On 2015-09-16 10:42, Stuart Haslam wrote:
> The name of the libraries generated by the test modules were recently
> changed from lib.la to libtest.la
>
> Signed-off-by: Stuart Haslam <stuart.has...@linaro.org>
Reviewed-by: Christophe Milard <christophe.mil...@lina
d as inactive.
>
> Signed-off-by: Stuart Haslam <stuart.has...@linaro.org>
Reviewed-by: Christophe Milard <christophe.mil...@linaro.org>
> ---
> test/validation/buffer/buffer.c| 20 +++---
> test/validation/buffer/buffer.h|
On 2015-09-16 10:42, Stuart Haslam wrote:
> Add an odp_cunit_update() function to allow some attributes of previously
> registered tests to be modified, such as whether it's active or not.
>
> Previously, registering and running tests was done in a single step;
>
> odp_cunit_run(testsuites);
>
On 2015-09-16 10:42, Stuart Haslam wrote:
> Update sections describing how a specific platform may skip tests by
> marking them as inactive.
>
> Signed-off-by: Stuart Haslam
> ---
> doc/implementers-guide/implementers-guide.adoc | 58
> +-
> 1
On 2015-09-16 10:41, Stuart Haslam wrote:
> This series adds the ability to skip individual test cases either at
> compile time or conditionally at run time. There's no functional change
> since none of the existing tests use this facility.
>
> There are a few checkpatch warnings about camel case
On 16 September 2015 at 18:07, Stuart Haslam <stuart.has...@linaro.org>
wrote:
> On Wed, Sep 16, 2015 at 05:03:38PM +0200, Christophe Milard wrote:
> > On 2015-09-16 10:42, Stuart Haslam wrote:
> > > Add an odp_cunit_update() function to allow some attributes of
>
libtestodp.la contains all platform agnostic test functions and symbols
defined testodp.h (from all modules)
It is meant to be used by ODP devloppers to pick up the tests they need
(and disgard others) during the devlopment process on their platform.
Signed-off-by: Christophe Milard
No functionnal changes: just code reordering to match the ODP modules.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
configure.ac|3 +
platform/linux-generic/test/Makefile.am |3 +
test/validation/Makefile.am |5 +-
Now redundant with atomic, barrier and lock tests.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
configure.ac |1 -
platform/linux-generic/test/Makefile.am|1 -
test/validation/Makef
Now redundant with atomic, barrier and lock tests.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
configure.ac |1 -
platform/linux-generic/test/Makefile.am|1 -
test/validation/Makef
No functionnal changes: just code reordering to match the ODP modules.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
configure.ac|3 +
platform/linux-generic/test/Makefile.am |3 +
test/validation/Makefile.am |5 +-
pools, created on
> different parts of the application).
>
>
>
> -Petri
>
>
>
>
>
>
>
> *From:* EXT Christophe Milard [mailto:christophe.mil...@linaro.org]
> *Sent:* Wednesday, December 16, 2015 5:39 PM
> *To:* Petri Savolainen; Ola Liljedahl
wrote:
> Why the driver must map pools one by one? Is this a (legacy) kernel driver?
> The driver can map one or more DMA-ble memory regions at initialization
> time and this memory region should be used for all PACKET type pools.
>
> Alex
>
> On 17 December 2015 at 15:15, Christoph
Hi,
Following the discussion at the ARCH call, today, would it be reasonable to
require that all packet pools that can be used by a NIC have to be created
before the related nic pktio is opened? -This is implicitly required in RX,
as the pool handle from which buffer should be allocated in RX is
Christophe Milard (31):
api: dma: defining the dma region descriptor
api: introducing the driver api definition file
linux-generix: dma: implementation
api: shared_memory: getting DMA descriptor
linux-generic: shmem: retrieving DMA map desriptor
linux-generic: pool: retrieving DMA map
not belong
to the ODP-application interface.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
include/odp/api/dma.h | 102 ++
1 file changed, 102 insertions(+)
create mode 100644 include/odp/api/dma.h
diff --git a/include/o
-by: Christophe Milard <christophe.mil...@linaro.org>
---
include/odp.h| 2 +-
include/odp_driver.h | 34 ++
2 files changed, 35 insertions(+), 1 deletion(-)
create mode 100644 include/odp_driver.h
diff --git a/include/odp.h b/include/odp.h
index 4a93c23..1
Linux-generic implementation of the function returning a DMA mapping
descriptor for one, or all, defined packet pools
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/include/odp_dma_internal.h | 1 +
platform/linux-generic/include/odp_pool_inte
A new pktio is created for nic cards. At this stage, only pci-vfio is
supported. The interface name format must have the form:
pmd, for instance "pmd::23:00.0"
A linux generic pci_vfio driver must be running on the interface,
of course.
