Re: [PATCH v6 1/5] mm/filemap: add mempolicy support to the filemap layer

[Ackerley Tng <ackerleytng@google.com>]

Vlastimil Babka <vbabka@suse.cz> writes:

> On 2/26/25 09:25, Shivank Garg wrote:
>> From: Shivansh Dhiman <shivansh.dhiman@amd.com>
>> 
>> Add NUMA mempolicy support to the filemap allocation path by introducing
>> new APIs that take a mempolicy argument:
>> - filemap_grab_folio_mpol()
>> - filemap_alloc_folio_mpol()
>> - __filemap_get_folio_mpol()
>> 
>> These APIs allow callers to specify a NUMA policy during page cache
>> allocations, enabling fine-grained control over memory placement. This is
>> particularly needed by KVM when using guest-memfd memory backends, where
>> the guest memory needs to be allocated according to the NUMA policy
>> specified by VMM.
>> 
>> The existing non-mempolicy APIs remain unchanged and continue to use the
>> default allocation behavior.
>> 
>> Signed-off-by: Shivansh Dhiman <shivansh.dhiman@amd.com>
>> Signed-off-by: Shivank Garg <shivankg@amd.com>
>
> <snip>
>
>> --- a/mm/filemap.c
>> +++ b/mm/filemap.c
>> @@ -1001,11 +1001,17 @@ int filemap_add_folio(struct address_space *mapping, struct folio *folio,
>>  EXPORT_SYMBOL_GPL(filemap_add_folio);
>>  
>>  #ifdef CONFIG_NUMA
>> -struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order)
>> +struct folio *filemap_alloc_folio_mpol_noprof(gfp_t gfp, unsigned int order,
>> +		struct mempolicy *mpol)
>>  {
>>  	int n;
>>  	struct folio *folio;
>>  
>> +	if (mpol)
>> +		return folio_alloc_mpol_noprof(gfp, order, mpol,
>> +					       NO_INTERLEAVE_INDEX,

Could we pass in the interleave index instead of hard-coding it?

>> +					       numa_node_id());
>> +
>>  	if (cpuset_do_page_mem_spread()) {
>>  		unsigned int cpuset_mems_cookie;
>>  		do {
>> @@ -1018,6 +1024,12 @@ struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order)
>>  	}
>>  	return folio_alloc_noprof(gfp, order);
>>  }
>> +EXPORT_SYMBOL(filemap_alloc_folio_mpol_noprof);
>> +
>> +struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order)
>> +{
>> +	return filemap_alloc_folio_mpol_noprof(gfp, order, NULL);
>> +}
>>  EXPORT_SYMBOL(filemap_alloc_folio_noprof);
>>  #endif
>
> Here it seems to me:
>
> - filemap_alloc_folio_noprof() could stay unchanged
> - filemap_alloc_folio_mpol_noprof() would
>   - call folio_alloc_mpol_noprof() if (mpol)
>   - call filemap_alloc_folio_noprof() otherwise
>
> The code would be a bit more clearly structured that way?
>

I feel that the original proposal makes it clearer that for all filemap
folio allocations, if mpol is defined, anything to do with cpuset's page
spread is overridden. Just a slight preference though. I do also agree
that having filemap_alloc_folio_mpol_noprof() call
filemap_alloc_folio_noprof() would result in fewer changes.

>> @@ -1881,11 +1893,12 @@ void *filemap_get_entry(struct address_space *mapping, pgoff_t index)
>>  }
>>  
>>  /**
>> - * __filemap_get_folio - Find and get a reference to a folio.
>> + * __filemap_get_folio_mpol - Find and get a reference to a folio.
>>   * @mapping: The address_space to search.
>>   * @index: The page index.
>>   * @fgp_flags: %FGP flags modify how the folio is returned.
>>   * @gfp: Memory allocation flags to use if %FGP_CREAT is specified.
>> + * @mpol: The mempolicy to apply when allocating a new folio.
>>   *
>>   * Looks up the page cache entry at @mapping & @index.
>>   *
>> @@ -1896,8 +1909,8 @@ void *filemap_get_entry(struct address_space *mapping, pgoff_t index)
>>   *
>>   * Return: The found folio or an ERR_PTR() otherwise.
>>   */
>> -struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
>> -		fgf_t fgp_flags, gfp_t gfp)
>> +struct folio *__filemap_get_folio_mpol(struct address_space *mapping, pgoff_t index,
>> +		fgf_t fgp_flags, gfp_t gfp, struct mempolicy *mpol)
>>  {
>>  	struct folio *folio;
>>  
>> @@ -1967,7 +1980,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
>>  			err = -ENOMEM;
>>  			if (order > min_order)
>>  				alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN;
>> -			folio = filemap_alloc_folio(alloc_gfp, order);
>> +			folio = filemap_alloc_folio_mpol(alloc_gfp, order, mpol);
>>  			if (!folio)
>>  				continue;
>>  
>> @@ -2003,6 +2016,13 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
>>  		folio_clear_dropbehind(folio);
>>  	return folio;
>>  }
>> +EXPORT_SYMBOL(__filemap_get_folio_mpol);
>> +
>> +struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
>> +		fgf_t fgp_flags, gfp_t gfp)
>> +{
>> +	return __filemap_get_folio_mpol(mapping, index, fgp_flags, gfp, NULL);
>> +}
>>  EXPORT_SYMBOL(__filemap_get_folio);
>>  
>>  static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max,