ixgbe: fix X540 Completion timeout

On topologies including few levels of PCIe switching X540 can run into an
unexpected completion error.  We get around this by waiting after enabling
loopback a sufficient amount of time until Tx Data Fetch is sent.  We then
poll the pending transaction bit to ensure we received the completion.  Only
then do we go on to clear the buffers.

Signed-of-by: Don Skidmore <donald.c.skidmore@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

drivers/net/ethernet/intel/ixgbe/ixgbe_common.c

@@ -3583,7 +3583,8 @@ s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min,
  **/
 void ixgbe_clear_tx_pending(struct ixgbe_hw *hw)
 {
-	u32 gcr_ext, hlreg0;
+	u32 gcr_ext, hlreg0, i, poll;
+	u16 value;
 
 	/*
 	 * If double reset is not requested then all transactions should
@@ -3600,6 +3601,23 @@ void ixgbe_clear_tx_pending(struct ixgbe_hw *hw)
 	hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0);
 	IXGBE_WRITE_REG(hw, IXGBE_HLREG0, hlreg0 | IXGBE_HLREG0_LPBK);
 
+	/* wait for a last completion before clearing buffers */
+	IXGBE_WRITE_FLUSH(hw);
+	usleep_range(3000, 6000);
+
+	/* Before proceeding, make sure that the PCIe block does not have
+	 * transactions pending.
+	 */
+	poll = ixgbe_pcie_timeout_poll(hw);
+	for (i = 0; i < poll; i++) {
+		usleep_range(100, 200);
+		value = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_DEVICE_STATUS);
+		if (ixgbe_removed(hw->hw_addr))
+			break;
+		if (!(value & IXGBE_PCI_DEVICE_STATUS_TRANSACTION_PENDING))
+			break;
+	}
+
 	/* initiate cleaning flow for buffers in the PCIe transaction layer */
 	gcr_ext = IXGBE_READ_REG(hw, IXGBE_GCR_EXT);
 	IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT,