Merge branch 'intel-wired-lan-driver-updates-2023-10-11-i40e-ice'

Jacob Keller says:

====================
Intel Wired LAN Driver Updates 2023-10-11 (i40e, ice)

This series contains fixes for the i40e and ice drivers.

Jesse adds handling to the ice driver which resetis the device when loading
on a crash kernel, preventing stale transactions from causing machine check
exceptions which could prevent capturing crash data.

Mateusz fixes a bug in the ice driver 'Safe mode' logic for handling the
device when the DDP is missing.

Michal fixes a crash when probing the i40e driver in the event that HW
registers are reporting invalid/unexpected values.

The following are changes since commit a950a59:
  net/smc: Fix pos miscalculation in statistics

I'm covering for Tony Nguyen while he's out, and don't have access to create
a pull request branch on his net-queue, so these are sent via mail only.
====================

Link: https://lore.kernel.org/r/20231011233334.336092-1-jacob.e.keller@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Author: kuba-moo

drivers/net/ethernet/intel/i40e/i40e_common.c

@@ -1082,7 +1082,7 @@ void i40e_clear_hw(struct i40e_hw *hw)
 		     I40E_PFLAN_QALLOC_FIRSTQ_SHIFT;
 	j = (val & I40E_PFLAN_QALLOC_LASTQ_MASK) >>
 	    I40E_PFLAN_QALLOC_LASTQ_SHIFT;
-	if (val & I40E_PFLAN_QALLOC_VALID_MASK)
+	if (val & I40E_PFLAN_QALLOC_VALID_MASK && j >= base_queue)
 		num_queues = (j - base_queue) + 1;
 	else
 		num_queues = 0;
@@ -1092,7 +1092,7 @@ void i40e_clear_hw(struct i40e_hw *hw)
 	    I40E_PF_VT_PFALLOC_FIRSTVF_SHIFT;
 	j = (val & I40E_PF_VT_PFALLOC_LASTVF_MASK) >>
 	    I40E_PF_VT_PFALLOC_LASTVF_SHIFT;
-	if (val & I40E_PF_VT_PFALLOC_VALID_MASK)
+	if (val & I40E_PF_VT_PFALLOC_VALID_MASK && j >= i)
 		num_vfs = (j - i) + 1;
 	else
 		num_vfs = 0;

drivers/net/ethernet/intel/ice/ice_main.c

@@ -6,6 +6,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <generated/utsrelease.h>
+#include <linux/crash_dump.h>
 #include "ice.h"
 #include "ice_base.h"
 #include "ice_lib.h"
@@ -4683,6 +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);
@@ -5014,6 +5018,20 @@ 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
 	 */