From: Barry Song <v-songbaohua@xxxxxxxx>
Currently, the PTEs and rmap of a large folio are removed one at a time.
This is not only slow but also causes the large folio to be unnecessarily
added to deferred_split, which can lead to races between the
deferred_split shrinker callback and memory reclamation. This patch
releases all PTEs and rmap entries in a batch.
Currently, it only handles lazyfree large folios.
The below microbench tries to reclaim 128MB lazyfree large folios
whose sizes are 64KiB:
#include <stdio.h>
#include <sys/mman.h>
#include <string.h>
#include <time.h>
#define SIZE 128*1024*1024 // 128 MB
unsigned long read_split_deferred()
{
FILE *file = fopen("/sys/kernel/mm/transparent_hugepage"
"/hugepages-64kB/stats/split_deferred", "r");
if (!file) {
perror("Error opening file");
return 0;
}
unsigned long value;
if (fscanf(file, "%lu", &value) != 1) {
perror("Error reading value");
fclose(file);
return 0;
}
fclose(file);
return value;
}
int main(int argc, char *argv[])
{
while(1) {
volatile int *p = mmap(0, SIZE, PROT_READ | PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
memset((void *)p, 1, SIZE);
madvise((void *)p, SIZE, MADV_FREE);
clock_t start_time = clock();
unsigned long start_split = read_split_deferred();
madvise((void *)p, SIZE, MADV_PAGEOUT);
clock_t end_time = clock();
unsigned long end_split = read_split_deferred();
double elapsed_time = (double)(end_time - start_time) / CLOCKS_PER_SEC;
printf("Time taken by reclamation: %f seconds, split_deferred: %ld\n",
elapsed_time, end_split - start_split);
munmap((void *)p, SIZE);
}
return 0;
}
w/o patch:
~ # ./a.out
Time taken by reclamation: 0.177418 seconds, split_deferred: 2048
Time taken by reclamation: 0.178348 seconds, split_deferred: 2048
Time taken by reclamation: 0.174525 seconds, split_deferred: 2048
Time taken by reclamation: 0.171620 seconds, split_deferred: 2048
Time taken by reclamation: 0.172241 seconds, split_deferred: 2048
Time taken by reclamation: 0.174003 seconds, split_deferred: 2048
Time taken by reclamation: 0.171058 seconds, split_deferred: 2048
Time taken by reclamation: 0.171993 seconds, split_deferred: 2048
Time taken by reclamation: 0.169829 seconds, split_deferred: 2048
Time taken by reclamation: 0.172895 seconds, split_deferred: 2048
Time taken by reclamation: 0.176063 seconds, split_deferred: 2048
Time taken by reclamation: 0.172568 seconds, split_deferred: 2048
Time taken by reclamation: 0.171185 seconds, split_deferred: 2048
Time taken by reclamation: 0.170632 seconds, split_deferred: 2048
Time taken by reclamation: 0.170208 seconds, split_deferred: 2048
Time taken by reclamation: 0.174192 seconds, split_deferred: 2048
...
w/ patch:
~ # ./a.out
Time taken by reclamation: 0.074231 seconds, split_deferred: 0
Time taken by reclamation: 0.071026 seconds, split_deferred: 0
Time taken by reclamation: 0.072029 seconds, split_deferred: 0
Time taken by reclamation: 0.071873 seconds, split_deferred: 0
Time taken by reclamation: 0.073573 seconds, split_deferred: 0
Time taken by reclamation: 0.071906 seconds, split_deferred: 0
Time taken by reclamation: 0.073604 seconds, split_deferred: 0
Time taken by reclamation: 0.075903 seconds, split_deferred: 0
Time taken by reclamation: 0.073191 seconds, split_deferred: 0
Time taken by reclamation: 0.071228 seconds, split_deferred: 0
Time taken by reclamation: 0.071391 seconds, split_deferred: 0
Time taken by reclamation: 0.071468 seconds, split_deferred: 0
Time taken by reclamation: 0.071896 seconds, split_deferred: 0
Time taken by reclamation: 0.072508 seconds, split_deferred: 0
Time taken by reclamation: 0.071884 seconds, split_deferred: 0
Time taken by reclamation: 0.072433 seconds, split_deferred: 0
Time taken by reclamation: 0.071939 seconds, split_deferred: 0
...
Signed-off-by: Barry Song <v-songbaohua@xxxxxxxx>
---
mm/rmap.c | 48 ++++++++++++++++++++++++++++++++++++++++++------
1 file changed, 42 insertions(+), 6 deletions(-)
diff --git a/mm/rmap.c b/mm/rmap.c
index 365112af5291..9424b96f8482 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1642,6 +1642,27 @@ void folio_remove_rmap_pmd(struct folio *folio, struct page *page,
#endif
}
+/* We support batch unmapping of PTEs for lazyfree large folios */
+static inline bool can_batch_unmap_folio_ptes(unsigned long addr,
+ struct folio *folio, pte_t *ptep)
+{
+ const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY;
+ int max_nr = folio_nr_pages(folio);
+ pte_t pte = ptep_get(ptep);
+
+ if (pte_none(pte))
+ return false;
+ if (!pte_present(pte))
+ return false;
+ if (!folio_test_anon(folio))
+ return false;
+ if (folio_test_swapbacked(folio))
+ return false;
+
+ return folio_pte_batch(folio, addr, ptep, pte, max_nr, fpb_flags, NULL,
+ NULL, NULL) == max_nr;
+}
+
/*
* @arg: enum ttu_flags will be passed to this argument
*/
@@ -1655,6 +1676,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
bool anon_exclusive, ret = true;
struct mmu_notifier_range range;
enum ttu_flags flags = (enum ttu_flags)(long)arg;
+ int nr_pages = 1;
unsigned long pfn;
unsigned long hsz = 0;
@@ -1780,6 +1802,15 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
hugetlb_vma_unlock_write(vma);
}
pteval = huge_ptep_clear_flush(vma, address, pvmw.pte);
+ } else if (folio_test_large(folio) &&
+ can_batch_unmap_folio_ptes(address, folio, pvmw.pte)) {
+ nr_pages = folio_nr_pages(folio);
+ flush_cache_range(vma, range.start, range.end);
+ pteval = get_and_clear_full_ptes(mm, address, pvmw.pte, nr_pages, 0);
+ if (should_defer_flush(mm, flags))
+ set_tlb_ubc_flush_pending(mm, pteval, address, folio_size(folio));
+ else
+ flush_tlb_range(vma, range.start, range.end);
} else {
flush_cache_page(vma, address, pfn);
/* Nuke the page table entry. */
@@ -1875,7 +1906,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
* redirtied either using the page table or a previously
* obtained GUP reference.
*/
- set_pte_at(mm, address, pvmw.pte, pteval);
+ set_ptes(mm, address, pvmw.pte, pteval, nr_pages);
folio_set_swapbacked(folio);
goto walk_abort;
} else if (ref_count != 1 + map_count) {
@@ -1888,10 +1919,10 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
* We'll come back here later and detect if the folio was
* dirtied when the additional reference is gone.
*/
- set_pte_at(mm, address, pvmw.pte, pteval);
+ set_ptes(mm, address, pvmw.pte, pteval, nr_pages);
goto walk_abort;
}
- dec_mm_counter(mm, MM_ANONPAGES);
+ add_mm_counter(mm, MM_ANONPAGES, -nr_pages);
goto discard;
}
@@ -1943,13 +1974,18 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
dec_mm_counter(mm, mm_counter_file(folio));
}
discard:
- if (unlikely(folio_test_hugetlb(folio)))
+ if (unlikely(folio_test_hugetlb(folio))) {
hugetlb_remove_rmap(folio);
- else
- folio_remove_rmap_pte(folio, subpage, vma);
+ } else {
+ folio_remove_rmap_ptes(folio, subpage, nr_pages, vma);
+ folio_ref_sub(folio, nr_pages - 1);
+ }
if (vma->vm_flags & VM_LOCKED)
mlock_drain_local();
folio_put(folio);
+ /* We have already batched the entire folio */
+ if (nr_pages > 1)
+ goto walk_done;
continue;
walk_abort:
ret = false;
--
2.39.3 (Apple Git-146)
