Re: [PATCH net-next v5 6/6] tls: Flush backlog before waiting for a new record

["Chuck Lever" <cel@kernel.org>]

On Tue, Mar 24, 2026, at 12:18 PM, Sabrina Dubroca wrote:
> 2026-03-24, 08:53:28 -0400, Chuck Lever wrote:
>> From: Chuck Lever <chuck.lever@oracle.com>
>> 
>> While lock_sock is held, incoming TCP segments land on
>> sk->sk_backlog rather than sk->sk_receive_queue.
>> tls_rx_rec_wait() inspects only sk_receive_queue, so
>> backlog data remains invisible. For non-blocking callers
>> (read_sock, and recvmsg or splice_read with MSG_DONTWAIT)
>> this causes a spurious -EAGAIN. For blocking callers it
>> forces an unnecessary sleep/wakeup cycle.
>> 
>> Flush the backlog inside tls_rx_rec_wait() before checking
>> sk_receive_queue so the strparser can parse newly-arrived
>> segments immediately.
>> 
>> Fixes: 20ffc7adf53a ("net/tls: missing received data after fast remote close")
>
> How did you pick that Fixes tag? That commit mentions FIN/connection
> closing, which doesn't seem related to the local backlog.

20ffc7adf53a introduced the sk_receive_queue check inside the
wait loop (then called tls_wait_data(), later refactored into
tls_rx_rec_wait()).

When lock_sock is held, incoming TCP will segments land on
sk->sk_backlog, not sk->sk_receive_queue. The sk_receive_queue
check introduced by 20ffc7adf53a doesn't see backlog data.


>> diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
>> index 8fb2f2a93846..84c4ae0330d1 100644
>> --- a/net/tls/tls_sw.c
>> +++ b/net/tls/tls_sw.c
>> @@ -1372,6 +1372,7 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock,
>>  		if (ret < 0)
>>  			return ret;
>>  
>> +		sk_flush_backlog(sk);
>
> Do we need to update released when this returns true, like callers of
> tls_read_flush_backlog() do?

Good catch. v6 will do that.


> I also wonder if we'd want to update the
> caller's flushed_at to avoid bypassing the "smart checks" in
> tls_read_flush_backlog().

The flush in tls_rx_rec_wait() only fires when the loop finds
no ready message, which is the cold path. The redundant flush
from tls_read_flush_backlog() on the next iteration is wasteful
but harmless. I'm not sure the additional complexity would be
worth it, but if you believe it will add some value, let me
know and I will add it.


>>  		if (!skb_queue_empty(&sk->sk_receive_queue)) {
>>  			/* Defer notification to the exit point;
>>  			 * this thread will consume the record
>
> -- 
> Sabrina

-- 
Chuck Lever