RE: [PATCH net-next v2 1/4] net: mana: Fix potential deadlocks in mana napi ops

[Long Li]

> Subject: [PATCH net-next v2 1/4] net: mana: Fix potential deadlocks in mana napi
> ops
> 
> When net_shaper_ops are enabled for MANA, netdev_ops_lock becomes active.
> 
> MANA VF setup/teardown by netvsc follows this call chain:
> 
> netvsc_vf_setup()
>         dev_change_flags()
> 		...
>          __dev_open() OR __dev_close()
> 
> dev_change_flags() holds the netdev mutex via netdev_lock_ops.
> 
> Meanwhile, mana_create_txq() and mana_create_rxq() in mana_open() path call
> NAPI APIs (netif_napi_add_tx(), netif_napi_add_weight(), napi_enable()), which
> also try to acquire the same lock, risking deadlock.
> 
> Similarly in the teardown path (mana_close()), netif_napi_disable() and
> netif_napi_del(), contend for the same lock.
> 
> Switch to the _locked variants of these APIs to avoid deadlocks when the
> netdev_ops_lock is held.
> 
> Fixes: d4c22ec680c8 ("net: hold netdev instance lock during
> ndo_open/ndo_stop")
> Signed-off-by: Erni Sri Satya Vennela <ernis@xxxxxxxxxxxxxxxxxxx>
> Reviewed-by: Haiyang Zhang <haiyangz@xxxxxxxxxxxxx>
> Reviewed-by: Shradha Gupta <shradhagupta@xxxxxxxxxxxxxxxxxxx>
> Reviewed-by: Saurabh Singh Sengar <ssengar@xxxxxxxxxxxxxxxxxxx>

Reviewed-by: Long Li <longli@xxxxxxxxxxxxx>

> ---
> Changes in v2:
> * Use netdev_lock_ops_to_full() instead of if...else statements for napi
>   APIs.
> * Edit commit message.
> ---
>  drivers/net/ethernet/microsoft/mana/mana_en.c | 30 +++++++++++++------
>  1 file changed, 21 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c
> b/drivers/net/ethernet/microsoft/mana/mana_en.c
> index e68b8190bb7a..ca5e9c3d374b 100644
> --- a/drivers/net/ethernet/microsoft/mana/mana_en.c
> +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
> @@ -1912,8 +1912,11 @@ static void mana_destroy_txq(struct
> mana_port_context *apc)
>  		napi = &apc->tx_qp[i].tx_cq.napi;
>  		if (apc->tx_qp[i].txq.napi_initialized) {
>  			napi_synchronize(napi);
> -			napi_disable(napi);
> -			netif_napi_del(napi);
> +			netdev_lock_ops_to_full(napi->dev);
> +			napi_disable_locked(napi);
> +			netif_napi_del_locked(napi);
> +			netdev_unlock_full_to_ops(napi->dev);
>  			apc->tx_qp[i].txq.napi_initialized = false;
>  		}
>  		mana_destroy_wq_obj(apc, GDMA_SQ, apc-
> >tx_qp[i].tx_object); @@ -2065,8 +2068,11 @@ static int
> mana_create_txq(struct mana_port_context *apc,
> 
>  		mana_create_txq_debugfs(apc, i);
> 
> -		netif_napi_add_tx(net, &cq->napi, mana_poll);
> -		napi_enable(&cq->napi);
> +		set_bit(NAPI_STATE_NO_BUSY_POLL, &cq->napi.state);
> +		netdev_lock_ops_to_full(net);
> +		netif_napi_add_locked(net, &cq->napi, mana_poll);
> +		napi_enable_locked(&cq->napi);
> +		netdev_unlock_full_to_ops(net);
>  		txq->napi_initialized = true;
> 
>  		mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT); @@ -2102,9
> +2108,11 @@ static void mana_destroy_rxq(struct mana_port_context *apc,
>  	if (napi_initialized) {
>  		napi_synchronize(napi);
> 
> -		napi_disable(napi);
> -
> -		netif_napi_del(napi);
> +		netdev_lock_ops_to_full(napi->dev);
> +		napi_disable_locked(napi);
> +		netif_napi_del_locked(napi);
> +		netdev_unlock_full_to_ops(napi->dev);
>  	}
>  	xdp_rxq_info_unreg(&rxq->xdp_rxq);
> 
> @@ -2355,14 +2363,18 @@ static struct mana_rxq *mana_create_rxq(struct
> mana_port_context *apc,
> 
>  	gc->cq_table[cq->gdma_id] = cq->gdma_cq;
> 
> -	netif_napi_add_weight(ndev, &cq->napi, mana_poll, 1);
> +	netdev_lock_ops_to_full(ndev);
> +	netif_napi_add_weight_locked(ndev, &cq->napi, mana_poll, 1);
> +	netdev_unlock_full_to_ops(ndev);
> 
>  	WARN_ON(xdp_rxq_info_reg(&rxq->xdp_rxq, ndev, rxq_idx,
>  				 cq->napi.napi_id));
>  	WARN_ON(xdp_rxq_info_reg_mem_model(&rxq->xdp_rxq,
> MEM_TYPE_PAGE_POOL,
>  					   rxq->page_pool));
> 
> -	napi_enable(&cq->napi);
> +	netdev_lock_ops_to_full(ndev);
> +	napi_enable_locked(&cq->napi);
> +	netdev_unlock_full_to_ops(ndev);
> 
>  	mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT);
>  out:
> --
> 2.34.1