From f3009d0d6ab78053117f8857b921a8237f4d17b3 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 14 Mar 2025 13:10:57 +0300
Subject: [PATCH 01/16] net: atm: fix use after free in lec_send()

The ->send() operation frees skb so save the length before calling
->send() to avoid a use after free.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/c751531d-4af4-42fe-affe-6104b34b791d@stanley.mountain
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/atm/lec.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/atm/lec.c b/net/atm/lec.c
index ffef658862db..a948dd47c3f3 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -181,6 +181,7 @@ static void
 lec_send(struct atm_vcc *vcc, struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
+	unsigned int len = skb->len;
 
 	ATM_SKB(skb)->vcc = vcc;
 	atm_account_tx(vcc, skb);
@@ -191,7 +192,7 @@ lec_send(struct atm_vcc *vcc, struct sk_buff *skb)
 	}
 
 	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
+	dev->stats.tx_bytes += len;
 }
 
 static void lec_tx_timeout(struct net_device *dev, unsigned int txqueue)
-- 
2.50.1


From 47a9b5e52abd2b717dfc8b9460589f89936d93cf Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Fri, 14 Mar 2025 15:57:21 +0530
Subject: [PATCH 02/16] net: ti: icssg-prueth: Add lock to stats

Currently the API emac_update_hardware_stats() reads different ICSSG
stats without any lock protection.

This API gets called by .ndo_get_stats64() which is only under RCU
protection and nothing else. Add lock to this API so that the reading of
statistics happens during lock.

Fixes: c1e10d5dc7a1 ("net: ti: icssg-prueth: Add ICSSG Stats")
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250314102721.1394366-1-danishanwar@ti.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/ti/icssg/icssg_prueth.c | 1 +
 drivers/net/ethernet/ti/icssg/icssg_prueth.h | 2 ++
 drivers/net/ethernet/ti/icssg/icssg_stats.c  | 4 ++++
 3 files changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 00ed97860547..9a75733e3f8f 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -1679,6 +1679,7 @@ static int prueth_probe(struct platform_device *pdev)
 	}
 
 	spin_lock_init(&prueth->vtbl_lock);
+	spin_lock_init(&prueth->stats_lock);
 	/* setup netdev interfaces */
 	if (eth0_node) {
 		ret = prueth_netdev_init(prueth, eth0_node);
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index 329b46e9ee53..f41786b05741 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -305,6 +305,8 @@ struct prueth {
 	int default_vlan;
 	/** @vtbl_lock: Lock for vtbl in shared memory */
 	spinlock_t vtbl_lock;
+	/** @stats_lock: Lock for reading icssg stats */
+	spinlock_t stats_lock;
 };
 
 struct emac_tx_ts_response {
diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.c b/drivers/net/ethernet/ti/icssg/icssg_stats.c
index 8800bd3a8d07..6f0edae38ea2 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_stats.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_stats.c
@@ -26,6 +26,8 @@ void emac_update_hardware_stats(struct prueth_emac *emac)
 	u32 val, reg;
 	int i;
 
+	spin_lock(&prueth->stats_lock);
+
 	for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++) {
 		regmap_read(prueth->miig_rt,
 			    base + icssg_all_miig_stats[i].offset,
@@ -51,6 +53,8 @@ void emac_update_hardware_stats(struct prueth_emac *emac)
 			emac->pa_stats[i] += val;
 		}
 	}
+
+	spin_unlock(&prueth->stats_lock);
 }
 
 void icssg_stats_work_handler(struct work_struct *work)
-- 
2.50.1


From 986ffb3a57c5650fb8bf6d59a8f0f07046abfeb6 Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Fri, 14 Mar 2025 13:00:46 +0100
Subject: [PATCH 03/16] net: lwtunnel: fix recursion loops

This patch acts as a parachute, catch all solution, by detecting
recursion loops in lwtunnel users and taking care of them (e.g., a loop
between routes, a loop within the same route, etc). In general, such
loops are the consequence of pathological configurations. Each lwtunnel
user is still free to catch such loops early and do whatever they want
with them. It will be the case in a separate patch for, e.g., seg6 and
seg6_local, in order to provide drop reasons and update statistics.
Another example of a lwtunnel user taking care of loops is ioam6, which
has valid use cases that include loops (e.g., inline mode), and which is
addressed by the next patch in this series. Overall, this patch acts as
a last resort to catch loops and drop packets, since we don't want to
leak something unintentionally because of a pathological configuration
in lwtunnels.

The solution in this patch reuses dev_xmit_recursion(),
dev_xmit_recursion_inc(), and dev_xmit_recursion_dec(), which seems fine
considering the context.

Closes: https://lore.kernel.org/netdev/2bc9e2079e864a9290561894d2a602d6@akamai.com/
Closes: https://lore.kernel.org/netdev/Z7NKYMY7fJT5cYWu@shredder/
Fixes: ffce41962ef6 ("lwtunnel: support dst output redirect function")
Fixes: 2536862311d2 ("lwt: Add support to redirect dst.input")
Fixes: 14972cbd34ff ("net: lwtunnel: Handle fragmentation")
Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Link: https://patch.msgid.link/20250314120048.12569-2-justin.iurman@uliege.be
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/lwtunnel.c | 65 ++++++++++++++++++++++++++++++++++++---------
 1 file changed, 53 insertions(+), 12 deletions(-)

diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 711cd3b4347a..4417a18b3e95 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -23,6 +23,8 @@
 #include <net/ip6_fib.h>
 #include <net/rtnh.h>
 
+#include "dev.h"
+
 DEFINE_STATIC_KEY_FALSE(nf_hooks_lwtunnel_enabled);
 EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_enabled);
 
@@ -325,13 +327,23 @@ EXPORT_SYMBOL_GPL(lwtunnel_cmp_encap);
 
 int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb);
 	const struct lwtunnel_encap_ops *ops;
 	struct lwtunnel_state *lwtstate;
-	int ret = -EINVAL;
+	struct dst_entry *dst;
+	int ret;
+
+	if (dev_xmit_recursion()) {
+		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
+				     __func__);
+		ret = -ENETDOWN;
+		goto drop;
+	}
 
-	if (!dst)
+	dst = skb_dst(skb);
+	if (!dst) {
+		ret = -EINVAL;
 		goto drop;
+	}
 	lwtstate = dst->lwtstate;
 
 	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
@@ -341,8 +353,11 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
-	if (likely(ops && ops->output))
+	if (likely(ops && ops->output)) {
+		dev_xmit_recursion_inc();
 		ret = ops->output(net, sk, skb);
+		dev_xmit_recursion_dec();
+	}
 	rcu_read_unlock();
 
 	if (ret == -EOPNOTSUPP)
@@ -359,13 +374,23 @@ EXPORT_SYMBOL_GPL(lwtunnel_output);
 
 int lwtunnel_xmit(struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb);
 	const struct lwtunnel_encap_ops *ops;
 	struct lwtunnel_state *lwtstate;
-	int ret = -EINVAL;
+	struct dst_entry *dst;
+	int ret;
+
+	if (dev_xmit_recursion()) {
+		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
+				     __func__);
+		ret = -ENETDOWN;
+		goto drop;
+	}
 
-	if (!dst)
+	dst = skb_dst(skb);
+	if (!dst) {
+		ret = -EINVAL;
 		goto drop;
+	}
 
 	lwtstate = dst->lwtstate;
 
@@ -376,8 +401,11 @@ int lwtunnel_xmit(struct sk_buff *skb)
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
-	if (likely(ops && ops->xmit))
+	if (likely(ops && ops->xmit)) {
+		dev_xmit_recursion_inc();
 		ret = ops->xmit(skb);
+		dev_xmit_recursion_dec();
+	}
 	rcu_read_unlock();
 
 	if (ret == -EOPNOTSUPP)
@@ -394,13 +422,23 @@ EXPORT_SYMBOL_GPL(lwtunnel_xmit);
 
 int lwtunnel_input(struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb);
 	const struct lwtunnel_encap_ops *ops;
 	struct lwtunnel_state *lwtstate;
-	int ret = -EINVAL;
+	struct dst_entry *dst;
+	int ret;
 
-	if (!dst)
+	if (dev_xmit_recursion()) {
+		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
+				     __func__);
+		ret = -ENETDOWN;
 		goto drop;
+	}
+
+	dst = skb_dst(skb);
+	if (!dst) {
+		ret = -EINVAL;
+		goto drop;
+	}
 	lwtstate = dst->lwtstate;
 
 	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
@@ -410,8 +448,11 @@ int lwtunnel_input(struct sk_buff *skb)
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
-	if (likely(ops && ops->input))
+	if (likely(ops && ops->input)) {
+		dev_xmit_recursion_inc();
 		ret = ops->input(skb);
+		dev_xmit_recursion_dec();
+	}
 	rcu_read_unlock();
 
 	if (ret == -EOPNOTSUPP)
-- 
2.50.1


From 3e7a60b368eadf6c30a4a79dea1eb8f88b6d620d Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Fri, 14 Mar 2025 13:00:47 +0100
Subject: [PATCH 04/16] net: ipv6: ioam6: fix lwtunnel_output() loop

Fix the lwtunnel_output() reentry loop in ioam6_iptunnel when the
destination is the same after transformation. Note that a check on the
destination address was already performed, but it was not enough. This
is the example of a lwtunnel user taking care of loops without relying
only on the last resort detection offered by lwtunnel.

