aboutsummaryrefslogtreecommitdiffstats
path: root/net/xdp
diff options
context:
space:
mode:
Diffstat (limited to 'net/xdp')
-rw-r--r--net/xdp/xdp_umem.c44
-rw-r--r--net/xdp/xdp_umem.h1
-rw-r--r--net/xdp/xsk.c167
-rw-r--r--net/xdp/xsk_queue.h16
4 files changed, 170 insertions, 58 deletions
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 2b18223e7eb8..83de74ca729a 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -87,27 +87,29 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
struct netdev_bpf bpf;
int err = 0;
+ ASSERT_RTNL();
+
force_zc = flags & XDP_ZEROCOPY;
force_copy = flags & XDP_COPY;
if (force_zc && force_copy)
return -EINVAL;
- rtnl_lock();
- if (xdp_get_umem_from_qid(dev, queue_id)) {
- err = -EBUSY;
- goto out_rtnl_unlock;
- }
+ if (xdp_get_umem_from_qid(dev, queue_id))
+ return -EBUSY;
err = xdp_reg_umem_at_qid(dev, umem, queue_id);
if (err)
- goto out_rtnl_unlock;
+ return err;
umem->dev = dev;
umem->queue_id = queue_id;
+
+ dev_hold(dev);
+
if (force_copy)
/* For copy-mode, we are done. */
- goto out_rtnl_unlock;
+ return 0;
if (!dev->netdev_ops->ndo_bpf ||
!dev->netdev_ops->ndo_xsk_async_xmit) {
@@ -122,9 +124,7 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
err = dev->netdev_ops->ndo_bpf(dev, &bpf);
if (err)
goto err_unreg_umem;
- rtnl_unlock();
- dev_hold(dev);
umem->zc = true;
return 0;
@@ -133,39 +133,35 @@ err_unreg_umem:
err = 0; /* fallback to copy mode */
if (err)
xdp_clear_umem_at_qid(dev, queue_id);
-out_rtnl_unlock:
- rtnl_unlock();
return err;
}
-static void xdp_umem_clear_dev(struct xdp_umem *umem)
+void xdp_umem_clear_dev(struct xdp_umem *umem)
{
struct netdev_bpf bpf;
int err;
+ ASSERT_RTNL();
+
+ if (!umem->dev)
+ return;
+
if (umem->zc) {
bpf.command = XDP_SETUP_XSK_UMEM;
bpf.xsk.umem = NULL;
bpf.xsk.queue_id = umem->queue_id;
- rtnl_lock();
err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf);
- rtnl_unlock();
if (err)
WARN(1, "failed to disable umem!\n");
}
- if (umem->dev) {
- rtnl_lock();
- xdp_clear_umem_at_qid(umem->dev, umem->queue_id);
- rtnl_unlock();
- }
+ xdp_clear_umem_at_qid(umem->dev, umem->queue_id);
- if (umem->zc) {
- dev_put(umem->dev);
- umem->zc = false;
- }
+ dev_put(umem->dev);
+ umem->dev = NULL;
+ umem->zc = false;
}
static void xdp_umem_unpin_pages(struct xdp_umem *umem)
@@ -193,7 +189,9 @@ static void xdp_umem_unaccount_pages(struct xdp_umem *umem)
static void xdp_umem_release(struct xdp_umem *umem)
{
+ rtnl_lock();
xdp_umem_clear_dev(umem);
+ rtnl_unlock();
ida_simple_remove(&umem_ida, umem->id);
diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h
index 27603227601b..a63a9fb251f5 100644
--- a/net/xdp/xdp_umem.h
+++ b/net/xdp/xdp_umem.h
@@ -10,6 +10,7 @@
int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
u16 queue_id, u16 flags);
+void xdp_umem_clear_dev(struct xdp_umem *umem);
bool xdp_umem_validate_queues(struct xdp_umem *umem);
void xdp_get_umem(struct xdp_umem *umem);
void xdp_put_umem(struct xdp_umem *umem);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index a14e8864e4fa..59b57d708697 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -37,6 +37,12 @@ bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
READ_ONCE(xs->umem->fq);
}
+bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt)
+{
+ return xskq_has_addrs(umem->fq, cnt);
+}
+EXPORT_SYMBOL(xsk_umem_has_addrs);
+
u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr)
{
return xskq_peek_addr(umem->fq, addr);
@@ -123,13 +129,17 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
u64 addr;
int err;
- if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
- return -EINVAL;
+ spin_lock_bh(&xs->rx_lock);
+
+ if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index) {
+ err = -EINVAL;
+ goto out_unlock;
+ }
if (!xskq_peek_addr(xs->umem->fq, &addr) ||
len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) {
- xs->rx_dropped++;
- return -ENOSPC;
+ err = -ENOSPC;
+ goto out_drop;
}
addr += xs->umem->headroom;
@@ -138,13 +148,21 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
memcpy(buffer, xdp->data_meta, len + metalen);
addr += metalen;
err = xskq_produce_batch_desc(xs->rx, addr, len);
- if (!err) {
- xskq_discard_addr(xs->umem->fq);
- xsk_flush(xs);
- return 0;
- }
+ if (err)
+ goto out_drop;
+
+ xskq_discard_addr(xs->umem->fq);
+ xskq_produce_flush_desc(xs->rx);
+
+ spin_unlock_bh(&xs->rx_lock);
+
+ xs->sk.sk_data_ready(&xs->sk);
+ return 0;
+out_drop:
xs->rx_dropped++;
+out_unlock:
+ spin_unlock_bh(&xs->rx_lock);
return err;
}
@@ -166,22 +184,18 @@ void xsk_umem_consume_tx_done(struct xdp_umem *umem)
}
EXPORT_SYMBOL(xsk_umem_consume_tx_done);
-bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len)
+bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc)
{
- struct xdp_desc desc;
struct xdp_sock *xs;
rcu_read_lock();
list_for_each_entry_rcu(xs, &umem->xsk_list, list) {
- if (!xskq_peek_desc(xs->tx, &desc))
+ if (!xskq_peek_desc(xs->tx, desc))
continue;
- if (xskq_produce_addr_lazy(umem->cq, desc.addr))
+ if (xskq_produce_addr_lazy(umem->cq, desc->addr))
goto out;
- *dma = xdp_umem_get_dma(umem, desc.addr);
- *len = desc.len;
-
xskq_discard_desc(xs->tx);
rcu_read_unlock();
return true;
@@ -226,6 +240,9 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
mutex_lock(&xs->mutex);
+ if (xs->queue_id >= xs->dev->real_num_tx_queues)
+ goto out;
+
while (xskq_peek_desc(xs->tx, &desc)) {
char *buffer;
u64 addr;
@@ -236,12 +253,6 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
goto out;
}
- if (xskq_reserve_addr(xs->umem->cq))
- goto out;
-
- if (xs->queue_id >= xs->dev->real_num_tx_queues)
- goto out;
-
len = desc.len;
skb = sock_alloc_send_skb(sk, len, 1, &err);
if (unlikely(!skb)) {
@@ -253,7 +264,7 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
addr = desc.addr;
buffer = xdp_umem_get_data(xs->umem, addr);
err = skb_store_bits(skb, 0, buffer, len);
- if (unlikely(err)) {
+ if (unlikely(err) || xskq_reserve_addr(xs->umem->cq)) {
kfree_skb(skb);
goto out;
}
@@ -335,6 +346,22 @@ static int xsk_init_queue(u32 entries, struct xsk_queue **queue,
return 0;
}
+static void xsk_unbind_dev(struct xdp_sock *xs)
+{
+ struct net_device *dev = xs->dev;
+
+ if (!dev || xs->state != XSK_BOUND)
+ return;
+
+ xs->state = XSK_UNBOUND;
+
+ /* Wait for driver to stop using the xdp socket. */
+ xdp_del_sk_umem(xs->umem, xs);
+ xs->dev = NULL;
+ synchronize_net();
+ dev_put(dev);
+}
+
static int xsk_release(struct socket *sock)
{
struct sock *sk = sock->sk;
@@ -354,15 +381,7 @@ static int xsk_release(struct socket *sock)
sock_prot_inuse_add(net, sk->sk_prot, -1);
local_bh_enable();
- if (xs->dev) {
- struct net_device *dev = xs->dev;
-
- /* Wait for driver to stop using the xdp socket. */
- xdp_del_sk_umem(xs->umem, xs);
- xs->dev = NULL;
- synchronize_net();
- dev_put(dev);
- }
+ xsk_unbind_dev(xs);
xskq_destroy(xs->rx);
xskq_destroy(xs->tx);
@@ -411,8 +430,9 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
if (flags & ~(XDP_SHARED_UMEM | XDP_COPY | XDP_ZEROCOPY))
return -EINVAL;
+ rtnl_lock();
mutex_lock(&xs->mutex);
- if (xs->dev) {
+ if (xs->state != XSK_READY) {
err = -EBUSY;
goto out_release;
}
@@ -492,8 +512,11 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
out_unlock:
if (err)
dev_put(dev);
+ else
+ xs->state = XSK_BOUND;
out_release:
mutex_unlock(&xs->mutex);
+ rtnl_unlock();
return err;
}
@@ -520,6 +543,10 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
return -EFAULT;
mutex_lock(&xs->mutex);
+ if (xs->state != XSK_READY) {
+ mutex_unlock(&xs->mutex);
+ return -EBUSY;
+ }
q = (optname == XDP_TX_RING) ? &xs->tx : &xs->rx;
err = xsk_init_queue(entries, q, false);
mutex_unlock(&xs->mutex);
@@ -534,7 +561,7 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
return -EFAULT;
mutex_lock(&xs->mutex);
- if (xs->umem) {
+ if (xs->state != XSK_READY || xs->umem) {
mutex_unlock(&xs->mutex);
return -EBUSY;
}
@@ -561,6 +588,10 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
return -EFAULT;
mutex_lock(&xs->mutex);
+ if (xs->state != XSK_READY) {
+ mutex_unlock(&xs->mutex);
+ return -EBUSY;
+ }
if (!xs->umem) {
mutex_unlock(&xs->mutex);
return -EINVAL;
@@ -644,6 +675,26 @@ static int xsk_getsockopt(struct socket *sock, int level, int optname,
return 0;
}
+ case XDP_OPTIONS:
+ {
+ struct xdp_options opts = {};
+
+ if (len < sizeof(opts))
+ return -EINVAL;
+
+ mutex_lock(&xs->mutex);
+ if (xs->zc)
+ opts.flags |= XDP_OPTIONS_ZEROCOPY;
+ mutex_unlock(&xs->mutex);
+
+ len = sizeof(opts);
+ if (copy_to_user(optval, &opts, len))
+ return -EFAULT;
+ if (put_user(len, optlen))
+ return -EFAULT;
+
+ return 0;
+ }
default:
break;
}
@@ -662,6 +713,9 @@ static int xsk_mmap(struct file *file, struct socket *sock,
unsigned long pfn;
struct page *qpg;
+ if (xs->state != XSK_READY)
+ return -EBUSY;
+
if (offset == XDP_PGOFF_RX_RING) {
q = READ_ONCE(xs->rx);
} else if (offset == XDP_PGOFF_TX_RING) {
@@ -693,6 +747,38 @@ static int xsk_mmap(struct file *file, struct socket *sock,
size, vma->vm_page_prot);
}
+static int xsk_notifier(struct notifier_block *this,
+ unsigned long msg, void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct net *net = dev_net(dev);
+ struct sock *sk;
+
+ switch (msg) {
+ case NETDEV_UNREGISTER:
+ mutex_lock(&net->xdp.lock);
+ sk_for_each(sk, &net->xdp.list) {
+ struct xdp_sock *xs = xdp_sk(sk);
+
+ mutex_lock(&xs->mutex);
+ if (xs->dev == dev) {
+ sk->sk_err = ENETDOWN;
+ if (!sock_flag(sk, SOCK_DEAD))
+ sk->sk_error_report(sk);
+
+ xsk_unbind_dev(xs);
+
+ /* Clear device references in umem. */
+ xdp_umem_clear_dev(xs->umem);
+ }
+ mutex_unlock(&xs->mutex);
+ }
+ mutex_unlock(&net->xdp.lock);
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
static struct proto xsk_proto = {
.name = "XDP",
.owner = THIS_MODULE,
@@ -764,7 +850,9 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
sock_set_flag(sk, SOCK_RCU_FREE);
xs = xdp_sk(sk);
+ xs->state = XSK_READY;
mutex_init(&xs->mutex);
+ spin_lock_init(&xs->rx_lock);
spin_lock_init(&xs->tx_completion_lock);
mutex_lock(&net->xdp.lock);
@@ -784,6 +872,10 @@ static const struct net_proto_family xsk_family_ops = {
.owner = THIS_MODULE,
};
+static struct notifier_block xsk_netdev_notifier = {
+ .notifier_call = xsk_notifier,
+};
+
static int __net_init xsk_net_init(struct net *net)
{
mutex_init(&net->xdp.lock);
@@ -816,8 +908,15 @@ static int __init xsk_init(void)
err = register_pernet_subsys(&xsk_net_ops);
if (err)
goto out_sk;
+
+ err = register_netdevice_notifier(&xsk_netdev_notifier);
+ if (err)
+ goto out_pernet;
+
return 0;
+out_pernet:
+ unregister_pernet_subsys(&xsk_net_ops);
out_sk:
sock_unregister(PF_XDP);
out_proto:
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 88b9ae24658d..909c5168ed0f 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -117,6 +117,20 @@ static inline u32 xskq_nb_free(struct xsk_queue *q, u32 producer, u32 dcnt)
return q->nentries - (producer - q->cons_tail);
}
+static inline bool xskq_has_addrs(struct xsk_queue *q, u32 cnt)
+{
+ u32 entries = q->prod_tail - q->cons_tail;
+
+ if (entries >= cnt)
+ return true;
+
+ /* Refresh the local pointer. */
+ q->prod_tail = READ_ONCE(q->ring->producer);
+ entries = q->prod_tail - q->cons_tail;
+
+ return entries >= cnt;
+}
+
/* UMEM queue */
static inline bool xskq_is_valid_addr(struct xsk_queue *q, u64 addr)
@@ -288,7 +302,7 @@ static inline void xskq_produce_flush_desc(struct xsk_queue *q)
/* Order producer and data */
smp_wmb(); /* B, matches C */
- q->prod_tail = q->prod_head,
+ q->prod_tail = q->prod_head;
WRITE_ONCE(q->ring->producer, q->prod_tail);
}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.