Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Here we go, another merge window full of networking and #ebpf changes:

   1) Snoop DHCPACKS in batman-adv to learn MAC/IP pairs in the DHCP
      range without dealing with floods of ARP traffic, from Linus
      Lüssing.

   2) Throttle buffered multicast packet transmission in mt76, from
      Felix Fietkau.

   3) Support adaptive interrupt moderation in ice, from Brett Creeley.

   4) A lot of struct_size conversions, from Gustavo A. R. Silva.

   5) Add peek/push/pop commands to bpftool, as well as bash completion,
      from Stanislav Fomichev.

   6) Optimize sk_msg_clone(), from Vakul Garg.

   7) Add SO_BINDTOIFINDEX, from David Herrmann.

   8) Be more conservative with local resends due to local congestion,
      from Yuchung Cheng.

   9) Allow vetoing of unsupported VXLAN FDBs, from Petr Machata.

  10) Add health buffer support to devlink, from Eran Ben Elisha.

  11) Add TXQ scheduling API to mac80211, from Toke Høiland-Jørgensen.

  12) Add statistics to basic packet scheduler filter, from Cong Wang.

  13) Add GRE tunnel support for mlxsw Spectrum-2, from Nir Dotan.

  14) Lots of new IP tunneling forwarding tests, also from Nir Dotan.

  15) Add 3ad stats to bonding, from Nikolay Aleksandrov.

  16) Lots of probing improvements for bpftool, from Quentin Monnet.

  17) Various nfp drive #ebpf JIT improvements from Jakub Kicinski.

  18) Allow #ebpf programs to access gso_segs from skb shared info, from
      Eric Dumazet.

  19) Add sock_diag support for AF_XDP sockets, from Björn Töpel.

  20) Support 22260 iwlwifi devices, from Luca Coelho.

  21) Use rbtree for ipv6 defragmentation, from Peter Oskolkov.

  22) Add JMP32 instruction class support to #ebpf, from Jiong Wang.

  23) Add spinlock support to #ebpf, from Alexei Starovoitov.

  24) Support 256-bit keys and TLS 1.3 in ktls, from Dave Watson.

  25) Add device infomation API to devlink, from Jakub Kicinski.

  26) Add new timestamping socket options which are y2038 safe, from
      Deepa Dinamani.

  27) Add RX checksum offloading for various sh_eth chips, from Sergei
      Shtylyov.

  28) Flow offload infrastructure, from Pablo Neira Ayuso.

  29) Numerous cleanups, improvements, and bug fixes to the PHY layer
      and many drivers from Heiner Kallweit.

  30) Lots of changes to try and make packet scheduler classifiers run
      lockless as much as possible, from Vlad Buslov.

  31) Support BCM957504 chip in bnxt_en driver, from Erik Burrows.

  32) Add concurrency tests to tc-tests infrastructure, from Vlad
      Buslov.

  33) Add hwmon support to aquantia, from Heiner Kallweit.

  34) Allow 64-bit values for SO_MAX_PACING_RATE, from Eric Dumazet.

  And I would be remiss if I didn't thank the various major networking
  subsystem maintainers for integrating much of this work before I even
  saw it. Alexei Starovoitov, Daniel Borkmann, Pablo Neira Ayuso,
  Johannes Berg, Kalle Valo, and many others. Thank you!"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2207 commits)
  net/sched: avoid unused-label warning
  net: ignore sysctl_devconf_inherit_init_net without SYSCTL
  phy: mdio-mux: fix Kconfig dependencies
  net: phy: use phy_modify_mmd_changed in genphy_c45_an_config_aneg
  net: dsa: mv88e6xxx: add call to mv88e6xxx_ports_cmode_init to probe for new DSA framework
  selftest/net: Remove duplicate header
  sky2: Disable MSI on Dell Inspiron 1545 and Gateway P-79
  net/mlx5e: Update tx reporter status in case channels were successfully opened
  devlink: Add support for direct reporter health state update
  devlink: Update reporter state to error even if recover aborted
  sctp: call iov_iter_revert() after sending ABORT
  team: Free BPF filter when unregistering netdev
  ip6mr: Do not call __IP6_INC_STATS() from preemptible context
  isdn: mISDN: Fix potential NULL pointer dereference of kzalloc
  net: dsa: mv88e6xxx: support in-band signalling on SGMII ports with external PHYs
  cxgb4/chtls: Prefix adapter flags with CXGB4
  net-sysfs: Switch to bitmap_zalloc()
  mellanox: Switch to bitmap_zalloc()
  bpf: add test cases for non-pointer sanitiation logic
  mlxsw: i2c: Extend initialization by querying resources data
  ...

1 files changed, 79 insertions, 190 deletions

diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 5df9d1138ac9..90ba4a1f0a6d 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -23,78 +23,6 @@
 #include <linux/rtnetlink.h>
 #include <net/switchdev.h>
 
-/**
- *	switchdev_trans_item_enqueue - Enqueue data item to transaction queue
- *
- *	@trans: transaction
- *	@data: pointer to data being queued
- *	@destructor: data destructor
- *	@tritem: transaction item being queued
- *
- *	Enqeueue data item to transaction queue. tritem is typically placed in
- *	cointainter pointed at by data pointer. Destructor is called on
- *	transaction abort and after successful commit phase in case
- *	the caller did not dequeue the item before.
- */
-void switchdev_trans_item_enqueue(struct switchdev_trans *trans,
-				  void *data, void (*destructor)(void const *),
-				  struct switchdev_trans_item *tritem)
-{
-	tritem->data = data;
-	tritem->destructor = destructor;
-	list_add_tail(&tritem->list, &trans->item_list);
-}
-EXPORT_SYMBOL_GPL(switchdev_trans_item_enqueue);
-
-static struct switchdev_trans_item *
-__switchdev_trans_item_dequeue(struct switchdev_trans *trans)
-{
-	struct switchdev_trans_item *tritem;
-
-	if (list_empty(&trans->item_list))
-		return NULL;
-	tritem = list_first_entry(&trans->item_list,
-				  struct switchdev_trans_item, list);
-	list_del(&tritem->list);
-	return tritem;
-}
-
-/**
- *	switchdev_trans_item_dequeue - Dequeue data item from transaction queue
- *
- *	@trans: transaction
- */
-void *switchdev_trans_item_dequeue(struct switchdev_trans *trans)
-{
-	struct switchdev_trans_item *tritem;
-
-	tritem = __switchdev_trans_item_dequeue(trans);
-	BUG_ON(!tritem);
-	return tritem->data;
-}
-EXPORT_SYMBOL_GPL(switchdev_trans_item_dequeue);
-
-static void switchdev_trans_init(struct switchdev_trans *trans)
-{
-	INIT_LIST_HEAD(&trans->item_list);
-}
-
-static void switchdev_trans_items_destroy(struct switchdev_trans *trans)
-{
-	struct switchdev_trans_item *tritem;
-
-	while ((tritem = __switchdev_trans_item_dequeue(trans)))
-		tritem->destructor(tritem->data);
-}
-
-static void switchdev_trans_items_warn_destroy(struct net_device *dev,
-					       struct switchdev_trans *trans)
-{
-	WARN(!list_empty(&trans->item_list), "%s: transaction item queue is not empty.\n",
-	     dev->name);
-	switchdev_trans_items_destroy(trans);
-}
-
 static LIST_HEAD(deferred);
 static DEFINE_SPINLOCK(deferred_lock);
 
@@ -174,81 +102,32 @@ static int switchdev_deferred_enqueue(struct net_device *dev,
 	return 0;
 }
 
-/**
- *	switchdev_port_attr_get - Get port attribute
- *
- *	@dev: port device
- *	@attr: attribute to get
- */
-int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+static int switchdev_port_attr_notify(enum switchdev_notifier_type nt,
+				      struct net_device *dev,
+				      const struct switchdev_attr *attr,
+				      struct switchdev_trans *trans)
 {
-	const struct switchdev_ops *ops = dev->switchdev_ops;
-	struct net_device *lower_dev;
-	struct list_head *iter;
-	struct switchdev_attr first = {
-		.id = SWITCHDEV_ATTR_ID_UNDEFINED
-	};
-	int err = -EOPNOTSUPP;
+	int err;
+	int rc;
 
-	if (ops && ops->switchdev_port_attr_get)
-		return ops->switchdev_port_attr_get(dev, attr);
+	struct switchdev_notifier_port_attr_info attr_info = {
+		.attr = attr,
+		.trans = trans,
+		.handled = false,
+	};
 
