The patch titled Subject: mm: thp: fix BUG on mm->nr_ptes has been removed from the -mm tree. Its filename was mm-thp-fix-bug-on-mm-nr_ptes.patch This patch was dropped because it was merged into mainline or a subsystem tree The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ From: Andrea Arcangeli <aarcange@xxxxxxxxxx> Subject: mm: thp: fix BUG on mm->nr_ptes Dave Jones reports a few Fedora users hitting the BUG_ON(mm->nr_ptes...) in exit_mmap() recently. Quoting Hugh's discovery and explanation of the SMP race condition: === mm->nr_ptes had unusual locking: down_read mmap_sem plus page_table_lock when incrementing, down_write mmap_sem (or mm_users 0) when decrementing; whereas THP is careful to increment and decrement it under page_table_lock. Now most of those paths in THP also hold mmap_sem for read or write (with appropriate checks on mm_users), but two do not: when split_huge_page() is called by hwpoison_user_mappings(), and when called by add_to_swap(). It's conceivable that the latter case is responsible for the exit_mmap() BUG_ON mm->nr_ptes that has been reported on Fedora. === The simplest way to fix it without having to alter the locking is to make split_huge_page() a noop in nr_ptes terms, so by counting the preallocated pagetables that exists for every mapped hugepage. It was an arbitrary choice not to count them and either way is not wrong or right, because they are not used but they're still allocated. Reported-by: Dave Jones <davej@xxxxxxxxxx> Reported-by: Hugh Dickins <hughd@xxxxxxxxxx> Signed-off-by: Andrea Arcangeli <aarcange@xxxxxxxxxx> Acked-by: Hugh Dickins <hughd@xxxxxxxxxx> Cc: David Rientjes <rientjes@xxxxxxxxxx> Cc: Josh Boyer <jwboyer@xxxxxxxxxx> Cc: <stable@xxxxxxxxxxxxxxx> [3.0.x, 3.1.x, 3.2.x] Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/huge_memory.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff -puN mm/huge_memory.c~mm-thp-fix-bug-on-mm-nr_ptes mm/huge_memory.c --- a/mm/huge_memory.c~mm-thp-fix-bug-on-mm-nr_ptes +++ a/mm/huge_memory.c @@ -671,6 +671,7 @@ static int __do_huge_pmd_anonymous_page( set_pmd_at(mm, haddr, pmd, entry); prepare_pmd_huge_pte(pgtable, mm); add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR); + mm->nr_ptes++; spin_unlock(&mm->page_table_lock); } @@ -789,6 +790,7 @@ int copy_huge_pmd(struct mm_struct *dst_ pmd = pmd_mkold(pmd_wrprotect(pmd)); set_pmd_at(dst_mm, addr, dst_pmd, pmd); prepare_pmd_huge_pte(pgtable, dst_mm); + dst_mm->nr_ptes++; ret = 0; out_unlock: @@ -887,7 +889,6 @@ static int do_huge_pmd_wp_page_fallback( } kfree(pages); - mm->nr_ptes++; smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable); page_remove_rmap(page); @@ -1047,6 +1048,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, VM_BUG_ON(page_mapcount(page) < 0); add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); VM_BUG_ON(!PageHead(page)); + tlb->mm->nr_ptes--; spin_unlock(&tlb->mm->page_table_lock); tlb_remove_page(tlb, page); pte_free(tlb->mm, pgtable); @@ -1375,7 +1377,6 @@ static int __split_huge_page_map(struct pte_unmap(pte); } - mm->nr_ptes++; smp_wmb(); /* make pte visible before pmd */ /* * Up to this point the pmd is present and huge and @@ -1988,7 +1989,6 @@ static void collapse_huge_page(struct mm set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache(vma, address, _pmd); prepare_pmd_huge_pte(pgtable, mm); - mm->nr_ptes--; spin_unlock(&mm->page_table_lock); #ifndef CONFIG_NUMA _ Patches currently in -mm which might be from aarcange@xxxxxxxxxx are origin.patch linux-next.patch vmscan-reclaim-at-order-0-when-compaction-is-enabled.patch vmscan-kswapd-carefully-call-compaction.patch vmscan-kswapd-carefully-call-compaction-fix.patch vmscan-only-defer-compaction-for-failed-order-and-higher.patch mm-compaction-make-compact_control-order-signed.patch mm-compaction-make-compact_control-order-signed-fix.patch hugetlbfs-fix-hugetlb_get_unmapped_area.patch hugetlb-drop-prev_vma-in-hugetlb_get_unmapped_area_topdown.patch hugetlb-try-to-search-again-if-it-is-really-needed.patch hugetlb-try-to-search-again-if-it-is-really-needed-fix.patch mm-do-not-reset-cached_hole_size-when-vma-is-unmapped.patch mm-search-from-free_area_cache-for-the-bigger-size.patch pagemap-avoid-splitting-thp-when-reading-proc-pid-pagemap.patch thp-optimize-away-unnecessary-page-table-locking.patch thp-optimize-away-unnecessary-page-table-locking-fix.patch pagemap-export-kpf_thp.patch pagemap-document-kpf_thp-and-make-page-types-aware-of-it.patch pagemap-introduce-data-structure-for-pagemap-entry.patch mm-hugetlb-defer-freeing-pages-when-gathering-surplus-pages.patch thp-transparent_hugepage=-can-also-be-specified-on-cmdline.patch thp-allow-a-hwpoisoned-head-page-to-be-put-back-to-lru.patch memcg-remove-unnecessary-thp-check-in-page-stat-accounting.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