[RFC,v2,4/5] lib/bpf: use wait event scheme for Rx/Tx iteration

  First, fix the bug that keyword const of func arg should be after "*".
This is because const before "*" means the value of "cbi" should not be
changed. But we should monitor that cbi->use changed and then we can
jump out of loop.

Second, instead of polling for cbi->use to be updated, use
wait event scheme.

Fixes: a93ff62a8938 ("bpf: introduce basic Rx/Tx filters")
Cc: konstantin.ananyev@intel.com
Cc: stable@dpdk.org

Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
---
 lib/bpf/bpf_pkt.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)
  

> 
> First, fix the bug that keyword const of func arg should be after "*".

I believe there is no bug here.

> This is because const before "*" means the value of "cbi" should not be
> changed. 

Exactly, it says that the function itself will not change the value of "cbi".
It just waits for the value to be changed by someone else.
So please keep parameter list intact.

> But we should monitor that cbi->use changed and then we can
> jump out of loop.
> 
> Second, instead of polling for cbi->use to be updated, use
> wait event scheme.
> 
> Fixes: a93ff62a8938 ("bpf: introduce basic Rx/Tx filters")
> Cc: konstantin.ananyev@intel.com
> Cc: stable@dpdk.org
> 
> Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> ---
>  lib/bpf/bpf_pkt.c | 11 ++++-------
>  1 file changed, 4 insertions(+), 7 deletions(-)
> 
> diff --git a/lib/bpf/bpf_pkt.c b/lib/bpf/bpf_pkt.c
> index 6e8248f0d6..08ed8ff68c 100644
> --- a/lib/bpf/bpf_pkt.c
> +++ b/lib/bpf/bpf_pkt.c
> @@ -111,9 +111,9 @@ bpf_eth_cbi_unuse(struct bpf_eth_cbi *cbi)
>   * Waits till datapath finished using given callback.
>   */
>  static void
> -bpf_eth_cbi_wait(const struct bpf_eth_cbi *cbi)
> +bpf_eth_cbi_wait(struct bpf_eth_cbi *const cbi)
>  {
> -	uint32_t nuse, puse;
> +	uint32_t puse;
> 
>  	/* make sure all previous loads and stores are completed */
>  	rte_smp_mb();
> @@ -122,11 +122,8 @@ bpf_eth_cbi_wait(const struct bpf_eth_cbi *cbi)
> 
>  	/* in use, busy wait till current RX/TX iteration is finished */
>  	if ((puse & BPF_ETH_CBI_INUSE) != 0) {
> -		do {
> -			rte_pause();
> -			rte_compiler_barrier();
> -			nuse = cbi->use;
> -		} while (nuse == puse);
> +		rte_compiler_barrier();
> +		rte_wait_event_32(&cbi->use, UINT_MAX, puse, ==, __ATOMIC_RELAXED);
>  	}
>  }
> 
> --
> 2.25.1
  

> -----邮件原件-----
> 发件人: Ananyev, Konstantin <konstantin.ananyev@intel.com>
> 发送时间: Saturday, September 25, 2021 2:08 AM
> 收件人: Feifei Wang <Feifei.Wang2@arm.com>; Yigit, Ferruh
> <ferruh.yigit@intel.com>
> 抄送: dev@dpdk.org; nd <nd@arm.com>; stable@dpdk.org; Ruifeng Wang
> <Ruifeng.Wang@arm.com>
> 主题: RE: [RFC PATCH v2 4/5] lib/bpf: use wait event scheme for Rx/Tx
> iteration
> 
> 
> >
> > First, fix the bug that keyword const of func arg should be after "*".
> 
> I believe there is no bug here.
> 
> > This is because const before "*" means the value of "cbi" should not
> > be changed.
> 
> Exactly, it says that the function itself will not change the value of "cbi".
> It just waits for the value to be changed by someone else.
> So please keep parameter list intact.

Thanks for your explanation. The reason I changed is that I ever used rte_wait_until_xx(validate *addr) API here,
And there is conflict between "const" and "validate", complier will report warning here.
But now I think since I keep it as it is, there will be no warning due to new macro has no "validate".
I will delete this unnecessary bug fix.
> 
> > But we should monitor that cbi->use changed and then we can jump out
> > of loop.
> >
> > Second, instead of polling for cbi->use to be updated, use wait event
> > scheme.
> >
> > Fixes: a93ff62a8938 ("bpf: introduce basic Rx/Tx filters")
> > Cc: konstantin.ananyev@intel.com
> > Cc: stable@dpdk.org
> >
> > Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
> > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > ---
> >  lib/bpf/bpf_pkt.c | 11 ++++-------
> >  1 file changed, 4 insertions(+), 7 deletions(-)
> >
> > diff --git a/lib/bpf/bpf_pkt.c b/lib/bpf/bpf_pkt.c index
> > 6e8248f0d6..08ed8ff68c 100644
> > --- a/lib/bpf/bpf_pkt.c
> > +++ b/lib/bpf/bpf_pkt.c
> > @@ -111,9 +111,9 @@ bpf_eth_cbi_unuse(struct bpf_eth_cbi *cbi)
> >   * Waits till datapath finished using given callback.
> >   */
> >  static void
> > -bpf_eth_cbi_wait(const struct bpf_eth_cbi *cbi)
> > +bpf_eth_cbi_wait(struct bpf_eth_cbi *const cbi)
> >  {
> > -	uint32_t nuse, puse;
> > +	uint32_t puse;
> >
> >  	/* make sure all previous loads and stores are completed */
> >  	rte_smp_mb();
> > @@ -122,11 +122,8 @@ bpf_eth_cbi_wait(const struct bpf_eth_cbi *cbi)
> >
> >  	/* in use, busy wait till current RX/TX iteration is finished */
> >  	if ((puse & BPF_ETH_CBI_INUSE) != 0) {
> > -		do {
> > -			rte_pause();
> > -			rte_compiler_barrier();
> > -			nuse = cbi->use;
> > -		} while (nuse == puse);
> > +		rte_compiler_barrier();
> > +		rte_wait_event_32(&cbi->use, UINT_MAX, puse, ==,
> __ATOMIC_RELAXED);
> >  	}
> >  }
> >
> > --
> > 2.25.1