[PATCH net 1/4] net: hsr: fix packet drops caused by GRO superpackets

[PATCH net 1/4] net: hsr: fix packet drops caused by GRO superpackets

[Xin Xie]

HSR/PRP append a 6-byte tag/RCT to every forwarded frame and process
each frame individually (sequence numbering, duplicate discard). When
a lower device aggregates received frames into a GRO super-packet --
in software, or in hardware on GRO_HW-capable NICs -- the HSR
receive/forward path mishandles it: frames are dropped and, on
memory-constrained devices, processing super-skbs in softirq context
can also pressure atomic memory allocation.

The HSR/PRP stack already disables LRO on enslaved devices for the
same reason. Extend that treatment to GRO: add netif_disable_gro()
and dev_disable_gro() mirroring netif_disable_lro()/dev_disable_lro(),
and call dev_disable_gro() from hsr_portdev_setup() so enslavement to
an HSR/PRP master automatically strips NETIF_F_GRO and NETIF_F_GRO_HW
on the lower device (recursively on its own lowers, as with LRO).

Fixes: f421436a591d ("net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)")
Cc: stable@vger.kernel.org
Signed-off-by: Xin Xie <xiexinet@gmail.com>
---
 include/linux/netdevice.h |  2 ++
 net/core/dev.c            | 18 ++++++++++++++++++
 net/core/dev_api.c        | 16 ++++++++++++++++
 net/hsr/hsr_slave.c       |  1 +
 4 files changed, 37 insertions(+)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9981d637f..eba2c26a4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3434,6 +3434,8 @@ void dev_close(struct net_device *dev);
 void netif_close_many(struct list_head *head, bool unlink);
 void netif_disable_lro(struct net_device *dev);
 void dev_disable_lro(struct net_device *dev);
+void netif_disable_gro(struct net_device *dev);
+void dev_disable_gro(struct net_device *dev);
 int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb);
 u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
 		     struct net_device *sb_dev);
diff --git a/net/core/dev.c b/net/core/dev.c
index 5933c5dab..a6cf2adc8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1840,6 +1840,24 @@ void netif_disable_lro(struct net_device *dev)
 	}
 }
 
+void netif_disable_gro(struct net_device *dev)
+{
+	struct net_device *lower_dev;
+	struct list_head *iter;
+
+	dev->wanted_features &= ~(NETIF_F_GRO | NETIF_F_GRO_HW);
+	netdev_update_features(dev);
+
+	if (unlikely(dev->features & (NETIF_F_GRO | NETIF_F_GRO_HW)))
+		netdev_WARN(dev, "failed to disable GRO!\n");
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		netdev_lock_ops(lower_dev);
+		netif_disable_gro(lower_dev);
+		netdev_unlock_ops(lower_dev);
+	}
+}
+
 /**
  *	dev_disable_gro_hw - disable HW Generic Receive Offload on a device
  *	@dev: device
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 437947dd0..02fb21629 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -269,6 +269,22 @@ void dev_disable_lro(struct net_device *dev)
 }
 EXPORT_SYMBOL(dev_disable_lro);
 
+/**
+ * dev_disable_gro() - disable Generic Receive Offload on a device
+ * @dev: device
+ *
+ * Disable Generic Receive Offload (GRO) on a net device.  Must be
+ * called under RTNL.  This is needed if received packets may be
+ * forwarded to another interface.
+ */
+void dev_disable_gro(struct net_device *dev)
+{
+	netdev_lock_ops(dev);
+	netif_disable_gro(dev);
+	netdev_unlock_ops(dev);
+}
+EXPORT_SYMBOL(dev_disable_gro);
+
 /**
  * dev_set_promiscuity() - update promiscuity count on a device
  * @dev: device
diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
index d9af9e65f..cefbbfbd5 100644
--- a/net/hsr/hsr_slave.c
+++ b/net/hsr/hsr_slave.c
@@ -170,6 +170,7 @@ static int hsr_portdev_setup(struct hsr_priv *hsr, struct net_device *dev,
 	if (res)
 		goto fail_rx_handler;
 	dev_disable_lro(dev);
+	dev_disable_gro(dev);
 
 	return 0;
 
-- 
2.43.0

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

[Xin Xie]

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.

Sequence numbers remain unique and monotonically allocated per
counter; concurrent inputs may now interleave allocations, which is
fine as the output paths were already concurrent.

This is a prerequisite for unfolding GSO super-packets at the forward
entry: segmentation with its dozens of GFP_ATOMIC allocations must
not run with BH disabled under the global sequence lock.

The locking being narrowed here was introduced by 06afd2c31d33
("hsr: Synchronize sending frames to have always incremented outgoing
seq nr."), briefly removed by b3c9e65eb227 ("net: hsr: remove
seqnr_lock") and reinstated for the interlink RX path by 430d67bdcb04
("net: hsr: Use the seqnr lock for frames received via interlink
port.") after a syzbot lockdep report. All sequence counter updates
remain protected; only the forwarding work moves out of the critical
section.

Cc: stable@vger.kernel.org
Signed-off-by: Xin Xie <xiexinet@gmail.com>
---
 net/hsr/hsr_device.c  | 15 ++++-----------
 net/hsr/hsr_forward.c |  3 ++-
 net/hsr/hsr_slave.c   | 11 +----------
 3 files changed, 7 insertions(+), 22 deletions(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 5555b71ab..3fd1762d8 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 0774981a6..8e4158a9b 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);
 	}
 }
 
diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
index cefbbfbd5..c7fd021f0 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

[PATCH net 3/4] net: hsr: unfold GSO super-packets at the forward entry

[Xin Xie]

HSR/PRP forward frames one by one: each wire frame gets its own tag
and sequence number, and duplicate discard is per frame. A GSO
super-packet reaching hsr_forward_skb() breaks that per-frame
semantics: it would be tagged and forwarded as a single frame.

Unfold such super-packets at the forward entry with the top-level GSO
dispatch: __skb_gso_segment() initializes SKB_GSO_CB() and performs
the L2->L3->L4 protocol dispatch (calling the low-level skb_segment()
helper directly is not allowed here -- it reads SKB_GSO_CB(skb) state
that only __skb_gso_segment() sets up). features = 0 requests full
software segmentation; tx_path is selected by ingress port (master =
locally generated TX, interlink = RX) to get the right checksum
semantics. Each segment then runs through the existing per-frame
path, which is split out as hsr_forward_skb_one() so that no GSO skb
can reach it.

Segmentation is only offered for the ingress roles whose frames are
known to be plain Ethernet: the master (locally generated) and the
interlink (SAN side, untagged). A super-packet received from a LAN
slave may carry per-frame HSR tags or PRP RCT trailers that software
segmentation cannot recover, and an already-tagged HSR/PRP
super-packet violates per-frame wire semantics; both are rejected by
ingress-port policy. (ETH_P_PRP identifies supervision traffic only;
a PRP data frame keeps its payload EtherType, so RCT carriage cannot
be tested by protocol.)

Also drop NETIF_F_GSO_MASK from the HSR master's hw_features so
locally generated traffic is segmented before reaching the forward
path whenever possible.

Fixes: f421436a591d ("net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)")
Cc: stable@vger.kernel.org
Signed-off-by: Xin Xie <xiexinet@gmail.com>
---
 net/hsr/hsr_device.c  |  2 +-
 net/hsr/hsr_forward.c | 50 ++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 50 insertions(+), 2 deletions(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 3fd1762d8..248cbb142 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -652,7 +652,7 @@ void hsr_dev_setup(struct net_device *dev)
 	dev->needs_free_netdev = true;
 
 	dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
-			   NETIF_F_GSO_MASK | NETIF_F_HW_CSUM |
+			   NETIF_F_HW_CSUM |
 			   NETIF_F_HW_VLAN_CTAG_TX |
 			   NETIF_F_HW_VLAN_CTAG_FILTER;
 
diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index 8e4158a9b..3fcdbac49 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -12,6 +12,7 @@
 #include <linux/skbuff.h>
 #include <linux/etherdevice.h>
 #include <linux/if_vlan.h>
+#include <net/gso.h>
 #include "hsr_main.h"
 #include "hsr_framereg.h"
 
@@ -732,7 +733,7 @@ static int fill_frame_info(struct hsr_frame_info *frame,
 }
 
 /* Must be called holding rcu read lock (because of the port parameter) */
-void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port)
+static void hsr_forward_skb_one(struct sk_buff *skb, struct hsr_port *port)
 {
 	struct hsr_frame_info frame;
 
@@ -761,3 +762,50 @@ void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port)
 	port->dev->stats.tx_dropped++;
 	kfree_skb(skb);
 }
+
+/* GSO fan-out funnel: unfold super-packets before per-frame processing so
+ * each wire frame gets its own HSR/PRP tag and sequence number.
+ */
+void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port)
+{
+	struct sk_buff *segs, *next;
+
+	if (likely(!skb_is_gso(skb))) {
+		hsr_forward_skb_one(skb, port);
+		return;
+	}
+
+	/* Unfold only plain-Ethernet GSO super-packets: locally generated
+	 * on the master, or arriving untagged from the SAN side on the
+	 * interlink. A super-packet from a LAN slave may carry per-frame
+	 * HSR tags / PRP RCT trailers that software segmentation cannot
+	 * recover; an already-tagged HSR/PRP super-packet violates
+	 * per-frame wire semantics. Drop both.
+	 */
+	if (port->type != HSR_PT_MASTER && port->type != HSR_PT_INTERLINK)
+		goto drop_gso;
+	if (skb->protocol == htons(ETH_P_HSR) ||
+	    skb->protocol == htons(ETH_P_PRP))
+		goto drop_gso;
+
+	/* features = 0: request full software segmentation. tx_path is true
+	 * only for locally generated traffic on the master; ingress from
+	 * the interlink follows RX checksum semantics.
+	 */
+	segs = __skb_gso_segment(skb, 0, port->type == HSR_PT_MASTER);
+	if (IS_ERR(segs) || unlikely(!segs))
+		goto drop_gso;
+
+	consume_skb(skb);
+	while (segs) {
+		next = segs->next;
+		segs->next = NULL;
+		hsr_forward_skb_one(segs, port);
+		segs = next;
+	}
+	return;
+
+drop_gso:
+	port->dev->stats.tx_dropped++;
+	kfree_skb(skb);
+}
-- 
2.43.0

[PATCH net 4/4] selftests: net: hsr: add GRO super-packet forwarding test

[Xin Xie]

Add a test exercising the HSR forward path with GSO super-packets:
a TSO-enabled SAN behind the interlink streams TCP through an HSR
DUT to a peer node. The test verifies that:

* enslaved devices have GRO and HW-GRO disabled automatically,
* the HSR master does not advertise GSO/TSO features,
* the stream completes with zero retransmits, i.e. super-packets are
  unfolded per-frame at the forward entry instead of being tagged
  and forwarded as single oversized frames (the stream is rate-capped
  so the zero-retransmit discriminator is stable on CI-class hosts).

The one-shot iperf3 server runs inside a wrapper shell with its exact
PID recorded (pidfile appearance is polled, no startup race): cleanup
kills the server and wait(1)s the wrapper on every exit path, and the
success path waits and checks the server exit status, so neither the
server process nor the namespaces can leak. Environments whose
iproute2 lacks the HSR interlink syntax are skipped with ksft_skip.

Without the fixes the feature checks fail, and on drivers that hand
GRO super-packets to the HSR receive path the stream degrades or
stalls.

Signed-off-by: Xin Xie <xiexinet@gmail.com>
---
 tools/testing/selftests/net/hsr/Makefile      |   1 +
 .../selftests/net/hsr/hsr_gro_superpacket.sh  | 249 ++++++++++++++++++
 2 files changed, 250 insertions(+)
 create mode 100755 tools/testing/selftests/net/hsr/hsr_gro_superpacket.sh

diff --git a/tools/testing/selftests/net/hsr/Makefile b/tools/testing/selftests/net/hsr/Makefile
index 31fb9326c..0d105476e 100644
--- a/tools/testing/selftests/net/hsr/Makefile
+++ b/tools/testing/selftests/net/hsr/Makefile
@@ -3,6 +3,7 @@
 top_srcdir = ../../../../..
 
 TEST_PROGS := \
+	hsr_gro_superpacket.sh \
 	hsr_ping.sh \
 	hsr_redbox.sh \
 	link_faults.sh \
diff --git a/tools/testing/selftests/net/hsr/hsr_gro_superpacket.sh b/tools/testing/selftests/net/hsr/hsr_gro_superpacket.sh
new file mode 100755
index 000000000..4b0a9ceea
--- /dev/null
+++ b/tools/testing/selftests/net/hsr/hsr_gro_superpacket.sh
@@ -0,0 +1,249 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test HSR handling of GRO/GSO super-packets:
+#
+#  1. Enslaving a device to an HSR master disables GRO on it
+#     (dev_disable_gro()).
+#  2. The HSR master does not advertise GSO/TSO features.
+#  3. A TCP stream from a TSO-enabled SAN (which therefore emits GSO
+#     super-packets) is unfolded at the HSR forward entry and delivered
+#     per-frame: the transfer completes with zero retransmits.
+#
+# Topology (100.64.0.0/24):
+#
+#   ns_san                    ns_dut                      ns_peer
+#  +-----------+  interlink  +---------------+  LAN A/B  +-----------+
+#  | s0 [0.1]  |-------------| d_il   hsr0   |-----------| hsr1 [0.3]|
+#  +-----------+             | d_a / d_b     |           | p_a / p_b |
+#                            +---------------+           +-----------+
+#
+# SAN traffic reaches ns_peer only through hsr0's forward path
+# (interlink RX -> LAN A/B TX), so every SAN frame is tagged and
+# forwarded by the DUT.
+
+source ./hsr_common.sh
+
+ns_dut="hsr-gro-dut"
+ns_san="hsr-gro-san"
+ns_peer="hsr-gro-peer"
+san_ip="100.64.0.1"
+peer_ip="100.64.0.3"
+iperf_pid=""
+server_wrapper=""
+iperf_pidfile="/tmp/hsr_gro_iperf.pid"
+
+cleanup()
+{
+	if [ -n "${iperf_pid}" ] && [[ "${iperf_pid}" =~ ^[0-9]+$ ]]; then
+		kill "${iperf_pid}" 2>/dev/null
+	fi
+	if [ -n "${server_wrapper}" ]; then
+		# the wrapper waits on the server; reap it with a 5s bound so a
+		# live-but-unpublished server can never hang cleanup
+		for _ in $(seq 1 50); do
+			kill -0 "${server_wrapper}" 2>/dev/null || break
+			sleep 0.1
+		done
+		kill "${server_wrapper}" 2>/dev/null
+		wait "${server_wrapper}" 2>/dev/null
+		server_wrapper=""
+	fi
+	# last resort, namespace-scoped only: kill iperf3 processes that
+	# actually live in the peer netns. netns != pidns: a blind pkill
+	# would scan the host PID space and hit unrelated tests.
+	for _p in $(ip netns pids "$ns_peer" 2>/dev/null); do
+		if [ "$(cat /proc/$_p/comm 2>/dev/null)" = "iperf3" ]; then
+			kill "$_p" 2>/dev/null
+		fi
+	done
+	iperf_pid=""
+	rm -f "${iperf_pidfile}"
+	ip netns del "$ns_dut" 2>/dev/null
+	ip netns del "$ns_san" 2>/dev/null
+	ip netns del "$ns_peer" 2>/dev/null
+}
+
+trap cleanup EXIT
+
+check_tool()
+{
