Subject: + mm-hugetlbfs-fix-rmapping-for-anonymous-hugepages-with-page_pgoff.patch added to -mm tree To: n-horiguchi@xxxxxxxxxxxxx,riel@xxxxxxxxxx,sasha.levin@xxxxxxxxxx,stable@xxxxxxxxxxxxxxx From: akpm@xxxxxxxxxxxxxxxxxxxx Date: Thu, 27 Feb 2014 13:21:04 -0800 The patch titled Subject: mm, hugetlbfs: fix rmapping for anonymous hugepages with page_pgoff() has been added to the -mm tree. Its filename is mm-hugetlbfs-fix-rmapping-for-anonymous-hugepages-with-page_pgoff.patch This patch should soon appear at http://ozlabs.org/~akpm/mmots/broken-out/mm-hugetlbfs-fix-rmapping-for-anonymous-hugepages-with-page_pgoff.patch and later at http://ozlabs.org/~akpm/mmotm/broken-out/mm-hugetlbfs-fix-rmapping-for-anonymous-hugepages-with-page_pgoff.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: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx> Subject: mm, hugetlbfs: fix rmapping for anonymous hugepages with page_pgoff() page->index stores pagecache index when the page is mapped into file mapping region, and the index is in pagecache size unit, so it depends on the page size. Some of users of reverse mapping obviously assumes that page->index is in PAGE_CACHE_SHIFT unit, so they don't work for anonymous hugepage. For example, consider that we have 3-hugepage vma and try to mbind the 2nd hugepage to migrate to another node. Then the vma is split and migrate_page() is called for the 2nd hugepage (belonging to the middle vma.) In migrate operation, rmap_walk_anon() tries to find the relevant vma to which the target hugepage belongs, but here we miscalculate pgoff. So anon_vma_interval_tree_foreach() grabs invalid vma, which fires VM_BUG_ON. This patch introduces a new API that is usable both for normal page and hugepage to get PAGE_SIZE offset from page->index. Users should clearly distinguish page_index for pagecache index and page_pgoff for page offset. Signed-off-by: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx> Reported-by: Sasha Levin <sasha.levin@xxxxxxxxxx> Cc: Rik van Riel <riel@xxxxxxxxxx> Cc: <stable@xxxxxxxxxxxxxxx> [3.12+] Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/pagemap.h | 13 +++++++++++++ mm/huge_memory.c | 2 +- mm/hugetlb.c | 5 +++++ mm/memory-failure.c | 4 ++-- mm/rmap.c | 8 ++------ 5 files changed, 23 insertions(+), 9 deletions(-) diff -puN include/linux/pagemap.h~mm-hugetlbfs-fix-rmapping-for-anonymous-hugepages-with-page_pgoff include/linux/pagemap.h --- a/include/linux/pagemap.h~mm-hugetlbfs-fix-rmapping-for-anonymous-hugepages-with-page_pgoff +++ a/include/linux/pagemap.h @@ -326,6 +326,19 @@ static inline loff_t page_file_offset(st return ((loff_t)page_file_index(page)) << PAGE_CACHE_SHIFT; } +extern pgoff_t hugepage_pgoff(struct page *page); + +/* + * page->index stores pagecache index whose unit is not always PAGE_SIZE. + * This function converts it into PAGE_SIZE offset. + */ +#define page_pgoff(page) \ +({ \ + unlikely(PageHuge(page)) ? \ + hugepage_pgoff(page) : \ + page->index >> (PAGE_CACHE_SHIFT - PAGE_SHIFT); \ +}) + extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, unsigned long address); diff -puN mm/huge_memory.c~mm-hugetlbfs-fix-rmapping-for-anonymous-hugepages-with-page_pgoff mm/huge_memory.c --- a/mm/huge_memory.c~mm-hugetlbfs-fix-rmapping-for-anonymous-hugepages-with-page_pgoff +++ a/mm/huge_memory.c @@ -1875,7 +1875,7 @@ static void __split_huge_page(struct pag struct list_head *list) { int mapcount, mapcount2; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff_t pgoff = page_pgoff(page); struct anon_vma_chain *avc; BUG_ON(!PageHead(page)); diff -puN mm/hugetlb.c~mm-hugetlbfs-fix-rmapping-for-anonymous-hugepages-with-page_pgoff mm/hugetlb.c --- a/mm/hugetlb.c~mm-hugetlbfs-fix-rmapping-for-anonymous-hugepages-with-page_pgoff +++ a/mm/hugetlb.c @@ -764,6 +764,11 @@ pgoff_t __basepage_index(struct page *pa return (index << compound_order(page_head)) + compound_idx; } +pgoff_t hugepage_pgoff(struct page *page) +{ + return page->index << huge_page_order(page_hstate(page)); +} + static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) { struct page *page; diff -puN mm/memory-failure.c~mm-hugetlbfs-fix-rmapping-for-anonymous-hugepages-with-page_pgoff mm/memory-failure.c --- a/mm/memory-failure.c~mm-hugetlbfs-fix-rmapping-for-anonymous-hugepages-with-page_pgoff +++ a/mm/memory-failure.c @@ -408,7 +408,7 @@ static void collect_procs_anon(struct pa if (av == NULL) /* Not actually mapped anymore */ return; - pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff = page_pgoff(page); read_lock(&tasklist_lock); for_each_process (tsk) { struct anon_vma_chain *vmac; @@ -441,7 +441,7 @@ static void collect_procs_file(struct pa mutex_lock(&mapping->i_mmap_mutex); read_lock(&tasklist_lock); for_each_process(tsk) { - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff_t pgoff = page_pgoff(page); if (!task_early_kill(tsk)) continue; diff -puN mm/rmap.c~mm-hugetlbfs-fix-rmapping-for-anonymous-hugepages-with-page_pgoff mm/rmap.c --- a/mm/rmap.c~mm-hugetlbfs-fix-rmapping-for-anonymous-hugepages-with-page_pgoff +++ a/mm/rmap.c @@ -515,11 +515,7 @@ void page_unlock_anon_vma_read(struct an static inline unsigned long __vma_address(struct page *page, struct vm_area_struct *vma) { - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - - if (unlikely(is_vm_hugetlb_page(vma))) - pgoff = page->index << huge_page_order(page_hstate(page)); - + pgoff_t pgoff = page_pgoff(page); return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); } @@ -1588,7 +1584,7 @@ static struct anon_vma *rmap_walk_anon_l static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff_t pgoff = page_pgoff(page); struct anon_vma_chain *avc; int ret = SWAP_AGAIN; _ Patches currently in -mm which might be from n-horiguchi@xxxxxxxxxxxxx are origin.patch mm-hugetlb-unify-region-structure-handling.patch mm-hugetlb-improve-cleanup-resv_map-parameters.patch mm-hugetlb-fix-race-in-region-tracking.patch mm-hugetlb-remove-resv_map_put.patch mm-hugetlb-use-vma_resv_map-map-types.patch mm-hugetlb-improve-page-fault-scalability.patch mm-hugetlb-improve-page-fault-scalability-fix.patch mm-hugetlbfs-fix-rmapping-for-anonymous-hugepages-with-page_pgoff.patch pagewalk-update-page-table-walker-core.patch pagewalk-update-page-table-walker-core-fix-end-address-calculation-in-walk_page_range.patch pagewalk-update-page-table-walker-core-fix-end-address-calculation-in-walk_page_range-fix.patch pagewalk-add-walk_page_vma.patch smaps-redefine-callback-functions-for-page-table-walker.patch clear_refs-redefine-callback-functions-for-page-table-walker.patch pagemap-redefine-callback-functions-for-page-table-walker.patch numa_maps-redefine-callback-functions-for-page-table-walker.patch memcg-redefine-callback-functions-for-page-table-walker.patch madvise-redefine-callback-functions-for-page-table-walker.patch arch-powerpc-mm-subpage-protc-use-walk_page_vma-instead-of-walk_page_range.patch pagewalk-remove-argument-hmask-from-hugetlb_entry.patch pagewalk-remove-argument-hmask-from-hugetlb_entry-fix.patch pagewalk-remove-argument-hmask-from-hugetlb_entry-fix-fix.patch mempolicy-apply-page-table-walker-on-queue_pages_range.patch mm-rename-__do_fault-do_fault.patch mm-do_fault-extract-to-call-vm_ops-do_fault-to-separate-function.patch mm-introduce-do_read_fault.patch mm-introduce-do_cow_fault.patch mm-introduce-do_shared_fault-and-drop-do_fault.patch mm-consolidate-code-to-call-vm_ops-page_mkwrite.patch mm-consolidate-code-to-call-vm_ops-page_mkwrite-fix.patch mm-consolidate-code-to-setup-pte.patch mm-call-vma_adjust_trans_huge-only-for-thp-enabled-vma.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