summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorMike Kravetz <mike.kravetz@oracle.com>2023-06-02 15:57:47 -0700
committerAndrew Morton <akpm@linux-foundation.org>2023-06-12 11:31:52 -0700
commit9425c591e06a9ab27a145ba655fb50532cf0bcc9 (patch)
treeeb209892e43937da7c09c58a60c3eeedecc589a0 /mm
parent26a6ffff7de5dd369cdb12e38ba11db682f1dec0 (diff)
page cache: fix page_cache_next/prev_miss off by one
Ackerley Tng reported an issue with hugetlbfs fallocate here[1]. The issue showed up after the conversion of hugetlb page cache lookup code to use page_cache_next_miss. Code in hugetlb fallocate, userfaultfd and GUP is now using page_cache_next_miss to determine if a page is present the page cache. The following statement is used. present = page_cache_next_miss(mapping, index, 1) != index; There are two issues with page_cache_next_miss when used in this way. 1) If the passed value for index is equal to the 'wrap-around' value, the same index will always be returned. This wrap-around value is 0, so 0 will be returned even if page is present at index 0. 2) If there is no gap in the range passed, the last index in the range will be returned. When passed a range of 1 as above, the passed index value will be returned even if the page is present. The end result is the statement above will NEVER indicate a page is present in the cache, even if it is. As noted by Ackerley in [1], users can see this by hugetlb fallocate incorrectly returning EEXIST if pages are already present in the file. In addition, hugetlb pages will not be included in core dumps if they need to be brought in via GUP. userfaultfd UFFDIO_COPY also uses this code and 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. Both page_cache_next_miss and page_cache_prev_miss have similar issues. Fix by: - Check for index equal to 'wrap-around' value and do not exit early. - If no gap is found in range, return index outside range. - Update function description to say 'wrap-around' value could be returned if passed as index. [1] https://lore.kernel.org/linux-mm/cover.1683069252.git.ackerleytng@google.com/ Link: https://lkml.kernel.org/r/20230602225747.103865-2-mike.kravetz@oracle.com Fixes: d0ce0e47b323 ("mm/hugetlb: convert hugetlb fault paths to use alloc_hugetlb_folio()") Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reported-by: Ackerley Tng <ackerleytng@google.com> Reviewed-by: Ackerley Tng <ackerleytng@google.com> Tested-by: Ackerley Tng <ackerleytng@google.com> Cc: Erdem Aktas <erdemaktas@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Muchun Song <songmuchun@bytedance.com> Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com> Cc: Vishal Annapurve <vannapurve@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/filemap.c26
1 files changed, 16 insertions, 10 deletions
diff --git a/mm/filemap.c b/mm/filemap.c
index b4c9bd368b7e..83dda76d1fc3 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1760,7 +1760,9 @@ bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm,
*
* Return: The index of the gap if found, otherwise an index outside the
* range specified (in which case 'return - index >= max_scan' will be true).
- * In the rare case of index wrap-around, 0 will be returned.
+ * In the rare case of index wrap-around, 0 will be returned. 0 will also
+ * be returned if index == 0 and there is a gap at the index. We can not
+ * wrap-around if passed index == 0.
*/
pgoff_t page_cache_next_miss(struct address_space *mapping,
pgoff_t index, unsigned long max_scan)
@@ -1770,12 +1772,13 @@ pgoff_t page_cache_next_miss(struct address_space *mapping,
while (max_scan--) {
void *entry = xas_next(&xas);
if (!entry || xa_is_value(entry))
- break;
- if (xas.xa_index == 0)
- break;
+ return xas.xa_index;
+ if (xas.xa_index == 0 && index != 0)
+ return xas.xa_index;
}
- return xas.xa_index;
+ /* No gaps in range and no wrap-around, return index beyond range */
+ return xas.xa_index + 1;
}
EXPORT_SYMBOL(page_cache_next_miss);
@@ -1796,7 +1799,9 @@ EXPORT_SYMBOL(page_cache_next_miss);
*
* Return: The index of the gap if found, otherwise an index outside the
* range specified (in which case 'index - return >= max_scan' will be true).
- * In the rare case of wrap-around, ULONG_MAX will be returned.
+ * In the rare case of wrap-around, ULONG_MAX will be returned. ULONG_MAX
+ * will also be returned if index == ULONG_MAX and there is a gap at the
+ * index. We can not wrap-around if passed index == ULONG_MAX.
*/
pgoff_t page_cache_prev_miss(struct address_space *mapping,
pgoff_t index, unsigned long max_scan)
@@ -1806,12 +1811,13 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping,
while (max_scan--) {
void *entry = xas_prev(&xas);
if (!entry || xa_is_value(entry))
- break;
- if (xas.xa_index == ULONG_MAX)
- break;
+ return xas.xa_index;
+ if (xas.xa_index == ULONG_MAX && index != ULONG_MAX)
+ return xas.xa_index;
}
- return xas.xa_index;
+ /* No gaps in range and no wrap-around, return index beyond range */
+ return xas.xa_index - 1;
}
EXPORT_SYMBOL(page_cache_prev_miss);