From 8962daccc2d32812fe24bd21496c036eb4f454b0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Feb 2024 14:43:12 +0000 Subject: xfrm: interface: use exit_batch_rtnl() method exit_batch_rtnl() is called while RTNL is held, and devices to be unregistered can be queued in the dev_kill_list. This saves one rtnl_lock()/rtnl_unlock() pair per netns and one unregister_netdevice_many() call. Signed-off-by: Eric Dumazet Reviewed-by: Antoine Tenart Link: https://lore.kernel.org/r/20240206144313.2050392-17-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/xfrm/xfrm_interface_core.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'net/xfrm/xfrm_interface_core.c') diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 21d50d75c260..dafefef3cf51 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -957,12 +957,12 @@ static struct rtnl_link_ops xfrmi_link_ops __read_mostly = { .get_link_net = xfrmi_get_link_net, }; -static void __net_exit xfrmi_exit_batch_net(struct list_head *net_exit_list) +static void __net_exit xfrmi_exit_batch_rtnl(struct list_head *net_exit_list, + struct list_head *dev_to_kill) { struct net *net; - LIST_HEAD(list); - rtnl_lock(); + ASSERT_RTNL(); list_for_each_entry(net, net_exit_list, exit_list) { struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); struct xfrm_if __rcu **xip; @@ -973,18 +973,16 @@ static void __net_exit xfrmi_exit_batch_net(struct list_head *net_exit_list) for (xip = &xfrmn->xfrmi[i]; (xi = rtnl_dereference(*xip)) != NULL; xip = &xi->next) - unregister_netdevice_queue(xi->dev, &list); + unregister_netdevice_queue(xi->dev, dev_to_kill); } xi = rtnl_dereference(xfrmn->collect_md_xfrmi); if (xi) - unregister_netdevice_queue(xi->dev, &list); + unregister_netdevice_queue(xi->dev, dev_to_kill); } - unregister_netdevice_many(&list); - rtnl_unlock(); } static struct pernet_operations xfrmi_net_ops = { - .exit_batch = xfrmi_exit_batch_net, + .exit_batch_rtnl = xfrmi_exit_batch_rtnl, .id = &xfrmi_net_id, .size = sizeof(struct xfrmi_net), }; -- cgit v1.2.3 From e353ea9ce471331c13edffd5977eadd602d1bb80 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 22 Feb 2024 10:50:08 +0000 Subject: rtnetlink: prepare nla_put_iflink() to run under RCU We want to be able to run rtnl_fill_ifinfo() under RCU protection instead of RTNL in the future. This patch prepares dev_get_iflink() and nla_put_iflink() to run either with RTNL or RCU held. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/infiniband/ulp/ipoib/ipoib_main.c | 4 ++-- drivers/net/can/vxcan.c | 2 +- drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c | 2 +- drivers/net/ipvlan/ipvlan_main.c | 2 +- drivers/net/macsec.c | 2 +- drivers/net/macvlan.c | 2 +- drivers/net/netkit.c | 2 +- drivers/net/veth.c | 2 +- drivers/net/wireless/virtual/virt_wifi.c | 2 +- net/8021q/vlan_dev.c | 4 ++-- net/core/dev.c | 2 +- net/core/rtnetlink.c | 6 +++--- net/dsa/user.c | 2 +- net/ieee802154/6lowpan/core.c | 2 +- net/ipv6/ip6_tunnel.c | 2 +- net/xfrm/xfrm_interface_core.c | 2 +- 16 files changed, 20 insertions(+), 20 deletions(-) (limited to 'net/xfrm/xfrm_interface_core.c') diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 7a5be705d718..6f2a688fccbf 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -1272,10 +1272,10 @@ static int ipoib_get_iflink(const struct net_device *dev) /* parent interface */ if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) - return dev->ifindex; + return READ_ONCE(dev->ifindex); /* child/vlan interface */ - return priv->parent->ifindex; + return READ_ONCE(priv->parent->ifindex); } static u32 ipoib_addr_hash(struct ipoib_neigh_hash *htbl, u8 *daddr) diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index 98c669ad5141..f7fabba707ea 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -119,7 +119,7 @@ static int vxcan_get_iflink(const struct net_device *dev) rcu_read_lock(); peer = rcu_dereference(priv->peer); - iflink = peer ? peer->ifindex : 0; + iflink = peer ? READ_ONCE(peer->ifindex) : 