Re: [PATCH 2/2] mm: mincore: use folio_pte_batch() to batch process large folios

[Baolin Wang <baolin.wang@linux.alibaba.com>]

On 2025/5/7 13:12, Dev Jain wrote:
> 
> 
> On 26/03/25 9:08 am, Baolin Wang wrote:
>> When I tested the mincore() syscall, I observed that it takes longer with
>> 64K mTHP enabled on my Arm64 server. The reason is the 
>> mincore_pte_range()
>> still checks each PTE individually, even when the PTEs are contiguous,
>> which is not efficient.
>>
>> Thus we can use folio_pte_batch() to get the batch number of the present
>> contiguous PTEs, which can improve the performance. I tested the 
>> mincore()
>> syscall with 1G anonymous memory populated with 64K mTHP, and observed an
>> obvious performance improvement:
>>
>> w/o patch        w/ patch        changes
>> 6022us            1115us            +81%
>>
>> Moreover, I also tested mincore() with disabling mTHP/THP, and did not
>> see any obvious regression.
>>
>> Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
>> ---
>>   mm/mincore.c | 27 ++++++++++++++++++++++-----
>>   1 file changed, 22 insertions(+), 5 deletions(-)
>>
>> diff --git a/mm/mincore.c b/mm/mincore.c
>> index 832f29f46767..88be180b5550 100644
>> --- a/mm/mincore.c
>> +++ b/mm/mincore.c
>> @@ -21,6 +21,7 @@
>>   #include <linux/uaccess.h>
>>   #include "swap.h"
>> +#include "internal.h"
>>   static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned 
>> long addr,
>>               unsigned long end, struct mm_walk *walk)
>> @@ -105,6 +106,7 @@ static int mincore_pte_range(pmd_t *pmd, unsigned 
>> long addr, unsigned long end,
>>       pte_t *ptep;
>>       unsigned char *vec = walk->private;
>>       int nr = (end - addr) >> PAGE_SHIFT;
>> +    int step, i;
>>       ptl = pmd_trans_huge_lock(pmd, vma);
>>       if (ptl) {
>> @@ -118,16 +120,31 @@ static int mincore_pte_range(pmd_t *pmd, 
>> unsigned long addr, unsigned long end,
>>           walk->action = ACTION_AGAIN;
>>           return 0;
>>       }
>> -    for (; addr != end; ptep++, addr += PAGE_SIZE) {
>> +    for (; addr != end; ptep += step, addr += step * PAGE_SIZE) {
>>           pte_t pte = ptep_get(ptep);
>> +        step = 1;
>>           /* We need to do cache lookup too for pte markers */
>>           if (pte_none_mostly(pte))
>>               __mincore_unmapped_range(addr, addr + PAGE_SIZE,
>>                            vma, vec);
>> -        else if (pte_present(pte))
>> -            *vec = 1;
>> -        else { /* pte is a swap entry */
>> +        else if (pte_present(pte)) {
>> +            if (pte_batch_hint(ptep, pte) > 1) {
>> +                struct folio *folio = vm_normal_folio(vma, addr, pte);
>> +
>> +                if (folio && folio_test_large(folio)) {
>> +                    const fpb_t fpb_flags = FPB_IGNORE_DIRTY |
>> +                                FPB_IGNORE_SOFT_DIRTY;
>> +                    int max_nr = (end - addr) / PAGE_SIZE;
>> +
>> +                    step = folio_pte_batch(folio, addr, ptep, pte,
>> +                            max_nr, fpb_flags, NULL, NULL, NULL);
>> +                }
>> +            }
> 
> Can we go ahead with this along with [1], that will help us generalize 
> for all arches.
> 
> [1] https://lore.kernel.org/all/20250506050056.59250-3-dev.jain@arm.com/
> (Please replace PAGE_SIZE with 1)

As discussed with Ryan, we don’t need to call folio_pte_batch() 
(something like the code below), so your patch seems unnecessarily 
complicated. However, David is unhappy about the open-coded 
pte_batch_hint().

  static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned 
long addr,
                         unsigned long end, struct mm_walk *walk)
@@ -105,6 +106,7 @@ static int mincore_pte_range(pmd_t *pmd, unsigned 
long addr, unsigned long end,
         pte_t *ptep;
         unsigned char *vec = walk->private;
         int nr = (end - addr) >> PAGE_SHIFT;
+       int step, i;

         ptl = pmd_trans_huge_lock(pmd, vma);
         if (ptl) {
@@ -118,16 +120,21 @@ static int mincore_pte_range(pmd_t *pmd, unsigned 
long addr, unsigned long end,
                 walk->action = ACTION_AGAIN;
                 return 0;
         }
-       for (; addr != end; ptep++, addr += PAGE_SIZE) {
+       for (; addr != end; ptep += step, addr += step * PAGE_SIZE) {
                 pte_t pte = ptep_get(ptep);

+               step = 1;
                 /* We need to do cache lookup too for pte markers */
                 if (pte_none_mostly(pte))
                         __mincore_unmapped_range(addr, addr + PAGE_SIZE,
                                                  vma, vec);
-               else if (pte_present(pte))
-                       *vec = 1;
-               else { /* pte is a swap entry */
+               else if (pte_present(pte)) {
+                       unsigned int max_nr = (end - addr) / PAGE_SIZE;
+
+                       step = min(pte_batch_hint(ptep, pte), max_nr);
+                       for (i = 0; i < step; i++)
+                               vec[i] = 1;
+               } else { /* pte is a swap entry */
                         swp_entry_t entry = pte_to_swp_entry(pte);

                         if (non_swap_entry(entry)) {
@@ -146,7 +153,7 @@ static int mincore_pte_range(pmd_t *pmd, unsigned 
long addr, unsigned long end,
  #endif
                         }
                 }
-               vec++;
+               vec += step;
         }
         pte_unmap_unlock(ptep - 1, ptl);
  out: