udp_tunnel: remove rtnl_lock dependency
Subsystems (17)
v5 cover udp_tunnel: remove rtnl_lock dependency
Recently bnxt had to grow back a bunch of rtnl dependencies because of udp_tunnel's infra. Add separate (global) mutext to protect udp_tunnel state.
v5:
- remove unused variable ([email protected])
v4:
- grab lock in more places, specifically netlink and notifiers (Jakub)
- convert geneve and vxlan notifiers to (sleepable) rtnl lock
v3:
- fix 2 test failures (Jakub NIPA)
v2:
- move the lock into udp_tunnel_nic (Jakub)
- reorder the lock ordering (Jakub)
- move udp_ports_sleep removal into separate patch and update the test (Jakub)
Stanislav Fomichev (6):
geneve: rely on rtnl lock in geneve_offload_rx_ports
vxlan: drop sock_lock
udp_tunnel: remove rtnl_lock dependency
net: remove redundant ASSERT_RTNL() in queue setup functions
netdevsim: remove udp_ports_sleep
Revert "bnxt_en: bring back rtnl_lock() in the bnxt_open() path"
.../net/ethernet/broadcom/bnx2x/bnx2x_main.c | 3 +- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 42 ++------- drivers/net/ethernet/emulex/benet/be_main.c | 3 +- drivers/net/ethernet/intel/i40e/i40e_main.c | 1 - drivers/net/ethernet/intel/ice/ice_main.c | 1 - .../net/ethernet/mellanox/mlx4/en_netdev.c | 3 +- .../net/ethernet/mellanox/mlx5/core/en_main.c | 3 +- .../ethernet/netronome/nfp/nfp_net_common.c | 3 +- .../net/ethernet/qlogic/qede/qede_filter.c | 3 - .../net/ethernet/qlogic/qlcnic/qlcnic_main.c | 1 - drivers/net/ethernet/sfc/ef10.c | 1 - drivers/net/geneve.c | 7 +- drivers/net/netdevsim/netdevsim.h | 2 - drivers/net/netdevsim/udp_tunnels.c | 12 --- drivers/net/vxlan/vxlan_core.c | 35 +++----- drivers/net/vxlan/vxlan_private.h | 2 +- drivers/net/vxlan/vxlan_vnifilter.c | 18 ++-- include/net/udp_tunnel.h | 87 ++++++++++++++----- net/core/dev.c | 4 +- net/ipv4/udp_tunnel_core.c | 16 ++-- net/ipv4/udp_tunnel_nic.c | 78 +++++++++++++---- .../drivers/net/netdevsim/udp_tunnel_nic.sh | 23 +---- 22 files changed, 176 insertions(+), 172 deletions(-)
Signature · 1 line
2.49.0
PATCH v5 1/6 geneve: rely on rtnl lock in geneve_offload_rx_ports
udp_tunnel_push_rx_port will grab mutex in the next patch so we can't use rcu. geneve_offload_rx_ports is called from geneve_netdevice_event for NETDEV_UDP_TUNNEL_PUSH_INFO and NETDEV_UDP_TUNNEL_DROP_INFO which both have ASSERT_RTNL. Entries are added to and removed from the sock_list under rtnl lock as well (when adding or removing a tunneling device).
--- drivers/net/geneve.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
drivers/net/geneve.c +4 -3
@@ -41,6 +41,7 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");/* per-network namespace private data for this module */ struct geneve_net {struct list_head geneve_list; +/* sock_list is protected by rtnl lock */ struct list_head sock_list; };
@@ -1179,8 +1180,9 @@ static void geneve_offload_rx_ports(struct net_device *dev, bool push)struct geneve_net *gn =net_generic (net, geneve_net_id);struct geneve_sock *gs; -rcu_read_lock (); -list_for_each_entry_rcu (gs, &gn->sock_list, list) { +ASSERT_RTNL (); + +list_for_each_entry (gs, &gn->sock_list, list) {if (push) {udp_tunnel_push_rx_port (dev, gs->sock,UDP_TUNNEL_TYPE_GENEVE );
@@ -1189,7 +1191,6 @@ static void geneve_offload_rx_ports(struct net_device *dev, bool push) UDP_TUNNEL_TYPE_GENEVE); } } -rcu_read_unlock (); }/* Initialize the device structure. */
Signature · 1 line
2.49.0
Re: [PATCH net-next v5 1/6] geneve: rely on rtnl lock in geneve_offload_rx_ports
Quoted 37 lines · Stanislav Fomichev
udp_tunnel_push_rx_portwill grab mutex in the next patch so we can't use rcu.geneve_offload_rx_portsis called fromgeneve_netdevice_eventforNETDEV_UDP_TUNNEL_PUSH_INFOandNETDEV_UDP_TUNNEL_DROP_INFOwhich both haveASSERT_RTNL. Entries are added to and removed from thesock_listunder rtnl lock as well (when adding or removing a tunneling device).Signed-off-by Stanislav Fomichev <[email protected]>--- drivers/net/geneve.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)drivers/net/geneve.c +4
-2@@ -41,6 +41,7 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");/* per-network namespace private data for this module */ struct geneve_net {struct list_head geneve_list; +/* sock_list is protected by rtnl lock */ struct list_head sock_list; };@@ -1179,8 +1180,9 @@ static void geneve_offload_rx_ports(struct net_device *dev, bool push)struct geneve_net *gn =net_generic (net, geneve_net_id);struct geneve_sock *gs; -rcu_read_lock (); -list_for_each_entry_rcu (gs, &gn->sock_list, list) { +ASSERT_RTNL (); + +list_for_each_entry (gs, &gn->sock_list, list) {if (push) {udp_tunnel_push_rx_port (dev, gs->sock,UDP_TUNNEL_TYPE_GENEVE );
drivers/net/geneve.c static void geneve_offload_rx_ports(struct net_device *dev, bool push) · line 1196
Quoted 7 lines
drivers/net/geneve.c +0
-1@@ -1189,7 +1191,6 @@ static void geneve_offload_rx_ports(struct net_device *dev, bool push) UDP_TUNNEL_TYPE_GENEVE); } } -rcu_read_unlock (); }/* Initialize the device structure. */
PATCH v5 2/6 vxlan: drop sock_lock
In reply to Stanislav FomichevWe won't be able to sleep soon in vxlan_offload_rx_ports and won't be able to grab sock_lock. Instead of having separate spinlock to manage sockets, rely on rtnl lock. This is similar to how geneve manages its sockets.
--- drivers/net/vxlan/vxlan_core.c | 35 ++++++++++++----------------- drivers/net/vxlan/vxlan_private.h | 2 +- drivers/net/vxlan/vxlan_vnifilter.c | 18 ++++++--------- 3 files changed, 22 insertions(+), 33 deletions(-)
drivers/net/vxlan/vxlan_core.c +14 -21
@@ -1485,21 +1485,18 @@ static enum skb_drop_reason vxlan_snoop(struct net_device *dev,static bool __vxlan_sock_release_prep (struct vxlan_sock *vs) { -struct vxlan_net *vn; +ASSERT_RTNL ();if (!vs)return false;if (!refcount_dec_and_test (&vs->refcnt))return false; - vn =net_generic (sock_net (vs->sock->sk), vxlan_net_id); -spin_lock (&vn->sock_lock);hlist_del_rcu (&vs->hlist);udp_tunnel_notify_del_rx_port (vs->sock, (vs->flags &VXLAN_F_GPE ) ?UDP_TUNNEL_TYPE_VXLAN_GPE :UDP_TUNNEL_TYPE_VXLAN ); -spin_unlock (&vn->sock_lock);return true; }
@@ -2847,26 +2844,23 @@ static void vxlan_cleanup(struct timer_list *t)static void vxlan_vs_del_dev (struct vxlan_dev *vxlan) { -struct vxlan_net *vn =net_generic (vxlan->net, vxlan_net_id); +ASSERT_RTNL (); -spin_lock (&vn->sock_lock);hlist_del_init_rcu (&vxlan->hlist4.hlist);#if IS_ENABLED (CONFIG_IPV6 )hlist_del_init_rcu (&vxlan->hlist6.hlist);#endif -spin_unlock (&vn->sock_lock); }static void vxlan_vs_add_dev (struct vxlan_sock *vs,struct vxlan_dev *vxlan,struct vxlan_dev_node *node) { -struct vxlan_net *vn =net_generic (vxlan->net, vxlan_net_id);__be32 vni = vxlan->default_dst.remote_vni; +ASSERT_RTNL (); + node->vxlan = vxlan; -spin_lock (&vn->sock_lock);hlist_add_head_rcu (&node->hlist,vni_head (vs, vni)); -spin_unlock (&vn->sock_lock); }/* Setup stats when device is created */
@@ -3291,9 +3285,10 @@ static void vxlan_offload_rx_ports(struct net_device *dev, bool push)struct vxlan_net *vn =net_generic (net, vxlan_net_id);unsigned int i; -spin_lock (&vn->sock_lock); +ASSERT_RTNL (); +for (i =0 ; i <PORT_HASH_SIZE ; ++i) { -hlist_for_each_entry_rcu (vs, &vn->sock_list[i], hlist) { +hlist_for_each_entry (vs, &vn->sock_list[i], hlist) {unsigned short type;if (vs->flags &VXLAN_F_GPE )
@@ -3307,7 +3302,6 @@ static void vxlan_offload_rx_ports(struct net_device *dev, bool push)udp_tunnel_drop_rx_port (dev, vs->sock, type); } } -spin_unlock (&vn->sock_lock); }/* Initialize the device structure. */
@@ -3537,12 +3531,13 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6, __be16 port, u32 flags, int ifindex) { - struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_sock *vs;struct socket *sock;unsigned int h;struct udp_tunnel_sock_cfg tunnel_cfg; +ASSERT_RTNL (); + vs =kzalloc (sizeof (*vs),GFP_KERNEL );if (!vs)return ERR_PTR (-ENOMEM );
@@ -3560,13 +3555,11 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6,refcount_set (&vs->refcnt,1 ); vs->flags = (flags &VXLAN_F_RCV_FLAGS ); -spin_lock (&vn->sock_lock);hlist_add_head_rcu (&vs->hlist,vs_head (net, port));udp_tunnel_notify_add_rx_port (sock, (vs->flags &VXLAN_F_GPE ) ?UDP_TUNNEL_TYPE_VXLAN_GPE :UDP_TUNNEL_TYPE_VXLAN ); -spin_unlock (&vn->sock_lock);/* Mark socket as an encapsulation socket. */ memset (&tunnel_cfg,0 ,sizeof (tunnel_cfg));
@@ -3590,26 +3583,27 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6,static int __vxlan_sock_add (struct vxlan_dev *vxlan,bool ipv6) { -struct vxlan_net *vn =net_generic (vxlan->net, vxlan_net_id);bool metadata = vxlan->cfg.flags &VXLAN_F_COLLECT_METADATA ;struct vxlan_sock *vs =NULL ;struct vxlan_dev_node *node;int l3mdev_index =0 ; +ASSERT_RTNL (); +if (vxlan->cfg.remote_ifindex) l3mdev_index =l3mdev_master_upper_ifindex_by_index ( vxlan->net, vxlan->cfg.remote_ifindex);if (!vxlan->cfg.no_share) { -spin_lock (&vn->sock_lock); +rcu_read_lock (); vs =vxlan_find_sock (vxlan->net, ipv6 ?AF_INET6 :AF_INET , vxlan->cfg.dst_port, vxlan->cfg.flags, l3mdev_index);if (vs && !refcount_inc_not_zero (&vs->refcnt)) { -spin_unlock (&vn->sock_lock); +rcu_read_unlock ();return -EBUSY ; } -spin_unlock (&vn->sock_lock); +rcu_read_unlock (); }if (!vs) vs = vxlan_socket_create(vxlan->net, ipv6,
