The patch titled
Subject: mm/khugepaged: allow pte_offset_map[_lock]() to fail
has been added to the -mm mm-unstable branch. Its filename is
mm-khugepaged-allow-pte_offset_map-to-fail.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-khugepaged-allow-pte_offset_map-to-fail.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: Hugh Dickins <hughd@xxxxxxxxxx>
Subject: mm/khugepaged: allow pte_offset_map[_lock]() to fail
Date: Thu, 8 Jun 2023 18:42:40 -0700 (PDT)
__collapse_huge_page_swapin(): don't drop the map after every pte, it only
has to be dropped by do_swap_page(); give up if pte_offset_map() fails;
trace_mm_collapse_huge_page_swapin() at the end, with result; fix comment
on returned result; fix vmf.pgoff, though it's not used.
collapse_huge_page(): use pte_offset_map_lock() on the _pmd returned from
clearing; allow failure, but it should be impossible there.
hpage_collapse_scan_pmd() and collapse_pte_mapped_thp() allow for
pte_offset_map_lock() failure.
Link: https://lkml.kernel.org/r/6513e85-d798-34ec-3762-7c24ffb9329@xxxxxxxxxx
Signed-off-by: Hugh Dickins <hughd@xxxxxxxxxx>
Reviewed-by: Yang Shi <shy828301@xxxxxxxxx>
Cc: Alistair Popple <apopple@xxxxxxxxxx>
Cc: Anshuman Khandual <anshuman.khandual@xxxxxxx>
Cc: Axel Rasmussen <axelrasmussen@xxxxxxxxxx>
Cc: Christophe Leroy <christophe.leroy@xxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: "Huang, Ying" <ying.huang@xxxxxxxxx>
Cc: Ira Weiny <ira.weiny@xxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Lorenzo Stoakes <lstoakes@xxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Mike Rapoport (IBM) <rppt@xxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>
Cc: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Qi Zheng <zhengqi.arch@xxxxxxxxxxxxx>
Cc: Ralph Campbell <rcampbell@xxxxxxxxxx>
Cc: Ryan Roberts <ryan.roberts@xxxxxxx>
Cc: SeongJae Park <sj@xxxxxxxxxx>
Cc: Song Liu <song@xxxxxxxxxx>
Cc: Steven Price <steven.price@xxxxxxx>
Cc: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Cc: Thomas Hellström <thomas.hellstrom@xxxxxxxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Yu Zhao <yuzhao@xxxxxxxxxx>
Cc: Zack Rusin <zackr@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/khugepaged.c | 72 +++++++++++++++++++++++++++++++---------------
1 file changed, 49 insertions(+), 23 deletions(-)
--- a/mm/khugepaged.c~mm-khugepaged-allow-pte_offset_map-to-fail
+++ a/mm/khugepaged.c
@@ -991,9 +991,8 @@ static int check_pmd_still_valid(struct
* Only done if hpage_collapse_scan_pmd believes it is worthwhile.
*
* Called and returns without pte mapped or spinlocks held.
- * Note that if false is returned, mmap_lock will be released.
+ * Returns result: if not SCAN_SUCCEED, mmap_lock has been released.
*/
-
static int __collapse_huge_page_swapin(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long haddr, pmd_t *pmd,
@@ -1002,23 +1001,35 @@ static int __collapse_huge_page_swapin(s
int swapped_in = 0;
vm_fault_t ret = 0;
unsigned long address, end = haddr + (HPAGE_PMD_NR * PAGE_SIZE);
+ int result;
+ pte_t *pte = NULL;
for (address = haddr; address < end; address += PAGE_SIZE) {
struct vm_fault vmf = {
.vma = vma,
.address = address,
- .pgoff = linear_page_index(vma, haddr),
+ .pgoff = linear_page_index(vma, address),
.flags = FAULT_FLAG_ALLOW_RETRY,
.pmd = pmd,
};
- vmf.pte = pte_offset_map(pmd, address);
- vmf.orig_pte = *vmf.pte;
- if (!is_swap_pte(vmf.orig_pte)) {
- pte_unmap(vmf.pte);
- continue;
+ if (!pte++) {
+ pte = pte_offset_map(pmd, address);
+ if (!pte) {
+ mmap_read_unlock(mm);
+ result = SCAN_PMD_NULL;
+ goto out;
+ }
}
+
+ vmf.orig_pte = *pte;
+ if (!is_swap_pte(vmf.orig_pte))
+ continue;
+
+ vmf.pte = pte;
ret = do_swap_page(&vmf);
+ /* Which unmaps pte (after perhaps re-checking the entry) */
+ pte = NULL;
/*
* do_swap_page returns VM_FAULT_RETRY with released mmap_lock.
@@ -1027,24 +1038,29 @@ static int __collapse_huge_page_swapin(s
* resulting in later failure.
*/
if (ret & VM_FAULT_RETRY) {
- trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
/* Likely, but not guaranteed, that page lock failed */
- return SCAN_PAGE_LOCK;
+ result = SCAN_PAGE_LOCK;
+ goto out;
}
if (ret & VM_FAULT_ERROR) {
mmap_read_unlock(mm);
- trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
- return SCAN_FAIL;
+ result = SCAN_FAIL;
+ goto out;
}
swapped_in++;
}
+ if (pte)
+ pte_unmap(pte);
+
/* Drain LRU add pagevec to remove extra pin on the swapped in pages */
if (swapped_in)
lru_add_drain();
- trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 1);
- return SCAN_SUCCEED;
+ result = SCAN_SUCCEED;
+out:
+ trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, result);
+ return result;
}
static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm,
@@ -1144,9 +1160,6 @@ static int collapse_huge_page(struct mm_
address + HPAGE_PMD_SIZE);
mmu_notifier_invalidate_range_start(&range);
- pte = pte_offset_map(pmd, address);
- pte_ptl = pte_lockptr(mm, pmd);
-
pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */
/*
* This removes any huge TLB entry from the CPU so we won't allow
@@ -1161,13 +1174,18 @@ static int collapse_huge_page(struct mm_
mmu_notifier_invalidate_range_end(&range);
tlb_remove_table_sync_one();
- spin_lock(pte_ptl);
- result = __collapse_huge_page_isolate(vma, address, pte, cc,
- &compound_pagelist);
- spin_unlock(pte_ptl);
+ pte = pte_offset_map_lock(mm, &_pmd, address, &pte_ptl);
+ if (pte) {
+ result = __collapse_huge_page_isolate(vma, address, pte, cc,
+ &compound_pagelist);
+ spin_unlock(pte_ptl);
+ } else {
+ result = SCAN_PMD_NULL;
+ }
if (unlikely(result != SCAN_SUCCEED)) {
- pte_unmap(pte);
+ if (pte)
+ pte_unmap(pte);
spin_lock(pmd_ptl);
BUG_ON(!pmd_none(*pmd));
/*
@@ -1251,6 +1269,11 @@ static int hpage_collapse_scan_pmd(struc
memset(cc->node_load, 0, sizeof(cc->node_load));
nodes_clear(cc->alloc_nmask);
pte = pte_offset_map_lock(mm, pmd, address, &ptl);
+ if (!pte) {
+ result = SCAN_PMD_NULL;
+ goto out;
+ }
+
for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR;
_pte++, _address += PAGE_SIZE) {
pte_t pteval = *_pte;
@@ -1620,8 +1643,10 @@ int collapse_pte_mapped_thp(struct mm_st
* lockless_pages_from_mm() and the hardware page walker can access page
* tables while all the high-level locks are held in write mode.
