Currently, we use bucket_lock when traversing bpf_sk_storage_map
elements. Since bpf_iter programs cannot use bpf_sk_storage_get()
and bpf_sk_storage_delete() helpers which may also grab bucket lock,
we do not have a deadlock issue which exists for hashmap when
using bucket_lock ([1]).
If a bucket contains a lot of sockets, during bpf_iter traversing
a bucket, concurrent bpf_sk_storage_{get,delete}() may experience
some undesirable delays. Using rcu_read_lock() is a reasonable
compromise here. Although it may lose some precision, e.g.,
access stale sockets, but it will not hurt performance of other
bpf programs.
[1] https://lore.kernel.org/bpf/20200902235341.2001534-1-yhs@xxxxxx
Cc: Martin KaFai Lau <kafai@xxxxxx>
Signed-off-by: Yonghong Song <yhs@xxxxxx>
---
net/core/bpf_sk_storage.c | 15 ++++++---------
1 file changed, 6 insertions(+), 9 deletions(-)
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 4a86ea34f29e..a1db5e988d19 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -701,7 +701,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
if (!selem) {
/* not found, unlock and go to the next bucket */
b = &smap->buckets[bucket_id++];
- raw_spin_unlock_bh(&b->lock);
+ rcu_read_unlock();
skip_elems = 0;
break;
}
@@ -715,7 +715,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
for (i = bucket_id; i < (1U << smap->bucket_log); i++) {
b = &smap->buckets[i];
- raw_spin_lock_bh(&b->lock);
+ rcu_read_lock();
count = 0;
hlist_for_each_entry(selem, &b->list, map_node) {
sk_storage = rcu_dereference_raw(selem->local_storage);
@@ -726,7 +726,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
}
count++;
}
- raw_spin_unlock_bh(&b->lock);
+ rcu_read_unlock();
skip_elems = 0;
}
@@ -806,13 +806,10 @@ static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v)
struct bpf_local_storage_map *smap;
struct bpf_local_storage_map_bucket *b;
- if (!v) {
+ if (!v)
(void)__bpf_sk_storage_map_seq_show(seq, v);
- } else {
- smap = (struct bpf_local_storage_map *)info->map;
- b = &smap->buckets[info->bucket_id];
- raw_spin_unlock_bh(&b->lock);
- }
+ else
+ rcu_read_unlock();
}
static int bpf_iter_init_sk_storage_map(void *priv_data,
--
2.24.1
