return group ? 1 << (group - 1) : 0;
}
+static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb,
+ gfp_t gfp_mask)
+{
+ unsigned int len = skb_end_offset(skb);
+ struct sk_buff *new;
+
+ new = alloc_skb(len, gfp_mask);
+ if (new == NULL)
+ return NULL;
+
+ NETLINK_CB(new).portid = NETLINK_CB(skb).portid;
+ NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group;
+ NETLINK_CB(new).creds = NETLINK_CB(skb).creds;
+
+ memcpy(skb_put(new, len), skb->data, len);
+ return new;
+}
+
int netlink_add_tap(struct netlink_tap *nt)
{
if (unlikely(nt->dev->type != ARPHRD_NETLINK))
int ret = -ENOMEM;
dev_hold(dev);
- nskb = skb_clone(skb, GFP_ATOMIC);
+
+ if (netlink_skb_is_mmaped(skb) || is_vmalloc_addr(skb->head))
+ nskb = netlink_to_full_skb(skb, GFP_ATOMIC);
+ else
+ nskb = skb_clone(skb, GFP_ATOMIC);
if (nskb) {
nskb->dev = dev;
nskb->protocol = htons((u16) sk->sk_protocol);
}
#ifdef CONFIG_NETLINK_MMAP
-static bool netlink_skb_is_mmaped(const struct sk_buff *skb)
-{
- return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
-}
-
static bool netlink_rx_is_mmaped(struct sock *sk)
{
return nlk_sk(sk)->rx_ring.pg_vec != NULL;
return NULL;
}
+
+static void
+__netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, bool tx_ring, void **pg_vec,
+ unsigned int order)
+{
+ struct netlink_sock *nlk = nlk_sk(sk);
+ struct sk_buff_head *queue;
+ struct netlink_ring *ring;
+
+ queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
+ ring = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
+
+ spin_lock_bh(&queue->lock);
+
+ ring->frame_max = req->nm_frame_nr - 1;
+ ring->head = 0;
+ ring->frame_size = req->nm_frame_size;
+ ring->pg_vec_pages = req->nm_block_size / PAGE_SIZE;
+
+ swap(ring->pg_vec_len, req->nm_block_nr);
+ swap(ring->pg_vec_order, order);
+ swap(ring->pg_vec, pg_vec);
+
+ __skb_queue_purge(queue);
+ spin_unlock_bh(&queue->lock);
+
+ WARN_ON(atomic_read(&nlk->mapped));
+
+ if (pg_vec)
+ free_pg_vec(pg_vec, order, req->nm_block_nr);
+}
+
static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
- bool closing, bool tx_ring)
+ bool tx_ring)
{
struct netlink_sock *nlk = nlk_sk(sk);
struct netlink_ring *ring;
- struct sk_buff_head *queue;
void **pg_vec = NULL;
unsigned int order = 0;
- int err;
ring = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
- queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
- if (!closing) {
- if (atomic_read(&nlk->mapped))
- return -EBUSY;
- if (atomic_read(&ring->pending))
- return -EBUSY;
- }
+ if (atomic_read(&nlk->mapped))
+ return -EBUSY;
+ if (atomic_read(&ring->pending))
+ return -EBUSY;
if (req->nm_block_nr) {
if (ring->pg_vec != NULL)
return -EINVAL;
}
- err = -EBUSY;
mutex_lock(&nlk->pg_vec_lock);
- if (closing || atomic_read(&nlk->mapped) == 0) {
- err = 0;
- spin_lock_bh(&queue->lock);
-
- ring->frame_max = req->nm_frame_nr - 1;
- ring->head = 0;
- ring->frame_size = req->nm_frame_size;
- ring->pg_vec_pages = req->nm_block_size / PAGE_SIZE;
-
- swap(ring->pg_vec_len, req->nm_block_nr);
