[PATCH net] net: flow_offload: protect driver_block_list in flow_block_cb_setup_simple()

[Shigeru Yoshida <syoshida@redhat.com>]

syzbot reported a list_del corruption in flow_block_cb_setup_simple(). [0]

flow_block_cb_setup_simple() accesses the driver_block_list (e.g.,
netdevsim's nsim_block_cb_list) without any synchronization. The
nftables offload path calls into this function via ndo_setup_tc while
holding the per-netns commit_mutex, but this mutex does not prevent
concurrent access from tasks in different network namespaces that
share the same driver_block_list, leading to list corruption:

- Task A (FLOW_BLOCK_BIND) calls list_add_tail() to insert a new
  flow_block_cb into driver_block_list.

- Task B (FLOW_BLOCK_UNBIND) concurrently calls list_del() on another
  flow_block_cb from the same list.

- The concurrent modifications corrupt the list pointers.

Fix this by adding a static mutex (flow_block_cb_list_lock) that
protects all driver_block_list operations within
flow_block_cb_setup_simple(). Also add a flow_block_cb_remove_driver()
helper for external callers that need to remove a block_cb from the
driver list under the same lock, and convert nft_indr_block_cleanup()
to use it.

[0]:
list_del corruption. prev->next should be ffff888028878200, but was ffffffff8e940fc0. (prev=ffffffff8e940fc0)
------------[ cut here ]------------
kernel BUG at lib/list_debug.c:64!
Oops: invalid opcode: 0000 [#1] SMP KASAN PTI
CPU: 1 UID: 0 PID: 6308 Comm: syz.3.231 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/18/2025
RIP: 0010:__list_del_entry_valid_or_report+0x15a/0x190 lib/list_debug.c:62
[...]
Call Trace:
 <TASK>
 __list_del_entry_valid include/linux/list.h:124 [inline]
 __list_del_entry include/linux/list.h:215 [inline]
 list_del include/linux/list.h:229 [inline]
 flow_block_cb_setup_simple+0x62d/0x740 net/core/flow_offload.c:369
 nft_block_offload_cmd net/netfilter/nf_tables_offload.c:397 [inline]
 nft_chain_offload_cmd+0x293/0x660 net/netfilter/nf_tables_offload.c:451
 nft_flow_block_chain net/netfilter/nf_tables_offload.c:471 [inline]
 nft_flow_offload_chain net/netfilter/nf_tables_offload.c:513 [inline]
 nft_flow_rule_offload_commit+0x40d/0x1b60 net/netfilter/nf_tables_offload.c:592
 nf_tables_commit+0x675/0x8710 net/netfilter/nf_tables_api.c:10925
 nfnetlink_rcv_batch net/netfilter/nfnetlink.c:576 [inline]
 nfnetlink_rcv_skb_batch net/netfilter/nfnetlink.c:649 [inline]
 nfnetlink_rcv+0x1ac9/0x2590 net/netfilter/nfnetlink.c:667
 netlink_unicast_kernel net/netlink/af_netlink.c:1320 [inline]
 netlink_unicast+0x82c/0x9e0 net/netlink/af_netlink.c:1346
 netlink_sendmsg+0x805/0xb30 net/netlink/af_netlink.c:1896
 sock_sendmsg_nosec net/socket.c:727 [inline]
 __sock_sendmsg+0x219/0x270 net/socket.c:742
 ____sys_sendmsg+0x505/0x830 net/socket.c:2630
 ___sys_sendmsg+0x21f/0x2a0 net/socket.c:2684
 __sys_sendmsg net/socket.c:2716 [inline]
 __do_sys_sendmsg net/socket.c:2721 [inline]
 __se_sys_sendmsg net/socket.c:2719 [inline]
 __x64_sys_sendmsg+0x19b/0x260 net/socket.c:2719
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fixes: 955bcb6ea0df ("drivers: net: use flow block API")
Reported-by: syzbot+5a66db916cdde0dbcc1c@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=5a66db916cdde0dbcc1c
Tested-by: syzbot+5a66db916cdde0dbcc1c@syzkaller.appspotmail.com
Signed-off-by: Shigeru Yoshida <syoshida@redhat.com>
---
 include/net/flow_offload.h        |  2 ++
 net/core/flow_offload.c           | 41 ++++++++++++++++++++++++-------
 net/netfilter/nf_tables_offload.c |  2 +-
 3 files changed, 35 insertions(+), 10 deletions(-)

diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index 596ab9791e4d..ff6d2bcb2cca 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -673,6 +673,8 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f,
 			       flow_setup_cb_t *cb,
 			       void *cb_ident, void *cb_priv, bool ingress_only);
 
