/* GSO packet is too big, segment it so that tbf can transmit
* each segment in time
*/
static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
{
struct tbf_sched_data *q = qdisc_priv(sch);
struct sk_buff *segs, *nskb;
netdev_features_t features = netif_skb_features(skb);
int ret, nb;
segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
if (IS_ERR_OR_NULL(segs))
return qdisc_reshape_fail(skb, sch);
nb = 0;
while (segs) {
nskb = segs->next;
segs->next = NULL;
qdisc_skb_cb(segs)->pkt_len = segs->len;
ret = qdisc_enqueue(segs, q->qdisc);
if (ret != NET_XMIT_SUCCESS) {
if (net_xmit_drop_count(ret))
sch->qstats.drops++;
} else {
nb++;
}
segs = nskb;
}
sch->q.qlen += nb;
if (nb > 1)
qdisc_tree_decrease_qlen(sch, 1 - nb);
consume_skb(skb);
return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
}
/* GSO packet is too big, segment it so that tbf can transmit
* each segment in time
*/
static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
{
struct tbf_sched_data *q = qdisc_priv(sch);
struct sk_buff *segs, *nskb;
netdev_features_t features = netif_skb_features(skb);
unsigned int len = 0, prev_len = qdisc_pkt_len(skb);
int ret, nb;
segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
if (IS_ERR_OR_NULL(segs))
return qdisc_drop(skb, sch, to_free);
nb = 0;
while (segs) {
nskb = segs->next;
skb_mark_not_on_list(segs);
qdisc_skb_cb(segs)->pkt_len = segs->len;
len += segs->len;
ret = qdisc_enqueue(segs, q->qdisc, to_free);
if (ret != NET_XMIT_SUCCESS) {
if (net_xmit_drop_count(ret))
qdisc_qstats_drop(sch);
} else {
nb++;
}
segs = nskb;
}
sch->q.qlen += nb;
if (nb > 1)
qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len);
consume_skb(skb);
return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
}
int rpl_dev_queue_xmit(struct sk_buff *skb)
{
#undef dev_queue_xmit
int err = -ENOMEM;
if (vlan_tx_tag_present(skb) && !dev_supports_vlan_tx(skb->dev)) {
int features;
features = netif_skb_features(skb);
if (!vlan_tso)
features &= ~(NETIF_F_TSO | NETIF_F_TSO6 |
NETIF_F_UFO | NETIF_F_FSO);
skb = __vlan_put_tag(skb, skb->vlan_proto, vlan_tx_tag_get(skb));
if (unlikely(!skb))
return err;
vlan_set_tci(skb, 0);
if (netif_needs_gso(skb, features)) {
struct sk_buff *nskb;
nskb = skb_gso_segment(skb, features);
if (!nskb) {
if (unlikely(skb_cloned(skb) &&
pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
goto drop;
skb_shinfo(skb)->gso_type &= ~SKB_GSO_DODGY;
goto xmit;
}
if (IS_ERR(nskb)) {
err = PTR_ERR(nskb);
goto drop;
}
consume_skb(skb);
skb = nskb;
do {
nskb = skb->next;
skb->next = NULL;
err = dev_queue_xmit(skb);
skb = nskb;
} while (skb);
return err;
}
}
xmit:
return dev_queue_xmit(skb);
drop:
kfree_skb(skb);
return err;
}
static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
netdev_features_t mpls_features;
__be16 mpls_protocol;
if (unlikely(skb_shinfo(skb)->gso_type &
~(SKB_GSO_TCPV4 |
SKB_GSO_TCPV6 |
SKB_GSO_UDP |
SKB_GSO_DODGY |
SKB_GSO_TCP_ECN |
SKB_GSO_GRE |
SKB_GSO_GRE_CSUM |
SKB_GSO_IPIP |
SKB_GSO_MPLS)))
goto out;
/* Setup inner SKB. */
mpls_protocol = skb->protocol;
skb->protocol = skb->inner_protocol;
/* Push back the mac header that skb_mac_gso_segment() has pulled.
* It will be re-pulled by the call to skb_mac_gso_segment() below
*/
__skb_push(skb, skb->mac_len);
/* Segment inner packet. */
mpls_features = skb->dev->mpls_features & netif_skb_features(skb);
segs = skb_mac_gso_segment(skb, mpls_features);
/* Restore outer protocol. */
skb->protocol = mpls_protocol;
/* Re-pull the mac header that the call to skb_mac_gso_segment()
* above pulled. It will be re-pushed after returning
* skb_mac_gso_segment(), an indirect caller of this function.
*/
__skb_push(skb, skb->data - skb_mac_header(skb));
out:
return segs;
}
static int netdev_send(struct vport *vport, struct sk_buff *skb)
{
struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
int mtu = netdev_vport->dev->mtu;
int len;
if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) {
if (net_ratelimit())
pr_warn("%s: dropped over-mtu packet: %d > %d\n",
ovs_dp_name(vport->dp), packet_length(skb), mtu);
goto error;
}
if (unlikely(skb_warn_if_lro(skb)))
goto error;
skb->dev = netdev_vport->dev;
forward_ip_summed(skb, true);
if (vlan_tx_tag_present(skb) && !dev_supports_vlan_tx(skb->dev)) {
int features;
features = netif_skb_features(skb);
if (!vlan_tso)
features &= ~(NETIF_F_TSO | NETIF_F_TSO6 |
NETIF_F_UFO | NETIF_F_FSO);
if (netif_needs_gso(skb, features)) {
struct sk_buff *nskb;
nskb = skb_gso_segment(skb, features);
if (!nskb) {
if (unlikely(skb_cloned(skb) &&
pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) {
kfree_skb(skb);
return 0;
}
skb_shinfo(skb)->gso_type &= ~SKB_GSO_DODGY;
goto tag;
}
if (IS_ERR(nskb)) {
kfree_skb(skb);
return 0;
}
consume_skb(skb);
skb = nskb;
len = 0;
do {
nskb = skb->next;
skb->next = NULL;
skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb));
if (likely(skb)) {
len += skb->len;
vlan_set_tci(skb, 0);
dev_queue_xmit(skb);
}
skb = nskb;
} while (skb);
return len;
}
tag:
skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb));
if (unlikely(!skb))
return 0;
vlan_set_tci(skb, 0);
}
len = skb->len;
dev_queue_xmit(skb);
return len;
error:
kfree_skb(skb);
ovs_vport_record_error(vport, VPORT_E_TX_DROPPED);
return 0;
}
static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
netdev_features_t enc_features;
int ghl = GRE_HEADER_SECTION;
struct gre_base_hdr *greh;
u16 mac_offset = skb->mac_header;
int mac_len = skb->mac_len;
__be16 protocol = skb->protocol;
int tnl_hlen;
bool csum;
if (unlikely(skb_shinfo(skb)->gso_type &
~(SKB_GSO_TCPV4 |
SKB_GSO_TCPV6 |
SKB_GSO_UDP |
SKB_GSO_DODGY |
SKB_GSO_TCP_ECN |
SKB_GSO_GRE |
SKB_GSO_IPIP)))
goto out;
if (unlikely(!pskb_may_pull(skb, sizeof(*greh))))
goto out;
greh = (struct gre_base_hdr *)skb_transport_header(skb);
if (greh->flags & GRE_KEY)
ghl += GRE_HEADER_SECTION;
if (greh->flags & GRE_SEQ)
ghl += GRE_HEADER_SECTION;
if (greh->flags & GRE_CSUM) {
ghl += GRE_HEADER_SECTION;
csum = true;
} else
csum = false;
if (unlikely(!pskb_may_pull(skb, ghl)))
goto out;
/* setup inner skb. */
skb->protocol = greh->protocol;
skb->encapsulation = 0;
__skb_pull(skb, ghl);
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb_inner_network_offset(skb));
skb->mac_len = skb_inner_network_offset(skb);
/* segment inner packet. */
enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
segs = skb_mac_gso_segment(skb, enc_features);
if (!segs || IS_ERR(segs)) {
skb_gso_error_unwind(skb, protocol, ghl, mac_offset, mac_len);
goto out;
}
skb = segs;
tnl_hlen = skb_tnl_header_len(skb);
do {
__skb_push(skb, ghl);
if (csum) {
__be32 *pcsum;
if (skb_has_shared_frag(skb)) {
int err;
err = __skb_linearize(skb);
if (err) {
kfree_skb_list(segs);
segs = ERR_PTR(err);
goto out;
}
}
greh = (struct gre_base_hdr *)(skb->data);
pcsum = (__be32 *)(greh + 1);
*pcsum = 0;
*(__sum16 *)pcsum = csum_fold(skb_checksum(skb, 0, skb->len, 0));
}
__skb_push(skb, tnl_hlen - ghl);
skb_reset_inner_headers(skb);
skb->encapsulation = 1;
skb_reset_mac_header(skb);
skb_set_network_header(skb, mac_len);
skb->mac_len = mac_len;
skb->protocol = protocol;
} while ((skb = skb->next));
out:
return segs;
}
static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
unsigned short id;
struct netfront_info *np = netdev_priv(dev);
struct netfront_stats *stats = this_cpu_ptr(np->stats);
struct xen_netif_tx_request *tx;
struct xen_netif_extra_info *extra;
char *data = skb->data;
RING_IDX i;
grant_ref_t ref;
unsigned long mfn;
int notify;
int slots;
unsigned int offset = offset_in_page(data);
unsigned int len = skb_headlen(skb);
unsigned long flags;
/* If skb->len is too big for wire format, drop skb and alert
* user about misconfiguration.
*/
if (unlikely(skb->len > XEN_NETIF_MAX_TX_SIZE)) {
net_alert_ratelimited(
"xennet: skb->len = %u, too big for wire format\n",
skb->len);
goto drop;
}
slots = DIV_ROUND_UP(offset + len, PAGE_SIZE) +
xennet_count_skb_frag_slots(skb);
if (unlikely(slots > MAX_SKB_FRAGS + 1)) {
net_alert_ratelimited(
"xennet: skb rides the rocket: %d slots\n", slots);
goto drop;
}
spin_lock_irqsave(&np->tx_lock, flags);
if (unlikely(!netif_carrier_ok(dev) ||
(slots > 1 && !xennet_can_sg(dev)) ||
netif_needs_gso(skb, netif_skb_features(skb)))) {
spin_unlock_irqrestore(&np->tx_lock, flags);
goto drop;
}
i = np->tx.req_prod_pvt;
id = get_id_from_freelist(&np->tx_skb_freelist, np->tx_skbs);
np->tx_skbs[id].skb = skb;
tx = RING_GET_REQUEST(&np->tx, i);
tx->id = id;
ref = gnttab_claim_grant_reference(&np->gref_tx_head);
BUG_ON((signed short)ref < 0);
mfn = virt_to_mfn(data);
gnttab_grant_foreign_access_ref(
ref, np->xbdev->otherend_id, mfn, GNTMAP_readonly);
tx->gref = np->grant_tx_ref[id] = ref;
tx->offset = offset;
tx->size = len;
extra = NULL;
tx->flags = 0;
if (skb->ip_summed == CHECKSUM_PARTIAL)
/* local packet? */
tx->flags |= XEN_NETTXF_csum_blank | XEN_NETTXF_data_validated;
else if (skb->ip_summed == CHECKSUM_UNNECESSARY)
/* remote but checksummed. */
tx->flags |= XEN_NETTXF_data_validated;
if (skb_shinfo(skb)->gso_size) {
struct xen_netif_extra_info *gso;
gso = (struct xen_netif_extra_info *)
RING_GET_REQUEST(&np->tx, ++i);
if (extra)
extra->flags |= XEN_NETIF_EXTRA_FLAG_MORE;
else
tx->flags |= XEN_NETTXF_extra_info;
gso->u.gso.size = skb_shinfo(skb)->gso_size;
gso->u.gso.type = XEN_NETIF_GSO_TYPE_TCPV4;
gso->u.gso.pad = 0;
gso->u.gso.features = 0;
gso->type = XEN_NETIF_EXTRA_TYPE_GSO;
gso->flags = 0;
extra = gso;
}
np->tx.req_prod_pvt = i + 1;
xennet_make_frags(skb, dev, tx);
tx->size = skb->len;
RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&np->tx, notify);
if (notify)
notify_remote_via_irq(np->netdev->irq);
u64_stats_update_begin(&stats->syncp);
stats->tx_bytes += skb->len;
stats->tx_packets++;
u64_stats_update_end(&stats->syncp);
/* Note: It is not safe to access skb after xennet_tx_buf_gc()! */
xennet_tx_buf_gc(dev);
if (!netfront_tx_slot_available(np))
netif_stop_queue(dev);
spin_unlock_irqrestore(&np->tx_lock, flags);
return NETDEV_TX_OK;
drop:
dev->stats.tx_dropped++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
int rpl_dev_queue_xmit(struct sk_buff *skb)
{
#undef dev_queue_xmit
int err = -ENOMEM;
bool mpls;
mpls = false;
/* Avoid traversing any VLAN tags that are present to determine if
* the ethtype is MPLS. Instead compare the mac_len (end of L2) and
* skb_network_offset() (beginning of L3) whose inequality will
* indicate the presence of an MPLS label stack. */
if (skb->mac_len != skb_network_offset(skb) && !supports_mpls_gso())
mpls = true;
if (mpls) {
int features;
features = netif_skb_features(skb);
/* As of v3.11 the kernel provides an mpls_features field in
* struct net_device which allows devices to advertise which
* features its supports for MPLS. This value defaults to
* NETIF_F_SG and as of v3.19.
