public inbox for netdev@vger.kernel.org
 help / color / mirror / Atom feed
From: Chuck Lever <cel@kernel.org>
To: john.fastabend@gmail.com, kuba@kernel.org, sd@queasysnail.net
Cc: netdev@vger.kernel.org, kernel-tls-handshake@lists.linux.dev,
	 Chuck Lever <chuck.lever@oracle.com>,
	 Alistair Francis <alistair.francis@wdc.com>,
	Hannes Reinecke <hare@suse.de>
Subject: [PATCH net-next v6 5/6] tls: Suppress spurious saved_data_ready on all receive paths
Date: Thu, 26 Mar 2026 09:50:50 -0400	[thread overview]
Message-ID: <20260326-tls-read-sock-v6-5-fd887b9e7f06@oracle.com> (raw)
In-Reply-To: <20260326-tls-read-sock-v6-0-fd887b9e7f06@oracle.com>

From: Chuck Lever <chuck.lever@oracle.com>

Each record release via tls_strp_msg_done() triggers
tls_strp_check_rcv(), which calls tls_rx_msg_ready() and
fires saved_data_ready(). During a multi-record receive,
the first N-1 wakeups are pure overhead: the caller is
already running and will pick up subsequent records on
the next loop iteration. On the splice_read path the
per-record wakeup is similarly unnecessary because the
caller still holds the socket lock.

Replace tls_strp_msg_done() with tls_strp_msg_release()
in all three receive paths (read_sock, recvmsg,
splice_read), deferring the tls_strp_check_rcv() call
to each path's exit point. Factor tls_rx_msg_ready()
out of tls_strp_read_sock() so that parsing a record
no longer fires the callback directly, and add a @wake
parameter to tls_strp_check_rcv() so callers can parse
queued data without notifying.

With no remaining callers, tls_strp_msg_done() and its
wrapper tls_rx_rec_done() are removed.

Acked-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 net/tls/tls.h      |  3 +--
 net/tls/tls_main.c |  2 +-
 net/tls/tls_strp.c | 35 +++++++++++++++++++++--------------
 net/tls/tls_sw.c   | 22 +++++++++++++++-------
 4 files changed, 38 insertions(+), 24 deletions(-)

diff --git a/net/tls/tls.h b/net/tls/tls.h
index a97f1acef31d..f41dac6305f4 100644
--- a/net/tls/tls.h
+++ b/net/tls/tls.h
@@ -192,9 +192,8 @@ void tls_strp_stop(struct tls_strparser *strp);
 int tls_strp_init(struct tls_strparser *strp, struct sock *sk);
 void tls_strp_data_ready(struct tls_strparser *strp);
 
-void tls_strp_check_rcv(struct tls_strparser *strp);
+void tls_strp_check_rcv(struct tls_strparser *strp, bool wake);
 void tls_strp_msg_release(struct tls_strparser *strp);
-void tls_strp_msg_done(struct tls_strparser *strp);
 
 int tls_rx_msg_size(struct tls_strparser *strp, struct sk_buff *skb);
 void tls_rx_msg_ready(struct tls_strparser *strp);
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index fd39acf41a61..c10a3fd7fc17 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -769,7 +769,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval,
 	} else {
 		struct tls_sw_context_rx *rx_ctx = tls_sw_ctx_rx(ctx);
 
-		tls_strp_check_rcv(&rx_ctx->strp);
+		tls_strp_check_rcv(&rx_ctx->strp, true);
 	}
 	return 0;
 
diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c
index a7648ebde162..b0b2ca92fa99 100644
--- a/net/tls/tls_strp.c
+++ b/net/tls/tls_strp.c
@@ -368,7 +368,6 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb,
 		desc->count = 0;
 
 		WRITE_ONCE(strp->msg_ready, 1);
-		tls_rx_msg_ready(strp);
 	}
 
 	return ret;
@@ -539,18 +538,32 @@ static int tls_strp_read_sock(struct tls_strparser *strp)
 		return tls_strp_read_copy(strp, false);
 
 	WRITE_ONCE(strp->msg_ready, 1);
-	tls_rx_msg_ready(strp);
 
 	return 0;
 }
 
-void tls_strp_check_rcv(struct tls_strparser *strp)
+/**
+ * tls_strp_check_rcv - parse queued data and optionally notify
+ * @strp: TLS stream parser instance
+ * @wake: if true, fire consumer notification when a message is ready
+ *
+ * When @wake is false, queued data is parsed without consumer
+ * notification. A subsequent call with @wake set to true is
+ * required before the socket lock is released; otherwise queued
+ * data stalls until the next tls_strp_data_ready() event.
+ */
+void tls_strp_check_rcv(struct tls_strparser *strp, bool wake)
 {
-	if (unlikely(strp->stopped) || strp->msg_ready)
+	if (unlikely(strp->stopped))
 		return;
 
-	if (tls_strp_read_sock(strp) == -ENOMEM)
-		queue_work(tls_strp_wq, &strp->work);
+	if (!strp->msg_ready) {
+		if (tls_strp_read_sock(strp) == -ENOMEM)
+			queue_work(tls_strp_wq, &strp->work);
+	}
+
+	if (wake && strp->msg_ready)
+		tls_rx_msg_ready(strp);
 }
 
 /* Lower sock lock held */
@@ -568,7 +581,7 @@ void tls_strp_data_ready(struct tls_strparser *strp)
 		return;
 	}
 
