[NET]: Make NAPI polling independent of struct net_device objects.
Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c
index 556962f..a30146e 100644
--- a/drivers/net/myri10ge/myri10ge.c
+++ b/drivers/net/myri10ge/myri10ge.c
@@ -163,6 +163,7 @@
int small_bytes;
int big_bytes;
struct net_device *dev;
+ struct napi_struct napi;
struct net_device_stats stats;
u8 __iomem *sram;
int sram_size;
@@ -1100,7 +1101,7 @@
}
}
-static inline void myri10ge_clean_rx_done(struct myri10ge_priv *mgp, int *limit)
+static inline int myri10ge_clean_rx_done(struct myri10ge_priv *mgp, int budget)
{
struct myri10ge_rx_done *rx_done = &mgp->rx_done;
unsigned long rx_bytes = 0;
@@ -1109,10 +1110,11 @@
int idx = rx_done->idx;
int cnt = rx_done->cnt;
+ int work_done = 0;
u16 length;
__wsum checksum;
- while (rx_done->entry[idx].length != 0 && *limit != 0) {
+ while (rx_done->entry[idx].length != 0 && work_done++ < budget) {
length = ntohs(rx_done->entry[idx].length);
rx_done->entry[idx].length = 0;
checksum = csum_unfold(rx_done->entry[idx].checksum);
@@ -1128,10 +1130,6 @@
rx_bytes += rx_ok * (unsigned long)length;
cnt++;
idx = cnt & (myri10ge_max_intr_slots - 1);
-
- /* limit potential for livelock by only handling a
- * limited number of frames. */
- (*limit)--;
}
rx_done->idx = idx;
rx_done->cnt = cnt;
@@ -1145,6 +1143,7 @@
if (mgp->rx_big.fill_cnt - mgp->rx_big.cnt < myri10ge_fill_thresh)
myri10ge_alloc_rx_pages(mgp, &mgp->rx_big, mgp->big_bytes, 0);
+ return work_done;
}
static inline void myri10ge_check_statblock(struct myri10ge_priv *mgp)
@@ -1189,26 +1188,21 @@
}
}
-static int myri10ge_poll(struct net_device *netdev, int *budget)
+static int myri10ge_poll(struct napi_struct *napi, int budget)
{
- struct myri10ge_priv *mgp = netdev_priv(netdev);
+ struct myri10ge_priv *mgp = container_of(napi, struct myri10ge_priv, napi);
+ struct net_device *netdev = mgp->dev;
struct myri10ge_rx_done *rx_done = &mgp->rx_done;
- int limit, orig_limit, work_done;
+ int work_done;
/* process as many rx events as NAPI will allow */
- limit = min(*budget, netdev->quota);
- orig_limit = limit;
- myri10ge_clean_rx_done(mgp, &limit);
- work_done = orig_limit - limit;
- *budget -= work_done;
- netdev->quota -= work_done;
+ work_done = myri10ge_clean_rx_done(mgp, budget);
if (rx_done->entry[rx_done->idx].length == 0 || !netif_running(netdev)) {
- netif_rx_complete(netdev);
+ netif_rx_complete(netdev, napi);
put_be32(htonl(3), mgp->irq_claim);
- return 0;
}
- return 1;
+ return work_done;
}
static irqreturn_t myri10ge_intr(int irq, void *arg)
@@ -1226,7 +1220,7 @@
/* low bit indicates receives are present, so schedule
* napi poll handler */
if (stats->valid & 1)
- netif_rx_schedule(mgp->dev);
+ netif_rx_schedule(mgp->dev, &mgp->napi);
if (!mgp->msi_enabled) {
put_be32(0, mgp->irq_deassert);
@@ -1853,7 +1847,7 @@
mgp->link_state = htonl(~0U);
mgp->rdma_tags_available = 15;
- netif_poll_enable(mgp->dev); /* must happen prior to any irq */
+ napi_enable(&mgp->napi); /* must happen prior to any irq */
status = myri10ge_send_cmd(mgp, MXGEFW_CMD_ETHERNET_UP, &cmd, 0);
if (status) {
@@ -1897,7 +1891,7 @@
del_timer_sync(&mgp->watchdog_timer);
mgp->running = MYRI10GE_ETH_STOPPING;
- netif_poll_disable(mgp->dev);
+ napi_disable(&mgp->napi);
netif_carrier_off(dev);
netif_stop_queue(dev);
old_down_cnt = mgp->down_cnt;
@@ -2857,6 +2851,8 @@
mgp = netdev_priv(netdev);
memset(mgp, 0, sizeof(*mgp));
mgp->dev = netdev;
+ netif_napi_add(netdev, &mgp->napi,
+ myri10ge_poll, myri10ge_napi_weight);
mgp->pdev = pdev;
mgp->csum_flag = MXGEFW_FLAGS_CKSUM;
mgp->pause = myri10ge_flow_control;
@@ -2981,8 +2977,6 @@
netdev->features = NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_TSO;
if (dac_enabled)
netdev->features |= NETIF_F_HIGHDMA;
- netdev->poll = myri10ge_poll;
- netdev->weight = myri10ge_napi_weight;
/* make sure we can get an irq, and that MSI can be
* setup (if available). Also ensure netdev->irq
