While injecting PCIe errors to the upstream PCIe switch of
a BCM57810 NIC, system hangs/crashes were observed.
After several calls to bnx2x_tx_timout() complete,
bnx2x_nic_unload() is called to free up HW resources
and bnx2x_napi_disable() is called to release NAPI objects.
Later, when the EEH driver calls bnx2x_io_slot_reset() to
complete the recovery process, bnx2x attempts to disable
NAPI again by calling bnx2x_napi_disable() and freeing
resources which have already been freed, resulting in a
hang or crash.
Introduce a new flag to track the HW resource and NAPI
allocation state, refactor duplicated code into a single
function, check page pool allocation status before freeing,
and reduces debug output when a TX timeout event occurs.
Reviewed-by: Manish Chopra <manishc@marvell.com>
Tested-by: Abdul Haleem <abdhalee@in.ibm.com>
Tested-by: David Christensen <drc@linux.vnet.ibm.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Tested-by: Venkata Sai Duggi <venkata.sai.duggi@ibm.com>
Signed-off-by: Thinh Tran <thinhtr@linux.vnet.ibm.com>
Link: https://lore.kernel.org/r/20230818161443.708785-2-thinhtr@linux.vnet.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
bool cnic_loaded;
struct cnic_eth_dev *(*cnic_probe)(struct net_device *);
+ bool nic_stopped;
+
/* Flag that indicates that we can start looking for FCoE L2 queue
* completions in the default status block.
*/
bnx2x_add_all_napi(bp);
DP(NETIF_MSG_IFUP, "napi added\n");
bnx2x_napi_enable(bp);
+ bp->nic_stopped = false;
if (IS_PF(bp)) {
/* set pf load just before approaching the MCP */
load_error1:
bnx2x_napi_disable(bp);
bnx2x_del_all_napi(bp);
+ bp->nic_stopped = true;
/* clear pf_load status, as it was already set */
if (IS_PF(bp))
if (!CHIP_IS_E1x(bp))
bnx2x_pf_disable(bp);
- /* Disable HW interrupts, NAPI */
- bnx2x_netif_stop(bp, 1);
- /* Delete all NAPI objects */
- bnx2x_del_all_napi(bp);
- if (CNIC_LOADED(bp))
- bnx2x_del_all_napi_cnic(bp);
- /* Release IRQs */
- bnx2x_free_irq(bp);
+ if (!bp->nic_stopped) {
+ /* Disable HW interrupts, NAPI */
+ bnx2x_netif_stop(bp, 1);
+ /* Delete all NAPI objects */
+ bnx2x_del_all_napi(bp);
+ if (CNIC_LOADED(bp))
+ bnx2x_del_all_napi_cnic(bp);
+ /* Release IRQs */
+ bnx2x_free_irq(bp);
+ bp->nic_stopped = true;
+ }
/* Report UNLOAD_DONE to MCP */
bnx2x_send_unload_done(bp, false);
}
}
- /* Disable HW interrupts, NAPI */
- bnx2x_netif_stop(bp, 1);
- /* Delete all NAPI objects */
- bnx2x_del_all_napi(bp);
- if (CNIC_LOADED(bp))
- bnx2x_del_all_napi_cnic(bp);
+ if (!bp->nic_stopped) {
+ /* Disable HW interrupts, NAPI */
+ bnx2x_netif_stop(bp, 1);
+ /* Delete all NAPI objects */
+ bnx2x_del_all_napi(bp);
+ if (CNIC_LOADED(bp))
+ bnx2x_del_all_napi_cnic(bp);
- /* Release IRQs */
- bnx2x_free_irq(bp);
+ /* Release IRQs */
+ bnx2x_free_irq(bp);
+ bp->nic_stopped = true;
+ }
/* Reset the chip, unless PCI function is offline. If we reach this
* point following a PCI error handling, it means device is really
}
bnx2x_drain_tx_queues(bp);
bnx2x_send_unload_req(bp, UNLOAD_RECOVERY);
- bnx2x_netif_stop(bp, 1);
- bnx2x_del_all_napi(bp);
+ if (!bp->nic_stopped) {
+ bnx2x_netif_stop(bp, 1);
+ bnx2x_del_all_napi(bp);
- if (CNIC_LOADED(bp))
- bnx2x_del_all_napi_cnic(bp);
+ if (CNIC_LOADED(bp))
+ bnx2x_del_all_napi_cnic(bp);
- bnx2x_free_irq(bp);
+ bnx2x_free_irq(bp);
+ bp->nic_stopped = true;
+ }
/* Report UNLOAD_DONE to MCP */
bnx2x_send_unload_done(bp, true);
bnx2x_vfpf_finalize(bp, &req->first_tlv);
free_irq:
- /* Disable HW interrupts, NAPI */
- bnx2x_netif_stop(bp, 0);
- /* Delete all NAPI objects */
- bnx2x_del_all_napi(bp);
-
- /* Release IRQs */
- bnx2x_free_irq(bp);
+ if (!bp->nic_stopped) {
+ /* Disable HW interrupts, NAPI */
+ bnx2x_netif_stop(bp, 0);
+ /* Delete all NAPI objects */
+ bnx2x_del_all_napi(bp);
+
+ /* Release IRQs */
+ bnx2x_free_irq(bp);
+ bp->nic_stopped = true;
+ }
}
static void bnx2x_leading_vfq_init(struct bnx2x *bp, struct bnx2x_virtf *vf,