Fixes: 8cb3bf8bff3c ("ipv6: ioam: Add support for the ip6ip6 encapsulation")
Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Link: https://patch.msgid.link/20250314120048.12569-3-justin.iurman@uliege.be
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/ioam6_iptunnel.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index 2c383c12a431..09065187378e 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -337,7 +337,6 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
 static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb), *cache_dst = NULL;
-	struct in6_addr orig_daddr;
 	struct ioam6_lwt *ilwt;
 	int err = -EINVAL;
 	u32 pkt_cnt;
@@ -352,8 +351,6 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	if (pkt_cnt % ilwt->freq.n >= ilwt->freq.k)
 		goto out;
 
-	orig_daddr = ipv6_hdr(skb)->daddr;
-
 	local_bh_disable();
 	cache_dst = dst_cache_get(&ilwt->cache);
 	local_bh_enable();
@@ -422,7 +419,10 @@ do_encap:
 			goto drop;
 	}
 
-	if (!ipv6_addr_equal(&orig_daddr, &ipv6_hdr(skb)->daddr)) {
+	/* avoid lwtunnel_output() reentry loop when destination is the same
+	 * after transformation (e.g., with the inline mode)
+	 */
+	if (dst->lwtstate != cache_dst->lwtstate) {
 		skb_dst_drop(skb);
 		skb_dst_set(skb, cache_dst);
 		return dst_output(net, sk, skb);
-- 
2.50.1


From 3ed61b8938c66680e13a1d1929afb9b145c26a86 Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Fri, 14 Mar 2025 13:00:48 +0100
Subject: [PATCH 05/16] selftests: net: test for lwtunnel dst ref loops

As recently specified by commit 0ea09cbf8350 ("docs: netdev: add a note
on selftest posting") in net-next, the selftest is therefore shipped in
this series. However, this selftest does not really test this series. It
needs this series to avoid crashing the kernel. What it really tests,
thanks to kmemleak, is what was fixed by the following commits:
- commit c71a192976de ("net: ipv6: fix dst refleaks in rpl, seg6 and
ioam6 lwtunnels")
- commit 92191dd10730 ("net: ipv6: fix dst ref loops in rpl, seg6 and
ioam6 lwtunnels")
- commit c64a0727f9b1 ("net: ipv6: fix dst ref loop on input in seg6
lwt")
- commit 13e55fbaec17 ("net: ipv6: fix dst ref loop on input in rpl
lwt")
- commit 0e7633d7b95b ("net: ipv6: fix dst ref loop in ila lwtunnel")
- commit 5da15a9c11c1 ("net: ipv6: fix missing dst ref drop in ila
lwtunnel")

Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Link: https://patch.msgid.link/20250314120048.12569-4-justin.iurman@uliege.be
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/Makefile          |   1 +
 tools/testing/selftests/net/config            |   2 +
 .../selftests/net/lwt_dst_cache_ref_loop.sh   | 246 ++++++++++++++++++
 3 files changed, 249 insertions(+)
 create mode 100755 tools/testing/selftests/net/lwt_dst_cache_ref_loop.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 5916f3b81c39..843ab747645d 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -101,6 +101,7 @@ TEST_PROGS += vlan_bridge_binding.sh
 TEST_PROGS += bpf_offload.py
 TEST_PROGS += ipv6_route_update_soft_lockup.sh
 TEST_PROGS += busy_poll_test.sh
+TEST_PROGS += lwt_dst_cache_ref_loop.sh
 
 # YNL files, must be before "include ..lib.mk"
 YNL_GEN_FILES := busy_poller netlink-dumps
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 5b9baf708950..61e5116987f3 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -107,3 +107,5 @@ CONFIG_XFRM_INTERFACE=m
 CONFIG_XFRM_USER=m
 CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP6_NF_MATCH_RPFILTER=m
+CONFIG_IPV6_ILA=m
+CONFIG_IPV6_RPL_LWTUNNEL=y
diff --git a/tools/testing/selftests/net/lwt_dst_cache_ref_loop.sh b/tools/testing/selftests/net/lwt_dst_cache_ref_loop.sh
new file mode 100755
index 000000000000..881eb399798f
--- /dev/null
+++ b/tools/testing/selftests/net/lwt_dst_cache_ref_loop.sh
@@ -0,0 +1,246 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Author: Justin Iurman <justin.iurman@uliege.be>
+#
+# WARNING
+# -------
+# This is just a dummy script that triggers encap cases with possible dst cache
+# reference loops in affected lwt users (see list below). Some cases are
+# pathological configurations for simplicity, others are valid. Overall, we
+# don't want this issue to happen, no matter what. In order to catch any
+# reference loops, kmemleak MUST be used. The results alone are always blindly
+# successful, don't rely on them. Note that the following tests may crash the
+# kernel if the fix to prevent lwtunnel_{input|output|xmit}() reentry loops is
+# not present.
+#
+# Affected lwt users so far (please update accordingly if needed):
+#  - ila_lwt (output only)
+#  - ioam6_iptunnel (output only)
+#  - rpl_iptunnel (both input and output)
+#  - seg6_iptunnel (both input and output)
+
+source lib.sh
+
+check_compatibility()
+{
+	setup_ns tmp_node &>/dev/null
+	if [ $? != 0 ]; then
+		echo "SKIP: Cannot create netns."
+		exit $ksft_skip
+	fi
+
+	ip link add name veth0 netns $tmp_node type veth \
+		peer name veth1 netns $tmp_node &>/dev/null
+	local ret=$?
+
+	ip -netns $tmp_node link set veth0 up &>/dev/null
+	ret=$((ret + $?))
+
+	ip -netns $tmp_node link set veth1 up &>/dev/null
+	ret=$((ret + $?))
+
+	if [ $ret != 0 ]; then
+		echo "SKIP: Cannot configure links."
+		cleanup_ns $tmp_node
+		exit $ksft_skip
+	fi
+
+	lsmod 2>/dev/null | grep -q "ila"
+	ila_lsmod=$?
+	[ $ila_lsmod != 0 ] && modprobe ila &>/dev/null
+
+	ip -netns $tmp_node route add 2001:db8:1::/64 \
+		encap ila 1:2:3:4 csum-mode no-action ident-type luid \
+			hook-type output \
+		dev veth0 &>/dev/null
+
+	ip -netns $tmp_node route add 2001:db8:2::/64 \
+		encap ioam6 trace prealloc type 0x800000 ns 0 size 4 \
+		dev veth0 &>/dev/null
+
+	ip -netns $tmp_node route add 2001:db8:3::/64 \
+		encap rpl segs 2001:db8:3::1 dev veth0 &>/dev/null
+
+	ip -netns $tmp_node route add 2001:db8:4::/64 \
+		encap seg6 mode inline segs 2001:db8:4::1 dev veth0 &>/dev/null
+
+	ip -netns $tmp_node -6 route 2>/dev/null | grep -q "encap ila"
+	skip_ila=$?
+
+	ip -netns $tmp_node -6 route 2>/dev/null | grep -q "encap ioam6"
+	skip_ioam6=$?
+
+	ip -netns $tmp_node -6 route 2>/dev/null | grep -q "encap rpl"
+	skip_rpl=$?
+
+	ip -netns $tmp_node -6 route 2>/dev/null | grep -q "encap seg6"
+	skip_seg6=$?
+
+	cleanup_ns $tmp_node
+}
+
+setup()
+{
+	setup_ns alpha beta gamma &>/dev/null
+
+	ip link add name veth-alpha netns $alpha type veth \
+		peer name veth-betaL netns $beta &>/dev/null
+
+	ip link add name veth-betaR netns $beta type veth \
+		peer name veth-gamma netns $gamma &>/dev/null
+
+	ip -netns $alpha link set veth-alpha name veth0 &>/dev/null
+	ip -netns $beta link set veth-betaL name veth0 &>/dev/null
+	ip -netns $beta link set veth-betaR name veth1 &>/dev/null
+	ip -netns $gamma link set veth-gamma name veth0 &>/dev/null
+
+	ip -netns $alpha addr add 2001:db8:1::2/64 dev veth0 &>/dev/null
+	ip -netns $alpha link set veth0 up &>/dev/null
+	ip -netns $alpha link set lo up &>/dev/null
+	ip -netns $alpha route add 2001:db8:2::/64 \
+		via 2001:db8:1::1 dev veth0 &>/dev/null
+
+	ip -netns $beta addr add 2001:db8:1::1/64 dev veth0 &>/dev/null
+	ip -netns $beta addr add 2001:db8:2::1/64 dev veth1 &>/dev/null
+	ip -netns $beta link set veth0 up &>/dev/null
+	ip -netns $beta link set veth1 up &>/dev/null
+	ip -netns $beta link set lo up &>/dev/null
+	ip -netns $beta route del 2001:db8:2::/64
+	ip -netns $beta route add 2001:db8:2::/64 dev veth1
+	ip netns exec $beta \
+		sysctl -wq net.ipv6.conf.all.forwarding=1 &>/dev/null
+
+	ip -netns $gamma addr add 2001:db8:2::2/64 dev veth0 &>/dev/null
+	ip -netns $gamma link set veth0 up &>/dev/null
+	ip -netns $gamma link set lo up &>/dev/null
+	ip -netns $gamma route add 2001:db8:1::/64 \
+		via 2001:db8:2::1 dev veth0 &>/dev/null
+
+	sleep 1
+
+	ip netns exec $alpha ping6 -c 5 -W 1 2001:db8:2::2 &>/dev/null
+	if [ $? != 0 ]; then
+		echo "SKIP: Setup failed."
+		exit $ksft_skip
+	fi
+
+	sleep 1
+}
+
+cleanup()
+{
+	cleanup_ns $alpha $beta $gamma
+	[ $ila_lsmod != 0 ] && modprobe -r ila &>/dev/null
+}
+
+run_ila()
+{
+	if [ $skip_ila != 0 ]; then
+		echo "SKIP: ila (output)"
+		return
+	fi
+
+	ip -netns $beta route del 2001:db8:2::/64
+	ip -netns $beta route add 2001:db8:2:0:0:0:0:2/128 \
+		encap ila 2001:db8:2:0 csum-mode no-action ident-type luid \
+			hook-type output \
+		dev veth1 &>/dev/null
+	sleep 1
+
+	echo "TEST: ila (output)"
+	ip netns exec $beta ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null
+	sleep 1
+
+	ip -netns $beta route del 2001:db8:2:0:0:0:0:2/128
+	ip -netns $beta route add 2001:db8:2::/64 dev veth1
+	sleep 1
+}
+
+run_ioam6()
+{
+	if [ $skip_ioam6 != 0 ]; then
+		echo "SKIP: ioam6 (output)"
+		return
+	fi
+
+	ip -netns $beta route change 2001:db8:2::/64 \
+		encap ioam6 trace prealloc type 0x800000 ns 1 size 4 \
+		dev veth1 &>/dev/null
+	sleep 1
+
+	echo "TEST: ioam6 (output)"
+	ip netns exec $beta ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null
+	sleep 1
+}
+
+run_rpl()
+{
+	if [ $skip_rpl != 0 ]; then
+		echo "SKIP: rpl (input)"
+		echo "SKIP: rpl (output)"
+		return
+	fi
+
+	ip -netns $beta route change 2001:db8:2::/64 \
+		encap rpl segs 2001:db8:2::2 \
+		dev veth1 &>/dev/null
+	sleep 1
+
+	echo "TEST: rpl (input)"
+	ip netns exec $alpha ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null
+	sleep 1
+
+	echo "TEST: rpl (output)"
+	ip netns exec $beta ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null
+	sleep 1
+}
+
+run_seg6()
+{
+	if [ $skip_seg6 != 0 ]; then
+		echo "SKIP: seg6 (input)"
+		echo "SKIP: seg6 (output)"
+		return
+	fi
+
+	ip -netns $beta route change 2001:db8:2::/64 \
+		encap seg6 mode inline segs 2001:db8:2::2 \
+		dev veth1 &>/dev/null
+	sleep 1
+
+	echo "TEST: seg6 (input)"
+	ip netns exec $alpha ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null
+	sleep 1
+
+	echo "TEST: seg6 (output)"
+	ip netns exec $beta ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null
+	sleep 1
+}
+
+run()
+{
+	run_ila
+	run_ioam6
+	run_rpl
+	run_seg6
+}
+
+if [ "$(id -u)" -ne 0 ]; then
+	echo "SKIP: Need root privileges."
+	exit $ksft_skip
+fi
+
+if [ ! -x "$(command -v ip)" ]; then
+	echo "SKIP: Could not run test without ip tool."
+	exit $ksft_skip
+fi
+
+check_compatibility
+
+trap cleanup EXIT
+
+setup
+run
+
+exit $ksft_pass
-- 
2.50.1


From 2c1f97a52cb827a5f2768e67a9dddffae1ed47ab Mon Sep 17 00:00:00 2001
From: Arthur Mongodin <amongodin@randorisec.fr>
Date: Fri, 14 Mar 2025 21:11:31 +0100
Subject: [PATCH 06/16] mptcp: Fix data stream corruption in the address
 announcement

Because of the size restriction in the TCP options space, the MPTCP
ADD_ADDR option is exclusive and cannot be sent with other MPTCP ones.
For this reason, in the linked mptcp_out_options structure, group of
fields linked to different options are part of the same union.

There is a case where the mptcp_pm_add_addr_signal() function can modify
opts->addr, but not ended up sending an ADD_ADDR. Later on, back in
mptcp_established_options, other options will be sent, but with
unexpected data written in other fields due to the union, e.g. in
opts->ext_copy. This could lead to a data stream corruption in the next
packet.

Using an intermediate variable, prevents from corrupting previously
established DSS option. The assignment of the ADD_ADDR option
parameters is now done once we are sure this ADD_ADDR option can be set
in the packet, e.g. after having dropped other suboptions.

Fixes: 1bff1e43a30e ("mptcp: optimize out option generation")
Cc: stable@vger.kernel.org
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Arthur Mongodin <amongodin@randorisec.fr>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
[ Matt: the commit message has been updated: long lines splits and some
  clarifications. ]
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250314-net-mptcp-fix-data-stream-corr-sockopt-v1-1-122dbb249db3@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/options.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index fd2de185bc93..23949ae2a3a8 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -651,6 +651,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
 	bool drop_other_suboptions = false;
 	unsigned int opt_size = *size;
+	struct mptcp_addr_info addr;
 	bool echo;
 	int len;
 
@@ -659,7 +660,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 	 */
 	if (!mptcp_pm_should_add_signal(msk) ||
 	    (opts->suboptions & (OPTION_MPTCP_MPJ_ACK | OPTION_MPTCP_MPC_ACK)) ||
-	    !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &opts->addr,
+	    !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &addr,
 		    &echo, &drop_other_suboptions))
 		return false;
 
@@ -672,7 +673,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 	else if (opts->suboptions & OPTION_MPTCP_DSS)
 		return false;
 
-	len = mptcp_add_addr_len(opts->addr.family, echo, !!opts->addr.port);
+	len = mptcp_add_addr_len(addr.family, echo, !!addr.port);
 	if (remaining < len)
 		return false;
 
@@ -689,6 +690,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 		opts->ahmac = 0;
 		*size -= opt_size;
 	}
+	opts->addr = addr;
 	opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
 	if (!echo) {
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDRTX);
-- 
2.50.1


From 23b763302ce068d7c97441e75434dc9f903adc7d Mon Sep 17 00:00:00 2001
From: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
Date: Fri, 14 Mar 2025 22:41:54 +0100
Subject: [PATCH 07/16] tools headers: Sync uapi/asm-generic/socket.h with the
 kernel sources

This also fixes a wrong definitions for SCM_TS_OPT_ID & SO_RCVPRIORITY.

