#include <linux/dma-mapping.h>
#include <rdma/ib_cache.h>
+#include <linux/ip.h>
+#include <linux/tcp.h>
#include "ipoib.h"
skb->dev = dev;
/* XXX get correct PACKET_ type here */
skb->pkt_type = PACKET_HOST;
+
+ if (test_bit(IPOIB_FLAG_CSUM, &priv->flags) && likely(wc->csum_ok))
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
netif_receive_skb(skb);
repost:
"for buf %d\n", wr_id);
}
+static int ipoib_dma_map_tx(struct ib_device *ca,
+ struct ipoib_tx_buf *tx_req)
+{
+ struct sk_buff *skb = tx_req->skb;
+ u64 *mapping = tx_req->mapping;
+ int i;
+ int off;
+
+ if (skb_headlen(skb)) {
+ mapping[0] = ib_dma_map_single(ca, skb->data, skb_headlen(skb),
+ DMA_TO_DEVICE);
+ if (unlikely(ib_dma_mapping_error(ca, mapping[0])))
+ return -EIO;
+
+ off = 1;
+ } else
+ off = 0;
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; ++i) {
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+ mapping[i + off] = ib_dma_map_page(ca, frag->page,
+ frag->page_offset, frag->size,
+ DMA_TO_DEVICE);
+ if (unlikely(ib_dma_mapping_error(ca, mapping[i + off])))
+ goto partial_error;
+ }
+ return 0;
+
+partial_error:
+ for (; i > 0; --i) {
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];
+ ib_dma_unmap_page(ca, mapping[i - !off], frag->size, DMA_TO_DEVICE);
+ }
+
+ if (off)
+ ib_dma_unmap_single(ca, mapping[0], skb_headlen(skb), DMA_TO_DEVICE);
+
+ return -EIO;
+}
+
+static void ipoib_dma_unmap_tx(struct ib_device *ca,
+ struct ipoib_tx_buf *tx_req)
+{
+ struct sk_buff *skb = tx_req->skb;
+ u64 *mapping = tx_req->mapping;
+ int i;
+ int off;
+
+ if (skb_headlen(skb)) {
+ ib_dma_unmap_single(ca, mapping[0], skb_headlen(skb), DMA_TO_DEVICE);
+ off = 1;
+ } else
+ off = 0;
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; ++i) {
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+ ib_dma_unmap_page(ca, mapping[i + off], frag->size,
+ DMA_TO_DEVICE);
+ }
+}
+
static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
tx_req = &priv->tx_ring[wr_id];
- ib_dma_unmap_single(priv->ca, tx_req->mapping,
- tx_req->skb->len, DMA_TO_DEVICE);
+ ipoib_dma_unmap_tx(priv->ca, tx_req);
++dev->stats.tx_packets;
dev->stats.tx_bytes += tx_req->skb->len;
spin_lock_irqsave(&priv->tx_lock, flags);
++priv->tx_tail;
- if (unlikely(test_bit(IPOIB_FLAG_NETIF_STOPPED, &priv->flags)) &&
- priv->tx_head - priv->tx_tail <= ipoib_sendq_size >> 1) {
- clear_bit(IPOIB_FLAG_NETIF_STOPPED, &priv->flags);
+ if (unlikely(--priv->tx_outstanding == ipoib_sendq_size >> 1) &&
+ netif_queue_stopped(dev) &&
+ test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
netif_wake_queue(dev);
- }
spin_unlock_irqrestore(&priv->tx_lock, flags);
if (wc->status != IB_WC_SUCCESS &&
for (i = 0; i < n; i++) {
struct ib_wc *wc = priv->ibwc + i;
- if (wc->wr_id & IPOIB_CM_OP_SRQ) {
- ++done;
- ipoib_cm_handle_rx_wc(dev, wc);
- } else if (wc->wr_id & IPOIB_OP_RECV) {
+ if (wc->wr_id & IPOIB_OP_RECV) {
++done;
- ipoib_ib_handle_rx_wc(dev, wc);
- } else
- ipoib_ib_handle_tx_wc(dev, wc);
+ if (wc->wr_id & IPOIB_OP_CM)
+ ipoib_cm_handle_rx_wc(dev, wc);
+ else
+ ipoib_ib_handle_rx_wc(dev, wc);
+ } else {
