e1000e: avoid failing the system during pm_suspend

[ Upstream commit 0a6ad4d9e1 ]

Occasionally when the system goes into pm_suspend, the suspend might fail
due to a PHY access error on the network adapter. Previously, this would
have caused the whole system to fail to go to a low power state.
An example of this was reported in the following Bugzilla:
https://bugzilla.kernel.org/show_bug.cgi?id=205015

[ 1663.694828] e1000e 0000:00:19.0 eth0: Failed to disable ULP
[ 1664.731040] asix 2-3:1.0 eth1: link up, 100Mbps, full-duplex, lpa 0xC1E1
[ 1665.093513] e1000e 0000:00:19.0 eth0: Hardware Error
[ 1665.596760] e1000e 0000:00:19.0: pci_pm_resume+0x0/0x80 returned 0 after 2975399 usecs

and then the system never recovers from it, and all the following suspend failed due to this
[22909.393854] PM: pci_pm_suspend(): e1000e_pm_suspend+0x0/0x760 [e1000e] returns -2
[22909.393858] PM: dpm_run_callback(): pci_pm_suspend+0x0/0x160 returns -2
[22909.393861] PM: Device 0000:00:1f.6 failed to suspend async: error -2

This can be avoided by changing the return values of __e1000_shutdown and
e1000e_pm_suspend functions so that they always return 0 (success). This
is consistent with what other drivers do.

If the e1000e driver encounters a hardware error during suspend, potential
side effects include slightly higher power draw or non-working wake on
LAN. This is preferred to a system-level suspend failure, and a warning
message is written to the system log, so that the user can be aware that
the LAN controller experienced a problem during suspend.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=205015
Suggested-by: Dima Ruinskiy <dima.ruinskiy@intel.com>
Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Tested-by: Mor Bar-Gabay <morx.bar.gabay@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
Vitaly Lifshits 2024-08-06 16:23:48 +03:00 committed by Greg Kroah-Hartman
parent 13ca2b3568
commit 1c6db07811

View File

@ -6672,8 +6672,10 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
if (adapter->flags2 & FLAG2_HAS_PHY_WAKEUP) { if (adapter->flags2 & FLAG2_HAS_PHY_WAKEUP) {
/* enable wakeup by the PHY */ /* enable wakeup by the PHY */
retval = e1000_init_phy_wakeup(adapter, wufc); retval = e1000_init_phy_wakeup(adapter, wufc);
if (retval) if (retval) {
return retval; e_err("Failed to enable wakeup\n");
goto skip_phy_configurations;
}
} else { } else {
/* enable wakeup by the MAC */ /* enable wakeup by the MAC */
ew32(WUFC, wufc); ew32(WUFC, wufc);
@ -6694,8 +6696,10 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
* or broadcast. * or broadcast.
*/ */
retval = e1000_enable_ulp_lpt_lp(hw, !runtime); retval = e1000_enable_ulp_lpt_lp(hw, !runtime);
if (retval) if (retval) {
return retval; e_err("Failed to enable ULP\n");
goto skip_phy_configurations;
}
} }
/* Force SMBUS to allow WOL */ /* Force SMBUS to allow WOL */
@ -6744,6 +6748,7 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
hw->phy.ops.release(hw); hw->phy.ops.release(hw);
} }
skip_phy_configurations:
/* Release control of h/w to f/w. If f/w is AMT enabled, this /* Release control of h/w to f/w. If f/w is AMT enabled, this
* would have already happened in close and is redundant. * would have already happened in close and is redundant.
*/ */
@ -6986,15 +6991,13 @@ static __maybe_unused int e1000e_pm_suspend(struct device *dev)
e1000e_pm_freeze(dev); e1000e_pm_freeze(dev);
rc = __e1000_shutdown(pdev, false); rc = __e1000_shutdown(pdev, false);
if (rc) { if (!rc) {
e1000e_pm_thaw(dev);
} else {
/* Introduce S0ix implementation */ /* Introduce S0ix implementation */
if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS) if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS)
e1000e_s0ix_entry_flow(adapter); e1000e_s0ix_entry_flow(adapter);
} }
return rc; return 0;
} }
static __maybe_unused int e1000e_pm_resume(struct device *dev) static __maybe_unused int e1000e_pm_resume(struct device *dev)