net: devmem: fix kernel panic when netlink socket close after module unload

Kernel panic occurs when a devmem TCP socket is closed after NIC module
is unloaded.

This is Devmem TCP unregistration scenarios. number is an order.
(a)netlink socket close    (b)pp destroy    (c)uninstall    result
1                          2                3               OK
1                          3                2               (d)Impossible
2                          1                3               OK
3                          1                2               (e)Kernel panic
2                          3                1               (d)Impossible
3                          2                1               (d)Impossible

(a) netdev_nl_sock_priv_destroy() is called when devmem TCP socket is
    closed.
(b) page_pool_destroy() is called when the interface is down.
(c) mp_ops->uninstall() is called when an interface is unregistered.
(d) There is no scenario in mp_ops->uninstall() is called before
    page_pool_destroy().
    Because unregister_netdevice_many_notify() closes interfaces first
    and then calls mp_ops->uninstall().
(e) netdev_nl_sock_priv_destroy() accesses struct net_device to acquire
    netdev_lock().
    But if the interface module has already been removed, net_device
    pointer is invalid, so it causes kernel panic.

In summary, there are only 3 possible scenarios.
 A. sk close -> pp destroy -> uninstall.
 B. pp destroy -> sk close -> uninstall.
 C. pp destroy -> uninstall -> sk close.

Case C is a kernel panic scenario.

In order to fix this problem, It makes mp_dmabuf_devmem_uninstall() set
binding->dev to NULL.
It indicates an bound net_device was unregistered.

It makes netdev_nl_sock_priv_destroy() do not acquire netdev_lock()
if binding->dev is NULL.

A new binding->lock is added to protect a dev of a binding.
So, lock ordering is like below.
 priv->lock
 netdev_lock(dev)
 binding->lock

Tests:
Scenario A:
    ./ncdevmem -s 192.168.1.4 -c 192.168.1.2 -f $interface -l -p 8000 \
        -v 7 -t 1 -q 1 &
    pid=$!
    sleep 10
    kill $pid
    ip link set $interface down
    modprobe -rv $module

Scenario B:
    ./ncdevmem -s 192.168.1.4 -c 192.168.1.2 -f $interface -l -p 8000 \
        -v 7 -t 1 -q 1 &
    pid=$!
    sleep 10
    ip link set $interface down
    kill $pid
    modprobe -rv $module

Scenario C:
    ./ncdevmem -s 192.168.1.4 -c 192.168.1.2 -f $interface -l -p 8000 \
        -v 7 -t 1 -q 1 &
    pid=$!
    sleep 10
    modprobe -rv $module
    sleep 5
    kill $pid

Splat looks like:
Oops: general protection fault, probably for non-canonical address 0xdffffc001fffa9f7: 0000 [kernel-patches#1] SMP DEBUG_PAGEALLOC KASAN NOPTI
KASAN: probably user-memory-access in range [0x00000000fffd4fb8-0x00000000fffd4fbf]
CPU: 0 UID: 0 PID: 2041 Comm: ncdevmem Tainted: G    B   W           6.15.0-rc1+ kernel-patches#2 PREEMPT(undef)  0947ec89efa0fd68838b78e36aa1617e97ff5d7f
Tainted: [B]=BAD_PAGE, [W]=WARN
RIP: 0010:__mutex_lock (./include/linux/sched.h:2244 kernel/locking/mutex.c:400 kernel/locking/mutex.c:443 kernel/locking/mutex.c:605 kernel/locking/mutex.c:746)
Code: ea 03 80 3c 02 00 0f 85 4f 13 00 00 49 8b 1e 48 83 e3 f8 74 6a 48 b8 00 00 00 00 00 fc ff df 48 8d 7b 34 48 89 fa 48 c1 ea 03 <0f> b6 f
RSP: 0018:ffff88826f7ef730 EFLAGS: 00010203
RAX: dffffc0000000000 RBX: 00000000fffd4f88 RCX: ffffffffaa9bc811
RDX: 000000001fffa9f7 RSI: 0000000000000008 RDI: 00000000fffd4fbc
RBP: ffff88826f7ef8b0 R08: 0000000000000000 R09: ffffed103e6aa1a4
R10: 0000000000000007 R11: ffff88826f7ef442 R12: fffffbfff669f65e
R13: ffff88812a830040 R14: ffff8881f3550d20 R15: 00000000fffd4f88
FS:  0000000000000000(0000) GS:ffff888866c05000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000563bed0cb288 CR3: 00000001a7c98000 CR4: 00000000007506f0
PKRU: 55555554
Call Trace:
<TASK>
 ...
 netdev_nl_sock_priv_destroy (net/core/netdev-genl.c:953 (discriminator 3))
 genl_release (net/netlink/genetlink.c:653 net/netlink/genetlink.c:694 net/netlink/genetlink.c:705)
 ...
 netlink_release (net/netlink/af_netlink.c:737)
 ...
 __sock_release (net/socket.c:647)
 sock_close (net/socket.c:1393)

