The patch titled
Subject: mm/khugepaged: stop swapping in page when VM_FAULT_RETRY occurs
has been added to the -mm mm-unstable branch. Its filename is
mm-khugepaged-stop-swapping-in-page-when-vm_fault_retry-occurs.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-khugepaged-stop-swapping-in-page-when-vm_fault_retry-occurs.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Subject: mm/khugepaged: stop swapping in page when VM_FAULT_RETRY occurs
Date: Sat, 25 Jun 2022 17:28:11 +0800
When do_swap_page returns VM_FAULT_RETRY, we do not retry here and thus
swap entry will remain in pagetable. This will result in later failure.
So stop swapping in pages in this case to save cpu cycles. As A further
optimization, mmap_lock is released when __collapse_huge_page_swapin()
fails to avoid relocking mmap_lock. And "swapped_in++" is moved after
error handling to make it more accurate.
Link: https://lkml.kernel.org/r/20220625092816.4856-3-linmiaohe@xxxxxxxxxx
Signed-off-by: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Cc: Alistair Popple <apopple@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: David Howells <dhowells@xxxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: NeilBrown <neilb@xxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Yang Shi <shy828301@xxxxxxxxx>
Cc: Zach O'Keefe <zokeefe@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/khugepaged.c | 32 ++++++++++++++------------------
1 file changed, 14 insertions(+), 18 deletions(-)
--- a/mm/khugepaged.c~mm-khugepaged-stop-swapping-in-page-when-vm_fault_retry-occurs
+++ a/mm/khugepaged.c
@@ -940,8 +940,8 @@ static int hugepage_vma_revalidate(struc
* Bring missing pages in from swap, to complete THP collapse.
* Only done if khugepaged_scan_pmd believes it is worthwhile.
*
- * Called and returns without pte mapped or spinlocks held,
- * but with mmap_lock held to protect against vma changes.
+ * Called and returns without pte mapped or spinlocks held.
+ * Note that if false is returned, mmap_lock will be released.
*/
static bool __collapse_huge_page_swapin(struct mm_struct *mm,
@@ -968,27 +968,24 @@ static bool __collapse_huge_page_swapin(
pte_unmap(vmf.pte);
continue;
}
- swapped_in++;
ret = do_swap_page(&vmf);
- /* do_swap_page returns VM_FAULT_RETRY with released mmap_lock */
+ /*
+ * do_swap_page returns VM_FAULT_RETRY with released mmap_lock.
+ * Note we treat VM_FAULT_RETRY as VM_FAULT_ERROR here because
+ * we do not retry here and swap entry will remain in pagetable
+ * resulting in later failure.
+ */
if (ret & VM_FAULT_RETRY) {
- mmap_read_lock(mm);
- if (hugepage_vma_revalidate(mm, haddr, &vma)) {
- /* vma is no longer available, don't continue to swapin */
- trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
- return false;
- }
- /* check if the pmd is still valid */
- if (mm_find_pmd(mm, haddr) != pmd) {
- trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
- return false;
- }
+ trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
+ return false;
}
if (ret & VM_FAULT_ERROR) {
+ mmap_read_unlock(mm);
trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
return false;
}
+ swapped_in++;
}
/* Drain LRU add pagevec to remove extra pin on the swapped in pages */
@@ -1054,13 +1051,12 @@ static void collapse_huge_page(struct mm
}
/*
- * __collapse_huge_page_swapin always returns with mmap_lock locked.
- * If it fails, we release mmap_lock and jump out_nolock.
+ * __collapse_huge_page_swapin will return with mmap_lock released
+ * when it fails. So we jump out_nolock directly in that case.
* Continuing to collapse causes inconsistency.
*/
if (unmapped && !__collapse_huge_page_swapin(mm, vma, address,
pmd, referenced)) {
- mmap_read_unlock(mm);
goto out_nolock;
}
_
Patches currently in -mm which might be from linmiaohe@xxxxxxxxxx are
mm-migration-remove-unneeded-lock-page-and-pagemovable-check.patch
mm-migration-return-errno-when-isolate_huge_page-failed.patch
mm-migration-fix-potential-pte_unmap-on-an-not-mapped-pte.patch
mm-swapfile-make-security_vm_enough_memory_mm-work-as-expected.patch
mm-swapfile-fix-possible-data-races-of-inuse_pages.patch
mm-swap-remove-swap_cache_info-statistics.patch
mm-vmscan-dont-try-to-reclaim-freed-folios.patch
mm-page_alloc-minor-clean-up-for-memmap_init_compound.patch
mm-madvise-minor-cleanup-for-swapin_walk_pmd_entry.patch
mm-mmapc-fix-missing-call-to-vm_unacct_memory-in-mmap_region.patch
mm-khugepaged-remove-unneeded-shmem_huge_enabled-check.patch
mm-khugepaged-stop-swapping-in-page-when-vm_fault_retry-occurs.patch
mm-khugepaged-trivial-typo-and-codestyle-cleanup.patch
mm-khugepaged-minor-cleanup-for-collapse_file.patch
mm-khugepaged-use-helper-macro-__attr_rw.patch
mm-khugepaged-remove-unneeded-return-value-of-khugepaged_add_pte_mapped_thp.patch
mm-khugepaged-try-to-free-transhuge-swapcache-when-possible.patch
