net: fec: add napi support to improve proformance

Add napi support

Before this patch

 iperf -s -i 1
 ------------------------------------------------------------
 Server listening on TCP port 5001
 TCP window size: 85.3 KByte (default)
 ------------------------------------------------------------
 [  4] local 10.192.242.153 port 5001 connected with 10.192.242.138 port 50004
 [ ID] Interval       Transfer     Bandwidth
 [  4]  0.0- 1.0 sec  41.2 MBytes   345 Mbits/sec
 [  4]  1.0- 2.0 sec  43.7 MBytes   367 Mbits/sec
 [  4]  2.0- 3.0 sec  42.8 MBytes   359 Mbits/sec
 [  4]  3.0- 4.0 sec  43.7 MBytes   367 Mbits/sec
 [  4]  4.0- 5.0 sec  42.7 MBytes   359 Mbits/sec
 [  4]  5.0- 6.0 sec  43.8 MBytes   367 Mbits/sec
 [  4]  6.0- 7.0 sec  43.0 MBytes   361 Mbits/sec

After this patch
 [  4]  2.0- 3.0 sec  51.6 MBytes   433 Mbits/sec
 [  4]  3.0- 4.0 sec  51.8 MBytes   435 Mbits/sec
 [  4]  4.0- 5.0 sec  52.2 MBytes   438 Mbits/sec
 [  4]  5.0- 6.0 sec  52.1 MBytes   437 Mbits/sec
 [  4]  6.0- 7.0 sec  52.1 MBytes   437 Mbits/sec
 [  4]  7.0- 8.0 sec  52.3 MBytes   439 Mbits/sec

Signed-off-by: Frank Li <Frank.Li@freescale.com>
Signed-off-by: Fugang Duan <B38611@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/freescale/fec.c b/drivers/net/ethernet/freescale/fec.c
index f52ba338d2c7c0bedca1d1d1e684c129acbd0ed5..0287675ddffb9f5feeaa5cc937fa9c41328989b9 100644 (file)
--- a/drivers/net/ethernet/freescale/fec.c
+++ b/drivers/net/ethernet/freescale/fec.c
@@ -67,6 +67,7 @@
 #endif
 
 #define DRIVER_NAME    "fec"
+#define FEC_NAPI_WEIGHT        64
 
 /* Pause frame feild and FIFO threshold */
 #define FEC_ENET_FCE   (1 << 5)
@@ -168,6 +169,7 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
 #define FEC_ENET_EBERR ((uint)0x00400000)      /* SDMA bus error */
 
 #define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF | FEC_ENET_MII)
+#define FEC_RX_DISABLED_IMASK (FEC_DEFAULT_IMASK & (~FEC_ENET_RXF))
 
 /* The FEC stores dest/src/type, data, and checksum for receive packets.
  */
@@ -656,8 +658,8 @@ fec_enet_tx(struct net_device *ndev)
  * not been given to the system, we just set the empty indicator,
  * effectively tossing the packet.
  */
-static void
-fec_enet_rx(struct net_device *ndev)
+static int
+fec_enet_rx(struct net_device *ndev, int budget)
 {
        struct fec_enet_private *fep = netdev_priv(ndev);
        const struct platform_device_id *id_entry =
@@ -667,13 +669,12 @@ fec_enet_rx(struct net_device *ndev)
        struct  sk_buff *skb;
        ushort  pkt_len;
        __u8 *data;
+       int     pkt_received = 0;
 
 #ifdef CONFIG_M532x
        flush_cache_all();
 #endif
 
-       spin_lock(&fep->hw_lock);
-
        /* First, grab all of the stats for the incoming packet.
         * These get messed up if we get called due to a busy condition.
         */
@@ -681,6 +682,10 @@ fec_enet_rx(struct net_device *ndev)
 
        while (!((status = bdp->cbd_sc) & BD_ENET_RX_EMPTY)) {
 
+               if (pkt_received >= budget)
+                       break;
+               pkt_received++;
+
                /* Since we have allocated space to hold a complete frame,
                 * the last indicator should be set.
                 */
@@ -762,7 +767,7 @@ fec_enet_rx(struct net_device *ndev)
                        }
 
                        if (!skb_defer_rx_timestamp(skb))
-                               netif_rx(skb);
+                               napi_gro_receive(&fep->napi, skb);
                }
 
                bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, data,
@@ -796,7 +801,7 @@ rx_processing_done:
        }
        fep->cur_rx = bdp;
 
-       spin_unlock(&fep->hw_lock);
+       return pkt_received;
 }
 
 static irqreturn_t
@@ -813,7 +818,13 @@ fec_enet_interrupt(int irq, void *dev_id)
 
                if (int_events & FEC_ENET_RXF) {
                        ret = IRQ_HANDLED;
-                       fec_enet_rx(ndev);
+
+                       /* Disable the RX interrupt */
+                       if (napi_schedule_prep(&fep->napi)) {
+                               writel(FEC_RX_DISABLED_IMASK,
+                                       fep->hwp + FEC_IMASK);
+                               __napi_schedule(&fep->napi);
+                       }
                }
 
                /* Transmit OK, or non-fatal error. Update the buffer
@@ -834,7 +845,18 @@ fec_enet_interrupt(int irq, void *dev_id)
        return ret;
 }
 
+static int fec_enet_rx_napi(struct napi_struct *napi, int budget)
+{
+       struct net_device *ndev = napi->dev;
+       int pkts = fec_enet_rx(ndev, budget);
+       struct fec_enet_private *fep = netdev_priv(ndev);
 
+       if (pkts < budget) {
+               napi_complete(napi);
+               writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
+       }
+       return pkts;
+}
 
 /* ------------------------------------------------------------------------- */
 static void fec_get_mac(struct net_device *ndev)
@@ -1392,6 +1414,8 @@ fec_enet_open(struct net_device *ndev)
        struct fec_enet_private *fep = netdev_priv(ndev);
        int ret;
 
+       napi_enable(&fep->napi);
+
        /* I should reset the ring buffers here, but I don't yet know
         * a simple way to do that.
         */
@@ -1604,6 +1628,9 @@ static int fec_enet_init(struct net_device *ndev)
        ndev->netdev_ops = &fec_netdev_ops;
        ndev->ethtool_ops = &fec_enet_ethtool_ops;
 
+       writel(FEC_RX_DISABLED_IMASK, fep->hwp + FEC_IMASK);
+       netif_napi_add(ndev, &fep->napi, fec_enet_rx_napi, FEC_NAPI_WEIGHT);
+
        /* Initialize the receive buffer descriptors. */
        bdp = fep->rx_bd_base;
        for (i = 0; i < RX_RING_SIZE; i++) {

diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 2ebedaf7ad810d9efb5fafa7123a271f2101192a..01579b8e37c4f979ea668b28538be4e22e255baa 100644 (file)
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -249,6 +249,8 @@ struct fec_enet_private {
        int     bufdesc_ex;
        int     pause_flag;
 
+       struct  napi_struct napi;
+
        struct ptp_clock *ptp_clock;
        struct ptp_clock_info ptp_caps;
        unsigned long last_overflow_check;