From: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx> Subject: thp: skip file huge pmd on copy_huge_pmd() copy_page_range() has a check for "Don't copy ptes where a page fault will fill them correctly." It works on VMA level. We still copy all page table entries from private mappings, even if they map page cache. We can simplify copy_huge_pmd() a bit by skipping file PMDs. We don't map file private pages with PMDs, so they only can map page cache. It's safe to skip them as they can be re-faulted later. Link: http://lkml.kernel.org/r/1466021202-61880-17-git-send-email-kirill.shutemov@xxxxxxxxxxxxxxx Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/huge_memory.c | 34 ++++++++++++++++------------------ 1 file changed, 16 insertions(+), 18 deletions(-) diff -puN mm/huge_memory.c~thp-skip-file-huge-pmd-on-copy_huge_pmd mm/huge_memory.c --- a/mm/huge_memory.c~thp-skip-file-huge-pmd-on-copy_huge_pmd +++ a/mm/huge_memory.c @@ -1098,14 +1098,15 @@ int copy_huge_pmd(struct mm_struct *dst_ struct page *src_page; pmd_t pmd; pgtable_t pgtable = NULL; - int ret; + int ret = -ENOMEM; - if (!vma_is_dax(vma)) { - ret = -ENOMEM; - pgtable = pte_alloc_one(dst_mm, addr); - if (unlikely(!pgtable)) - goto out; - } + /* Skip if can be re-fill on fault */ + if (!vma_is_anonymous(vma)) + return 0; + + pgtable = pte_alloc_one(dst_mm, addr); + if (unlikely(!pgtable)) + goto out; dst_ptl = pmd_lock(dst_mm, dst_pmd); src_ptl = pmd_lockptr(src_mm, src_pmd); @@ -1113,7 +1114,7 @@ int copy_huge_pmd(struct mm_struct *dst_ ret = -EAGAIN; pmd = *src_pmd; - if (unlikely(!pmd_trans_huge(pmd) && !pmd_devmap(pmd))) { + if (unlikely(!pmd_trans_huge(pmd))) { pte_free(dst_mm, pgtable); goto out_unlock; } @@ -1136,16 +1137,13 @@ int copy_huge_pmd(struct mm_struct *dst_ goto out_unlock; } - if (!vma_is_dax(vma)) { - /* thp accounting separate from pmd_devmap accounting */ - src_page = pmd_page(pmd); - VM_BUG_ON_PAGE(!PageHead(src_page), src_page); - get_page(src_page); - page_dup_rmap(src_page, true); - add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); - atomic_long_inc(&dst_mm->nr_ptes); - pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); - } + src_page = pmd_page(pmd); + VM_BUG_ON_PAGE(!PageHead(src_page), src_page); + get_page(src_page); + page_dup_rmap(src_page, true); + add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); + atomic_long_inc(&dst_mm->nr_ptes); + pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); pmdp_set_wrprotect(src_mm, addr, src_pmd); pmd = pmd_mkold(pmd_wrprotect(pmd)); _ -- 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
