r8169: revert 2ab19de ("r8169: remove ASPM restrictions now that ASPM…

… is disabled during NAPI poll")

There have been reports that on a number of systems this change breaks
network connectivity. Therefore effectively revert it. Mainly affected
seem to be systems where BIOS denies ASPM access to OS.
Due to later changes we can't do a direct revert.

Fixes: 2ab19de ("r8169: remove ASPM restrictions now that ASPM is disabled during NAPI poll")
Cc: [email protected]
Link: https://lore.kernel.org/netdev/[email protected]/T/
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217596
Signed-off-by: Heiner Kallweit <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

drivers/net/ethernet/realtek/r8169_main.c

@@ -623,6 +623,7 @@ struct rtl8169_private {
 	int cfg9346_usage_count;
 
 	unsigned supports_gmii:1;
+	unsigned aspm_manageable:1;
 	dma_addr_t counters_phys_addr;
 	struct rtl8169_counters *counters;
 	struct rtl8169_tc_offsets tc_offset;
@@ -2746,7 +2747,8 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 	if (tp->mac_version < RTL_GIGA_MAC_VER_32)
 		return;
 
-	if (enable) {
+	/* Don't enable ASPM in the chip if OS can't control ASPM */
+	if (enable && tp->aspm_manageable) {
 		/* On these chip versions ASPM can even harm
 		 * bus communication of other PCI devices.
 		 */
@@ -5165,6 +5167,16 @@ static void rtl_init_mac_address(struct rtl8169_private *tp)
 	rtl_rar_set(tp, mac_addr);
 }
 
+/* register is set if system vendor successfully tested ASPM 1.2 */
+static bool rtl_aspm_is_safe(struct rtl8169_private *tp)
+{
+	if (tp->mac_version >= RTL_GIGA_MAC_VER_61 &&
+	    r8168_mac_ocp_read(tp, 0xc0b2) & 0xf)
+		return true;
+
+	return false;
+}
+
 static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct rtl8169_private *tp;
@@ -5234,6 +5246,19 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 				     xid);
 	tp->mac_version = chipset;
 
+	/* Disable ASPM L1 as that cause random device stop working
+	 * problems as well as full system hangs for some PCIe devices users.
+	 * Chips from RTL8168h partially have issues with L1.2, but seem
+	 * to work fine with L1 and L1.1.
+	 */
+	if (rtl_aspm_is_safe(tp))
+		rc = 0;
+	else if (tp->mac_version >= RTL_GIGA_MAC_VER_46)
+		rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2);
+	else
+		rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1);
+	tp->aspm_manageable = !rc;
+
 	tp->dash_type = rtl_check_dash(tp);
 
 	tp->cp_cmd = RTL_R16(tp, CPlusCmd) & CPCMD_MASK;