+	if ! command -v "$1" > /dev/null 2>&1; then
+		echo "SKIP: Could not run test without $1"
+		exit $ksft_skip
+	fi
+}
+
+nsx()
+{
+	ip netns exec "$1" bash -c "$2"
+}
+
+setup_topo()
+{
+	local ns
+
+	cleanup
+	for ns in "$ns_dut" "$ns_san" "$ns_peer"; do
+		ip netns add "$ns"
+	done
+
+	ip link add d_a netns "$ns_dut" type veth peer name p_a netns "$ns_peer"
+	ip link add d_b netns "$ns_dut" type veth peer name p_b netns "$ns_peer"
+	ip link add d_il netns "$ns_dut" type veth peer name s0 netns "$ns_san"
+
+	# HSR tags add 6 bytes per frame; give the LAN legs headroom.
+	for iface in d_a d_b; do
+		nsx "$ns_dut" "ip link set $iface mtu 1600; ip link set $iface up"
+	done
+	for iface in p_a p_b; do
+		nsx "$ns_peer" "ip link set $iface mtu 1600; ip link set $iface up"
+	done
+
+	nsx "$ns_dut" "ip link set d_il up"
+	nsx "$ns_san" "ip link set s0 up; ip addr add $san_ip/24 dev s0"
+
+	nsx "$ns_dut" "ip link add hsr0 type hsr \
+		slave1 d_a slave2 d_b interlink d_il proto 0; \
+		ip link set hsr0 up"
+	nsx "$ns_peer" "ip link add hsr1 type hsr \
+		slave1 p_a slave2 p_b proto 0; \
+		ip link set hsr1 up; ip addr add $peer_ip/24 dev hsr1"
+
+	# Let the nodes see each other's supervision frames.
+	sleep 2
+}
+
+check_feature()
+{
+	local ns="$1"
+	local iface="$2"
+	local feature="$3"
+	local want="$4"
+
+	if nsx "$ns" "ethtool -k $iface" | grep -q "^$feature: $want"; then
+		echo "INFO: $ns/$iface $feature is $want [ OK ]"
+	else
+		echo "FAIL: $ns/$iface $feature is not $want" 1>&2
+		ret=1
+	fi
+}
+
+do_gro_feature_checks()
+{
+	echo "INFO: Checking that enslavement disabled GRO."
+	check_feature "$ns_dut" d_a generic-receive-offload off
+	check_feature "$ns_dut" d_b generic-receive-offload off
+	check_feature "$ns_dut" d_il generic-receive-offload off
+	stop_if_error "GRO not disabled on enslaved devices."
+
+	echo "INFO: Checking that enslavement disabled HW-GRO."
+	check_feature "$ns_dut" d_a rx-gro-hw off
+	check_feature "$ns_dut" d_b rx-gro-hw off
+	check_feature "$ns_dut" d_il rx-gro-hw off
+	stop_if_error "HW-GRO not disabled on enslaved devices."
+
+	echo "INFO: Checking that the HSR master does not advertise GSO/TSO."
+	check_feature "$ns_dut" hsr0 generic-segmentation-offload off
+	check_feature "$ns_dut" hsr0 tcp-segmentation-offload off
+	stop_if_error "HSR master still advertises GSO/TSO."
+}
+
+start_iperf_server()
+{
+	# One-shot server, no -D: record its exact PID (netns shares the PID
+	# namespace). The wrapping shell waits on the server so the script can
+	# really wait(1) for the whole tree, on success and failure alike.
+	rm -f "${iperf_pidfile}"
+	( nsx "$ns_peer" "iperf3 -s -1 > /dev/null 2>&1 & echo \$! > ${iperf_pidfile}; wait" ) &
+	server_wrapper=$!
+	# the wrapper writes the pidfile asynchronously; wait for it to
+	# appear instead of racing the read
+	for _ in $(seq 1 50); do
+		[ -s "${iperf_pidfile}" ] && break
+		sleep 0.1
+	done
+	if [ ! -s "${iperf_pidfile}" ]; then
+		echo "FAIL: iperf3 server did not publish a pid (no pidfile)" 1>&2
+		ret=1
+		return 1
+	fi
+	iperf_pid=$(cat "${iperf_pidfile}")
+	if ! [[ "${iperf_pid}" =~ ^[0-9]+$ ]] || ! kill -0 "${iperf_pid}" 2>/dev/null; then
+		echo "FAIL: iperf3 server pid '${iperf_pid}' invalid or not alive" 1>&2
+		ret=1
+		return 1
+	fi
+	sleep 1
+	return 0
+}
+
+do_tso_stream_test()
+{
+	local out sender_retr
+
+	echo "INFO: Enabling TSO/GSO on the SAN interface."
+	nsx "$ns_san" "ethtool -K s0 tso on gso on"
+	check_feature "$ns_san" s0 tcp-segmentation-offload on
+	stop_if_error "Could not enable TSO on the SAN interface."
+
+	echo "INFO: Running 10s TCP stream SAN -> peer through the HSR DUT."
+	start_iperf_server || return
+		# rate-capped: the discriminator is per-frame unfold (completion with
+	# 0 retransmits), not max throughput; uncapped runs flap at VM/CI
+	# edge rates without indicating a functional problem.
+	out=$(nsx "$ns_san" "timeout 60 iperf3 -c $peer_ip -M 1446 -b 2G -t 10" 2>&1)
+	if [ $? -ne 0 ]; then
+		echo "FAIL: iperf3 client failed:" 1>&2
+		echo "$out" 1>&2
+		ret=1
+		return
+	fi
+
+	# success path: the one-shot server exits by itself; really wait for
+	# the wrapper to reap it, and check its exit status
+	wait "${server_wrapper}"
+	server_rc=$?
+	server_wrapper=""
+	iperf_pid=""
+	if [ "$server_rc" -ne 0 ]; then
+		echo "FAIL: iperf3 server exited with rc=$server_rc" 1>&2
+		ret=1
+		return
+	fi
+
+	sender_retr=$(echo "$out" | awk '/sender/ {print $(NF-1)}')
+	if [ -z "$sender_retr" ] || [ "$sender_retr" -ne 0 ]; then
+		echo "FAIL: retransmits during GSO unfold: ${sender_retr:-unknown}" 1>&2
+		echo "$out" 1>&2
+		ret=1
+		return
+	fi
+
+	echo "INFO: TCP stream completed with 0 retransmits [ OK ]"
+	echo "$out" | grep -E "sender|receiver"
+}
+
+check_prerequisites
+check_tool ethtool
+check_tool iperf3
+check_tool timeout
+
+# iproute2 must know the HSR interlink syntax.
+if ! ip link help hsr 2>&1 | grep -qi interlink; then
+	echo "SKIP: iproute2 has no HSR interlink support"
+	exit $ksft_skip
+fi
+
+setup_topo
+
+echo "INFO: Initial validation ping (SAN -> peer through the DUT)."
+do_ping "$ns_san" "$peer_ip"
+stop_if_error "Initial validation failed."
+
+do_gro_feature_checks
+do_tso_stream_test
+stop_if_error "GSO super-packet stream test failed."
+
+echo "INFO: All good."
+exit $ret
-- 
2.43.0

