[PATCH v3 01/29] bpf: replace deprecated SMP barriers with C11 fences

[Marat Khalili]

On 12/10/2026 19:52, Marat Khalili wrote:

> On 09/10/2026 07:05, Wathsala Vithanage wrote:
>>>   /*
>>>    * Marks given callback as used by datapath.
>>>    */
>>>   static __rte_always_inline void
>>>   bpf_eth_cbi_inuse(struct bpf_eth_cbi *cbi)
>>>   {
>>> -    cbi->use++;
>>> -    /* make sure no store/load reordering could happen */
>>> -    rte_smp_mb();
>>> +    rte_atomic_store_explicit(&cbi->use,
>>> +        rte_atomic_load_explicit(&cbi->use, 
>>> rte_memory_order_relaxed) + 1,
>>> +        rte_memory_order_relaxed);
>>> +
>>> +    /* full barrier: count must be visible before cb is read */
>>> +    rte_atomic_thread_fence(rte_memory_order_seq_cst);
>
> NAK: optimizing this increment makes little sense when more careful 
> analysis shows that it can be simply removed.
>
> I highly recommend keeping this patchset dedicated to removing 
> rte_smp_XX barriers and moving other bpf_pkt.c improvements elsewhere.

Withdrawing my NAK. It was mostly for stylistic and commit history 
considerations, we have run out of time and this is the only version 
that has a reviewed-by.