The patch titled Subject: mm: numa: do not trap faults on the huge zero page has been added to the -mm tree. Its filename is mm-numa-do-not-trap-faults-on-the-huge-zero-page.patch This patch should soon appear at http://ozlabs.org/~akpm/mmots/broken-out/mm-numa-do-not-trap-faults-on-the-huge-zero-page.patch and later at http://ozlabs.org/~akpm/mmotm/broken-out/mm-numa-do-not-trap-faults-on-the-huge-zero-page.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: Mel Gorman <mgorman@xxxxxxx> Subject: mm: numa: do not trap faults on the huge zero page Faults on the huge zero page are pointless and there is a BUG_ON to catch them during fault time. This patch reintroduces a check that avoids marking the zero page PAGE_NONE. Signed-off-by: Mel Gorman <mgorman@xxxxxxx> Cc: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx> Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx> Cc: Dave Jones <davej@xxxxxxxxxx> Cc: Hugh Dickins <hughd@xxxxxxxxxx> Cc: Ingo Molnar <mingo@xxxxxxxxxx> Cc: Kirill Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx> Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Cc: Paul Mackerras <paulus@xxxxxxxxx> Cc: Rik van Riel <riel@xxxxxxxxxx> Cc: Sasha Levin <sasha.levin@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/huge_mm.h | 3 ++- mm/huge_memory.c | 13 ++++++++++++- mm/memory.c | 1 - mm/mprotect.c | 14 +++++++++++++- 4 files changed, 27 insertions(+), 4 deletions(-) diff -puN include/linux/huge_mm.h~mm-numa-do-not-trap-faults-on-the-huge-zero-page include/linux/huge_mm.h --- a/include/linux/huge_mm.h~mm-numa-do-not-trap-faults-on-the-huge-zero-page +++ a/include/linux/huge_mm.h @@ -31,7 +31,8 @@ extern int move_huge_pmd(struct vm_area_ unsigned long new_addr, unsigned long old_end, pmd_t *old_pmd, pmd_t *new_pmd); extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, pgprot_t newprot); + unsigned long addr, pgprot_t newprot, + int prot_numa); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_FLAG, diff -puN mm/huge_memory.c~mm-numa-do-not-trap-faults-on-the-huge-zero-page mm/huge_memory.c --- a/mm/huge_memory.c~mm-numa-do-not-trap-faults-on-the-huge-zero-page +++ a/mm/huge_memory.c @@ -1497,7 +1497,7 @@ out: * - HPAGE_PMD_NR is protections changed and TLB flush necessary */ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, pgprot_t newprot) + unsigned long addr, pgprot_t newprot, int prot_numa) { struct mm_struct *mm = vma->vm_mm; spinlock_t *ptl; @@ -1505,6 +1505,17 @@ int change_huge_pmd(struct vm_area_struc if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { pmd_t entry; + + /* + * Avoid trapping faults against the zero page. The read-only + * data is likely to be read-cached on the local CPU and + * local/remote hits to the zero page are not interesting. + */ + if (prot_numa && is_huge_zero_pmd(*pmd)) { + spin_unlock(ptl); + return 0; + } + ret = 1; entry = pmdp_get_and_clear_notify(mm, addr, pmd); entry = pmd_modify(entry, newprot); diff -puN mm/memory.c~mm-numa-do-not-trap-faults-on-the-huge-zero-page mm/memory.c --- a/mm/memory.c~mm-numa-do-not-trap-faults-on-the-huge-zero-page +++ a/mm/memory.c @@ -3037,7 +3037,6 @@ static int do_numa_page(struct mm_struct pte_unmap_unlock(ptep, ptl); return 0; } - BUG_ON(is_zero_pfn(page_to_pfn(page))); /* * Avoid grouping on DSO/COW pages in specific and RO pages diff -puN mm/mprotect.c~mm-numa-do-not-trap-faults-on-the-huge-zero-page mm/mprotect.c --- a/mm/mprotect.c~mm-numa-do-not-trap-faults-on-the-huge-zero-page +++ a/mm/mprotect.c @@ -76,6 +76,18 @@ static unsigned long change_pte_range(st if (pte_present(oldpte)) { pte_t ptent; + /* + * Avoid trapping faults against the zero or KSM + * pages. See similar comment in change_huge_pmd. + */ + if (prot_numa) { + struct page *page; + + page = vm_normal_page(vma, addr, oldpte); + if (!page || PageKsm(page)) + continue; + } + ptent = ptep_modify_prot_start(mm, addr, pte); ptent = pte_modify(ptent, newprot); @@ -142,7 +154,7 @@ static inline unsigned long change_pmd_r split_huge_page_pmd(vma, addr, pmd); else { int nr_ptes = change_huge_pmd(vma, pmd, addr, - newprot); + newprot, prot_numa); if (nr_ptes) { if (nr_ptes == HPAGE_PMD_NR) { _ Patches currently in -mm which might be from mgorman@xxxxxxx are mm-debug-pagealloc-prepare-boottime-configurable-on-off.patch mm-vmscan-prevent-kswapd-livelock-due-to-pfmemalloc-throttled-process-being-killed.patch mm-page_alloc-place-zone_id-check-before-vm_bug_on_page-check.patch mm-vmscan-wake-up-all-pfmemalloc-throttled-processes-at-once.patch mm-numa-do-not-dereference-pmd-outside-of-the-lock-during-numa-hinting-fault.patch mm-add-p-protnone-helpers-for-use-by-numa-balancing.patch mm-convert-p_numa-users-to-p_protnone_numa.patch ppc64-add-paranoid-warnings-for-unexpected-dsisr_protfault.patch mm-convert-p_mknonnuma-and-remaining-page-table-manipulations.patch mm-remove-remaining-references-to-numa-hinting-bits-and-helpers.patch mm-numa-do-not-trap-faults-on-the-huge-zero-page.patch x86-mm-restore-original-pte_special-check.patch mm-numa-add-paranoid-check-around-pte_protnone_numa.patch mm-numa-avoid-unnecessary-tlb-flushes-when-setting-numa-hinting-entries.patch do_shared_fault-check-that-mmap_sem-is-held.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