aboutsummaryrefslogtreecommitdiff
path: root/net/packet/af_packet.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/packet/af_packet.c')
-rw-r--r--net/packet/af_packet.c66
1 files changed, 44 insertions, 22 deletions
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 008a45ca3112..2986941164b1 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -177,8 +177,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
#define BLK_PLUS_PRIV(sz_of_priv) \
(BLK_HDR_LEN + ALIGN((sz_of_priv), V3_ALIGNMENT))
-#define PGV_FROM_VMALLOC 1
-
#define BLOCK_STATUS(x) ((x)->hdr.bh1.block_status)
#define BLOCK_NUM_PKTS(x) ((x)->hdr.bh1.num_pkts)
#define BLOCK_O2FP(x) ((x)->hdr.bh1.offset_to_first_pkt)
@@ -1686,10 +1684,6 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
mutex_lock(&fanout_mutex);
- err = -EINVAL;
- if (!po->running)
- goto out;
-
err = -EALREADY;
if (po->fanout)
goto out;
@@ -1751,7 +1745,10 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
list_add(&match->list, &fanout_list);
}
err = -EINVAL;
- if (match->type == type &&
+
+ spin_lock(&po->bind_lock);
+ if (po->running &&
+ match->type == type &&
match->prot_hook.type == po->prot_hook.type &&
match->prot_hook.dev == po->prot_hook.dev) {
err = -ENOSPC;
@@ -1763,9 +1760,16 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
err = 0;
}
}
+ spin_unlock(&po->bind_lock);
+
+ if (err && !refcount_read(&match->sk_ref)) {
+ list_del(&match->list);
+ kfree(match);
+ }
+
out:
if (err && rollover) {
- kfree(rollover);
+ kfree_rcu(rollover, rcu);
po->rollover = NULL;
}
mutex_unlock(&fanout_mutex);
@@ -1792,8 +1796,10 @@ static struct packet_fanout *fanout_release(struct sock *sk)
else
f = NULL;
- if (po->rollover)
+ if (po->rollover) {
kfree_rcu(po->rollover, rcu);
+ po->rollover = NULL;
+ }
}
mutex_unlock(&fanout_mutex);
@@ -2191,6 +2197,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
struct timespec ts;
__u32 ts_status;
bool is_drop_n_account = false;
+ bool do_vnet = false;
/* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT.
* We may add members to them until current aligned size without forcing
@@ -2241,8 +2248,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
netoff = TPACKET_ALIGN(po->tp_hdrlen +
(maclen < 16 ? 16 : maclen)) +
po->tp_reserve;
- if (po->has_vnet_hdr)
+ if (po->has_vnet_hdr) {
netoff += sizeof(struct virtio_net_hdr);
+ do_vnet = true;
+ }
macoff = netoff - maclen;
}
if (po->tp_version <= TPACKET_V2) {
@@ -2259,8 +2268,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
skb_set_owner_r(copy_skb, sk);
}
snaplen = po->rx_ring.frame_size - macoff;
- if ((int)snaplen < 0)
+ if ((int)snaplen < 0) {
snaplen = 0;
+ do_vnet = false;
+ }
}
} else if (unlikely(macoff + snaplen >
GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) {
@@ -2273,6 +2284,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
if (unlikely((int)snaplen < 0)) {
snaplen = 0;
macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len;
+ do_vnet = false;
}
}
spin_lock(&sk->sk_receive_queue.lock);
@@ -2298,7 +2310,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
}
spin_unlock(&sk->sk_receive_queue.lock);
- if (po->has_vnet_hdr) {
+ if (do_vnet) {
if (virtio_net_hdr_from_skb(skb, h.raw + macoff -
sizeof(struct virtio_net_hdr),
vio_le(), true)) {
@@ -2830,6 +2842,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
struct virtio_net_hdr vnet_hdr = { 0 };
int offset = 0;
struct packet_sock *po = pkt_sk(sk);
+ bool has_vnet_hdr = false;
int hlen, tlen, linear;
int extra_len = 0;
@@ -2873,6 +2886,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
err = packet_snd_vnet_parse(msg, &len, &vnet_hdr);
if (err)
goto out_unlock;
+ has_vnet_hdr = true;
}
if (unlikely(sock_flag(sk, SOCK_NOFCS))) {
@@ -2931,7 +2945,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
skb->priority = sk->sk_priority;
skb->mark = sockc.mark;
- if (po->has_vnet_hdr) {
+ if (has_vnet_hdr) {
err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le());
if (err)
goto out_free;
@@ -3059,13 +3073,15 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
int ret = 0;
bool unlisted = false;
- if (po->fanout)
- return -EINVAL;
-
lock_sock(sk);
spin_lock(&po->bind_lock);
rcu_read_lock();
+ if (po->fanout) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
if (name) {
dev = dev_get_by_name_rcu(sock_net(sk), name);
if (!dev) {
@@ -3837,6 +3853,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
void *data = &val;
union tpacket_stats_u st;
struct tpacket_rollover_stats rstats;
+ struct packet_rollover *rollover;
if (level != SOL_PACKET)
return -ENOPROTOOPT;
@@ -3915,13 +3932,18 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
0);
break;
case PACKET_ROLLOVER_STATS:
- if (!po->rollover)
+ rcu_read_lock();
+ rollover = rcu_dereference(po->rollover);
+ if (rollover) {
+ rstats.tp_all = atomic_long_read(&rollover->num);
+ rstats.tp_huge = atomic_long_read(&rollover->num_huge);
+ rstats.tp_failed = atomic_long_read(&rollover->num_failed);
+ data = &rstats;
+ lv = sizeof(rstats);
+ }
+ rcu_read_unlock();
+ if (!rollover)
return -EINVAL;
- rstats.tp_all = atomic_long_read(&po->rollover->num);
- rstats.tp_huge = atomic_long_read(&po->rollover->num_huge);
- rstats.tp_failed = atomic_long_read(&po->rollover->num_failed);
- data = &rstats;
- lv = sizeof(rstats);
break;
case PACKET_TX_HAS_OFF:
val = po->tp_tx_has_off;