| 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
| ||
|
Date: Wed, 28 Sep 2011 15:02:04 -0700
From: Greg KH <gregkh@...e.de>
To: linux-kernel@...r.kernel.org, stable@...nel.org
Cc: stable-review@...nel.org, torvalds@...ux-foundation.org,
akpm@...ux-foundation.org, alan@...rguk.ukuu.org.uk,
Jan Kara <jack@...e.cz>, Dave Chinner <david@...morbit.com>,
Wu Fengguang <fengguang.wu@...el.com>
Subject: [160/244] writeback: introduce .tagged_writepages for the WB_SYNC_NONE sync stage
3.0-stable review patch. If anyone has any objections, please let us know.
------------------
From: Wu Fengguang <fengguang.wu@...el.com>
commit 6e6938b6d3130305a5960c86b1a9b21e58cf6144 upstream.
sync(2) is performed in two stages: the WB_SYNC_NONE sync and the
WB_SYNC_ALL sync. Identify the first stage with .tagged_writepages and
do livelock prevention for it, too.
Jan's commit f446daaea9 ("mm: implement writeback livelock avoidance
using page tagging") is a partial fix in that it only fixed the
WB_SYNC_ALL phase livelock.
Although ext4 is tested to no longer livelock with commit f446daaea9,
it may due to some "redirty_tail() after pages_skipped" effect which
is by no means a guarantee for _all_ the file systems.
Note that writeback_inodes_sb() is called by not only sync(), they are
treated the same because the other callers also need livelock prevention.
Impact: It changes the order in which pages/inodes are synced to disk.
Now in the WB_SYNC_NONE stage, it won't proceed to write the next inode
until finished with the current inode.
Acked-by: Jan Kara <jack@...e.cz>
CC: Dave Chinner <david@...morbit.com>
Signed-off-by: Wu Fengguang <fengguang.wu@...el.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@...e.de>
---
fs/ext4/inode.c | 4 ++--
fs/fs-writeback.c | 17 +++++++++--------
include/linux/writeback.h | 1 +
mm/page-writeback.c | 4 ++--
4 files changed, 14 insertions(+), 12 deletions(-)
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2756,7 +2756,7 @@ static int write_cache_pages_da(struct a
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
- if (wbc->sync_mode == WB_SYNC_ALL)
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
@@ -2988,7 +2988,7 @@ static int ext4_da_writepages(struct add
}
retry:
- if (wbc->sync_mode == WB_SYNC_ALL)
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
while (!ret && wbc->nr_to_write > 0) {
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -36,6 +36,7 @@ struct wb_writeback_work {
long nr_pages;
struct super_block *sb;
enum writeback_sync_modes sync_mode;
+ unsigned int tagged_writepages:1;
unsigned int for_kupdate:1;
unsigned int range_cyclic:1;
unsigned int for_background:1;
@@ -650,6 +651,7 @@ static long wb_writeback(struct bdi_writ
{
struct writeback_control wbc = {
.sync_mode = work->sync_mode,
+ .tagged_writepages = work->tagged_writepages,
.older_than_this = NULL,
.for_kupdate = work->for_kupdate,
.for_background = work->for_background,
@@ -657,7 +659,7 @@ static long wb_writeback(struct bdi_writ
};
unsigned long oldest_jif;
long wrote = 0;
- long write_chunk;
+ long write_chunk = MAX_WRITEBACK_PAGES;
struct inode *inode;
if (wbc.for_kupdate) {
@@ -683,9 +685,7 @@ static long wb_writeback(struct bdi_writ
* (quickly) tag currently dirty pages
* (maybe slowly) sync all tagged pages
*/
- if (wbc.sync_mode == WB_SYNC_NONE)
- write_chunk = MAX_WRITEBACK_PAGES;
- else
+ if (wbc.sync_mode == WB_SYNC_ALL || wbc.tagged_writepages)
write_chunk = LONG_MAX;
wbc.wb_start = jiffies; /* livelock avoidance */
@@ -1188,10 +1188,11 @@ void writeback_inodes_sb_nr(struct super
{
DECLARE_COMPLETION_ONSTACK(done);
struct wb_writeback_work work = {
- .sb = sb,
- .sync_mode = WB_SYNC_NONE,
- .done = &done,
- .nr_pages = nr,
+ .sb = sb,
+ .sync_mode = WB_SYNC_NONE,
+ .tagged_writepages = 1,
+ .done = &done,
+ .nr_pages = nr,
};
WARN_ON(!rwsem_is_locked(&sb->s_umount));
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -47,6 +47,7 @@ struct writeback_control {
unsigned encountered_congestion:1; /* An output: a queue is full */
unsigned for_kupdate:1; /* A kupdate writeback */
unsigned for_background:1; /* A background writeback */
+ unsigned tagged_writepages:1; /* tag-and-write to avoid livelock */
unsigned for_reclaim:1; /* Invoked from the page allocator */
unsigned range_cyclic:1; /* range_start is cyclic */
unsigned more_io:1; /* more io to be dispatched */
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -892,12 +892,12 @@ int write_cache_pages(struct address_spa
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
}
- if (wbc->sync_mode == WB_SYNC_ALL)
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
retry:
- if (wbc->sync_mode == WB_SYNC_ALL)
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end)) {
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists