Hello Guenter,
On 04/07/2015 09:22 PM, Guenter Roeck wrote:
Hi Cedric,
On Tue, Apr 07, 2015 at 08:03:46PM +0200, Cedric Le Goater wrote:
on a P7 :
# ppc64_cpu --info
Core 0:0*1*2*3*
Core 1:4*5*6*7*
Core 2:8*9* 10*
The new OPAL device tree adds a few properties which can be used to add
extra information on the sensor label.
In the case of a cpu core sensor, the firmware exposes the physical
identifier of the core in the ibm,pir property. The driver
translates this identifier in a linux cpu number and
On Tue, Apr 07, 2015 at 05:34:55PM -0700, Sukadev Bhattiprolu wrote:
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2b62198..4dc3d70 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -240,20 +240,27 @@ struct pmu {
*
*
On Wed, Apr 08, 2015 at 12:32:01PM +0200, Brice Goglin wrote:
Le 07/04/2015 21:41, Peter Zijlstra a écrit :
No, that's very much not the same. Even if it were dealing with hotplug
it would still assume the cpu to return to the same node.
But mostly people do not even bother to handle
T1024RDB is a Freescale Reference Design Board that hosts the T1024 SoC.
T1024RDB board Overview
---
- Processor: T1024 SoC integrating two 64-bit e5500 cores up to 1.4GHz
- Memory: 64-bit 4GB DDR3L UDIMM with ECC and interleaving support
- Ethernet: two 1G RGMII ports, one
On (04/08/15 18:30), Benjamin Herrenschmidt wrote:
I'm happy with your last version, feel free to add my
Acked-by: Benjamin Herrenschmidt b...@kernel.crashing.org
sounds good, I'll do this and rese a non-RFC version today.
Thanks for all the feedback - it was very useful to me, and
I'm
The T1024 SoC includes the following function and features:
- Two 64-bit Power architecture e5500 cores, up to 1.4GHz
- private 256KB L2 cache each core and shared 256KB CoreNet platform cache (CPC)
- 32-/64-bit DDR3L/DDR4 SDRAM memory controller with ECC and interleaving
support
- Data Path
From: Igal Liberman igal.liber...@freescale.com
v2: Addressed feedback from Scott:
- Moved the fman-clk-mux clock provider details
under clocks property.
Signed-off-by: Igal Liberman igal.liber...@freescale.com
---
.../devicetree/bindings/clock/qoriq-clock.txt | 63
Hi Kumar.
Regards,
Igal Liberman.
-Original Message-
From: Kumar Gala [mailto:ga...@kernel.crashing.org]
Sent: Friday, February 27, 2015 6:02 PM
To: Liberman Igal-B31950
Cc: linuxppc-dev@lists.ozlabs.org; Wood Scott-B07421; Medve Emilian-
EMMEDVE1
Subject: Re: [PATCH] clk:
Le 07/04/2015 21:41, Peter Zijlstra a écrit :
No, that's very much not the same. Even if it were dealing with hotplug
it would still assume the cpu to return to the same node.
But mostly people do not even bother to handle hotplug.
You said userspace assumes the cpu-node relation is a
Add support for Freescale T1024/T1023 QorIQ Development System Board.
T1024QDS is a high-performance computing evaluation, development and
test platform for T1024 QorIQ Power Architecture processor.
T1024QDS board Overview
---
- T1024 SoC integrating two 64-bit e5500 cores up
T1023RDB is a Freescale Reference Design Board that hosts T1023 SoC.
T1023RDB board Overview
---
- T1023 SoC integrating two 64-bit e5500 cores up to 1.4GHz
- CoreNet fabric supporting coherent and noncoherent transactions with
prioritization and bandwidth allocation
-
On Tue, 2015-04-07 at 22:39 -0700, Yinghai Lu wrote:
On Tue, Apr 7, 2015 at 8:49 PM, Benjamin Herrenschmidt
b...@kernel.crashing.org wrote:
On Tue, 2015-04-07 at 17:24 -0700, Yinghai Lu wrote:
For device resource PREF bit setting under bridge 64-bit pref resource,
we need to make sure only
On Sun, 2015-04-05 at 07:49 -0400, Sowmini Varadhan wrote:
Investigation of multithreaded iperf experiments on an ethernet
interface show the iommu-lock as the hottest lock identified by
lockstat, with something of the order of 21M contentions out of
27M acquisitions, and an average wait time
Hi Scott
Regards,
Igal Liberman.
-Original Message-
From: Wood Scott-B07421
Sent: Wednesday, April 08, 2015 1:40 AM
To: Liberman Igal-B31950
Cc: devicet...@vger.kernel.org; linuxppc-dev@lists.ozlabs.org
Subject: Re: [PATCH] dt/bindings: qoriq-clock: Add binding for FMan clock
mux
The opal_{get,set}_param calls return internal error codes which need
to be translated in errnos in Linux.
Signed-off-by: Cédric Le Goater c...@fr.ibm.com
---
arch/powerpc/platforms/powernv/opal-sysparam.c | 12
arch/powerpc/platforms/powernv/opal.c |1 +
2 files
On 30 March 2015 at 16:46, Suman Tripathi stripa...@apm.com wrote:
This patch adds some quirks support to be read from fdt.
Signed-off-by: Suman Tripathi stripa...@apm.com
---
drivers/mmc/host/sdhci-pltfm.c | 15 +++
1 file changed, 15 insertions(+)
diff --git
On Wed, 2015-04-08 at 13:22 +1000, Alexey Kardashevskiy wrote:
On 04/03/2015 07:50 AM, Alex Williamson wrote:
Should have sent this with the other comments, but found it hiding on my
desktop...
On Sat, 2015-03-28 at 01:55 +1100, Alexey Kardashevskiy wrote:
In order to support memory
On 04/08/2015 05:20 PM, Guenter Roeck wrote:
On Wed, Apr 01, 2015 at 12:15:04PM +0200, Cédric Le Goater wrote:
The new OPAL device tree for sensors has a different layout and uses new
property names, for the type and for the handler used to capture the
sensor data.
This patch modifies the
On Wed, Apr 01, 2015 at 12:15:04PM +0200, Cédric Le Goater wrote:
The new OPAL device tree for sensors has a different layout and uses new
property names, for the type and for the handler used to capture the
sensor data.
This patch modifies the ibmpowernv driver to support such a tree in a
Hello !
These patches extend the ibmpowernv driver to support the new OPAL firmware
which now exposes in its device tree the Digital Temperature Sensors of
a P8 system.
They are based on Linux 4.0.0-rc7 + the initial cleanup serie :
This should shorten a bit the code necessary to create a hmwon attribute.
Signed-off-by: Cédric Le Goater c...@fr.ibm.com
---
Changes since v1:
- fix alignment of create_hwmon_attr() prototype
drivers/hwmon/ibmpowernv.c | 24
1 file changed, 16 insertions(+), 8
The new OPAL device tree adds a few properties which can be used to add
extra information on the sensor label.
In the case of a cpu core sensor, the firmware exposes the physical
identifier of the core in the ibm,pir property. The driver
translates this identifier in a linux cpu number and prints
Currently, sensors are only identified by their type and index.
The new OPAL device tree can expose extra properties to identify
some sensors by their name or location. This patch adds the creation
of a new hwmon *_label attribute when such properties are detected.
Signed-off-by: Cédric Le
The new OPAL device tree for sensors has a different layout and uses new
property names, for the type and for the handler used to capture the
sensor data.
This patch modifies the ibmpowernv driver to support such a tree in a
way preserving compatibility with older OPAL firmwares.
This is
On 04/08/2015 07:32 PM, Guenter Roeck wrote:
On Wed, Apr 08, 2015 at 07:19:46PM +0200, Cédric Le Goater wrote:
Hello !
These patches extend the ibmpowernv driver to support the new OPAL firmware
which now exposes in its device tree the Digital Temperature Sensors of
a P8 system.
They are
On Wed, Apr 08, 2015 at 07:19:46PM +0200, Cédric Le Goater wrote:
Hello !
These patches extend the ibmpowernv driver to support the new OPAL firmware
which now exposes in its device tree the Digital Temperature Sensors of
a P8 system.
They are based on Linux 4.0.0-rc7 + the initial
On Tue, Apr 07, 2015 at 05:34:59PM -0700, Sukadev Bhattiprolu wrote:
@@ -1213,9 +1221,47 @@ static void update_event_count(struct perf_event
*event, u64 now)
static void h_24x7_event_read(struct perf_event *event)
{
u64 now;
+ struct h_24x7_hw *h24x7hw;
+ struct
On 04/08/2015 03:26 PM, Guenter Roeck wrote:
On 04/08/2015 12:00 AM, Cédric Le Goater wrote:
The new OPAL device tree adds a few properties which can be used to add
extra information on the sensor label.
In the case of a cpu core sensor, the firmware exposes the physical
identifier of the
On Tue, Apr 07, 2015 at 05:34:57PM -0700, Sukadev Bhattiprolu wrote:
perf_event_read_value() is mostly computing the event count and enabled/
running times. Move the perf_event_read() into caller and rename
perf_event_read_value() to perf_event_compute_values().
Changelog[v2]
Export
The new OPAL device tree adds a few properties which can be used to add
extra information on the sensor label.
In the case of a cpu core sensor, the firmware exposes the physical
identifier of the core in the ibm,pir property. The driver
translates this identifier in a linux cpu number and
On 4/3/2015 10:24 PM, Scott Wood wrote:
What are you using PPC_MPC8306 for in your custom board code?
Sorry for the late reply, I was a bit busy over the Easter weekend.
I'm not currently using it for anything, so I guess I could remove it
and just use PPC_MPC830x in my board code.
On Tue, Apr 07, 2015 at 05:34:58PM -0700, Sukadev Bhattiprolu wrote:
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1ac99d1..a001582 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3644,6 +3644,33 @@ static void orphans_remove_work(struct work_struct
*work)
On 04/08/2015 12:00 AM, Cédric Le Goater wrote:
The new OPAL device tree adds a few properties which can be used to add
extra information on the sensor label.
In the case of a cpu core sensor, the firmware exposes the physical
identifier of the core in the ibm,pir property. The driver
On Tue, Apr 07, 2015 at 01:34:30PM -0400, Dan Streetman wrote:
Add configurable module to perform self-tests on any crypto compression
driver.
This allows testing any crypto compression driver with any input buffer,
at varying alignments and lengths. It calculates the average bytes per
On Wed, Apr 8, 2015 at 10:38 AM, Herbert Xu herb...@gondor.apana.org.au wrote:
On Wed, Apr 08, 2015 at 10:28:23AM -0400, Dan Streetman wrote:
So, the sw implementation is only for decompression; there's no sw
compression implementation in these patches.
As a general rule we don't add any
On Wed, Apr 08, 2015 at 10:45:45AM -0400, Dan Streetman wrote:
Ok I'll see if I can include a sw compression implementation.
That would be great!
ah ok, so you mean it can still be a crypto_comp interface, just move
its location and/or merge it into nx-842.c?
Oh yes of course. There is
On Wed, Apr 08, 2015 at 03:42:07PM +0200, Cédric Le Goater wrote:
The new OPAL device tree adds a few properties which can be used to add
extra information on the sensor label.
In the case of a cpu core sensor, the firmware exposes the physical
identifier of the core in the ibm,pir
On Wed, Apr 8, 2015 at 10:16 AM, Herbert Xu herb...@gondor.apana.org.au wrote:
On Tue, Apr 07, 2015 at 01:34:28PM -0400, Dan Streetman wrote:
Update the crypto 842 driver to no longer fallback to LZO if the 842
hardware is unavailable. Simplify the crpypto 842 driver to remove all
headers
On Tue, Apr 07, 2015 at 01:34:28PM -0400, Dan Streetman wrote:
Update the crypto 842 driver to no longer fallback to LZO if the 842
hardware is unavailable. Simplify the crpypto 842 driver to remove all
headers indicating 842/lzo.
The crypto 842 driver should do 842-format compression and
On Wed, Apr 08, 2015 at 10:28:23AM -0400, Dan Streetman wrote:
So, the sw implementation is only for decompression; there's no sw
compression implementation in these patches.
As a general rule we don't add any hardware implementation unless
there is a software implementation. The reason is
On Wed, Apr 8, 2015 at 10:16 AM, Herbert Xu herb...@gondor.apana.org.au wrote:
On Tue, Apr 07, 2015 at 01:34:30PM -0400, Dan Streetman wrote:
Add configurable module to perform self-tests on any crypto compression
driver.
