summaryrefslogtreecommitdiff
path: root/net/packet
diff options
context:
space:
mode:
Diffstat (limited to 'net/packet')
-rw-r--r--net/packet/af_packet.c185
-rw-r--r--net/packet/internal.h1
2 files changed, 133 insertions, 53 deletions
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 18f616f487ea..3d43f3eae759 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -538,9 +538,50 @@ static void *packet_current_frame(struct packet_sock *po,
return packet_lookup_frame(po, rb, rb->head, status);
}
+static u16 vlan_get_tci(const struct sk_buff *skb, struct net_device *dev)
+{
+ struct vlan_hdr vhdr, *vh;
+ unsigned int header_len;
+
+ if (!dev)
+ return 0;
+
+ /* In the SOCK_DGRAM scenario, skb data starts at the network
+ * protocol, which is after the VLAN headers. The outer VLAN
+ * header is at the hard_header_len offset in non-variable
+ * length link layer headers. If it's a VLAN device, the
+ * min_header_len should be used to exclude the VLAN header
+ * size.
+ */
+ if (dev->min_header_len == dev->hard_header_len)
+ header_len = dev->hard_header_len;
+ else if (is_vlan_dev(dev))
+ header_len = dev->min_header_len;
+ else
+ return 0;
+
+ vh = skb_header_pointer(skb, skb_mac_offset(skb) + header_len,
+ sizeof(vhdr), &vhdr);
+ if (unlikely(!vh))
+ return 0;
+
+ return ntohs(vh->h_vlan_TCI);
+}
+
+static __be16 vlan_get_protocol_dgram(const struct sk_buff *skb)
+{
+ __be16 proto = skb->protocol;
+
+ if (unlikely(eth_type_vlan(proto)))
+ proto = __vlan_get_protocol_offset(skb, proto,
+ skb_mac_offset(skb), NULL);
+
+ return proto;
+}
+
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,
@@ -681,7 +722,7 @@ static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc)
static void prb_retire_rx_blk_timer_expired(struct timer_list *t)
{
struct packet_sock *po =
- from_timer(po, t, rx_ring.prb_bdqc.retire_blk_timer);
+ timer_container_of(po, t, rx_ring.prb_bdqc.retire_blk_timer);
struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(&po->rx_ring);
unsigned int frozen;
struct tpacket_block_desc *pbd;
@@ -1007,10 +1048,16 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc,
static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
struct tpacket3_hdr *ppd)
{
+ struct packet_sock *po = container_of(pkc, struct packet_sock, rx_ring.prb_bdqc);
+
if (skb_vlan_tag_present(pkc->skb)) {
ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb);
ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto);
ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
+ } else if (unlikely(po->sk.sk_type == SOCK_DGRAM && eth_type_vlan(pkc->skb->protocol))) {
+ ppd->hv1.tp_vlan_tci = vlan_get_tci(pkc->skb, pkc->skb->dev);
+ ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->protocol);
+ ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
} else {
ppd->hv1.tp_vlan_tci = 0;
ppd->hv1.tp_vlan_tpid = 0;
@@ -1785,21 +1832,22 @@ static int fanout_add(struct sock *sk, struct fanout_args *args)
err = -EINVAL;
spin_lock(&po->bind_lock);
- if (packet_sock_flag(po, PACKET_SOCK_RUNNING) &&
+ if (po->num &&
match->type == type &&
match->prot_hook.type == po->prot_hook.type &&
match->prot_hook.dev == po->prot_hook.dev) {
err = -ENOSPC;
if (refcount_read(&match->sk_ref) < match->max_num_members) {
- __dev_remove_pack(&po->prot_hook);
-
/* Paired with packet_setsockopt(PACKET_FANOUT_DATA) */
WRITE_ONCE(po->fanout, match);
po->rollover = rollover;
rollover = NULL;
refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1);
- __fanout_link(sk, po);
+ if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) {
+ __dev_remove_pack(&po->prot_hook);
