summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorNamjae Jeon <namjae.jeon@samsung.com>2014-05-12 08:12:25 -0400
committerTheodore Ts'o <tytso@mit.edu>2014-05-12 08:12:25 -0400
commit1c8349a17137b93f0a83f276c764a6df1b9a116e (patch)
tree27a59d4a8ba3ce8cf426a3c55b07d259eb356598
parent236f5ecb4a5876977837376729a7599cc1ab2cc3 (diff)
ext4: fix data integrity sync in ordered mode
When we perform a data integrity sync we tag all the dirty pages with PAGECACHE_TAG_TOWRITE at start of ext4_da_writepages. Later we check for this tag in write_cache_pages_da and creates a struct mpage_da_data containing contiguously indexed pages tagged with this tag and sync these pages with a call to mpage_da_map_and_submit. This process is done in while loop until all the PAGECACHE_TAG_TOWRITE pages are synced. We also do journal start and stop in each iteration. journal_stop could initiate journal commit which would call ext4_writepage which in turn will call ext4_bio_write_page even for delayed OR unwritten buffers. When ext4_bio_write_page is called for such buffers, even though it does not sync them but it clears the PAGECACHE_TAG_TOWRITE of the corresponding page and hence these pages are also not synced by the currently running data integrity sync. We will end up with dirty pages although sync is completed. This could cause a potential data loss when the sync call is followed by a truncate_pagecache call, which is exactly the case in collapse_range. (It will cause generic/127 failure in xfstests) To avoid this issue, we can use set_page_writeback_keepwrite instead of set_page_writeback, which doesn't clear TOWRITE tag. Cc: stable@vger.kernel.org Signed-off-by: Namjae Jeon <namjae.jeon@samsung.com> Signed-off-by: Ashish Sangwan <a.sangwan@samsung.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Jan Kara <jack@suse.cz>
-rw-r--r--fs/ext4/ext4.h3
-rw-r--r--fs/ext4/inode.c6
-rw-r--r--fs/ext4/page-io.c8
-rw-r--r--include/linux/page-flags.h12
-rw-r--r--mm/page-writeback.c11
5 files changed, 29 insertions, 11 deletions
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 1d08a1b51bdd..aeda5061a59a 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2772,7 +2772,8 @@ extern void ext4_io_submit(struct ext4_io_submit *io);
extern int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
- struct writeback_control *wbc);
+ struct writeback_control *wbc,
+ bool keep_towrite);
/* mmp.c */
extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9b3c52fbe86d..04dd2de10796 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1846,6 +1846,7 @@ static int ext4_writepage(struct page *page,
struct buffer_head *page_bufs = NULL;
struct inode *inode = page->mapping->host;
struct ext4_io_submit io_submit;
+ bool keep_towrite = false;
trace_ext4_writepage(page);
size = i_size_read(inode);
@@ -1876,6 +1877,7 @@ static int ext4_writepage(struct page *page,
unlock_page(page);
return 0;
}
+ keep_towrite = true;
}
if (PageChecked(page) && ext4_should_journal_data(inode))
@@ -1892,7 +1894,7 @@ static int ext4_writepage(struct page *page,
unlock_page(page);
return -ENOMEM;
}
- ret = ext4_bio_write_page(&io_submit, page, len, wbc);
+ ret = ext4_bio_write_page(&io_submit, page, len, wbc, keep_towrite);
ext4_io_submit(&io_submit);
/* Drop io_end reference we got from init */
ext4_put_io_end_defer(io_submit.io_end);
@@ -1911,7 +1913,7 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
else
len = PAGE_CACHE_SIZE;
clear_page_dirty_for_io(page);
- err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc);
+ err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false);
if (!err)
mpd->wbc->nr_to_write--;
mpd->first_page++;
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index c18d95b50540..4cb2743cb2e3 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -401,7 +401,8 @@ submit_and_retry:
int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
- struct writeback_control *wbc)
+ struct writeback_control *wbc,
+ bool keep_towrite)
{
struct inode *inode = page->mapping->host;
unsigned block_start, blocksize;
@@ -414,7 +415,10 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
- set_page_writeback(page);
+ if (keep_towrite)
+ set_page_writeback_keepwrite(page);
+ else
+ set_page_writeback(page);
ClearPageError(page);
/*
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index d1fe1a761047..ca71a1d347a0 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -317,13 +317,23 @@ CLEARPAGEFLAG(Uptodate, uptodate)
extern void cancel_dirty_page(struct page *page, unsigned int account_size);
int test_clear_page_writeback(struct page *page);
-int test_set_page_writeback(struct page *page);
+int __test_set_page_writeback(struct page *page, bool keep_write);
+
+#define test_set_page_writeback(page) \
+ __test_set_page_writeback(page, false)
+#define test_set_page_writeback_keepwrite(page) \
+ __test_set_page_writeback(page, true)
static inline void set_page_writeback(struct page *page)
{
test_set_page_writeback(page);
}
+static inline void set_page_writeback_keepwrite(struct page *page)
+{
+ test_set_page_writeback_keepwrite(page);
+}
+
#ifdef CONFIG_PAGEFLAGS_EXTENDED
/*
* System with lots of page flags available. This allows separate
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index ef413492a149..d8691d9de3c4 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2398,7 +2398,7 @@ int test_clear_page_writeback(struct page *page)
return ret;
}
-int test_set_page_writeback(struct page *page)
+int __test_set_page_writeback(struct page *page, bool keep_write)
{
struct address_space *mapping = page_mapping(page);
int ret;
@@ -2423,9 +2423,10 @@ int test_set_page_writeback(struct page *page)
radix_tree_tag_clear(&mapping->page_tree,
page_index(page),
PAGECACHE_TAG_DIRTY);
- radix_tree_tag_clear(&mapping->page_tree,
- page_index(page),
- PAGECACHE_TAG_TOWRITE);
+ if (!keep_write)
+ radix_tree_tag_clear(&mapping->page_tree,
+ page_index(page),
+ PAGECACHE_TAG_TOWRITE);
spin_unlock_irqrestore(&mapping->tree_lock, flags);
} else {
ret = TestSetPageWriteback(page);
@@ -2436,7 +2437,7 @@ int test_set_page_writeback(struct page *page)
return ret;
}
-EXPORT_SYMBOL(test_set_page_writeback);
+EXPORT_SYMBOL(__test_set_page_writeback);
/*
* Return true if any of the pages in the mapping are marked with the