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

Pull networking updates from Davic Miller:

 1) Support busy polling generically, for all NAPI drivers.  From Eric
    Dumazet.

 2) Add byte/packet counter support to nft_ct, from Floriani Westphal.

 3) Add RSS/XPS support to mvneta driver, from Gregory Clement.

 4) Implement IPV6_HDRINCL socket option for raw sockets, from Hannes
    Frederic Sowa.

 5) Add support for T6 adapter to cxgb4 driver, from Hariprasad Shenai.

 6) Add support for VLAN device bridging to mlxsw switch driver, from
    Ido Schimmel.

 7) Add driver for Netronome NFP4000/NFP6000, from Jakub Kicinski.

 8) Provide hwmon interface to mlxsw switch driver, from Jiri Pirko.

 9) Reorganize wireless drivers into per-vendor directories just like we
    do for ethernet drivers.  From Kalle Valo.

10) Provide a way for administrators "destroy" connected sockets via the
    SOCK_DESTROY socket netlink diag operation.  From Lorenzo Colitti.

11) Add support to add/remove multicast routes via netlink, from Nikolay
    Aleksandrov.

12) Make TCP keepalive settings per-namespace, from Nikolay Borisov.

13) Add forwarding and packet duplication facilities to nf_tables, from
    Pablo Neira Ayuso.

14) Dead route support in MPLS, from Roopa Prabhu.

15) TSO support for thunderx chips, from Sunil Goutham.

16) Add driver for IBM's System i/p VNIC protocol, from Thomas Falcon.

17) Rationalize, consolidate, and more completely document the checksum
    offloading facilities in the networking stack.  From Tom Herbert.

18) Support aborting an ongoing scan in mac80211/cfg80211, from
    Vidyullatha Kanchanapally.

19) Use per-bucket spinlock for bpf hash facility, from Tom Leiming.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1375 commits)
  net: bnxt: always return values from _bnxt_get_max_rings
  net: bpf: reject invalid shifts
  phonet: properly unshare skbs in phonet_rcv()
  dwc_eth_qos: Fix dma address for multi-fragment skbs
  phy: remove an unneeded condition
  mdio: remove an unneed condition
  mdio_bus: NULL dereference on allocation error
  net: Fix typo in netdev_intersect_features
  net: freescale: mac-fec: Fix build error from phy_device API change
  net: freescale: ucc_geth: Fix build error from phy_device API change
  bonding: Prevent IPv6 link local address on enslaved devices
  IB/mlx5: Add flow steering support
  net/mlx5_core: Export flow steering API
  net/mlx5_core: Make ipv4/ipv6 location more clear
  net/mlx5_core: Enable flow steering support for the IB driver
  net/mlx5_core: Initialize namespaces only when supported by device
  net/mlx5_core: Set priority attributes
  net/mlx5_core: Connect flow tables
  net/mlx5_core: Introduce modify flow table command
  net/mlx5_core: Managing root flow table
  ...

40 files changed, 1493 insertions, 290 deletions

diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 59f4a7304419..f0ba9c2ec639 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -26,6 +26,7 @@
 #define PHY_ID_BCM7366			0x600d8490
 #define PHY_ID_BCM7425			0x600d86b0
 #define PHY_ID_BCM7429			0x600d8730
+#define PHY_ID_BCM7435			0x600d8750
 #define PHY_ID_BCM7439			0x600d8480
 #define PHY_ID_BCM7439_2		0xae025080
 #define PHY_ID_BCM7445			0x600d8510
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 06b77f9dd3f2..e5f4164cbd99 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -231,6 +231,14 @@ struct cgroup {
 	int id;
 
 	/*
+	 * The depth this cgroup is at.  The root is at depth zero and each
+	 * step down the hierarchy increments the level.  This along with
+	 * ancestor_ids[] can determine whether a given cgroup is a
+	 * descendant of another without traversing the hierarchy.
+	 */
+	int level;
+
+	/*
 	 * Each non-empty css_set associated with this cgroup contributes
 	 * one to populated_cnt.  All children with non-zero popuplated_cnt
 	 * of their own contribute one.  The count is zero iff there's no
@@ -285,6 +293,9 @@ struct cgroup {
 
 	/* used to schedule release agent */
 	struct work_struct release_agent_work;
+
+	/* ids of the ancestors at each level including self */
+	int ancestor_ids[];
 };
 
 /*
@@ -304,6 +315,9 @@ struct cgroup_root {
 	/* The root cgroup.  Root is destroyed on its release. */
 	struct cgroup cgrp;
 
