Merge branch 'rtnetlink-reduce-rtnl-pressure'

Eric Dumazet says: ==================== rtnetlink: reduce RTNL pressure for dumps This series restarts the conversion of rtnl dump operations to RCU protection, instead of requiring RTNL. In this new attempt (prior one failed in 2011), I chose to allow a gradual conversion of selected operations. After this series, "ip -6 addr" and "ip -4 ro" no longer need to acquire RTNL. I refrained from changing inet_dump_ifaddr() and inet6_dump_addr() to avoid merge conflicts because of two fixes in net tree. I also started the work for "ip link" future conversion. v2: rtnl_fill_link_ifmap() always emit IFLA_MAP (Jiri Pirko) Added "nexthop: allow nexthop_mpath_fill_node() to be called without RTNL" to avoid a lockdep splat (Ido Schimmel) ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
mariux64 · Feb 26, 2024 · 5fc3903 · 5fc3903
2 parents 5f6000a + 0ec4e48
commit 5fc3903
Show file tree

Hide file tree

Showing 32 changed files with 238 additions and 198 deletions.
diff --git 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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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/include/linux/netdevice.h b/include/linux/netdevice.h
@@ -4354,8 +4354,10 @@ static inline bool netif_testing(const struct net_device *dev)
  */
 static inline bool netif_oper_up(const struct net_device *dev)
 {
-	return (dev->operstate == IF_OPER_UP ||
-		dev->operstate == IF_OPER_UNKNOWN /* backward compat */);
+	unsigned int operstate = READ_ONCE(dev->operstate);
+
+	return	operstate == IF_OPER_UP ||
+		operstate == IF_OPER_UNKNOWN /* backward compat */;
 }
 
 /**

diff --git a/include/linux/netlink.h b/include/linux/netlink.h
@@ -291,6 +291,7 @@ struct netlink_callback {
 	u16			answer_flags;
 	u32			min_dump_alloc;
 	unsigned int		prev_seq, seq;
+	int			flags;
 	bool			strict_check;
 	union {
 		u8		ctx[48];
@@ -323,6 +324,7 @@ struct netlink_dump_control {
 	void *data;
 	struct module *module;
 	u32 min_dump_alloc;
+	int flags;
 };
 
 int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
@@ -264,6 +264,7 @@ struct fib_dump_filter {
 	bool			filter_set;
 	bool			dump_routes;
 	bool			dump_exceptions;
+	bool			rtnl_held;
 	unsigned char		protocol;
 	unsigned char		rt_type;
 	unsigned int		flags;

diff --git a/include/net/nexthop.h b/include/net/nexthop.h
@@ -317,7 +317,7 @@ static inline
 int nexthop_mpath_fill_node(struct sk_buff *skb, struct nexthop *nh,
 			    u8 rt_family)
 {
-	struct nh_group *nhg = rtnl_dereference(nh->nh_grp);
+	struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp);
 	int i;
 
 	for (i = 0; i < nhg->num_nh; i++) {

diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
@@ -12,6 +12,7 @@ typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *);
 enum rtnl_link_flags {
 	RTNL_FLAG_DOIT_UNLOCKED		= BIT(0),
 	RTNL_FLAG_BULK_DEL_SUPPORTED	= BIT(1),
+	RTNL_FLAG_DUMP_UNLOCKED		= BIT(2),
 };
 
 enum rtnl_kinds {

diff --git 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
@@ -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);
 
@@ -8632,12 +8632,12 @@ unsigned int dev_get_flags(const struct net_device *dev)
 {
 	unsigned int flags;
 
-	flags = (dev->flags & ~(IFF_PROMISC |
+	flags = (READ_ONCE(dev->flags) & ~(IFF_PROMISC |
 				IFF_ALLMULTI |
 				IFF_RUNNING |
 				IFF_LOWER_UP |
 				IFF_DORMANT)) |
-		(dev->gflags & (IFF_PROMISC |
+		(READ_ONCE(dev->gflags) & (IFF_PROMISC |
 				IFF_ALLMULTI));
 
 	if (netif_running(dev)) {

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
@@ -1455,17 +1455,18 @@ static noinline_for_stack int rtnl_fill_vf(struct sk_buff *skb,
 	return 0;
 }
 
-static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev)
+static int rtnl_fill_link_ifmap(struct sk_buff *skb,
+				const struct net_device *dev)
 {
 	struct rtnl_link_ifmap map;
 
 	memset(&map, 0, sizeof(map));
-	map.mem_start   = dev->mem_start;
-	map.mem_end     = dev->mem_end;
-	map.base_addr   = dev->base_addr;
-	map.irq         = dev->irq;
-	map.dma         = dev->dma;
-	map.port        = dev->if_port;
+	map.mem_start = READ_ONCE(dev->mem_start);
+	map.mem_end   = READ_ONCE(dev->mem_end);
+	map.base_addr = READ_ONCE(dev->base_addr);
+	map.irq       = READ_ONCE(dev->irq);
+	map.dma       = READ_ONCE(dev->dma);
+	map.port      = READ_ONCE(dev->if_port);
 
 	if (nla_put_64bit(skb, IFLA_MAP, sizeof(map), &map, IFLA_PAD))
 		return -EMSGSIZE;
@@ -1611,10 +1612,10 @@ 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;
 }
@@ -1698,14 +1699,15 @@ static int rtnl_fill_alt_ifnames(struct sk_buff *skb,
 	struct netdev_name_node *name_node;
 	int count = 0;
 
-	list_for_each_entry(name_node, &dev->name_node->list, list) {
+	list_for_each_entry_rcu(name_node, &dev->name_node->list, list) {
 		if (nla_put_string(skb, IFLA_ALT_IFNAME, name_node->name))
 			return -EMSGSIZE;
 		count++;
 	}
 	return count;
 }
 
+/* RCU protected. */
 static int rtnl_fill_prop_list(struct sk_buff *skb,
 			       const struct net_device *dev)
 {
@@ -1875,9 +1877,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 			goto nla_put_failure;
 	}
 
-	if (rtnl_fill_link_ifmap(skb, dev))
-		goto nla_put_failure;
-
 	if (dev->addr_len) {
 		if (nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr) ||
 		    nla_put(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast))
@@ -1927,10 +1926,11 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	rcu_read_lock();
 	if (rtnl_fill_link_af(skb, dev, ext_filter_mask))
 		goto nla_put_failure_rcu;
-	rcu_read_unlock();
-
+	if (rtnl_fill_link_ifmap(skb, dev))
+		goto nla_put_failure_rcu;
 	if (rtnl_fill_prop_list(skb, dev))
-		goto nla_put_failure;
+		goto nla_put_failure_rcu;
+	rcu_read_unlock();
 
 	if (dev->dev.parent &&
 	    nla_put_string(skb, IFLA_PARENT_DEV_NAME,
@@ -6532,6 +6532,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 		}
 		owner = link->owner;
 		dumpit = link->dumpit;
+		flags = link->flags;
 
 		if (type == RTM_GETLINK - RTM_BASE)
 			min_dump_alloc = rtnl_calcit(skb, nlh);
@@ -6549,6 +6550,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 				.dump		= dumpit,
 				.min_dump_alloc	= min_dump_alloc,
 				.module		= owner,
+				.flags		= flags,
 			};
 			err = netlink_dump_start(rtnl, skb, nlh, &c);
 			/* netlink_dump_start() will keep a reference on

diff --git 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
@@ -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 = {