And here's the patch to convert IPoIB over to using NAPI...
---
Convert the IP-over-InfiniBand network device driver over to using
NAPI to handle all completions (both receive and send).
Signed-off-by: Roland Dreier <[EMAIL PROTECTED]>
---
drivers/infiniband/ulp/ipoib/ipoib.h | 1 +
drivers/infiniband/ulp/ipoib/ipoib_cm.c | 2 +-
drivers/infiniband/ulp/ipoib/ipoib_ib.c | 89 ++++++++++++++++++++++------
drivers/infiniband/ulp/ipoib/ipoib_main.c | 2 +
4 files changed, 74 insertions(+), 20 deletions(-)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h
b/drivers/infiniband/ulp/ipoib/ipoib.h
index fd55826..15867af 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -311,6 +311,7 @@ extern struct workqueue_struct *ipoib_workqueue;
/* functions */
+int ipoib_poll(struct net_device *dev, int *budget);
void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr);
struct ipoib_ah *ipoib_create_ah(struct net_device *dev,
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 2b242a4..e1fdae1 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -418,7 +418,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct
ib_wc *wc)
skb->dev = dev;
/* XXX get correct PACKET_ type here */
skb->pkt_type = PACKET_HOST;
- netif_rx_ni(skb);
+ netif_receive_skb(skb);
repost:
if (unlikely(ipoib_cm_post_receive(dev, wr_id)))
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index ba0ee5c..e3cc241 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -226,7 +226,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev,
struct ib_wc *wc)
skb->dev = dev;
/* XXX get correct PACKET_ type here */
skb->pkt_type = PACKET_HOST;
- netif_rx_ni(skb);
+ netif_receive_skb(skb);
} else {
ipoib_dbg_data(priv, "dropping loopback packet\n");
dev_kfree_skb_any(skb);
@@ -280,28 +280,65 @@ static void ipoib_ib_handle_tx_wc(struct net_device *dev,
struct ib_wc *wc)
wc->status, wr_id, wc->vendor_err);
}
-static void ipoib_ib_handle_wc(struct net_device *dev, struct ib_wc *wc)
+int ipoib_poll(struct net_device *dev, int *budget)
{
- if (wc->wr_id & IPOIB_CM_OP_SRQ)
- ipoib_cm_handle_rx_wc(dev, wc);
- else if (wc->wr_id & IPOIB_OP_RECV)
- ipoib_ib_handle_rx_wc(dev, wc);
- else
- ipoib_ib_handle_tx_wc(dev, wc);
+ struct ipoib_dev_priv *priv = netdev_priv(dev);
+ int max = min(*budget, dev->quota);
+ int done;
+ int t;
+ int empty;
+ int n, i;
+
+repoll:
+ done = 0;
+ empty = 0;
+
+ while (max) {
+ t = min(IPOIB_NUM_WC, max);
+ n = ib_poll_cq(priv->cq, t, priv->ibwc);
+
+ for (i = 0; i < n; ++i) {
+ struct ib_wc *wc = priv->ibwc + i;
+
+ if (wc->wr_id & IPOIB_CM_OP_SRQ) {
+ ++done;
+ --max;
+ ipoib_cm_handle_rx_wc(dev, wc);
+ } else if (wc->wr_id & IPOIB_OP_RECV) {
+ ++done;
+ --max;
+ ipoib_ib_handle_rx_wc(dev, wc);
+ } else
+ ipoib_ib_handle_tx_wc(dev, wc);
+ }
+
+ if (n != t) {
+ empty = 1;
+ break;
+ }
+ }
+
+ dev->quota -= done;
+ *budget -= done;
+
+ if (empty) {
+ netif_rx_complete(dev);
+ if (unlikely(ib_req_notify_cq(priv->cq,
+ IB_CQ_NEXT_COMP |
+ IB_CQ_REPORT_MISSED_EVENTS))) {
+ netif_rx_reschedule(dev, 0);
+ return 1;
+ }
+
+ return 0;
+ }
+
+ return 1;
}
void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr)
{
- struct net_device *dev = (struct net_device *) dev_ptr;
- struct ipoib_dev_priv *priv = netdev_priv(dev);
- int n, i;
-
- ib_req_notify_cq(cq, IB_CQ_NEXT_COMP);
- do {
- n = ib_poll_cq(cq, IPOIB_NUM_WC, priv->ibwc);
- for (i = 0; i < n; ++i)
- ipoib_ib_handle_wc(dev, priv->ibwc + i);
- } while (n == IPOIB_NUM_WC);
+ netif_rx_schedule(dev_ptr);
}
static inline int post_send(struct ipoib_dev_priv *priv,
@@ -514,9 +551,10 @@ int ipoib_ib_dev_stop(struct net_device *dev)
struct ib_qp_attr qp_attr;
unsigned long begin;
struct ipoib_tx_buf *tx_req;
- int i;
+ int i, n;
clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);
+ netif_poll_disable(dev);
ipoib_cm_dev_stop(dev);
@@ -568,6 +606,16 @@ int ipoib_ib_dev_stop(struct net_device *dev)
goto timeout;
}
+ do {
+ n = ib_poll_cq(priv->cq, IPOIB_NUM_WC, priv->ibwc);
+ for (i = 0; i < n; ++i) {
+ 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);
+ }
+ } while (n == IPOIB_NUM_WC);
+
msleep(1);
}
@@ -596,6 +644,9 @@ timeout:
msleep(1);
}
+ netif_poll_enable(dev);
+ ib_req_notify_cq(priv->cq, IB_CQ_NEXT_COMP);
+
return 0;
}
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c
b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index f2a40ae..a69c472 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -952,6 +952,8 @@ static void ipoib_setup(struct net_device *dev)
dev->hard_header = ipoib_hard_header;
dev->set_multicast_list = ipoib_set_mcast_list;
dev->neigh_setup = ipoib_neigh_setup_dev;
+ dev->poll = ipoib_poll;
+ dev->weight = 100;
dev->watchdog_timeo = HZ;
--
1.5.1.2
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
