netdev - Re: [PATCH net-next v3 05/15] net: Proxy net_mp_{open,close}

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <bbab235a-826c-4051-930f-e4209da0c067@davidwei.uk>
Date: Tue, 28 Oct 2025 19:07:30 -0700
From: David Wei <dw@...idwei.uk>
To: Stanislav Fomichev <stfomichev@...il.com>,
 Daniel Borkmann <daniel@...earbox.net>
Cc: netdev@...r.kernel.org, bpf@...r.kernel.org, kuba@...nel.org,
 davem@...emloft.net, razor@...ckwall.org, pabeni@...hat.com,
 willemb@...gle.com, sdf@...ichev.me, john.fastabend@...il.com,
 martin.lau@...nel.org, jordan@...fe.io, maciej.fijalkowski@...el.com,
 magnus.karlsson@...el.com, toke@...hat.com, yangzhenze@...edance.com,
 wangdongdong.6@...edance.com
Subject: Re: [PATCH net-next v3 05/15] net: Proxy net_mp_{open,close}_rxq for
 mapped queues

On 2025-10-24 11:36, Stanislav Fomichev wrote:
> On 10/20, Daniel Borkmann wrote:
>> From: David Wei <dw@...idwei.uk>
>>
>> When a process in a container wants to setup a memory provider, it will
>> use the virtual netdev and a mapped rxq, and call net_mp_{open,close}_rxq
>> to try and restart the queue. At this point, proxy the queue restart on
>> the real rxq in the physical netdev.
>>
>> For memory providers (io_uring zero-copy rx and devmem), it causes the
>> real rxq in the physical netdev to be filled from a memory provider that
>> has DMA mapped memory from a process within a container.
>>
>> Signed-off-by: David Wei <dw@...idwei.uk>
>> Co-developed-by: Daniel Borkmann <daniel@...earbox.net>
>> Signed-off-by: Daniel Borkmann <daniel@...earbox.net>
>> ---
>>   include/net/page_pool/memory_provider.h |  4 +-
>>   net/core/netdev_rx_queue.c              | 57 +++++++++++++++++--------
>>   2 files changed, 41 insertions(+), 20 deletions(-)
>>
>> diff --git a/include/net/page_pool/memory_provider.h b/include/net/page_pool/memory_provider.h
>> index ada4f968960a..b6f811c3416b 100644
>> --- a/include/net/page_pool/memory_provider.h
>> +++ b/include/net/page_pool/memory_provider.h
>> @@ -23,12 +23,12 @@ bool net_mp_niov_set_dma_addr(struct net_iov *niov, dma_addr_t addr);
>>   void net_mp_niov_set_page_pool(struct page_pool *pool, struct net_iov *niov);
>>   void net_mp_niov_clear_page_pool(struct net_iov *niov);
>>   
>> -int net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx,
>> +int net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx,
>>   		    struct pp_memory_provider_params *p);
>>   int __net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx,
>>   		      const struct pp_memory_provider_params *p,
>>   		      struct netlink_ext_ack *extack);
>> -void net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx,
>> +void net_mp_close_rxq(struct net_device *dev, unsigned int rxq_idx,
>>   		      struct pp_memory_provider_params *old_p);
>>   void __net_mp_close_rxq(struct net_device *dev, unsigned int rxq_idx,
>>   			const struct pp_memory_provider_params *old_p);
>> diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
>> index 8ee289316c06..b4ff3497e086 100644
>> --- a/net/core/netdev_rx_queue.c
>> +++ b/net/core/netdev_rx_queue.c
>> @@ -170,48 +170,63 @@ int __net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx,
>>   		      struct netlink_ext_ack *extack)
>>   {
>>   	struct netdev_rx_queue *rxq;
>> +	bool needs_unlock = false;
>>   	int ret;
>>   
>>   	if (!netdev_need_ops_lock(dev))
>>   		return -EOPNOTSUPP;
>> -
>>   	if (rxq_idx >= dev->real_num_rx_queues) {
>>   		NL_SET_ERR_MSG(extack, "rx queue index out of range");
>>   		return -ERANGE;
>>   	}
>> -	rxq_idx = array_index_nospec(rxq_idx, dev->real_num_rx_queues);
>>   
>> +	rxq_idx = array_index_nospec(rxq_idx, dev->real_num_rx_queues);
>> +	rxq = netif_get_rx_queue_peer_locked(&dev, &rxq_idx, &needs_unlock);
>> +	if (!rxq) {
>> +		NL_SET_ERR_MSG(extack, "rx queue peered to a virtual netdev");
>> +		return -EBUSY;
>> +	}
>> +	if (!dev->dev.parent) {
>> +		NL_SET_ERR_MSG(extack, "rx queue is mapped to a virtual netdev");
>> +		ret = -EBUSY;
>> +		goto out;
>> +	}
>>   	if (dev->cfg->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED) {
>>   		NL_SET_ERR_MSG(extack, "tcp-data-split is disabled");
>> -		return -EINVAL;
>> +		ret = -EINVAL;
>> +		goto out;
>>   	}
>>   	if (dev->cfg->hds_thresh) {
>>   		NL_SET_ERR_MSG(extack, "hds-thresh is not zero");
>> -		return -EINVAL;
>> +		ret = -EINVAL;
>> +		goto out;
>>   	}
>>   	if (dev_xdp_prog_count(dev)) {
>>   		NL_SET_ERR_MSG(extack, "unable to custom memory provider to device with XDP program attached");
>> -		return -EEXIST;
>> +		ret = -EEXIST;
>> +		goto out;
>>   	}
>> -
>> -	rxq = __netif_get_rx_queue(dev, rxq_idx);
>>   	if (rxq->mp_params.mp_ops) {
>>   		NL_SET_ERR_MSG(extack, "designated queue already memory provider bound");
>> -		return -EEXIST;
>> +		ret = -EEXIST;
>> +		goto out;
>>   	}
>>   #ifdef CONFIG_XDP_SOCKETS
>>   	if (rxq->pool) {
>>   		NL_SET_ERR_MSG(extack, "designated queue already in use by AF_XDP");
>> -		return -EBUSY;
>> +		ret = -EBUSY;
>> +		goto out;
>>   	}
>>   #endif
>> -
>>   	rxq->mp_params = *p;
>>   	ret = netdev_rx_queue_restart(dev, rxq_idx);
>>   	if (ret) {
>>   		rxq->mp_params.mp_ops = NULL;
>>   		rxq->mp_params.mp_priv = NULL;
>>   	}
>> +out:
>> +	if (needs_unlock)
>> +		netdev_unlock(dev);
> 
> Can we do something better than needs_unlock flag? Maybe something like the
> following?
> 
> netif_put_rx_queue_peer_locked(orig_dev, dev)
> {
> 	if (orig_dev != dev)
> 		netdev_unlock(dev);
> }
> 
> Then we can do:
> 
> orig_dev = dev;
> rxq = netif_get_rx_queue_peer_locked(&dev, &rx_idx);
> ...
> netif_put_rx_queue_peer_locked(orig_dev, dev);

Thanks, that's a lot cleaner, changed in v4.