Merge branch 'net-tls-minor-micro-optimizations'

Jakub Kicinski says:

====================
net/tls: minor micro optimizations

This set brings a number of minor code changes from my tree which
don't have a noticeable impact on performance but seem reasonable
nonetheless.

First sk_msg_sg copy array is converted to a bitmap, zeroing that
structure takes a lot of time, hence we should try to keep it
small.

Next two conditions are marked as unlikely, GCC seemed to had
little trouble correctly reasoning about those.

Patch 4 adds parameters to tls_device_decrypted() to avoid
walking structures, as all callers already have the relevant
pointers.

Lastly two boolean members of TLS context structures are
converted to a bitfield.
====================

Signed-off-by: David S. Miller <[email protected]>

2 files changed, 16 insertions, 9 deletions

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index e4b3fb4bb77c..fe80d537945d 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -28,13 +28,14 @@ struct sk_msg_sg {
 	u32				end;
 	u32				size;
 	u32				copybreak;
-	bool				copy[MAX_MSG_FRAGS];
+	unsigned long			copy;
 	/* The extra element is used for chaining the front and sections when
 	 * the list becomes partitioned (e.g. end < start). The crypto APIs
 	 * require the chaining.
 	 */
 	struct scatterlist		data[MAX_MSG_FRAGS + 1];
 };
+static_assert(BITS_PER_LONG >= MAX_MSG_FRAGS);
 
 /* UAPI in filter.c depends on struct sk_msg_sg being first element. */
 struct sk_msg {
@@ -227,7 +228,7 @@ static inline void sk_msg_compute_data_pointers(struct sk_msg *msg)
 {
 	struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start);
 
-	if (msg->sg.copy[msg->sg.start]) {
+	if (test_bit(msg->sg.start, &msg->sg.copy)) {
 		msg->data = NULL;
 		msg->data_end = NULL;
 	} else {
@@ -246,7 +247,7 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page,
 	sg_set_page(sge, page, len, offset);
 	sg_unmark_end(sge);
 
-	msg->sg.copy[msg->sg.end] = true;
+	__set_bit(msg->sg.end, &msg->sg.copy);
 	msg->sg.size += len;
 	sk_msg_iter_next(msg, end);
 }
@@ -254,7 +255,10 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page,
 static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state)
 {
 	do {
-		msg->sg.copy[i] = copy_state;
+		if (copy_state)
+			__set_bit(i, &msg->sg.copy);
+		else
+			__clear_bit(i, &msg->sg.copy);
 		sk_msg_iter_var_next(i);
 		if (i == msg->sg.end)
 			break;
diff --git a/include/net/tls.h b/include/net/tls.h
index 24c37bffc961..41265e542e71 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -136,7 +136,7 @@ struct tls_sw_context_tx {
 	struct list_head tx_list;
 	atomic_t encrypt_pending;
 	int async_notify;
-	int async_capable;
+	u8 async_capable:1;
 
 #define BIT_TX_SCHEDULED	0
 #define BIT_TX_CLOSING		1
@@ -152,8 +152,8 @@ struct tls_sw_context_rx {
 
 	struct sk_buff *recv_pkt;
 	u8 control;
-	int async_capable;
-	bool decrypted;
+	u8 async_capable:1;
+	u8 decrypted:1;
 	atomic_t decrypt_pending;
 	bool async_notify;
 };
@@ -641,7 +641,8 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx);
 void tls_device_offload_cleanup_rx(struct sock *sk);
 void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq);
 void tls_offload_tx_resync_request(struct sock *sk, u32 got_seq, u32 exp_seq);
-int tls_device_decrypted(struct sock *sk, struct sk_buff *skb);
+int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx,
+			 struct sk_buff *skb, struct strp_msg *rxm);
 #else
 static inline void tls_device_init(void) {}
 static inline void tls_device_cleanup(void) {}
@@ -664,7 +665,9 @@ static inline void tls_device_offload_cleanup_rx(struct sock *sk) {}
 static inline void
 tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) {}
 
-static inline int tls_device_decrypted(struct sock *sk, struct sk_buff *skb)
+static inline int
+tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx,
+		     struct sk_buff *skb, struct strp_msg *rxm)
 {
 	return 0;
 }