(the number changes slightly because the weak group retries
work differently and the test case relies on weak groups)
Committer notes:
Added one of the hunks in a patch provided by Andi after I noticed that
the "event times" 'perf test' entry was segfaulting.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lore.kernel.org/lkml/20191121001522.180827-10-andi@firstfloor.org
Link: http://lore.kernel.org/lkml/20191127232657.GL84886@tassilo.jf.intel.com # Fix
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Closing a perf fd can also trigger an IPI to the target CPU.
Use the same affinity technique as we use for reading/enabling events to
closing to optimize the CPU transitions.
Before on a large test case with 94 CPUs:
% time seconds usecs/call calls errors syscall
------ ----------- ----------- --------- --------- ----------------
32.56 3.085463 50 61483 close
After:
10.54 0.735704 11 61485 close
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lore.kernel.org/lkml/20191121001522.180827-8-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Maintain a cpumap in the evlist that is the union of all the cpus of the
events.
This needs a cpumap merge operation, which is added together with tests.
v2:
Add tests for cpu map merge
Fix handling of duplicates
Rename _update to _merge
Factor out sorting.
Fix handling of NULL maps in merge
v3:
Add comments and empty lines to _merge
Committer testing:
# perf test "Merge cpu map"
52: Merge cpu map : Ok
#
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lore.kernel.org/lkml/20191121001522.180827-5-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The auto-parser assigns the bass speaker to DAC3 (NID 0x06) which
is without the volume control. I do not see a reason to use DAC2,
because the shared output to all speakers produces the sufficient
and well balanced sound. The stereo support is enough for this
purpose (laptop).
Signed-off-by: Jaroslav Kysela <perex@perex.cz>
Link: https://lore.kernel.org/r/20191129144027.14765-1-perex@perex.cz
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Commit 5398e94fb7 ("ALSA: hda - Add DP-MST support for NVIDIA codecs")
introduced a slight change of behaviour how non-MST monitors are
assigned to PCMs on Intel platforms.
In the drm_audio_component.h interface, the third parameter
to pin_eld_notify() is pipe number. On Intel platforms, this value
is -1 for MST. On other platforms, a non-zero pipe id is used to
signal MST use.
This difference leads to some subtle differences in hdmi_find_pcm_slot()
with regards to how non-MST monitors are assigned to PCMs.
This patch restores the original behaviour on Intel platforms while
keeping the new allocation policy on other platforms.
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Link: https://lore.kernel.org/r/20191129143756.23941-2-kai.vehmanen@linux.intel.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Commit 2abb0d5268 ("PM / devfreq: Lock devfreq in trans_stat_show")
revealed a missing locking while calling devfreq_update_status() function
during suspend/resume cycle.
Code analysis revealed that devfreq_set_target() function was called
without needed locks held for setting device specific suspend_freq if such
has been defined. This patch fixes that by adding the needed locking, what
fixes following kernel warning on Exynos4412-based OdroidU3 board during
system suspend:
PM: suspend entry (deep)
Filesystems sync: 0.002 seconds
Freezing user space processes ... (elapsed 0.001 seconds) done.
OOM killer disabled.
Freezing remaining freezable tasks ... (elapsed 0.001 seconds) done.
