The quilt patch titled
Subject: mm/khugepaged: refactor collapse_file control flow
has been removed from the -mm tree. Its filename was
mm-khugepaged-refactor-collapse_file-control-flow.patch
This patch was dropped because an updated version will be merged
------------------------------------------------------
From: David Stevens <stevensd@xxxxxxxxxxxx>
Subject: mm/khugepaged: refactor collapse_file control flow
Date: Tue, 7 Mar 2023 14:20:34 +0900
Patch series "mm/khugepaged: fix khugepaged+shmem races", v5.
Fix two races in khugepaged+shmem that cause issues with userfaultfd and
lseek, respectively.
This patch (of 3):
Add a rollback label to deal with failure, instead of continuously
checking for RESULT_SUCCESS, to make it easier to add more failure cases.
The refactoring also allows the collapse_file tracepoint to include hpage
on success (instead of NULL).
Link: https://lkml.kernel.org/r/20230307052036.1520708-1-stevensd@xxxxxxxxxx
Link: https://lkml.kernel.org/r/20230307052036.1520708-2-stevensd@xxxxxxxxxx
Signed-off-by: David Stevens <stevensd@xxxxxxxxxxxx>
Acked-by: Peter Xu <peterx@xxxxxxxxxx>
Reviewed-by: Yang Shi <shy828301@xxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Jiaqi Yan <jiaqiyan@xxxxxxxxxx>
Cc: "Kirill A . Shutemov" <kirill@xxxxxxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
--- a/mm/khugepaged.c~mm-khugepaged-refactor-collapse_file-control-flow
+++ a/mm/khugepaged.c
@@ -1907,6 +1907,12 @@ static int collapse_file(struct mm_struc
if (result != SCAN_SUCCEED)
goto out;
+ __SetPageLocked(hpage);
+ if (is_shmem)
+ __SetPageSwapBacked(hpage);
+ hpage->index = start;
+ hpage->mapping = mapping;
+
/*
* Ensure we have slots for all the pages in the range. This is
* almost certainly a no-op because most of the pages must be present
@@ -1919,16 +1925,10 @@ static int collapse_file(struct mm_struc
xas_unlock_irq(&xas);
if (!xas_nomem(&xas, GFP_KERNEL)) {
result = SCAN_FAIL;
- goto out;
+ goto rollback;
}
} while (1);
- __SetPageLocked(hpage);
- if (is_shmem)
- __SetPageSwapBacked(hpage);
- hpage->index = start;
- hpage->mapping = mapping;
-
/*
* At this point the hpage is locked and not up-to-date.
* It's safe to insert it into the page cache, because nobody would
@@ -2145,129 +2145,126 @@ xa_unlocked:
*/
try_to_unmap_flush();
- if (result == SCAN_SUCCEED) {
- /*
- * Replacing old pages with new one has succeeded, now we
- * attempt to copy the contents.
- */
- index = start;
- list_for_each_entry(page, &pagelist, lru) {
- while (index < page->index) {
- clear_highpage(hpage + (index % HPAGE_PMD_NR));
- index++;
- }
- if (copy_mc_highpage(hpage + (page->index % HPAGE_PMD_NR),
- page) > 0) {
- result = SCAN_COPY_MC;
- break;
- }
- index++;
- }
- while (result == SCAN_SUCCEED && index < end) {
+ if (result != SCAN_SUCCEED)
+ goto rollback;
+
+ /*
+ * Replacing old pages with new one has succeeded, now we
+ * attempt to copy the contents.
+ */
+ index = start;
+ list_for_each_entry(page, &pagelist, lru) {
+ while (index < page->index) {
clear_highpage(hpage + (index % HPAGE_PMD_NR));
index++;
}
- }
-
- if (result == SCAN_SUCCEED) {
- /*
- * Copying old pages to huge one has succeeded, now we
- * need to free the old pages.
- */
- list_for_each_entry_safe(page, tmp, &pagelist, lru) {
- list_del(&page->lru);
- page->mapping = NULL;
- page_ref_unfreeze(page, 1);
- ClearPageActive(page);
- ClearPageUnevictable(page);
- unlock_page(page);
- put_page(page);
+ if (copy_mc_highpage(hpage + (page->index % HPAGE_PMD_NR), page) > 0) {
+ result = SCAN_COPY_MC;
+ goto rollback;
}
+ index++;
+ }
+ while (index < end) {
+ clear_highpage(hpage + (index % HPAGE_PMD_NR));
+ index++;
+ }
- xas_lock_irq(&xas);
- if (is_shmem)
- __mod_lruvec_page_state(hpage, NR_SHMEM_THPS, nr);
- else
- __mod_lruvec_page_state(hpage, NR_FILE_THPS, nr);
-
- if (nr_none) {
- __mod_lruvec_page_state(hpage, NR_FILE_PAGES, nr_none);
- /* nr_none is always 0 for non-shmem. */
- __mod_lruvec_page_state(hpage, NR_SHMEM, nr_none);
- }
- /* Join all the small entries into a single multi-index entry. */
- xas_set_order(&xas, start, HPAGE_PMD_ORDER);
- xas_store(&xas, hpage);
- xas_unlock_irq(&xas);
+ /*
+ * Copying old pages to huge one has succeeded, now we
+ * need to free the old pages.
+ */
+ list_for_each_entry_safe(page, tmp, &pagelist, lru) {
+ list_del(&page->lru);
+ page->mapping = NULL;
+ page_ref_unfreeze(page, 1);
+ ClearPageActive(page);
+ ClearPageUnevictable(page);
+ unlock_page(page);
+ put_page(page);
+ }
- folio = page_folio(hpage);
- folio_mark_uptodate(folio);
- folio_ref_add(folio, HPAGE_PMD_NR - 1);
-
- if (is_shmem)
- folio_mark_dirty(folio);
- folio_add_lru(folio);
+ xas_lock_irq(&xas);
+ if (is_shmem)
+ __mod_lruvec_page_state(hpage, NR_SHMEM_THPS, nr);
+ else
+ __mod_lruvec_page_state(hpage, NR_FILE_THPS, nr);
+
+ if (nr_none) {
+ __mod_lruvec_page_state(hpage, NR_FILE_PAGES, nr_none);
+ /* nr_none is always 0 for non-shmem. */
+ __mod_lruvec_page_state(hpage, NR_SHMEM, nr_none);
+ }
+ /* Join all the small entries into a single multi-index entry. */
+ xas_set_order(&xas, start, HPAGE_PMD_ORDER);
+ xas_store(&xas, hpage);
+ xas_unlock_irq(&xas);
- /*
- * Remove pte page tables, so we can re-fault the page as huge.
- */
- result = retract_page_tables(mapping, start, mm, addr, hpage,
- cc);
- unlock_page(hpage);
- hpage = NULL;
- } else {
- /* Something went wrong: roll back page cache changes */
- xas_lock_irq(&xas);
- if (nr_none) {
- mapping->nrpages -= nr_none;
- shmem_uncharge(mapping->host, nr_none);
- }
+ folio = page_folio(hpage);
+ folio_mark_uptodate(folio);
+ folio_ref_add(folio, HPAGE_PMD_NR - 1);
- xas_set(&xas, start);
- xas_for_each(&xas, page, end - 1) {
- page = list_first_entry_or_null(&pagelist,
- struct page, lru);
- if (!page || xas.xa_index < page->index) {
- if (!nr_none)
- break;
- nr_none--;
- /* Put holes back where they were */
- xas_store(&xas, NULL);
- continue;
- }
+ if (is_shmem)
+ folio_mark_dirty(folio);
+ folio_add_lru(folio);
- VM_BUG_ON_PAGE(page->index != xas.xa_index, page);
+ /*
+ * Remove pte page tables, so we can re-fault the page as huge.
+ */
+ result = retract_page_tables(mapping, start, mm, addr, hpage,
+ cc);
+ unlock_page(hpage);
+ goto out;
+
+rollback:
+ /* Something went wrong: roll back page cache changes */
+ xas_lock_irq(&xas);
+ if (nr_none) {
+ mapping->nrpages -= nr_none;
+ shmem_uncharge(mapping->host, nr_none);
+ }
- /* Unfreeze the page. */
- list_del(&page->lru);
- page_ref_unfreeze(page, 2);
- xas_store(&xas, page);
- xas_pause(&xas);
- xas_unlock_irq(&xas);
- unlock_page(page);
- putback_lru_page(page);
- xas_lock_irq(&xas);
+ xas_set(&xas, start);
+ xas_for_each(&xas, page, end - 1) {
+ page = list_first_entry_or_null(&pagelist,
+ struct page, lru);
+ if (!page || xas.xa_index < page->index) {
+ if (!nr_none)
+ break;
+ nr_none--;
+ /* Put holes back where they were */
+ xas_store(&xas, NULL);
+ continue;
}
- VM_BUG_ON(nr_none);
- /*
- * Undo the updates of filemap_nr_thps_inc for non-SHMEM file only.
- * This undo is not needed unless failure is due to SCAN_COPY_MC.
- */
- if (!is_shmem && result == SCAN_COPY_MC)
- filemap_nr_thps_dec(mapping);
+ VM_BUG_ON_PAGE(page->index != xas.xa_index, page);
+
+ /* Unfreeze the page. */
+ list_del(&page->lru);
+ page_ref_unfreeze(page, 2);
+ xas_store(&xas, page);
+ xas_pause(&xas);
xas_unlock_irq(&xas);
-
- hpage->mapping = NULL;
+ unlock_page(page);
+ putback_lru_page(page);
+ xas_lock_irq(&xas);
}
+ VM_BUG_ON(nr_none);
+ /*
+ * Undo the updates of filemap_nr_thps_inc for non-SHMEM file only.
+ * This undo is not needed unless failure is due to SCAN_COPY_MC.
+ */
+ if (!is_shmem && result == SCAN_COPY_MC)
+ filemap_nr_thps_dec(mapping);
+
+ xas_unlock_irq(&xas);
+
+ hpage->mapping = NULL;
+
+ unlock_page(hpage);
+ put_page(hpage);
- if (hpage)
- unlock_page(hpage);
out:
VM_BUG_ON(!list_empty(&pagelist));
- if (hpage)
- put_page(hpage);
-
trace_mm_khugepaged_collapse_file(mm, hpage, index, is_shmem, addr, file, nr, result);
return result;
}
_
Patches currently in -mm which might be from stevensd@xxxxxxxxxxxx are
mm-khugepaged-skip-shmem-with-userfaultfd.patch
mm-khugepaged-maintain-page-cache-uptodate-flag.patch
