The patch titled Subject: mm/thp: add flag to enforce sysfs THP in hugepage_vma_check() has been added to the -mm mm-unstable branch. Its filename is mm-thp-add-flag-to-enforce-sysfs-thp-in-hugepage_vma_check.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-thp-add-flag-to-enforce-sysfs-thp-in-hugepage_vma_check.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: "Zach O'Keefe" <zokeefe@xxxxxxxxxx> Subject: mm/thp: add flag to enforce sysfs THP in hugepage_vma_check() Date: Wed, 6 Jul 2022 16:59:25 -0700 MADV_COLLAPSE is not coupled to the kernel-oriented sysfs THP settings[1]. hugepage_vma_check() is the authority on determining if a VMA is eligible for THP allocation/collapse, and currently enforces the sysfs THP settings. Add a flag to disable these checks. For now, only apply this arg to anon and file, which use /sys/kernel/transparent_hugepage/enabled. We can expand this to shmem, which uses /sys/kernel/transparent_hugepage/shmem_enabled, later. Use this flag in collapse_pte_mapped_thp() where previously the VMA flags passed to hugepage_vma_check() were OR'd with VM_HUGEPAGE to elide the VM_HUGEPAGE check in "madvise" THP mode. Prior to "mm: khugepaged: check THP flag in hugepage_vma_check()", this check also didn't check "never" THP mode. As such, this restores the previous behavior of collapse_pte_mapped_thp() where sysfs THP settings are ignored. See comment in code for justification why this is OK. [1] https://lore.kernel.org/linux-mm/CAAa6QmQxay1_=Pmt8oCX2-Va18t44FV-Vs-WsQt_6+qBks4nZA@xxxxxxxxxxxxxx/ Link: https://lkml.kernel.org/r/20220706235936.2197195-8-zokeefe@xxxxxxxxxx Signed-off-by: Zach O'Keefe <zokeefe@xxxxxxxxxx> Cc: Alex Shi <alex.shi@xxxxxxxxxxxxxxxxx> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx> Cc: Arnd Bergmann <arnd@xxxxxxxx> Cc: Axel Rasmussen <axelrasmussen@xxxxxxxxxx> Cc: Chris Kennelly <ckennelly@xxxxxxxxxx> Cc: Chris Zankel <chris@xxxxxxxxxx> Cc: David Hildenbrand <david@xxxxxxxxxx> Cc: David Rientjes <rientjes@xxxxxxxxxx> Cc: Helge Deller <deller@xxxxxx> Cc: Hugh Dickins <hughd@xxxxxxxxxx> Cc: Ivan Kokshaysky <ink@xxxxxxxxxxxxxxxxxxxx> Cc: James Bottomley <James.Bottomley@xxxxxxxxxxxxxxxxxxxxx> Cc: Jens Axboe <axboe@xxxxxxxxx> Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx> Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx> Cc: Matt Turner <mattst88@xxxxxxxxx> Cc: Max Filippov <jcmvbkbc@xxxxxxxxx> Cc: Miaohe Lin <linmiaohe@xxxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxxx> Cc: Minchan Kim <minchan@xxxxxxxxxx> Cc: Pasha Tatashin <pasha.tatashin@xxxxxxxxxx> Cc: Pavel Begunkov <asml.silence@xxxxxxxxx> Cc: Peter Xu <peterx@xxxxxxxxxx> Cc: Rongwei Wang <rongwei.wang@xxxxxxxxxxxxxxxxx> Cc: SeongJae Park <sj@xxxxxxxxxx> Cc: Song Liu <songliubraving@xxxxxx> Cc: Thomas Bogendoerfer <tsbogend@xxxxxxxxxxxxxxxx> Cc: Vlastimil Babka <vbabka@xxxxxxx> Cc: Yang Shi <shy828301@xxxxxxxxx> Cc: Zi Yan <ziy@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- fs/proc/task_mmu.c | 2 +- include/linux/huge_mm.h | 9 ++++----- mm/huge_memory.c | 14 ++++++-------- mm/khugepaged.c | 25 ++++++++++++++----------- mm/memory.c | 4 ++-- 5 files changed, 27 insertions(+), 27 deletions(-) --- a/fs/proc/task_mmu.c~mm-thp-add-flag-to-enforce-sysfs-thp-in-hugepage_vma_check +++ a/fs/proc/task_mmu.c @@ -866,7 +866,7 @@ static int show_smap(struct seq_file *m, __show_smap(m, &mss, false); seq_printf(m, "THPeligible: %d\n", - hugepage_vma_check(vma, vma->vm_flags, true, false)); + hugepage_vma_check(vma, vma->vm_flags, true, false, true)); if (arch_pkeys_enabled()) seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma)); --- a/include/linux/huge_mm.h~mm-thp-add-flag-to-enforce-sysfs-thp-in-hugepage_vma_check +++ a/include/linux/huge_mm.h @@ -168,9 +168,8 @@ static inline bool file_thp_enabled(stru !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); } -bool hugepage_vma_check(struct vm_area_struct *vma, - unsigned long vm_flags, - bool smaps, bool in_pf); +bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, + bool smaps, bool in_pf, bool enforce_sysfs); #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ @@ -321,8 +320,8 @@ static inline bool transhuge_vma_suitabl } static inline bool hugepage_vma_check(struct vm_area_struct *vma, - unsigned long vm_flags, - bool smaps, bool in_pf) + unsigned long vm_flags, bool smaps, + bool in_pf, bool enforce_sysfs) { return false; } --- a/mm/huge_memory.c~mm-thp-add-flag-to-enforce-sysfs-thp-in-hugepage_vma_check +++ a/mm/huge_memory.c @@ -69,9 +69,8 @@ static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; unsigned long huge_zero_pfn __read_mostly = ~0UL; -bool hugepage_vma_check(struct vm_area_struct *vma, - unsigned long vm_flags, - bool smaps, bool in_pf) +bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, + bool smaps, bool in_pf, bool enforce_sysfs) { if (!vma->vm_mm) /* vdso */ return false; @@ -120,11 +119,10 @@ bool hugepage_vma_check(struct vm_area_s if (!in_pf && shmem_file(vma->vm_file)) return shmem_huge_enabled(vma); - if (!hugepage_flags_enabled()) - return false; - - /* THP settings require madvise. */ - if (!(vm_flags & VM_HUGEPAGE) && !hugepage_flags_always()) + /* Enforce sysfs THP requirements as necessary */ + if (enforce_sysfs && + (!hugepage_flags_enabled() || (!(vm_flags & VM_HUGEPAGE) && + !hugepage_flags_always()))) return false; /* Only regular file is valid */ --- a/mm/khugepaged.c~mm-thp-add-flag-to-enforce-sysfs-thp-in-hugepage_vma_check +++ a/mm/khugepaged.c @@ -478,7 +478,7 @@ void khugepaged_enter_vma(struct vm_area { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && hugepage_flags_enabled()) { - if (hugepage_vma_check(vma, vm_flags, false, false)) + if (hugepage_vma_check(vma, vm_flags, false, false, true)) __khugepaged_enter(vma->vm_mm); } } @@ -844,7 +844,8 @@ static bool khugepaged_alloc_page(struct */ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, - struct vm_area_struct **vmap) + struct vm_area_struct **vmap, + struct collapse_control *cc) { struct vm_area_struct *vma; @@ -855,7 +856,8 @@ static int hugepage_vma_revalidate(struc if (!vma) return SCAN_VMA_NULL; - if (!hugepage_vma_check(vma, vma->vm_flags, false, false)) + if (!hugepage_vma_check(vma, vma->vm_flags, false, false, + cc->is_khugepaged)) return SCAN_VMA_CHECK; /* * Anon VMA expected, the address may be unmapped then @@ -974,7 +976,7 @@ static int collapse_huge_page(struct mm_ goto out_nolock; mmap_read_lock(mm); - result = hugepage_vma_revalidate(mm, address, &vma); + result = hugepage_vma_revalidate(mm, address, &vma, cc); if (result != SCAN_SUCCEED) { mmap_read_unlock(mm); goto out_nolock; @@ -1006,7 +1008,7 @@ static int collapse_huge_page(struct mm_ * handled by the anon_vma lock + PG_lock. */ mmap_write_lock(mm); - result = hugepage_vma_revalidate(mm, address, &vma); + result = hugepage_vma_revalidate(mm, address, &vma, cc); if (result != SCAN_SUCCEED) goto out_up_write; /* check if the pmd is still valid */ @@ -1350,12 +1352,13 @@ void collapse_pte_mapped_thp(struct mm_s return; /* - * This vm_flags may not have VM_HUGEPAGE if the page was not - * collapsed by this mm. But we can still collapse if the page is - * the valid THP. Add extra VM_HUGEPAGE so hugepage_vma_check() - * will not fail the vma for missing VM_HUGEPAGE + * If we are here, we've succeeded in replacing all the native pages + * in the page cache with a single hugepage. If a mm were to fault-in + * this memory (mapped by a suitably aligned VMA), we'd get the hugepage + * and map it by a PMD, regardless of sysfs THP settings. As such, let's + * analogously elide sysfs THP settings here. */ - if (!hugepage_vma_check(vma, vma->vm_flags | VM_HUGEPAGE, false, false)) + if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false)) return; /* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */ @@ -2042,7 +2045,7 @@ static unsigned int khugepaged_scan_mm_s progress++; break; } - if (!hugepage_vma_check(vma, vma->vm_flags, false, false)) { + if (!hugepage_vma_check(vma, vma->vm_flags, false, false, true)) { skip: progress++; continue; --- a/mm/memory.c~mm-thp-add-flag-to-enforce-sysfs-thp-in-hugepage_vma_check +++ a/mm/memory.c @@ -5002,7 +5002,7 @@ static vm_fault_t __handle_mm_fault(stru return VM_FAULT_OOM; retry_pud: if (pud_none(*vmf.pud) && - hugepage_vma_check(vma, vm_flags, false, true)) { + hugepage_vma_check(vma, vm_flags, false, true, true)) { ret = create_huge_pud(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; @@ -5036,7 +5036,7 @@ retry_pud: goto retry_pud; if (pmd_none(*vmf.pmd) && - hugepage_vma_check(vma, vm_flags, false, true)) { + hugepage_vma_check(vma, vm_flags, false, true, true)) { ret = create_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; _ Patches currently in -mm which might be from zokeefe@xxxxxxxxxx are mm-khugepaged-remove-redundant-transhuge_vma_suitable-check.patch mm-khugepaged-add-struct-collapse_control.patch mm-khugepaged-dedup-and-simplify-hugepage-alloc-and-charging.patch mm-khugepaged-pipe-enum-scan_result-codes-back-to-callers.patch mm-khugepaged-add-flag-to-predicate-khugepaged-only-behavior.patch mm-thp-add-flag-to-enforce-sysfs-thp-in-hugepage_vma_check.patch mm-khugepaged-record-scan_pmd_mapped-when-scan_pmd-finds-hugepage.patch mm-madvise-introduce-madv_collapse-sync-hugepage-collapse.patch mm-khugepaged-rename-prefix-of-shared-collapse-functions.patch mm-madvise-add-huge_memory-mm_madvise_collapse-tracepoint.patch mm-madvise-add-madv_collapse-to-process_madvise.patch proc-smaps-add-pmdmappable-field-to-smaps.patch selftests-vm-modularize-collapse-selftests.patch selftests-vm-dedup-hugepage-allocation-logic.patch selftests-vm-add-madv_collapse-collapse-context-to-selftests.patch selftests-vm-add-selftest-to-verify-recollapse-of-thps.patch selftests-vm-add-selftest-to-verify-multi-thp-collapse.patch