------------[ cut here ]------------
WARNING: CPU: 2 PID: 1385 at drivers/devfreq/devfreq.c:204 devfreq_update_status+0xc0/0x188
Modules linked in:
CPU: 2 PID: 1385 Comm: rtcwake Not tainted 5.4.0-rc6-next-20191111 #6848
Hardware name: SAMSUNG EXYNOS (Flattened Device Tree)
[<c0112588>] (unwind_backtrace) from [<c010e070>] (show_stack+0x10/0x14)
[<c010e070>] (show_stack) from [<c0afb010>] (dump_stack+0xb4/0xe0)
[<c0afb010>] (dump_stack) from [<c01272e0>] (__warn+0xf4/0x10c)
[<c01272e0>] (__warn) from [<c01273a8>] (warn_slowpath_fmt+0xb0/0xb8)
[<c01273a8>] (warn_slowpath_fmt) from [<c07d105c>] (devfreq_update_status+0xc0/0x188)
[<c07d105c>] (devfreq_update_status) from [<c07d2d70>] (devfreq_set_target+0xb0/0x15c)
[<c07d2d70>] (devfreq_set_target) from [<c07d3598>] (devfreq_suspend+0x2c/0x64)
[<c07d3598>] (devfreq_suspend) from [<c05de0b0>] (dpm_suspend+0xa4/0x57c)
[<c05de0b0>] (dpm_suspend) from [<c05def74>] (dpm_suspend_start+0x98/0xa0)
[<c05def74>] (dpm_suspend_start) from [<c0195b58>] (suspend_devices_and_enter+0xec/0xc74)
[<c0195b58>] (suspend_devices_and_enter) from [<c0196a20>] (pm_suspend+0x340/0x410)
[<c0196a20>] (pm_suspend) from [<c019480c>] (state_store+0x6c/0xc8)
[<c019480c>] (state_store) from [<c033fc50>] (kernfs_fop_write+0x10c/0x228)
[<c033fc50>] (kernfs_fop_write) from [<c02a6d3c>] (__vfs_write+0x30/0x1d0)
[<c02a6d3c>] (__vfs_write) from [<c02a9afc>] (vfs_write+0xa4/0x180)
[<c02a9afc>] (vfs_write) from [<c02a9d58>] (ksys_write+0x60/0xd8)
[<c02a9d58>] (ksys_write) from [<c0101000>] (ret_fast_syscall+0x0/0x28)
Exception stack(0xed3d7fa8 to 0xed3d7ff0)
...
irq event stamp: 9667
hardirqs last enabled at (9679): [<c0b1e7c4>] _raw_spin_unlock_irq+0x20/0x58
hardirqs last disabled at (9698): [<c0b16a20>] __schedule+0xd8/0x818
softirqs last enabled at (9694): [<c01026fc>] __do_softirq+0x4fc/0x5fc
softirqs last disabled at (9719): [<c012fe68>] irq_exit+0x16c/0x170
---[ end trace 41ac5b57d046bdbc ]---
------------[ cut here ]------------
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Acked-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Support for adding per-device frequency limits was removed in
commit 2aac8bdf7a ("PM: QoS: Drop frequency QoS types from device PM QoS")
after cpufreq switched to use a new "freq_constraints" construct.
Restore support for per-device freq limits but base this upon
freq_constraints. This is primarily meant to be used by the devfreq
subsystem.
This removes the "static" marking on freq_qos_apply but does not export
it for modules.
Signed-off-by: Leonard Crestez <leonard.crestez@nxp.com>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Tested-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
This allows dev_pm_qos to embed freq_qos structs, which is done in the
next patch. Separate commit to make it easier to review.
Signed-off-by: Leonard Crestez <leonard.crestez@nxp.com>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
QOS requests for DEFAULT_VALUE are supposed to be ignored but this is
not the case for FREQ_QOS_MAX. Adding one request for MAX_DEFAULT_VALUE
and one for a real value will cause freq_qos_read_value to unexpectedly
return MAX_DEFAULT_VALUE (-1).
This happens because freq_qos max value is aggregated with PM_QOS_MIN
but FREQ_QOS_MAX_DEFAULT_VALUE is (-1) so it's smaller than other
values.
Fix this by redefining FREQ_QOS_MAX_DEFAULT_VALUE to S32_MAX.
Looking at current users for freq_qos it seems that none of them create
requests for FREQ_QOS_MAX_DEFAULT_VALUE.
