[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>

1 files changed, 23 insertions, 31 deletions

diff --git a/drivers/net/tulip/interrupt.c b/drivers/net/tulip/interrupt.c
index 53efd6694e75..365331446387 100644
--- a/drivers/net/tulip/interrupt.c
+++ b/drivers/net/tulip/interrupt.c
@@ -103,28 +103,29 @@ int tulip_refill_rx(struct net_device *dev)
 void oom_timer(unsigned long data)
 {
         struct net_device *dev = (struct net_device *)data;
-	netif_rx_schedule(dev);
+	struct tulip_private *tp = netdev_priv(dev);
+	netif_rx_schedule(dev, &tp->napi);
 }
 
-int tulip_poll(struct net_device *dev, int *budget)
+int tulip_poll(struct napi_struct *napi, int budget)
 {
-	struct tulip_private *tp = netdev_priv(dev);
+	struct tulip_private *tp = container_of(napi, struct tulip_private, napi);
+	struct net_device *dev = tp->dev;
 	int entry = tp->cur_rx % RX_RING_SIZE;
-	int rx_work_limit = *budget;
+	int work_done = 0;
+#ifdef CONFIG_TULIP_NAPI_HW_MITIGATION
 	int received = 0;
+#endif
 
 	if (!netif_running(dev))
 		goto done;
 
-	if (rx_work_limit > dev->quota)
-		rx_work_limit = dev->quota;
-
 #ifdef CONFIG_TULIP_NAPI_HW_MITIGATION
 
 /* that one buffer is needed for mit activation; or might be a
    bug in the ring buffer code; check later -- JHS*/
 
-        if (rx_work_limit >=RX_RING_SIZE) rx_work_limit--;
+        if (budget >=RX_RING_SIZE) budget--;
 #endif
 
 	if (tulip_debug > 4)
@@ -144,14 +145,13 @@ int tulip_poll(struct net_device *dev, int *budget)
                while ( ! (tp->rx_ring[entry].status & cpu_to_le32(DescOwned))) {
                        s32 status = le32_to_cpu(tp->rx_ring[entry].status);
 
-
                        if (tp->dirty_rx + RX_RING_SIZE == tp->cur_rx)
                                break;
 
                        if (tulip_debug > 5)
                                printk(KERN_DEBUG "%s: In tulip_rx(), entry %d %8.8x.\n",
                                       dev->name, entry, status);
-                       if (--rx_work_limit < 0)
+		       if (work_done++ >= budget)
                                goto not_done;
 
                        if ((status & 0x38008300) != 0x0300) {
@@ -238,7 +238,9 @@ int tulip_poll(struct net_device *dev, int *budget)
                                tp->stats.rx_packets++;
                                tp->stats.rx_bytes += pkt_len;
                        }
-                       received++;
+#ifdef CONFIG_TULIP_NAPI_HW_MITIGATION
+		       received++;
+#endif
 
                        entry = (++tp->cur_rx) % RX_RING_SIZE;
                        if (tp->cur_rx - tp->dirty_rx > RX_RING_SIZE/4)
@@ -296,17 +298,15 @@ done:
 
 #endif /* CONFIG_TULIP_NAPI_HW_MITIGATION */
 
-         dev->quota -= received;
-         *budget -= received;
-
          tulip_refill_rx(dev);
 
          /* If RX ring is not full we are out of memory. */
-         if (tp->rx_buffers[tp->dirty_rx % RX_RING_SIZE].skb == NULL) goto oom;
+         if (tp->rx_buffers[tp->dirty_rx % RX_RING_SIZE].skb == NULL)
+		 goto oom;
 
          /* Remove us from polling list and enable RX intr. */
 
-         netif_rx_complete(dev);
+         netif_rx_complete(dev, napi);
          iowrite32(tulip_tbl[tp->chip_id].valid_intrs, tp->base_addr+CSR7);
 
          /* The last op happens after poll completion. Which means the following:
@@ -320,28 +320,20 @@ done:
           * processed irqs. But it must not result in losing events.
           */
 
-         return 0;
+         return work_done;
 
  not_done:
-         if (!received) {
-
-                 received = dev->quota; /* Not to happen */
-         }
-         dev->quota -= received;
-         *budget -= received;
-
          if (tp->cur_rx - tp->dirty_rx > RX_RING_SIZE/2 ||
              tp->rx_buffers[tp->dirty_rx % RX_RING_SIZE].skb == NULL)
                  tulip_refill_rx(dev);
 
-         if (tp->rx_buffers[tp->dirty_rx % RX_RING_SIZE].skb == NULL) goto oom;
-
-         return 1;
+         if (tp->rx_buffers[tp->dirty_rx % RX_RING_SIZE].skb == NULL)
+		 goto oom;
 
+         return work_done;
 
  oom:    /* Executed with RX ints disabled */
 
-
          /* Start timer, stop polling, but do not enable rx interrupts. */
          mod_timer(&tp->oom_timer, jiffies+1);
 
@@ -350,9 +342,9 @@ done:
           * before we did netif_rx_complete(). See? We would lose it. */
 
          /* remove ourselves from the polling list */
-         netif_rx_complete(dev);
+         netif_rx_complete(dev, napi);
 
-         return 0;
+         return work_done;
 }
 
 #else /* CONFIG_TULIP_NAPI */
@@ -534,7 +526,7 @@ irqreturn_t tulip_interrupt(int irq, void *dev_instance)
 			rxd++;
 			/* Mask RX intrs and add the device to poll list. */
 			iowrite32(tulip_tbl[tp->chip_id].valid_intrs&~RxPollInt, ioaddr + CSR7);
-			netif_rx_schedule(dev);
+			netif_rx_schedule(dev, &tp->napi);
 
 			if (!(csr5&~(AbnormalIntr|NormalIntr|RxPollInt|TPLnkPass)))
                                break;