Accidentally found while working on another patchset.

Cc: linux-kernel@vger.kernel.org
Cc: netdev@vger.kernel.org
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Jason Xing <kerneljasonxing@gmail.com>
Cc: Anna Emese Nyiri <annaemesenyiri@gmail.com>
Cc: Kuniyuki Iwashima <kuniyu@amazon.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Fixes: a89568e9be75 ("selftests: txtimestamp: add SCM_TS_OPT_ID test")
Fixes: e45469e594b2 ("sock: Introduce SO_RCVPRIORITY socket option")
Link: https://lore.kernel.org/netdev/20250314195257.34854-1-kuniyu@amazon.com/
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://patch.msgid.link/20250314214155.16046-1-aleksandr.mikhalitsyn@canonical.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/include/uapi/asm-generic/socket.h | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h
index ffff554a5230..aa5016ff3d91 100644
--- a/tools/include/uapi/asm-generic/socket.h
+++ b/tools/include/uapi/asm-generic/socket.h
@@ -119,14 +119,31 @@
 
 #define SO_DETACH_REUSEPORT_BPF 68
 
+#define SO_PREFER_BUSY_POLL	69
+#define SO_BUSY_POLL_BUDGET	70
+
+#define SO_NETNS_COOKIE		71
+
+#define SO_BUF_LOCK		72
+
+#define SO_RESERVE_MEM		73
+
+#define SO_TXREHASH		74
+
 #define SO_RCVMARK		75
 
 #define SO_PASSPIDFD		76
 #define SO_PEERPIDFD		77
 
-#define SCM_TS_OPT_ID		78
+#define SO_DEVMEM_LINEAR	78
+#define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
+#define SO_DEVMEM_DMABUF	79
+#define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+#define SO_DEVMEM_DONTNEED	80
+
+#define SCM_TS_OPT_ID		81
 
-#define SO_RCVPRIORITY		79
+#define SO_RCVPRIORITY		82
 
 #if !defined(__KERNEL__)
 
-- 
2.50.1


From 90a7138619a0c55e2aefaad27b12ffc2ddbeed78 Mon Sep 17 00:00:00 2001
From: Lin Ma <linma@zju.edu.cn>
Date: Sun, 16 Mar 2025 00:51:13 +0800
Subject: [PATCH 08/16] net/neighbor: add missing policy for
 NDTPA_QUEUE_LENBYTES

Previous commit 8b5c171bb3dc ("neigh: new unresolved queue limits")
introduces new netlink attribute NDTPA_QUEUE_LENBYTES to represent
approximative value for deprecated QUEUE_LEN. However, it forgot to add
the associated nla_policy in nl_ntbl_parm_policy array. Fix it with one
simple NLA_U32 type policy.

Fixes: 8b5c171bb3dc ("neigh: new unresolved queue limits")
Signed-off-by: Lin Ma <linma@zju.edu.cn>
Link: https://patch.msgid.link/20250315165113.37600-1-linma@zju.edu.cn
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/neighbour.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index bd0251bd74a1..1a620f903c56 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2250,6 +2250,7 @@ static const struct nla_policy nl_neightbl_policy[NDTA_MAX+1] = {
 static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = {
 	[NDTPA_IFINDEX]			= { .type = NLA_U32 },
 	[NDTPA_QUEUE_LEN]		= { .type = NLA_U32 },
+	[NDTPA_QUEUE_LENBYTES]		= { .type = NLA_U32 },
 	[NDTPA_PROXY_QLEN]		= { .type = NLA_U32 },
 	[NDTPA_APP_PROBES]		= { .type = NLA_U32 },
 	[NDTPA_UCAST_PROBES]		= { .type = NLA_U32 },
-- 
2.50.1


From 355d940f4d5ae56ed082a455ce2cc737c7e898e8 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Wed, 19 Mar 2025 22:26:45 +0100
Subject: [PATCH 09/16] Revert "selftests: Add IPv6 link-local address
 generation tests for GRE devices."

This reverts commit 6f50175ccad4278ed3a9394c00b797b75441bd6e.

Commit 183185a18ff9 ("gre: Fix IPv6 link-local address generation.") is
going to be reverted. So let's revert the corresponding kselftest
first.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Link: https://patch.msgid.link/259a9e98f7f1be7ce02b53d0b4afb7c18a8ff747.1742418408.git.gnault@redhat.com
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/Makefile          |   1 -
 .../testing/selftests/net/gre_ipv6_lladdr.sh  | 177 ------------------
 2 files changed, 178 deletions(-)
 delete mode 100755 tools/testing/selftests/net/gre_ipv6_lladdr.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 843ab747645d..8f32b4f01aee 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -31,7 +31,6 @@ TEST_PROGS += veth.sh
 TEST_PROGS += ioam6.sh
 TEST_PROGS += gro.sh
 TEST_PROGS += gre_gso.sh
-TEST_PROGS += gre_ipv6_lladdr.sh
 TEST_PROGS += cmsg_so_mark.sh
 TEST_PROGS += cmsg_so_priority.sh
 TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh
diff --git a/tools/testing/selftests/net/gre_ipv6_lladdr.sh b/tools/testing/selftests/net/gre_ipv6_lladdr.sh
deleted file mode 100755
index 5b34f6e1f831..000000000000
--- a/tools/testing/selftests/net/gre_ipv6_lladdr.sh
+++ /dev/null
@@ -1,177 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-source ./lib.sh
-
-PAUSE_ON_FAIL="no"
-
-# The trap function handler
-#
-exit_cleanup_all()
-{
-	cleanup_all_ns
-
-	exit "${EXIT_STATUS}"
-}
-
-# Add fake IPv4 and IPv6 networks on the loopback device, to be used as
-# underlay by future GRE devices.
-#
-setup_basenet()
-{
-	ip -netns "${NS0}" link set dev lo up
-	ip -netns "${NS0}" address add dev lo 192.0.2.10/24
-	ip -netns "${NS0}" address add dev lo 2001:db8::10/64 nodad
-}
-
-# Check if network device has an IPv6 link-local address assigned.
-#
-# Parameters:
-#
-#   * $1: The network device to test
-#   * $2: An extra regular expression that should be matched (to verify the
-#         presence of extra attributes)
-#   * $3: The expected return code from grep (to allow checking the absence of
-#         a link-local address)
-#   * $4: The user visible name for the scenario being tested
-#
-check_ipv6_ll_addr()
-{
-	local DEV="$1"
-	local EXTRA_MATCH="$2"
-	local XRET="$3"
-	local MSG="$4"
-
-	RET=0
-	set +e
-	ip -netns "${NS0}" -6 address show dev "${DEV}" scope link | grep "fe80::" | grep -q "${EXTRA_MATCH}"
-	check_err_fail "${XRET}" $? ""
-	log_test "${MSG}"
-	set -e
-}
-
-# Create a GRE device and verify that it gets an IPv6 link-local address as
-# expected.
-#
-# Parameters:
-#
-#   * $1: The device type (gre, ip6gre, gretap or ip6gretap)
-#   * $2: The local underlay IP address (can be an IPv4, an IPv6 or "any")
-#   * $3: The remote underlay IP address (can be an IPv4, an IPv6 or "any")
-#   * $4: The IPv6 interface identifier generation mode to use for the GRE
-#         device (eui64, none, stable-privacy or random).
-#
-test_gre_device()
-{
-	local GRE_TYPE="$1"
-	local LOCAL_IP="$2"
-	local REMOTE_IP="$3"
-	local MODE="$4"
-	local ADDR_GEN_MODE
-	local MATCH_REGEXP
-	local MSG
-
-	ip link add netns "${NS0}" name gretest type "${GRE_TYPE}" local "${LOCAL_IP}" remote "${REMOTE_IP}"
-
-	case "${MODE}" in
-	    "eui64")
-		ADDR_GEN_MODE=0
-		MATCH_REGEXP=""
-		MSG="${GRE_TYPE}, mode: 0 (EUI64), ${LOCAL_IP} -> ${REMOTE_IP}"
-		XRET=0
-		;;
-	    "none")
-		ADDR_GEN_MODE=1
-		MATCH_REGEXP=""
-		MSG="${GRE_TYPE}, mode: 1 (none), ${LOCAL_IP} -> ${REMOTE_IP}"
-		XRET=1 # No link-local address should be generated
-		;;
-	    "stable-privacy")
-		ADDR_GEN_MODE=2
-		MATCH_REGEXP="stable-privacy"
-		MSG="${GRE_TYPE}, mode: 2 (stable privacy), ${LOCAL_IP} -> ${REMOTE_IP}"
-		XRET=0
-		# Initialise stable_secret (required for stable-privacy mode)
-		ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.stable_secret="2001:db8::abcd"
-		;;
-	    "random")
-		ADDR_GEN_MODE=3
-		MATCH_REGEXP="stable-privacy"
-		MSG="${GRE_TYPE}, mode: 3 (random), ${LOCAL_IP} -> ${REMOTE_IP}"
-		XRET=0
-		;;
-	esac
-
-	# Check that IPv6 link-local address is generated when device goes up
-	ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
-	ip -netns "${NS0}" link set dev gretest up
-	check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "config: ${MSG}"
-
-	# Now disable link-local address generation
-	ip -netns "${NS0}" link set dev gretest down
-	ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode=1
-	ip -netns "${NS0}" link set dev gretest up
-
-	# Check that link-local address generation works when re-enabled while
-	# the device is already up
-	ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
-	check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "update: ${MSG}"
-
-	ip -netns "${NS0}" link del dev gretest
-}
-
-test_gre4()
-{
-	local GRE_TYPE
-	local MODE
-
-	for GRE_TYPE in "gre" "gretap"; do
-		printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
-
-		for MODE in "eui64" "none" "stable-privacy" "random"; do
-			test_gre_device "${GRE_TYPE}" 192.0.2.10 192.0.2.11 "${MODE}"
-			test_gre_device "${GRE_TYPE}" any 192.0.2.11 "${MODE}"
-			test_gre_device "${GRE_TYPE}" 192.0.2.10 any "${MODE}"
-		done
-	done
-}
-
-test_gre6()
-{
-	local GRE_TYPE
-	local MODE
-
-	for GRE_TYPE in "ip6gre" "ip6gretap"; do
-		printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
-
-		for MODE in "eui64" "none" "stable-privacy" "random"; do
-			test_gre_device "${GRE_TYPE}" 2001:db8::10 2001:db8::11 "${MODE}"
-			test_gre_device "${GRE_TYPE}" any 2001:db8::11 "${MODE}"
-			test_gre_device "${GRE_TYPE}" 2001:db8::10 any "${MODE}"
-		done
-	done
-}
-
-usage()
-{
-	echo "Usage: $0 [-p]"
-	exit 1
-}
-
-while getopts :p o
-do
-	case $o in
-		p) PAUSE_ON_FAIL="yes";;
-		*) usage;;
-	esac
-done
-
-setup_ns NS0
-
-set -e
-trap exit_cleanup_all EXIT
-
-setup_basenet
-
-test_gre4
-test_gre6
-- 
2.50.1


