[PATCH net-next resubmit v2] r8169: disable ASPM in case of tx timeout

From: Heiner Kallweit <hkallweit1@gmail.com>
To: Jakub Kicinski <kuba@kernel.org>,
	David Miller <davem@davemloft.net>,
	Realtek linux nic maintainers <nic_swsd@realtek.com>,
	Eric Dumazet <edumazet@google.com>,
	Paolo Abeni <pabeni@redhat.com>
Cc: "netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	Stephen Hemminger <stephen@networkplumber.org>
Subject: [PATCH net-next resubmit v2] r8169: disable ASPM in case of tx timeout
Date: Tue, 10 Jan 2023 23:03:18 +0100	[thread overview]
Message-ID: <92369a92-dc32-4529-0509-11459ba0e391@gmail.com> (raw)

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>
---
 drivers/net/ethernet/realtek/r8169_main.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index a9dcc98b6..49c124d8e 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -576,6 +576,7 @@ 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
 };
 
@@ -3931,7 +3932,7 @@ 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,
@@ -4525,6 +4526,7 @@ static void rtl_task(struct work_struct *work)
 {
 	struct rtl8169_private *tp =
 		container_of(work, struct rtl8169_private, wk.work);
+	int ret;
 
 	rtnl_lock();
 
@@ -4532,7 +4534,17 @@ 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);
 	}
-- 
2.39.0

