The patch titled
Subject: mm/pagewalkers: ACTION_AGAIN if pte_offset_map_lock() fails
has been added to the -mm mm-unstable branch. Its filename is
mm-pagewalkers-action_again-if-pte_offset_map_lock-fails.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-pagewalkers-action_again-if-pte_offset_map_lock-fails.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/pagewalkers: ACTION_AGAIN if pte_offset_map_lock() fails
Date: Thu, 8 Jun 2023 18:17:26 -0700 (PDT)
Simple walk_page_range() users should set ACTION_AGAIN to retry when
pte_offset_map_lock() fails.
No need to check pmd_trans_unstable(): that was precisely to avoid the
possiblity of calling pte_offset_map() on a racily removed or inserted THP
entry, but such cases are now safely handled inside it. Likewise there is
no need to check pmd_none() or pmd_bad() before calling it.
Link: https://lkml.kernel.org/r/c77d9d10-3aad-e3ce-4896-99e91c7947f3@xxxxxxxxxx
Signed-off-by: Hugh Dickins <hughd@xxxxxxxxxx>
Reviewed-by: SeongJae Park <sj@xxxxxxxxxx> for mm/damon part
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: 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>
---
fs/proc/task_mmu.c | 32 ++++++++++++++++----------------
mm/damon/vaddr.c | 12 ++++++++----
mm/mempolicy.c | 7 ++++---
mm/mincore.c | 9 ++++-----
mm/mlock.c | 4 ++++
5 files changed, 36 insertions(+), 28 deletions(-)
--- a/fs/proc/task_mmu.c~mm-pagewalkers-action_again-if-pte_offset_map_lock-fails
+++ a/fs/proc/task_mmu.c
@@ -631,14 +631,11 @@ static int smaps_pte_range(pmd_t *pmd, u
goto out;
}
- if (pmd_trans_unstable(pmd))
- goto out;
- /*
- * The mmap_lock held all the way back in m_start() is what
- * keeps khugepaged out of here and from collapsing things
- * in here.
- */
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ if (!pte) {
+ walk->action = ACTION_AGAIN;
+ return 0;
+ }
for (; addr != end; pte++, addr += PAGE_SIZE)
smaps_pte_entry(pte, addr, walk);
pte_unmap_unlock(pte - 1, ptl);
@@ -1191,10 +1188,11 @@ out:
return 0;
}
- if (pmd_trans_unstable(pmd))
- return 0;
-
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ if (!pte) {
+ walk->action = ACTION_AGAIN;
+ return 0;
+ }
for (; addr != end; pte++, addr += PAGE_SIZE) {
ptent = *pte;
@@ -1538,9 +1536,6 @@ static int pagemap_pmd_range(pmd_t *pmdp
spin_unlock(ptl);
return err;
}
-
- if (pmd_trans_unstable(pmdp))
- return 0;
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/*
@@ -1548,6 +1543,10 @@ static int pagemap_pmd_range(pmd_t *pmdp
* goes beyond vma->vm_end.
*/
orig_pte = pte = pte_offset_map_lock(walk->mm, pmdp, addr, &ptl);
+ if (!pte) {
+ walk->action = ACTION_AGAIN;
+ return err;
+ }
for (; addr < end; pte++, addr += PAGE_SIZE) {
pagemap_entry_t pme;
@@ -1887,11 +1886,12 @@ static int gather_pte_stats(pmd_t *pmd,
spin_unlock(ptl);
return 0;
}
-
- if (pmd_trans_unstable(pmd))
- return 0;
#endif
orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ if (!pte) {
+ walk->action = ACTION_AGAIN;
+ return 0;
+ }
do {
struct page *page = can_gather_numa_stats(*pte, vma, addr);
if (!page)
--- a/mm/damon/vaddr.c~mm-pagewalkers-action_again-if-pte_offset_map_lock-fails
+++ a/mm/damon/vaddr.c
@@ -318,9 +318,11 @@ static int damon_mkold_pmd_entry(pmd_t *
spin_unlock(ptl);
}
- if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
- return 0;
pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ if (!pte) {
+ walk->action = ACTION_AGAIN;
+ return 0;
+ }
if (!pte_present(*pte))
goto out;
damon_ptep_mkold(pte, walk->vma, addr);
@@ -464,9 +466,11 @@ huge_out:
regular_page:
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
- if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
- return -EINVAL;
pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ if (!pte) {
+ walk->action = ACTION_AGAIN;
+ return 0;
+ }
if (!pte_present(*pte))
goto out;
folio = damon_get_folio(pte_pfn(*pte));
--- a/mm/mempolicy.c~mm-pagewalkers-action_again-if-pte_offset_map_lock-fails
+++ a/mm/mempolicy.c
@@ -514,10 +514,11 @@ static int queue_folios_pte_range(pmd_t
if (ptl)
return queue_folios_pmd(pmd, ptl, addr, end, walk);
- if (pmd_trans_unstable(pmd))
- return 0;
-
mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ if (!pte) {
+ walk->action = ACTION_AGAIN;
+ return 0;
+ }
for (; addr != end; pte++, addr += PAGE_SIZE) {
if (!pte_present(*pte))
continue;
--- a/mm/mincore.c~mm-pagewalkers-action_again-if-pte_offset_map_lock-fails
+++ a/mm/mincore.c
@@ -113,12 +113,11 @@ static int mincore_pte_range(pmd_t *pmd,
goto out;
}
- if (pmd_trans_unstable(pmd)) {
- __mincore_unmapped_range(addr, end, vma, vec);
- goto out;
- }
-
ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ if (!ptep) {
+ walk->action = ACTION_AGAIN;
+ return 0;
+ }
for (; addr != end; ptep++, addr += PAGE_SIZE) {
pte_t pte = *ptep;
--- a/mm/mlock.c~mm-pagewalkers-action_again-if-pte_offset_map_lock-fails
+++ a/mm/mlock.c
@@ -329,6 +329,10 @@ static int mlock_pte_range(pmd_t *pmd, u
}
start_pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ if (!start_pte) {
+ walk->action = ACTION_AGAIN;
+ return 0;
+ }
for (pte = start_pte; addr != end; pte++, addr += PAGE_SIZE) {
if (!pte_present(*pte))
continue;
_
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
