The patch titled
Subject: mm/swapoff: allow pte_offset_map[_lock]() to fail
has been added to the -mm mm-unstable branch. Its filename is
mm-swapoff-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-swapoff-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/swapoff: allow pte_offset_map[_lock]() to fail
Date: Thu, 8 Jun 2023 18:36:11 -0700 (PDT)
Adjust unuse_pte() and unuse_pte_range() to allow pte_offset_map_lock()
and pte_offset_map() failure; remove pmd_none_or_trans_huge_or_clear_bad()
from unuse_pmd_range() now that pte_offset_map() does all that itself.
Link: https://lkml.kernel.org/r/c4d831-13c3-9dfd-70c2-64514ad951fd@xxxxxxxxxx
Signed-off-by: Hugh Dickins <hughd@xxxxxxxxxx>
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: Yang Shi <shy828301@xxxxxxxxx>
Cc: Yu Zhao <yuzhao@xxxxxxxxxx>
Cc: Zack Rusin <zackr@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/swapfile.c | 38 ++++++++++++++++++++------------------
1 file changed, 20 insertions(+), 18 deletions(-)
--- a/mm/swapfile.c~mm-swapoff-allow-pte_offset_map-to-fail
+++ a/mm/swapfile.c
@@ -1757,7 +1757,7 @@ static int unuse_pte(struct vm_area_stru
hwposioned = true;
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
- if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) {
+ if (unlikely(!pte || !pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) {
ret = 0;
goto out;
}
@@ -1810,7 +1810,8 @@ setpte:
set_pte_at(vma->vm_mm, addr, pte, new_pte);
swap_free(entry);
out:
- pte_unmap_unlock(pte, ptl);
+ if (pte)
+ pte_unmap_unlock(pte, ptl);
if (page != swapcache) {
unlock_page(page);
put_page(page);
@@ -1822,17 +1823,22 @@ static int unuse_pte_range(struct vm_are
unsigned long addr, unsigned long end,
unsigned int type)
{
- swp_entry_t entry;
- pte_t *pte;
+ pte_t *pte = NULL;
struct swap_info_struct *si;
- int ret = 0;
si = swap_info[type];
- pte = pte_offset_map(pmd, addr);
do {
struct folio *folio;
unsigned long offset;
unsigned char swp_count;
+ swp_entry_t entry;
+ int ret;
+
+ if (!pte++) {
+ pte = pte_offset_map(pmd, addr);
+ if (!pte)
+ break;
+ }
if (!is_swap_pte(*pte))
continue;
@@ -1843,6 +1849,8 @@ static int unuse_pte_range(struct vm_are
offset = swp_offset(entry);
pte_unmap(pte);
+ pte = NULL;
+
folio = swap_cache_get_folio(entry, vma, addr);
if (!folio) {
struct page *page;
@@ -1861,8 +1869,7 @@ static int unuse_pte_range(struct vm_are
if (!folio) {
swp_count = READ_ONCE(si->swap_map[offset]);
if (swp_count == 0 || swp_count == SWAP_MAP_BAD)
- goto try_next;
-
+ continue;
return -ENOMEM;
}
@@ -1872,20 +1879,17 @@ static int unuse_pte_range(struct vm_are
if (ret < 0) {
folio_unlock(folio);
folio_put(folio);
- goto out;
+ return ret;
}
folio_free_swap(folio);
folio_unlock(folio);
folio_put(folio);
-try_next:
- pte = pte_offset_map(pmd, addr);
- } while (pte++, addr += PAGE_SIZE, addr != end);
- pte_unmap(pte - 1);
+ } while (addr += PAGE_SIZE, addr != end);
- ret = 0;
-out:
- return ret;
+ if (pte)
+ pte_unmap(pte);
+ return 0;
}
static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
@@ -1900,8 +1904,6 @@ static inline int unuse_pmd_range(struct
do {
cond_resched();
next = pmd_addr_end(addr, end);
- if (pmd_none_or_trans_huge_or_clear_bad(pmd))
- continue;
ret = unuse_pte_range(vma, pmd, addr, next, type);
if (ret)
return ret;
_
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