From fc486c2d060f67d672ddad81724f7c8a4d329570 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Wed, 19 Mar 2025 22:26:50 +0100
Subject: [PATCH 10/16] Revert "gre: Fix IPv6 link-local address generation."

This reverts commit 183185a18ff96751db52a46ccf93fff3a1f42815.

This patch broke net/forwarding/ip6gre_custom_multipath_hash.sh in some
circumstances (https://lore.kernel.org/netdev/Z9RIyKZDNoka53EO@mini-arch/).
Let's revert it while the problem is being investigated.

Fixes: 183185a18ff9 ("gre: Fix IPv6 link-local address generation.")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Link: https://patch.msgid.link/8b1ce738eb15dd841aab9ef888640cab4f6ccfea.1742418408.git.gnault@redhat.com
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/addrconf.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 8b6258819dad..ac8cc1076536 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3209,13 +3209,16 @@ static void add_v4_addrs(struct inet6_dev *idev)
 	struct in6_addr addr;
 	struct net_device *dev;
 	struct net *net = dev_net(idev->dev);
-	int scope, plen;
+	int scope, plen, offset = 0;
 	u32 pflags = 0;
 
 	ASSERT_RTNL();
 
 	memset(&addr, 0, sizeof(struct in6_addr));
-	memcpy(&addr.s6_addr32[3], idev->dev->dev_addr, 4);
+	/* in case of IP6GRE the dev_addr is an IPv6 and therefore we use only the last 4 bytes */
+	if (idev->dev->addr_len == sizeof(struct in6_addr))
+		offset = sizeof(struct in6_addr) - 4;
+	memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4);
 
 	if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) {
 		scope = IPV6_ADDR_COMPATv4;
@@ -3526,13 +3529,7 @@ static void addrconf_gre_config(struct net_device *dev)
 		return;
 	}
 
-	/* Generate the IPv6 link-local address using addrconf_addr_gen(),
-	 * unless we have an IPv4 GRE device not bound to an IP address and
-	 * which is in EUI64 mode (as __ipv6_isatap_ifid() would fail in this
-	 * case). Such devices fall back to add_v4_addrs() instead.
-	 */
-	if (!(dev->type == ARPHRD_IPGRE && *(__be32 *)dev->dev_addr == 0 &&
-	      idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64)) {
+	if (dev->type == ARPHRD_ETHER) {
 		addrconf_addr_gen(idev, true);
 		return;
 	}
-- 
2.50.1


From feaee98c6c505494e2188e5c644b881f5c81ee59 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@kernel.org>
Date: Wed, 12 Mar 2025 10:22:12 +0100
Subject: [PATCH 11/16] MAINTAINERS: Add Andrea Mayer as a maintainer of SRv6

Andrea has made significant contributions to SRv6 support in Linux.
Acknowledge the work and on-going interest in Srv6 support with a
maintainers entry for these files so hopefully he is included
on patches going forward.

Signed-off-by: David Ahern <dsahern@kernel.org>
Acked-by: Andrea Mayer <andrea.mayer@uniroma2.it>
Link: https://patch.msgid.link/20250312092212.46299-1-dsahern@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 MAINTAINERS | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 625f3758c880..1ca95d95c489 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16663,6 +16663,17 @@ F:	net/mptcp/
 F:	tools/testing/selftests/bpf/*/*mptcp*.[ch]
 F:	tools/testing/selftests/net/mptcp/
 
+NETWORKING [SRv6]
+M:	Andrea Mayer <andrea.mayer@uniroma2.it>
+L:	netdev@vger.kernel.org
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
+F:	include/linux/seg6*
+F:	include/net/seg6*
+F:	include/uapi/linux/seg6*
+F:	net/ipv6/seg6*
+F:	tools/testing/selftests/net/srv6*
+
 NETWORKING [TCP]
 M:	Eric Dumazet <edumazet@google.com>
 M:	Neal Cardwell <ncardwell@google.com>
-- 
2.50.1


From f653b608f78363c26dc4ffd6c2465eb743ebdc13 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Fri, 14 Mar 2025 12:06:31 +0200
Subject: [PATCH 12/16] MAINTAINERS: update bridge entry

Roopa has decided to withdraw as a bridge maintainer and Ido has agreed to
step up and co-maintain the bridge with me. He has been very helpful in
bridge patch reviews and has contributed a lot to the bridge over the
years. Add an entry for Roopa to CREDITS and also add bridge's headers
to its MAINTAINERS entry.

Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250314100631.40999-1-razor@blackwall.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 CREDITS     | 4 ++++
 MAINTAINERS | 4 +++-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/CREDITS b/CREDITS
index 53d11a46fd69..d71d42c30044 100644
--- a/CREDITS
+++ b/CREDITS
@@ -3233,6 +3233,10 @@ N: Rui Prior
 E: rprior@inescn.pt
 D: ATM device driver for NICStAR based cards
 
+N: Roopa Prabhu
+E: roopa@nvidia.com
+D: Bridge co-maintainer, vxlan and networking contributor
+
 N: Stefan Probst
 E: sp@caldera.de
 D: The Linux Support Team Erlangen, 1993-97
diff --git a/MAINTAINERS b/MAINTAINERS
index 00e94bec401e..a0e48e8c7870 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8593,12 +8593,14 @@ F:	Documentation/networking/devlink/etas_es58x.rst
 F:	drivers/net/can/usb/etas_es58x/
 
 ETHERNET BRIDGE
-M:	Roopa Prabhu <roopa@nvidia.com>
 M:	Nikolay Aleksandrov <razor@blackwall.org>
+M:	Ido Schimmel <idosch@nvidia.com>
 L:	bridge@lists.linux.dev
 L:	netdev@vger.kernel.org
 S:	Maintained
 W:	http://www.linuxfoundation.org/en/Net:Bridge
+F:	include/linux/if_bridge.h
+F:	include/uapi/linux/if_bridge.h
 F:	include/linux/netfilter_bridge/
 F:	net/bridge/
 
-- 
2.50.1


From 919f9f497dbcee75d487400e8f9815b74a6a37df Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 16 Mar 2025 02:58:37 +0000
Subject: [PATCH 13/16] eth: bnxt: fix out-of-range access of vnic_info array

The bnxt_queue_{start | stop}() access vnic_info as much as allocated,
which indicates bp->nr_vnics.
So, it should not reach bp->vnic_info[bp->nr_vnics].

