On Mon, 25 Mar 2019 10:35:35 +0100 Felix Fietkau wrote:
> On 2019-03-25 10:31, Eric Dumazet wrote:
> > On 03/25/2019 02:09 AM, Felix Fietkau wrote:
> >> On 2019-03-25 09:51, Eric Dumazet wrote:
> >>> On 03/24/2019 09:56 AM, Felix Fietkau wrote:
>
> Since we're freeing multiple skbs
On 2019-03-25 10:31, Eric Dumazet wrote:
>
>
> On 03/25/2019 02:09 AM, Felix Fietkau wrote:
>> On 2019-03-25 09:51, Eric Dumazet wrote:
>>>
>>>
>>> On 03/24/2019 09:56 AM, Felix Fietkau wrote:
Since we're freeing multiple skbs, we might as well use bulk free to save a
few cycles. Use th
On 03/25/2019 02:09 AM, Felix Fietkau wrote:
> On 2019-03-25 09:51, Eric Dumazet wrote:
>>
>>
>> On 03/24/2019 09:56 AM, Felix Fietkau wrote:
>>> Since we're freeing multiple skbs, we might as well use bulk free to save a
>>> few cycles. Use the same conditions for bulk free as in napi_consume_s
On 2019-03-25 09:51, Eric Dumazet wrote:
>
>
> On 03/24/2019 09:56 AM, Felix Fietkau wrote:
>> Since we're freeing multiple skbs, we might as well use bulk free to save a
>> few cycles. Use the same conditions for bulk free as in napi_consume_skb.
>>
>
> I do not believe kfree_skb_list() is use
Hi,
On Sun, 2019-03-24 at 17:56 +0100, Felix Fietkau wrote:
> Since we're freeing multiple skbs, we might as well use bulk free to save a
> few cycles. Use the same conditions for bulk free as in napi_consume_skb.
>
> Signed-off-by: Felix Fietkau
> ---
> v2: call kmem_cache_free_bulk once the sk
On 03/24/2019 09:56 AM, Felix Fietkau wrote:
> Since we're freeing multiple skbs, we might as well use bulk free to save a
> few cycles. Use the same conditions for bulk free as in napi_consume_skb.
>
I do not believe kfree_skb_list() is used in the fast path, so do we really
need to make it s
On Sun, 24 Mar 2019 17:56:44 +0100
Felix Fietkau wrote:
> Since we're freeing multiple skbs, we might as well use bulk free to save a
> few cycles. Use the same conditions for bulk free as in napi_consume_skb.
>
> Signed-off-by: Felix Fietkau
> ---
> v2: call kmem_cache_free_bulk once the skb a
Since we're freeing multiple skbs, we might as well use bulk free to save a
few cycles. Use the same conditions for bulk free as in napi_consume_skb.
Signed-off-by: Felix Fietkau
---
v2: call kmem_cache_free_bulk once the skb array is full instead of
falling back to kfree_skb
net/core/skbuff