+ __fanout_link(sk, po);
+ }
err = 0;
}
}
@@ -2054,11 +2102,10 @@ retry:
skb->protocol = proto;
skb->dev = dev;
- skb->priority = READ_ONCE(sk->sk_priority);
- skb->mark = READ_ONCE(sk->sk_mark);
- skb->tstamp = sockc.transmit_time;
-
- skb_setup_tx_timestamp(skb, sockc.tsflags);
+ 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);
if (unlikely(extra_len == 4))
skb->no_fcs = 1;
@@ -2122,7 +2169,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
enum skb_drop_reason drop_reason = SKB_CONSUMED;
- struct sock *sk;
+ struct sock *sk = NULL;
struct sockaddr_ll *sll;
struct packet_sock *po;
u8 *skb_head = skb->data;
@@ -2156,7 +2203,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
}
}
- snaplen = skb->len;
+ snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb);
res = run_filter(skb, sk, snaplen);
if (!res)
@@ -2227,7 +2274,7 @@ drop_n_restore:
skb->len = skb_len;
}
drop:
- kfree_skb_reason(skb, drop_reason);
+ sk_skb_reason_drop(sk, skb, drop_reason);
return 0;
}
@@ -2235,7 +2282,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
enum skb_drop_reason drop_reason = SKB_CONSUMED;
- struct sock *sk;
+ struct sock *sk = NULL;
struct packet_sock *po;
struct sockaddr_ll *sll;
union tpacket_uhdr h;
@@ -2276,7 +2323,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
}
}
- snaplen = skb->len;
+ snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb);
res = run_filter(skb, sk, snaplen);
if (!res)
@@ -2428,6 +2475,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
h.h2->tp_vlan_tci = skb_vlan_tag_get(skb);
h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto);
status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
+ } else if (unlikely(sk->sk_type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) {
+ h.h2->tp_vlan_tci = vlan_get_tci(skb, skb->dev);
+ h.h2->tp_vlan_tpid = ntohs(skb->protocol);
+ status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
} else {
h.h2->tp_vlan_tci = 0;
h.h2->tp_vlan_tpid = 0;
@@ -2457,7 +2508,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
sll->sll_halen = dev_parse_header(skb, sll->sll_addr);
sll->sll_family = AF_PACKET;
sll->sll_hatype = dev->type;
- sll->sll_protocol = skb->protocol;
+ sll->sll_protocol = (sk->sk_type == SOCK_DGRAM) ?
+ vlan_get_protocol_dgram(skb) : skb->protocol;
sll->sll_pkttype = skb->pkt_type;
if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV)))
sll->sll_ifindex = orig_dev->ifindex;
@@ -2495,7 +2547,7 @@ drop_n_restore:
skb->len = skb_len;
}
drop:
- kfree_skb_reason(skb, drop_reason);
+ sk_skb_reason_drop(sk, skb, drop_reason);
return 0;
drop_n_account:
@@ -2504,7 +2556,7 @@ drop_n_account:
drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR;
sk->sk_data_ready(sk);
- kfree_skb_reason(copy_skb, drop_reason);
+ sk_skb_reason_drop(sk, copy_skb, drop_reason);
goto drop_n_restore;
}
@@ -2522,8 +2574,7 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
ts = __packet_set_timestamp(po, ph, skb);
__packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts);
- if (!packet_read_pending(&po->tx_ring))
- complete(&po->skb_completion);
+ complete(&po->skb_completion);
}
sock_wfree(skb);
@@ -2583,10 +2634,10 @@ 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->tstamp = sockc->transmit_time;
- skb_setup_tx_timestamp(skb, sockc->tsflags);
+ 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);
skb_reserve(skb, hlen);
@@ -2988,7 +3039,6 @@ 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))
@@ -3051,7 +3101,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
goto out_free;
}
