We will encounter deadloop in below scenario:
1. increase page count for F2FS_DIRTY_META type in following path:
->recover_fsync_data
->recover_data
->do_recover_data
->recover_data_page
->change_curseg
->write_sum_page
->set_page_dirty
2. fail in recover_data()
3. invalidate meta pages in truncate_inode_pages_final without decreasing page
count.
4. deadloop when sync_meta_pages as page count will always be non-zero.
message:
NMI watchdog: BUG: soft lockup - CPU#0 stuck for 22s!
[<c1129a37>] pagevec_lookup_tag+0x27/0x30
[<f0e774c7>] sync_meta_pages+0x87/0x160 [f2fs]
[<f0e86dd9>] recover_fsync_data+0xeb9/0xf10 [f2fs]
[<f0e75398>] f2fs_fill_super+0x888/0x980 [f2fs]
[<c11733ca>] mount_bdev+0x16a/0x1a0
[<f0e7180f>] f2fs_mount+0x1f/0x30 [f2fs]
[<c1173da6>] mount_fs+0x36/0x170
[<c118b6f5>] vfs_kern_mount+0x55/0xe0
[<c118d63f>] do_mount+0x1df/0x9f0
[<c118e110>] SyS_mount+0x70/0xb0
[<c15a0c48>] sysenter_do_call+0x12/0x12
To avoid page count leak, let's add ->invalidatepage and ->releasepage in
f2fs_meta_aops as f2fs_node_aops to release meta page count correctly.
Signed-off-by: Chao Yu <chao2...@samsung.com>
---
fs/f2fs/checkpoint.c | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 9f5317c..63bf844 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -302,16 +302,35 @@ static int f2fs_set_meta_page_dirty(struct page *page)
if (!PageDirty(page)) {
__set_page_dirty_nobuffers(page);
inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
+ SetPagePrivate(page);
f2fs_trace_pid(page);
return 1;
}
return 0;
}
+static void f2fs_invalidate_meta_page(struct page *page, unsigned int offset,
+ unsigned int length)
+{
+ struct inode *inode = page->mapping->host;
+
+ if (PageDirty(page))
+ dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_META);
+ ClearPagePrivate(page);
+}
+
+static int f2fs_release_meta_page(struct page *page, gfp_t wait)
+{
+ ClearPagePrivate(page);
+ return 1;
+}
+
const struct address_space_operations f2fs_meta_aops = {
.writepage = f2fs_write_meta_page,
.writepages = f2fs_write_meta_pages,
.set_page_dirty = f2fs_set_meta_page_dirty,
+ .invalidatepage = f2fs_invalidate_meta_page,
+ .releasepage = f2fs_release_meta_page,
};
static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
--
2.2.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
