Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Resolve conflict between commit 264640fc2c5f4f ("ipv6: distinguish frag
queues by device for multicast and link-local packets") from the net
tree and commit 029f7f3b8701c ("netfilter: ipv6: nf_defrag: avoid/free
clone operations") from the nf-next tree.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

Conflicts:
	net/ipv6/netfilter/nf_conntrack_reasm.c

42 files changed, 892 insertions, 343 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 3fe27f8d91f0..c06f8eaa42ff 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -773,7 +773,6 @@ extern void blk_rq_set_block_pc(struct request *);
 extern void blk_requeue_request(struct request_queue *, struct request *);
 extern void blk_add_request_payload(struct request *rq, struct page *page,
 		unsigned int len);
-extern int blk_rq_check_limits(struct request_queue *q, struct request *rq);
 extern int blk_lld_busy(struct request_queue *q);
 extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 			     struct bio_set *bs, gfp_t gfp_mask,
@@ -794,6 +793,8 @@ extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t,
 extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
 			 struct scsi_ioctl_command __user *);
 
+extern int blk_queue_enter(struct request_queue *q, gfp_t gfp);
+extern void blk_queue_exit(struct request_queue *q);
 extern void blk_start_queue(struct request_queue *q);
 extern void blk_stop_queue(struct request_queue *q);
 extern void blk_sync_queue(struct request_queue *q);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index de464e6683b6..83d1926c61e4 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -40,6 +40,7 @@ struct bpf_map {
 	struct user_struct *user;
 	const struct bpf_map_ops *ops;
 	struct work_struct work;
+	atomic_t usercnt;
 };
 
 struct bpf_map_type_list {
@@ -167,8 +168,10 @@ struct bpf_prog *bpf_prog_get(u32 ufd);
 void bpf_prog_put(struct bpf_prog *prog);
 void bpf_prog_put_rcu(struct bpf_prog *prog);
 
-struct bpf_map *bpf_map_get(u32 ufd);
+struct bpf_map *bpf_map_get_with_uref(u32 ufd);
 struct bpf_map *__bpf_map_get(struct fd f);
+void bpf_map_inc(struct bpf_map *map, bool uref);
+void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 
 extern int sysctl_unprivileged_bpf_disabled;
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 60d44b26276d..097901a68671 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -235,6 +235,14 @@ 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
@@ -289,6 +297,9 @@ 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[];
 };
 
 /*
@@ -308,6 +319,9 @@ 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;
 
@@ -528,4 +542,116 @@ 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 22e3754f89c5..a8ba1ea0ea5a 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);
 
@@ -352,6 +353,11 @@ 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
@@ -459,6 +465,23 @@ 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)
 {
@@ -555,4 +578,45 @@ 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/configfs.h b/include/linux/configfs.h
index a8a335b7fce0..758a029011b1 100644
--- a/include/linux/configfs.h
+++ b/include/linux/configfs.h
@@ -197,6 +197,16 @@ static inline struct configfs_subsystem *to_configfs_subsystem(struct config_gro
 int configfs_register_subsystem(struct configfs_subsystem *subsys);
 void configfs_unregister_subsystem(struct configfs_subsystem *subsys);
 
+int configfs_register_group(struct config_group *parent_group,
+			    struct config_group *group);
+void configfs_unregister_group(struct config_group *group);
+
+struct config_group *
+configfs_register_default_group(struct config_group *parent_group,
+				const char *name,
+				struct config_item_type *item_type);
+void configfs_unregister_default_group(struct config_group *group);
+
 /* These functions can sleep and can alloc with GFP_KERNEL */
 /* WARNING: These cannot be called underneath configfs callbacks!! */
 int configfs_depend_item(struct configfs_subsystem *subsys, struct config_item *target);
diff --git a/include/linux/dns_resolver.h b/include/linux/dns_resolver.h
index cc92268af89a..6ac3cad9aef1 100644
--- a/include/linux/dns_resolver.h
+++ b/include/linux/dns_resolver.h
@@ -27,7 +27,7 @@
 #ifdef __KERNEL__
 
 extern int dns_query(const char *type, const char *name, size_t namelen,
-		     const char *options, char **_result, time_t *_expiry);
+		     const char *options, char **_result, time64_t *_expiry);
 
 #endif /* KERNEL */
 
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 6523109e136d..8942af0813e3 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -271,7 +271,7 @@ static inline int gfpflags_to_migratetype(const gfp_t gfp_flags)
 
 static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
 {
-	return gfp_flags & __GFP_DIRECT_RECLAIM;
+	return (bool __force)(gfp_flags & __GFP_DIRECT_RECLAIM);
 }
 
 #ifdef CONFIG_HIGHMEM
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_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..05f5879821b8 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;
 }
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 0ef2a97ccdb5..402753bccafa 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -227,7 +227,7 @@ struct ipv6_pinfo {
 	struct ipv6_ac_socklist	*ipv6_ac_list;
 	struct ipv6_fl_socklist __rcu *ipv6_fl_list;
 
-	struct ipv6_txoptions	*opt;
+	struct ipv6_txoptions __rcu	*opt;
 	struct sk_buff		*pktoptions;
 	struct sk_buff		*rxpmtu;
 	struct inet6_cork	cork;
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/kref.h b/include/linux/kref.h
index 484604d184be..e15828fd71f1 100644
--- a/include/linux/kref.h
+++ b/include/linux/kref.h
@@ -19,7 +19,6 @@
 #include <linux/atomic.h>
 #include <linux/kernel.h>
 #include <linux/mutex.h>
-#include <linux/spinlock.h>
 
 struct kref {
 	atomic_t refcount;
@@ -99,38 +98,6 @@ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)
 	return kref_sub(kref, 1, release);
 }
 
-/**
- * kref_put_spinlock_irqsave - decrement refcount for object.
- * @kref: object.
- * @release: pointer to the function that will clean up the object when the
- *	     last reference to the object is released.
- *	     This pointer is required, and it is not acceptable to pass kfree
- *	     in as this function.
- * @lock: lock to take in release case
- *
- * Behaves identical to kref_put with one exception.  If the reference count
- * drops to zero, the lock will be taken atomically wrt dropping the reference
- * count.  The release function has to call spin_unlock() without _irqrestore.
- */
-static inline int kref_put_spinlock_irqsave(struct kref *kref,
-		void (*release)(struct kref *kref),
-		spinlock_t *lock)
-{
-	unsigned long flags;
-
-	WARN_ON(release == NULL);
-	if (atomic_add_unless(&kref->refcount, -1, 1))
-		return 0;
-	spin_lock_irqsave(lock, flags);
-	if (atomic_dec_and_test(&kref->refcount)) {
-		release(kref);
-		local_irq_restore(flags);
-		return 1;
-	}
-	spin_unlock_irqrestore(lock, flags);
-	return 0;
-}
-
 static inline int kref_put_mutex(struct kref *kref,
 				 void (*release)(struct kref *kref),
 				 struct mutex *lock)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 5706a2108f0a..c923350ca20a 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -460,6 +460,17 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
 	     (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \
 	     idx++)
 
+static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id)
+{
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		if (vcpu->vcpu_id == id)
+			return vcpu;
+	return NULL;
+}
+
 #define kvm_for_each_memslot(memslot, slots)	\
 	for (memslot = &slots->memslots[0];	\
 	      memslot < slots->memslots + KVM_MEM_SLOTS_NUM && memslot->npages;\
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 69c9057e1ab8..c6916aec43b6 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -58,7 +58,6 @@ enum {
 struct nvm_id_group {
 	u8	mtype;
 	u8	fmtype;
-	u16	res16;
 	u8	num_ch;
 	u8	num_lun;
 	u8	num_pln;
@@ -74,9 +73,9 @@ struct nvm_id_group {
 	u32	tbet;
 	u32	tbem;
 	u32	mpos;
+	u32	mccap;
 	u16	cpar;
-	u8	res[913];
-} __packed;
+};
 
 struct nvm_addr_format {
 	u8	ch_offset;
@@ -91,19 +90,15 @@ struct nvm_addr_format {
 	u8	pg_len;
 	u8	sect_offset;
 	u8	sect_len;
-	u8	res[4];
 };
 
 struct nvm_id {
 	u8	ver_id;
 	u8	vmnt;
 	u8	cgrps;
-	u8	res[5];
 	u32	cap;
 	u32	dom;
 	struct nvm_addr_format ppaf;
-	u8	ppat;
-	u8	resv[224];
 	struct nvm_id_group groups[4];
 } __packed;
 
@@ -123,39 +118,28 @@ struct nvm_tgt_instance {
 #define NVM_VERSION_MINOR 0
 #define NVM_VERSION_PATCH 0
 
-#define NVM_SEC_BITS (8)
-#define NVM_PL_BITS  (6)
-#define NVM_PG_BITS  (16)
 #define NVM_BLK_BITS (16)
-#define NVM_LUN_BITS (10)
+#define NVM_PG_BITS  (16)
+#define NVM_SEC_BITS (8)
+#define NVM_PL_BITS  (8)
+#define NVM_LUN_BITS (8)
 #define NVM_CH_BITS  (8)
 
 struct ppa_addr {
+	/* Generic structure for all addresses */
 	union {
-		/* Channel-based PPA format in nand 4x2x2x2x8x10 */
-		struct {
-			u64 ch		: 4;
-			u64 sec		: 2; /* 4 sectors per page */
-			u64 pl		: 2; /* 4 planes per LUN */
-			u64 lun		: 2; /* 4 LUNs per channel */
-			u64 pg		: 8; /* 256 pages per block */
-			u64 blk		: 10;/* 1024 blocks per plane */
-			u64 resved		: 36;
-		} chnl;
-
-		/* Generic structure for all addresses */
 		struct {
+			u64 blk		: NVM_BLK_BITS;
+			u64 pg		: NVM_PG_BITS;
 			u64 sec		: NVM_SEC_BITS;
 			u64 pl		: NVM_PL_BITS;
-			u64 pg		: NVM_PG_BITS;
-			u64 blk		: NVM_BLK_BITS;
 			u64 lun		: NVM_LUN_BITS;
 			u64 ch		: NVM_CH_BITS;
 		} g;
 
 		u64 ppa;
 	};
-} __packed;
+};
 
 struct nvm_rq {
 	struct nvm_tgt_instance *ins;
@@ -191,11 +175,11 @@ static inline void *nvm_rq_to_pdu(struct nvm_rq *rqdata)
 struct nvm_block;
 
 typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *);
-typedef int (nvm_bb_update_fn)(u32, void *, unsigned int, void *);
+typedef int (nvm_bb_update_fn)(struct ppa_addr, int, u8 *, void *);
 typedef int (nvm_id_fn)(struct request_queue *, struct nvm_id *);
 typedef int (nvm_get_l2p_tbl_fn)(struct request_queue *, u64, u32,
 				nvm_l2p_update_fn *, void *);
-typedef int (nvm_op_bb_tbl_fn)(struct request_queue *, int, unsigned int,
+typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, int,
 				nvm_bb_update_fn *, void *);
 typedef int (nvm_op_set_bb_fn)(struct request_queue *, struct nvm_rq *, int);
 typedef int (nvm_submit_io_fn)(struct request_queue *, struct nvm_rq *);
@@ -210,7 +194,7 @@ struct nvm_dev_ops {
 	nvm_id_fn		*identity;
 	nvm_get_l2p_tbl_fn	*get_l2p_tbl;
 	nvm_op_bb_tbl_fn	*get_bb_tbl;
-	nvm_op_set_bb_fn	*set_bb;
+	nvm_op_set_bb_fn	*set_bb_tbl;
 
 	nvm_submit_io_fn	*submit_io;
 	nvm_erase_blk_fn	*erase_block;
@@ -220,7 +204,7 @@ struct nvm_dev_ops {
 	nvm_dev_dma_alloc_fn	*dev_dma_alloc;
 	nvm_dev_dma_free_fn	*dev_dma_free;
 
-	uint8_t			max_phys_sect;
+	unsigned int		max_phys_sect;
 };
 
 struct nvm_lun {
@@ -229,7 +213,9 @@ struct nvm_lun {
 	int lun_id;
 	int chnl_id;
 
+	unsigned int nr_inuse_blocks;	/* Number of used blocks */
 	unsigned int nr_free_blocks;	/* Number of unused blocks */
+	unsigned int nr_bad_blocks;	/* Number of bad blocks */
 	struct nvm_block *blocks;
 
 	spinlock_t lock;
@@ -263,8 +249,7 @@ struct nvm_dev {
 	int blks_per_lun;
 	int sec_size;
 	int oob_size;
-	int addr_mode;
-	struct nvm_addr_format addr_format;
+	struct nvm_addr_format ppaf;
 
 	/* Calculated/Cached values. These do not reflect the actual usable
 	 * blocks at run-time.
@@ -290,118 +275,45 @@ struct nvm_dev {
 	char name[DISK_NAME_LEN];
 };
 
-/* fallback conversion */
-static struct ppa_addr __generic_to_linear_addr(struct nvm_dev *dev,
-							struct ppa_addr r)
-{
-	struct ppa_addr l;
-
-	l.ppa = r.g.sec +
-		r.g.pg  * dev->sec_per_pg +
-		r.g.blk * (dev->pgs_per_blk *
-				dev->sec_per_pg) +
-		r.g.lun * (dev->blks_per_lun *
-				dev->pgs_per_blk *
-				dev->sec_per_pg) +
-		r.g.ch * (dev->blks_per_lun *
-				dev->pgs_per_blk *
-				dev->luns_per_chnl *
-				dev->sec_per_pg);
-
-	return l;
-}
-
-/* fallback conversion */
-static struct ppa_addr __linear_to_generic_addr(struct nvm_dev *dev,
-							struct ppa_addr r)
+static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev,
+						struct ppa_addr r)
 {
 	struct ppa_addr l;
-	int secs, pgs, blks, luns;
-	sector_t ppa = r.ppa;
 
-	l.ppa = 0;
-
-	div_u64_rem(ppa, dev->sec_per_pg, &secs);
-	l.g.sec = secs;
-
-	sector_div(ppa, dev->sec_per_pg);
-	div_u64_rem(ppa, dev->sec_per_blk, &pgs);
-	l.g.pg = pgs;
-
-	sector_div(ppa, dev->pgs_per_blk);
-	div_u64_rem(ppa, dev->blks_per_lun, &blks);
-	l.g.blk = blks;
-
-	sector_div(ppa, dev->blks_per_lun);
-	div_u64_rem(ppa, dev->luns_per_chnl, &luns);
-	l.g.lun = luns;
-
-	sector_div(ppa, dev->luns_per_chnl);
-	l.g.ch = ppa;
+	l.ppa = ((u64)r.g.blk) << dev->ppaf.blk_offset;
+	l.ppa |= ((u64)r.g.pg) << dev->ppaf.pg_offset;
+	l.ppa |= ((u64)r.g.sec) << dev->ppaf.sect_offset;
+	l.ppa |= ((u64)r.g.pl) << dev->ppaf.pln_offset;
+	l.ppa |= ((u64)r.g.lun) << dev->ppaf.lun_offset;
+	l.ppa |= ((u64)r.g.ch) << dev->ppaf.ch_offset;
 
 	return l;
 }
 
-static struct ppa_addr __generic_to_chnl_addr(struct ppa_addr r)
+static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev,
+						struct ppa_addr r)
 {
 	struct ppa_addr l;
 
-	l.ppa = 0;
-
-	l.chnl.sec = r.g.sec;
-	l.chnl.pl = r.g.pl;
-	l.chnl.pg = r.g.pg;
-	l.chnl.blk = r.g.blk;
-	l.chnl.lun = r.g.lun;
-	l.chnl.ch = r.g.ch;
-
-	return l;
-}
-
-static struct ppa_addr __chnl_to_generic_addr(struct ppa_addr r)
-{
-	struct ppa_addr l;
-
-	l.ppa = 0;
-
-	l.g.sec = r.chnl.sec;
-	l.g.pl = r.chnl.pl;
-	l.g.pg = r.chnl.pg;
-	l.g.blk = r.chnl.blk;
-	l.g.lun = r.chnl.lun;
-	l.g.ch = r.chnl.ch;
+	/*
+	 * (r.ppa << X offset) & X len bitmask. X eq. blk, pg, etc.
+	 */
+	l.g.blk = (r.ppa >> dev->ppaf.blk_offset) &
+					(((1 << dev->ppaf.blk_len) - 1));
+	l.g.pg |= (r.ppa >> dev->ppaf.pg_offset) &
+					(((1 << dev->ppaf.pg_len) - 1));
+	l.g.sec |= (r.ppa >> dev->ppaf.sect_offset) &
+					(((1 << dev->ppaf.sect_len) - 1));
+	l.g.pl |= (r.ppa >> dev->ppaf.pln_offset) &
+					(((1 << dev->ppaf.pln_len) - 1));
+	l.g.lun |= (r.ppa >> dev->ppaf.lun_offset) &
+					(((1 << dev->ppaf.lun_len) - 1));
+	l.g.ch |= (r.ppa >> dev->ppaf.ch_offset) &
+					(((1 << dev->ppaf.ch_len) - 1));
 
 	return l;
 }
 
-static inline struct ppa_addr addr_to_generic_mode(struct nvm_dev *dev,
-						struct ppa_addr gppa)
-{
-	switch (dev->addr_mode) {
-	case NVM_ADDRMODE_LINEAR:
-		return __linear_to_generic_addr(dev, gppa);
-	case NVM_ADDRMODE_CHANNEL:
-		return __chnl_to_generic_addr(gppa);
-	default:
-		BUG();
-	}
-	return gppa;
-}
-
-static inline struct ppa_addr generic_to_addr_mode(struct nvm_dev *dev,
-						struct ppa_addr gppa)
-{
-	switch (dev->addr_mode) {
-	case NVM_ADDRMODE_LINEAR:
-		return __generic_to_linear_addr(dev, gppa);
-	case NVM_ADDRMODE_CHANNEL:
-		return __generic_to_chnl_addr(gppa);
-	default:
-		BUG();
-	}
-	return gppa;
-}
-
 static inline int ppa_empty(struct ppa_addr ppa_addr)
 {
 	return (ppa_addr.ppa == ADDR_EMPTY);
@@ -468,7 +380,7 @@ typedef int (nvmm_end_io_fn)(struct nvm_rq *, int);
 typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *,
 								unsigned long);
 typedef struct nvm_lun *(nvmm_get_lun_fn)(struct nvm_dev *, int);
-typedef void (nvmm_free_blocks_print_fn)(struct nvm_dev *);
+typedef void (nvmm_lun_info_print_fn)(struct nvm_dev *);
 
 struct nvmm_type {
 	const char *name;
@@ -492,7 +404,7 @@ struct nvmm_type {
 	nvmm_get_lun_fn *get_lun;
 
 	/* Statistics */
-	nvmm_free_blocks_print_fn *free_blocks_print;
+	nvmm_lun_info_print_fn *lun_info_print;
 	struct list_head list;
 };
 
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..7d3a85faefb7 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 {
@@ -520,6 +521,12 @@ 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 +539,7 @@ union ev_data {
 	struct mlx5_eqe_stall_vl	stall_vl;
 	struct mlx5_eqe_page_req	req_pages;
 	struct mlx5_eqe_page_fault	page_fault;
+	struct mlx5_eqe_vport_change	vport_change;
 } __packed;
 
 struct mlx5_eqe {
@@ -1067,6 +1075,12 @@ enum {
 };
 
 enum {
+	MLX5_ESW_VPORT_ADMIN_STATE_DOWN  = 0x0,
+	MLX5_ESW_VPORT_ADMIN_STATE_UP    = 0x1,
+	MLX5_ESW_VPORT_ADMIN_STATE_AUTO  = 0x2,
+};
+
+enum {
 	MLX5_L3_PROT_TYPE_IPV4		= 0,
 	MLX5_L3_PROT_TYPE_IPV6		= 1,
 };
@@ -1102,6 +1116,12 @@ enum {
 	MLX5_FLOW_CONTEXT_DEST_TYPE_TIR		= 2,
 };
 
+enum mlx5_list_type {
+	MLX5_NVPRT_LIST_TYPE_UC   = 0x0,
+	MLX5_NVPRT_LIST_TYPE_MC   = 0x1,
+	MLX5_NVPRT_LIST_TYPE_VLAN = 0x2,
+};
+
 enum {
 	MLX5_RQC_RQ_TYPE_MEMORY_RQ_INLINE = 0x0,
 	MLX5_RQC_RQ_TYPE_MEMORY_RQ_RPM    = 0x1,
@@ -1124,6 +1144,8 @@ enum mlx5_cap_type {
 	MLX5_CAP_IPOIB_OFFLOADS,
 	MLX5_CAP_EOIB_OFFLOADS,
 	MLX5_CAP_FLOW_TABLE,
+	MLX5_CAP_ESWITCH_FLOW_TABLE,
+	MLX5_CAP_ESWITCH,
 	/* NUM OF CAP Types */
 	MLX5_CAP_NUM
 };
@@ -1161,6 +1183,28 @@ enum mlx5_cap_type {
 #define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \
 	MLX5_GET(flow_table_nic_cap, mdev->hca_caps_max[MLX5_CAP_FLOW_TABLE], cap)
 
+#define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \
+	MLX5_GET(flow_table_eswitch_cap, \
+		 mdev->hca_caps_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap)
+
+#define MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, cap) \
+	MLX5_GET(flow_table_eswitch_cap, \
+		 mdev->hca_caps_max[MLX5_CAP_ESWITCH_FLOW_TABLE], cap)
+
+#define MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) \
+	MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_nic_esw_fdb.cap)
+
+#define MLX5_CAP_ESW_FLOWTABLE_FDB_MAX(mdev, cap) \
+	MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_nic_esw_fdb.cap)
+
+#define MLX5_CAP_ESW(mdev, cap) \
+	MLX5_GET(e_switch_cap, \
+		 mdev->hca_caps_cur[MLX5_CAP_ESWITCH], cap)
+
+#define MLX5_CAP_ESW_MAX(mdev, cap) \
+	MLX5_GET(e_switch_cap, \
+		 mdev->hca_caps_max[MLX5_CAP_ESWITCH], cap)
+
 #define MLX5_CAP_ODP(mdev, cap)\
 	MLX5_GET(odp_cap, mdev->hca_caps_cur[MLX5_CAP_ODP], cap)
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 5c857f2a20d7..2fd7019f69db 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -426,11 +426,23 @@ struct mlx5_mr_table {
 	struct radix_tree_root	tree;
 };
 
+struct mlx5_vf_context {
+	int	enabled;
+};
+
+struct mlx5_core_sriov {
+	struct mlx5_vf_context	*vfs_ctx;
+	int			num_vfs;
+	int			enabled_vfs;
+};
+
 struct mlx5_irq_info {
 	cpumask_var_t mask;
 	char name[MLX5_MAX_IRQ_NAME];
 };
 
+struct mlx5_eswitch;
+
 struct mlx5_priv {
 	char			name[MLX5_MAX_NAME_LEN];
 	struct mlx5_eq_table	eq_table;
@@ -447,6 +459,7 @@ struct mlx5_priv {
 	int			fw_pages;
 	atomic_t		reg_pages;
 	struct list_head	free_list;
+	int			vfs_pages;
 
 	struct mlx5_core_health health;
 
@@ -485,6 +498,12 @@ struct mlx5_priv {
 	struct list_head        dev_list;
 	struct list_head        ctx_list;
 	spinlock_t              ctx_lock;
+
+	struct mlx5_eswitch     *eswitch;
+	struct mlx5_core_sriov	sriov;
+	unsigned long		pci_dev_data;
+	struct mlx5_flow_root_namespace *root_ns;
+	struct mlx5_flow_root_namespace *fdb_root_ns;
 };
 
 enum mlx5_device_state {
@@ -739,6 +758,8 @@ void mlx5_pagealloc_init(struct mlx5_core_dev *dev);
 void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev);
 int mlx5_pagealloc_start(struct mlx5_core_dev *dev);
 void mlx5_pagealloc_stop(struct mlx5_core_dev *dev);
+int mlx5_sriov_init(struct mlx5_core_dev *dev);
+int mlx5_sriov_cleanup(struct mlx5_core_dev *dev);
 void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id,
 				 s32 npages);
 int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot);
@@ -884,6 +905,15 @@ struct mlx5_profile {
 	} mr_cache[MAX_MR_CACHE_ENTRIES];
 };
 