@@ -4875,7 +4869,6 @@ static __net_init int vxlan_init_net(struct net *net)unsigned int h;INIT_LIST_HEAD (&vn->vxlan_list); -spin_lock_init (&vn->sock_lock); vn->nexthop_notifier_block.notifier_call = vxlan_nexthop_event;for (h =0 ; h <PORT_HASH_SIZE ; ++h)
drivers/net/vxlan/vxlan_private.h +1 -1
@@ -19,8 +19,8 @@ extern const struct rhashtable_params vxlan_vni_rht_params;/* per-network namespace private data for this module */ struct vxlan_net {struct list_head vxlan_list; +/* sock_list is protected by rtnl lock */ struct hlist_head sock_list[PORT_HASH_SIZE ]; -spinlock_t sock_lock;struct notifier_block nexthop_notifier_block; };
drivers/net/vxlan/vxlan_vnifilter.c +7 -11
@@ -40,11 +40,11 @@ static void vxlan_vs_add_del_vninode(struct vxlan_dev *vxlan, struct vxlan_vni_node *v, bool del) { -struct vxlan_net *vn =net_generic (vxlan->net, vxlan_net_id);struct vxlan_dev_node *node;struct vxlan_sock *vs; -spin_lock (&vn->sock_lock); +ASSERT_RTNL (); +if (del) {if (!hlist_unhashed (&v->hlist4.hlist))hlist_del_init_rcu (&v->hlist4.hlist);
@@ -52,7 +52,7 @@ static void vxlan_vs_add_del_vninode(struct vxlan_dev *vxlan,if (!hlist_unhashed (&v->hlist6.hlist))hlist_del_init_rcu (&v->hlist6.hlist);#endif - goto out; +return ; }#if IS_ENABLED (CONFIG_IPV6 )
@@ -67,23 +67,21 @@ static void vxlan_vs_add_del_vninode(struct vxlan_dev *vxlan, node = &v->hlist4;hlist_add_head_rcu (&node->hlist,vni_head (vs, v->vni)); } -out: -spin_unlock (&vn->sock_lock); }void vxlan_vs_add_vnigrp (struct vxlan_dev *vxlan,struct vxlan_sock *vs,bool ipv6) { -struct vxlan_net *vn =net_generic (vxlan->net, vxlan_net_id);struct vxlan_vni_group *vg =rtnl_dereference (vxlan->vnigrp);struct vxlan_vni_node *v, *tmp;struct vxlan_dev_node *node; +ASSERT_RTNL (); +if (!vg)return ; -spin_lock (&vn->sock_lock);list_for_each_entry_safe (v, tmp, &vg->vni_list, vlist) {#if IS_ENABLED (CONFIG_IPV6 )if (ipv6)
@@ -94,26 +92,24 @@ void vxlan_vs_add_vnigrp(struct vxlan_dev *vxlan, node->vxlan = vxlan;hlist_add_head_rcu (&node->hlist,vni_head (vs, v->vni)); } -spin_unlock (&vn->sock_lock); }void vxlan_vs_del_vnigrp (struct vxlan_dev *vxlan) {struct vxlan_vni_group *vg =rtnl_dereference (vxlan->vnigrp); -struct vxlan_net *vn =net_generic (vxlan->net, vxlan_net_id);struct vxlan_vni_node *v, *tmp; +ASSERT_RTNL (); +if (!vg)return ; -spin_lock (&vn->sock_lock);list_for_each_entry_safe (v, tmp, &vg->vni_list, vlist) {hlist_del_init_rcu (&v->hlist4.hlist);#if IS_ENABLED (CONFIG_IPV6 )hlist_del_init_rcu (&v->hlist6.hlist);#endif } -spin_unlock (&vn->sock_lock); } static void vxlan_vnifilter_stats_get(const struct vxlan_vni_node *vninode,
Signature · 1 line
2.49.0
Re: [PATCH net-next v5 2/6] vxlan: drop sock_lock
Quoted 6 lines · Stanislav Fomichev
We won't be able to sleep soon in
vxlan_offload_rx_portsand won't be able to grabsock_lock. Instead of having separate spinlock to manage sockets, rely on rtnl lock. This is similar to how geneve manages its sockets.Signed-off-by Stanislav Fomichev <[email protected]>
Re: [PATCH net-next v5 2/6] vxlan: drop sock_lock
In reply to Stanislav FomichevQuoted 5 lines · Stanislav Fomichev
We won't be able to sleep soon in
vxlan_offload_rx_portsand won't be able to grabsock_lock. Instead of having separate spinlock to manage sockets, rely on rtnl lock. This is similar to how geneve manages its sockets.
Quoted 7 lines
Signed-off-by Stanislav Fomichev <[email protected]>--- drivers/net/vxlan/vxlan_core.c | 35 ++++++++++++----------------- drivers/net/vxlan/vxlan_private.h | 2 +- drivers/net/vxlan/vxlan_vnifilter.c | 18 ++++++--------- 3 files changed, 22 insertions(+), 33 deletions(-)
PATCH v5 3/6 udp_tunnel: remove rtnl_lock dependency
In reply to Stanislav FomichevDrivers that are using ops lock and don't depend on RTNL lock still need to manage it because udp_tunnel's RTNL dependency. Introduce new udp_tunnel_nic_lock and use it instead of rtnl_lock. Drop non-UDP_TUNNEL_NIC_INFO_MAY_SLEEP mode from udp_tunnel infra (udp_tunnel_nic_device_sync_work needs to grab udp_tunnel_nic_lock mutex and might sleep).
Cover more places in v4:
- netlink
- udp_tunnel_notify_add_rx_port (ndo_open)
- triggers udp_tunnel_nic_device_sync_work
- udp_tunnel_notify_del_rx_port (ndo_stop)
- triggers udp_tunnel_nic_device_sync_work
- udp_tunnel_get_rx_info (__netdev_update_features)
- triggers NETDEV_UDP_TUNNEL_PUSH_INFO
- udp_tunnel_drop_rx_info (__netdev_update_features)
- triggers NETDEV_UDP_TUNNEL_DROP_INFO
- udp_tunnel_nic_reset_ntf (ndo_open)
- notifiers
- udp_tunnel_nic_netdevice_event, depending on the event:
- triggers NETDEV_UDP_TUNNEL_PUSH_INFO
- triggers NETDEV_UDP_TUNNEL_DROP_INFO
- ethnl_tunnel_info_reply_size
- udp_tunnel_nic_set_port_priv (two intel drivers)
--- .../net/ethernet/broadcom/bnx2x/bnx2x_main.c | 3 +- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 +- drivers/net/ethernet/emulex/benet/be_main.c | 3 +- drivers/net/ethernet/intel/i40e/i40e_main.c | 1 - drivers/net/ethernet/intel/ice/ice_main.c | 1 - .../net/ethernet/mellanox/mlx4/en_netdev.c | 3 +- .../net/ethernet/mellanox/mlx5/core/en_main.c | 3 +- .../ethernet/netronome/nfp/nfp_net_common.c | 3 +- .../net/ethernet/qlogic/qede/qede_filter.c | 3 - .../net/ethernet/qlogic/qlcnic/qlcnic_main.c | 1 - drivers/net/ethernet/sfc/ef10.c | 1 - drivers/net/netdevsim/udp_tunnels.c | 4 - include/net/udp_tunnel.h | 87 ++++++++++++++----- net/core/dev.c | 2 + net/ipv4/udp_tunnel_core.c | 16 ++-- net/ipv4/udp_tunnel_nic.c | 78 +++++++++++++---- 16 files changed, 142 insertions(+), 73 deletions(-)
drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +1 -2
@@ -10219,8 +10219,7 @@ static int bnx2x_udp_tunnel_sync(struct net_device *netdev, unsigned int table)static const struct udp_tunnel_nic_info bnx2x_udp_tunnels = { .sync_table = bnx2x_udp_tunnel_sync, - .flags =UDP_TUNNEL_NIC_INFO_MAY_SLEEP | -UDP_TUNNEL_NIC_INFO_OPEN_ONLY , + .flags =UDP_TUNNEL_NIC_INFO_OPEN_ONLY , .tables = { { .n_entries =1 , .tunnel_types =UDP_TUNNEL_TYPE_VXLAN , }, { .n_entries =1 , .tunnel_types =UDP_TUNNEL_TYPE_GENEVE , },
drivers/net/ethernet/broadcom/bnxt/bnxt.c +2 -4
@@ -15573,8 +15573,7 @@ static int bnxt_udp_tunnel_unset_port(struct net_device *netdev, unsigned int tastatic const struct udp_tunnel_nic_info bnxt_udp_tunnels = { .set_port = bnxt_udp_tunnel_set_port, .unset_port = bnxt_udp_tunnel_unset_port, - .flags =UDP_TUNNEL_NIC_INFO_MAY_SLEEP | -UDP_TUNNEL_NIC_INFO_OPEN_ONLY , + .flags =UDP_TUNNEL_NIC_INFO_OPEN_ONLY , .tables = { { .n_entries =1 , .tunnel_types =UDP_TUNNEL_TYPE_VXLAN , }, { .n_entries =1 , .tunnel_types =UDP_TUNNEL_TYPE_GENEVE , },
@@ -15582,8 +15581,7 @@ static const struct udp_tunnel_nic_info bnxt_udp_tunnels = { }, bnxt_udp_tunnels_p7 = { .set_port = bnxt_udp_tunnel_set_port, .unset_port = bnxt_udp_tunnel_unset_port, - .flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP | - UDP_TUNNEL_NIC_INFO_OPEN_ONLY, + .flags = UDP_TUNNEL_NIC_INFO_OPEN_ONLY, .tables = { { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
drivers/net/ethernet/emulex/benet/be_main.c +1 -2
@@ -4031,8 +4031,7 @@ static int be_vxlan_unset_port(struct net_device *netdev, unsigned int table,static const struct udp_tunnel_nic_info be_udp_tunnels = { .set_port = be_vxlan_set_port, .unset_port = be_vxlan_unset_port, - .flags =UDP_TUNNEL_NIC_INFO_MAY_SLEEP | -UDP_TUNNEL_NIC_INFO_OPEN_ONLY , + .flags =UDP_TUNNEL_NIC_INFO_OPEN_ONLY , .tables = { { .n_entries =1 , .tunnel_types =UDP_TUNNEL_TYPE_VXLAN , }, },
drivers/net/ethernet/intel/i40e/i40e_main.c +0 -1
@@ -15895,7 +15895,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pf->udp_tunnel_nic.set_port = i40e_udp_tunnel_set_port; pf->udp_tunnel_nic.unset_port = i40e_udp_tunnel_unset_port; - pf->udp_tunnel_nic.flags =UDP_TUNNEL_NIC_INFO_MAY_SLEEP ; pf->udp_tunnel_nic.shared = &pf->udp_tunnel_shared; pf->udp_tunnel_nic.tables[0 ].n_entries =I40E_MAX_PF_UDP_OFFLOAD_PORTS ; pf->udp_tunnel_nic.tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN |
drivers/net/ethernet/intel/ice/ice_main.c +0 -1
@@ -4767,7 +4767,6 @@ int ice_init_dev(struct ice_pf *pf) pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port; pf->hw.udp_tunnel_nic.unset_port = ice_udp_tunnel_unset_port; - pf->hw.udp_tunnel_nic.flags =UDP_TUNNEL_NIC_INFO_MAY_SLEEP ; pf->hw.udp_tunnel_nic.shared = &pf->hw.udp_tunnel_shared;if (pf->hw.tnl.valid_count[TNL_VXLAN ]) { pf->hw.udp_tunnel_nic.tables[0].n_entries =
drivers/net/ethernet/mellanox/mlx4/en_netdev.c +1 -2
@@ -2670,8 +2670,7 @@ static int mlx4_udp_tunnel_sync(struct net_device *dev, unsigned int table)static const struct udp_tunnel_nic_info mlx4_udp_tunnels = { .sync_table = mlx4_udp_tunnel_sync, - .flags =UDP_TUNNEL_NIC_INFO_MAY_SLEEP | -UDP_TUNNEL_NIC_INFO_IPV4_ONLY , + .flags =UDP_TUNNEL_NIC_INFO_IPV4_ONLY , .tables = { { .n_entries =1 , .tunnel_types =UDP_TUNNEL_TYPE_VXLAN , }, },
drivers/net/ethernet/mellanox/mlx5/core/en_main.c +1 -2
@@ -5303,8 +5303,7 @@ void mlx5e_vxlan_set_netdev_info(struct mlx5e_priv *priv) priv->nic_info.set_port = mlx5e_vxlan_set_port; priv->nic_info.unset_port = mlx5e_vxlan_unset_port; - priv->nic_info.flags =UDP_TUNNEL_NIC_INFO_MAY_SLEEP | -UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN ; + priv->nic_info.flags =UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN ; priv->nic_info.tables[0 ].tunnel_types =UDP_TUNNEL_TYPE_VXLAN ;/* Don't count the space hard-coded to the IANA port */ priv->nic_info.tables[0].n_entries =
drivers/net/ethernet/netronome/nfp/nfp_net_common.c +1 -2
@@ -2394,8 +2394,7 @@ static int nfp_udp_tunnel_sync(struct net_device *netdev, unsigned int table)static const struct udp_tunnel_nic_info nfp_udp_tunnels = { .sync_table = nfp_udp_tunnel_sync, - .flags =UDP_TUNNEL_NIC_INFO_MAY_SLEEP | -UDP_TUNNEL_NIC_INFO_OPEN_ONLY , + .flags =UDP_TUNNEL_NIC_INFO_OPEN_ONLY , .tables = { { .n_entries =NFP_NET_N_VXLAN_PORTS ,
drivers/net/ethernet/qlogic/qede/qede_filter.c +0 -3
@@ -987,20 +987,17 @@ static int qede_udp_tunnel_sync(struct net_device *dev, unsigned int table)static const struct udp_tunnel_nic_info qede_udp_tunnels_both = { .sync_table = qede_udp_tunnel_sync, - .flags =UDP_TUNNEL_NIC_INFO_MAY_SLEEP , .tables = { { .n_entries =1 , .tunnel_types =UDP_TUNNEL_TYPE_VXLAN , }, { .n_entries =1 , .tunnel_types =UDP_TUNNEL_TYPE_GENEVE , }, }, }, qede_udp_tunnels_vxlan = { .sync_table = qede_udp_tunnel_sync, - .flags =UDP_TUNNEL_NIC_INFO_MAY_SLEEP , .tables = { { .n_entries =1 , .tunnel_types =UDP_TUNNEL_TYPE_VXLAN , }, }, }, qede_udp_tunnels_geneve = { .sync_table = qede_udp_tunnel_sync, - .flags =UDP_TUNNEL_NIC_INFO_MAY_SLEEP , .tables = { { .n_entries =1 , .tunnel_types =UDP_TUNNEL_TYPE_GENEVE , }, },
drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +0 -1
@@ -486,7 +486,6 @@ static int qlcnic_udp_tunnel_sync(struct net_device *dev, unsigned int table)static const struct udp_tunnel_nic_info qlcnic_udp_tunnels = { .sync_table = qlcnic_udp_tunnel_sync, - .flags =UDP_TUNNEL_NIC_INFO_MAY_SLEEP , .tables = { { .n_entries =1 , .tunnel_types =UDP_TUNNEL_TYPE_VXLAN , }, },
drivers/net/ethernet/sfc/ef10.c +0 -1
@@ -3985,7 +3985,6 @@ static int efx_ef10_udp_tnl_unset_port(struct net_device *dev,static const struct udp_tunnel_nic_info efx_ef10_udp_tunnels = { .set_port = efx_ef10_udp_tnl_set_port, .unset_port = efx_ef10_udp_tnl_unset_port, - .flags =UDP_TUNNEL_NIC_INFO_MAY_SLEEP , .tables = { { .n_entries =16 ,
drivers/net/netdevsim/udp_tunnels.c +0 -4
@@ -112,12 +112,10 @@ nsim_udp_tunnels_info_reset_write(struct file *file, const char __user *data,struct net_device *dev = file->private_data;struct netdevsim *ns =netdev_priv (dev); -rtnl_lock ();if (dev->reg_state ==NETREG_REGISTERED ) {memset (ns->udp_ports.ports,0 ,sizeof (ns->udp_ports.__ports));udp_tunnel_nic_reset_ntf (dev); } -rtnl_unlock ();return count; }
@@ -181,8 +179,6 @@ int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev, info->sync_table =NULL ; } -if (ns->udp_ports.sleep) - info->flags |=UDP_TUNNEL_NIC_INFO_MAY_SLEEP ;if (nsim_dev->udp_ports.open_only) info->flags |=UDP_TUNNEL_NIC_INFO_OPEN_ONLY ;if (nsim_dev->udp_ports.ipv4_only)
include/net/udp_tunnel.h +63 -24
135 lines not on this page · raw message
net/core/dev.c +2 -0
@@ -10771,12 +10771,14 @@ int __netdev_update_features(struct net_device *dev)* *before* calling udp_tunnel_get_rx_info, * but *after* calling udp_tunnel_drop_rx_info. */ +udp_tunnel_nic_lock (dev);if (features &NETIF_F_RX_UDP_TUNNEL_PORT ) { dev->features = features;udp_tunnel_get_rx_info (dev); }else {udp_tunnel_drop_rx_info (dev); } +udp_tunnel_nic_unlock (dev); }if (diff &NETIF_F_HW_VLAN_CTAG_FILTER ) {
net/ipv4/udp_tunnel_core.c +10 -6
@@ -134,15 +134,17 @@ void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type)struct udp_tunnel_info ti;struct net_device *dev; +ASSERT_RTNL (); + ti.type = type; ti.sa_family = sk->sk_family; ti.port =inet_sk (sk)->inet_sport; -rcu_read_lock (); -for_each_netdev_rcu (net, dev) { +for_each_netdev (net, dev) { +udp_tunnel_nic_lock (dev);udp_tunnel_nic_add_port (dev, &ti); +udp_tunnel_nic_unlock (dev); } -rcu_read_unlock (); }EXPORT_SYMBOL_GPL (udp_tunnel_notify_add_rx_port);
@@ -154,15 +156,17 @@ void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type)struct udp_tunnel_info ti;struct net_device *dev; +ASSERT_RTNL (); + ti.type = type; ti.sa_family = sk->sk_family; ti.port =inet_sk (sk)->inet_sport; -rcu_read_lock (); -for_each_netdev_rcu (net, dev) { +for_each_netdev (net, dev) { +udp_tunnel_nic_lock (dev);udp_tunnel_nic_del_port (dev, &ti); +udp_tunnel_nic_unlock (dev); } -rcu_read_unlock (); }EXPORT_SYMBOL_GPL (udp_tunnel_notify_del_rx_port);
net/ipv4/udp_tunnel_nic.c +60 -18
194 lines not on this page · raw message
Signature · 1 line
2.49.0
PATCH v5 4/6 net: remove redundant ASSERT_RTNL() in queue setup functions
In reply to Stanislav FomichevThe existing netdev_ops_assert_locked() already asserts that either the RTNL lock or the per-device lock is held, making the explicit ASSERT_RTNL() redundant.
--- net/core/dev.c | 2 -- 1 file changed, 2 deletions(-)
net/core/dev.c +0 -2
@@ -3179,7 +3179,6 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)if (dev->reg_state ==NETREG_REGISTERED || dev->reg_state ==NETREG_UNREGISTERING ) { -ASSERT_RTNL ();netdev_ops_assert_locked (dev); rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues,
@@ -3229,7 +3228,6 @@ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq)return -EINVAL ;if (dev->reg_state ==NETREG_REGISTERED ) { -ASSERT_RTNL ();netdev_ops_assert_locked (dev); rc = net_rx_queue_update_kobjects(dev, dev->real_num_rx_queues,
Signature · 1 line
2.49.0
PATCH v5 5/6 netdevsim: remove udp_ports_sleep
In reply to Stanislav FomichevNow that there is only one path in udp_tunnel, there is no need to have udp_ports_sleep knob. Remove it and adjust the test.
--- drivers/net/netdevsim/netdevsim.h | 2 -- drivers/net/netdevsim/udp_tunnels.c | 8 ------- .../drivers/net/netdevsim/udp_tunnel_nic.sh | 23 +------------------ 3 files changed, 1 insertion(+), 32 deletions(-)
drivers/net/netdevsim/netdevsim.h +0 -2
@@ -131,7 +131,6 @@ struct netdevsim {struct nsim_macsec macsec;struct {u32 inject_error; -u32 sleep;u32 __ports[2 ][NSIM_UDP_TUNNEL_N_PORTS ];u32 (*ports)[NSIM_UDP_TUNNEL_N_PORTS ];struct dentry *ddir;
@@ -342,7 +341,6 @@ struct nsim_dev {bool ipv4_only;bool shared;bool static_iana_vxlan; -u32 sleep; } udp_ports;struct nsim_dev_psample *psample;u16 esw_mode;
drivers/net/netdevsim/udp_tunnels.c +0 -8
@@ -18,9 +18,6 @@ nsim_udp_tunnel_set_port(struct net_device *dev, unsigned int table, ret = -ns->udp_ports.inject_error; ns->udp_ports.inject_error =0 ; -if (ns->udp_ports.sleep) -msleep (ns->udp_ports.sleep); -if (!ret) {if (ns->udp_ports.ports[table][entry]) {WARN (1 ,"entry already in use\n" );
@@ -47,8 +44,6 @@ nsim_udp_tunnel_unset_port(struct net_device *dev, unsigned int table, ret = -ns->udp_ports.inject_error; ns->udp_ports.inject_error =0 ; -if (ns->udp_ports.sleep) -msleep (ns->udp_ports.sleep);if (!ret) {u32 val =be16_to_cpu (ti->port) <<16 | ti->type;
@@ -170,7 +165,6 @@ int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev, GFP_KERNEL);if (!info)return -ENOMEM ; - ns->udp_ports.sleep = nsim_dev->udp_ports.sleep;if (nsim_dev->udp_ports.sync_all) { info->set_port =NULL ;
@@ -213,6 +207,4 @@ void nsim_udp_tunnels_debugfs_create(struct nsim_dev *nsim_dev) &nsim_dev->udp_ports.shared);debugfs_create_bool ("udp_ports_static_iana_vxlan" ,0600 , nsim_dev->ddir, &nsim_dev->udp_ports.static_iana_vxlan); -debugfs_create_u32 ("udp_ports_sleep" ,0600 , nsim_dev->ddir, - &nsim_dev->udp_ports.sleep); }
tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh +1 -22
@@ -266,7 +266,6 @@ for port in 0 1; do echo $NSIM_ID > /sys/bus/netdevsim/new_device else echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep echo 1 > $NSIM_DEV_SYS/new_port fi NSIM_NETDEV=`get_netdev_name old_netdevs`
@@ -350,23 +349,11 @@ old_netdevs=$(ls /sys/class/net) port=0 echo $NSIM_ID > /sys/bus/netdevsim/new_device echo 0 > $NSIM_DEV_SYS/del_port -echo 1000 > $NSIM_DEV_DFS/udp_ports_sleep echo 0 > $NSIM_DEV_SYS/new_port NSIM_NETDEV=`get_netdev_name old_netdevs` msg="create VxLANs" -exp0=( 0 0 0 0 ) # sleep is longer than out wait -new_vxlan vxlan0 10000 $NSIM_NETDEV - -modprobe -r vxlan -modprobe -r udp_tunnel - -msg="remove tunnels" -exp0=( 0 0 0 0 ) -check_tables - -msg="create VxLANs" -exp0=( 0 0 0 0 ) # sleep is longer than out wait +exp0=( `mke 10000 1` 0 0 0 ) new_vxlan vxlan0 10000 $NSIM_NETDEV exp0=( 0 0 0 0 )
@@ -428,7 +415,6 @@ echo 0 > $NSIM_DEV_SYS/del_port for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port
@@ -486,7 +472,6 @@ echo 1 > $NSIM_DEV_DFS/udp_ports_sync_all for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port
@@ -543,7 +528,6 @@ echo 0 > $NSIM_DEV_SYS/del_port for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port
@@ -573,7 +557,6 @@ echo 1 > $NSIM_DEV_DFS/udp_ports_ipv4_only for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port
@@ -634,7 +617,6 @@ echo 0 > $NSIM_DEV_SYS/del_port for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port
@@ -690,7 +672,6 @@ echo 0 > $NSIM_DEV_SYS/del_port for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port
@@ -750,7 +731,6 @@ echo 0 > $NSIM_DEV_SYS/del_port for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port
@@ -809,7 +789,6 @@ echo $NSIM_ID > /sys/bus/netdevsim/new_device echo 0 > $NSIM_DEV_SYS/del_port echo 0 > $NSIM_DEV_DFS/udp_ports_open_only -echo 1 > $NSIM_DEV_DFS/udp_ports_sleep echo 1 > $NSIM_DEV_DFS/udp_ports_shared old_netdevs=$(ls /sys/class/net)
Signature · 1 line
2.49.0
PATCH v5 6/6 Revert "bnxt_en: bring back rtnl_lock() in the bnxt_open() path"
In reply to Stanislav FomichevThis reverts commit 325eb217e41fa14f307c7cc702bd18d0bb38fe84.
udp_tunnel infra doesn't need RTNL, should be safe to get back to only netdev instance lock.
--- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 36 +++++------------------ 1 file changed, 7 insertions(+), 29 deletions(-)
drivers/net/ethernet/broadcom/bnxt/bnxt.c +7 -29
@@ -14055,28 +14055,13 @@ static void bnxt_unlock_sp(struct bnxt *bp)netdev_unlock (bp->dev); } -/* Same as bnxt_lock_sp() with additional rtnl_lock */ -static void bnxt_rtnl_lock_sp (struct bnxt *bp) -{ -clear_bit (BNXT_STATE_IN_SP_TASK , &bp->state); -rtnl_lock (); -netdev_lock (bp->dev); -} - -static void bnxt_rtnl_unlock_sp (struct bnxt *bp) -{ -set_bit (BNXT_STATE_IN_SP_TASK , &bp->state); -netdev_unlock (bp->dev); -rtnl_unlock (); -} -/* Only called from bnxt_sp_task() */ static void bnxt_reset (struct bnxt *bp,bool silent) { -bnxt_rtnl_lock_sp (bp); +bnxt_lock_sp (bp);if (test_bit (BNXT_STATE_OPEN , &bp->state))bnxt_reset_task (bp, silent); -bnxt_rtnl_unlock_sp (bp); +bnxt_unlock_sp (bp); }/* Only called from bnxt_sp_task() */
@@ -14084,9 +14069,9 @@ static void bnxt_rx_ring_reset(struct bnxt *bp) {int i; -bnxt_rtnl_lock_sp (bp); +bnxt_lock_sp (bp);if (!test_bit (BNXT_STATE_OPEN , &bp->state)) { -bnxt_rtnl_unlock_sp (bp); +bnxt_unlock_sp (bp);return ; }/* Disable and flush TPA before resetting the RX ring */
@@ -14125,7 +14110,7 @@ static void bnxt_rx_ring_reset(struct bnxt *bp) }if (bp->flags &BNXT_FLAG_TPA )bnxt_set_tpa (bp, true); -bnxt_rtnl_unlock_sp (bp); +bnxt_unlock_sp (bp); }static void bnxt_fw_fatal_close (struct bnxt *bp)
@@ -15017,17 +15002,15 @@ static void bnxt_fw_reset_task(struct work_struct *work) bp->fw_reset_state =BNXT_FW_RESET_STATE_OPENING ; fallthrough;case BNXT_FW_RESET_STATE_OPENING : -while (!rtnl_trylock ()) { +while (!netdev_trylock (bp->dev)) {bnxt_queue_fw_reset_work (bp,HZ /10 );return ; } -netdev_lock (bp->dev); rc =bnxt_open (bp->dev);if (rc) {netdev_err (bp->dev,"bnxt_open() failed during FW reset\n" );bnxt_fw_reset_abort (bp, rc);netdev_unlock (bp->dev); -rtnl_unlock (); goto ulp_start; }
@@ -15047,7 +15030,6 @@ static void bnxt_fw_reset_task(struct work_struct *work)bnxt_dl_health_fw_status_update (bp, true); }netdev_unlock (bp->dev); -rtnl_unlock ();bnxt_ulp_start (bp,0 );bnxt_reenable_sriov (bp);netdev_lock (bp->dev);
@@ -15996,7 +15978,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx) rc);napi_enable_locked (&bnapi->napi);bnxt_db_nq_arm (bp, &cpr->cp_db, cpr->cp_raw_cons); -netif_close (dev); +bnxt_reset_task (bp, true);return rc; }
@@ -16812,7 +16794,6 @@ static int bnxt_resume(struct device *device)struct bnxt *bp =netdev_priv (dev);int rc =0 ; -rtnl_lock ();netdev_lock (dev); rc =pci_enable_device (bp->pdev);if (rc) {
@@ -16857,7 +16838,6 @@ static int bnxt_resume(struct device *device) resume_exit:netdev_unlock (bp->dev); -rtnl_unlock ();bnxt_ulp_start (bp, rc);if (!rc)bnxt_reenable_sriov (bp);
@@ -17023,7 +17003,6 @@ static void bnxt_io_resume(struct pci_dev *pdev)int err;netdev_info (bp->dev,"PCI Slot Resume\n" ); -rtnl_lock ();netdev_lock (netdev); err =bnxt_hwrm_func_qcaps (bp);
@@ -17041,7 +17020,6 @@ static void bnxt_io_resume(struct pci_dev *pdev)netif_device_attach (netdev);netdev_unlock (netdev); -rtnl_unlock ();bnxt_ulp_start (bp, err);if (!err)bnxt_reenable_sriov (bp);
Signature · 1 line
2.49.0
This series was applied to netdev/net-next.git (main) by Jakub Kicinski <[email protected]>:
Hello:
This series was applied to netdev/net-next.git (main) by Jakub Kicinski <[email protected]>:
Quoted 8 lines · On Mon, 16 Jun 2025 09:21:11 -0700 you wrote:
Recently bnxt had to grow back a bunch of rtnl dependencies because of udp_tunnel's infra. Add separate (global) mutext to protect
udp_tunnelstate.v5:
- remove unused variable ([email protected])[...]
Here is the summary with links:
- [net-next,v5,1/6] geneve: rely on rtnl lock in geneve_offload_rx_ports
https://git.kernel.org/netdev/net-next/c/3e14960f3bd2 - [net-next,v5,2/6] vxlan: drop sock_lock https://git.kernel.org/netdev/net-next/c/df5425b3bd85 - [net-next,v5,3/6] udp_tunnel: remove rtnl_lock dependency https://git.kernel.org/netdev/net-next/c/1ead7501094c - [net-next,v5,4/6] net: remove redundant ASSERT_RTNL() in queue setup functions https://git.kernel.org/netdev/net-next/c/3a321b6b1f76 - [net-next,v5,5/6] netdevsim: remove udp_ports_sleep https://git.kernel.org/netdev/net-next/c/e054c8ba3bce - [net-next,v5,6/6] Revert "bnxt_en: bring back rtnl_lock() in the bnxt_open() path" https://git.kernel.org/netdev/net-next/c/850d9248d2ea
You are awesome, thank you!
Signature · 2 lines
Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html