Commit 17bfe0a8 authored by Dipayaan Roy's avatar Dipayaan Roy Committed by Jakub Kicinski
Browse files

net: mana: Add NULL guards in teardown path to prevent panic on attach failure 



When queue allocation fails partway through, the error cleanup frees
and NULLs apc->tx_qp and apc->rxqs. Multiple teardown paths such as
mana_remove(), mana_change_mtu() recovery, and internal error handling
in mana_alloc_queues() can subsequently call into functions that
dereference these pointers without NULL checks:

- mana_chn_setxdp() dereferences apc->rxqs[0], causing a NULL pointer
  dereference panic (CR2: 0000000000000000 at mana_chn_setxdp+0x26).
- mana_destroy_vport() iterates apc->rxqs without a NULL check.
- mana_fence_rqs() iterates apc->rxqs without a NULL check.
- mana_dealloc_queues() iterates apc->tx_qp without a NULL check.

Add NULL guards for apc->rxqs in mana_fence_rqs(),
mana_destroy_vport(), and before the mana_chn_setxdp() call. Add a
NULL guard for apc->tx_qp in mana_dealloc_queues() to skip TX queue
draining when TX queues were never allocated or already freed.

Fixes: ca9c54d2 ("net: mana: Add a driver for Microsoft Azure Network Adapter (MANA)")
Reviewed-by: default avatarHaiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: default avatarDipayaan Roy <dipayanroy@linux.microsoft.com>
Link: https://patch.msgid.link/20260525081129.1230035-2-dipayanroy@linux.microsoft.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 3e200099

drivers/net/ethernet/microsoft/mana/mana_en.c

+41 −29
Original line number Diff line number Diff line
@@ -1727,6 +1727,9 @@ static void mana_fence_rqs(struct mana_port_context *apc) 
	struct mana_rxq *rxq;

	int err;



	if (!apc->rxqs)

		return;



	for (rxq_idx = 0; rxq_idx < apc->num_queues; rxq_idx++) {

		rxq = apc->rxqs[rxq_idx];

		err = mana_fence_rq(apc, rxq);
@@ -2858,6 +2861,8 @@ static void mana_destroy_vport(struct mana_port_context *apc) 
	struct mana_rxq *rxq;

	u32 rxq_idx;



	if (apc->rxqs) {



		for (rxq_idx = 0; rxq_idx < apc->num_queues; rxq_idx++) {

			rxq = apc->rxqs[rxq_idx];

			if (!rxq)
@@ -2866,6 +2871,7 @@ static void mana_destroy_vport(struct mana_port_context *apc) 
			mana_destroy_rxq(apc, rxq, true);

			apc->rxqs[rxq_idx] = NULL;

		}

	}



	mana_destroy_txq(apc);

	mana_uncfg_vport(apc);
@@ -3269,6 +3275,7 @@ static int mana_dealloc_queues(struct net_device *ndev) 
	if (apc->port_is_up)

		return -EINVAL;



	if (apc->rxqs)

		mana_chn_setxdp(apc, NULL);



	if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode)
@@ -3287,6 +3294,7 @@ static int mana_dealloc_queues(struct net_device *ndev) 
	 * number of queues.

	 */



	if (apc->tx_qp) {

		for (i = 0; i < apc->num_queues; i++) {

			txq = &apc->tx_qp[i].txq;

			tsleep = 1000;
@@ -3296,10 +3304,12 @@ static int mana_dealloc_queues(struct net_device *ndev) 
				tsleep <<= 1;

			}

			if (atomic_read(&txq->pending_sends)) {

			err = pcie_flr(to_pci_dev(gd->gdma_context->dev));

				err =

				    pcie_flr(to_pci_dev(gd->gdma_context->dev));

				if (err) {

					netdev_err(ndev, "flr failed %d with %d pkts pending in txq %u\n",

					   err, atomic_read(&txq->pending_sends),

						   err,

					    atomic_read(&txq->pending_sends),

					    txq->gdma_txq_id);

				}

				break;
@@ -3314,6 +3324,8 @@ static int mana_dealloc_queues(struct net_device *ndev) 
			}

			atomic_set(&txq->pending_sends, 0);

		}

	}



	/* We're 100% sure the queues can no longer be woken up, because

	 * we're sure now mana_poll_tx_cq() can't be running.

	 */