-	if (attr->flags & SWITCHDEV_F_NO_RECURSE)
+	rc = call_switchdev_blocking_notifiers(nt, dev,
+					       &attr_info.info, NULL);
+	err = notifier_to_errno(rc);
+	if (err) {
+		WARN_ON(!attr_info.handled);
 		return err;
-
-	/* Switch device port(s) may be stacked under
-	 * bond/team/vlan dev, so recurse down to get attr on
-	 * each port.  Return -ENODATA if attr values don't
-	 * compare across ports.
-	 */
-
-	netdev_for_each_lower_dev(dev, lower_dev, iter) {
-		err = switchdev_port_attr_get(lower_dev, attr);
-		if (err)
-			break;
-		if (first.id == SWITCHDEV_ATTR_ID_UNDEFINED)
-			first = *attr;
-		else if (memcmp(&first, attr, sizeof(*attr)))
-			return -ENODATA;
-	}
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(switchdev_port_attr_get);
-
-static int __switchdev_port_attr_set(struct net_device *dev,
-				     const struct switchdev_attr *attr,
-				     struct switchdev_trans *trans)
-{
-	const struct switchdev_ops *ops = dev->switchdev_ops;
-	struct net_device *lower_dev;
-	struct list_head *iter;
-	int err = -EOPNOTSUPP;
-
-	if (ops && ops->switchdev_port_attr_set) {
-		err = ops->switchdev_port_attr_set(dev, attr, trans);
-		goto done;
 	}
 
-	if (attr->flags & SWITCHDEV_F_NO_RECURSE)
-		goto done;
-
-	/* Switch device port(s) may be stacked under
-	 * bond/team/vlan dev, so recurse down to set attr on
-	 * each port.
-	 */
-
-	netdev_for_each_lower_dev(dev, lower_dev, iter) {
-		err = __switchdev_port_attr_set(lower_dev, attr, trans);
-		if (err)
-			break;
-	}
-
-done:
-	if (err == -EOPNOTSUPP && attr->flags & SWITCHDEV_F_SKIP_EOPNOTSUPP)
-		err = 0;
+	if (!attr_info.handled)
+		return -EOPNOTSUPP;
 
-	return err;
+	return 0;
 }
 
 static int switchdev_port_attr_set_now(struct net_device *dev,
@@ -257,8 +136,6 @@ static int switchdev_port_attr_set_now(struct net_device *dev,
 	struct switchdev_trans trans;
 	int err;
 
-	switchdev_trans_init(&trans);
-
 	/* Phase I: prepare for attr set. Driver/device should fail
 	 * here if there are going to be issues in the commit phase,
 	 * such as lack of resources or support.  The driver/device
@@ -267,18 +144,10 @@ static int switchdev_port_attr_set_now(struct net_device *dev,
 	 */
 
 	trans.ph_prepare = true;
-	err = __switchdev_port_attr_set(dev, attr, &trans);
-	if (err) {
-		/* Prepare phase failed: abort the transaction.  Any
-		 * resources reserved in the prepare phase are
-		 * released.
-		 */
-
-		if (err != -EOPNOTSUPP)
-			switchdev_trans_items_destroy(&trans);
-
+	err = switchdev_port_attr_notify(SWITCHDEV_PORT_ATTR_SET, dev, attr,
+					 &trans);
+	if (err)
 		return err;
-	}
 
 	/* Phase II: commit attr set.  This cannot fail as a fault
 	 * of driver/device.  If it does, it's a bug in the driver/device
@@ -286,10 +155,10 @@ static int switchdev_port_attr_set_now(struct net_device *dev,
 	 */
 
 	trans.ph_prepare = false;
-	err = __switchdev_port_attr_set(dev, attr, &trans);
+	err = switchdev_port_attr_notify(SWITCHDEV_PORT_ATTR_SET, dev, attr,
+					 &trans);
 	WARN(err, "%s: Commit of attribute (id=%d) failed.\n",
 	     dev->name, attr->id);
-	switchdev_trans_items_warn_destroy(dev, &trans);
 
 	return err;
 }
@@ -388,8 +257,6 @@ static int switchdev_port_obj_add_now(struct net_device *dev,
 
 	ASSERT_RTNL();
 
-	switchdev_trans_init(&trans);
-
 	/* Phase I: prepare for obj add. Driver/device should fail
 	 * here if there are going to be issues in the commit phase,
 	 * such as lack of resources or support.  The driver/device
@@ -400,17 +267,8 @@ static int switchdev_port_obj_add_now(struct net_device *dev,
 	trans.ph_prepare = true;
 	err = switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_ADD,
 					dev, obj, &trans, extack);
-	if (err) {
-		/* Prepare phase failed: abort the transaction.  Any
-		 * resources reserved in the prepare phase are
-		 * released.
-		 */
-
-		if (err != -EOPNOTSUPP)
-			switchdev_trans_items_destroy(&trans);
-
+	if (err)
 		return err;
-	}
 
