Re: [RFC PATCH v4 4/6] mm/migrate: add copy offload registration infrastructure

["Garg, Shivank" <shivankg@amd.com>]

On 4/3/2026 4:41 PM, Garg, Shivank wrote:
> 
> 
> On 3/24/2026 4:24 PM, Huang, Ying wrote:
>> Shivank Garg <shivankg@amd.com> writes:
>>
>>> Introduce CONFIG_MIGRATION_COPY_OFFLOAD, which lets offload driver
>>
>> Do we really need a new kconfig option?  IMHO, we have too many now.
>> Because we have a jump label already, the performance difference should
>> be trivial.  Can you measure the size difference?
> 
> BASELINE (offload=n)
>    text    data     bss     dec  filename
>   23577    1632      32   25241  mm/migrate.o
> 39202900        14159750        6502152 59864802     vmlinux
> 
> WITH OFFLOAD (offload=y)
>    text    data     bss     dec  filename
>   24444    2568      32   27044  mm/migrate.o
>     676      64       8     748  mm/migrate_copy_offload.o
> 39208218        14163942        6498120 59870280     vmlinux
> 
> WITHOUT CONFIG (always-on)
>    text    data     bss     dec  filename
>   24444    2568      32   27044  mm/migrate.o
>     676      64       8     748  mm/migrate_copy_offload.o
> 39208405        14163942        6498120 59870467     vmlinux
> 
> It saves around 5.5KB of size, when offload support is disabled.
> Is it meaningful savings? What do you think?
> 
>>
>>> +#ifdef CONFIG_MIGRATION_COPY_OFFLOAD
>>> +extern struct static_key_false migrate_offload_enabled;
>>> +extern struct srcu_struct migrate_offload_srcu;
>>> +bool migrate_should_batch_default(int reason);
>>> +int migrate_offload_start(struct migrator *m);
>>> +int migrate_offload_stop(struct migrator *m);
>>
>> Why not naming the function migrate_offload_register/unregister()?
>> IMHO, that sounds more natural.
> 
> Ack. I'll rename to migrate_offload_register/unregister().
> 
>>
>>>  
>>> +#ifdef CONFIG_MIGRATION_COPY_OFFLOAD
>>> +	/* Check if the offload driver wants to batch for this reason */
>>> +	if (static_branch_unlikely(&migrate_offload_enabled))
>>> +		do_batch = static_call(migrate_should_batch)(reason);
>>
>> Should batching based on "reason" be determined by the general migrate
>> code instead of the migrator implementation?  For example, if we only
>> batch copying for ASYNC migration, we should determine that in
>> migrate_pages_batch() instead of the migreation implementation.  Or am I
>> missed something?  If so, can you provide an example?
>>
> 
> My idea was that different drivers may have different cost/benefit
> profiles(e.g. setup cost, migrate batch-size, etc..) 
> 
> For instance, a DMA driver may want to target only bulk migration usecase.
> And a CPU-thread based driver can be used more broadly, without worrying
> about setup-costs.
> 
> But I agree it's premature with only one-driver.
> I'll move the reason check with target usecases into migrate_pages_batch()
> and drop the should_batch() callback. If a future driver needs different
> filtering, we can add it back then.
> 
>>>  
>>> +#ifdef CONFIG_MIGRATION_COPY_OFFLOAD
>>>  	/* Batch-copy eligible folios before the move phase */
>>>  	if (!list_empty(&src_batch)) {
>>
>> Guard with "static_branch_unlikely(&migrate_offload_enabled)" first?
>> Better to define a inline function to shorten the expression.
>>
> 
> Sure, will add the static_branch_unlikely guard and wrap in a helper
> function. Thanks.

Coming back to this while reworking the patch.
I think the static branch guard here is actually redundant. We already check it at
the per-folio classification that builds src_batch,
so when offload is disabled src_batch stays empty and the list_empty() check
short-circuits. I'll still wrap the SRCU + static_call into a helper at this call
site, as you suggested. Sorry for the flip-flop.

Thanks,
Shivank