static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
struct net_device *netdev)
{
struct ibmveth_adapter *adapter = netdev_priv(netdev);
unsigned int desc_flags;
union ibmveth_buf_desc descs[6];
int last, i;
int force_bounce = 0;
dma_addr_t dma_addr;
/*
* veth handles a maximum of 6 segments including the header, so
* we have to linearize the skb if there are more than this.
*/
if (skb_shinfo(skb)->nr_frags > 5 && __skb_linearize(skb)) {
netdev->stats.tx_dropped++;
goto out;
}
/* veth can't checksum offload UDP */
if (skb->ip_summed == CHECKSUM_PARTIAL &&
((skb->protocol == htons(ETH_P_IP) &&
ip_hdr(skb)->protocol != IPPROTO_TCP) ||
(skb->protocol == htons(ETH_P_IPV6) &&
ipv6_hdr(skb)->nexthdr != IPPROTO_TCP)) &&
skb_checksum_help(skb)) {
netdev_err(netdev, "tx: failed to checksum packet\n");
netdev->stats.tx_dropped++;
goto out;
}
desc_flags = IBMVETH_BUF_VALID;
if (skb->ip_summed == CHECKSUM_PARTIAL) {
unsigned char *buf = skb_transport_header(skb) +
skb->csum_offset;
desc_flags |= (IBMVETH_BUF_NO_CSUM | IBMVETH_BUF_CSUM_GOOD);
/* Need to zero out the checksum */
buf[0] = 0;
buf[1] = 0;
}
retry_bounce:
memset(descs, 0, sizeof(descs));
/*
* If a linear packet is below the rx threshold then
* copy it into the static bounce buffer. This avoids the
* cost of a TCE insert and remove.
*/
if (force_bounce || (!skb_is_nonlinear(skb) &&
(skb->len < tx_copybreak))) {
skb_copy_from_linear_data(skb, adapter->bounce_buffer,
skb->len);
descs[0].fields.flags_len = desc_flags | skb->len;
descs[0].fields.address = adapter->bounce_buffer_dma;
if (ibmveth_send(adapter, descs)) {
adapter->tx_send_failed++;
netdev->stats.tx_dropped++;
} else {
netdev->stats.tx_packets++;
netdev->stats.tx_bytes += skb->len;
}
goto out;
}
/* Map the header */
dma_addr = dma_map_single(&adapter->vdev->dev, skb->data,
skb_headlen(skb), DMA_TO_DEVICE);
if (dma_mapping_error(&adapter->vdev->dev, dma_addr))
goto map_failed;
descs[0].fields.flags_len = desc_flags | skb_headlen(skb);
descs[0].fields.address = dma_addr;
/* Map the frags */
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
dma_addr = dma_map_page(&adapter->vdev->dev, frag->page,
frag->page_offset, frag->size,
DMA_TO_DEVICE);
if (dma_mapping_error(&adapter->vdev->dev, dma_addr))
goto map_failed_frags;
descs[i+1].fields.flags_len = desc_flags | frag->size;
descs[i+1].fields.address = dma_addr;
}
if (ibmveth_send(adapter, descs)) {
adapter->tx_send_failed++;
netdev->stats.tx_dropped++;
} else {
netdev->stats.tx_packets++;
netdev->stats.tx_bytes += skb->len;
}
dma_unmap_single(&adapter->vdev->dev,
descs[0].fields.address,
descs[0].fields.flags_len & IBMVETH_BUF_LEN_MASK,
DMA_TO_DEVICE);
for (i = 1; i < skb_shinfo(skb)->nr_frags + 1; i++)
dma_unmap_page(&adapter->vdev->dev, descs[i].fields.address,
descs[i].fields.flags_len & IBMVETH_BUF_LEN_MASK,
DMA_TO_DEVICE);
out:
dev_kfree_skb(skb);
