From a7dfeda6fdeccab4c7c3dce9a72c4262b9530c80 Mon Sep 17 00:00:00 2001 From: Souradeep Chakrabarti Date: Wed, 9 Aug 2023 03:22:05 -0700 Subject: net: mana: Fix MANA VF unload when hardware is unresponsive When unloading the MANA driver, mana_dealloc_queues() waits for the MANA hardware to complete any inflight packets and set the pending send count to zero. But if the hardware has failed, mana_dealloc_queues() could wait forever. Fix this by adding a timeout to the wait. Set the timeout to 120 seconds, which is a somewhat arbitrary value that is more than long enough for functional hardware to complete any sends. Cc: stable@vger.kernel.org Fixes: ca9c54d2d6a5 ("net: mana: Add a driver for Microsoft Azure Network Adapter (MANA)") Signed-off-by: Souradeep Chakrabarti Link: https://lore.kernel.org/r/1691576525-24271-1-git-send-email-schakrabarti@linux.microsoft.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/microsoft/mana/mana_en.c | 37 ++++++++++++++++++++++++--- 1 file changed, 33 insertions(+), 4 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index a499e460594b..c2ad0921e893 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -2345,9 +2346,12 @@ int mana_attach(struct net_device *ndev) static int mana_dealloc_queues(struct net_device *ndev) { struct mana_port_context *apc = netdev_priv(ndev); + unsigned long timeout = jiffies + 120 * HZ; struct gdma_dev *gd = apc->ac->gdma_dev; struct mana_txq *txq; + struct sk_buff *skb; int i, err; + u32 tsleep; if (apc->port_is_up) return -EINVAL; @@ -2363,15 +2367,40 @@ static int mana_dealloc_queues(struct net_device *ndev) * to false, but it doesn't matter since mana_start_xmit() drops any * new packets due to apc->port_is_up being false. * - * Drain all the in-flight TX packets + * Drain all the in-flight TX packets. + * A timeout of 120 seconds for all the queues is used. + * This will break the while loop when h/w is not responding. + * This value of 120 has been decided here considering max + * number of queues. */ + for (i = 0; i < apc->num_queues; i++) { txq = &apc->tx_qp[i].txq; - - while (atomic_read(&txq->pending_sends) > 0) - usleep_range(1000, 2000); + 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; + } } + 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); + } /* 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. */ -- cgit v1.2.3