summaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
authorJohn Fastabend <john.fastabend@gmail.com>2020-10-09 11:36:37 -0700
committerAlexei Starovoitov <ast@kernel.org>2020-10-11 18:00:57 -0700
commit9ecbfb06a078c4911fb444203e8e41d93d22f886 (patch)
tree49709bfd4bc4f7eb681c79a237c2210137af757f /net/core
parentcfea28f890cf292d5fe90680db64b68086ef25ba (diff)
downloadlinux-9ecbfb06a078c4911fb444203e8e41d93d22f886.tar.bz2
bpf, sockmap: On receive programs try to fast track SK_PASS ingress
When we receive an skb and the ingress skb verdict program returns SK_PASS we currently set the ingress flag and put it on the workqueue so it can be turned into a sk_msg and put on the sk_msg ingress queue. Then finally telling userspace with data_ready hook. Here we observe that if the workqueue is empty then we can try to convert into a sk_msg type and call data_ready directly without bouncing through a workqueue. Its a common pattern to have a recv verdict program for visibility that always returns SK_PASS. In this case unless there is an ENOMEM error or we overrun the socket we can avoid the workqueue completely only using it when we fall back to error cases caused by memory pressure. By doing this we eliminate another case where data may be dropped if errors occur on memory limits in workqueue. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/160226859704.5692.12929678876744977669.stgit@john-Precision-5820-Tower
Diffstat (limited to 'net/core')
-rw-r--r--net/core/skmsg.c17
1 files changed, 15 insertions, 2 deletions
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 040ae1d75b65..4b160d97b7f9 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -773,6 +773,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
{
struct tcp_skb_cb *tcp;
struct sock *sk_other;
+ int err = -EIO;
switch (verdict) {
case __SK_PASS:
@@ -784,8 +785,20 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
tcp = TCP_SKB_CB(skb);
tcp->bpf.flags |= BPF_F_INGRESS;
- skb_queue_tail(&psock->ingress_skb, skb);
- schedule_work(&psock->work);
+
+ /* If the queue is empty then we can submit directly
+ * into the msg queue. If its not empty we have to
+ * queue work otherwise we may get OOO data. Otherwise,
+ * if sk_psock_skb_ingress errors will be handled by
+ * retrying later from workqueue.
+ */
+ if (skb_queue_empty(&psock->ingress_skb)) {
+ err = sk_psock_skb_ingress(psock, skb);
+ }
+ if (err < 0) {
+ skb_queue_tail(&psock->ingress_skb, skb);
+ schedule_work(&psock->work);
+ }
break;
case __SK_REDIRECT:
sk_psock_skb_redirect(skb);