From aaa52e340073b7f4593b3c4ddafcafa70cf838b5 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Fri, 30 Nov 2018 14:10:29 -0800 Subject: [PATCH] mm/khugepaged: fix crashes due to misaccounted holes Huge tmpfs testing on a shortish file mapped into a pmd-rounded extent hit shmem_evict_inode()'s WARN_ON(inode->i_blocks) followed by clear_inode()'s BUG_ON(inode->i_data.nrpages) when the file was later closed and unlinked. khugepaged's collapse_shmem() was forgetting to update mapping->nrpages on the rollback path, after it had added but then needs to undo some holes. There is indeed an irritating asymmetry between shmem_charge(), whose callers want it to increment nrpages after successfully accounting blocks, and shmem_uncharge(), when __delete_from_page_cache() already decremented nrpages itself: oh well, just add a comment on that to them both. And shmem_recalc_inode() is supposed to be called when the accounting is expected to be in balance (so it can deduce from imbalance that reclaim discarded some pages): so change shmem_charge() to update nrpages earlier (though it's rare for the difference to matter at all). Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261523450.2275@eggly.anvils Fixes: 800d8c63b2e98 ("shmem: add huge pages support") Fixes: f3f0e1d2150b2 ("khugepaged: add support of collapse for tmpfs/shmem pages") Signed-off-by: Hugh Dickins Acked-by: Kirill A. Shutemov Cc: Jerome Glisse Cc: Konstantin Khlebnikov Cc: Matthew Wilcox Cc: [4.8+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/khugepaged.c | 5 ++++- mm/shmem.c | 6 +++++- 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 2070c316f06e..65e82f665c7c 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1506,9 +1506,12 @@ xa_unlocked: khugepaged_pages_collapsed++; } else { struct page *page; + /* Something went wrong: roll back page cache changes */ - shmem_uncharge(mapping->host, nr_none); xas_lock_irq(&xas); + mapping->nrpages -= nr_none; + shmem_uncharge(mapping->host, nr_none); + xas_set(&xas, start); xas_for_each(&xas, page, end - 1) { page = list_first_entry_or_null(&pagelist, diff --git a/mm/shmem.c b/mm/shmem.c index 16a3d7044c52..cddc72ac44d8 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -297,12 +297,14 @@ bool shmem_charge(struct inode *inode, long pages) if (!shmem_inode_acct_block(inode, pages)) return false; + /* nrpages adjustment first, then shmem_recalc_inode() when balanced */ + inode->i_mapping->nrpages += pages; + spin_lock_irqsave(&info->lock, flags); info->alloced += pages; inode->i_blocks += pages * BLOCKS_PER_PAGE; shmem_recalc_inode(inode); spin_unlock_irqrestore(&info->lock, flags); - inode->i_mapping->nrpages += pages; return true; } @@ -312,6 +314,8 @@ void shmem_uncharge(struct inode *inode, long pages) struct shmem_inode_info *info = SHMEM_I(inode); unsigned long flags; + /* nrpages adjustment done by __delete_from_page_cache() or caller */ + spin_lock_irqsave(&info->lock, flags); info->alloced -= pages; inode->i_blocks -= pages * BLOCKS_PER_PAGE;