+enum {
+	MLX5_PCI_DEV_IS_VF		= 1 << 0,
+};
+
+static inline int mlx5_core_is_pf(struct mlx5_core_dev *dev)
+{
+	return !(dev->priv.pci_dev_data & MLX5_PCI_DEV_IS_VF);
+}
+
 static inline int mlx5_get_gid_table_len(u16 param)
 {
 	if (param > 4) {
diff --git a/include/linux/mlx5/flow_table.h b/include/linux/mlx5/flow_table.h
deleted file mode 100644
index 5f922c6d4fc2..000000000000
--- a/include/linux/mlx5/flow_table.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * Copyright (c) 2013-2015, Mellanox Technologies, Ltd.  All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#ifndef MLX5_FLOW_TABLE_H
-#define MLX5_FLOW_TABLE_H
-
-#include <linux/mlx5/driver.h>
-
-struct mlx5_flow_table_group {
-	u8	log_sz;
-	u8	match_criteria_enable;
-	u32	match_criteria[MLX5_ST_SZ_DW(fte_match_param)];
-};
-
-void *mlx5_create_flow_table(struct mlx5_core_dev *dev, u8 level, u8 table_type,
-			     u16 num_groups,
-			     struct mlx5_flow_table_group *group);
-void mlx5_destroy_flow_table(void *flow_table);
-int mlx5_add_flow_table_entry(void *flow_table, u8 match_criteria_enable,
-			      void *match_criteria, void *flow_context,
-			      u32 *flow_index);
-void mlx5_del_flow_table_entry(void *flow_table, u32 flow_index);
-u32 mlx5_get_flow_table_id(void *flow_table);
-
-#endif /* MLX5_FLOW_TABLE_H */
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
new file mode 100644
index 000000000000..bc7ad019afde
--- /dev/null
+++ b/include/linux/mlx5/fs.h
@@ -0,0 +1,93 @@
+/*
+ * Copyright (c) 2015, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _MLX5_FS_
+#define _MLX5_FS_
+
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/mlx5_ifc.h>
+
+#define MLX5_FS_DEFAULT_FLOW_TAG 0x0
+
+enum mlx5_flow_namespace_type {
+	MLX5_FLOW_NAMESPACE_KERNEL,
+	MLX5_FLOW_NAMESPACE_FDB,
+};
+
+struct mlx5_flow_table;
+struct mlx5_flow_group;
+struct mlx5_flow_rule;
+struct mlx5_flow_namespace;
+
+struct mlx5_flow_destination {
+	enum mlx5_flow_destination_type	type;
+	union {
+		u32			tir_num;
+		struct mlx5_flow_table	*ft;
+		u32			vport_num;
+	};
+};
+
+struct mlx5_flow_namespace *
+mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
+			enum mlx5_flow_namespace_type type);
+
+struct mlx5_flow_table *
+mlx5_create_flow_table(struct mlx5_flow_namespace *ns,
+		       int prio,
+		       int num_flow_table_entries);
+int mlx5_destroy_flow_table(struct mlx5_flow_table *ft);
+
+/* inbox should be set with the following values:
+ * start_flow_index
+ * end_flow_index
+ * match_criteria_enable
+ * match_criteria
+ */
+struct mlx5_flow_group *
+mlx5_create_flow_group(struct mlx5_flow_table *ft, u32 *in);
+void mlx5_destroy_flow_group(struct mlx5_flow_group *fg);
+
+/* Single destination per rule.
+ * Group ID is implied by the match criteria.
+ */
+struct mlx5_flow_rule *
+mlx5_add_flow_rule(struct mlx5_flow_table *ft,
+		   u8 match_criteria_enable,
+		   u32 *match_criteria,
+		   u32 *match_value,
+		   u32 action,
+		   u32 flow_tag,
+		   struct mlx5_flow_destination *dest);
+void mlx5_del_flow_rule(struct mlx5_flow_rule *fr);
+
+#endif
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 1565324eb620..131a2737cfa3 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -256,25 +256,27 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
 
 struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8         ft_support[0x1];
-	u8         reserved_0[0x1f];
+	u8         reserved_0[0x2];
+	u8	   flow_modify_en[0x1];
+	u8         reserved_1[0x1c];
 
-	u8         reserved_1[0x2];
+	u8         reserved_2[0x2];
 	u8         log_max_ft_size[0x6];
-	u8         reserved_2[0x10];
+	u8         reserved_3[0x10];
 	u8         max_ft_level[0x8];
 
-	u8         reserved_3[0x20];
+	u8         reserved_4[0x20];
 
-	u8         reserved_4[0x18];
+	u8         reserved_5[0x18];
 	u8         log_max_ft_num[0x8];
 
-	u8         reserved_5[0x18];
+	u8         reserved_6[0x18];
 	u8         log_max_destination[0x8];
 
-	u8         reserved_6[0x18];
+	u8         reserved_7[0x18];
 	u8         log_max_flow[0x8];
 
-	u8         reserved_7[0x40];
+	u8         reserved_8[0x40];
 
 	struct mlx5_ifc_flow_table_fields_supported_bits ft_field_support;
 
@@ -447,6 +449,29 @@ struct mlx5_ifc_flow_table_nic_cap_bits {
 	u8         reserved_3[0x7200];
 };
 
+struct mlx5_ifc_flow_table_eswitch_cap_bits {
+	u8     reserved_0[0x200];
+
+	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_esw_fdb;
+
+	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_esw_acl_ingress;
+
+	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_esw_acl_egress;
+
+	u8      reserved_1[0x7800];
+};
+
+struct mlx5_ifc_e_switch_cap_bits {
+	u8         vport_svlan_strip[0x1];
+	u8         vport_cvlan_strip[0x1];
+	u8         vport_svlan_insert[0x1];
+	u8         vport_cvlan_insert_if_not_exist[0x1];
+	u8         vport_cvlan_insert_overwrite[0x1];
+	u8         reserved_0[0x1b];
+
+	u8         reserved_1[0x7e0];
+};
+
 struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
 	u8         csum_cap[0x1];
 	u8         vlan_cap[0x1];
@@ -665,7 +690,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_17[0x1];
 	u8         ets[0x1];
 	u8         nic_flow_table[0x1];
-	u8         reserved_18[0x4];
+	u8         eswitch_flow_table[0x1];
+	u8	   early_vf_enable;
+	u8         reserved_18[0x2];
 	u8         local_ca_ack_delay[0x5];
 	u8         reserved_19[0x6];
 	u8         port_type[0x2];
@@ -787,27 +814,36 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_60[0x1b];
 	u8         log_max_wq_sz[0x5];
 
-	u8         reserved_61[0xa0];
-
+	u8         nic_vport_change_event[0x1];
+	u8         reserved_61[0xa];
+	u8         log_max_vlan_list[0x5];
 	u8         reserved_62[0x3];
+	u8         log_max_current_mc_list[0x5];
+	u8         reserved_63[0x3];
+	u8         log_max_current_uc_list[0x5];
+
+	u8         reserved_64[0x80];
+
+	u8         reserved_65[0x3];
 	u8         log_max_l2_table[0x5];
-	u8         reserved_63[0x8];
+	u8         reserved_66[0x8];
 	u8         log_uar_page_sz[0x10];
 
-	u8         reserved_64[0x100];
+	u8         reserved_67[0xe0];
 
-	u8         reserved_65[0x1f];
+	u8         reserved_68[0x1f];
 	u8         cqe_zip[0x1];
 
 	u8         cqe_zip_timeout[0x10];
 	u8         cqe_zip_max_num[0x10];
 
-	u8         reserved_66[0x220];
+	u8         reserved_69[0x220];
 };
 
-enum {
-	MLX5_DEST_FORMAT_STRUCT_DESTINATION_TYPE_FLOW_TABLE_  = 0x1,
-	MLX5_DEST_FORMAT_STRUCT_DESTINATION_TYPE_TIR          = 0x2,
+enum mlx5_flow_destination_type {
+	MLX5_FLOW_DESTINATION_TYPE_VPORT        = 0x0,
+	MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE   = 0x1,
+	MLX5_FLOW_DESTINATION_TYPE_TIR          = 0x2,
 };
 
 struct mlx5_ifc_dest_format_struct_bits {
@@ -900,6 +936,13 @@ struct mlx5_ifc_mac_address_layout_bits {
 	u8         mac_addr_31_0[0x20];
 };
 
+struct mlx5_ifc_vlan_layout_bits {
+	u8         reserved_0[0x14];
+	u8         vlan[0x0c];
+
+	u8         reserved_1[0x20];
+};
+
 struct mlx5_ifc_cong_control_r_roce_ecn_np_bits {
 	u8         reserved_0[0xa0];
 
@@ -1829,6 +1872,8 @@ union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_roce_cap_bits roce_cap;
 	struct mlx5_ifc_per_protocol_networking_offload_caps_bits per_protocol_networking_offload_caps;
 	struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap;
+	struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap;
+	struct mlx5_ifc_e_switch_cap_bits e_switch_cap;
 	u8         reserved_0[0x8000];
 };
 
@@ -2133,24 +2178,35 @@ struct mlx5_ifc_rmpc_bits {
 	struct mlx5_ifc_wq_bits wq;
 };
 
-enum {
-	MLX5_NIC_VPORT_CONTEXT_ALLOWED_LIST_TYPE_CURRENT_UC_MAC_ADDRESS  = 0x0,
-};
-
 struct mlx5_ifc_nic_vport_context_bits {
 	u8         reserved_0[0x1f];
 	u8         roce_en[0x1];
 
-	u8         reserved_1[0x760];
+	u8         arm_change_event[0x1];
+	u8         reserved_1[0x1a];
+	u8         event_on_mtu[0x1];
+	u8         event_on_promisc_change[0x1];
+	u8         event_on_vlan_change[0x1];
+	u8         event_on_mc_address_change[0x1];
+	u8         event_on_uc_address_change[0x1];
 
-	u8         reserved_2[0x5];
+	u8         reserved_2[0xf0];
+
+	u8         mtu[0x10];
+
+	u8         reserved_3[0x640];
+
+	u8         promisc_uc[0x1];
+	u8         promisc_mc[0x1];
+	u8         promisc_all[0x1];
+	u8         reserved_4[0x2];
 	u8         allowed_list_type[0x3];
-	u8         reserved_3[0xc];
+	u8         reserved_5[0xc];
 	u8         allowed_list_size[0xc];
 
 	struct mlx5_ifc_mac_address_layout_bits permanent_address;
 
-	u8         reserved_4[0x20];
+	u8         reserved_6[0x20];
 
 	u8         current_uc_mac_address[0][0x40];
 };
@@ -2263,6 +2319,26 @@ struct mlx5_ifc_hca_vport_context_bits {
 	u8         reserved_6[0xca0];
 };
 
+struct mlx5_ifc_esw_vport_context_bits {
+	u8         reserved_0[0x3];
+	u8         vport_svlan_strip[0x1];
+	u8         vport_cvlan_strip[0x1];
+	u8         vport_svlan_insert[0x1];
+	u8         vport_cvlan_insert[0x2];
+	u8         reserved_1[0x18];
+
+	u8         reserved_2[0x20];
+
+	u8         svlan_cfi[0x1];
+	u8         svlan_pcp[0x3];
+	u8         svlan_id[0xc];
+	u8         cvlan_cfi[0x1];
+	u8         cvlan_pcp[0x3];
+	u8         cvlan_id[0xc];
+
+	u8         reserved_3[0x7a0];
+};
+
 enum {
 	MLX5_EQC_STATUS_OK                = 0x0,
 	MLX5_EQC_STATUS_EQ_WRITE_FAILURE  = 0xa,
@@ -2769,6 +2845,13 @@ struct mlx5_ifc_set_hca_cap_in_bits {
 	union mlx5_ifc_hca_cap_union_bits capability;
 };
 
+enum {
+	MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION    = 0x0,
+	MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_TAG  = 0x1,
+	MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST    = 0x2,
+	MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS    = 0x3
+};
+
 struct mlx5_ifc_set_fte_out_bits {
 	u8         status[0x8];
 	u8         reserved_0[0x18];
@@ -2793,11 +2876,14 @@ struct mlx5_ifc_set_fte_in_bits {
 	u8         reserved_4[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_5[0x40];
+	u8         reserved_5[0x18];
+	u8         modify_enable_mask[0x8];
+
+	u8         reserved_6[0x20];
 
 	u8         flow_index[0x20];
 
-	u8         reserved_6[0xe0];
+	u8         reserved_7[0xe0];
 
 	struct mlx5_ifc_flow_context_bits flow_context;
 };
@@ -2940,6 +3026,7 @@ struct mlx5_ifc_query_vport_state_out_bits {
 
 enum {
 	MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT  = 0x0,
+	MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT   = 0x1,
 };
 
 struct mlx5_ifc_query_vport_state_in_bits {
@@ -3700,6 +3787,64 @@ struct mlx5_ifc_query_flow_group_in_bits {
 	u8         reserved_5[0x120];
 };
 
+struct mlx5_ifc_query_esw_vport_context_out_bits {
+	u8         status[0x8];
+	u8         reserved_0[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_1[0x40];
+
+	struct mlx5_ifc_esw_vport_context_bits esw_vport_context;
+};
+
+struct mlx5_ifc_query_esw_vport_context_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_0[0x10];
+
+	u8         reserved_1[0x10];
+	u8         op_mod[0x10];
+
+	u8         other_vport[0x1];
+	u8         reserved_2[0xf];
+	u8         vport_number[0x10];
+
+	u8         reserved_3[0x20];
+};
+
+struct mlx5_ifc_modify_esw_vport_context_out_bits {
+	u8         status[0x8];
+	u8         reserved_0[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_1[0x40];
+};
+
+struct mlx5_ifc_esw_vport_context_fields_select_bits {
+	u8         reserved[0x1c];
+	u8         vport_cvlan_insert[0x1];
+	u8         vport_svlan_insert[0x1];
+	u8         vport_cvlan_strip[0x1];
+	u8         vport_svlan_strip[0x1];
+};
+
+struct mlx5_ifc_modify_esw_vport_context_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_0[0x10];
+
+	u8         reserved_1[0x10];
+	u8         op_mod[0x10];
+
+	u8         other_vport[0x1];
+	u8         reserved_2[0xf];
+	u8         vport_number[0x10];
+
+	struct mlx5_ifc_esw_vport_context_fields_select_bits field_select;
+
+	struct mlx5_ifc_esw_vport_context_bits esw_vport_context;
+};
+
 struct mlx5_ifc_query_eq_out_bits {
 	u8         status[0x8];
 	u8         reserved_0[0x18];
@@ -4228,7 +4373,10 @@ struct mlx5_ifc_modify_nic_vport_context_out_bits {
 };
 
 struct mlx5_ifc_modify_nic_vport_field_select_bits {
-	u8         reserved_0[0x1c];
+	u8         reserved_0[0x19];
+	u8         mtu[0x1];
+	u8         change_event[0x1];
+	u8         promisc[0x1];
 	u8         permanent_address[0x1];
 	u8         addresses_list[0x1];
 	u8         roce_en[0x1];
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index 967e0fd06e89..638f2ca7a527 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -34,9 +34,17 @@
 #define __MLX5_VPORT_H__
 
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/device.h>
 
-u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod);
-void mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, u8 *addr);
+u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport);
+u8 mlx5_query_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
+				u16 vport);
+int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
+				  u16 vport, u8 state);
+int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,
+				     u16 vport, u8 *addr);
+int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *dev,
+				      u16 vport, u8 *addr);
 int mlx5_query_hca_vport_gid(struct mlx5_core_dev *dev, u8 other_vport,
 			     u8 port_num, u16  vf_num, u16 gid_index,
 			     union ib_gid *gid);
@@ -51,5 +59,30 @@ int mlx5_query_hca_vport_system_image_guid(struct mlx5_core_dev *dev,
 					   u64 *sys_image_guid);
 int mlx5_query_hca_vport_node_guid(struct mlx5_core_dev *dev,
 				   u64 *node_guid);
+int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev,
+				  u32 vport,
+				  enum mlx5_list_type list_type,
+				  u8 addr_list[][ETH_ALEN],
+				  int *list_size);
+int mlx5_modify_nic_vport_mac_list(struct mlx5_core_dev *dev,
+				   enum mlx5_list_type list_type,
+				   u8 addr_list[][ETH_ALEN],
+				   int list_size);
+int mlx5_query_nic_vport_promisc(struct mlx5_core_dev *mdev,
+				 u32 vport,
+				 int *promisc_uc,
+				 int *promisc_mc,
+				 int *promisc_all);
+int mlx5_modify_nic_vport_promisc(struct mlx5_core_dev *mdev,
+				  int promisc_uc,
+				  int promisc_mc,
+				  int promisc_all);
+int mlx5_query_nic_vport_vlans(struct mlx5_core_dev *dev,
+			       u32 vport,
+			       u16 vlans[],
+			       int *size);
+int mlx5_modify_nic_vport_vlans(struct mlx5_core_dev *dev,
+				u16 vlans[],
+				int list_size);
 
 #endif /* __MLX5_VPORT_H__ */
diff --git a/include/linux/mroute.h b/include/linux/mroute.h
index 79aaa9fc1a15..bf9b322cb0b0 100644
--- a/include/linux/mroute.h
+++ b/include/linux/mroute.h
@@ -9,38 +9,28 @@
 #ifdef CONFIG_IP_MROUTE
 static inline int ip_mroute_opt(int opt)
 {
-	return (opt >= MRT_BASE) && (opt <= MRT_MAX);
+	return opt >= MRT_BASE && opt <= MRT_MAX;
 }
-#else
-static inline int ip_mroute_opt(int opt)
-{
-	return 0;
-}
-#endif
 
-#ifdef CONFIG_IP_MROUTE
-extern int ip_mroute_setsockopt(struct sock *, int, char __user *, unsigned int);
-extern int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *);
-extern int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg);
-extern int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
-extern int ip_mr_init(void);
+int ip_mroute_setsockopt(struct sock *, int, char __user *, unsigned int);
+int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *);
+int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg);
+int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
+int ip_mr_init(void);
 #else
-static inline
-int ip_mroute_setsockopt(struct sock *sock,
-			 int optname, char __user *optval, unsigned int optlen)
+static inline int ip_mroute_setsockopt(struct sock *sock, int optname,
+				       char __user *optval, unsigned int optlen)
 {
 	return -ENOPROTOOPT;
 }
 
