summaryrefslogtreecommitdiff
path: root/net/packet
diff options
context:
space:
mode:
Diffstat (limited to 'net/packet')
-rw-r--r--net/packet/af_packet.c73
-rw-r--r--net/packet/internal.h1
2 files changed, 42 insertions, 32 deletions
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 2d73769d67f4..0184e74f8adf 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -581,7 +581,7 @@ static __be16 vlan_get_protocol_dgram(const struct sk_buff *skb)
static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc)
{
- del_timer_sync(&pkc->retire_blk_timer);
+ timer_delete_sync(&pkc->retire_blk_timer);
}
static void prb_shutdown_retire_blk_timer(struct packet_sock *po,
@@ -2102,8 +2102,8 @@ retry:
skb->protocol = proto;
skb->dev = dev;
- skb->priority = READ_ONCE(sk->sk_priority);
- skb->mark = READ_ONCE(sk->sk_mark);
+ skb->priority = sockc.priority;
+ skb->mark = sockc.mark;
skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid);
skb_setup_tx_timestamp(skb, &sockc);
@@ -2634,8 +2634,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
skb->protocol = proto;
skb->dev = dev;
- skb->priority = READ_ONCE(po->sk.sk_priority);
- skb->mark = READ_ONCE(po->sk.sk_mark);
+ skb->priority = sockc->priority;
+ skb->mark = sockc->mark;
skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, po->sk.sk_clockid);
skb_setup_tx_timestamp(skb, sockc);
skb_zcopy_set_nouarg(skb, ph.raw);
@@ -2785,7 +2785,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
int len_sum = 0;
int status = TP_STATUS_AVAILABLE;
int hlen, tlen, copylen = 0;
- long timeo = 0;
+ long timeo;
mutex_lock(&po->pg_vec_lock);
@@ -2839,22 +2839,28 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
if ((size_max > dev->mtu + reserve + VLAN_HLEN) && !vnet_hdr_sz)
size_max = dev->mtu + reserve + VLAN_HLEN;
+ timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT);
reinit_completion(&po->skb_completion);
do {
ph = packet_current_frame(po, &po->tx_ring,
TP_STATUS_SEND_REQUEST);
if (unlikely(ph == NULL)) {
- if (need_wait && skb) {
- timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT);
+ /* Note: packet_read_pending() might be slow if we
+ * have to call it as it's per_cpu variable, but in
+ * fast-path we don't have to call it, only when ph
+ * is NULL, we need to check the pending_refcnt.
+ */
+ if (need_wait && packet_read_pending(&po->tx_ring)) {
timeo = wait_for_completion_interruptible_timeout(&po->skb_completion, timeo);
if (timeo <= 0) {
err = !timeo ? -ETIMEDOUT : -ERESTARTSYS;
goto out_put;
}
- }
- /* check for additional frames */
- continue;
+ /* check for additional frames */
+ continue;
+ } else
+ break;
}
skb = NULL;
@@ -2943,14 +2949,7 @@ tpacket_error:
}
packet_increment_head(&po->tx_ring);
len_sum += tp_len;
- } while (likely((ph != NULL) ||
- /* Note: packet_read_pending() might be slow if we have
- * to call it as it's per_cpu variable, but in fast-path
- * we already short-circuit the loop with the first
- * condition, and luckily don't have to go that path
- * anyway.
- */
- (need_wait && packet_read_pending(&po->tx_ring))));
+ } while (1);
err = len_sum;
goto out_put;
@@ -3039,7 +3038,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
goto out_unlock;
sockcm_init(&sockc, sk);
- sockc.mark = READ_ONCE(sk->sk_mark);
if (msg->msg_controllen) {
err = sock_cmsg_send(sk, msg, &sockc);
if (unlikely(err))
@@ -3112,7 +3110,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
skb->protocol = proto;
skb->dev = dev;
- skb->priority = READ_ONCE(sk->sk_priority);
+ skb->priority = sockc.priority;
skb->mark = sockc.mark;
skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid);
@@ -3714,15 +3712,15 @@ static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i,
}
static void packet_dev_mclist_delete(struct net_device *dev,
- struct packet_mclist **mlp)
+ struct packet_mclist **mlp,
+ struct list_head *list)
{
struct packet_mclist *ml;
while ((ml = *mlp) != NULL) {
if (ml->ifindex == dev->ifindex) {
- packet_dev_mc(dev, ml, -1);
+ list_add(&ml->remove_list, list);
*mlp = ml->next;
- kfree(ml);
} else
mlp = &ml->next;
}
@@ -3770,6 +3768,7 @@ static int packet_mc_add(struct sock *sk, struct packet_mreq_max *mreq)
memcpy(i->addr, mreq->mr_address, i->alen);
memset(i->addr + i->alen, 0, sizeof(i->addr) - i->alen);
i->count = 1;
+ INIT_LIST_HEAD(&i->remove_list);
i->next = po->mclist;
po->mclist = i;
err = packet_dev_mc(dev, i, 1);
@@ -4234,9 +4233,11 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
static int packet_notifier(struct notifier_block *this,
unsigned long msg, void *ptr)
{
- struct sock *sk;
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
+ struct packet_mclist *ml, *tmp;
+ LIST_HEAD(mclist);
+ struct sock *sk;
rcu_read_lock();
sk_for_each_rcu(sk, &net->packet.sklist) {
@@ -4245,7 +4246,8 @@ static int packet_notifier(struct notifier_block *this,
switch (msg) {
case NETDEV_UNREGISTER:
if (po->mclist)
- packet_dev_mclist_delete(dev, &po->mclist);
+ packet_dev_mclist_delete(dev, &po->mclist,
+ &mclist);
fallthrough;
case NETDEV_DOWN:
@@ -4278,6 +4280,13 @@ static int packet_notifier(struct notifier_block *this,
}
}
rcu_read_unlock();
+
+ /* packet_dev_mc might grab instance locks so can't run under rcu */
+ list_for_each_entry_safe(ml, tmp, &mclist, remove_list) {
+ packet_dev_mc(dev, ml, -1);
+ kfree(ml);
+ }
+
return NOTIFY_DONE;
}
@@ -4564,10 +4573,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
spin_lock(&po->bind_lock);
was_running = packet_sock_flag(po, PACKET_SOCK_RUNNING);
num = po->num;
- if (was_running) {
- WRITE_ONCE(po->num, 0);
+ WRITE_ONCE(po->num, 0);
+ if (was_running)
__unregister_prot_hook(sk, false);
- }
+
spin_unlock(&po->bind_lock);
synchronize_net();
@@ -4599,10 +4608,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
mutex_unlock(&po->pg_vec_lock);
spin_lock(&po->bind_lock);
- if (was_running) {
- WRITE_ONCE(po->num, num);
+ WRITE_ONCE(po->num, num);
+ if (was_running)
register_prot_hook(sk);
- }
+
spin_unlock(&po->bind_lock);
if (pg_vec && (po->tp_version > TPACKET_V2)) {
/* Because we don't support block-based V3 on tx-ring */
diff --git a/net/packet/internal.h b/net/packet/internal.h
index d5d70712007a..1e743d0316fd 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -11,6 +11,7 @@ struct packet_mclist {
unsigned short type;
unsigned short alen;
unsigned char addr[MAX_ADDR_LEN];
+ struct list_head remove_list;
};
/* kbdq - kernel block descriptor queue */
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-21 04:21:40 +0300