Signed-off-by: Christophe Milard <c
Implementation (for linux generic) of the DMA descriptor and related
methods.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/Makefile.am | 4 ++
platform/linux-generic/include/odp/dma.h | 36 ++
.../linux-g
This implementation just acts as a simple wrapper around pci-vfio.
This could grow if other pci access (such as user-io) get involved.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/Makefile.am | 1 +
platform/linux-generic/odp_pci.c
Implementation for NIC driver segments and segment pool and related
methods.
As in linux generic, nic segments matches ODP packets, most of these
functions are just wrappers around packet function equivalents.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
include/o
:
ODP_TEST_INFO_INACTIVE(send_failure)
Remarking the test as active later on is then only a matter of changing
back the macro name.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
test/validation/common/odp_cunit_common.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
The number of RX packets in the RX packet pool has to be increased as
the driver will prefill its RX ring directely at init time,
hence consuming as many RX packets as there are entries in the ring.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
test/validation
These map 1:1 to the ODP ones at the time being but may be redefined
if needed.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
drivers/driver_log.h | 26 ++
1 file changed, 26 insertions(+)
create mode 100644 drivers/driver_log.h
diff
Defining the internal implementation of a PCI device and related methods.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/Makefile.am | 3 +
platform/linux-generic/include/odp/pci.h | 36 +++
.../linux-generic/i
The NIC driver table is defined here, as well as the registration function
called by each driver at init time.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/include/odp_internal.h | 2 ++
platform/linux-generic/odp_init.c
as it refers to mtu_get
which is not implemented either
This patch is a temporary hack, of course.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
test/validation/pktio/pktio.c | 60 ++-
1 file changed, 31 insertions(+), 29 deletions(-)
Linux-generic implementation of the function returning a DMA mapping
descriptor for an allocated shared memory block.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/odp_shared_memory.c | 26 ++
1 file changed, 26 inse
Adding a function to get a DMA descriptor (describing how to perform a DMA
mapping on the given shared memory block). Also added a flag (ODP_SHM_DMA)
to be given at block reservation time, when DMA reachable memory is
required.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.
Implementation of the PCI api, using pci-vfio.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/Makefile.am | 2 +
.../linux-generic/include/odp_pci_vfio_internal.h | 92 +++
platform/linux-generic/odp_pci_vfio.c
Defining the ODP functions used to register a nic driver (which includes
the probing function prototype)
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
include/odp/api/nic.h| 117 +++
platform/linux-generic/include/odp
also depending on what we want to
achieve (thread safe / process safe / single queue sharing...)
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
drivers/driver_init.c |2 +
drivers/ixgbe/Makefile.am |2 +-
drivers/ixgbe/ixgbe_common.h
The eaxtra delay enabled by the env variable ODP_WAIT_FOR_NETWORK
is now much longer. Obviously needed by some Nic.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
test/validation/pktio/pktio.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git
Note that the functions to init/release the pci device are not part of
the interface as they are expected to be used by ODP (internaly) only.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
include/odp/api/pci.h
A mappable).
This patch defines the segments and segment pool (where NIC segments are
allocated from), as well as the different methods which can be used on
those.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
include/odp/api/nic.h | 152 +++
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
drivers/ixgbe/base/ixgbe_osdep.h | 77 +++-
1 file changed, 45 insertions(+), 32 deletions(-)
diff --git a/drivers/ixgbe/base/ixgbe_osdep.h b/drivers/ixgbe/base/ixgbe_osdep.h
index 4
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/pktio/nic.c | 12 +++-
1 file changed, 11 insertions(+), 1 deletion(-)
diff --git a/platform/linux-generic/pktio/nic.c
b/platform/linux-generic/pktio/nic.c
index 1c25c90..446cc98
Defining the Makefile.inc, common for all drivers.
Curentely defining the path to compile with the driver (south) api.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
drivers/Makefile.inc | 6 ++
1 file changed, 6 insertions(+)
create mode 100644 drivers/Makefi
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
drivers/ixgbe/ixgbe_logs.h | 67 ++
1 file changed, 67 insertions(+)
create mode 100644 drivers/ixgbe/ixgbe_logs.h
diff --git a/drivers/ixgbe/ixgbe_logs.h b/drivers/ixgbe/ixgbe_
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/include/odp_nic_internal.h | 5
platform/linux-generic/pktio/nic.c| 31 +--
2 files changed, 34 insertions(+), 2 deletions(-)
diff --git a/platform/linux-g
environment variables.
For instance, syntax is: source pktio_setup_nic :23:00.0 :23:00.1
The usage of this script is still manual. It is meant to be called in the
future pktio_run_nic script in the future.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-g
On 2015-12-18 15:54, Stuart Haslam wrote:
> All test functions should be non-static and declared in the module's
> header file.
>
> Signed-off-by: Stuart Haslam <stuart.has...@linaro.org>
Reviewed-by: Christophe Milard <christophe.mil...@linaro.org>
> ---
>
which aren't particularly easy to interpret.
>
> Signed-off-by: Stuart Haslam <stuart.has...@linaro.org>
Reviewed-by: Christophe Milard <christophe.mil...@linaro.org>
> ---
> platform/linux-generic/test/pktio/pktio_run | 4
> 1 file changed, 4 insertions(+)
>
My question relates to pktio when ODP tasks are implemented as unix
processes (as opposed to threads).
I can see that the pktio_entry struct used is allocated as shared mem.
If I take the socket pktio as an example, the socket file descriptor is
stored in th pktio struct.
In other words, the
will use the file descriptor created by A.
I must be missing something. But that is doomed to fail in my eyes.
On 30 December 2015 at 08:57, Maxim Uvarov <maxim.uva...@linaro.org> wrote:
> On 12/30/2015 10:42, Christophe Milard wrote:
>
>>
>> My question relates to pktio when O
But from an application perspective, the odp_pktio_t handle
> is the same and all pktio APIs behave the same.
>
> On Wed, Dec 30, 2015 at 6:00 AM, Christophe Milard <
> christophe.mil...@linaro.org> wrote:
>
>> I am confused here: The rules (e.g. order in which different
in the API (e.g. in the global init phase), we’ll fix
> those.
>
>
>
> - Petri
>
>
>
>
>
> *From:* lng-odp [mailto:lng-odp-boun...@lists.linaro.org] *On Behalf Of *EXT
> Christophe Milard
> *Sent:* Wednesday, December 30, 2015 10:10 AM
> *To:* Maxim Uva
Hi,
A colleague at Ericsson is having the following issue. It sounds quite
similar to the one I have reported earlyer (https://patches.linaro.org/49661),
But I have honestlely not digged deeply into it... Bill, does it ring a
bell to you?
/Christophe.
>Here is a short description of the ODP bug
(not under
> api).
>
>
> -Petri
>
>
>
>
> > -Original Message-
> > From: EXT Christophe Milard [mailto:christophe.mil...@linaro.org]
> > Sent: Friday, January 08, 2016 10:30 PM
> > To: anders.rox...@linaro.org; mike.hol...@linaro.org;
> > stuart.has
Limiting the usage of the C library to the functions defined in its
C99 version.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
doc/implementers-guide/implementers-guide.adoc | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/doc/implementers
t;
> On 11 January 2016 at 03:54, Savolainen, Petri (Nokia - FI/Espoo) <
> petri.savolai...@nokia.com> wrote:
>
>> CC’d the list again.
>>
>>
>>
>>
>>
>> *From:* EXT Christophe Milard [mailto:christophe.mil...@linaro.org]
>> *Sent:* Monday, Janu
n (drv fills x, y, z – implementation fills the
> rest).
>
There is no need to expose ODP packets as such to the drivers. In the
proposed implementation, drivers uses a new object called NIC segments
instead. Yes, they can match the packets. And the last segment of a
received packet would h
Hi Yi!
Your first diagram shows at least one thing very clearly, apart the
mess we have with dependencies: The location of the
platform//test directory is confusing!
This directory is *NOT* a part of the ODP implementation, despite its
location: it is a part of the test structure: that part
ed in the (now ancient) programming
> language PL/I. Pointers to BASED storage were stored as offsets and the
> compiler automatically handled the relative addressing. They are very
> convenient for this sort of purpose.
>
>>
>>
>> S23: agree with Bill's com
t;
> On Thu, Jun 9, 2016 at 9:01 AM, Christophe Milard
> <christophe.mil...@linaro.org> wrote:
>>
>> On 9 June 2016 at 14:30, Bill Fischofer <bill.fischo...@linaro.org> wrote:
>> >
>> >
>> > On Thu, Jun 9, 2016 at 7:13 AM, Christophe M
On 9 June 2016 at 14:30, Bill Fischofer <bill.fischo...@linaro.org> wrote:
>
>
> On Thu, Jun 9, 2016 at 7:13 AM, Christophe Milard
> <christophe.mil...@linaro.org> wrote:
>>
>> Bill:
>> S19: When you write:"These addresses are intended to be
at 14:11, Jerin Jacob <jerin.ja...@caviumnetworks.com> wrote:
> On Fri, Jun 03, 2016 at 11:15:43AM +0200, Christophe Milard wrote:
>> since V3: Update following Bill's comments
>> since V2: Update following Barry and Bill's comments
>> since V1: Update foll
On 7 June 2016 at 11:04, Xuelin Shi wrote:
> multi-thread, multi-queue and bi-directional forwarding.
>
> support (port, queue, core) arguments in cmdline.
> it means core will handle rx queue at port.
> forwarding logic will decide out port by this specification.
> if no
on cpu 1,2,3 again.) There could be theoriticaly complex such
dependency graphs where all cpus cannot be pinned from the beginning,
and where your approach seem too restrictive.
But I am glad to hear your voice on the arch call :-)
Christophe.
>
> Best Regards, Yi
>
>
> On 4 June 2016 a
on guide to form a platform specific guide.
>> The application guide is now ONLY the public specification.
>> The new platform guide includes the additional definitions specific to
>> odp-linux and it can contain platform specific notes and other
>> documentation as needed
in 2 different threads (for the same ODP object name), meaning
that the scope of the handle is actually the ODP thread.?
Thanks,
Christophe.
On 9 June 2016 at 14:54, Jerin Jacob <jerin.ja...@caviumnetworks.com> wrote:
> On Thu, Jun 09, 2016 at 02:13:49PM +0200, Christophe Milard wrote
since V3: Update following Bill's comments
since V2: Update following Barry and Bill's comments
since V1: Update following arch call 31 may 2016
This is a tentative to sum up the discussions around the thread/process
that have been happening these last weeks.
Sorry for the formalism of this mail,
On 26 May 2016 at 14:25, Yi He <yi...@linaro.org> wrote:
>
>
> On 26 May 2016 at 18:39, Christophe Milard <christophe.mil...@linaro.org>
> wrote:
>
>>
>>
>> On 26 May 2016 at 11:50, Yi He <yi...@linaro.org> wrote:
>>
>>>
Hi Yi,
installcheck fails.
I have not fully looked why, but if you run:
./bootstrap && ./configure --with-testdir=yes --enable-test-vald
--prefix=/home/linaro/INSTALL && make -j 8 && make install && make
installcheck
Before and after you changes, you'll see that the tests are not run properly.
I
Forwarded again to the list as the address I wrote was obviously wrong
(no change for those who already received a personnal copy)
-- Forwarded message --
From: Christophe Milard <christophe.mil...@linaro.org>
Date: 26 May 2016 at 17:11
Subject: thread/shmem discussion s
On 30 May 2016 at 11:23, Savolainen, Petri (Nokia - FI/Espoo) <
petri.savolai...@nokia.com> wrote:
>
>
> From: Christophe Milard [mailto:christophe.mil...@linaro.org]
> Sent: Friday, May 27, 2016 4:08 PM
> To: Savolainen, Petri (Nokia - FI/Espoo) <petri.savola
On 30 May 2016 at 14:12, Savolainen, Petri (Nokia - FI/Espoo)
<petri.savolai...@nokia.com> wrote:
>
>
>
> From: Christophe Milard [mailto:christophe.mil...@linaro.org]
> Sent: Monday, May 30, 2016 1:34 PM
> To: Savolainen, Petri (Nokia - FI/Espoo) <petri.sav
On 30 May 2016 at 15:44, Savolainen, Petri (Nokia - FI/Espoo) <
petri.savolai...@nokia.com> wrote:
>
>
>> -Original Message-
>> From: Christophe Milard [mailto:christophe.mil...@linaro.org]
>> Sent: Monday, May 30, 2016 3:52 PM
>> To: Savolainen, Pet
Why does it have to be visible in the API, Maxim? (even introducing a
specific prefix is really an API change, I think: Those app that happened
to use the prefix before will not work as before).
If IPC need its specific stuff, shouldn't it be using ODP internal
functions, e.g. _odp_pool_create()
The odph_odpthread_t (non opaque array of odpthread) is now replaced by a
single type odph_odpthread_tbl_t abstracted as a void*.
The table describing the odpthreads being created is now malloc'd and
freed by the helper function themselves.
Signed-off-by: Christophe Milard <christophe.
since V2: Update following Barry and Bill's comments
since V1: Update following arch call 31 may 2016
This is a tentative to sum up the discussions around the thread/process
that have been happening these last weeks.
Sorry for the formalism of this mail, but it seems we need accuracy here...
Maxim, maybe you can find a better title when merging :-)
Christophe.
On 26 May 2016 at 07:21, Yi He <yi...@linaro.org> wrote:
> Signed-off-by: Yi He <yi...@linaro.org>
>
Reviewed-by: Christophe Milard <christophe.mil...@linaro.org>
---
> platform/linux-gener
On 26 May 2016 at 07:39, Yi He wrote:
> Provide helper APIs to set and get cpu affinity in ODP threads,
> and set cpu affinity to the 1st available control cpu for all odp
> test/validation programs in odp_cunit_common library.
>
> Signed-off-by: Yi He
> ---
He <yi...@linaro.org>
>
Reviewed-by: Christophe Milard <christophe.mil...@linaro.org>
> ---
> helper/include/odp/helper/linux.h | 23 -
> helper/linux.c| 54
> helper/test/odpthreads.c | 83
>
h_odpthread_tbl_t to odph_odpthread_array_t? I feel
> table and array are different thing, but it is up to you :)
>
> thanks and best regards, Yi
>
> On 27 May 2016 at 00:27, Christophe Milard <christophe.mil...@linaro.org>
> wrote:
>
>> The odph_odpthread_t (non opaque a
The odph_odpthread_t (non opaque array of odpthread) is now replaced by a
single type odph_odpthread_tbl_t abstracted as a void*.
The table describing the odpthreads being created is now malloc'd and
freed by the helper function themselves.
Signed-off-by: Christophe Milard <christophe.
On 1 June 2016 at 02:08, Bill Fischofer <bill.fischo...@linaro.org> wrote:
> Thanks, Christophe, for this excellent summary. Comments inline.
>
> On Tue, May 31, 2016 at 11:00 AM, Christophe Milard
> <christophe.mil...@linaro.org> wrote:
>>
>> since V1: Up
re. J
>
>
>
> Thanx Barry.
>
>
>
>
>
> -Original Message-
> From: Christophe Milard [mailto:christophe.mil...@linaro.org]
> Sent: Tuesday, May 31, 2016 12:00 PM
> To: Petri Savolainen; Barry Spinney; Krishna Garapati; Mike Holmes; Bill
> Fischofer; LNG ODP Mailma
since V1: Update following arch call 31 may 2016
This is a tentative to sum up the discussions around the thread/process
that have been happening these last weeks.
Sorry for the formalism of this mail, but it seems we need accuracy here...
This summary is organized as follows:
It is a set of
On 2016-06-16 07:56, Yi He wrote:
> Move platform tests from odp/platform/linux-generic/test
> into test suite at odp/test/platform/linux-generic.
>
> Signed-off-by: Yi He
> ---
> v3 fixed missing validation tests in target 'installcheck' by
> lifting run-tests script to test/
On 17 June 2016 at 08:10, Yi He <yi...@linaro.org> wrote:
> Move platform tests from odp/platform/linux-generic/test
> into test suite at odp/test/platform/linux-generic.
>
> Signed-off-by: Yi He <yi...@linaro.org>
Reviewed-by: Christophe Milard <christophe.mil...@lina
On 2016-06-23 12:19, Bill Fischofer wrote:
> Clean up whitespace and line length issues with current doc.
>
> Signed-off-by: Bill Fischofer
> ---
> doc/implementers-guide/implementers-guide.adoc | 253
> -
> 1 file changed, 121 insertions(+),
On 21 June 2016 at 06:52, Yi He <yi...@linaro.org> wrote:
> Move platform tests from odp/platform/linux-generic/test
> into test suite at odp/test/platform/linux-generic.
>
> Signed-off-by: Yi He <yi...@linaro.org>
Reviewed-by: Christophe Milard <christophe.mil...@l
:
ODP_TEST_INFO_INACTIVE(send_failure)
Remarking the test as active later on is then only a matter of changing
back the macro name.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
test/validation/common/odp_cunit_common.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
Hi,
Today the situation as I see it, is as follows:
We have a single interface to ODP, the application interface, A.
This interface is defined by a file which any application includes:
include/odp.h
includes in turn a set of
platform//include/odp/.
These files are given a chance to define
On Tuesday's ARCH call, we will be discussing the above topic.
Nicolas (Kalray) will try to join, but he is very uncertain at this stage
(if he can be there)...
___
lng-odp mailing list
lng-odp@lists.linaro.org
This is regarding ODP 226 (Tests assuming pthreads)
Kalray is facing a problem actually larger than this thread vs process
problem:
The basic question is: when N processors share the same memory (shmem
object),
is it acceptable to force a cache update for the whole shmem'd area for N-1
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
doc/implementers-guide/implementers-guide.adoc | 21 +
1 file changed, 21 insertions(+)
diff --git a/doc/implementers-guide/implementers-guide.adoc
b/doc/implementers-guide/implementers-guide.adoc
:
ODP_TEST_INFO_INACTIVE(send_failure)
Remarking the test as active later on is then only a matter of changing
back the macro name.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
test/validation/common/odp_cunit_common.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
Documentation on conditional test is added here, as it seemed to be missing
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
doc/implementers-guide/implementers-guide.adoc | 29 ++
1 file changed, 29 insertions(+)
diff --git a/doc/implementers
hat I can see ODP_SHM_PROC relates to use MAP_ANONYMOUS
> vs shm_open(), so mainly publishes the name of the mapping (so other
> processes can use it) and I suspect that ODP_SHM_SW_ONLY relates to things
> like DMA cache-coherency (well, lack of)?
>
> ben
>
> On 01/18/2016 10:38
On 28 June 2016 at 00:40, Bill Fischofer wrote:
> Signed-off-by: Bill Fischofer
> ---
> v2: Incorporate comments from Mike and Petri
>
> CONTRIBUTING | 141
> +--
> 1 file changed, 137
On 2016-06-17 06:10, Yi He wrote:
> Move platform tests from odp/platform/linux-generic/test
> into test suite at odp/test/platform/linux-generic.
>
> Signed-off-by: Yi He
> ---
> v4 restore the invocation of general validation tests:
> The Validation tests HAVE to be called
ailures I did not encounter and would you like
> to send me a log in this case.
>
> thanks very much and best regards, Yi
>
>
>
> On 14 June 2016 at 21:38, Christophe Milard <christophe.mil...@linaro.org>
> wrote:
>>
>> Hi Yi,
>> installcheck fails.
>
can never happen due to num_ifaces always > 1 in our test.
> Add special check for that to make new gcc happy.
>
> Signed-off-by: Maxim Uvarov <maxim.uva...@linaro.org>
For api-next:
Reviewed-by: Christophe Milard <christophe.mil...@linaro.org>
> ---
> I can not repr
odp.h actually describes the applicatiion interface of ODP and is
logicaly moved to odp_api.h.
Applications now includes .
This simplifies the addition of other ODP interfaces (e.g. drivers may
include odp_drv.h in the future.)
Signed-off-by: Christophe Milard <christophe.mil...@linaro.
during this transition period.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
include/odp.h | 30 ++
platform/linux-generic/Makefile.am | 1 +
2 files changed, 31 insertions(+)
create mode 100644 include/odp.h
diff
during this transition period.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
include/odp.h | 23 +++
platform/linux-generic/Makefile.am | 1 +
2 files changed, 24 insertions(+)
create mode 100644 include/odp.h
diff --git a/include
Hi,
If I understand correctly, the usage of this flag tells that Non ODP
processes/thread can gain access to the shared memory.
My question is: through which interface?
- the ODP API? (which means that non ODP processes/thread could be linked
with the ODP lib and however remain non ODP)
- or the
401 - 500 of 1514 matches
Mail list logo