diff mbox series

[net-next,v6,2/4] netdevsim: forward skbs from one connected port to another

Message ID 20240126012357.535494-3-dw@davidwei.uk (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series netdevsim: link and forward skbs between ports | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 1064 this patch: 1064
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers success CCed 0 of 0 maintainers
netdev/build_clang success Errors and warnings before: 1081 this patch: 1081
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 1081 this patch: 1081
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 59 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

David Wei Jan. 26, 2024, 1:23 a.m. UTC
Forward skbs sent from one netdevsim port to its connected netdevsim
port using dev_forward_skb, in a spirit similar to veth.

Add a tx_dropped variable to struct netdevsim, tracking the number of
skbs that could not be forwarded using dev_forward_skb().

The xmit() function accessing the peer ptr is protected by an RCU read
critical section. The rcu_read_lock() is functionally redundant as since
v5.0 all softirqs are implicitly RCU read critical sections; but it is
useful for human readers.

If another CPU is concurrently in nsim_destroy(), then it will first set
the peer ptr to NULL. This does not affect any existing readers that
dereferenced a non-NULL peer. Then, in unregister_netdevice(), there is
a synchronize_rcu() before the netdev is actually unregistered and
freed. This ensures that any readers i.e. xmit() that got a non-NULL
peer will complete before the netdev is freed.

Any readers after the RCU_INIT_POINTER() but before synchronize_rcu()
will dereference NULL, making it safe.

The codepath to nsim_destroy() and nsim_create() takes rtnl_lock, making
it safe with concurrent calls to linking two netdevsims together.

Signed-off-by: David Wei <dw@davidwei.uk>
---
 drivers/net/netdevsim/netdev.c    | 24 ++++++++++++++++++++----
 drivers/net/netdevsim/netdevsim.h |  1 +
 2 files changed, 21 insertions(+), 4 deletions(-)

Comments

Jakub Kicinski Jan. 26, 2024, 2:26 a.m. UTC | #1
On Thu, 25 Jan 2024 17:23:55 -0800 David Wei wrote:
>  	struct netdevsim *ns = netdev_priv(dev);
> +	struct netdevsim *peer_ns;
> +	unsigned int len = skb->len;
> +	int ret = NETDEV_TX_OK;

nit: order variables longest to shortest

>  	if (!nsim_ipsec_tx(ns, skb))
>  		goto out;
>  
> +	rcu_read_lock();
> +	peer_ns = rcu_dereference(ns->peer);
> +	if (!peer_ns)
> +		goto out_stats;
> +
> +	skb_tx_timestamp(skb);
> +	if (unlikely(dev_forward_skb(peer_ns->netdev, skb) == NET_RX_DROP))
> +		ret = NET_XMIT_DROP;
> +
> +out_stats:
> +	rcu_read_unlock();
>  	u64_stats_update_begin(&ns->syncp);
>  	ns->tx_packets++;
> -	ns->tx_bytes += skb->len;
> +	ns->tx_bytes += len;
> +	if (ret == NET_XMIT_DROP)
> +		ns->tx_dropped++;

drops should not be counted as Tx

>  	u64_stats_update_end(&ns->syncp);
> +	return ret;
David Wei Jan. 26, 2024, 6:55 p.m. UTC | #2
On 2024-01-25 18:26, Jakub Kicinski wrote:
> On Thu, 25 Jan 2024 17:23:55 -0800 David Wei wrote:
>>  	struct netdevsim *ns = netdev_priv(dev);
>> +	struct netdevsim *peer_ns;
>> +	unsigned int len = skb->len;
>> +	int ret = NETDEV_TX_OK;
> 
> nit: order variables longest to shortest

Thanks, I'll be more mindful about this.

> 
>>  	if (!nsim_ipsec_tx(ns, skb))
>>  		goto out;
>>  
>> +	rcu_read_lock();
>> +	peer_ns = rcu_dereference(ns->peer);
>> +	if (!peer_ns)
>> +		goto out_stats;
>> +
>> +	skb_tx_timestamp(skb);
>> +	if (unlikely(dev_forward_skb(peer_ns->netdev, skb) == NET_RX_DROP))
>> +		ret = NET_XMIT_DROP;
>> +
>> +out_stats:
>> +	rcu_read_unlock();
>>  	u64_stats_update_begin(&ns->syncp);
>>  	ns->tx_packets++;
>> -	ns->tx_bytes += skb->len;
>> +	ns->tx_bytes += len;
>> +	if (ret == NET_XMIT_DROP)
>> +		ns->tx_dropped++;
> 
> drops should not be counted as Tx

Will address.

> 
>>  	u64_stats_update_end(&ns->syncp);
>> +	return ret;
diff mbox series

Patch

diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 969248ffeca8..978c34334018 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -29,19 +29,35 @@ 
 static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct netdevsim *ns = netdev_priv(dev);
+	struct netdevsim *peer_ns;
+	unsigned int len = skb->len;
+	int ret = NETDEV_TX_OK;
 
 	if (!nsim_ipsec_tx(ns, skb))
 		goto out;
 
+	rcu_read_lock();
+	peer_ns = rcu_dereference(ns->peer);
+	if (!peer_ns)
+		goto out_stats;
+
+	skb_tx_timestamp(skb);
+	if (unlikely(dev_forward_skb(peer_ns->netdev, skb) == NET_RX_DROP))
+		ret = NET_XMIT_DROP;
+
+out_stats:
+	rcu_read_unlock();
 	u64_stats_update_begin(&ns->syncp);
 	ns->tx_packets++;
-	ns->tx_bytes += skb->len;
+	ns->tx_bytes += len;
+	if (ret == NET_XMIT_DROP)
+		ns->tx_dropped++;
 	u64_stats_update_end(&ns->syncp);
+	return ret;
 
 out:
 	dev_kfree_skb(skb);
-
-	return NETDEV_TX_OK;
+	return ret;
 }
 
 static void nsim_set_rx_mode(struct net_device *dev)
@@ -70,6 +86,7 @@  nsim_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 		start = u64_stats_fetch_begin(&ns->syncp);
 		stats->tx_bytes = ns->tx_bytes;
 		stats->tx_packets = ns->tx_packets;
+		stats->tx_dropped = ns->tx_dropped;
 	} while (u64_stats_fetch_retry(&ns->syncp, start));
 }
 
@@ -302,7 +319,6 @@  static void nsim_setup(struct net_device *dev)
 	eth_hw_addr_random(dev);
 
 	dev->tx_queue_len = 0;
-	dev->flags |= IFF_NOARP;
 	dev->flags &= ~IFF_MULTICAST;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE |
 			   IFF_NO_QUEUE;
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index c8b45b0d955e..553c4b9b4f63 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -98,6 +98,7 @@  struct netdevsim {
 
 	u64 tx_packets;
 	u64 tx_bytes;
+	u64 tx_dropped;
 	struct u64_stats_sync syncp;
 
 	struct nsim_bus_dev *nsim_bus_dev;