+ if (wc->wr_id & IPOIB_OP_CM)
+ ipoib_cm_handle_tx_wc(dev, wc);
+ else
+ ipoib_ib_handle_tx_wc(dev, wc);
+ }
}
if (n != t)
static inline int post_send(struct ipoib_dev_priv *priv,
unsigned int wr_id,
struct ib_ah *address, u32 qpn,
- u64 addr, int len)
+ struct ipoib_tx_buf *tx_req,
+ void *head, int hlen)
{
struct ib_send_wr *bad_wr;
+ int i, off;
+ struct sk_buff *skb = tx_req->skb;
+ skb_frag_t *frags = skb_shinfo(skb)->frags;
+ int nr_frags = skb_shinfo(skb)->nr_frags;
+ u64 *mapping = tx_req->mapping;
+
+ if (skb_headlen(skb)) {
+ priv->tx_sge[0].addr = mapping[0];
+ priv->tx_sge[0].length = skb_headlen(skb);
+ off = 1;
+ } else
+ off = 0;
- priv->tx_sge.addr = addr;
- priv->tx_sge.length = len;
-
- priv->tx_wr.wr_id = wr_id;
- priv->tx_wr.wr.ud.remote_qpn = qpn;
- priv->tx_wr.wr.ud.ah = address;
+ for (i = 0; i < nr_frags; ++i) {
+ priv->tx_sge[i + off].addr = mapping[i + off];
+ priv->tx_sge[i + off].length = frags[i].size;
+ }
+ priv->tx_wr.num_sge = nr_frags + off;
+ priv->tx_wr.wr_id = wr_id;
+ priv->tx_wr.wr.ud.remote_qpn = qpn;
+ priv->tx_wr.wr.ud.ah = address;
+
+ if (head) {
+ priv->tx_wr.wr.ud.mss = skb_shinfo(skb)->gso_size;
+ priv->tx_wr.wr.ud.header = head;
+ priv->tx_wr.wr.ud.hlen = hlen;
+ priv->tx_wr.opcode = IB_WR_LSO;
+ } else
+ priv->tx_wr.opcode = IB_WR_SEND;
return ib_post_send(priv->qp, &priv->tx_wr, &bad_wr);
}
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_tx_buf *tx_req;
- u64 addr;
-
- if (unlikely(skb->len > priv->mcast_mtu + IPOIB_ENCAP_LEN)) {
- ipoib_warn(priv, "packet len %d (> %d) too long to send, dropping\n",
- skb->len, priv->mcast_mtu + IPOIB_ENCAP_LEN);
- ++dev->stats.tx_dropped;
- ++dev->stats.tx_errors;
- ipoib_cm_skb_too_long(dev, skb, priv->mcast_mtu);
- return;
+ int hlen;
+ void *phead;
+
+ if (skb_is_gso(skb)) {
+ hlen = skb_transport_offset(skb) + tcp_hdrlen(skb);
+ phead = skb->data;
+ if (unlikely(!skb_pull(skb, hlen))) {
+ ipoib_warn(priv, "linear data too small\n");
+ ++dev->stats.tx_dropped;
+ ++dev->stats.tx_errors;
+ dev_kfree_skb_any(skb);
+ return;
+ }
+ } else {
+ if (unlikely(skb->len > priv->mcast_mtu + IPOIB_ENCAP_LEN)) {
+ ipoib_warn(priv, "packet len %d (> %d) too long to send, dropping\n",
+ skb->len, priv->mcast_mtu + IPOIB_ENCAP_LEN);
+ ++dev->stats.tx_dropped;
+ ++dev->stats.tx_errors;
+ ipoib_cm_skb_too_long(dev, skb, priv->mcast_mtu);
+ return;
+ }
+ phead = NULL;
+ hlen = 0;
}
ipoib_dbg_data(priv, "sending packet, length=%d address=%p qpn=0x%06x\n",
*/
tx_req = &priv->tx_ring[priv->tx_head & (ipoib_sendq_size - 1)];
tx_req->skb = skb;
- addr = ib_dma_map_single(priv->ca, skb->data, skb->len,
- DMA_TO_DEVICE);
- if (unlikely(ib_dma_mapping_error(priv->ca, addr))) {
+ if (unlikely(ipoib_dma_map_tx(priv->ca, tx_req))) {
++dev->stats.tx_errors;
dev_kfree_skb_any(skb);
return;
}
- tx_req->mapping = addr;
+
+ if (skb->ip_summed == CHECKSUM_PARTIAL)
+ priv->tx_wr.send_flags |= IB_SEND_IP_CSUM;
+ else
+ priv->tx_wr.send_flags &= ~IB_SEND_IP_CSUM;
if (unlikely(post_send(priv, priv->tx_head & (ipoib_sendq_size - 1),
- address->ah, qpn, addr, skb->len))) {
+ address->ah, qpn, tx_req, phead, hlen))) {
