r8169: disable ASPM in case of tx timeout

[ Upstream commit 80c0576ef179311f624bc450fede30a89afe9792 ]

There are still single reports of systems where ASPM incompatibilities
cause tx timeouts. It's not clear whom to blame, so let's disable
ASPM in case of a tx timeout.

v2:
- add one-time warning for informing the user

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/92369a92-dc32-4529-0509-11459ba0e391@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stable-dep-of: 59d395ed606d ("r8169: fix deadlock on RTL8125 in jumbo mtu mode")
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 84fb739679298b9fe0344ad5c867cc0662fd0169..c640896f7b7e2e3d31798db092cc0c191fc20c7c 100644 (file)
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -588,6 +588,7 @@ struct rtl8169_tc_offsets {
 enum rtl_flag {
        RTL_FLAG_TASK_ENABLED = 0,
        RTL_FLAG_TASK_RESET_PENDING,
+       RTL_FLAG_TASK_TX_TIMEOUT,
        RTL_FLAG_MAX
 };
 
@@ -4029,7 +4030,7 @@ static void rtl8169_tx_timeout(struct net_device *dev, unsigned int txqueue)
 {
        struct rtl8169_private *tp = netdev_priv(dev);
 
-       rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING);
+       rtl_schedule_task(tp, RTL_FLAG_TASK_TX_TIMEOUT);
 }
 
 static int rtl8169_tx_map(struct rtl8169_private *tp, const u32 *opts, u32 len,
@@ -4624,6 +4625,7 @@ static void rtl_task(struct work_struct *work)
 {
        struct rtl8169_private *tp =
                container_of(work, struct rtl8169_private, wk.work);
+       int ret;
 
        rtnl_lock();
 
@@ -4631,7 +4633,17 @@ static void rtl_task(struct work_struct *work)
            !test_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags))
                goto out_unlock;
 
+       if (test_and_clear_bit(RTL_FLAG_TASK_TX_TIMEOUT, tp->wk.flags)) {
+               /* ASPM compatibility issues are a typical reason for tx timeouts */
+               ret = pci_disable_link_state(tp->pci_dev, PCIE_LINK_STATE_L1 |
+                                                         PCIE_LINK_STATE_L0S);
+               if (!ret)
+                       netdev_warn_once(tp->dev, "ASPM disabled on Tx timeout\n");
+               goto reset;
+       }
+
        if (test_and_clear_bit(RTL_FLAG_TASK_RESET_PENDING, tp->wk.flags)) {
+reset:
                rtl_reset_work(tp);
                netif_wake_queue(tp->dev);
        }