*
* This compatibility code is intended for kernels older
* than v3.19 that do not support MPLS GSO and do not
* use mpls_features. Thus this code uses NETIF_F_SG
* directly in place of mpls_features.
*/
if (mpls)
features &= NETIF_F_SG;
if (netif_needs_gso(skb, features)) {
struct sk_buff *nskb;
nskb = skb_gso_segment(skb, features);
if (!nskb) {
if (unlikely(skb_cloned(skb) &&
pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
goto drop;
skb_shinfo(skb)->gso_type &= ~SKB_GSO_DODGY;
goto xmit;
}
if (IS_ERR(nskb)) {
err = PTR_ERR(nskb);
goto drop;
}
consume_skb(skb);
skb = nskb;
do {
nskb = skb->next;
skb->next = NULL;
err = dev_queue_xmit(skb);
skb = nskb;
} while (skb);
return err;
}
}
xmit:
return dev_queue_xmit(skb);
drop:
kfree_skb(skb);
return err;
}
static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
struct ipv6hdr *ipv6h;
const struct net_offload *ops;
int proto;
struct frag_hdr *fptr;
unsigned int unfrag_ip6hlen;
u8 *prevhdr;
int offset = 0;
bool encap, udpfrag;
int nhoff;
if (unlikely(skb_shinfo(skb)->gso_type &
~(SKB_GSO_UDP |
SKB_GSO_DODGY |
SKB_GSO_TCP_ECN |
SKB_GSO_GRE |
SKB_GSO_IPIP |
SKB_GSO_SIT |
SKB_GSO_UDP_TUNNEL |
SKB_GSO_MPLS |
SKB_GSO_TCPV6 |
0)))
goto out;
skb_reset_network_header(skb);
nhoff = skb_network_header(skb) - skb_mac_header(skb);
if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
goto out;
encap = SKB_GSO_CB(skb)->encap_level > 0;
if (encap)
features = skb->dev->hw_enc_features & netif_skb_features(skb);
SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h);
ipv6h = ipv6_hdr(skb);
__skb_pull(skb, sizeof(*ipv6h));
segs = ERR_PTR(-EPROTONOSUPPORT);
proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
if (skb->encapsulation &&
skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
udpfrag = proto == IPPROTO_UDP && encap;
else
udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
ops = rcu_dereference(inet6_offloads[proto]);
if (likely(ops && ops->callbacks.gso_segment)) {
skb_reset_transport_header(skb);
segs = ops->callbacks.gso_segment(skb, features);
}
if (IS_ERR(segs))
goto out;
for (skb = segs; skb; skb = skb->next) {
ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
ipv6h->payload_len = htons(skb->len - nhoff - sizeof(*ipv6h));
skb->network_header = (u8 *)ipv6h - skb->head;
if (udpfrag) {
unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen);
fptr->frag_off = htons(offset);
if (skb->next != NULL)
fptr->frag_off |= htons(IP6_MF);
offset += (ntohs(ipv6h->payload_len) -
sizeof(struct frag_hdr));
}
if (encap)
skb_reset_inner_headers(skb);
}
out:
return segs;
}
