Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

4 files changed, 88 insertions, 38 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index ff31535126..7554803218 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -130,7 +130,7 @@ static const char *const nlk_cb_mutex_key_strings[MAX_LINKS + 1] = {
 	"nlk_cb_mutex-MAX_LINKS"
 };
 
-static int netlink_dump(struct sock *sk);
+static int netlink_dump(struct sock *sk, bool lock_taken);
 
 /* nl_table locking explained:
  * Lookup and traversal are protected with an RCU read-side lock. Insertion
@@ -636,7 +636,7 @@ static struct proto netlink_proto = {
 };
 
 static int __netlink_create(struct net *net, struct socket *sock,
-			    struct mutex *cb_mutex, int protocol,
+			    struct mutex *dump_cb_mutex, int protocol,
 			    int kern)
 {
 	struct sock *sk;
@@ -651,15 +651,11 @@ static int __netlink_create(struct net *net, struct socket *sock,
 	sock_init_data(sock, sk);
 
 	nlk = nlk_sk(sk);
-	if (cb_mutex) {
-		nlk->cb_mutex = cb_mutex;
-	} else {
-		nlk->cb_mutex = &nlk->cb_def_mutex;
-		mutex_init(nlk->cb_mutex);
-		lockdep_set_class_and_name(nlk->cb_mutex,
+	mutex_init(&nlk->nl_cb_mutex);
+	lockdep_set_class_and_name(&nlk->nl_cb_mutex,
 					   nlk_cb_mutex_keys + protocol,
 					   nlk_cb_mutex_key_strings[protocol]);
-	}
+	nlk->dump_cb_mutex = dump_cb_mutex;
 	init_waitqueue_head(&nlk->wait);
 
 	sk->sk_destruct = netlink_sock_destruct;
@@ -1206,23 +1202,21 @@ struct sock *netlink_getsockbyfilp(struct file *filp)
 
 struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast)
 {
+	size_t head_size = SKB_HEAD_ALIGN(size);
 	struct sk_buff *skb;
 	void *data;
 
-	if (size <= NLMSG_GOODSIZE || broadcast)
+	if (head_size <= PAGE_SIZE || broadcast)
 		return alloc_skb(size, GFP_KERNEL);
 
-	size = SKB_DATA_ALIGN(size) +
-	       SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-
-	data = vmalloc(size);
-	if (data == NULL)
+	data = kvmalloc(head_size, GFP_KERNEL);
+	if (!data)
 		return NULL;
 
-	skb = __build_skb(data, size);
-	if (skb == NULL)
-		vfree(data);
-	else
+	skb = __build_skb(data, head_size);
+	if (!skb)
+		kvfree(data);
+	else if (is_vmalloc_addr(data))
 		skb->destructor = netlink_skb_destructor;
 
 	return skb;
@@ -1779,6 +1773,9 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 		netlink_unlock_table();
 		return err;
 	}
+	case NETLINK_LISTEN_ALL_NSID:
+		flag = NETLINK_F_LISTEN_ALL_NSID;
+		break;
 	case NETLINK_CAP_ACK:
 		flag = NETLINK_F_CAP_ACK;
 		break;
@@ -1987,7 +1984,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 	if (READ_ONCE(nlk->cb_running) &&
 	    atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) {
-		ret = netlink_dump(sk);
+		ret = netlink_dump(sk, false);
 		if (ret) {
 			WRITE_ONCE(sk->sk_err, -ret);
 			sk_error_report(sk);
@@ -2196,7 +2193,7 @@ static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb,
 	return 0;
 }
 
-static int netlink_dump(struct sock *sk)
+static int netlink_dump(struct sock *sk, bool lock_taken)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct netlink_ext_ack extack = {};
@@ -2208,7 +2205,8 @@ static int netlink_dump(struct sock *sk)
 	int alloc_min_size;
 	int alloc_size;
 
-	mutex_lock(nlk->cb_mutex);
+	if (!lock_taken)
+		mutex_lock(&nlk->nl_cb_mutex);
 	if (!nlk->cb_running) {
 		err = -EINVAL;
 		goto errout_skb;
@@ -2260,14 +2258,33 @@ static int netlink_dump(struct sock *sk)
 	netlink_skb_set_owner_r(skb, sk);
 
 	if (nlk->dump_done_errno > 0) {
+		struct mutex *extra_mutex = nlk->dump_cb_mutex;
+
 		cb->extack = &extack;
+
+		if (cb->flags & RTNL_FLAG_DUMP_UNLOCKED)
+			extra_mutex = NULL;
+		if (extra_mutex)
+			mutex_lock(extra_mutex);
 		nlk->dump_done_errno = cb->dump(skb, cb);
+		if (extra_mutex)
+			mutex_unlock(extra_mutex);
+
+		/* EMSGSIZE plus something already in the skb means
+		 * that there's more to dump but current skb has filled up.
+		 * If the callback really wants to return EMSGSIZE to user space
+		 * it needs to do so again, on the next cb->dump() call,
+		 * without putting data in the skb.
+		 */
+		if (nlk->dump_done_errno == -EMSGSIZE && skb->len)
+			nlk->dump_done_errno = skb->len;
+
 		cb->extack = NULL;
 	}
 
 	if (nlk->dump_done_errno > 0 ||
 	    skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) {
-		mutex_unlock(nlk->cb_mutex);
+		mutex_unlock(&nlk->nl_cb_mutex);
 
 		if (sk_filter(sk, skb))
 			kfree_skb(skb);
@@ -2301,13 +2318,13 @@ static int netlink_dump(struct sock *sk)
 	WRITE_ONCE(nlk->cb_running, false);
 	module = cb->module;
 	skb = cb->skb;
-	mutex_unlock(nlk->cb_mutex);
+	mutex_unlock(&nlk->nl_cb_mutex);
 	module_put(module);
 	consume_skb(skb);
 	return 0;
 
 errout_skb:
-	mutex_unlock(nlk->cb_mutex);
+	mutex_unlock(&nlk->nl_cb_mutex);
 	kfree_skb(skb);
 	return err;
 }
@@ -2330,7 +2347,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	}
 
 	nlk = nlk_sk(sk);
-	mutex_lock(nlk->cb_mutex);
+	mutex_lock(&nlk->nl_cb_mutex);
 	/* A dump is in progress... */
 	if (nlk->cb_running) {
 		ret = -EBUSY;
@@ -2350,6 +2367,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	cb->data = control->data;
 	cb->module = control->module;
 	cb->min_dump_alloc = control->min_dump_alloc;
+	cb->flags = control->flags;
 	cb->skb = skb;
 
 	cb->strict_check = nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk);
@@ -2365,9 +2383,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	WRITE_ONCE(nlk->cb_running, true);
 	nlk->dump_done_errno = INT_MAX;
 
-	mutex_unlock(nlk->cb_mutex);
-
-	ret = netlink_dump(sk);
+	ret = netlink_dump(sk, true);
 
 	sock_put(sk);
 
@@ -2383,7 +2399,7 @@ error_put:
 	module_put(control->module);
 error_unlock:
 	sock_put(sk);
-	mutex_unlock(nlk->cb_mutex);
+	mutex_unlock(&nlk->nl_cb_mutex);
 error_free:
 	kfree_skb(skb);
 	return ret;
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 2145979b99..9751e29d4b 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -39,8 +39,9 @@ struct netlink_sock {
 	bool			cb_running;
 	int			dump_done_errno;
 	struct netlink_callback	cb;
-	struct mutex		*cb_mutex;
-	struct mutex		cb_def_mutex;
+	struct mutex		nl_cb_mutex;
+
+	struct mutex		*dump_cb_mutex;
 	void			(*netlink_rcv)(struct sk_buff *skb);
 	int			(*netlink_bind)(struct net *net, int group);
 	void			(*netlink_unbind)(struct net *net, int group);
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index 1eeff94228..61981e01fd 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -207,7 +207,7 @@ static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		err = __netlink_diag_dump(skb, cb, req->sdiag_protocol, s_num);
 	}
 
-	return err < 0 ? err : skb->len;
+	return err <= 0 ? err : skb->len;
 }
 
 static int netlink_diag_dump_done(struct netlink_callback *cb)
@@ -241,6 +241,7 @@ static int netlink_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
 }
 
 static const struct sock_diag_handler netlink_diag_handler = {
+	.owner = THIS_MODULE,
 	.family = AF_NETLINK,
 	.dump = netlink_diag_handler_dump,
 };
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 8c7af02f84..3b7666944b 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1232,7 +1232,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq,
 
 	hdr = genlmsg_put(skb, portid, seq, &genl_ctrl, flags, cmd);
 	if (hdr == NULL)
-		return -1;
+		return -EMSGSIZE;
 
 	if (nla_put_string(skb, CTRL_ATTR_FAMILY_NAME, family->name) ||
 	    nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, family->id) ||
@@ -1355,6 +1355,7 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb)
 	struct net *net = sock_net(skb->sk);
 	int fams_to_skip = cb->args[0];
 	unsigned int id;
+	int err = 0;
 
 	idr_for_each_entry(&genl_fam_idr, rt, id) {
 		if (!rt->netnsok && !net_eq(net, &init_net))
@@ -1363,16 +1364,17 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb)
 		if (n++ < fams_to_skip)
 			continue;
 
-		if (ctrl_fill_info(rt, NETLINK_CB(cb->skb).portid,
-				   cb->nlh->nlmsg_seq, NLM_F_MULTI,
-				   skb, CTRL_CMD_NEWFAMILY) < 0) {
+		err = ctrl_fill_info(rt, NETLINK_CB(cb->skb).portid,
+				     cb->nlh->nlmsg_seq, NLM_F_MULTI,
+				     skb, CTRL_CMD_NEWFAMILY);
+		if (err) {
 			n--;
 			break;
 		}
 	}
 
 	cb->args[0] = n;
-	return skb->len;
+	return err;
 }
 
 static struct sk_buff *ctrl_build_family_msg(const struct genl_family *family,
@@ -1836,6 +1838,9 @@ static int genl_bind(struct net *net, int group)
 		    !ns_capable(net->user_ns, CAP_SYS_ADMIN))
 			ret = -EPERM;
 
+		if (family->bind)
+			family->bind(i);
+
 		break;
 	}
 
@@ -1843,12 +1848,39 @@ static int genl_bind(struct net *net, int group)
 	return ret;
 }
 
+static void genl_unbind(struct net *net, int group)
+{
+	const struct genl_family *family;
+	unsigned int id;
+
+	down_read(&cb_lock);
+
+	idr_for_each_entry(&genl_fam_idr, family, id) {
+		int i;
+
+		if (family->n_mcgrps == 0)
+			continue;
+
+		i = group - family->mcgrp_offset;
+		if (i < 0 || i >= family->n_mcgrps)
+			continue;
+
+		if (family->unbind)
+			family->unbind(i);
+
+		break;
+	}
+
+	up_read(&cb_lock);
+}
+
 static int __net_init genl_pernet_init(struct net *net)
 {
 	struct netlink_kernel_cfg cfg = {
 		.input		= genl_rcv,
 		.flags		= NL_CFG_F_NONROOT_RECV,
 		.bind		= genl_bind,
+		.unbind		= genl_unbind,
 		.release	= genl_release,
 	};