-static inline
-int ip_mroute_getsockopt(struct sock *sock,
-			 int optname, char __user *optval, int __user *optlen)
+static inline int ip_mroute_getsockopt(struct sock *sock, int optname,
+				       char __user *optval, int __user *optlen)
 {
 	return -ENOPROTOOPT;
 }
 
-static inline
-int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
+static inline int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
 {
 	return -ENOIOCTLCMD;
 }
@@ -49,6 +39,11 @@ static inline int ip_mr_init(void)
 {
 	return 0;
 }
+
+static inline int ip_mroute_opt(int opt)
+{
+	return 0;
+}
 #endif
 
 struct vif_device {
@@ -64,6 +59,32 @@ struct vif_device {
 
 #define VIFF_STATIC 0x8000
 
+#define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL)
+#define MFC_LINES 64
+
+struct mr_table {
+	struct list_head	list;
+	possible_net_t		net;
+	u32			id;
+	struct sock __rcu	*mroute_sk;
+	struct timer_list	ipmr_expire_timer;
+	struct list_head	mfc_unres_queue;
+	struct list_head	mfc_cache_array[MFC_LINES];
+	struct vif_device	vif_table[MAXVIFS];
+	int			maxvif;
+	atomic_t		cache_resolve_queue_len;
+	bool			mroute_do_assert;
+	bool			mroute_do_pim;
+	int			mroute_reg_vif_num;
+};
+
+/* mfc_flags:
+ * MFC_STATIC - the entry was added statically (not by a routing daemon)
+ */
+enum {
+	MFC_STATIC = BIT(0),
+};
+
 struct mfc_cache {
 	struct list_head list;
 	__be32 mfc_mcastgrp;			/* Group the entry belongs to 	*/
@@ -89,19 +110,14 @@ struct mfc_cache {
 	struct rcu_head	rcu;
 };
 
-#define MFC_STATIC		1
-#define MFC_NOTIFY		2
-
-#define MFC_LINES		64
-
 #ifdef __BIG_ENDIAN
 #define MFC_HASH(a,b)	(((((__force u32)(__be32)a)>>24)^(((__force u32)(__be32)b)>>26))&(MFC_LINES-1))
 #else
 #define MFC_HASH(a,b)	((((__force u32)(__be32)a)^(((__force u32)(__be32)b)>>2))&(MFC_LINES-1))
-#endif		
+#endif
 
 struct rtmsg;
-extern int ipmr_get_route(struct net *net, struct sk_buff *skb,
-			  __be32 saddr, __be32 daddr,
-			  struct rtmsg *rtm, int nowait);
+int ipmr_get_route(struct net *net, struct sk_buff *skb,
+		   __be32 saddr, __be32 daddr,
+		   struct rtmsg *rtm, int nowait);
 #endif
diff --git a/include/linux/net.h b/include/linux/net.h
index 70ac5e28e6b7..0b4ac7da583a 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -34,8 +34,12 @@ struct inode;
 struct file;
 struct net;
 
-#define SOCK_ASYNC_NOSPACE	0
-#define SOCK_ASYNC_WAITDATA	1
+/* Historically, SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA were located
+ * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected.
+ * Eventually all flags will be in sk->sk_wq_flags.
+ */
+#define SOCKWQ_ASYNC_NOSPACE	0
+#define SOCKWQ_ASYNC_WAITDATA	1
 #define SOCK_NOSPACE		2
 #define SOCK_PASSCRED		3
 #define SOCK_PASSSEC		4
@@ -89,6 +93,7 @@ struct socket_wq {
 	/* Note: wait MUST be first field of socket_wq */
 	wait_queue_head_t	wait;
 	struct fasync_struct	*fasync_list;
+	unsigned long		flags; /* %SOCKWQ_ASYNC_NOSPACE, etc */
 	struct rcu_head		rcu;
 } ____cacheline_aligned_in_smp;
 
@@ -96,7 +101,7 @@ struct socket_wq {
  *  struct socket - general BSD socket
  *  @state: socket state (%SS_CONNECTED, etc)
  *  @type: socket type (%SOCK_STREAM, etc)
- *  @flags: socket flags (%SOCK_ASYNC_NOSPACE, etc)
+ *  @flags: socket flags (%SOCK_NOSPACE, etc)
  *  @ops: protocol specific socket operations
  *  @file: File back pointer for gc
  *  @sk: internal networking protocol agnostic socket representation
@@ -202,7 +207,7 @@ enum {
 	SOCK_WAKE_URG,
 };
 
-int sock_wake_async(struct socket *sk, int how, int band);
+int sock_wake_async(struct socket_wq *sk_wq, int how, int band);
 int sock_register(const struct net_proto_family *fam);
 void sock_unregister(int family);
 int __sock_create(struct net *net, int family, int type, int proto,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7d2d1d7aaec7..1bb21ff0fa64 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -132,7 +132,9 @@ static inline bool dev_xmit_complete(int rc)
  *	used.
  */
 
-#if defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25)
+#if defined(CONFIG_HYPERV_NET)
+# define LL_MAX_HEADER 128
+#elif defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25)
 # if defined(CONFIG_MAC80211_MESH)
 #  define LL_MAX_HEADER 128
 # else
@@ -1271,6 +1273,7 @@ struct net_device_ops {
  * @IFF_NO_QUEUE: device can run without qdisc attached
  * @IFF_OPENVSWITCH: device is a Open vSwitch master
  * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device
+ * @IFF_TEAM: device is a team device
  */
 enum netdev_priv_flags {
 	IFF_802_1Q_VLAN			= 1<<0,
@@ -1297,6 +1300,7 @@ enum netdev_priv_flags {
 	IFF_NO_QUEUE			= 1<<21,
 	IFF_OPENVSWITCH			= 1<<22,
 	IFF_L3MDEV_SLAVE		= 1<<23,
+	IFF_TEAM			= 1<<24,
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
@@ -1323,6 +1327,7 @@ enum netdev_priv_flags {
 #define IFF_NO_QUEUE			IFF_NO_QUEUE
 #define IFF_OPENVSWITCH			IFF_OPENVSWITCH
 #define IFF_L3MDEV_SLAVE		IFF_L3MDEV_SLAVE
+#define IFF_TEAM			IFF_TEAM
 
 /**
  *	struct net_device - The DEVICE structure.
@@ -1398,7 +1403,8 @@ enum netdev_priv_flags {
  *	@dma:		DMA channel
  *	@mtu:		Interface MTU value
  *	@type:		Interface hardware type
- *	@hard_header_len: Hardware header length
+ *	@hard_header_len: Hardware header length, which means that this is the
+ *			  minimum size of a packet.
  *
  *	@needed_headroom: Extra headroom the hardware may need, but not in all
  *			  cases can this be guaranteed
@@ -2105,6 +2111,24 @@ struct pcpu_sw_netstats {
 #define netdev_alloc_pcpu_stats(type)					\
 	__netdev_alloc_pcpu_stats(type, GFP_KERNEL);
 
+enum netdev_lag_tx_type {
+	NETDEV_LAG_TX_TYPE_UNKNOWN,
+	NETDEV_LAG_TX_TYPE_RANDOM,
+	NETDEV_LAG_TX_TYPE_BROADCAST,
+	NETDEV_LAG_TX_TYPE_ROUNDROBIN,
+	NETDEV_LAG_TX_TYPE_ACTIVEBACKUP,
+	NETDEV_LAG_TX_TYPE_HASH,
+};
+
+struct netdev_lag_upper_info {
+	enum netdev_lag_tx_type tx_type;
+};
+
+struct netdev_lag_lower_state_info {
+	u8 link_up : 1,
+	   tx_enabled : 1;
+};
+
 #include <linux/notifier.h>
 
