[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, 19 insertions, 27 deletions

diff --git a/drivers/net/e1000/e1000.h b/drivers/net/e1000/e1000.h
index 16a6edfeba41..781ed9968489 100644
--- a/drivers/net/e1000/e1000.h
+++ b/drivers/net/e1000/e1000.h
@@ -300,6 +300,7 @@ struct e1000_adapter {
                                 int cleaned_count);
         struct e1000_rx_ring *rx_ring;      /* One per active queue */
 #ifdef CONFIG_E1000_NAPI
+        struct napi_struct napi;
         struct net_device *polling_netdev;  /* One per active queue */
 #endif
         int num_tx_queues;
diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c
index e7c8951f47fa..723568d6e44a 100644
--- a/drivers/net/e1000/e1000_main.c
+++ b/drivers/net/e1000/e1000_main.c
@@ -166,7 +166,7 @@ static irqreturn_t e1000_intr_msi(int irq, void *data);
 static boolean_t e1000_clean_tx_irq(struct e1000_adapter *adapter,
                                     struct e1000_tx_ring *tx_ring);
 #ifdef CONFIG_E1000_NAPI
-static int e1000_clean(struct net_device *poll_dev, int *budget);
+static int e1000_clean(struct napi_struct *napi, int budget);
 static boolean_t e1000_clean_rx_irq(struct e1000_adapter *adapter,
                                     struct e1000_rx_ring *rx_ring,
                                     int *work_done, int work_to_do);
@@ -545,7 +545,7 @@ int e1000_up(struct e1000_adapter *adapter)
         clear_bit(__E1000_DOWN, &adapter->flags);
 
 #ifdef CONFIG_E1000_NAPI
-        netif_poll_enable(adapter->netdev);
+        napi_enable(&adapter->napi);
 #endif
         e1000_irq_enable(adapter);
 
@@ -634,7 +634,7 @@ e1000_down(struct e1000_adapter *adapter)
         set_bit(__E1000_DOWN, &adapter->flags);
 
 #ifdef CONFIG_E1000_NAPI
-        netif_poll_disable(netdev);
+        napi_disable(&adapter->napi);
 #endif
         e1000_irq_disable(adapter);
 
@@ -936,8 +936,7 @@ e1000_probe(struct pci_dev *pdev,
         netdev->tx_timeout = &e1000_tx_timeout;
         netdev->watchdog_timeo = 5 * HZ;
 #ifdef CONFIG_E1000_NAPI
-        netdev->poll = &e1000_clean;
-        netdev->weight = 64;
+        netif_napi_add(netdev, &adapter->napi, e1000_clean, 64);
 #endif
         netdev->vlan_rx_register = e1000_vlan_rx_register;
         netdev->vlan_rx_add_vid = e1000_vlan_rx_add_vid;
@@ -1151,9 +1150,6 @@ e1000_probe(struct pci_dev *pdev,
         /* tell the stack to leave us alone until e1000_open() is called */
         netif_carrier_off(netdev);
         netif_stop_queue(netdev);
-#ifdef CONFIG_E1000_NAPI
-        netif_poll_disable(netdev);
-#endif
 
         strcpy(netdev->name, "eth%d");
         if ((err = register_netdev(netdev)))
@@ -1222,12 +1218,13 @@ e1000_remove(struct pci_dev *pdev)
          * would have already happened in close and is redundant. */
         e1000_release_hw_control(adapter);
 
-        unregister_netdev(netdev);
 #ifdef CONFIG_E1000_NAPI
         for (i = 0; i < adapter->num_rx_queues; i++)
                 dev_put(&adapter->polling_netdev[i]);
 #endif
 
+        unregister_netdev(netdev);
+
         if (!e1000_check_phy_reset_block(&adapter->hw))
                 e1000_phy_hw_reset(&adapter->hw);
 
@@ -1325,8 +1322,6 @@ e1000_sw_init(struct e1000_adapter *adapter)
 #ifdef CONFIG_E1000_NAPI
         for (i = 0; i < adapter->num_rx_queues; i++) {
                 adapter->polling_netdev[i].priv = adapter;
-                adapter->polling_netdev[i].poll = &e1000_clean;
-                adapter->polling_netdev[i].weight = 64;
                 dev_hold(&adapter->polling_netdev[i]);
                 set_bit(__LINK_STATE_START, &adapter->polling_netdev[i].state);
         }
@@ -1443,7 +1438,7 @@ e1000_open(struct net_device *netdev)
         clear_bit(__E1000_DOWN, &adapter->flags);
 
 #ifdef CONFIG_E1000_NAPI
-        netif_poll_enable(netdev);
+        napi_enable(&adapter->napi);
 #endif
 
         e1000_irq_enable(adapter);
@@ -3786,12 +3781,12 @@ e1000_intr_msi(int irq, void *data)
         }
 
 #ifdef CONFIG_E1000_NAPI
-        if (likely(netif_rx_schedule_prep(netdev))) {
+        if (likely(netif_rx_schedule_prep(netdev, &adapter->napi))) {
                 adapter->total_tx_bytes = 0;
                 adapter->total_tx_packets = 0;
                 adapter->total_rx_bytes = 0;
                 adapter->total_rx_packets = 0;
-                __netif_rx_schedule(netdev);
+                __netif_rx_schedule(netdev, &adapter->napi);
         } else
                 e1000_irq_enable(adapter);
 #else
@@ -3871,12 +3866,12 @@ e1000_intr(int irq, void *data)
                 E1000_WRITE_REG(hw, IMC, ~0);
                 E1000_WRITE_FLUSH(hw);
         }
-        if (likely(netif_rx_schedule_prep(netdev))) {
+        if (likely(netif_rx_schedule_prep(netdev, &adapter->napi))) {
                 adapter->total_tx_bytes = 0;
                 adapter->total_tx_packets = 0;
                 adapter->total_rx_bytes = 0;
                 adapter->total_rx_packets = 0;
-                __netif_rx_schedule(netdev);
+                __netif_rx_schedule(netdev, &adapter->napi);
         } else
                 /* this really should not happen! if it does it is basically a
                  * bug, but not a hard error, so enable ints and continue */
@@ -3924,10 +3919,10 @@ e1000_intr(int irq, void *data)
  **/
 
 static int
-e1000_clean(struct net_device *poll_dev, int *budget)
+e1000_clean(struct napi_struct *napi, int budget)
 {
-        struct e1000_adapter *adapter;
-        int work_to_do = min(*budget, poll_dev->quota);
+        struct e1000_adapter *adapter = container_of(napi, struct e1000_adapter, napi);
+        struct net_device *poll_dev = adapter->netdev;
         int tx_cleaned = 0, work_done = 0;
 
         /* Must NOT use netdev_priv macro here. */
@@ -3948,23 +3943,19 @@ e1000_clean(struct net_device *poll_dev, int *budget)
         }
 
         adapter->clean_rx(adapter, &adapter->rx_ring[0],
-                          &work_done, work_to_do);
-
-        *budget -= work_done;
-        poll_dev->quota -= work_done;
+                          &work_done, budget);
 
         /* If no Tx and not enough Rx work done, exit the polling mode */
-        if ((!tx_cleaned && (work_done == 0)) ||
+        if ((!tx_cleaned && (work_done < budget)) ||
            !netif_running(poll_dev)) {
 quit_polling:
                 if (likely(adapter->itr_setting & 3))
                         e1000_set_itr(adapter);
-                netif_rx_complete(poll_dev);
+                netif_rx_complete(poll_dev, napi);
                 e1000_irq_enable(adapter);
-                return 0;
         }
 
-        return 1;
+        return work_done;
 }
 
 #endif