From b1c2d0ded4dc33f3940d8fe8e5d1ed1f95d204af Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 21 Jun 2023 14:24:03 -0700 Subject: [PATCH] hugetlb: revert use of page_cache_next_miss() commit fd4aed8d985a3236d0877ff6d0c80ad39d4ce81a upstream. Ackerley Tng reported an issue with hugetlbfs fallocate as noted in the Closes tag. The issue showed up after the conversion of hugetlb page cache lookup code to use page_cache_next_miss. User visible effects are: - hugetlbfs fallocate incorrectly returns -EEXIST if pages are presnet in the file. - hugetlb pages will not be included in core dumps if they need to be brought in via GUP. - userfaultfd UFFDIO_COPY will not notice pages already present in the cache. It may try to allocate a new page and potentially return ENOMEM as opposed to EEXIST. Revert the use page_cache_next_miss() in hugetlb code. IMPORTANT NOTE FOR STABLE BACKPORTS: This patch will apply cleanly to v6.3. However, due to the change of filemap_get_folio() return values, it will not function correctly. This patch must be modified for stable backports. [dan.carpenter@linaro.org: fix hugetlbfs_pagecache_present()] Link: https://lkml.kernel.org/r/efa86091-6a2c-4064-8f55-9b44e1313015@moroto.mountain Link: https://lkml.kernel.org/r/20230621212403.174710-2-mike.kravetz@oracle.com Fixes: d0ce0e47b323 ("mm/hugetlb: convert hugetlb fault paths to use alloc_hugetlb_folio()") Signed-off-by: Mike Kravetz Signed-off-by: Dan Carpenter Reported-by: Ackerley Tng Closes: https://lore.kernel.org/linux-mm/cover.1683069252.git.ackerleytng@google.com Reviewed-by: Sidhartha Kumar Cc: Erdem Aktas Cc: Greg Kroah-Hartman Cc: Matthew Wilcox Cc: Muchun Song Cc: Vishal Annapurve Signed-off-by: Andrew Morton Signed-off-by: Sidhartha Kumar Signed-off-by: Greg Kroah-Hartman --- fs/hugetlbfs/inode.c | 8 +++----- mm/hugetlb.c | 12 ++++++------ 2 files changed, 9 insertions(+), 11 deletions(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index ecfdfb2529a3..581201818ed8 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -821,7 +821,6 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, */ struct folio *folio; unsigned long addr; - bool present; cond_resched(); @@ -845,10 +844,9 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, mutex_lock(&hugetlb_fault_mutex_table[hash]); /* See if already present in mapping to avoid alloc/free */ - rcu_read_lock(); - present = page_cache_next_miss(mapping, index, 1) != index; - rcu_read_unlock(); - if (present) { + folio = filemap_get_folio(mapping, index); + if (!IS_ERR(folio)) { + folio_put(folio); mutex_unlock(&hugetlb_fault_mutex_table[hash]); hugetlb_drop_vma_policy(&pseudo_vma); continue; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f154019e6b84..f791076da157 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5731,13 +5731,13 @@ static bool hugetlbfs_pagecache_present(struct hstate *h, { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = vma_hugecache_offset(h, vma, address); - bool present; + struct folio *folio; - rcu_read_lock(); - present = page_cache_next_miss(mapping, idx, 1) != idx; - rcu_read_unlock(); - - return present; + folio = filemap_get_folio(mapping, idx); + if (IS_ERR(folio)) + return false; + folio_put(folio); + return true; } int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping,