[PATCH net v4 2/4] net: hsr: shrink seqnr_lock to sequence counter updates

hsr->seqnr_lock is currently held across entire hsr_forward_skb()
calls: master TX (hsr_dev_xmit()), interlink RX (hsr_handle_frame()),
and both supervision frame builders hold it while frames are built,
classified, duplicated and forwarded on every port. The only state
that actually needs the lock is the sequence counters themselves
(hsr->sequence_nr / hsr->sup_sequence_nr).

Shrink the locking to the individual counter updates:
handle_std_frame() now takes the lock around its sequence number
allocation (replacing the lockdep assertion), the master TX and
interlink RX paths drop their outer lock, and the supervision
builders release the lock right after updating their counter instead
of holding it across frame construction and forwarding.

Statistics: the outer seqnr_lock also incidentally serialized the
tx_packets/tx_bytes/tx_dropped updates in hsr_forward_skb(), which are
reachable from the concurrently callable master-TX, supervision and
interlink-RX paths. Those updates now use DEV_STATS_INC()/
DEV_STATS_ADD(), the atomic legacy-stat helpers, so narrowing the lock
does not turn them into lossy plain read-modify-writes.

Ordering: with IFF_NO_QUEUE and dev->lltx, hsr_dev_xmit() is
concurrently callable, and this change removes the old
allocation-through-forward ordering guarantee there: master-TX frames
may now be emitted out of sequence-allocation order. On the current
tree this is safe because duplicate discard tracks individual
sequence numbers in sparse bitmaps (commit aae9d6b616b5 ("hsr:
Implement more robust duplicate discard for HSR") and
commit 415e6367512b ("hsr: Implement more robust duplicate discard
for PRP")) rather than requiring monotonic arrival. Sequence numbers
remain unique and monotonically allocated per counter.

This is a latency/critical-section prerequisite for unfolding GSO
super-packets at the forward entry (not a functional prerequisite):
the segmentation work should not extend the global sequence lock's
critical section. Patch 3 depends on this change; their automatic
stable selection is limited to 7.0 and newer, where sparse-bitmap
duplicate discard accepts out-of-order arrival. Older stable branches
require an adapted backport.

History of the lock being narrowed: it was introduced by
commit 06afd2c31d33 ("hsr: Synchronize sending frames to have always
incremented outgoing seq nr.") and briefly removed by
commit b3c9e65eb227 ("net: hsr: remove seqnr_lock") in net. Merge
commit 46ae4d0a4897 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net")
reverted that removal because
commit 430d67bdcb04 ("net: hsr: Use the seqnr lock for frames
received via interlink port.") in net-next had already superseded it
by adding locking for the interlink RX path. All sequence counter
updates remain protected; only the forwarding work moves out of the
critical section.

Cc: <[email protected]> # 7.0.x
Signed-off-by: Xin Xie <[email protected]>
---
 net/hsr/hsr_device.c  | 15 ++++-----------
 net/hsr/hsr_forward.c |  9 +++++----
 net/hsr/hsr_slave.c   | 11 +----------
 3 files changed, 10 insertions(+), 25 deletions(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 5555b71ab19b..3fd1762d8916 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -232,9 +232,7 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 		skb->dev = master->dev;
 		skb_reset_mac_header(skb);
 		skb_reset_mac_len(skb);
-		spin_lock_bh(&hsr->seqnr_lock);
 		hsr_forward_skb(skb, master);
-		spin_unlock_bh(&hsr->seqnr_lock);
 	} else {
 		dev_core_stats_tx_dropped_inc(dev);
 		dev_kfree_skb_any(skb);
@@ -335,6 +333,7 @@ static void send_hsr_supervision_frame(struct hsr_port *port,
 		hsr_stag->sequence_nr = htons(hsr->sequence_nr);
 		hsr->sequence_nr++;
 	}
+	spin_unlock_bh(&hsr->seqnr_lock);
 
 	hsr_stag->tlv.HSR_TLV_type = type;
 	/* HSRv0 has 6 unused bytes after the MAC */
@@ -356,14 +355,10 @@ static void send_hsr_supervision_frame(struct hsr_port *port,
 		ether_addr_copy(hsr_sp->macaddress_A, hsr->macaddress_redbox);
 	}
 
-	if (skb_put_padto(skb, ETH_ZLEN)) {
-		spin_unlock_bh(&hsr->seqnr_lock);
+	if (skb_put_padto(skb, ETH_ZLEN))
 		return;
-	}
 
 	hsr_forward_skb(skb, port);
-	spin_unlock_bh(&hsr->seqnr_lock);
-	return;
 }
 
 static void send_prp_supervision_frame(struct hsr_port *master,
@@ -390,6 +385,7 @@ static void send_prp_supervision_frame(struct hsr_port *master,
 	spin_lock_bh(&hsr->seqnr_lock);
 	hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr);
 	hsr->sup_sequence_nr++;
+	spin_unlock_bh(&hsr->seqnr_lock);
 	hsr_stag->tlv.HSR_TLV_type = PRP_TLV_LIFE_CHECK_DD;
 	hsr_stag->tlv.HSR_TLV_length = sizeof(struct hsr_sup_payload);
 
@@ -397,13 +393,10 @@ static void send_prp_supervision_frame(struct hsr_port *master,
 	hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload));
 	ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr);
 
-	if (skb_put_padto(skb, ETH_ZLEN)) {
-		spin_unlock_bh(&hsr->seqnr_lock);
+	if (skb_put_padto(skb, ETH_ZLEN))
 		return;
-	}
 
 	hsr_forward_skb(skb, master);
-	spin_unlock_bh(&hsr->seqnr_lock);
 }
 
 /* Announce (supervision frame) timer function
diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index 0774981a65c1..87cd72a1dc65 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -621,9 +621,10 @@ static void handle_std_frame(struct sk_buff *skb,
 	if (port->type == HSR_PT_MASTER ||
 	    port->type == HSR_PT_INTERLINK) {
 		/* Sequence nr for the master/interlink node */
-		lockdep_assert_held(&hsr->seqnr_lock);
+		spin_lock_bh(&hsr->seqnr_lock);
 		frame->sequence_nr = hsr->sequence_nr;
 		hsr->sequence_nr++;
+		spin_unlock_bh(&hsr->seqnr_lock);
 	}
 }
 
@@ -746,8 +747,8 @@ void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port)
 	 * So check and increment stats for master port only here.
 	 */
 	if (port->type == HSR_PT_MASTER || port->type == HSR_PT_INTERLINK) {
-		port->dev->stats.tx_packets++;
-		port->dev->stats.tx_bytes += skb->len;
+		DEV_STATS_INC(port->dev, tx_packets);
+		DEV_STATS_ADD(port->dev, tx_bytes, skb->len);
 	}
 
 	kfree_skb(frame.skb_hsr);
@@ -757,6 +758,6 @@ void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port)
 
 out_drop:
 	rcu_read_unlock();
-	port->dev->stats.tx_dropped++;
+	DEV_STATS_INC(port->dev, tx_dropped);
 	kfree_skb(skb);
 }
diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
index da06b21cdf51..0ca55d9323c5 100644
--- a/net/hsr/hsr_slave.c
+++ b/net/hsr/hsr_slave.c
@@ -73,16 +73,7 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb)
 	}
 	skb_reset_mac_len(skb);
 
-	/* Only the frames received over the interlink port will assign a
-	 * sequence number and require synchronisation vs other sender.
-	 */
-	if (port->type == HSR_PT_INTERLINK) {
-		spin_lock_bh(&hsr->seqnr_lock);
-		hsr_forward_skb(skb, port);
-		spin_unlock_bh(&hsr->seqnr_lock);
-	} else {
-		hsr_forward_skb(skb, port);
-	}
+	hsr_forward_skb(skb, port);
 
 finish_consume:
 	return RX_HANDLER_CONSUMED;
-- 
2.43.0