On Fri, May 22, 2026 at 04:33:12PM -0700, Dipayaan Roy wrote:
> 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: ca9c54d2d6a5 ("net: mana: Add a driver for Microsoft Azure Network
> Adapter (MANA)")
>
> Signed-off-by: Dipayaan Roy <[email protected]>
Hi,
I will send a v3 to fix the fixes tag issue highlighted in:
https://netdev-ctrl.bots.linux.dev/logs/build/1099669/14590738/verify_fixes/summary
> ---
> drivers/net/ethernet/microsoft/mana/mana_en.c | 70 +++++++++++--------
> 1 file changed, 41 insertions(+), 29 deletions(-)
>
> diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c
> b/drivers/net/ethernet/microsoft/mana/mana_en.c
> index 9afc786b297a..0582803907a8 100644
> --- a/drivers/net/ethernet/microsoft/mana/mana_en.c
> +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
> @@ -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);
> @@ -2858,13 +2861,16 @@ static void mana_destroy_vport(struct
> mana_port_context *apc)
> struct mana_rxq *rxq;
> u32 rxq_idx;
>
> - for (rxq_idx = 0; rxq_idx < apc->num_queues; rxq_idx++) {
> - rxq = apc->rxqs[rxq_idx];
> - if (!rxq)
> - continue;
> + if (apc->rxqs) {
>
> - mana_destroy_rxq(apc, rxq, true);
> - apc->rxqs[rxq_idx] = NULL;
> + for (rxq_idx = 0; rxq_idx < apc->num_queues; rxq_idx++) {
> + rxq = apc->rxqs[rxq_idx];
> + if (!rxq)
> + continue;
> +
> + mana_destroy_rxq(apc, rxq, true);
> + apc->rxqs[rxq_idx] = NULL;
> + }
> }
>
> mana_destroy_txq(apc);
> @@ -3269,7 +3275,8 @@ static int mana_dealloc_queues(struct net_device *ndev)
> if (apc->port_is_up)
> return -EINVAL;
>
> - mana_chn_setxdp(apc, NULL);
> + if (apc->rxqs)
> + mana_chn_setxdp(apc, NULL);
>
> if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode)
> mana_pf_deregister_filter(apc);
> @@ -3287,33 +3294,38 @@ static int mana_dealloc_queues(struct net_device
> *ndev)
> * number of queues.
> */
>
> - for (i = 0; i < apc->num_queues; i++) {
> - txq = &apc->tx_qp[i].txq;
> - tsleep = 1000;
> - while (atomic_read(&txq->pending_sends) > 0 &&
> - time_before(jiffies, timeout)) {
> - usleep_range(tsleep, tsleep + 1000);
> - tsleep <<= 1;
> - }
> - if (atomic_read(&txq->pending_sends)) {
> - 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),
> - txq->gdma_txq_id);
> + if (apc->tx_qp) {
> + for (i = 0; i < apc->num_queues; i++) {
> + txq = &apc->tx_qp[i].txq;
> + tsleep = 1000;
> + while (atomic_read(&txq->pending_sends) > 0 &&
> + time_before(jiffies, timeout)) {
> + usleep_range(tsleep, tsleep + 1000);
> + tsleep <<= 1;
> + }
> + if (atomic_read(&txq->pending_sends)) {
> + 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),
> + txq->gdma_txq_id);
> + }
> + break;
> }
> - break;
> }
> - }
>
> - for (i = 0; i < apc->num_queues; i++) {
> - txq = &apc->tx_qp[i].txq;
> - while ((skb = skb_dequeue(&txq->pending_skbs))) {
> - mana_unmap_skb(skb, apc);
> - dev_kfree_skb_any(skb);
> + for (i = 0; i < apc->num_queues; i++) {
> + txq = &apc->tx_qp[i].txq;
> + while ((skb = skb_dequeue(&txq->pending_skbs))) {
> + mana_unmap_skb(skb, apc);
> + dev_kfree_skb_any(skb);
> + }
> + atomic_set(&txq->pending_sends, 0);
> }
> - 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.
> */
> --
> 2.43.0
>
