On 03/04/15 20:54, Stephen Hemminger wrote:
> On Wed, 04 Mar 2015 09:57:24 +0200
> Vlad Zolotarov wrote:
>
>>
>> On 03/04/15 02:33, Stephen Hemminger wrote:
>>> On Tue, 3 Mar 2015 21:48:43 +0200
>>> Vlad Zolotarov wrote:
>>>
+ next_desc:
+ /*
+ * The code in
On Wed, 04 Mar 2015 09:57:24 +0200
Vlad Zolotarov wrote:
>
>
> On 03/04/15 02:33, Stephen Hemminger wrote:
> > On Tue, 3 Mar 2015 21:48:43 +0200
> > Vlad Zolotarov wrote:
> >
> >> + next_desc:
> >> + /*
> >> + * The code in this whole file uses the volatile pointer to
>
On Wed, 04 Mar 2015 09:59:38 +0200
Vlad Zolotarov wrote:
> > Checkpatch warnings (edited to remove ones that should be ok)
>
> I was unaware that checkpatch rules apply here - at least looking at the
> current code it looks like it... ;)
> But I'm all for it! I'll fix all the issues and
On 03/04/2015 02:33 AM, Stephen Hemminger wrote:
> On Tue, 3 Mar 2015 21:48:43 +0200
> Vlad Zolotarov wrote:
>
>> + * TODO:
>> + *- Get rid of "volatile" crap and let the compiler do its
>> + * job.
>> + *- Use the proper memory
On 03/04/15 02:36, Stephen Hemminger wrote:
> On Tue, 3 Mar 2015 21:48:43 +0200
> Vlad Zolotarov wrote:
>
>> - Only x540 and 82599 devices support LRO.
>> - Add the appropriate HW configuration.
>> - Add RSC aware rx_pkt_burst() handlers:
>> - Implemented bulk allocation
On 03/04/15 02:34, Stephen Hemminger wrote:
> On Tue, 3 Mar 2015 21:48:43 +0200
> Vlad Zolotarov wrote:
>
>> +
>> +if (!bulk_alloc) {
>> +__le64 dma =
>> + rte_cpu_to_le_64(RTE_MBUF_DATA_DMA_ADDR_DEFAULT(nmb));
>> +/*
>>
On 03/04/15 02:33, Stephen Hemminger wrote:
> On Tue, 3 Mar 2015 21:48:43 +0200
> Vlad Zolotarov wrote:
>
>> +next_desc:
>> +/*
>> + * The code in this whole file uses the volatile pointer to
>> + * ensure the read ordering of the status and the rest of
On 03/04/15 02:33, Stephen Hemminger wrote:
> On Tue, 3 Mar 2015 21:48:43 +0200
> Vlad Zolotarov wrote:
>
>> +lro_bulk_alloc: 1, /**< RX LRO with bulk alloc is ON(1) /
>> OFF(0) */
> This is an internal decision and should not be exposed in the API.
> We need less knobs not more.
- Only x540 and 82599 devices support LRO.
- Add the appropriate HW configuration.
- Add RSC aware rx_pkt_burst() handlers:
- Implemented bulk allocation and non-bulk allocation versions.
- Add LRO-specific fields to rte_eth_rxmode, to rte_eth_dev_data
and to
On Tue, 3 Mar 2015 21:48:43 +0200
Vlad Zolotarov wrote:
> - Only x540 and 82599 devices support LRO.
> - Add the appropriate HW configuration.
> - Add RSC aware rx_pkt_burst() handlers:
>- Implemented bulk allocation and non-bulk allocation versions.
>- Add
On Tue, 3 Mar 2015 21:48:43 +0200
Vlad Zolotarov wrote:
> +
> + if (!bulk_alloc) {
> + __le64 dma =
> + rte_cpu_to_le_64(RTE_MBUF_DATA_DMA_ADDR_DEFAULT(nmb));
> + /*
> + * Update RX descriptor with
On Tue, 3 Mar 2015 21:48:43 +0200
Vlad Zolotarov wrote:
> + next_desc:
> + /*
> + * The code in this whole file uses the volatile pointer to
> + * ensure the read ordering of the status and the rest of the
> + * descriptor fields (on the
On Tue, 3 Mar 2015 21:48:43 +0200
Vlad Zolotarov wrote:
> + lro_bulk_alloc: 1, /**< RX LRO with bulk alloc is ON(1) /
> OFF(0) */
This is an internal decision and should not be exposed in the API.
We need less knobs not more.
13 matches
Mail list logo
