[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250730105118.GA26100@hu-sharathv-hyd.qualcomm.com>
Date: Wed, 30 Jul 2025 16:21:18 +0530
From: Sharath Chandra Vurukala <quic_sharathv@...cinc.com>
To: <davem@...emloft.net>, <dsahern@...nel.org>, <edumazet@...gle.com>,
<kuba@...nel.org>, <pabeni@...hat.com>, <netdev@...r.kernel.org>
CC: <quic_kapandey@...cinc.com>, <quic_subashab@...cinc.com>
Subject: [PATCH v3] net: Add locking to protect skb->dev access in ip_output
In ip_output() skb->dev is updated from the skb_dst(skb)->dev
this can become invalid when the interface is unregistered and freed,
Introduced new skb_dst_dev_rcu() function to be used instead of
skb_dst_dev() within rcu_locks in ip_output.This will ensure that
all the skb's associated with the dev being deregistered will
be transnmitted out first, before freeing the dev.
Given that ip_output() is called within an rcu_read_lock()
critical section or from a bottom-half context, it is safe to introduce
an RCU read-side critical section within it.
Multiple panic call stacks were observed when UL traffic was run
in concurrency with device deregistration from different functions,
pasting one sample for reference.
[496733.627565][T13385] Call trace:
[496733.627570][T13385] bpf_prog_ce7c9180c3b128ea_cgroupskb_egres+0x24c/0x7f0
[496733.627581][T13385] __cgroup_bpf_run_filter_skb+0x128/0x498
[496733.627595][T13385] ip_finish_output+0xa4/0xf4
[496733.627605][T13385] ip_output+0x100/0x1a0
[496733.627613][T13385] ip_send_skb+0x68/0x100
[496733.627618][T13385] udp_send_skb+0x1c4/0x384
[496733.627625][T13385] udp_sendmsg+0x7b0/0x898
[496733.627631][T13385] inet_sendmsg+0x5c/0x7c
[496733.627639][T13385] __sys_sendto+0x174/0x1e4
[496733.627647][T13385] __arm64_sys_sendto+0x28/0x3c
[496733.627653][T13385] invoke_syscall+0x58/0x11c
[496733.627662][T13385] el0_svc_common+0x88/0xf4
[496733.627669][T13385] do_el0_svc+0x2c/0xb0
[496733.627676][T13385] el0_svc+0x2c/0xa4
[496733.627683][T13385] el0t_64_sync_handler+0x68/0xb4
[496733.627689][T13385] el0t_64_sync+0x1a4/0x1a8
Changes in v3:
- Replaced WARN_ON() with WARN_ON_ONCE(), as suggested by Willem de Bruijn.
- Dropped legacy lines mistakenly pulled in from an outdated branch.
Changes in v2:
- Addressed review comments from Eric Dumazet
- Used READ_ONCE() to prevent potential load/store tearing
- Added skb_dst_dev_rcu() and used along with rcu_read_lock() in ip_output
Signed-off-by: Sharath Chandra Vurukala <quic_sharathv@...cinc.com>
---
include/net/dst.h | 12 ++++++++++++
net/ipv4/ip_output.c | 15 ++++++++++-----
2 files changed, 22 insertions(+), 5 deletions(-)
diff --git a/include/net/dst.h b/include/net/dst.h
index 00467c1b5093..bab01363bb97 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -568,11 +568,23 @@ static inline struct net_device *dst_dev(const struct dst_entry *dst)
return READ_ONCE(dst->dev);
}
+static inline struct net_device *dst_dev_rcu(const struct dst_entry *dst)
+{
+ /* In the future, use rcu_dereference(dst->dev) */
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ return READ_ONCE(dst->dev);
+}
+
static inline struct net_device *skb_dst_dev(const struct sk_buff *skb)
{
return dst_dev(skb_dst(skb));
}
+static inline struct net_device *skb_dst_dev_rcu(const struct sk_buff *skb)
+{
+ return dst_dev_rcu(skb_dst(skb));
+}
+
static inline struct net *skb_dst_dev_net(const struct sk_buff *skb)
{
return dev_net(skb_dst_dev(skb));
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 10a1d182fd84..84e7f8a2f50f 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -425,15 +425,20 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct net_device *dev = skb_dst_dev(skb), *indev = skb->dev;
+ struct net_device *dev, *indev = skb->dev;
+ int ret_val;
+ rcu_read_lock();
+ dev = skb_dst_dev_rcu(skb);
skb->dev = dev;
skb->protocol = htons(ETH_P_IP);
- return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
- net, sk, skb, indev, dev,
- ip_finish_output,
- !(IPCB(skb)->flags & IPSKB_REROUTED));
+ ret_val = NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
+ net, sk, skb, indev, dev,
+ ip_finish_output,
+ !(IPCB(skb)->flags & IPSKB_REROUTED));
+ rcu_read_unlock();
+ return ret_val;
}
EXPORT_SYMBOL(ip_output);
Powered by blists - more mailing lists