[PATCH net-next v10 5/7] tls: Suppress spurious saved_data_ready on all receive paths

[Chuck Lever <cel@kernel.org>]

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

Each record release via tls_strp_msg_done() triggered
tls_strp_check_rcv(), which called tls_rx_msg_ready() and
fired 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. The recvmsg and splice_read paths share this waste.

Suppress per-record notifications and emit a single one on
reader exit. tls_rx_rec_done() releases the current record
and parses the next without announcing; tls_strp_check_rcv()
gains a bool announce parameter so callers can request the
quiet form. tls_rx_reader_release() fires the deferred
announce on exit through tls_rx_msg_maybe_announce(), an
idempotent helper that calls saved_data_ready() only when a
record is parsed and has not yet been announced.

To keep the final notification idempotent against records that
the BH or the worker has already announced, tls_strparser gains
a msg_announced bit. tls_rx_msg_maybe_announce() sets the bit
when firing saved_data_ready(); the bit is cleared whenever
the parsed record is wiped, by tls_strp_msg_consume() on
consumption or by tls_strp_msg_load() when the lower socket
loses bytes from under the parse. A second call for the same
parsed record -- as when recvmsg() satisfies the request from
ctx->rx_list without touching the strparser -- becomes a
no-op.

With no remaining callers, tls_strp_msg_done() is removed.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/net/tls.h  |  5 +++++
 net/tls/tls.h      |  5 ++---
 net/tls/tls_main.c |  2 +-
 net/tls/tls_strp.c | 23 ++++++++++++-----------
 net/tls/tls_sw.c   | 27 ++++++++++++++++++++++++---
 5 files changed, 44 insertions(+), 18 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index ebd2550280ae..3811943288b3 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -111,11 +111,16 @@ struct tls_sw_context_tx {
 struct tls_strparser {
 	struct sock *sk;
 
+	/* Bitfield word and msg_ready are serialized by the lower
+	 * socket lock; BH and worker contexts both acquire it.
+	 */
 	u32 mark : 8;
 	u32 stopped : 1;
 	u32 copy_mode : 1;
 	u32 mixed_decrypted : 1;
 
+	u32 msg_announced : 1;
+
 	bool msg_ready;
 
 	struct strp_msg stm;
diff --git a/net/tls/tls.h b/net/tls/tls.h
index cb0091e03f41..60a37bdaaa25 100644
--- a/net/tls/tls.h
+++ b/net/tls/tls.h
@@ -193,12 +193,11 @@ 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 announce);
 void tls_strp_msg_consume(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);
+void tls_rx_msg_maybe_announce(struct tls_strparser *strp);
 
 bool tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh);
 int tls_strp_msg_cow(struct tls_sw_context_rx *ctx);
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 e7aaee6efe6e..61b10c697ecc 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;
@@ -492,6 +491,7 @@ bool tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh)
 	if (!strp->copy_mode && force_refresh) {
 		if (unlikely(tcp_inq(strp->sk) < strp->stm.full_len)) {
 			WRITE_ONCE(strp->msg_ready, 0);
+			strp->msg_announced = 0;
 			memset(&strp->stm, 0, sizeof(strp->stm));
 			return false;
 		}
@@ -539,18 +539,24 @@ 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)
+/* Parse queued data. When @announce is true and parsing produces a
+ * newly-ready record, fire the consumer notification. Callers that
+ * need to notify a waiter about a record parsed by another path
+ * should invoke tls_rx_msg_maybe_announce() directly.
+ */
+void tls_strp_check_rcv(struct tls_strparser *strp, bool announce)
 {
 	if (unlikely(strp->stopped) || strp->msg_ready)
 		return;
 
 	if (tls_strp_read_sock(strp) == -ENOMEM)
 		queue_work(tls_strp_wq, &strp->work);
+	else if (announce && strp->msg_ready)
+		tls_rx_msg_maybe_announce(strp);
 }
 
 /* Lower sock lock held */
@@ -568,7 +574,7 @@ 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 +583,7 @@ 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);
 }
 
@@ -596,15 +602,10 @@ void tls_strp_msg_consume(struct tls_strparser *strp)
 		tls_strp_flush_anchor_copy(strp);
 
 	WRITE_ONCE(strp->msg_ready, 0);
+	strp->msg_announced = 0;
 	memset(&strp->stm, 0, sizeof(strp->stm));
 }
 
-void tls_strp_msg_done(struct tls_strparser *strp)
-{
-	tls_strp_msg_consume(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 40cb0a92d88a..88d07199d5aa 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1383,7 +1383,10 @@ 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;
 		}
@@ -1869,9 +1872,13 @@ static int tls_record_content_type(struct msghdr *msg, struct tls_msg *tlm,
 	return 1;
 }
 
+/* The deferred announce is fired once on reader exit by
+ * tls_rx_reader_release().
+ */
 static void tls_rx_rec_done(struct tls_sw_context_rx *ctx)
 {
-	tls_strp_msg_done(&ctx->strp);
+	tls_strp_msg_consume(&ctx->strp);
+	tls_strp_check_rcv(&ctx->strp, false);
 }
 
 /* This function traverses the rx_list in tls receive context to copies the
@@ -2026,6 +2033,12 @@ static int tls_rx_reader_lock(struct sock *sk, struct tls_sw_context_rx *ctx,
 
 static void tls_rx_reader_release(struct sock *sk, struct tls_sw_context_rx *ctx)
 {
+	/* Fire any deferred announce once per reader so that a record
+	 * parsed but not yet announced becomes visible to the next
+	 * reader. The call is idempotent through msg_announced.
+	 */
+	tls_rx_msg_maybe_announce(&ctx->strp);
+
 	if (unlikely(ctx->reader_contended)) {
 		if (wq_has_sleeper(&ctx->wq))
 			wake_up(&ctx->wq);
@@ -2505,10 +2518,18 @@ int tls_rx_msg_size(struct tls_strparser *strp, struct sk_buff *skb)
 	return ret;
 }
 
-void tls_rx_msg_ready(struct tls_strparser *strp)
+/* Fire saved_data_ready() at most once per parsed record. The
+ * msg_announced bit is cleared by tls_strp_msg_consume() when the
+ * record is consumed, arming the next announcement.
+ */
+void tls_rx_msg_maybe_announce(struct tls_strparser *strp)
 {
 	struct tls_sw_context_rx *ctx;
 
+	if (!READ_ONCE(strp->msg_ready) || strp->msg_announced)
+		return;
+	strp->msg_announced = 1;
+
 	ctx = container_of(strp, struct tls_sw_context_rx, strp);
 	ctx->saved_data_ready(strp->sk);
 }

-- 
2.54.0