+	/* for cgrp->ancestor_ids[0] */
+	int cgrp_ancestor_id_storage;
+
 	/* Number of cgroups in the hierarchy, used only for /proc/cgroups */
 	atomic_t nr_cgrps;
 
@@ -521,4 +535,116 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {}
 
 #endif	/* CONFIG_CGROUPS */
 
+#ifdef CONFIG_SOCK_CGROUP_DATA
+
+/*
+ * sock_cgroup_data is embedded at sock->sk_cgrp_data and contains
+ * per-socket cgroup information except for memcg association.
+ *
+ * On legacy hierarchies, net_prio and net_cls controllers directly set
+ * attributes on each sock which can then be tested by the network layer.
+ * On the default hierarchy, each sock is associated with the cgroup it was
+ * created in and the networking layer can match the cgroup directly.
+ *
+ * To avoid carrying all three cgroup related fields separately in sock,
+ * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer.
+ * On boot, sock_cgroup_data records the cgroup that the sock was created
+ * in so that cgroup2 matches can be made; however, once either net_prio or
+ * net_cls starts being used, the area is overriden to carry prioidx and/or
+ * classid.  The two modes are distinguished by whether the lowest bit is
+ * set.  Clear bit indicates cgroup pointer while set bit prioidx and
+ * classid.
+ *
+ * While userland may start using net_prio or net_cls at any time, once
+ * either is used, cgroup2 matching no longer works.  There is no reason to
+ * mix the two and this is in line with how legacy and v2 compatibility is
+ * handled.  On mode switch, cgroup references which are already being
+ * pointed to by socks may be leaked.  While this can be remedied by adding
+ * synchronization around sock_cgroup_data, given that the number of leaked
+ * cgroups is bound and highly unlikely to be high, this seems to be the
+ * better trade-off.
+ */
+struct sock_cgroup_data {
+	union {
+#ifdef __LITTLE_ENDIAN
+		struct {
+			u8	is_data;
+			u8	padding;
+			u16	prioidx;
+			u32	classid;
+		} __packed;
+#else
+		struct {
+			u32	classid;
+			u16	prioidx;
+			u8	padding;
+			u8	is_data;
+		} __packed;
+#endif
+		u64		val;
+	};
+};
+
+/*
+ * There's a theoretical window where the following accessors race with
+ * updaters and return part of the previous pointer as the prioidx or
+ * classid.  Such races are short-lived and the result isn't critical.
+ */
+static inline u16 sock_cgroup_prioidx(struct sock_cgroup_data *skcd)
+{
+	/* fallback to 1 which is always the ID of the root cgroup */
+	return (skcd->is_data & 1) ? skcd->prioidx : 1;
+}
+
+static inline u32 sock_cgroup_classid(struct sock_cgroup_data *skcd)
+{
+	/* fallback to 0 which is the unconfigured default classid */
+	return (skcd->is_data & 1) ? skcd->classid : 0;
+}
+
+/*
+ * If invoked concurrently, the updaters may clobber each other.  The
+ * caller is responsible for synchronization.
+ */
+static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd,
+					   u16 prioidx)
+{
+	struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }};
+
+	if (sock_cgroup_prioidx(&skcd_buf) == prioidx)
+		return;
+
+	if (!(skcd_buf.is_data & 1)) {
+		skcd_buf.val = 0;
+		skcd_buf.is_data = 1;
+	}
+
+	skcd_buf.prioidx = prioidx;
+	WRITE_ONCE(skcd->val, skcd_buf.val);	/* see sock_cgroup_ptr() */
+}
+
+static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd,
+					   u32 classid)
+{
+	struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }};
+
+	if (sock_cgroup_classid(&skcd_buf) == classid)
+		return;
+
+	if (!(skcd_buf.is_data & 1)) {
+		skcd_buf.val = 0;
+		skcd_buf.is_data = 1;
+	}
+
+	skcd_buf.classid = classid;
+	WRITE_ONCE(skcd->val, skcd_buf.val);	/* see sock_cgroup_ptr() */
+}
+
+#else	/* CONFIG_SOCK_CGROUP_DATA */
+
+struct sock_cgroup_data {
+};
+
+#endif	/* CONFIG_SOCK_CGROUP_DATA */
+
 #endif	/* _LINUX_CGROUP_DEFS_H */
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index cb91b44f5f78..322a28482745 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -81,7 +81,8 @@ struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup,
 struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
 						       struct cgroup_subsys *ss);
 
-bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor);
+struct cgroup *cgroup_get_from_path(const char *path);
+
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
 
@@ -364,6 +365,11 @@ static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n)
 		percpu_ref_put_many(&css->refcnt, n);
 }
 
+static inline void cgroup_put(struct cgroup *cgrp)
+{
+	css_put(&cgrp->self);
+}
+
 /**
  * task_css_set_check - obtain a task's css_set with extra access conditions
  * @task: the task to obtain css_set for
@@ -471,6 +477,23 @@ static inline struct cgroup *task_cgroup(struct task_struct *task,
 	return task_css(task, subsys_id)->cgroup;
 }
 
+/**
+ * cgroup_is_descendant - test ancestry
+ * @cgrp: the cgroup to be tested
+ * @ancestor: possible ancestor of @cgrp
+ *
+ * Test whether @cgrp is a descendant of @ancestor.  It also returns %true
+ * if @cgrp == @ancestor.  This function is safe to call as long as @cgrp
+ * and @ancestor are accessible.
+ */
+static inline bool cgroup_is_descendant(struct cgroup *cgrp,
+					struct cgroup *ancestor)
+{
+	if (cgrp->root != ancestor->root || cgrp->level < ancestor->level)
+		return false;
+	return cgrp->ancestor_ids[ancestor->level] == ancestor->id;
+}
+
 /* no synchronization, the result can only be used as a hint */
 static inline bool cgroup_is_populated(struct cgroup *cgrp)
 {
@@ -554,4 +577,45 @@ static inline int cgroup_init(void) { return 0; }
 
 #endif /* !CONFIG_CGROUPS */
 
+/*
+ * sock->sk_cgrp_data handling.  For more info, see sock_cgroup_data
+ * definition in cgroup-defs.h.
+ */
+#ifdef CONFIG_SOCK_CGROUP_DATA
+
+#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
+extern spinlock_t cgroup_sk_update_lock;
+#endif
+
+void cgroup_sk_alloc_disable(void);
+void cgroup_sk_alloc(struct sock_cgroup_data *skcd);
+void cgroup_sk_free(struct sock_cgroup_data *skcd);
+
+static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
+{
+#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
+	unsigned long v;
+
+	/*
+	 * @skcd->val is 64bit but the following is safe on 32bit too as we
+	 * just need the lower ulong to be written and read atomically.
+	 */
+	v = READ_ONCE(skcd->val);
+
+	if (v & 1)
+		return &cgrp_dfl_root.cgrp;
+
+	return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp;
+#else
+	return (struct cgroup *)(unsigned long)skcd->val;
+#endif
+}
+
+#else	/* CONFIG_CGROUP_DATA */
+
+static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {}
+static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {}
+
+#endif	/* CONFIG_CGROUP_DATA */
+
 #endif /* _LINUX_CGROUP_H */
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index eb049c622208..37ff4a6faa9a 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -29,6 +29,9 @@
 #include <asm/bitsperlong.h>
 
 #ifdef __KERNEL__
+struct device;
+int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr);
+unsigned char *arch_get_platform_get_mac_address(void);
 u32 eth_get_headlen(void *data, unsigned int max_len);
 __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
 extern const struct header_ops eth_header_ops;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 5972ffe5719a..43aa1f8855c7 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -350,25 +350,43 @@ struct sk_filter {
 
 #define BPF_PROG_RUN(filter, ctx)  (*filter->bpf_func)(ctx, filter->insnsi)
 
+#define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN
+
+static inline u8 *bpf_skb_cb(struct sk_buff *skb)
+{
+	/* eBPF programs may read/write skb->cb[] area to transfer meta
+	 * data between tail calls. Since this also needs to work with
+	 * tc, that scratch memory is mapped to qdisc_skb_cb's data area.
+	 *
+	 * In some socket filter cases, the cb unfortunately needs to be
+	 * saved/restored so that protocol specific skb->cb[] data won't
+	 * be lost. In any case, due to unpriviledged eBPF programs
+	 * attached to sockets, we need to clear the bpf_skb_cb() area
+	 * to not leak previous contents to user space.
+	 */
+	BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) != BPF_SKB_CB_LEN);
+	BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) !=
+		     FIELD_SIZEOF(struct qdisc_skb_cb, data));
+
+	return qdisc_skb_cb(skb)->data;
+}
+
 static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog,
 				       struct sk_buff *skb)
 {
-	u8 *cb_data = qdisc_skb_cb(skb)->data;
-	u8 saved_cb[QDISC_CB_PRIV_LEN];
+	u8 *cb_data = bpf_skb_cb(skb);
+	u8 cb_saved[BPF_SKB_CB_LEN];
 	u32 res;
 
