The patch titled
Subject: mm/fadvise.c: do not discard partial pages with POSIX_FADV_DONTNEED
has been removed from the -mm tree. Its filename was
mm-do-not-discard-partial-pages-with-posix_fadv_dontneed.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
From: Oleg Drokin <green@xxxxxxxxxxxxxx>
Subject: 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@xxxxxxxxxxxxxx
Signed-off-by: Oleg Drokin <green@xxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/fadvise.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff -puN mm/fadvise.c~mm-do-not-discard-partial-pages-with-posix_fadv_dontneed mm/fadvise.c
--- a/mm/fadvise.c~mm-do-not-discard-partial-pages-with-posix_fadv_dontneed
+++ a/mm/fadvise.c
@@ -126,6 +126,17 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, l
*/
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,
_
Patches currently in -mm which might be from green@xxxxxxxxxxxxxx are
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
