Re: [PATCH hazptr v3 4/4] hazptr: Introduce "try acquire" fast path, fallback to overflow list

[Bradley Morgan]

On 11 October 2026 21:06:24 BST, Mathieu Desnoyers
<mathieu.desnoyers@xxxxxxxxxxxx> wrote:
>On 2026-10-11 15:59, Bradley Morgan wrote:
>> On 11 October 2026 20:48:50 BST, Mathieu Desnoyers
>> <mathieu.desnoyers@xxxxxxxxxxxx> wrote:
>>> Introduce a "try acquire" hazard pointer fast path, which performs an
>>> early load of the address to store it into the hazard pointer slot, and
>>> then re-loads that address after a barrier to check whether it has
>>> changed meanwhile.
>>> 
>>> On comparison failure, rather than re-try, guarantee forward progress
>by
>>> falling back to the __hazptr_acquire slow path on failure.
>>> 
>>> The acquire slow path attempts a try-acquire for any available per-CPU
>>> slot. If that fails, it chains the backup slot into the overflow list,
>>> therefore guaranteeing forward progress for both hazard pointer
>>> read-side and synchronize:
>>> 
>>> - Readers set the wildcard, and then proceed to set the more
>>>   specific address to replace the wildcard.
>>> 
>>> - One synchronize alternates between two overflow list periods,
>>>   scanning each one while readers are added to the other period,
>>>   thus preventing a steady flow of readers from preventing
>>>   synchronize forward progress.
>>> 
>>> With this change, the scan on per-CPU slots don't need to expect a
>>> wildcard anymore, because none can be produced by readers. Wildcards
>are
>>> only expected within overflow lists.
>>> 
>>> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
>>> Suggested-by: Gary Guo <gary@xxxxxxxxxxx>
>>> Link:
>https://lore.kernel.org/lkmm/DLK9MW1N86KD.2GRWUAD2NX4FU@xxxxxxxxxxx/
>>> Reviewed-by: Gary Guo <gary@xxxxxxxxxxx>
>> 
>> Hi, my R-B still stands from
>> 
>>
>https://lore.kernel.org/all/C53DEBF5-555F-44A8-A11C-A15C83AAD341@xxxxxxxxxxxxxx/
>> 
>> Reviewed-by: Bradley Morgan <brads@xxxxxxxxxxxxxx>
>
>Sorry, I forgot to add it to my commit message. I'll add it to the next
>round (if there is one), else hopefully Paul can add the R-B tag if he
>picks up this series.
>
>Thanks!

Thanks, this thing happens.. :)

>
>Mathieu
>
>
>

--- Thanks!
"I'm not a very positive person" - Linus torvalds