-	BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) !=
-		     QDISC_CB_PRIV_LEN);
-
 	if (unlikely(prog->cb_access)) {
-		memcpy(saved_cb, cb_data, sizeof(saved_cb));
-		memset(cb_data, 0, sizeof(saved_cb));
+		memcpy(cb_saved, cb_data, sizeof(cb_saved));
+		memset(cb_data, 0, sizeof(cb_saved));
 	}
 
 	res = BPF_PROG_RUN(prog, skb);
 
 	if (unlikely(prog->cb_access))
-		memcpy(cb_data, saved_cb, sizeof(saved_cb));
+		memcpy(cb_data, cb_saved, sizeof(cb_saved));
 
 	return res;
 }
@@ -376,10 +394,11 @@ static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog,
 static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog,
 					struct sk_buff *skb)
 {
-	u8 *cb_data = qdisc_skb_cb(skb)->data;
+	u8 *cb_data = bpf_skb_cb(skb);
 
 	if (unlikely(prog->cb_access))
-		memset(cb_data, 0, QDISC_CB_PRIV_LEN);
+		memset(cb_data, 0, BPF_SKB_CB_LEN);
+
 	return BPF_PROG_RUN(prog, skb);
 }
 
@@ -447,6 +466,8 @@ void bpf_prog_destroy(struct bpf_prog *fp);
 
 int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
 int sk_attach_bpf(u32 ufd, struct sock *sk);
+int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk);
+int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk);
 int sk_detach_filter(struct sock *sk);
 int sk_get_filter(struct sock *sk, struct sock_filter __user *filter,
 		  unsigned int len);
diff --git a/include/linux/hashtable.h b/include/linux/hashtable.h
index 519b6e2d769e..661e5c2a8e2a 100644
--- a/include/linux/hashtable.h
+++ b/include/linux/hashtable.h
@@ -16,6 +16,10 @@
 	struct hlist_head name[1 << (bits)] =					\
 			{ [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT }
 
+#define DEFINE_READ_MOSTLY_HASHTABLE(name, bits)				\
+	struct hlist_head name[1 << (bits)] __read_mostly =			\
+			{ [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT }
+
 #define DECLARE_HASHTABLE(name, bits)                                   	\
 	struct hlist_head name[1 << (bits)]
 
diff --git a/include/linux/hdlc.h b/include/linux/hdlc.h
index 1acb1445e05f..e31bcd4c7859 100644
--- a/include/linux/hdlc.h
+++ b/include/linux/hdlc.h
@@ -101,7 +101,7 @@ netdev_tx_t hdlc_start_xmit(struct sk_buff *skb, struct net_device *dev);
 int attach_hdlc_protocol(struct net_device *dev, struct hdlc_proto *proto,
 			 size_t size);
 /* May be used by hardware driver to gain control over HDLC device */
-void detach_hdlc_protocol(struct net_device *dev);
+int detach_hdlc_protocol(struct net_device *dev);
 
 static __inline__ __be16 hdlc_type_trans(struct sk_buff *skb,
 					 struct net_device *dev)
diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h
index b49cf923becc..ba7a9b0c7c57 100644
--- a/include/linux/if_pppox.h
+++ b/include/linux/if_pppox.h
@@ -91,7 +91,6 @@ enum {
     PPPOX_CONNECTED	= 1,  /* connection established ==TCP_ESTABLISHED */
     PPPOX_BOUND		= 2,  /* bound to ppp device */
     PPPOX_RELAY		= 4,  /* forwarding is enabled */
-    PPPOX_ZOMBIE	= 8,  /* dead, but still bound to ppp device */
     PPPOX_DEAD		= 16  /* dead, useless, please clean me up!*/
 };
 
diff --git a/include/linux/if_team.h b/include/linux/if_team.h
index a6aa970758a2..b84e49c3a738 100644
--- a/include/linux/if_team.h
+++ b/include/linux/if_team.h
@@ -164,6 +164,7 @@ struct team_mode {
 	size_t priv_size;
 	size_t port_priv_size;
 	const struct team_mode_ops *ops;
+	enum netdev_lag_tx_type lag_tx_type;
 };
 
 #define TEAM_PORT_HASHBITS 4
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 67ce5bd3b56a..a5f6ce6b578c 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -73,7 +73,7 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb)
 /* found in socket.c */
 extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *));
 