0; rcu_read_unlock(); return iflink; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 046b5f7d8e7c..9d2a9562c96f 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -98,7 +98,7 @@ static int rmnet_vnd_get_iflink(const struct net_device *dev) { struct rmnet_priv *priv = netdev_priv(dev); - return priv->real_dev->ifindex; + return READ_ONCE(priv->real_dev->ifindex); } static int rmnet_vnd_init(struct net_device *dev) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index df7c43a109e1..5920f7e63352 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -349,7 +349,7 @@ static int ipvlan_get_iflink(const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); - return ipvlan->phy_dev->ifindex; + return READ_ONCE(ipvlan->phy_dev->ifindex); } static const struct net_device_ops ipvlan_netdev_ops = { diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 7f5426285c61..4b5513c9c2be 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3753,7 +3753,7 @@ static void macsec_get_stats64(struct net_device *dev, static int macsec_get_iflink(const struct net_device *dev) { - return macsec_priv(dev)->real_dev->ifindex; + return READ_ONCE(macsec_priv(dev)->real_dev->ifindex); } static const struct net_device_ops macsec_netdev_ops = { diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index a3cc665757e8..0cec2783a3e7 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1158,7 +1158,7 @@ static int macvlan_dev_get_iflink(const struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); - return vlan->lowerdev->ifindex; + return READ_ONCE(vlan->lowerdev->ifindex); } static const struct ethtool_ops macvlan_ethtool_ops = { diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index 39171380ccf2..a4d2e76a8d58 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -145,7 +145,7 @@ static int netkit_get_iflink(const struct net_device *dev) rcu_read_lock(); peer = rcu_dereference(nk->peer); if (peer) - iflink = peer->ifindex; + iflink = READ_ONCE(peer->ifindex); rcu_read_unlock(); return iflink; } diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 500b9dfccd08..dd5aa8ab65a8 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1461,7 +1461,7 @@ static int veth_get_iflink(const struct net_device *dev) rcu_read_lock(); peer = rcu_dereference(priv->peer); - iflink = peer ? peer->ifindex : 0; + iflink = peer ? READ_ONCE(peer->ifindex) : 0; rcu_read_unlock(); return iflink; diff --git a/drivers/net/wireless/virtual/virt_wifi.c b/drivers/net/wireless/virtual/virt_wifi.c index ba14d83353a4..6a84ec58d618 100644 --- a/drivers/net/wireless/virtual/virt_wifi.c +++ b/drivers/net/wireless/virtual/virt_wifi.c @@ -453,7 +453,7 @@ static int virt_wifi_net_device_get_iflink(const struct net_device *dev) { struct virt_wifi_netdev_priv *priv = netdev_priv(dev); - return priv->lowerdev->ifindex; + return READ_ONCE(priv->lowerdev->ifindex); } static const struct net_device_ops virt_wifi_ops = { diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index df5552518251..39876eff51d2 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -762,9 +762,9 @@ static void vlan_dev_netpoll_cleanup(struct net_device *dev) static int vlan_dev_get_iflink(const struct net_device *dev) { - struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; + const struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; - return real_dev->ifindex; + return READ_ONCE(real_dev->ifindex); } static int vlan_dev_fill_forward_path(struct net_device_path_ctx *ctx, diff --git a/net/core/dev.c b/net/core/dev.c index c588808be77f..0628d8ff1ed9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -641,7 +641,7 @@ int dev_get_iflink(const struct net_device *dev) if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink) return dev->netdev_ops->ndo_get_iflink(dev); - return dev->ifindex; + return READ_ONCE(dev->ifindex); } EXPORT_SYMBOL(dev_get_iflink); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index c54dbe05c4c5..060543fe7919 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1611,10 +1611,10 @@ static int put_master_ifindex(struct sk_buff *skb, struct net_device *dev) static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev, bool force) { - int ifindex = dev_get_iflink(dev); + int iflink = dev_get_iflink(dev); - if (force || dev->ifindex != ifindex) - return nla_put_u32(skb, IFLA_LINK, ifindex); + if (force || READ_ONCE(dev->ifindex) != iflink) + return nla_put_u32(skb, IFLA_LINK, iflink); return 0; } diff --git a/net/dsa/user.c b/net/dsa/user.c index 4d53c76a9840..9c42a6edcdc8 100644 --- a/net/dsa/user.c +++ b/net/dsa/user.c @@ -352,7 +352,7 @@ void dsa_user_mii_bus_init(struct dsa_switch *ds) /* user device handling ****************************************************/ static int dsa_user_get_iflink(const struct net_device *dev) { - return dsa_user_to_conduit(dev)->ifindex; + return READ_ONCE(dsa_user_to_conduit(dev)->ifindex); } static int dsa_user_open(struct net_device *dev) diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index e643f52663f9..77b4e92027c5 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -93,7 +93,7 @@ static int lowpan_neigh_construct(struct net_device *dev, struct neighbour *n) static int lowpan_get_iflink(const struct net_device *dev) { - return lowpan_802154_dev(dev)->wdev->ifindex; + return READ_ONCE(lowpan_802154_dev(dev)->wdev->ifindex); } static const struct net_device_ops lowpan_netdev_ops = { diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 44406c28445d..5fd07581efaf 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1756,7 +1756,7 @@ int ip6_tnl_get_iflink(const struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - return t->parms.link; + return READ_ONCE(t->parms.link); } EXPORT_SYMBOL(ip6_tnl_get_iflink); diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index dafefef3cf51..717855b9acf1 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -727,7 +727,7 @@ static int xfrmi_get_iflink(const struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); - return xi->p.link; + return READ_ONCE(xi->p.link); } static const struct net_device_ops xfrmi_netdev_ops = { -- cgit v1.2.3 From aceb147b20a2eda9a10bdd4b5650718f731ef3e1 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 22 Feb 2024 06:41:17 -0800 Subject: xfrm: Do not allocate stats in the driver With commit 34d21de99cea9 ("net: Move {l,t,d}stats allocation to core and convert veth & vrf"), stats allocation could be done on net core instead of this driver. With this new approach, the driver doesn't have to bother with error handling (allocation failure checking, making sure free happens in the right spot, etc). This is core responsibility now. Remove the allocation in the xfrm driver and leverage the network core allocation. Signed-off-by: Breno Leitao Reviewed-by: Simon Horman Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_interface_core.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'net/xfrm/xfrm_interface_core.c') diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 21d50d75c260..1a1f6613fda2 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -240,7 +240,6 @@ static void xfrmi_dev_free(struct net_device *dev) struct xfrm_if *xi = netdev_priv(dev); gro_cells_destroy(&xi->gro_cells); - free_percpu(dev->tstats); } static int xfrmi_create(struct net_device *dev) @@ -749,6 +748,7 @@ static void xfrmi_dev_setup(struct net_device *dev) dev->flags = IFF_NOARP; dev->needs_free_netdev = true; dev->priv_destructor = xfrmi_dev_free; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; netif_keep_dst(dev); eth_broadcast_addr(dev->broadcast); @@ -765,15 +765,9 @@ static int xfrmi_dev_init(struct net_device *dev) struct net_device *phydev = __dev_get_by_index(xi->net, xi->p.link); int err; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - err = gro_cells_init(&xi->gro_cells, dev); - if (err) { - free_percpu(dev->tstats); + if (err) return err; - } dev->features |= NETIF_F_LLTX; dev->features |= XFRMI_FEATURES; -- cgit v1.2.3