- skb_setup_tx_timestamp(skb, sockc.tsflags);
+ skb_setup_tx_timestamp(skb, &sockc);
if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + extra_len) &&
!packet_extra_vlan_len_allowed(dev, skb)) {
@@ -3061,9 +3111,9 @@ 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->tstamp = sockc.transmit_time;
+ skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid);
if (unlikely(extra_len == 4))
skb->no_fcs = 1;
@@ -3357,17 +3407,17 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
if (sock->type == SOCK_PACKET)
sock->ops = &packet_ops_spkt;
+ po = pkt_sk(sk);
+ err = packet_alloc_pending(po);
+ if (err)
+ goto out_sk_free;
+
sock_init_data(sock, sk);
- po = pkt_sk(sk);
init_completion(&po->skb_completion);
sk->sk_family = PF_PACKET;
po->num = proto;
- err = packet_alloc_pending(po);
- if (err)
- goto out2;
-
packet_cached_dev_reset(po);
sk->sk_destruct = packet_sock_destruct;
@@ -3399,7 +3449,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
sock_prot_inuse_add(net, &packet_proto, 1);
return 0;
-out2:
+out_sk_free:
sk_free(sk);
out:
return err;
@@ -3483,7 +3533,8 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
/* Original length was stored in sockaddr_ll fields */
origlen = PACKET_SKB_CB(skb)->sa.origlen;
sll->sll_family = AF_PACKET;
- sll->sll_protocol = skb->protocol;
+ sll->sll_protocol = (sock->type == SOCK_DGRAM) ?
+ vlan_get_protocol_dgram(skb) : skb->protocol;
}
sock_recv_cmsgs(msg, sk, skb);
@@ -3540,6 +3591,21 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
aux.tp_vlan_tci = skb_vlan_tag_get(skb);
aux.tp_vlan_tpid = ntohs(skb->vlan_proto);
aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
+ } else if (unlikely(sock->type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) {
+ struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
+ struct net_device *dev;
+
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(sock_net(sk), sll->sll_ifindex);
+ if (dev) {
+ aux.tp_vlan_tci = vlan_get_tci(skb, dev);
+ aux.tp_vlan_tpid = ntohs(skb->protocol);
+ aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
+ } else {
+ aux.tp_vlan_tci = 0;
+ aux.tp_vlan_tpid = 0;
+ }
+ rcu_read_unlock();
} else {
aux.tp_vlan_tci = 0;
aux.tp_vlan_tpid = 0;
@@ -3647,15 +3713,15 @@ 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;
}
@@ -3703,6 +3769,7 @@ 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);
@@ -3800,28 +3867,30 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval,
case PACKET_TX_RING:
{
union tpacket_req_u req_u;
- int len;
+ ret = -EINVAL;
lock_sock(sk);
switch (po->tp_version) {
case TPACKET_V1:
case TPACKET_V2:
- len = sizeof(req_u.req);
+ if (optlen < sizeof(req_u.req))
+ break;
+ ret = copy_from_sockptr(&req_u.req, optval,
+ sizeof(req_u.req)) ?
+ -EINVAL : 0;
break;
case TPACKET_V3:
default:
- len = sizeof(req_u.req3);
+ if (optlen < sizeof(req_u.req3))
+ break;
+ ret = copy_from_sockptr(&req_u.req3, optval,
+ sizeof(req_u.req3)) ?
+ -EINVAL : 0;
break;
}
- if (optlen < len) {
- ret = -EINVAL;
- } else {
- if (copy_from_sockptr(&req_u.req, optval, len))
- ret = -EFAULT;
- else
- ret = packet_set_ring(sk, &req_u, 0,
- optname == PACKET_TX_RING);
- }
+ if (!ret)
+ ret = packet_set_ring(sk, &req_u, 0,
+ optname == PACKET_TX_RING);
release_sock(sk);
return ret;
}
@@ -4165,9 +4234,11 @@ 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) {
@@ -4176,7 +4247,8 @@ 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:
@@ -4209,6 +4281,13 @@ 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;
}
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 (git 2.34.1) at 2025-07-12 09:53:56 +0000