-static inline bool is_vlan_dev(struct net_device *dev)
+static inline bool is_vlan_dev(const struct net_device *dev)
 {
         return dev->priv_flags & IFF_802_1Q_VLAN;
 }
@@ -621,7 +621,7 @@ static inline netdev_features_t vlan_features_check(const struct sk_buff *skb,
 						     NETIF_F_SG |
 						     NETIF_F_HIGHDMA |
 						     NETIF_F_FRAGLIST |
-						     NETIF_F_GEN_CSUM |
+						     NETIF_F_HW_CSUM |
 						     NETIF_F_HW_VLAN_CTAG_TX |
 						     NETIF_F_HW_VLAN_STAG_TX);
 
diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h
index 0e707f0c1a3e..7c27fa1030e8 100644
--- a/include/linux/inet_diag.h
+++ b/include/linux/inet_diag.h
@@ -3,6 +3,7 @@
 
 #include <uapi/linux/inet_diag.h>
 
+struct net;
 struct sock;
 struct inet_hashinfo;
 struct nlattr;
@@ -23,6 +24,10 @@ struct inet_diag_handler {
 	void		(*idiag_get_info)(struct sock *sk,
 					  struct inet_diag_msg *r,
 					  void *info);
+
+	int		(*destroy)(struct sk_buff *in_skb,
+				   const struct inet_diag_req_v2 *req);
+
 	__u16		idiag_type;
 	__u16		idiag_info_size;
 };
@@ -41,6 +46,10 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
 			    struct sk_buff *in_skb, const struct nlmsghdr *nlh,
 			    const struct inet_diag_req_v2 *req);
 
+struct sock *inet_diag_find_one_icsk(struct net *net,
+				     struct inet_hashinfo *hashinfo,
+				     const struct inet_diag_req_v2 *req);
+
 int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk);
 
 extern int  inet_diag_register(const struct inet_diag_handler *handler);
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 5d4e9c4b821d..af51df35d749 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -274,6 +274,8 @@ void pr_cont_kernfs_path(struct kernfs_node *kn);
 struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn);
 struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent,
 					   const char *name, const void *ns);
+struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent,
+					   const char *path, const void *ns);
 void kernfs_get(struct kernfs_node *kn);
 void kernfs_put(struct kernfs_node *kn);
 
@@ -350,6 +352,10 @@ static inline struct kernfs_node *
 kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name,
 		       const void *ns)
 { return NULL; }
+static inline struct kernfs_node *
+kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path,
+		       const void *ns)
+{ return NULL; }
 
 static inline void kernfs_get(struct kernfs_node *kn) { }
 static inline void kernfs_put(struct kernfs_node *kn) { }
@@ -431,6 +437,12 @@ kernfs_find_and_get(struct kernfs_node *kn, const char *name)
 }
 
 static inline struct kernfs_node *
+kernfs_walk_and_get(struct kernfs_node *kn, const char *path)
+{
+	return kernfs_walk_and_get_ns(kn, path, NULL);
+}
+
+static inline struct kernfs_node *
 kernfs_create_dir(struct kernfs_node *parent, const char *name, umode_t mode,
 		  void *priv)
 {
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index b42963bc81dd..5bfd99d1a40a 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -11,6 +11,55 @@
 
 #include <uapi/linux/mdio.h>
 
+struct mii_bus;
+
+struct mdio_device {
+	struct device dev;
+
+	const struct dev_pm_ops *pm_ops;
+	struct mii_bus *bus;
+
+	int (*bus_match)(struct device *dev, struct device_driver *drv);
+	void (*device_free)(struct mdio_device *mdiodev);
+	void (*device_remove)(struct mdio_device *mdiodev);
+
+	/* Bus address of the MDIO device (0-31) */
+	int addr;
+	int flags;
+};
+#define to_mdio_device(d) container_of(d, struct mdio_device, dev)
+
+/* struct mdio_driver_common: Common to all MDIO drivers */
+struct mdio_driver_common {
+	struct device_driver driver;
+	int flags;
+};
+#define MDIO_DEVICE_FLAG_PHY		1
+#define to_mdio_common_driver(d) \
+	container_of(d, struct mdio_driver_common, driver)
+
+/* struct mdio_driver: Generic MDIO driver */
+struct mdio_driver {
+	struct mdio_driver_common mdiodrv;
+
+	/*
+	 * Called during discovery.  Used to set
+	 * up device-specific structures, if any
+	 */
+	int (*probe)(struct mdio_device *mdiodev);
+
+	/* Clears up any memory if needed */
+	void (*remove)(struct mdio_device *mdiodev);
+};
+#define to_mdio_driver(d)						\
+	container_of(to_mdio_common_driver(d), struct mdio_driver, mdiodrv)
+
+void mdio_device_free(struct mdio_device *mdiodev);
+struct mdio_device *mdio_device_create(struct mii_bus *bus, int addr);
+int mdio_device_register(struct mdio_device *mdiodev);
+void mdio_device_remove(struct mdio_device *mdiodev);
+int mdio_driver_register(struct mdio_driver *drv);
+void mdio_driver_unregister(struct mdio_driver *drv);
 
