linux-kernel - [RESEND] [PATCH] mm: Do not discard partial pages with POSIX_FADV

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [day] [month] [year] [list]

Message-Id: <1464917140-1506698-1-git-send-email-green@linuxhacker.ru>
Date:	Thu,  2 Jun 2016 21:25:40 -0400
From:	green@...uxhacker.ru
To:	Andrew Morton <akpm@...ux-foundation.org>
Cc:	"<linux-kernel@...r.kernel.org> Mailing List" 
	<linux-kernel@...r.kernel.org>, linux-mm@...ck.org,
	Oleg Drokin <green@...uxhacker.ru>
Subject: [RESEND] [PATCH] mm: Do not discard partial pages with POSIX_FADV_DONTNEED

From: Oleg Drokin <green@...uxhacker.ru>

I noticed that if the logic in 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.

Signed-off-by: Oleg Drokin <green@...uxhacker.ru>
---
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 the result.

 mm/fadvise.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/mm/fadvise.c b/mm/fadvise.c
index b8024fa..6c707bf 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,
-- 
2.1.0