On 22 December 2016 at 21:40, Maxim Uvarov <maxim.uva...@linaro.org> wrote:
> On 12/19/16 13:50, Christophe Milard wrote:
>> The enumerator class, enumerator instance, devio and driver registration
>> functions prototypes (and a draft of their parameters) are
>> define
Stress tests for the random size allocator (buddy allocator in
linux-generic) are added here.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
.../common_plat/validation/drv/drvshmem/drvshmem.c | 177 +
.../common_plat/validation/drv/drvshmem/drvs
Basic tests for odpdrv_shm_pool are added here, creating a fixed size
pool and performing basic alloc/free on it
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
.../common_plat/validation/drv/drvshmem/drvshmem.c | 86 ++
.../common_plat/validati
Basic tests for odpdrv_shm_pool are added here, creating a buddy
pool and performing basic alloc/free on it
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
.../common_plat/validation/drv/drvshmem/drvshmem.c | 92 ++
.../common_plat/validation/drv/dr
_ishm now provides functions to create/destroy pools for buddy/slab
memory allocation, as well as functions to allocated/release memory
from the created pools.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/Makefile.am | 2 +
pl
Adding functions to create memory pools and allocate / free memory from
the created pools.
These functions calls their _ishm conterpart, of course.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/drv_shm.
is sharable
between ODP threads. (using malloc would not work when ODP threads
are linux processes).
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
include/odp/drv/spec/shm.h | 97 ++
.../linux-generic/include/odp/drv/plat/shm_types.
, drivers...
(PS:I guess this concept will be needed as well on the north (API) interface
when we start looking into having things working "in process mode")
Christophe Milard (6):
linux-gen: _ishm: adding buddy and slab allocation
drv: adding odpdrv_shm_pool functions
linux-gen: drv: s
should not call
> this function but leave it to the main application thread/process.
>
> Signed-off-by: Stanislaw Kardach <k...@semihalf.com>
Reviewed-by: Christophe Milard <christophe.mil...@linaro.org>
> ---
> helper/linux.c | 4
> 1 file changed, 4 deletion
Still the same:
Applying: helper: do not break odp_term_global protocol
error: patch failed: helper/linux.c:42
error: helper/linux.c: patch does not apply
Patch failed at 0001 helper: do not break odp_term_global protocol
The copy of the patch that failed is found in: .git/rebase-apply/patch
When
This seems a good correction. However I get the following when
applying this patch:
git am
~/incoming/lng-odp_PATCH_helper_do_not_break_odp_term_global_protocol.mbox
Applying: helper: do not break odp_term_global protocol
error: patch failed: helper/linux.c:42
error: helper/linux.c: patch does
Ok. thx
On 27 December 2016 at 16:21, Maxim Uvarov <maxim.uva...@linaro.org> wrote:
> I merged it with my review.
>
> Maxim.
>
> On 27 December 2016 at 17:57, Christophe Milard
> <christophe.mil...@linaro.org> wrote:
>>
>> It needs revi
>
> On 12/21/16 14:11, Christophe Milard wrote:
>> The size of the shared memory and its user flag set, as given at reserve
>> time, are exported and imported so that odp_shm_info() return proper
>> values on imported blocks
>>
>> Signed-off-by: Christophe Milard <chr
On 27 December 2016 at 09:58, Savolainen, Petri (Nokia - FI/Espoo)
<petri.savolai...@nokia-bell-labs.com> wrote:
>
>
>> -Original Message-
>> From: Christophe Milard [mailto:christophe.mil...@linaro.org]
>> Sent: Friday, December 23, 2016 3:36 PM
>> To:
On 23 December 2016 at 09:15, Savolainen, Petri (Nokia - FI/Espoo)
<petri.savolai...@nokia-bell-labs.com> wrote:
>
>
>> -Original Message-
>> From: Christophe Milard [mailto:christophe.mil...@linaro.org]
>> Sent: Thursday, December 22, 2016 3:13 PM
>&g
revert to HTML from
time to time.
>
>
>
> From: Christophe Milard [mailto:christophe.mil...@linaro.org]
> Sent: Thursday, December 22, 2016 11:24 AM
> To: Savolainen, Petri (Nokia - FI/Espoo)
> <petri.savolai...@nokia-bell-labs.com>; Mike Holmes <mike.hol..
Hi,
I am trying to sum up what was said at the arch call yesterday, regarding
memory allocation to figure out how to rewrite my "buddy allocator for drv
interface" patch series.
- Some voices seemed to say that a single allocation would be best,
regardless of the size being allocated (mostly at
Fixing a set of iritating typos. just in comments.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
Since V1:
another typo found by Bill
platform/linux-generic/_ishm.c | 24
1 file changed, 12 insertions(+), 12 deletions(-)
diff
stress tests added for allocation of small memory units using
odpdrv_shm_sreserve() and odpdrv_shm_sfree().
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
.../common_plat/validation/drv/drvshmem/drvshmem.c | 164 +
.../common_plat/validation/drv/dr
Tests for odpdrv_shm_sreserve() and odpdrv_shm_sfree are added,
testing the ishm small memory unit allocator.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
.../common_plat/validation/drv/drvshmem/drvshmem.c | 77 ++
.../common_plat/validati
as process case)
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/drv_shm.c | 44 +-
.../linux-generic/include/odp_config_internal.h| 10 +
platform/linux-generic/include/odp_internal.h | 4 ++
platform
_ishm now provides a function to create a pool for buddy memory allocation,
as well as functions to allocated/release memory from the created pool.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/Makefile.am | 2 +
platform
The two functions are meant to be used fo small amount of memory
allocation.
They are quicker, lighter and have a smaller granularity than the
odpdrv_shm_reserve() / odpdrv_shm_free_*() sets of function, but also
lacks some of their functionality (lookup, export, flags).
Signed-off-by: Christophe
it for building list of things such as
enumerators, devio, drivers...
(PS:I guess this concept will be needed as well on the north (API) interface
when we start looking into having things working "in process mode")
Christophe Milard (5):
linux-gen: _ishm: adding buddy allocation
d
Fixing a set of iritating typos. just in comments.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/_ishm.c | 24
1 file changed, 12 insertions(+), 12 deletions(-)
diff --git a/platform/linux-generic/_ishm.c b/platform
Checking that the block size returned by odp_shm_info() matches
the exported block length.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
test/linux-generic/validation/api/shmem/shmem_odp2.c | 8
1 file changed, 8 insertions(+)
diff --git a/test/linux-g
The size of the shared memory and its user flag set, as given at reserve
time, are exported and imported so that odp_shm_info() return proper
values on imported blocks
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/_ishm.c
Ping.
I think this patch would ease cleaning up the Huge pages. If reviewed, it
is candidate for "next" and master.
Christophe.
On 6 December 2016 at 18:25, Christophe Milard <christophe.mil...@linaro.org
> wrote:
> _ishm now unlinks the created files as soon as possi
stress tests added for allocation of small memory units using
odpdrv_shm_sreserve() and odpdrv_shm_sfree().
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
.../common_plat/validation/drv/drvshmem/drvshmem.c | 164 +
.../common_plat/validation/drv/dr
Tests for odpdrv_shm_sreserve() and odpdrv_shm_sfree are added,
testing the ishm small memory unit allocator.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
.../common_plat/validation/drv/drvshmem/drvshmem.c | 77 ++
.../common_plat/validati
_ishm now provides a function to create a pool for buddy memory allocation,
as well as functions to allocated/release memory from the created pool.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/Makefile.am | 2 +
platform
The two functions are meant to be used fo small amount of memory
allocation.
They are quicker, lighter and have a smaller granularity than the
odpdrv_shm_reserve() / odpdrv_shm_free_*() sets of function, but also
lacks some of their functionality (lookup, export, flags).
Signed-off-by: Christophe
as process case)
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/drv_shm.c | 44 +-
.../linux-generic/include/odp_config_internal.h| 10 +
platform/linux-generic/include/odp_internal.h | 4 ++
platform
it for building list of things such as
enumerators, devio, drivers...
(PS:I guess this concept will be needed as well on the north (API) interface
when we start looking into having things working "in process mode")
Christophe Milard (5):
linux-gen: _ishm: adding buddy allocation
d
(not using make check) may be affected
by configuration files. Setting ODP_SYSCONFIG_FILE to an appropriate value
(possibly "none") may be required.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
test/Makefile.inc | 4 +++-
1 file changed, 3 insertions(+),
The shared objects listed in the ODP configuration files are
loaded at init time. The odp configuration file list the
shared objects to be loaded as shown in the following example:
module = {
modules = ["enumerator1.so", "driver1.so"];
};
Signed-off-by: Christophe Mi
The parsing of the odp.conf configuration file is added.
The file is searched first in the local directory (.) and
then is the $prefix/etc directory.
This requires libconfig (sudo apt-get install libconfig-dev)
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
DEPEND
The linux implementation for the enumerator class registration function,
enumerator instance registration function,
devio and driver registration functions (stub)
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
include/odp_drv.h | 1 +
pl
int an error message).
odp_driver_register() is of course part of the driver interface (south).
Christophe Milard (5):
drv: adding driver registration interface (stub)
linux-gen: adding enum, devio and driver registration interface (stub)
linux-gen: init: adding configuration file parsing
test:
The enumerator class, enumerator instance, devio and driver registration
functions prototypes (and a draft of their parameters) are
defined, the goal being to define the registration framework only.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
include/odp/drv/spec/dr
, Yi
>
> On 8 December 2016 at 17:20, Christophe Milard <
> christophe.mil...@linaro.org> wrote:
>
>> The enumerator class, enumerator instance, devio and driver registration
>> functions prototypes (and a draft of their parameters) are
>> defined, the g
;>
>>
>> On 8 December 2016 at 17:20, Christophe Milard <
>> christophe.mil...@linaro.org> wrote:
>>
>>> The linux implementation for the enumerator class registration function,
>>> enumerator instance registration function,
>>>
...continued first part got sent for some reason...
-should a size be given on import (for a check)
On 15 December 2016 at 14:05, Christophe Milard <
christophe.mil...@linaro.org> wrote:
> I guess Petri is God when it comes to API:
> questions are:
> - should the size ret
I guess Petri is God when it comes to API:
questions are:
- should the size return as a result of the shm_get_info be the real size
or just the requested size?
On 15 December 2016 at 13:54, Maxim Uvarov <maxim.uva...@linaro.org> wrote:
> On 12/15/16 10:47, Christophe Mil
On 14 December 2016 at 20:33, Maxim Uvarov wrote:
> Size might be not passed to that function if is is read
> from file. But it has to be set to provide valid number
> in odp_shm_info().
>
> Signed-off-by: Maxim Uvarov
> ---
>
the problems that follows)
Chrstophe
On 13 December 2016 at 09:01, Nicolas Morey-Chaisemartin <nmo...@kalray.eu>
wrote:
>
>
> Le 12/13/2016 à 08:46 AM, Christophe Milard a écrit :
> > On 12 December 2016 at 15:52, Mike Holmes <mike.hol...@linaro.org>
> wrote:
>
On 12 December 2016 at 15:52, Mike Holmes wrote:
> Signed-off-by: Mike Holmes
> ---
> configure.ac | 14 ++
> helper/Makefile.am | 2 +-
> 2 files changed, 15 insertions(+), 1 deletion(-)
>
> diff --git a/configure.ac
On 12 December 2016 at 15:52, Mike Holmes wrote:
> Signed-off-by: Mike Holmes
> ---
> configure.ac | 4 ++--
> platform/linux-generic/m4/configure.m4 | 2 ++
> 2 files changed, 4 insertions(+), 2 deletions(-)
>
> diff
they were old test for linux only. process and thread omplementation of odp
threads are tested in odpthread.c
On 12 December 2016 at 19:51, Maxim Uvarov <maxim.uva...@linaro.org> wrote:
> On 12/12/16 21:08, Christophe Milard wrote:
> > Why that question? The files are deleted,
the
result of a long series of trial and errors with autotools.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
Note: must be applied on top of:
[API-NEXT PATCHv4 0/5] driver initialisation framework
Since V2: includes a needed change for V4 of "driver initialisation frame
the
result of a long series of trial and errors with autotools.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
Note: must be applied on top of:
[API-NEXT PATCHv4 0/5] driver initialisation framework
Since V1: updates for V4 of "driver initialisation framework"
The shared objects listed in the ODP configuration files are
loaded at init time. The odp configuration file list the
shared objects to be loaded as shown in the following example:
module = {
modules = ["enumerator1.so", "driver1.so"];
};
Signed-off-by: Christophe Mi
The parsing of the odp.conf configuration file is added.
The file is searched first in the local directory (.) and
then is the $prefix/etc directory.
This requires libconfig (sudo apt-get install libconfig-dev)
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
DEPEND
(not using make check) may be affected
by configuration files. Setting ODP_SYSCONFIG_FILE to an appropriate value
(possibly "none") may be required.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
test/Makefile.inc | 4 +++-
1 file changed, 3 insertions(+),
parate patch as many questions remains.
-All libdl tests removed: libdl is assumed to always be on linux (Maxim)
Since V1:
-enum names prefixed by ODPDRV (Yi)
-better commit message for last patch (Christophe)
-typo fix (Christophe)
Christophe Milard (5):
drv: adding driver registration inte
The linux implementation for the enumerator class registration function,
enumerator instance registration function,
devio and driver registration functions (stub)
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
include/odp_drv.h | 1 +
pl
The enumerator class, enumerator instance, devio and driver registration
functions prototypes (and a draft of their parameters) are
defined, the goal being to define the registration framework only.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
include/odp/drv/spec/dr
Ooops Clang. forgot this one will go through this. thanks...
On 7 December 2016 at 13:21, Bill Fischofer <bill.fischo...@linaro.org>
wrote:
> On Wed, Dec 7, 2016 at 1:19 AM, Christophe Milard
> <christophe.mil...@linaro.org> wrote:
> >
> > On 7 December
n extra dependency is
added?
Thanks for your attention,
Christophe
> On Tue, Dec 6, 2016 at 8:23 AM, Christophe Milard
> <christophe.mil...@linaro.org> wrote:
> > Since V2:
> > -function odp_load_driver removed. replaced by config file. (Petri, FF)
> > -configur
On 6 December 2016 at 15:28, Nicolas Morey-Chaisemartin
wrote:
> As a side effect, debug print are turned off by default
>
> Signed-off-by: Nicolas Morey-Chaisemartin
> ---
> configure.ac | 14 ++
> helper/Makefile.am | 3 ++-
> 2 files
_ODP_ISHM_EXPORT),
whose names shall be seen in the file system.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
Since V1:
-flag size reduced to 1 bit (maxim)
-typo fix (Maxim)
platform/linux-generic/_ishm.c | 14 --
1 file changed, 12 insertions
the
result of a long series of trial and errors with autotools.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
Note: must be applied on top of:
[API-NEXT PATCHv3 0/5] driver initialisation framework
Is this good enough to go in the test structure?
I assumed this is
The shared objects listed in the ODP configuration files are
loaded at init time. The odp configuration file list the
shared objects to be loaded as shown in the following example:
module = {
modules = ["enumerator1.so", "driver1.so"];
};
Signed-off-by: Christophe Mi
(not using make check) may be affected
by configuration files. Setting ODP_SYSCONFIG_FILE to an appropriate value
(possibly "none") may be required.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
test/Makefile.inc | 4 +++-
1 file changed, 3 insertions(+),
odp_driver_register() is of course part of the driver interface (south).
Christophe Milard (5):
drv: adding driver registration interface (stub)
linux-gen: adding enum, devio and driver registration interface (stub)
linux-gen: init: adding configuration file parsing
test: preventing odp.co
The enumerator class, enumerator instance, devio and driver registration
functions prototypes (and a draft of their parameters) are
defined, the goal being to define the registration framework only.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
include/odp/drv/spec/dr
The linux implementation for the enumerator class registration function,
enumerator instance registration function,
devio and driver registration functions (stub)
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
include/odp_drv.h | 1 +
pl
The _ishm flag _ODP_ISHM_LOCK is no longer set when doing shm_reserve(),
hence enabling non-root user to exceed the 64MB mlock memory limit
(ulimit).
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/odp_shared_memory.c | 3 ---
1 file chan
If you want to re-open that question, schedule it ay tomorrow (tuesday)
arch call, as I won't be bale to attend neither the arch call nor the sync
call today due to conflicting compulsory ericsson meetings.
Thanks,
Christophe
On 4 December 2016 at 12:39, Christophe Milard <christophe.
The original patch set had a flag for mlock . Petri requested mlock for
any allocation . I mentioned the ulimit issue at the arch call if I
remember right. I still have a flag on the south API.
On 3 Dec 2016 20:24, "Maxim Uvarov" wrote:
> Hello Christophe,
>
> Found
_ODP_ISHM_EXPORT),
whose names shall be seen in the file system.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/_ishm.c | 14 --
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/platform/linux-generic/_ishm.c b/platform/linux-g
Savolainen <petri.savolai...@nokia.com>
>
>
>> -----Original Message-
>> From: Christophe Milard [mailto:christophe.mil...@linaro.org]
>> Sent: Tuesday, November 29, 2016 4:46 PM
>> To: maxim.uva...@linaro.com; Savolainen, Petri (Nokia - FI/Espoo)
>> <petri
ping
This should be straightforward to review and would help (partly) avoiding
hanging processes when killing ODP (e.g. ctrl-C)
Thanks
On 2016-11-25 15:39, Christophe Milard wrote:
> _fdserver now request SIGTERM if parent process (ODP instantiation
> process) dies, hence avoiding it to
On 29 November 2016 at 20:00, Francois Ozog <francois.o...@linaro.org>
wrote:
>
>
> On 29 November 2016 at 19:03, Christophe Milard <
> christophe.mil...@linaro.org> wrote:
>
>>
>>
>> On 29 November 2016 at 18:13, Francois Ozog <francois.o...@lin
On 29 November 2016 at 18:13, Francois Ozog <francois.o...@linaro.org>
wrote:
>
>
> On 29 November 2016 at 16:44, Christophe Milard <
> christophe.mil...@linaro.org> wrote:
>
>>
>>
>> On 29 November 2016 at 13:22, Francois Ozog <francois.o...@l
On 29 November 2016 at 13:22, Francois Ozog <francois.o...@linaro.org>
wrote:
> Hi,
>
> comments inline
>
> On 29 November 2016 at 10:58, Christophe Milard <
> christophe.mil...@linaro.org> wrote:
>
>> Hi,
>>
>> In our last meeting, yesterday, w
The test trying to free a unallocated address is now erroneous since
ODP is using ishm too: unknown drvshm addresses may well be valid ODP
addresses, in which case the test frees someone else memory!
The test is simply suppressed.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.
Hi,
In our last meeting, yesterday, we agreed on the following objects:
1) enumerator class
2) enumerator
3) enumerated_device
4) devio
5) driver
and to come: pktio_interface...
At registration time, the driver have to tell:
- The enumerator class it expects devices from (string E)
- The devio
Both term function were missing for the ODP main process.
Added here.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
test/common_plat/performance/odp_pktio_perf.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/test/common_plat/performance/odp_pktio_perf.c
is the best,
If you have better approach, please suggest (better patch welcome!)
Christophe Milard (2):
linux-gen: packet_io: handling term_global while in CLOSE_PENDING
performance: odp_pktio_perf: adding missing term functions
platform/linux-generic/odp_packet_io.c| 6 --
test
ping
On 9 November 2016 at 14:28, Bill Fischofer <bill.fischo...@linaro.org> wrote:
> For this series:
>
> Reviewed-by: Bill Fischofer <bill.fischo...@linaro.org>
>
> On Tue, Nov 8, 2016 at 3:49 AM, Christophe Milard
> <christophe.mil...@linaro.org> wrote
_fdserver now request SIGTERM if parent process (ODP instantiation
process) dies, hence avoiding it to become orphan and reattached to the
init process.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/_fdserver.c | 6 ++
1 file changed, 6 inse
Please ignore: this is meant for API-NEXt!: sending a new one!
On 25 November 2016 at 15:01, Christophe Milard
<christophe.mil...@linaro.org> wrote:
> _fdserver now request SIGTERM if parent process (ODP instantiation
> process) dies, hence avoiding it to become orphan an
_fdserver now request SIGTERM if parent process (ODP instantiation
process) dies, hence avoiding it to become orphan and reattached to the
init process.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/_fdserver.c | 6 ++
1 file changed, 6 inse
uva...@linaro.org> wrote:
> I forgot to say that I see back ground process only after make check. And
> run single process works.
>
> On 25 November 2016 at 12:23, Christophe Milard
> <christophe.mil...@linaro.org> wrote:
>>
>> On 24 November 2016 at 21:07, Maxim Uv
andle_request():drop {ctx=1, key=11}->fd=16
_fdserver.c:321:_odp_fdserver_deregister_fd():FD client deregister:
pid=7625 key=8
_fdserver.c:513:handle_request():drop {ctx=1, key=8}->fd=13
erachmi@erachmi-ericsson:~/linaro/ODP/odp$
>
> On 11/24/16 19:22, Christophe Milard wrote:
>>
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
doc/users-guide/users-guide.adoc | 68 ++--
1 file changed, 66 insertions(+), 2 deletions(-)
diff --git a/doc/users-guide/users-guide.adoc b/doc/users-guide/users-guide.adoc
index 6
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/_ishm.c | 22 --
1 file changed, 16 insertions(+), 6 deletions(-)
diff --git a/platform/linux-generic/_ishm.c b/platform/linux-generic/_ishm.c
index b00f8f1..7d9c213
Remaining (forgotten, not freed) blocks are gathered and related files
cleaned when odp_term_global() is called. An error message is also issued
so the application writters get to know about these blocks
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-g
e test procedure.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
test/linux-generic/validation/api/shmem/.gitignore | 3 +-
.../linux-generic/validation/api/shmem/Makefile.am | 22 ++--
.../validation/api/shmem/shmem_linux.c | 140 +++--
.
Implemented by calling the related functions from _ishm.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/odp_shared_memory.c | 31 +++---
1 file changed, 28 insertions(+), 3 deletions(-)
diff --git a/platform/linux-g
ing
trying to provoque race conditions. The new shmem tests do not assume
pthreads any longer and are runnable in process mode.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
test/common_plat/validation/api/shmem/shmem.c | 687 --
test/common_plat/vali
-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/_ishm.c | 160 +++-
platform/linux-generic/include/_ishm_internal.h | 5 +
2 files changed, 136 insertions(+), 29 deletions(-)
diff --git a/platform/linux-generic/_ishm.c b/platform
at odp_shm_reserve() time
the memory block becomes visible to other ODP instances.
The function odp_shm_import() is added: this function enables to
reserve block of memories exported by other ODP instances (using the
ODP_SHM_EXPORT flag).
Signed-off-by: Christophe Milard <christophe.mil...@linaro.
This flag guarentess the unicity the the block address on all ODP threads.
The patch just exposes the _ODP_ISHM_SINGLE_VA flag of the internal memory
allocator, ishm.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/odp_shared_memory.c | 1 +
long as we have the current IPC,
removing the file would break compilation.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/include/odp_shm_internal.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/platform/linux
-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/include/odp_internal.h | 5 -
platform/linux-generic/odp_init.c | 19 -
platform/linux-generic/odp_shared_memory.c | 406 ++---
.../validation/api/shmem/shmem_l
for the main process, hence making the ishm_reserve()
and ishm_free() functions available at init_global/term_global time.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/_ishm.c | 189 +
1 file change
ying block attributes.
This file is meant to be used by processes external to ODP willing to
share this memory.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/_ishm.c | 74 ++---
platform/linux-generic/include/_ishm_inte
as the PID is unique and
therefore, there cannot be another ODP instance with the same PID.
This patch does this cleanup at startup.
Signed-off-by: Christophe Milard <christophe.mil...@linaro.org>
---
platform/linux-generic/odp_init.c | 60 +++
1 file change
201 - 300 of 1514 matches
Mail list logo