f2fs crypto: fix racing of accessing encrypted page among
different competitors
Since we use different page cache (normally inode's page cache for R/W
and meta inode's page cache for GC) to cache the same physical block
which is belong to an encrypted inode. Writeback of these two page
cache should be exclusive, but now we didn't handle writeback state
well, so there may be potential racing problem:
a)
kworker: f2fs_gc:
- f2fs_write_data_pages
- f2fs_write_data_page
- do_write_data_page
- write_data_page
- f2fs_submit_page_mbio
(page#1 in inode's page cache was queued
in f2fs bio cache, and be ready to write
to new blkaddr)
- gc_data_segment
- move_encrypted_block
- pagecache_get_page
(page#2 in meta inode's page cache
was cached with the invalid datas
of physical block located in new
blkaddr)
- f2fs_submit_page_mbio
(page#1 was submitted, later, page#2
with invalid data will be submitted)
b)
f2fs_gc:
- gc_data_segment
- move_encrypted_block
- f2fs_submit_page_mbio
(page#1 in meta inode's page cache was
queued in f2fs bio cache, and be ready
to write to new blkaddr)
user thread:
- f2fs_write_begin
- f2fs_submit_page_bio
(we submit the request to block layer
to update page#2 in inode's page cache
with physical block located in new
blkaddr, so here we may read gabbage
data from new blkaddr since GC hasn't
writebacked the page#1 yet)
This patch fixes above potential racing problem for encrypted inode.
Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 2285376..77dfc9e 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -956,21 +956,14 @@
if (f2fs_encrypted_inode(inode) &&
S_ISREG(inode->i_mode)) {
- struct page *cpage;
ctx = f2fs_get_crypto_ctx(inode);
if (IS_ERR(ctx))
goto set_error_page;
/* wait the page to be moved by cleaning */
- cpage = find_lock_page(
- META_MAPPING(F2FS_I_SB(inode)),
- block_nr);
- if (cpage) {
- f2fs_wait_on_page_writeback(cpage,
- DATA);
- f2fs_put_page(cpage, 1);
- }
+ f2fs_wait_on_encrypted_page_writeback(
+ F2FS_I_SB(inode), block_nr);
}
bio = bio_alloc(GFP_KERNEL,
@@ -1064,6 +1057,11 @@
}
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
+
+ /* wait for GCed encrypted page writeback */
+ f2fs_wait_on_encrypted_page_writeback(F2FS_I_SB(inode),
+ fio->blk_addr);
+
fio->encrypted_page = f2fs_encrypt(inode, fio->page);
if (IS_ERR(fio->encrypted_page)) {
err = PTR_ERR(fio->encrypted_page);
@@ -1452,6 +1450,10 @@
f2fs_wait_on_page_writeback(page, DATA);
+ /* wait for GCed encrypted page writeback */
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+ f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr);
+
if (len == PAGE_CACHE_SIZE)
goto out_update;
if (PageUptodate(page))
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 94cf6bc..c3443da 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1792,6 +1792,7 @@
void allocate_data_block(struct f2fs_sb_info *, struct page *,
block_t, block_t *, struct f2fs_summary *, int);
void f2fs_wait_on_page_writeback(struct page *, enum page_type);
+void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *, block_t);
void write_data_summaries(struct f2fs_sb_info *, block_t);
void write_node_summaries(struct f2fs_sb_info *, block_t);
int lookup_journal_in_cursum(struct f2fs_summary_block *,
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 5d2a2ee..91c51a6 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -87,6 +87,11 @@
mapped:
/* fill the page */
f2fs_wait_on_page_writeback(page, DATA);
+
+ /* wait for GCed encrypted page writeback */
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+ f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr);
+
/* if gced page is attached, don't write to cold segment */
clear_cold_data(page);
out:
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 3f19634..af7c24c 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -559,8 +559,16 @@
if (err)
goto out;
- if (unlikely(dn.data_blkaddr == NULL_ADDR))
+ if (unlikely(dn.data_blkaddr == NULL_ADDR)) {
+ ClearPageUptodate(page);
goto put_out;
+ }
+
+ /*
+ * don't cache encrypted data into meta inode until previous dirty
+ * data were writebacked to avoid racing between GC and flush.
+ */
+ f2fs_wait_on_page_writeback(page, DATA);
get_node_info(fio.sbi, dn.nid, &ni);
set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version);
@@ -589,7 +597,7 @@
goto put_page_out;
set_page_dirty(fio.encrypted_page);
- f2fs_wait_on_page_writeback(fio.encrypted_page, META);
+ f2fs_wait_on_page_writeback(fio.encrypted_page, DATA);
if (clear_page_dirty_for_io(fio.encrypted_page))
dec_page_count(fio.sbi, F2FS_DIRTY_META);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 5337fd6..f37c212 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1484,6 +1484,23 @@
}
}
+void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
+ block_t blkaddr)
+{
+ struct page *cpage;
+
+ if (blkaddr == NEW_ADDR)
+ return;
+
+ f2fs_bug_on(sbi, blkaddr == NULL_ADDR);
+
+ cpage = find_lock_page(META_MAPPING(sbi), blkaddr);
+ if (cpage) {
+ f2fs_wait_on_page_writeback(cpage, DATA);
+ f2fs_put_page(cpage, 1);
+ }
+}
+
static int read_compacted_summaries(struct f2fs_sb_info *sbi)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);