-	tls_strp_check_rcv(strp);
+	tls_strp_check_rcv(strp, true);
 }
 
 static void tls_strp_work(struct work_struct *w)
@@ -577,7 +590,7 @@ static void tls_strp_work(struct work_struct *w)
 		container_of(w, struct tls_strparser, work);
 
 	lock_sock(strp->sk);
-	tls_strp_check_rcv(strp);
+	tls_strp_check_rcv(strp, true);
 	release_sock(strp->sk);
 }
 
@@ -603,12 +616,6 @@ void tls_strp_msg_release(struct tls_strparser *strp)
 	memset(&strp->stm, 0, sizeof(strp->stm));
 }
 
-void tls_strp_msg_done(struct tls_strparser *strp)
-{
-	tls_strp_msg_release(strp);
-	tls_strp_check_rcv(strp);
-}
-
 void tls_strp_stop(struct tls_strparser *strp)
 {
 	strp->stopped = 1;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 5fdd43a55f1e..8fb2f2a93846 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1373,7 +1373,11 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock,
 			return ret;
 
 		if (!skb_queue_empty(&sk->sk_receive_queue)) {
-			tls_strp_check_rcv(&ctx->strp);
+			/* Defer notification to the exit point;
+			 * this thread will consume the record
+			 * directly.
+			 */
+			tls_strp_check_rcv(&ctx->strp, false);
 			if (tls_strp_msg_ready(ctx))
 				break;
 		}
@@ -1859,9 +1863,9 @@ static int tls_record_content_type(struct msghdr *msg, struct tls_msg *tlm,
 	return 1;
 }
 
-static void tls_rx_rec_done(struct tls_sw_context_rx *ctx)
+static void tls_rx_rec_release(struct tls_sw_context_rx *ctx)
 {
-	tls_strp_msg_done(&ctx->strp);
+	tls_strp_msg_release(&ctx->strp);
 }
 
 /* This function traverses the rx_list in tls receive context to copies the
@@ -2142,7 +2146,7 @@ int tls_sw_recvmsg(struct sock *sk,
 		err = tls_record_content_type(msg, tls_msg(darg.skb), &control);
 		if (err <= 0) {
 			DEBUG_NET_WARN_ON_ONCE(darg.zc);
-			tls_rx_rec_done(ctx);
+			tls_rx_rec_release(ctx);
 put_on_rx_list_err:
 			__skb_queue_tail(&ctx->rx_list, darg.skb);
 			goto recv_end;
@@ -2156,7 +2160,8 @@ int tls_sw_recvmsg(struct sock *sk,
 		/* TLS 1.3 may have updated the length by more than overhead */
 		rxm = strp_msg(darg.skb);
 		chunk = rxm->full_len;
-		tls_rx_rec_done(ctx);
+		tls_rx_rec_release(ctx);
+		tls_strp_check_rcv(&ctx->strp, false);
 
 		if (!darg.zc) {
 			bool partially_consumed = chunk > len;
@@ -2250,6 +2255,7 @@ int tls_sw_recvmsg(struct sock *sk,
 	copied += decrypted;
 
 end:
+	tls_strp_check_rcv(&ctx->strp, true);
 	tls_rx_reader_unlock(sk, ctx);
 	if (psock)
 		sk_psock_put(sk, psock);
@@ -2290,7 +2296,7 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 		if (err < 0)
 			goto splice_read_end;
 
-		tls_rx_rec_done(ctx);
+		tls_rx_rec_release(ctx);
 		skb = darg.skb;
 	}
 
@@ -2317,6 +2323,7 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 	consume_skb(skb);
 
 splice_read_end:
+	tls_strp_check_rcv(&ctx->strp, true);
 	tls_rx_reader_unlock(sk, ctx);
 	return copied ? : err;
 
@@ -2382,7 +2389,7 @@ int tls_sw_read_sock(struct sock *sk, read_descriptor_t *desc,
 			tlm = tls_msg(skb);
 			decrypted += rxm->full_len;
 
-			tls_rx_rec_done(ctx);
+			tls_rx_rec_release(ctx);
 		}
 
 		/* read_sock does not support reading control messages */
@@ -2412,6 +2419,7 @@ int tls_sw_read_sock(struct sock *sk, read_descriptor_t *desc,
 	}
 
 read_sock_end:
+	tls_strp_check_rcv(&ctx->strp, true);
 	tls_rx_reader_release(sk, ctx);
 	return copied ? : err;
 

-- 
2.53.0


  parent reply	other threads:[~2026-03-26 13:51 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-26 13:50 [PATCH net-next v6 0/6] TLS read_sock performance scalability Chuck Lever
2026-03-26 13:50 ` [PATCH net-next v6 1/6] tls: Purge async_hold in tls_decrypt_async_wait() Chuck Lever
2026-03-26 13:50 ` [PATCH net-next v6 2/6] tls: Abort the connection on decrypt failure Chuck Lever
2026-03-26 13:50 ` [PATCH net-next v6 3/6] tls: Fix dangling skb pointer in tls_sw_read_sock() Chuck Lever
2026-03-26 13:50 ` [PATCH net-next v6 4/6] tls: Factor tls_strp_msg_release() from tls_strp_msg_done() Chuck Lever
2026-03-26 13:50 ` Chuck Lever [this message]
2026-03-26 13:50 ` [PATCH net-next v6 6/6] tls: Flush backlog before waiting for a new record Chuck Lever

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260326-tls-read-sock-v6-5-fd887b9e7f06@oracle.com \
    --to=cel@kernel.org \
    --cc=alistair.francis@wdc.com \
    --cc=chuck.lever@oracle.com \
    --cc=hare@suse.de \
    --cc=john.fastabend@gmail.com \
    --cc=kernel-tls-handshake@lists.linux.dev \
    --cc=kuba@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=sd@queasysnail.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox