From 0288c3e709e5fabd51e84715c5c798a02f43061a Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Wed, 11 Oct 2023 16:33:33 -0700 Subject: ice: reset first in crash dump kernels When the system boots into the crash dump kernel after a panic, the ice networking device may still have pending transactions that can cause errors or machine checks when the device is re-enabled. This can prevent the crash dump kernel from loading the driver or collecting the crash data. To avoid this issue, perform a function level reset (FLR) on the ice device via PCIe config space before enabling it on the crash kernel. This will clear any outstanding transactions and stop all queues and interrupts. Restore the config space after the FLR, otherwise it was found in testing that the driver wouldn't load successfully. The following sequence causes the original issue: - Load the ice driver with modprobe ice - Enable SR-IOV with 2 VFs: echo 2 > /sys/class/net/eth0/device/sriov_num_vfs - Trigger a crash with echo c > /proc/sysrq-trigger - Load the ice driver again (or let it load automatically) with modprobe ice - The system crashes again during pcim_enable_device() Fixes: 837f08fdecbe ("ice: Add basic driver framework for Intel(R) E800 Series") Reported-by: Vishal Agrawal Reviewed-by: Jay Vosburgh Reviewed-by: Przemek Kitszel Signed-off-by: Jesse Brandeburg Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Link: https://lore.kernel.org/r/20231011233334.336092-3-jacob.e.keller@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/ice/ice_main.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'drivers/net/ethernet/intel/ice/ice_main.c') diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index c8286adae946..6550c46e4e36 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -6,6 +6,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include +#include #include "ice.h" #include "ice_base.h" #include "ice_lib.h" @@ -5014,6 +5015,20 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) return -EINVAL; } + /* when under a kdump kernel initiate a reset before enabling the + * device in order to clear out any pending DMA transactions. These + * transactions can cause some systems to machine check when doing + * the pcim_enable_device() below. + */ + if (is_kdump_kernel()) { + pci_save_state(pdev); + pci_clear_master(pdev); + err = pcie_flr(pdev); + if (err) + return err; + pci_restore_state(pdev); + } + /* this driver uses devres, see * Documentation/driver-api/driver-model/devres.rst */ -- cgit From 42066c4d5d344cdf8564556cdbe0aa36854fefa4 Mon Sep 17 00:00:00 2001 From: Mateusz Pacuszka Date: Wed, 11 Oct 2023 16:33:34 -0700 Subject: ice: Fix safe mode when DDP is missing One thing is broken in the safe mode, that is ice_deinit_features() is being executed even that ice_init_features() was not causing stack trace during pci_unregister_driver(). Add check on the top of the function. Fixes: 5b246e533d01 ("ice: split probe into smaller functions") Signed-off-by: Mateusz Pacuszka Signed-off-by: Jan Sokolowski Reviewed-by: Przemek Kitszel Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Link: https://lore.kernel.org/r/20231011233334.336092-4-jacob.e.keller@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/ice/ice_main.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/net/ethernet/intel/ice/ice_main.c') diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 6550c46e4e36..7784135160fd 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4684,6 +4684,9 @@ static void ice_init_features(struct ice_pf *pf) static void ice_deinit_features(struct ice_pf *pf) { + if (ice_is_safe_mode(pf)) + return; + ice_deinit_lag(pf); if (test_bit(ICE_FLAG_DCB_CAPABLE, pf->flags)) ice_cfg_lldp_mib_change(&pf->hw, false); -- cgit