On 01/27/2015 04:25 PM, Maxim Uvarov wrote:
We need to take some decision here.
If KS2 does not support enq to a pktin queue or deq from a pktout queue
lets apply this patch.
As I've noted in this thread there are no limitations in HW to support
it. I just don't see a real use-case for this
On 11/27/2014 06:56 PM, Stuart Haslam wrote:
Attempts to enq to a pktin queue or deq from a pktout queue are
programming errors, so abort.
Signed-off-by: Stuart Haslam stuart.has...@arm.com
---
(This code contribution is provided under the terms of agreement LES-LTM-21309)
We need to take some decision here.
If KS2 does not support enq to a pktin queue or deq from a pktout queue
lets apply this patch.
Maxim.
On 11/28/2014 06:28 PM, Taras Kondratiuk wrote:
On 11/28/2014 04:47 PM, Alexandru Badicioiu wrote:
Why using a HW feature (which was not an error in
We need to take some dessision here.
If KS2 does not support enq to a pktin queue or deq from a pktout queue
lets apply this patch.
Maxim.
On 11/28/2014 06:28 PM, Taras Kondratiuk wrote:
On 11/28/2014 04:47 PM, Alexandru Badicioiu wrote:
Why using a HW feature (which was not an error in
On 01/27/2015 06:15 PM, Taras Kondratiuk wrote:
On 11/27/2014 06:56 PM, Stuart Haslam wrote:
Attempts to enq to a pktin queue or deq from a pktout queue are
programming errors, so abort.
Signed-off-by: Stuart Haslam stuart.has...@arm.com
---
(This code contribution is provided under the terms
On 11/28/2014 07:28 AM, Bill Fischofer wrote:
The real issue here is expected frequency. With the exception of
read/write operations on polled queues, most pktio operations are
low-frequency initialization-time calls. As such, doing additional
validation in these routines carries no
On 27 November 2014 at 18:56, Stuart Haslam stuart.has...@arm.com wrote:
Attempts to enq to a pktin queue or deq from a pktout queue are
programming errors, so abort.
[Alex] Is this an ODP convention valid for all implementations? I f we
talk about HW I think these are debatable and SoC
On 28 November 2014 at 14:41, Alexandru Badicioiu
alexandru.badici...@linaro.org wrote:
One reason to allow enqueue to pktin would be for debugging and testing
packet applications without using external traffic.
Would this be portable?
Couldn't we define some concept of loopback mode or
On 11/28/2014 01:47 PM, Stuart Haslam wrote:
On Fri, Nov 28, 2014 at 09:48:29AM +, Alexandru Badicioiu wrote:
On 27 November 2014 at 18:56, Stuart Haslam
stuart.has...@arm.commailto:stuart.has...@arm.com wrote:
Attempts to enq to a pktin queue or deq from a pktout queue are
programming
Attempts to enq to a pktin queue or deq from a pktout queue are
programming errors, so abort.
Signed-off-by: Stuart Haslam stuart.has...@arm.com
---
(This code contribution is provided under the terms of agreement LES-LTM-21309)
platform/linux-generic/odp_packet_io.c | 22 ++
On 27 November 2014 at 17:56, Stuart Haslam stuart.has...@arm.com wrote:
Attempts to enq to a pktin queue or deq from a pktout queue are
programming errors, so abort.
Are there more cases of such programming errors where we should
specify the API semantics to be undefined instead of having to
On Thu, Nov 27, 2014 at 05:09:06PM +, Ola Liljedahl wrote:
On 27 November 2014 at 17:56, Stuart Haslam stuart.has...@arm.com wrote:
Attempts to enq to a pktin queue or deq from a pktout queue are
programming errors, so abort.
Are there more cases of such programming errors where we
12 matches
Mail list logo
