mv643xx_eth: fix NAPI 'rotting packet' issue

When a receive interrupt occurs, mv643xx_eth would first process the
receive descriptors and then ACK the receive interrupt, instead of the
other way round.

This would leave a small race window between processing the last
receive descriptor and clearing the receive interrupt status in which
a new packet could come in, which would then 'rot' in the receive
ring until the next receive interrupt would come in.

Fix this by ACKing (clearing) the receive interrupt condition before
processing the receive descriptors.

Signed-off-by: Lennert Buytenhek <buytenh@marvell.com>

diff --git a/drivers/net/mv643xx_eth.c b/drivers/net/mv643xx_eth.c
index 46819af3b0627aec89649245ded32ccf53c7e028..af279f26c4070cbf883fb3b2b39ca89172236830 100644 (file)
--- a/drivers/net/mv643xx_eth.c
+++ b/drivers/net/mv643xx_eth.c
@@ -650,8 +650,6 @@ static int mv643xx_eth_poll(struct napi_struct *napi, int budget)
 
        if (rx < budget) {
                netif_rx_complete(mp->dev, napi);
-               wrl(mp, INT_CAUSE(mp->port_num), 0);
-               wrl(mp, INT_CAUSE_EXT(mp->port_num), 0);
                wrl(mp, INT_MASK(mp->port_num), INT_TX_END | INT_RX | INT_EXT);
        }
 
@@ -1796,6 +1794,7 @@ static irqreturn_t mv643xx_eth_irq(int irq, void *dev_id)
         */
 #ifdef MV643XX_ETH_NAPI
        if (int_cause & INT_RX) {
+               wrl(mp, INT_CAUSE(mp->port_num), ~(int_cause & INT_RX));
                wrl(mp, INT_MASK(mp->port_num), 0x00000000);
                rdl(mp, INT_MASK(mp->port_num));