[dpdk-dev] [PATCH 5/5] net/softnic: update headers size calculation

Ferruh Yigit ferruh.yigit at intel.com
Tue Nov 17 11:30:12 CET 2020


On 11/16/2020 7:09 PM, Dekel Peled wrote:

< Please don't top post, reply moved to the bottom >

>> -----Original Message-----
>> From: Ferruh Yigit <ferruh.yigit at intel.com>
>> Sent: Monday, November 16, 2020 6:27 PM
>> To: Xiaoyu Min <jackmin at mellanox.com>; Jasvinder Singh
>> <jasvinder.singh at intel.com>; Cristian Dumitrescu
>> <cristian.dumitrescu at intel.com>
>> Cc: dev at dpdk.org; Dekel Peled <dekelp at nvidia.com>
>> Subject: Re: [dpdk-dev] [PATCH 5/5] net/softnic: update headers size
>> calculation
>>
>> On 11/16/2020 7:55 AM, Xiaoyu Min wrote:
>>> From: Dekel Peled <dekelp at nvidia.com>
>>>
>>> The rte_flow_item_eth and rte_flow_item_vlan items were updated in
>> [1].
>>> The rte_flow_item_ipv6 item was updated in [2].
>>> The structs now contain additional metadata following the header data.
>>> The size to use for match should be the header data size only, and not
>>> the size of the whole struct.
>>>
>>> This patch replaces the rte_flow_item_* with the corresponding
>> rte_*_hdr.
>>>
>>> [1]:commit 09315fc83861 ("ethdev: add VLAN attributes to ethernet and
>>> VLAN
>>> items")
>>>
>>> [2]: commit ad976bd40d28 ("ethdev: add extensions attributes to IPv6
>>> item")
>>>
>>> Signed-off-by: Dekel Peled <dekelp at nvidia.com>
>>> ---
>>>    drivers/net/softnic/rte_eth_softnic_flow.c | 8 ++++----
>>>    1 file changed, 4 insertions(+), 4 deletions(-)
>>>
>>> diff --git a/drivers/net/softnic/rte_eth_softnic_flow.c
>>> b/drivers/net/softnic/rte_eth_softnic_flow.c
>>> index f05ff092fa..7925bad1c0 100644
>>> --- a/drivers/net/softnic/rte_eth_softnic_flow.c
>>> +++ b/drivers/net/softnic/rte_eth_softnic_flow.c
>>> @@ -169,22 +169,22 @@ flow_item_is_proto(enum rte_flow_item_type
>> type,
>>>
>>>    	case RTE_FLOW_ITEM_TYPE_ETH:
>>>    		*mask = &rte_flow_item_eth_mask;
>>> -		*size = sizeof(struct rte_flow_item_eth);
>>> +		*size = sizeof(struct rte_ether_hdr);
>>>    		return 1; /* TRUE */
>>>
>>>    	case RTE_FLOW_ITEM_TYPE_VLAN:
>>>    		*mask = &rte_flow_item_vlan_mask;
>>> -		*size = sizeof(struct rte_flow_item_vlan);
>>> +		*size = sizeof(struct rte_vlan_hdr);
>>>    		return 1;
>>>
>>>    	case RTE_FLOW_ITEM_TYPE_IPV4:
>>>    		*mask = &rte_flow_item_ipv4_mask;
>>> -		*size = sizeof(struct rte_flow_item_ipv4);
>>> +		*size = sizeof(struct rte_ipv4_hdr);
>>>    		return 1;
>>>
>>>    	case RTE_FLOW_ITEM_TYPE_IPV6:
>>>    		*mask = &rte_flow_item_ipv6_mask;
>>> -		*size = sizeof(struct rte_flow_item_ipv6);
>>> +		*size = sizeof(struct rte_ipv6_hdr);
>>>    		return 1;
>>>
>>
>> As far as I can see the 'flow_item_is_proto' sets the size to be used over
>> 'rte_flow_item_*" types, the original values seems correct to me, am I
>> missing something.
>>
>> Can you please elaborate why the change is needed?
> 
 > Hi Ferruh,
 >
 > The failure occur at hash_key_mask_is_same() which uses the size returned by 
flow_item_is_proto() for comparison.
 > Since the rte_flow_item_* of some types is now different than the rte_*_hdr 
size of these types, need to use the rte_*_hdr size.
 >

Got it.

Using "rte_*_hdr" structs size will strip the new additions to the 
"rte_flow_item_*" structs and won't able to use them.
But at least using old sizes should preserve old functionality and prevent any 
unexpected side affect, so I am OK to continue with this change but code needs 
to be updated later to benefit from latest "rte_flow_item_*" structs.

Cristian, Jasvinder,

Can you please acknowledge that you are aware of the reason of this change and 
possible updates may be required later?


More information about the dev mailing list