This allows testing any crypto compression driver with any input
Anshuman Khandual khand...@linux.vnet.ibm.com wrote on 23.03.2015
11:34:30:
With that in mind, do we have a way to set the top 32bits of the MSR
(which contain the TM bits) when ptracing 32 bit processes? I can't
find anything like that in this patch set.
No, we dont have that yet. When
On Thu, 2015-04-09 at 13:21 +1000, Alexey Kardashevskiy wrote:
On 04/09/2015 01:43 AM, Alex Williamson wrote:
On Wed, 2015-04-08 at 13:22 +1000, Alexey Kardashevskiy wrote:
On 04/03/2015 07:50 AM, Alex Williamson wrote:
Should have sent this with the other comments, but found it hiding on
Commit 1bc9e47aa8e4 (powerpc/jump_label: Use HAVE_JUMP_LABEL)
converted uses of CONFIG_JUMP_LABEL to HAVE_JUMP_LABEL in
some assembly files.
HAVE_JUMP_LABEL is defined in linux/jump_label.h, so we need to
include this or we always get the non jump label fallback code.
Fixes: 1bc9e47aa8e4
On Wed, 2015-04-08 at 18:46 +0800, Shengzhou Liu wrote:
T1024RDB is a Freescale Reference Design Board that hosts the T1024 SoC.
T1024RDB board Overview
---
- Processor: T1024 SoC integrating two 64-bit e5500 cores up to 1.4GHz
- Memory: 64-bit 4GB DDR3L UDIMM with ECC
On Wed, 2015-04-08 at 18:46 +0800, Shengzhou Liu wrote:
The T1024 SoC includes the following function and features:
- Two 64-bit Power architecture e5500 cores, up to 1.4GHz
- private 256KB L2 cache each core and shared 256KB CoreNet platform cache
(CPC)
- 32-/64-bit DDR3L/DDR4 SDRAM memory
The hard lockup detector uses a PMU event as a periodic NMI to
detect if we are stuck (where stuck means no timer interrupts have
occurred).
Ben's rework of the ppc64 soft disable code has made ppc64 PMU
exceptions a partial NMI. They can get disabled if an external
interrupt comes in, but
On Thu, Apr 9, 2015 at 2:12 AM, Julian Calaby julian.cal...@gmail.com wrote:
Hi Konstantin,
On Thu, Apr 9, 2015 at 3:04 AM, Konstantin Khlebnikov
khlebni...@yandex-team.ru wrote:
On 08.04.2015 19:59, Konstantin Khlebnikov wrote:
Node 0 might be offline as well as any other numa node,
in
On 08.04.2015 19:59, Konstantin Khlebnikov wrote:
Node 0 might be offline as well as any other numa node,
in this case kernel cannot handle memory allocation and crashes.
Example:
[0.027133] [ cut here ]
[0.027938] kernel BUG at include/linux/gfp.h:322!
[
On 08.04.2015 [20:04:04 +0300], Konstantin Khlebnikov wrote:
On 08.04.2015 19:59, Konstantin Khlebnikov wrote:
Node 0 might be offline as well as any other numa node,
in this case kernel cannot handle memory allocation and crashes.
Isn't the bug that numa_node_id() returned an offline node?
Hi Konstantin,
On Thu, Apr 9, 2015 at 3:04 AM, Konstantin Khlebnikov
khlebni...@yandex-team.ru wrote:
On 08.04.2015 19:59, Konstantin Khlebnikov wrote:
Node 0 might be offline as well as any other numa node,
in this case kernel cannot handle memory allocation and crashes.
Example:
[
On 04/09/2015 01:43 AM, Alex Williamson wrote:
On Wed, 2015-04-08 at 13:22 +1000, Alexey Kardashevskiy wrote:
On 04/03/2015 07:50 AM, Alex Williamson wrote:
Should have sent this with the other comments, but found it hiding on my
desktop...
On Sat, 2015-03-28 at 01:55 +1100, Alexey
Add a devicetree description for property nodes for the NX Coprocessor
in an IBM PowerPC processor.
Signed-off-by: Dan Streetman ddstr...@ieee.org
---
Is this the right location/naming for this file?
And did I get the content format right?
Should this file be called ibm-nx-opal.txt instead of
On 09.04.15 12:52:55, Anton Blanchard wrote:
We want to enable the hard lockup detector on ppc64, but right now
that enables the oprofile NMI timer too.
We'd prefer not to enable the oprofile NMI timer, it adds another
element to our PMU testing and it requires us to increase our
exported
To use jump labels in assembly we need the HAVE_JUMP_LABEL define,
so we select a fallback version if the toolchain does not support
them.
Modify linux/jump_label.h so it can be included by assembly files.
We also need to add -DCC_HAVE_ASM_GOTO to KBUILD_AFLAGS.
Signed-off-by: Anton Blanchard
Node 0 might be offline as well as any other numa node,
in this case kernel cannot handle memory allocation and crashes.
Signed-off-by: Konstantin Khlebnikov khlebni...@yandex-team.ru
Fixes: 0c3f061c195c (of: implement of_node_to_nid as a weak function)
---
drivers/of/base.c |2 +-
On Wed, 2015-04-08 at 19:50 +0200, Ulrich Weigand wrote:
Anshuman Khandual khand...@linux.vnet.ibm.com wrote on 23.03.2015
11:34:30:
With that in mind, do we have a way to set the top 32bits of the MSR
(which contain the TM bits) when ptracing 32 bit processes? I can't
find anything
On Thu, Apr 9, 2015 at 2:07 AM, Nishanth Aravamudan
n...@linux.vnet.ibm.com wrote:
On 08.04.2015 [20:04:04 +0300], Konstantin Khlebnikov wrote:
On 08.04.2015 19:59, Konstantin Khlebnikov wrote:
Node 0 might be offline as well as any other numa node,
in this case kernel cannot handle memory
We want to enable the hard lockup detector on ppc64, but right now
that enables the oprofile NMI timer too.
We'd prefer not to enable the oprofile NMI timer, it adds another
element to our PMU testing and it requires us to increase our
exported symbols (eg cpu_khz).
Modify the config entry for
Wrap asm/jump_label.h for all archs with #ifndef __ASSEMBLY__.
Since these are kernel only headers, we don't need #ifdef __KERNEL__
so can simplify things a bit.
If an architecture wants to use jump labels in assembly, it
will still need to define a macro to create the __jump_table
entries (see
Commit 1bc9e47aa8e4 (powerpc/jump_label: Use HAVE_JUMP_LABEL)
converted uses of CONFIG_JUMP_LABEL to HAVE_JUMP_LABEL in
some assembly files.
HAVE_JUMP_LABEL is defined in linux/jump_label.h, so we need to
include this or we always get the non jump label fallback code.
Fixes: 1bc9e47aa8e4
To use jump labels in assembly we need the HAVE_JUMP_LABEL define,
so we select a fallback version if the toolchain does not support
them.
Modify linux/jump_label.h so it can be included by assembly files.
We also need to add -DCC_HAVE_ASM_GOTO to KBUILD_AFLAGS.
Signed-off-by: Anton Blanchard
On Wed, Apr 8, 2015 at 1:01 AM, Benjamin Herrenschmidt
b...@kernel.crashing.org wrote:
Use a different flag to indicate the BAR policy or temporarily tweak a
local copy of the resource flag during BAR assignment or whatever you
prefer to fix the original problem but do *not* change the Linux
On Wed, 2015-04-08 at 18:46 +0800, Shengzhou Liu wrote:
+ clockgen: global-utilities@e1000 {
+ compatible = fsl,t1023-clockgen, fsl,qoriq-clockgen-2.0,
+fixed-clock;
+ reg = 0xe1000 0x1000;
+ clock-output-names = sysclk;
On Wed, 2015-04-08 at 10:43 +0300, Igal.Liberman wrote:
@@ -76,6 +77,52 @@ Required properties:
Recommended properties:
- clocks: Should be the phandle of input parent clock
+ For fsl,fman-clk-mux clock there are several options for parent
+ clock (clock provider), the parent is
Wrap asm/jump_label.h for all archs with #ifndef __ASSEMBLY__.
Since these are kernel only headers, we don't need #ifdef __KERNEL__
so can simplify things a bit.
If an architecture wants to use jump labels in assembly, it
will still need to define a macro to create the __jump_table
entries (see
67 matches
Mail list logo