[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>

2 files changed, 13 insertions, 17 deletions

diff --git a/drivers/net/ixgb/ixgb.h b/drivers/net/ixgb/ixgb.h
index 3569d5b03388..1eee8894c732 100644
--- a/drivers/net/ixgb/ixgb.h
+++ b/drivers/net/ixgb/ixgb.h
@@ -184,6 +184,7 @@ struct ixgb_adapter {
         boolean_t rx_csum;
 
         /* OS defined structs */
+        struct napi_struct napi;
         struct net_device *netdev;
         struct pci_dev *pdev;
         struct net_device_stats net_stats;
diff --git a/drivers/net/ixgb/ixgb_main.c b/drivers/net/ixgb/ixgb_main.c
index 991c8833e23c..e3f27c67fb28 100644
--- a/drivers/net/ixgb/ixgb_main.c
+++ b/drivers/net/ixgb/ixgb_main.c
@@ -97,7 +97,7 @@ static irqreturn_t ixgb_intr(int irq, void *data);
 static boolean_t ixgb_clean_tx_irq(struct ixgb_adapter *adapter);
 
 #ifdef CONFIG_IXGB_NAPI
-static int ixgb_clean(struct net_device *netdev, int *budget);
+static int ixgb_clean(struct napi_struct *napi, int budget);
 static boolean_t ixgb_clean_rx_irq(struct ixgb_adapter *adapter,
                                    int *work_done, int work_to_do);
 #else
@@ -288,7 +288,7 @@ ixgb_up(struct ixgb_adapter *adapter)
         mod_timer(&adapter->watchdog_timer, jiffies);
 
 #ifdef CONFIG_IXGB_NAPI
-        netif_poll_enable(netdev);
+        napi_enable(&adapter->napi);
 #endif
         ixgb_irq_enable(adapter);
 
@@ -309,7 +309,7 @@ ixgb_down(struct ixgb_adapter *adapter, boolean_t kill_watchdog)
         if(kill_watchdog)
                 del_timer_sync(&adapter->watchdog_timer);
 #ifdef CONFIG_IXGB_NAPI
-        netif_poll_disable(netdev);
+        napi_disable(&adapter->napi);
 #endif
         adapter->link_speed = 0;
         adapter->link_duplex = 0;
@@ -421,8 +421,7 @@ ixgb_probe(struct pci_dev *pdev,
         netdev->tx_timeout = &ixgb_tx_timeout;
         netdev->watchdog_timeo = 5 * HZ;
 #ifdef CONFIG_IXGB_NAPI
-        netdev->poll = &ixgb_clean;
-        netdev->weight = 64;
+        netif_napi_add(netdev, &adapter->napi, ixgb_clean, 64);
 #endif
         netdev->vlan_rx_register = ixgb_vlan_rx_register;
         netdev->vlan_rx_add_vid = ixgb_vlan_rx_add_vid;
@@ -1746,7 +1745,7 @@ ixgb_intr(int irq, void *data)
         }
 
 #ifdef CONFIG_IXGB_NAPI
-        if(netif_rx_schedule_prep(netdev)) {
+        if (netif_rx_schedule_prep(netdev, &adapter->napi)) {
 
                 /* Disable interrupts and register for poll. The flush 
                   of the posted write is intentionally left out.
@@ -1754,7 +1753,7 @@ ixgb_intr(int irq, void *data)
 
                 atomic_inc(&adapter->irq_sem);
                 IXGB_WRITE_REG(&adapter->hw, IMC, ~0);
-                __netif_rx_schedule(netdev);
+                __netif_rx_schedule(netdev, &adapter->napi);
         }
 #else
         /* yes, that is actually a & and it is meant to make sure that
@@ -1776,27 +1775,23 @@ ixgb_intr(int irq, void *data)
  **/
 
 static int
-ixgb_clean(struct net_device *netdev, int *budget)
+ixgb_clean(struct napi_struct *napi, int budget)
 {
-        struct ixgb_adapter *adapter = netdev_priv(netdev);
-        int work_to_do = min(*budget, netdev->quota);
+        struct ixgb_adapter *adapter = container_of(napi, struct ixgb_adapter, napi);
+        struct net_device *netdev = adapter->netdev;
         int tx_cleaned;
         int work_done = 0;
 
         tx_cleaned = ixgb_clean_tx_irq(adapter);
-        ixgb_clean_rx_irq(adapter, &work_done, work_to_do);
-
-        *budget -= work_done;
-        netdev->quota -= work_done;
+        ixgb_clean_rx_irq(adapter, &work_done, budget);
 
         /* if no Tx and not enough Rx work done, exit the polling mode */
         if((!tx_cleaned && (work_done == 0)) || !netif_running(netdev)) {
-                netif_rx_complete(netdev);
+                netif_rx_complete(netdev, napi);
                 ixgb_irq_enable(adapter);
-                return 0;
         }
 
-        return 1;
+        return work_done;
 }
 #endif