There is a chance that between the time EOP is read and the time it is
used another transmit on a different CPU could have run and completed,
thus leaving EOP in a bad state.
Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
(count < tx_ring->work_limit)) {
bool cleaned = false;
rmb(); /* read buffer_info after eop_desc */
+ /* eop could change between read and DD-check */
+ if (unlikely(eop != tx_ring->tx_buffer_info[i].next_to_watch))
+ goto cont_loop;
for ( ; !cleaned; count++) {
struct sk_buff *skb;
tx_desc = IXGBE_TX_DESC_ADV(*tx_ring, i);
i = 0;
}
+cont_loop:
eop = tx_ring->tx_buffer_info[i].next_to_watch;
eop_desc = IXGBE_TX_DESC_ADV(*tx_ring, eop);
}