Hi,
On Mon, Feb 7, 2022 at 9:48 AM Miquel Raynal <miquel.raynal@xxxxxxxxxxx> wrote:
>
> Right now we are able to stop a queue but we have no indication if a
> transmission is ongoing or not.
>
> Thanks to recent additions, we can track the number of ongoing
> transmissions so we know if the last transmission is over. Adding on top
> of it an internal wait queue also allows to be woken up asynchronously
> when this happens. If, beforehands, we marked the queue to be held and
> stopped it, we end up flushing and stopping the tx queue.
>
> Thanks to this feature, we will soon be able to introduce a synchronous
> transmit API.
>
> Signed-off-by: Miquel Raynal <miquel.raynal@xxxxxxxxxxx>
> ---
> include/net/cfg802154.h | 1 +
> net/ieee802154/core.c | 1 +
> net/mac802154/cfg.c | 5 ++---
> net/mac802154/ieee802154_i.h | 1 +
> net/mac802154/tx.c | 11 ++++++++++-
> net/mac802154/util.c | 3 ++-
> 6 files changed, 17 insertions(+), 5 deletions(-)
>
> diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
> index 043d8e4359e7..0d385a214da3 100644
> --- a/include/net/cfg802154.h
> +++ b/include/net/cfg802154.h
> @@ -217,6 +217,7 @@ struct wpan_phy {
> /* Transmission monitoring and control */
> atomic_t ongoing_txs;
> atomic_t hold_txs;
> + wait_queue_head_t sync_txq;
>
> char priv[] __aligned(NETDEV_ALIGN);
> };
> diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
> index de259b5170ab..0953cacafbff 100644
> --- a/net/ieee802154/core.c
> +++ b/net/ieee802154/core.c
> @@ -129,6 +129,7 @@ wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size)
> wpan_phy_net_set(&rdev->wpan_phy, &init_net);
>
> init_waitqueue_head(&rdev->dev_wait);
> + init_waitqueue_head(&rdev->wpan_phy.sync_txq);
>
> return &rdev->wpan_phy;
> }
> diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
> index e8aabf215286..da94aaa32fcb 100644
> --- a/net/mac802154/cfg.c
> +++ b/net/mac802154/cfg.c
> @@ -46,8 +46,7 @@ static int ieee802154_suspend(struct wpan_phy *wpan_phy)
> if (!local->open_count)
> goto suspend;
>
> - atomic_inc(&wpan_phy->hold_txs);
> - ieee802154_stop_queue(&local->hw);
> + ieee802154_sync_and_stop_tx(local);
> synchronize_net();
>
> /* stop hardware - this must stop RX */
> @@ -73,7 +72,7 @@ static int ieee802154_resume(struct wpan_phy *wpan_phy)
> return ret;
>
> wake_up:
> - if (!atomic_dec_and_test(&wpan_phy->hold_txs))
> + if (!atomic_read(&wpan_phy->hold_txs))
> ieee802154_wake_queue(&local->hw);
> local->suspended = false;
> return 0;
> diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
> index 56fcd7ef5b6f..295c9ce091e1 100644
> --- a/net/mac802154/ieee802154_i.h
> +++ b/net/mac802154/ieee802154_i.h
> @@ -122,6 +122,7 @@ extern struct ieee802154_mlme_ops mac802154_mlme_wpan;
>
> void ieee802154_rx(struct ieee802154_local *local, struct sk_buff *skb);
> void ieee802154_xmit_sync_worker(struct work_struct *work);
> +void ieee802154_sync_and_stop_tx(struct ieee802154_local *local);
> netdev_tx_t
> ieee802154_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev);
> netdev_tx_t
> diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c
> index abd9a057521e..06ae2e6cea43 100644
> --- a/net/mac802154/tx.c
> +++ b/net/mac802154/tx.c
> @@ -47,7 +47,8 @@ void ieee802154_xmit_sync_worker(struct work_struct *work)
> ieee802154_wake_queue(&local->hw);
>
> kfree_skb(skb);
> - atomic_dec(&local->phy->ongoing_txs);
> + if (!atomic_dec_and_test(&local->phy->ongoing_txs))
> + wake_up(&local->phy->sync_txq);
> netdev_dbg(dev, "transmission failed\n");
> }
>
> @@ -117,6 +118,14 @@ ieee802154_hot_tx(struct ieee802154_local *local, struct sk_buff *skb)
> return ieee802154_tx(local, skb);
> }
>
> +void ieee802154_sync_and_stop_tx(struct ieee802154_local *local)
> +{
> + atomic_inc(&local->phy->hold_txs);
> + ieee802154_stop_queue(&local->hw);
> + wait_event(local->phy->sync_txq, !atomic_read(&local->phy->ongoing_txs));
> + atomic_dec(&local->phy->hold_txs);
In my opinion this _still_ races as I mentioned earlier. You need to
be sure that if you do ieee802154_stop_queue() that no ieee802154_tx()
or hot_tx() is running at this time. Look into the function I
mentioned earlier "?netif_tx_disable()?".
- Alex