Fixes: 77751a466e ("PM: QoS: Introduce frequency QoS")
Signed-off-by: Leonard Crestez <leonard.crestez@nxp.com>
Reported-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Cc: 5.4+ <stable@vger.kernel.org> # 5.4+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Adjust indentation from spaces to tab (+optional two spaces) as in
coding style with command like:
$ sed -e 's/^ /\t/' -i */Kconfig
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Acked-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Adjust indentation from spaces to tab (+optional two spaces) as in
coding style with command like:
$ sed -e 's/^ /\t/' -i */Kconfig
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
After recent cpuidle updates the "disabled" field in struct
cpuidle_state is only used by two drivers (intel_idle and shmobile
cpuidle) for marking unusable idle states, but that may as well be
achieved with the help of a state flag, so define an "unusable" idle
state flag, CPUIDLE_FLAG_UNUSABLE, make the drivers in question use
it instead of the "disabled" field and make the core set
CPUIDLE_STATE_DISABLED_BY_DRIVER for the idle states with that flag
set.
After the above changes, the "disabled" field in struct cpuidle_state
is not used any more, so drop it.
No intentional functional impact.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Adjust indentation from spaces to tab (+optional two spaces) as in
coding style with command like:
$ sed -e 's/^ /\t/' -i */Kconfig
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
kmemleak reported backtrace:
[<bbee0454>] kmem_cache_alloc_trace+0x128/0x260
[<6677f215>] i2c_acpi_install_space_handler+0x4b/0xe0
[<1180f4fc>] i2c_register_adapter+0x186/0x400
[<6083baf7>] i2c_add_adapter+0x4e/0x70
[<a3ddf966>] intel_gmbus_setup+0x1a2/0x2c0 [i915]
[<84cb69ae>] i915_driver_probe+0x8d8/0x13a0 [i915]
[<81911d4b>] i915_pci_probe+0x48/0x160 [i915]
[<4b159af1>] pci_device_probe+0xdc/0x160
[<b3c64704>] really_probe+0x1ee/0x450
[<bc029f5a>] driver_probe_device+0x142/0x1b0
[<d8829d20>] device_driver_attach+0x49/0x50
[<de71f045>] __driver_attach+0xc9/0x150
[<df33ac83>] bus_for_each_dev+0x56/0xa0
[<80089bba>] driver_attach+0x19/0x20
[<cc73f583>] bus_add_driver+0x177/0x220
[<7b29d8c7>] driver_register+0x56/0xf0
In i2c_acpi_remove_space_handler(), a leak occurs whenever the
"data" parameter is initialized to 0 before being passed to
acpi_bus_get_private_data().
This is because the NULL pointer check in acpi_bus_get_private_data()
(condition->if(!*data)) returns EINVAL and, in consequence, memory is
never freed in i2c_acpi_remove_space_handler().
Fix the NULL pointer check in acpi_bus_get_private_data() to follow
the analogous check in acpi_get_data_full().
Signed-off-by: Vamshi K Sthambamkadi <vamshi.k.sthambamkadi@gmail.com>
[ rjw: Subject & changelog ]
Cc: All applicable <stable@vger.kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
This reverts commit f2538f9993. The patch
stopped JFFS2 from being able to mount an existing filesystem with the
following errors:
jffs2: error: (77) jffs2_build_inode_fragtree: Add node to tree failed -22
jffs2: error: (77) jffs2_do_read_inode_internal: Failed to build final fragtree for inode #5377: error -22
Fixes: f2538f9993 ("jffs2: Fix possible null-pointer dereferences...")
Cc: stable@vger.kernel.org
Suggested-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Richard Weinberger <richard@nod.at>
Adjust indentation from spaces to tab (+optional two spaces) as in
coding style with command like:
$ sed -e 's/^ /\t/' -i */Kconfig
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
acpi_os_map_cleanup checks map->refcount outside of acpi_ioremap_lock
before freeing the map. This creates a race condition the can result
in the map being freed more than once.
A panic can be caused by running
for ((i=0; i<10; i++))
do
for ((j=0; j<100000; j++))
do
cat /sys/firmware/acpi/tables/data/BERT >/dev/null
done &
done
This patch makes sure that only the process that drops the reference
to 0 does the freeing.
Fixes: b7c1fadd6c ("ACPI: Do not use krefs under a mutex in osl.c")
Signed-off-by: Francesco Ruggeri <fruggeri@arista.com>
Reviewed-by: Dmitry Safonov <0x7f454c46@gmail.com>
Cc: All applicable <stable@vger.kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
