diff options
| author | Konrad Knitter <konrad.knitter@intel.com> | 2024-11-06 10:36:43 +0100 |
|---|---|---|
| committer | Tony Nguyen <anthony.l.nguyen@intel.com> | 2025-01-16 13:05:06 -0800 |
| commit | 1de25c6b984d71a7961065e27514b4fd51b2daae (patch) | |
| tree | 96f2b32817af0926a26656b4a50a556c0bf72809 /drivers/net/ethernet/intel/ice/ice_main.c | |
| parent | 0502bd2e06055646f43871f76fb7bdd57f7c0939 (diff) | |
| download | lwn-1de25c6b984d71a7961065e27514b4fd51b2daae.tar.gz lwn-1de25c6b984d71a7961065e27514b4fd51b2daae.zip | |
ice: support FW Recovery Mode
Recovery Mode is intended to recover from a fatal failure scenario in
which the device is not accessible to the host, meaning the firmware is
non-responsive.
The purpose of the Firmware Recovery Mode is to enable software tools to
update firmware and/or device configuration so the fatal error can be
resolved.
Recovery Mode Firmware supports a limited set of admin commands required
for NVM update.
Recovery Firmware does not support hardware interrupts so a polling mode
is used.
The driver will expose only the minimum set of devlink commands required
for the recovery of the adapter.
Using an appropriate NVM image, the user can recover the adapter using
the devlink flash API.
Prior to 4.20 E810 Adapter Recovery Firmware supports only the update
and erase of the "fw.mgmt" component.
E810 Adapter Recovery Firmware doesn't support selected preservation of
cards settings or identifiers.
The following command can be used to recover the adapter:
$ devlink dev flash <pci-address> <update-image.bin> component fw.mgmt
overwrite settings overwrite identifier
Newer FW versions (4.20 or newer) supports update of "fw.undi" and
"fw.netlist" components.
$ devlink dev flash <pci-address> <update-image.bin>
Tested on Intel Corporation Ethernet Controller E810-C for SFP
FW revision 3.20 and 4.30.
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Konrad Knitter <konrad.knitter@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Diffstat (limited to 'drivers/net/ethernet/intel/ice/ice_main.c')
| -rw-r--r-- | drivers/net/ethernet/intel/ice/ice_main.c | 53 |
1 files changed, 53 insertions, 0 deletions
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 749b5e29e83a..2205ea871209 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2364,6 +2364,18 @@ static void ice_check_media_subtask(struct ice_pf *pf) } } +static void ice_service_task_recovery_mode(struct work_struct *work) +{ + struct ice_pf *pf = container_of(work, struct ice_pf, serv_task); + + set_bit(ICE_ADMINQ_EVENT_PENDING, pf->state); + ice_clean_adminq_subtask(pf); + + ice_service_task_complete(pf); + + mod_timer(&pf->serv_tmr, jiffies + msecs_to_jiffies(100)); +} + /** * ice_service_task - manage and run subtasks * @work: pointer to work_struct contained by the PF struct @@ -5217,6 +5229,36 @@ void ice_unload(struct ice_pf *pf) ice_decfg_netdev(vsi); } +static int ice_probe_recovery_mode(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + + dev_err(dev, "Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode\n"); + + INIT_HLIST_HEAD(&pf->aq_wait_list); + spin_lock_init(&pf->aq_wait_lock); + init_waitqueue_head(&pf->aq_wait_queue); + + timer_setup(&pf->serv_tmr, ice_service_timer, 0); + pf->serv_tmr_period = HZ; + INIT_WORK(&pf->serv_task, ice_service_task_recovery_mode); + clear_bit(ICE_SERVICE_SCHED, pf->state); + err = ice_create_all_ctrlq(&pf->hw); + if (err) + return err; + + scoped_guard(devl, priv_to_devlink(pf)) { + err = ice_init_devlink(pf); + if (err) + return err; + } + + ice_service_task_restart(pf); + + return 0; +} + /** * ice_probe - Device initialization routine * @pdev: PCI device information struct @@ -5308,6 +5350,9 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) hw->debug_mask = debug; #endif + if (ice_is_recovery_mode(hw)) + return ice_probe_recovery_mode(pf); + err = ice_init_hw(hw); if (err) { dev_err(dev, "ice_init_hw failed: %d\n", err); @@ -5425,6 +5470,14 @@ static void ice_remove(struct pci_dev *pdev) msleep(100); } + if (ice_is_recovery_mode(&pf->hw)) { + ice_service_task_stop(pf); + scoped_guard(devl, priv_to_devlink(pf)) { + ice_deinit_devlink(pf); + } + return; + } + if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) { set_bit(ICE_VF_RESETS_DISABLED, pf->state); ice_free_vfs(pf); |