 /* netdevice notifier chain. Please remember to update the rtnetlink
@@ -2140,6 +2164,7 @@ struct pcpu_sw_netstats {
 #define NETDEV_CHANGEINFODATA	0x0018
 #define NETDEV_BONDING_INFO	0x0019
 #define NETDEV_PRECHANGEUPPER	0x001A
+#define NETDEV_CHANGELOWERSTATE	0x001B
 
 int register_netdevice_notifier(struct notifier_block *nb);
 int unregister_netdevice_notifier(struct notifier_block *nb);
@@ -2158,6 +2183,12 @@ struct netdev_notifier_changeupper_info {
 	struct net_device *upper_dev; /* new upper dev */
 	bool master; /* is upper dev master */
 	bool linking; /* is the nofication for link or unlink */
+	void *upper_info; /* upper dev info */
+};
+
+struct netdev_notifier_changelowerstate_info {
+	struct netdev_notifier_info info; /* must be first */
+	void *lower_state_info; /* is lower dev state */
 };
 
 static inline void netdev_notifier_info_init(struct netdev_notifier_info *info,
@@ -3614,15 +3645,15 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
 struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev);
 int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev);
 int netdev_master_upper_dev_link(struct net_device *dev,
-				 struct net_device *upper_dev);
-int netdev_master_upper_dev_link_private(struct net_device *dev,
-					 struct net_device *upper_dev,
-					 void *private);
+				 struct net_device *upper_dev,
+				 void *upper_priv, void *upper_info);
 void netdev_upper_dev_unlink(struct net_device *dev,
 			     struct net_device *upper_dev);
 void netdev_adjacent_rename_links(struct net_device *dev, char *oldname);
 void *netdev_lower_dev_get_private(struct net_device *dev,
 				   struct net_device *lower_dev);
+void netdev_lower_state_changed(struct net_device *lower_dev,
+				void *lower_state_info);
 
 /* RSS keys are 40 or 52 bytes long */
 #define NETDEV_RSS_KEY_LEN 52
@@ -3630,7 +3661,7 @@ extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN];
 void netdev_rss_key_fill(void *buffer, size_t len);
 
 int dev_get_nest_level(struct net_device *dev,
-		       bool (*type_check)(struct net_device *dev));
+		       bool (*type_check)(const struct net_device *dev));
 int skb_checksum_help(struct sk_buff *skb);
 struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 				  netdev_features_t features, bool tx_path);
@@ -3827,32 +3858,32 @@ static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol,
 	skb->mac_len = mac_len;
 }
 
-static inline bool netif_is_macvlan(struct net_device *dev)
+static inline bool netif_is_macvlan(const struct net_device *dev)
 {
 	return dev->priv_flags & IFF_MACVLAN;
 }
 
-static inline bool netif_is_macvlan_port(struct net_device *dev)
+static inline bool netif_is_macvlan_port(const struct net_device *dev)
 {
 	return dev->priv_flags & IFF_MACVLAN_PORT;
 }
 
-static inline bool netif_is_ipvlan(struct net_device *dev)
+static inline bool netif_is_ipvlan(const struct net_device *dev)
 {
 	return dev->priv_flags & IFF_IPVLAN_SLAVE;
 }
 
-static inline bool netif_is_ipvlan_port(struct net_device *dev)
+static inline bool netif_is_ipvlan_port(const struct net_device *dev)
 {
 	return dev->priv_flags & IFF_IPVLAN_MASTER;
 }
 
-static inline bool netif_is_bond_master(struct net_device *dev)
+static inline bool netif_is_bond_master(const struct net_device *dev)
 {
 	return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING;
 }
 
-static inline bool netif_is_bond_slave(struct net_device *dev)
+static inline bool netif_is_bond_slave(const struct net_device *dev)
 {
 	return dev->flags & IFF_SLAVE && dev->priv_flags & IFF_BONDING;
 }
@@ -3887,6 +3918,26 @@ static inline bool netif_is_ovs_master(const struct net_device *dev)
 	return dev->priv_flags & IFF_OPENVSWITCH;
 }
 
+static inline bool netif_is_team_master(const struct net_device *dev)
+{
+	return dev->priv_flags & IFF_TEAM;
+}
+
+static inline bool netif_is_team_port(const struct net_device *dev)
+{
+	return dev->priv_flags & IFF_TEAM_PORT;
+}
+
+static inline bool netif_is_lag_master(const struct net_device *dev)
+{
+	return netif_is_bond_master(dev) || netif_is_team_master(dev);
+}
+
+static inline bool netif_is_lag_port(const struct net_device *dev)
+{
+	return netif_is_bond_slave(dev) || netif_is_team_port(dev);
+}
+
 /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */
 static inline void netif_keep_dst(struct net_device *dev)
 {
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 570d630f98ae..11bbae44f4cb 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -251,6 +251,7 @@ struct nfs4_layoutget {
 	struct nfs4_layoutget_res res;
 	struct rpc_cred *cred;
 	gfp_t gfp_flags;
+	long timeout;
 };
 
 struct nfs4_getdeviceinfo_args {
diff --git a/include/linux/of_dma.h b/include/linux/of_dma.h
index 36112cdd665a..b90d8ec57c1f 100644
--- a/include/linux/of_dma.h
+++ b/include/linux/of_dma.h
@@ -80,7 +80,7 @@ static inline int of_dma_router_register(struct device_node *np,
 static inline struct dma_chan *of_dma_request_slave_channel(struct device_node *np,
 						     const char *name)
 {
-	return NULL;
+	return ERR_PTR(-ENODEV);
 }
 
 static inline struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec,
diff --git a/include/linux/pci.h b/include/linux/pci.h
index e828e7b4afec..6ae25aae88fd 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -412,9 +412,18 @@ struct pci_host_bridge {
 	void (*release_fn)(struct pci_host_bridge *);
 	void *release_data;
 	unsigned int ignore_reset_delay:1;	/* for entire hierarchy */
+	/* Resource alignment requirements */
+	resource_size_t (*align_resource)(struct pci_dev *dev,
+			const struct resource *res,
+			resource_size_t start,
+			resource_size_t size,
+			resource_size_t align);
 };
 
 #define	to_pci_host_bridge(n) container_of(n, struct pci_host_bridge, dev)
+
+struct pci_host_bridge *pci_find_host_bridge(struct pci_bus *bus);
+
 void pci_set_host_bridge_release(struct pci_host_bridge *bridge,
 		     void (*release_fn)(struct pci_host_bridge *),
 		     void *release_data);
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index d9ba49cedc5d..1acbefc4bbda 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2495,6 +2495,8 @@
 #define PCI_DEVICE_ID_KORENIX_JETCARDF2	0x1700
 #define PCI_DEVICE_ID_KORENIX_JETCARDF3	0x17ff
 
+#define PCI_VENDOR_ID_NETRONOME		0x19ee
+
 #define PCI_VENDOR_ID_QMI		0x1a32
 
 #define PCI_VENDOR_ID_AZWAVE		0x1a3b
diff --git a/include/linux/pim.h b/include/linux/pim.h
index 252bf6644c51..e1d756f81348 100644
--- a/include/linux/pim.h
+++ b/include/linux/pim.h
@@ -13,6 +13,11 @@
 
 #define PIM_NULL_REGISTER	cpu_to_be32(0x40000000)
 
+static inline bool ipmr_pimsm_enabled(void)
+{
+	return IS_BUILTIN(CONFIG_IP_PIMSM_V1) || IS_BUILTIN(CONFIG_IP_PIMSM_V2);
+}
+
 /* PIMv2 register message header layout (ietf-draft-idmr-pimvsm-v2-00.ps */
 struct pimreghdr
 {
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index dc9a1353f971..d4a32e878180 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -25,6 +25,12 @@
 #include <linux/qed/common_hsi.h>
 #include <linux/qed/qed_chain.h>
 
+enum qed_led_mode {
+	QED_LED_MODE_OFF,
+	QED_LED_MODE_ON,
+	QED_LED_MODE_RESTORE
+};
+
 #define DIRECT_REG_WR(reg_addr, val) writel((u32)val, \
 					    (void __iomem *)(reg_addr))
 
@@ -252,6 +258,17 @@ struct qed_common_ops {
 
 	void		(*chain_free)(struct qed_dev *cdev,
 				      struct qed_chain *p_chain);
+
+/**
+ * @brief set_led - Configure LED mode
+ *
+ * @param cdev
+ * @param mode - LED mode
+ *
+ * @return 0 on success, error otherwise.
+ */
+	int (*set_led)(struct qed_dev *cdev,
+		       enum qed_led_mode mode);
 };
 
 /**
diff --git a/include/linux/scpi_protocol.h b/include/linux/scpi_protocol.h
index 80af3cd35ae4..72ce932c69b2 100644
--- a/include/linux/scpi_protocol.h
+++ b/include/linux/scpi_protocol.h
@@ -71,7 +71,7 @@ struct scpi_ops {
 	int (*sensor_get_value)(u16, u32 *);
 };
 
