[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, 22 insertions, 20 deletions

diff --git a/drivers/net/natsemi.c b/drivers/net/natsemi.c
index b47a12d684f..43cfa4b3e29 100644
--- a/drivers/net/natsemi.c
+++ b/drivers/net/natsemi.c
@@ -560,6 +560,8 @@ struct netdev_private {
         /* address of a sent-in-place packet/buffer, for later free() */
         struct sk_buff *tx_skbuff[TX_RING_SIZE];
         dma_addr_t tx_dma[TX_RING_SIZE];
+        struct net_device *dev;
+        struct napi_struct napi;
         struct net_device_stats stats;
         /* Media monitoring timer */
         struct timer_list timer;
@@ -636,7 +638,7 @@ static void init_registers(struct net_device *dev);
 static int start_tx(struct sk_buff *skb, struct net_device *dev);
 static irqreturn_t intr_handler(int irq, void *dev_instance);
 static void netdev_error(struct net_device *dev, int intr_status);
-static int natsemi_poll(struct net_device *dev, int *budget);
+static int natsemi_poll(struct napi_struct *napi, int budget);
 static void netdev_rx(struct net_device *dev, int *work_done, int work_to_do);
 static void netdev_tx_done(struct net_device *dev);
 static int natsemi_change_mtu(struct net_device *dev, int new_mtu);
@@ -861,6 +863,7 @@ static int __devinit natsemi_probe1 (struct pci_dev *pdev,
         dev->irq = irq;
 
         np = netdev_priv(dev);
+        netif_napi_add(dev, &np->napi, natsemi_poll, 64);
 
         np->pci_dev = pdev;
         pci_set_drvdata(pdev, dev);
@@ -931,8 +934,6 @@ static int __devinit natsemi_probe1 (struct pci_dev *pdev,
         dev->do_ioctl = &netdev_ioctl;
         dev->tx_timeout = &tx_timeout;
         dev->watchdog_timeo = TX_TIMEOUT;
-        dev->poll = natsemi_poll;
-        dev->weight = 64;
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
         dev->poll_controller = &natsemi_poll_controller;
@@ -1554,6 +1555,8 @@ static int netdev_open(struct net_device *dev)
                 free_irq(dev->irq, dev);
                 return i;
         }
+        napi_enable(&np->napi);
+
         init_ring(dev);
         spin_lock_irq(&np->lock);
         init_registers(dev);
@@ -2200,10 +2203,10 @@ static irqreturn_t intr_handler(int irq, void *dev_instance)
 
         prefetch(&np->rx_skbuff[np->cur_rx % RX_RING_SIZE]);
 
-        if (netif_rx_schedule_prep(dev)) {
+        if (netif_rx_schedule_prep(dev, &np->napi)) {
                 /* Disable interrupts and register for poll */
                 natsemi_irq_disable(dev);
-                __netif_rx_schedule(dev);
+                __netif_rx_schedule(dev, &np->napi);
         } else
                 printk(KERN_WARNING
                        "%s: Ignoring interrupt, status %#08x, mask %#08x.\n",
@@ -2216,12 +2219,11 @@ static irqreturn_t intr_handler(int irq, void *dev_instance)
 /* This is the NAPI poll routine.  As well as the standard RX handling
  * it also handles all other interrupts that the chip might raise.
  */
-static int natsemi_poll(struct net_device *dev, int *budget)
+static int natsemi_poll(struct napi_struct *napi, int budget)
 {
-        struct netdev_private *np = netdev_priv(dev);
+        struct netdev_private *np = container_of(napi, struct netdev_private, napi);
+        struct net_device *dev = np->dev;
         void __iomem * ioaddr = ns_ioaddr(dev);
-
-        int work_to_do = min(*budget, dev->quota);
         int work_done = 0;
 
         do {
@@ -2236,7 +2238,7 @@ static int natsemi_poll(struct net_device *dev, int *budget)
                 if (np->intr_status &
                     (IntrRxDone | IntrRxIntr | RxStatusFIFOOver |
                      IntrRxErr | IntrRxOverrun)) {
-                        netdev_rx(dev, &work_done, work_to_do);
+                        netdev_rx(dev, &work_done, budget);
                 }
 
                 if (np->intr_status &
@@ -2250,16 +2252,13 @@ static int natsemi_poll(struct net_device *dev, int *budget)
                 if (np->intr_status & IntrAbnormalSummary)
                         netdev_error(dev, np->intr_status);
 
-                *budget -= work_done;
-                dev->quota -= work_done;
-
-                if (work_done >= work_to_do)
-                        return 1;
+                if (work_done >= budget)
+                        return work_done;
 
                 np->intr_status = readl(ioaddr + IntrStatus);
         } while (np->intr_status);
 
-        netif_rx_complete(dev);
+        netif_rx_complete(dev, napi);
 
         /* Reenable interrupts providing nothing is trying to shut
          * the chip down. */
@@ -2268,7 +2267,7 @@ static int natsemi_poll(struct net_device *dev, int *budget)
                 natsemi_irq_enable(dev);
         spin_unlock(&np->lock);
 
-        return 0;
+        return work_done;
 }
 
 /* This routine is logically part of the interrupt handler, but separated
@@ -3158,6 +3157,8 @@ static int netdev_close(struct net_device *dev)
                         dev->name, np->cur_tx, np->dirty_tx,
                         np->cur_rx, np->dirty_rx);
 
+        napi_disable(&np->napi);
+
         /*
          * FIXME: what if someone tries to close a device
          * that is suspended?
@@ -3253,7 +3254,7 @@ static void __devexit natsemi_remove1 (struct pci_dev *pdev)
  *              disable_irq() to enforce synchronization.
  *      * natsemi_poll: checks before reenabling interrupts.  suspend
  *              sets hands_off, disables interrupts and then waits with
- *              netif_poll_disable().
+ *              napi_disable().
  *
  * Interrupts must be disabled, otherwise hands_off can cause irq storms.
  */
@@ -3279,7 +3280,7 @@ static int natsemi_suspend (struct pci_dev *pdev, pm_message_t state)
                 spin_unlock_irq(&np->lock);
                 enable_irq(dev->irq);
 
-                netif_poll_disable(dev);
+                napi_disable(&np->napi);
 
                 /* Update the error counts. */
                 __get_stats(dev);
@@ -3320,6 +3321,8 @@ static int natsemi_resume (struct pci_dev *pdev)
                 pci_enable_device(pdev);
         /*      pci_power_on(pdev); */
 
+                napi_enable(&np->napi);
+
                 natsemi_reset(dev);
                 init_ring(dev);
                 disable_irq(dev->irq);
@@ -3333,7 +3336,6 @@ static int natsemi_resume (struct pci_dev *pdev)
                 mod_timer(&np->timer, jiffies + 1*HZ);
         }
         netif_device_attach(dev);
-        netif_poll_enable(dev);
 out:
         rtnl_unlock();
         return 0;