Commit bf23ffc8 authored by Thinh Tran's avatar Thinh Tran Committed by Jakub Kicinski
Browse files

bnx2x: new flag for track HW resource allocation 



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: default avatarManish Chopra <manishc@marvell.com>
Tested-by: default avatarAbdul Haleem <abdhalee@in.ibm.com>
Tested-by: default avatarDavid Christensen <drc@linux.vnet.ibm.com>
Reviewed-by: default avatarSimon Horman <simon.horman@corigine.com>
Tested-by: default avatarVenkata Sai Duggi <venkata.sai.duggi@ibm.com>
Signed-off-by: default avatarThinh Tran <thinhtr@linux.vnet.ibm.com>
Link: https://lore.kernel.org/r/20230818161443.708785-2-thinhtr@linux.vnet.ibm.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 6dc5774d

drivers/net/ethernet/broadcom/bnx2x/bnx2x.h

+2 −0
Original line number Diff line number Diff line
@@ -1508,6 +1508,8 @@ struct bnx2x { 
	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.

	 */

drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c

+13 −8
Original line number Diff line number Diff line
@@ -2715,6 +2715,7 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) 
	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 */
@@ -2960,6 +2961,7 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) 
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))
@@ -3095,6 +3097,7 @@ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode, bool keep_link) 
		if (!CHIP_IS_E1x(bp))

			bnx2x_pf_disable(bp);



		if (!bp->nic_stopped) {

			/* Disable HW interrupts, NAPI */

			bnx2x_netif_stop(bp, 1);

			/* Delete all NAPI objects */
@@ -3103,6 +3106,8 @@ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode, bool keep_link) 
				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);

drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c

+19 −13
Original line number Diff line number Diff line
@@ -9474,6 +9474,7 @@ void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode, bool keep_link) 
		}

	}



	if (!bp->nic_stopped) {

		/* Disable HW interrupts, NAPI */

		bnx2x_netif_stop(bp, 1);

		/* Delete all NAPI objects */
@@ -9483,6 +9484,8 @@ void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode, bool keep_link) 


		/* 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
@@ -14238,6 +14241,7 @@ static pci_ers_result_t bnx2x_io_slot_reset(struct pci_dev *pdev) 
		}

		bnx2x_drain_tx_queues(bp);

		bnx2x_send_unload_req(bp, UNLOAD_RECOVERY);

		if (!bp->nic_stopped) {

			bnx2x_netif_stop(bp, 1);

			bnx2x_del_all_napi(bp);
@@ -14245,6 +14249,8 @@ static pci_ers_result_t bnx2x_io_slot_reset(struct pci_dev *pdev) 
				bnx2x_del_all_napi_cnic(bp);



			bnx2x_free_irq(bp);

			bp->nic_stopped = true;

		}



		/* Report UNLOAD_DONE to MCP */

		bnx2x_send_unload_done(bp, true);

drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c

+10 −7
Original line number Diff line number Diff line
@@ -529,6 +529,7 @@ void bnx2x_vfpf_close_vf(struct bnx2x *bp) 
	bnx2x_vfpf_finalize(bp, &req->first_tlv);



free_irq:

	if (!bp->nic_stopped) {

		/* Disable HW interrupts, NAPI */

		bnx2x_netif_stop(bp, 0);

		/* Delete all NAPI objects */
@@ -536,6 +537,8 @@ void bnx2x_vfpf_close_vf(struct bnx2x *bp) 


		/* Release IRQs */

		bnx2x_free_irq(bp);

		bp->nic_stopped = true;

	}

}



static void bnx2x_leading_vfq_init(struct bnx2x *bp, struct bnx2x_virtf *vf,