 	/* Phase II: commit obj add.  This cannot fail as a fault
 	 * of driver/device.  If it does, it's a bug in the driver/device
@@ -421,7 +279,6 @@ static int switchdev_port_obj_add_now(struct net_device *dev,
 	err = switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_ADD,
 					dev, obj, &trans, extack);
 	WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id);
-	switchdev_trans_items_warn_destroy(dev, &trans);
 
 	return err;
 }
@@ -556,10 +413,11 @@ EXPORT_SYMBOL_GPL(unregister_switchdev_notifier);
  *	Call all network notifier blocks.
  */
 int call_switchdev_notifiers(unsigned long val, struct net_device *dev,
-			     struct switchdev_notifier_info *info)
+			     struct switchdev_notifier_info *info,
+			     struct netlink_ext_ack *extack)
 {
 	info->dev = dev;
-	info->extack = NULL;
+	info->extack = extack;
 	return atomic_notifier_call_chain(&switchdev_notif_chain, val, info);
 }
 EXPORT_SYMBOL_GPL(call_switchdev_notifiers);
@@ -591,26 +449,6 @@ int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev,
 }
 EXPORT_SYMBOL_GPL(call_switchdev_blocking_notifiers);
 
-bool switchdev_port_same_parent_id(struct net_device *a,
-				   struct net_device *b)
-{
-	struct switchdev_attr a_attr = {
-		.orig_dev = a,
-		.id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
-	};
-	struct switchdev_attr b_attr = {
-		.orig_dev = b,
-		.id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
-	};
-
-	if (switchdev_port_attr_get(a, &a_attr) ||
-	    switchdev_port_attr_get(b, &b_attr))
-		return false;
-
-	return netdev_phys_item_id_same(&a_attr.u.ppid, &b_attr.u.ppid);
-}
-EXPORT_SYMBOL_GPL(switchdev_port_same_parent_id);
-
 static int __switchdev_handle_port_obj_add(struct net_device *dev,
 			struct switchdev_notifier_port_obj_info *port_obj_info,
 			bool (*check_cb)(const struct net_device *dev),
@@ -716,3 +554,54 @@ int switchdev_handle_port_obj_del(struct net_device *dev,
 	return err;
 }
 EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_del);
+
+static int __switchdev_handle_port_attr_set(struct net_device *dev,
+			struct switchdev_notifier_port_attr_info *port_attr_info,
+			bool (*check_cb)(const struct net_device *dev),
+			int (*set_cb)(struct net_device *dev,
+				      const struct switchdev_attr *attr,
+				      struct switchdev_trans *trans))
+{
+	struct net_device *lower_dev;
+	struct list_head *iter;
+	int err = -EOPNOTSUPP;
+
+	if (check_cb(dev)) {
+		port_attr_info->handled = true;
+		return set_cb(dev, port_attr_info->attr,
+			      port_attr_info->trans);
+	}
+
+	/* Switch ports might be stacked under e.g. a LAG. Ignore the
+	 * unsupported devices, another driver might be able to handle them. But
+	 * propagate to the callers any hard errors.
+	 *
+	 * If the driver does its own bookkeeping of stacked ports, it's not
+	 * necessary to go through this helper.
+	 */
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		err = __switchdev_handle_port_attr_set(lower_dev, port_attr_info,
+						       check_cb, set_cb);
+		if (err && err != -EOPNOTSUPP)
+			return err;
+	}
+
+	return err;
+}
+
+int switchdev_handle_port_attr_set(struct net_device *dev,
+			struct switchdev_notifier_port_attr_info *port_attr_info,
+			bool (*check_cb)(const struct net_device *dev),
+			int (*set_cb)(struct net_device *dev,
+				      const struct switchdev_attr *attr,
+				      struct switchdev_trans *trans))
+{
+	int err;
+
+	err = __switchdev_handle_port_attr_set(dev, port_attr_info, check_cb,
+					       set_cb);
+	if (err == -EOPNOTSUPP)
+		err = 0;
+	return err;
+}
+EXPORT_SYMBOL_GPL(switchdev_handle_port_attr_set);