- swap(ring->pg_vec_order, order);
- swap(ring->pg_vec, pg_vec);
-
- __skb_queue_purge(queue);
- spin_unlock_bh(&queue->lock);
-
- WARN_ON(atomic_read(&nlk->mapped));
+ if (atomic_read(&nlk->mapped) == 0) {
+ __netlink_set_ring(sk, req, tx_ring, pg_vec, order);
+ mutex_unlock(&nlk->pg_vec_lock);
+ return 0;
}
+
mutex_unlock(&nlk->pg_vec_lock);
if (pg_vec)
free_pg_vec(pg_vec, order, req->nm_block_nr);
- return err;
+
+ return -EBUSY;
}
static void netlink_mm_open(struct vm_area_struct *vma)
}
#else /* CONFIG_NETLINK_MMAP */
-#define netlink_skb_is_mmaped(skb) false
#define netlink_rx_is_mmaped(sk) false
#define netlink_tx_is_mmaped(sk) false
#define netlink_mmap sock_no_mmap
memset(&req, 0, sizeof(req));
if (nlk->rx_ring.pg_vec)
- netlink_set_ring(sk, &req, true, false);
+ __netlink_set_ring(sk, &req, false, NULL, 0);
memset(&req, 0, sizeof(req));
if (nlk->tx_ring.pg_vec)
- netlink_set_ring(sk, &req, true, true);
+ __netlink_set_ring(sk, &req, true, NULL, 0);
}
#endif /* CONFIG_NETLINK_MMAP */
lock_sock(sk);
- err = -EBUSY;
- if (nlk_sk(sk)->portid)
+ err = nlk_sk(sk)->portid == portid ? 0 : -EBUSY;
+ if (nlk_sk(sk)->bound)
goto err;
err = -ENOMEM;
err = __netlink_insert(table, sk);
if (err) {
+ /* In case the hashtable backend returns with -EBUSY
+ * from here, it must not escape to the caller.
+ */
+ if (unlikely(err == -EBUSY))
+ err = -EOVERFLOW;
if (err == -EEXIST)
err = -EADDRINUSE;
- nlk_sk(sk)->portid = 0;
sock_put(sk);
}
+ /* We need to ensure that the socket is hashed and visible. */
+ smp_wmb();
+ nlk_sk(sk)->bound = portid;
+
err:
release_sock(sk);
return err;
struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
int err;
long unsigned int groups = nladdr->nl_groups;
+ bool bound;
if (addr_len < sizeof(struct sockaddr_nl))
return -EINVAL;
return err;
}
- if (nlk->portid)
+ bound = nlk->bound;
+ if (bound) {
+ /* Ensure nlk->portid is up-to-date. */
+ smp_rmb();
+
if (nladdr->nl_pid != nlk->portid)
return -EINVAL;
+ }
if (nlk->netlink_bind && groups) {
int group;
}
}
- if (!nlk->portid) {
+ /* No need for barriers here as we return to user-space without
+ * using any of the bound attributes.
+ */
+ if (!bound) {
err = nladdr->nl_pid ?
netlink_insert(sk, nladdr->nl_pid) :
netlink_autobind(sock);
!netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
return -EPERM;
- if (!nlk->portid)
+ /* No need for barriers here as we return to user-space without
+ * using any of the bound attributes.
+ */
+ if (!nlk->bound)
err = netlink_autobind(sock);
if (err == 0) {
return -EINVAL;
if (copy_from_user(&req, optval, sizeof(req)))
return -EFAULT;
- err = netlink_set_ring(sk, &req, false,
+ err = netlink_set_ring(sk, &req,
optname == NETLINK_TX_RING);
break;
}
dst_group = nlk->dst_group;
}
- if (!nlk->portid) {
+ if (!nlk->bound) {
err = netlink_autobind(sock);
if (err)
goto out;
+ } else {
+ /* Ensure nlk is hashed and visible. */
+ smp_rmb();
}
/* It's a really convoluted way for userland to ask for mmaped
Code Review / kvmfornfv.git / blobdiff