 static inline bool mdio_phy_id_is_c45(int phy_id)
 {
@@ -173,4 +222,33 @@ static inline u16 ethtool_adv_to_mmd_eee_adv_t(u32 adv)
 	return reg;
 }
 
+int mdiobus_read(struct mii_bus *bus, int addr, u32 regnum);
+int mdiobus_read_nested(struct mii_bus *bus, int addr, u32 regnum);
+int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val);
+int mdiobus_write_nested(struct mii_bus *bus, int addr, u32 regnum, u16 val);
+
+int mdiobus_register_device(struct mdio_device *mdiodev);
+int mdiobus_unregister_device(struct mdio_device *mdiodev);
+bool mdiobus_is_registered_device(struct mii_bus *bus, int addr);
+struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr);
+
+/**
+ * module_mdio_driver() - Helper macro for registering mdio drivers
+ *
+ * Helper macro for MDIO drivers which do not do anything special in module
+ * init/exit. Each module may only use this macro once, and calling it
+ * replaces module_init() and module_exit().
+ */
+#define mdio_module_driver(_mdio_driver)				\
+static int __init mdio_module_init(void)				\
+{									\
+	return mdio_driver_register(&_mdio_driver);			\
+}									\
+module_init(mdio_module_init);						\
+static void __exit mdio_module_exit(void)				\
+{									\
+	mdio_driver_unregister(&_mdio_driver);				\
+}									\
+module_exit(mdio_module_exit)
+
 #endif /* __LINUX_MDIO_H__ */
diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index 5a06d969338e..2e8af001c5da 100644
--- a/include/linux/mlx4/driver.h
+++ b/include/linux/mlx4/driver.h
@@ -75,6 +75,11 @@ static inline int mlx4_is_bonded(struct mlx4_dev *dev)
 	return !!(dev->flags & MLX4_FLAG_BONDED);
 }
 
+static inline int mlx4_is_mf_bonded(struct mlx4_dev *dev)
+{
+	return (mlx4_is_bonded(dev) && mlx4_is_mfunc(dev));
+}
+
 struct mlx4_port_map {
 	u8	port1;
 	u8	port2;
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 0b473cbfa7ef..7be845e30689 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -251,6 +251,7 @@ enum mlx5_event {
 	MLX5_EVENT_TYPE_PAGE_REQUEST	   = 0xb,
 
 	MLX5_EVENT_TYPE_PAGE_FAULT	   = 0xc,
+	MLX5_EVENT_TYPE_NIC_VPORT_CHANGE   = 0xd,
 };
 
 enum {
@@ -442,9 +443,12 @@ struct mlx5_init_seg {
 	__be32			rsvd1[120];
 	__be32			initializing;
 	struct health_buffer	health;
-	__be32			rsvd2[884];
+	__be32			rsvd2[880];
+	__be32			internal_timer_h;
+	__be32			internal_timer_l;
+	__be32			rsrv3[2];
 	__be32			health_counter;
-	__be32			rsvd3[1019];
+	__be32			rsvd4[1019];
 	__be64			ieee1588_clk;
 	__be32			ieee1588_clk_type;
 	__be32			clr_intx;
@@ -520,6 +524,12 @@ struct mlx5_eqe_page_fault {
 	__be32 flags_qpn;
 } __packed;
 
+struct mlx5_eqe_vport_change {
+	u8		rsvd0[2];
+	__be16		vport_num;
+	__be32		rsvd1[6];
+} __packed;
+
 union ev_data {
 	__be32				raw[7];
 	struct mlx5_eqe_cmd		cmd;
@@ -532,6 +542,7 @@ union ev_data {
 	struct mlx5_eqe_stall_vl	stall_vl;
 	struct mlx5_eqe_page_req	req_pages;
 	struct