tg3: Disable tg3 PCIe AER on system reboot

JIRA: https://issues.redhat.com/browse/RHEL-63747

Upstream Status: https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git

commit e0efe83
Author: Lenny Szubowicz <lszubowi@redhat.com>
Date:   Thu Jan 30 16:57:54 2025 -0500

    tg3: Disable tg3 PCIe AER on system reboot

    Disable PCIe AER on the tg3 device on system reboot on a limited
    list of Dell PowerEdge systems. This prevents a fatal PCIe AER event
    on the tg3 device during the ACPI _PTS (prepare to sleep) method for
    S5 on those systems. The _PTS is invoked by acpi_enter_sleep_state_prep()
    as part of the kernel's reboot sequence as a result of commit
    38f34db ("PM: ACPI: reboot: Reinstate S5 for reboot").

    There was an earlier fix for this problem by commit 2ca1c94
    ("tg3: Disable tg3 device on system reboot to avoid triggering AER").
    But it was discovered that this earlier fix caused a reboot hang
    when some Dell PowerEdge servers were booted via ipxe. To address
    this reboot hang, the earlier fix was essentially reverted by commit
    9fc3bc7 ("tg3: power down device only on SYSTEM_POWER_OFF").
    This re-exposed the tg3 PCIe AER on reboot problem.

    This fix is not an ideal solution because the root cause of the AER
    is in system firmware. Instead, it's a targeted work-around in the
    tg3 driver.

    Note also that the PCIe AER must be disabled on the tg3 device even
    if the system is configured to use "firmware first" error handling.

    V3:
       - Fix sparse warning on improper comparison of pdev->current_state
       - Adhere to netdev comment style

    Fixes: 9fc3bc7 ("tg3: power down device only on SYSTEM_POWER_OFF")
    Signed-off-by: Lenny Szubowicz <lszubowi@redhat.com>
    Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
    Reviewed-by: Simon Horman <horms@kernel.org>
    Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Lenny Szubowicz <lszubowi@redhat.com>

Author: LennySzubowicz

drivers/net/ethernet/broadcom/tg3.c

@@ -55,6 +55,7 @@
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
 #include <linux/crc32poly.h>
+#include <linux/dmi.h>
 
 #include <net/checksum.h>
 #include <net/gso.h>
@@ -18151,6 +18152,50 @@ static int tg3_resume(struct device *device)
 
 static SIMPLE_DEV_PM_OPS(tg3_pm_ops, tg3_suspend, tg3_resume);
 
+/* Systems where ACPI _PTS (Prepare To Sleep) S5 will result in a fatal
+ * PCIe AER event on the tg3 device if the tg3 device is not, or cannot
+ * be, powered down.
+ */
+static const struct dmi_system_id tg3_restart_aer_quirk_table[] = {
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R440"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R540"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R640"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R650"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R740"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R750"),
+		},
+	},
+	{}
+};
+
 static void tg3_shutdown(struct pci_dev *pdev)
 {
 	struct net_device *dev = pci_get_drvdata(pdev);
@@ -18167,6 +18212,19 @@ static void tg3_shutdown(struct pci_dev *pdev)
 
 	if (system_state == SYSTEM_POWER_OFF)
 		tg3_power_down(tp);
+	else if (system_state == SYSTEM_RESTART &&
+		 dmi_first_match(tg3_restart_aer_quirk_table) &&
+		 pdev->current_state != PCI_D3cold &&
+		 pdev->current_state != PCI_UNKNOWN) {
+		/* Disable PCIe AER on the tg3 to avoid a fatal
+		 * error during this system restart.
+		 */
+		pcie_capability_clear_word(pdev, PCI_EXP_DEVCTL,
+					   PCI_EXP_DEVCTL_CERE |
+					   PCI_EXP_DEVCTL_NFERE |
+					   PCI_EXP_DEVCTL_FERE |
+					   PCI_EXP_DEVCTL_URRE);
+	}
 
 	rtnl_unlock();