[PATCH net 3/4] net: hsr: unfold GSO super-packets at the forward entry

[Xin Xie]

HSR/PRP forward frames one by one: each wire frame gets its own tag
and sequence number, and duplicate discard is per frame. A GSO
super-packet reaching hsr_forward_skb() breaks that per-frame
semantics: it would be tagged and forwarded as a single frame.

Unfold such super-packets at the forward entry with the top-level GSO
dispatch: __skb_gso_segment() initializes SKB_GSO_CB() and performs
the L2->L3->L4 protocol dispatch (calling the low-level skb_segment()
helper directly is not allowed here -- it reads SKB_GSO_CB(skb) state
that only __skb_gso_segment() sets up). features = 0 requests full
software segmentation; tx_path is selected by ingress port (master =
locally generated TX, interlink = RX) to get the right checksum
semantics. Each segment then runs through the existing per-frame
path, which is split out as hsr_forward_skb_one() so that no GSO skb
can reach it.

Segmentation is only offered for the ingress roles whose frames are
known to be plain Ethernet: the master (locally generated) and the
interlink (SAN side, untagged). A super-packet received from a LAN
slave may carry per-frame HSR tags or PRP RCT trailers that software
segmentation cannot recover, and an already-tagged HSR/PRP
super-packet violates per-frame wire semantics; both are rejected by
ingress-port policy. (ETH_P_PRP identifies supervision traffic only;
a PRP data frame keeps its payload EtherType, so RCT carriage cannot
be tested by protocol.)

Also drop NETIF_F_GSO_MASK from the HSR master's hw_features so
locally generated traffic is segmented before reaching the forward
path whenever possible.

Fixes: f421436a591d ("net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)")
Cc: stable@vger.kernel.org
Signed-off-by: Xin Xie <xiexinet@gmail.com>
---
 net/hsr/hsr_device.c  |  2 +-
 net/hsr/hsr_forward.c | 50 ++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 50 insertions(+), 2 deletions(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 3fd1762d8..248cbb142 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -652,7 +652,7 @@ void hsr_dev_setup(struct net_device *dev)
 	dev->needs_free_netdev = true;
 
 	dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
-			   NETIF_F_GSO_MASK | NETIF_F_HW_CSUM |
+			   NETIF_F_HW_CSUM |
 			   NETIF_F_HW_VLAN_CTAG_TX |
 			   NETIF_F_HW_VLAN_CTAG_FILTER;
 
diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index 8e4158a9b..3fcdbac49 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -12,6 +12,7 @@
 #include <linux/skbuff.h>
 #include <linux/etherdevice.h>
 #include <linux/if_vlan.h>
+#include <net/gso.h>
 #include "hsr_main.h"
 #include "hsr_framereg.h"
 
@@ -732,7 +733,7 @@ static int fill_frame_info(struct hsr_frame_info *frame,
 }
 
 /* Must be called holding rcu read lock (because of the port parameter) */
-void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port)
+static void hsr_forward_skb_one(struct sk_buff *skb, struct hsr_port *port)
 {
 	struct hsr_frame_info frame;
 
@@ -761,3 +762,50 @@ void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port)
 	port->dev->stats.tx_dropped++;
 	kfree_skb(skb);
 }
+
+/* GSO fan-out funnel: unfold super-packets before per-frame processing so
+ * each wire frame gets its own HSR/PRP tag and sequence number.
+ */
+void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port)
+{
+	struct sk_buff *segs, *next;
+
+	if (likely(!skb_is_gso(skb))) {
+		hsr_forward_skb_one(skb, port);
+		return;
+	}
+
+	/* Unfold only plain-Ethernet GSO super-packets: locally generated
+	 * on the master, or arriving untagged from the SAN side on the
+	 * interlink. A super-packet from a LAN slave may carry per-frame
+	 * HSR tags / PRP RCT trailers that software segmentation cannot
+	 * recover; an already-tagged HSR/PRP super-packet violates
+	 * per-frame wire semantics. Drop both.
+	 */
+	if (port->type != HSR_PT_MASTER && port->type != HSR_PT_INTERLINK)
+		goto drop_gso;
+	if (skb->protocol == htons(ETH_P_HSR) ||
+	    skb->protocol == htons(ETH_P_PRP))
+		goto drop_gso;
+
+	/* features = 0: request full software segmentation. tx_path is true
+	 * only for locally generated traffic on the master; ingress from
+	 * the interlink follows RX checksum semantics.
+	 */
+	segs = __skb_gso_segment(skb, 0, port->type == HSR_PT_MASTER);
+	if (IS_ERR(segs) || unlikely(!segs))
+		goto drop_gso;
+
+	consume_skb(skb);
+	while (segs) {
+		next = segs->next;
+		segs->next = NULL;
+		hsr_forward_skb_one(segs, port);
+		segs = next;
+	}
+	return;
+
+drop_gso:
+	port->dev->stats.tx_dropped++;
+	kfree_skb(skb);
+}
-- 
2.43.0