[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ZYKuDmMh_PyouG8K@nanopsycho>
Date: Wed, 20 Dec 2023 10:04:14 +0100
From: Jiri Pirko <jiri@...nulli.us>
To: David Wei <dw@...idwei.uk>
Cc: Jakub Kicinski <kuba@...nel.org>, Sabrina Dubroca <sd@...asysnail.net>,
netdev@...r.kernel.org, "David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>, Paolo Abeni <pabeni@...hat.com>
Subject: Re: [PATCH net-next v4 3/5] netdevsim: forward skbs from one
connected port to another
Wed, Dec 20, 2023 at 02:47:45AM CET, dw@...idwei.uk wrote:
>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 both the newly
>added nsim_dev_list_lock and rtnl_lock. This makes it safe with
>concurrent calls to linking two netdevsims together.
>
>Signed-off-by: David Wei <dw@...idwei.uk>
>---
> drivers/net/netdevsim/netdev.c | 25 ++++++++++++++++++++++---
> drivers/net/netdevsim/netdevsim.h | 1 +
> 2 files changed, 23 insertions(+), 3 deletions(-)
>
>diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
>index 434322f6a565..00ab3098eb9f 100644
>--- a/drivers/net/netdevsim/netdev.c
>+++ b/drivers/net/netdevsim/netdev.c
>@@ -29,6 +29,8 @@
> 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;
>+ int ret = NETDEV_TX_OK;
>
> if (!nsim_ipsec_tx(ns, skb))
> goto out;
>@@ -36,12 +38,29 @@ static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev)
> u64_stats_update_begin(&ns->syncp);
> ns->tx_packets++;
> ns->tx_bytes += skb->len;
>+
>+ 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;
>+ ns->tx_dropped++;
Idk, does not look fine to me to be in u64_stats_update section while
calling dev_forward_skb()
>+ }
>+
>+ rcu_read_unlock();
> u64_stats_update_end(&ns->syncp);
>
>+ return ret;
>+
>+out_stats:
>+ rcu_read_unlock();
>+ u64_stats_update_end(&ns->syncp);
> out:
> dev_kfree_skb(skb);
>-
>- return NETDEV_TX_OK;
>+ return ret;
> }
>
> static void nsim_set_rx_mode(struct net_device *dev)
>@@ -70,6 +89,7 @@ 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 +322,6 @@ 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 24fc3fbda791..083b1ee7a1a2 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;
>--
>2.39.3
>
Powered by blists - more mailing lists