return NETDEV_TX_OK;
map_failed_frags:
last = i+1;
for (i = 0; i < last; i++)
dma_unmap_page(&adapter->vdev->dev, descs[i].fields.address,
descs[i].fields.flags_len & IBMVETH_BUF_LEN_MASK,
DMA_TO_DEVICE);
map_failed:
if (!firmware_has_feature(FW_FEATURE_CMO))
netdev_err(netdev, "tx: unable to map xmit buffer\n");
adapter->tx_map_failed++;
skb_linearize(skb);
force_bounce = 1;
goto retry_bounce;
}
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;
}
int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
struct iwl_device_cmd *dev_cmd, int txq_id)
{
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
struct iwl_cmd_meta *out_meta;
struct iwl_txq *txq = trans_pcie->txq[txq_id];
u16 cmd_len;
int idx;
void *tfd;
if (WARN_ONCE(!test_bit(txq_id, trans_pcie->queue_used),
"TX on unused queue %d\n", txq_id))
return -EINVAL;
if (skb_is_nonlinear(skb) &&
skb_shinfo(skb)->nr_frags > IWL_PCIE_MAX_FRAGS(trans_pcie) &&
__skb_linearize(skb))
return -ENOMEM;
spin_lock(&txq->lock);
if (iwl_queue_space(trans, txq) < txq->high_mark) {
iwl_stop_queue(trans, txq);
/* don't put the packet on the ring, if there is no room */
if (unlikely(iwl_queue_space(trans, txq) < 3)) {
struct iwl_device_cmd **dev_cmd_ptr;
dev_cmd_ptr = (void *)((u8 *)skb->cb +
trans_pcie->dev_cmd_offs);
*dev_cmd_ptr = dev_cmd;
__skb_queue_tail(&txq->overflow_q, skb);
spin_unlock(&txq->lock);
return 0;
}
}
idx = iwl_pcie_get_cmd_index(txq, txq->write_ptr);
/* Set up driver data for this TFD */
txq->entries[idx].skb = skb;
txq->entries[idx].cmd = dev_cmd;
dev_cmd->hdr.sequence =
cpu_to_le16((u16)(QUEUE_TO_SEQ(txq_id) |
INDEX_TO_SEQ(idx)));
/* Set up first empty entry in queue's array of Tx/cmd buffers */
out_meta = &txq->entries[idx].meta;
out_meta->flags = 0;
tfd = iwl_pcie_gen2_build_tfd(trans, txq, dev_cmd, skb, out_meta);
if (!tfd) {
spin_unlock(&txq->lock);
return -1;
}
if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
struct iwl_tx_cmd_gen3 *tx_cmd_gen3 =
(void *)dev_cmd->payload;
cmd_len = le16_to_cpu(tx_cmd_gen3->len);
} else {
struct iwl_tx_cmd_gen2 *tx_cmd_gen2 =
(void *)dev_cmd->payload;
cmd_len = le16_to_cpu(tx_cmd_gen2->len);
}
/* Set up entry for this TFD in Tx byte-count array */
iwl_pcie_gen2_update_byte_tbl(trans_pcie, txq, cmd_len,
iwl_pcie_gen2_get_num_tbs(trans, tfd));
/* start timer if queue currently empty */
if (txq->read_ptr == txq->write_ptr) {
if (txq->wd_timeout)
mod_timer(&txq->stuck_timer, jiffies + txq->wd_timeout);
IWL_DEBUG_RPM(trans, "Q: %d first tx - take ref\n", txq->id);
iwl_trans_ref(trans);
}
/* Tell device the write index *just past* this latest filled TFD */
txq->write_ptr = iwl_queue_inc_wrap(trans, txq->write_ptr);
iwl_pcie_gen2_txq_inc_wr_ptr(trans, txq);
/*
* At this point the frame is "transmitted" successfully
* and we will get a TX status notification eventually.
*/
spin_unlock(&txq->lock);
return 0;
}
