The patch titled
Subject: mm/mprotect: delete pmd_none_or_clear_bad_unless_trans_huge()
has been added to the -mm mm-unstable branch. Its filename is
mm-mprotect-delete-pmd_none_or_clear_bad_unless_trans_huge.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-mprotect-delete-pmd_none_or_clear_bad_unless_trans_huge.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/mprotect: delete pmd_none_or_clear_bad_unless_trans_huge()
Date: Thu, 8 Jun 2023 18:30:48 -0700 (PDT)
change_pmd_range() had special pmd_none_or_clear_bad_unless_trans_huge(),
required to avoid "bad" choices when setting automatic NUMA hinting under
mmap_read_lock(); but most of that is already covered in pte_offset_map()
now. change_pmd_range() just wants a pmd_none() check before wasting time
on MMU notifiers, then checks on the read-once _pmd value to work out
what's needed for huge cases. If change_pte_range() returns -EAGAIN to
retry if pte_offset_map_lock() fails, nothing more special is needed.
Link: https://lkml.kernel.org/r/725a42a9-91e9-c868-925-e3a5fd40bb4f@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/mprotect.c | 74 +++++++++++-------------------------------------
1 file changed, 17 insertions(+), 57 deletions(-)
--- a/mm/mprotect.c~mm-mprotect-delete-pmd_none_or_clear_bad_unless_trans_huge
+++ a/mm/mprotect.c
@@ -93,22 +93,9 @@ static long change_pte_range(struct mmu_
bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
tlb_change_page_size(tlb, PAGE_SIZE);
-
- /*
- * Can be called with only the mmap_lock for reading by
- * prot_numa so we must check the pmd isn't constantly
- * changing from under us from pmd_none to pmd_trans_huge
- * and/or the other way around.
- */
- if (pmd_trans_unstable(pmd))
- return 0;
-
- /*
- * The pmd points to a regular pte so the pmd can't change
- * from under us even if the mmap_lock is only hold for
- * reading.
- */
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ if (!pte)
+ return -EAGAIN;
/* Get target node for single threaded private VMAs */
if (prot_numa && !(vma->vm_flags & VM_SHARED) &&
@@ -302,26 +289,6 @@ static long change_pte_range(struct mmu_
}
/*
- * Used when setting automatic NUMA hinting protection where it is
- * critical that a numa hinting PMD is not confused with a bad PMD.
- */
-static inline int pmd_none_or_clear_bad_unless_trans_huge(pmd_t *pmd)
-{
- pmd_t pmdval = pmdp_get_lockless(pmd);
-
- if (pmd_none(pmdval))
- return 1;
- if (pmd_trans_huge(pmdval))
- return 0;
- if (unlikely(pmd_bad(pmdval))) {
- pmd_clear_bad(pmd);
- return 1;
- }
-
- return 0;
-}
-
-/*
* Return true if we want to split THPs into PTE mappings in change
* protection procedure, false otherwise.
*/
@@ -398,7 +365,8 @@ static inline long change_pmd_range(stru
pmd = pmd_offset(pud, addr);
do {
long ret;
-
+ pmd_t _pmd;
+again:
next = pmd_addr_end(addr, end);
ret = change_pmd_prepare(vma, pmd, cp_flags);
@@ -406,16 +374,8 @@ static inline long change_pmd_range(stru
pages = ret;
break;
}
- /*
- * Automatic NUMA balancing walks the tables with mmap_lock
- * held for read. It's possible a parallel update to occur
- * between pmd_trans_huge() and a pmd_none_or_clear_bad()
- * check leading to a false positive and clearing.
- * Hence, it's necessary to atomically read the PMD value
- * for all the checks.
- */
- if (!is_swap_pmd(*pmd) && !pmd_devmap(*pmd) &&
- pmd_none_or_clear_bad_unless_trans_huge(pmd))
+
+ if (pmd_none(*pmd))
goto next;
/* invoke the mmu notifier if the pmd is populated */
@@ -426,7 +386,8 @@ static inline long change_pmd_range(stru
mmu_notifier_invalidate_range_start(&range);
}
- if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
+ _pmd = pmdp_get_lockless(pmd);
+ if (is_swap_pmd(_pmd) || pmd_trans_huge(_pmd) || pmd_devmap(_pmd)) {
if ((next - addr != HPAGE_PMD_SIZE) ||
pgtable_split_needed(vma, cp_flags)) {
__split_huge_pmd(vma, pmd, addr, false, NULL);
@@ -441,15 +402,10 @@ static inline long change_pmd_range(stru
break;
}
} else {
- /*
- * change_huge_pmd() does not defer TLB flushes,
- * so no need to propagate the tlb argument.
- */
- int nr_ptes = change_huge_pmd(tlb, vma, pmd,
+ ret = change_huge_pmd(tlb, vma, pmd,
addr, newprot, cp_flags);
-
- if (nr_ptes) {
- if (nr_ptes == HPAGE_PMD_NR) {
+ if (ret) {
+ if (ret == HPAGE_PMD_NR) {
pages += HPAGE_PMD_NR;
nr_huge_updates++;
}
@@ -460,8 +416,12 @@ static inline long change_pmd_range(stru
}
/* fall through, the trans huge pmd just split */
}
- pages += change_pte_range(tlb, vma, pmd, addr, next,
- newprot, cp_flags);
+
+ ret = change_pte_range(tlb, vma, pmd, addr, next, newprot,
+ cp_flags);
+ if (ret < 0)
+ goto again;
+ pages += ret;
next:
cond_resched();
} while (pmd++, addr = next, addr != end);
_
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