+void flow_block_cb_remove_driver(struct flow_block_cb *block_cb);
+
 enum flow_cls_command {
 	FLOW_CLS_REPLACE,
 	FLOW_CLS_DESTROY,
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index bc5169482710..137a44af5e1c 100644
--- a/net/core/flow_offload.c
+++ b/net/core/flow_offload.c
@@ -334,6 +334,8 @@ bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident,
 }
 EXPORT_SYMBOL(flow_block_cb_is_busy);
 
+static DEFINE_MUTEX(flow_block_cb_list_lock);
+
 int flow_block_cb_setup_simple(struct flow_block_offload *f,
 			       struct list_head *driver_block_list,
 			       flow_setup_cb_t *cb,
@@ -341,6 +343,7 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f,
 			       bool ingress_only)
 {
 	struct flow_block_cb *block_cb;
+	int err = 0;
 
 	if (ingress_only &&
 	    f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
@@ -348,32 +351,52 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f,
 
 	f->driver_block_list = driver_block_list;
 
+	mutex_lock(&flow_block_cb_list_lock);
+
 	switch (f->command) {
 	case FLOW_BLOCK_BIND:
-		if (flow_block_cb_is_busy(cb, cb_ident, driver_block_list))
-			return -EBUSY;
+		if (flow_block_cb_is_busy(cb, cb_ident, driver_block_list)) {
+			err = -EBUSY;
+			break;
+		}
 
 		block_cb = flow_block_cb_alloc(cb, cb_ident, cb_priv, NULL);
-		if (IS_ERR(block_cb))
-			return PTR_ERR(block_cb);
+		if (IS_ERR(block_cb)) {
+			err = PTR_ERR(block_cb);
+			break;
+		}
 
 		flow_block_cb_add(block_cb, f);
 		list_add_tail(&block_cb->driver_list, driver_block_list);
-		return 0;
+		break;
 	case FLOW_BLOCK_UNBIND:
 		block_cb = flow_block_cb_lookup(f->block, cb, cb_ident);
-		if (!block_cb)
-			return -ENOENT;
+		if (!block_cb) {
+			err = -ENOENT;
+			break;
+		}
 
 		flow_block_cb_remove(block_cb, f);
 		list_del(&block_cb->driver_list);
-		return 0;
+		break;
 	default:
-		return -EOPNOTSUPP;
+		err = -EOPNOTSUPP;
+		break;
 	}
+
+	mutex_unlock(&flow_block_cb_list_lock);
+	return err;
 }
 EXPORT_SYMBOL(flow_block_cb_setup_simple);
 
+void flow_block_cb_remove_driver(struct flow_block_cb *block_cb)
+{
+	mutex_lock(&flow_block_cb_list_lock);
+	list_del(&block_cb->driver_list);
+	mutex_unlock(&flow_block_cb_list_lock);
+}
+EXPORT_SYMBOL(flow_block_cb_remove_driver);
+
 static DEFINE_MUTEX(flow_indr_block_lock);
 static LIST_HEAD(flow_block_indr_list);
 static LIST_HEAD(flow_block_indr_dev_list);
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index fd30e205de84..d60838bceafb 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -414,7 +414,7 @@ static void nft_indr_block_cleanup(struct flow_block_cb *block_cb)
 				    basechain, &extack);
 	nft_net = nft_pernet(net);
 	mutex_lock(&nft_net->commit_mutex);
-	list_del(&block_cb->driver_list);
+	flow_block_cb_remove_driver(block_cb);
 	list_move(&block_cb->list, &bo.cb_list);
 	nft_flow_offload_unbind(&bo, basechain);
 	mutex_unlock(&nft_net->commit_mutex);
-- 
2.52.0