summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorJohn Fastabend <john.fastabend@gmail.com>2023-05-22 19:56:06 -0700
committerDaniel Borkmann <daniel@iogearbox.net>2023-05-23 16:09:56 +0200
commit29173d07f79883ac94f5570294f98af3d4287382 (patch)
tree9c6d24f64a295265999954fc35a79004932fcc77 /net
parent78fa0d61d97a728d306b0c23d353c0e340756437 (diff)
bpf, sockmap: Convert schedule_work into delayed_work
Sk_buffs are fed into sockmap verdict programs either from a strparser (when the user might want to decide how framing of skb is done by attaching another parser program) or directly through tcp_read_sock. The tcp_read_sock is the preferred method for performance when the BPF logic is a stream parser. The flow for Cilium's common use case with a stream parser is, tcp_read_sock() sk_psock_verdict_recv ret = bpf_prog_run_pin_on_cpu() sk_psock_verdict_apply(sock, skb, ret) // if system is under memory pressure or app is slow we may // need to queue skb. Do this queuing through ingress_skb and // then kick timer to wake up handler skb_queue_tail(ingress_skb, skb) schedule_work(work); The work queue is wired up to sk_psock_backlog(). This will then walk the ingress_skb skb list that holds our sk_buffs that could not be handled, but should be OK to run at some later point. However, its possible that the workqueue doing this work still hits an error when sending the skb. When this happens the skbuff is requeued on a temporary 'state' struct kept with the workqueue. This is necessary because its possible to partially send an skbuff before hitting an error and we need to know how and where to restart when the workqueue runs next. Now for the trouble, we don't rekick the workqueue. This can cause a stall where the skbuff we just cached on the state variable might never be sent. This happens when its the last packet in a flow and no further packets come along that would cause the system to kick the workqueue from that side. To fix we could do simple schedule_work(), but while under memory pressure it makes sense to back off some instead of continue to retry repeatedly. So instead to fix convert schedule_work to schedule_delayed_work and add backoff logic to reschedule from backlog queue on errors. Its not obvious though what a good backoff is so use '1'. To test we observed some flakes whil running NGINX compliance test with sockmap we attributed these failed test to this bug and subsequent issue. >From on list discussion. This commit bec217197b41("skmsg: Schedule psock work if the cached skb exists on the psock") was intended to address similar race, but had a couple cases it missed. Most obvious it only accounted for receiving traffic on the local socket so if redirecting into another socket we could still get an sk_buff stuck here. Next it missed the case where copied=0 in the recv() handler and then we wouldn't kick the scheduler. Also its sub-optimal to require userspace to kick the internal mechanisms of sockmap to wake it up and copy data to user. It results in an extra syscall and requires the app to actual handle the EAGAIN correctly. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Tested-by: William Findlay <will@isovalent.com> Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://lore.kernel.org/bpf/20230523025618.113937-3-john.fastabend@gmail.com
Diffstat (limited to 'net')
-rw-r--r--net/core/skmsg.c21
-rw-r--r--net/core/sock_map.c3
2 files changed, 16 insertions, 8 deletions
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 4a3dc8d27295..0a9ee2acac0b 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -482,7 +482,7 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
}
out:
if (psock->work_state.skb && copied > 0)
- schedule_work(&psock->work);
+ schedule_delayed_work(&psock->work, 0);
return copied;
}
EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
@@ -640,7 +640,8 @@ static void sk_psock_skb_state(struct sk_psock *psock,
static void sk_psock_backlog(struct work_struct *work)
{
- struct sk_psock *psock = container_of(work, struct sk_psock, work);
+ struct delayed_work *dwork = to_delayed_work(work);
+ struct sk_psock *psock = container_of(dwork, struct sk_psock, work);
struct sk_psock_work_state *state = &psock->work_state;
struct sk_buff *skb = NULL;
bool ingress;
@@ -680,6 +681,12 @@ start:
if (ret == -EAGAIN) {
sk_psock_skb_state(psock, state, skb,
len, off);
+
+ /* Delay slightly to prioritize any
+ * other work that might be here.
+ */
+ if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
+ schedule_delayed_work(&psock->work, 1);
goto end;
}
/* Hard errors break pipe and stop xmit. */
@@ -734,7 +741,7 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
INIT_LIST_HEAD(&psock->link);
spin_lock_init(&psock->link_lock);
- INIT_WORK(&psock->work, sk_psock_backlog);
+ INIT_DELAYED_WORK(&psock->work, sk_psock_backlog);
mutex_init(&psock->work_mutex);
INIT_LIST_HEAD(&psock->ingress_msg);
spin_lock_init(&psock->ingress_lock);
@@ -823,7 +830,7 @@ static void sk_psock_destroy(struct work_struct *work)
sk_psock_done_strp(psock);
- cancel_work_sync(&psock->work);
+ cancel_delayed_work_sync(&psock->work);
mutex_destroy(&psock->work_mutex);
psock_progs_drop(&psock->progs);
@@ -938,7 +945,7 @@ static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb)
}
skb_queue_tail(&psock_other->ingress_skb, skb);
- schedule_work(&psock_other->work);
+ schedule_delayed_work(&psock_other->work, 0);
spin_unlock_bh(&psock_other->ingress_lock);
return 0;
}
@@ -1018,7 +1025,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
spin_lock_bh(&psock->ingress_lock);
if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
skb_queue_tail(&psock->ingress_skb, skb);
- schedule_work(&psock->work);
+ schedule_delayed_work(&psock->work, 0);
err = 0;
}
spin_unlock_bh(&psock->ingress_lock);
@@ -1049,7 +1056,7 @@ static void sk_psock_write_space(struct sock *sk)
psock = sk_psock(sk);
if (likely(psock)) {
if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
- schedule_work(&psock->work);
+ schedule_delayed_work(&psock->work, 0);
write_space = psock->saved_write_space;
}
rcu_read_unlock();
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 7c189c2e2fbf..00afb66cd095 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -1644,9 +1644,10 @@ void sock_map_close(struct sock *sk, long timeout)
rcu_read_unlock();
sk_psock_stop(psock);
release_sock(sk);
- cancel_work_sync(&psock->work);
+ cancel_delayed_work_sync(&psock->work);
sk_psock_put(sk, psock);
}
+
/* Make sure we do not recurse. This is a bug.
* Leak the socket instead of crashing on a stack overflow.
*/