bpf: Using rcu_read_lock for bpf_sk_storage_map iterator

If a bucket contains a lot of sockets, during bpf_iter traversing
a bucket, concurrent userspace bpf_map_update_elem() and
bpf program bpf_sk_storage_{get,delete}() may experience
some undesirable delays as they will compete with bpf_iter
for bucket lock.

Note that the number of buckets for bpf_sk_storage_map
is roughly the same as the number of cpus. So if there
are lots of sockets in the system, each bucket could
contain lots of sockets.

Different actual use cases may experience different delays.
Here, using selftest bpf_iter subtest bpf_sk_storage_map,
I hacked the kernel with ktime_get_mono_fast_ns()
to collect the time when a bucket was locked
during bpf_iter prog traversing that bucket. This way,
the maximum incurred delay was measured w.r.t. the
number of elements in a bucket.
    # elems in each bucket          delay(ns)
      64                            17000
      256                           72512
      2048                          875246

The potential delays will be further increased if
we have even more elemnts in a bucket. Using rcu_read_lock()
is a reasonable compromise here. It may lose some precision, e.g.,
access stale sockets, but it will not hurt performance of
bpf program or user space application which also tries
to get/delete or update map elements.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200916224645.720172-1-yhs@fb.com

1 files changed, 13 insertions, 18 deletions

diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index d653a583dbc9..838efc682cff 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -674,6 +674,7 @@ struct bpf_iter_seq_sk_storage_map_info {
 static struct bpf_local_storage_elem *
 bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
 				 struct bpf_local_storage_elem *prev_selem)
+	__acquires(RCU) __releases(RCU)
 {
 	struct bpf_local_storage *sk_storage;
 	struct bpf_local_storage_elem *selem;
@@ -692,16 +693,16 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
 	selem = prev_selem;
 	count = 0;
 	while (selem) {
-		selem = hlist_entry_safe(selem->map_node.next,
+		selem = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&selem->map_node)),
 					 struct bpf_local_storage_elem, map_node);
 		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;
 		}
-		sk_storage = rcu_dereference_raw(selem->local_storage);
+		sk_storage = rcu_dereference(selem->local_storage);
 		if (sk_storage) {
 			info->skip_elems = skip_elems + count;
 			return selem;
@@ -711,10 +712,10 @@ 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);
+		hlist_for_each_entry_rcu(selem, &b->list, map_node) {
+			sk_storage = rcu_dereference(selem->local_storage);
 			if (sk_storage && count >= skip_elems) {
 				info->bucket_id = i;
 				info->skip_elems = count;
@@ -722,7 +723,7 @@ 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;
 	}
 
@@ -781,7 +782,7 @@ static int __bpf_sk_storage_map_seq_show(struct seq_file *seq,
 		ctx.meta = &meta;
 		ctx.map = info->map;
 		if (selem) {
-			sk_storage = rcu_dereference_raw(selem->local_storage);
+			sk_storage = rcu_dereference(selem->local_storage);
 			ctx.sk = sk_storage->owner;
 			ctx.value = SDATA(selem)->data;
 		}
@@ -797,18 +798,12 @@ static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v)
 }
 
 static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v)
+	__releases(RCU)
 {
-	struct bpf_iter_seq_sk_storage_map_info *info = seq->private;
-	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,