*/
- start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl);
result = SCAN_FAIL;
+ start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl);
+ if (!start_pte)
+ goto drop_immap;
/* step 1: check all mapped PTEs are to the right huge page */
for (i = 0, addr = haddr, pte = start_pte;
@@ -1695,6 +1720,7 @@ drop_hpage:
abort:
pte_unmap_unlock(start_pte, ptl);
+drop_immap:
i_mmap_unlock_write(vma->vm_file->f_mapping);
goto drop_hpage;
}
_
Patches currently in -mm which might be from hughd@xxxxxxxxxx are
arm-allow-pte_offset_map-to-fail.patch
arm64-allow-pte_offset_map-to-fail.patch
arm64-hugetlb-pte_alloc_huge-pte_offset_huge.patch
ia64-hugetlb-pte_alloc_huge-pte_offset_huge.patch
m68k-allow-pte_offset_map-to-fail.patch
microblaze-allow-pte_offset_map-to-fail.patch
mips-update_mmu_cache-can-replace-__update_tlb.patch
mips-update_mmu_cache-can-replace-__update_tlb-fix.patch
parisc-add-pte_unmap-to-balance-get_ptep.patch
parisc-unmap_uncached_pte-use-pte_offset_kernel.patch
parisc-hugetlb-pte_alloc_huge-pte_offset_huge.patch
powerpc-kvmppc_unmap_free_pmd-pte_offset_kernel.patch
powerpc-allow-pte_offset_map-to-fail.patch
powerpc-hugetlb-pte_alloc_huge.patch
riscv-hugetlb-pte_alloc_huge-pte_offset_huge.patch
s390-allow-pte_offset_map_lock-to-fail.patch
s390-gmap-use-pte_unmap_unlock-not-spin_unlock.patch
sh-hugetlb-pte_alloc_huge-pte_offset_huge.patch
sparc-hugetlb-pte_alloc_huge-pte_offset_huge.patch
sparc-allow-pte_offset_map-to-fail.patch
sparc-iounit-and-iommu-use-pte_offset_kernel.patch
x86-allow-get_locked_pte-to-fail.patch
x86-sme_populate_pgd-use-pte_offset_kernel.patch
xtensa-add-pte_unmap-to-balance-pte_offset_map.patch
mm-use-pmdp_get_lockless-without-surplus-barrier.patch
mm-migrate-remove-cruft-from-migration_entry_waits.patch
mm-pgtable-kmap_local_page-instead-of-kmap_atomic.patch
mm-pgtable-allow-pte_offset_map-to-fail.patch
mm-filemap-allow-pte_offset_map_lock-to-fail.patch
mm-page_vma_mapped-delete-bogosity-in-page_vma_mapped_walk.patch
mm-page_vma_mapped-reformat-map_pte-with-less-indentation.patch
mm-page_vma_mapped-pte_offset_map_nolock-not-pte_lockptr.patch
mm-pagewalkers-action_again-if-pte_offset_map_lock-fails.patch
mm-pagewalk-walk_pte_range-allow-for-pte_offset_map.patch
mm-vmwgfx-simplify-pmd-pud-mapping-dirty-helpers.patch
mm-vmalloc-vmalloc_to_page-use-pte_offset_kernel.patch
mm-hmm-retry-if-pte_offset_map-fails.patch
mm-userfaultfd-retry-if-pte_offset_map-fails.patch
mm-userfaultfd-allow-pte_offset_map_lock-to-fail.patch
mm-debug_vm_pgtablepage_table_check-warn-pte-map-fails.patch
mm-various-give-up-if-pte_offset_map-fails.patch
mm-mprotect-delete-pmd_none_or_clear_bad_unless_trans_huge.patch
mm-mremap-retry-if-either-pte_offset_map_lock-fails.patch
mm-madvise-clean-up-pte_offset_map_lock-scans.patch
mm-madvise-clean-up-force_shm_swapin_readahead.patch
mm-swapoff-allow-pte_offset_map-to-fail.patch
mm-mglru-allow-pte_offset_map_nolock-to-fail.patch
mm-migrate_device-allow-pte_offset_map_lock-to-fail.patch
mm-gup-remove-foll_split_pmd-use-of-pmd_trans_unstable.patch
mm-huge_memory-split-huge-pmd-under-one-pte_offset_map.patch
mm-khugepaged-allow-pte_offset_map-to-fail.patch
mm-memory-allow-pte_offset_map-to-fail.patch
mm-memory-handle_pte_fault-use-pte_offset_map_nolock.patch
mm-pgtable-delete-pmd_trans_unstable-and-friends.patch
mm-swap-swap_vma_readahead-do-the-pte_offset_map.patch
perf-core-allow-pte_offset_map-to-fail.patch