Fixes: 1d22d30 ("net: drop rtnl_lock for queue_mgmt operations")
Signed-off-by: Taehee Yoo <[email protected]>
Signed-off-by: NipaLocal <nipa@local>

Author: TaeheeYoo

net/core/devmem.c

@@ -167,6 +167,7 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 
 struct net_devmem_dmabuf_binding *
 net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
+		       struct netdev_nl_sock *priv,
 		       struct netlink_ext_ack *extack)
 {
 	struct net_devmem_dmabuf_binding *binding;
@@ -200,6 +201,8 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
 
 	refcount_set(&binding->ref, 1);
 
+	mutex_init(&binding->lock);
+
 	binding->dmabuf = dmabuf;
 
 	binding->attachment = dma_buf_attach(binding->dmabuf, dev->dev.parent);
@@ -274,6 +277,8 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
 		virtual += len;
 	}
 
+	list_add(&binding->list, &priv->bindings);
+
 	return binding;
 
 err_free_chunks:
@@ -379,6 +384,11 @@ static void mp_dmabuf_devmem_uninstall(void *mp_priv,
 	xa_for_each(&binding->bound_rxqs, xa_idx, bound_rxq) {
 		if (bound_rxq == rxq) {
 			xa_erase(&binding->bound_rxqs, xa_idx);
+			if (xa_empty(&binding->bound_rxqs)) {
+				mutex_lock(&binding->lock);
+				binding->dev = NULL;
+				mutex_unlock(&binding->lock);
+			}
 			break;
 		}
 	}

net/core/devmem.h

@@ -11,6 +11,7 @@
 #define _NET_DEVMEM_H
 
 #include <net/netmem.h>
+#include <net/netdev_netlink.h>
 
 struct netlink_ext_ack;
 
@@ -20,6 +21,8 @@ struct net_devmem_dmabuf_binding {
 	struct sg_table *sgt;
 	struct net_device *dev;
 	struct gen_pool *chunk_pool;
+	/* Protect dev */
+	struct mutex lock;
 
 	/* The user holds a ref (via the netlink API) for as long as they want
 	 * the binding to remain alive. Each page pool using this binding holds
@@ -63,6 +66,7 @@ struct dmabuf_genpool_chunk_owner {
 void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding);
 struct net_devmem_dmabuf_binding *
 net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
+		       struct netdev_nl_sock *priv,
 		       struct netlink_ext_ack *extack);
 void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding);
 int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
@@ -127,6 +131,7 @@ __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
 
 static inline struct net_devmem_dmabuf_binding *
 net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
+		       struct netdev_nl_sock *priv,
 		       struct netlink_ext_ack *extack)
 {
 	return ERR_PTR(-EOPNOTSUPP);

net/core/netdev-genl.c

@@ -907,7 +907,7 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 		goto err_unlock;
 	}
 
-	binding = net_devmem_bind_dmabuf(netdev, dmabuf_fd, info->extack);
+	binding = net_devmem_bind_dmabuf(netdev, dmabuf_fd, priv, info->extack);
 	if (IS_ERR(binding)) {
 		err = PTR_ERR(binding);
 		goto err_unlock;
@@ -942,8 +942,6 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 			goto err_unbind;
 	}
 
-	list_add(&binding->list, &priv->bindings);
-
 	nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id);
 	genlmsg_end(rsp, hdr);
 
@@ -978,14 +976,25 @@ void netdev_nl_sock_priv_destroy(struct netdev_nl_sock *priv)
 {
 	struct net_devmem_dmabuf_binding *binding;
 	struct net_devmem_dmabuf_binding *temp;
+	netdevice_tracker dev_tracker;
 	struct net_device *dev;
 
 	mutex_lock(&priv->lock);
 	list_for_each_entry_safe(binding, temp, &priv->bindings, list) {
+		mutex_lock(&binding->lock);
 		dev = binding->dev;
+		if (!dev) {
+			mutex_unlock(&binding->lock);
+			net_devmem_unbind_dmabuf(binding);
+			continue;
+		}
+		netdev_hold(dev, &dev_tracker, GFP_KERNEL);
+		mutex_unlock(&binding->lock);
+
 		netdev_lock(dev);
 		net_devmem_unbind_dmabuf(binding);
 		netdev_unlock(dev);
+		netdev_put(dev, &dev_tracker);
 	}
 	mutex_unlock(&priv->lock);
 }