On 5/3/19 2:07 AM, Steffen Klassert wrote: > On Wed, Apr 24, 2019 at 12:40:23PM +0200, Florian Westphal wrote: >> I'm not sure this is a good idea to begin with, refcount >> is right next to state spinlock which is taken for both tx and rx ops, >> plus this complicates debugging quite a bit. > > For some reason I have not received Florian response. Florian, when the percpu counters are in nominal mode, the updates are only in percpu memory, so the cache line containing struct percpu_ref in the main object is not dirtied. (This field/object can be placed in a read-mostly location of the structure if needed) I would definitely try to use this.
- Re: ipsec tunnel performance degrade David Miller
- RE: ipsec tunnel performance degrade Vakul Garg
- [RFC HACK] xfrm: make state refcounting percpu Florian Westphal
- Re: [RFC HACK] xfrm: make state refcounting percpu Eric Dumazet
- Re: [RFC HACK] xfrm: make state refcounting percpu Steffen Klassert
- RE: [RFC HACK] xfrm: make state refcounting percpu Vakul Garg
- Re: [RFC HACK] xfrm: make state refcounting percpu Steffen Klassert
- RE: [RFC HACK] xfrm: make state refcounting percpu Vakul Garg
- Re: [RFC HACK] xfrm: make state refcounting percpu Steffen Klassert
- RE: [RFC HACK] xfrm: make state refcounting percpu Vakul Garg
- Re: [RFC HACK] xfrm: make state refcounting percpu Eric Dumazet
- Re: [RFC HACK] xfrm: make state refcounting percpu Florian Westphal