ipoib_warn(priv, "post_send failed\n");
++dev->stats.tx_errors;
- ib_dma_unmap_single(priv->ca, addr, skb->len, DMA_TO_DEVICE);
+ ipoib_dma_unmap_tx(priv->ca, tx_req);
dev_kfree_skb_any(skb);
} else {
dev->trans_start = jiffies;
address->last_send = priv->tx_head;
++priv->tx_head;
- if (priv->tx_head - priv->tx_tail == ipoib_sendq_size) {
+ if (++priv->tx_outstanding == ipoib_sendq_size) {
ipoib_dbg(priv, "TX ring full, stopping kernel net queue\n");
netif_stop_queue(dev);
- set_bit(IPOIB_FLAG_NETIF_STOPPED, &priv->flags);
}
}
}
__ipoib_reap_ah(dev);
if (!test_bit(IPOIB_STOP_REAPER, &priv->flags))
- queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task, HZ);
+ queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task,
+ round_jiffies_relative(HZ));
}
int ipoib_ib_dev_open(struct net_device *dev)
}
clear_bit(IPOIB_STOP_REAPER, &priv->flags);
- queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task, HZ);
+ queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task,
+ round_jiffies_relative(HZ));
set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);
struct ipoib_dev_priv *priv = netdev_priv(dev);
u16 pkey_index = 0;
- if (ib_find_cached_pkey(priv->ca, priv->port, priv->pkey, &pkey_index))
+ if (ib_find_pkey(priv->ca, priv->port, priv->pkey, &pkey_index))
clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
else
set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
if (priv->ibwc[i].status == IB_WC_SUCCESS)
priv->ibwc[i].status = IB_WC_WR_FLUSH_ERR;
- if (priv->ibwc[i].wr_id & IPOIB_CM_OP_SRQ)
- ipoib_cm_handle_rx_wc(dev, priv->ibwc + i);
- else if (priv->ibwc[i].wr_id & IPOIB_OP_RECV)
- ipoib_ib_handle_rx_wc(dev, priv->ibwc + i);
- else
- ipoib_ib_handle_tx_wc(dev, priv->ibwc + i);
+ if (priv->ibwc[i].wr_id & IPOIB_OP_RECV) {
+ if (priv->ibwc[i].wr_id & IPOIB_OP_CM)
+ ipoib_cm_handle_rx_wc(dev, priv->ibwc + i);
+ else
+ ipoib_ib_handle_rx_wc(dev, priv->ibwc + i);
+ } else {
+ if (priv->ibwc[i].wr_id & IPOIB_OP_CM)
+ ipoib_cm_handle_tx_wc(dev, priv->ibwc + i);
+ else
+ ipoib_ib_handle_tx_wc(dev, priv->ibwc + i);
+ }
}
} while (n == IPOIB_NUM_WC);
}
while ((int) priv->tx_tail - (int) priv->tx_head < 0) {
tx_req = &priv->tx_ring[priv->tx_tail &
(ipoib_sendq_size - 1)];
- ib_dma_unmap_single(priv->ca,
- tx_req->mapping,
- tx_req->skb->len,
- DMA_TO_DEVICE);
+ ipoib_dma_unmap_tx(priv->ca, tx_req);
dev_kfree_skb_any(tx_req->skb);
++priv->tx_tail;
+ --priv->tx_outstanding;
}
for (i = 0; i < ipoib_recvq_size; ++i) {
if (ib_find_pkey(priv->ca, priv->port, priv->pkey, &new_index)) {
clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
ipoib_ib_dev_down(dev, 0);
- ipoib_pkey_dev_delay_open(dev);
- return;
+ ipoib_ib_dev_stop(dev, 0);
+ if (ipoib_pkey_dev_delay_open(dev))
+ return;
}
- set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
/* restart QP only if P_Key index is changed */
- if (new_index == priv->pkey_index) {
+ if (test_and_set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags) &&
+ new_index == priv->pkey_index) {
ipoib_dbg(priv, "Not flushing - P_Key index not changed.\n");
return;
}