summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorOleg Drokin <green@linuxhacker.ru>2016-06-08 15:33:59 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-06-09 14:23:11 -0700
commit18aba41cbfbcd138e9f6d8d446427d8b7691c194 (patch)
treec75be3a413a4fca8c2e0058d75df06a2c22610fa
parentf3a932baa7f65072434f1c04c02c8a4d2746fcfc (diff)
mm/fadvise.c: do not discard partial pages with POSIX_FADV_DONTNEED
I noticed that the logic in the fadvise64_64 syscall is incorrect for partial pages. While first page of the region is correctly skipped if it is partial, the last page of the region is mistakenly discarded. This leads to problems for applications that read data in non-page-aligned chunks discarding already processed data between the reads. A somewhat misguided application that does something like write(XX bytes (non-page-alligned)); drop the data it just wrote; repeat gets a significant penalty in performance as a result. Link: http://lkml.kernel.org/r/1464917140-1506698-1-git-send-email-green@linuxhacker.ru Signed-off-by: Oleg Drokin <green@linuxhacker.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--mm/fadvise.c11
1 files changed, 11 insertions, 0 deletions
diff --git a/mm/fadvise.c b/mm/fadvise.c
index b8024fa7101d..6c707bfe02fd 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -126,6 +126,17 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
*/
start_index = (offset+(PAGE_SIZE-1)) >> PAGE_SHIFT;
end_index = (endbyte >> PAGE_SHIFT);
+ if ((endbyte & ~PAGE_MASK) != ~PAGE_MASK) {
+ /* First page is tricky as 0 - 1 = -1, but pgoff_t
+ * is unsigned, so the end_index >= start_index
+ * check below would be true and we'll discard the whole
+ * file cache which is not what was asked.
+ */
+ if (end_index == 0)
+ break;
+
+ end_index--;
+ }
if (end_index >= start_index) {
unsigned long count = invalidate_mapping_pages(mapping,