From fa27759af4a6d7494c986c44695b13bcd6eaf46b Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 14 Sep 2022 15:18:10 -0700 Subject: [PATCH] hugetlb: clean up code checking for fault/truncation races With the new hugetlb vma lock in place, it can also be used to handle page fault races with file truncation. The lock is taken at the beginning of the code fault path in read mode. During truncation, it is taken in write mode for each vma which has the file mapped. The file's size (i_size) is modified before taking the vma lock to unmap. How are races handled? The page fault code checks i_size early in processing after taking the vma lock. If the fault is beyond i_size, the fault is aborted. If the fault is not beyond i_size the fault will continue and a new page will be added to the file. It could be that truncation code modifies i_size after the check in fault code. That is OK, as truncation code will soon remove the page. The truncation code will wait until the fault is finished, as it must obtain the vma lock in write mode. This patch cleans up/removes late checks in the fault paths that try to back out pages racing with truncation. As noted above, we just let the truncation code remove the pages. [mike.kravetz@oracle.com: fix reserve_alloc set but not used compiler warning] Link: https://lkml.kernel.org/r/Yyj7HsJWfHDoU24U@monkey Link: https://lkml.kernel.org/r/20220914221810.95771-10-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Cc: Andrea Arcangeli Cc: "Aneesh Kumar K.V" Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: James Houghton Cc: "Kirill A. Shutemov" Cc: Miaohe Lin Cc: Michal Hocko Cc: Mina Almasry Cc: Muchun Song Cc: Naoya Horiguchi Cc: Pasha Tatashin Cc: Peter Xu Cc: Prakash Sangappa Cc: Sven Schnelle Signed-off-by: Andrew Morton --- fs/hugetlbfs/inode.c | 31 ++++++++++++------------------- mm/hugetlb.c | 24 +++--------------------- 2 files changed, 15 insertions(+), 40 deletions(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 009ae53..ed57a02 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -568,26 +568,19 @@ static bool remove_inode_single_folio(struct hstate *h, struct inode *inode, folio_lock(folio); /* - * After locking page, make sure mapping is the same. - * We could have raced with page fault populate and - * backout code. + * We must remove the folio from page cache before removing + * the region/ reserve map (hugetlb_unreserve_pages). In + * rare out of memory conditions, removal of the region/reserve + * map could fail. Correspondingly, the subpool and global + * reserve usage count can need to be adjusted. */ - if (folio_mapping(folio) == mapping) { - /* - * We must remove the folio from page cache before removing - * the region/ reserve map (hugetlb_unreserve_pages). In - * rare out of memory conditions, removal of the region/reserve - * map could fail. Correspondingly, the subpool and global - * reserve usage count can need to be adjusted. - */ - VM_BUG_ON(HPageRestoreReserve(&folio->page)); - hugetlb_delete_from_page_cache(&folio->page); - ret = true; - if (!truncate_op) { - if (unlikely(hugetlb_unreserve_pages(inode, index, - index + 1, 1))) - hugetlb_fix_reserve_counts(inode); - } + VM_BUG_ON(HPageRestoreReserve(&folio->page)); + hugetlb_delete_from_page_cache(&folio->page); + ret = true; + if (!truncate_op) { + if (unlikely(hugetlb_unreserve_pages(inode, index, + index + 1, 1))) + hugetlb_fix_reserve_counts(inode); } folio_unlock(folio); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index d785049..b0e3904 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5680,10 +5680,6 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, } ptl = huge_pte_lock(h, mm, ptep); - size = i_size_read(mapping->host) >> huge_page_shift(h); - if (idx >= size) - goto backout; - ret = 0; /* If pte changed from under us, retry */ if (!pte_same(huge_ptep_get(ptep), old_pte)) @@ -5727,10 +5723,10 @@ out: backout: spin_unlock(ptl); backout_unlocked: - unlock_page(page); - /* restore reserve for newly allocated pages not in page cache */ if (new_page && !new_pagecache_page) restore_reserve_on_error(h, vma, haddr, page); + + unlock_page(page); put_page(page); goto out; } @@ -6063,25 +6059,11 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, ptl = huge_pte_lock(h, dst_mm, dst_pte); /* - * Recheck the i_size after holding PT lock to make sure not - * to leave any page mapped (as page_mapped()) beyond the end - * of the i_size (remove_inode_hugepages() is strict about - * enforcing that). If we bail out here, we'll also leave a - * page in the radix tree in the vm_shared case beyond the end - * of the i_size, but remove_inode_hugepages() will take care - * of it as soon as we drop the hugetlb_fault_mutex_table. - */ - size = i_size_read(mapping->host) >> huge_page_shift(h); - ret = -EFAULT; - if (idx >= size) - goto out_release_unlock; - - ret = -EEXIST; - /* * We allow to overwrite a pte marker: consider when both MISSING|WP * registered, we firstly wr-protect a none pte which has no page cache * page backing it, then access the page. */ + ret = -EEXIST; if (!huge_pte_none_mostly(huge_ptep_get(dst_pte))) goto out_release_unlock; -- 2.7.4