From 2d383afbfc2e1b21b1f4fc4359a24e05462263bd Mon Sep 17 00:00:00 2001 From: Oleg Drokin Date: Wed, 8 Jun 2016 15:33:59 -0700 Subject: [PATCH] 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 Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/fadvise.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/mm/fadvise.c b/mm/fadvise.c index b8024fa7101d9..6c707bfe02fde 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, -- 2.39.5