-#if IS_ENABLED(CONFIG_ARM_SCPI_PROTOCOL)
+#if IS_REACHABLE(CONFIG_ARM_SCPI_PROTOCOL)
 struct scpi_ops *get_scpi_ops(void);
 #else
 static inline struct scpi_ops *get_scpi_ops(void) { return NULL; }
diff --git a/include/linux/signal.h b/include/linux/signal.h
index ab1e0392b5ac..92557bbce7e7 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -239,7 +239,6 @@ extern int sigprocmask(int, sigset_t *, sigset_t *);
 extern void set_current_blocked(sigset_t *);
 extern void __set_current_blocked(const sigset_t *);
 extern int show_unhandled_signals;
-extern int sigsuspend(sigset_t *);
 
 struct sigaction {
 #ifndef __ARCH_HAS_IRIX_SIGACTION
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index c9c394bf0771..9b9b9ead7bb3 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2785,6 +2785,12 @@ static inline void skb_frag_list_init(struct sk_buff *skb)
 #define skb_walk_frags(skb, iter)	\
 	for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next)
 
+
+int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
+				const struct sk_buff *skb);
+struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned flags,
+					int *peeked, int *off, int *err,
+					struct sk_buff **last);
 struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
 				    int *peeked, int *off, int *err);
 struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock,
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 7c82e3b307a3..2037a861e367 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -158,6 +158,24 @@ size_t ksize(const void *);
 #endif
 
 /*
+ * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment.
+ * Intended for arches that get misalignment faults even for 64 bit integer
+ * aligned buffers.
+ */
+#ifndef ARCH_SLAB_MINALIGN
+#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
+#endif
+
+/*
+ * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned
+ * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN
+ * aligned pointers.
+ */
+#define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN)
+#define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN)
+#define __assume_page_alignment __assume_aligned(PAGE_SIZE)
+
+/*
  * Kmalloc array related definitions
  */
 
@@ -286,8 +304,8 @@ static __always_inline int kmalloc_index(size_t size)
 }
 #endif /* !CONFIG_SLOB */
 
-void *__kmalloc(size_t size, gfp_t flags);
-void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags);
+void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment;
+void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags) __assume_slab_alignment;
 void kmem_cache_free(struct kmem_cache *, void *);
 
 /*
@@ -298,11 +316,11 @@ void kmem_cache_free(struct kmem_cache *, void *);
  * Note that interrupts must be enabled when calling these functions.
  */
 void kmem_cache_free_bulk(struct kmem_cache *, size_t, void **);
-bool kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **);
+int kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **);
 
 #ifdef CONFIG_NUMA
-void *__kmalloc_node(size_t size, gfp_t flags, int node);
-void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node);
+void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment;
+void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment;
 #else
 static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node)
 {
@@ -316,12 +334,12 @@ static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t f
 #endif
 
 #ifdef CONFIG_TRACING
-extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t);
+extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t) __assume_slab_alignment;
 
 #ifdef CONFIG_NUMA
 extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s,
 					   gfp_t gfpflags,
-					   int node, size_t size);
+					   int node, size_t size) __assume_slab_alignment;
 #else
 static __always_inline void *
 kmem_cache_alloc_node_trace(struct kmem_cache *s,
@@ -354,10 +372,10 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s,
 }
 #endif /* CONFIG_TRACING */
 
-extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order);
+extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment;
 
 #ifdef CONFIG_TRACING
-extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order);
+extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment;
 #else
 static __always_inline void *
 kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order)
@@ -482,15 +500,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 	return __kmalloc_node(size, flags, node);
 }
 
-/*
- * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment.
- * Intended for arches that get misalignment faults even for 64 bit integer
- * aligned buffers.
- */
-#ifndef ARCH_SLAB_MINALIGN
-#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
-#endif
-
 struct memcg_cache_array {
 	struct rcu_head rcu;
 	struct kmem_cache *entries[0];
diff --git a/include/linux/soc/ti/knav_dma.h b/include/linux/soc/ti/knav_dma.h
index dad035c16d94..343c13ac4f71 100644
--- a/include/linux/soc/ti/knav_dma.h
+++ b/include/linux/soc/ti/knav_dma.h
@@ -144,17 +144,17 @@ struct knav_dma_cfg {
  * @psdata:			Protocol specific
  */
 struct knav_dma_desc {
-	u32	desc_info;
-	u32	tag_info;
-	u32	packet_info;
-	u32	buff_len;
-	u32	buff;
-	u32	next_desc;
-	u32	orig_len;
-	u32	orig_buff;
-	u32	epib[KNAV_DMA_NUM_EPIB_WORDS];
-	u32	psdata[KNAV_DMA_NUM_PS_WORDS];
-	u32	pad[4];
+	__le32	desc_info;
+	__le32	tag_info;
+	__le32	packet_info;
+	__le32	buff_len;
+	__le32	buff;
+	__le32	next_desc;
+	__le32	orig_len;
+	__le32	orig_buff;
+	__le32	epib[KNAV_DMA_NUM_EPIB_WORDS];
+	__le32	psdata[KNAV_DMA_NUM_PS_WORDS];
+	__le32	pad[4];
 } ____cacheline_aligned;
 
 #if IS_ENABLED(CONFIG_KEYSTONE_NAVIGATOR_DMA)
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a156b82dd14c..c2b66a277e98 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -524,7 +524,7 @@ asmlinkage long sys_chown(const char __user *filename,
 asmlinkage long sys_lchown(const char __user *filename,
 				uid_t user, gid_t group);
 asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group);
-#ifdef CONFIG_UID16
+#ifdef CONFIG_HAVE_UID16
 asmlinkage long sys_chown16(const char __user *filename,
 				old_uid_t user, old_gid_t group);
 asmlinkage long sys_lchown16(const char __user *filename,
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 4014a59828fc..613c29bd6baf 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -438,7 +438,8 @@ static inline void thermal_zone_device_unregister(
 static inline int thermal_zone_bind_cooling_device(
 	struct thermal_zone_device *tz, int trip,
 	struct thermal_cooling_device *cdev,
-	unsigned long upper, unsigned long lower)
+	unsigned long upper, unsigned long lower,
+	unsigned int weight)
 { return -ENODEV; }
 static inline int thermal_zone_unbind_cooling_device(
 	struct thermal_zone_device *tz, int trip,
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 5b04b0a5375b..5e31f1b99037 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -607,7 +607,7 @@ extern void n_tty_inherit_ops(struct tty_ldisc_ops *ops);
 
 /* tty_audit.c */
 #ifdef CONFIG_AUDIT
-extern void tty_audit_add_data(struct tty_struct *tty, unsigned char *data,
+extern void tty_audit_add_data(struct tty_struct *tty, const void *data,
 			       size_t size, unsigned icanon);
 extern void tty_audit_exit(void);
 extern void tty_audit_fork(struct signal_struct *sig);
@@ -615,8 +615,8 @@ extern void tty_audit_tiocsti(struct tty_struct *tty, char ch);
 extern void tty_audit_push(struct tty_struct *tty);
 extern int tty_audit_push_current(void);
 #else
-static inline void tty_audit_add_data(struct tty_struct *tty,
-		unsigned char *data, size_t size, unsigned icanon)
+static inline void tty_audit_add_data(struct tty_struct *tty, const void *data,
+				      size_t size, unsigned icanon)
 {
 }
 static inline void tty_audit_tiocsti(struct tty_struct *tty, char ch)
diff --git a/include/linux/types.h b/include/linux/types.h
index 70d8500bddf1..70dd3dfde631 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -35,7 +35,7 @@ typedef __kernel_gid16_t        gid16_t;
 
 typedef unsigned long		uintptr_t;
 
-#ifdef CONFIG_UID16
+#ifdef CONFIG_HAVE_UID16
 /* This is defined by include/asm-{arch}/posix_types.h */
 typedef __kernel_old_uid_t	old_uid_t;
 typedef __kernel_old_gid_t	old_gid_t;
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 1e1bf9f963a9..6aa09a875fbd 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -107,6 +107,27 @@ static inline int waitqueue_active(wait_queue_head_t *q)
 	return !list_empty(&q->task_list);
 }
 
+/**
+ * wq_has_sleeper - check if there are any waiting processes
+ * @wq: wait queue head
+ *
+ * Returns true if wq has waiting processes
+ *
+ * Please refer to the comment for waitqueue_active.
+ */
+static inline bool wq_has_sleeper(wait_queue_head_t *wq)
+{
+	/*
+	 * We need to be sure we are in sync with the
+	 * add_wait_queue modifications to the wait queue.
+	 *
+	 * This memory barrier should be paired with one on the
+	 * waiting side.
+	 */
+	smp_mb();
+	return waitqueue_active(wq);
+}
+
 extern void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait);
 extern void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait);
 extern void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait);