[lng-odp] [API-NEXT PATCHv9 00/15] using _ishm as north API mem allocator

ocator that broke ODP instance scoping. I don't think this should be kept. I have included in this patch series a function to share memory between designated ODP instances. If we want to have IPC, it should use that. Christophe Milard (15): linux-gen: _ishm: fix for alignment request matching page si

[lng-odp] [API-NEXT PATCHv9 01/15] linux-gen: _ishm: fix for alignment request matching page size

There is no reason to toggle the _ODP_ISHM_SINGLE_VA flag when the alignment exactly matches the page size. This just results in wasting the odp-common virtual space Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- platform/linux-generic/_ishm.c | 4 ++-- 1 file chan

Re: [lng-odp] [API-NEXT PATCHv8 02/15] linux-gen: init: removing possible obsolete ODP files at startup

On 24 November 2016 at 15:36, Maxim Uvarov <maxim.uva...@linaro.org> wrote: > On 11/24/16 11:24, Christophe Milard wrote: >> >> When an ODP program is killed, some odp files may remain in /tmp and >> the huge page mount point. As signal KILL cannot be caught, ther

[lng-odp] [API-NEXT PATCHv8 15/15] doc: updating docs for the shm interface extension

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

[lng-odp] [API-NEXT PATCHv8 12/15] test: linux-gen: api: shmem: test sharing memory between ODP instances

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 +++-- .

[lng-odp] [API-NEXT PATCHv8 14/15] linux_gen: _ishm: decreasing the number of error messages when no huge pages

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

[lng-odp] [API-NEXT PATCHv8 13/15] linux-gen: _ishm: cleaning remaining block at odp_term_global

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

[lng-odp] [API-NEXT PATCHv8 10/15] linux-gen: _ishm: adding function to map memory from other ODP

-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

[lng-odp] [API-NEXT PATCHv8 11/15] linux-gen: shm: add flag and function to share memory between ODP instances

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

[lng-odp] [API-NEXT PATCHv8 09/15] test: api: shmem: new proper tests for shm API

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

[lng-odp] [API-NEXT PATCHv8 08/15] linux-gen: shm: new ODP_SHM_SINGLE_VA flag implementation

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 +

[lng-odp] [API-NEXT PATCHv8 07/15] api: shm: add flags to shm_reserve and function to find external mem

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.

[lng-odp] [API-NEXT PATCHv8 05/15] linux-gen: use ishm as north API mem allocator

-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

[lng-odp] [API-NEXT PATCHv8 06/15] linux-gen: push internal flag definition

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

[lng-odp] [API-NEXT PATCHv8 04/15] linux-gen: _ishm: allow memory alloc/free at global init/term

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

[lng-odp] [API-NEXT PATCHv8 03/15] linux-gen: _ishm: create description file for external memory sharing

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

[lng-odp] [API-NEXT PATCHv8 02/15] linux-gen: init: removing possible obsolete ODP files at startup

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 | 51 +++ 1 file change

[lng-odp] [API-NEXT PATCHv8 01/15] linux-gen: _ishm: fix for alignment request matching page size

There is no reason to toggle the _ODP_ISHM_SINGLE_VA flag when the alignment exactely matches the page size. This just results in wasting the odp-common virtual space Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- platform/linux-generic/_ishm.c | 4 ++-- 1 file chan

[lng-odp] [API-NEXT PATCHv8 00/15] using _ishm as north API mem allocator

tween designated ODP instances. If we want to have IPC, it should use that. Christophe Milard (15): linux-gen: _ishm: fix for alignment request matching page size linux-gen: init: removing possible obsolete ODP files at startup linux-gen: _ishm: create description file for external memory sha

Re: [lng-odp] [API-NEXT PATCHv7 00/13] using _ishm as north API mem allocator

On 23 November 2016 at 07:32, Christophe Milard <christophe.mil...@linaro.org> wrote: > On 22 November 2016 at 21:18, Maxim Uvarov <maxim.uva...@linaro.org> wrote: >> On 11/22/16 22:07, Christophe Milard wrote: >>> >>> On 22 November 2016 at 16:05, Maxim Uva

Re: [lng-odp] [API-NEXT PATCHv7 00/13] using _ishm as north API mem allocator

On 22 November 2016 at 21:18, Maxim Uvarov <maxim.uva...@linaro.org> wrote: > On 11/22/16 22:07, Christophe Milard wrote: >> >> On 22 November 2016 at 16:05, Maxim Uvarov <maxim.uva...@linaro.org> >> wrote: >>> >>> Christophe, >>>

Re: [lng-odp] [API-NEXT PATCHv7 00/13] using _ishm as north API mem allocator

pages allocation. Sorry, I don't really understand what you mean... > > regards, > Maxim. > > > > On 11/21/16 16:29, Christophe Milard wrote: >> >> ping >> >> On 17 November 2016 at 16:46, Christophe Milard >> <christophe.mil...@linaro.org>

Re: [lng-odp] [API-NEXT PATCHv7 00/13] using _ishm as north API mem allocator

ping On 17 November 2016 at 16:46, Christophe Milard <christophe.mil...@linaro.org> wrote: > since v6: > - All points according to Petri's request i.e.: > Odp_shm_find_external() changed again: now odp_shm_import(). > Function description updated. > >

[lng-odp] enumerator and driver registration

Here follows a first draft of what the API around this topic could be. A few comments: -The part concerning the enumerator registration and the driver registration could well be separated in different files. Nevertheless I think they should both be part of the same south interface (odpdrv_*):

[lng-odp] [API-NEXT PATCHv7 08/13] linux-gen: _ishm: adding function to map memory from other ODP

-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

[lng-odp] [API-NEXT PATCHv7 11/13] linux-gen: _ishm: cleaning remaining block at odp_term_global

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

[lng-odp] [API-NEXT PATCHv7 10/13] test: linux-gen: api: shmem: test sharing memory between ODP instances

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 +++-- .

[lng-odp] [API-NEXT PATCHv7 13/13] doc: updating docs for the shm interface extension

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

[lng-odp] [API-NEXT PATCHv7 07/13] test: api: shmem: new proper tests for shm API

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

[lng-odp] [API-NEXT PATCHv7 12/13] linux_gen: _ishm: decreasing the number of error messages when no huge pages

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 0586a96..782c32f

[lng-odp] [API-NEXT PATCHv7 09/13] linux-gen: shm: add flag and function to share memory between ODP instances

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

[lng-odp] [API-NEXT PATCHv7 03/13] linux-gen: use ishm as north API mem allocator

-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

[lng-odp] [API-NEXT PATCHv7 02/13] linux-gen: _ishm: allow memory alloc/free at global init/term

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

[lng-odp] [API-NEXT PATCHv7 05/13] api: shm: add flags to shm_reserve and function to find external mem

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.

[lng-odp] [API-NEXT PATCHv7 06/13] linux-gen: shm: new ODP_SHM_SINGLE_VA flag implementation

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 +

[lng-odp] [API-NEXT PATCHv7 04/13] linux-gen: Push internal flag definition

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

[lng-odp] [API-NEXT PATCHv7 01/13] linux-gen: _ishm: create description file for external memory sharing

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

[lng-odp] [API-NEXT PATCHv7 00/13] using _ishm as north API mem allocator

tances. If we want to have IPC, it should use that. Christophe Milard (13): linux-gen: _ishm: create description file for external memory sharing linux-gen: _ishm: allow memory alloc/free at global init/term linux-gen: use ishm as north API mem allocator linux-gen: Push internal flag de

Re: [lng-odp] [API-NEXT PATCHv2 3/5] api: init: driver load function added

<francois.o...@linaro.org> wrote: > Why not just scanning a directory or give a command line parameter? > > On 16 November 2016 at 12:05, Christophe Milard < > christophe.mil...@linaro.org> wrote: > >> So what? >> If we don't allow to load a driver

Re: [lng-odp] [API-NEXT PATCHv2 3/5] api: init: driver load function added

or on the platform (SoC). > It can be done as a PoC (that's what I do with virtio-net exploratiry > project) but that is not a long term solution. > > FF > > > Le mercredi 16 novembre 2016, Christophe Milard < > christophe.mil...@linaro.org> a écrit : > >> On

Re: [lng-odp] [API-NEXT PATCHv2 3/5] api: init: driver load function added

On 16 November 2016 at 10:07, Savolainen, Petri (Nokia - FI/Espoo) wrote: > >> /** >> + * Driver loading >> + * >> + * This function is used by the application to load NIC drivers into ODP. >> + * Calls to this function are optional, but should be performed

Re: [lng-odp] [API-NEXT PATCHv2 2/2] linux-gen: _ishmphy: adding debug function for pysical address mapping

On 14 November 2016 at 06:02, Yi He <yi...@linaro.org> wrote: > One comment inline: > > On 11 November 2016 at 22:50, Christophe Milard > <christophe.mil...@linaro.org> wrote: >> >> _odp_ishmphy_memmap_print() prints the virtual to physical address >&

Re: [lng-odp] [API-NEXT PATCHv2 1/2] linux-gen: _ishmphy: adding function for physical address query

to the _ishm _ODP_ISHM_LOCK flag. Christophe On 14 November 2016 at 06:00, Yi He <yi...@linaro.org> wrote: > One comment inline: > > On 11 November 2016 at 22:50, Christophe Milard > <christophe.mil...@linaro.org> wrote: >> >> The function _odp_ishmphy_virt_to_p

Re: [lng-odp] virtio and vhost support in ODP

in the hypervisor and intercepting the VM's > traffic directly into hypervisor's user-space. > > I was wondering which of the 2 you are implementing The target is: The driver side: virtio-net Christophe > Thanks > > Yehuda > > >> -Original Message- >> From:

[lng-odp] [API-NEXT PATCHv2 3/3] test: drv: shm: adding test for physical address queries

Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- .../common_plat/validation/drv/drvshmem/drvshmem.c | 37 ++ .../common_plat/validation/drv/drvshmem/drvshmem.h | 1 + 2 files changed, 38 insertions(+) diff --git a/test/common_plat/validation/drv/dr

[lng-odp] [API-NEXT PATCHv2 2/3] linux-gen: drv: functions to query for physical addresses

The capability "phys_addr" is introduced and tells whether physical address queries are available. The function odpdrv_virt_to_phys() is added to query for physical address (from virtual address) Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- platform/linux-g

[lng-odp] [API-NEXT PATCHv2 0/3] physical address query on DRV interface

NOTE: Must be applied on top of "getting physical addresses from _ishmphy", V2 since V1: -name changes (Maxim, Francois) -comments errors (Maxim) Brings the physical address query functions on the driver interface. Christophe Milard (3): drv: shm: function to query fo

[lng-odp] [API-NEXT PATCHv2 1/3] drv: shm: function to query for physical addresses

The capability "phys_addr" is introduced and tells whether physical address queries are available. The function odpdrv_virt_to_phys() is added to query for physical address (from virtual address) Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- include/odp/drv

[lng-odp] [API-NEXT PATCHv2 2/2] linux-gen: _ishmphy: adding debug function for pysical address mapping

_odp_ishmphy_memmap_print() prints the virtual to physical address mapping of some memory region (defined by virtuall address + length). Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- platform/linux-generic/_ishmphy.c | 58 ++ pl

[lng-odp] [API-NEXT PATCHv2 1/2] linux-gen: _ishmphy: adding function for physical address query

added, return true if _odp_ishmphy_virt_to_phys() is able to works (as it requires specific permission) Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- platform/linux-generic/_ishmphy.c | 82 ++ platform/linux-generic/include/_ishmphy_inte

Re: [lng-odp] [API-NEXT PATCH 1/3] drv: shm: function to query for physical addresses

On 10 November 2016 at 20:05, Maxim Uvarov <maxim.uva...@linaro.org> wrote: > On 11/10/16 20:21, Christophe Milard wrote: >> >> The capability "can_getphy" is introduced and tells whether physical >> address queries are available. >> The function odp

Re: [lng-odp] continuous memory allocation for drivers

On 10 November 2016 at 12:52, Christophe Milard > <christophe.mil...@linaro.org> wrote: >> >> Hi, >> >> My hope was that packet segments would all be smaller than one page >> (either normal pages or huge pages) to guarantee physical memory >> conti

[lng-odp] continuous memory allocation for drivers

Hi, My hope was that packet segments would all be smaller than one page (either normal pages or huge pages) to guarantee physical memory continuity which is needed by some drivers (read non vfio drivers for PCI). Francois Ozog's experience (with dpdk)shows that this hope will fail in some case:

[lng-odp] [API-NEXT PATCH 2/3] linux-gen: drv: functions to query for physical addresses

The capability "can_getphy" is introduced and tells whether physical address queries are available. The function odpdrv_getphy() is added to query for physical address (from virtual address) Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- platform/linux-g

[lng-odp] [API-NEXT PATCH 3/3] test: drv: shm: adding test for physical address queries

Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- .../common_plat/validation/drv/drvshmem/drvshmem.c | 37 ++ .../common_plat/validation/drv/drvshmem/drvshmem.h | 1 + 2 files changed, 38 insertions(+) diff --git a/test/common_plat/validation/drv/dr

[lng-odp] [API-NEXT PATCH 1/3] drv: shm: function to query for physical addresses

The capability "can_getphy" is introduced and tells whether physical address queries are available. The function odpdrv_getphy() is added to query for physical address (from virtual address) Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- include/odp/drv

[lng-odp] [API-NEXT PATCH 0/3] physical address query on DRV interface

NOTE: Must be applied on top of "getting physical addresses from _ishmphy" Brings the physical address query functions on the driver interface. Christophe Milard (3): drv: shm: function to query for physical addresses linux-gen: drv: functions to query for physical addresses test

Re: [lng-odp] driver interface thinkings....

ects in ODP > odp_pktio_t is somewhat corresponding to a port "driver". it does properly > adapts to a device with multiple ports. > Not sure of the match when you started talking about the embeded switches... Christophe. > > FF > > > > > > On 7 Novembe

Re: [lng-odp] [API-NEXT PATCHv2 4/5] linux-gen: implementation of odp_load_driver function

On 8 November 2016 at 15:24, Maxim Uvarov <maxim.uva...@linaro.org> wrote: > On 11/08/16 17:15, Christophe Milard wrote: >> >> On 8 November 2016 at 15:06, Maxim Uvarov <maxim.uva...@linaro.org> wrote: >>> >>> are there any system for linux-generic plat

Re: [lng-odp] [API-NEXT PATCHv2 4/5] linux-gen: implementation of odp_load_driver function

ot sure I agree with this really,... Any other voices? > > Maxim. > > > > On 11/07/16 14:15, Christophe Milard wrote: >> >> Implementation of the driver loading function, of north API >> >> Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> >

Re: [lng-odp] [API-NEXT PATCHv2 3/5] api: init: driver load function added

On 8 November 2016 at 14:56, Maxim Uvarov <maxim.uva...@linaro.org> wrote: > On 11/07/16 14:15, Christophe Milard wrote: >> >> Function added on the north API to load drivers. >> >> Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> >&

[lng-odp] [API-NEXT PATCH 3/3] doc: shm: defining behaviour when blocks have same name

Defining the reserve and lookup behaviour when multiple blocks are reserved using the same name. Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- doc/users-guide/users-guide.adoc | 8 ++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/doc/users-guide

[lng-odp] [API-NEXT PATCH 2/3] test: api: shm: test using the same block name multiple times

Make sure that many memory blocks can be created with the name. Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- test/common_plat/validation/api/shmem/shmem.c | 9 + 1 file changed, 9 insertions(+) diff --git a/test/common_plat/validation/api/shmem/shmem.c

[lng-odp] [API-NEXT PATCH 1/3] linux-gen: _ishm: accept multiple usage of same block name

This is following the request that using the same name for multiple memory blocks should be allowed on north API. The change made here will affect any _ishm users (i.e. both north and south API), which is probably better for consistency. Signed-off-by: Christophe Milard <christophe.

[lng-odp] [API-NEXT PATCH 0/3] _ishm: multiple blocks using identical names

being used multiple times. Christophe Milard (3): linux-gen: _ishm: accept multiple usage of same block name test: api: shm: test using the same block name multiple times doc: shm: defining behaviour when blocks have same name doc/users-guide/users-guide.adoc | 8 ++-- plat

[lng-odp] driver interface thinkings....

Bonsoir Francois, I'll take that in English thereafter so that other can read (copy to the list). I have looked at that: https://dpdksummit.com/Archive/pdf/2016Userspace/Day02-Session03-ShreyanshJain-Userspace2016.pdf I guess that is what you referred to, Francois, when talking at the SYNC

Re: [lng-odp] [API-NEXT PATCH 0/5] driver initialisation framework

river registration. This would require to drop the > -std=c99 compliance flag from the compilation, correct? > That is correct. I actually did not realize that clashes with the c99 flag. would .init be better in your eyes? Or any other idea? Christophe. > Best Regards, > Stanislaw

Re: [lng-odp] [API-NEXT PATCHv6 00/13] using _ishm as north API mem allocator

ping On 31 October 2016 at 12:47, Bill Fischofer <bill.fischo...@linaro.org> wrote: > For this series: > > Reviewed-and-tested-by: Bill Fischofer <bill.fischo...@linaro.org> > > On Mon, Oct 31, 2016 at 3:52 AM, Christophe Milard > <christophe.mil...@

Re: [lng-odp] [API-NEXT PATCH 1/5] drv: adding driver registration interface (stub)

On 7 November 2016 at 08:02, Yi He <yi...@linaro.org> wrote: > Minor issues to avoid names conflict. > > On 1 November 2016 at 15:51, Christophe Milard > <christophe.mil...@linaro.org> wrote: >> >> On 25 October 2016 at 08:39, Brian Brooks <brian.bro...@li

[lng-odp] [API-NEXT PATCHv2 5/5] test: adding test for driver load function

ion (which is surprising). So this patch just point at the .so path usiong rpath. Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- test/.gitignore| 1 + test/Makefile.inc | 3 +- test/common_plat

[lng-odp] [API-NEXT PATCHv2 4/5] linux-gen: implementation of odp_load_driver function

Implementation of the driver loading function, of north API Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- configure.ac | 4 ++-- platform/linux-generic/include/.gitignore | 1 + .../linux-generic/i

[lng-odp] [API-NEXT PATCHv2 2/5] linux-gen: adding driver registration interface (stub)

The linux implementation for the driver registration interface (stub) Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- include/odp_drv.h | 1 + platform/linux-generic/Makefile.am | 2 ++ platform/linux-generic/drv_dr

[lng-odp] [API-NEXT PATCHv2 3/5] api: init: driver load function added

Function added on the north API to load drivers. Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- include/odp/api/spec/init.h | 16 1 file changed, 16 insertions(+) diff --git a/include/odp/api/spec/init.h b/include/odp/api/spec/init.h index 154cdf8..b

[lng-odp] [API-NEXT PATCHv2 0/5] driver initialisation framework

drivers. Once loaded, drivers init function (declared as __constructor__) call the ODP odp_driver_register() intialialisation function which, at this stage does nothing (just print an error message). odp_driver_register() is of course part of the driver interface (south). Christophe Milard (5

Re: [lng-odp] [API-NEXT PATCH 0/5] driver initialisation framework

is needed is a driver team, i.e. a set of persons which follows and work on the driver stuff. I'd be happy to have regular meetings to discuss the questions :-)... Then, maybe a doc would make sense as they would be readers :-) want to joín? ;-) regards, CHristophe > > Thanks and Best Regards, Yi

Re: [lng-odp] [API-NEXT PATCH 1/2] linux-gen: _ishmphy: adding function for physical address query

<bill.fischo...@linaro.org> wrote: > > > On Fri, Nov 4, 2016 at 7:32 AM, Christophe Milard > <christophe.mil...@linaro.org> wrote: >> >> The function _odp_ishmphy_getphy() is added to query for physical >> addresses (given a virtual address) >> This funct

[lng-odp] [API-NEXT PATCH 2/2] linux-gen: _ishmphy: adding debug function for pysical address mapping

_odp_ishmphy_dumpphy() prints the virtual to physical address mapping of some memory region (defined by virtuall address + length). Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- platform/linux-generic/_ishmphy.c | 57 ++ platform

[lng-odp] [API-NEXT PATCH 1/2] linux-gen: _ishmphy: adding function for physical address query

true if _odp_ishmphy_getphy() is able to works (as it requires specific permission) Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- platform/linux-generic/_ishmphy.c | 82 ++ platform/linux-generic/include/_ishmphy_internal.h | 14 +

[lng-odp] [API-NEXT PATCH 0/2] getting physical addresses from _ishmphy

shmphy_dumpphy():Virtual: 7fb81259c000 <--> Phy: 285a79000 1 PFNs, 4096 bytes _ishmphy.c:309:_odp_ishmphy_dumpphy():Virtual: 7fb81259d000 <--> Phy: 285a78000 1 PFNs, 4096 bytes _ishmphy.c:309:_odp_ishmphy_dumpphy():Virtual: 7fb81259e000 <--> Phy: 3a8a11000 1 PFNs, 40

Re: [lng-odp] [PATCHv2] linux-generic: add vlan insertion test

On 31 October 2016 at 20:53, Maxim Uvarov wrote: > Use vlan tagged traffic for example validation test > to add code coverage for pkt_mmap_vlan_insert() internal > function. > > Signed-off-by: Maxim Uvarov > --- > v2: update to current master. >

Re: [lng-odp] [API-NEXT PATCH 5/5] test: adding test for driver load function

On 25 October 2016 at 08:56, Brian Brooks <brian.bro...@linaro.org> wrote: > On 10/31 19:58:43, Christophe Milard wrote: >> Trying to fix a proper structure for driver tests in the hard world >> of autotools >> >> Signed-off-by: Christophe Milard <christoph

Re: [lng-odp] [API-NEXT PATCH 4/5] linux-gen: implementation of odp_load_driver function

On 25 October 2016 at 08:43, Brian Brooks <brian.bro...@linaro.org> wrote: > On 10/31 19:58:42, Christophe Milard wrote: >> Implementation of the driver loading function, of north API >> >> Signed-off-by: Christophe Milard <christophe.mil...@linar

Re: [lng-odp] [API-NEXT PATCH 1/5] drv: adding driver registration interface (stub)

On 25 October 2016 at 08:39, Brian Brooks <brian.bro...@linaro.org> wrote: > On 10/31 19:58:39, Christophe Milard wrote: >> The driver registration function (and a draft of its parameters) is >> defined, the goal being to define the driver registration framework o

Re: [lng-odp] driver test autotools issue

On 31 October 2016 at 22:32, Brian Brooks <brian.bro...@linaro.org> wrote: > On 10/31 18:48:38, Christophe Milard wrote: >> Thanks for trying Brian. >> >> ...Tried this as well :-)... >> >> >> On 31 October 2016 at 18:03, Brian Brooks <brian.bro...@l

[lng-odp] [API-NEXT PATCH 5/5] test: adding test for driver load function

Trying to fix a proper structure for driver tests in the hard world of autotools Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- test/.gitignore| 1 + test/Makefile.inc | 3 +- test/common_p

[lng-odp] [API-NEXT PATCH 4/5] linux-gen: implementation of odp_load_driver function

Implementation of the driver loading function, of north API Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- configure.ac | 4 ++-- platform/linux-generic/include/.gitignore | 1 + .../linux-generic/i

[lng-odp] [API-NEXT PATCH 0/5] driver initialisation framework

which, at this stage does nothing (just print 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 driver registration interface (stub) api: init: driver load function

[lng-odp] [API-NEXT PATCH 3/5] api: init: driver load function added

Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> Function added on the north API to load drivers. --- include/odp/api/spec/init.h | 16 1 file changed, 16 insertions(+) diff --git a/include/odp/api/spec/init.h b/include/odp/api/spec/init.h index 154cdf8..b

[lng-odp] [API-NEXT PATCH 2/5] linux-gen: adding driver registration interface (stub)

The linux implementation for the driver registration interface (stub) Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- include/odp_drv.h | 1 + platform/linux-generic/Makefile.am | 2 ++ platform/linux-generic/drv_dr

[lng-odp] [API-NEXT PATCH 1/5] drv: adding driver registration interface (stub)

The driver registration function (and a draft of its parameters) is defined, the goal being to define the driver registration framework only. Signed-off-by: Christophe Milard <christophe.mil...@linaro.org> --- include/odp/drv/spec/driver.

Re: [lng-odp] driver test autotools issue

Thanks for trying Brian. ...Tried this as well :-)... On 31 October 2016 at 18:03, Brian Brooks <brian.bro...@linaro.org> wrote: > On Fri, Oct 28, 2016 at 8:58 AM, Christophe Milard > <christophe.mil...@linaro.org> wrote: >> Hi, >> >> The ODP driver

Re: [lng-odp] [API-NEXT PATCHv6 05/13] api: shm: add flags to shm_reserve and function to find external mem

, Maxim Uvarov <maxim.uva...@linaro.org> wrote: > Petri, > > please review API patch. > > > > On 10/31/16 11:52, Christophe Milard wrote: >> >> The ODP_SHM_SINGLE_VA flag is created: when set (at odp_shm_reserve()), >> this flag guarantees that all ODP

[lng-odp] [API-NEXT PATCHv6 13/13] doc: updating docs for the shm interface extension

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

[lng-odp] [API-NEXT PATCHv6 11/13] linux-gen: _ishm: cleaning remaining block at odp_term_global

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

[lng-odp] [API-NEXT PATCHv6 12/13] linux_gen: _ishm: decreasing the number of error messages when no huge pages

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 0586a96..782c32f

[lng-odp] [API-NEXT PATCHv6 10/13] test: linux-gen: api: shmem: test sharing memory between ODP instances

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 +++-- .

[lng-odp] [API-NEXT PATCHv6 09/13] linux-gen: shm: add flag and function to share memory between ODP instances

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

[lng-odp] [API-NEXT PATCHv6 08/13] linux-gen: _ishm: adding function to map memory from other ODP

-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

[lng-odp] [API-NEXT PATCHv6 07/13] test: api: shmem: new proper tests for shm API

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

[lng-odp] [API-NEXT PATCHv6 06/13] linux-gen: shm: new ODP_SHM_SINGLE_VA flag implementation

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 +

<    1   2   3   4   5   6   7   8   9   10   >