r8169: fix Rx index race between FIFO overflow recovery and NAPI handler.
Since 92fc43b4159b518f5baae57301f26d770b0834c9, rtl8169_tx_timeout ends up
resetting Rx and Tx indexes and thus racing with the NAPI handler via
-> rtl8169_hw_reset
-> rtl_hw_reset
-> rtl8169_init_ring_indexes
What about returning to the original state ?
rtl_hw_reset is only used by rtl8169_hw_reset and rtl8169_init_one.
The latter does not need rtl8169_init_ring_indexes because the indexes
still contain their original values from the newly allocated network
device private data area (i.e. 0).
rtl8169_hw_reset is used by:
1. rtl8169_down
Helper for rtl8169_close. rtl8169_open explicitely inits the indexes
anyway.
2. rtl8169_pcierr_interrupt
Indexes are set by rtl8169_reinit_task.
3. rtl8169_interrupt
rtl8169_hw_reset is needed when the device goes down. See 1.
4. rtl_shutdown
System shutdown handler. Indexes are irrelevant.
5. rtl8169_reset_task
Indexes must be set before rtl_hw_start is called.
6. rtl8169_tx_timeout
Indexes should not be set. This is the job of rtl8169_reset_task anyway.
The removal of rtl8169_hw_reset in rtl8169_tx_timeout and its move in
rtl8169_reset_task do not change the analysis.
Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Cc: hayeswang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 7a1e3a6..67bf078 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -3935,8 +3935,6 @@
break;
udelay(100);
}
-
- rtl8169_init_ring_indexes(tp);
}
static int __devinit
@@ -5395,14 +5393,16 @@
if (!netif_running(dev))
goto out_unlock;
+ rtl8169_hw_reset(tp);
+
rtl8169_wait_for_quiescence(dev);
for (i = 0; i < NUM_RX_DESC; i++)
rtl8169_mark_to_asic(tp->RxDescArray + i, rx_buf_sz);
rtl8169_tx_clear(tp);
+ rtl8169_init_ring_indexes(tp);
- rtl8169_hw_reset(tp);
rtl_hw_start(dev);
netif_wake_queue(dev);
rtl8169_check_link_status(dev, tp, tp->mmio_addr);
@@ -5413,11 +5413,6 @@
static void rtl8169_tx_timeout(struct net_device *dev)
{
- struct rtl8169_private *tp = netdev_priv(dev);
-
- rtl8169_hw_reset(tp);
-
- /* Let's wait a bit while any (async) irq lands on */
rtl8169_schedule_work(dev, rtl8169_reset_task);
}