The patch titled Subject: thp: Prepare for DAX huge pages has been added to the -mm tree. Its filename is thp-prepare-for-dax-huge-pages.patch This patch should soon appear at http://ozlabs.org/~akpm/mmots/broken-out/thp-prepare-for-dax-huge-pages.patch and later at http://ozlabs.org/~akpm/mmotm/broken-out/thp-prepare-for-dax-huge-pages.patch 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/SubmitChecklist when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Matthew Wilcox <willy@xxxxxxxxxxxxxxx> Subject: thp: Prepare for DAX huge pages Add a vma_is_dax() helper macro to test whether the VMA is DAX, and use it in zap_huge_pmd() and __split_huge_page_pmd(). Signed-off-by: Matthew Wilcox <willy@xxxxxxxxxxxxxxx> Cc: Hillf Danton <dhillf@xxxxxxxxx> Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx> Cc: Theodore Ts'o <tytso@xxxxxxx> Cc: Jan Kara <jack@xxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/dax.h | 4 +++ mm/huge_memory.c | 45 +++++++++++++++++++++++++----------------- 2 files changed, 31 insertions(+), 18 deletions(-) diff -puN include/linux/dax.h~thp-prepare-for-dax-huge-pages include/linux/dax.h --- a/include/linux/dax.h~thp-prepare-for-dax-huge-pages +++ a/include/linux/dax.h @@ -18,4 +18,8 @@ int dax_pfn_mkwrite(struct vm_area_struc #define dax_mkwrite(vma, vmf, gb, iod) dax_fault(vma, vmf, gb, iod) #define __dax_mkwrite(vma, vmf, gb, iod) __dax_fault(vma, vmf, gb, iod) +static inline bool vma_is_dax(struct vm_area_struct *vma) +{ + return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); +} #endif diff -puN mm/huge_memory.c~thp-prepare-for-dax-huge-pages mm/huge_memory.c --- a/mm/huge_memory.c~thp-prepare-for-dax-huge-pages +++ a/mm/huge_memory.c @@ -1418,7 +1418,6 @@ int zap_huge_pmd(struct mmu_gather *tlb, int ret = 0; if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { - struct page *page; pgtable_t pgtable; pmd_t orig_pmd; /* @@ -1430,13 +1429,22 @@ int zap_huge_pmd(struct mmu_gather *tlb, orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd, tlb->fullmm); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); - pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd); + if (vma_is_dax(vma)) { + if (is_huge_zero_pmd(orig_pmd)) { + pgtable = NULL; + } else { + spin_unlock(ptl); + return 1; + } + } else { + pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd); + } if (is_huge_zero_pmd(orig_pmd)) { atomic_long_dec(&tlb->mm->nr_ptes); spin_unlock(ptl); put_huge_zero_page(); } else { - page = pmd_page(orig_pmd); + struct page *page = pmd_page(orig_pmd); page_remove_rmap(page); VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); @@ -1445,7 +1453,8 @@ int zap_huge_pmd(struct mmu_gather *tlb, spin_unlock(ptl); tlb_remove_page(tlb, page); } - pte_free(tlb->mm, pgtable); + if (pgtable) + pte_free(tlb->mm, pgtable); ret = 1; } return ret; @@ -2916,7 +2925,7 @@ void __split_huge_page_pmd(struct vm_are pmd_t *pmd) { spinlock_t *ptl; - struct page *page; + struct page *page = NULL; struct mm_struct *mm = vma->vm_mm; unsigned long haddr = address & HPAGE_PMD_MASK; unsigned long mmun_start; /* For mmu_notifiers */ @@ -2929,25 +2938,25 @@ void __split_huge_page_pmd(struct vm_are again: mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); ptl = pmd_lock(mm, pmd); - if (unlikely(!pmd_trans_huge(*pmd))) { - spin_unlock(ptl); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - return; - } - if (is_huge_zero_pmd(*pmd)) { + if (unlikely(!pmd_trans_huge(*pmd))) + goto unlock; + if (vma_is_dax(vma)) { + pmdp_huge_clear_flush(vma, haddr, pmd); + } else if (is_huge_zero_pmd(*pmd)) { __split_huge_zero_page_pmd(vma, haddr, pmd); - spin_unlock(ptl); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - return; + } else { + page = pmd_page(*pmd); + VM_BUG_ON_PAGE(!page_count(page), page); + get_page(page); } - page = pmd_page(*pmd); - VM_BUG_ON_PAGE(!page_count(page), page); - get_page(page); + unlock: spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - split_huge_page(page); + if (!page) + return; + split_huge_page(page); put_page(page); /* _ Patches currently in -mm which might be from willy@xxxxxxxxxxxxxxx are mm-make-gup-handle-pfn-mapping-unless-foll_get-is-requested.patch dax-move-dax-related-functions-to-a-new-header.patch thp-prepare-for-dax-huge-pages.patch mm-add-a-pmd_fault-handler.patch mm-export-various-functions-for-the-benefit-of-dax.patch mm-add-vmf_insert_pfn_pmd.patch dax-add-huge-page-fault-support.patch ext2-huge-page-fault-support.patch ext4-huge-page-fault-support.patch xfs-huge-page-fault-support.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html