Fixes: 661958552eda ("eth: bnxt: do not use BNXT_VNIC_NTUPLE unconditionally in queue restart logic")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250316025837.939527-1-ap420073@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 55f553debd3b..0ddc3d41e2d8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -15651,7 +15651,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	cpr = &rxr->bnapi->cp_ring;
 	cpr->sw_stats->rx.rx_resets++;
 
-	for (i = 0; i <= bp->nr_vnics; i++) {
+	for (i = 0; i < bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
 
 		rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
@@ -15679,7 +15679,7 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx)
 	struct bnxt_vnic_info *vnic;
 	int i;
 
-	for (i = 0; i <= bp->nr_vnics; i++) {
+	for (i = 0; i < bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
 		vnic->mru = 0;
 		bnxt_hwrm_vnic_update(bp, vnic,
-- 
2.50.1


From ed3ba9b6e280e14cc3148c1b226ba453f02fa76c Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Sun, 16 Mar 2025 12:28:37 -0700
Subject: [PATCH 14/16] net: Remove RTNL dance for SIOCBRADDIF and SIOCBRDELIF.

SIOCBRDELIF is passed to dev_ioctl() first and later forwarded to
br_ioctl_call(), which causes unnecessary RTNL dance and the splat
below [0] under RTNL pressure.

Let's say Thread A is trying to detach a device from a bridge and
Thread B is trying to remove the bridge.

In dev_ioctl(), Thread A bumps the bridge device's refcnt by
netdev_hold() and releases RTNL because the following br_ioctl_call()
also re-acquires RTNL.

In the race window, Thread B could acquire RTNL and try to remove
the bridge device.  Then, rtnl_unlock() by Thread B will release RTNL
and wait for netdev_put() by Thread A.

Thread A, however, must hold RTNL after the unlock in dev_ifsioc(),
which may take long under RTNL pressure, resulting in the splat by
Thread B.

  Thread A (SIOCBRDELIF)           Thread B (SIOCBRDELBR)
  ----------------------           ----------------------
  sock_ioctl                       sock_ioctl
  `- sock_do_ioctl                 `- br_ioctl_call
     `- dev_ioctl                     `- br_ioctl_stub
        |- rtnl_lock                     |
        |- dev_ifsioc                    '
        '  |- dev = __dev_get_by_name(...)
           |- netdev_hold(dev, ...)      .
       /   |- rtnl_unlock  ------.       |
       |   |- br_ioctl_call       `--->  |- rtnl_lock
  Race |   |  `- br_ioctl_stub           |- br_del_bridge
  Window   |     |                       |  |- dev = __dev_get_by_name(...)
       |   |     |  May take long        |  `- br_dev_delete(dev, ...)
       |   |     |  under RTNL pressure  |     `- unregister_netdevice_queue(dev, ...)
       |   |     |               |       `- rtnl_unlock
       \   |     |- rtnl_lock  <-'          `- netdev_run_todo
           |     |- ...                        `- netdev_run_todo
           |     `- rtnl_unlock                   |- __rtnl_unlock
           |                                      |- netdev_wait_allrefs_any
           |- netdev_put(dev, ...)  <----------------'
                                                Wait refcnt decrement
                                                and log splat below

To avoid blocking SIOCBRDELBR unnecessarily, let's not call
dev_ioctl() for SIOCBRADDIF and SIOCBRDELIF.

In the dev_ioctl() path, we do the following:

  1. Copy struct ifreq by get_user_ifreq in sock_do_ioctl()
  2. Check CAP_NET_ADMIN in dev_ioctl()
  3. Call dev_load() in dev_ioctl()
  4. Fetch the master dev from ifr.ifr_name in dev_ifsioc()

3. can be done by request_module() in br_ioctl_call(), so we move
1., 2., and 4. to br_ioctl_stub().

Note that 2. is also checked later in add_del_if(), but it's better
performed before RTNL.

SIOCBRADDIF and SIOCBRDELIF have been processed in dev_ioctl() since
the pre-git era, and there seems to be no specific reason to process
them there.

[0]:
unregister_netdevice: waiting for wpan3 to become free. Usage count = 2
ref_tracker: wpan3@ffff8880662d8608 has 1/1 users at
     __netdev_tracker_alloc include/linux/netdevice.h:4282 [inline]
     netdev_hold include/linux/netdevice.h:4311 [inline]
     dev_ifsioc+0xc6a/0x1160 net/core/dev_ioctl.c:624
     dev_ioctl+0x255/0x10c0 net/core/dev_ioctl.c:826
     sock_do_ioctl+0x1ca/0x260 net/socket.c:1213
     sock_ioctl+0x23a/0x6c0 net/socket.c:1318
     vfs_ioctl fs/ioctl.c:51 [inline]
     __do_sys_ioctl fs/ioctl.c:906 [inline]
     __se_sys_ioctl fs/ioctl.c:892 [inline]
     __x64_sys_ioctl+0x1a4/0x210 fs/ioctl.c:892
     do_syscall_x64 arch/x86/entry/common.c:52 [inline]
     do_syscall_64+0xcb/0x250 arch/x86/entry/common.c:83
     entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fixes: 893b19587534 ("net: bridge: fix ioctl locking")
Reported-by: syzkaller <syzkaller@googlegroups.com>
Reported-by: yan kang <kangyan91@outlook.com>
Reported-by: yue sun <samsun1006219@gmail.com>
Closes: https://lore.kernel.org/netdev/SY8P300MB0421225D54EB92762AE8F0F2A1D32@SY8P300MB0421.AUSP300.PROD.OUTLOOK.COM/
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250316192851.19781-1-kuniyu@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/if_bridge.h |  6 ++----
 net/bridge/br_ioctl.c     | 36 +++++++++++++++++++++++++++++++++---
 net/bridge/br_private.h   |  3 +--
 net/core/dev_ioctl.c      | 19 -------------------
 net/socket.c              | 19 +++++++++----------
 5 files changed, 45 insertions(+), 38 deletions(-)

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 3ff96ae31bf6..c5fe3b2a53e8 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -65,11 +65,9 @@ struct br_ip_list {
 #define BR_DEFAULT_AGEING_TIME	(300 * HZ)
 
 struct net_bridge;
-void brioctl_set(int (*hook)(struct net *net, struct net_bridge *br,
-			     unsigned int cmd, struct ifreq *ifr,
+void brioctl_set(int (*hook)(struct net *net, unsigned int cmd,
 			     void __user *uarg));
-int br_ioctl_call(struct net *net, struct net_bridge *br, unsigned int cmd,
-		  struct ifreq *ifr, void __user *uarg);
+int br_ioctl_call(struct net *net, unsigned int cmd, void __user *uarg);
 
 #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING)
 int br_multicast_list_adjacent(struct net_device *dev,
diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index f213ed108361..6bc0a11f2ed3 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -394,10 +394,26 @@ static int old_deviceless(struct net *net, void __user *data)
 	return -EOPNOTSUPP;
 }
 
-int br_ioctl_stub(struct net *net, struct net_bridge *br, unsigned int cmd,
-		  struct ifreq *ifr, void __user *uarg)
+int br_ioctl_stub(struct net *net, unsigned int cmd, void __user *uarg)
 {
 	int ret = -EOPNOTSUPP;
+	struct ifreq ifr;
+
+	if (cmd == SIOCBRADDIF || cmd == SIOCBRDELIF) {
+		void __user *data;
+		char *colon;
+
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+
+		if (get_user_ifreq(&ifr, &data, uarg))
+			return -EFAULT;
+
+		ifr.ifr_name[IFNAMSIZ - 1] = 0;
+		colon = strchr(ifr.ifr_name, ':');
+		if (colon)
+			*colon = 0;
+	}
 
 	rtnl_lock();
 
@@ -430,7 +446,21 @@ int br_ioctl_stub(struct net *net, struct net_bridge *br, unsigned int cmd,
 		break;
 	case SIOCBRADDIF:
 	case SIOCBRDELIF:
-		ret = add_del_if(br, ifr->ifr_ifindex, cmd == SIOCBRADDIF);
+	{
+		struct net_device *dev;
+
+		dev = __dev_get_by_name(net, ifr.ifr_name);
+		if (!dev || !netif_device_present(dev)) {
+			ret = -ENODEV;
+			break;
+		}
+		if (!netif_is_bridge_master(dev)) {
+			ret = -EOPNOTSUPP;
+			break;
+		}
+
+		ret = add_del_if(netdev_priv(dev), ifr.ifr_ifindex, cmd == SIOCBRADDIF);
+	}
 		break;
 	}
 
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 1054b8a88edc..d5b3c5936a79 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -949,8 +949,7 @@ br_port_get_check_rtnl(const struct net_device *dev)
 /* br_ioctl.c */
 int br_dev_siocdevprivate(struct net_device *dev, struct ifreq *rq,
 			  void __user *data, int cmd);
-int br_ioctl_stub(struct net *net, struct net_bridge *br, unsigned int cmd,
-		  struct ifreq *ifr, void __user *uarg);
+int br_ioctl_stub(struct net *net, unsigned int cmd, void __user *uarg);
 
 /* br_multicast.c */
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 4c2098ac9d72..57f79f8e8466 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -551,7 +551,6 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data,
 	int err;
 	struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name);
 	const struct net_device_ops *ops;
-	netdevice_tracker dev_tracker;
 
 	if (!dev)
 		return -ENODEV;
@@ -614,22 +613,6 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data,
 	case SIOCWANDEV:
 		return dev_siocwandev(dev, &ifr->ifr_settings);
 
-	case SIOCBRADDIF:
-	case SIOCBRDELIF:
-		if (!netif_device_present(dev))
-			return -ENODEV;
-		if (!netif_is_bridge_master(dev))
-			return -EOPNOTSUPP;
-
-		netdev_hold(dev, &dev_tracker, GFP_KERNEL);
-		rtnl_net_unlock(net);
-
-		err = br_ioctl_call(net, netdev_priv(dev), cmd, ifr, NULL);
-
-		netdev_put(dev, &dev_tracker);
-		rtnl_net_lock(net);
-		return err;
-
 	case SIOCDEVPRIVATE ... SIOCDEVPRIVATE + 15:
 		return dev_siocdevprivate(dev, ifr, data, cmd);
 
@@ -812,8 +795,6 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr,
 	case SIOCBONDRELEASE:
 	case SIOCBONDSETHWADDR:
 	case SIOCBONDCHANGEACTIVE:
-	case SIOCBRADDIF:
-	case SIOCBRDELIF:
 	case SIOCSHWTSTAMP:
 		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
diff --git a/net/socket.c b/net/socket.c
index 28bae5a94234..38227d00d198 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1145,12 +1145,10 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from)
  */
 
 static DEFINE_MUTEX(br_ioctl_mutex);
-static int (*br_ioctl_hook)(struct net *net, struct net_bridge *br,
-			    unsigned int cmd, struct ifreq *ifr,
+static int (*br_ioctl_hook)(struct net *net, unsigned int cmd,
 			    void __user *uarg);
 
-void brioctl_set(int (*hook)(struct net *net, struct net_bridge *br,
-			     unsigned int cmd, struct ifreq *ifr,
+void brioctl_set(int (*hook)(struct net *net, unsigned int cmd,
 			     void __user *uarg))
 {
 	mutex_lock(&br_ioctl_mutex);
@@ -1159,8 +1157,7 @@ void brioctl_set(int (*hook)(struct net *net, struct net_bridge *br,
 }
 EXPORT_SYMBOL(brioctl_set);
 
-int br_ioctl_call(struct net *net, struct net_bridge *br, unsigned int cmd,
-		  struct ifreq *ifr, void __user *uarg)
+int br_ioctl_call(struct net *net, unsigned int cmd, void __user *uarg)
 {
 	int err = -ENOPKG;
 
@@ -1169,7 +1166,7 @@ int br_ioctl_call(struct net *net, struct net_bridge *br, unsigned int cmd,
 
 	mutex_lock(&br_ioctl_mutex);
 	if (br_ioctl_hook)
-		err = br_ioctl_hook(net, br, cmd, ifr, uarg);
+		err = br_ioctl_hook(net, cmd, uarg);
 	mutex_unlock(&br_ioctl_mutex);
 
 	return err;
@@ -1269,7 +1266,9 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 		case SIOCSIFBR:
 		case SIOCBRADDBR:
 		case SIOCBRDELBR:
-			err = br_ioctl_call(net, NULL, cmd, NULL, argp);
+		case SIOCBRADDIF:
+		case SIOCBRDELIF:
+			err = br_ioctl_call(net, cmd, argp);
 			break;
 		case SIOCGIFVLAN:
 		case SIOCSIFVLAN:
@@ -3429,6 +3428,8 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCGPGRP:
 	case SIOCBRADDBR:
 	case SIOCBRDELBR:
+	case SIOCBRADDIF:
+	case SIOCBRDELIF:
 	case SIOCGIFVLAN:
 	case SIOCSIFVLAN:
 	case SIOCGSKNS:
@@ -3468,8 +3469,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCGIFPFLAGS:
 	case SIOCGIFTXQLEN:
 	case SIOCSIFTXQLEN:
-	case SIOCBRADDIF:
-	case SIOCBRDELIF:
 	case SIOCGIFNAME:
 	case SIOCSIFNAME:
 	case SIOCGMIIPHY:
-- 
2.50.1


From 2f6efbabceb6b2914ee9bafb86d9a51feae9cce8 Mon Sep 17 00:00:00 2001
From: Murad Masimov <m.masimov@mt-integration.ru>
Date: Mon, 17 Mar 2025 13:53:52 +0300
Subject: [PATCH 15/16] ax25: Remove broken autobind

Binding AX25 socket by using the autobind feature leads to memory leaks
in ax25_connect() and also refcount leaks in ax25_release(). Memory
leak was detected with kmemleak:

================================================================
unreferenced object 0xffff8880253cd680 (size 96):
backtrace:
__kmalloc_node_track_caller_noprof (./include/linux/kmemleak.h:43)
kmemdup_noprof (mm/util.c:136)
ax25_rt_autobind (net/ax25/ax25_route.c:428)
ax25_connect (net/ax25/af_ax25.c:1282)
__sys_connect_file (net/socket.c:2045)
__sys_connect (net/socket.c:2064)
__x64_sys_connect (net/socket.c:2067)
do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83)
entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)
================================================================

When socket is bound, refcounts must be incremented the way it is done
in ax25_bind() and ax25_setsockopt() (SO_BINDTODEVICE). In case of
autobind, the refcounts are not incremented.

This bug leads to the following issue reported by Syzkaller:

================================================================
ax25_connect(): syz-executor318 uses autobind, please contact jreuter@yaina.de
------------[ cut here ]------------
refcount_t: decrement hit 0; leaking memory.
WARNING: CPU: 0 PID: 5317 at lib/refcount.c:31 refcount_warn_saturate+0xfa/0x1d0 lib/refcount.c:31
Modules linked in:
CPU: 0 UID: 0 PID: 5317 Comm: syz-executor318 Not tainted 6.14.0-rc4-syzkaller-00278-gece144f151ac #0
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
RIP: 0010:refcount_warn_saturate+0xfa/0x1d0 lib/refcount.c:31
...
Call Trace:
 <TASK>
 __refcount_dec include/linux/refcount.h:336 [inline]
 refcount_dec include/linux/refcount.h:351 [inline]
 ref_tracker_free+0x6af/0x7e0 lib/ref_tracker.c:236
 netdev_tracker_free include/linux/netdevice.h:4302 [inline]
 netdev_put include/linux/netdevice.h:4319 [inline]
 ax25_release+0x368/0x960 net/ax25/af_ax25.c:1080
 __sock_release net/socket.c:647 [inline]
 sock_close+0xbc/0x240 net/socket.c:1398
 __fput+0x3e9/0x9f0 fs/file_table.c:464
 __do_sys_close fs/open.c:1580 [inline]
 __se_sys_close fs/open.c:1565 [inline]
 __x64_sys_close+0x7f/0x110 fs/open.c:1565
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
 ...
 </TASK>
================================================================

Considering the issues above and the comments left in the code that say:
"check if we can remove this feature. It is broken."; "autobinding in this
may or may not work"; - it is better to completely remove this feature than
to fix it because it is broken and leads to various kinds of memory bugs.

Now calling connect() without first binding socket will result in an
error (-EINVAL). Userspace software that relies on the autobind feature
might get broken. However, this feature does not seem widely used with
this specific driver as it was not reliable at any point of time, and it
is already broken anyway. E.g. ax25-tools and ax25-apps packages for
popular distributions do not use the autobind feature for AF_AX25.

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+33841dc6aa3e1d86b78a@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=33841dc6aa3e1d86b78a
Signed-off-by: Murad Masimov <m.masimov@mt-integration.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ax25.h    |  1 -
 net/ax25/af_ax25.c    | 30 ++++++------------
 net/ax25/ax25_route.c | 74 -------------------------------------------
 3 files changed, 10 insertions(+), 95 deletions(-)

diff --git a/include/net/ax25.h b/include/net/ax25.h
index 4ee141aae0a2..a7bba42dde15 100644
--- a/include/net/ax25.h
+++ b/include/net/ax25.h
@@ -418,7 +418,6 @@ void ax25_rt_device_down(struct net_device *);
 int ax25_rt_ioctl(unsigned int, void __user *);
 extern const struct seq_operations ax25_rt_seqops;
 ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev);
-int ax25_rt_autobind(ax25_cb *, ax25_address *);
 struct sk_buff *ax25_rt_build_path(struct sk_buff *, ax25_address *,
 				   ax25_address *, ax25_digi *);
 void ax25_rt_free(void);
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 9f3b8b682adb..3ee7dba34310 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1270,28 +1270,18 @@ static int __must_check ax25_connect(struct socket *sock,
 		}
 	}
 
-	/*
-	 *	Must bind first - autobinding in this may or may not work. If
-	 *	the socket is already bound, check to see if the device has
-	 *	been filled in, error if it hasn't.
-	 */
+	/* Must bind first - autobinding does not work. */
 	if (sock_flag(sk, SOCK_ZAPPED)) {
-		/* check if we can remove this feature. It is broken. */
-		printk(KERN_WARNING "ax25_connect(): %s uses autobind, please contact jreuter@yaina.de\n",
-			current->comm);
-		if ((err = ax25_rt_autobind(ax25, &fsa->fsa_ax25.sax25_call)) < 0) {
-			kfree(digi);
-			goto out_release;
-		}
+		kfree(digi);
+		err = -EINVAL;
+		goto out_release;
+	}
 
-		ax25_fillin_cb(ax25, ax25->ax25_dev);
-		ax25_cb_add(ax25);
-	} else {
-		if (ax25->ax25_dev == NULL) {
-			kfree(digi);
-			err = -EHOSTUNREACH;
-			goto out_release;
-		}
+	/* Check to see if the device has been filled in, error if it hasn't. */
+	if (ax25->ax25_dev == NULL) {
+		kfree(digi);
+		err = -EHOSTUNREACH;
+		goto out_release;
 	}
 
 	if (sk->sk_type == SOCK_SEQPACKET &&
diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c
index 69de75db0c9c..10577434f40b 100644
--- a/net/ax25/ax25_route.c
+++ b/net/ax25/ax25_route.c
@@ -373,80 +373,6 @@ ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev)
 	return ax25_rt;
 }
 
-/*
- *	Adjust path: If you specify a default route and want to connect
- *      a target on the digipeater path but w/o having a special route
- *	set before, the path has to be truncated from your target on.
- */
-static inline void ax25_adjust_path(ax25_address *addr, ax25_digi *digipeat)
-{
-	int k;
-
-	for (k = 0; k < digipeat->ndigi; k++) {
-		if (ax25cmp(addr, &digipeat->calls[k]) == 0)
-			break;
-	}
-
-	digipeat->ndigi = k;
-}
-
-
-/*
- *	Find which interface to use.
- */
-int ax25_rt_autobind(ax25_cb *ax25, ax25_address *addr)
-{
-	ax25_uid_assoc *user;
-	ax25_route *ax25_rt;
-	int err = 0;
-
-	ax25_route_lock_use();
-	ax25_rt = ax25_get_route(addr, NULL);
-	if (!ax25_rt) {
-		ax25_route_lock_unuse();
-		return -EHOSTUNREACH;
-	}
-	rcu_read_lock();
-	if ((ax25->ax25_dev = ax25_dev_ax25dev(ax25_rt->dev)) == NULL) {
-		err = -EHOSTUNREACH;
-		goto put;
-	}
-
-	user = ax25_findbyuid(current_euid());
-	if (user) {
-		ax25->source_addr = user->call;
-		ax25_uid_put(user);
-	} else {
-		if (ax25_uid_policy && !capable(CAP_NET_BIND_SERVICE)) {
-			err = -EPERM;
-			goto put;
-		}
-		ax25->source_addr = *(ax25_address *)ax25->ax25_dev->dev->dev_addr;
-	}
-
-	if (ax25_rt->digipeat != NULL) {
-		ax25->digipeat = kmemdup(ax25_rt->digipeat, sizeof(ax25_digi),
-					 GFP_ATOMIC);
-		if (ax25->digipeat == NULL) {
-			err = -ENOMEM;
-			goto put;
-		}
-		ax25_adjust_path(addr, ax25->digipeat);
-	}
-
-	if (ax25->sk != NULL) {
-		local_bh_disable();
-		bh_lock_sock(ax25->sk);
-		sock_reset_flag(ax25->sk, SOCK_ZAPPED);
-		bh_unlock_sock(ax25->sk);
-		local_bh_enable();
-	}
-
-put:
-	rcu_read_unlock();
-	ax25_route_lock_unuse();
-	return err;
-}
 
 struct sk_buff *ax25_rt_build_path(struct sk_buff *skb, ax25_address *src,
 	ax25_address *dest, ax25_digi *digi)
-- 
2.50.1


From c60d101a226f18e9a8f01bb4c6ca2b47dfcb15ef Mon Sep 17 00:00:00 2001
From: Qingfang Deng <dqfext@gmail.com>
Date: Tue, 18 Mar 2025 11:24:23 +0800
Subject: [PATCH 16/16] net: stmmac: Fix accessing freed irq affinity_hint

The cpumask should not be a local variable, since its pointer is saved
to irq_desc and may be accessed from procfs.
To fix it, use the persistent mask cpumask_of(cpu#).

Cc: stable@vger.kernel.org
Fixes: 8deec94c6040 ("net: stmmac: set IRQ affinity hint for multi MSI vectors")
Signed-off-by: Qingfang Deng <dqfext@gmail.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250318032424.112067-1-dqfext@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c0ae7db96f46..b7c3bfdaa180 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3640,7 +3640,6 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	enum request_irq_err irq_err;
-	cpumask_t cpu_mask;
 	int irq_idx = 0;
 	char *int_name;
 	int ret;
@@ -3769,9 +3768,8 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 			irq_idx = i;
 			goto irq_error;
 		}
-		cpumask_clear(&cpu_mask);
-		cpumask_set_cpu(i % num_online_cpus(), &cpu_mask);
-		irq_set_affinity_hint(priv->rx_irq[i], &cpu_mask);
+		irq_set_affinity_hint(priv->rx_irq[i],
+				      cpumask_of(i % num_online_cpus()));
 	}
 
 	/* Request Tx MSI irq */
@@ -3794,9 +3792,8 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 			irq_idx = i;
 			goto irq_error;
 		}
-		cpumask_clear(&cpu_mask);
-		cpumask_set_cpu(i % num_online_cpus(), &cpu_mask);
-		irq_set_affinity_hint(priv->tx_irq[i], &cpu_mask);
+		irq_set_affinity_hint(priv->tx_irq[i],
+				      cpumask_of(i % num_online_cpus()));
 	}
 
 	return 0;
-- 
2.50.1