nm_i->nat_tree_lock is used to sync both the operations of nat entry
cache tree and nat set cache tree, however, it isn't held when flush
nat entries during checkpoint which lead to potential race, this patch
fix it by holding the lock when gang lookup nat set cache and delete
item from nat set cache.
Signed-off-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxxxxxx>
---
fs/f2fs/node.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 8751375..14e4387 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1837,6 +1837,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
struct f2fs_nat_block *nat_blk;
struct nat_entry *ne, *cur;
struct page *page = NULL;
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
/*
* there are two steps to flush nat entries:
@@ -1890,7 +1891,9 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
f2fs_bug_on(sbi, set->entry_cnt);
+ down_write(&nm_i->nat_tree_lock);
radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set);
+ up_write(&nm_i->nat_tree_lock);
kmem_cache_free(nat_entry_set_slab, set);
}
@@ -1918,6 +1921,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt, NAT_JOURNAL))
remove_nats_in_journal(sbi);
+ down_write(&nm_i->nat_tree_lock);
while ((found = __gang_lookup_nat_set(nm_i,
set_idx, SETVEC_SIZE, setvec))) {
unsigned idx;
@@ -1926,6 +1930,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
__adjust_nat_entry_set(setvec[idx], &sets,
MAX_NAT_JENTRIES(sum));
}
+ up_write(&nm_i->nat_tree_lock);
/* flush dirty nats in nat entry set */
list_for_each_entry_safe(set, tmp, &sets, set_list)
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
